2022/10/12 11:02:19 - mmengine - INFO - ------------------------------------------------------------ System environment: sys.platform: linux Python: 3.8.13 (default, Mar 28 2022, 11:38:47) [GCC 7.5.0] CUDA available: True numpy_random_seed: 2121173851 GPU 0,1,2,3,4,5,6,7: NVIDIA A100-SXM4-80GB CUDA_HOME: /mnt/petrelfs/share/cuda-11.3 NVCC: Cuda compilation tools, release 11.3, V11.3.109 GCC: gcc (GCC) 4.8.5 20150623 (Red Hat 4.8.5-44) PyTorch: 1.12.0+cu113 PyTorch compiling details: PyTorch built with: - GCC 9.3 - C++ Version: 201402 - Intel(R) Math Kernel Library Version 2020.0.0 Product Build 20191122 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v2.6.0 (Git Hash 52b5f107dd9cf10910aaa19cb47f3abf9b349815) - OpenMP 201511 (a.k.a. OpenMP 4.5) - LAPACK is enabled (usually provided by MKL) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 11.3 - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86 - CuDNN 8.2.1 - Built with CuDNN 8.3.2 - Magma 2.5.2 - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.3, CUDNN_VERSION=8.3.2, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.12.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=OFF, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, TorchVision: 0.13.0+cu113 OpenCV: 4.6.0 MMEngine: 0.1.0 Runtime environment: cudnn_benchmark: False mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0} dist_cfg: {'backend': 'nccl'} seed: None Distributed launcher: slurm Distributed training: True GPU number: 8 ------------------------------------------------------------ 2022/10/12 11:02:20 - mmengine - INFO - Config: default_scope = 'mmpose' default_hooks = dict( timer=dict(type='IterTimerHook'), logger=dict(type='LoggerHook', interval=50), param_scheduler=dict(type='ParamSchedulerHook'), checkpoint=dict( type='CheckpointHook', interval=10, max_keep_ckpts=1, save_best='coco/AP', rule='greater'), sampler_seed=dict(type='DistSamplerSeedHook'), visualization=dict(type='PoseVisualizationHook', enable=False)) custom_hooks = [dict(type='SyncBuffersHook')] env_cfg = dict( cudnn_benchmark=False, mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0), dist_cfg=dict(backend='nccl')) vis_backends = [dict(type='LocalVisBackend')] visualizer = dict( type='PoseLocalVisualizer', vis_backends=[dict(type='LocalVisBackend')], name='visualizer') log_processor = dict( type='LogProcessor', window_size=50, by_epoch=True, num_digits=6) log_level = 'INFO' load_from = None resume = False file_client_args = dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' })) train_cfg = dict(by_epoch=True, max_epochs=210, val_interval=10) val_cfg = dict() test_cfg = dict() optim_wrapper = dict(optimizer=dict(type='Adam', lr=0.005)) param_scheduler = [ dict( type='LinearLR', begin=0, end=500, start_factor=0.001, by_epoch=False), dict( type='MultiStepLR', begin=0, end=210, milestones=[170, 200], gamma=0.1, by_epoch=True) ] auto_scale_lr = dict(base_batch_size=256) kernel_sizes = [15, 11, 9, 7, 5] codec = [ dict( type='MegviiHeatmap', input_size=(192, 256), heatmap_size=(48, 64), kernel_size=15), dict( type='MegviiHeatmap', input_size=(192, 256), heatmap_size=(48, 64), kernel_size=11), dict( type='MegviiHeatmap', input_size=(192, 256), heatmap_size=(48, 64), kernel_size=9), dict( type='MegviiHeatmap', input_size=(192, 256), heatmap_size=(48, 64), kernel_size=7), dict( type='MegviiHeatmap', input_size=(192, 256), heatmap_size=(48, 64), kernel_size=5) ] model = dict( type='TopdownPoseEstimator', data_preprocessor=dict( type='PoseDataPreprocessor', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], bgr_to_rgb=True), backbone=dict( type='RSN', unit_channels=256, num_stages=2, num_units=4, num_blocks=[3, 4, 6, 3], num_steps=4, norm_cfg=dict(type='BN')), head=dict( type='MSPNHead', out_shape=(64, 48), unit_channels=256, out_channels=17, num_stages=2, num_units=4, norm_cfg=dict(type='BN'), level_indices=[0, 1, 2, 3, 1, 2, 3, 4], loss=[ dict( type='KeypointMSELoss', use_target_weight=True, loss_weight=0.25), dict( type='KeypointMSELoss', use_target_weight=True, loss_weight=0.25), dict( type='KeypointMSELoss', use_target_weight=True, loss_weight=0.25), dict( type='KeypointOHKMMSELoss', use_target_weight=True, loss_weight=1.0), dict( type='KeypointMSELoss', use_target_weight=True, loss_weight=0.25), dict( type='KeypointMSELoss', use_target_weight=True, loss_weight=0.25), dict( type='KeypointMSELoss', use_target_weight=True, loss_weight=0.25), dict( type='KeypointOHKMMSELoss', use_target_weight=True, loss_weight=1.0) ], decoder=dict( type='MegviiHeatmap', input_size=(192, 256), heatmap_size=(48, 64), kernel_size=5)), test_cfg=dict(flip_test=True, flip_mode='heatmap', shift_heatmap=False)) dataset_type = 'CocoDataset' data_mode = 'topdown' data_root = 'data/coco/' train_pipeline = [ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='RandomFlip', direction='horizontal'), dict(type='RandomHalfBody'), dict(type='RandomBBoxTransform'), dict(type='TopdownAffine', input_size=(192, 256)), dict( type='GenerateTarget', target_type='multilevel_heatmap', encoder=[ dict( type='MegviiHeatmap', input_size=(192, 256), heatmap_size=(48, 64), kernel_size=15), dict( type='MegviiHeatmap', input_size=(192, 256), heatmap_size=(48, 64), kernel_size=11), dict( type='MegviiHeatmap', input_size=(192, 256), heatmap_size=(48, 64), kernel_size=9), dict( type='MegviiHeatmap', input_size=(192, 256), heatmap_size=(48, 64), kernel_size=7), dict( type='MegviiHeatmap', input_size=(192, 256), heatmap_size=(48, 64), kernel_size=5) ]), dict(type='PackPoseInputs') ] val_pipeline = [ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='TopdownAffine', input_size=(192, 256)), dict(type='PackPoseInputs') ] train_dataloader = dict( batch_size=32, num_workers=4, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=True), dataset=dict( type='CocoDataset', data_root='data/coco/', data_mode='topdown', ann_file='annotations/person_keypoints_train2017.json', data_prefix=dict(img='train2017/'), pipeline=[ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='RandomFlip', direction='horizontal'), dict(type='RandomHalfBody'), dict(type='RandomBBoxTransform'), dict(type='TopdownAffine', input_size=(192, 256)), dict( type='GenerateTarget', target_type='multilevel_heatmap', encoder=[ dict( type='MegviiHeatmap', input_size=(192, 256), heatmap_size=(48, 64), kernel_size=15), dict( type='MegviiHeatmap', input_size=(192, 256), heatmap_size=(48, 64), kernel_size=11), dict( type='MegviiHeatmap', input_size=(192, 256), heatmap_size=(48, 64), kernel_size=9), dict( type='MegviiHeatmap', input_size=(192, 256), heatmap_size=(48, 64), kernel_size=7), dict( type='MegviiHeatmap', input_size=(192, 256), heatmap_size=(48, 64), kernel_size=5) ]), dict(type='PackPoseInputs') ])) val_dataloader = dict( batch_size=32, num_workers=4, persistent_workers=True, drop_last=False, sampler=dict(type='DefaultSampler', shuffle=False, round_up=False), dataset=dict( type='CocoDataset', data_root='data/coco/', data_mode='topdown', ann_file='annotations/person_keypoints_val2017.json', bbox_file= 'data/coco/person_detection_results/COCO_val2017_detections_AP_H_56_person.json', data_prefix=dict(img='val2017/'), test_mode=True, pipeline=[ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='TopdownAffine', input_size=(192, 256)), dict(type='PackPoseInputs') ])) test_dataloader = dict( batch_size=32, num_workers=4, persistent_workers=True, drop_last=False, sampler=dict(type='DefaultSampler', shuffle=False, round_up=False), dataset=dict( type='CocoDataset', data_root='data/coco/', data_mode='topdown', ann_file='annotations/person_keypoints_val2017.json', bbox_file= 'data/coco/person_detection_results/COCO_val2017_detections_AP_H_56_person.json', data_prefix=dict(img='val2017/'), test_mode=True, pipeline=[ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='TopdownAffine', input_size=(192, 256)), dict(type='PackPoseInputs') ])) val_evaluator = dict( type='CocoMetric', ann_file='data/coco/annotations/person_keypoints_val2017.json', nms_mode='none') test_evaluator = dict( type='CocoMetric', ann_file='data/coco/annotations/person_keypoints_val2017.json', nms_mode='none') fp16 = dict(loss_scale='dynamic') launcher = 'slurm' work_dir = 'work_dirs/20221012/rsn2x/' 2022/10/12 11:02:56 - mmengine - WARNING - Failed to search registry with scope "mmpose" in the "data sampler" registry tree. As a workaround, the current "data sampler" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmpose" is a correct scope, or whether the registry is initialized. 2022/10/12 11:02:56 - mmengine - WARNING - Failed to search registry with scope "mmpose" in the "optimizer wrapper constructor" registry tree. As a workaround, the current "optimizer wrapper constructor" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmpose" is a correct scope, or whether the registry is initialized. 2022/10/12 11:02:56 - mmengine - WARNING - Failed to search registry with scope "mmpose" in the "optimizer" registry tree. As a workaround, the current "optimizer" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmpose" is a correct scope, or whether the registry is initialized. 2022/10/12 11:02:56 - mmengine - WARNING - Failed to search registry with scope "mmpose" in the "optim_wrapper" registry tree. As a workaround, the current "optim_wrapper" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmpose" is a correct scope, or whether the registry is initialized. 2022/10/12 11:02:56 - mmengine - WARNING - Failed to search registry with scope "mmpose" in the "parameter scheduler" registry tree. As a workaround, the current "parameter scheduler" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmpose" is a correct scope, or whether the registry is initialized. 2022/10/12 11:02:56 - mmengine - WARNING - Failed to search registry with scope "mmpose" in the "parameter scheduler" registry tree. As a workaround, the current "parameter scheduler" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmpose" is a correct scope, or whether the registry is initialized. 2022/10/12 11:02:56 - mmengine - WARNING - Failed to search registry with scope "mmpose" in the "parameter scheduler" registry tree. As a workaround, the current "parameter scheduler" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmpose" is a correct scope, or whether the registry is initialized. 2022/10/12 11:02:56 - mmengine - WARNING - Failed to search registry with scope "mmpose" in the "parameter scheduler" registry tree. As a workaround, the current "parameter scheduler" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmpose" is a correct scope, or whether the registry is initialized. 2022/10/12 11:02:59 - mmengine - WARNING - Failed to search registry with scope "mmpose" in the "data sampler" registry tree. As a workaround, the current "data sampler" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmpose" is a correct scope, or whether the registry is initialized. 2022/10/12 11:03:02 - mmengine - WARNING - Failed to search registry with scope "mmpose" in the "weight initializer" registry tree. As a workaround, the current "weight initializer" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmpose" is a correct scope, or whether the registry is initialized. 2022/10/12 11:03:02 - mmengine - WARNING - Failed to search registry with scope "mmpose" in the "weight initializer" registry tree. As a workaround, the current "weight initializer" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmpose" is a correct scope, or whether the registry is initialized. 2022/10/12 11:03:02 - mmengine - WARNING - Failed to search registry with scope "mmpose" in the "weight initializer" registry tree. As a workaround, the current "weight initializer" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmpose" is a correct scope, or whether the registry is initialized. 2022/10/12 11:03:02 - mmengine - WARNING - Failed to search registry with scope "mmpose" in the "weight initializer" registry tree. As a workaround, the current "weight initializer" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmpose" is a correct scope, or whether the registry is initialized. 2022/10/12 11:03:02 - mmengine - WARNING - Failed to search registry with scope "mmpose" in the "weight initializer" registry tree. As a workaround, the current "weight initializer" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmpose" is a correct scope, or whether the registry is initialized. 2022/10/12 11:03:02 - mmengine - WARNING - Failed to search registry with scope "mmpose" in the "weight initializer" registry tree. As a workaround, the current "weight initializer" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmpose" is a correct scope, or whether the registry is initialized. Name of parameter - Initialization information backbone.top.top.0.conv.weight - torch.Size([64, 3, 7, 7]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.top.top.0.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.top.top.0.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.0.conv_bn_relu1.conv.weight - torch.Size([104, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer1.0.conv_bn_relu1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.0.conv_bn_relu1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.0.conv_bn_relu2_1_1.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer1.0.conv_bn_relu2_1_1.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.0.conv_bn_relu2_1_1.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.0.conv_bn_relu2_2_1.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer1.0.conv_bn_relu2_2_1.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.0.conv_bn_relu2_2_1.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.0.conv_bn_relu2_2_2.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer1.0.conv_bn_relu2_2_2.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.0.conv_bn_relu2_2_2.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.0.conv_bn_relu2_3_1.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer1.0.conv_bn_relu2_3_1.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.0.conv_bn_relu2_3_1.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.0.conv_bn_relu2_3_2.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer1.0.conv_bn_relu2_3_2.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.0.conv_bn_relu2_3_2.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.0.conv_bn_relu2_3_3.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer1.0.conv_bn_relu2_3_3.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.0.conv_bn_relu2_3_3.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.0.conv_bn_relu2_4_1.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer1.0.conv_bn_relu2_4_1.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.0.conv_bn_relu2_4_1.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.0.conv_bn_relu2_4_2.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer1.0.conv_bn_relu2_4_2.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.0.conv_bn_relu2_4_2.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.0.conv_bn_relu2_4_3.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer1.0.conv_bn_relu2_4_3.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.0.conv_bn_relu2_4_3.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.0.conv_bn_relu2_4_4.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer1.0.conv_bn_relu2_4_4.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.0.conv_bn_relu2_4_4.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.0.conv_bn3.conv.weight - torch.Size([64, 104, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer1.0.conv_bn3.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.0.conv_bn3.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.1.conv_bn_relu1.conv.weight - torch.Size([104, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer1.1.conv_bn_relu1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.1.conv_bn_relu1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.1.conv_bn_relu2_1_1.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer1.1.conv_bn_relu2_1_1.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.1.conv_bn_relu2_1_1.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.1.conv_bn_relu2_2_1.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer1.1.conv_bn_relu2_2_1.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.1.conv_bn_relu2_2_1.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.1.conv_bn_relu2_2_2.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer1.1.conv_bn_relu2_2_2.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.1.conv_bn_relu2_2_2.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.1.conv_bn_relu2_3_1.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer1.1.conv_bn_relu2_3_1.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.1.conv_bn_relu2_3_1.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.1.conv_bn_relu2_3_2.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer1.1.conv_bn_relu2_3_2.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.1.conv_bn_relu2_3_2.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.1.conv_bn_relu2_3_3.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer1.1.conv_bn_relu2_3_3.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.1.conv_bn_relu2_3_3.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.1.conv_bn_relu2_4_1.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer1.1.conv_bn_relu2_4_1.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.1.conv_bn_relu2_4_1.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.1.conv_bn_relu2_4_2.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer1.1.conv_bn_relu2_4_2.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.1.conv_bn_relu2_4_2.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.1.conv_bn_relu2_4_3.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer1.1.conv_bn_relu2_4_3.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.1.conv_bn_relu2_4_3.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.1.conv_bn_relu2_4_4.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer1.1.conv_bn_relu2_4_4.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.1.conv_bn_relu2_4_4.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.1.conv_bn3.conv.weight - torch.Size([64, 104, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer1.1.conv_bn3.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.1.conv_bn3.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.2.conv_bn_relu1.conv.weight - torch.Size([104, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer1.2.conv_bn_relu1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.2.conv_bn_relu1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.2.conv_bn_relu2_1_1.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer1.2.conv_bn_relu2_1_1.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.2.conv_bn_relu2_1_1.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.2.conv_bn_relu2_2_1.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer1.2.conv_bn_relu2_2_1.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.2.conv_bn_relu2_2_1.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.2.conv_bn_relu2_2_2.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer1.2.conv_bn_relu2_2_2.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.2.conv_bn_relu2_2_2.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.2.conv_bn_relu2_3_1.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer1.2.conv_bn_relu2_3_1.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.2.conv_bn_relu2_3_1.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.2.conv_bn_relu2_3_2.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer1.2.conv_bn_relu2_3_2.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.2.conv_bn_relu2_3_2.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.2.conv_bn_relu2_3_3.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer1.2.conv_bn_relu2_3_3.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.2.conv_bn_relu2_3_3.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.2.conv_bn_relu2_4_1.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer1.2.conv_bn_relu2_4_1.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.2.conv_bn_relu2_4_1.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.2.conv_bn_relu2_4_2.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer1.2.conv_bn_relu2_4_2.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.2.conv_bn_relu2_4_2.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.2.conv_bn_relu2_4_3.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer1.2.conv_bn_relu2_4_3.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.2.conv_bn_relu2_4_3.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.2.conv_bn_relu2_4_4.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer1.2.conv_bn_relu2_4_4.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.2.conv_bn_relu2_4_4.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.2.conv_bn3.conv.weight - torch.Size([64, 104, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer1.2.conv_bn3.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer1.2.conv_bn3.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.0.downsample.conv.weight - torch.Size([128, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.0.downsample.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.0.downsample.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.0.conv_bn_relu1.conv.weight - torch.Size([104, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.0.conv_bn_relu1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.0.conv_bn_relu1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.0.conv_bn_relu2_1_1.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.0.conv_bn_relu2_1_1.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.0.conv_bn_relu2_1_1.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.0.conv_bn_relu2_2_1.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.0.conv_bn_relu2_2_1.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.0.conv_bn_relu2_2_1.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.0.conv_bn_relu2_2_2.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.0.conv_bn_relu2_2_2.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.0.conv_bn_relu2_2_2.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.0.conv_bn_relu2_3_1.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.0.conv_bn_relu2_3_1.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.0.conv_bn_relu2_3_1.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.0.conv_bn_relu2_3_2.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.0.conv_bn_relu2_3_2.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.0.conv_bn_relu2_3_2.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.0.conv_bn_relu2_3_3.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.0.conv_bn_relu2_3_3.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.0.conv_bn_relu2_3_3.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.0.conv_bn_relu2_4_1.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.0.conv_bn_relu2_4_1.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.0.conv_bn_relu2_4_1.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.0.conv_bn_relu2_4_2.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.0.conv_bn_relu2_4_2.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.0.conv_bn_relu2_4_2.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.0.conv_bn_relu2_4_3.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.0.conv_bn_relu2_4_3.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.0.conv_bn_relu2_4_3.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.0.conv_bn_relu2_4_4.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.0.conv_bn_relu2_4_4.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.0.conv_bn_relu2_4_4.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.0.conv_bn3.conv.weight - torch.Size([128, 104, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.0.conv_bn3.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.0.conv_bn3.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.1.conv_bn_relu1.conv.weight - torch.Size([208, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.1.conv_bn_relu1.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.1.conv_bn_relu1.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.1.conv_bn_relu2_1_1.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.1.conv_bn_relu2_1_1.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.1.conv_bn_relu2_1_1.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.1.conv_bn_relu2_2_1.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.1.conv_bn_relu2_2_1.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.1.conv_bn_relu2_2_1.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.1.conv_bn_relu2_2_2.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.1.conv_bn_relu2_2_2.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.1.conv_bn_relu2_2_2.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.1.conv_bn_relu2_3_1.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.1.conv_bn_relu2_3_1.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.1.conv_bn_relu2_3_1.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.1.conv_bn_relu2_3_2.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.1.conv_bn_relu2_3_2.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.1.conv_bn_relu2_3_2.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.1.conv_bn_relu2_3_3.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.1.conv_bn_relu2_3_3.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.1.conv_bn_relu2_3_3.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.1.conv_bn_relu2_4_1.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.1.conv_bn_relu2_4_1.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.1.conv_bn_relu2_4_1.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.1.conv_bn_relu2_4_2.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.1.conv_bn_relu2_4_2.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.1.conv_bn_relu2_4_2.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.1.conv_bn_relu2_4_3.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.1.conv_bn_relu2_4_3.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.1.conv_bn_relu2_4_3.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.1.conv_bn_relu2_4_4.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.1.conv_bn_relu2_4_4.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.1.conv_bn_relu2_4_4.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.1.conv_bn3.conv.weight - torch.Size([128, 208, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.1.conv_bn3.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.1.conv_bn3.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.2.conv_bn_relu1.conv.weight - torch.Size([208, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.2.conv_bn_relu1.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.2.conv_bn_relu1.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.2.conv_bn_relu2_1_1.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.2.conv_bn_relu2_1_1.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.2.conv_bn_relu2_1_1.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.2.conv_bn_relu2_2_1.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.2.conv_bn_relu2_2_1.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.2.conv_bn_relu2_2_1.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.2.conv_bn_relu2_2_2.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.2.conv_bn_relu2_2_2.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.2.conv_bn_relu2_2_2.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.2.conv_bn_relu2_3_1.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.2.conv_bn_relu2_3_1.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.2.conv_bn_relu2_3_1.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.2.conv_bn_relu2_3_2.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.2.conv_bn_relu2_3_2.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.2.conv_bn_relu2_3_2.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.2.conv_bn_relu2_3_3.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.2.conv_bn_relu2_3_3.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.2.conv_bn_relu2_3_3.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.2.conv_bn_relu2_4_1.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.2.conv_bn_relu2_4_1.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.2.conv_bn_relu2_4_1.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.2.conv_bn_relu2_4_2.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.2.conv_bn_relu2_4_2.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.2.conv_bn_relu2_4_2.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.2.conv_bn_relu2_4_3.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.2.conv_bn_relu2_4_3.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.2.conv_bn_relu2_4_3.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.2.conv_bn_relu2_4_4.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.2.conv_bn_relu2_4_4.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.2.conv_bn_relu2_4_4.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.2.conv_bn3.conv.weight - torch.Size([128, 208, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.2.conv_bn3.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.2.conv_bn3.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.3.conv_bn_relu1.conv.weight - torch.Size([208, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.3.conv_bn_relu1.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.3.conv_bn_relu1.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.3.conv_bn_relu2_1_1.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.3.conv_bn_relu2_1_1.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.3.conv_bn_relu2_1_1.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.3.conv_bn_relu2_2_1.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.3.conv_bn_relu2_2_1.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.3.conv_bn_relu2_2_1.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.3.conv_bn_relu2_2_2.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.3.conv_bn_relu2_2_2.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.3.conv_bn_relu2_2_2.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.3.conv_bn_relu2_3_1.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.3.conv_bn_relu2_3_1.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.3.conv_bn_relu2_3_1.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.3.conv_bn_relu2_3_2.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.3.conv_bn_relu2_3_2.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.3.conv_bn_relu2_3_2.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.3.conv_bn_relu2_3_3.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.3.conv_bn_relu2_3_3.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.3.conv_bn_relu2_3_3.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.3.conv_bn_relu2_4_1.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.3.conv_bn_relu2_4_1.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.3.conv_bn_relu2_4_1.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.3.conv_bn_relu2_4_2.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.3.conv_bn_relu2_4_2.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.3.conv_bn_relu2_4_2.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.3.conv_bn_relu2_4_3.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.3.conv_bn_relu2_4_3.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.3.conv_bn_relu2_4_3.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.3.conv_bn_relu2_4_4.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.3.conv_bn_relu2_4_4.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.3.conv_bn_relu2_4_4.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.3.conv_bn3.conv.weight - torch.Size([128, 208, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer2.3.conv_bn3.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer2.3.conv_bn3.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.0.downsample.conv.weight - torch.Size([256, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.0.downsample.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.0.downsample.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.0.conv_bn_relu1.conv.weight - torch.Size([208, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.0.conv_bn_relu1.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.0.conv_bn_relu1.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.0.conv_bn_relu2_1_1.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.0.conv_bn_relu2_1_1.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.0.conv_bn_relu2_1_1.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.0.conv_bn_relu2_2_1.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.0.conv_bn_relu2_2_1.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.0.conv_bn_relu2_2_1.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.0.conv_bn_relu2_2_2.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.0.conv_bn_relu2_2_2.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.0.conv_bn_relu2_2_2.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.0.conv_bn_relu2_3_1.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.0.conv_bn_relu2_3_1.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.0.conv_bn_relu2_3_1.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.0.conv_bn_relu2_3_2.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.0.conv_bn_relu2_3_2.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.0.conv_bn_relu2_3_2.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.0.conv_bn_relu2_3_3.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.0.conv_bn_relu2_3_3.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.0.conv_bn_relu2_3_3.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.0.conv_bn_relu2_4_1.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.0.conv_bn_relu2_4_1.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.0.conv_bn_relu2_4_1.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.0.conv_bn_relu2_4_2.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.0.conv_bn_relu2_4_2.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.0.conv_bn_relu2_4_2.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.0.conv_bn_relu2_4_3.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.0.conv_bn_relu2_4_3.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.0.conv_bn_relu2_4_3.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.0.conv_bn_relu2_4_4.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.0.conv_bn_relu2_4_4.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.0.conv_bn_relu2_4_4.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.0.conv_bn3.conv.weight - torch.Size([256, 208, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.0.conv_bn3.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.0.conv_bn3.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.1.conv_bn_relu1.conv.weight - torch.Size([416, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.1.conv_bn_relu1.bn.weight - torch.Size([416]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.1.conv_bn_relu1.bn.bias - torch.Size([416]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.1.conv_bn_relu2_1_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.1.conv_bn_relu2_1_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.1.conv_bn_relu2_1_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.1.conv_bn_relu2_2_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.1.conv_bn_relu2_2_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.1.conv_bn_relu2_2_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.1.conv_bn_relu2_2_2.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.1.conv_bn_relu2_2_2.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.1.conv_bn_relu2_2_2.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.1.conv_bn_relu2_3_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.1.conv_bn_relu2_3_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.1.conv_bn_relu2_3_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.1.conv_bn_relu2_3_2.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.1.conv_bn_relu2_3_2.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.1.conv_bn_relu2_3_2.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.1.conv_bn_relu2_3_3.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.1.conv_bn_relu2_3_3.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.1.conv_bn_relu2_3_3.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.1.conv_bn_relu2_4_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.1.conv_bn_relu2_4_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.1.conv_bn_relu2_4_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.1.conv_bn_relu2_4_2.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.1.conv_bn_relu2_4_2.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.1.conv_bn_relu2_4_2.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.1.conv_bn_relu2_4_3.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.1.conv_bn_relu2_4_3.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.1.conv_bn_relu2_4_3.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.1.conv_bn_relu2_4_4.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.1.conv_bn_relu2_4_4.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.1.conv_bn_relu2_4_4.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.1.conv_bn3.conv.weight - torch.Size([256, 416, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.1.conv_bn3.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.1.conv_bn3.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.2.conv_bn_relu1.conv.weight - torch.Size([416, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.2.conv_bn_relu1.bn.weight - torch.Size([416]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.2.conv_bn_relu1.bn.bias - torch.Size([416]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.2.conv_bn_relu2_1_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.2.conv_bn_relu2_1_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.2.conv_bn_relu2_1_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.2.conv_bn_relu2_2_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.2.conv_bn_relu2_2_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.2.conv_bn_relu2_2_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.2.conv_bn_relu2_2_2.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.2.conv_bn_relu2_2_2.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.2.conv_bn_relu2_2_2.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.2.conv_bn_relu2_3_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.2.conv_bn_relu2_3_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.2.conv_bn_relu2_3_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.2.conv_bn_relu2_3_2.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.2.conv_bn_relu2_3_2.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.2.conv_bn_relu2_3_2.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.2.conv_bn_relu2_3_3.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.2.conv_bn_relu2_3_3.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.2.conv_bn_relu2_3_3.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.2.conv_bn_relu2_4_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.2.conv_bn_relu2_4_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.2.conv_bn_relu2_4_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.2.conv_bn_relu2_4_2.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.2.conv_bn_relu2_4_2.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.2.conv_bn_relu2_4_2.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.2.conv_bn_relu2_4_3.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.2.conv_bn_relu2_4_3.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.2.conv_bn_relu2_4_3.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.2.conv_bn_relu2_4_4.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.2.conv_bn_relu2_4_4.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.2.conv_bn_relu2_4_4.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.2.conv_bn3.conv.weight - torch.Size([256, 416, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.2.conv_bn3.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.2.conv_bn3.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.3.conv_bn_relu1.conv.weight - torch.Size([416, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.3.conv_bn_relu1.bn.weight - torch.Size([416]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.3.conv_bn_relu1.bn.bias - torch.Size([416]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.3.conv_bn_relu2_1_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.3.conv_bn_relu2_1_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.3.conv_bn_relu2_1_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.3.conv_bn_relu2_2_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.3.conv_bn_relu2_2_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.3.conv_bn_relu2_2_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.3.conv_bn_relu2_2_2.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.3.conv_bn_relu2_2_2.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.3.conv_bn_relu2_2_2.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.3.conv_bn_relu2_3_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.3.conv_bn_relu2_3_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.3.conv_bn_relu2_3_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.3.conv_bn_relu2_3_2.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.3.conv_bn_relu2_3_2.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.3.conv_bn_relu2_3_2.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.3.conv_bn_relu2_3_3.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.3.conv_bn_relu2_3_3.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.3.conv_bn_relu2_3_3.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.3.conv_bn_relu2_4_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.3.conv_bn_relu2_4_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.3.conv_bn_relu2_4_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.3.conv_bn_relu2_4_2.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.3.conv_bn_relu2_4_2.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.3.conv_bn_relu2_4_2.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.3.conv_bn_relu2_4_3.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.3.conv_bn_relu2_4_3.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.3.conv_bn_relu2_4_3.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.3.conv_bn_relu2_4_4.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.3.conv_bn_relu2_4_4.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.3.conv_bn_relu2_4_4.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.3.conv_bn3.conv.weight - torch.Size([256, 416, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.3.conv_bn3.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.3.conv_bn3.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.4.conv_bn_relu1.conv.weight - torch.Size([416, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.4.conv_bn_relu1.bn.weight - torch.Size([416]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.4.conv_bn_relu1.bn.bias - torch.Size([416]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.4.conv_bn_relu2_1_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.4.conv_bn_relu2_1_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.4.conv_bn_relu2_1_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.4.conv_bn_relu2_2_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.4.conv_bn_relu2_2_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.4.conv_bn_relu2_2_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.4.conv_bn_relu2_2_2.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.4.conv_bn_relu2_2_2.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.4.conv_bn_relu2_2_2.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.4.conv_bn_relu2_3_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.4.conv_bn_relu2_3_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.4.conv_bn_relu2_3_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.4.conv_bn_relu2_3_2.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.4.conv_bn_relu2_3_2.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.4.conv_bn_relu2_3_2.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.4.conv_bn_relu2_3_3.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.4.conv_bn_relu2_3_3.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.4.conv_bn_relu2_3_3.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.4.conv_bn_relu2_4_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.4.conv_bn_relu2_4_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.4.conv_bn_relu2_4_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.4.conv_bn_relu2_4_2.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.4.conv_bn_relu2_4_2.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.4.conv_bn_relu2_4_2.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.4.conv_bn_relu2_4_3.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.4.conv_bn_relu2_4_3.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.4.conv_bn_relu2_4_3.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.4.conv_bn_relu2_4_4.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.4.conv_bn_relu2_4_4.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.4.conv_bn_relu2_4_4.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.4.conv_bn3.conv.weight - torch.Size([256, 416, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.4.conv_bn3.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.4.conv_bn3.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.5.conv_bn_relu1.conv.weight - torch.Size([416, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.5.conv_bn_relu1.bn.weight - torch.Size([416]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.5.conv_bn_relu1.bn.bias - torch.Size([416]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.5.conv_bn_relu2_1_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.5.conv_bn_relu2_1_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.5.conv_bn_relu2_1_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.5.conv_bn_relu2_2_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.5.conv_bn_relu2_2_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.5.conv_bn_relu2_2_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.5.conv_bn_relu2_2_2.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.5.conv_bn_relu2_2_2.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.5.conv_bn_relu2_2_2.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.5.conv_bn_relu2_3_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.5.conv_bn_relu2_3_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.5.conv_bn_relu2_3_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.5.conv_bn_relu2_3_2.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.5.conv_bn_relu2_3_2.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.5.conv_bn_relu2_3_2.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.5.conv_bn_relu2_3_3.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.5.conv_bn_relu2_3_3.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.5.conv_bn_relu2_3_3.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.5.conv_bn_relu2_4_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.5.conv_bn_relu2_4_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.5.conv_bn_relu2_4_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.5.conv_bn_relu2_4_2.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.5.conv_bn_relu2_4_2.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.5.conv_bn_relu2_4_2.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.5.conv_bn_relu2_4_3.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.5.conv_bn_relu2_4_3.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.5.conv_bn_relu2_4_3.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.5.conv_bn_relu2_4_4.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.5.conv_bn_relu2_4_4.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.5.conv_bn_relu2_4_4.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.5.conv_bn3.conv.weight - torch.Size([256, 416, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer3.5.conv_bn3.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer3.5.conv_bn3.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.0.downsample.conv.weight - torch.Size([512, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer4.0.downsample.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.0.downsample.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.0.conv_bn_relu1.conv.weight - torch.Size([416, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer4.0.conv_bn_relu1.bn.weight - torch.Size([416]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.0.conv_bn_relu1.bn.bias - torch.Size([416]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.0.conv_bn_relu2_1_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer4.0.conv_bn_relu2_1_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.0.conv_bn_relu2_1_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.0.conv_bn_relu2_2_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer4.0.conv_bn_relu2_2_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.0.conv_bn_relu2_2_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.0.conv_bn_relu2_2_2.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer4.0.conv_bn_relu2_2_2.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.0.conv_bn_relu2_2_2.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.0.conv_bn_relu2_3_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer4.0.conv_bn_relu2_3_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.0.conv_bn_relu2_3_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.0.conv_bn_relu2_3_2.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer4.0.conv_bn_relu2_3_2.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.0.conv_bn_relu2_3_2.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.0.conv_bn_relu2_3_3.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer4.0.conv_bn_relu2_3_3.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.0.conv_bn_relu2_3_3.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.0.conv_bn_relu2_4_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer4.0.conv_bn_relu2_4_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.0.conv_bn_relu2_4_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.0.conv_bn_relu2_4_2.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer4.0.conv_bn_relu2_4_2.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.0.conv_bn_relu2_4_2.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.0.conv_bn_relu2_4_3.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer4.0.conv_bn_relu2_4_3.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.0.conv_bn_relu2_4_3.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.0.conv_bn_relu2_4_4.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer4.0.conv_bn_relu2_4_4.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.0.conv_bn_relu2_4_4.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.0.conv_bn3.conv.weight - torch.Size([512, 416, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer4.0.conv_bn3.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.0.conv_bn3.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.1.conv_bn_relu1.conv.weight - torch.Size([832, 512, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer4.1.conv_bn_relu1.bn.weight - torch.Size([832]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.1.conv_bn_relu1.bn.bias - torch.Size([832]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.1.conv_bn_relu2_1_1.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer4.1.conv_bn_relu2_1_1.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.1.conv_bn_relu2_1_1.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.1.conv_bn_relu2_2_1.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer4.1.conv_bn_relu2_2_1.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.1.conv_bn_relu2_2_1.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.1.conv_bn_relu2_2_2.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer4.1.conv_bn_relu2_2_2.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.1.conv_bn_relu2_2_2.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.1.conv_bn_relu2_3_1.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer4.1.conv_bn_relu2_3_1.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.1.conv_bn_relu2_3_1.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.1.conv_bn_relu2_3_2.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer4.1.conv_bn_relu2_3_2.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.1.conv_bn_relu2_3_2.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.1.conv_bn_relu2_3_3.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer4.1.conv_bn_relu2_3_3.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.1.conv_bn_relu2_3_3.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.1.conv_bn_relu2_4_1.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer4.1.conv_bn_relu2_4_1.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.1.conv_bn_relu2_4_1.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.1.conv_bn_relu2_4_2.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer4.1.conv_bn_relu2_4_2.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.1.conv_bn_relu2_4_2.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.1.conv_bn_relu2_4_3.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer4.1.conv_bn_relu2_4_3.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.1.conv_bn_relu2_4_3.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.1.conv_bn_relu2_4_4.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer4.1.conv_bn_relu2_4_4.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.1.conv_bn_relu2_4_4.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.1.conv_bn3.conv.weight - torch.Size([512, 832, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer4.1.conv_bn3.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.1.conv_bn3.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.2.conv_bn_relu1.conv.weight - torch.Size([832, 512, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer4.2.conv_bn_relu1.bn.weight - torch.Size([832]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.2.conv_bn_relu1.bn.bias - torch.Size([832]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.2.conv_bn_relu2_1_1.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer4.2.conv_bn_relu2_1_1.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.2.conv_bn_relu2_1_1.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.2.conv_bn_relu2_2_1.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer4.2.conv_bn_relu2_2_1.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.2.conv_bn_relu2_2_1.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.2.conv_bn_relu2_2_2.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer4.2.conv_bn_relu2_2_2.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.2.conv_bn_relu2_2_2.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.2.conv_bn_relu2_3_1.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer4.2.conv_bn_relu2_3_1.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.2.conv_bn_relu2_3_1.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.2.conv_bn_relu2_3_2.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer4.2.conv_bn_relu2_3_2.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.2.conv_bn_relu2_3_2.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.2.conv_bn_relu2_3_3.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer4.2.conv_bn_relu2_3_3.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.2.conv_bn_relu2_3_3.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.2.conv_bn_relu2_4_1.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer4.2.conv_bn_relu2_4_1.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.2.conv_bn_relu2_4_1.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.2.conv_bn_relu2_4_2.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer4.2.conv_bn_relu2_4_2.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.2.conv_bn_relu2_4_2.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.2.conv_bn_relu2_4_3.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer4.2.conv_bn_relu2_4_3.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.2.conv_bn_relu2_4_3.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.2.conv_bn_relu2_4_4.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer4.2.conv_bn_relu2_4_4.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.2.conv_bn_relu2_4_4.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.2.conv_bn3.conv.weight - torch.Size([512, 832, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.downsample.layer4.2.conv_bn3.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.downsample.layer4.2.conv_bn3.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.upsample.up1.in_skip.conv.weight - torch.Size([256, 512, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.upsample.up1.in_skip.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.upsample.up1.in_skip.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.upsample.up1.out_skip1.conv.weight - torch.Size([512, 512, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.upsample.up1.out_skip1.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.upsample.up1.out_skip1.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.upsample.up1.out_skip2.conv.weight - torch.Size([512, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.upsample.up1.out_skip2.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.upsample.up1.out_skip2.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.upsample.up2.in_skip.conv.weight - torch.Size([256, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.upsample.up2.in_skip.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.upsample.up2.in_skip.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.upsample.up2.up_conv.conv.weight - torch.Size([256, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.upsample.up2.up_conv.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.upsample.up2.up_conv.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.upsample.up2.out_skip1.conv.weight - torch.Size([256, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.upsample.up2.out_skip1.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.upsample.up2.out_skip1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.upsample.up2.out_skip2.conv.weight - torch.Size([256, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.upsample.up2.out_skip2.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.upsample.up2.out_skip2.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.upsample.up3.in_skip.conv.weight - torch.Size([256, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.upsample.up3.in_skip.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.upsample.up3.in_skip.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.upsample.up3.up_conv.conv.weight - torch.Size([256, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.upsample.up3.up_conv.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.upsample.up3.up_conv.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.upsample.up3.out_skip1.conv.weight - torch.Size([128, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.upsample.up3.out_skip1.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.upsample.up3.out_skip1.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.upsample.up3.out_skip2.conv.weight - torch.Size([128, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.upsample.up3.out_skip2.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.upsample.up3.out_skip2.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.upsample.up4.in_skip.conv.weight - torch.Size([256, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.upsample.up4.in_skip.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.upsample.up4.in_skip.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.upsample.up4.up_conv.conv.weight - torch.Size([256, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.upsample.up4.up_conv.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.upsample.up4.up_conv.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.upsample.up4.out_skip1.conv.weight - torch.Size([64, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.upsample.up4.out_skip1.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.upsample.up4.out_skip1.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.upsample.up4.out_skip2.conv.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.upsample.up4.out_skip2.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.upsample.up4.out_skip2.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.upsample.up4.cross_conv.conv.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.0.upsample.up4.cross_conv.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.0.upsample.up4.cross_conv.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.0.conv_bn_relu1.conv.weight - torch.Size([104, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer1.0.conv_bn_relu1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.0.conv_bn_relu1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.0.conv_bn_relu2_1_1.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer1.0.conv_bn_relu2_1_1.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.0.conv_bn_relu2_1_1.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.0.conv_bn_relu2_2_1.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer1.0.conv_bn_relu2_2_1.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.0.conv_bn_relu2_2_1.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.0.conv_bn_relu2_2_2.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer1.0.conv_bn_relu2_2_2.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.0.conv_bn_relu2_2_2.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.0.conv_bn_relu2_3_1.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer1.0.conv_bn_relu2_3_1.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.0.conv_bn_relu2_3_1.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.0.conv_bn_relu2_3_2.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer1.0.conv_bn_relu2_3_2.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.0.conv_bn_relu2_3_2.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.0.conv_bn_relu2_3_3.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer1.0.conv_bn_relu2_3_3.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.0.conv_bn_relu2_3_3.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.0.conv_bn_relu2_4_1.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer1.0.conv_bn_relu2_4_1.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.0.conv_bn_relu2_4_1.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.0.conv_bn_relu2_4_2.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer1.0.conv_bn_relu2_4_2.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.0.conv_bn_relu2_4_2.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.0.conv_bn_relu2_4_3.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer1.0.conv_bn_relu2_4_3.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.0.conv_bn_relu2_4_3.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.0.conv_bn_relu2_4_4.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer1.0.conv_bn_relu2_4_4.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.0.conv_bn_relu2_4_4.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.0.conv_bn3.conv.weight - torch.Size([64, 104, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer1.0.conv_bn3.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.0.conv_bn3.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.1.conv_bn_relu1.conv.weight - torch.Size([104, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer1.1.conv_bn_relu1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.1.conv_bn_relu1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.1.conv_bn_relu2_1_1.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer1.1.conv_bn_relu2_1_1.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.1.conv_bn_relu2_1_1.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.1.conv_bn_relu2_2_1.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer1.1.conv_bn_relu2_2_1.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.1.conv_bn_relu2_2_1.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.1.conv_bn_relu2_2_2.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer1.1.conv_bn_relu2_2_2.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.1.conv_bn_relu2_2_2.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.1.conv_bn_relu2_3_1.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer1.1.conv_bn_relu2_3_1.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.1.conv_bn_relu2_3_1.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.1.conv_bn_relu2_3_2.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer1.1.conv_bn_relu2_3_2.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.1.conv_bn_relu2_3_2.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.1.conv_bn_relu2_3_3.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer1.1.conv_bn_relu2_3_3.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.1.conv_bn_relu2_3_3.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.1.conv_bn_relu2_4_1.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer1.1.conv_bn_relu2_4_1.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.1.conv_bn_relu2_4_1.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.1.conv_bn_relu2_4_2.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer1.1.conv_bn_relu2_4_2.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.1.conv_bn_relu2_4_2.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.1.conv_bn_relu2_4_3.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer1.1.conv_bn_relu2_4_3.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.1.conv_bn_relu2_4_3.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.1.conv_bn_relu2_4_4.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer1.1.conv_bn_relu2_4_4.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.1.conv_bn_relu2_4_4.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.1.conv_bn3.conv.weight - torch.Size([64, 104, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer1.1.conv_bn3.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.1.conv_bn3.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.2.conv_bn_relu1.conv.weight - torch.Size([104, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer1.2.conv_bn_relu1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.2.conv_bn_relu1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.2.conv_bn_relu2_1_1.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer1.2.conv_bn_relu2_1_1.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.2.conv_bn_relu2_1_1.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.2.conv_bn_relu2_2_1.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer1.2.conv_bn_relu2_2_1.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.2.conv_bn_relu2_2_1.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.2.conv_bn_relu2_2_2.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer1.2.conv_bn_relu2_2_2.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.2.conv_bn_relu2_2_2.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.2.conv_bn_relu2_3_1.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer1.2.conv_bn_relu2_3_1.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.2.conv_bn_relu2_3_1.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.2.conv_bn_relu2_3_2.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer1.2.conv_bn_relu2_3_2.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.2.conv_bn_relu2_3_2.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.2.conv_bn_relu2_3_3.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer1.2.conv_bn_relu2_3_3.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.2.conv_bn_relu2_3_3.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.2.conv_bn_relu2_4_1.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer1.2.conv_bn_relu2_4_1.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.2.conv_bn_relu2_4_1.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.2.conv_bn_relu2_4_2.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer1.2.conv_bn_relu2_4_2.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.2.conv_bn_relu2_4_2.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.2.conv_bn_relu2_4_3.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer1.2.conv_bn_relu2_4_3.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.2.conv_bn_relu2_4_3.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.2.conv_bn_relu2_4_4.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer1.2.conv_bn_relu2_4_4.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.2.conv_bn_relu2_4_4.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.2.conv_bn3.conv.weight - torch.Size([64, 104, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer1.2.conv_bn3.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer1.2.conv_bn3.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.0.downsample.conv.weight - torch.Size([128, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.0.downsample.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.0.downsample.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.0.conv_bn_relu1.conv.weight - torch.Size([104, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.0.conv_bn_relu1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.0.conv_bn_relu1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.0.conv_bn_relu2_1_1.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.0.conv_bn_relu2_1_1.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.0.conv_bn_relu2_1_1.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.0.conv_bn_relu2_2_1.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.0.conv_bn_relu2_2_1.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.0.conv_bn_relu2_2_1.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.0.conv_bn_relu2_2_2.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.0.conv_bn_relu2_2_2.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.0.conv_bn_relu2_2_2.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.0.conv_bn_relu2_3_1.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.0.conv_bn_relu2_3_1.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.0.conv_bn_relu2_3_1.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.0.conv_bn_relu2_3_2.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.0.conv_bn_relu2_3_2.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.0.conv_bn_relu2_3_2.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.0.conv_bn_relu2_3_3.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.0.conv_bn_relu2_3_3.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.0.conv_bn_relu2_3_3.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.0.conv_bn_relu2_4_1.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.0.conv_bn_relu2_4_1.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.0.conv_bn_relu2_4_1.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.0.conv_bn_relu2_4_2.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.0.conv_bn_relu2_4_2.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.0.conv_bn_relu2_4_2.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.0.conv_bn_relu2_4_3.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.0.conv_bn_relu2_4_3.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.0.conv_bn_relu2_4_3.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.0.conv_bn_relu2_4_4.conv.weight - torch.Size([26, 26, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.0.conv_bn_relu2_4_4.bn.weight - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.0.conv_bn_relu2_4_4.bn.bias - torch.Size([26]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.0.conv_bn3.conv.weight - torch.Size([128, 104, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.0.conv_bn3.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.0.conv_bn3.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.1.conv_bn_relu1.conv.weight - torch.Size([208, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.1.conv_bn_relu1.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.1.conv_bn_relu1.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.1.conv_bn_relu2_1_1.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.1.conv_bn_relu2_1_1.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.1.conv_bn_relu2_1_1.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.1.conv_bn_relu2_2_1.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.1.conv_bn_relu2_2_1.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.1.conv_bn_relu2_2_1.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.1.conv_bn_relu2_2_2.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.1.conv_bn_relu2_2_2.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.1.conv_bn_relu2_2_2.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.1.conv_bn_relu2_3_1.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.1.conv_bn_relu2_3_1.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.1.conv_bn_relu2_3_1.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.1.conv_bn_relu2_3_2.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.1.conv_bn_relu2_3_2.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.1.conv_bn_relu2_3_2.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.1.conv_bn_relu2_3_3.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.1.conv_bn_relu2_3_3.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.1.conv_bn_relu2_3_3.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.1.conv_bn_relu2_4_1.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.1.conv_bn_relu2_4_1.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.1.conv_bn_relu2_4_1.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.1.conv_bn_relu2_4_2.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.1.conv_bn_relu2_4_2.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.1.conv_bn_relu2_4_2.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.1.conv_bn_relu2_4_3.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.1.conv_bn_relu2_4_3.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.1.conv_bn_relu2_4_3.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.1.conv_bn_relu2_4_4.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.1.conv_bn_relu2_4_4.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.1.conv_bn_relu2_4_4.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.1.conv_bn3.conv.weight - torch.Size([128, 208, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.1.conv_bn3.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.1.conv_bn3.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.2.conv_bn_relu1.conv.weight - torch.Size([208, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.2.conv_bn_relu1.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.2.conv_bn_relu1.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.2.conv_bn_relu2_1_1.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.2.conv_bn_relu2_1_1.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.2.conv_bn_relu2_1_1.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.2.conv_bn_relu2_2_1.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.2.conv_bn_relu2_2_1.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.2.conv_bn_relu2_2_1.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.2.conv_bn_relu2_2_2.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.2.conv_bn_relu2_2_2.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.2.conv_bn_relu2_2_2.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.2.conv_bn_relu2_3_1.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.2.conv_bn_relu2_3_1.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.2.conv_bn_relu2_3_1.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.2.conv_bn_relu2_3_2.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.2.conv_bn_relu2_3_2.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.2.conv_bn_relu2_3_2.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.2.conv_bn_relu2_3_3.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.2.conv_bn_relu2_3_3.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.2.conv_bn_relu2_3_3.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.2.conv_bn_relu2_4_1.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.2.conv_bn_relu2_4_1.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.2.conv_bn_relu2_4_1.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.2.conv_bn_relu2_4_2.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.2.conv_bn_relu2_4_2.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.2.conv_bn_relu2_4_2.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.2.conv_bn_relu2_4_3.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.2.conv_bn_relu2_4_3.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.2.conv_bn_relu2_4_3.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.2.conv_bn_relu2_4_4.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.2.conv_bn_relu2_4_4.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.2.conv_bn_relu2_4_4.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.2.conv_bn3.conv.weight - torch.Size([128, 208, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.2.conv_bn3.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.2.conv_bn3.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.3.conv_bn_relu1.conv.weight - torch.Size([208, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.3.conv_bn_relu1.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.3.conv_bn_relu1.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.3.conv_bn_relu2_1_1.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.3.conv_bn_relu2_1_1.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.3.conv_bn_relu2_1_1.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.3.conv_bn_relu2_2_1.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.3.conv_bn_relu2_2_1.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.3.conv_bn_relu2_2_1.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.3.conv_bn_relu2_2_2.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.3.conv_bn_relu2_2_2.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.3.conv_bn_relu2_2_2.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.3.conv_bn_relu2_3_1.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.3.conv_bn_relu2_3_1.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.3.conv_bn_relu2_3_1.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.3.conv_bn_relu2_3_2.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.3.conv_bn_relu2_3_2.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.3.conv_bn_relu2_3_2.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.3.conv_bn_relu2_3_3.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.3.conv_bn_relu2_3_3.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.3.conv_bn_relu2_3_3.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.3.conv_bn_relu2_4_1.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.3.conv_bn_relu2_4_1.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.3.conv_bn_relu2_4_1.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.3.conv_bn_relu2_4_2.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.3.conv_bn_relu2_4_2.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.3.conv_bn_relu2_4_2.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.3.conv_bn_relu2_4_3.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.3.conv_bn_relu2_4_3.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.3.conv_bn_relu2_4_3.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.3.conv_bn_relu2_4_4.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.3.conv_bn_relu2_4_4.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.3.conv_bn_relu2_4_4.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.3.conv_bn3.conv.weight - torch.Size([128, 208, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer2.3.conv_bn3.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer2.3.conv_bn3.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.0.downsample.conv.weight - torch.Size([256, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.0.downsample.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.0.downsample.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.0.conv_bn_relu1.conv.weight - torch.Size([208, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.0.conv_bn_relu1.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.0.conv_bn_relu1.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.0.conv_bn_relu2_1_1.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.0.conv_bn_relu2_1_1.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.0.conv_bn_relu2_1_1.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.0.conv_bn_relu2_2_1.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.0.conv_bn_relu2_2_1.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.0.conv_bn_relu2_2_1.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.0.conv_bn_relu2_2_2.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.0.conv_bn_relu2_2_2.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.0.conv_bn_relu2_2_2.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.0.conv_bn_relu2_3_1.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.0.conv_bn_relu2_3_1.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.0.conv_bn_relu2_3_1.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.0.conv_bn_relu2_3_2.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.0.conv_bn_relu2_3_2.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.0.conv_bn_relu2_3_2.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.0.conv_bn_relu2_3_3.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.0.conv_bn_relu2_3_3.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.0.conv_bn_relu2_3_3.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.0.conv_bn_relu2_4_1.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.0.conv_bn_relu2_4_1.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.0.conv_bn_relu2_4_1.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.0.conv_bn_relu2_4_2.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.0.conv_bn_relu2_4_2.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.0.conv_bn_relu2_4_2.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.0.conv_bn_relu2_4_3.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.0.conv_bn_relu2_4_3.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.0.conv_bn_relu2_4_3.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.0.conv_bn_relu2_4_4.conv.weight - torch.Size([52, 52, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.0.conv_bn_relu2_4_4.bn.weight - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.0.conv_bn_relu2_4_4.bn.bias - torch.Size([52]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.0.conv_bn3.conv.weight - torch.Size([256, 208, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.0.conv_bn3.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.0.conv_bn3.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.1.conv_bn_relu1.conv.weight - torch.Size([416, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.1.conv_bn_relu1.bn.weight - torch.Size([416]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.1.conv_bn_relu1.bn.bias - torch.Size([416]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.1.conv_bn_relu2_1_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.1.conv_bn_relu2_1_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.1.conv_bn_relu2_1_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.1.conv_bn_relu2_2_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.1.conv_bn_relu2_2_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.1.conv_bn_relu2_2_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.1.conv_bn_relu2_2_2.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.1.conv_bn_relu2_2_2.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.1.conv_bn_relu2_2_2.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.1.conv_bn_relu2_3_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.1.conv_bn_relu2_3_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.1.conv_bn_relu2_3_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.1.conv_bn_relu2_3_2.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.1.conv_bn_relu2_3_2.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.1.conv_bn_relu2_3_2.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.1.conv_bn_relu2_3_3.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.1.conv_bn_relu2_3_3.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.1.conv_bn_relu2_3_3.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.1.conv_bn_relu2_4_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.1.conv_bn_relu2_4_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.1.conv_bn_relu2_4_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.1.conv_bn_relu2_4_2.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.1.conv_bn_relu2_4_2.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.1.conv_bn_relu2_4_2.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.1.conv_bn_relu2_4_3.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.1.conv_bn_relu2_4_3.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.1.conv_bn_relu2_4_3.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.1.conv_bn_relu2_4_4.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.1.conv_bn_relu2_4_4.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.1.conv_bn_relu2_4_4.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.1.conv_bn3.conv.weight - torch.Size([256, 416, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.1.conv_bn3.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.1.conv_bn3.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.2.conv_bn_relu1.conv.weight - torch.Size([416, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.2.conv_bn_relu1.bn.weight - torch.Size([416]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.2.conv_bn_relu1.bn.bias - torch.Size([416]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.2.conv_bn_relu2_1_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.2.conv_bn_relu2_1_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.2.conv_bn_relu2_1_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.2.conv_bn_relu2_2_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.2.conv_bn_relu2_2_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.2.conv_bn_relu2_2_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.2.conv_bn_relu2_2_2.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.2.conv_bn_relu2_2_2.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.2.conv_bn_relu2_2_2.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.2.conv_bn_relu2_3_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.2.conv_bn_relu2_3_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.2.conv_bn_relu2_3_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.2.conv_bn_relu2_3_2.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.2.conv_bn_relu2_3_2.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.2.conv_bn_relu2_3_2.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.2.conv_bn_relu2_3_3.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.2.conv_bn_relu2_3_3.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.2.conv_bn_relu2_3_3.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.2.conv_bn_relu2_4_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.2.conv_bn_relu2_4_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.2.conv_bn_relu2_4_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.2.conv_bn_relu2_4_2.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.2.conv_bn_relu2_4_2.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.2.conv_bn_relu2_4_2.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.2.conv_bn_relu2_4_3.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.2.conv_bn_relu2_4_3.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.2.conv_bn_relu2_4_3.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.2.conv_bn_relu2_4_4.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.2.conv_bn_relu2_4_4.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.2.conv_bn_relu2_4_4.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.2.conv_bn3.conv.weight - torch.Size([256, 416, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.2.conv_bn3.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.2.conv_bn3.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.3.conv_bn_relu1.conv.weight - torch.Size([416, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.3.conv_bn_relu1.bn.weight - torch.Size([416]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.3.conv_bn_relu1.bn.bias - torch.Size([416]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.3.conv_bn_relu2_1_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.3.conv_bn_relu2_1_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.3.conv_bn_relu2_1_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.3.conv_bn_relu2_2_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.3.conv_bn_relu2_2_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.3.conv_bn_relu2_2_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.3.conv_bn_relu2_2_2.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.3.conv_bn_relu2_2_2.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.3.conv_bn_relu2_2_2.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.3.conv_bn_relu2_3_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.3.conv_bn_relu2_3_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.3.conv_bn_relu2_3_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.3.conv_bn_relu2_3_2.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.3.conv_bn_relu2_3_2.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.3.conv_bn_relu2_3_2.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.3.conv_bn_relu2_3_3.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.3.conv_bn_relu2_3_3.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.3.conv_bn_relu2_3_3.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.3.conv_bn_relu2_4_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.3.conv_bn_relu2_4_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.3.conv_bn_relu2_4_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.3.conv_bn_relu2_4_2.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.3.conv_bn_relu2_4_2.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.3.conv_bn_relu2_4_2.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.3.conv_bn_relu2_4_3.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.3.conv_bn_relu2_4_3.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.3.conv_bn_relu2_4_3.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.3.conv_bn_relu2_4_4.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.3.conv_bn_relu2_4_4.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.3.conv_bn_relu2_4_4.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.3.conv_bn3.conv.weight - torch.Size([256, 416, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.3.conv_bn3.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.3.conv_bn3.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.4.conv_bn_relu1.conv.weight - torch.Size([416, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.4.conv_bn_relu1.bn.weight - torch.Size([416]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.4.conv_bn_relu1.bn.bias - torch.Size([416]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.4.conv_bn_relu2_1_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.4.conv_bn_relu2_1_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.4.conv_bn_relu2_1_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.4.conv_bn_relu2_2_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.4.conv_bn_relu2_2_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.4.conv_bn_relu2_2_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.4.conv_bn_relu2_2_2.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.4.conv_bn_relu2_2_2.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.4.conv_bn_relu2_2_2.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.4.conv_bn_relu2_3_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.4.conv_bn_relu2_3_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.4.conv_bn_relu2_3_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.4.conv_bn_relu2_3_2.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.4.conv_bn_relu2_3_2.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.4.conv_bn_relu2_3_2.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.4.conv_bn_relu2_3_3.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.4.conv_bn_relu2_3_3.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.4.conv_bn_relu2_3_3.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.4.conv_bn_relu2_4_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.4.conv_bn_relu2_4_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.4.conv_bn_relu2_4_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.4.conv_bn_relu2_4_2.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.4.conv_bn_relu2_4_2.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.4.conv_bn_relu2_4_2.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.4.conv_bn_relu2_4_3.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.4.conv_bn_relu2_4_3.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.4.conv_bn_relu2_4_3.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.4.conv_bn_relu2_4_4.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.4.conv_bn_relu2_4_4.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.4.conv_bn_relu2_4_4.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.4.conv_bn3.conv.weight - torch.Size([256, 416, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.4.conv_bn3.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.4.conv_bn3.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.5.conv_bn_relu1.conv.weight - torch.Size([416, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.5.conv_bn_relu1.bn.weight - torch.Size([416]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.5.conv_bn_relu1.bn.bias - torch.Size([416]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.5.conv_bn_relu2_1_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.5.conv_bn_relu2_1_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.5.conv_bn_relu2_1_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.5.conv_bn_relu2_2_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.5.conv_bn_relu2_2_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.5.conv_bn_relu2_2_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.5.conv_bn_relu2_2_2.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.5.conv_bn_relu2_2_2.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.5.conv_bn_relu2_2_2.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.5.conv_bn_relu2_3_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.5.conv_bn_relu2_3_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.5.conv_bn_relu2_3_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.5.conv_bn_relu2_3_2.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.5.conv_bn_relu2_3_2.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.5.conv_bn_relu2_3_2.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.5.conv_bn_relu2_3_3.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.5.conv_bn_relu2_3_3.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.5.conv_bn_relu2_3_3.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.5.conv_bn_relu2_4_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.5.conv_bn_relu2_4_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.5.conv_bn_relu2_4_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.5.conv_bn_relu2_4_2.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.5.conv_bn_relu2_4_2.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.5.conv_bn_relu2_4_2.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.5.conv_bn_relu2_4_3.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.5.conv_bn_relu2_4_3.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.5.conv_bn_relu2_4_3.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.5.conv_bn_relu2_4_4.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.5.conv_bn_relu2_4_4.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.5.conv_bn_relu2_4_4.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.5.conv_bn3.conv.weight - torch.Size([256, 416, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer3.5.conv_bn3.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer3.5.conv_bn3.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.0.downsample.conv.weight - torch.Size([512, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer4.0.downsample.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.0.downsample.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.0.conv_bn_relu1.conv.weight - torch.Size([416, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer4.0.conv_bn_relu1.bn.weight - torch.Size([416]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.0.conv_bn_relu1.bn.bias - torch.Size([416]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.0.conv_bn_relu2_1_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer4.0.conv_bn_relu2_1_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.0.conv_bn_relu2_1_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.0.conv_bn_relu2_2_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer4.0.conv_bn_relu2_2_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.0.conv_bn_relu2_2_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.0.conv_bn_relu2_2_2.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer4.0.conv_bn_relu2_2_2.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.0.conv_bn_relu2_2_2.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.0.conv_bn_relu2_3_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer4.0.conv_bn_relu2_3_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.0.conv_bn_relu2_3_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.0.conv_bn_relu2_3_2.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer4.0.conv_bn_relu2_3_2.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.0.conv_bn_relu2_3_2.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.0.conv_bn_relu2_3_3.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer4.0.conv_bn_relu2_3_3.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.0.conv_bn_relu2_3_3.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.0.conv_bn_relu2_4_1.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer4.0.conv_bn_relu2_4_1.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.0.conv_bn_relu2_4_1.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.0.conv_bn_relu2_4_2.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer4.0.conv_bn_relu2_4_2.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.0.conv_bn_relu2_4_2.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.0.conv_bn_relu2_4_3.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer4.0.conv_bn_relu2_4_3.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.0.conv_bn_relu2_4_3.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.0.conv_bn_relu2_4_4.conv.weight - torch.Size([104, 104, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer4.0.conv_bn_relu2_4_4.bn.weight - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.0.conv_bn_relu2_4_4.bn.bias - torch.Size([104]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.0.conv_bn3.conv.weight - torch.Size([512, 416, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer4.0.conv_bn3.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.0.conv_bn3.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.1.conv_bn_relu1.conv.weight - torch.Size([832, 512, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer4.1.conv_bn_relu1.bn.weight - torch.Size([832]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.1.conv_bn_relu1.bn.bias - torch.Size([832]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.1.conv_bn_relu2_1_1.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer4.1.conv_bn_relu2_1_1.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.1.conv_bn_relu2_1_1.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.1.conv_bn_relu2_2_1.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer4.1.conv_bn_relu2_2_1.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.1.conv_bn_relu2_2_1.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.1.conv_bn_relu2_2_2.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer4.1.conv_bn_relu2_2_2.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.1.conv_bn_relu2_2_2.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.1.conv_bn_relu2_3_1.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer4.1.conv_bn_relu2_3_1.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.1.conv_bn_relu2_3_1.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.1.conv_bn_relu2_3_2.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer4.1.conv_bn_relu2_3_2.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.1.conv_bn_relu2_3_2.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.1.conv_bn_relu2_3_3.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer4.1.conv_bn_relu2_3_3.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.1.conv_bn_relu2_3_3.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.1.conv_bn_relu2_4_1.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer4.1.conv_bn_relu2_4_1.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.1.conv_bn_relu2_4_1.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.1.conv_bn_relu2_4_2.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer4.1.conv_bn_relu2_4_2.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.1.conv_bn_relu2_4_2.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.1.conv_bn_relu2_4_3.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer4.1.conv_bn_relu2_4_3.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.1.conv_bn_relu2_4_3.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.1.conv_bn_relu2_4_4.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer4.1.conv_bn_relu2_4_4.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.1.conv_bn_relu2_4_4.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.1.conv_bn3.conv.weight - torch.Size([512, 832, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer4.1.conv_bn3.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.1.conv_bn3.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.2.conv_bn_relu1.conv.weight - torch.Size([832, 512, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer4.2.conv_bn_relu1.bn.weight - torch.Size([832]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.2.conv_bn_relu1.bn.bias - torch.Size([832]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.2.conv_bn_relu2_1_1.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer4.2.conv_bn_relu2_1_1.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.2.conv_bn_relu2_1_1.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.2.conv_bn_relu2_2_1.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer4.2.conv_bn_relu2_2_1.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.2.conv_bn_relu2_2_1.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.2.conv_bn_relu2_2_2.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer4.2.conv_bn_relu2_2_2.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.2.conv_bn_relu2_2_2.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.2.conv_bn_relu2_3_1.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer4.2.conv_bn_relu2_3_1.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.2.conv_bn_relu2_3_1.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.2.conv_bn_relu2_3_2.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer4.2.conv_bn_relu2_3_2.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.2.conv_bn_relu2_3_2.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.2.conv_bn_relu2_3_3.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer4.2.conv_bn_relu2_3_3.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.2.conv_bn_relu2_3_3.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.2.conv_bn_relu2_4_1.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer4.2.conv_bn_relu2_4_1.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.2.conv_bn_relu2_4_1.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.2.conv_bn_relu2_4_2.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer4.2.conv_bn_relu2_4_2.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.2.conv_bn_relu2_4_2.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.2.conv_bn_relu2_4_3.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer4.2.conv_bn_relu2_4_3.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.2.conv_bn_relu2_4_3.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.2.conv_bn_relu2_4_4.conv.weight - torch.Size([208, 208, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer4.2.conv_bn_relu2_4_4.bn.weight - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.2.conv_bn_relu2_4_4.bn.bias - torch.Size([208]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.2.conv_bn3.conv.weight - torch.Size([512, 832, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.downsample.layer4.2.conv_bn3.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.downsample.layer4.2.conv_bn3.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.upsample.up1.in_skip.conv.weight - torch.Size([256, 512, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.upsample.up1.in_skip.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.upsample.up1.in_skip.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.upsample.up2.in_skip.conv.weight - torch.Size([256, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.upsample.up2.in_skip.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.upsample.up2.in_skip.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.upsample.up2.up_conv.conv.weight - torch.Size([256, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.upsample.up2.up_conv.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.upsample.up2.up_conv.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.upsample.up3.in_skip.conv.weight - torch.Size([256, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.upsample.up3.in_skip.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.upsample.up3.in_skip.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.upsample.up3.up_conv.conv.weight - torch.Size([256, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.upsample.up3.up_conv.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.upsample.up3.up_conv.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.upsample.up4.in_skip.conv.weight - torch.Size([256, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.upsample.up4.in_skip.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.upsample.up4.in_skip.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.upsample.up4.up_conv.conv.weight - torch.Size([256, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.multi_stage_rsn.1.upsample.up4.up_conv.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.multi_stage_rsn.1.upsample.up4.up_conv.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.predict_layers.0.conv_layers.0.conv.weight - torch.Size([256, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 head.predict_layers.0.conv_layers.0.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.predict_layers.0.conv_layers.0.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.predict_layers.0.conv_layers.1.conv.weight - torch.Size([17, 256, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 head.predict_layers.0.conv_layers.1.bn.weight - torch.Size([17]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.predict_layers.0.conv_layers.1.bn.bias - torch.Size([17]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.predict_layers.1.conv_layers.0.conv.weight - torch.Size([256, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 head.predict_layers.1.conv_layers.0.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.predict_layers.1.conv_layers.0.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.predict_layers.1.conv_layers.1.conv.weight - torch.Size([17, 256, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 head.predict_layers.1.conv_layers.1.bn.weight - torch.Size([17]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.predict_layers.1.conv_layers.1.bn.bias - torch.Size([17]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.predict_layers.2.conv_layers.0.conv.weight - torch.Size([256, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 head.predict_layers.2.conv_layers.0.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.predict_layers.2.conv_layers.0.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.predict_layers.2.conv_layers.1.conv.weight - torch.Size([17, 256, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 head.predict_layers.2.conv_layers.1.bn.weight - torch.Size([17]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.predict_layers.2.conv_layers.1.bn.bias - torch.Size([17]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.predict_layers.3.conv_layers.0.conv.weight - torch.Size([256, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 head.predict_layers.3.conv_layers.0.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.predict_layers.3.conv_layers.0.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.predict_layers.3.conv_layers.1.conv.weight - torch.Size([17, 256, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 head.predict_layers.3.conv_layers.1.bn.weight - torch.Size([17]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.predict_layers.3.conv_layers.1.bn.bias - torch.Size([17]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.predict_layers.4.conv_layers.0.conv.weight - torch.Size([256, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 head.predict_layers.4.conv_layers.0.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.predict_layers.4.conv_layers.0.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.predict_layers.4.conv_layers.1.conv.weight - torch.Size([17, 256, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 head.predict_layers.4.conv_layers.1.bn.weight - torch.Size([17]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.predict_layers.4.conv_layers.1.bn.bias - torch.Size([17]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.predict_layers.5.conv_layers.0.conv.weight - torch.Size([256, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 head.predict_layers.5.conv_layers.0.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.predict_layers.5.conv_layers.0.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.predict_layers.5.conv_layers.1.conv.weight - torch.Size([17, 256, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 head.predict_layers.5.conv_layers.1.bn.weight - torch.Size([17]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.predict_layers.5.conv_layers.1.bn.bias - torch.Size([17]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.predict_layers.6.conv_layers.0.conv.weight - torch.Size([256, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 head.predict_layers.6.conv_layers.0.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.predict_layers.6.conv_layers.0.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.predict_layers.6.conv_layers.1.conv.weight - torch.Size([17, 256, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 head.predict_layers.6.conv_layers.1.bn.weight - torch.Size([17]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.predict_layers.6.conv_layers.1.bn.bias - torch.Size([17]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.predict_layers.7.conv_layers.0.conv.weight - torch.Size([256, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 head.predict_layers.7.conv_layers.0.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.predict_layers.7.conv_layers.0.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.predict_layers.7.conv_layers.1.conv.weight - torch.Size([17, 256, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 head.predict_layers.7.conv_layers.1.bn.weight - torch.Size([17]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.predict_layers.7.conv_layers.1.bn.bias - torch.Size([17]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator 2022/10/12 11:03:02 - mmengine - INFO - Checkpoints will be saved to /mnt/petrelfs/liqikai/openmmlab/pt112cu113py38/mmpose/work_dirs/20221012/rsn2x by HardDiskBackend. 2022/10/12 11:03:43 - mmengine - INFO - Epoch(train) [1][50/586] lr: 4.954910e-04 eta: 1 day, 3:51:34 time: 0.815335 data_time: 0.204584 memory: 8713 loss_kpt: 394.914722 acc_pose: 0.057591 loss: 394.914722 2022/10/12 11:04:11 - mmengine - INFO - Epoch(train) [1][100/586] lr: 9.959920e-04 eta: 23:31:01 time: 0.561731 data_time: 0.058854 memory: 8713 loss_kpt: 397.046662 acc_pose: 0.087613 loss: 397.046662 2022/10/12 11:04:36 - mmengine - INFO - Epoch(train) [1][150/586] lr: 1.496493e-03 eta: 21:25:44 time: 0.505892 data_time: 0.055704 memory: 8713 loss_kpt: 388.557634 acc_pose: 0.073867 loss: 388.557634 2022/10/12 11:05:02 - mmengine - INFO - Epoch(train) [1][200/586] lr: 1.996994e-03 eta: 20:29:08 time: 0.518094 data_time: 0.056160 memory: 8713 loss_kpt: 392.235378 acc_pose: 0.064187 loss: 392.235378 2022/10/12 11:05:28 - mmengine - INFO - Epoch(train) [1][250/586] lr: 2.497495e-03 eta: 19:56:35 time: 0.521977 data_time: 0.055593 memory: 8713 loss_kpt: 393.065562 acc_pose: 0.086706 loss: 393.065562 2022/10/12 11:05:55 - mmengine - INFO - Epoch(train) [1][300/586] lr: 2.997996e-03 eta: 19:39:30 time: 0.535915 data_time: 0.058549 memory: 8713 loss_kpt: 392.649555 acc_pose: 0.104451 loss: 392.649555 2022/10/12 11:06:22 - mmengine - INFO - Epoch(train) [1][350/586] lr: 3.498497e-03 eta: 19:27:06 time: 0.535719 data_time: 0.059885 memory: 8713 loss_kpt: 390.498819 acc_pose: 0.110005 loss: 390.498819 2022/10/12 11:06:48 - mmengine - INFO - Epoch(train) [1][400/586] lr: 3.998998e-03 eta: 19:12:28 time: 0.515239 data_time: 0.054548 memory: 8713 loss_kpt: 388.761401 acc_pose: 0.107201 loss: 388.761401 2022/10/12 11:07:13 - mmengine - INFO - Epoch(train) [1][450/586] lr: 4.499499e-03 eta: 18:59:50 time: 0.510164 data_time: 0.059033 memory: 8713 loss_kpt: 389.918567 acc_pose: 0.119591 loss: 389.918567 2022/10/12 11:07:39 - mmengine - INFO - Epoch(train) [1][500/586] lr: 5.000000e-03 eta: 18:49:17 time: 0.508470 data_time: 0.055313 memory: 8713 loss_kpt: 383.193659 acc_pose: 0.113878 loss: 383.193659 2022/10/12 11:08:05 - mmengine - INFO - Epoch(train) [1][550/586] lr: 5.000000e-03 eta: 18:45:24 time: 0.534388 data_time: 0.057447 memory: 8713 loss_kpt: 380.646312 acc_pose: 0.163634 loss: 380.646312 2022/10/12 11:08:24 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:08:51 - mmengine - INFO - Epoch(train) [2][50/586] lr: 5.000000e-03 eta: 17:38:04 time: 0.533239 data_time: 0.071916 memory: 8713 loss_kpt: 384.602126 acc_pose: 0.151430 loss: 384.602126 2022/10/12 11:09:17 - mmengine - INFO - Epoch(train) [2][100/586] lr: 5.000000e-03 eta: 17:38:43 time: 0.525809 data_time: 0.060258 memory: 8713 loss_kpt: 378.521389 acc_pose: 0.177443 loss: 378.521389 2022/10/12 11:09:43 - mmengine - INFO - Epoch(train) [2][150/586] lr: 5.000000e-03 eta: 17:36:56 time: 0.509381 data_time: 0.054667 memory: 8713 loss_kpt: 374.888221 acc_pose: 0.184358 loss: 374.888221 2022/10/12 11:10:08 - mmengine - INFO - Epoch(train) [2][200/586] lr: 5.000000e-03 eta: 17:34:58 time: 0.506559 data_time: 0.055216 memory: 8713 loss_kpt: 376.760076 acc_pose: 0.196043 loss: 376.760076 2022/10/12 11:10:34 - mmengine - INFO - Epoch(train) [2][250/586] lr: 5.000000e-03 eta: 17:35:38 time: 0.526628 data_time: 0.052941 memory: 8713 loss_kpt: 375.844318 acc_pose: 0.176612 loss: 375.844318 2022/10/12 11:11:01 - mmengine - INFO - Epoch(train) [2][300/586] lr: 5.000000e-03 eta: 17:36:56 time: 0.533386 data_time: 0.053655 memory: 8713 loss_kpt: 377.329503 acc_pose: 0.281055 loss: 377.329503 2022/10/12 11:11:28 - mmengine - INFO - Epoch(train) [2][350/586] lr: 5.000000e-03 eta: 17:38:36 time: 0.538382 data_time: 0.056160 memory: 8713 loss_kpt: 381.215298 acc_pose: 0.196895 loss: 381.215298 2022/10/12 11:11:55 - mmengine - INFO - Epoch(train) [2][400/586] lr: 5.000000e-03 eta: 17:41:18 time: 0.550476 data_time: 0.065774 memory: 8713 loss_kpt: 377.882502 acc_pose: 0.217932 loss: 377.882502 2022/10/12 11:12:03 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:12:23 - mmengine - INFO - Epoch(train) [2][450/586] lr: 5.000000e-03 eta: 17:43:57 time: 0.553004 data_time: 0.057443 memory: 8713 loss_kpt: 378.522385 acc_pose: 0.414453 loss: 378.522385 2022/10/12 11:12:50 - mmengine - INFO - Epoch(train) [2][500/586] lr: 5.000000e-03 eta: 17:45:44 time: 0.546942 data_time: 0.058342 memory: 8713 loss_kpt: 377.428249 acc_pose: 0.254176 loss: 377.428249 2022/10/12 11:13:18 - mmengine - INFO - Epoch(train) [2][550/586] lr: 5.000000e-03 eta: 17:47:58 time: 0.554008 data_time: 0.058925 memory: 8713 loss_kpt: 374.121860 acc_pose: 0.191557 loss: 374.121860 2022/10/12 11:13:37 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:14:05 - mmengine - INFO - Epoch(train) [3][50/586] lr: 5.000000e-03 eta: 17:17:16 time: 0.543598 data_time: 0.066039 memory: 8713 loss_kpt: 371.895148 acc_pose: 0.249241 loss: 371.895148 2022/10/12 11:14:31 - mmengine - INFO - Epoch(train) [3][100/586] lr: 5.000000e-03 eta: 17:17:32 time: 0.519440 data_time: 0.056986 memory: 8713 loss_kpt: 368.876177 acc_pose: 0.388744 loss: 368.876177 2022/10/12 11:14:57 - mmengine - INFO - Epoch(train) [3][150/586] lr: 5.000000e-03 eta: 17:17:38 time: 0.517919 data_time: 0.060901 memory: 8713 loss_kpt: 372.480023 acc_pose: 0.275492 loss: 372.480023 2022/10/12 11:15:22 - mmengine - INFO - Epoch(train) [3][200/586] lr: 5.000000e-03 eta: 17:17:00 time: 0.508699 data_time: 0.050780 memory: 8713 loss_kpt: 368.423508 acc_pose: 0.324213 loss: 368.423508 2022/10/12 11:15:48 - mmengine - INFO - Epoch(train) [3][250/586] lr: 5.000000e-03 eta: 17:16:59 time: 0.517083 data_time: 0.056988 memory: 8713 loss_kpt: 365.524047 acc_pose: 0.330033 loss: 365.524047 2022/10/12 11:16:13 - mmengine - INFO - Epoch(train) [3][300/586] lr: 5.000000e-03 eta: 17:16:30 time: 0.510612 data_time: 0.051235 memory: 8713 loss_kpt: 364.402311 acc_pose: 0.345837 loss: 364.402311 2022/10/12 11:16:39 - mmengine - INFO - Epoch(train) [3][350/586] lr: 5.000000e-03 eta: 17:15:53 time: 0.508672 data_time: 0.060106 memory: 8713 loss_kpt: 371.526821 acc_pose: 0.362910 loss: 371.526821 2022/10/12 11:17:04 - mmengine - INFO - Epoch(train) [3][400/586] lr: 5.000000e-03 eta: 17:14:49 time: 0.501525 data_time: 0.056595 memory: 8713 loss_kpt: 371.370380 acc_pose: 0.404946 loss: 371.370380 2022/10/12 11:17:29 - mmengine - INFO - Epoch(train) [3][450/586] lr: 5.000000e-03 eta: 17:14:29 time: 0.512389 data_time: 0.058287 memory: 8713 loss_kpt: 364.497942 acc_pose: 0.412548 loss: 364.497942 2022/10/12 11:17:55 - mmengine - INFO - Epoch(train) [3][500/586] lr: 5.000000e-03 eta: 17:13:50 time: 0.507513 data_time: 0.055251 memory: 8713 loss_kpt: 367.655929 acc_pose: 0.358092 loss: 367.655929 2022/10/12 11:18:21 - mmengine - INFO - Epoch(train) [3][550/586] lr: 5.000000e-03 eta: 17:14:03 time: 0.522008 data_time: 0.058415 memory: 8713 loss_kpt: 362.241010 acc_pose: 0.337930 loss: 362.241010 2022/10/12 11:18:39 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:19:06 - mmengine - INFO - Epoch(train) [4][50/586] lr: 5.000000e-03 eta: 16:54:07 time: 0.535756 data_time: 0.066364 memory: 8713 loss_kpt: 362.903193 acc_pose: 0.328228 loss: 362.903193 2022/10/12 11:19:32 - mmengine - INFO - Epoch(train) [4][100/586] lr: 5.000000e-03 eta: 16:54:56 time: 0.524509 data_time: 0.056415 memory: 8713 loss_kpt: 365.156284 acc_pose: 0.379445 loss: 365.156284 2022/10/12 11:19:58 - mmengine - INFO - Epoch(train) [4][150/586] lr: 5.000000e-03 eta: 16:55:19 time: 0.517651 data_time: 0.057390 memory: 8713 loss_kpt: 363.556579 acc_pose: 0.364137 loss: 363.556579 2022/10/12 11:20:24 - mmengine - INFO - Epoch(train) [4][200/586] lr: 5.000000e-03 eta: 16:56:02 time: 0.525004 data_time: 0.057268 memory: 8713 loss_kpt: 365.607822 acc_pose: 0.425161 loss: 365.607822 2022/10/12 11:20:46 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:20:50 - mmengine - INFO - Epoch(train) [4][250/586] lr: 5.000000e-03 eta: 16:56:19 time: 0.517499 data_time: 0.052719 memory: 8713 loss_kpt: 360.315176 acc_pose: 0.308515 loss: 360.315176 2022/10/12 11:21:15 - mmengine - INFO - Epoch(train) [4][300/586] lr: 5.000000e-03 eta: 16:55:46 time: 0.500863 data_time: 0.053809 memory: 8713 loss_kpt: 361.529931 acc_pose: 0.493397 loss: 361.529931 2022/10/12 11:21:41 - mmengine - INFO - Epoch(train) [4][350/586] lr: 5.000000e-03 eta: 16:55:43 time: 0.511610 data_time: 0.055703 memory: 8713 loss_kpt: 359.533835 acc_pose: 0.396275 loss: 359.533835 2022/10/12 11:22:06 - mmengine - INFO - Epoch(train) [4][400/586] lr: 5.000000e-03 eta: 16:55:54 time: 0.516693 data_time: 0.058471 memory: 8713 loss_kpt: 361.026780 acc_pose: 0.313283 loss: 361.026780 2022/10/12 11:22:32 - mmengine - INFO - Epoch(train) [4][450/586] lr: 5.000000e-03 eta: 16:55:51 time: 0.512274 data_time: 0.056597 memory: 8713 loss_kpt: 359.029394 acc_pose: 0.494206 loss: 359.029394 2022/10/12 11:22:58 - mmengine - INFO - Epoch(train) [4][500/586] lr: 5.000000e-03 eta: 16:56:03 time: 0.518270 data_time: 0.055116 memory: 8713 loss_kpt: 357.556086 acc_pose: 0.425601 loss: 357.556086 2022/10/12 11:23:24 - mmengine - INFO - Epoch(train) [4][550/586] lr: 5.000000e-03 eta: 16:56:28 time: 0.523956 data_time: 0.056720 memory: 8713 loss_kpt: 354.271105 acc_pose: 0.309969 loss: 354.271105 2022/10/12 11:23:42 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:24:09 - mmengine - INFO - Epoch(train) [5][50/586] lr: 5.000000e-03 eta: 16:41:53 time: 0.538689 data_time: 0.069133 memory: 8713 loss_kpt: 359.442171 acc_pose: 0.443868 loss: 359.442171 2022/10/12 11:24:35 - mmengine - INFO - Epoch(train) [5][100/586] lr: 5.000000e-03 eta: 16:41:58 time: 0.510256 data_time: 0.052394 memory: 8713 loss_kpt: 360.398321 acc_pose: 0.401488 loss: 360.398321 2022/10/12 11:25:01 - mmengine - INFO - Epoch(train) [5][150/586] lr: 5.000000e-03 eta: 16:42:34 time: 0.523794 data_time: 0.057517 memory: 8713 loss_kpt: 359.642285 acc_pose: 0.423413 loss: 359.642285 2022/10/12 11:25:27 - mmengine - INFO - Epoch(train) [5][200/586] lr: 5.000000e-03 eta: 16:43:11 time: 0.524708 data_time: 0.052648 memory: 8713 loss_kpt: 356.065543 acc_pose: 0.469698 loss: 356.065543 2022/10/12 11:25:53 - mmengine - INFO - Epoch(train) [5][250/586] lr: 5.000000e-03 eta: 16:43:23 time: 0.515530 data_time: 0.053410 memory: 8713 loss_kpt: 353.727965 acc_pose: 0.458248 loss: 353.727965 2022/10/12 11:26:19 - mmengine - INFO - Epoch(train) [5][300/586] lr: 5.000000e-03 eta: 16:44:01 time: 0.527539 data_time: 0.051416 memory: 8713 loss_kpt: 350.170786 acc_pose: 0.499864 loss: 350.170786 2022/10/12 11:26:45 - mmengine - INFO - Epoch(train) [5][350/586] lr: 5.000000e-03 eta: 16:44:17 time: 0.518515 data_time: 0.057007 memory: 8713 loss_kpt: 358.389106 acc_pose: 0.419478 loss: 358.389106 2022/10/12 11:27:10 - mmengine - INFO - Epoch(train) [5][400/586] lr: 5.000000e-03 eta: 16:44:06 time: 0.507252 data_time: 0.053789 memory: 8713 loss_kpt: 350.612809 acc_pose: 0.493388 loss: 350.612809 2022/10/12 11:27:37 - mmengine - INFO - Epoch(train) [5][450/586] lr: 5.000000e-03 eta: 16:44:48 time: 0.531683 data_time: 0.056476 memory: 8713 loss_kpt: 352.136047 acc_pose: 0.405938 loss: 352.136047 2022/10/12 11:28:03 - mmengine - INFO - Epoch(train) [5][500/586] lr: 5.000000e-03 eta: 16:45:13 time: 0.524909 data_time: 0.054777 memory: 8713 loss_kpt: 351.305425 acc_pose: 0.486680 loss: 351.305425 2022/10/12 11:28:30 - mmengine - INFO - Epoch(train) [5][550/586] lr: 5.000000e-03 eta: 16:45:59 time: 0.535882 data_time: 0.055842 memory: 8713 loss_kpt: 351.744241 acc_pose: 0.412702 loss: 351.744241 2022/10/12 11:28:49 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:29:15 - mmengine - INFO - Epoch(train) [6][50/586] lr: 5.000000e-03 eta: 16:34:10 time: 0.533653 data_time: 0.069483 memory: 8713 loss_kpt: 357.736685 acc_pose: 0.529305 loss: 357.736685 2022/10/12 11:29:26 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:29:41 - mmengine - INFO - Epoch(train) [6][100/586] lr: 5.000000e-03 eta: 16:34:20 time: 0.514446 data_time: 0.052791 memory: 8713 loss_kpt: 350.599617 acc_pose: 0.416865 loss: 350.599617 2022/10/12 11:30:07 - mmengine - INFO - Epoch(train) [6][150/586] lr: 5.000000e-03 eta: 16:34:35 time: 0.517423 data_time: 0.053397 memory: 8713 loss_kpt: 356.012416 acc_pose: 0.411770 loss: 356.012416 2022/10/12 11:30:32 - mmengine - INFO - Epoch(train) [6][200/586] lr: 5.000000e-03 eta: 16:34:22 time: 0.503691 data_time: 0.052048 memory: 8713 loss_kpt: 345.854523 acc_pose: 0.502254 loss: 345.854523 2022/10/12 11:30:58 - mmengine - INFO - Epoch(train) [6][250/586] lr: 5.000000e-03 eta: 16:34:23 time: 0.510848 data_time: 0.055374 memory: 8713 loss_kpt: 351.510845 acc_pose: 0.426075 loss: 351.510845 2022/10/12 11:31:23 - mmengine - INFO - Epoch(train) [6][300/586] lr: 5.000000e-03 eta: 16:34:13 time: 0.505697 data_time: 0.053181 memory: 8713 loss_kpt: 349.428159 acc_pose: 0.346459 loss: 349.428159 2022/10/12 11:31:49 - mmengine - INFO - Epoch(train) [6][350/586] lr: 5.000000e-03 eta: 16:34:13 time: 0.511589 data_time: 0.059343 memory: 8713 loss_kpt: 348.650338 acc_pose: 0.509018 loss: 348.650338 2022/10/12 11:32:14 - mmengine - INFO - Epoch(train) [6][400/586] lr: 5.000000e-03 eta: 16:34:02 time: 0.506046 data_time: 0.051242 memory: 8713 loss_kpt: 345.936521 acc_pose: 0.562000 loss: 345.936521 2022/10/12 11:32:39 - mmengine - INFO - Epoch(train) [6][450/586] lr: 5.000000e-03 eta: 16:33:45 time: 0.502535 data_time: 0.055345 memory: 8713 loss_kpt: 347.711176 acc_pose: 0.512699 loss: 347.711176 2022/10/12 11:33:05 - mmengine - INFO - Epoch(train) [6][500/586] lr: 5.000000e-03 eta: 16:33:44 time: 0.511746 data_time: 0.054755 memory: 8713 loss_kpt: 346.511694 acc_pose: 0.415526 loss: 346.511694 2022/10/12 11:33:30 - mmengine - INFO - Epoch(train) [6][550/586] lr: 5.000000e-03 eta: 16:33:40 time: 0.510477 data_time: 0.061679 memory: 8713 loss_kpt: 345.449828 acc_pose: 0.422360 loss: 345.449828 2022/10/12 11:33:48 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:34:14 - mmengine - INFO - Epoch(train) [7][50/586] lr: 5.000000e-03 eta: 16:23:42 time: 0.526403 data_time: 0.072894 memory: 8713 loss_kpt: 343.581735 acc_pose: 0.421619 loss: 343.581735 2022/10/12 11:34:39 - mmengine - INFO - Epoch(train) [7][100/586] lr: 5.000000e-03 eta: 16:23:46 time: 0.511094 data_time: 0.054794 memory: 8713 loss_kpt: 347.049047 acc_pose: 0.512416 loss: 347.049047 2022/10/12 11:35:05 - mmengine - INFO - Epoch(train) [7][150/586] lr: 5.000000e-03 eta: 16:23:37 time: 0.503765 data_time: 0.057161 memory: 8713 loss_kpt: 344.760503 acc_pose: 0.527171 loss: 344.760503 2022/10/12 11:35:30 - mmengine - INFO - Epoch(train) [7][200/586] lr: 5.000000e-03 eta: 16:23:18 time: 0.498125 data_time: 0.054513 memory: 8713 loss_kpt: 338.154279 acc_pose: 0.539215 loss: 338.154279 2022/10/12 11:35:55 - mmengine - INFO - Epoch(train) [7][250/586] lr: 5.000000e-03 eta: 16:23:16 time: 0.508751 data_time: 0.059920 memory: 8713 loss_kpt: 336.552184 acc_pose: 0.572347 loss: 336.552184 2022/10/12 11:36:21 - mmengine - INFO - Epoch(train) [7][300/586] lr: 5.000000e-03 eta: 16:23:40 time: 0.525946 data_time: 0.053810 memory: 8713 loss_kpt: 344.209616 acc_pose: 0.505573 loss: 344.209616 2022/10/12 11:36:48 - mmengine - INFO - Epoch(train) [7][350/586] lr: 5.000000e-03 eta: 16:24:02 time: 0.525095 data_time: 0.054661 memory: 8713 loss_kpt: 344.141533 acc_pose: 0.573439 loss: 344.141533 2022/10/12 11:37:13 - mmengine - INFO - Epoch(train) [7][400/586] lr: 5.000000e-03 eta: 16:24:07 time: 0.514820 data_time: 0.052894 memory: 8713 loss_kpt: 346.233090 acc_pose: 0.437741 loss: 346.233090 2022/10/12 11:37:39 - mmengine - INFO - Epoch(train) [7][450/586] lr: 5.000000e-03 eta: 16:24:13 time: 0.516462 data_time: 0.060683 memory: 8713 loss_kpt: 329.980888 acc_pose: 0.584684 loss: 329.980888 2022/10/12 11:37:57 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:38:05 - mmengine - INFO - Epoch(train) [7][500/586] lr: 5.000000e-03 eta: 16:24:17 time: 0.514854 data_time: 0.054921 memory: 8713 loss_kpt: 333.560918 acc_pose: 0.555646 loss: 333.560918 2022/10/12 11:38:30 - mmengine - INFO - Epoch(train) [7][550/586] lr: 5.000000e-03 eta: 16:24:08 time: 0.507109 data_time: 0.058955 memory: 8713 loss_kpt: 336.760705 acc_pose: 0.433534 loss: 336.760705 2022/10/12 11:38:48 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:39:15 - mmengine - INFO - Epoch(train) [8][50/586] lr: 5.000000e-03 eta: 16:15:50 time: 0.535632 data_time: 0.064961 memory: 8713 loss_kpt: 332.408181 acc_pose: 0.571534 loss: 332.408181 2022/10/12 11:39:42 - mmengine - INFO - Epoch(train) [8][100/586] lr: 5.000000e-03 eta: 16:16:38 time: 0.543370 data_time: 0.051677 memory: 8713 loss_kpt: 335.402543 acc_pose: 0.533738 loss: 335.402543 2022/10/12 11:40:09 - mmengine - INFO - Epoch(train) [8][150/586] lr: 5.000000e-03 eta: 16:17:24 time: 0.544019 data_time: 0.063212 memory: 8713 loss_kpt: 331.902509 acc_pose: 0.537551 loss: 331.902509 2022/10/12 11:40:35 - mmengine - INFO - Epoch(train) [8][200/586] lr: 5.000000e-03 eta: 16:17:40 time: 0.522918 data_time: 0.056055 memory: 8713 loss_kpt: 332.288732 acc_pose: 0.543998 loss: 332.288732 2022/10/12 11:41:01 - mmengine - INFO - Epoch(train) [8][250/586] lr: 5.000000e-03 eta: 16:17:40 time: 0.511708 data_time: 0.061808 memory: 8713 loss_kpt: 336.906968 acc_pose: 0.674634 loss: 336.906968 2022/10/12 11:41:27 - mmengine - INFO - Epoch(train) [8][300/586] lr: 5.000000e-03 eta: 16:17:43 time: 0.515125 data_time: 0.055327 memory: 8713 loss_kpt: 331.540224 acc_pose: 0.589407 loss: 331.540224 2022/10/12 11:41:53 - mmengine - INFO - Epoch(train) [8][350/586] lr: 5.000000e-03 eta: 16:18:06 time: 0.529912 data_time: 0.064582 memory: 8713 loss_kpt: 332.511386 acc_pose: 0.616967 loss: 332.511386 2022/10/12 11:42:20 - mmengine - INFO - Epoch(train) [8][400/586] lr: 5.000000e-03 eta: 16:18:24 time: 0.527608 data_time: 0.054953 memory: 8713 loss_kpt: 326.848383 acc_pose: 0.527429 loss: 326.848383 2022/10/12 11:42:45 - mmengine - INFO - Epoch(train) [8][450/586] lr: 5.000000e-03 eta: 16:18:26 time: 0.515398 data_time: 0.059166 memory: 8713 loss_kpt: 328.125444 acc_pose: 0.489621 loss: 328.125444 2022/10/12 11:43:11 - mmengine - INFO - Epoch(train) [8][500/586] lr: 5.000000e-03 eta: 16:18:20 time: 0.509815 data_time: 0.056127 memory: 8713 loss_kpt: 329.781371 acc_pose: 0.511789 loss: 329.781371 2022/10/12 11:43:37 - mmengine - INFO - Epoch(train) [8][550/586] lr: 5.000000e-03 eta: 16:18:23 time: 0.517523 data_time: 0.064954 memory: 8713 loss_kpt: 320.168406 acc_pose: 0.534931 loss: 320.168406 2022/10/12 11:43:55 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:44:21 - mmengine - INFO - Epoch(train) [9][50/586] lr: 5.000000e-03 eta: 16:10:58 time: 0.530552 data_time: 0.068261 memory: 8713 loss_kpt: 326.573227 acc_pose: 0.610759 loss: 326.573227 2022/10/12 11:44:47 - mmengine - INFO - Epoch(train) [9][100/586] lr: 5.000000e-03 eta: 16:11:04 time: 0.517401 data_time: 0.052491 memory: 8713 loss_kpt: 329.763264 acc_pose: 0.565285 loss: 329.763264 2022/10/12 11:45:14 - mmengine - INFO - Epoch(train) [9][150/586] lr: 5.000000e-03 eta: 16:11:24 time: 0.528883 data_time: 0.058741 memory: 8713 loss_kpt: 329.167560 acc_pose: 0.583906 loss: 329.167560 2022/10/12 11:45:40 - mmengine - INFO - Epoch(train) [9][200/586] lr: 5.000000e-03 eta: 16:11:35 time: 0.522923 data_time: 0.058259 memory: 8713 loss_kpt: 322.257662 acc_pose: 0.488693 loss: 322.257662 2022/10/12 11:46:06 - mmengine - INFO - Epoch(train) [9][250/586] lr: 5.000000e-03 eta: 16:11:38 time: 0.516273 data_time: 0.057499 memory: 8713 loss_kpt: 320.987388 acc_pose: 0.531147 loss: 320.987388 2022/10/12 11:46:32 - mmengine - INFO - Epoch(train) [9][300/586] lr: 5.000000e-03 eta: 16:11:45 time: 0.520501 data_time: 0.060974 memory: 8713 loss_kpt: 323.254633 acc_pose: 0.557160 loss: 323.254633 2022/10/12 11:46:38 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:46:58 - mmengine - INFO - Epoch(train) [9][350/586] lr: 5.000000e-03 eta: 16:11:58 time: 0.525860 data_time: 0.060498 memory: 8713 loss_kpt: 325.586052 acc_pose: 0.557959 loss: 325.586052 2022/10/12 11:47:24 - mmengine - INFO - Epoch(train) [9][400/586] lr: 5.000000e-03 eta: 16:12:10 time: 0.525712 data_time: 0.055782 memory: 8713 loss_kpt: 319.799910 acc_pose: 0.587249 loss: 319.799910 2022/10/12 11:47:50 - mmengine - INFO - Epoch(train) [9][450/586] lr: 5.000000e-03 eta: 16:12:16 time: 0.520870 data_time: 0.056042 memory: 8713 loss_kpt: 325.359973 acc_pose: 0.623745 loss: 325.359973 2022/10/12 11:48:16 - mmengine - INFO - Epoch(train) [9][500/586] lr: 5.000000e-03 eta: 16:12:18 time: 0.518554 data_time: 0.056104 memory: 8713 loss_kpt: 317.627131 acc_pose: 0.611527 loss: 317.627131 2022/10/12 11:48:42 - mmengine - INFO - Epoch(train) [9][550/586] lr: 5.000000e-03 eta: 16:12:28 time: 0.525282 data_time: 0.059508 memory: 8713 loss_kpt: 323.395181 acc_pose: 0.641991 loss: 323.395181 2022/10/12 11:49:02 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:49:29 - mmengine - INFO - Epoch(train) [10][50/586] lr: 5.000000e-03 eta: 16:06:10 time: 0.548625 data_time: 0.075280 memory: 8713 loss_kpt: 322.520874 acc_pose: 0.581004 loss: 322.520874 2022/10/12 11:49:55 - mmengine - INFO - Epoch(train) [10][100/586] lr: 5.000000e-03 eta: 16:06:17 time: 0.521229 data_time: 0.065194 memory: 8713 loss_kpt: 310.622238 acc_pose: 0.522011 loss: 310.622238 2022/10/12 11:50:21 - mmengine - INFO - Epoch(train) [10][150/586] lr: 5.000000e-03 eta: 16:06:15 time: 0.514157 data_time: 0.060156 memory: 8713 loss_kpt: 317.077535 acc_pose: 0.565159 loss: 317.077535 2022/10/12 11:50:46 - mmengine - INFO - Epoch(train) [10][200/586] lr: 5.000000e-03 eta: 16:06:10 time: 0.510934 data_time: 0.059422 memory: 8713 loss_kpt: 322.374370 acc_pose: 0.611376 loss: 322.374370 2022/10/12 11:51:12 - mmengine - INFO - Epoch(train) [10][250/586] lr: 5.000000e-03 eta: 16:06:08 time: 0.514105 data_time: 0.060935 memory: 8713 loss_kpt: 318.930220 acc_pose: 0.695886 loss: 318.930220 2022/10/12 11:51:38 - mmengine - INFO - Epoch(train) [10][300/586] lr: 5.000000e-03 eta: 16:06:15 time: 0.523422 data_time: 0.058983 memory: 8713 loss_kpt: 320.333485 acc_pose: 0.609586 loss: 320.333485 2022/10/12 11:52:04 - mmengine - INFO - Epoch(train) [10][350/586] lr: 5.000000e-03 eta: 16:06:18 time: 0.520186 data_time: 0.057011 memory: 8713 loss_kpt: 316.166176 acc_pose: 0.628954 loss: 316.166176 2022/10/12 11:52:31 - mmengine - INFO - Epoch(train) [10][400/586] lr: 5.000000e-03 eta: 16:06:30 time: 0.528321 data_time: 0.059868 memory: 8713 loss_kpt: 319.717352 acc_pose: 0.691316 loss: 319.717352 2022/10/12 11:52:57 - mmengine - INFO - Epoch(train) [10][450/586] lr: 5.000000e-03 eta: 16:06:35 time: 0.523021 data_time: 0.053253 memory: 8713 loss_kpt: 318.051923 acc_pose: 0.593192 loss: 318.051923 2022/10/12 11:53:22 - mmengine - INFO - Epoch(train) [10][500/586] lr: 5.000000e-03 eta: 16:06:23 time: 0.506892 data_time: 0.056631 memory: 8713 loss_kpt: 317.359905 acc_pose: 0.597872 loss: 317.359905 2022/10/12 11:53:48 - mmengine - INFO - Epoch(train) [10][550/586] lr: 5.000000e-03 eta: 16:06:19 time: 0.515096 data_time: 0.058980 memory: 8713 loss_kpt: 312.356348 acc_pose: 0.537960 loss: 312.356348 2022/10/12 11:54:06 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:54:06 - mmengine - INFO - Saving checkpoint at 10 epochs 2022/10/12 11:54:23 - mmengine - INFO - Epoch(val) [10][50/407] eta: 0:01:36 time: 0.269536 data_time: 0.086778 memory: 8713 2022/10/12 11:54:32 - mmengine - INFO - Epoch(val) [10][100/407] eta: 0:00:59 time: 0.193799 data_time: 0.007752 memory: 1759 2022/10/12 11:54:42 - mmengine - INFO - Epoch(val) [10][150/407] eta: 0:00:48 time: 0.189256 data_time: 0.007544 memory: 1759 2022/10/12 11:54:51 - mmengine - INFO - Epoch(val) [10][200/407] eta: 0:00:39 time: 0.190900 data_time: 0.007609 memory: 1759 2022/10/12 11:55:01 - mmengine - INFO - Epoch(val) [10][250/407] eta: 0:00:29 time: 0.189841 data_time: 0.007688 memory: 1759 2022/10/12 11:55:10 - mmengine - INFO - Epoch(val) [10][300/407] eta: 0:00:20 time: 0.190250 data_time: 0.007552 memory: 1759 2022/10/12 11:55:20 - mmengine - INFO - Epoch(val) [10][350/407] eta: 0:00:10 time: 0.188359 data_time: 0.008045 memory: 1759 2022/10/12 11:55:29 - mmengine - INFO - Epoch(val) [10][400/407] eta: 0:00:01 time: 0.188703 data_time: 0.007405 memory: 1759 2022/10/12 11:55:46 - mmengine - INFO - Evaluating CocoMetric... 2022/10/12 11:56:02 - mmengine - INFO - Epoch(val) [10][407/407] coco/AP: 0.445027 coco/AP .5: 0.752969 coco/AP .75: 0.452732 coco/AP (M): 0.431811 coco/AP (L): 0.481366 coco/AR: 0.535815 coco/AR .5: 0.820529 coco/AR .75: 0.565176 coco/AR (M): 0.500519 coco/AR (L): 0.584541 2022/10/12 11:56:04 - mmengine - INFO - The best checkpoint with 0.4450 coco/AP at 10 epoch is saved to best_coco/AP_epoch_10.pth. 2022/10/12 11:56:31 - mmengine - INFO - Epoch(train) [11][50/586] lr: 5.000000e-03 eta: 16:00:24 time: 0.535714 data_time: 0.068791 memory: 8713 loss_kpt: 315.196926 acc_pose: 0.648777 loss: 315.196926 2022/10/12 11:56:56 - mmengine - INFO - Epoch(train) [11][100/586] lr: 5.000000e-03 eta: 16:00:13 time: 0.505799 data_time: 0.059320 memory: 8713 loss_kpt: 312.387231 acc_pose: 0.600008 loss: 312.387231 2022/10/12 11:57:17 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:57:21 - mmengine - INFO - Epoch(train) [11][150/586] lr: 5.000000e-03 eta: 16:00:00 time: 0.504135 data_time: 0.058905 memory: 8713 loss_kpt: 312.498474 acc_pose: 0.693413 loss: 312.498474 2022/10/12 11:57:46 - mmengine - INFO - Epoch(train) [11][200/586] lr: 5.000000e-03 eta: 15:59:42 time: 0.498528 data_time: 0.061248 memory: 8713 loss_kpt: 310.970718 acc_pose: 0.556535 loss: 310.970718 2022/10/12 11:58:11 - mmengine - INFO - Epoch(train) [11][250/586] lr: 5.000000e-03 eta: 15:59:29 time: 0.503715 data_time: 0.059599 memory: 8713 loss_kpt: 314.052575 acc_pose: 0.553634 loss: 314.052575 2022/10/12 11:58:37 - mmengine - INFO - Epoch(train) [11][300/586] lr: 5.000000e-03 eta: 15:59:17 time: 0.506224 data_time: 0.058480 memory: 8713 loss_kpt: 304.027791 acc_pose: 0.576859 loss: 304.027791 2022/10/12 11:59:02 - mmengine - INFO - Epoch(train) [11][350/586] lr: 5.000000e-03 eta: 15:58:58 time: 0.498390 data_time: 0.053970 memory: 8713 loss_kpt: 307.500045 acc_pose: 0.516574 loss: 307.500045 2022/10/12 11:59:27 - mmengine - INFO - Epoch(train) [11][400/586] lr: 5.000000e-03 eta: 15:58:40 time: 0.499620 data_time: 0.058604 memory: 8713 loss_kpt: 309.262607 acc_pose: 0.584023 loss: 309.262607 2022/10/12 11:59:52 - mmengine - INFO - Epoch(train) [11][450/586] lr: 5.000000e-03 eta: 15:58:22 time: 0.499851 data_time: 0.059370 memory: 8713 loss_kpt: 304.504609 acc_pose: 0.590578 loss: 304.504609 2022/10/12 12:00:16 - mmengine - INFO - Epoch(train) [11][500/586] lr: 5.000000e-03 eta: 15:58:01 time: 0.496462 data_time: 0.058590 memory: 8713 loss_kpt: 304.061505 acc_pose: 0.672610 loss: 304.061505 2022/10/12 12:00:41 - mmengine - INFO - Epoch(train) [11][550/586] lr: 5.000000e-03 eta: 15:57:43 time: 0.499136 data_time: 0.058277 memory: 8713 loss_kpt: 305.212906 acc_pose: 0.678925 loss: 305.212906 2022/10/12 12:00:59 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:01:26 - mmengine - INFO - Epoch(train) [12][50/586] lr: 5.000000e-03 eta: 15:52:16 time: 0.530276 data_time: 0.068854 memory: 8713 loss_kpt: 309.073724 acc_pose: 0.581309 loss: 309.073724 2022/10/12 12:01:51 - mmengine - INFO - Epoch(train) [12][100/586] lr: 5.000000e-03 eta: 15:52:05 time: 0.504808 data_time: 0.055361 memory: 8713 loss_kpt: 310.127277 acc_pose: 0.590294 loss: 310.127277 2022/10/12 12:02:17 - mmengine - INFO - Epoch(train) [12][150/586] lr: 5.000000e-03 eta: 15:52:13 time: 0.527999 data_time: 0.070418 memory: 8713 loss_kpt: 305.055454 acc_pose: 0.573043 loss: 305.055454 2022/10/12 12:02:44 - mmengine - INFO - Epoch(train) [12][200/586] lr: 5.000000e-03 eta: 15:52:19 time: 0.525493 data_time: 0.053888 memory: 8713 loss_kpt: 300.768817 acc_pose: 0.733119 loss: 300.768817 2022/10/12 12:03:10 - mmengine - INFO - Epoch(train) [12][250/586] lr: 5.000000e-03 eta: 15:52:33 time: 0.534417 data_time: 0.062054 memory: 8713 loss_kpt: 306.274844 acc_pose: 0.671979 loss: 306.274844 2022/10/12 12:03:36 - mmengine - INFO - Epoch(train) [12][300/586] lr: 5.000000e-03 eta: 15:52:33 time: 0.520324 data_time: 0.058892 memory: 8713 loss_kpt: 303.966607 acc_pose: 0.634753 loss: 303.966607 2022/10/12 12:04:03 - mmengine - INFO - Epoch(train) [12][350/586] lr: 5.000000e-03 eta: 15:52:38 time: 0.525911 data_time: 0.061689 memory: 8713 loss_kpt: 305.304598 acc_pose: 0.615290 loss: 305.304598 2022/10/12 12:04:29 - mmengine - INFO - Epoch(train) [12][400/586] lr: 5.000000e-03 eta: 15:52:47 time: 0.530832 data_time: 0.055323 memory: 8713 loss_kpt: 299.509902 acc_pose: 0.621390 loss: 299.509902 2022/10/12 12:04:56 - mmengine - INFO - Epoch(train) [12][450/586] lr: 5.000000e-03 eta: 15:53:05 time: 0.542434 data_time: 0.062241 memory: 8713 loss_kpt: 305.910961 acc_pose: 0.655524 loss: 305.910961 2022/10/12 12:05:23 - mmengine - INFO - Epoch(train) [12][500/586] lr: 5.000000e-03 eta: 15:53:08 time: 0.524894 data_time: 0.055679 memory: 8713 loss_kpt: 305.211996 acc_pose: 0.592047 loss: 305.211996 2022/10/12 12:05:49 - mmengine - INFO - Epoch(train) [12][550/586] lr: 5.000000e-03 eta: 15:53:10 time: 0.524800 data_time: 0.063638 memory: 8713 loss_kpt: 303.822843 acc_pose: 0.572578 loss: 303.822843 2022/10/12 12:05:51 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:06:07 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:06:34 - mmengine - INFO - Epoch(train) [13][50/586] lr: 5.000000e-03 eta: 15:48:19 time: 0.543945 data_time: 0.074640 memory: 8713 loss_kpt: 298.782484 acc_pose: 0.598805 loss: 298.782484 2022/10/12 12:07:01 - mmengine - INFO - Epoch(train) [13][100/586] lr: 5.000000e-03 eta: 15:48:23 time: 0.525617 data_time: 0.057064 memory: 8713 loss_kpt: 296.144904 acc_pose: 0.634212 loss: 296.144904 2022/10/12 12:07:26 - mmengine - INFO - Epoch(train) [13][150/586] lr: 5.000000e-03 eta: 15:48:17 time: 0.514782 data_time: 0.057317 memory: 8713 loss_kpt: 300.796628 acc_pose: 0.627633 loss: 300.796628 2022/10/12 12:07:51 - mmengine - INFO - Epoch(train) [13][200/586] lr: 5.000000e-03 eta: 15:47:58 time: 0.497794 data_time: 0.056891 memory: 8713 loss_kpt: 300.643096 acc_pose: 0.640247 loss: 300.643096 2022/10/12 12:08:17 - mmengine - INFO - Epoch(train) [13][250/586] lr: 5.000000e-03 eta: 15:47:47 time: 0.507307 data_time: 0.061702 memory: 8713 loss_kpt: 298.984421 acc_pose: 0.603197 loss: 298.984421 2022/10/12 12:08:43 - mmengine - INFO - Epoch(train) [13][300/586] lr: 5.000000e-03 eta: 15:47:47 time: 0.523224 data_time: 0.056715 memory: 8713 loss_kpt: 295.694671 acc_pose: 0.722407 loss: 295.694671 2022/10/12 12:09:09 - mmengine - INFO - Epoch(train) [13][350/586] lr: 5.000000e-03 eta: 15:47:54 time: 0.531103 data_time: 0.060551 memory: 8713 loss_kpt: 295.376215 acc_pose: 0.603909 loss: 295.376215 2022/10/12 12:09:35 - mmengine - INFO - Epoch(train) [13][400/586] lr: 5.000000e-03 eta: 15:47:43 time: 0.509698 data_time: 0.054672 memory: 8713 loss_kpt: 292.782789 acc_pose: 0.654972 loss: 292.782789 2022/10/12 12:10:01 - mmengine - INFO - Epoch(train) [13][450/586] lr: 5.000000e-03 eta: 15:47:39 time: 0.518533 data_time: 0.059892 memory: 8713 loss_kpt: 298.484600 acc_pose: 0.716669 loss: 298.484600 2022/10/12 12:10:27 - mmengine - INFO - Epoch(train) [13][500/586] lr: 5.000000e-03 eta: 15:47:39 time: 0.523606 data_time: 0.060184 memory: 8713 loss_kpt: 296.860676 acc_pose: 0.621044 loss: 296.860676 2022/10/12 12:10:53 - mmengine - INFO - Epoch(train) [13][550/586] lr: 5.000000e-03 eta: 15:47:31 time: 0.513338 data_time: 0.056087 memory: 8713 loss_kpt: 297.848624 acc_pose: 0.577478 loss: 297.848624 2022/10/12 12:11:11 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:11:38 - mmengine - INFO - Epoch(train) [14][50/586] lr: 5.000000e-03 eta: 15:42:59 time: 0.541628 data_time: 0.068649 memory: 8713 loss_kpt: 295.559574 acc_pose: 0.550890 loss: 295.559574 2022/10/12 12:12:04 - mmengine - INFO - Epoch(train) [14][100/586] lr: 5.000000e-03 eta: 15:42:50 time: 0.510783 data_time: 0.056373 memory: 8713 loss_kpt: 289.523408 acc_pose: 0.641675 loss: 289.523408 2022/10/12 12:12:29 - mmengine - INFO - Epoch(train) [14][150/586] lr: 5.000000e-03 eta: 15:42:45 time: 0.517249 data_time: 0.062967 memory: 8713 loss_kpt: 295.065068 acc_pose: 0.709295 loss: 295.065068 2022/10/12 12:12:56 - mmengine - INFO - Epoch(train) [14][200/586] lr: 5.000000e-03 eta: 15:42:52 time: 0.532965 data_time: 0.057541 memory: 8713 loss_kpt: 294.298822 acc_pose: 0.739993 loss: 294.298822 2022/10/12 12:13:23 - mmengine - INFO - Epoch(train) [14][250/586] lr: 5.000000e-03 eta: 15:42:58 time: 0.533238 data_time: 0.059913 memory: 8713 loss_kpt: 293.082093 acc_pose: 0.610248 loss: 293.082093 2022/10/12 12:13:50 - mmengine - INFO - Epoch(train) [14][300/586] lr: 5.000000e-03 eta: 15:43:06 time: 0.535483 data_time: 0.060784 memory: 8713 loss_kpt: 290.159520 acc_pose: 0.682657 loss: 290.159520 2022/10/12 12:14:15 - mmengine - INFO - Epoch(train) [14][350/586] lr: 5.000000e-03 eta: 15:42:58 time: 0.515037 data_time: 0.062318 memory: 8713 loss_kpt: 290.728927 acc_pose: 0.613135 loss: 290.728927 2022/10/12 12:14:32 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:14:42 - mmengine - INFO - Epoch(train) [14][400/586] lr: 5.000000e-03 eta: 15:42:59 time: 0.527358 data_time: 0.061702 memory: 8713 loss_kpt: 292.542330 acc_pose: 0.580871 loss: 292.542330 2022/10/12 12:15:07 - mmengine - INFO - Epoch(train) [14][450/586] lr: 5.000000e-03 eta: 15:42:49 time: 0.512216 data_time: 0.063631 memory: 8713 loss_kpt: 285.909414 acc_pose: 0.616009 loss: 285.909414 2022/10/12 12:15:33 - mmengine - INFO - Epoch(train) [14][500/586] lr: 5.000000e-03 eta: 15:42:38 time: 0.510615 data_time: 0.057059 memory: 8713 loss_kpt: 287.142967 acc_pose: 0.710816 loss: 287.142967 2022/10/12 12:15:58 - mmengine - INFO - Epoch(train) [14][550/586] lr: 5.000000e-03 eta: 15:42:19 time: 0.500490 data_time: 0.059087 memory: 8713 loss_kpt: 290.233690 acc_pose: 0.632798 loss: 290.233690 2022/10/12 12:16:16 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:16:42 - mmengine - INFO - Epoch(train) [15][50/586] lr: 5.000000e-03 eta: 15:37:53 time: 0.524273 data_time: 0.072522 memory: 8713 loss_kpt: 288.222009 acc_pose: 0.607504 loss: 288.222009 2022/10/12 12:17:08 - mmengine - INFO - Epoch(train) [15][100/586] lr: 5.000000e-03 eta: 15:37:47 time: 0.517673 data_time: 0.066452 memory: 8713 loss_kpt: 292.770588 acc_pose: 0.669828 loss: 292.770588 2022/10/12 12:17:34 - mmengine - INFO - Epoch(train) [15][150/586] lr: 5.000000e-03 eta: 15:37:40 time: 0.515847 data_time: 0.058214 memory: 8713 loss_kpt: 290.202916 acc_pose: 0.631263 loss: 290.202916 2022/10/12 12:18:00 - mmengine - INFO - Epoch(train) [15][200/586] lr: 5.000000e-03 eta: 15:37:41 time: 0.527605 data_time: 0.062175 memory: 8713 loss_kpt: 285.479082 acc_pose: 0.652253 loss: 285.479082 2022/10/12 12:18:26 - mmengine - INFO - Epoch(train) [15][250/586] lr: 5.000000e-03 eta: 15:37:38 time: 0.521780 data_time: 0.058371 memory: 8713 loss_kpt: 281.148468 acc_pose: 0.710680 loss: 281.148468 2022/10/12 12:18:52 - mmengine - INFO - Epoch(train) [15][300/586] lr: 5.000000e-03 eta: 15:37:31 time: 0.518095 data_time: 0.059637 memory: 8713 loss_kpt: 288.345588 acc_pose: 0.698304 loss: 288.345588 2022/10/12 12:19:19 - mmengine - INFO - Epoch(train) [15][350/586] lr: 5.000000e-03 eta: 15:37:35 time: 0.533484 data_time: 0.062631 memory: 8713 loss_kpt: 287.418479 acc_pose: 0.590957 loss: 287.418479 2022/10/12 12:19:46 - mmengine - INFO - Epoch(train) [15][400/586] lr: 5.000000e-03 eta: 15:37:45 time: 0.542864 data_time: 0.063741 memory: 8713 loss_kpt: 289.703070 acc_pose: 0.611458 loss: 289.703070 2022/10/12 12:20:14 - mmengine - INFO - Epoch(train) [15][450/586] lr: 5.000000e-03 eta: 15:38:04 time: 0.556957 data_time: 0.062429 memory: 8713 loss_kpt: 287.142755 acc_pose: 0.679785 loss: 287.142755 2022/10/12 12:20:41 - mmengine - INFO - Epoch(train) [15][500/586] lr: 5.000000e-03 eta: 15:38:08 time: 0.536053 data_time: 0.062001 memory: 8713 loss_kpt: 290.116334 acc_pose: 0.720781 loss: 290.116334 2022/10/12 12:21:08 - mmengine - INFO - Epoch(train) [15][550/586] lr: 5.000000e-03 eta: 15:38:12 time: 0.536380 data_time: 0.061147 memory: 8713 loss_kpt: 279.950302 acc_pose: 0.628741 loss: 279.950302 2022/10/12 12:21:27 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:21:54 - mmengine - INFO - Epoch(train) [16][50/586] lr: 5.000000e-03 eta: 15:34:08 time: 0.534975 data_time: 0.067727 memory: 8713 loss_kpt: 287.663270 acc_pose: 0.702823 loss: 287.663270 2022/10/12 12:22:19 - mmengine - INFO - Epoch(train) [16][100/586] lr: 5.000000e-03 eta: 15:33:59 time: 0.514745 data_time: 0.056925 memory: 8713 loss_kpt: 282.173802 acc_pose: 0.664733 loss: 282.173802 2022/10/12 12:22:45 - mmengine - INFO - Epoch(train) [16][150/586] lr: 5.000000e-03 eta: 15:33:53 time: 0.519736 data_time: 0.056549 memory: 8713 loss_kpt: 287.562680 acc_pose: 0.687430 loss: 287.562680 2022/10/12 12:23:11 - mmengine - INFO - Epoch(train) [16][200/586] lr: 5.000000e-03 eta: 15:33:44 time: 0.515418 data_time: 0.053612 memory: 8713 loss_kpt: 284.802089 acc_pose: 0.627277 loss: 284.802089 2022/10/12 12:23:17 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:23:39 - mmengine - INFO - Epoch(train) [16][250/586] lr: 5.000000e-03 eta: 15:33:56 time: 0.549051 data_time: 0.064223 memory: 8713 loss_kpt: 276.795714 acc_pose: 0.684153 loss: 276.795714 2022/10/12 12:24:05 - mmengine - INFO - Epoch(train) [16][300/586] lr: 5.000000e-03 eta: 15:33:57 time: 0.531708 data_time: 0.060321 memory: 8713 loss_kpt: 282.754628 acc_pose: 0.707470 loss: 282.754628 2022/10/12 12:24:32 - mmengine - INFO - Epoch(train) [16][350/586] lr: 5.000000e-03 eta: 15:34:03 time: 0.541606 data_time: 0.059740 memory: 8713 loss_kpt: 281.175759 acc_pose: 0.749702 loss: 281.175759 2022/10/12 12:24:59 - mmengine - INFO - Epoch(train) [16][400/586] lr: 5.000000e-03 eta: 15:33:59 time: 0.525093 data_time: 0.054115 memory: 8713 loss_kpt: 279.954686 acc_pose: 0.594307 loss: 279.954686 2022/10/12 12:25:25 - mmengine - INFO - Epoch(train) [16][450/586] lr: 5.000000e-03 eta: 15:33:54 time: 0.523960 data_time: 0.055082 memory: 8713 loss_kpt: 286.908282 acc_pose: 0.672297 loss: 286.908282 2022/10/12 12:25:51 - mmengine - INFO - Epoch(train) [16][500/586] lr: 5.000000e-03 eta: 15:33:50 time: 0.526085 data_time: 0.061179 memory: 8713 loss_kpt: 274.757766 acc_pose: 0.739497 loss: 274.757766 2022/10/12 12:26:18 - mmengine - INFO - Epoch(train) [16][550/586] lr: 5.000000e-03 eta: 15:33:50 time: 0.532913 data_time: 0.058687 memory: 8713 loss_kpt: 279.196773 acc_pose: 0.646838 loss: 279.196773 2022/10/12 12:26:37 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:27:03 - mmengine - INFO - Epoch(train) [17][50/586] lr: 5.000000e-03 eta: 15:29:56 time: 0.529146 data_time: 0.069678 memory: 8713 loss_kpt: 283.224248 acc_pose: 0.705152 loss: 283.224248 2022/10/12 12:27:29 - mmengine - INFO - Epoch(train) [17][100/586] lr: 5.000000e-03 eta: 15:29:45 time: 0.514648 data_time: 0.055983 memory: 8713 loss_kpt: 279.884604 acc_pose: 0.635773 loss: 279.884604 2022/10/12 12:27:55 - mmengine - INFO - Epoch(train) [17][150/586] lr: 5.000000e-03 eta: 15:29:44 time: 0.529270 data_time: 0.068260 memory: 8713 loss_kpt: 278.497633 acc_pose: 0.700746 loss: 278.497633 2022/10/12 12:28:21 - mmengine - INFO - Epoch(train) [17][200/586] lr: 5.000000e-03 eta: 15:29:32 time: 0.512570 data_time: 0.057311 memory: 8713 loss_kpt: 280.839983 acc_pose: 0.614119 loss: 280.839983 2022/10/12 12:28:47 - mmengine - INFO - Epoch(train) [17][250/586] lr: 5.000000e-03 eta: 15:29:27 time: 0.526005 data_time: 0.064643 memory: 8713 loss_kpt: 277.887884 acc_pose: 0.650521 loss: 277.887884 2022/10/12 12:29:14 - mmengine - INFO - Epoch(train) [17][300/586] lr: 5.000000e-03 eta: 15:29:25 time: 0.529120 data_time: 0.058435 memory: 8713 loss_kpt: 278.083517 acc_pose: 0.644338 loss: 278.083517 2022/10/12 12:29:41 - mmengine - INFO - Epoch(train) [17][350/586] lr: 5.000000e-03 eta: 15:29:28 time: 0.539584 data_time: 0.066626 memory: 8713 loss_kpt: 275.681367 acc_pose: 0.690239 loss: 275.681367 2022/10/12 12:30:08 - mmengine - INFO - Epoch(train) [17][400/586] lr: 5.000000e-03 eta: 15:29:31 time: 0.538866 data_time: 0.064242 memory: 8713 loss_kpt: 279.594079 acc_pose: 0.683730 loss: 279.594079 2022/10/12 12:30:35 - mmengine - INFO - Epoch(train) [17][450/586] lr: 5.000000e-03 eta: 15:29:36 time: 0.544947 data_time: 0.062147 memory: 8713 loss_kpt: 280.111318 acc_pose: 0.639317 loss: 280.111318 2022/10/12 12:31:02 - mmengine - INFO - Epoch(train) [17][500/586] lr: 5.000000e-03 eta: 15:29:41 time: 0.543579 data_time: 0.064770 memory: 8713 loss_kpt: 272.645079 acc_pose: 0.711803 loss: 272.645079 2022/10/12 12:31:30 - mmengine - INFO - Epoch(train) [17][550/586] lr: 5.000000e-03 eta: 15:29:51 time: 0.553247 data_time: 0.060993 memory: 8713 loss_kpt: 274.084196 acc_pose: 0.706808 loss: 274.084196 2022/10/12 12:31:49 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:32:10 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:32:16 - mmengine - INFO - Epoch(train) [18][50/586] lr: 5.000000e-03 eta: 15:26:16 time: 0.544045 data_time: 0.073440 memory: 8713 loss_kpt: 277.007222 acc_pose: 0.615785 loss: 277.007222 2022/10/12 12:32:43 - mmengine - INFO - Epoch(train) [18][100/586] lr: 5.000000e-03 eta: 15:26:17 time: 0.537070 data_time: 0.060257 memory: 8713 loss_kpt: 279.258316 acc_pose: 0.721150 loss: 279.258316 2022/10/12 12:33:09 - mmengine - INFO - Epoch(train) [18][150/586] lr: 5.000000e-03 eta: 15:26:14 time: 0.529923 data_time: 0.059597 memory: 8713 loss_kpt: 278.843915 acc_pose: 0.665221 loss: 278.843915 2022/10/12 12:33:36 - mmengine - INFO - Epoch(train) [18][200/586] lr: 5.000000e-03 eta: 15:26:11 time: 0.531518 data_time: 0.062465 memory: 8713 loss_kpt: 280.468506 acc_pose: 0.672804 loss: 280.468506 2022/10/12 12:34:03 - mmengine - INFO - Epoch(train) [18][250/586] lr: 5.000000e-03 eta: 15:26:10 time: 0.533880 data_time: 0.060493 memory: 8713 loss_kpt: 273.458483 acc_pose: 0.729756 loss: 273.458483 2022/10/12 12:34:29 - mmengine - INFO - Epoch(train) [18][300/586] lr: 5.000000e-03 eta: 15:26:09 time: 0.535668 data_time: 0.057176 memory: 8713 loss_kpt: 270.427636 acc_pose: 0.746245 loss: 270.427636 2022/10/12 12:34:56 - mmengine - INFO - Epoch(train) [18][350/586] lr: 5.000000e-03 eta: 15:26:10 time: 0.539994 data_time: 0.054544 memory: 8713 loss_kpt: 276.919741 acc_pose: 0.678824 loss: 276.919741 2022/10/12 12:35:23 - mmengine - INFO - Epoch(train) [18][400/586] lr: 5.000000e-03 eta: 15:26:02 time: 0.523451 data_time: 0.060054 memory: 8713 loss_kpt: 270.212267 acc_pose: 0.689598 loss: 270.212267 2022/10/12 12:35:49 - mmengine - INFO - Epoch(train) [18][450/586] lr: 5.000000e-03 eta: 15:26:00 time: 0.534745 data_time: 0.056029 memory: 8713 loss_kpt: 272.607491 acc_pose: 0.666806 loss: 272.607491 2022/10/12 12:36:17 - mmengine - INFO - Epoch(train) [18][500/586] lr: 5.000000e-03 eta: 15:26:04 time: 0.547205 data_time: 0.060174 memory: 8713 loss_kpt: 273.825291 acc_pose: 0.678019 loss: 273.825291 2022/10/12 12:36:44 - mmengine - INFO - Epoch(train) [18][550/586] lr: 5.000000e-03 eta: 15:26:05 time: 0.540886 data_time: 0.055849 memory: 8713 loss_kpt: 277.364037 acc_pose: 0.774782 loss: 277.364037 2022/10/12 12:37:03 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:37:29 - mmengine - INFO - Epoch(train) [19][50/586] lr: 5.000000e-03 eta: 15:22:31 time: 0.524833 data_time: 0.067729 memory: 8713 loss_kpt: 273.805179 acc_pose: 0.751993 loss: 273.805179 2022/10/12 12:37:55 - mmengine - INFO - Epoch(train) [19][100/586] lr: 5.000000e-03 eta: 15:22:15 time: 0.508245 data_time: 0.064662 memory: 8713 loss_kpt: 275.318361 acc_pose: 0.597852 loss: 275.318361 2022/10/12 12:38:21 - mmengine - INFO - Epoch(train) [19][150/586] lr: 5.000000e-03 eta: 15:22:03 time: 0.517577 data_time: 0.057192 memory: 8713 loss_kpt: 273.465994 acc_pose: 0.723676 loss: 273.465994 2022/10/12 12:38:45 - mmengine - INFO - Epoch(train) [19][200/586] lr: 5.000000e-03 eta: 15:21:41 time: 0.497175 data_time: 0.062467 memory: 8713 loss_kpt: 272.116794 acc_pose: 0.656804 loss: 272.116794 2022/10/12 12:39:10 - mmengine - INFO - Epoch(train) [19][250/586] lr: 5.000000e-03 eta: 15:21:20 time: 0.500043 data_time: 0.062790 memory: 8713 loss_kpt: 273.327581 acc_pose: 0.682774 loss: 273.327581 2022/10/12 12:39:36 - mmengine - INFO - Epoch(train) [19][300/586] lr: 5.000000e-03 eta: 15:21:04 time: 0.507846 data_time: 0.058634 memory: 8713 loss_kpt: 273.037647 acc_pose: 0.627279 loss: 273.037647 2022/10/12 12:40:01 - mmengine - INFO - Epoch(train) [19][350/586] lr: 5.000000e-03 eta: 15:20:44 time: 0.501780 data_time: 0.061588 memory: 8713 loss_kpt: 269.971388 acc_pose: 0.683001 loss: 269.971388 2022/10/12 12:40:26 - mmengine - INFO - Epoch(train) [19][400/586] lr: 5.000000e-03 eta: 15:20:27 time: 0.508045 data_time: 0.060886 memory: 8713 loss_kpt: 268.362879 acc_pose: 0.745142 loss: 268.362879 2022/10/12 12:40:52 - mmengine - INFO - Epoch(train) [19][450/586] lr: 5.000000e-03 eta: 15:20:10 time: 0.507724 data_time: 0.059819 memory: 8713 loss_kpt: 273.637651 acc_pose: 0.813602 loss: 273.637651 2022/10/12 12:40:53 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:41:17 - mmengine - INFO - Epoch(train) [19][500/586] lr: 5.000000e-03 eta: 15:19:54 time: 0.508996 data_time: 0.057837 memory: 8713 loss_kpt: 267.111077 acc_pose: 0.683171 loss: 267.111077 2022/10/12 12:41:43 - mmengine - INFO - Epoch(train) [19][550/586] lr: 5.000000e-03 eta: 15:19:43 time: 0.520177 data_time: 0.056981 memory: 8713 loss_kpt: 270.718350 acc_pose: 0.557631 loss: 270.718350 2022/10/12 12:42:01 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:42:28 - mmengine - INFO - Epoch(train) [20][50/586] lr: 5.000000e-03 eta: 15:16:23 time: 0.533202 data_time: 0.071545 memory: 8713 loss_kpt: 271.637641 acc_pose: 0.735137 loss: 271.637641 2022/10/12 12:42:53 - mmengine - INFO - Epoch(train) [20][100/586] lr: 5.000000e-03 eta: 15:16:08 time: 0.509964 data_time: 0.060003 memory: 8713 loss_kpt: 264.953633 acc_pose: 0.772240 loss: 264.953633 2022/10/12 12:43:19 - mmengine - INFO - Epoch(train) [20][150/586] lr: 5.000000e-03 eta: 15:15:52 time: 0.508165 data_time: 0.065969 memory: 8713 loss_kpt: 269.538742 acc_pose: 0.675341 loss: 269.538742 2022/10/12 12:43:44 - mmengine - INFO - Epoch(train) [20][200/586] lr: 5.000000e-03 eta: 15:15:36 time: 0.510204 data_time: 0.058014 memory: 8713 loss_kpt: 264.876237 acc_pose: 0.610271 loss: 264.876237 2022/10/12 12:44:09 - mmengine - INFO - Epoch(train) [20][250/586] lr: 5.000000e-03 eta: 15:15:19 time: 0.505604 data_time: 0.061867 memory: 8713 loss_kpt: 268.513835 acc_pose: 0.684111 loss: 268.513835 2022/10/12 12:44:35 - mmengine - INFO - Epoch(train) [20][300/586] lr: 5.000000e-03 eta: 15:15:03 time: 0.511337 data_time: 0.064306 memory: 8713 loss_kpt: 270.035189 acc_pose: 0.699962 loss: 270.035189 2022/10/12 12:45:01 - mmengine - INFO - Epoch(train) [20][350/586] lr: 5.000000e-03 eta: 15:14:51 time: 0.516975 data_time: 0.067233 memory: 8713 loss_kpt: 271.673562 acc_pose: 0.641781 loss: 271.673562 2022/10/12 12:45:26 - mmengine - INFO - Epoch(train) [20][400/586] lr: 5.000000e-03 eta: 15:14:30 time: 0.499751 data_time: 0.059107 memory: 8713 loss_kpt: 268.878034 acc_pose: 0.705652 loss: 268.878034 2022/10/12 12:45:52 - mmengine - INFO - Epoch(train) [20][450/586] lr: 5.000000e-03 eta: 15:14:16 time: 0.512953 data_time: 0.062277 memory: 8713 loss_kpt: 271.956574 acc_pose: 0.646649 loss: 271.956574 2022/10/12 12:46:17 - mmengine - INFO - Epoch(train) [20][500/586] lr: 5.000000e-03 eta: 15:13:57 time: 0.504372 data_time: 0.060977 memory: 8713 loss_kpt: 269.719060 acc_pose: 0.743152 loss: 269.719060 2022/10/12 12:46:42 - mmengine - INFO - Epoch(train) [20][550/586] lr: 5.000000e-03 eta: 15:13:39 time: 0.504904 data_time: 0.057940 memory: 8713 loss_kpt: 266.444470 acc_pose: 0.627726 loss: 266.444470 2022/10/12 12:47:00 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:47:00 - mmengine - INFO - Saving checkpoint at 20 epochs 2022/10/12 12:47:13 - mmengine - INFO - Epoch(val) [20][50/407] eta: 0:01:09 time: 0.195963 data_time: 0.012805 memory: 8713 2022/10/12 12:47:23 - mmengine - INFO - Epoch(val) [20][100/407] eta: 0:00:59 time: 0.193041 data_time: 0.007704 memory: 1759 2022/10/12 12:47:32 - mmengine - INFO - Epoch(val) [20][150/407] eta: 0:00:48 time: 0.189172 data_time: 0.007695 memory: 1759 2022/10/12 12:47:42 - mmengine - INFO - Epoch(val) [20][200/407] eta: 0:00:40 time: 0.194394 data_time: 0.011165 memory: 1759 2022/10/12 12:47:51 - mmengine - INFO - Epoch(val) [20][250/407] eta: 0:00:30 time: 0.191642 data_time: 0.007710 memory: 1759 2022/10/12 12:48:01 - mmengine - INFO - Epoch(val) [20][300/407] eta: 0:00:20 time: 0.190695 data_time: 0.007698 memory: 1759 2022/10/12 12:48:10 - mmengine - INFO - Epoch(val) [20][350/407] eta: 0:00:10 time: 0.189249 data_time: 0.007820 memory: 1759 2022/10/12 12:48:20 - mmengine - INFO - Epoch(val) [20][400/407] eta: 0:00:01 time: 0.189131 data_time: 0.007386 memory: 1759 2022/10/12 12:48:35 - mmengine - INFO - Evaluating CocoMetric... 2022/10/12 12:48:51 - mmengine - INFO - Epoch(val) [20][407/407] coco/AP: 0.551700 coco/AP .5: 0.799116 coco/AP .75: 0.610534 coco/AP (M): 0.536090 coco/AP (L): 0.600992 coco/AR: 0.644647 coco/AR .5: 0.867128 coco/AR .75: 0.702141 coco/AR (M): 0.604452 coco/AR (L): 0.699926 2022/10/12 12:48:51 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/liqikai/openmmlab/pt112cu113py38/mmpose/work_dirs/20221012/rsn2x/best_coco/AP_epoch_10.pth is removed 2022/10/12 12:48:53 - mmengine - INFO - The best checkpoint with 0.5517 coco/AP at 20 epoch is saved to best_coco/AP_epoch_20.pth. 2022/10/12 12:49:20 - mmengine - INFO - Epoch(train) [21][50/586] lr: 5.000000e-03 eta: 15:10:31 time: 0.539429 data_time: 0.067353 memory: 8713 loss_kpt: 263.485178 acc_pose: 0.689471 loss: 263.485178 2022/10/12 12:49:47 - mmengine - INFO - Epoch(train) [21][100/586] lr: 5.000000e-03 eta: 15:10:27 time: 0.534108 data_time: 0.068364 memory: 8713 loss_kpt: 269.190598 acc_pose: 0.683556 loss: 269.190598 2022/10/12 12:50:12 - mmengine - INFO - Epoch(train) [21][150/586] lr: 5.000000e-03 eta: 15:10:10 time: 0.507444 data_time: 0.061736 memory: 8713 loss_kpt: 265.085380 acc_pose: 0.632639 loss: 265.085380 2022/10/12 12:50:37 - mmengine - INFO - Epoch(train) [21][200/586] lr: 5.000000e-03 eta: 15:09:48 time: 0.497882 data_time: 0.056349 memory: 8713 loss_kpt: 264.409026 acc_pose: 0.607367 loss: 264.409026 2022/10/12 12:51:02 - mmengine - INFO - Epoch(train) [21][250/586] lr: 5.000000e-03 eta: 15:09:28 time: 0.500770 data_time: 0.060345 memory: 8713 loss_kpt: 264.383102 acc_pose: 0.776934 loss: 264.383102 2022/10/12 12:51:17 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:51:27 - mmengine - INFO - Epoch(train) [21][300/586] lr: 5.000000e-03 eta: 15:09:07 time: 0.498576 data_time: 0.060811 memory: 8713 loss_kpt: 262.662011 acc_pose: 0.672734 loss: 262.662011 2022/10/12 12:51:52 - mmengine - INFO - Epoch(train) [21][350/586] lr: 5.000000e-03 eta: 15:08:50 time: 0.506959 data_time: 0.061208 memory: 8713 loss_kpt: 266.324983 acc_pose: 0.673088 loss: 266.324983 2022/10/12 12:52:17 - mmengine - INFO - Epoch(train) [21][400/586] lr: 5.000000e-03 eta: 15:08:30 time: 0.501256 data_time: 0.058037 memory: 8713 loss_kpt: 266.783121 acc_pose: 0.737328 loss: 266.783121 2022/10/12 12:52:43 - mmengine - INFO - Epoch(train) [21][450/586] lr: 5.000000e-03 eta: 15:08:14 time: 0.510882 data_time: 0.057618 memory: 8713 loss_kpt: 268.229948 acc_pose: 0.739368 loss: 268.229948 2022/10/12 12:53:08 - mmengine - INFO - Epoch(train) [21][500/586] lr: 5.000000e-03 eta: 15:07:57 time: 0.508466 data_time: 0.058314 memory: 8713 loss_kpt: 265.119344 acc_pose: 0.670752 loss: 265.119344 2022/10/12 12:53:34 - mmengine - INFO - Epoch(train) [21][550/586] lr: 5.000000e-03 eta: 15:07:41 time: 0.508785 data_time: 0.058545 memory: 8713 loss_kpt: 266.537198 acc_pose: 0.713070 loss: 266.537198 2022/10/12 12:53:52 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:54:18 - mmengine - INFO - Epoch(train) [22][50/586] lr: 5.000000e-03 eta: 15:04:37 time: 0.530512 data_time: 0.069686 memory: 8713 loss_kpt: 263.580660 acc_pose: 0.669994 loss: 263.580660 2022/10/12 12:54:44 - mmengine - INFO - Epoch(train) [22][100/586] lr: 5.000000e-03 eta: 15:04:22 time: 0.510682 data_time: 0.061002 memory: 8713 loss_kpt: 264.766543 acc_pose: 0.654607 loss: 264.766543 2022/10/12 12:55:09 - mmengine - INFO - Epoch(train) [22][150/586] lr: 5.000000e-03 eta: 15:04:07 time: 0.512615 data_time: 0.058895 memory: 8713 loss_kpt: 262.076148 acc_pose: 0.695793 loss: 262.076148 2022/10/12 12:55:35 - mmengine - INFO - Epoch(train) [22][200/586] lr: 5.000000e-03 eta: 15:03:50 time: 0.508107 data_time: 0.058532 memory: 8713 loss_kpt: 272.799606 acc_pose: 0.680960 loss: 272.799606 2022/10/12 12:56:01 - mmengine - INFO - Epoch(train) [22][250/586] lr: 5.000000e-03 eta: 15:03:37 time: 0.515358 data_time: 0.059471 memory: 8713 loss_kpt: 264.673502 acc_pose: 0.619597 loss: 264.673502 2022/10/12 12:56:25 - mmengine - INFO - Epoch(train) [22][300/586] lr: 5.000000e-03 eta: 15:03:15 time: 0.496936 data_time: 0.058961 memory: 8713 loss_kpt: 265.841562 acc_pose: 0.723765 loss: 265.841562 2022/10/12 12:56:50 - mmengine - INFO - Epoch(train) [22][350/586] lr: 5.000000e-03 eta: 15:02:56 time: 0.502443 data_time: 0.054160 memory: 8713 loss_kpt: 261.937892 acc_pose: 0.741898 loss: 261.937892 2022/10/12 12:57:15 - mmengine - INFO - Epoch(train) [22][400/586] lr: 5.000000e-03 eta: 15:02:35 time: 0.499206 data_time: 0.061291 memory: 8713 loss_kpt: 261.140081 acc_pose: 0.720021 loss: 261.140081 2022/10/12 12:57:41 - mmengine - INFO - Epoch(train) [22][450/586] lr: 5.000000e-03 eta: 15:02:19 time: 0.510769 data_time: 0.053947 memory: 8713 loss_kpt: 267.469665 acc_pose: 0.715908 loss: 267.469665 2022/10/12 12:58:06 - mmengine - INFO - Epoch(train) [22][500/586] lr: 5.000000e-03 eta: 15:02:00 time: 0.503834 data_time: 0.058056 memory: 8713 loss_kpt: 262.564401 acc_pose: 0.748323 loss: 262.564401 2022/10/12 12:58:31 - mmengine - INFO - Epoch(train) [22][550/586] lr: 5.000000e-03 eta: 15:01:39 time: 0.498597 data_time: 0.055897 memory: 8713 loss_kpt: 263.350048 acc_pose: 0.689188 loss: 263.350048 2022/10/12 12:58:49 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:59:16 - mmengine - INFO - Epoch(train) [23][50/586] lr: 5.000000e-03 eta: 14:58:45 time: 0.535837 data_time: 0.070744 memory: 8713 loss_kpt: 262.776371 acc_pose: 0.682845 loss: 262.776371 2022/10/12 12:59:42 - mmengine - INFO - Epoch(train) [23][100/586] lr: 5.000000e-03 eta: 14:58:32 time: 0.515080 data_time: 0.059200 memory: 8713 loss_kpt: 264.785699 acc_pose: 0.735703 loss: 264.785699 2022/10/12 12:59:46 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:00:08 - mmengine - INFO - Epoch(train) [23][150/586] lr: 5.000000e-03 eta: 14:58:21 time: 0.523531 data_time: 0.057215 memory: 8713 loss_kpt: 263.479224 acc_pose: 0.740916 loss: 263.479224 2022/10/12 13:00:34 - mmengine - INFO - Epoch(train) [23][200/586] lr: 5.000000e-03 eta: 14:58:06 time: 0.512116 data_time: 0.064023 memory: 8713 loss_kpt: 265.391402 acc_pose: 0.805344 loss: 265.391402 2022/10/12 13:01:00 - mmengine - INFO - Epoch(train) [23][250/586] lr: 5.000000e-03 eta: 14:57:54 time: 0.520057 data_time: 0.058644 memory: 8713 loss_kpt: 257.547724 acc_pose: 0.634620 loss: 257.547724 2022/10/12 13:01:26 - mmengine - INFO - Epoch(train) [23][300/586] lr: 5.000000e-03 eta: 14:57:42 time: 0.520085 data_time: 0.059294 memory: 8713 loss_kpt: 257.476737 acc_pose: 0.704651 loss: 257.476737 2022/10/12 13:01:53 - mmengine - INFO - Epoch(train) [23][350/586] lr: 5.000000e-03 eta: 14:57:38 time: 0.540127 data_time: 0.058061 memory: 8713 loss_kpt: 267.025638 acc_pose: 0.763839 loss: 267.025638 2022/10/12 13:02:19 - mmengine - INFO - Epoch(train) [23][400/586] lr: 5.000000e-03 eta: 14:57:27 time: 0.521749 data_time: 0.056852 memory: 8713 loss_kpt: 259.261742 acc_pose: 0.704713 loss: 259.261742 2022/10/12 13:02:45 - mmengine - INFO - Epoch(train) [23][450/586] lr: 5.000000e-03 eta: 14:57:17 time: 0.527779 data_time: 0.058344 memory: 8713 loss_kpt: 263.188780 acc_pose: 0.730965 loss: 263.188780 2022/10/12 13:03:12 - mmengine - INFO - Epoch(train) [23][500/586] lr: 5.000000e-03 eta: 14:57:11 time: 0.534396 data_time: 0.057454 memory: 8713 loss_kpt: 260.161364 acc_pose: 0.685577 loss: 260.161364 2022/10/12 13:03:38 - mmengine - INFO - Epoch(train) [23][550/586] lr: 5.000000e-03 eta: 14:56:57 time: 0.517635 data_time: 0.060359 memory: 8713 loss_kpt: 260.030350 acc_pose: 0.687263 loss: 260.030350 2022/10/12 13:03:56 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:04:24 - mmengine - INFO - Epoch(train) [24][50/586] lr: 5.000000e-03 eta: 14:54:13 time: 0.543834 data_time: 0.066942 memory: 8713 loss_kpt: 263.195875 acc_pose: 0.723780 loss: 263.195875 2022/10/12 13:04:50 - mmengine - INFO - Epoch(train) [24][100/586] lr: 5.000000e-03 eta: 14:54:08 time: 0.538171 data_time: 0.059950 memory: 8713 loss_kpt: 261.362253 acc_pose: 0.714251 loss: 261.362253 2022/10/12 13:05:18 - mmengine - INFO - Epoch(train) [24][150/586] lr: 5.000000e-03 eta: 14:54:06 time: 0.544949 data_time: 0.060660 memory: 8713 loss_kpt: 261.690429 acc_pose: 0.707998 loss: 261.690429 2022/10/12 13:05:44 - mmengine - INFO - Epoch(train) [24][200/586] lr: 5.000000e-03 eta: 14:53:56 time: 0.527608 data_time: 0.060544 memory: 8713 loss_kpt: 259.004319 acc_pose: 0.826085 loss: 259.004319 2022/10/12 13:06:10 - mmengine - INFO - Epoch(train) [24][250/586] lr: 5.000000e-03 eta: 14:53:44 time: 0.521011 data_time: 0.056943 memory: 8713 loss_kpt: 258.858558 acc_pose: 0.726946 loss: 258.858558 2022/10/12 13:06:36 - mmengine - INFO - Epoch(train) [24][300/586] lr: 5.000000e-03 eta: 14:53:32 time: 0.521068 data_time: 0.057066 memory: 8713 loss_kpt: 255.248167 acc_pose: 0.646915 loss: 255.248167 2022/10/12 13:07:03 - mmengine - INFO - Epoch(train) [24][350/586] lr: 5.000000e-03 eta: 14:53:21 time: 0.525445 data_time: 0.062323 memory: 8713 loss_kpt: 257.648279 acc_pose: 0.791469 loss: 257.648279 2022/10/12 13:07:29 - mmengine - INFO - Epoch(train) [24][400/586] lr: 5.000000e-03 eta: 14:53:10 time: 0.525703 data_time: 0.057650 memory: 8713 loss_kpt: 260.003120 acc_pose: 0.692611 loss: 260.003120 2022/10/12 13:07:55 - mmengine - INFO - Epoch(train) [24][450/586] lr: 5.000000e-03 eta: 14:52:57 time: 0.519959 data_time: 0.057535 memory: 8713 loss_kpt: 255.272297 acc_pose: 0.767776 loss: 255.272297 2022/10/12 13:08:21 - mmengine - INFO - Epoch(train) [24][500/586] lr: 5.000000e-03 eta: 14:52:43 time: 0.518830 data_time: 0.057219 memory: 8713 loss_kpt: 257.378035 acc_pose: 0.693900 loss: 257.378035 2022/10/12 13:08:32 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:08:47 - mmengine - INFO - Epoch(train) [24][550/586] lr: 5.000000e-03 eta: 14:52:28 time: 0.516067 data_time: 0.061539 memory: 8713 loss_kpt: 258.574009 acc_pose: 0.801441 loss: 258.574009 2022/10/12 13:09:05 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:09:32 - mmengine - INFO - Epoch(train) [25][50/586] lr: 5.000000e-03 eta: 14:49:44 time: 0.527091 data_time: 0.068285 memory: 8713 loss_kpt: 257.048622 acc_pose: 0.687262 loss: 257.048622 2022/10/12 13:09:57 - mmengine - INFO - Epoch(train) [25][100/586] lr: 5.000000e-03 eta: 14:49:24 time: 0.502614 data_time: 0.059694 memory: 8713 loss_kpt: 257.871946 acc_pose: 0.761661 loss: 257.871946 2022/10/12 13:10:22 - mmengine - INFO - Epoch(train) [25][150/586] lr: 5.000000e-03 eta: 14:49:02 time: 0.496101 data_time: 0.059098 memory: 8713 loss_kpt: 262.596310 acc_pose: 0.699849 loss: 262.596310 2022/10/12 13:10:47 - mmengine - INFO - Epoch(train) [25][200/586] lr: 5.000000e-03 eta: 14:48:43 time: 0.505071 data_time: 0.059348 memory: 8713 loss_kpt: 260.098442 acc_pose: 0.765343 loss: 260.098442 2022/10/12 13:11:13 - mmengine - INFO - Epoch(train) [25][250/586] lr: 5.000000e-03 eta: 14:48:29 time: 0.519023 data_time: 0.058189 memory: 8713 loss_kpt: 253.521442 acc_pose: 0.722463 loss: 253.521442 2022/10/12 13:11:39 - mmengine - INFO - Epoch(train) [25][300/586] lr: 5.000000e-03 eta: 14:48:15 time: 0.516969 data_time: 0.063277 memory: 8713 loss_kpt: 261.257978 acc_pose: 0.747046 loss: 261.257978 2022/10/12 13:12:04 - mmengine - INFO - Epoch(train) [25][350/586] lr: 5.000000e-03 eta: 14:48:00 time: 0.514526 data_time: 0.064748 memory: 8713 loss_kpt: 253.650492 acc_pose: 0.705318 loss: 253.650492 2022/10/12 13:12:30 - mmengine - INFO - Epoch(train) [25][400/586] lr: 5.000000e-03 eta: 14:47:43 time: 0.510574 data_time: 0.064622 memory: 8713 loss_kpt: 260.044146 acc_pose: 0.715825 loss: 260.044146 2022/10/12 13:12:56 - mmengine - INFO - Epoch(train) [25][450/586] lr: 5.000000e-03 eta: 14:47:31 time: 0.525008 data_time: 0.060422 memory: 8713 loss_kpt: 250.526444 acc_pose: 0.642060 loss: 250.526444 2022/10/12 13:13:22 - mmengine - INFO - Epoch(train) [25][500/586] lr: 5.000000e-03 eta: 14:47:15 time: 0.513151 data_time: 0.063963 memory: 8713 loss_kpt: 257.603030 acc_pose: 0.753857 loss: 257.603030 2022/10/12 13:13:47 - mmengine - INFO - Epoch(train) [25][550/586] lr: 5.000000e-03 eta: 14:46:59 time: 0.513723 data_time: 0.064870 memory: 8713 loss_kpt: 253.077315 acc_pose: 0.738043 loss: 253.077315 2022/10/12 13:14:05 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:14:32 - mmengine - INFO - Epoch(train) [26][50/586] lr: 5.000000e-03 eta: 14:44:23 time: 0.535209 data_time: 0.077857 memory: 8713 loss_kpt: 257.591198 acc_pose: 0.707006 loss: 257.591198 2022/10/12 13:14:59 - mmengine - INFO - Epoch(train) [26][100/586] lr: 5.000000e-03 eta: 14:44:18 time: 0.543019 data_time: 0.058518 memory: 8713 loss_kpt: 254.838848 acc_pose: 0.777758 loss: 254.838848 2022/10/12 13:15:26 - mmengine - INFO - Epoch(train) [26][150/586] lr: 5.000000e-03 eta: 14:44:11 time: 0.537116 data_time: 0.062262 memory: 8713 loss_kpt: 252.932611 acc_pose: 0.722122 loss: 252.932611 2022/10/12 13:15:53 - mmengine - INFO - Epoch(train) [26][200/586] lr: 5.000000e-03 eta: 14:44:00 time: 0.526368 data_time: 0.056767 memory: 8713 loss_kpt: 258.267907 acc_pose: 0.750145 loss: 258.267907 2022/10/12 13:16:19 - mmengine - INFO - Epoch(train) [26][250/586] lr: 5.000000e-03 eta: 14:43:51 time: 0.533398 data_time: 0.065019 memory: 8713 loss_kpt: 257.680587 acc_pose: 0.750526 loss: 257.680587 2022/10/12 13:16:46 - mmengine - INFO - Epoch(train) [26][300/586] lr: 5.000000e-03 eta: 14:43:39 time: 0.525259 data_time: 0.055907 memory: 8713 loss_kpt: 253.504514 acc_pose: 0.667896 loss: 253.504514 2022/10/12 13:17:12 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:17:12 - mmengine - INFO - Epoch(train) [26][350/586] lr: 5.000000e-03 eta: 14:43:27 time: 0.524331 data_time: 0.058764 memory: 8713 loss_kpt: 252.324572 acc_pose: 0.705920 loss: 252.324572 2022/10/12 13:17:38 - mmengine - INFO - Epoch(train) [26][400/586] lr: 5.000000e-03 eta: 14:43:14 time: 0.523961 data_time: 0.062635 memory: 8713 loss_kpt: 254.024462 acc_pose: 0.689734 loss: 254.024462 2022/10/12 13:18:04 - mmengine - INFO - Epoch(train) [26][450/586] lr: 5.000000e-03 eta: 14:43:02 time: 0.525326 data_time: 0.059131 memory: 8713 loss_kpt: 255.338331 acc_pose: 0.678636 loss: 255.338331 2022/10/12 13:18:32 - mmengine - INFO - Epoch(train) [26][500/586] lr: 5.000000e-03 eta: 14:42:57 time: 0.545894 data_time: 0.060283 memory: 8713 loss_kpt: 256.174428 acc_pose: 0.752365 loss: 256.174428 2022/10/12 13:18:58 - mmengine - INFO - Epoch(train) [26][550/586] lr: 5.000000e-03 eta: 14:42:49 time: 0.537378 data_time: 0.065119 memory: 8713 loss_kpt: 251.542122 acc_pose: 0.763630 loss: 251.542122 2022/10/12 13:19:18 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:19:44 - mmengine - INFO - Epoch(train) [27][50/586] lr: 5.000000e-03 eta: 14:40:13 time: 0.522093 data_time: 0.069057 memory: 8713 loss_kpt: 256.341099 acc_pose: 0.731506 loss: 256.341099 2022/10/12 13:20:10 - mmengine - INFO - Epoch(train) [27][100/586] lr: 5.000000e-03 eta: 14:39:57 time: 0.513622 data_time: 0.058488 memory: 8713 loss_kpt: 254.109042 acc_pose: 0.765847 loss: 254.109042 2022/10/12 13:20:37 - mmengine - INFO - Epoch(train) [27][150/586] lr: 5.000000e-03 eta: 14:39:49 time: 0.538867 data_time: 0.059883 memory: 8713 loss_kpt: 256.090478 acc_pose: 0.699512 loss: 256.090478 2022/10/12 13:21:02 - mmengine - INFO - Epoch(train) [27][200/586] lr: 5.000000e-03 eta: 14:39:33 time: 0.512961 data_time: 0.053303 memory: 8713 loss_kpt: 254.724698 acc_pose: 0.688043 loss: 254.724698 2022/10/12 13:21:29 - mmengine - INFO - Epoch(train) [27][250/586] lr: 5.000000e-03 eta: 14:39:24 time: 0.534804 data_time: 0.058982 memory: 8713 loss_kpt: 257.010205 acc_pose: 0.720915 loss: 257.010205 2022/10/12 13:21:56 - mmengine - INFO - Epoch(train) [27][300/586] lr: 5.000000e-03 eta: 14:39:16 time: 0.540117 data_time: 0.063028 memory: 8713 loss_kpt: 253.454737 acc_pose: 0.675677 loss: 253.454737 2022/10/12 13:22:23 - mmengine - INFO - Epoch(train) [27][350/586] lr: 5.000000e-03 eta: 14:39:06 time: 0.532743 data_time: 0.057977 memory: 8713 loss_kpt: 248.507034 acc_pose: 0.633884 loss: 248.507034 2022/10/12 13:22:48 - mmengine - INFO - Epoch(train) [27][400/586] lr: 5.000000e-03 eta: 14:38:49 time: 0.513470 data_time: 0.056786 memory: 8713 loss_kpt: 252.697430 acc_pose: 0.782410 loss: 252.697430 2022/10/12 13:23:14 - mmengine - INFO - Epoch(train) [27][450/586] lr: 5.000000e-03 eta: 14:38:31 time: 0.508114 data_time: 0.060132 memory: 8713 loss_kpt: 256.410261 acc_pose: 0.733327 loss: 256.410261 2022/10/12 13:23:40 - mmengine - INFO - Epoch(train) [27][500/586] lr: 5.000000e-03 eta: 14:38:15 time: 0.517712 data_time: 0.055379 memory: 8713 loss_kpt: 254.624111 acc_pose: 0.709832 loss: 254.624111 2022/10/12 13:24:06 - mmengine - INFO - Epoch(train) [27][550/586] lr: 5.000000e-03 eta: 14:38:00 time: 0.518014 data_time: 0.062176 memory: 8713 loss_kpt: 247.083143 acc_pose: 0.811225 loss: 247.083143 2022/10/12 13:24:24 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:24:51 - mmengine - INFO - Epoch(train) [28][50/586] lr: 5.000000e-03 eta: 14:35:38 time: 0.550137 data_time: 0.069568 memory: 8713 loss_kpt: 252.757908 acc_pose: 0.710196 loss: 252.757908 2022/10/12 13:25:17 - mmengine - INFO - Epoch(train) [28][100/586] lr: 5.000000e-03 eta: 14:35:26 time: 0.525199 data_time: 0.062356 memory: 8713 loss_kpt: 258.049584 acc_pose: 0.671475 loss: 258.049584 2022/10/12 13:25:44 - mmengine - INFO - Epoch(train) [28][150/586] lr: 5.000000e-03 eta: 14:35:16 time: 0.534297 data_time: 0.060688 memory: 8713 loss_kpt: 257.640231 acc_pose: 0.717796 loss: 257.640231 2022/10/12 13:25:59 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:26:10 - mmengine - INFO - Epoch(train) [28][200/586] lr: 5.000000e-03 eta: 14:35:03 time: 0.524468 data_time: 0.058077 memory: 8713 loss_kpt: 255.433308 acc_pose: 0.714041 loss: 255.433308 2022/10/12 13:26:37 - mmengine - INFO - Epoch(train) [28][250/586] lr: 5.000000e-03 eta: 14:34:55 time: 0.540890 data_time: 0.058428 memory: 8713 loss_kpt: 248.715260 acc_pose: 0.744621 loss: 248.715260 2022/10/12 13:27:04 - mmengine - INFO - Epoch(train) [28][300/586] lr: 5.000000e-03 eta: 14:34:42 time: 0.524640 data_time: 0.056201 memory: 8713 loss_kpt: 258.194291 acc_pose: 0.600003 loss: 258.194291 2022/10/12 13:27:30 - mmengine - INFO - Epoch(train) [28][350/586] lr: 5.000000e-03 eta: 14:34:31 time: 0.533566 data_time: 0.061265 memory: 8713 loss_kpt: 254.514732 acc_pose: 0.701826 loss: 254.514732 2022/10/12 13:27:58 - mmengine - INFO - Epoch(train) [28][400/586] lr: 5.000000e-03 eta: 14:34:25 time: 0.545173 data_time: 0.062741 memory: 8713 loss_kpt: 249.088750 acc_pose: 0.729578 loss: 249.088750 2022/10/12 13:28:24 - mmengine - INFO - Epoch(train) [28][450/586] lr: 5.000000e-03 eta: 14:34:13 time: 0.529949 data_time: 0.059235 memory: 8713 loss_kpt: 254.220786 acc_pose: 0.711013 loss: 254.220786 2022/10/12 13:28:50 - mmengine - INFO - Epoch(train) [28][500/586] lr: 5.000000e-03 eta: 14:34:00 time: 0.526271 data_time: 0.061221 memory: 8713 loss_kpt: 252.691598 acc_pose: 0.682283 loss: 252.691598 2022/10/12 13:29:16 - mmengine - INFO - Epoch(train) [28][550/586] lr: 5.000000e-03 eta: 14:33:40 time: 0.506213 data_time: 0.059216 memory: 8713 loss_kpt: 251.148666 acc_pose: 0.742862 loss: 251.148666 2022/10/12 13:29:34 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:29:59 - mmengine - INFO - Epoch(train) [29][50/586] lr: 5.000000e-03 eta: 14:31:11 time: 0.513959 data_time: 0.068350 memory: 8713 loss_kpt: 251.950680 acc_pose: 0.644454 loss: 251.950680 2022/10/12 13:30:24 - mmengine - INFO - Epoch(train) [29][100/586] lr: 5.000000e-03 eta: 14:30:49 time: 0.500238 data_time: 0.057778 memory: 8713 loss_kpt: 249.140254 acc_pose: 0.681746 loss: 249.140254 2022/10/12 13:30:50 - mmengine - INFO - Epoch(train) [29][150/586] lr: 5.000000e-03 eta: 14:30:31 time: 0.510957 data_time: 0.056843 memory: 8713 loss_kpt: 250.063940 acc_pose: 0.767524 loss: 250.063940 2022/10/12 13:31:16 - mmengine - INFO - Epoch(train) [29][200/586] lr: 5.000000e-03 eta: 14:30:16 time: 0.520402 data_time: 0.053948 memory: 8713 loss_kpt: 251.444995 acc_pose: 0.738708 loss: 251.444995 2022/10/12 13:31:42 - mmengine - INFO - Epoch(train) [29][250/586] lr: 5.000000e-03 eta: 14:30:00 time: 0.515196 data_time: 0.059160 memory: 8713 loss_kpt: 249.544081 acc_pose: 0.764740 loss: 249.544081 2022/10/12 13:32:07 - mmengine - INFO - Epoch(train) [29][300/586] lr: 5.000000e-03 eta: 14:29:42 time: 0.510483 data_time: 0.057139 memory: 8713 loss_kpt: 249.202404 acc_pose: 0.742896 loss: 249.202404 2022/10/12 13:32:33 - mmengine - INFO - Epoch(train) [29][350/586] lr: 5.000000e-03 eta: 14:29:25 time: 0.514400 data_time: 0.062928 memory: 8713 loss_kpt: 251.586334 acc_pose: 0.764271 loss: 251.586334 2022/10/12 13:32:59 - mmengine - INFO - Epoch(train) [29][400/586] lr: 5.000000e-03 eta: 14:29:07 time: 0.513499 data_time: 0.053237 memory: 8713 loss_kpt: 252.378291 acc_pose: 0.693878 loss: 252.378291 2022/10/12 13:33:24 - mmengine - INFO - Epoch(train) [29][450/586] lr: 5.000000e-03 eta: 14:28:49 time: 0.512045 data_time: 0.061248 memory: 8713 loss_kpt: 247.033532 acc_pose: 0.780864 loss: 247.033532 2022/10/12 13:33:50 - mmengine - INFO - Epoch(train) [29][500/586] lr: 5.000000e-03 eta: 14:28:33 time: 0.517109 data_time: 0.058116 memory: 8713 loss_kpt: 248.778101 acc_pose: 0.721948 loss: 248.778101 2022/10/12 13:34:16 - mmengine - INFO - Epoch(train) [29][550/586] lr: 5.000000e-03 eta: 14:28:16 time: 0.515132 data_time: 0.060865 memory: 8713 loss_kpt: 248.632417 acc_pose: 0.716960 loss: 248.632417 2022/10/12 13:34:34 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:34:38 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:35:02 - mmengine - INFO - Epoch(train) [30][50/586] lr: 5.000000e-03 eta: 14:26:01 time: 0.547001 data_time: 0.068264 memory: 8713 loss_kpt: 251.056754 acc_pose: 0.708216 loss: 251.056754 2022/10/12 13:35:28 - mmengine - INFO - Epoch(train) [30][100/586] lr: 5.000000e-03 eta: 14:25:49 time: 0.529823 data_time: 0.059220 memory: 8713 loss_kpt: 253.947431 acc_pose: 0.697074 loss: 253.947431 2022/10/12 13:35:54 - mmengine - INFO - Epoch(train) [30][150/586] lr: 5.000000e-03 eta: 14:25:36 time: 0.525587 data_time: 0.060085 memory: 8713 loss_kpt: 250.126019 acc_pose: 0.756949 loss: 250.126019 2022/10/12 13:36:20 - mmengine - INFO - Epoch(train) [30][200/586] lr: 5.000000e-03 eta: 14:25:18 time: 0.513746 data_time: 0.058895 memory: 8713 loss_kpt: 251.485609 acc_pose: 0.799738 loss: 251.485609 2022/10/12 13:36:46 - mmengine - INFO - Epoch(train) [30][250/586] lr: 5.000000e-03 eta: 14:25:06 time: 0.529554 data_time: 0.059382 memory: 8713 loss_kpt: 249.052725 acc_pose: 0.828198 loss: 249.052725 2022/10/12 13:37:13 - mmengine - INFO - Epoch(train) [30][300/586] lr: 5.000000e-03 eta: 14:24:52 time: 0.526327 data_time: 0.058852 memory: 8713 loss_kpt: 250.647531 acc_pose: 0.725232 loss: 250.647531 2022/10/12 13:37:39 - mmengine - INFO - Epoch(train) [30][350/586] lr: 5.000000e-03 eta: 14:24:37 time: 0.522120 data_time: 0.060601 memory: 8713 loss_kpt: 247.396978 acc_pose: 0.689068 loss: 247.396978 2022/10/12 13:38:05 - mmengine - INFO - Epoch(train) [30][400/586] lr: 5.000000e-03 eta: 14:24:22 time: 0.519875 data_time: 0.054840 memory: 8713 loss_kpt: 249.683966 acc_pose: 0.718811 loss: 249.683966 2022/10/12 13:38:31 - mmengine - INFO - Epoch(train) [30][450/586] lr: 5.000000e-03 eta: 14:24:04 time: 0.515582 data_time: 0.065147 memory: 8713 loss_kpt: 252.063717 acc_pose: 0.759483 loss: 252.063717 2022/10/12 13:38:56 - mmengine - INFO - Epoch(train) [30][500/586] lr: 5.000000e-03 eta: 14:23:46 time: 0.511521 data_time: 0.061962 memory: 8713 loss_kpt: 249.923587 acc_pose: 0.785558 loss: 249.923587 2022/10/12 13:39:22 - mmengine - INFO - Epoch(train) [30][550/586] lr: 5.000000e-03 eta: 14:23:30 time: 0.519399 data_time: 0.061191 memory: 8713 loss_kpt: 249.509907 acc_pose: 0.733107 loss: 249.509907 2022/10/12 13:39:41 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:39:41 - mmengine - INFO - Saving checkpoint at 30 epochs 2022/10/12 13:39:54 - mmengine - INFO - Epoch(val) [30][50/407] eta: 0:01:10 time: 0.198067 data_time: 0.012688 memory: 8713 2022/10/12 13:40:03 - mmengine - INFO - Epoch(val) [30][100/407] eta: 0:00:58 time: 0.191210 data_time: 0.007857 memory: 1759 2022/10/12 13:40:13 - mmengine - INFO - Epoch(val) [30][150/407] eta: 0:00:49 time: 0.191415 data_time: 0.007724 memory: 1759 2022/10/12 13:40:22 - mmengine - INFO - Epoch(val) [30][200/407] eta: 0:00:39 time: 0.190676 data_time: 0.007967 memory: 1759 2022/10/12 13:40:32 - mmengine - INFO - Epoch(val) [30][250/407] eta: 0:00:29 time: 0.189085 data_time: 0.007420 memory: 1759 2022/10/12 13:40:41 - mmengine - INFO - Epoch(val) [30][300/407] eta: 0:00:20 time: 0.189277 data_time: 0.008364 memory: 1759 2022/10/12 13:40:51 - mmengine - INFO - Epoch(val) [30][350/407] eta: 0:00:11 time: 0.193083 data_time: 0.010985 memory: 1759 2022/10/12 13:41:00 - mmengine - INFO - Epoch(val) [30][400/407] eta: 0:00:01 time: 0.189523 data_time: 0.007794 memory: 1759 2022/10/12 13:41:15 - mmengine - INFO - Evaluating CocoMetric... 2022/10/12 13:41:31 - mmengine - INFO - Epoch(val) [30][407/407] coco/AP: 0.613293 coco/AP .5: 0.844470 coco/AP .75: 0.681083 coco/AP (M): 0.588192 coco/AP (L): 0.665057 coco/AR: 0.687437 coco/AR .5: 0.891688 coco/AR .75: 0.747953 coco/AR (M): 0.645261 coco/AR (L): 0.745634 2022/10/12 13:41:31 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/liqikai/openmmlab/pt112cu113py38/mmpose/work_dirs/20221012/rsn2x/best_coco/AP_epoch_20.pth is removed 2022/10/12 13:41:33 - mmengine - INFO - The best checkpoint with 0.6133 coco/AP at 30 epoch is saved to best_coco/AP_epoch_30.pth. 2022/10/12 13:42:00 - mmengine - INFO - Epoch(train) [31][50/586] lr: 5.000000e-03 eta: 14:21:13 time: 0.525613 data_time: 0.069379 memory: 8713 loss_kpt: 247.768520 acc_pose: 0.745996 loss: 247.768520 2022/10/12 13:42:25 - mmengine - INFO - Epoch(train) [31][100/586] lr: 5.000000e-03 eta: 14:20:56 time: 0.515810 data_time: 0.064545 memory: 8713 loss_kpt: 246.473349 acc_pose: 0.743212 loss: 246.473349 2022/10/12 13:42:51 - mmengine - INFO - Epoch(train) [31][150/586] lr: 5.000000e-03 eta: 14:20:38 time: 0.513542 data_time: 0.063366 memory: 8713 loss_kpt: 247.938460 acc_pose: 0.757681 loss: 247.938460 2022/10/12 13:43:17 - mmengine - INFO - Epoch(train) [31][200/586] lr: 5.000000e-03 eta: 14:20:23 time: 0.520411 data_time: 0.066389 memory: 8713 loss_kpt: 250.522962 acc_pose: 0.752655 loss: 250.522962 2022/10/12 13:43:43 - mmengine - INFO - Epoch(train) [31][250/586] lr: 5.000000e-03 eta: 14:20:07 time: 0.519112 data_time: 0.058760 memory: 8713 loss_kpt: 246.627446 acc_pose: 0.783360 loss: 246.627446 2022/10/12 13:44:08 - mmengine - INFO - Epoch(train) [31][300/586] lr: 5.000000e-03 eta: 14:19:45 time: 0.502169 data_time: 0.060720 memory: 8713 loss_kpt: 245.075502 acc_pose: 0.744160 loss: 245.075502 2022/10/12 13:44:34 - mmengine - INFO - Epoch(train) [31][350/586] lr: 5.000000e-03 eta: 14:19:28 time: 0.515869 data_time: 0.062292 memory: 8713 loss_kpt: 247.899665 acc_pose: 0.715919 loss: 247.899665 2022/10/12 13:44:59 - mmengine - INFO - Epoch(train) [31][400/586] lr: 5.000000e-03 eta: 14:19:08 time: 0.504554 data_time: 0.056861 memory: 8713 loss_kpt: 248.468229 acc_pose: 0.747334 loss: 248.468229 2022/10/12 13:45:10 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:45:25 - mmengine - INFO - Epoch(train) [31][450/586] lr: 5.000000e-03 eta: 14:18:52 time: 0.521322 data_time: 0.058851 memory: 8713 loss_kpt: 248.619675 acc_pose: 0.644778 loss: 248.619675 2022/10/12 13:45:51 - mmengine - INFO - Epoch(train) [31][500/586] lr: 5.000000e-03 eta: 14:18:36 time: 0.517022 data_time: 0.055991 memory: 8713 loss_kpt: 243.607300 acc_pose: 0.745510 loss: 243.607300 2022/10/12 13:46:17 - mmengine - INFO - Epoch(train) [31][550/586] lr: 5.000000e-03 eta: 14:18:16 time: 0.507185 data_time: 0.054029 memory: 8713 loss_kpt: 245.072322 acc_pose: 0.725741 loss: 245.072322 2022/10/12 13:46:34 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:47:01 - mmengine - INFO - Epoch(train) [32][50/586] lr: 5.000000e-03 eta: 14:16:04 time: 0.533049 data_time: 0.067138 memory: 8713 loss_kpt: 247.428371 acc_pose: 0.760015 loss: 247.428371 2022/10/12 13:47:27 - mmengine - INFO - Epoch(train) [32][100/586] lr: 5.000000e-03 eta: 14:15:50 time: 0.526343 data_time: 0.056496 memory: 8713 loss_kpt: 244.817911 acc_pose: 0.730877 loss: 244.817911 2022/10/12 13:47:54 - mmengine - INFO - Epoch(train) [32][150/586] lr: 5.000000e-03 eta: 14:15:36 time: 0.527993 data_time: 0.062193 memory: 8713 loss_kpt: 251.145981 acc_pose: 0.698826 loss: 251.145981 2022/10/12 13:48:20 - mmengine - INFO - Epoch(train) [32][200/586] lr: 5.000000e-03 eta: 14:15:25 time: 0.536457 data_time: 0.063208 memory: 8713 loss_kpt: 241.389832 acc_pose: 0.768995 loss: 241.389832 2022/10/12 13:48:47 - mmengine - INFO - Epoch(train) [32][250/586] lr: 5.000000e-03 eta: 14:15:13 time: 0.535480 data_time: 0.062457 memory: 8713 loss_kpt: 250.449989 acc_pose: 0.775809 loss: 250.449989 2022/10/12 13:49:13 - mmengine - INFO - Epoch(train) [32][300/586] lr: 5.000000e-03 eta: 14:14:58 time: 0.521462 data_time: 0.059054 memory: 8713 loss_kpt: 242.015545 acc_pose: 0.747952 loss: 242.015545 2022/10/12 13:49:40 - mmengine - INFO - Epoch(train) [32][350/586] lr: 5.000000e-03 eta: 14:14:44 time: 0.530177 data_time: 0.056014 memory: 8713 loss_kpt: 242.608383 acc_pose: 0.688885 loss: 242.608383 2022/10/12 13:50:06 - mmengine - INFO - Epoch(train) [32][400/586] lr: 5.000000e-03 eta: 14:14:29 time: 0.524353 data_time: 0.060662 memory: 8713 loss_kpt: 248.647884 acc_pose: 0.742250 loss: 248.647884 2022/10/12 13:50:32 - mmengine - INFO - Epoch(train) [32][450/586] lr: 5.000000e-03 eta: 14:14:15 time: 0.528241 data_time: 0.061836 memory: 8713 loss_kpt: 251.511457 acc_pose: 0.728201 loss: 251.511457 2022/10/12 13:50:59 - mmengine - INFO - Epoch(train) [32][500/586] lr: 5.000000e-03 eta: 14:14:01 time: 0.527656 data_time: 0.056323 memory: 8713 loss_kpt: 240.691837 acc_pose: 0.826348 loss: 240.691837 2022/10/12 13:51:25 - mmengine - INFO - Epoch(train) [32][550/586] lr: 5.000000e-03 eta: 14:13:45 time: 0.521384 data_time: 0.060273 memory: 8713 loss_kpt: 248.148864 acc_pose: 0.783979 loss: 248.148864 2022/10/12 13:51:44 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:52:10 - mmengine - INFO - Epoch(train) [33][50/586] lr: 5.000000e-03 eta: 14:11:35 time: 0.527851 data_time: 0.074576 memory: 8713 loss_kpt: 249.832228 acc_pose: 0.755340 loss: 249.832228 2022/10/12 13:52:36 - mmengine - INFO - Epoch(train) [33][100/586] lr: 5.000000e-03 eta: 14:11:18 time: 0.515915 data_time: 0.055011 memory: 8713 loss_kpt: 245.425826 acc_pose: 0.725356 loss: 245.425826 2022/10/12 13:53:02 - mmengine - INFO - Epoch(train) [33][150/586] lr: 5.000000e-03 eta: 14:11:00 time: 0.514628 data_time: 0.061109 memory: 8713 loss_kpt: 247.036200 acc_pose: 0.695821 loss: 247.036200 2022/10/12 13:53:27 - mmengine - INFO - Epoch(train) [33][200/586] lr: 5.000000e-03 eta: 14:10:41 time: 0.508474 data_time: 0.058061 memory: 8713 loss_kpt: 244.531544 acc_pose: 0.753011 loss: 244.531544 2022/10/12 13:53:52 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:53:53 - mmengine - INFO - Epoch(train) [33][250/586] lr: 5.000000e-03 eta: 14:10:24 time: 0.520606 data_time: 0.062054 memory: 8713 loss_kpt: 246.697203 acc_pose: 0.737128 loss: 246.697203 2022/10/12 13:54:18 - mmengine - INFO - Epoch(train) [33][300/586] lr: 5.000000e-03 eta: 14:10:03 time: 0.501141 data_time: 0.059470 memory: 8713 loss_kpt: 244.344103 acc_pose: 0.761442 loss: 244.344103 2022/10/12 13:54:44 - mmengine - INFO - Epoch(train) [33][350/586] lr: 5.000000e-03 eta: 14:09:43 time: 0.509314 data_time: 0.063747 memory: 8713 loss_kpt: 245.058947 acc_pose: 0.706605 loss: 245.058947 2022/10/12 13:55:09 - mmengine - INFO - Epoch(train) [33][400/586] lr: 5.000000e-03 eta: 14:09:26 time: 0.516077 data_time: 0.056573 memory: 8713 loss_kpt: 248.324348 acc_pose: 0.759005 loss: 248.324348 2022/10/12 13:55:35 - mmengine - INFO - Epoch(train) [33][450/586] lr: 5.000000e-03 eta: 14:09:08 time: 0.514660 data_time: 0.061828 memory: 8713 loss_kpt: 248.962722 acc_pose: 0.758187 loss: 248.962722 2022/10/12 13:56:01 - mmengine - INFO - Epoch(train) [33][500/586] lr: 5.000000e-03 eta: 14:08:49 time: 0.512689 data_time: 0.062271 memory: 8713 loss_kpt: 250.623380 acc_pose: 0.864181 loss: 250.623380 2022/10/12 13:56:27 - mmengine - INFO - Epoch(train) [33][550/586] lr: 5.000000e-03 eta: 14:08:32 time: 0.516480 data_time: 0.059106 memory: 8713 loss_kpt: 245.817578 acc_pose: 0.758808 loss: 245.817578 2022/10/12 13:56:45 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:57:12 - mmengine - INFO - Epoch(train) [34][50/586] lr: 5.000000e-03 eta: 14:06:29 time: 0.544235 data_time: 0.066992 memory: 8713 loss_kpt: 243.464616 acc_pose: 0.773581 loss: 243.464616 2022/10/12 13:57:39 - mmengine - INFO - Epoch(train) [34][100/586] lr: 5.000000e-03 eta: 14:06:16 time: 0.530607 data_time: 0.058492 memory: 8713 loss_kpt: 248.550342 acc_pose: 0.741248 loss: 248.550342 2022/10/12 13:58:05 - mmengine - INFO - Epoch(train) [34][150/586] lr: 5.000000e-03 eta: 14:06:01 time: 0.525114 data_time: 0.063471 memory: 8713 loss_kpt: 246.979090 acc_pose: 0.753280 loss: 246.979090 2022/10/12 13:58:31 - mmengine - INFO - Epoch(train) [34][200/586] lr: 5.000000e-03 eta: 14:05:45 time: 0.525612 data_time: 0.058355 memory: 8713 loss_kpt: 244.927535 acc_pose: 0.767220 loss: 244.927535 2022/10/12 13:58:58 - mmengine - INFO - Epoch(train) [34][250/586] lr: 5.000000e-03 eta: 14:05:32 time: 0.534056 data_time: 0.060045 memory: 8713 loss_kpt: 243.061487 acc_pose: 0.740167 loss: 243.061487 2022/10/12 13:59:24 - mmengine - INFO - Epoch(train) [34][300/586] lr: 5.000000e-03 eta: 14:05:18 time: 0.527868 data_time: 0.062087 memory: 8713 loss_kpt: 243.637737 acc_pose: 0.650461 loss: 243.637737 2022/10/12 13:59:50 - mmengine - INFO - Epoch(train) [34][350/586] lr: 5.000000e-03 eta: 14:04:59 time: 0.513430 data_time: 0.062170 memory: 8713 loss_kpt: 243.479796 acc_pose: 0.736815 loss: 243.479796 2022/10/12 14:00:16 - mmengine - INFO - Epoch(train) [34][400/586] lr: 5.000000e-03 eta: 14:04:41 time: 0.513388 data_time: 0.056944 memory: 8713 loss_kpt: 243.343794 acc_pose: 0.671889 loss: 243.343794 2022/10/12 14:00:42 - mmengine - INFO - Epoch(train) [34][450/586] lr: 5.000000e-03 eta: 14:04:24 time: 0.518877 data_time: 0.069311 memory: 8713 loss_kpt: 247.895324 acc_pose: 0.752222 loss: 247.895324 2022/10/12 14:01:07 - mmengine - INFO - Epoch(train) [34][500/586] lr: 5.000000e-03 eta: 14:04:06 time: 0.515456 data_time: 0.058389 memory: 8713 loss_kpt: 243.424286 acc_pose: 0.738238 loss: 243.424286 2022/10/12 14:01:33 - mmengine - INFO - Epoch(train) [34][550/586] lr: 5.000000e-03 eta: 14:03:49 time: 0.521320 data_time: 0.063084 memory: 8713 loss_kpt: 243.305517 acc_pose: 0.691836 loss: 243.305517 2022/10/12 14:01:52 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:02:19 - mmengine - INFO - Epoch(train) [35][50/586] lr: 5.000000e-03 eta: 14:01:49 time: 0.543662 data_time: 0.075806 memory: 8713 loss_kpt: 244.307023 acc_pose: 0.817103 loss: 244.307023 2022/10/12 14:02:33 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:02:46 - mmengine - INFO - Epoch(train) [35][100/586] lr: 5.000000e-03 eta: 14:01:36 time: 0.531434 data_time: 0.059804 memory: 8713 loss_kpt: 243.011190 acc_pose: 0.819164 loss: 243.011190 2022/10/12 14:03:13 - mmengine - INFO - Epoch(train) [35][150/586] lr: 5.000000e-03 eta: 14:01:26 time: 0.550311 data_time: 0.064651 memory: 8713 loss_kpt: 241.996621 acc_pose: 0.638929 loss: 241.996621 2022/10/12 14:03:40 - mmengine - INFO - Epoch(train) [35][200/586] lr: 5.000000e-03 eta: 14:01:12 time: 0.528170 data_time: 0.061897 memory: 8713 loss_kpt: 241.674609 acc_pose: 0.735240 loss: 241.674609 2022/10/12 14:04:07 - mmengine - INFO - Epoch(train) [35][250/586] lr: 5.000000e-03 eta: 14:01:00 time: 0.539994 data_time: 0.059382 memory: 8713 loss_kpt: 244.435134 acc_pose: 0.689047 loss: 244.435134 2022/10/12 14:04:33 - mmengine - INFO - Epoch(train) [35][300/586] lr: 5.000000e-03 eta: 14:00:44 time: 0.525595 data_time: 0.065053 memory: 8713 loss_kpt: 240.573072 acc_pose: 0.724507 loss: 240.573072 2022/10/12 14:05:00 - mmengine - INFO - Epoch(train) [35][350/586] lr: 5.000000e-03 eta: 14:00:30 time: 0.532130 data_time: 0.068080 memory: 8713 loss_kpt: 244.504364 acc_pose: 0.766728 loss: 244.504364 2022/10/12 14:05:26 - mmengine - INFO - Epoch(train) [35][400/586] lr: 5.000000e-03 eta: 14:00:14 time: 0.525257 data_time: 0.061062 memory: 8713 loss_kpt: 237.572944 acc_pose: 0.752368 loss: 237.572944 2022/10/12 14:05:52 - mmengine - INFO - Epoch(train) [35][450/586] lr: 5.000000e-03 eta: 13:59:56 time: 0.515252 data_time: 0.059397 memory: 8713 loss_kpt: 240.105006 acc_pose: 0.765993 loss: 240.105006 2022/10/12 14:06:17 - mmengine - INFO - Epoch(train) [35][500/586] lr: 5.000000e-03 eta: 13:59:36 time: 0.509491 data_time: 0.059314 memory: 8713 loss_kpt: 249.348992 acc_pose: 0.757962 loss: 249.348992 2022/10/12 14:06:44 - mmengine - INFO - Epoch(train) [35][550/586] lr: 5.000000e-03 eta: 13:59:22 time: 0.532114 data_time: 0.058362 memory: 8713 loss_kpt: 242.000748 acc_pose: 0.700133 loss: 242.000748 2022/10/12 14:07:02 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:07:31 - mmengine - INFO - Epoch(train) [36][50/586] lr: 5.000000e-03 eta: 13:57:34 time: 0.581017 data_time: 0.077410 memory: 8713 loss_kpt: 241.761337 acc_pose: 0.762498 loss: 241.761337 2022/10/12 14:07:59 - mmengine - INFO - Epoch(train) [36][100/586] lr: 5.000000e-03 eta: 13:57:23 time: 0.544285 data_time: 0.068467 memory: 8713 loss_kpt: 243.990939 acc_pose: 0.777230 loss: 243.990939 2022/10/12 14:08:26 - mmengine - INFO - Epoch(train) [36][150/586] lr: 5.000000e-03 eta: 13:57:11 time: 0.541946 data_time: 0.063300 memory: 8713 loss_kpt: 237.371556 acc_pose: 0.778869 loss: 237.371556 2022/10/12 14:08:53 - mmengine - INFO - Epoch(train) [36][200/586] lr: 5.000000e-03 eta: 13:56:58 time: 0.536475 data_time: 0.062226 memory: 8713 loss_kpt: 244.505493 acc_pose: 0.756835 loss: 244.505493 2022/10/12 14:09:20 - mmengine - INFO - Epoch(train) [36][250/586] lr: 5.000000e-03 eta: 13:56:49 time: 0.554298 data_time: 0.064435 memory: 8713 loss_kpt: 244.512148 acc_pose: 0.772812 loss: 244.512148 2022/10/12 14:09:48 - mmengine - INFO - Epoch(train) [36][300/586] lr: 5.000000e-03 eta: 13:56:39 time: 0.549284 data_time: 0.067037 memory: 8713 loss_kpt: 242.817034 acc_pose: 0.787420 loss: 242.817034 2022/10/12 14:10:14 - mmengine - INFO - Epoch(train) [36][350/586] lr: 5.000000e-03 eta: 13:56:25 time: 0.533333 data_time: 0.067052 memory: 8713 loss_kpt: 240.927929 acc_pose: 0.713723 loss: 240.927929 2022/10/12 14:10:41 - mmengine - INFO - Epoch(train) [36][400/586] lr: 5.000000e-03 eta: 13:56:10 time: 0.530663 data_time: 0.058299 memory: 8713 loss_kpt: 246.805509 acc_pose: 0.772599 loss: 246.805509 2022/10/12 14:11:07 - mmengine - INFO - Epoch(train) [36][450/586] lr: 5.000000e-03 eta: 13:55:54 time: 0.527079 data_time: 0.060869 memory: 8713 loss_kpt: 240.633412 acc_pose: 0.729450 loss: 240.633412 2022/10/12 14:11:29 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:11:34 - mmengine - INFO - Epoch(train) [36][500/586] lr: 5.000000e-03 eta: 13:55:40 time: 0.533905 data_time: 0.068339 memory: 8713 loss_kpt: 236.179116 acc_pose: 0.822128 loss: 236.179116 2022/10/12 14:12:00 - mmengine - INFO - Epoch(train) [36][550/586] lr: 5.000000e-03 eta: 13:55:24 time: 0.527757 data_time: 0.064109 memory: 8713 loss_kpt: 239.246234 acc_pose: 0.847180 loss: 239.246234 2022/10/12 14:12:19 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:12:46 - mmengine - INFO - Epoch(train) [37][50/586] lr: 5.000000e-03 eta: 13:53:30 time: 0.544369 data_time: 0.076607 memory: 8713 loss_kpt: 238.270654 acc_pose: 0.764664 loss: 238.270654 2022/10/12 14:13:12 - mmengine - INFO - Epoch(train) [37][100/586] lr: 5.000000e-03 eta: 13:53:13 time: 0.525597 data_time: 0.059386 memory: 8713 loss_kpt: 239.373225 acc_pose: 0.781263 loss: 239.373225 2022/10/12 14:13:39 - mmengine - INFO - Epoch(train) [37][150/586] lr: 5.000000e-03 eta: 13:53:01 time: 0.539578 data_time: 0.064665 memory: 8713 loss_kpt: 240.316169 acc_pose: 0.758104 loss: 240.316169 2022/10/12 14:14:07 - mmengine - INFO - Epoch(train) [37][200/586] lr: 5.000000e-03 eta: 13:52:51 time: 0.552835 data_time: 0.059268 memory: 8713 loss_kpt: 238.089684 acc_pose: 0.716196 loss: 238.089684 2022/10/12 14:14:34 - mmengine - INFO - Epoch(train) [37][250/586] lr: 5.000000e-03 eta: 13:52:38 time: 0.539977 data_time: 0.059519 memory: 8713 loss_kpt: 241.376719 acc_pose: 0.699077 loss: 241.376719 2022/10/12 14:15:01 - mmengine - INFO - Epoch(train) [37][300/586] lr: 5.000000e-03 eta: 13:52:27 time: 0.548242 data_time: 0.060337 memory: 8713 loss_kpt: 244.884459 acc_pose: 0.812404 loss: 244.884459 2022/10/12 14:15:28 - mmengine - INFO - Epoch(train) [37][350/586] lr: 5.000000e-03 eta: 13:52:11 time: 0.529266 data_time: 0.059671 memory: 8713 loss_kpt: 237.076970 acc_pose: 0.723393 loss: 237.076970 2022/10/12 14:15:55 - mmengine - INFO - Epoch(train) [37][400/586] lr: 5.000000e-03 eta: 13:52:01 time: 0.550710 data_time: 0.058687 memory: 8713 loss_kpt: 237.951690 acc_pose: 0.786884 loss: 237.951690 2022/10/12 14:16:22 - mmengine - INFO - Epoch(train) [37][450/586] lr: 5.000000e-03 eta: 13:51:48 time: 0.541023 data_time: 0.058731 memory: 8713 loss_kpt: 239.988441 acc_pose: 0.728627 loss: 239.988441 2022/10/12 14:16:51 - mmengine - INFO - Epoch(train) [37][500/586] lr: 5.000000e-03 eta: 13:51:41 time: 0.568286 data_time: 0.064250 memory: 8713 loss_kpt: 243.504140 acc_pose: 0.822744 loss: 243.504140 2022/10/12 14:17:18 - mmengine - INFO - Epoch(train) [37][550/586] lr: 5.000000e-03 eta: 13:51:29 time: 0.545316 data_time: 0.059043 memory: 8713 loss_kpt: 237.850778 acc_pose: 0.706837 loss: 237.850778 2022/10/12 14:17:37 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:18:04 - mmengine - INFO - Epoch(train) [38][50/586] lr: 5.000000e-03 eta: 13:49:34 time: 0.534850 data_time: 0.075201 memory: 8713 loss_kpt: 233.635050 acc_pose: 0.772786 loss: 233.635050 2022/10/12 14:18:30 - mmengine - INFO - Epoch(train) [38][100/586] lr: 5.000000e-03 eta: 13:49:17 time: 0.521215 data_time: 0.064790 memory: 8713 loss_kpt: 241.316506 acc_pose: 0.758205 loss: 241.316506 2022/10/12 14:18:56 - mmengine - INFO - Epoch(train) [38][150/586] lr: 5.000000e-03 eta: 13:48:58 time: 0.516954 data_time: 0.060251 memory: 8713 loss_kpt: 244.414482 acc_pose: 0.682893 loss: 244.414482 2022/10/12 14:19:22 - mmengine - INFO - Epoch(train) [38][200/586] lr: 5.000000e-03 eta: 13:48:40 time: 0.518170 data_time: 0.061177 memory: 8713 loss_kpt: 237.807417 acc_pose: 0.667867 loss: 237.807417 2022/10/12 14:19:47 - mmengine - INFO - Epoch(train) [38][250/586] lr: 5.000000e-03 eta: 13:48:19 time: 0.507381 data_time: 0.064566 memory: 8713 loss_kpt: 241.939889 acc_pose: 0.805455 loss: 241.939889 2022/10/12 14:20:13 - mmengine - INFO - Epoch(train) [38][300/586] lr: 5.000000e-03 eta: 13:47:58 time: 0.507566 data_time: 0.059929 memory: 8713 loss_kpt: 238.240777 acc_pose: 0.765878 loss: 238.240777 2022/10/12 14:20:22 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:20:38 - mmengine - INFO - Epoch(train) [38][350/586] lr: 5.000000e-03 eta: 13:47:39 time: 0.517285 data_time: 0.060118 memory: 8713 loss_kpt: 237.095143 acc_pose: 0.811036 loss: 237.095143 2022/10/12 14:21:05 - mmengine - INFO - Epoch(train) [38][400/586] lr: 5.000000e-03 eta: 13:47:21 time: 0.520494 data_time: 0.067345 memory: 8713 loss_kpt: 241.484171 acc_pose: 0.801832 loss: 241.484171 2022/10/12 14:21:30 - mmengine - INFO - Epoch(train) [38][450/586] lr: 5.000000e-03 eta: 13:47:01 time: 0.511874 data_time: 0.061745 memory: 8713 loss_kpt: 234.735711 acc_pose: 0.789246 loss: 234.735711 2022/10/12 14:21:56 - mmengine - INFO - Epoch(train) [38][500/586] lr: 5.000000e-03 eta: 13:46:42 time: 0.514440 data_time: 0.060266 memory: 8713 loss_kpt: 238.043531 acc_pose: 0.804089 loss: 238.043531 2022/10/12 14:22:22 - mmengine - INFO - Epoch(train) [38][550/586] lr: 5.000000e-03 eta: 13:46:23 time: 0.515480 data_time: 0.061443 memory: 8713 loss_kpt: 238.993162 acc_pose: 0.786073 loss: 238.993162 2022/10/12 14:22:40 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:23:07 - mmengine - INFO - Epoch(train) [39][50/586] lr: 5.000000e-03 eta: 13:44:31 time: 0.536463 data_time: 0.074329 memory: 8713 loss_kpt: 237.006334 acc_pose: 0.805514 loss: 237.006334 2022/10/12 14:23:34 - mmengine - INFO - Epoch(train) [39][100/586] lr: 5.000000e-03 eta: 13:44:18 time: 0.542123 data_time: 0.062285 memory: 8713 loss_kpt: 238.357104 acc_pose: 0.784837 loss: 238.357104 2022/10/12 14:24:01 - mmengine - INFO - Epoch(train) [39][150/586] lr: 5.000000e-03 eta: 13:44:08 time: 0.555703 data_time: 0.063095 memory: 8713 loss_kpt: 234.191950 acc_pose: 0.748254 loss: 234.191950 2022/10/12 14:24:29 - mmengine - INFO - Epoch(train) [39][200/586] lr: 5.000000e-03 eta: 13:43:56 time: 0.547144 data_time: 0.061634 memory: 8713 loss_kpt: 240.905650 acc_pose: 0.815776 loss: 240.905650 2022/10/12 14:24:56 - mmengine - INFO - Epoch(train) [39][250/586] lr: 5.000000e-03 eta: 13:43:43 time: 0.545767 data_time: 0.065966 memory: 8713 loss_kpt: 236.007094 acc_pose: 0.717108 loss: 236.007094 2022/10/12 14:25:23 - mmengine - INFO - Epoch(train) [39][300/586] lr: 5.000000e-03 eta: 13:43:28 time: 0.535163 data_time: 0.057930 memory: 8713 loss_kpt: 240.553939 acc_pose: 0.790407 loss: 240.553939 2022/10/12 14:25:49 - mmengine - INFO - Epoch(train) [39][350/586] lr: 5.000000e-03 eta: 13:43:11 time: 0.523861 data_time: 0.066202 memory: 8713 loss_kpt: 234.658160 acc_pose: 0.759473 loss: 234.658160 2022/10/12 14:26:15 - mmengine - INFO - Epoch(train) [39][400/586] lr: 5.000000e-03 eta: 13:42:54 time: 0.526942 data_time: 0.058474 memory: 8713 loss_kpt: 237.587643 acc_pose: 0.798646 loss: 237.587643 2022/10/12 14:26:42 - mmengine - INFO - Epoch(train) [39][450/586] lr: 5.000000e-03 eta: 13:42:37 time: 0.527253 data_time: 0.064236 memory: 8713 loss_kpt: 237.741629 acc_pose: 0.786435 loss: 237.741629 2022/10/12 14:27:09 - mmengine - INFO - Epoch(train) [39][500/586] lr: 5.000000e-03 eta: 13:42:23 time: 0.540198 data_time: 0.071393 memory: 8713 loss_kpt: 238.657397 acc_pose: 0.724216 loss: 238.657397 2022/10/12 14:27:36 - mmengine - INFO - Epoch(train) [39][550/586] lr: 5.000000e-03 eta: 13:42:09 time: 0.539672 data_time: 0.061368 memory: 8713 loss_kpt: 235.663663 acc_pose: 0.782403 loss: 235.663663 2022/10/12 14:27:54 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:28:21 - mmengine - INFO - Epoch(train) [40][50/586] lr: 5.000000e-03 eta: 13:40:22 time: 0.547716 data_time: 0.072839 memory: 8713 loss_kpt: 238.454072 acc_pose: 0.789389 loss: 238.454072 2022/10/12 14:28:48 - mmengine - INFO - Epoch(train) [40][100/586] lr: 5.000000e-03 eta: 13:40:06 time: 0.533414 data_time: 0.063029 memory: 8713 loss_kpt: 238.667502 acc_pose: 0.783314 loss: 238.667502 2022/10/12 14:29:12 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:29:14 - mmengine - INFO - Epoch(train) [40][150/586] lr: 5.000000e-03 eta: 13:39:50 time: 0.531067 data_time: 0.063910 memory: 8713 loss_kpt: 231.601943 acc_pose: 0.689101 loss: 231.601943 2022/10/12 14:29:40 - mmengine - INFO - Epoch(train) [40][200/586] lr: 5.000000e-03 eta: 13:39:28 time: 0.504809 data_time: 0.060486 memory: 8713 loss_kpt: 238.165904 acc_pose: 0.723434 loss: 238.165904 2022/10/12 14:30:07 - mmengine - INFO - Epoch(train) [40][250/586] lr: 5.000000e-03 eta: 13:39:14 time: 0.540524 data_time: 0.064300 memory: 8713 loss_kpt: 236.892702 acc_pose: 0.780310 loss: 236.892702 2022/10/12 14:30:32 - mmengine - INFO - Epoch(train) [40][300/586] lr: 5.000000e-03 eta: 13:38:54 time: 0.512846 data_time: 0.059873 memory: 8713 loss_kpt: 238.203401 acc_pose: 0.798879 loss: 238.203401 2022/10/12 14:30:59 - mmengine - INFO - Epoch(train) [40][350/586] lr: 5.000000e-03 eta: 13:38:40 time: 0.539202 data_time: 0.063255 memory: 8713 loss_kpt: 237.084400 acc_pose: 0.804856 loss: 237.084400 2022/10/12 14:31:26 - mmengine - INFO - Epoch(train) [40][400/586] lr: 5.000000e-03 eta: 13:38:24 time: 0.533257 data_time: 0.057959 memory: 8713 loss_kpt: 236.194796 acc_pose: 0.694909 loss: 236.194796 2022/10/12 14:31:53 - mmengine - INFO - Epoch(train) [40][450/586] lr: 5.000000e-03 eta: 13:38:12 time: 0.547727 data_time: 0.061284 memory: 8713 loss_kpt: 243.776910 acc_pose: 0.738696 loss: 243.776910 2022/10/12 14:32:20 - mmengine - INFO - Epoch(train) [40][500/586] lr: 5.000000e-03 eta: 13:37:55 time: 0.531775 data_time: 0.059856 memory: 8713 loss_kpt: 236.762213 acc_pose: 0.773672 loss: 236.762213 2022/10/12 14:32:47 - mmengine - INFO - Epoch(train) [40][550/586] lr: 5.000000e-03 eta: 13:37:39 time: 0.531415 data_time: 0.069042 memory: 8713 loss_kpt: 236.571846 acc_pose: 0.674625 loss: 236.571846 2022/10/12 14:33:05 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:33:06 - mmengine - INFO - Saving checkpoint at 40 epochs 2022/10/12 14:33:19 - mmengine - INFO - Epoch(val) [40][50/407] eta: 0:01:10 time: 0.198708 data_time: 0.012620 memory: 8713 2022/10/12 14:33:28 - mmengine - INFO - Epoch(val) [40][100/407] eta: 0:00:58 time: 0.190900 data_time: 0.007522 memory: 1759 2022/10/12 14:33:38 - mmengine - INFO - Epoch(val) [40][150/407] eta: 0:00:49 time: 0.190940 data_time: 0.007832 memory: 1759 2022/10/12 14:33:48 - mmengine - INFO - Epoch(val) [40][200/407] eta: 0:00:39 time: 0.192818 data_time: 0.007513 memory: 1759 2022/10/12 14:33:57 - mmengine - INFO - Epoch(val) [40][250/407] eta: 0:00:30 time: 0.191272 data_time: 0.007614 memory: 1759 2022/10/12 14:34:07 - mmengine - INFO - Epoch(val) [40][300/407] eta: 0:00:20 time: 0.191212 data_time: 0.008119 memory: 1759 2022/10/12 14:34:16 - mmengine - INFO - Epoch(val) [40][350/407] eta: 0:00:10 time: 0.192756 data_time: 0.007531 memory: 1759 2022/10/12 14:34:26 - mmengine - INFO - Epoch(val) [40][400/407] eta: 0:00:01 time: 0.196761 data_time: 0.007738 memory: 1759 2022/10/12 14:34:40 - mmengine - INFO - Evaluating CocoMetric... 2022/10/12 14:34:56 - mmengine - INFO - Epoch(val) [40][407/407] coco/AP: 0.662508 coco/AP .5: 0.868392 coco/AP .75: 0.738681 coco/AP (M): 0.636724 coco/AP (L): 0.714537 coco/AR: 0.734871 coco/AR .5: 0.915145 coco/AR .75: 0.798646 coco/AR (M): 0.695247 coco/AR (L): 0.789483 2022/10/12 14:34:56 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/liqikai/openmmlab/pt112cu113py38/mmpose/work_dirs/20221012/rsn2x/best_coco/AP_epoch_30.pth is removed 2022/10/12 14:34:59 - mmengine - INFO - The best checkpoint with 0.6625 coco/AP at 40 epoch is saved to best_coco/AP_epoch_40.pth. 2022/10/12 14:35:25 - mmengine - INFO - Epoch(train) [41][50/586] lr: 5.000000e-03 eta: 13:35:49 time: 0.525187 data_time: 0.070943 memory: 8713 loss_kpt: 233.942005 acc_pose: 0.817670 loss: 233.942005 2022/10/12 14:35:51 - mmengine - INFO - Epoch(train) [41][100/586] lr: 5.000000e-03 eta: 13:35:28 time: 0.510109 data_time: 0.061051 memory: 8713 loss_kpt: 231.541255 acc_pose: 0.810905 loss: 231.541255 2022/10/12 14:36:17 - mmengine - INFO - Epoch(train) [41][150/586] lr: 5.000000e-03 eta: 13:35:11 time: 0.526093 data_time: 0.059576 memory: 8713 loss_kpt: 230.219086 acc_pose: 0.765955 loss: 230.219086 2022/10/12 14:36:44 - mmengine - INFO - Epoch(train) [41][200/586] lr: 5.000000e-03 eta: 13:34:55 time: 0.536187 data_time: 0.055971 memory: 8713 loss_kpt: 240.391435 acc_pose: 0.799425 loss: 240.391435 2022/10/12 14:37:10 - mmengine - INFO - Epoch(train) [41][250/586] lr: 5.000000e-03 eta: 13:34:39 time: 0.532046 data_time: 0.059835 memory: 8713 loss_kpt: 238.518478 acc_pose: 0.793248 loss: 238.518478 2022/10/12 14:37:36 - mmengine - INFO - Epoch(train) [41][300/586] lr: 5.000000e-03 eta: 13:34:18 time: 0.509224 data_time: 0.058039 memory: 8713 loss_kpt: 234.566535 acc_pose: 0.728523 loss: 234.566535 2022/10/12 14:38:02 - mmengine - INFO - Epoch(train) [41][350/586] lr: 5.000000e-03 eta: 13:34:02 time: 0.532938 data_time: 0.063142 memory: 8713 loss_kpt: 238.111681 acc_pose: 0.774057 loss: 238.111681 2022/10/12 14:38:29 - mmengine - INFO - Epoch(train) [41][400/586] lr: 5.000000e-03 eta: 13:33:44 time: 0.521387 data_time: 0.056228 memory: 8713 loss_kpt: 237.294454 acc_pose: 0.769925 loss: 237.294454 2022/10/12 14:38:55 - mmengine - INFO - Epoch(train) [41][450/586] lr: 5.000000e-03 eta: 13:33:28 time: 0.533157 data_time: 0.057508 memory: 8713 loss_kpt: 234.963447 acc_pose: 0.729090 loss: 234.963447 2022/10/12 14:39:22 - mmengine - INFO - Epoch(train) [41][500/586] lr: 5.000000e-03 eta: 13:33:10 time: 0.527747 data_time: 0.052706 memory: 8713 loss_kpt: 239.332951 acc_pose: 0.767870 loss: 239.332951 2022/10/12 14:39:49 - mmengine - INFO - Epoch(train) [41][550/586] lr: 5.000000e-03 eta: 13:32:57 time: 0.547399 data_time: 0.068130 memory: 8713 loss_kpt: 237.570508 acc_pose: 0.828654 loss: 237.570508 2022/10/12 14:39:54 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:40:08 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:40:35 - mmengine - INFO - Epoch(train) [42][50/586] lr: 5.000000e-03 eta: 13:31:11 time: 0.533991 data_time: 0.074002 memory: 8713 loss_kpt: 240.128212 acc_pose: 0.707503 loss: 240.128212 2022/10/12 14:41:01 - mmengine - INFO - Epoch(train) [42][100/586] lr: 5.000000e-03 eta: 13:30:52 time: 0.519226 data_time: 0.053656 memory: 8713 loss_kpt: 239.650239 acc_pose: 0.703660 loss: 239.650239 2022/10/12 14:41:27 - mmengine - INFO - Epoch(train) [42][150/586] lr: 5.000000e-03 eta: 13:30:34 time: 0.525263 data_time: 0.059160 memory: 8713 loss_kpt: 239.724616 acc_pose: 0.711529 loss: 239.724616 2022/10/12 14:41:53 - mmengine - INFO - Epoch(train) [42][200/586] lr: 5.000000e-03 eta: 13:30:17 time: 0.527766 data_time: 0.055018 memory: 8713 loss_kpt: 239.432473 acc_pose: 0.720837 loss: 239.432473 2022/10/12 14:42:20 - mmengine - INFO - Epoch(train) [42][250/586] lr: 5.000000e-03 eta: 13:30:02 time: 0.540867 data_time: 0.054832 memory: 8713 loss_kpt: 235.942098 acc_pose: 0.822365 loss: 235.942098 2022/10/12 14:42:47 - mmengine - INFO - Epoch(train) [42][300/586] lr: 5.000000e-03 eta: 13:29:45 time: 0.529481 data_time: 0.062002 memory: 8713 loss_kpt: 237.261001 acc_pose: 0.788819 loss: 237.261001 2022/10/12 14:43:15 - mmengine - INFO - Epoch(train) [42][350/586] lr: 5.000000e-03 eta: 13:29:33 time: 0.555558 data_time: 0.059037 memory: 8713 loss_kpt: 231.438342 acc_pose: 0.757400 loss: 231.438342 2022/10/12 14:43:42 - mmengine - INFO - Epoch(train) [42][400/586] lr: 5.000000e-03 eta: 13:29:18 time: 0.539995 data_time: 0.058432 memory: 8713 loss_kpt: 237.180092 acc_pose: 0.796407 loss: 237.180092 2022/10/12 14:44:09 - mmengine - INFO - Epoch(train) [42][450/586] lr: 5.000000e-03 eta: 13:29:03 time: 0.538163 data_time: 0.055773 memory: 8713 loss_kpt: 239.341873 acc_pose: 0.866288 loss: 239.341873 2022/10/12 14:44:35 - mmengine - INFO - Epoch(train) [42][500/586] lr: 5.000000e-03 eta: 13:28:45 time: 0.525190 data_time: 0.057904 memory: 8713 loss_kpt: 234.977323 acc_pose: 0.793110 loss: 234.977323 2022/10/12 14:45:01 - mmengine - INFO - Epoch(train) [42][550/586] lr: 5.000000e-03 eta: 13:28:27 time: 0.527160 data_time: 0.061304 memory: 8713 loss_kpt: 234.386396 acc_pose: 0.800635 loss: 234.386396 2022/10/12 14:45:20 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:45:47 - mmengine - INFO - Epoch(train) [43][50/586] lr: 5.000000e-03 eta: 13:26:43 time: 0.536708 data_time: 0.068590 memory: 8713 loss_kpt: 236.297317 acc_pose: 0.756962 loss: 236.297317 2022/10/12 14:46:14 - mmengine - INFO - Epoch(train) [43][100/586] lr: 5.000000e-03 eta: 13:26:28 time: 0.538806 data_time: 0.058311 memory: 8713 loss_kpt: 232.161272 acc_pose: 0.810292 loss: 232.161272 2022/10/12 14:46:40 - mmengine - INFO - Epoch(train) [43][150/586] lr: 5.000000e-03 eta: 13:26:10 time: 0.528282 data_time: 0.056080 memory: 8713 loss_kpt: 238.512733 acc_pose: 0.684181 loss: 238.512733 2022/10/12 14:47:06 - mmengine - INFO - Epoch(train) [43][200/586] lr: 5.000000e-03 eta: 13:25:50 time: 0.513247 data_time: 0.058755 memory: 8713 loss_kpt: 236.258375 acc_pose: 0.740319 loss: 236.258375 2022/10/12 14:47:32 - mmengine - INFO - Epoch(train) [43][250/586] lr: 5.000000e-03 eta: 13:25:33 time: 0.529591 data_time: 0.061678 memory: 8713 loss_kpt: 231.026551 acc_pose: 0.751785 loss: 231.026551 2022/10/12 14:47:58 - mmengine - INFO - Epoch(train) [43][300/586] lr: 5.000000e-03 eta: 13:25:12 time: 0.514469 data_time: 0.056415 memory: 8713 loss_kpt: 235.986337 acc_pose: 0.819154 loss: 235.986337 2022/10/12 14:48:24 - mmengine - INFO - Epoch(train) [43][350/586] lr: 5.000000e-03 eta: 13:24:53 time: 0.517929 data_time: 0.060774 memory: 8713 loss_kpt: 234.171164 acc_pose: 0.673209 loss: 234.171164 2022/10/12 14:48:44 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:48:50 - mmengine - INFO - Epoch(train) [43][400/586] lr: 5.000000e-03 eta: 13:24:32 time: 0.511475 data_time: 0.057428 memory: 8713 loss_kpt: 235.437199 acc_pose: 0.730265 loss: 235.437199 2022/10/12 14:49:15 - mmengine - INFO - Epoch(train) [43][450/586] lr: 5.000000e-03 eta: 13:24:12 time: 0.513701 data_time: 0.055465 memory: 8713 loss_kpt: 232.955431 acc_pose: 0.828513 loss: 232.955431 2022/10/12 14:49:42 - mmengine - INFO - Epoch(train) [43][500/586] lr: 5.000000e-03 eta: 13:23:54 time: 0.527443 data_time: 0.060252 memory: 8713 loss_kpt: 235.537169 acc_pose: 0.706168 loss: 235.537169 2022/10/12 14:50:07 - mmengine - INFO - Epoch(train) [43][550/586] lr: 5.000000e-03 eta: 13:23:32 time: 0.506491 data_time: 0.055087 memory: 8713 loss_kpt: 235.515818 acc_pose: 0.697410 loss: 235.515818 2022/10/12 14:50:25 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:50:52 - mmengine - INFO - Epoch(train) [44][50/586] lr: 5.000000e-03 eta: 13:21:47 time: 0.526526 data_time: 0.068258 memory: 8713 loss_kpt: 233.981625 acc_pose: 0.736286 loss: 233.981625 2022/10/12 14:51:18 - mmengine - INFO - Epoch(train) [44][100/586] lr: 5.000000e-03 eta: 13:21:29 time: 0.524393 data_time: 0.057554 memory: 8713 loss_kpt: 234.429810 acc_pose: 0.748532 loss: 234.429810 2022/10/12 14:51:44 - mmengine - INFO - Epoch(train) [44][150/586] lr: 5.000000e-03 eta: 13:21:11 time: 0.523119 data_time: 0.061520 memory: 8713 loss_kpt: 236.043969 acc_pose: 0.750040 loss: 236.043969 2022/10/12 14:52:11 - mmengine - INFO - Epoch(train) [44][200/586] lr: 5.000000e-03 eta: 13:20:54 time: 0.534954 data_time: 0.061206 memory: 8713 loss_kpt: 238.997379 acc_pose: 0.672707 loss: 238.997379 2022/10/12 14:52:37 - mmengine - INFO - Epoch(train) [44][250/586] lr: 5.000000e-03 eta: 13:20:37 time: 0.529186 data_time: 0.060855 memory: 8713 loss_kpt: 231.438477 acc_pose: 0.795598 loss: 231.438477 2022/10/12 14:53:04 - mmengine - INFO - Epoch(train) [44][300/586] lr: 5.000000e-03 eta: 13:20:19 time: 0.528044 data_time: 0.065012 memory: 8713 loss_kpt: 234.438228 acc_pose: 0.767275 loss: 234.438228 2022/10/12 14:53:30 - mmengine - INFO - Epoch(train) [44][350/586] lr: 5.000000e-03 eta: 13:20:01 time: 0.528512 data_time: 0.057772 memory: 8713 loss_kpt: 237.072718 acc_pose: 0.709388 loss: 237.072718 2022/10/12 14:53:57 - mmengine - INFO - Epoch(train) [44][400/586] lr: 5.000000e-03 eta: 13:19:45 time: 0.533896 data_time: 0.059514 memory: 8713 loss_kpt: 231.507809 acc_pose: 0.784191 loss: 231.507809 2022/10/12 14:54:23 - mmengine - INFO - Epoch(train) [44][450/586] lr: 5.000000e-03 eta: 13:19:26 time: 0.525610 data_time: 0.060506 memory: 8713 loss_kpt: 231.756253 acc_pose: 0.771980 loss: 231.756253 2022/10/12 14:54:50 - mmengine - INFO - Epoch(train) [44][500/586] lr: 5.000000e-03 eta: 13:19:09 time: 0.528626 data_time: 0.062292 memory: 8713 loss_kpt: 234.038195 acc_pose: 0.671151 loss: 234.038195 2022/10/12 14:55:17 - mmengine - INFO - Epoch(train) [44][550/586] lr: 5.000000e-03 eta: 13:18:53 time: 0.539337 data_time: 0.061309 memory: 8713 loss_kpt: 230.632358 acc_pose: 0.749193 loss: 230.632358 2022/10/12 14:55:35 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:56:02 - mmengine - INFO - Epoch(train) [45][50/586] lr: 5.000000e-03 eta: 13:17:13 time: 0.539332 data_time: 0.073344 memory: 8713 loss_kpt: 236.650624 acc_pose: 0.798016 loss: 236.650624 2022/10/12 14:56:29 - mmengine - INFO - Epoch(train) [45][100/586] lr: 5.000000e-03 eta: 13:16:58 time: 0.543473 data_time: 0.060899 memory: 8713 loss_kpt: 235.781265 acc_pose: 0.764207 loss: 235.781265 2022/10/12 14:56:55 - mmengine - INFO - Epoch(train) [45][150/586] lr: 5.000000e-03 eta: 13:16:39 time: 0.521815 data_time: 0.059568 memory: 8713 loss_kpt: 231.552760 acc_pose: 0.794035 loss: 231.552760 2022/10/12 14:57:22 - mmengine - INFO - Epoch(train) [45][200/586] lr: 5.000000e-03 eta: 13:16:20 time: 0.525749 data_time: 0.057633 memory: 8713 loss_kpt: 235.390305 acc_pose: 0.772213 loss: 235.390305 2022/10/12 14:57:30 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:57:48 - mmengine - INFO - Epoch(train) [45][250/586] lr: 5.000000e-03 eta: 13:16:03 time: 0.529446 data_time: 0.062188 memory: 8713 loss_kpt: 236.981147 acc_pose: 0.803458 loss: 236.981147 2022/10/12 14:58:14 - mmengine - INFO - Epoch(train) [45][300/586] lr: 5.000000e-03 eta: 13:15:44 time: 0.522219 data_time: 0.058567 memory: 8713 loss_kpt: 234.755431 acc_pose: 0.750312 loss: 234.755431 2022/10/12 14:58:40 - mmengine - INFO - Epoch(train) [45][350/586] lr: 5.000000e-03 eta: 13:15:24 time: 0.520987 data_time: 0.061354 memory: 8713 loss_kpt: 236.491725 acc_pose: 0.775808 loss: 236.491725 2022/10/12 14:59:06 - mmengine - INFO - Epoch(train) [45][400/586] lr: 5.000000e-03 eta: 13:15:05 time: 0.522754 data_time: 0.057510 memory: 8713 loss_kpt: 235.346001 acc_pose: 0.783064 loss: 235.346001 2022/10/12 14:59:33 - mmengine - INFO - Epoch(train) [45][450/586] lr: 5.000000e-03 eta: 13:14:47 time: 0.526072 data_time: 0.060398 memory: 8713 loss_kpt: 231.672080 acc_pose: 0.823902 loss: 231.672080 2022/10/12 14:59:59 - mmengine - INFO - Epoch(train) [45][500/586] lr: 5.000000e-03 eta: 13:14:28 time: 0.521997 data_time: 0.057300 memory: 8713 loss_kpt: 235.224756 acc_pose: 0.787111 loss: 235.224756 2022/10/12 15:00:24 - mmengine - INFO - Epoch(train) [45][550/586] lr: 5.000000e-03 eta: 13:14:06 time: 0.506550 data_time: 0.060162 memory: 8713 loss_kpt: 228.855822 acc_pose: 0.765995 loss: 228.855822 2022/10/12 15:00:42 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:01:09 - mmengine - INFO - Epoch(train) [46][50/586] lr: 5.000000e-03 eta: 13:12:27 time: 0.538851 data_time: 0.072323 memory: 8713 loss_kpt: 230.442993 acc_pose: 0.794357 loss: 230.442993 2022/10/12 15:01:36 - mmengine - INFO - Epoch(train) [46][100/586] lr: 5.000000e-03 eta: 13:12:09 time: 0.529304 data_time: 0.062320 memory: 8713 loss_kpt: 240.494966 acc_pose: 0.767045 loss: 240.494966 2022/10/12 15:02:02 - mmengine - INFO - Epoch(train) [46][150/586] lr: 5.000000e-03 eta: 13:11:50 time: 0.520781 data_time: 0.062186 memory: 8713 loss_kpt: 231.809636 acc_pose: 0.777284 loss: 231.809636 2022/10/12 15:02:27 - mmengine - INFO - Epoch(train) [46][200/586] lr: 5.000000e-03 eta: 13:11:28 time: 0.508928 data_time: 0.053200 memory: 8713 loss_kpt: 229.614120 acc_pose: 0.803324 loss: 229.614120 2022/10/12 15:02:53 - mmengine - INFO - Epoch(train) [46][250/586] lr: 5.000000e-03 eta: 13:11:07 time: 0.514277 data_time: 0.064128 memory: 8713 loss_kpt: 233.509667 acc_pose: 0.785567 loss: 233.509667 2022/10/12 15:03:19 - mmengine - INFO - Epoch(train) [46][300/586] lr: 5.000000e-03 eta: 13:10:47 time: 0.512886 data_time: 0.058111 memory: 8713 loss_kpt: 234.488925 acc_pose: 0.745194 loss: 234.488925 2022/10/12 15:03:45 - mmengine - INFO - Epoch(train) [46][350/586] lr: 5.000000e-03 eta: 13:10:27 time: 0.522988 data_time: 0.056993 memory: 8713 loss_kpt: 229.966488 acc_pose: 0.721581 loss: 229.966488 2022/10/12 15:04:10 - mmengine - INFO - Epoch(train) [46][400/586] lr: 5.000000e-03 eta: 13:10:06 time: 0.510818 data_time: 0.054425 memory: 8713 loss_kpt: 234.367107 acc_pose: 0.758167 loss: 234.367107 2022/10/12 15:04:36 - mmengine - INFO - Epoch(train) [46][450/586] lr: 5.000000e-03 eta: 13:09:45 time: 0.513664 data_time: 0.061404 memory: 8713 loss_kpt: 235.268922 acc_pose: 0.808161 loss: 235.268922 2022/10/12 15:05:01 - mmengine - INFO - Epoch(train) [46][500/586] lr: 5.000000e-03 eta: 13:09:23 time: 0.503438 data_time: 0.053873 memory: 8713 loss_kpt: 232.877537 acc_pose: 0.740841 loss: 232.877537 2022/10/12 15:05:27 - mmengine - INFO - Epoch(train) [46][550/586] lr: 5.000000e-03 eta: 13:09:02 time: 0.511276 data_time: 0.064252 memory: 8713 loss_kpt: 232.431070 acc_pose: 0.776677 loss: 232.431070 2022/10/12 15:05:45 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:06:08 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:06:11 - mmengine - INFO - Epoch(train) [47][50/586] lr: 5.000000e-03 eta: 13:07:22 time: 0.527735 data_time: 0.065170 memory: 8713 loss_kpt: 235.164182 acc_pose: 0.793254 loss: 235.164182 2022/10/12 15:06:37 - mmengine - INFO - Epoch(train) [47][100/586] lr: 5.000000e-03 eta: 13:07:05 time: 0.529537 data_time: 0.062879 memory: 8713 loss_kpt: 231.869808 acc_pose: 0.752448 loss: 231.869808 2022/10/12 15:07:03 - mmengine - INFO - Epoch(train) [47][150/586] lr: 5.000000e-03 eta: 13:06:45 time: 0.520218 data_time: 0.058846 memory: 8713 loss_kpt: 227.811110 acc_pose: 0.857929 loss: 227.811110 2022/10/12 15:07:30 - mmengine - INFO - Epoch(train) [47][200/586] lr: 5.000000e-03 eta: 13:06:25 time: 0.521050 data_time: 0.059404 memory: 8713 loss_kpt: 231.899661 acc_pose: 0.784785 loss: 231.899661 2022/10/12 15:07:56 - mmengine - INFO - Epoch(train) [47][250/586] lr: 5.000000e-03 eta: 13:06:06 time: 0.522765 data_time: 0.055359 memory: 8713 loss_kpt: 234.426194 acc_pose: 0.846773 loss: 234.426194 2022/10/12 15:08:21 - mmengine - INFO - Epoch(train) [47][300/586] lr: 5.000000e-03 eta: 13:05:45 time: 0.510634 data_time: 0.057412 memory: 8713 loss_kpt: 234.426520 acc_pose: 0.781067 loss: 234.426520 2022/10/12 15:08:47 - mmengine - INFO - Epoch(train) [47][350/586] lr: 5.000000e-03 eta: 13:05:23 time: 0.507753 data_time: 0.059971 memory: 8713 loss_kpt: 232.593351 acc_pose: 0.744682 loss: 232.593351 2022/10/12 15:09:12 - mmengine - INFO - Epoch(train) [47][400/586] lr: 5.000000e-03 eta: 13:05:00 time: 0.498497 data_time: 0.054844 memory: 8713 loss_kpt: 229.547643 acc_pose: 0.799695 loss: 229.547643 2022/10/12 15:09:37 - mmengine - INFO - Epoch(train) [47][450/586] lr: 5.000000e-03 eta: 13:04:39 time: 0.513500 data_time: 0.061902 memory: 8713 loss_kpt: 229.679866 acc_pose: 0.847650 loss: 229.679866 2022/10/12 15:10:02 - mmengine - INFO - Epoch(train) [47][500/586] lr: 5.000000e-03 eta: 13:04:16 time: 0.503876 data_time: 0.053110 memory: 8713 loss_kpt: 231.615033 acc_pose: 0.793783 loss: 231.615033 2022/10/12 15:10:27 - mmengine - INFO - Epoch(train) [47][550/586] lr: 5.000000e-03 eta: 13:03:53 time: 0.501367 data_time: 0.058962 memory: 8713 loss_kpt: 232.621603 acc_pose: 0.812187 loss: 232.621603 2022/10/12 15:10:45 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:11:13 - mmengine - INFO - Epoch(train) [48][50/586] lr: 5.000000e-03 eta: 13:02:20 time: 0.550900 data_time: 0.072730 memory: 8713 loss_kpt: 231.747847 acc_pose: 0.785906 loss: 231.747847 2022/10/12 15:11:39 - mmengine - INFO - Epoch(train) [48][100/586] lr: 5.000000e-03 eta: 13:02:00 time: 0.518539 data_time: 0.065503 memory: 8713 loss_kpt: 226.880985 acc_pose: 0.783629 loss: 226.880985 2022/10/12 15:12:05 - mmengine - INFO - Epoch(train) [48][150/586] lr: 5.000000e-03 eta: 13:01:39 time: 0.512888 data_time: 0.061730 memory: 8713 loss_kpt: 225.678635 acc_pose: 0.779481 loss: 225.678635 2022/10/12 15:12:30 - mmengine - INFO - Epoch(train) [48][200/586] lr: 5.000000e-03 eta: 13:01:18 time: 0.516904 data_time: 0.056149 memory: 8713 loss_kpt: 230.951781 acc_pose: 0.727292 loss: 230.951781 2022/10/12 15:12:56 - mmengine - INFO - Epoch(train) [48][250/586] lr: 5.000000e-03 eta: 13:00:58 time: 0.517579 data_time: 0.059495 memory: 8713 loss_kpt: 234.375884 acc_pose: 0.747633 loss: 234.375884 2022/10/12 15:13:22 - mmengine - INFO - Epoch(train) [48][300/586] lr: 5.000000e-03 eta: 13:00:36 time: 0.506913 data_time: 0.056658 memory: 8713 loss_kpt: 230.863161 acc_pose: 0.839646 loss: 230.863161 2022/10/12 15:13:47 - mmengine - INFO - Epoch(train) [48][350/586] lr: 5.000000e-03 eta: 13:00:15 time: 0.510787 data_time: 0.061314 memory: 8713 loss_kpt: 230.939185 acc_pose: 0.754115 loss: 230.939185 2022/10/12 15:14:13 - mmengine - INFO - Epoch(train) [48][400/586] lr: 5.000000e-03 eta: 12:59:55 time: 0.520160 data_time: 0.058711 memory: 8713 loss_kpt: 231.090170 acc_pose: 0.779851 loss: 231.090170 2022/10/12 15:14:39 - mmengine - INFO - Epoch(train) [48][450/586] lr: 5.000000e-03 eta: 12:59:35 time: 0.520745 data_time: 0.058047 memory: 8713 loss_kpt: 232.391481 acc_pose: 0.805026 loss: 232.391481 2022/10/12 15:14:44 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:15:05 - mmengine - INFO - Epoch(train) [48][500/586] lr: 5.000000e-03 eta: 12:59:14 time: 0.510722 data_time: 0.055657 memory: 8713 loss_kpt: 229.848384 acc_pose: 0.775466 loss: 229.848384 2022/10/12 15:15:30 - mmengine - INFO - Epoch(train) [48][550/586] lr: 5.000000e-03 eta: 12:58:53 time: 0.510886 data_time: 0.065266 memory: 8713 loss_kpt: 228.359905 acc_pose: 0.799486 loss: 228.359905 2022/10/12 15:15:48 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:16:15 - mmengine - INFO - Epoch(train) [49][50/586] lr: 5.000000e-03 eta: 12:57:18 time: 0.535602 data_time: 0.068511 memory: 8713 loss_kpt: 229.139444 acc_pose: 0.799813 loss: 229.139444 2022/10/12 15:16:41 - mmengine - INFO - Epoch(train) [49][100/586] lr: 5.000000e-03 eta: 12:56:59 time: 0.523890 data_time: 0.055446 memory: 8713 loss_kpt: 225.830988 acc_pose: 0.825863 loss: 225.830988 2022/10/12 15:17:07 - mmengine - INFO - Epoch(train) [49][150/586] lr: 5.000000e-03 eta: 12:56:39 time: 0.519007 data_time: 0.060448 memory: 8713 loss_kpt: 228.566589 acc_pose: 0.847155 loss: 228.566589 2022/10/12 15:17:34 - mmengine - INFO - Epoch(train) [49][200/586] lr: 5.000000e-03 eta: 12:56:20 time: 0.525330 data_time: 0.058127 memory: 8713 loss_kpt: 225.681490 acc_pose: 0.718408 loss: 225.681490 2022/10/12 15:17:59 - mmengine - INFO - Epoch(train) [49][250/586] lr: 5.000000e-03 eta: 12:55:59 time: 0.514790 data_time: 0.063281 memory: 8713 loss_kpt: 233.372515 acc_pose: 0.696590 loss: 233.372515 2022/10/12 15:18:25 - mmengine - INFO - Epoch(train) [49][300/586] lr: 5.000000e-03 eta: 12:55:39 time: 0.517958 data_time: 0.056780 memory: 8713 loss_kpt: 230.827771 acc_pose: 0.774381 loss: 230.827771 2022/10/12 15:18:52 - mmengine - INFO - Epoch(train) [49][350/586] lr: 5.000000e-03 eta: 12:55:20 time: 0.527044 data_time: 0.058211 memory: 8713 loss_kpt: 225.704618 acc_pose: 0.711232 loss: 225.704618 2022/10/12 15:19:18 - mmengine - INFO - Epoch(train) [49][400/586] lr: 5.000000e-03 eta: 12:55:01 time: 0.525859 data_time: 0.054381 memory: 8713 loss_kpt: 227.917105 acc_pose: 0.782575 loss: 227.917105 2022/10/12 15:19:44 - mmengine - INFO - Epoch(train) [49][450/586] lr: 5.000000e-03 eta: 12:54:41 time: 0.518507 data_time: 0.061351 memory: 8713 loss_kpt: 228.733755 acc_pose: 0.765516 loss: 228.733755 2022/10/12 15:20:09 - mmengine - INFO - Epoch(train) [49][500/586] lr: 5.000000e-03 eta: 12:54:20 time: 0.513389 data_time: 0.058906 memory: 8713 loss_kpt: 228.130162 acc_pose: 0.832565 loss: 228.130162 2022/10/12 15:20:35 - mmengine - INFO - Epoch(train) [49][550/586] lr: 5.000000e-03 eta: 12:54:00 time: 0.518955 data_time: 0.059313 memory: 8713 loss_kpt: 229.676951 acc_pose: 0.772486 loss: 229.676951 2022/10/12 15:20:53 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:21:21 - mmengine - INFO - Epoch(train) [50][50/586] lr: 5.000000e-03 eta: 12:52:29 time: 0.549052 data_time: 0.069478 memory: 8713 loss_kpt: 223.937458 acc_pose: 0.772695 loss: 223.937458 2022/10/12 15:21:47 - mmengine - INFO - Epoch(train) [50][100/586] lr: 5.000000e-03 eta: 12:52:10 time: 0.528993 data_time: 0.060049 memory: 8713 loss_kpt: 230.784878 acc_pose: 0.831656 loss: 230.784878 2022/10/12 15:22:13 - mmengine - INFO - Epoch(train) [50][150/586] lr: 5.000000e-03 eta: 12:51:50 time: 0.518639 data_time: 0.060097 memory: 8713 loss_kpt: 230.771824 acc_pose: 0.771246 loss: 230.771824 2022/10/12 15:22:40 - mmengine - INFO - Epoch(train) [50][200/586] lr: 5.000000e-03 eta: 12:51:33 time: 0.535928 data_time: 0.059571 memory: 8713 loss_kpt: 228.589745 acc_pose: 0.722401 loss: 228.589745 2022/10/12 15:23:07 - mmengine - INFO - Epoch(train) [50][250/586] lr: 5.000000e-03 eta: 12:51:16 time: 0.540525 data_time: 0.059578 memory: 8713 loss_kpt: 231.998000 acc_pose: 0.790904 loss: 231.998000 2022/10/12 15:23:26 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:23:33 - mmengine - INFO - Epoch(train) [50][300/586] lr: 5.000000e-03 eta: 12:50:56 time: 0.522217 data_time: 0.059199 memory: 8713 loss_kpt: 229.203428 acc_pose: 0.762159 loss: 229.203428 2022/10/12 15:24:00 - mmengine - INFO - Epoch(train) [50][350/586] lr: 5.000000e-03 eta: 12:50:39 time: 0.535727 data_time: 0.059885 memory: 8713 loss_kpt: 230.486696 acc_pose: 0.781024 loss: 230.486696 2022/10/12 15:24:27 - mmengine - INFO - Epoch(train) [50][400/586] lr: 5.000000e-03 eta: 12:50:21 time: 0.535406 data_time: 0.064893 memory: 8713 loss_kpt: 231.589066 acc_pose: 0.803599 loss: 231.589066 2022/10/12 15:24:53 - mmengine - INFO - Epoch(train) [50][450/586] lr: 5.000000e-03 eta: 12:50:03 time: 0.530292 data_time: 0.055402 memory: 8713 loss_kpt: 231.829136 acc_pose: 0.829369 loss: 231.829136 2022/10/12 15:25:20 - mmengine - INFO - Epoch(train) [50][500/586] lr: 5.000000e-03 eta: 12:49:45 time: 0.532510 data_time: 0.058699 memory: 8713 loss_kpt: 223.907679 acc_pose: 0.779535 loss: 223.907679 2022/10/12 15:25:47 - mmengine - INFO - Epoch(train) [50][550/586] lr: 5.000000e-03 eta: 12:49:26 time: 0.530820 data_time: 0.054003 memory: 8713 loss_kpt: 225.395062 acc_pose: 0.826321 loss: 225.395062 2022/10/12 15:26:05 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:26:05 - mmengine - INFO - Saving checkpoint at 50 epochs 2022/10/12 15:26:19 - mmengine - INFO - Epoch(val) [50][50/407] eta: 0:01:14 time: 0.208997 data_time: 0.013987 memory: 8713 2022/10/12 15:26:29 - mmengine - INFO - Epoch(val) [50][100/407] eta: 0:01:01 time: 0.199161 data_time: 0.009150 memory: 1759 2022/10/12 15:26:39 - mmengine - INFO - Epoch(val) [50][150/407] eta: 0:00:51 time: 0.201397 data_time: 0.008851 memory: 1759 2022/10/12 15:26:50 - mmengine - INFO - Epoch(val) [50][200/407] eta: 0:00:41 time: 0.201817 data_time: 0.008875 memory: 1759 2022/10/12 15:26:59 - mmengine - INFO - Epoch(val) [50][250/407] eta: 0:00:31 time: 0.198591 data_time: 0.008708 memory: 1759 2022/10/12 15:27:09 - mmengine - INFO - Epoch(val) [50][300/407] eta: 0:00:21 time: 0.198520 data_time: 0.008477 memory: 1759 2022/10/12 15:27:19 - mmengine - INFO - Epoch(val) [50][350/407] eta: 0:00:11 time: 0.200252 data_time: 0.008327 memory: 1759 2022/10/12 15:27:29 - mmengine - INFO - Epoch(val) [50][400/407] eta: 0:00:01 time: 0.189351 data_time: 0.007969 memory: 1759 2022/10/12 15:27:42 - mmengine - INFO - Evaluating CocoMetric... 2022/10/12 15:27:58 - mmengine - INFO - Epoch(val) [50][407/407] coco/AP: 0.667191 coco/AP .5: 0.868904 coco/AP .75: 0.738670 coco/AP (M): 0.641486 coco/AP (L): 0.719580 coco/AR: 0.738838 coco/AR .5: 0.912154 coco/AR .75: 0.798331 coco/AR (M): 0.697815 coco/AR (L): 0.795281 2022/10/12 15:27:58 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/liqikai/openmmlab/pt112cu113py38/mmpose/work_dirs/20221012/rsn2x/best_coco/AP_epoch_40.pth is removed 2022/10/12 15:28:00 - mmengine - INFO - The best checkpoint with 0.6672 coco/AP at 50 epoch is saved to best_coco/AP_epoch_50.pth. 2022/10/12 15:28:27 - mmengine - INFO - Epoch(train) [51][50/586] lr: 5.000000e-03 eta: 12:47:53 time: 0.527441 data_time: 0.068705 memory: 8713 loss_kpt: 224.543647 acc_pose: 0.816075 loss: 224.543647 2022/10/12 15:28:53 - mmengine - INFO - Epoch(train) [51][100/586] lr: 5.000000e-03 eta: 12:47:32 time: 0.516783 data_time: 0.062480 memory: 8713 loss_kpt: 228.600202 acc_pose: 0.814852 loss: 228.600202 2022/10/12 15:29:19 - mmengine - INFO - Epoch(train) [51][150/586] lr: 5.000000e-03 eta: 12:47:13 time: 0.525518 data_time: 0.062128 memory: 8713 loss_kpt: 232.637469 acc_pose: 0.755821 loss: 232.637469 2022/10/12 15:29:45 - mmengine - INFO - Epoch(train) [51][200/586] lr: 5.000000e-03 eta: 12:46:52 time: 0.514596 data_time: 0.059799 memory: 8713 loss_kpt: 226.956147 acc_pose: 0.806354 loss: 226.956147 2022/10/12 15:30:11 - mmengine - INFO - Epoch(train) [51][250/586] lr: 5.000000e-03 eta: 12:46:33 time: 0.522136 data_time: 0.059435 memory: 8713 loss_kpt: 229.837340 acc_pose: 0.777047 loss: 229.837340 2022/10/12 15:30:37 - mmengine - INFO - Epoch(train) [51][300/586] lr: 5.000000e-03 eta: 12:46:12 time: 0.516521 data_time: 0.056800 memory: 8713 loss_kpt: 229.037776 acc_pose: 0.803822 loss: 229.037776 2022/10/12 15:31:04 - mmengine - INFO - Epoch(train) [51][350/586] lr: 5.000000e-03 eta: 12:45:55 time: 0.538532 data_time: 0.054828 memory: 8713 loss_kpt: 231.591213 acc_pose: 0.781616 loss: 231.591213 2022/10/12 15:31:30 - mmengine - INFO - Epoch(train) [51][400/586] lr: 5.000000e-03 eta: 12:45:35 time: 0.521253 data_time: 0.061782 memory: 8713 loss_kpt: 227.083160 acc_pose: 0.730349 loss: 227.083160 2022/10/12 15:31:56 - mmengine - INFO - Epoch(train) [51][450/586] lr: 5.000000e-03 eta: 12:45:14 time: 0.517933 data_time: 0.054364 memory: 8713 loss_kpt: 229.087637 acc_pose: 0.821112 loss: 229.087637 2022/10/12 15:32:21 - mmengine - INFO - Epoch(train) [51][500/586] lr: 5.000000e-03 eta: 12:44:52 time: 0.509033 data_time: 0.059661 memory: 8713 loss_kpt: 229.152563 acc_pose: 0.802172 loss: 229.152563 2022/10/12 15:32:48 - mmengine - INFO - Epoch(train) [51][550/586] lr: 5.000000e-03 eta: 12:44:35 time: 0.537025 data_time: 0.060087 memory: 8713 loss_kpt: 231.312975 acc_pose: 0.824285 loss: 231.312975 2022/10/12 15:33:06 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:33:33 - mmengine - INFO - Epoch(train) [52][50/586] lr: 5.000000e-03 eta: 12:43:04 time: 0.534674 data_time: 0.062222 memory: 8713 loss_kpt: 226.812518 acc_pose: 0.776187 loss: 226.812518 2022/10/12 15:33:58 - mmengine - INFO - Epoch(train) [52][100/586] lr: 5.000000e-03 eta: 12:42:41 time: 0.502686 data_time: 0.057374 memory: 8713 loss_kpt: 225.749033 acc_pose: 0.787537 loss: 225.749033 2022/10/12 15:34:05 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:34:23 - mmengine - INFO - Epoch(train) [52][150/586] lr: 5.000000e-03 eta: 12:42:17 time: 0.499603 data_time: 0.057751 memory: 8713 loss_kpt: 229.409801 acc_pose: 0.783781 loss: 229.409801 2022/10/12 15:34:49 - mmengine - INFO - Epoch(train) [52][200/586] lr: 5.000000e-03 eta: 12:41:56 time: 0.512996 data_time: 0.054938 memory: 8713 loss_kpt: 225.882053 acc_pose: 0.796483 loss: 225.882053 2022/10/12 15:35:15 - mmengine - INFO - Epoch(train) [52][250/586] lr: 5.000000e-03 eta: 12:41:37 time: 0.525252 data_time: 0.058515 memory: 8713 loss_kpt: 229.619220 acc_pose: 0.784651 loss: 229.619220 2022/10/12 15:35:43 - mmengine - INFO - Epoch(train) [52][300/586] lr: 5.000000e-03 eta: 12:41:23 time: 0.560715 data_time: 0.054460 memory: 8713 loss_kpt: 225.108444 acc_pose: 0.834538 loss: 225.108444 2022/10/12 15:36:10 - mmengine - INFO - Epoch(train) [52][350/586] lr: 5.000000e-03 eta: 12:41:06 time: 0.543882 data_time: 0.053502 memory: 8713 loss_kpt: 229.309402 acc_pose: 0.790249 loss: 229.309402 2022/10/12 15:36:36 - mmengine - INFO - Epoch(train) [52][400/586] lr: 5.000000e-03 eta: 12:40:45 time: 0.514567 data_time: 0.057832 memory: 8713 loss_kpt: 225.970405 acc_pose: 0.660887 loss: 225.970405 2022/10/12 15:37:02 - mmengine - INFO - Epoch(train) [52][450/586] lr: 5.000000e-03 eta: 12:40:25 time: 0.519216 data_time: 0.054452 memory: 8713 loss_kpt: 226.038075 acc_pose: 0.829178 loss: 226.038075 2022/10/12 15:37:27 - mmengine - INFO - Epoch(train) [52][500/586] lr: 5.000000e-03 eta: 12:40:02 time: 0.506510 data_time: 0.055091 memory: 8713 loss_kpt: 224.966988 acc_pose: 0.761316 loss: 224.966988 2022/10/12 15:37:53 - mmengine - INFO - Epoch(train) [52][550/586] lr: 5.000000e-03 eta: 12:39:42 time: 0.518219 data_time: 0.059573 memory: 8713 loss_kpt: 232.034127 acc_pose: 0.799631 loss: 232.034127 2022/10/12 15:38:11 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:38:38 - mmengine - INFO - Epoch(train) [53][50/586] lr: 5.000000e-03 eta: 12:38:13 time: 0.538677 data_time: 0.071541 memory: 8713 loss_kpt: 225.861665 acc_pose: 0.810442 loss: 225.861665 2022/10/12 15:39:04 - mmengine - INFO - Epoch(train) [53][100/586] lr: 5.000000e-03 eta: 12:37:54 time: 0.530038 data_time: 0.059258 memory: 8713 loss_kpt: 228.031961 acc_pose: 0.796312 loss: 228.031961 2022/10/12 15:39:30 - mmengine - INFO - Epoch(train) [53][150/586] lr: 5.000000e-03 eta: 12:37:33 time: 0.518799 data_time: 0.063320 memory: 8713 loss_kpt: 227.787637 acc_pose: 0.776465 loss: 227.787637 2022/10/12 15:39:57 - mmengine - INFO - Epoch(train) [53][200/586] lr: 5.000000e-03 eta: 12:37:14 time: 0.527129 data_time: 0.054461 memory: 8713 loss_kpt: 222.121683 acc_pose: 0.802701 loss: 222.121683 2022/10/12 15:40:23 - mmengine - INFO - Epoch(train) [53][250/586] lr: 5.000000e-03 eta: 12:36:54 time: 0.518993 data_time: 0.063974 memory: 8713 loss_kpt: 227.763842 acc_pose: 0.800013 loss: 227.763842 2022/10/12 15:40:49 - mmengine - INFO - Epoch(train) [53][300/586] lr: 5.000000e-03 eta: 12:36:35 time: 0.531249 data_time: 0.060494 memory: 8713 loss_kpt: 223.514465 acc_pose: 0.757638 loss: 223.514465 2022/10/12 15:41:16 - mmengine - INFO - Epoch(train) [53][350/586] lr: 5.000000e-03 eta: 12:36:16 time: 0.530932 data_time: 0.056179 memory: 8713 loss_kpt: 228.826592 acc_pose: 0.735697 loss: 228.826592 2022/10/12 15:41:42 - mmengine - INFO - Epoch(train) [53][400/586] lr: 5.000000e-03 eta: 12:35:57 time: 0.530392 data_time: 0.055082 memory: 8713 loss_kpt: 226.711447 acc_pose: 0.832982 loss: 226.711447 2022/10/12 15:42:09 - mmengine - INFO - Epoch(train) [53][450/586] lr: 5.000000e-03 eta: 12:35:39 time: 0.533232 data_time: 0.064041 memory: 8713 loss_kpt: 223.541280 acc_pose: 0.804410 loss: 223.541280 2022/10/12 15:42:35 - mmengine - INFO - Epoch(train) [53][500/586] lr: 5.000000e-03 eta: 12:35:19 time: 0.522264 data_time: 0.059665 memory: 8713 loss_kpt: 229.448704 acc_pose: 0.768143 loss: 229.448704 2022/10/12 15:42:50 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:43:02 - mmengine - INFO - Epoch(train) [53][550/586] lr: 5.000000e-03 eta: 12:35:00 time: 0.532662 data_time: 0.058939 memory: 8713 loss_kpt: 225.566635 acc_pose: 0.755597 loss: 225.566635 2022/10/12 15:43:20 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:43:47 - mmengine - INFO - Epoch(train) [54][50/586] lr: 5.000000e-03 eta: 12:33:32 time: 0.539985 data_time: 0.072272 memory: 8713 loss_kpt: 228.321914 acc_pose: 0.767430 loss: 228.321914 2022/10/12 15:44:14 - mmengine - INFO - Epoch(train) [54][100/586] lr: 5.000000e-03 eta: 12:33:13 time: 0.525696 data_time: 0.060559 memory: 8713 loss_kpt: 229.427582 acc_pose: 0.796060 loss: 229.427582 2022/10/12 15:44:40 - mmengine - INFO - Epoch(train) [54][150/586] lr: 5.000000e-03 eta: 12:32:53 time: 0.521637 data_time: 0.063019 memory: 8713 loss_kpt: 224.705511 acc_pose: 0.763517 loss: 224.705511 2022/10/12 15:45:06 - mmengine - INFO - Epoch(train) [54][200/586] lr: 5.000000e-03 eta: 12:32:34 time: 0.533862 data_time: 0.058631 memory: 8713 loss_kpt: 224.128221 acc_pose: 0.799303 loss: 224.128221 2022/10/12 15:45:33 - mmengine - INFO - Epoch(train) [54][250/586] lr: 5.000000e-03 eta: 12:32:15 time: 0.527726 data_time: 0.059408 memory: 8713 loss_kpt: 228.090885 acc_pose: 0.791751 loss: 228.090885 2022/10/12 15:46:00 - mmengine - INFO - Epoch(train) [54][300/586] lr: 5.000000e-03 eta: 12:31:57 time: 0.535529 data_time: 0.056102 memory: 8713 loss_kpt: 224.634509 acc_pose: 0.675532 loss: 224.634509 2022/10/12 15:46:27 - mmengine - INFO - Epoch(train) [54][350/586] lr: 5.000000e-03 eta: 12:31:39 time: 0.540502 data_time: 0.060113 memory: 8713 loss_kpt: 226.300076 acc_pose: 0.764329 loss: 226.300076 2022/10/12 15:46:54 - mmengine - INFO - Epoch(train) [54][400/586] lr: 5.000000e-03 eta: 12:31:21 time: 0.538340 data_time: 0.056008 memory: 8713 loss_kpt: 228.204243 acc_pose: 0.808838 loss: 228.204243 2022/10/12 15:47:21 - mmengine - INFO - Epoch(train) [54][450/586] lr: 5.000000e-03 eta: 12:31:04 time: 0.539874 data_time: 0.063746 memory: 8713 loss_kpt: 225.849603 acc_pose: 0.796992 loss: 225.849603 2022/10/12 15:47:47 - mmengine - INFO - Epoch(train) [54][500/586] lr: 5.000000e-03 eta: 12:30:46 time: 0.536980 data_time: 0.059341 memory: 8713 loss_kpt: 225.677379 acc_pose: 0.771224 loss: 225.677379 2022/10/12 15:48:14 - mmengine - INFO - Epoch(train) [54][550/586] lr: 5.000000e-03 eta: 12:30:26 time: 0.530612 data_time: 0.058906 memory: 8713 loss_kpt: 226.140970 acc_pose: 0.736632 loss: 226.140970 2022/10/12 15:48:33 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:49:00 - mmengine - INFO - Epoch(train) [55][50/586] lr: 5.000000e-03 eta: 12:29:00 time: 0.538066 data_time: 0.066834 memory: 8713 loss_kpt: 221.515097 acc_pose: 0.809599 loss: 221.515097 2022/10/12 15:49:26 - mmengine - INFO - Epoch(train) [55][100/586] lr: 5.000000e-03 eta: 12:28:39 time: 0.520655 data_time: 0.059498 memory: 8713 loss_kpt: 223.933535 acc_pose: 0.787227 loss: 223.933535 2022/10/12 15:49:52 - mmengine - INFO - Epoch(train) [55][150/586] lr: 5.000000e-03 eta: 12:28:19 time: 0.526293 data_time: 0.056010 memory: 8713 loss_kpt: 226.020128 acc_pose: 0.783797 loss: 226.020128 2022/10/12 15:50:18 - mmengine - INFO - Epoch(train) [55][200/586] lr: 5.000000e-03 eta: 12:27:59 time: 0.521884 data_time: 0.061512 memory: 8713 loss_kpt: 225.515172 acc_pose: 0.809114 loss: 225.515172 2022/10/12 15:50:44 - mmengine - INFO - Epoch(train) [55][250/586] lr: 5.000000e-03 eta: 12:27:39 time: 0.525240 data_time: 0.056648 memory: 8713 loss_kpt: 226.846766 acc_pose: 0.807965 loss: 226.846766 2022/10/12 15:51:10 - mmengine - INFO - Epoch(train) [55][300/586] lr: 5.000000e-03 eta: 12:27:19 time: 0.522127 data_time: 0.057365 memory: 8713 loss_kpt: 230.017108 acc_pose: 0.799435 loss: 230.017108 2022/10/12 15:51:37 - mmengine - INFO - Epoch(train) [55][350/586] lr: 5.000000e-03 eta: 12:26:59 time: 0.522844 data_time: 0.055193 memory: 8713 loss_kpt: 229.031668 acc_pose: 0.774161 loss: 229.031668 2022/10/12 15:51:40 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:52:03 - mmengine - INFO - Epoch(train) [55][400/586] lr: 5.000000e-03 eta: 12:26:38 time: 0.522516 data_time: 0.058783 memory: 8713 loss_kpt: 225.310681 acc_pose: 0.809147 loss: 225.310681 2022/10/12 15:52:29 - mmengine - INFO - Epoch(train) [55][450/586] lr: 5.000000e-03 eta: 12:26:19 time: 0.526196 data_time: 0.057903 memory: 8713 loss_kpt: 224.613137 acc_pose: 0.842614 loss: 224.613137 2022/10/12 15:52:55 - mmengine - INFO - Epoch(train) [55][500/586] lr: 5.000000e-03 eta: 12:25:59 time: 0.526387 data_time: 0.058903 memory: 8713 loss_kpt: 226.290521 acc_pose: 0.747316 loss: 226.290521 2022/10/12 15:53:22 - mmengine - INFO - Epoch(train) [55][550/586] lr: 5.000000e-03 eta: 12:25:39 time: 0.524963 data_time: 0.056965 memory: 8713 loss_kpt: 226.674996 acc_pose: 0.711648 loss: 226.674996 2022/10/12 15:53:41 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:54:07 - mmengine - INFO - Epoch(train) [56][50/586] lr: 5.000000e-03 eta: 12:24:11 time: 0.521551 data_time: 0.065989 memory: 8713 loss_kpt: 226.896183 acc_pose: 0.804564 loss: 226.896183 2022/10/12 15:54:33 - mmengine - INFO - Epoch(train) [56][100/586] lr: 5.000000e-03 eta: 12:23:50 time: 0.518541 data_time: 0.062402 memory: 8713 loss_kpt: 225.219367 acc_pose: 0.809509 loss: 225.219367 2022/10/12 15:54:58 - mmengine - INFO - Epoch(train) [56][150/586] lr: 5.000000e-03 eta: 12:23:29 time: 0.516436 data_time: 0.055944 memory: 8713 loss_kpt: 226.516578 acc_pose: 0.801654 loss: 226.516578 2022/10/12 15:55:24 - mmengine - INFO - Epoch(train) [56][200/586] lr: 5.000000e-03 eta: 12:23:08 time: 0.516063 data_time: 0.054497 memory: 8713 loss_kpt: 222.533271 acc_pose: 0.768067 loss: 222.533271 2022/10/12 15:55:50 - mmengine - INFO - Epoch(train) [56][250/586] lr: 5.000000e-03 eta: 12:22:47 time: 0.518586 data_time: 0.060046 memory: 8713 loss_kpt: 223.697735 acc_pose: 0.791294 loss: 223.697735 2022/10/12 15:56:16 - mmengine - INFO - Epoch(train) [56][300/586] lr: 5.000000e-03 eta: 12:22:25 time: 0.514846 data_time: 0.057465 memory: 8713 loss_kpt: 225.827745 acc_pose: 0.833757 loss: 225.827745 2022/10/12 15:56:43 - mmengine - INFO - Epoch(train) [56][350/586] lr: 5.000000e-03 eta: 12:22:06 time: 0.532006 data_time: 0.063869 memory: 8713 loss_kpt: 225.953809 acc_pose: 0.713913 loss: 225.953809 2022/10/12 15:57:09 - mmengine - INFO - Epoch(train) [56][400/586] lr: 5.000000e-03 eta: 12:21:46 time: 0.527134 data_time: 0.057589 memory: 8713 loss_kpt: 224.882392 acc_pose: 0.830058 loss: 224.882392 2022/10/12 15:57:35 - mmengine - INFO - Epoch(train) [56][450/586] lr: 5.000000e-03 eta: 12:21:27 time: 0.531786 data_time: 0.060898 memory: 8713 loss_kpt: 225.371823 acc_pose: 0.818246 loss: 225.371823 2022/10/12 15:58:02 - mmengine - INFO - Epoch(train) [56][500/586] lr: 5.000000e-03 eta: 12:21:07 time: 0.522983 data_time: 0.057790 memory: 8713 loss_kpt: 224.879562 acc_pose: 0.823636 loss: 224.879562 2022/10/12 15:58:28 - mmengine - INFO - Epoch(train) [56][550/586] lr: 5.000000e-03 eta: 12:20:46 time: 0.520830 data_time: 0.056036 memory: 8713 loss_kpt: 224.741346 acc_pose: 0.756991 loss: 224.741346 2022/10/12 15:58:46 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:59:13 - mmengine - INFO - Epoch(train) [57][50/586] lr: 5.000000e-03 eta: 12:19:22 time: 0.542521 data_time: 0.074702 memory: 8713 loss_kpt: 224.927975 acc_pose: 0.789261 loss: 224.927975 2022/10/12 15:59:39 - mmengine - INFO - Epoch(train) [57][100/586] lr: 5.000000e-03 eta: 12:19:00 time: 0.508673 data_time: 0.061555 memory: 8713 loss_kpt: 225.201050 acc_pose: 0.797791 loss: 225.201050 2022/10/12 16:00:04 - mmengine - INFO - Epoch(train) [57][150/586] lr: 5.000000e-03 eta: 12:18:38 time: 0.510348 data_time: 0.059191 memory: 8713 loss_kpt: 225.285231 acc_pose: 0.822148 loss: 225.285231 2022/10/12 16:00:22 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:00:30 - mmengine - INFO - Epoch(train) [57][200/586] lr: 5.000000e-03 eta: 12:18:16 time: 0.509644 data_time: 0.056360 memory: 8713 loss_kpt: 226.558918 acc_pose: 0.755074 loss: 226.558918 2022/10/12 16:00:55 - mmengine - INFO - Epoch(train) [57][250/586] lr: 5.000000e-03 eta: 12:17:53 time: 0.508252 data_time: 0.055690 memory: 8713 loss_kpt: 227.086175 acc_pose: 0.726091 loss: 227.086175 2022/10/12 16:01:21 - mmengine - INFO - Epoch(train) [57][300/586] lr: 5.000000e-03 eta: 12:17:32 time: 0.512965 data_time: 0.057554 memory: 8713 loss_kpt: 225.020775 acc_pose: 0.776169 loss: 225.020775 2022/10/12 16:01:47 - mmengine - INFO - Epoch(train) [57][350/586] lr: 5.000000e-03 eta: 12:17:10 time: 0.516056 data_time: 0.063292 memory: 8713 loss_kpt: 225.802700 acc_pose: 0.826096 loss: 225.802700 2022/10/12 16:02:12 - mmengine - INFO - Epoch(train) [57][400/586] lr: 5.000000e-03 eta: 12:16:48 time: 0.510997 data_time: 0.057830 memory: 8713 loss_kpt: 226.551694 acc_pose: 0.806970 loss: 226.551694 2022/10/12 16:02:38 - mmengine - INFO - Epoch(train) [57][450/586] lr: 5.000000e-03 eta: 12:16:28 time: 0.522379 data_time: 0.060401 memory: 8713 loss_kpt: 226.541487 acc_pose: 0.713143 loss: 226.541487 2022/10/12 16:03:04 - mmengine - INFO - Epoch(train) [57][500/586] lr: 5.000000e-03 eta: 12:16:06 time: 0.514829 data_time: 0.053664 memory: 8713 loss_kpt: 220.481745 acc_pose: 0.781268 loss: 220.481745 2022/10/12 16:03:30 - mmengine - INFO - Epoch(train) [57][550/586] lr: 5.000000e-03 eta: 12:15:44 time: 0.510289 data_time: 0.057666 memory: 8713 loss_kpt: 222.395204 acc_pose: 0.816128 loss: 222.395204 2022/10/12 16:03:48 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:04:16 - mmengine - INFO - Epoch(train) [58][50/586] lr: 5.000000e-03 eta: 12:14:24 time: 0.562551 data_time: 0.068215 memory: 8713 loss_kpt: 227.288623 acc_pose: 0.734007 loss: 227.288623 2022/10/12 16:04:43 - mmengine - INFO - Epoch(train) [58][100/586] lr: 5.000000e-03 eta: 12:14:06 time: 0.544851 data_time: 0.056434 memory: 8713 loss_kpt: 225.037023 acc_pose: 0.800529 loss: 225.037023 2022/10/12 16:05:10 - mmengine - INFO - Epoch(train) [58][150/586] lr: 5.000000e-03 eta: 12:13:48 time: 0.537856 data_time: 0.066145 memory: 8713 loss_kpt: 222.095345 acc_pose: 0.863855 loss: 222.095345 2022/10/12 16:05:37 - mmengine - INFO - Epoch(train) [58][200/586] lr: 5.000000e-03 eta: 12:13:29 time: 0.533562 data_time: 0.052098 memory: 8713 loss_kpt: 225.522720 acc_pose: 0.809039 loss: 225.522720 2022/10/12 16:06:03 - mmengine - INFO - Epoch(train) [58][250/586] lr: 5.000000e-03 eta: 12:13:08 time: 0.519517 data_time: 0.056912 memory: 8713 loss_kpt: 222.948347 acc_pose: 0.743742 loss: 222.948347 2022/10/12 16:06:29 - mmengine - INFO - Epoch(train) [58][300/586] lr: 5.000000e-03 eta: 12:12:47 time: 0.525313 data_time: 0.059978 memory: 8713 loss_kpt: 221.683006 acc_pose: 0.741977 loss: 221.683006 2022/10/12 16:06:56 - mmengine - INFO - Epoch(train) [58][350/586] lr: 5.000000e-03 eta: 12:12:29 time: 0.536617 data_time: 0.063331 memory: 8713 loss_kpt: 222.802902 acc_pose: 0.775052 loss: 222.802902 2022/10/12 16:07:23 - mmengine - INFO - Epoch(train) [58][400/586] lr: 5.000000e-03 eta: 12:12:09 time: 0.529411 data_time: 0.056362 memory: 8713 loss_kpt: 225.298347 acc_pose: 0.770416 loss: 225.298347 2022/10/12 16:07:49 - mmengine - INFO - Epoch(train) [58][450/586] lr: 5.000000e-03 eta: 12:11:49 time: 0.530118 data_time: 0.061349 memory: 8713 loss_kpt: 223.288278 acc_pose: 0.773605 loss: 223.288278 2022/10/12 16:08:17 - mmengine - INFO - Epoch(train) [58][500/586] lr: 5.000000e-03 eta: 12:11:33 time: 0.553313 data_time: 0.061188 memory: 8713 loss_kpt: 226.048500 acc_pose: 0.811807 loss: 226.048500 2022/10/12 16:08:44 - mmengine - INFO - Epoch(train) [58][550/586] lr: 5.000000e-03 eta: 12:11:16 time: 0.547896 data_time: 0.064017 memory: 8713 loss_kpt: 224.442484 acc_pose: 0.825955 loss: 224.442484 2022/10/12 16:09:03 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:09:10 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:09:30 - mmengine - INFO - Epoch(train) [59][50/586] lr: 5.000000e-03 eta: 12:09:53 time: 0.541181 data_time: 0.068615 memory: 8713 loss_kpt: 227.577912 acc_pose: 0.817114 loss: 227.577912 2022/10/12 16:09:56 - mmengine - INFO - Epoch(train) [59][100/586] lr: 5.000000e-03 eta: 12:09:33 time: 0.528023 data_time: 0.060895 memory: 8713 loss_kpt: 225.227501 acc_pose: 0.752039 loss: 225.227501 2022/10/12 16:10:23 - mmengine - INFO - Epoch(train) [59][150/586] lr: 5.000000e-03 eta: 12:09:15 time: 0.536628 data_time: 0.056047 memory: 8713 loss_kpt: 223.071239 acc_pose: 0.755910 loss: 223.071239 2022/10/12 16:10:49 - mmengine - INFO - Epoch(train) [59][200/586] lr: 5.000000e-03 eta: 12:08:54 time: 0.521677 data_time: 0.060896 memory: 8713 loss_kpt: 225.866452 acc_pose: 0.811350 loss: 225.866452 2022/10/12 16:11:16 - mmengine - INFO - Epoch(train) [59][250/586] lr: 5.000000e-03 eta: 12:08:35 time: 0.537204 data_time: 0.061203 memory: 8713 loss_kpt: 222.216669 acc_pose: 0.777852 loss: 222.216669 2022/10/12 16:11:43 - mmengine - INFO - Epoch(train) [59][300/586] lr: 5.000000e-03 eta: 12:08:15 time: 0.528870 data_time: 0.060750 memory: 8713 loss_kpt: 221.109851 acc_pose: 0.778902 loss: 221.109851 2022/10/12 16:12:10 - mmengine - INFO - Epoch(train) [59][350/586] lr: 5.000000e-03 eta: 12:07:57 time: 0.538885 data_time: 0.058490 memory: 8713 loss_kpt: 225.847704 acc_pose: 0.756988 loss: 225.847704 2022/10/12 16:12:36 - mmengine - INFO - Epoch(train) [59][400/586] lr: 5.000000e-03 eta: 12:07:36 time: 0.527134 data_time: 0.054676 memory: 8713 loss_kpt: 227.179347 acc_pose: 0.813866 loss: 227.179347 2022/10/12 16:13:02 - mmengine - INFO - Epoch(train) [59][450/586] lr: 5.000000e-03 eta: 12:07:16 time: 0.525468 data_time: 0.058386 memory: 8713 loss_kpt: 224.919172 acc_pose: 0.776337 loss: 224.919172 2022/10/12 16:13:29 - mmengine - INFO - Epoch(train) [59][500/586] lr: 5.000000e-03 eta: 12:06:56 time: 0.524621 data_time: 0.057229 memory: 8713 loss_kpt: 226.952130 acc_pose: 0.704799 loss: 226.952130 2022/10/12 16:13:55 - mmengine - INFO - Epoch(train) [59][550/586] lr: 5.000000e-03 eta: 12:06:36 time: 0.528982 data_time: 0.058038 memory: 8713 loss_kpt: 226.441545 acc_pose: 0.864261 loss: 226.441545 2022/10/12 16:14:14 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:14:41 - mmengine - INFO - Epoch(train) [60][50/586] lr: 5.000000e-03 eta: 12:05:14 time: 0.541669 data_time: 0.071867 memory: 8713 loss_kpt: 223.096193 acc_pose: 0.755321 loss: 223.096193 2022/10/12 16:15:08 - mmengine - INFO - Epoch(train) [60][100/586] lr: 5.000000e-03 eta: 12:04:56 time: 0.537586 data_time: 0.059108 memory: 8713 loss_kpt: 225.084496 acc_pose: 0.756847 loss: 225.084496 2022/10/12 16:15:34 - mmengine - INFO - Epoch(train) [60][150/586] lr: 5.000000e-03 eta: 12:04:35 time: 0.524834 data_time: 0.055276 memory: 8713 loss_kpt: 228.650274 acc_pose: 0.769281 loss: 228.650274 2022/10/12 16:16:00 - mmengine - INFO - Epoch(train) [60][200/586] lr: 5.000000e-03 eta: 12:04:15 time: 0.525505 data_time: 0.060746 memory: 8713 loss_kpt: 223.565634 acc_pose: 0.857510 loss: 223.565634 2022/10/12 16:16:27 - mmengine - INFO - Epoch(train) [60][250/586] lr: 5.000000e-03 eta: 12:03:55 time: 0.529386 data_time: 0.059301 memory: 8713 loss_kpt: 223.717920 acc_pose: 0.741519 loss: 223.717920 2022/10/12 16:16:53 - mmengine - INFO - Epoch(train) [60][300/586] lr: 5.000000e-03 eta: 12:03:36 time: 0.537033 data_time: 0.061511 memory: 8713 loss_kpt: 222.055655 acc_pose: 0.835776 loss: 222.055655 2022/10/12 16:17:20 - mmengine - INFO - Epoch(train) [60][350/586] lr: 5.000000e-03 eta: 12:03:15 time: 0.523160 data_time: 0.056624 memory: 8713 loss_kpt: 224.789795 acc_pose: 0.827758 loss: 224.789795 2022/10/12 16:17:46 - mmengine - INFO - Epoch(train) [60][400/586] lr: 5.000000e-03 eta: 12:02:56 time: 0.533808 data_time: 0.060045 memory: 8713 loss_kpt: 227.290847 acc_pose: 0.791324 loss: 227.290847 2022/10/12 16:18:00 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:18:12 - mmengine - INFO - Epoch(train) [60][450/586] lr: 5.000000e-03 eta: 12:02:34 time: 0.514787 data_time: 0.058603 memory: 8713 loss_kpt: 223.236552 acc_pose: 0.787001 loss: 223.236552 2022/10/12 16:18:39 - mmengine - INFO - Epoch(train) [60][500/586] lr: 5.000000e-03 eta: 12:02:14 time: 0.530221 data_time: 0.062412 memory: 8713 loss_kpt: 218.648547 acc_pose: 0.793606 loss: 218.648547 2022/10/12 16:19:05 - mmengine - INFO - Epoch(train) [60][550/586] lr: 5.000000e-03 eta: 12:01:55 time: 0.534253 data_time: 0.059365 memory: 8713 loss_kpt: 222.623103 acc_pose: 0.812015 loss: 222.623103 2022/10/12 16:19:24 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:19:24 - mmengine - INFO - Saving checkpoint at 60 epochs 2022/10/12 16:19:38 - mmengine - INFO - Epoch(val) [60][50/407] eta: 0:01:11 time: 0.201093 data_time: 0.012808 memory: 8713 2022/10/12 16:19:48 - mmengine - INFO - Epoch(val) [60][100/407] eta: 0:00:59 time: 0.193432 data_time: 0.007980 memory: 1759 2022/10/12 16:19:58 - mmengine - INFO - Epoch(val) [60][150/407] eta: 0:00:51 time: 0.198914 data_time: 0.008653 memory: 1759 2022/10/12 16:20:08 - mmengine - INFO - Epoch(val) [60][200/407] eta: 0:00:41 time: 0.202830 data_time: 0.012185 memory: 1759 2022/10/12 16:20:18 - mmengine - INFO - Epoch(val) [60][250/407] eta: 0:00:31 time: 0.197973 data_time: 0.008222 memory: 1759 2022/10/12 16:20:27 - mmengine - INFO - Epoch(val) [60][300/407] eta: 0:00:20 time: 0.194966 data_time: 0.008245 memory: 1759 2022/10/12 16:20:37 - mmengine - INFO - Epoch(val) [60][350/407] eta: 0:00:11 time: 0.196686 data_time: 0.008659 memory: 1759 2022/10/12 16:20:47 - mmengine - INFO - Epoch(val) [60][400/407] eta: 0:00:01 time: 0.189854 data_time: 0.007660 memory: 1759 2022/10/12 16:21:00 - mmengine - INFO - Evaluating CocoMetric... 2022/10/12 16:21:16 - mmengine - INFO - Epoch(val) [60][407/407] coco/AP: 0.685450 coco/AP .5: 0.879254 coco/AP .75: 0.760756 coco/AP (M): 0.657617 coco/AP (L): 0.742268 coco/AR: 0.756911 coco/AR .5: 0.921757 coco/AR .75: 0.819112 coco/AR (M): 0.714532 coco/AR (L): 0.814827 2022/10/12 16:21:16 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/liqikai/openmmlab/pt112cu113py38/mmpose/work_dirs/20221012/rsn2x/best_coco/AP_epoch_50.pth is removed 2022/10/12 16:21:18 - mmengine - INFO - The best checkpoint with 0.6855 coco/AP at 60 epoch is saved to best_coco/AP_epoch_60.pth. 2022/10/12 16:21:45 - mmengine - INFO - Epoch(train) [61][50/586] lr: 5.000000e-03 eta: 12:00:33 time: 0.528858 data_time: 0.069051 memory: 8713 loss_kpt: 227.086903 acc_pose: 0.764021 loss: 227.086903 2022/10/12 16:22:12 - mmengine - INFO - Epoch(train) [61][100/586] lr: 5.000000e-03 eta: 12:00:14 time: 0.536610 data_time: 0.054570 memory: 8713 loss_kpt: 222.044759 acc_pose: 0.837784 loss: 222.044759 2022/10/12 16:22:38 - mmengine - INFO - Epoch(train) [61][150/586] lr: 5.000000e-03 eta: 11:59:53 time: 0.523734 data_time: 0.055886 memory: 8713 loss_kpt: 225.829785 acc_pose: 0.811847 loss: 225.829785 2022/10/12 16:23:04 - mmengine - INFO - Epoch(train) [61][200/586] lr: 5.000000e-03 eta: 11:59:32 time: 0.525358 data_time: 0.059770 memory: 8713 loss_kpt: 220.454923 acc_pose: 0.755377 loss: 220.454923 2022/10/12 16:23:30 - mmengine - INFO - Epoch(train) [61][250/586] lr: 5.000000e-03 eta: 11:59:11 time: 0.516500 data_time: 0.059553 memory: 8713 loss_kpt: 221.876234 acc_pose: 0.769320 loss: 221.876234 2022/10/12 16:23:56 - mmengine - INFO - Epoch(train) [61][300/586] lr: 5.000000e-03 eta: 11:58:51 time: 0.529875 data_time: 0.054448 memory: 8713 loss_kpt: 221.700728 acc_pose: 0.808755 loss: 221.700728 2022/10/12 16:24:23 - mmengine - INFO - Epoch(train) [61][350/586] lr: 5.000000e-03 eta: 11:58:30 time: 0.522497 data_time: 0.059634 memory: 8713 loss_kpt: 226.136024 acc_pose: 0.784785 loss: 226.136024 2022/10/12 16:24:49 - mmengine - INFO - Epoch(train) [61][400/586] lr: 5.000000e-03 eta: 11:58:09 time: 0.522262 data_time: 0.055888 memory: 8713 loss_kpt: 222.883680 acc_pose: 0.824449 loss: 222.883680 2022/10/12 16:25:14 - mmengine - INFO - Epoch(train) [61][450/586] lr: 5.000000e-03 eta: 11:57:46 time: 0.507824 data_time: 0.056447 memory: 8713 loss_kpt: 218.279265 acc_pose: 0.743768 loss: 218.279265 2022/10/12 16:25:40 - mmengine - INFO - Epoch(train) [61][500/586] lr: 5.000000e-03 eta: 11:57:25 time: 0.524014 data_time: 0.057572 memory: 8713 loss_kpt: 220.157569 acc_pose: 0.834195 loss: 220.157569 2022/10/12 16:26:06 - mmengine - INFO - Epoch(train) [61][550/586] lr: 5.000000e-03 eta: 11:57:05 time: 0.523828 data_time: 0.052587 memory: 8713 loss_kpt: 221.142911 acc_pose: 0.832964 loss: 221.142911 2022/10/12 16:26:25 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:26:51 - mmengine - INFO - Epoch(train) [62][50/586] lr: 5.000000e-03 eta: 11:55:42 time: 0.518207 data_time: 0.068758 memory: 8713 loss_kpt: 219.322922 acc_pose: 0.736837 loss: 219.322922 2022/10/12 16:27:16 - mmengine - INFO - Epoch(train) [62][100/586] lr: 5.000000e-03 eta: 11:55:19 time: 0.502440 data_time: 0.056190 memory: 8713 loss_kpt: 218.265578 acc_pose: 0.815604 loss: 218.265578 2022/10/12 16:27:42 - mmengine - INFO - Epoch(train) [62][150/586] lr: 5.000000e-03 eta: 11:54:57 time: 0.514408 data_time: 0.058016 memory: 8713 loss_kpt: 221.803112 acc_pose: 0.851849 loss: 221.803112 2022/10/12 16:28:07 - mmengine - INFO - Epoch(train) [62][200/586] lr: 5.000000e-03 eta: 11:54:34 time: 0.502891 data_time: 0.057080 memory: 8713 loss_kpt: 220.881522 acc_pose: 0.794511 loss: 220.881522 2022/10/12 16:28:32 - mmengine - INFO - Epoch(train) [62][250/586] lr: 5.000000e-03 eta: 11:54:11 time: 0.505074 data_time: 0.056273 memory: 8713 loss_kpt: 226.407697 acc_pose: 0.639964 loss: 226.407697 2022/10/12 16:28:34 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:28:57 - mmengine - INFO - Epoch(train) [62][300/586] lr: 5.000000e-03 eta: 11:53:47 time: 0.504884 data_time: 0.056205 memory: 8713 loss_kpt: 216.747386 acc_pose: 0.838794 loss: 216.747386 2022/10/12 16:29:23 - mmengine - INFO - Epoch(train) [62][350/586] lr: 5.000000e-03 eta: 11:53:25 time: 0.512529 data_time: 0.055776 memory: 8713 loss_kpt: 223.334614 acc_pose: 0.859179 loss: 223.334614 2022/10/12 16:29:48 - mmengine - INFO - Epoch(train) [62][400/586] lr: 5.000000e-03 eta: 11:53:01 time: 0.496669 data_time: 0.053145 memory: 8713 loss_kpt: 222.437137 acc_pose: 0.778075 loss: 222.437137 2022/10/12 16:30:13 - mmengine - INFO - Epoch(train) [62][450/586] lr: 5.000000e-03 eta: 11:52:39 time: 0.508365 data_time: 0.057400 memory: 8713 loss_kpt: 222.882245 acc_pose: 0.802534 loss: 222.882245 2022/10/12 16:30:39 - mmengine - INFO - Epoch(train) [62][500/586] lr: 5.000000e-03 eta: 11:52:16 time: 0.512543 data_time: 0.056618 memory: 8713 loss_kpt: 221.577898 acc_pose: 0.836359 loss: 221.577898 2022/10/12 16:31:04 - mmengine - INFO - Epoch(train) [62][550/586] lr: 5.000000e-03 eta: 11:51:54 time: 0.512684 data_time: 0.054405 memory: 8713 loss_kpt: 220.078997 acc_pose: 0.744705 loss: 220.078997 2022/10/12 16:31:23 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:31:50 - mmengine - INFO - Epoch(train) [63][50/586] lr: 5.000000e-03 eta: 11:50:35 time: 0.536070 data_time: 0.073812 memory: 8713 loss_kpt: 220.520978 acc_pose: 0.811630 loss: 220.520978 2022/10/12 16:32:16 - mmengine - INFO - Epoch(train) [63][100/586] lr: 5.000000e-03 eta: 11:50:14 time: 0.520286 data_time: 0.056328 memory: 8713 loss_kpt: 223.633987 acc_pose: 0.743115 loss: 223.633987 2022/10/12 16:32:42 - mmengine - INFO - Epoch(train) [63][150/586] lr: 5.000000e-03 eta: 11:49:53 time: 0.525556 data_time: 0.058331 memory: 8713 loss_kpt: 225.381063 acc_pose: 0.782818 loss: 225.381063 2022/10/12 16:33:08 - mmengine - INFO - Epoch(train) [63][200/586] lr: 5.000000e-03 eta: 11:49:31 time: 0.515241 data_time: 0.060199 memory: 8713 loss_kpt: 222.657510 acc_pose: 0.669161 loss: 222.657510 2022/10/12 16:33:34 - mmengine - INFO - Epoch(train) [63][250/586] lr: 5.000000e-03 eta: 11:49:10 time: 0.516907 data_time: 0.062032 memory: 8713 loss_kpt: 223.066699 acc_pose: 0.792939 loss: 223.066699 2022/10/12 16:34:00 - mmengine - INFO - Epoch(train) [63][300/586] lr: 5.000000e-03 eta: 11:48:50 time: 0.532430 data_time: 0.060435 memory: 8713 loss_kpt: 221.164288 acc_pose: 0.810111 loss: 221.164288 2022/10/12 16:34:27 - mmengine - INFO - Epoch(train) [63][350/586] lr: 5.000000e-03 eta: 11:48:30 time: 0.530314 data_time: 0.062432 memory: 8713 loss_kpt: 224.851203 acc_pose: 0.729563 loss: 224.851203 2022/10/12 16:34:53 - mmengine - INFO - Epoch(train) [63][400/586] lr: 5.000000e-03 eta: 11:48:08 time: 0.517453 data_time: 0.058475 memory: 8713 loss_kpt: 220.199503 acc_pose: 0.823613 loss: 220.199503 2022/10/12 16:35:19 - mmengine - INFO - Epoch(train) [63][450/586] lr: 5.000000e-03 eta: 11:47:48 time: 0.529593 data_time: 0.062410 memory: 8713 loss_kpt: 219.052622 acc_pose: 0.737986 loss: 219.052622 2022/10/12 16:35:45 - mmengine - INFO - Epoch(train) [63][500/586] lr: 5.000000e-03 eta: 11:47:27 time: 0.526067 data_time: 0.061533 memory: 8713 loss_kpt: 218.764594 acc_pose: 0.852522 loss: 218.764594 2022/10/12 16:36:12 - mmengine - INFO - Epoch(train) [63][550/586] lr: 5.000000e-03 eta: 11:47:08 time: 0.539956 data_time: 0.065119 memory: 8713 loss_kpt: 223.806214 acc_pose: 0.777075 loss: 223.806214 2022/10/12 16:36:31 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:36:57 - mmengine - INFO - Epoch(train) [64][50/586] lr: 5.000000e-03 eta: 11:45:48 time: 0.521586 data_time: 0.066623 memory: 8713 loss_kpt: 220.035292 acc_pose: 0.851075 loss: 220.035292 2022/10/12 16:37:14 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:37:23 - mmengine - INFO - Epoch(train) [64][100/586] lr: 5.000000e-03 eta: 11:45:27 time: 0.522798 data_time: 0.057882 memory: 8713 loss_kpt: 220.597961 acc_pose: 0.782127 loss: 220.597961 2022/10/12 16:37:50 - mmengine - INFO - Epoch(train) [64][150/586] lr: 5.000000e-03 eta: 11:45:07 time: 0.534553 data_time: 0.060450 memory: 8713 loss_kpt: 220.503690 acc_pose: 0.774350 loss: 220.503690 2022/10/12 16:38:16 - mmengine - INFO - Epoch(train) [64][200/586] lr: 5.000000e-03 eta: 11:44:46 time: 0.522569 data_time: 0.057191 memory: 8713 loss_kpt: 215.891517 acc_pose: 0.846101 loss: 215.891517 2022/10/12 16:38:43 - mmengine - INFO - Epoch(train) [64][250/586] lr: 5.000000e-03 eta: 11:44:26 time: 0.528880 data_time: 0.064629 memory: 8713 loss_kpt: 219.405109 acc_pose: 0.812898 loss: 219.405109 2022/10/12 16:39:10 - mmengine - INFO - Epoch(train) [64][300/586] lr: 5.000000e-03 eta: 11:44:06 time: 0.537710 data_time: 0.055024 memory: 8713 loss_kpt: 216.495806 acc_pose: 0.755767 loss: 216.495806 2022/10/12 16:39:36 - mmengine - INFO - Epoch(train) [64][350/586] lr: 5.000000e-03 eta: 11:43:46 time: 0.528703 data_time: 0.059358 memory: 8713 loss_kpt: 222.696265 acc_pose: 0.825491 loss: 222.696265 2022/10/12 16:40:03 - mmengine - INFO - Epoch(train) [64][400/586] lr: 5.000000e-03 eta: 11:43:27 time: 0.545250 data_time: 0.064045 memory: 8713 loss_kpt: 224.943276 acc_pose: 0.849964 loss: 224.943276 2022/10/12 16:40:29 - mmengine - INFO - Epoch(train) [64][450/586] lr: 5.000000e-03 eta: 11:43:06 time: 0.523755 data_time: 0.057301 memory: 8713 loss_kpt: 225.011592 acc_pose: 0.799806 loss: 225.011592 2022/10/12 16:40:56 - mmengine - INFO - Epoch(train) [64][500/586] lr: 5.000000e-03 eta: 11:42:47 time: 0.539232 data_time: 0.055555 memory: 8713 loss_kpt: 223.164139 acc_pose: 0.835445 loss: 223.164139 2022/10/12 16:41:23 - mmengine - INFO - Epoch(train) [64][550/586] lr: 5.000000e-03 eta: 11:42:27 time: 0.527736 data_time: 0.061296 memory: 8713 loss_kpt: 226.422180 acc_pose: 0.825472 loss: 226.422180 2022/10/12 16:41:42 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:42:09 - mmengine - INFO - Epoch(train) [65][50/586] lr: 5.000000e-03 eta: 11:41:09 time: 0.535186 data_time: 0.074291 memory: 8713 loss_kpt: 223.047971 acc_pose: 0.759572 loss: 223.047971 2022/10/12 16:42:35 - mmengine - INFO - Epoch(train) [65][100/586] lr: 5.000000e-03 eta: 11:40:49 time: 0.533948 data_time: 0.057968 memory: 8713 loss_kpt: 228.822421 acc_pose: 0.726818 loss: 228.822421 2022/10/12 16:43:02 - mmengine - INFO - Epoch(train) [65][150/586] lr: 5.000000e-03 eta: 11:40:29 time: 0.536129 data_time: 0.058149 memory: 8713 loss_kpt: 221.815457 acc_pose: 0.823170 loss: 221.815457 2022/10/12 16:43:28 - mmengine - INFO - Epoch(train) [65][200/586] lr: 5.000000e-03 eta: 11:40:08 time: 0.520701 data_time: 0.053349 memory: 8713 loss_kpt: 221.392208 acc_pose: 0.793227 loss: 221.392208 2022/10/12 16:43:54 - mmengine - INFO - Epoch(train) [65][250/586] lr: 5.000000e-03 eta: 11:39:46 time: 0.516877 data_time: 0.055214 memory: 8713 loss_kpt: 221.009168 acc_pose: 0.828488 loss: 221.009168 2022/10/12 16:44:21 - mmengine - INFO - Epoch(train) [65][300/586] lr: 5.000000e-03 eta: 11:39:28 time: 0.547600 data_time: 0.057702 memory: 8713 loss_kpt: 221.744211 acc_pose: 0.860710 loss: 221.744211 2022/10/12 16:44:48 - mmengine - INFO - Epoch(train) [65][350/586] lr: 5.000000e-03 eta: 11:39:08 time: 0.536799 data_time: 0.059309 memory: 8713 loss_kpt: 217.976424 acc_pose: 0.797617 loss: 217.976424 2022/10/12 16:45:15 - mmengine - INFO - Epoch(train) [65][400/586] lr: 5.000000e-03 eta: 11:38:48 time: 0.534644 data_time: 0.057671 memory: 8713 loss_kpt: 222.657608 acc_pose: 0.840134 loss: 222.657608 2022/10/12 16:45:41 - mmengine - INFO - Epoch(train) [65][450/586] lr: 5.000000e-03 eta: 11:38:28 time: 0.526152 data_time: 0.058598 memory: 8713 loss_kpt: 218.302699 acc_pose: 0.811294 loss: 218.302699 2022/10/12 16:46:05 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:46:07 - mmengine - INFO - Epoch(train) [65][500/586] lr: 5.000000e-03 eta: 11:38:06 time: 0.522216 data_time: 0.056295 memory: 8713 loss_kpt: 218.310408 acc_pose: 0.827838 loss: 218.310408 2022/10/12 16:46:34 - mmengine - INFO - Epoch(train) [65][550/586] lr: 5.000000e-03 eta: 11:37:46 time: 0.529658 data_time: 0.057059 memory: 8713 loss_kpt: 221.725994 acc_pose: 0.777332 loss: 221.725994 2022/10/12 16:46:53 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:47:21 - mmengine - INFO - Epoch(train) [66][50/586] lr: 5.000000e-03 eta: 11:36:31 time: 0.553744 data_time: 0.067182 memory: 8713 loss_kpt: 218.626004 acc_pose: 0.737382 loss: 218.626004 2022/10/12 16:47:49 - mmengine - INFO - Epoch(train) [66][100/586] lr: 5.000000e-03 eta: 11:36:13 time: 0.549777 data_time: 0.056218 memory: 8713 loss_kpt: 218.068730 acc_pose: 0.769821 loss: 218.068730 2022/10/12 16:48:16 - mmengine - INFO - Epoch(train) [66][150/586] lr: 5.000000e-03 eta: 11:35:54 time: 0.544947 data_time: 0.054827 memory: 8713 loss_kpt: 221.961204 acc_pose: 0.822639 loss: 221.961204 2022/10/12 16:48:42 - mmengine - INFO - Epoch(train) [66][200/586] lr: 5.000000e-03 eta: 11:35:34 time: 0.533284 data_time: 0.057211 memory: 8713 loss_kpt: 224.568169 acc_pose: 0.812088 loss: 224.568169 2022/10/12 16:49:09 - mmengine - INFO - Epoch(train) [66][250/586] lr: 5.000000e-03 eta: 11:35:14 time: 0.537950 data_time: 0.058306 memory: 8713 loss_kpt: 218.861108 acc_pose: 0.816103 loss: 218.861108 2022/10/12 16:49:37 - mmengine - INFO - Epoch(train) [66][300/586] lr: 5.000000e-03 eta: 11:34:56 time: 0.551243 data_time: 0.061908 memory: 8713 loss_kpt: 219.652744 acc_pose: 0.784819 loss: 219.652744 2022/10/12 16:50:04 - mmengine - INFO - Epoch(train) [66][350/586] lr: 5.000000e-03 eta: 11:34:38 time: 0.549235 data_time: 0.060900 memory: 8713 loss_kpt: 219.238905 acc_pose: 0.810490 loss: 219.238905 2022/10/12 16:50:31 - mmengine - INFO - Epoch(train) [66][400/586] lr: 5.000000e-03 eta: 11:34:17 time: 0.528141 data_time: 0.056445 memory: 8713 loss_kpt: 224.537458 acc_pose: 0.793834 loss: 224.537458 2022/10/12 16:50:57 - mmengine - INFO - Epoch(train) [66][450/586] lr: 5.000000e-03 eta: 11:33:56 time: 0.523637 data_time: 0.060040 memory: 8713 loss_kpt: 219.780518 acc_pose: 0.793834 loss: 219.780518 2022/10/12 16:51:23 - mmengine - INFO - Epoch(train) [66][500/586] lr: 5.000000e-03 eta: 11:33:35 time: 0.528683 data_time: 0.056808 memory: 8713 loss_kpt: 217.806536 acc_pose: 0.822411 loss: 217.806536 2022/10/12 16:51:49 - mmengine - INFO - Epoch(train) [66][550/586] lr: 5.000000e-03 eta: 11:33:13 time: 0.520691 data_time: 0.057910 memory: 8713 loss_kpt: 220.988155 acc_pose: 0.834535 loss: 220.988155 2022/10/12 16:52:08 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:52:34 - mmengine - INFO - Epoch(train) [67][50/586] lr: 5.000000e-03 eta: 11:31:57 time: 0.530885 data_time: 0.066539 memory: 8713 loss_kpt: 220.900030 acc_pose: 0.751177 loss: 220.900030 2022/10/12 16:53:00 - mmengine - INFO - Epoch(train) [67][100/586] lr: 5.000000e-03 eta: 11:31:34 time: 0.510850 data_time: 0.055574 memory: 8713 loss_kpt: 219.122086 acc_pose: 0.741782 loss: 219.122086 2022/10/12 16:53:26 - mmengine - INFO - Epoch(train) [67][150/586] lr: 5.000000e-03 eta: 11:31:12 time: 0.515062 data_time: 0.055536 memory: 8713 loss_kpt: 217.262874 acc_pose: 0.771340 loss: 217.262874 2022/10/12 16:53:51 - mmengine - INFO - Epoch(train) [67][200/586] lr: 5.000000e-03 eta: 11:30:50 time: 0.513925 data_time: 0.054472 memory: 8713 loss_kpt: 214.608444 acc_pose: 0.849511 loss: 214.608444 2022/10/12 16:54:17 - mmengine - INFO - Epoch(train) [67][250/586] lr: 5.000000e-03 eta: 11:30:26 time: 0.505293 data_time: 0.054321 memory: 8713 loss_kpt: 223.016732 acc_pose: 0.773749 loss: 223.016732 2022/10/12 16:54:42 - mmengine - INFO - Epoch(train) [67][300/586] lr: 5.000000e-03 eta: 11:30:04 time: 0.515868 data_time: 0.060286 memory: 8713 loss_kpt: 221.067346 acc_pose: 0.812365 loss: 221.067346 2022/10/12 16:54:55 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:55:08 - mmengine - INFO - Epoch(train) [67][350/586] lr: 5.000000e-03 eta: 11:29:41 time: 0.503309 data_time: 0.059564 memory: 8713 loss_kpt: 216.475417 acc_pose: 0.823776 loss: 216.475417 2022/10/12 16:55:33 - mmengine - INFO - Epoch(train) [67][400/586] lr: 5.000000e-03 eta: 11:29:17 time: 0.502505 data_time: 0.057821 memory: 8713 loss_kpt: 213.737529 acc_pose: 0.812610 loss: 213.737529 2022/10/12 16:55:59 - mmengine - INFO - Epoch(train) [67][450/586] lr: 5.000000e-03 eta: 11:28:56 time: 0.519761 data_time: 0.056891 memory: 8713 loss_kpt: 222.363994 acc_pose: 0.745595 loss: 222.363994 2022/10/12 16:56:24 - mmengine - INFO - Epoch(train) [67][500/586] lr: 5.000000e-03 eta: 11:28:33 time: 0.512274 data_time: 0.056220 memory: 8713 loss_kpt: 219.621821 acc_pose: 0.797762 loss: 219.621821 2022/10/12 16:56:51 - mmengine - INFO - Epoch(train) [67][550/586] lr: 5.000000e-03 eta: 11:28:12 time: 0.525555 data_time: 0.062052 memory: 8713 loss_kpt: 220.745028 acc_pose: 0.782701 loss: 220.745028 2022/10/12 16:57:09 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:57:37 - mmengine - INFO - Epoch(train) [68][50/586] lr: 5.000000e-03 eta: 11:26:58 time: 0.546665 data_time: 0.073562 memory: 8713 loss_kpt: 218.554932 acc_pose: 0.798201 loss: 218.554932 2022/10/12 16:58:03 - mmengine - INFO - Epoch(train) [68][100/586] lr: 5.000000e-03 eta: 11:26:37 time: 0.526522 data_time: 0.059090 memory: 8713 loss_kpt: 217.796158 acc_pose: 0.832256 loss: 217.796158 2022/10/12 16:58:29 - mmengine - INFO - Epoch(train) [68][150/586] lr: 5.000000e-03 eta: 11:26:16 time: 0.527854 data_time: 0.059354 memory: 8713 loss_kpt: 222.406238 acc_pose: 0.795749 loss: 222.406238 2022/10/12 16:58:56 - mmengine - INFO - Epoch(train) [68][200/586] lr: 5.000000e-03 eta: 11:25:55 time: 0.529620 data_time: 0.060860 memory: 8713 loss_kpt: 218.035075 acc_pose: 0.716457 loss: 218.035075 2022/10/12 16:59:22 - mmengine - INFO - Epoch(train) [68][250/586] lr: 5.000000e-03 eta: 11:25:33 time: 0.517085 data_time: 0.054898 memory: 8713 loss_kpt: 215.485848 acc_pose: 0.793577 loss: 215.485848 2022/10/12 16:59:48 - mmengine - INFO - Epoch(train) [68][300/586] lr: 5.000000e-03 eta: 11:25:12 time: 0.521251 data_time: 0.058799 memory: 8713 loss_kpt: 218.899870 acc_pose: 0.867810 loss: 218.899870 2022/10/12 17:00:14 - mmengine - INFO - Epoch(train) [68][350/586] lr: 5.000000e-03 eta: 11:24:51 time: 0.529392 data_time: 0.055565 memory: 8713 loss_kpt: 216.917557 acc_pose: 0.825001 loss: 216.917557 2022/10/12 17:00:40 - mmengine - INFO - Epoch(train) [68][400/586] lr: 5.000000e-03 eta: 11:24:29 time: 0.515884 data_time: 0.054221 memory: 8713 loss_kpt: 218.489302 acc_pose: 0.793628 loss: 218.489302 2022/10/12 17:01:06 - mmengine - INFO - Epoch(train) [68][450/586] lr: 5.000000e-03 eta: 11:24:06 time: 0.514215 data_time: 0.054814 memory: 8713 loss_kpt: 221.611046 acc_pose: 0.699783 loss: 221.611046 2022/10/12 17:01:31 - mmengine - INFO - Epoch(train) [68][500/586] lr: 5.000000e-03 eta: 11:23:43 time: 0.507387 data_time: 0.057368 memory: 8713 loss_kpt: 218.270046 acc_pose: 0.803123 loss: 218.270046 2022/10/12 17:01:58 - mmengine - INFO - Epoch(train) [68][550/586] lr: 5.000000e-03 eta: 11:23:23 time: 0.529187 data_time: 0.055003 memory: 8713 loss_kpt: 219.810428 acc_pose: 0.792773 loss: 219.810428 2022/10/12 17:02:17 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:02:43 - mmengine - INFO - Epoch(train) [69][50/586] lr: 5.000000e-03 eta: 11:22:06 time: 0.523662 data_time: 0.074335 memory: 8713 loss_kpt: 222.250121 acc_pose: 0.765983 loss: 222.250121 2022/10/12 17:03:09 - mmengine - INFO - Epoch(train) [69][100/586] lr: 5.000000e-03 eta: 11:21:44 time: 0.514469 data_time: 0.053817 memory: 8713 loss_kpt: 216.002661 acc_pose: 0.721107 loss: 216.002661 2022/10/12 17:03:35 - mmengine - INFO - Epoch(train) [69][150/586] lr: 5.000000e-03 eta: 11:21:22 time: 0.514304 data_time: 0.059528 memory: 8713 loss_kpt: 217.130247 acc_pose: 0.810107 loss: 217.130247 2022/10/12 17:03:35 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:04:00 - mmengine - INFO - Epoch(train) [69][200/586] lr: 5.000000e-03 eta: 11:20:59 time: 0.513275 data_time: 0.057275 memory: 8713 loss_kpt: 220.453839 acc_pose: 0.765835 loss: 220.453839 2022/10/12 17:04:26 - mmengine - INFO - Epoch(train) [69][250/586] lr: 5.000000e-03 eta: 11:20:38 time: 0.517844 data_time: 0.060147 memory: 8713 loss_kpt: 217.547080 acc_pose: 0.794620 loss: 217.547080 2022/10/12 17:04:52 - mmengine - INFO - Epoch(train) [69][300/586] lr: 5.000000e-03 eta: 11:20:15 time: 0.509726 data_time: 0.057215 memory: 8713 loss_kpt: 219.179212 acc_pose: 0.743525 loss: 219.179212 2022/10/12 17:05:17 - mmengine - INFO - Epoch(train) [69][350/586] lr: 5.000000e-03 eta: 11:19:52 time: 0.511504 data_time: 0.061417 memory: 8713 loss_kpt: 216.409270 acc_pose: 0.797603 loss: 216.409270 2022/10/12 17:05:42 - mmengine - INFO - Epoch(train) [69][400/586] lr: 5.000000e-03 eta: 11:19:27 time: 0.490695 data_time: 0.055833 memory: 8713 loss_kpt: 216.981089 acc_pose: 0.765510 loss: 216.981089 2022/10/12 17:06:07 - mmengine - INFO - Epoch(train) [69][450/586] lr: 5.000000e-03 eta: 11:19:04 time: 0.502734 data_time: 0.060763 memory: 8713 loss_kpt: 219.569296 acc_pose: 0.756964 loss: 219.569296 2022/10/12 17:06:32 - mmengine - INFO - Epoch(train) [69][500/586] lr: 5.000000e-03 eta: 11:18:41 time: 0.508771 data_time: 0.058830 memory: 8713 loss_kpt: 217.100036 acc_pose: 0.754112 loss: 217.100036 2022/10/12 17:06:58 - mmengine - INFO - Epoch(train) [69][550/586] lr: 5.000000e-03 eta: 11:18:18 time: 0.514333 data_time: 0.055919 memory: 8713 loss_kpt: 216.544773 acc_pose: 0.763462 loss: 216.544773 2022/10/12 17:07:16 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:07:43 - mmengine - INFO - Epoch(train) [70][50/586] lr: 5.000000e-03 eta: 11:17:05 time: 0.542653 data_time: 0.074039 memory: 8713 loss_kpt: 221.969796 acc_pose: 0.796232 loss: 221.969796 2022/10/12 17:08:08 - mmengine - INFO - Epoch(train) [70][100/586] lr: 5.000000e-03 eta: 11:16:42 time: 0.507819 data_time: 0.061297 memory: 8713 loss_kpt: 217.373934 acc_pose: 0.816909 loss: 217.373934 2022/10/12 17:08:34 - mmengine - INFO - Epoch(train) [70][150/586] lr: 5.000000e-03 eta: 11:16:21 time: 0.522726 data_time: 0.061284 memory: 8713 loss_kpt: 216.125075 acc_pose: 0.826192 loss: 216.125075 2022/10/12 17:09:00 - mmengine - INFO - Epoch(train) [70][200/586] lr: 5.000000e-03 eta: 11:15:59 time: 0.516657 data_time: 0.064364 memory: 8713 loss_kpt: 220.863560 acc_pose: 0.824405 loss: 220.863560 2022/10/12 17:09:26 - mmengine - INFO - Epoch(train) [70][250/586] lr: 5.000000e-03 eta: 11:15:36 time: 0.516426 data_time: 0.058122 memory: 8713 loss_kpt: 222.785649 acc_pose: 0.708409 loss: 222.785649 2022/10/12 17:09:52 - mmengine - INFO - Epoch(train) [70][300/586] lr: 5.000000e-03 eta: 11:15:14 time: 0.513003 data_time: 0.057870 memory: 8713 loss_kpt: 219.747388 acc_pose: 0.766404 loss: 219.747388 2022/10/12 17:10:18 - mmengine - INFO - Epoch(train) [70][350/586] lr: 5.000000e-03 eta: 11:14:52 time: 0.516930 data_time: 0.056295 memory: 8713 loss_kpt: 216.230469 acc_pose: 0.764711 loss: 216.230469 2022/10/12 17:10:43 - mmengine - INFO - Epoch(train) [70][400/586] lr: 5.000000e-03 eta: 11:14:29 time: 0.509632 data_time: 0.058768 memory: 8713 loss_kpt: 217.054717 acc_pose: 0.818050 loss: 217.054717 2022/10/12 17:11:09 - mmengine - INFO - Epoch(train) [70][450/586] lr: 5.000000e-03 eta: 11:14:06 time: 0.511099 data_time: 0.056538 memory: 8713 loss_kpt: 219.371854 acc_pose: 0.841897 loss: 219.371854 2022/10/12 17:11:35 - mmengine - INFO - Epoch(train) [70][500/586] lr: 5.000000e-03 eta: 11:13:44 time: 0.517027 data_time: 0.061933 memory: 8713 loss_kpt: 222.249429 acc_pose: 0.800125 loss: 222.249429 2022/10/12 17:12:01 - mmengine - INFO - Epoch(train) [70][550/586] lr: 5.000000e-03 eta: 11:13:22 time: 0.520306 data_time: 0.056292 memory: 8713 loss_kpt: 219.919155 acc_pose: 0.657364 loss: 219.919155 2022/10/12 17:12:09 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:12:19 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:12:19 - mmengine - INFO - Saving checkpoint at 70 epochs 2022/10/12 17:12:32 - mmengine - INFO - Epoch(val) [70][50/407] eta: 0:01:11 time: 0.200848 data_time: 0.013040 memory: 8713 2022/10/12 17:12:42 - mmengine - INFO - Epoch(val) [70][100/407] eta: 0:00:59 time: 0.192831 data_time: 0.007945 memory: 1759 2022/10/12 17:12:52 - mmengine - INFO - Epoch(val) [70][150/407] eta: 0:00:50 time: 0.195630 data_time: 0.008486 memory: 1759 2022/10/12 17:13:02 - mmengine - INFO - Epoch(val) [70][200/407] eta: 0:00:40 time: 0.195699 data_time: 0.008255 memory: 1759 2022/10/12 17:13:11 - mmengine - INFO - Epoch(val) [70][250/407] eta: 0:00:30 time: 0.194859 data_time: 0.008406 memory: 1759 2022/10/12 17:13:21 - mmengine - INFO - Epoch(val) [70][300/407] eta: 0:00:20 time: 0.196110 data_time: 0.008508 memory: 1759 2022/10/12 17:13:31 - mmengine - INFO - Epoch(val) [70][350/407] eta: 0:00:11 time: 0.194699 data_time: 0.008350 memory: 1759 2022/10/12 17:13:40 - mmengine - INFO - Epoch(val) [70][400/407] eta: 0:00:01 time: 0.192163 data_time: 0.007971 memory: 1759 2022/10/12 17:13:54 - mmengine - INFO - Evaluating CocoMetric... 2022/10/12 17:14:10 - mmengine - INFO - Epoch(val) [70][407/407] coco/AP: 0.696059 coco/AP .5: 0.881083 coco/AP .75: 0.772531 coco/AP (M): 0.667771 coco/AP (L): 0.753770 coco/AR: 0.766058 coco/AR .5: 0.923331 coco/AR .75: 0.829503 coco/AR (M): 0.723327 coco/AR (L): 0.824935 2022/10/12 17:14:10 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/liqikai/openmmlab/pt112cu113py38/mmpose/work_dirs/20221012/rsn2x/best_coco/AP_epoch_60.pth is removed 2022/10/12 17:14:12 - mmengine - INFO - The best checkpoint with 0.6961 coco/AP at 70 epoch is saved to best_coco/AP_epoch_70.pth. 2022/10/12 17:14:39 - mmengine - INFO - Epoch(train) [71][50/586] lr: 5.000000e-03 eta: 11:12:08 time: 0.525907 data_time: 0.063133 memory: 8713 loss_kpt: 220.357050 acc_pose: 0.741877 loss: 220.357050 2022/10/12 17:15:05 - mmengine - INFO - Epoch(train) [71][100/586] lr: 5.000000e-03 eta: 11:11:47 time: 0.524470 data_time: 0.056570 memory: 8713 loss_kpt: 220.084976 acc_pose: 0.841386 loss: 220.084976 2022/10/12 17:15:31 - mmengine - INFO - Epoch(train) [71][150/586] lr: 5.000000e-03 eta: 11:11:25 time: 0.525354 data_time: 0.058006 memory: 8713 loss_kpt: 219.666381 acc_pose: 0.738712 loss: 219.666381 2022/10/12 17:15:57 - mmengine - INFO - Epoch(train) [71][200/586] lr: 5.000000e-03 eta: 11:11:04 time: 0.520739 data_time: 0.053714 memory: 8713 loss_kpt: 220.861854 acc_pose: 0.826822 loss: 220.861854 2022/10/12 17:16:23 - mmengine - INFO - Epoch(train) [71][250/586] lr: 5.000000e-03 eta: 11:10:41 time: 0.513137 data_time: 0.054455 memory: 8713 loss_kpt: 219.100436 acc_pose: 0.874180 loss: 219.100436 2022/10/12 17:16:49 - mmengine - INFO - Epoch(train) [71][300/586] lr: 5.000000e-03 eta: 11:10:19 time: 0.520177 data_time: 0.060097 memory: 8713 loss_kpt: 220.502222 acc_pose: 0.710018 loss: 220.502222 2022/10/12 17:17:15 - mmengine - INFO - Epoch(train) [71][350/586] lr: 5.000000e-03 eta: 11:09:58 time: 0.523959 data_time: 0.055111 memory: 8713 loss_kpt: 219.518070 acc_pose: 0.788898 loss: 219.518070 2022/10/12 17:17:41 - mmengine - INFO - Epoch(train) [71][400/586] lr: 5.000000e-03 eta: 11:09:36 time: 0.517186 data_time: 0.054890 memory: 8713 loss_kpt: 217.735634 acc_pose: 0.827442 loss: 217.735634 2022/10/12 17:18:07 - mmengine - INFO - Epoch(train) [71][450/586] lr: 5.000000e-03 eta: 11:09:14 time: 0.520939 data_time: 0.059154 memory: 8713 loss_kpt: 219.768854 acc_pose: 0.718320 loss: 219.768854 2022/10/12 17:18:33 - mmengine - INFO - Epoch(train) [71][500/586] lr: 5.000000e-03 eta: 11:08:52 time: 0.516429 data_time: 0.056162 memory: 8713 loss_kpt: 215.193211 acc_pose: 0.820984 loss: 215.193211 2022/10/12 17:18:59 - mmengine - INFO - Epoch(train) [71][550/586] lr: 5.000000e-03 eta: 11:08:30 time: 0.523266 data_time: 0.056218 memory: 8713 loss_kpt: 223.422326 acc_pose: 0.802977 loss: 223.422326 2022/10/12 17:19:18 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:19:45 - mmengine - INFO - Epoch(train) [72][50/586] lr: 5.000000e-03 eta: 11:07:18 time: 0.538223 data_time: 0.078302 memory: 8713 loss_kpt: 216.694915 acc_pose: 0.814301 loss: 216.694915 2022/10/12 17:20:10 - mmengine - INFO - Epoch(train) [72][100/586] lr: 5.000000e-03 eta: 11:06:56 time: 0.517162 data_time: 0.060951 memory: 8713 loss_kpt: 218.383835 acc_pose: 0.743461 loss: 218.383835 2022/10/12 17:20:37 - mmengine - INFO - Epoch(train) [72][150/586] lr: 5.000000e-03 eta: 11:06:34 time: 0.524225 data_time: 0.062542 memory: 8713 loss_kpt: 219.502576 acc_pose: 0.775848 loss: 219.502576 2022/10/12 17:21:03 - mmengine - INFO - Epoch(train) [72][200/586] lr: 5.000000e-03 eta: 11:06:13 time: 0.531240 data_time: 0.057602 memory: 8713 loss_kpt: 218.464186 acc_pose: 0.797097 loss: 218.464186 2022/10/12 17:21:30 - mmengine - INFO - Epoch(train) [72][250/586] lr: 5.000000e-03 eta: 11:05:52 time: 0.530272 data_time: 0.057819 memory: 8713 loss_kpt: 219.921309 acc_pose: 0.796111 loss: 219.921309 2022/10/12 17:21:56 - mmengine - INFO - Epoch(train) [72][300/586] lr: 5.000000e-03 eta: 11:05:30 time: 0.518411 data_time: 0.060419 memory: 8713 loss_kpt: 224.827875 acc_pose: 0.771273 loss: 224.827875 2022/10/12 17:22:22 - mmengine - INFO - Epoch(train) [72][350/586] lr: 5.000000e-03 eta: 11:05:10 time: 0.535486 data_time: 0.066142 memory: 8713 loss_kpt: 218.621530 acc_pose: 0.832116 loss: 218.621530 2022/10/12 17:22:46 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:22:49 - mmengine - INFO - Epoch(train) [72][400/586] lr: 5.000000e-03 eta: 11:04:49 time: 0.532464 data_time: 0.057228 memory: 8713 loss_kpt: 214.357249 acc_pose: 0.819263 loss: 214.357249 2022/10/12 17:23:16 - mmengine - INFO - Epoch(train) [72][450/586] lr: 5.000000e-03 eta: 11:04:28 time: 0.530029 data_time: 0.057777 memory: 8713 loss_kpt: 217.225190 acc_pose: 0.780389 loss: 217.225190 2022/10/12 17:23:42 - mmengine - INFO - Epoch(train) [72][500/586] lr: 5.000000e-03 eta: 11:04:06 time: 0.520141 data_time: 0.057599 memory: 8713 loss_kpt: 213.135594 acc_pose: 0.807927 loss: 213.135594 2022/10/12 17:24:08 - mmengine - INFO - Epoch(train) [72][550/586] lr: 5.000000e-03 eta: 11:03:45 time: 0.521930 data_time: 0.056521 memory: 8713 loss_kpt: 216.863978 acc_pose: 0.801723 loss: 216.863978 2022/10/12 17:24:26 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:24:53 - mmengine - INFO - Epoch(train) [73][50/586] lr: 5.000000e-03 eta: 11:02:32 time: 0.531502 data_time: 0.070005 memory: 8713 loss_kpt: 217.485217 acc_pose: 0.848109 loss: 217.485217 2022/10/12 17:25:20 - mmengine - INFO - Epoch(train) [73][100/586] lr: 5.000000e-03 eta: 11:02:11 time: 0.532019 data_time: 0.061897 memory: 8713 loss_kpt: 217.419355 acc_pose: 0.831663 loss: 217.419355 2022/10/12 17:25:47 - mmengine - INFO - Epoch(train) [73][150/586] lr: 5.000000e-03 eta: 11:01:52 time: 0.543318 data_time: 0.062741 memory: 8713 loss_kpt: 218.591441 acc_pose: 0.853093 loss: 218.591441 2022/10/12 17:26:14 - mmengine - INFO - Epoch(train) [73][200/586] lr: 5.000000e-03 eta: 11:01:32 time: 0.538957 data_time: 0.060495 memory: 8713 loss_kpt: 218.273124 acc_pose: 0.826381 loss: 218.273124 2022/10/12 17:26:41 - mmengine - INFO - Epoch(train) [73][250/586] lr: 5.000000e-03 eta: 11:01:11 time: 0.535839 data_time: 0.060974 memory: 8713 loss_kpt: 214.940470 acc_pose: 0.784659 loss: 214.940470 2022/10/12 17:27:07 - mmengine - INFO - Epoch(train) [73][300/586] lr: 5.000000e-03 eta: 11:00:50 time: 0.524695 data_time: 0.060791 memory: 8713 loss_kpt: 217.626139 acc_pose: 0.810129 loss: 217.626139 2022/10/12 17:27:33 - mmengine - INFO - Epoch(train) [73][350/586] lr: 5.000000e-03 eta: 11:00:28 time: 0.526067 data_time: 0.063093 memory: 8713 loss_kpt: 217.097270 acc_pose: 0.753997 loss: 217.097270 2022/10/12 17:28:00 - mmengine - INFO - Epoch(train) [73][400/586] lr: 5.000000e-03 eta: 11:00:07 time: 0.532227 data_time: 0.059047 memory: 8713 loss_kpt: 216.785824 acc_pose: 0.813655 loss: 216.785824 2022/10/12 17:28:27 - mmengine - INFO - Epoch(train) [73][450/586] lr: 5.000000e-03 eta: 10:59:47 time: 0.535176 data_time: 0.057701 memory: 8713 loss_kpt: 217.880631 acc_pose: 0.830933 loss: 217.880631 2022/10/12 17:28:53 - mmengine - INFO - Epoch(train) [73][500/586] lr: 5.000000e-03 eta: 10:59:25 time: 0.526115 data_time: 0.058180 memory: 8713 loss_kpt: 218.242041 acc_pose: 0.777787 loss: 218.242041 2022/10/12 17:29:19 - mmengine - INFO - Epoch(train) [73][550/586] lr: 5.000000e-03 eta: 10:59:05 time: 0.531743 data_time: 0.059948 memory: 8713 loss_kpt: 219.143301 acc_pose: 0.831187 loss: 219.143301 2022/10/12 17:29:38 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:30:05 - mmengine - INFO - Epoch(train) [74][50/586] lr: 5.000000e-03 eta: 10:57:52 time: 0.527852 data_time: 0.067335 memory: 8713 loss_kpt: 218.830036 acc_pose: 0.808326 loss: 218.830036 2022/10/12 17:30:30 - mmengine - INFO - Epoch(train) [74][100/586] lr: 5.000000e-03 eta: 10:57:29 time: 0.506017 data_time: 0.058746 memory: 8713 loss_kpt: 213.868596 acc_pose: 0.810875 loss: 213.868596 2022/10/12 17:30:55 - mmengine - INFO - Epoch(train) [74][150/586] lr: 5.000000e-03 eta: 10:57:06 time: 0.504967 data_time: 0.061862 memory: 8713 loss_kpt: 217.423919 acc_pose: 0.761983 loss: 217.423919 2022/10/12 17:31:20 - mmengine - INFO - Epoch(train) [74][200/586] lr: 5.000000e-03 eta: 10:56:42 time: 0.501332 data_time: 0.054117 memory: 8713 loss_kpt: 217.133365 acc_pose: 0.855633 loss: 217.133365 2022/10/12 17:31:31 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:31:45 - mmengine - INFO - Epoch(train) [74][250/586] lr: 5.000000e-03 eta: 10:56:19 time: 0.505476 data_time: 0.055434 memory: 8713 loss_kpt: 218.626891 acc_pose: 0.776756 loss: 218.626891 2022/10/12 17:32:11 - mmengine - INFO - Epoch(train) [74][300/586] lr: 5.000000e-03 eta: 10:55:56 time: 0.509936 data_time: 0.054613 memory: 8713 loss_kpt: 215.466829 acc_pose: 0.839564 loss: 215.466829 2022/10/12 17:32:36 - mmengine - INFO - Epoch(train) [74][350/586] lr: 5.000000e-03 eta: 10:55:33 time: 0.509284 data_time: 0.064115 memory: 8713 loss_kpt: 218.698745 acc_pose: 0.858244 loss: 218.698745 2022/10/12 17:33:02 - mmengine - INFO - Epoch(train) [74][400/586] lr: 5.000000e-03 eta: 10:55:10 time: 0.510054 data_time: 0.054958 memory: 8713 loss_kpt: 215.613816 acc_pose: 0.775958 loss: 215.613816 2022/10/12 17:33:27 - mmengine - INFO - Epoch(train) [74][450/586] lr: 5.000000e-03 eta: 10:54:46 time: 0.505043 data_time: 0.057009 memory: 8713 loss_kpt: 218.658370 acc_pose: 0.764458 loss: 218.658370 2022/10/12 17:33:53 - mmengine - INFO - Epoch(train) [74][500/586] lr: 5.000000e-03 eta: 10:54:23 time: 0.507863 data_time: 0.058565 memory: 8713 loss_kpt: 216.879120 acc_pose: 0.838638 loss: 216.879120 2022/10/12 17:34:18 - mmengine - INFO - Epoch(train) [74][550/586] lr: 5.000000e-03 eta: 10:54:00 time: 0.507925 data_time: 0.059375 memory: 8713 loss_kpt: 221.444797 acc_pose: 0.837241 loss: 221.444797 2022/10/12 17:34:36 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:35:03 - mmengine - INFO - Epoch(train) [75][50/586] lr: 5.000000e-03 eta: 10:52:50 time: 0.543401 data_time: 0.077401 memory: 8713 loss_kpt: 218.417063 acc_pose: 0.810252 loss: 218.417063 2022/10/12 17:35:29 - mmengine - INFO - Epoch(train) [75][100/586] lr: 5.000000e-03 eta: 10:52:27 time: 0.513372 data_time: 0.057957 memory: 8713 loss_kpt: 218.215439 acc_pose: 0.812797 loss: 218.215439 2022/10/12 17:35:55 - mmengine - INFO - Epoch(train) [75][150/586] lr: 5.000000e-03 eta: 10:52:05 time: 0.515392 data_time: 0.061832 memory: 8713 loss_kpt: 217.829978 acc_pose: 0.771555 loss: 217.829978 2022/10/12 17:36:21 - mmengine - INFO - Epoch(train) [75][200/586] lr: 5.000000e-03 eta: 10:51:42 time: 0.515243 data_time: 0.057298 memory: 8713 loss_kpt: 217.977740 acc_pose: 0.818405 loss: 217.977740 2022/10/12 17:36:46 - mmengine - INFO - Epoch(train) [75][250/586] lr: 5.000000e-03 eta: 10:51:20 time: 0.517748 data_time: 0.061474 memory: 8713 loss_kpt: 219.630752 acc_pose: 0.817613 loss: 219.630752 2022/10/12 17:37:12 - mmengine - INFO - Epoch(train) [75][300/586] lr: 5.000000e-03 eta: 10:50:58 time: 0.518269 data_time: 0.058606 memory: 8713 loss_kpt: 219.078774 acc_pose: 0.715366 loss: 219.078774 2022/10/12 17:37:39 - mmengine - INFO - Epoch(train) [75][350/586] lr: 5.000000e-03 eta: 10:50:37 time: 0.535581 data_time: 0.064481 memory: 8713 loss_kpt: 219.136833 acc_pose: 0.785733 loss: 219.136833 2022/10/12 17:38:06 - mmengine - INFO - Epoch(train) [75][400/586] lr: 5.000000e-03 eta: 10:50:17 time: 0.537205 data_time: 0.058594 memory: 8713 loss_kpt: 218.730386 acc_pose: 0.744610 loss: 218.730386 2022/10/12 17:38:33 - mmengine - INFO - Epoch(train) [75][450/586] lr: 5.000000e-03 eta: 10:49:56 time: 0.539750 data_time: 0.059192 memory: 8713 loss_kpt: 217.360667 acc_pose: 0.852690 loss: 217.360667 2022/10/12 17:39:01 - mmengine - INFO - Epoch(train) [75][500/586] lr: 5.000000e-03 eta: 10:49:37 time: 0.553154 data_time: 0.056757 memory: 8713 loss_kpt: 219.391622 acc_pose: 0.881732 loss: 219.391622 2022/10/12 17:39:27 - mmengine - INFO - Epoch(train) [75][550/586] lr: 5.000000e-03 eta: 10:49:16 time: 0.530984 data_time: 0.058200 memory: 8713 loss_kpt: 217.420007 acc_pose: 0.764852 loss: 217.420007 2022/10/12 17:39:46 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:40:13 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:40:13 - mmengine - INFO - Epoch(train) [76][50/586] lr: 5.000000e-03 eta: 10:48:06 time: 0.532490 data_time: 0.070390 memory: 8713 loss_kpt: 215.108251 acc_pose: 0.780476 loss: 215.108251 2022/10/12 17:40:38 - mmengine - INFO - Epoch(train) [76][100/586] lr: 5.000000e-03 eta: 10:47:43 time: 0.507940 data_time: 0.058607 memory: 8713 loss_kpt: 217.109052 acc_pose: 0.803844 loss: 217.109052 2022/10/12 17:41:04 - mmengine - INFO - Epoch(train) [76][150/586] lr: 5.000000e-03 eta: 10:47:21 time: 0.523268 data_time: 0.056383 memory: 8713 loss_kpt: 214.432297 acc_pose: 0.760938 loss: 214.432297 2022/10/12 17:41:30 - mmengine - INFO - Epoch(train) [76][200/586] lr: 5.000000e-03 eta: 10:46:58 time: 0.516816 data_time: 0.062016 memory: 8713 loss_kpt: 218.338545 acc_pose: 0.802123 loss: 218.338545 2022/10/12 17:41:56 - mmengine - INFO - Epoch(train) [76][250/586] lr: 5.000000e-03 eta: 10:46:36 time: 0.519976 data_time: 0.058242 memory: 8713 loss_kpt: 215.110370 acc_pose: 0.743402 loss: 215.110370 2022/10/12 17:42:22 - mmengine - INFO - Epoch(train) [76][300/586] lr: 5.000000e-03 eta: 10:46:14 time: 0.520801 data_time: 0.058502 memory: 8713 loss_kpt: 217.720279 acc_pose: 0.840341 loss: 217.720279 2022/10/12 17:42:48 - mmengine - INFO - Epoch(train) [76][350/586] lr: 5.000000e-03 eta: 10:45:52 time: 0.515218 data_time: 0.060054 memory: 8713 loss_kpt: 215.064174 acc_pose: 0.802706 loss: 215.064174 2022/10/12 17:43:14 - mmengine - INFO - Epoch(train) [76][400/586] lr: 5.000000e-03 eta: 10:45:30 time: 0.524671 data_time: 0.059855 memory: 8713 loss_kpt: 216.338721 acc_pose: 0.767506 loss: 216.338721 2022/10/12 17:43:40 - mmengine - INFO - Epoch(train) [76][450/586] lr: 5.000000e-03 eta: 10:45:08 time: 0.523092 data_time: 0.058696 memory: 8713 loss_kpt: 216.283377 acc_pose: 0.807370 loss: 216.283377 2022/10/12 17:44:06 - mmengine - INFO - Epoch(train) [76][500/586] lr: 5.000000e-03 eta: 10:44:45 time: 0.513735 data_time: 0.058126 memory: 8713 loss_kpt: 213.606345 acc_pose: 0.835788 loss: 213.606345 2022/10/12 17:44:32 - mmengine - INFO - Epoch(train) [76][550/586] lr: 5.000000e-03 eta: 10:44:23 time: 0.512330 data_time: 0.056791 memory: 8713 loss_kpt: 217.705732 acc_pose: 0.840334 loss: 217.705732 2022/10/12 17:44:50 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:45:17 - mmengine - INFO - Epoch(train) [77][50/586] lr: 5.000000e-03 eta: 10:43:13 time: 0.532582 data_time: 0.071702 memory: 8713 loss_kpt: 219.294955 acc_pose: 0.824003 loss: 219.294955 2022/10/12 17:45:43 - mmengine - INFO - Epoch(train) [77][100/586] lr: 5.000000e-03 eta: 10:42:51 time: 0.521732 data_time: 0.061249 memory: 8713 loss_kpt: 217.125672 acc_pose: 0.809818 loss: 217.125672 2022/10/12 17:46:09 - mmengine - INFO - Epoch(train) [77][150/586] lr: 5.000000e-03 eta: 10:42:30 time: 0.530270 data_time: 0.062407 memory: 8713 loss_kpt: 210.615579 acc_pose: 0.815426 loss: 210.615579 2022/10/12 17:46:35 - mmengine - INFO - Epoch(train) [77][200/586] lr: 5.000000e-03 eta: 10:42:07 time: 0.517082 data_time: 0.058943 memory: 8713 loss_kpt: 220.412836 acc_pose: 0.832582 loss: 220.412836 2022/10/12 17:47:01 - mmengine - INFO - Epoch(train) [77][250/586] lr: 5.000000e-03 eta: 10:41:45 time: 0.518570 data_time: 0.057019 memory: 8713 loss_kpt: 215.201314 acc_pose: 0.814854 loss: 215.201314 2022/10/12 17:47:27 - mmengine - INFO - Epoch(train) [77][300/586] lr: 5.000000e-03 eta: 10:41:22 time: 0.517015 data_time: 0.057144 memory: 8713 loss_kpt: 220.230125 acc_pose: 0.782643 loss: 220.230125 2022/10/12 17:47:52 - mmengine - INFO - Epoch(train) [77][350/586] lr: 5.000000e-03 eta: 10:41:00 time: 0.511448 data_time: 0.059256 memory: 8713 loss_kpt: 216.771968 acc_pose: 0.910137 loss: 216.771968 2022/10/12 17:48:18 - mmengine - INFO - Epoch(train) [77][400/586] lr: 5.000000e-03 eta: 10:40:37 time: 0.511975 data_time: 0.058875 memory: 8713 loss_kpt: 213.949600 acc_pose: 0.823901 loss: 213.949600 2022/10/12 17:48:44 - mmengine - INFO - Epoch(train) [77][450/586] lr: 5.000000e-03 eta: 10:40:14 time: 0.518132 data_time: 0.065162 memory: 8713 loss_kpt: 213.477715 acc_pose: 0.805563 loss: 213.477715 2022/10/12 17:48:51 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:49:10 - mmengine - INFO - Epoch(train) [77][500/586] lr: 5.000000e-03 eta: 10:39:52 time: 0.512825 data_time: 0.060867 memory: 8713 loss_kpt: 218.834914 acc_pose: 0.766804 loss: 218.834914 2022/10/12 17:49:36 - mmengine - INFO - Epoch(train) [77][550/586] lr: 5.000000e-03 eta: 10:39:30 time: 0.525036 data_time: 0.062206 memory: 8713 loss_kpt: 218.318498 acc_pose: 0.837492 loss: 218.318498 2022/10/12 17:49:55 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:50:22 - mmengine - INFO - Epoch(train) [78][50/586] lr: 5.000000e-03 eta: 10:38:21 time: 0.544220 data_time: 0.070571 memory: 8713 loss_kpt: 216.437444 acc_pose: 0.836472 loss: 216.437444 2022/10/12 17:50:48 - mmengine - INFO - Epoch(train) [78][100/586] lr: 5.000000e-03 eta: 10:38:00 time: 0.527969 data_time: 0.058238 memory: 8713 loss_kpt: 214.963973 acc_pose: 0.781391 loss: 214.963973 2022/10/12 17:51:14 - mmengine - INFO - Epoch(train) [78][150/586] lr: 5.000000e-03 eta: 10:37:38 time: 0.519900 data_time: 0.057176 memory: 8713 loss_kpt: 216.949304 acc_pose: 0.867351 loss: 216.949304 2022/10/12 17:51:40 - mmengine - INFO - Epoch(train) [78][200/586] lr: 5.000000e-03 eta: 10:37:16 time: 0.520375 data_time: 0.052834 memory: 8713 loss_kpt: 213.502852 acc_pose: 0.850708 loss: 213.502852 2022/10/12 17:52:06 - mmengine - INFO - Epoch(train) [78][250/586] lr: 5.000000e-03 eta: 10:36:54 time: 0.521250 data_time: 0.056920 memory: 8713 loss_kpt: 222.059536 acc_pose: 0.837717 loss: 222.059536 2022/10/12 17:52:33 - mmengine - INFO - Epoch(train) [78][300/586] lr: 5.000000e-03 eta: 10:36:32 time: 0.524838 data_time: 0.057411 memory: 8713 loss_kpt: 218.908906 acc_pose: 0.845911 loss: 218.908906 2022/10/12 17:52:58 - mmengine - INFO - Epoch(train) [78][350/586] lr: 5.000000e-03 eta: 10:36:09 time: 0.516980 data_time: 0.058619 memory: 8713 loss_kpt: 217.899813 acc_pose: 0.782619 loss: 217.899813 2022/10/12 17:53:24 - mmengine - INFO - Epoch(train) [78][400/586] lr: 5.000000e-03 eta: 10:35:47 time: 0.514493 data_time: 0.052346 memory: 8713 loss_kpt: 214.637718 acc_pose: 0.822973 loss: 214.637718 2022/10/12 17:53:50 - mmengine - INFO - Epoch(train) [78][450/586] lr: 5.000000e-03 eta: 10:35:24 time: 0.514354 data_time: 0.056011 memory: 8713 loss_kpt: 216.077863 acc_pose: 0.810275 loss: 216.077863 2022/10/12 17:54:16 - mmengine - INFO - Epoch(train) [78][500/586] lr: 5.000000e-03 eta: 10:35:01 time: 0.513732 data_time: 0.059375 memory: 8713 loss_kpt: 216.601738 acc_pose: 0.807689 loss: 216.601738 2022/10/12 17:54:41 - mmengine - INFO - Epoch(train) [78][550/586] lr: 5.000000e-03 eta: 10:34:38 time: 0.514111 data_time: 0.060813 memory: 8713 loss_kpt: 212.156984 acc_pose: 0.855068 loss: 212.156984 2022/10/12 17:55:00 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:55:27 - mmengine - INFO - Epoch(train) [79][50/586] lr: 5.000000e-03 eta: 10:33:31 time: 0.542976 data_time: 0.074308 memory: 8713 loss_kpt: 212.785689 acc_pose: 0.840652 loss: 212.785689 2022/10/12 17:55:53 - mmengine - INFO - Epoch(train) [79][100/586] lr: 5.000000e-03 eta: 10:33:08 time: 0.516197 data_time: 0.054031 memory: 8713 loss_kpt: 214.926637 acc_pose: 0.853748 loss: 214.926637 2022/10/12 17:56:19 - mmengine - INFO - Epoch(train) [79][150/586] lr: 5.000000e-03 eta: 10:32:46 time: 0.521923 data_time: 0.062740 memory: 8713 loss_kpt: 212.665088 acc_pose: 0.796631 loss: 212.665088 2022/10/12 17:56:44 - mmengine - INFO - Epoch(train) [79][200/586] lr: 5.000000e-03 eta: 10:32:22 time: 0.503984 data_time: 0.061380 memory: 8713 loss_kpt: 213.576767 acc_pose: 0.789581 loss: 213.576767 2022/10/12 17:57:10 - mmengine - INFO - Epoch(train) [79][250/586] lr: 5.000000e-03 eta: 10:32:00 time: 0.515472 data_time: 0.061958 memory: 8713 loss_kpt: 217.880804 acc_pose: 0.796861 loss: 217.880804 2022/10/12 17:57:31 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:57:35 - mmengine - INFO - Epoch(train) [79][300/586] lr: 5.000000e-03 eta: 10:31:37 time: 0.512511 data_time: 0.058604 memory: 8713 loss_kpt: 219.775610 acc_pose: 0.787189 loss: 219.775610 2022/10/12 17:58:01 - mmengine - INFO - Epoch(train) [79][350/586] lr: 5.000000e-03 eta: 10:31:14 time: 0.506483 data_time: 0.060455 memory: 8713 loss_kpt: 219.275050 acc_pose: 0.710896 loss: 219.275050 2022/10/12 17:58:26 - mmengine - INFO - Epoch(train) [79][400/586] lr: 5.000000e-03 eta: 10:30:50 time: 0.505845 data_time: 0.056226 memory: 8713 loss_kpt: 214.107401 acc_pose: 0.784429 loss: 214.107401 2022/10/12 17:58:52 - mmengine - INFO - Epoch(train) [79][450/586] lr: 5.000000e-03 eta: 10:30:27 time: 0.512388 data_time: 0.056860 memory: 8713 loss_kpt: 213.028796 acc_pose: 0.824921 loss: 213.028796 2022/10/12 17:59:17 - mmengine - INFO - Epoch(train) [79][500/586] lr: 5.000000e-03 eta: 10:30:04 time: 0.505260 data_time: 0.055489 memory: 8713 loss_kpt: 220.688732 acc_pose: 0.811579 loss: 220.688732 2022/10/12 17:59:42 - mmengine - INFO - Epoch(train) [79][550/586] lr: 5.000000e-03 eta: 10:29:40 time: 0.502669 data_time: 0.059474 memory: 8713 loss_kpt: 217.446529 acc_pose: 0.766869 loss: 217.446529 2022/10/12 18:00:00 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:00:27 - mmengine - INFO - Epoch(train) [80][50/586] lr: 5.000000e-03 eta: 10:28:33 time: 0.545611 data_time: 0.072181 memory: 8713 loss_kpt: 218.096238 acc_pose: 0.837650 loss: 218.096238 2022/10/12 18:00:53 - mmengine - INFO - Epoch(train) [80][100/586] lr: 5.000000e-03 eta: 10:28:11 time: 0.519689 data_time: 0.056712 memory: 8713 loss_kpt: 215.457868 acc_pose: 0.827887 loss: 215.457868 2022/10/12 18:01:20 - mmengine - INFO - Epoch(train) [80][150/586] lr: 5.000000e-03 eta: 10:27:50 time: 0.536482 data_time: 0.056711 memory: 8713 loss_kpt: 212.443414 acc_pose: 0.798096 loss: 212.443414 2022/10/12 18:01:46 - mmengine - INFO - Epoch(train) [80][200/586] lr: 5.000000e-03 eta: 10:27:28 time: 0.526667 data_time: 0.060135 memory: 8713 loss_kpt: 214.757690 acc_pose: 0.869179 loss: 214.757690 2022/10/12 18:02:13 - mmengine - INFO - Epoch(train) [80][250/586] lr: 5.000000e-03 eta: 10:27:07 time: 0.538408 data_time: 0.056460 memory: 8713 loss_kpt: 215.604772 acc_pose: 0.828314 loss: 215.604772 2022/10/12 18:02:40 - mmengine - INFO - Epoch(train) [80][300/586] lr: 5.000000e-03 eta: 10:26:47 time: 0.538736 data_time: 0.062685 memory: 8713 loss_kpt: 217.717969 acc_pose: 0.810174 loss: 217.717969 2022/10/12 18:03:07 - mmengine - INFO - Epoch(train) [80][350/586] lr: 5.000000e-03 eta: 10:26:25 time: 0.533808 data_time: 0.059146 memory: 8713 loss_kpt: 217.558833 acc_pose: 0.852660 loss: 217.558833 2022/10/12 18:03:34 - mmengine - INFO - Epoch(train) [80][400/586] lr: 5.000000e-03 eta: 10:26:04 time: 0.531195 data_time: 0.061357 memory: 8713 loss_kpt: 218.272041 acc_pose: 0.807155 loss: 218.272041 2022/10/12 18:04:00 - mmengine - INFO - Epoch(train) [80][450/586] lr: 5.000000e-03 eta: 10:25:42 time: 0.527564 data_time: 0.057561 memory: 8713 loss_kpt: 214.645262 acc_pose: 0.839387 loss: 214.645262 2022/10/12 18:04:26 - mmengine - INFO - Epoch(train) [80][500/586] lr: 5.000000e-03 eta: 10:25:21 time: 0.528156 data_time: 0.060720 memory: 8713 loss_kpt: 216.808660 acc_pose: 0.728291 loss: 216.808660 2022/10/12 18:04:53 - mmengine - INFO - Epoch(train) [80][550/586] lr: 5.000000e-03 eta: 10:24:59 time: 0.523438 data_time: 0.055681 memory: 8713 loss_kpt: 213.137822 acc_pose: 0.818585 loss: 213.137822 2022/10/12 18:05:11 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:05:11 - mmengine - INFO - Saving checkpoint at 80 epochs 2022/10/12 18:05:24 - mmengine - INFO - Epoch(val) [80][50/407] eta: 0:01:11 time: 0.200978 data_time: 0.012870 memory: 8713 2022/10/12 18:05:34 - mmengine - INFO - Epoch(val) [80][100/407] eta: 0:00:59 time: 0.192371 data_time: 0.007651 memory: 1759 2022/10/12 18:05:44 - mmengine - INFO - Epoch(val) [80][150/407] eta: 0:00:49 time: 0.193469 data_time: 0.007965 memory: 1759 2022/10/12 18:05:54 - mmengine - INFO - Epoch(val) [80][200/407] eta: 0:00:40 time: 0.196218 data_time: 0.008176 memory: 1759 2022/10/12 18:06:04 - mmengine - INFO - Epoch(val) [80][250/407] eta: 0:00:31 time: 0.199242 data_time: 0.008593 memory: 1759 2022/10/12 18:06:13 - mmengine - INFO - Epoch(val) [80][300/407] eta: 0:00:20 time: 0.193039 data_time: 0.007914 memory: 1759 2022/10/12 18:06:23 - mmengine - INFO - Epoch(val) [80][350/407] eta: 0:00:11 time: 0.199945 data_time: 0.012089 memory: 1759 2022/10/12 18:06:33 - mmengine - INFO - Epoch(val) [80][400/407] eta: 0:00:01 time: 0.192510 data_time: 0.007852 memory: 1759 2022/10/12 18:06:47 - mmengine - INFO - Evaluating CocoMetric... 2022/10/12 18:07:02 - mmengine - INFO - Epoch(val) [80][407/407] coco/AP: 0.700759 coco/AP .5: 0.881214 coco/AP .75: 0.774472 coco/AP (M): 0.669870 coco/AP (L): 0.761049 coco/AR: 0.769742 coco/AR .5: 0.923804 coco/AR .75: 0.832336 coco/AR (M): 0.724720 coco/AR (L): 0.831773 2022/10/12 18:07:02 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/liqikai/openmmlab/pt112cu113py38/mmpose/work_dirs/20221012/rsn2x/best_coco/AP_epoch_70.pth is removed 2022/10/12 18:07:04 - mmengine - INFO - The best checkpoint with 0.7008 coco/AP at 80 epoch is saved to best_coco/AP_epoch_80.pth. 2022/10/12 18:07:31 - mmengine - INFO - Epoch(train) [81][50/586] lr: 5.000000e-03 eta: 10:23:51 time: 0.535192 data_time: 0.061033 memory: 8713 loss_kpt: 214.461878 acc_pose: 0.839488 loss: 214.461878 2022/10/12 18:07:57 - mmengine - INFO - Epoch(train) [81][100/586] lr: 5.000000e-03 eta: 10:23:29 time: 0.520131 data_time: 0.060082 memory: 8713 loss_kpt: 217.205562 acc_pose: 0.760076 loss: 217.205562 2022/10/12 18:08:08 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:08:24 - mmengine - INFO - Epoch(train) [81][150/586] lr: 5.000000e-03 eta: 10:23:07 time: 0.529095 data_time: 0.054941 memory: 8713 loss_kpt: 213.861671 acc_pose: 0.759325 loss: 213.861671 2022/10/12 18:08:50 - mmengine - INFO - Epoch(train) [81][200/586] lr: 5.000000e-03 eta: 10:22:46 time: 0.534665 data_time: 0.058573 memory: 8713 loss_kpt: 216.280540 acc_pose: 0.789090 loss: 216.280540 2022/10/12 18:09:17 - mmengine - INFO - Epoch(train) [81][250/586] lr: 5.000000e-03 eta: 10:22:24 time: 0.526956 data_time: 0.056060 memory: 8713 loss_kpt: 214.027687 acc_pose: 0.752676 loss: 214.027687 2022/10/12 18:09:43 - mmengine - INFO - Epoch(train) [81][300/586] lr: 5.000000e-03 eta: 10:22:02 time: 0.517396 data_time: 0.054232 memory: 8713 loss_kpt: 213.422410 acc_pose: 0.660526 loss: 213.422410 2022/10/12 18:10:09 - mmengine - INFO - Epoch(train) [81][350/586] lr: 5.000000e-03 eta: 10:21:40 time: 0.526781 data_time: 0.057815 memory: 8713 loss_kpt: 210.408017 acc_pose: 0.834846 loss: 210.408017 2022/10/12 18:10:35 - mmengine - INFO - Epoch(train) [81][400/586] lr: 5.000000e-03 eta: 10:21:18 time: 0.529659 data_time: 0.057065 memory: 8713 loss_kpt: 217.744074 acc_pose: 0.804107 loss: 217.744074 2022/10/12 18:11:02 - mmengine - INFO - Epoch(train) [81][450/586] lr: 5.000000e-03 eta: 10:20:57 time: 0.527564 data_time: 0.056750 memory: 8713 loss_kpt: 211.571541 acc_pose: 0.817525 loss: 211.571541 2022/10/12 18:11:28 - mmengine - INFO - Epoch(train) [81][500/586] lr: 5.000000e-03 eta: 10:20:35 time: 0.524134 data_time: 0.057100 memory: 8713 loss_kpt: 214.735269 acc_pose: 0.795035 loss: 214.735269 2022/10/12 18:11:54 - mmengine - INFO - Epoch(train) [81][550/586] lr: 5.000000e-03 eta: 10:20:13 time: 0.525295 data_time: 0.053782 memory: 8713 loss_kpt: 214.087553 acc_pose: 0.832470 loss: 214.087553 2022/10/12 18:12:13 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:12:39 - mmengine - INFO - Epoch(train) [82][50/586] lr: 5.000000e-03 eta: 10:19:05 time: 0.522747 data_time: 0.067977 memory: 8713 loss_kpt: 217.984378 acc_pose: 0.837533 loss: 217.984378 2022/10/12 18:13:04 - mmengine - INFO - Epoch(train) [82][100/586] lr: 5.000000e-03 eta: 10:18:41 time: 0.506790 data_time: 0.052673 memory: 8713 loss_kpt: 215.186591 acc_pose: 0.817198 loss: 215.186591 2022/10/12 18:13:30 - mmengine - INFO - Epoch(train) [82][150/586] lr: 5.000000e-03 eta: 10:18:19 time: 0.518215 data_time: 0.061692 memory: 8713 loss_kpt: 219.088977 acc_pose: 0.860440 loss: 219.088977 2022/10/12 18:13:57 - mmengine - INFO - Epoch(train) [82][200/586] lr: 5.000000e-03 eta: 10:17:57 time: 0.529270 data_time: 0.052673 memory: 8713 loss_kpt: 216.549194 acc_pose: 0.775179 loss: 216.549194 2022/10/12 18:14:23 - mmengine - INFO - Epoch(train) [82][250/586] lr: 5.000000e-03 eta: 10:17:35 time: 0.526375 data_time: 0.060199 memory: 8713 loss_kpt: 219.687582 acc_pose: 0.767002 loss: 219.687582 2022/10/12 18:14:49 - mmengine - INFO - Epoch(train) [82][300/586] lr: 5.000000e-03 eta: 10:17:13 time: 0.523247 data_time: 0.058395 memory: 8713 loss_kpt: 212.268354 acc_pose: 0.842725 loss: 212.268354 2022/10/12 18:15:15 - mmengine - INFO - Epoch(train) [82][350/586] lr: 5.000000e-03 eta: 10:16:51 time: 0.517714 data_time: 0.059485 memory: 8713 loss_kpt: 217.637609 acc_pose: 0.825667 loss: 217.637609 2022/10/12 18:15:41 - mmengine - INFO - Epoch(train) [82][400/586] lr: 5.000000e-03 eta: 10:16:28 time: 0.520107 data_time: 0.056852 memory: 8713 loss_kpt: 213.208993 acc_pose: 0.798303 loss: 213.208993 2022/10/12 18:16:07 - mmengine - INFO - Epoch(train) [82][450/586] lr: 5.000000e-03 eta: 10:16:06 time: 0.524855 data_time: 0.060640 memory: 8713 loss_kpt: 215.381681 acc_pose: 0.782108 loss: 215.381681 2022/10/12 18:16:33 - mmengine - INFO - Epoch(train) [82][500/586] lr: 5.000000e-03 eta: 10:15:43 time: 0.510091 data_time: 0.056449 memory: 8713 loss_kpt: 215.764393 acc_pose: 0.800249 loss: 215.764393 2022/10/12 18:16:51 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:16:59 - mmengine - INFO - Epoch(train) [82][550/586] lr: 5.000000e-03 eta: 10:15:20 time: 0.513971 data_time: 0.060280 memory: 8713 loss_kpt: 215.623158 acc_pose: 0.835670 loss: 215.623158 2022/10/12 18:17:17 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:17:44 - mmengine - INFO - Epoch(train) [83][50/586] lr: 5.000000e-03 eta: 10:14:14 time: 0.544954 data_time: 0.067710 memory: 8713 loss_kpt: 215.984858 acc_pose: 0.829159 loss: 215.984858 2022/10/12 18:18:11 - mmengine - INFO - Epoch(train) [83][100/586] lr: 5.000000e-03 eta: 10:13:54 time: 0.541698 data_time: 0.061545 memory: 8713 loss_kpt: 214.108235 acc_pose: 0.759749 loss: 214.108235 2022/10/12 18:18:38 - mmengine - INFO - Epoch(train) [83][150/586] lr: 5.000000e-03 eta: 10:13:33 time: 0.535978 data_time: 0.058146 memory: 8713 loss_kpt: 220.183046 acc_pose: 0.834140 loss: 220.183046 2022/10/12 18:19:05 - mmengine - INFO - Epoch(train) [83][200/586] lr: 5.000000e-03 eta: 10:13:11 time: 0.531388 data_time: 0.058671 memory: 8713 loss_kpt: 215.842550 acc_pose: 0.863789 loss: 215.842550 2022/10/12 18:19:32 - mmengine - INFO - Epoch(train) [83][250/586] lr: 5.000000e-03 eta: 10:12:51 time: 0.548126 data_time: 0.063190 memory: 8713 loss_kpt: 210.292555 acc_pose: 0.842489 loss: 210.292555 2022/10/12 18:20:00 - mmengine - INFO - Epoch(train) [83][300/586] lr: 5.000000e-03 eta: 10:12:31 time: 0.549192 data_time: 0.057625 memory: 8713 loss_kpt: 213.635495 acc_pose: 0.772227 loss: 213.635495 2022/10/12 18:20:27 - mmengine - INFO - Epoch(train) [83][350/586] lr: 5.000000e-03 eta: 10:12:10 time: 0.535732 data_time: 0.060398 memory: 8713 loss_kpt: 216.407716 acc_pose: 0.817132 loss: 216.407716 2022/10/12 18:20:54 - mmengine - INFO - Epoch(train) [83][400/586] lr: 5.000000e-03 eta: 10:11:49 time: 0.547519 data_time: 0.058416 memory: 8713 loss_kpt: 213.904834 acc_pose: 0.758071 loss: 213.904834 2022/10/12 18:21:21 - mmengine - INFO - Epoch(train) [83][450/586] lr: 5.000000e-03 eta: 10:11:28 time: 0.538177 data_time: 0.059854 memory: 8713 loss_kpt: 215.595111 acc_pose: 0.832960 loss: 215.595111 2022/10/12 18:21:48 - mmengine - INFO - Epoch(train) [83][500/586] lr: 5.000000e-03 eta: 10:11:08 time: 0.549419 data_time: 0.059405 memory: 8713 loss_kpt: 213.467300 acc_pose: 0.815086 loss: 213.467300 2022/10/12 18:22:14 - mmengine - INFO - Epoch(train) [83][550/586] lr: 5.000000e-03 eta: 10:10:46 time: 0.521770 data_time: 0.057270 memory: 8713 loss_kpt: 211.881879 acc_pose: 0.828584 loss: 211.881879 2022/10/12 18:22:33 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:23:01 - mmengine - INFO - Epoch(train) [84][50/586] lr: 5.000000e-03 eta: 10:09:41 time: 0.558613 data_time: 0.073166 memory: 8713 loss_kpt: 215.055636 acc_pose: 0.790749 loss: 215.055636 2022/10/12 18:23:28 - mmengine - INFO - Epoch(train) [84][100/586] lr: 5.000000e-03 eta: 10:09:20 time: 0.535215 data_time: 0.060655 memory: 8713 loss_kpt: 213.644781 acc_pose: 0.742043 loss: 213.644781 2022/10/12 18:23:55 - mmengine - INFO - Epoch(train) [84][150/586] lr: 5.000000e-03 eta: 10:08:59 time: 0.539822 data_time: 0.059668 memory: 8713 loss_kpt: 216.952189 acc_pose: 0.812057 loss: 216.952189 2022/10/12 18:24:21 - mmengine - INFO - Epoch(train) [84][200/586] lr: 5.000000e-03 eta: 10:08:37 time: 0.526840 data_time: 0.056337 memory: 8713 loss_kpt: 212.222233 acc_pose: 0.823444 loss: 212.222233 2022/10/12 18:24:47 - mmengine - INFO - Epoch(train) [84][250/586] lr: 5.000000e-03 eta: 10:08:15 time: 0.521255 data_time: 0.059266 memory: 8713 loss_kpt: 215.171482 acc_pose: 0.783452 loss: 215.171482 2022/10/12 18:25:13 - mmengine - INFO - Epoch(train) [84][300/586] lr: 5.000000e-03 eta: 10:07:52 time: 0.512849 data_time: 0.059883 memory: 8713 loss_kpt: 214.415111 acc_pose: 0.749835 loss: 214.415111 2022/10/12 18:25:38 - mmengine - INFO - Epoch(train) [84][350/586] lr: 5.000000e-03 eta: 10:07:28 time: 0.505818 data_time: 0.056365 memory: 8713 loss_kpt: 214.391342 acc_pose: 0.801288 loss: 214.391342 2022/10/12 18:25:45 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:26:04 - mmengine - INFO - Epoch(train) [84][400/586] lr: 5.000000e-03 eta: 10:07:05 time: 0.517653 data_time: 0.055635 memory: 8713 loss_kpt: 216.188741 acc_pose: 0.852538 loss: 216.188741 2022/10/12 18:26:30 - mmengine - INFO - Epoch(train) [84][450/586] lr: 5.000000e-03 eta: 10:06:42 time: 0.504198 data_time: 0.057336 memory: 8713 loss_kpt: 211.510084 acc_pose: 0.767911 loss: 211.510084 2022/10/12 18:26:55 - mmengine - INFO - Epoch(train) [84][500/586] lr: 5.000000e-03 eta: 10:06:18 time: 0.501924 data_time: 0.059139 memory: 8713 loss_kpt: 213.609195 acc_pose: 0.822981 loss: 213.609195 2022/10/12 18:27:20 - mmengine - INFO - Epoch(train) [84][550/586] lr: 5.000000e-03 eta: 10:05:55 time: 0.510498 data_time: 0.056604 memory: 8713 loss_kpt: 210.363503 acc_pose: 0.861599 loss: 210.363503 2022/10/12 18:27:39 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:28:07 - mmengine - INFO - Epoch(train) [85][50/586] lr: 5.000000e-03 eta: 10:04:52 time: 0.573182 data_time: 0.075878 memory: 8713 loss_kpt: 211.888359 acc_pose: 0.849081 loss: 211.888359 2022/10/12 18:28:35 - mmengine - INFO - Epoch(train) [85][100/586] lr: 5.000000e-03 eta: 10:04:31 time: 0.547339 data_time: 0.057997 memory: 8713 loss_kpt: 214.057071 acc_pose: 0.733614 loss: 214.057071 2022/10/12 18:29:01 - mmengine - INFO - Epoch(train) [85][150/586] lr: 5.000000e-03 eta: 10:04:10 time: 0.530322 data_time: 0.061195 memory: 8713 loss_kpt: 209.624835 acc_pose: 0.827349 loss: 209.624835 2022/10/12 18:29:28 - mmengine - INFO - Epoch(train) [85][200/586] lr: 5.000000e-03 eta: 10:03:49 time: 0.540571 data_time: 0.057864 memory: 8713 loss_kpt: 212.116736 acc_pose: 0.821841 loss: 212.116736 2022/10/12 18:29:56 - mmengine - INFO - Epoch(train) [85][250/586] lr: 5.000000e-03 eta: 10:03:29 time: 0.554623 data_time: 0.062997 memory: 8713 loss_kpt: 215.089426 acc_pose: 0.824239 loss: 215.089426 2022/10/12 18:30:23 - mmengine - INFO - Epoch(train) [85][300/586] lr: 5.000000e-03 eta: 10:03:08 time: 0.547240 data_time: 0.062339 memory: 8713 loss_kpt: 212.571239 acc_pose: 0.824021 loss: 212.571239 2022/10/12 18:30:50 - mmengine - INFO - Epoch(train) [85][350/586] lr: 5.000000e-03 eta: 10:02:47 time: 0.537318 data_time: 0.060554 memory: 8713 loss_kpt: 210.895695 acc_pose: 0.847051 loss: 210.895695 2022/10/12 18:31:17 - mmengine - INFO - Epoch(train) [85][400/586] lr: 5.000000e-03 eta: 10:02:26 time: 0.534095 data_time: 0.064415 memory: 8713 loss_kpt: 214.427951 acc_pose: 0.819853 loss: 214.427951 2022/10/12 18:31:44 - mmengine - INFO - Epoch(train) [85][450/586] lr: 5.000000e-03 eta: 10:02:04 time: 0.539507 data_time: 0.059479 memory: 8713 loss_kpt: 217.973014 acc_pose: 0.765983 loss: 217.973014 2022/10/12 18:32:12 - mmengine - INFO - Epoch(train) [85][500/586] lr: 5.000000e-03 eta: 10:01:46 time: 0.571812 data_time: 0.056853 memory: 8713 loss_kpt: 215.403668 acc_pose: 0.758593 loss: 215.403668 2022/10/12 18:32:41 - mmengine - INFO - Epoch(train) [85][550/586] lr: 5.000000e-03 eta: 10:01:27 time: 0.574996 data_time: 0.062933 memory: 8713 loss_kpt: 213.412506 acc_pose: 0.675506 loss: 213.412506 2022/10/12 18:33:02 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:33:29 - mmengine - INFO - Epoch(train) [86][50/586] lr: 5.000000e-03 eta: 10:00:23 time: 0.545958 data_time: 0.070728 memory: 8713 loss_kpt: 210.887181 acc_pose: 0.812618 loss: 210.887181 2022/10/12 18:33:55 - mmengine - INFO - Epoch(train) [86][100/586] lr: 5.000000e-03 eta: 10:00:00 time: 0.523794 data_time: 0.056651 memory: 8713 loss_kpt: 217.360064 acc_pose: 0.836669 loss: 217.360064 2022/10/12 18:34:22 - mmengine - INFO - Epoch(train) [86][150/586] lr: 5.000000e-03 eta: 9:59:39 time: 0.531702 data_time: 0.063945 memory: 8713 loss_kpt: 209.907649 acc_pose: 0.829371 loss: 209.907649 2022/10/12 18:34:43 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:34:48 - mmengine - INFO - Epoch(train) [86][200/586] lr: 5.000000e-03 eta: 9:59:17 time: 0.531455 data_time: 0.054682 memory: 8713 loss_kpt: 213.899721 acc_pose: 0.802434 loss: 213.899721 2022/10/12 18:35:14 - mmengine - INFO - Epoch(train) [86][250/586] lr: 5.000000e-03 eta: 9:58:55 time: 0.524677 data_time: 0.057857 memory: 8713 loss_kpt: 212.420911 acc_pose: 0.703255 loss: 212.420911 2022/10/12 18:35:40 - mmengine - INFO - Epoch(train) [86][300/586] lr: 5.000000e-03 eta: 9:58:32 time: 0.520092 data_time: 0.052888 memory: 8713 loss_kpt: 211.001621 acc_pose: 0.852862 loss: 211.001621 2022/10/12 18:36:07 - mmengine - INFO - Epoch(train) [86][350/586] lr: 5.000000e-03 eta: 9:58:10 time: 0.520949 data_time: 0.060524 memory: 8713 loss_kpt: 216.054880 acc_pose: 0.752484 loss: 216.054880 2022/10/12 18:36:33 - mmengine - INFO - Epoch(train) [86][400/586] lr: 5.000000e-03 eta: 9:57:47 time: 0.523128 data_time: 0.059052 memory: 8713 loss_kpt: 212.473883 acc_pose: 0.759719 loss: 212.473883 2022/10/12 18:36:59 - mmengine - INFO - Epoch(train) [86][450/586] lr: 5.000000e-03 eta: 9:57:25 time: 0.526403 data_time: 0.055760 memory: 8713 loss_kpt: 208.156874 acc_pose: 0.819437 loss: 208.156874 2022/10/12 18:37:25 - mmengine - INFO - Epoch(train) [86][500/586] lr: 5.000000e-03 eta: 9:57:03 time: 0.525005 data_time: 0.052605 memory: 8713 loss_kpt: 217.512568 acc_pose: 0.783509 loss: 217.512568 2022/10/12 18:37:52 - mmengine - INFO - Epoch(train) [86][550/586] lr: 5.000000e-03 eta: 9:56:41 time: 0.538041 data_time: 0.066007 memory: 8713 loss_kpt: 212.414912 acc_pose: 0.781448 loss: 212.414912 2022/10/12 18:38:11 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:38:38 - mmengine - INFO - Epoch(train) [87][50/586] lr: 5.000000e-03 eta: 9:55:37 time: 0.534594 data_time: 0.077657 memory: 8713 loss_kpt: 215.474888 acc_pose: 0.860548 loss: 215.474888 2022/10/12 18:39:04 - mmengine - INFO - Epoch(train) [87][100/586] lr: 5.000000e-03 eta: 9:55:14 time: 0.515232 data_time: 0.055758 memory: 8713 loss_kpt: 218.820246 acc_pose: 0.877539 loss: 218.820246 2022/10/12 18:39:29 - mmengine - INFO - Epoch(train) [87][150/586] lr: 5.000000e-03 eta: 9:54:50 time: 0.512245 data_time: 0.057305 memory: 8713 loss_kpt: 210.570735 acc_pose: 0.792129 loss: 210.570735 2022/10/12 18:39:56 - mmengine - INFO - Epoch(train) [87][200/586] lr: 5.000000e-03 eta: 9:54:28 time: 0.523792 data_time: 0.057284 memory: 8713 loss_kpt: 210.151176 acc_pose: 0.778782 loss: 210.151176 2022/10/12 18:40:22 - mmengine - INFO - Epoch(train) [87][250/586] lr: 5.000000e-03 eta: 9:54:06 time: 0.527034 data_time: 0.059132 memory: 8713 loss_kpt: 215.262455 acc_pose: 0.804733 loss: 215.262455 2022/10/12 18:40:48 - mmengine - INFO - Epoch(train) [87][300/586] lr: 5.000000e-03 eta: 9:53:43 time: 0.519538 data_time: 0.056413 memory: 8713 loss_kpt: 213.249427 acc_pose: 0.835941 loss: 213.249427 2022/10/12 18:41:13 - mmengine - INFO - Epoch(train) [87][350/586] lr: 5.000000e-03 eta: 9:53:20 time: 0.509120 data_time: 0.057398 memory: 8713 loss_kpt: 211.063445 acc_pose: 0.842709 loss: 211.063445 2022/10/12 18:41:39 - mmengine - INFO - Epoch(train) [87][400/586] lr: 5.000000e-03 eta: 9:52:56 time: 0.507352 data_time: 0.057896 memory: 8713 loss_kpt: 216.314005 acc_pose: 0.810406 loss: 216.314005 2022/10/12 18:42:05 - mmengine - INFO - Epoch(train) [87][450/586] lr: 5.000000e-03 eta: 9:52:34 time: 0.527345 data_time: 0.058281 memory: 8713 loss_kpt: 215.278514 acc_pose: 0.862272 loss: 215.278514 2022/10/12 18:42:31 - mmengine - INFO - Epoch(train) [87][500/586] lr: 5.000000e-03 eta: 9:52:12 time: 0.520354 data_time: 0.057820 memory: 8713 loss_kpt: 213.429636 acc_pose: 0.723271 loss: 213.429636 2022/10/12 18:42:57 - mmengine - INFO - Epoch(train) [87][550/586] lr: 5.000000e-03 eta: 9:51:49 time: 0.516395 data_time: 0.057539 memory: 8713 loss_kpt: 209.987878 acc_pose: 0.851128 loss: 209.987878 2022/10/12 18:43:15 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:43:26 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:43:43 - mmengine - INFO - Epoch(train) [88][50/586] lr: 5.000000e-03 eta: 9:50:45 time: 0.546245 data_time: 0.073657 memory: 8713 loss_kpt: 208.550144 acc_pose: 0.785717 loss: 208.550144 2022/10/12 18:44:09 - mmengine - INFO - Epoch(train) [88][100/586] lr: 5.000000e-03 eta: 9:50:22 time: 0.518997 data_time: 0.056759 memory: 8713 loss_kpt: 211.666893 acc_pose: 0.831229 loss: 211.666893 2022/10/12 18:44:36 - mmengine - INFO - Epoch(train) [88][150/586] lr: 5.000000e-03 eta: 9:50:01 time: 0.536280 data_time: 0.057990 memory: 8713 loss_kpt: 211.718523 acc_pose: 0.793383 loss: 211.718523 2022/10/12 18:45:02 - mmengine - INFO - Epoch(train) [88][200/586] lr: 5.000000e-03 eta: 9:49:39 time: 0.531001 data_time: 0.060455 memory: 8713 loss_kpt: 208.115341 acc_pose: 0.805162 loss: 208.115341 2022/10/12 18:45:28 - mmengine - INFO - Epoch(train) [88][250/586] lr: 5.000000e-03 eta: 9:49:16 time: 0.518984 data_time: 0.061800 memory: 8713 loss_kpt: 212.730222 acc_pose: 0.823376 loss: 212.730222 2022/10/12 18:45:54 - mmengine - INFO - Epoch(train) [88][300/586] lr: 5.000000e-03 eta: 9:48:53 time: 0.514696 data_time: 0.053049 memory: 8713 loss_kpt: 212.966216 acc_pose: 0.859203 loss: 212.966216 2022/10/12 18:46:20 - mmengine - INFO - Epoch(train) [88][350/586] lr: 5.000000e-03 eta: 9:48:30 time: 0.517482 data_time: 0.058176 memory: 8713 loss_kpt: 213.971447 acc_pose: 0.814915 loss: 213.971447 2022/10/12 18:46:45 - mmengine - INFO - Epoch(train) [88][400/586] lr: 5.000000e-03 eta: 9:48:07 time: 0.508670 data_time: 0.052164 memory: 8713 loss_kpt: 214.707472 acc_pose: 0.766716 loss: 214.707472 2022/10/12 18:47:11 - mmengine - INFO - Epoch(train) [88][450/586] lr: 5.000000e-03 eta: 9:47:44 time: 0.517095 data_time: 0.064005 memory: 8713 loss_kpt: 212.556707 acc_pose: 0.828195 loss: 212.556707 2022/10/12 18:47:37 - mmengine - INFO - Epoch(train) [88][500/586] lr: 5.000000e-03 eta: 9:47:21 time: 0.519821 data_time: 0.053075 memory: 8713 loss_kpt: 214.889769 acc_pose: 0.879090 loss: 214.889769 2022/10/12 18:48:03 - mmengine - INFO - Epoch(train) [88][550/586] lr: 5.000000e-03 eta: 9:46:58 time: 0.517841 data_time: 0.058757 memory: 8713 loss_kpt: 215.183892 acc_pose: 0.788893 loss: 215.183892 2022/10/12 18:48:22 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:48:49 - mmengine - INFO - Epoch(train) [89][50/586] lr: 5.000000e-03 eta: 9:45:55 time: 0.535811 data_time: 0.068224 memory: 8713 loss_kpt: 216.306810 acc_pose: 0.813374 loss: 216.306810 2022/10/12 18:49:15 - mmengine - INFO - Epoch(train) [89][100/586] lr: 5.000000e-03 eta: 9:45:32 time: 0.527330 data_time: 0.056144 memory: 8713 loss_kpt: 211.402495 acc_pose: 0.799972 loss: 211.402495 2022/10/12 18:49:41 - mmengine - INFO - Epoch(train) [89][150/586] lr: 5.000000e-03 eta: 9:45:10 time: 0.526302 data_time: 0.062753 memory: 8713 loss_kpt: 215.779842 acc_pose: 0.779941 loss: 215.779842 2022/10/12 18:50:08 - mmengine - INFO - Epoch(train) [89][200/586] lr: 5.000000e-03 eta: 9:44:48 time: 0.531471 data_time: 0.057362 memory: 8713 loss_kpt: 213.974410 acc_pose: 0.718280 loss: 213.974410 2022/10/12 18:50:34 - mmengine - INFO - Epoch(train) [89][250/586] lr: 5.000000e-03 eta: 9:44:26 time: 0.532246 data_time: 0.058956 memory: 8713 loss_kpt: 212.749380 acc_pose: 0.743310 loss: 212.749380 2022/10/12 18:51:01 - mmengine - INFO - Epoch(train) [89][300/586] lr: 5.000000e-03 eta: 9:44:04 time: 0.521194 data_time: 0.054003 memory: 8713 loss_kpt: 212.125078 acc_pose: 0.854364 loss: 212.125078 2022/10/12 18:51:27 - mmengine - INFO - Epoch(train) [89][350/586] lr: 5.000000e-03 eta: 9:43:42 time: 0.532618 data_time: 0.058784 memory: 8713 loss_kpt: 212.346677 acc_pose: 0.880612 loss: 212.346677 2022/10/12 18:51:53 - mmengine - INFO - Epoch(train) [89][400/586] lr: 5.000000e-03 eta: 9:43:20 time: 0.526029 data_time: 0.055325 memory: 8713 loss_kpt: 214.207998 acc_pose: 0.780460 loss: 214.207998 2022/10/12 18:52:10 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:52:20 - mmengine - INFO - Epoch(train) [89][450/586] lr: 5.000000e-03 eta: 9:42:57 time: 0.524795 data_time: 0.058174 memory: 8713 loss_kpt: 219.017993 acc_pose: 0.775071 loss: 219.017993 2022/10/12 18:52:46 - mmengine - INFO - Epoch(train) [89][500/586] lr: 5.000000e-03 eta: 9:42:35 time: 0.522965 data_time: 0.054192 memory: 8713 loss_kpt: 212.750448 acc_pose: 0.718300 loss: 212.750448 2022/10/12 18:53:12 - mmengine - INFO - Epoch(train) [89][550/586] lr: 5.000000e-03 eta: 9:42:12 time: 0.519847 data_time: 0.059278 memory: 8713 loss_kpt: 216.230031 acc_pose: 0.819029 loss: 216.230031 2022/10/12 18:53:30 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:53:57 - mmengine - INFO - Epoch(train) [90][50/586] lr: 5.000000e-03 eta: 9:41:08 time: 0.533592 data_time: 0.072062 memory: 8713 loss_kpt: 212.116162 acc_pose: 0.772992 loss: 212.116162 2022/10/12 18:54:23 - mmengine - INFO - Epoch(train) [90][100/586] lr: 5.000000e-03 eta: 9:40:46 time: 0.529022 data_time: 0.062173 memory: 8713 loss_kpt: 210.695599 acc_pose: 0.834509 loss: 210.695599 2022/10/12 18:54:49 - mmengine - INFO - Epoch(train) [90][150/586] lr: 5.000000e-03 eta: 9:40:24 time: 0.521944 data_time: 0.061346 memory: 8713 loss_kpt: 215.120388 acc_pose: 0.828231 loss: 215.120388 2022/10/12 18:55:15 - mmengine - INFO - Epoch(train) [90][200/586] lr: 5.000000e-03 eta: 9:40:01 time: 0.519138 data_time: 0.057085 memory: 8713 loss_kpt: 212.009846 acc_pose: 0.896386 loss: 212.009846 2022/10/12 18:55:42 - mmengine - INFO - Epoch(train) [90][250/586] lr: 5.000000e-03 eta: 9:39:39 time: 0.528959 data_time: 0.058495 memory: 8713 loss_kpt: 213.274160 acc_pose: 0.849419 loss: 213.274160 2022/10/12 18:56:08 - mmengine - INFO - Epoch(train) [90][300/586] lr: 5.000000e-03 eta: 9:39:16 time: 0.515313 data_time: 0.060122 memory: 8713 loss_kpt: 212.876528 acc_pose: 0.834314 loss: 212.876528 2022/10/12 18:56:33 - mmengine - INFO - Epoch(train) [90][350/586] lr: 5.000000e-03 eta: 9:38:52 time: 0.511949 data_time: 0.056638 memory: 8713 loss_kpt: 209.435590 acc_pose: 0.846412 loss: 209.435590 2022/10/12 18:56:59 - mmengine - INFO - Epoch(train) [90][400/586] lr: 5.000000e-03 eta: 9:38:30 time: 0.521004 data_time: 0.057566 memory: 8713 loss_kpt: 216.772513 acc_pose: 0.794498 loss: 216.772513 2022/10/12 18:57:25 - mmengine - INFO - Epoch(train) [90][450/586] lr: 5.000000e-03 eta: 9:38:07 time: 0.513671 data_time: 0.055709 memory: 8713 loss_kpt: 212.452873 acc_pose: 0.848918 loss: 212.452873 2022/10/12 18:57:51 - mmengine - INFO - Epoch(train) [90][500/586] lr: 5.000000e-03 eta: 9:37:43 time: 0.513455 data_time: 0.052757 memory: 8713 loss_kpt: 216.155264 acc_pose: 0.803359 loss: 216.155264 2022/10/12 18:58:17 - mmengine - INFO - Epoch(train) [90][550/586] lr: 5.000000e-03 eta: 9:37:21 time: 0.523017 data_time: 0.056915 memory: 8713 loss_kpt: 213.545560 acc_pose: 0.831488 loss: 213.545560 2022/10/12 18:58:35 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:58:35 - mmengine - INFO - Saving checkpoint at 90 epochs 2022/10/12 18:58:48 - mmengine - INFO - Epoch(val) [90][50/407] eta: 0:01:10 time: 0.198390 data_time: 0.012739 memory: 8713 2022/10/12 18:58:58 - mmengine - INFO - Epoch(val) [90][100/407] eta: 0:00:59 time: 0.193361 data_time: 0.007854 memory: 1759 2022/10/12 18:59:08 - mmengine - INFO - Epoch(val) [90][150/407] eta: 0:00:52 time: 0.203422 data_time: 0.008744 memory: 1759 2022/10/12 18:59:18 - mmengine - INFO - Epoch(val) [90][200/407] eta: 0:00:40 time: 0.197378 data_time: 0.007862 memory: 1759 2022/10/12 18:59:28 - mmengine - INFO - Epoch(val) [90][250/407] eta: 0:00:30 time: 0.191583 data_time: 0.007805 memory: 1759 2022/10/12 18:59:37 - mmengine - INFO - Epoch(val) [90][300/407] eta: 0:00:21 time: 0.196787 data_time: 0.008578 memory: 1759 2022/10/12 18:59:47 - mmengine - INFO - Epoch(val) [90][350/407] eta: 0:00:11 time: 0.197204 data_time: 0.008061 memory: 1759 2022/10/12 18:59:57 - mmengine - INFO - Epoch(val) [90][400/407] eta: 0:00:01 time: 0.192284 data_time: 0.008274 memory: 1759 2022/10/12 19:00:11 - mmengine - INFO - Evaluating CocoMetric... 2022/10/12 19:00:26 - mmengine - INFO - Epoch(val) [90][407/407] coco/AP: 0.706821 coco/AP .5: 0.885621 coco/AP .75: 0.779330 coco/AP (M): 0.675166 coco/AP (L): 0.768680 coco/AR: 0.775630 coco/AR .5: 0.928054 coco/AR .75: 0.835800 coco/AR (M): 0.731303 coco/AR (L): 0.836864 2022/10/12 19:00:26 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/liqikai/openmmlab/pt112cu113py38/mmpose/work_dirs/20221012/rsn2x/best_coco/AP_epoch_80.pth is removed 2022/10/12 19:00:29 - mmengine - INFO - The best checkpoint with 0.7068 coco/AP at 90 epoch is saved to best_coco/AP_epoch_90.pth. 2022/10/12 19:00:56 - mmengine - INFO - Epoch(train) [91][50/586] lr: 5.000000e-03 eta: 9:36:18 time: 0.545126 data_time: 0.067549 memory: 8713 loss_kpt: 215.981163 acc_pose: 0.832943 loss: 215.981163 2022/10/12 19:01:23 - mmengine - INFO - Epoch(train) [91][100/586] lr: 5.000000e-03 eta: 9:35:57 time: 0.536743 data_time: 0.061764 memory: 8713 loss_kpt: 209.845450 acc_pose: 0.853079 loss: 209.845450 2022/10/12 19:01:50 - mmengine - INFO - Epoch(train) [91][150/586] lr: 5.000000e-03 eta: 9:35:35 time: 0.541968 data_time: 0.054867 memory: 8713 loss_kpt: 210.797054 acc_pose: 0.841364 loss: 210.797054 2022/10/12 19:02:17 - mmengine - INFO - Epoch(train) [91][200/586] lr: 5.000000e-03 eta: 9:35:13 time: 0.532181 data_time: 0.062223 memory: 8713 loss_kpt: 213.010103 acc_pose: 0.753887 loss: 213.010103 2022/10/12 19:02:43 - mmengine - INFO - Epoch(train) [91][250/586] lr: 5.000000e-03 eta: 9:34:51 time: 0.528215 data_time: 0.059137 memory: 8713 loss_kpt: 213.304113 acc_pose: 0.851675 loss: 213.304113 2022/10/12 19:02:48 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:03:09 - mmengine - INFO - Epoch(train) [91][300/586] lr: 5.000000e-03 eta: 9:34:29 time: 0.524659 data_time: 0.057121 memory: 8713 loss_kpt: 214.962820 acc_pose: 0.796748 loss: 214.962820 2022/10/12 19:03:36 - mmengine - INFO - Epoch(train) [91][350/586] lr: 5.000000e-03 eta: 9:34:07 time: 0.531908 data_time: 0.056112 memory: 8713 loss_kpt: 216.475891 acc_pose: 0.817475 loss: 216.475891 2022/10/12 19:04:03 - mmengine - INFO - Epoch(train) [91][400/586] lr: 5.000000e-03 eta: 9:33:45 time: 0.531929 data_time: 0.064484 memory: 8713 loss_kpt: 218.206571 acc_pose: 0.864380 loss: 218.206571 2022/10/12 19:04:29 - mmengine - INFO - Epoch(train) [91][450/586] lr: 5.000000e-03 eta: 9:33:23 time: 0.532192 data_time: 0.060983 memory: 8713 loss_kpt: 210.057636 acc_pose: 0.750371 loss: 210.057636 2022/10/12 19:04:55 - mmengine - INFO - Epoch(train) [91][500/586] lr: 5.000000e-03 eta: 9:33:00 time: 0.526073 data_time: 0.061516 memory: 8713 loss_kpt: 213.502886 acc_pose: 0.757583 loss: 213.502886 2022/10/12 19:05:22 - mmengine - INFO - Epoch(train) [91][550/586] lr: 5.000000e-03 eta: 9:32:39 time: 0.535849 data_time: 0.059254 memory: 8713 loss_kpt: 212.990983 acc_pose: 0.849033 loss: 212.990983 2022/10/12 19:05:41 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:06:07 - mmengine - INFO - Epoch(train) [92][50/586] lr: 5.000000e-03 eta: 9:31:35 time: 0.527341 data_time: 0.068431 memory: 8713 loss_kpt: 217.925398 acc_pose: 0.805401 loss: 217.925398 2022/10/12 19:06:32 - mmengine - INFO - Epoch(train) [92][100/586] lr: 5.000000e-03 eta: 9:31:11 time: 0.498521 data_time: 0.054997 memory: 8713 loss_kpt: 211.291505 acc_pose: 0.846724 loss: 211.291505 2022/10/12 19:06:58 - mmengine - INFO - Epoch(train) [92][150/586] lr: 5.000000e-03 eta: 9:30:49 time: 0.524068 data_time: 0.059589 memory: 8713 loss_kpt: 216.738483 acc_pose: 0.856258 loss: 216.738483 2022/10/12 19:07:24 - mmengine - INFO - Epoch(train) [92][200/586] lr: 5.000000e-03 eta: 9:30:25 time: 0.509559 data_time: 0.057366 memory: 8713 loss_kpt: 215.529990 acc_pose: 0.765147 loss: 215.529990 2022/10/12 19:07:50 - mmengine - INFO - Epoch(train) [92][250/586] lr: 5.000000e-03 eta: 9:30:02 time: 0.517040 data_time: 0.053508 memory: 8713 loss_kpt: 211.640511 acc_pose: 0.826715 loss: 211.640511 2022/10/12 19:08:16 - mmengine - INFO - Epoch(train) [92][300/586] lr: 5.000000e-03 eta: 9:29:39 time: 0.516007 data_time: 0.052545 memory: 8713 loss_kpt: 210.749736 acc_pose: 0.882405 loss: 210.749736 2022/10/12 19:08:41 - mmengine - INFO - Epoch(train) [92][350/586] lr: 5.000000e-03 eta: 9:29:15 time: 0.504681 data_time: 0.059340 memory: 8713 loss_kpt: 211.412905 acc_pose: 0.860856 loss: 211.412905 2022/10/12 19:09:06 - mmengine - INFO - Epoch(train) [92][400/586] lr: 5.000000e-03 eta: 9:28:52 time: 0.506596 data_time: 0.055339 memory: 8713 loss_kpt: 212.698936 acc_pose: 0.921838 loss: 212.698936 2022/10/12 19:09:32 - mmengine - INFO - Epoch(train) [92][450/586] lr: 5.000000e-03 eta: 9:28:29 time: 0.517111 data_time: 0.054295 memory: 8713 loss_kpt: 210.004813 acc_pose: 0.806845 loss: 210.004813 2022/10/12 19:09:58 - mmengine - INFO - Epoch(train) [92][500/586] lr: 5.000000e-03 eta: 9:28:05 time: 0.510937 data_time: 0.058430 memory: 8713 loss_kpt: 210.600283 acc_pose: 0.853743 loss: 210.600283 2022/10/12 19:10:23 - mmengine - INFO - Epoch(train) [92][550/586] lr: 5.000000e-03 eta: 9:27:41 time: 0.507685 data_time: 0.056405 memory: 8713 loss_kpt: 213.279518 acc_pose: 0.749131 loss: 213.279518 2022/10/12 19:10:41 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:11:08 - mmengine - INFO - Epoch(train) [93][50/586] lr: 5.000000e-03 eta: 9:26:39 time: 0.531027 data_time: 0.068392 memory: 8713 loss_kpt: 210.298678 acc_pose: 0.882471 loss: 210.298678 2022/10/12 19:11:27 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:11:33 - mmengine - INFO - Epoch(train) [93][100/586] lr: 5.000000e-03 eta: 9:26:15 time: 0.505817 data_time: 0.051449 memory: 8713 loss_kpt: 212.714218 acc_pose: 0.822549 loss: 212.714218 2022/10/12 19:11:59 - mmengine - INFO - Epoch(train) [93][150/586] lr: 5.000000e-03 eta: 9:25:52 time: 0.514918 data_time: 0.055002 memory: 8713 loss_kpt: 212.470144 acc_pose: 0.747773 loss: 212.470144 2022/10/12 19:12:25 - mmengine - INFO - Epoch(train) [93][200/586] lr: 5.000000e-03 eta: 9:25:29 time: 0.514943 data_time: 0.059277 memory: 8713 loss_kpt: 211.488369 acc_pose: 0.794192 loss: 211.488369 2022/10/12 19:12:50 - mmengine - INFO - Epoch(train) [93][250/586] lr: 5.000000e-03 eta: 9:25:05 time: 0.510586 data_time: 0.059333 memory: 8713 loss_kpt: 209.998980 acc_pose: 0.852875 loss: 209.998980 2022/10/12 19:13:16 - mmengine - INFO - Epoch(train) [93][300/586] lr: 5.000000e-03 eta: 9:24:42 time: 0.509695 data_time: 0.054593 memory: 8713 loss_kpt: 213.174893 acc_pose: 0.838364 loss: 213.174893 2022/10/12 19:13:42 - mmengine - INFO - Epoch(train) [93][350/586] lr: 5.000000e-03 eta: 9:24:19 time: 0.519072 data_time: 0.060182 memory: 8713 loss_kpt: 210.937522 acc_pose: 0.859441 loss: 210.937522 2022/10/12 19:14:08 - mmengine - INFO - Epoch(train) [93][400/586] lr: 5.000000e-03 eta: 9:23:56 time: 0.519739 data_time: 0.058028 memory: 8713 loss_kpt: 214.168379 acc_pose: 0.853534 loss: 214.168379 2022/10/12 19:14:34 - mmengine - INFO - Epoch(train) [93][450/586] lr: 5.000000e-03 eta: 9:23:34 time: 0.522615 data_time: 0.062338 memory: 8713 loss_kpt: 213.239380 acc_pose: 0.869396 loss: 213.239380 2022/10/12 19:14:59 - mmengine - INFO - Epoch(train) [93][500/586] lr: 5.000000e-03 eta: 9:23:10 time: 0.506317 data_time: 0.055808 memory: 8713 loss_kpt: 213.611354 acc_pose: 0.821635 loss: 213.611354 2022/10/12 19:15:25 - mmengine - INFO - Epoch(train) [93][550/586] lr: 5.000000e-03 eta: 9:22:47 time: 0.520439 data_time: 0.054676 memory: 8713 loss_kpt: 209.072715 acc_pose: 0.806296 loss: 209.072715 2022/10/12 19:15:43 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:16:10 - mmengine - INFO - Epoch(train) [94][50/586] lr: 5.000000e-03 eta: 9:21:46 time: 0.548333 data_time: 0.070677 memory: 8713 loss_kpt: 211.623665 acc_pose: 0.833516 loss: 211.623665 2022/10/12 19:16:37 - mmengine - INFO - Epoch(train) [94][100/586] lr: 5.000000e-03 eta: 9:21:24 time: 0.531911 data_time: 0.060626 memory: 8713 loss_kpt: 211.569279 acc_pose: 0.786820 loss: 211.569279 2022/10/12 19:17:04 - mmengine - INFO - Epoch(train) [94][150/586] lr: 5.000000e-03 eta: 9:21:02 time: 0.529306 data_time: 0.056551 memory: 8713 loss_kpt: 211.628498 acc_pose: 0.837010 loss: 211.628498 2022/10/12 19:17:30 - mmengine - INFO - Epoch(train) [94][200/586] lr: 5.000000e-03 eta: 9:20:40 time: 0.536199 data_time: 0.059708 memory: 8713 loss_kpt: 210.004312 acc_pose: 0.821869 loss: 210.004312 2022/10/12 19:17:57 - mmengine - INFO - Epoch(train) [94][250/586] lr: 5.000000e-03 eta: 9:20:18 time: 0.531641 data_time: 0.059830 memory: 8713 loss_kpt: 215.013909 acc_pose: 0.805742 loss: 215.013909 2022/10/12 19:18:23 - mmengine - INFO - Epoch(train) [94][300/586] lr: 5.000000e-03 eta: 9:19:55 time: 0.526768 data_time: 0.060680 memory: 8713 loss_kpt: 210.592649 acc_pose: 0.787475 loss: 210.592649 2022/10/12 19:18:50 - mmengine - INFO - Epoch(train) [94][350/586] lr: 5.000000e-03 eta: 9:19:33 time: 0.537129 data_time: 0.056739 memory: 8713 loss_kpt: 208.724398 acc_pose: 0.839497 loss: 208.724398 2022/10/12 19:19:17 - mmengine - INFO - Epoch(train) [94][400/586] lr: 5.000000e-03 eta: 9:19:11 time: 0.529469 data_time: 0.058118 memory: 8713 loss_kpt: 212.874417 acc_pose: 0.803535 loss: 212.874417 2022/10/12 19:19:43 - mmengine - INFO - Epoch(train) [94][450/586] lr: 5.000000e-03 eta: 9:18:49 time: 0.531027 data_time: 0.056419 memory: 8713 loss_kpt: 214.606119 acc_pose: 0.812122 loss: 214.606119 2022/10/12 19:20:10 - mmengine - INFO - Epoch(train) [94][500/586] lr: 5.000000e-03 eta: 9:18:26 time: 0.528990 data_time: 0.062698 memory: 8713 loss_kpt: 213.700172 acc_pose: 0.828584 loss: 213.700172 2022/10/12 19:20:11 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:20:36 - mmengine - INFO - Epoch(train) [94][550/586] lr: 5.000000e-03 eta: 9:18:03 time: 0.518095 data_time: 0.062093 memory: 8713 loss_kpt: 211.009826 acc_pose: 0.860261 loss: 211.009826 2022/10/12 19:20:54 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:21:21 - mmengine - INFO - Epoch(train) [95][50/586] lr: 5.000000e-03 eta: 9:17:02 time: 0.535674 data_time: 0.068763 memory: 8713 loss_kpt: 208.624969 acc_pose: 0.857190 loss: 208.624969 2022/10/12 19:21:47 - mmengine - INFO - Epoch(train) [95][100/586] lr: 5.000000e-03 eta: 9:16:40 time: 0.531925 data_time: 0.058349 memory: 8713 loss_kpt: 210.455663 acc_pose: 0.792965 loss: 210.455663 2022/10/12 19:22:14 - mmengine - INFO - Epoch(train) [95][150/586] lr: 5.000000e-03 eta: 9:16:17 time: 0.523381 data_time: 0.060378 memory: 8713 loss_kpt: 214.364239 acc_pose: 0.800003 loss: 214.364239 2022/10/12 19:22:40 - mmengine - INFO - Epoch(train) [95][200/586] lr: 5.000000e-03 eta: 9:15:54 time: 0.519781 data_time: 0.057771 memory: 8713 loss_kpt: 209.385831 acc_pose: 0.835391 loss: 209.385831 2022/10/12 19:23:06 - mmengine - INFO - Epoch(train) [95][250/586] lr: 5.000000e-03 eta: 9:15:31 time: 0.521392 data_time: 0.059204 memory: 8713 loss_kpt: 211.913218 acc_pose: 0.759402 loss: 211.913218 2022/10/12 19:23:32 - mmengine - INFO - Epoch(train) [95][300/586] lr: 5.000000e-03 eta: 9:15:08 time: 0.519351 data_time: 0.055395 memory: 8713 loss_kpt: 211.745581 acc_pose: 0.797645 loss: 211.745581 2022/10/12 19:23:58 - mmengine - INFO - Epoch(train) [95][350/586] lr: 5.000000e-03 eta: 9:14:46 time: 0.522673 data_time: 0.054626 memory: 8713 loss_kpt: 218.091469 acc_pose: 0.783379 loss: 218.091469 2022/10/12 19:24:24 - mmengine - INFO - Epoch(train) [95][400/586] lr: 5.000000e-03 eta: 9:14:23 time: 0.520122 data_time: 0.057666 memory: 8713 loss_kpt: 211.963024 acc_pose: 0.763871 loss: 211.963024 2022/10/12 19:24:50 - mmengine - INFO - Epoch(train) [95][450/586] lr: 5.000000e-03 eta: 9:14:00 time: 0.523802 data_time: 0.053466 memory: 8713 loss_kpt: 215.305880 acc_pose: 0.755972 loss: 215.305880 2022/10/12 19:25:16 - mmengine - INFO - Epoch(train) [95][500/586] lr: 5.000000e-03 eta: 9:13:37 time: 0.516882 data_time: 0.056864 memory: 8713 loss_kpt: 213.037126 acc_pose: 0.813543 loss: 213.037126 2022/10/12 19:25:42 - mmengine - INFO - Epoch(train) [95][550/586] lr: 5.000000e-03 eta: 9:13:15 time: 0.531862 data_time: 0.059602 memory: 8713 loss_kpt: 215.134370 acc_pose: 0.716914 loss: 215.134370 2022/10/12 19:26:01 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:26:28 - mmengine - INFO - Epoch(train) [96][50/586] lr: 5.000000e-03 eta: 9:12:14 time: 0.543805 data_time: 0.070277 memory: 8713 loss_kpt: 214.077913 acc_pose: 0.776371 loss: 214.077913 2022/10/12 19:26:54 - mmengine - INFO - Epoch(train) [96][100/586] lr: 5.000000e-03 eta: 9:11:51 time: 0.520876 data_time: 0.056119 memory: 8713 loss_kpt: 212.366863 acc_pose: 0.862516 loss: 212.366863 2022/10/12 19:27:21 - mmengine - INFO - Epoch(train) [96][150/586] lr: 5.000000e-03 eta: 9:11:29 time: 0.528768 data_time: 0.057470 memory: 8713 loss_kpt: 209.172374 acc_pose: 0.745304 loss: 209.172374 2022/10/12 19:27:47 - mmengine - INFO - Epoch(train) [96][200/586] lr: 5.000000e-03 eta: 9:11:06 time: 0.524135 data_time: 0.054236 memory: 8713 loss_kpt: 211.211956 acc_pose: 0.857071 loss: 211.211956 2022/10/12 19:28:13 - mmengine - INFO - Epoch(train) [96][250/586] lr: 5.000000e-03 eta: 9:10:44 time: 0.526451 data_time: 0.055513 memory: 8713 loss_kpt: 209.785118 acc_pose: 0.745339 loss: 209.785118 2022/10/12 19:28:40 - mmengine - INFO - Epoch(train) [96][300/586] lr: 5.000000e-03 eta: 9:10:21 time: 0.532281 data_time: 0.055930 memory: 8713 loss_kpt: 209.750562 acc_pose: 0.856330 loss: 209.750562 2022/10/12 19:28:56 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:29:07 - mmengine - INFO - Epoch(train) [96][350/586] lr: 5.000000e-03 eta: 9:10:00 time: 0.544560 data_time: 0.055543 memory: 8713 loss_kpt: 210.887220 acc_pose: 0.750084 loss: 210.887220 2022/10/12 19:29:34 - mmengine - INFO - Epoch(train) [96][400/586] lr: 5.000000e-03 eta: 9:09:38 time: 0.529887 data_time: 0.055329 memory: 8713 loss_kpt: 212.819107 acc_pose: 0.825572 loss: 212.819107 2022/10/12 19:30:01 - mmengine - INFO - Epoch(train) [96][450/586] lr: 5.000000e-03 eta: 9:09:16 time: 0.536549 data_time: 0.052895 memory: 8713 loss_kpt: 210.550230 acc_pose: 0.760879 loss: 210.550230 2022/10/12 19:30:27 - mmengine - INFO - Epoch(train) [96][500/586] lr: 5.000000e-03 eta: 9:08:53 time: 0.523365 data_time: 0.055396 memory: 8713 loss_kpt: 208.131068 acc_pose: 0.796319 loss: 208.131068 2022/10/12 19:30:53 - mmengine - INFO - Epoch(train) [96][550/586] lr: 5.000000e-03 eta: 9:08:30 time: 0.520390 data_time: 0.058016 memory: 8713 loss_kpt: 211.066856 acc_pose: 0.858121 loss: 211.066856 2022/10/12 19:31:11 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:31:39 - mmengine - INFO - Epoch(train) [97][50/586] lr: 5.000000e-03 eta: 9:07:31 time: 0.563102 data_time: 0.071052 memory: 8713 loss_kpt: 214.040461 acc_pose: 0.857179 loss: 214.040461 2022/10/12 19:32:06 - mmengine - INFO - Epoch(train) [97][100/586] lr: 5.000000e-03 eta: 9:07:09 time: 0.543487 data_time: 0.060003 memory: 8713 loss_kpt: 210.068063 acc_pose: 0.807572 loss: 210.068063 2022/10/12 19:32:33 - mmengine - INFO - Epoch(train) [97][150/586] lr: 5.000000e-03 eta: 9:06:47 time: 0.538871 data_time: 0.055506 memory: 8713 loss_kpt: 211.255597 acc_pose: 0.886051 loss: 211.255597 2022/10/12 19:33:00 - mmengine - INFO - Epoch(train) [97][200/586] lr: 5.000000e-03 eta: 9:06:25 time: 0.523206 data_time: 0.055744 memory: 8713 loss_kpt: 212.390893 acc_pose: 0.776442 loss: 212.390893 2022/10/12 19:33:26 - mmengine - INFO - Epoch(train) [97][250/586] lr: 5.000000e-03 eta: 9:06:02 time: 0.529174 data_time: 0.059140 memory: 8713 loss_kpt: 209.149434 acc_pose: 0.797241 loss: 209.149434 2022/10/12 19:33:52 - mmengine - INFO - Epoch(train) [97][300/586] lr: 5.000000e-03 eta: 9:05:39 time: 0.524674 data_time: 0.056181 memory: 8713 loss_kpt: 207.560766 acc_pose: 0.876075 loss: 207.560766 2022/10/12 19:34:19 - mmengine - INFO - Epoch(train) [97][350/586] lr: 5.000000e-03 eta: 9:05:18 time: 0.541017 data_time: 0.055016 memory: 8713 loss_kpt: 208.733950 acc_pose: 0.800993 loss: 208.733950 2022/10/12 19:34:46 - mmengine - INFO - Epoch(train) [97][400/586] lr: 5.000000e-03 eta: 9:04:55 time: 0.529820 data_time: 0.054979 memory: 8713 loss_kpt: 212.674744 acc_pose: 0.844910 loss: 212.674744 2022/10/12 19:35:12 - mmengine - INFO - Epoch(train) [97][450/586] lr: 5.000000e-03 eta: 9:04:32 time: 0.525130 data_time: 0.056194 memory: 8713 loss_kpt: 211.062474 acc_pose: 0.811813 loss: 211.062474 2022/10/12 19:35:38 - mmengine - INFO - Epoch(train) [97][500/586] lr: 5.000000e-03 eta: 9:04:10 time: 0.525471 data_time: 0.053842 memory: 8713 loss_kpt: 210.223355 acc_pose: 0.805944 loss: 210.223355 2022/10/12 19:36:04 - mmengine - INFO - Epoch(train) [97][550/586] lr: 5.000000e-03 eta: 9:03:47 time: 0.520908 data_time: 0.055999 memory: 8713 loss_kpt: 215.653036 acc_pose: 0.730345 loss: 215.653036 2022/10/12 19:36:23 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:36:50 - mmengine - INFO - Epoch(train) [98][50/586] lr: 5.000000e-03 eta: 9:02:46 time: 0.527732 data_time: 0.066390 memory: 8713 loss_kpt: 211.332076 acc_pose: 0.802147 loss: 211.332076 2022/10/12 19:37:15 - mmengine - INFO - Epoch(train) [98][100/586] lr: 5.000000e-03 eta: 9:02:22 time: 0.509437 data_time: 0.058405 memory: 8713 loss_kpt: 208.575060 acc_pose: 0.806381 loss: 208.575060 2022/10/12 19:37:40 - mmengine - INFO - Epoch(train) [98][150/586] lr: 5.000000e-03 eta: 9:01:59 time: 0.506246 data_time: 0.053157 memory: 8713 loss_kpt: 212.401267 acc_pose: 0.755073 loss: 212.401267 2022/10/12 19:37:44 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:38:06 - mmengine - INFO - Epoch(train) [98][200/586] lr: 5.000000e-03 eta: 9:01:35 time: 0.512288 data_time: 0.055502 memory: 8713 loss_kpt: 214.123407 acc_pose: 0.741633 loss: 214.123407 2022/10/12 19:38:32 - mmengine - INFO - Epoch(train) [98][250/586] lr: 5.000000e-03 eta: 9:01:12 time: 0.518067 data_time: 0.055543 memory: 8713 loss_kpt: 213.343159 acc_pose: 0.815147 loss: 213.343159 2022/10/12 19:38:57 - mmengine - INFO - Epoch(train) [98][300/586] lr: 5.000000e-03 eta: 9:00:48 time: 0.506378 data_time: 0.053976 memory: 8713 loss_kpt: 214.892408 acc_pose: 0.808186 loss: 214.892408 2022/10/12 19:39:22 - mmengine - INFO - Epoch(train) [98][350/586] lr: 5.000000e-03 eta: 9:00:24 time: 0.501286 data_time: 0.058681 memory: 8713 loss_kpt: 210.308642 acc_pose: 0.841511 loss: 210.308642 2022/10/12 19:39:48 - mmengine - INFO - Epoch(train) [98][400/586] lr: 5.000000e-03 eta: 9:00:00 time: 0.507145 data_time: 0.052995 memory: 8713 loss_kpt: 208.788169 acc_pose: 0.881291 loss: 208.788169 2022/10/12 19:40:14 - mmengine - INFO - Epoch(train) [98][450/586] lr: 5.000000e-03 eta: 8:59:37 time: 0.519634 data_time: 0.052411 memory: 8713 loss_kpt: 212.889303 acc_pose: 0.828410 loss: 212.889303 2022/10/12 19:40:39 - mmengine - INFO - Epoch(train) [98][500/586] lr: 5.000000e-03 eta: 8:59:14 time: 0.513097 data_time: 0.053726 memory: 8713 loss_kpt: 218.523785 acc_pose: 0.810678 loss: 218.523785 2022/10/12 19:41:04 - mmengine - INFO - Epoch(train) [98][550/586] lr: 5.000000e-03 eta: 8:58:50 time: 0.501443 data_time: 0.057746 memory: 8713 loss_kpt: 211.854912 acc_pose: 0.809713 loss: 211.854912 2022/10/12 19:41:22 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:41:50 - mmengine - INFO - Epoch(train) [99][50/586] lr: 5.000000e-03 eta: 8:57:50 time: 0.549599 data_time: 0.070633 memory: 8713 loss_kpt: 212.288842 acc_pose: 0.812724 loss: 212.288842 2022/10/12 19:42:16 - mmengine - INFO - Epoch(train) [99][100/586] lr: 5.000000e-03 eta: 8:57:28 time: 0.529877 data_time: 0.061637 memory: 8713 loss_kpt: 214.306135 acc_pose: 0.766135 loss: 214.306135 2022/10/12 19:42:43 - mmengine - INFO - Epoch(train) [99][150/586] lr: 5.000000e-03 eta: 8:57:06 time: 0.539389 data_time: 0.058293 memory: 8713 loss_kpt: 212.501532 acc_pose: 0.863808 loss: 212.501532 2022/10/12 19:43:10 - mmengine - INFO - Epoch(train) [99][200/586] lr: 5.000000e-03 eta: 8:56:44 time: 0.537501 data_time: 0.060429 memory: 8713 loss_kpt: 208.210901 acc_pose: 0.789716 loss: 208.210901 2022/10/12 19:43:37 - mmengine - INFO - Epoch(train) [99][250/586] lr: 5.000000e-03 eta: 8:56:22 time: 0.532224 data_time: 0.058897 memory: 8713 loss_kpt: 212.872073 acc_pose: 0.863819 loss: 212.872073 2022/10/12 19:44:04 - mmengine - INFO - Epoch(train) [99][300/586] lr: 5.000000e-03 eta: 8:56:00 time: 0.550587 data_time: 0.068658 memory: 8713 loss_kpt: 209.990840 acc_pose: 0.821147 loss: 209.990840 2022/10/12 19:44:32 - mmengine - INFO - Epoch(train) [99][350/586] lr: 5.000000e-03 eta: 8:55:39 time: 0.556789 data_time: 0.057101 memory: 8713 loss_kpt: 207.490786 acc_pose: 0.872112 loss: 207.490786 2022/10/12 19:45:00 - mmengine - INFO - Epoch(train) [99][400/586] lr: 5.000000e-03 eta: 8:55:18 time: 0.549428 data_time: 0.061302 memory: 8713 loss_kpt: 207.141512 acc_pose: 0.858725 loss: 207.141512 2022/10/12 19:45:27 - mmengine - INFO - Epoch(train) [99][450/586] lr: 5.000000e-03 eta: 8:54:56 time: 0.543151 data_time: 0.052140 memory: 8713 loss_kpt: 210.928944 acc_pose: 0.825415 loss: 210.928944 2022/10/12 19:45:54 - mmengine - INFO - Epoch(train) [99][500/586] lr: 5.000000e-03 eta: 8:54:35 time: 0.545052 data_time: 0.060642 memory: 8713 loss_kpt: 209.505050 acc_pose: 0.808588 loss: 209.505050 2022/10/12 19:46:21 - mmengine - INFO - Epoch(train) [99][550/586] lr: 5.000000e-03 eta: 8:54:13 time: 0.543775 data_time: 0.056724 memory: 8713 loss_kpt: 211.284497 acc_pose: 0.853543 loss: 211.284497 2022/10/12 19:46:33 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:46:40 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:47:07 - mmengine - INFO - Epoch(train) [100][50/586] lr: 5.000000e-03 eta: 8:53:13 time: 0.525699 data_time: 0.067959 memory: 8713 loss_kpt: 210.383993 acc_pose: 0.796885 loss: 210.383993 2022/10/12 19:47:33 - mmengine - INFO - Epoch(train) [100][100/586] lr: 5.000000e-03 eta: 8:52:50 time: 0.526658 data_time: 0.057568 memory: 8713 loss_kpt: 213.079790 acc_pose: 0.781938 loss: 213.079790 2022/10/12 19:48:00 - mmengine - INFO - Epoch(train) [100][150/586] lr: 5.000000e-03 eta: 8:52:27 time: 0.528066 data_time: 0.055681 memory: 8713 loss_kpt: 209.774277 acc_pose: 0.729471 loss: 209.774277 2022/10/12 19:48:25 - mmengine - INFO - Epoch(train) [100][200/586] lr: 5.000000e-03 eta: 8:52:04 time: 0.512593 data_time: 0.054808 memory: 8713 loss_kpt: 209.789169 acc_pose: 0.852299 loss: 209.789169 2022/10/12 19:48:51 - mmengine - INFO - Epoch(train) [100][250/586] lr: 5.000000e-03 eta: 8:51:41 time: 0.519483 data_time: 0.061533 memory: 8713 loss_kpt: 209.461765 acc_pose: 0.835555 loss: 209.461765 2022/10/12 19:49:17 - mmengine - INFO - Epoch(train) [100][300/586] lr: 5.000000e-03 eta: 8:51:18 time: 0.522973 data_time: 0.055186 memory: 8713 loss_kpt: 213.581236 acc_pose: 0.883561 loss: 213.581236 2022/10/12 19:49:44 - mmengine - INFO - Epoch(train) [100][350/586] lr: 5.000000e-03 eta: 8:50:55 time: 0.526776 data_time: 0.059779 memory: 8713 loss_kpt: 210.048192 acc_pose: 0.829801 loss: 210.048192 2022/10/12 19:50:09 - mmengine - INFO - Epoch(train) [100][400/586] lr: 5.000000e-03 eta: 8:50:32 time: 0.513406 data_time: 0.057745 memory: 8713 loss_kpt: 209.499820 acc_pose: 0.821753 loss: 209.499820 2022/10/12 19:50:36 - mmengine - INFO - Epoch(train) [100][450/586] lr: 5.000000e-03 eta: 8:50:09 time: 0.526298 data_time: 0.061805 memory: 8713 loss_kpt: 210.609206 acc_pose: 0.824328 loss: 210.609206 2022/10/12 19:51:01 - mmengine - INFO - Epoch(train) [100][500/586] lr: 5.000000e-03 eta: 8:49:45 time: 0.515062 data_time: 0.054875 memory: 8713 loss_kpt: 213.045745 acc_pose: 0.842373 loss: 213.045745 2022/10/12 19:51:27 - mmengine - INFO - Epoch(train) [100][550/586] lr: 5.000000e-03 eta: 8:49:22 time: 0.519645 data_time: 0.060605 memory: 8713 loss_kpt: 211.636675 acc_pose: 0.824987 loss: 211.636675 2022/10/12 19:51:46 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:51:46 - mmengine - INFO - Saving checkpoint at 100 epochs 2022/10/12 19:52:00 - mmengine - INFO - Epoch(val) [100][50/407] eta: 0:01:12 time: 0.203992 data_time: 0.013372 memory: 8713 2022/10/12 19:52:09 - mmengine - INFO - Epoch(val) [100][100/407] eta: 0:00:59 time: 0.192359 data_time: 0.008054 memory: 1759 2022/10/12 19:52:19 - mmengine - INFO - Epoch(val) [100][150/407] eta: 0:00:49 time: 0.193301 data_time: 0.008000 memory: 1759 2022/10/12 19:52:29 - mmengine - INFO - Epoch(val) [100][200/407] eta: 0:00:39 time: 0.190926 data_time: 0.007936 memory: 1759 2022/10/12 19:52:38 - mmengine - INFO - Epoch(val) [100][250/407] eta: 0:00:30 time: 0.191963 data_time: 0.007997 memory: 1759 2022/10/12 19:52:48 - mmengine - INFO - Epoch(val) [100][300/407] eta: 0:00:20 time: 0.192110 data_time: 0.008210 memory: 1759 2022/10/12 19:52:58 - mmengine - INFO - Epoch(val) [100][350/407] eta: 0:00:10 time: 0.192650 data_time: 0.008465 memory: 1759 2022/10/12 19:53:07 - mmengine - INFO - Epoch(val) [100][400/407] eta: 0:00:01 time: 0.192378 data_time: 0.007778 memory: 1759 2022/10/12 19:53:21 - mmengine - INFO - Evaluating CocoMetric... 2022/10/12 19:53:37 - mmengine - INFO - Epoch(val) [100][407/407] coco/AP: 0.715062 coco/AP .5: 0.888912 coco/AP .75: 0.790038 coco/AP (M): 0.683123 coco/AP (L): 0.774949 coco/AR: 0.781187 coco/AR .5: 0.929943 coco/AR .75: 0.842097 coco/AR (M): 0.736001 coco/AR (L): 0.843404 2022/10/12 19:53:37 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/liqikai/openmmlab/pt112cu113py38/mmpose/work_dirs/20221012/rsn2x/best_coco/AP_epoch_90.pth is removed 2022/10/12 19:53:39 - mmengine - INFO - The best checkpoint with 0.7151 coco/AP at 100 epoch is saved to best_coco/AP_epoch_100.pth. 2022/10/12 19:54:05 - mmengine - INFO - Epoch(train) [101][50/586] lr: 5.000000e-03 eta: 8:48:22 time: 0.522374 data_time: 0.070167 memory: 8713 loss_kpt: 213.118627 acc_pose: 0.860395 loss: 213.118627 2022/10/12 19:54:31 - mmengine - INFO - Epoch(train) [101][100/586] lr: 5.000000e-03 eta: 8:47:59 time: 0.517807 data_time: 0.056240 memory: 8713 loss_kpt: 212.238979 acc_pose: 0.858637 loss: 212.238979 2022/10/12 19:54:58 - mmengine - INFO - Epoch(train) [101][150/586] lr: 5.000000e-03 eta: 8:47:37 time: 0.537444 data_time: 0.057977 memory: 8713 loss_kpt: 213.131614 acc_pose: 0.868885 loss: 213.131614 2022/10/12 19:55:25 - mmengine - INFO - Epoch(train) [101][200/586] lr: 5.000000e-03 eta: 8:47:15 time: 0.546824 data_time: 0.054788 memory: 8713 loss_kpt: 209.253071 acc_pose: 0.842099 loss: 209.253071 2022/10/12 19:55:52 - mmengine - INFO - Epoch(train) [101][250/586] lr: 5.000000e-03 eta: 8:46:53 time: 0.541421 data_time: 0.053971 memory: 8713 loss_kpt: 201.506611 acc_pose: 0.769284 loss: 201.506611 2022/10/12 19:56:20 - mmengine - INFO - Epoch(train) [101][300/586] lr: 5.000000e-03 eta: 8:46:32 time: 0.551539 data_time: 0.058563 memory: 8713 loss_kpt: 211.861991 acc_pose: 0.772610 loss: 211.861991 2022/10/12 19:56:47 - mmengine - INFO - Epoch(train) [101][350/586] lr: 5.000000e-03 eta: 8:46:10 time: 0.543149 data_time: 0.053267 memory: 8713 loss_kpt: 212.517426 acc_pose: 0.827475 loss: 212.517426 2022/10/12 19:57:14 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:57:14 - mmengine - INFO - Epoch(train) [101][400/586] lr: 5.000000e-03 eta: 8:45:48 time: 0.538500 data_time: 0.054186 memory: 8713 loss_kpt: 213.634585 acc_pose: 0.905680 loss: 213.634585 2022/10/12 19:57:41 - mmengine - INFO - Epoch(train) [101][450/586] lr: 5.000000e-03 eta: 8:45:26 time: 0.535539 data_time: 0.054897 memory: 8713 loss_kpt: 207.932936 acc_pose: 0.800898 loss: 207.932936 2022/10/12 19:58:07 - mmengine - INFO - Epoch(train) [101][500/586] lr: 5.000000e-03 eta: 8:45:03 time: 0.534438 data_time: 0.051504 memory: 8713 loss_kpt: 209.374726 acc_pose: 0.858248 loss: 209.374726 2022/10/12 19:58:34 - mmengine - INFO - Epoch(train) [101][550/586] lr: 5.000000e-03 eta: 8:44:41 time: 0.533839 data_time: 0.052838 memory: 8713 loss_kpt: 211.969388 acc_pose: 0.748357 loss: 211.969388 2022/10/12 19:58:53 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:59:20 - mmengine - INFO - Epoch(train) [102][50/586] lr: 5.000000e-03 eta: 8:43:42 time: 0.536101 data_time: 0.069536 memory: 8713 loss_kpt: 212.215251 acc_pose: 0.843508 loss: 212.215251 2022/10/12 19:59:46 - mmengine - INFO - Epoch(train) [102][100/586] lr: 5.000000e-03 eta: 8:43:18 time: 0.516511 data_time: 0.050819 memory: 8713 loss_kpt: 210.939513 acc_pose: 0.796373 loss: 210.939513 2022/10/12 20:00:12 - mmengine - INFO - Epoch(train) [102][150/586] lr: 5.000000e-03 eta: 8:42:55 time: 0.520774 data_time: 0.055030 memory: 8713 loss_kpt: 209.945161 acc_pose: 0.812969 loss: 209.945161 2022/10/12 20:00:38 - mmengine - INFO - Epoch(train) [102][200/586] lr: 5.000000e-03 eta: 8:42:32 time: 0.514930 data_time: 0.055817 memory: 8713 loss_kpt: 208.623535 acc_pose: 0.856201 loss: 208.623535 2022/10/12 20:01:04 - mmengine - INFO - Epoch(train) [102][250/586] lr: 5.000000e-03 eta: 8:42:09 time: 0.519538 data_time: 0.054119 memory: 8713 loss_kpt: 209.543905 acc_pose: 0.796167 loss: 209.543905 2022/10/12 20:01:30 - mmengine - INFO - Epoch(train) [102][300/586] lr: 5.000000e-03 eta: 8:41:46 time: 0.532993 data_time: 0.055458 memory: 8713 loss_kpt: 210.603710 acc_pose: 0.854047 loss: 210.603710 2022/10/12 20:01:57 - mmengine - INFO - Epoch(train) [102][350/586] lr: 5.000000e-03 eta: 8:41:24 time: 0.538172 data_time: 0.057018 memory: 8713 loss_kpt: 214.606914 acc_pose: 0.821566 loss: 214.606914 2022/10/12 20:02:24 - mmengine - INFO - Epoch(train) [102][400/586] lr: 5.000000e-03 eta: 8:41:02 time: 0.534892 data_time: 0.058097 memory: 8713 loss_kpt: 211.196407 acc_pose: 0.882885 loss: 211.196407 2022/10/12 20:02:51 - mmengine - INFO - Epoch(train) [102][450/586] lr: 5.000000e-03 eta: 8:40:39 time: 0.533056 data_time: 0.054488 memory: 8713 loss_kpt: 216.060421 acc_pose: 0.845497 loss: 216.060421 2022/10/12 20:03:18 - mmengine - INFO - Epoch(train) [102][500/586] lr: 5.000000e-03 eta: 8:40:17 time: 0.543651 data_time: 0.054569 memory: 8713 loss_kpt: 210.093295 acc_pose: 0.798014 loss: 210.093295 2022/10/12 20:03:44 - mmengine - INFO - Epoch(train) [102][550/586] lr: 5.000000e-03 eta: 8:39:54 time: 0.524896 data_time: 0.054325 memory: 8713 loss_kpt: 210.260671 acc_pose: 0.833619 loss: 210.260671 2022/10/12 20:04:03 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:04:30 - mmengine - INFO - Epoch(train) [103][50/586] lr: 5.000000e-03 eta: 8:38:56 time: 0.549272 data_time: 0.068408 memory: 8713 loss_kpt: 209.593102 acc_pose: 0.833265 loss: 209.593102 2022/10/12 20:04:57 - mmengine - INFO - Epoch(train) [103][100/586] lr: 5.000000e-03 eta: 8:38:34 time: 0.541807 data_time: 0.061797 memory: 8713 loss_kpt: 208.345729 acc_pose: 0.816601 loss: 208.345729 2022/10/12 20:05:24 - mmengine - INFO - Epoch(train) [103][150/586] lr: 5.000000e-03 eta: 8:38:12 time: 0.534619 data_time: 0.055438 memory: 8713 loss_kpt: 212.788786 acc_pose: 0.880550 loss: 212.788786 2022/10/12 20:05:51 - mmengine - INFO - Epoch(train) [103][200/586] lr: 5.000000e-03 eta: 8:37:49 time: 0.531326 data_time: 0.060030 memory: 8713 loss_kpt: 213.254034 acc_pose: 0.854272 loss: 213.254034 2022/10/12 20:06:06 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:06:17 - mmengine - INFO - Epoch(train) [103][250/586] lr: 5.000000e-03 eta: 8:37:27 time: 0.528712 data_time: 0.050919 memory: 8713 loss_kpt: 209.393568 acc_pose: 0.749110 loss: 209.393568 2022/10/12 20:06:44 - mmengine - INFO - Epoch(train) [103][300/586] lr: 5.000000e-03 eta: 8:37:05 time: 0.545249 data_time: 0.053673 memory: 8713 loss_kpt: 207.702772 acc_pose: 0.802567 loss: 207.702772 2022/10/12 20:07:11 - mmengine - INFO - Epoch(train) [103][350/586] lr: 5.000000e-03 eta: 8:36:43 time: 0.539285 data_time: 0.056400 memory: 8713 loss_kpt: 209.235233 acc_pose: 0.817530 loss: 209.235233 2022/10/12 20:07:38 - mmengine - INFO - Epoch(train) [103][400/586] lr: 5.000000e-03 eta: 8:36:20 time: 0.529694 data_time: 0.058964 memory: 8713 loss_kpt: 207.407604 acc_pose: 0.726414 loss: 207.407604 2022/10/12 20:08:05 - mmengine - INFO - Epoch(train) [103][450/586] lr: 5.000000e-03 eta: 8:35:58 time: 0.546093 data_time: 0.057938 memory: 8713 loss_kpt: 209.184297 acc_pose: 0.773243 loss: 209.184297 2022/10/12 20:08:32 - mmengine - INFO - Epoch(train) [103][500/586] lr: 5.000000e-03 eta: 8:35:35 time: 0.527607 data_time: 0.054498 memory: 8713 loss_kpt: 212.401576 acc_pose: 0.840185 loss: 212.401576 2022/10/12 20:08:58 - mmengine - INFO - Epoch(train) [103][550/586] lr: 5.000000e-03 eta: 8:35:13 time: 0.535019 data_time: 0.055045 memory: 8713 loss_kpt: 209.820176 acc_pose: 0.829474 loss: 209.820176 2022/10/12 20:09:17 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:09:45 - mmengine - INFO - Epoch(train) [104][50/586] lr: 5.000000e-03 eta: 8:34:15 time: 0.549990 data_time: 0.071557 memory: 8713 loss_kpt: 210.761799 acc_pose: 0.844751 loss: 210.761799 2022/10/12 20:10:13 - mmengine - INFO - Epoch(train) [104][100/586] lr: 5.000000e-03 eta: 8:33:54 time: 0.561621 data_time: 0.058891 memory: 8713 loss_kpt: 210.889230 acc_pose: 0.872249 loss: 210.889230 2022/10/12 20:10:42 - mmengine - INFO - Epoch(train) [104][150/586] lr: 5.000000e-03 eta: 8:33:34 time: 0.577944 data_time: 0.059244 memory: 8713 loss_kpt: 214.204715 acc_pose: 0.786351 loss: 214.204715 2022/10/12 20:11:10 - mmengine - INFO - Epoch(train) [104][200/586] lr: 5.000000e-03 eta: 8:33:13 time: 0.564220 data_time: 0.062765 memory: 8713 loss_kpt: 210.276022 acc_pose: 0.833476 loss: 210.276022 2022/10/12 20:11:38 - mmengine - INFO - Epoch(train) [104][250/586] lr: 5.000000e-03 eta: 8:32:52 time: 0.569639 data_time: 0.058518 memory: 8713 loss_kpt: 213.457856 acc_pose: 0.807286 loss: 213.457856 2022/10/12 20:12:06 - mmengine - INFO - Epoch(train) [104][300/586] lr: 5.000000e-03 eta: 8:32:31 time: 0.557458 data_time: 0.061267 memory: 8713 loss_kpt: 211.567341 acc_pose: 0.758099 loss: 211.567341 2022/10/12 20:12:33 - mmengine - INFO - Epoch(train) [104][350/586] lr: 5.000000e-03 eta: 8:32:09 time: 0.541996 data_time: 0.058282 memory: 8713 loss_kpt: 211.602211 acc_pose: 0.832491 loss: 211.602211 2022/10/12 20:12:59 - mmengine - INFO - Epoch(train) [104][400/586] lr: 5.000000e-03 eta: 8:31:46 time: 0.524781 data_time: 0.059650 memory: 8713 loss_kpt: 207.840860 acc_pose: 0.854662 loss: 207.840860 2022/10/12 20:13:26 - mmengine - INFO - Epoch(train) [104][450/586] lr: 5.000000e-03 eta: 8:31:23 time: 0.539087 data_time: 0.056010 memory: 8713 loss_kpt: 207.551377 acc_pose: 0.809858 loss: 207.551377 2022/10/12 20:13:53 - mmengine - INFO - Epoch(train) [104][500/586] lr: 5.000000e-03 eta: 8:31:01 time: 0.537368 data_time: 0.062084 memory: 8713 loss_kpt: 209.295926 acc_pose: 0.836312 loss: 209.295926 2022/10/12 20:14:20 - mmengine - INFO - Epoch(train) [104][550/586] lr: 5.000000e-03 eta: 8:30:38 time: 0.525962 data_time: 0.055615 memory: 8713 loss_kpt: 210.144214 acc_pose: 0.805840 loss: 210.144214 2022/10/12 20:14:39 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:15:06 - mmengine - INFO - Epoch(train) [105][50/586] lr: 5.000000e-03 eta: 8:29:40 time: 0.537837 data_time: 0.067274 memory: 8713 loss_kpt: 212.711819 acc_pose: 0.808689 loss: 212.711819 2022/10/12 20:15:09 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:15:32 - mmengine - INFO - Epoch(train) [105][100/586] lr: 5.000000e-03 eta: 8:29:17 time: 0.526437 data_time: 0.057681 memory: 8713 loss_kpt: 209.807935 acc_pose: 0.787192 loss: 209.807935 2022/10/12 20:15:58 - mmengine - INFO - Epoch(train) [105][150/586] lr: 5.000000e-03 eta: 8:28:54 time: 0.521256 data_time: 0.054621 memory: 8713 loss_kpt: 210.121754 acc_pose: 0.804304 loss: 210.121754 2022/10/12 20:16:24 - mmengine - INFO - Epoch(train) [105][200/586] lr: 5.000000e-03 eta: 8:28:30 time: 0.519109 data_time: 0.056953 memory: 8713 loss_kpt: 208.807090 acc_pose: 0.798005 loss: 208.807090 2022/10/12 20:16:50 - mmengine - INFO - Epoch(train) [105][250/586] lr: 5.000000e-03 eta: 8:28:07 time: 0.517738 data_time: 0.058071 memory: 8713 loss_kpt: 210.946446 acc_pose: 0.780858 loss: 210.946446 2022/10/12 20:17:16 - mmengine - INFO - Epoch(train) [105][300/586] lr: 5.000000e-03 eta: 8:27:44 time: 0.518486 data_time: 0.054650 memory: 8713 loss_kpt: 207.977048 acc_pose: 0.800558 loss: 207.977048 2022/10/12 20:17:43 - mmengine - INFO - Epoch(train) [105][350/586] lr: 5.000000e-03 eta: 8:27:21 time: 0.532435 data_time: 0.054289 memory: 8713 loss_kpt: 208.699045 acc_pose: 0.752402 loss: 208.699045 2022/10/12 20:18:09 - mmengine - INFO - Epoch(train) [105][400/586] lr: 5.000000e-03 eta: 8:26:58 time: 0.531106 data_time: 0.052042 memory: 8713 loss_kpt: 208.960844 acc_pose: 0.833098 loss: 208.960844 2022/10/12 20:18:35 - mmengine - INFO - Epoch(train) [105][450/586] lr: 5.000000e-03 eta: 8:26:35 time: 0.516214 data_time: 0.056568 memory: 8713 loss_kpt: 209.035200 acc_pose: 0.833564 loss: 209.035200 2022/10/12 20:19:01 - mmengine - INFO - Epoch(train) [105][500/586] lr: 5.000000e-03 eta: 8:26:12 time: 0.524932 data_time: 0.059203 memory: 8713 loss_kpt: 207.225011 acc_pose: 0.857501 loss: 207.225011 2022/10/12 20:19:27 - mmengine - INFO - Epoch(train) [105][550/586] lr: 5.000000e-03 eta: 8:25:49 time: 0.524404 data_time: 0.056499 memory: 8713 loss_kpt: 210.753665 acc_pose: 0.795545 loss: 210.753665 2022/10/12 20:19:46 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:20:13 - mmengine - INFO - Epoch(train) [106][50/586] lr: 5.000000e-03 eta: 8:24:51 time: 0.533590 data_time: 0.070730 memory: 8713 loss_kpt: 211.592928 acc_pose: 0.789570 loss: 211.592928 2022/10/12 20:20:39 - mmengine - INFO - Epoch(train) [106][100/586] lr: 5.000000e-03 eta: 8:24:27 time: 0.520324 data_time: 0.053206 memory: 8713 loss_kpt: 208.412292 acc_pose: 0.856887 loss: 208.412292 2022/10/12 20:21:05 - mmengine - INFO - Epoch(train) [106][150/586] lr: 5.000000e-03 eta: 8:24:04 time: 0.523183 data_time: 0.059608 memory: 8713 loss_kpt: 209.508954 acc_pose: 0.880647 loss: 209.508954 2022/10/12 20:21:31 - mmengine - INFO - Epoch(train) [106][200/586] lr: 5.000000e-03 eta: 8:23:41 time: 0.521277 data_time: 0.054387 memory: 8713 loss_kpt: 211.976538 acc_pose: 0.822758 loss: 211.976538 2022/10/12 20:21:58 - mmengine - INFO - Epoch(train) [106][250/586] lr: 5.000000e-03 eta: 8:23:18 time: 0.525183 data_time: 0.053146 memory: 8713 loss_kpt: 208.683347 acc_pose: 0.821495 loss: 208.683347 2022/10/12 20:22:24 - mmengine - INFO - Epoch(train) [106][300/586] lr: 5.000000e-03 eta: 8:22:55 time: 0.525612 data_time: 0.057041 memory: 8713 loss_kpt: 211.673373 acc_pose: 0.825889 loss: 211.673373 2022/10/12 20:22:50 - mmengine - INFO - Epoch(train) [106][350/586] lr: 5.000000e-03 eta: 8:22:32 time: 0.518979 data_time: 0.059158 memory: 8713 loss_kpt: 210.671255 acc_pose: 0.789952 loss: 210.671255 2022/10/12 20:23:16 - mmengine - INFO - Epoch(train) [106][400/586] lr: 5.000000e-03 eta: 8:22:08 time: 0.519802 data_time: 0.055370 memory: 8713 loss_kpt: 210.970096 acc_pose: 0.867133 loss: 210.970096 2022/10/12 20:23:43 - mmengine - INFO - Epoch(train) [106][450/586] lr: 5.000000e-03 eta: 8:21:47 time: 0.549586 data_time: 0.058027 memory: 8713 loss_kpt: 211.185975 acc_pose: 0.789568 loss: 211.185975 2022/10/12 20:23:54 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:24:10 - mmengine - INFO - Epoch(train) [106][500/586] lr: 5.000000e-03 eta: 8:21:24 time: 0.534118 data_time: 0.058603 memory: 8713 loss_kpt: 209.852276 acc_pose: 0.865587 loss: 209.852276 2022/10/12 20:24:37 - mmengine - INFO - Epoch(train) [106][550/586] lr: 5.000000e-03 eta: 8:21:02 time: 0.541691 data_time: 0.057687 memory: 8713 loss_kpt: 209.004818 acc_pose: 0.807274 loss: 209.004818 2022/10/12 20:24:56 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:25:23 - mmengine - INFO - Epoch(train) [107][50/586] lr: 5.000000e-03 eta: 8:20:04 time: 0.528505 data_time: 0.062097 memory: 8713 loss_kpt: 209.137823 acc_pose: 0.878785 loss: 209.137823 2022/10/12 20:25:49 - mmengine - INFO - Epoch(train) [107][100/586] lr: 5.000000e-03 eta: 8:19:41 time: 0.533093 data_time: 0.059851 memory: 8713 loss_kpt: 213.541707 acc_pose: 0.822649 loss: 213.541707 2022/10/12 20:26:16 - mmengine - INFO - Epoch(train) [107][150/586] lr: 5.000000e-03 eta: 8:19:18 time: 0.530477 data_time: 0.054900 memory: 8713 loss_kpt: 206.309249 acc_pose: 0.888483 loss: 206.309249 2022/10/12 20:26:42 - mmengine - INFO - Epoch(train) [107][200/586] lr: 5.000000e-03 eta: 8:18:55 time: 0.518856 data_time: 0.056710 memory: 8713 loss_kpt: 209.776766 acc_pose: 0.867041 loss: 209.776766 2022/10/12 20:27:08 - mmengine - INFO - Epoch(train) [107][250/586] lr: 5.000000e-03 eta: 8:18:32 time: 0.531317 data_time: 0.054968 memory: 8713 loss_kpt: 208.598214 acc_pose: 0.749790 loss: 208.598214 2022/10/12 20:27:35 - mmengine - INFO - Epoch(train) [107][300/586] lr: 5.000000e-03 eta: 8:18:09 time: 0.535505 data_time: 0.061039 memory: 8713 loss_kpt: 207.200141 acc_pose: 0.848815 loss: 207.200141 2022/10/12 20:28:02 - mmengine - INFO - Epoch(train) [107][350/586] lr: 5.000000e-03 eta: 8:17:47 time: 0.546054 data_time: 0.054434 memory: 8713 loss_kpt: 212.562927 acc_pose: 0.808581 loss: 212.562927 2022/10/12 20:28:30 - mmengine - INFO - Epoch(train) [107][400/586] lr: 5.000000e-03 eta: 8:17:25 time: 0.548197 data_time: 0.061182 memory: 8713 loss_kpt: 210.268823 acc_pose: 0.838487 loss: 210.268823 2022/10/12 20:28:57 - mmengine - INFO - Epoch(train) [107][450/586] lr: 5.000000e-03 eta: 8:17:04 time: 0.549133 data_time: 0.057075 memory: 8713 loss_kpt: 205.396271 acc_pose: 0.860401 loss: 205.396271 2022/10/12 20:29:25 - mmengine - INFO - Epoch(train) [107][500/586] lr: 5.000000e-03 eta: 8:16:42 time: 0.550671 data_time: 0.060848 memory: 8713 loss_kpt: 209.180907 acc_pose: 0.819014 loss: 209.180907 2022/10/12 20:29:53 - mmengine - INFO - Epoch(train) [107][550/586] lr: 5.000000e-03 eta: 8:16:20 time: 0.554620 data_time: 0.058103 memory: 8713 loss_kpt: 207.877010 acc_pose: 0.817003 loss: 207.877010 2022/10/12 20:30:12 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:30:39 - mmengine - INFO - Epoch(train) [108][50/586] lr: 5.000000e-03 eta: 8:15:23 time: 0.543900 data_time: 0.066705 memory: 8713 loss_kpt: 207.005533 acc_pose: 0.820740 loss: 207.005533 2022/10/12 20:31:06 - mmengine - INFO - Epoch(train) [108][100/586] lr: 5.000000e-03 eta: 8:15:00 time: 0.528648 data_time: 0.057251 memory: 8713 loss_kpt: 209.540977 acc_pose: 0.864556 loss: 209.540977 2022/10/12 20:31:33 - mmengine - INFO - Epoch(train) [108][150/586] lr: 5.000000e-03 eta: 8:14:37 time: 0.535878 data_time: 0.062974 memory: 8713 loss_kpt: 208.064436 acc_pose: 0.829246 loss: 208.064436 2022/10/12 20:31:59 - mmengine - INFO - Epoch(train) [108][200/586] lr: 5.000000e-03 eta: 8:14:14 time: 0.528282 data_time: 0.054500 memory: 8713 loss_kpt: 205.274236 acc_pose: 0.842130 loss: 205.274236 2022/10/12 20:32:26 - mmengine - INFO - Epoch(train) [108][250/586] lr: 5.000000e-03 eta: 8:13:52 time: 0.547071 data_time: 0.058570 memory: 8713 loss_kpt: 211.952536 acc_pose: 0.874930 loss: 211.952536 2022/10/12 20:32:52 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:32:53 - mmengine - INFO - Epoch(train) [108][300/586] lr: 5.000000e-03 eta: 8:13:30 time: 0.532716 data_time: 0.051560 memory: 8713 loss_kpt: 208.448054 acc_pose: 0.830434 loss: 208.448054 2022/10/12 20:33:20 - mmengine - INFO - Epoch(train) [108][350/586] lr: 5.000000e-03 eta: 8:13:07 time: 0.535001 data_time: 0.059002 memory: 8713 loss_kpt: 212.016692 acc_pose: 0.779947 loss: 212.016692 2022/10/12 20:33:46 - mmengine - INFO - Epoch(train) [108][400/586] lr: 5.000000e-03 eta: 8:12:44 time: 0.532952 data_time: 0.052821 memory: 8713 loss_kpt: 210.390720 acc_pose: 0.835992 loss: 210.390720 2022/10/12 20:34:13 - mmengine - INFO - Epoch(train) [108][450/586] lr: 5.000000e-03 eta: 8:12:22 time: 0.540460 data_time: 0.058997 memory: 8713 loss_kpt: 208.551637 acc_pose: 0.771462 loss: 208.551637 2022/10/12 20:34:39 - mmengine - INFO - Epoch(train) [108][500/586] lr: 5.000000e-03 eta: 8:11:59 time: 0.521656 data_time: 0.056206 memory: 8713 loss_kpt: 206.840492 acc_pose: 0.826604 loss: 206.840492 2022/10/12 20:35:06 - mmengine - INFO - Epoch(train) [108][550/586] lr: 5.000000e-03 eta: 8:11:36 time: 0.531629 data_time: 0.057254 memory: 8713 loss_kpt: 207.061926 acc_pose: 0.798539 loss: 207.061926 2022/10/12 20:35:25 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:35:52 - mmengine - INFO - Epoch(train) [109][50/586] lr: 5.000000e-03 eta: 8:10:38 time: 0.532522 data_time: 0.067646 memory: 8713 loss_kpt: 213.974807 acc_pose: 0.853851 loss: 213.974807 2022/10/12 20:36:18 - mmengine - INFO - Epoch(train) [109][100/586] lr: 5.000000e-03 eta: 8:10:15 time: 0.528831 data_time: 0.057751 memory: 8713 loss_kpt: 205.661416 acc_pose: 0.776992 loss: 205.661416 2022/10/12 20:36:44 - mmengine - INFO - Epoch(train) [109][150/586] lr: 5.000000e-03 eta: 8:09:52 time: 0.519819 data_time: 0.056690 memory: 8713 loss_kpt: 207.830738 acc_pose: 0.846940 loss: 207.830738 2022/10/12 20:37:11 - mmengine - INFO - Epoch(train) [109][200/586] lr: 5.000000e-03 eta: 8:09:30 time: 0.541595 data_time: 0.058990 memory: 8713 loss_kpt: 208.601561 acc_pose: 0.797532 loss: 208.601561 2022/10/12 20:37:37 - mmengine - INFO - Epoch(train) [109][250/586] lr: 5.000000e-03 eta: 8:09:06 time: 0.508209 data_time: 0.052780 memory: 8713 loss_kpt: 211.485361 acc_pose: 0.801498 loss: 211.485361 2022/10/12 20:38:02 - mmengine - INFO - Epoch(train) [109][300/586] lr: 5.000000e-03 eta: 8:08:42 time: 0.505171 data_time: 0.054746 memory: 8713 loss_kpt: 209.516120 acc_pose: 0.805461 loss: 209.516120 2022/10/12 20:38:28 - mmengine - INFO - Epoch(train) [109][350/586] lr: 5.000000e-03 eta: 8:08:18 time: 0.515332 data_time: 0.059345 memory: 8713 loss_kpt: 210.316344 acc_pose: 0.857178 loss: 210.316344 2022/10/12 20:38:54 - mmengine - INFO - Epoch(train) [109][400/586] lr: 5.000000e-03 eta: 8:07:54 time: 0.516087 data_time: 0.057669 memory: 8713 loss_kpt: 213.170247 acc_pose: 0.856194 loss: 213.170247 2022/10/12 20:39:20 - mmengine - INFO - Epoch(train) [109][450/586] lr: 5.000000e-03 eta: 8:07:31 time: 0.526946 data_time: 0.056170 memory: 8713 loss_kpt: 205.350438 acc_pose: 0.849899 loss: 205.350438 2022/10/12 20:39:46 - mmengine - INFO - Epoch(train) [109][500/586] lr: 5.000000e-03 eta: 8:07:08 time: 0.525926 data_time: 0.053025 memory: 8713 loss_kpt: 211.542645 acc_pose: 0.879914 loss: 211.542645 2022/10/12 20:40:13 - mmengine - INFO - Epoch(train) [109][550/586] lr: 5.000000e-03 eta: 8:06:45 time: 0.530319 data_time: 0.057050 memory: 8713 loss_kpt: 207.493074 acc_pose: 0.768476 loss: 207.493074 2022/10/12 20:40:31 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:40:58 - mmengine - INFO - Epoch(train) [110][50/586] lr: 5.000000e-03 eta: 8:05:49 time: 0.540778 data_time: 0.066829 memory: 8713 loss_kpt: 209.016517 acc_pose: 0.851836 loss: 209.016517 2022/10/12 20:41:24 - mmengine - INFO - Epoch(train) [110][100/586] lr: 5.000000e-03 eta: 8:05:25 time: 0.513317 data_time: 0.054053 memory: 8713 loss_kpt: 208.259958 acc_pose: 0.809243 loss: 208.259958 2022/10/12 20:41:37 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:41:50 - mmengine - INFO - Epoch(train) [110][150/586] lr: 5.000000e-03 eta: 8:05:01 time: 0.514419 data_time: 0.058913 memory: 8713 loss_kpt: 208.549568 acc_pose: 0.825656 loss: 208.549568 2022/10/12 20:42:15 - mmengine - INFO - Epoch(train) [110][200/586] lr: 5.000000e-03 eta: 8:04:37 time: 0.507774 data_time: 0.052835 memory: 8713 loss_kpt: 211.941365 acc_pose: 0.862916 loss: 211.941365 2022/10/12 20:42:40 - mmengine - INFO - Epoch(train) [110][250/586] lr: 5.000000e-03 eta: 8:04:13 time: 0.507256 data_time: 0.058248 memory: 8713 loss_kpt: 210.118373 acc_pose: 0.794240 loss: 210.118373 2022/10/12 20:43:06 - mmengine - INFO - Epoch(train) [110][300/586] lr: 5.000000e-03 eta: 8:03:50 time: 0.510785 data_time: 0.055524 memory: 8713 loss_kpt: 205.803355 acc_pose: 0.830729 loss: 205.803355 2022/10/12 20:43:31 - mmengine - INFO - Epoch(train) [110][350/586] lr: 5.000000e-03 eta: 8:03:26 time: 0.508558 data_time: 0.061191 memory: 8713 loss_kpt: 212.291874 acc_pose: 0.799299 loss: 212.291874 2022/10/12 20:43:57 - mmengine - INFO - Epoch(train) [110][400/586] lr: 5.000000e-03 eta: 8:03:02 time: 0.514164 data_time: 0.054368 memory: 8713 loss_kpt: 209.964533 acc_pose: 0.764112 loss: 209.964533 2022/10/12 20:44:23 - mmengine - INFO - Epoch(train) [110][450/586] lr: 5.000000e-03 eta: 8:02:38 time: 0.519046 data_time: 0.057958 memory: 8713 loss_kpt: 209.192277 acc_pose: 0.847137 loss: 209.192277 2022/10/12 20:44:48 - mmengine - INFO - Epoch(train) [110][500/586] lr: 5.000000e-03 eta: 8:02:14 time: 0.508392 data_time: 0.055056 memory: 8713 loss_kpt: 209.222981 acc_pose: 0.771589 loss: 209.222981 2022/10/12 20:45:14 - mmengine - INFO - Epoch(train) [110][550/586] lr: 5.000000e-03 eta: 8:01:51 time: 0.513380 data_time: 0.061350 memory: 8713 loss_kpt: 208.689779 acc_pose: 0.827087 loss: 208.689779 2022/10/12 20:45:32 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:45:33 - mmengine - INFO - Saving checkpoint at 110 epochs 2022/10/12 20:45:46 - mmengine - INFO - Epoch(val) [110][50/407] eta: 0:01:10 time: 0.197706 data_time: 0.012290 memory: 8713 2022/10/12 20:45:56 - mmengine - INFO - Epoch(val) [110][100/407] eta: 0:00:59 time: 0.195338 data_time: 0.007987 memory: 1759 2022/10/12 20:46:05 - mmengine - INFO - Epoch(val) [110][150/407] eta: 0:00:49 time: 0.192539 data_time: 0.008053 memory: 1759 2022/10/12 20:46:15 - mmengine - INFO - Epoch(val) [110][200/407] eta: 0:00:39 time: 0.190266 data_time: 0.007925 memory: 1759 2022/10/12 20:46:24 - mmengine - INFO - Epoch(val) [110][250/407] eta: 0:00:29 time: 0.190931 data_time: 0.008169 memory: 1759 2022/10/12 20:46:34 - mmengine - INFO - Epoch(val) [110][300/407] eta: 0:00:20 time: 0.192487 data_time: 0.008115 memory: 1759 2022/10/12 20:46:44 - mmengine - INFO - Epoch(val) [110][350/407] eta: 0:00:11 time: 0.195642 data_time: 0.007990 memory: 1759 2022/10/12 20:46:53 - mmengine - INFO - Epoch(val) [110][400/407] eta: 0:00:01 time: 0.190293 data_time: 0.008097 memory: 1759 2022/10/12 20:47:07 - mmengine - INFO - Evaluating CocoMetric... 2022/10/12 20:47:23 - mmengine - INFO - Epoch(val) [110][407/407] coco/AP: 0.713493 coco/AP .5: 0.887146 coco/AP .75: 0.788041 coco/AP (M): 0.681104 coco/AP (L): 0.774353 coco/AR: 0.780746 coco/AR .5: 0.929628 coco/AR .75: 0.842097 coco/AR (M): 0.736984 coco/AR (L): 0.841249 2022/10/12 20:47:50 - mmengine - INFO - Epoch(train) [111][50/586] lr: 5.000000e-03 eta: 8:00:55 time: 0.543125 data_time: 0.064935 memory: 8713 loss_kpt: 207.657777 acc_pose: 0.876984 loss: 207.657777 2022/10/12 20:48:16 - mmengine - INFO - Epoch(train) [111][100/586] lr: 5.000000e-03 eta: 8:00:31 time: 0.518126 data_time: 0.056239 memory: 8713 loss_kpt: 208.158841 acc_pose: 0.758008 loss: 208.158841 2022/10/12 20:48:41 - mmengine - INFO - Epoch(train) [111][150/586] lr: 5.000000e-03 eta: 8:00:07 time: 0.513882 data_time: 0.055959 memory: 8713 loss_kpt: 211.856912 acc_pose: 0.878161 loss: 211.856912 2022/10/12 20:49:07 - mmengine - INFO - Epoch(train) [111][200/586] lr: 5.000000e-03 eta: 7:59:43 time: 0.505707 data_time: 0.055829 memory: 8713 loss_kpt: 208.802026 acc_pose: 0.768614 loss: 208.802026 2022/10/12 20:49:32 - mmengine - INFO - Epoch(train) [111][250/586] lr: 5.000000e-03 eta: 7:59:19 time: 0.510799 data_time: 0.055816 memory: 8713 loss_kpt: 205.186115 acc_pose: 0.861094 loss: 205.186115 2022/10/12 20:49:58 - mmengine - INFO - Epoch(train) [111][300/586] lr: 5.000000e-03 eta: 7:58:56 time: 0.510917 data_time: 0.057214 memory: 8713 loss_kpt: 208.215254 acc_pose: 0.861506 loss: 208.215254 2022/10/12 20:50:24 - mmengine - INFO - Epoch(train) [111][350/586] lr: 5.000000e-03 eta: 7:58:32 time: 0.517709 data_time: 0.059583 memory: 8713 loss_kpt: 210.715741 acc_pose: 0.830031 loss: 210.715741 2022/10/12 20:50:49 - mmengine - INFO - Epoch(train) [111][400/586] lr: 5.000000e-03 eta: 7:58:08 time: 0.511163 data_time: 0.056821 memory: 8713 loss_kpt: 206.948332 acc_pose: 0.778395 loss: 206.948332 2022/10/12 20:51:15 - mmengine - INFO - Epoch(train) [111][450/586] lr: 5.000000e-03 eta: 7:57:45 time: 0.515460 data_time: 0.057400 memory: 8713 loss_kpt: 207.740835 acc_pose: 0.823660 loss: 207.740835 2022/10/12 20:51:40 - mmengine - INFO - Epoch(train) [111][500/586] lr: 5.000000e-03 eta: 7:57:21 time: 0.505331 data_time: 0.053182 memory: 8713 loss_kpt: 207.945929 acc_pose: 0.831489 loss: 207.945929 2022/10/12 20:52:01 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:52:06 - mmengine - INFO - Epoch(train) [111][550/586] lr: 5.000000e-03 eta: 7:56:56 time: 0.506446 data_time: 0.052896 memory: 8713 loss_kpt: 209.105204 acc_pose: 0.835586 loss: 209.105204 2022/10/12 20:52:23 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:52:50 - mmengine - INFO - Epoch(train) [112][50/586] lr: 5.000000e-03 eta: 7:56:00 time: 0.527223 data_time: 0.063069 memory: 8713 loss_kpt: 211.624617 acc_pose: 0.857456 loss: 211.624617 2022/10/12 20:53:15 - mmengine - INFO - Epoch(train) [112][100/586] lr: 5.000000e-03 eta: 7:55:36 time: 0.511035 data_time: 0.051714 memory: 8713 loss_kpt: 211.590643 acc_pose: 0.832330 loss: 211.590643 2022/10/12 20:53:41 - mmengine - INFO - Epoch(train) [112][150/586] lr: 5.000000e-03 eta: 7:55:13 time: 0.521921 data_time: 0.054667 memory: 8713 loss_kpt: 210.849834 acc_pose: 0.772608 loss: 210.849834 2022/10/12 20:54:07 - mmengine - INFO - Epoch(train) [112][200/586] lr: 5.000000e-03 eta: 7:54:49 time: 0.512722 data_time: 0.056521 memory: 8713 loss_kpt: 209.651288 acc_pose: 0.813005 loss: 209.651288 2022/10/12 20:54:33 - mmengine - INFO - Epoch(train) [112][250/586] lr: 5.000000e-03 eta: 7:54:25 time: 0.519142 data_time: 0.057122 memory: 8713 loss_kpt: 206.747065 acc_pose: 0.825945 loss: 206.747065 2022/10/12 20:55:00 - mmengine - INFO - Epoch(train) [112][300/586] lr: 5.000000e-03 eta: 7:54:03 time: 0.533012 data_time: 0.053789 memory: 8713 loss_kpt: 204.496277 acc_pose: 0.825600 loss: 204.496277 2022/10/12 20:55:26 - mmengine - INFO - Epoch(train) [112][350/586] lr: 5.000000e-03 eta: 7:53:40 time: 0.529357 data_time: 0.054137 memory: 8713 loss_kpt: 211.528113 acc_pose: 0.761955 loss: 211.528113 2022/10/12 20:55:52 - mmengine - INFO - Epoch(train) [112][400/586] lr: 5.000000e-03 eta: 7:53:16 time: 0.520268 data_time: 0.060231 memory: 8713 loss_kpt: 208.507265 acc_pose: 0.796104 loss: 208.507265 2022/10/12 20:56:18 - mmengine - INFO - Epoch(train) [112][450/586] lr: 5.000000e-03 eta: 7:52:52 time: 0.514146 data_time: 0.059538 memory: 8713 loss_kpt: 207.020958 acc_pose: 0.810849 loss: 207.020958 2022/10/12 20:56:44 - mmengine - INFO - Epoch(train) [112][500/586] lr: 5.000000e-03 eta: 7:52:29 time: 0.519011 data_time: 0.055498 memory: 8713 loss_kpt: 207.595736 acc_pose: 0.852570 loss: 207.595736 2022/10/12 20:57:10 - mmengine - INFO - Epoch(train) [112][550/586] lr: 5.000000e-03 eta: 7:52:06 time: 0.524289 data_time: 0.061675 memory: 8713 loss_kpt: 211.723373 acc_pose: 0.819312 loss: 211.723373 2022/10/12 20:57:28 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:57:56 - mmengine - INFO - Epoch(train) [113][50/586] lr: 5.000000e-03 eta: 7:51:10 time: 0.546790 data_time: 0.069119 memory: 8713 loss_kpt: 209.216041 acc_pose: 0.781323 loss: 209.216041 2022/10/12 20:58:22 - mmengine - INFO - Epoch(train) [113][100/586] lr: 5.000000e-03 eta: 7:50:47 time: 0.532240 data_time: 0.065638 memory: 8713 loss_kpt: 209.694827 acc_pose: 0.794741 loss: 209.694827 2022/10/12 20:58:48 - mmengine - INFO - Epoch(train) [113][150/586] lr: 5.000000e-03 eta: 7:50:23 time: 0.509958 data_time: 0.056068 memory: 8713 loss_kpt: 208.803608 acc_pose: 0.827650 loss: 208.803608 2022/10/12 20:59:14 - mmengine - INFO - Epoch(train) [113][200/586] lr: 5.000000e-03 eta: 7:50:00 time: 0.518482 data_time: 0.055550 memory: 8713 loss_kpt: 206.949142 acc_pose: 0.827424 loss: 206.949142 2022/10/12 20:59:40 - mmengine - INFO - Epoch(train) [113][250/586] lr: 5.000000e-03 eta: 7:49:36 time: 0.516064 data_time: 0.054548 memory: 8713 loss_kpt: 208.840698 acc_pose: 0.850735 loss: 208.840698 2022/10/12 21:00:06 - mmengine - INFO - Epoch(train) [113][300/586] lr: 5.000000e-03 eta: 7:49:13 time: 0.531427 data_time: 0.063783 memory: 8713 loss_kpt: 207.393338 acc_pose: 0.785121 loss: 207.393338 2022/10/12 21:00:33 - mmengine - INFO - Epoch(train) [113][350/586] lr: 5.000000e-03 eta: 7:48:50 time: 0.530516 data_time: 0.059103 memory: 8713 loss_kpt: 206.509340 acc_pose: 0.743029 loss: 206.509340 2022/10/12 21:00:42 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:00:59 - mmengine - INFO - Epoch(train) [113][400/586] lr: 5.000000e-03 eta: 7:48:27 time: 0.528124 data_time: 0.061877 memory: 8713 loss_kpt: 207.924510 acc_pose: 0.802424 loss: 207.924510 2022/10/12 21:01:25 - mmengine - INFO - Epoch(train) [113][450/586] lr: 5.000000e-03 eta: 7:48:04 time: 0.521464 data_time: 0.060446 memory: 8713 loss_kpt: 209.769320 acc_pose: 0.825180 loss: 209.769320 2022/10/12 21:01:51 - mmengine - INFO - Epoch(train) [113][500/586] lr: 5.000000e-03 eta: 7:47:40 time: 0.517725 data_time: 0.058912 memory: 8713 loss_kpt: 209.374418 acc_pose: 0.847359 loss: 209.374418 2022/10/12 21:02:17 - mmengine - INFO - Epoch(train) [113][550/586] lr: 5.000000e-03 eta: 7:47:16 time: 0.515266 data_time: 0.054785 memory: 8713 loss_kpt: 207.897592 acc_pose: 0.771205 loss: 207.897592 2022/10/12 21:02:35 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:03:02 - mmengine - INFO - Epoch(train) [114][50/586] lr: 5.000000e-03 eta: 7:46:21 time: 0.534529 data_time: 0.065834 memory: 8713 loss_kpt: 209.810813 acc_pose: 0.859365 loss: 209.810813 2022/10/12 21:03:28 - mmengine - INFO - Epoch(train) [114][100/586] lr: 5.000000e-03 eta: 7:45:58 time: 0.532039 data_time: 0.058004 memory: 8713 loss_kpt: 208.768174 acc_pose: 0.766732 loss: 208.768174 2022/10/12 21:03:55 - mmengine - INFO - Epoch(train) [114][150/586] lr: 5.000000e-03 eta: 7:45:34 time: 0.525323 data_time: 0.054335 memory: 8713 loss_kpt: 210.591390 acc_pose: 0.848212 loss: 210.591390 2022/10/12 21:04:21 - mmengine - INFO - Epoch(train) [114][200/586] lr: 5.000000e-03 eta: 7:45:11 time: 0.527245 data_time: 0.055936 memory: 8713 loss_kpt: 207.273131 acc_pose: 0.757870 loss: 207.273131 2022/10/12 21:04:47 - mmengine - INFO - Epoch(train) [114][250/586] lr: 5.000000e-03 eta: 7:44:48 time: 0.517493 data_time: 0.057185 memory: 8713 loss_kpt: 208.000195 acc_pose: 0.829434 loss: 208.000195 2022/10/12 21:05:13 - mmengine - INFO - Epoch(train) [114][300/586] lr: 5.000000e-03 eta: 7:44:24 time: 0.519915 data_time: 0.059909 memory: 8713 loss_kpt: 208.038285 acc_pose: 0.824827 loss: 208.038285 2022/10/12 21:05:39 - mmengine - INFO - Epoch(train) [114][350/586] lr: 5.000000e-03 eta: 7:44:01 time: 0.524349 data_time: 0.054110 memory: 8713 loss_kpt: 205.859133 acc_pose: 0.797804 loss: 205.859133 2022/10/12 21:06:06 - mmengine - INFO - Epoch(train) [114][400/586] lr: 5.000000e-03 eta: 7:43:38 time: 0.534771 data_time: 0.064424 memory: 8713 loss_kpt: 204.081673 acc_pose: 0.851173 loss: 204.081673 2022/10/12 21:06:32 - mmengine - INFO - Epoch(train) [114][450/586] lr: 5.000000e-03 eta: 7:43:14 time: 0.520858 data_time: 0.057467 memory: 8713 loss_kpt: 207.374522 acc_pose: 0.802563 loss: 207.374522 2022/10/12 21:06:58 - mmengine - INFO - Epoch(train) [114][500/586] lr: 5.000000e-03 eta: 7:42:51 time: 0.529907 data_time: 0.056072 memory: 8713 loss_kpt: 208.005410 acc_pose: 0.806684 loss: 208.005410 2022/10/12 21:07:24 - mmengine - INFO - Epoch(train) [114][550/586] lr: 5.000000e-03 eta: 7:42:28 time: 0.519788 data_time: 0.053568 memory: 8713 loss_kpt: 206.883070 acc_pose: 0.749975 loss: 206.883070 2022/10/12 21:07:43 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:08:10 - mmengine - INFO - Epoch(train) [115][50/586] lr: 5.000000e-03 eta: 7:41:33 time: 0.539525 data_time: 0.066173 memory: 8713 loss_kpt: 208.410550 acc_pose: 0.776570 loss: 208.410550 2022/10/12 21:08:37 - mmengine - INFO - Epoch(train) [115][100/586] lr: 5.000000e-03 eta: 7:41:10 time: 0.540457 data_time: 0.058925 memory: 8713 loss_kpt: 204.889844 acc_pose: 0.783528 loss: 204.889844 2022/10/12 21:09:04 - mmengine - INFO - Epoch(train) [115][150/586] lr: 5.000000e-03 eta: 7:40:47 time: 0.532616 data_time: 0.055590 memory: 8713 loss_kpt: 208.134334 acc_pose: 0.859724 loss: 208.134334 2022/10/12 21:09:28 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:09:30 - mmengine - INFO - Epoch(train) [115][200/586] lr: 5.000000e-03 eta: 7:40:24 time: 0.535743 data_time: 0.058850 memory: 8713 loss_kpt: 207.132874 acc_pose: 0.800912 loss: 207.132874 2022/10/12 21:09:57 - mmengine - INFO - Epoch(train) [115][250/586] lr: 5.000000e-03 eta: 7:40:01 time: 0.536990 data_time: 0.053335 memory: 8713 loss_kpt: 209.263151 acc_pose: 0.859860 loss: 209.263151 2022/10/12 21:10:24 - mmengine - INFO - Epoch(train) [115][300/586] lr: 5.000000e-03 eta: 7:39:38 time: 0.535362 data_time: 0.053506 memory: 8713 loss_kpt: 209.794376 acc_pose: 0.800829 loss: 209.794376 2022/10/12 21:10:51 - mmengine - INFO - Epoch(train) [115][350/586] lr: 5.000000e-03 eta: 7:39:16 time: 0.539133 data_time: 0.058425 memory: 8713 loss_kpt: 209.736700 acc_pose: 0.835670 loss: 209.736700 2022/10/12 21:11:17 - mmengine - INFO - Epoch(train) [115][400/586] lr: 5.000000e-03 eta: 7:38:53 time: 0.527883 data_time: 0.059654 memory: 8713 loss_kpt: 206.656150 acc_pose: 0.857430 loss: 206.656150 2022/10/12 21:11:44 - mmengine - INFO - Epoch(train) [115][450/586] lr: 5.000000e-03 eta: 7:38:30 time: 0.534478 data_time: 0.059165 memory: 8713 loss_kpt: 207.293279 acc_pose: 0.867843 loss: 207.293279 2022/10/12 21:12:11 - mmengine - INFO - Epoch(train) [115][500/586] lr: 5.000000e-03 eta: 7:38:07 time: 0.534031 data_time: 0.055749 memory: 8713 loss_kpt: 211.585412 acc_pose: 0.802060 loss: 211.585412 2022/10/12 21:12:38 - mmengine - INFO - Epoch(train) [115][550/586] lr: 5.000000e-03 eta: 7:37:44 time: 0.534277 data_time: 0.054015 memory: 8713 loss_kpt: 210.924394 acc_pose: 0.852216 loss: 210.924394 2022/10/12 21:12:56 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:13:23 - mmengine - INFO - Epoch(train) [116][50/586] lr: 5.000000e-03 eta: 7:36:49 time: 0.544568 data_time: 0.066438 memory: 8713 loss_kpt: 205.722665 acc_pose: 0.835353 loss: 205.722665 2022/10/12 21:13:49 - mmengine - INFO - Epoch(train) [116][100/586] lr: 5.000000e-03 eta: 7:36:25 time: 0.517603 data_time: 0.056523 memory: 8713 loss_kpt: 207.815268 acc_pose: 0.843079 loss: 207.815268 2022/10/12 21:14:15 - mmengine - INFO - Epoch(train) [116][150/586] lr: 5.000000e-03 eta: 7:36:01 time: 0.513951 data_time: 0.053327 memory: 8713 loss_kpt: 207.543406 acc_pose: 0.795046 loss: 207.543406 2022/10/12 21:14:41 - mmengine - INFO - Epoch(train) [116][200/586] lr: 5.000000e-03 eta: 7:35:38 time: 0.512808 data_time: 0.058655 memory: 8713 loss_kpt: 207.120681 acc_pose: 0.744993 loss: 207.120681 2022/10/12 21:15:06 - mmengine - INFO - Epoch(train) [116][250/586] lr: 5.000000e-03 eta: 7:35:14 time: 0.513236 data_time: 0.057736 memory: 8713 loss_kpt: 204.378092 acc_pose: 0.857980 loss: 204.378092 2022/10/12 21:15:32 - mmengine - INFO - Epoch(train) [116][300/586] lr: 5.000000e-03 eta: 7:34:50 time: 0.518166 data_time: 0.055712 memory: 8713 loss_kpt: 207.742206 acc_pose: 0.855368 loss: 207.742206 2022/10/12 21:15:58 - mmengine - INFO - Epoch(train) [116][350/586] lr: 5.000000e-03 eta: 7:34:26 time: 0.506160 data_time: 0.054908 memory: 8713 loss_kpt: 206.110597 acc_pose: 0.780630 loss: 206.110597 2022/10/12 21:16:24 - mmengine - INFO - Epoch(train) [116][400/586] lr: 5.000000e-03 eta: 7:34:02 time: 0.518100 data_time: 0.053426 memory: 8713 loss_kpt: 208.400787 acc_pose: 0.826000 loss: 208.400787 2022/10/12 21:16:49 - mmengine - INFO - Epoch(train) [116][450/586] lr: 5.000000e-03 eta: 7:33:39 time: 0.513244 data_time: 0.053600 memory: 8713 loss_kpt: 207.629502 acc_pose: 0.867060 loss: 207.629502 2022/10/12 21:17:14 - mmengine - INFO - Epoch(train) [116][500/586] lr: 5.000000e-03 eta: 7:33:14 time: 0.502360 data_time: 0.056404 memory: 8713 loss_kpt: 211.359675 acc_pose: 0.766562 loss: 211.359675 2022/10/12 21:17:40 - mmengine - INFO - Epoch(train) [116][550/586] lr: 5.000000e-03 eta: 7:32:51 time: 0.521701 data_time: 0.054196 memory: 8713 loss_kpt: 207.230121 acc_pose: 0.804979 loss: 207.230121 2022/10/12 21:17:59 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:18:12 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:18:25 - mmengine - INFO - Epoch(train) [117][50/586] lr: 5.000000e-03 eta: 7:31:56 time: 0.537957 data_time: 0.070233 memory: 8713 loss_kpt: 209.304843 acc_pose: 0.830510 loss: 209.304843 2022/10/12 21:18:52 - mmengine - INFO - Epoch(train) [117][100/586] lr: 5.000000e-03 eta: 7:31:33 time: 0.532413 data_time: 0.056533 memory: 8713 loss_kpt: 208.598167 acc_pose: 0.863062 loss: 208.598167 2022/10/12 21:19:18 - mmengine - INFO - Epoch(train) [117][150/586] lr: 5.000000e-03 eta: 7:31:10 time: 0.527142 data_time: 0.057426 memory: 8713 loss_kpt: 206.235204 acc_pose: 0.856073 loss: 206.235204 2022/10/12 21:19:44 - mmengine - INFO - Epoch(train) [117][200/586] lr: 5.000000e-03 eta: 7:30:46 time: 0.516726 data_time: 0.053425 memory: 8713 loss_kpt: 209.412166 acc_pose: 0.833775 loss: 209.412166 2022/10/12 21:20:11 - mmengine - INFO - Epoch(train) [117][250/586] lr: 5.000000e-03 eta: 7:30:23 time: 0.529251 data_time: 0.056979 memory: 8713 loss_kpt: 209.143104 acc_pose: 0.860069 loss: 209.143104 2022/10/12 21:20:37 - mmengine - INFO - Epoch(train) [117][300/586] lr: 5.000000e-03 eta: 7:29:59 time: 0.522751 data_time: 0.053027 memory: 8713 loss_kpt: 204.962726 acc_pose: 0.904900 loss: 204.962726 2022/10/12 21:21:03 - mmengine - INFO - Epoch(train) [117][350/586] lr: 5.000000e-03 eta: 7:29:36 time: 0.529906 data_time: 0.052809 memory: 8713 loss_kpt: 205.089525 acc_pose: 0.838479 loss: 205.089525 2022/10/12 21:21:30 - mmengine - INFO - Epoch(train) [117][400/586] lr: 5.000000e-03 eta: 7:29:13 time: 0.523702 data_time: 0.057105 memory: 8713 loss_kpt: 204.024191 acc_pose: 0.788639 loss: 204.024191 2022/10/12 21:21:56 - mmengine - INFO - Epoch(train) [117][450/586] lr: 5.000000e-03 eta: 7:28:49 time: 0.521624 data_time: 0.051986 memory: 8713 loss_kpt: 208.124986 acc_pose: 0.866119 loss: 208.124986 2022/10/12 21:22:22 - mmengine - INFO - Epoch(train) [117][500/586] lr: 5.000000e-03 eta: 7:28:26 time: 0.516616 data_time: 0.051733 memory: 8713 loss_kpt: 205.089179 acc_pose: 0.784909 loss: 205.089179 2022/10/12 21:22:47 - mmengine - INFO - Epoch(train) [117][550/586] lr: 5.000000e-03 eta: 7:28:02 time: 0.516491 data_time: 0.053899 memory: 8713 loss_kpt: 209.219922 acc_pose: 0.839969 loss: 209.219922 2022/10/12 21:23:06 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:23:32 - mmengine - INFO - Epoch(train) [118][50/586] lr: 5.000000e-03 eta: 7:27:07 time: 0.526044 data_time: 0.068684 memory: 8713 loss_kpt: 206.835132 acc_pose: 0.891217 loss: 206.835132 2022/10/12 21:23:58 - mmengine - INFO - Epoch(train) [118][100/586] lr: 5.000000e-03 eta: 7:26:43 time: 0.517318 data_time: 0.055955 memory: 8713 loss_kpt: 204.234935 acc_pose: 0.850892 loss: 204.234935 2022/10/12 21:24:24 - mmengine - INFO - Epoch(train) [118][150/586] lr: 5.000000e-03 eta: 7:26:19 time: 0.512751 data_time: 0.061631 memory: 8713 loss_kpt: 209.962701 acc_pose: 0.834627 loss: 209.962701 2022/10/12 21:24:49 - mmengine - INFO - Epoch(train) [118][200/586] lr: 5.000000e-03 eta: 7:25:55 time: 0.512726 data_time: 0.055754 memory: 8713 loss_kpt: 205.965547 acc_pose: 0.881477 loss: 205.965547 2022/10/12 21:25:15 - mmengine - INFO - Epoch(train) [118][250/586] lr: 5.000000e-03 eta: 7:25:32 time: 0.516808 data_time: 0.055999 memory: 8713 loss_kpt: 208.534702 acc_pose: 0.860927 loss: 208.534702 2022/10/12 21:25:41 - mmengine - INFO - Epoch(train) [118][300/586] lr: 5.000000e-03 eta: 7:25:08 time: 0.517258 data_time: 0.054058 memory: 8713 loss_kpt: 205.685489 acc_pose: 0.844386 loss: 205.685489 2022/10/12 21:26:07 - mmengine - INFO - Epoch(train) [118][350/586] lr: 5.000000e-03 eta: 7:24:44 time: 0.511593 data_time: 0.058072 memory: 8713 loss_kpt: 205.262522 acc_pose: 0.864284 loss: 205.262522 2022/10/12 21:26:32 - mmengine - INFO - Epoch(train) [118][400/586] lr: 5.000000e-03 eta: 7:24:20 time: 0.506118 data_time: 0.055074 memory: 8713 loss_kpt: 207.114136 acc_pose: 0.793286 loss: 207.114136 2022/10/12 21:26:52 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:26:58 - mmengine - INFO - Epoch(train) [118][450/586] lr: 5.000000e-03 eta: 7:23:56 time: 0.515345 data_time: 0.054504 memory: 8713 loss_kpt: 209.098705 acc_pose: 0.872284 loss: 209.098705 2022/10/12 21:27:23 - mmengine - INFO - Epoch(train) [118][500/586] lr: 5.000000e-03 eta: 7:23:32 time: 0.509027 data_time: 0.055915 memory: 8713 loss_kpt: 209.714296 acc_pose: 0.837676 loss: 209.714296 2022/10/12 21:27:49 - mmengine - INFO - Epoch(train) [118][550/586] lr: 5.000000e-03 eta: 7:23:08 time: 0.508396 data_time: 0.059118 memory: 8713 loss_kpt: 209.013275 acc_pose: 0.833234 loss: 209.013275 2022/10/12 21:28:07 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:28:33 - mmengine - INFO - Epoch(train) [119][50/586] lr: 5.000000e-03 eta: 7:22:13 time: 0.528760 data_time: 0.071943 memory: 8713 loss_kpt: 205.789556 acc_pose: 0.833383 loss: 205.789556 2022/10/12 21:28:59 - mmengine - INFO - Epoch(train) [119][100/586] lr: 5.000000e-03 eta: 7:21:50 time: 0.511782 data_time: 0.060824 memory: 8713 loss_kpt: 205.372389 acc_pose: 0.823469 loss: 205.372389 2022/10/12 21:29:25 - mmengine - INFO - Epoch(train) [119][150/586] lr: 5.000000e-03 eta: 7:21:26 time: 0.515545 data_time: 0.058249 memory: 8713 loss_kpt: 208.618491 acc_pose: 0.755352 loss: 208.618491 2022/10/12 21:29:51 - mmengine - INFO - Epoch(train) [119][200/586] lr: 5.000000e-03 eta: 7:21:02 time: 0.519881 data_time: 0.055593 memory: 8713 loss_kpt: 209.394313 acc_pose: 0.747780 loss: 209.394313 2022/10/12 21:30:16 - mmengine - INFO - Epoch(train) [119][250/586] lr: 5.000000e-03 eta: 7:20:38 time: 0.512771 data_time: 0.058429 memory: 8713 loss_kpt: 210.183506 acc_pose: 0.823654 loss: 210.183506 2022/10/12 21:30:41 - mmengine - INFO - Epoch(train) [119][300/586] lr: 5.000000e-03 eta: 7:20:14 time: 0.501270 data_time: 0.051822 memory: 8713 loss_kpt: 207.666183 acc_pose: 0.869733 loss: 207.666183 2022/10/12 21:31:07 - mmengine - INFO - Epoch(train) [119][350/586] lr: 5.000000e-03 eta: 7:19:51 time: 0.524831 data_time: 0.061454 memory: 8713 loss_kpt: 206.129178 acc_pose: 0.868420 loss: 206.129178 2022/10/12 21:31:33 - mmengine - INFO - Epoch(train) [119][400/586] lr: 5.000000e-03 eta: 7:19:27 time: 0.510860 data_time: 0.056500 memory: 8713 loss_kpt: 204.874634 acc_pose: 0.903827 loss: 204.874634 2022/10/12 21:31:59 - mmengine - INFO - Epoch(train) [119][450/586] lr: 5.000000e-03 eta: 7:19:03 time: 0.518381 data_time: 0.054446 memory: 8713 loss_kpt: 207.673845 acc_pose: 0.818647 loss: 207.673845 2022/10/12 21:32:25 - mmengine - INFO - Epoch(train) [119][500/586] lr: 5.000000e-03 eta: 7:18:39 time: 0.510491 data_time: 0.052764 memory: 8713 loss_kpt: 208.361752 acc_pose: 0.825466 loss: 208.361752 2022/10/12 21:32:50 - mmengine - INFO - Epoch(train) [119][550/586] lr: 5.000000e-03 eta: 7:18:15 time: 0.510171 data_time: 0.055981 memory: 8713 loss_kpt: 205.550443 acc_pose: 0.785952 loss: 205.550443 2022/10/12 21:33:08 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:33:35 - mmengine - INFO - Epoch(train) [120][50/586] lr: 5.000000e-03 eta: 7:17:21 time: 0.536280 data_time: 0.070254 memory: 8713 loss_kpt: 208.004986 acc_pose: 0.878000 loss: 208.004986 2022/10/12 21:34:01 - mmengine - INFO - Epoch(train) [120][100/586] lr: 5.000000e-03 eta: 7:16:57 time: 0.515322 data_time: 0.054810 memory: 8713 loss_kpt: 207.143824 acc_pose: 0.804861 loss: 207.143824 2022/10/12 21:34:27 - mmengine - INFO - Epoch(train) [120][150/586] lr: 5.000000e-03 eta: 7:16:34 time: 0.525920 data_time: 0.058664 memory: 8713 loss_kpt: 204.516003 acc_pose: 0.873081 loss: 204.516003 2022/10/12 21:34:53 - mmengine - INFO - Epoch(train) [120][200/586] lr: 5.000000e-03 eta: 7:16:10 time: 0.511524 data_time: 0.056960 memory: 8713 loss_kpt: 208.952839 acc_pose: 0.825160 loss: 208.952839 2022/10/12 21:35:19 - mmengine - INFO - Epoch(train) [120][250/586] lr: 5.000000e-03 eta: 7:15:47 time: 0.527220 data_time: 0.063555 memory: 8713 loss_kpt: 206.071543 acc_pose: 0.871865 loss: 206.071543 2022/10/12 21:35:27 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:35:45 - mmengine - INFO - Epoch(train) [120][300/586] lr: 5.000000e-03 eta: 7:15:23 time: 0.528656 data_time: 0.054436 memory: 8713 loss_kpt: 207.587836 acc_pose: 0.873927 loss: 207.587836 2022/10/12 21:36:12 - mmengine - INFO - Epoch(train) [120][350/586] lr: 5.000000e-03 eta: 7:15:00 time: 0.525642 data_time: 0.063196 memory: 8713 loss_kpt: 208.764434 acc_pose: 0.807623 loss: 208.764434 2022/10/12 21:36:38 - mmengine - INFO - Epoch(train) [120][400/586] lr: 5.000000e-03 eta: 7:14:36 time: 0.522723 data_time: 0.060011 memory: 8713 loss_kpt: 207.971103 acc_pose: 0.815747 loss: 207.971103 2022/10/12 21:37:05 - mmengine - INFO - Epoch(train) [120][450/586] lr: 5.000000e-03 eta: 7:14:13 time: 0.537722 data_time: 0.061685 memory: 8713 loss_kpt: 209.394574 acc_pose: 0.849371 loss: 209.394574 2022/10/12 21:37:31 - mmengine - INFO - Epoch(train) [120][500/586] lr: 5.000000e-03 eta: 7:13:50 time: 0.525234 data_time: 0.058625 memory: 8713 loss_kpt: 209.264064 acc_pose: 0.832151 loss: 209.264064 2022/10/12 21:37:58 - mmengine - INFO - Epoch(train) [120][550/586] lr: 5.000000e-03 eta: 7:13:27 time: 0.533107 data_time: 0.059406 memory: 8713 loss_kpt: 205.300189 acc_pose: 0.831530 loss: 205.300189 2022/10/12 21:38:16 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:38:16 - mmengine - INFO - Saving checkpoint at 120 epochs 2022/10/12 21:38:29 - mmengine - INFO - Epoch(val) [120][50/407] eta: 0:01:10 time: 0.197778 data_time: 0.012297 memory: 8713 2022/10/12 21:38:39 - mmengine - INFO - Epoch(val) [120][100/407] eta: 0:01:00 time: 0.198190 data_time: 0.008058 memory: 1759 2022/10/12 21:38:49 - mmengine - INFO - Epoch(val) [120][150/407] eta: 0:00:49 time: 0.193943 data_time: 0.008062 memory: 1759 2022/10/12 21:38:59 - mmengine - INFO - Epoch(val) [120][200/407] eta: 0:00:40 time: 0.197238 data_time: 0.008085 memory: 1759 2022/10/12 21:39:09 - mmengine - INFO - Epoch(val) [120][250/407] eta: 0:00:30 time: 0.197369 data_time: 0.007822 memory: 1759 2022/10/12 21:39:18 - mmengine - INFO - Epoch(val) [120][300/407] eta: 0:00:20 time: 0.189338 data_time: 0.007514 memory: 1759 2022/10/12 21:39:28 - mmengine - INFO - Epoch(val) [120][350/407] eta: 0:00:10 time: 0.190361 data_time: 0.007787 memory: 1759 2022/10/12 21:39:37 - mmengine - INFO - Epoch(val) [120][400/407] eta: 0:00:01 time: 0.189943 data_time: 0.007568 memory: 1759 2022/10/12 21:39:51 - mmengine - INFO - Evaluating CocoMetric... 2022/10/12 21:40:07 - mmengine - INFO - Epoch(val) [120][407/407] coco/AP: 0.716337 coco/AP .5: 0.886413 coco/AP .75: 0.789834 coco/AP (M): 0.684344 coco/AP (L): 0.777062 coco/AR: 0.783155 coco/AR .5: 0.929314 coco/AR .75: 0.843829 coco/AR (M): 0.739552 coco/AR (L): 0.843515 2022/10/12 21:40:07 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/liqikai/openmmlab/pt112cu113py38/mmpose/work_dirs/20221012/rsn2x/best_coco/AP_epoch_100.pth is removed 2022/10/12 21:40:09 - mmengine - INFO - The best checkpoint with 0.7163 coco/AP at 120 epoch is saved to best_coco/AP_epoch_120.pth. 2022/10/12 21:40:34 - mmengine - INFO - Epoch(train) [121][50/586] lr: 5.000000e-03 eta: 7:12:32 time: 0.511283 data_time: 0.064440 memory: 8713 loss_kpt: 209.318451 acc_pose: 0.870080 loss: 209.318451 2022/10/12 21:41:00 - mmengine - INFO - Epoch(train) [121][100/586] lr: 5.000000e-03 eta: 7:12:08 time: 0.522053 data_time: 0.054657 memory: 8713 loss_kpt: 203.758323 acc_pose: 0.816414 loss: 203.758323 2022/10/12 21:41:27 - mmengine - INFO - Epoch(train) [121][150/586] lr: 5.000000e-03 eta: 7:11:45 time: 0.524249 data_time: 0.055957 memory: 8713 loss_kpt: 206.672916 acc_pose: 0.822631 loss: 206.672916 2022/10/12 21:41:52 - mmengine - INFO - Epoch(train) [121][200/586] lr: 5.000000e-03 eta: 7:11:21 time: 0.501519 data_time: 0.052118 memory: 8713 loss_kpt: 204.770923 acc_pose: 0.796765 loss: 204.770923 2022/10/12 21:42:18 - mmengine - INFO - Epoch(train) [121][250/586] lr: 5.000000e-03 eta: 7:10:57 time: 0.525834 data_time: 0.056069 memory: 8713 loss_kpt: 205.434595 acc_pose: 0.804468 loss: 205.434595 2022/10/12 21:42:45 - mmengine - INFO - Epoch(train) [121][300/586] lr: 5.000000e-03 eta: 7:10:34 time: 0.529314 data_time: 0.056680 memory: 8713 loss_kpt: 207.390615 acc_pose: 0.798716 loss: 207.390615 2022/10/12 21:43:11 - mmengine - INFO - Epoch(train) [121][350/586] lr: 5.000000e-03 eta: 7:10:11 time: 0.524363 data_time: 0.051636 memory: 8713 loss_kpt: 209.709724 acc_pose: 0.814620 loss: 209.709724 2022/10/12 21:43:36 - mmengine - INFO - Epoch(train) [121][400/586] lr: 5.000000e-03 eta: 7:09:47 time: 0.514695 data_time: 0.059376 memory: 8713 loss_kpt: 209.813875 acc_pose: 0.791212 loss: 209.813875 2022/10/12 21:44:02 - mmengine - INFO - Epoch(train) [121][450/586] lr: 5.000000e-03 eta: 7:09:23 time: 0.512735 data_time: 0.051238 memory: 8713 loss_kpt: 207.311930 acc_pose: 0.854253 loss: 207.311930 2022/10/12 21:44:28 - mmengine - INFO - Epoch(train) [121][500/586] lr: 5.000000e-03 eta: 7:08:59 time: 0.512036 data_time: 0.058745 memory: 8713 loss_kpt: 206.844497 acc_pose: 0.813972 loss: 206.844497 2022/10/12 21:44:53 - mmengine - INFO - Epoch(train) [121][550/586] lr: 5.000000e-03 eta: 7:08:35 time: 0.514014 data_time: 0.056048 memory: 8713 loss_kpt: 206.663108 acc_pose: 0.784922 loss: 206.663108 2022/10/12 21:45:11 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:45:38 - mmengine - INFO - Epoch(train) [122][50/586] lr: 5.000000e-03 eta: 7:07:41 time: 0.535526 data_time: 0.073651 memory: 8713 loss_kpt: 204.402928 acc_pose: 0.880159 loss: 204.402928 2022/10/12 21:46:01 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:46:04 - mmengine - INFO - Epoch(train) [122][100/586] lr: 5.000000e-03 eta: 7:07:17 time: 0.513894 data_time: 0.053488 memory: 8713 loss_kpt: 207.706716 acc_pose: 0.788599 loss: 207.706716 2022/10/12 21:46:30 - mmengine - INFO - Epoch(train) [122][150/586] lr: 5.000000e-03 eta: 7:06:54 time: 0.522759 data_time: 0.062014 memory: 8713 loss_kpt: 207.272618 acc_pose: 0.773344 loss: 207.272618 2022/10/12 21:46:56 - mmengine - INFO - Epoch(train) [122][200/586] lr: 5.000000e-03 eta: 7:06:30 time: 0.511037 data_time: 0.054266 memory: 8713 loss_kpt: 204.258761 acc_pose: 0.834148 loss: 204.258761 2022/10/12 21:47:22 - mmengine - INFO - Epoch(train) [122][250/586] lr: 5.000000e-03 eta: 7:06:06 time: 0.521743 data_time: 0.055180 memory: 8713 loss_kpt: 206.771269 acc_pose: 0.859940 loss: 206.771269 2022/10/12 21:47:47 - mmengine - INFO - Epoch(train) [122][300/586] lr: 5.000000e-03 eta: 7:05:42 time: 0.508535 data_time: 0.056070 memory: 8713 loss_kpt: 206.326747 acc_pose: 0.825923 loss: 206.326747 2022/10/12 21:48:14 - mmengine - INFO - Epoch(train) [122][350/586] lr: 5.000000e-03 eta: 7:05:19 time: 0.527078 data_time: 0.060748 memory: 8713 loss_kpt: 208.996075 acc_pose: 0.780090 loss: 208.996075 2022/10/12 21:48:39 - mmengine - INFO - Epoch(train) [122][400/586] lr: 5.000000e-03 eta: 7:04:55 time: 0.518211 data_time: 0.055926 memory: 8713 loss_kpt: 208.674763 acc_pose: 0.827092 loss: 208.674763 2022/10/12 21:49:06 - mmengine - INFO - Epoch(train) [122][450/586] lr: 5.000000e-03 eta: 7:04:32 time: 0.523806 data_time: 0.060216 memory: 8713 loss_kpt: 205.910498 acc_pose: 0.791291 loss: 205.910498 2022/10/12 21:49:32 - mmengine - INFO - Epoch(train) [122][500/586] lr: 5.000000e-03 eta: 7:04:08 time: 0.521469 data_time: 0.056337 memory: 8713 loss_kpt: 206.486555 acc_pose: 0.868752 loss: 206.486555 2022/10/12 21:49:58 - mmengine - INFO - Epoch(train) [122][550/586] lr: 5.000000e-03 eta: 7:03:44 time: 0.515686 data_time: 0.058865 memory: 8713 loss_kpt: 206.444126 acc_pose: 0.851915 loss: 206.444126 2022/10/12 21:50:16 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:50:43 - mmengine - INFO - Epoch(train) [123][50/586] lr: 5.000000e-03 eta: 7:02:51 time: 0.550457 data_time: 0.075626 memory: 8713 loss_kpt: 207.734328 acc_pose: 0.866065 loss: 207.734328 2022/10/12 21:51:10 - mmengine - INFO - Epoch(train) [123][100/586] lr: 5.000000e-03 eta: 7:02:28 time: 0.528484 data_time: 0.053494 memory: 8713 loss_kpt: 205.457484 acc_pose: 0.880660 loss: 205.457484 2022/10/12 21:51:36 - mmengine - INFO - Epoch(train) [123][150/586] lr: 5.000000e-03 eta: 7:02:05 time: 0.527333 data_time: 0.059975 memory: 8713 loss_kpt: 205.535063 acc_pose: 0.851575 loss: 205.535063 2022/10/12 21:52:02 - mmengine - INFO - Epoch(train) [123][200/586] lr: 5.000000e-03 eta: 7:01:41 time: 0.521842 data_time: 0.055425 memory: 8713 loss_kpt: 209.109564 acc_pose: 0.706862 loss: 209.109564 2022/10/12 21:52:29 - mmengine - INFO - Epoch(train) [123][250/586] lr: 5.000000e-03 eta: 7:01:18 time: 0.535192 data_time: 0.055603 memory: 8713 loss_kpt: 203.834557 acc_pose: 0.845935 loss: 203.834557 2022/10/12 21:52:56 - mmengine - INFO - Epoch(train) [123][300/586] lr: 5.000000e-03 eta: 7:00:54 time: 0.526789 data_time: 0.056135 memory: 8713 loss_kpt: 206.919940 acc_pose: 0.892104 loss: 206.919940 2022/10/12 21:53:22 - mmengine - INFO - Epoch(train) [123][350/586] lr: 5.000000e-03 eta: 7:00:31 time: 0.531769 data_time: 0.059194 memory: 8713 loss_kpt: 208.055404 acc_pose: 0.782320 loss: 208.055404 2022/10/12 21:53:48 - mmengine - INFO - Epoch(train) [123][400/586] lr: 5.000000e-03 eta: 7:00:08 time: 0.522229 data_time: 0.058429 memory: 8713 loss_kpt: 204.147600 acc_pose: 0.862604 loss: 204.147600 2022/10/12 21:54:14 - mmengine - INFO - Epoch(train) [123][450/586] lr: 5.000000e-03 eta: 6:59:44 time: 0.515614 data_time: 0.055367 memory: 8713 loss_kpt: 208.083678 acc_pose: 0.858943 loss: 208.083678 2022/10/12 21:54:40 - mmengine - INFO - Epoch(train) [123][500/586] lr: 5.000000e-03 eta: 6:59:20 time: 0.515803 data_time: 0.062499 memory: 8713 loss_kpt: 205.962829 acc_pose: 0.830359 loss: 205.962829 2022/10/12 21:54:44 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:55:06 - mmengine - INFO - Epoch(train) [123][550/586] lr: 5.000000e-03 eta: 6:58:56 time: 0.521487 data_time: 0.054357 memory: 8713 loss_kpt: 206.561846 acc_pose: 0.773156 loss: 206.561846 2022/10/12 21:55:24 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:55:51 - mmengine - INFO - Epoch(train) [124][50/586] lr: 5.000000e-03 eta: 6:58:03 time: 0.537349 data_time: 0.066753 memory: 8713 loss_kpt: 208.026271 acc_pose: 0.836235 loss: 208.026271 2022/10/12 21:56:18 - mmengine - INFO - Epoch(train) [124][100/586] lr: 5.000000e-03 eta: 6:57:40 time: 0.524764 data_time: 0.055734 memory: 8713 loss_kpt: 206.258474 acc_pose: 0.882868 loss: 206.258474 2022/10/12 21:56:44 - mmengine - INFO - Epoch(train) [124][150/586] lr: 5.000000e-03 eta: 6:57:16 time: 0.529241 data_time: 0.055665 memory: 8713 loss_kpt: 210.168531 acc_pose: 0.839647 loss: 210.168531 2022/10/12 21:57:10 - mmengine - INFO - Epoch(train) [124][200/586] lr: 5.000000e-03 eta: 6:56:52 time: 0.514630 data_time: 0.057270 memory: 8713 loss_kpt: 201.066921 acc_pose: 0.870499 loss: 201.066921 2022/10/12 21:57:36 - mmengine - INFO - Epoch(train) [124][250/586] lr: 5.000000e-03 eta: 6:56:29 time: 0.524090 data_time: 0.055147 memory: 8713 loss_kpt: 207.622011 acc_pose: 0.782542 loss: 207.622011 2022/10/12 21:58:02 - mmengine - INFO - Epoch(train) [124][300/586] lr: 5.000000e-03 eta: 6:56:05 time: 0.519834 data_time: 0.054576 memory: 8713 loss_kpt: 211.497449 acc_pose: 0.800814 loss: 211.497449 2022/10/12 21:58:29 - mmengine - INFO - Epoch(train) [124][350/586] lr: 5.000000e-03 eta: 6:55:42 time: 0.531554 data_time: 0.057299 memory: 8713 loss_kpt: 205.420723 acc_pose: 0.881043 loss: 205.420723 2022/10/12 21:58:55 - mmengine - INFO - Epoch(train) [124][400/586] lr: 5.000000e-03 eta: 6:55:18 time: 0.526101 data_time: 0.053084 memory: 8713 loss_kpt: 205.523064 acc_pose: 0.863544 loss: 205.523064 2022/10/12 21:59:21 - mmengine - INFO - Epoch(train) [124][450/586] lr: 5.000000e-03 eta: 6:54:55 time: 0.527568 data_time: 0.058369 memory: 8713 loss_kpt: 208.465304 acc_pose: 0.809438 loss: 208.465304 2022/10/12 21:59:48 - mmengine - INFO - Epoch(train) [124][500/586] lr: 5.000000e-03 eta: 6:54:32 time: 0.533800 data_time: 0.053172 memory: 8713 loss_kpt: 205.807339 acc_pose: 0.801259 loss: 205.807339 2022/10/12 22:00:14 - mmengine - INFO - Epoch(train) [124][550/586] lr: 5.000000e-03 eta: 6:54:08 time: 0.523780 data_time: 0.056634 memory: 8713 loss_kpt: 205.067126 acc_pose: 0.838987 loss: 205.067126 2022/10/12 22:00:33 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:01:00 - mmengine - INFO - Epoch(train) [125][50/586] lr: 5.000000e-03 eta: 6:53:16 time: 0.550662 data_time: 0.074128 memory: 8713 loss_kpt: 206.742331 acc_pose: 0.829498 loss: 206.742331 2022/10/12 22:01:26 - mmengine - INFO - Epoch(train) [125][100/586] lr: 5.000000e-03 eta: 6:52:52 time: 0.514958 data_time: 0.056239 memory: 8713 loss_kpt: 207.630166 acc_pose: 0.830935 loss: 207.630166 2022/10/12 22:01:52 - mmengine - INFO - Epoch(train) [125][150/586] lr: 5.000000e-03 eta: 6:52:28 time: 0.521346 data_time: 0.055769 memory: 8713 loss_kpt: 206.620458 acc_pose: 0.772897 loss: 206.620458 2022/10/12 22:02:19 - mmengine - INFO - Epoch(train) [125][200/586] lr: 5.000000e-03 eta: 6:52:05 time: 0.535371 data_time: 0.055429 memory: 8713 loss_kpt: 209.744279 acc_pose: 0.865671 loss: 209.744279 2022/10/12 22:02:45 - mmengine - INFO - Epoch(train) [125][250/586] lr: 5.000000e-03 eta: 6:51:41 time: 0.521905 data_time: 0.059012 memory: 8713 loss_kpt: 203.138266 acc_pose: 0.869981 loss: 203.138266 2022/10/12 22:03:11 - mmengine - INFO - Epoch(train) [125][300/586] lr: 5.000000e-03 eta: 6:51:18 time: 0.515222 data_time: 0.051803 memory: 8713 loss_kpt: 206.757187 acc_pose: 0.829871 loss: 206.757187 2022/10/12 22:03:30 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:03:37 - mmengine - INFO - Epoch(train) [125][350/586] lr: 5.000000e-03 eta: 6:50:54 time: 0.533268 data_time: 0.057658 memory: 8713 loss_kpt: 204.281822 acc_pose: 0.755051 loss: 204.281822 2022/10/12 22:04:04 - mmengine - INFO - Epoch(train) [125][400/586] lr: 5.000000e-03 eta: 6:50:31 time: 0.531633 data_time: 0.054736 memory: 8713 loss_kpt: 204.317739 acc_pose: 0.895555 loss: 204.317739 2022/10/12 22:04:31 - mmengine - INFO - Epoch(train) [125][450/586] lr: 5.000000e-03 eta: 6:50:08 time: 0.536932 data_time: 0.059385 memory: 8713 loss_kpt: 208.221819 acc_pose: 0.741767 loss: 208.221819 2022/10/12 22:04:58 - mmengine - INFO - Epoch(train) [125][500/586] lr: 5.000000e-03 eta: 6:49:45 time: 0.537217 data_time: 0.058241 memory: 8713 loss_kpt: 205.368941 acc_pose: 0.857884 loss: 205.368941 2022/10/12 22:05:25 - mmengine - INFO - Epoch(train) [125][550/586] lr: 5.000000e-03 eta: 6:49:22 time: 0.539649 data_time: 0.056163 memory: 8713 loss_kpt: 203.833248 acc_pose: 0.741405 loss: 203.833248 2022/10/12 22:05:43 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:06:10 - mmengine - INFO - Epoch(train) [126][50/586] lr: 5.000000e-03 eta: 6:48:29 time: 0.541184 data_time: 0.077358 memory: 8713 loss_kpt: 199.922094 acc_pose: 0.799358 loss: 199.922094 2022/10/12 22:06:37 - mmengine - INFO - Epoch(train) [126][100/586] lr: 5.000000e-03 eta: 6:48:06 time: 0.528769 data_time: 0.058491 memory: 8713 loss_kpt: 209.058553 acc_pose: 0.765516 loss: 209.058553 2022/10/12 22:07:04 - mmengine - INFO - Epoch(train) [126][150/586] lr: 5.000000e-03 eta: 6:47:42 time: 0.538562 data_time: 0.061373 memory: 8713 loss_kpt: 202.067362 acc_pose: 0.828686 loss: 202.067362 2022/10/12 22:07:30 - mmengine - INFO - Epoch(train) [126][200/586] lr: 5.000000e-03 eta: 6:47:19 time: 0.529889 data_time: 0.056898 memory: 8713 loss_kpt: 208.382679 acc_pose: 0.836886 loss: 208.382679 2022/10/12 22:07:57 - mmengine - INFO - Epoch(train) [126][250/586] lr: 5.000000e-03 eta: 6:46:56 time: 0.529354 data_time: 0.062639 memory: 8713 loss_kpt: 203.184033 acc_pose: 0.903687 loss: 203.184033 2022/10/12 22:08:23 - mmengine - INFO - Epoch(train) [126][300/586] lr: 5.000000e-03 eta: 6:46:32 time: 0.531433 data_time: 0.062034 memory: 8713 loss_kpt: 210.730288 acc_pose: 0.846390 loss: 210.730288 2022/10/12 22:08:49 - mmengine - INFO - Epoch(train) [126][350/586] lr: 5.000000e-03 eta: 6:46:09 time: 0.525070 data_time: 0.060665 memory: 8713 loss_kpt: 201.081884 acc_pose: 0.778229 loss: 201.081884 2022/10/12 22:09:15 - mmengine - INFO - Epoch(train) [126][400/586] lr: 5.000000e-03 eta: 6:45:45 time: 0.513451 data_time: 0.053487 memory: 8713 loss_kpt: 201.880553 acc_pose: 0.888552 loss: 201.880553 2022/10/12 22:09:41 - mmengine - INFO - Epoch(train) [126][450/586] lr: 5.000000e-03 eta: 6:45:21 time: 0.515810 data_time: 0.056957 memory: 8713 loss_kpt: 202.245253 acc_pose: 0.785654 loss: 202.245253 2022/10/12 22:10:07 - mmengine - INFO - Epoch(train) [126][500/586] lr: 5.000000e-03 eta: 6:44:58 time: 0.530062 data_time: 0.060878 memory: 8713 loss_kpt: 206.981831 acc_pose: 0.768983 loss: 206.981831 2022/10/12 22:10:34 - mmengine - INFO - Epoch(train) [126][550/586] lr: 5.000000e-03 eta: 6:44:34 time: 0.533653 data_time: 0.061359 memory: 8713 loss_kpt: 206.704968 acc_pose: 0.832353 loss: 206.704968 2022/10/12 22:10:54 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:11:20 - mmengine - INFO - Epoch(train) [127][50/586] lr: 5.000000e-03 eta: 6:43:41 time: 0.526258 data_time: 0.066494 memory: 8713 loss_kpt: 203.858617 acc_pose: 0.761074 loss: 203.858617 2022/10/12 22:11:46 - mmengine - INFO - Epoch(train) [127][100/586] lr: 5.000000e-03 eta: 6:43:17 time: 0.512776 data_time: 0.058159 memory: 8713 loss_kpt: 207.300436 acc_pose: 0.881387 loss: 207.300436 2022/10/12 22:12:11 - mmengine - INFO - Epoch(train) [127][150/586] lr: 5.000000e-03 eta: 6:42:53 time: 0.516212 data_time: 0.055786 memory: 8713 loss_kpt: 208.660919 acc_pose: 0.838441 loss: 208.660919 2022/10/12 22:12:19 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:12:37 - mmengine - INFO - Epoch(train) [127][200/586] lr: 5.000000e-03 eta: 6:42:30 time: 0.521642 data_time: 0.053873 memory: 8713 loss_kpt: 201.846709 acc_pose: 0.817554 loss: 201.846709 2022/10/12 22:13:04 - mmengine - INFO - Epoch(train) [127][250/586] lr: 5.000000e-03 eta: 6:42:06 time: 0.522346 data_time: 0.056548 memory: 8713 loss_kpt: 208.650374 acc_pose: 0.845937 loss: 208.650374 2022/10/12 22:13:29 - mmengine - INFO - Epoch(train) [127][300/586] lr: 5.000000e-03 eta: 6:41:42 time: 0.512250 data_time: 0.053199 memory: 8713 loss_kpt: 203.299028 acc_pose: 0.844206 loss: 203.299028 2022/10/12 22:13:56 - mmengine - INFO - Epoch(train) [127][350/586] lr: 5.000000e-03 eta: 6:41:19 time: 0.526568 data_time: 0.054425 memory: 8713 loss_kpt: 206.968017 acc_pose: 0.872167 loss: 206.968017 2022/10/12 22:14:22 - mmengine - INFO - Epoch(train) [127][400/586] lr: 5.000000e-03 eta: 6:40:55 time: 0.524654 data_time: 0.058819 memory: 8713 loss_kpt: 205.877221 acc_pose: 0.737570 loss: 205.877221 2022/10/12 22:14:47 - mmengine - INFO - Epoch(train) [127][450/586] lr: 5.000000e-03 eta: 6:40:31 time: 0.512704 data_time: 0.051053 memory: 8713 loss_kpt: 209.728500 acc_pose: 0.800825 loss: 209.728500 2022/10/12 22:15:13 - mmengine - INFO - Epoch(train) [127][500/586] lr: 5.000000e-03 eta: 6:40:07 time: 0.511901 data_time: 0.053865 memory: 8713 loss_kpt: 207.547077 acc_pose: 0.793670 loss: 207.547077 2022/10/12 22:15:39 - mmengine - INFO - Epoch(train) [127][550/586] lr: 5.000000e-03 eta: 6:39:43 time: 0.511918 data_time: 0.052588 memory: 8713 loss_kpt: 210.360050 acc_pose: 0.854995 loss: 210.360050 2022/10/12 22:15:57 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:16:25 - mmengine - INFO - Epoch(train) [128][50/586] lr: 5.000000e-03 eta: 6:38:51 time: 0.551537 data_time: 0.060182 memory: 8713 loss_kpt: 207.046102 acc_pose: 0.889967 loss: 207.046102 2022/10/12 22:16:51 - mmengine - INFO - Epoch(train) [128][100/586] lr: 5.000000e-03 eta: 6:38:27 time: 0.519276 data_time: 0.060385 memory: 8713 loss_kpt: 203.253275 acc_pose: 0.828197 loss: 203.253275 2022/10/12 22:17:17 - mmengine - INFO - Epoch(train) [128][150/586] lr: 5.000000e-03 eta: 6:38:03 time: 0.515993 data_time: 0.054481 memory: 8713 loss_kpt: 204.408573 acc_pose: 0.883941 loss: 204.408573 2022/10/12 22:17:42 - mmengine - INFO - Epoch(train) [128][200/586] lr: 5.000000e-03 eta: 6:37:40 time: 0.515741 data_time: 0.058189 memory: 8713 loss_kpt: 208.540513 acc_pose: 0.784706 loss: 208.540513 2022/10/12 22:18:08 - mmengine - INFO - Epoch(train) [128][250/586] lr: 5.000000e-03 eta: 6:37:16 time: 0.515287 data_time: 0.057721 memory: 8713 loss_kpt: 203.787426 acc_pose: 0.884336 loss: 203.787426 2022/10/12 22:18:34 - mmengine - INFO - Epoch(train) [128][300/586] lr: 5.000000e-03 eta: 6:36:52 time: 0.516924 data_time: 0.055669 memory: 8713 loss_kpt: 203.202896 acc_pose: 0.878505 loss: 203.202896 2022/10/12 22:19:00 - mmengine - INFO - Epoch(train) [128][350/586] lr: 5.000000e-03 eta: 6:36:28 time: 0.522527 data_time: 0.059676 memory: 8713 loss_kpt: 206.681147 acc_pose: 0.858599 loss: 206.681147 2022/10/12 22:19:26 - mmengine - INFO - Epoch(train) [128][400/586] lr: 5.000000e-03 eta: 6:36:04 time: 0.511016 data_time: 0.054467 memory: 8713 loss_kpt: 206.052948 acc_pose: 0.856624 loss: 206.052948 2022/10/12 22:19:51 - mmengine - INFO - Epoch(train) [128][450/586] lr: 5.000000e-03 eta: 6:35:40 time: 0.509885 data_time: 0.059779 memory: 8713 loss_kpt: 205.153631 acc_pose: 0.825804 loss: 205.153631 2022/10/12 22:20:17 - mmengine - INFO - Epoch(train) [128][500/586] lr: 5.000000e-03 eta: 6:35:16 time: 0.521449 data_time: 0.059052 memory: 8713 loss_kpt: 204.127572 acc_pose: 0.801752 loss: 204.127572 2022/10/12 22:20:43 - mmengine - INFO - Epoch(train) [128][550/586] lr: 5.000000e-03 eta: 6:34:52 time: 0.511501 data_time: 0.055207 memory: 8713 loss_kpt: 208.589259 acc_pose: 0.783611 loss: 208.589259 2022/10/12 22:20:57 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:21:01 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:21:27 - mmengine - INFO - Epoch(train) [129][50/586] lr: 5.000000e-03 eta: 6:34:00 time: 0.527496 data_time: 0.071844 memory: 8713 loss_kpt: 206.789640 acc_pose: 0.864190 loss: 206.789640 2022/10/12 22:21:54 - mmengine - INFO - Epoch(train) [129][100/586] lr: 5.000000e-03 eta: 6:33:36 time: 0.530575 data_time: 0.056235 memory: 8713 loss_kpt: 204.111615 acc_pose: 0.855084 loss: 204.111615 2022/10/12 22:22:20 - mmengine - INFO - Epoch(train) [129][150/586] lr: 5.000000e-03 eta: 6:33:13 time: 0.524194 data_time: 0.056278 memory: 8713 loss_kpt: 203.205966 acc_pose: 0.839996 loss: 203.205966 2022/10/12 22:22:46 - mmengine - INFO - Epoch(train) [129][200/586] lr: 5.000000e-03 eta: 6:32:49 time: 0.519439 data_time: 0.054823 memory: 8713 loss_kpt: 207.965374 acc_pose: 0.830159 loss: 207.965374 2022/10/12 22:23:12 - mmengine - INFO - Epoch(train) [129][250/586] lr: 5.000000e-03 eta: 6:32:25 time: 0.517157 data_time: 0.055276 memory: 8713 loss_kpt: 207.086138 acc_pose: 0.887614 loss: 207.086138 2022/10/12 22:23:38 - mmengine - INFO - Epoch(train) [129][300/586] lr: 5.000000e-03 eta: 6:32:01 time: 0.518708 data_time: 0.054460 memory: 8713 loss_kpt: 204.968379 acc_pose: 0.811261 loss: 204.968379 2022/10/12 22:24:05 - mmengine - INFO - Epoch(train) [129][350/586] lr: 5.000000e-03 eta: 6:31:38 time: 0.531497 data_time: 0.056790 memory: 8713 loss_kpt: 203.419060 acc_pose: 0.844404 loss: 203.419060 2022/10/12 22:24:31 - mmengine - INFO - Epoch(train) [129][400/586] lr: 5.000000e-03 eta: 6:31:14 time: 0.525699 data_time: 0.053225 memory: 8713 loss_kpt: 203.814162 acc_pose: 0.799002 loss: 203.814162 2022/10/12 22:24:58 - mmengine - INFO - Epoch(train) [129][450/586] lr: 5.000000e-03 eta: 6:30:51 time: 0.534733 data_time: 0.057780 memory: 8713 loss_kpt: 206.533981 acc_pose: 0.834237 loss: 206.533981 2022/10/12 22:25:25 - mmengine - INFO - Epoch(train) [129][500/586] lr: 5.000000e-03 eta: 6:30:28 time: 0.548190 data_time: 0.054871 memory: 8713 loss_kpt: 205.622280 acc_pose: 0.814662 loss: 205.622280 2022/10/12 22:25:52 - mmengine - INFO - Epoch(train) [129][550/586] lr: 5.000000e-03 eta: 6:30:05 time: 0.547977 data_time: 0.057509 memory: 8713 loss_kpt: 203.822268 acc_pose: 0.831725 loss: 203.822268 2022/10/12 22:26:12 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:26:39 - mmengine - INFO - Epoch(train) [130][50/586] lr: 5.000000e-03 eta: 6:29:13 time: 0.545215 data_time: 0.070099 memory: 8713 loss_kpt: 206.112263 acc_pose: 0.797276 loss: 206.112263 2022/10/12 22:27:06 - mmengine - INFO - Epoch(train) [130][100/586] lr: 5.000000e-03 eta: 6:28:50 time: 0.538537 data_time: 0.058085 memory: 8713 loss_kpt: 205.356003 acc_pose: 0.890847 loss: 205.356003 2022/10/12 22:27:33 - mmengine - INFO - Epoch(train) [130][150/586] lr: 5.000000e-03 eta: 6:28:27 time: 0.530294 data_time: 0.057717 memory: 8713 loss_kpt: 204.477979 acc_pose: 0.858399 loss: 204.477979 2022/10/12 22:27:59 - mmengine - INFO - Epoch(train) [130][200/586] lr: 5.000000e-03 eta: 6:28:03 time: 0.532320 data_time: 0.053686 memory: 8713 loss_kpt: 207.853613 acc_pose: 0.810483 loss: 207.853613 2022/10/12 22:28:26 - mmengine - INFO - Epoch(train) [130][250/586] lr: 5.000000e-03 eta: 6:27:40 time: 0.529127 data_time: 0.058173 memory: 8713 loss_kpt: 204.389133 acc_pose: 0.880665 loss: 204.389133 2022/10/12 22:28:53 - mmengine - INFO - Epoch(train) [130][300/586] lr: 5.000000e-03 eta: 6:27:17 time: 0.552509 data_time: 0.061325 memory: 8713 loss_kpt: 205.119374 acc_pose: 0.844437 loss: 205.119374 2022/10/12 22:29:21 - mmengine - INFO - Epoch(train) [130][350/586] lr: 5.000000e-03 eta: 6:26:54 time: 0.551760 data_time: 0.062334 memory: 8713 loss_kpt: 203.895276 acc_pose: 0.826839 loss: 203.895276 2022/10/12 22:29:48 - mmengine - INFO - Epoch(train) [130][400/586] lr: 5.000000e-03 eta: 6:26:31 time: 0.543029 data_time: 0.057289 memory: 8713 loss_kpt: 204.151132 acc_pose: 0.874194 loss: 204.151132 2022/10/12 22:29:51 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:30:15 - mmengine - INFO - Epoch(train) [130][450/586] lr: 5.000000e-03 eta: 6:26:08 time: 0.533648 data_time: 0.055204 memory: 8713 loss_kpt: 200.216203 acc_pose: 0.888546 loss: 200.216203 2022/10/12 22:30:41 - mmengine - INFO - Epoch(train) [130][500/586] lr: 5.000000e-03 eta: 6:25:44 time: 0.532606 data_time: 0.056220 memory: 8713 loss_kpt: 207.631934 acc_pose: 0.876385 loss: 207.631934 2022/10/12 22:31:09 - mmengine - INFO - Epoch(train) [130][550/586] lr: 5.000000e-03 eta: 6:25:21 time: 0.542021 data_time: 0.061363 memory: 8713 loss_kpt: 206.880459 acc_pose: 0.857464 loss: 206.880459 2022/10/12 22:31:28 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:31:28 - mmengine - INFO - Saving checkpoint at 130 epochs 2022/10/12 22:31:41 - mmengine - INFO - Epoch(val) [130][50/407] eta: 0:01:12 time: 0.202448 data_time: 0.016138 memory: 8713 2022/10/12 22:31:51 - mmengine - INFO - Epoch(val) [130][100/407] eta: 0:01:00 time: 0.196946 data_time: 0.008039 memory: 1759 2022/10/12 22:32:01 - mmengine - INFO - Epoch(val) [130][150/407] eta: 0:00:50 time: 0.196345 data_time: 0.008512 memory: 1759 2022/10/12 22:32:10 - mmengine - INFO - Epoch(val) [130][200/407] eta: 0:00:39 time: 0.191766 data_time: 0.007643 memory: 1759 2022/10/12 22:32:20 - mmengine - INFO - Epoch(val) [130][250/407] eta: 0:00:30 time: 0.194967 data_time: 0.008274 memory: 1759 2022/10/12 22:32:30 - mmengine - INFO - Epoch(val) [130][300/407] eta: 0:00:20 time: 0.194825 data_time: 0.007722 memory: 1759 2022/10/12 22:32:40 - mmengine - INFO - Epoch(val) [130][350/407] eta: 0:00:11 time: 0.195552 data_time: 0.008231 memory: 1759 2022/10/12 22:32:49 - mmengine - INFO - Epoch(val) [130][400/407] eta: 0:00:01 time: 0.191209 data_time: 0.010582 memory: 1759 2022/10/12 22:33:03 - mmengine - INFO - Evaluating CocoMetric... 2022/10/12 22:33:18 - mmengine - INFO - Epoch(val) [130][407/407] coco/AP: 0.723435 coco/AP .5: 0.892639 coco/AP .75: 0.795714 coco/AP (M): 0.691500 coco/AP (L): 0.784665 coco/AR: 0.788523 coco/AR .5: 0.933407 coco/AR .75: 0.848394 coco/AR (M): 0.744278 coco/AR (L): 0.849387 2022/10/12 22:33:18 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/liqikai/openmmlab/pt112cu113py38/mmpose/work_dirs/20221012/rsn2x/best_coco/AP_epoch_120.pth is removed 2022/10/12 22:33:21 - mmengine - INFO - The best checkpoint with 0.7234 coco/AP at 130 epoch is saved to best_coco/AP_epoch_130.pth. 2022/10/12 22:33:47 - mmengine - INFO - Epoch(train) [131][50/586] lr: 5.000000e-03 eta: 6:24:29 time: 0.539161 data_time: 0.065874 memory: 8713 loss_kpt: 204.248530 acc_pose: 0.807385 loss: 204.248530 2022/10/12 22:34:14 - mmengine - INFO - Epoch(train) [131][100/586] lr: 5.000000e-03 eta: 6:24:06 time: 0.537428 data_time: 0.060278 memory: 8713 loss_kpt: 209.092512 acc_pose: 0.787089 loss: 209.092512 2022/10/12 22:34:41 - mmengine - INFO - Epoch(train) [131][150/586] lr: 5.000000e-03 eta: 6:23:43 time: 0.540342 data_time: 0.057108 memory: 8713 loss_kpt: 208.728712 acc_pose: 0.841073 loss: 208.728712 2022/10/12 22:35:08 - mmengine - INFO - Epoch(train) [131][200/586] lr: 5.000000e-03 eta: 6:23:19 time: 0.529832 data_time: 0.057327 memory: 8713 loss_kpt: 202.084439 acc_pose: 0.810456 loss: 202.084439 2022/10/12 22:35:34 - mmengine - INFO - Epoch(train) [131][250/586] lr: 5.000000e-03 eta: 6:22:56 time: 0.527464 data_time: 0.063771 memory: 8713 loss_kpt: 204.327595 acc_pose: 0.865367 loss: 204.327595 2022/10/12 22:36:00 - mmengine - INFO - Epoch(train) [131][300/586] lr: 5.000000e-03 eta: 6:22:32 time: 0.514744 data_time: 0.052865 memory: 8713 loss_kpt: 207.550302 acc_pose: 0.823452 loss: 207.550302 2022/10/12 22:36:26 - mmengine - INFO - Epoch(train) [131][350/586] lr: 5.000000e-03 eta: 6:22:08 time: 0.518523 data_time: 0.060574 memory: 8713 loss_kpt: 202.781266 acc_pose: 0.832024 loss: 202.781266 2022/10/12 22:36:52 - mmengine - INFO - Epoch(train) [131][400/586] lr: 5.000000e-03 eta: 6:21:44 time: 0.517887 data_time: 0.056261 memory: 8713 loss_kpt: 205.566470 acc_pose: 0.834731 loss: 205.566470 2022/10/12 22:37:18 - mmengine - INFO - Epoch(train) [131][450/586] lr: 5.000000e-03 eta: 6:21:21 time: 0.528754 data_time: 0.064239 memory: 8713 loss_kpt: 206.904403 acc_pose: 0.831822 loss: 206.904403 2022/10/12 22:37:44 - mmengine - INFO - Epoch(train) [131][500/586] lr: 5.000000e-03 eta: 6:20:57 time: 0.514802 data_time: 0.052776 memory: 8713 loss_kpt: 206.629472 acc_pose: 0.774736 loss: 206.629472 2022/10/12 22:38:10 - mmengine - INFO - Epoch(train) [131][550/586] lr: 5.000000e-03 eta: 6:20:33 time: 0.527057 data_time: 0.060901 memory: 8713 loss_kpt: 204.963552 acc_pose: 0.816848 loss: 204.963552 2022/10/12 22:38:29 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:38:56 - mmengine - INFO - Epoch(train) [132][50/586] lr: 5.000000e-03 eta: 6:19:41 time: 0.540294 data_time: 0.068248 memory: 8713 loss_kpt: 205.861756 acc_pose: 0.827694 loss: 205.861756 2022/10/12 22:39:23 - mmengine - INFO - Epoch(train) [132][100/586] lr: 5.000000e-03 eta: 6:19:18 time: 0.527761 data_time: 0.053981 memory: 8713 loss_kpt: 206.092323 acc_pose: 0.885400 loss: 206.092323 2022/10/12 22:39:50 - mmengine - INFO - Epoch(train) [132][150/586] lr: 5.000000e-03 eta: 6:18:54 time: 0.533245 data_time: 0.057370 memory: 8713 loss_kpt: 201.789650 acc_pose: 0.865583 loss: 201.789650 2022/10/12 22:40:16 - mmengine - INFO - Epoch(train) [132][200/586] lr: 5.000000e-03 eta: 6:18:31 time: 0.527432 data_time: 0.056045 memory: 8713 loss_kpt: 207.991242 acc_pose: 0.807694 loss: 207.991242 2022/10/12 22:40:34 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:40:43 - mmengine - INFO - Epoch(train) [132][250/586] lr: 5.000000e-03 eta: 6:18:07 time: 0.531292 data_time: 0.065207 memory: 8713 loss_kpt: 205.944481 acc_pose: 0.808763 loss: 205.944481 2022/10/12 22:41:09 - mmengine - INFO - Epoch(train) [132][300/586] lr: 5.000000e-03 eta: 6:17:44 time: 0.527544 data_time: 0.057100 memory: 8713 loss_kpt: 206.997674 acc_pose: 0.873947 loss: 206.997674 2022/10/12 22:41:35 - mmengine - INFO - Epoch(train) [132][350/586] lr: 5.000000e-03 eta: 6:17:20 time: 0.519341 data_time: 0.060464 memory: 8713 loss_kpt: 203.954852 acc_pose: 0.837521 loss: 203.954852 2022/10/12 22:42:01 - mmengine - INFO - Epoch(train) [132][400/586] lr: 5.000000e-03 eta: 6:16:56 time: 0.517049 data_time: 0.052760 memory: 8713 loss_kpt: 202.868068 acc_pose: 0.873933 loss: 202.868068 2022/10/12 22:42:27 - mmengine - INFO - Epoch(train) [132][450/586] lr: 5.000000e-03 eta: 6:16:32 time: 0.520992 data_time: 0.059992 memory: 8713 loss_kpt: 206.920698 acc_pose: 0.885737 loss: 206.920698 2022/10/12 22:42:53 - mmengine - INFO - Epoch(train) [132][500/586] lr: 5.000000e-03 eta: 6:16:09 time: 0.525778 data_time: 0.057354 memory: 8713 loss_kpt: 202.723823 acc_pose: 0.850992 loss: 202.723823 2022/10/12 22:43:19 - mmengine - INFO - Epoch(train) [132][550/586] lr: 5.000000e-03 eta: 6:15:45 time: 0.526234 data_time: 0.057230 memory: 8713 loss_kpt: 205.290351 acc_pose: 0.826256 loss: 205.290351 2022/10/12 22:43:38 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:44:05 - mmengine - INFO - Epoch(train) [133][50/586] lr: 5.000000e-03 eta: 6:14:53 time: 0.527439 data_time: 0.071338 memory: 8713 loss_kpt: 207.674802 acc_pose: 0.790467 loss: 207.674802 2022/10/12 22:44:30 - mmengine - INFO - Epoch(train) [133][100/586] lr: 5.000000e-03 eta: 6:14:29 time: 0.510509 data_time: 0.057631 memory: 8713 loss_kpt: 209.222671 acc_pose: 0.782403 loss: 209.222671 2022/10/12 22:44:56 - mmengine - INFO - Epoch(train) [133][150/586] lr: 5.000000e-03 eta: 6:14:05 time: 0.521256 data_time: 0.062624 memory: 8713 loss_kpt: 202.900457 acc_pose: 0.820383 loss: 202.900457 2022/10/12 22:45:22 - mmengine - INFO - Epoch(train) [133][200/586] lr: 5.000000e-03 eta: 6:13:41 time: 0.510147 data_time: 0.056855 memory: 8713 loss_kpt: 204.140299 acc_pose: 0.779044 loss: 204.140299 2022/10/12 22:45:47 - mmengine - INFO - Epoch(train) [133][250/586] lr: 5.000000e-03 eta: 6:13:17 time: 0.513460 data_time: 0.061573 memory: 8713 loss_kpt: 203.518282 acc_pose: 0.829179 loss: 203.518282 2022/10/12 22:46:13 - mmengine - INFO - Epoch(train) [133][300/586] lr: 5.000000e-03 eta: 6:12:53 time: 0.509580 data_time: 0.052716 memory: 8713 loss_kpt: 204.171970 acc_pose: 0.841623 loss: 204.171970 2022/10/12 22:46:39 - mmengine - INFO - Epoch(train) [133][350/586] lr: 5.000000e-03 eta: 6:12:29 time: 0.518411 data_time: 0.064161 memory: 8713 loss_kpt: 207.221631 acc_pose: 0.855567 loss: 207.221631 2022/10/12 22:47:05 - mmengine - INFO - Epoch(train) [133][400/586] lr: 5.000000e-03 eta: 6:12:05 time: 0.519512 data_time: 0.053292 memory: 8713 loss_kpt: 205.600690 acc_pose: 0.750719 loss: 205.600690 2022/10/12 22:47:31 - mmengine - INFO - Epoch(train) [133][450/586] lr: 5.000000e-03 eta: 6:11:41 time: 0.525836 data_time: 0.062037 memory: 8713 loss_kpt: 204.061323 acc_pose: 0.777000 loss: 204.061323 2022/10/12 22:47:57 - mmengine - INFO - Epoch(train) [133][500/586] lr: 5.000000e-03 eta: 6:11:18 time: 0.525902 data_time: 0.057665 memory: 8713 loss_kpt: 201.435840 acc_pose: 0.880607 loss: 201.435840 2022/10/12 22:48:23 - mmengine - INFO - Epoch(train) [133][550/586] lr: 5.000000e-03 eta: 6:10:54 time: 0.513532 data_time: 0.061351 memory: 8713 loss_kpt: 204.933346 acc_pose: 0.843714 loss: 204.933346 2022/10/12 22:48:41 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:49:09 - mmengine - INFO - Epoch(train) [134][50/586] lr: 5.000000e-03 eta: 6:10:03 time: 0.549212 data_time: 0.071874 memory: 8713 loss_kpt: 200.206513 acc_pose: 0.785055 loss: 200.206513 2022/10/12 22:49:15 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:49:35 - mmengine - INFO - Epoch(train) [134][100/586] lr: 5.000000e-03 eta: 6:09:39 time: 0.533013 data_time: 0.057253 memory: 8713 loss_kpt: 206.407924 acc_pose: 0.810585 loss: 206.407924 2022/10/12 22:50:01 - mmengine - INFO - Epoch(train) [134][150/586] lr: 5.000000e-03 eta: 6:09:15 time: 0.522073 data_time: 0.059911 memory: 8713 loss_kpt: 203.390697 acc_pose: 0.796191 loss: 203.390697 2022/10/12 22:50:28 - mmengine - INFO - Epoch(train) [134][200/586] lr: 5.000000e-03 eta: 6:08:52 time: 0.532786 data_time: 0.054561 memory: 8713 loss_kpt: 203.200232 acc_pose: 0.800307 loss: 203.200232 2022/10/12 22:50:54 - mmengine - INFO - Epoch(train) [134][250/586] lr: 5.000000e-03 eta: 6:08:28 time: 0.530408 data_time: 0.063411 memory: 8713 loss_kpt: 204.008533 acc_pose: 0.844049 loss: 204.008533 2022/10/12 22:51:20 - mmengine - INFO - Epoch(train) [134][300/586] lr: 5.000000e-03 eta: 6:08:05 time: 0.518768 data_time: 0.056921 memory: 8713 loss_kpt: 206.067748 acc_pose: 0.852231 loss: 206.067748 2022/10/12 22:51:47 - mmengine - INFO - Epoch(train) [134][350/586] lr: 5.000000e-03 eta: 6:07:41 time: 0.531031 data_time: 0.057202 memory: 8713 loss_kpt: 208.405322 acc_pose: 0.793210 loss: 208.405322 2022/10/12 22:52:13 - mmengine - INFO - Epoch(train) [134][400/586] lr: 5.000000e-03 eta: 6:07:17 time: 0.523771 data_time: 0.054667 memory: 8713 loss_kpt: 206.363678 acc_pose: 0.806739 loss: 206.363678 2022/10/12 22:52:40 - mmengine - INFO - Epoch(train) [134][450/586] lr: 5.000000e-03 eta: 6:06:54 time: 0.537799 data_time: 0.056514 memory: 8713 loss_kpt: 206.091099 acc_pose: 0.779576 loss: 206.091099 2022/10/12 22:53:07 - mmengine - INFO - Epoch(train) [134][500/586] lr: 5.000000e-03 eta: 6:06:31 time: 0.537866 data_time: 0.056106 memory: 8713 loss_kpt: 205.276442 acc_pose: 0.787643 loss: 205.276442 2022/10/12 22:53:35 - mmengine - INFO - Epoch(train) [134][550/586] lr: 5.000000e-03 eta: 6:06:08 time: 0.551180 data_time: 0.063899 memory: 8713 loss_kpt: 207.711768 acc_pose: 0.784321 loss: 207.711768 2022/10/12 22:53:54 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:54:21 - mmengine - INFO - Epoch(train) [135][50/586] lr: 5.000000e-03 eta: 6:05:16 time: 0.530741 data_time: 0.074380 memory: 8713 loss_kpt: 204.151773 acc_pose: 0.789162 loss: 204.151773 2022/10/12 22:54:46 - mmengine - INFO - Epoch(train) [135][100/586] lr: 5.000000e-03 eta: 6:04:52 time: 0.510733 data_time: 0.055750 memory: 8713 loss_kpt: 203.684727 acc_pose: 0.745706 loss: 203.684727 2022/10/12 22:55:13 - mmengine - INFO - Epoch(train) [135][150/586] lr: 5.000000e-03 eta: 6:04:28 time: 0.525389 data_time: 0.062053 memory: 8713 loss_kpt: 198.847471 acc_pose: 0.892994 loss: 198.847471 2022/10/12 22:55:38 - mmengine - INFO - Epoch(train) [135][200/586] lr: 5.000000e-03 eta: 6:04:04 time: 0.511137 data_time: 0.059840 memory: 8713 loss_kpt: 205.470560 acc_pose: 0.817911 loss: 205.470560 2022/10/12 22:56:04 - mmengine - INFO - Epoch(train) [135][250/586] lr: 5.000000e-03 eta: 6:03:40 time: 0.509574 data_time: 0.063565 memory: 8713 loss_kpt: 205.525520 acc_pose: 0.878827 loss: 205.525520 2022/10/12 22:56:29 - mmengine - INFO - Epoch(train) [135][300/586] lr: 5.000000e-03 eta: 6:03:16 time: 0.507943 data_time: 0.060768 memory: 8713 loss_kpt: 203.935744 acc_pose: 0.810302 loss: 203.935744 2022/10/12 22:56:55 - mmengine - INFO - Epoch(train) [135][350/586] lr: 5.000000e-03 eta: 6:02:52 time: 0.512559 data_time: 0.062630 memory: 8713 loss_kpt: 203.991985 acc_pose: 0.853536 loss: 203.991985 2022/10/12 22:57:20 - mmengine - INFO - Epoch(train) [135][400/586] lr: 5.000000e-03 eta: 6:02:28 time: 0.514716 data_time: 0.059922 memory: 8713 loss_kpt: 204.255119 acc_pose: 0.913161 loss: 204.255119 2022/10/12 22:57:46 - mmengine - INFO - Epoch(train) [135][450/586] lr: 5.000000e-03 eta: 6:02:04 time: 0.519487 data_time: 0.061869 memory: 8713 loss_kpt: 202.148666 acc_pose: 0.782449 loss: 202.148666 2022/10/12 22:58:00 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:58:12 - mmengine - INFO - Epoch(train) [135][500/586] lr: 5.000000e-03 eta: 6:01:40 time: 0.516077 data_time: 0.057872 memory: 8713 loss_kpt: 206.719293 acc_pose: 0.850003 loss: 206.719293 2022/10/12 22:58:38 - mmengine - INFO - Epoch(train) [135][550/586] lr: 5.000000e-03 eta: 6:01:16 time: 0.523931 data_time: 0.059435 memory: 8713 loss_kpt: 207.551489 acc_pose: 0.809269 loss: 207.551489 2022/10/12 22:58:57 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:59:24 - mmengine - INFO - Epoch(train) [136][50/586] lr: 5.000000e-03 eta: 6:00:25 time: 0.542924 data_time: 0.071355 memory: 8713 loss_kpt: 206.873681 acc_pose: 0.824862 loss: 206.873681 2022/10/12 22:59:50 - mmengine - INFO - Epoch(train) [136][100/586] lr: 5.000000e-03 eta: 6:00:02 time: 0.532682 data_time: 0.064591 memory: 8713 loss_kpt: 203.160771 acc_pose: 0.819593 loss: 203.160771 2022/10/12 23:00:17 - mmengine - INFO - Epoch(train) [136][150/586] lr: 5.000000e-03 eta: 5:59:38 time: 0.523612 data_time: 0.059604 memory: 8713 loss_kpt: 205.128823 acc_pose: 0.835751 loss: 205.128823 2022/10/12 23:00:43 - mmengine - INFO - Epoch(train) [136][200/586] lr: 5.000000e-03 eta: 5:59:14 time: 0.525117 data_time: 0.059794 memory: 8713 loss_kpt: 204.228573 acc_pose: 0.801668 loss: 204.228573 2022/10/12 23:01:10 - mmengine - INFO - Epoch(train) [136][250/586] lr: 5.000000e-03 eta: 5:58:51 time: 0.541653 data_time: 0.059890 memory: 8713 loss_kpt: 209.563048 acc_pose: 0.829587 loss: 209.563048 2022/10/12 23:01:37 - mmengine - INFO - Epoch(train) [136][300/586] lr: 5.000000e-03 eta: 5:58:28 time: 0.542329 data_time: 0.059410 memory: 8713 loss_kpt: 206.036054 acc_pose: 0.857272 loss: 206.036054 2022/10/12 23:02:04 - mmengine - INFO - Epoch(train) [136][350/586] lr: 5.000000e-03 eta: 5:58:04 time: 0.528979 data_time: 0.065482 memory: 8713 loss_kpt: 208.186563 acc_pose: 0.820986 loss: 208.186563 2022/10/12 23:02:30 - mmengine - INFO - Epoch(train) [136][400/586] lr: 5.000000e-03 eta: 5:57:40 time: 0.526607 data_time: 0.061122 memory: 8713 loss_kpt: 208.571945 acc_pose: 0.860035 loss: 208.571945 2022/10/12 23:02:57 - mmengine - INFO - Epoch(train) [136][450/586] lr: 5.000000e-03 eta: 5:57:17 time: 0.542440 data_time: 0.066685 memory: 8713 loss_kpt: 204.212265 acc_pose: 0.841335 loss: 204.212265 2022/10/12 23:03:24 - mmengine - INFO - Epoch(train) [136][500/586] lr: 5.000000e-03 eta: 5:56:54 time: 0.534292 data_time: 0.061359 memory: 8713 loss_kpt: 204.282856 acc_pose: 0.878567 loss: 204.282856 2022/10/12 23:03:51 - mmengine - INFO - Epoch(train) [136][550/586] lr: 5.000000e-03 eta: 5:56:30 time: 0.536946 data_time: 0.065144 memory: 8713 loss_kpt: 203.367163 acc_pose: 0.858897 loss: 203.367163 2022/10/12 23:04:09 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 23:04:36 - mmengine - INFO - Epoch(train) [137][50/586] lr: 5.000000e-03 eta: 5:55:39 time: 0.532658 data_time: 0.080430 memory: 8713 loss_kpt: 206.059074 acc_pose: 0.785333 loss: 206.059074 2022/10/12 23:05:03 - mmengine - INFO - Epoch(train) [137][100/586] lr: 5.000000e-03 eta: 5:55:16 time: 0.534172 data_time: 0.063008 memory: 8713 loss_kpt: 205.308582 acc_pose: 0.833418 loss: 205.308582 2022/10/12 23:05:30 - mmengine - INFO - Epoch(train) [137][150/586] lr: 5.000000e-03 eta: 5:54:52 time: 0.537484 data_time: 0.064806 memory: 8713 loss_kpt: 203.870810 acc_pose: 0.896670 loss: 203.870810 2022/10/12 23:05:57 - mmengine - INFO - Epoch(train) [137][200/586] lr: 5.000000e-03 eta: 5:54:29 time: 0.549695 data_time: 0.058437 memory: 8713 loss_kpt: 204.785444 acc_pose: 0.849852 loss: 204.785444 2022/10/12 23:06:25 - mmengine - INFO - Epoch(train) [137][250/586] lr: 5.000000e-03 eta: 5:54:06 time: 0.562017 data_time: 0.067705 memory: 8713 loss_kpt: 204.561854 acc_pose: 0.870939 loss: 204.561854 2022/10/12 23:06:53 - mmengine - INFO - Epoch(train) [137][300/586] lr: 5.000000e-03 eta: 5:53:43 time: 0.550376 data_time: 0.060555 memory: 8713 loss_kpt: 202.518158 acc_pose: 0.876703 loss: 202.518158 2022/10/12 23:06:55 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 23:07:20 - mmengine - INFO - Epoch(train) [137][350/586] lr: 5.000000e-03 eta: 5:53:20 time: 0.542787 data_time: 0.062229 memory: 8713 loss_kpt: 205.566609 acc_pose: 0.847743 loss: 205.566609 2022/10/12 23:07:47 - mmengine - INFO - Epoch(train) [137][400/586] lr: 5.000000e-03 eta: 5:52:56 time: 0.529564 data_time: 0.057847 memory: 8713 loss_kpt: 206.492975 acc_pose: 0.803176 loss: 206.492975 2022/10/12 23:08:14 - mmengine - INFO - Epoch(train) [137][450/586] lr: 5.000000e-03 eta: 5:52:33 time: 0.550698 data_time: 0.065398 memory: 8713 loss_kpt: 203.788181 acc_pose: 0.879742 loss: 203.788181 2022/10/12 23:08:41 - mmengine - INFO - Epoch(train) [137][500/586] lr: 5.000000e-03 eta: 5:52:10 time: 0.540884 data_time: 0.060534 memory: 8713 loss_kpt: 202.093348 acc_pose: 0.857477 loss: 202.093348 2022/10/12 23:09:08 - mmengine - INFO - Epoch(train) [137][550/586] lr: 5.000000e-03 eta: 5:51:47 time: 0.542594 data_time: 0.063738 memory: 8713 loss_kpt: 200.689258 acc_pose: 0.803382 loss: 200.689258 2022/10/12 23:09:28 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 23:09:55 - mmengine - INFO - Epoch(train) [138][50/586] lr: 5.000000e-03 eta: 5:50:56 time: 0.541633 data_time: 0.074187 memory: 8713 loss_kpt: 208.711701 acc_pose: 0.702257 loss: 208.711701 2022/10/12 23:10:21 - mmengine - INFO - Epoch(train) [138][100/586] lr: 5.000000e-03 eta: 5:50:32 time: 0.534960 data_time: 0.065189 memory: 8713 loss_kpt: 206.494198 acc_pose: 0.769935 loss: 206.494198 2022/10/12 23:10:48 - mmengine - INFO - Epoch(train) [138][150/586] lr: 5.000000e-03 eta: 5:50:09 time: 0.529121 data_time: 0.061496 memory: 8713 loss_kpt: 204.746709 acc_pose: 0.762400 loss: 204.746709 2022/10/12 23:11:15 - mmengine - INFO - Epoch(train) [138][200/586] lr: 5.000000e-03 eta: 5:49:45 time: 0.532163 data_time: 0.063220 memory: 8713 loss_kpt: 205.828987 acc_pose: 0.867169 loss: 205.828987 2022/10/12 23:11:42 - mmengine - INFO - Epoch(train) [138][250/586] lr: 5.000000e-03 eta: 5:49:22 time: 0.539598 data_time: 0.063477 memory: 8713 loss_kpt: 201.743383 acc_pose: 0.819736 loss: 201.743383 2022/10/12 23:12:09 - mmengine - INFO - Epoch(train) [138][300/586] lr: 5.000000e-03 eta: 5:48:59 time: 0.545737 data_time: 0.068619 memory: 8713 loss_kpt: 204.400767 acc_pose: 0.767184 loss: 204.400767 2022/10/12 23:12:36 - mmengine - INFO - Epoch(train) [138][350/586] lr: 5.000000e-03 eta: 5:48:35 time: 0.550936 data_time: 0.059249 memory: 8713 loss_kpt: 205.737238 acc_pose: 0.800210 loss: 205.737238 2022/10/12 23:13:04 - mmengine - INFO - Epoch(train) [138][400/586] lr: 5.000000e-03 eta: 5:48:12 time: 0.548543 data_time: 0.063483 memory: 8713 loss_kpt: 199.471721 acc_pose: 0.866320 loss: 199.471721 2022/10/12 23:13:30 - mmengine - INFO - Epoch(train) [138][450/586] lr: 5.000000e-03 eta: 5:47:49 time: 0.531027 data_time: 0.061131 memory: 8713 loss_kpt: 205.684387 acc_pose: 0.821826 loss: 205.684387 2022/10/12 23:13:57 - mmengine - INFO - Epoch(train) [138][500/586] lr: 5.000000e-03 eta: 5:47:25 time: 0.526381 data_time: 0.064286 memory: 8713 loss_kpt: 202.740382 acc_pose: 0.862927 loss: 202.740382 2022/10/12 23:14:23 - mmengine - INFO - Epoch(train) [138][550/586] lr: 5.000000e-03 eta: 5:47:01 time: 0.521557 data_time: 0.063617 memory: 8713 loss_kpt: 204.360273 acc_pose: 0.764785 loss: 204.360273 2022/10/12 23:14:42 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 23:15:08 - mmengine - INFO - Epoch(train) [139][50/586] lr: 5.000000e-03 eta: 5:46:10 time: 0.528859 data_time: 0.071067 memory: 8713 loss_kpt: 202.194037 acc_pose: 0.840863 loss: 202.194037 2022/10/12 23:15:35 - mmengine - INFO - Epoch(train) [139][100/586] lr: 5.000000e-03 eta: 5:45:46 time: 0.527946 data_time: 0.062182 memory: 8713 loss_kpt: 204.215862 acc_pose: 0.798561 loss: 204.215862 2022/10/12 23:15:51 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 23:16:01 - mmengine - INFO - Epoch(train) [139][150/586] lr: 5.000000e-03 eta: 5:45:23 time: 0.526261 data_time: 0.060077 memory: 8713 loss_kpt: 203.425878 acc_pose: 0.823965 loss: 203.425878 2022/10/12 23:16:27 - mmengine - INFO - Epoch(train) [139][200/586] lr: 5.000000e-03 eta: 5:44:59 time: 0.528137 data_time: 0.060258 memory: 8713 loss_kpt: 205.282679 acc_pose: 0.893405 loss: 205.282679 2022/10/12 23:16:54 - mmengine - INFO - Epoch(train) [139][250/586] lr: 5.000000e-03 eta: 5:44:35 time: 0.525429 data_time: 0.063502 memory: 8713 loss_kpt: 203.251372 acc_pose: 0.826663 loss: 203.251372 2022/10/12 23:17:20 - mmengine - INFO - Epoch(train) [139][300/586] lr: 5.000000e-03 eta: 5:44:11 time: 0.523550 data_time: 0.067057 memory: 8713 loss_kpt: 209.598220 acc_pose: 0.862662 loss: 209.598220 2022/10/12 23:17:46 - mmengine - INFO - Epoch(train) [139][350/586] lr: 5.000000e-03 eta: 5:43:47 time: 0.523765 data_time: 0.064730 memory: 8713 loss_kpt: 202.614496 acc_pose: 0.828750 loss: 202.614496 2022/10/12 23:18:13 - mmengine - INFO - Epoch(train) [139][400/586] lr: 5.000000e-03 eta: 5:43:24 time: 0.544996 data_time: 0.060611 memory: 8713 loss_kpt: 206.599929 acc_pose: 0.830813 loss: 206.599929 2022/10/12 23:18:40 - mmengine - INFO - Epoch(train) [139][450/586] lr: 5.000000e-03 eta: 5:43:01 time: 0.536344 data_time: 0.063538 memory: 8713 loss_kpt: 202.350706 acc_pose: 0.804054 loss: 202.350706 2022/10/12 23:19:07 - mmengine - INFO - Epoch(train) [139][500/586] lr: 5.000000e-03 eta: 5:42:37 time: 0.542005 data_time: 0.067790 memory: 8713 loss_kpt: 202.137331 acc_pose: 0.765393 loss: 202.137331 2022/10/12 23:19:35 - mmengine - INFO - Epoch(train) [139][550/586] lr: 5.000000e-03 eta: 5:42:14 time: 0.547769 data_time: 0.060852 memory: 8713 loss_kpt: 201.872082 acc_pose: 0.909437 loss: 201.872082 2022/10/12 23:19:54 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 23:20:21 - mmengine - INFO - Epoch(train) [140][50/586] lr: 5.000000e-03 eta: 5:41:24 time: 0.546134 data_time: 0.070053 memory: 8713 loss_kpt: 206.919946 acc_pose: 0.854634 loss: 206.919946 2022/10/12 23:20:48 - mmengine - INFO - Epoch(train) [140][100/586] lr: 5.000000e-03 eta: 5:41:00 time: 0.545244 data_time: 0.056686 memory: 8713 loss_kpt: 203.687444 acc_pose: 0.842585 loss: 203.687444 2022/10/12 23:21:16 - mmengine - INFO - Epoch(train) [140][150/586] lr: 5.000000e-03 eta: 5:40:37 time: 0.553406 data_time: 0.064672 memory: 8713 loss_kpt: 203.735516 acc_pose: 0.846482 loss: 203.735516 2022/10/12 23:21:43 - mmengine - INFO - Epoch(train) [140][200/586] lr: 5.000000e-03 eta: 5:40:14 time: 0.547033 data_time: 0.056047 memory: 8713 loss_kpt: 201.470388 acc_pose: 0.850941 loss: 201.470388 2022/10/12 23:22:11 - mmengine - INFO - Epoch(train) [140][250/586] lr: 5.000000e-03 eta: 5:39:51 time: 0.559532 data_time: 0.061414 memory: 8713 loss_kpt: 205.197036 acc_pose: 0.817551 loss: 205.197036 2022/10/12 23:22:39 - mmengine - INFO - Epoch(train) [140][300/586] lr: 5.000000e-03 eta: 5:39:28 time: 0.550176 data_time: 0.059642 memory: 8713 loss_kpt: 204.814146 acc_pose: 0.807207 loss: 204.814146 2022/10/12 23:23:06 - mmengine - INFO - Epoch(train) [140][350/586] lr: 5.000000e-03 eta: 5:39:04 time: 0.537737 data_time: 0.064208 memory: 8713 loss_kpt: 200.625702 acc_pose: 0.866098 loss: 200.625702 2022/10/12 23:23:33 - mmengine - INFO - Epoch(train) [140][400/586] lr: 5.000000e-03 eta: 5:38:41 time: 0.535268 data_time: 0.060885 memory: 8713 loss_kpt: 201.803406 acc_pose: 0.833189 loss: 201.803406 2022/10/12 23:23:59 - mmengine - INFO - Epoch(train) [140][450/586] lr: 5.000000e-03 eta: 5:38:17 time: 0.531651 data_time: 0.063129 memory: 8713 loss_kpt: 201.783042 acc_pose: 0.813679 loss: 201.783042 2022/10/12 23:24:25 - mmengine - INFO - Epoch(train) [140][500/586] lr: 5.000000e-03 eta: 5:37:53 time: 0.522196 data_time: 0.056004 memory: 8713 loss_kpt: 204.368972 acc_pose: 0.886192 loss: 204.368972 2022/10/12 23:24:50 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 23:24:52 - mmengine - INFO - Epoch(train) [140][550/586] lr: 5.000000e-03 eta: 5:37:29 time: 0.527794 data_time: 0.060960 memory: 8713 loss_kpt: 204.728741 acc_pose: 0.846698 loss: 204.728741 2022/10/12 23:25:10 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 23:25:10 - mmengine - INFO - Saving checkpoint at 140 epochs 2022/10/12 23:25:24 - mmengine - INFO - Epoch(val) [140][50/407] eta: 0:01:11 time: 0.200400 data_time: 0.012748 memory: 8713 2022/10/12 23:25:33 - mmengine - INFO - Epoch(val) [140][100/407] eta: 0:00:59 time: 0.193303 data_time: 0.007917 memory: 1759 2022/10/12 23:25:43 - mmengine - INFO - Epoch(val) [140][150/407] eta: 0:00:49 time: 0.192176 data_time: 0.008769 memory: 1759 2022/10/12 23:25:53 - mmengine - INFO - Epoch(val) [140][200/407] eta: 0:00:39 time: 0.192429 data_time: 0.007985 memory: 1759 2022/10/12 23:26:02 - mmengine - INFO - Epoch(val) [140][250/407] eta: 0:00:30 time: 0.191677 data_time: 0.008525 memory: 1759 2022/10/12 23:26:12 - mmengine - INFO - Epoch(val) [140][300/407] eta: 0:00:20 time: 0.194587 data_time: 0.007628 memory: 1759 2022/10/12 23:26:22 - mmengine - INFO - Epoch(val) [140][350/407] eta: 0:00:10 time: 0.191458 data_time: 0.008002 memory: 1759 2022/10/12 23:26:31 - mmengine - INFO - Epoch(val) [140][400/407] eta: 0:00:01 time: 0.190199 data_time: 0.007826 memory: 1759 2022/10/12 23:26:45 - mmengine - INFO - Evaluating CocoMetric... 2022/10/12 23:27:01 - mmengine - INFO - Epoch(val) [140][407/407] coco/AP: 0.727311 coco/AP .5: 0.894734 coco/AP .75: 0.801215 coco/AP (M): 0.695418 coco/AP (L): 0.788670 coco/AR: 0.792805 coco/AR .5: 0.934509 coco/AR .75: 0.853117 coco/AR (M): 0.749768 coco/AR (L): 0.852471 2022/10/12 23:27:01 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/liqikai/openmmlab/pt112cu113py38/mmpose/work_dirs/20221012/rsn2x/best_coco/AP_epoch_130.pth is removed 2022/10/12 23:27:04 - mmengine - INFO - The best checkpoint with 0.7273 coco/AP at 140 epoch is saved to best_coco/AP_epoch_140.pth. 2022/10/12 23:27:30 - mmengine - INFO - Epoch(train) [141][50/586] lr: 5.000000e-03 eta: 5:36:39 time: 0.534175 data_time: 0.072209 memory: 8713 loss_kpt: 203.769611 acc_pose: 0.869969 loss: 203.769611 2022/10/12 23:27:57 - mmengine - INFO - Epoch(train) [141][100/586] lr: 5.000000e-03 eta: 5:36:15 time: 0.529309 data_time: 0.061156 memory: 8713 loss_kpt: 201.922586 acc_pose: 0.892683 loss: 201.922586 2022/10/12 23:28:24 - mmengine - INFO - Epoch(train) [141][150/586] lr: 5.000000e-03 eta: 5:35:52 time: 0.541715 data_time: 0.064475 memory: 8713 loss_kpt: 203.519971 acc_pose: 0.770716 loss: 203.519971 2022/10/12 23:28:51 - mmengine - INFO - Epoch(train) [141][200/586] lr: 5.000000e-03 eta: 5:35:28 time: 0.533016 data_time: 0.062999 memory: 8713 loss_kpt: 204.664034 acc_pose: 0.914351 loss: 204.664034 2022/10/12 23:29:17 - mmengine - INFO - Epoch(train) [141][250/586] lr: 5.000000e-03 eta: 5:35:05 time: 0.537321 data_time: 0.060246 memory: 8713 loss_kpt: 203.309586 acc_pose: 0.819599 loss: 203.309586 2022/10/12 23:29:44 - mmengine - INFO - Epoch(train) [141][300/586] lr: 5.000000e-03 eta: 5:34:41 time: 0.541160 data_time: 0.064325 memory: 8713 loss_kpt: 205.133729 acc_pose: 0.861588 loss: 205.133729 2022/10/12 23:30:12 - mmengine - INFO - Epoch(train) [141][350/586] lr: 5.000000e-03 eta: 5:34:18 time: 0.542722 data_time: 0.061475 memory: 8713 loss_kpt: 203.872095 acc_pose: 0.798083 loss: 203.872095 2022/10/12 23:30:38 - mmengine - INFO - Epoch(train) [141][400/586] lr: 5.000000e-03 eta: 5:33:54 time: 0.532793 data_time: 0.061626 memory: 8713 loss_kpt: 203.487466 acc_pose: 0.837726 loss: 203.487466 2022/10/12 23:31:05 - mmengine - INFO - Epoch(train) [141][450/586] lr: 5.000000e-03 eta: 5:33:30 time: 0.535303 data_time: 0.060096 memory: 8713 loss_kpt: 202.818946 acc_pose: 0.804966 loss: 202.818946 2022/10/12 23:31:31 - mmengine - INFO - Epoch(train) [141][500/586] lr: 5.000000e-03 eta: 5:33:07 time: 0.527794 data_time: 0.062845 memory: 8713 loss_kpt: 203.378974 acc_pose: 0.791682 loss: 203.378974 2022/10/12 23:31:59 - mmengine - INFO - Epoch(train) [141][550/586] lr: 5.000000e-03 eta: 5:32:43 time: 0.544840 data_time: 0.061855 memory: 8713 loss_kpt: 204.259326 acc_pose: 0.836397 loss: 204.259326 2022/10/12 23:32:18 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 23:32:45 - mmengine - INFO - Epoch(train) [142][50/586] lr: 5.000000e-03 eta: 5:31:53 time: 0.536431 data_time: 0.073906 memory: 8713 loss_kpt: 202.830767 acc_pose: 0.861430 loss: 202.830767 2022/10/12 23:33:11 - mmengine - INFO - Epoch(train) [142][100/586] lr: 5.000000e-03 eta: 5:31:29 time: 0.522817 data_time: 0.067986 memory: 8713 loss_kpt: 204.943536 acc_pose: 0.736637 loss: 204.943536 2022/10/12 23:33:37 - mmengine - INFO - Epoch(train) [142][150/586] lr: 5.000000e-03 eta: 5:31:05 time: 0.521488 data_time: 0.066009 memory: 8713 loss_kpt: 203.912812 acc_pose: 0.775373 loss: 203.912812 2022/10/12 23:34:04 - mmengine - INFO - Epoch(train) [142][200/586] lr: 5.000000e-03 eta: 5:30:42 time: 0.535609 data_time: 0.061500 memory: 8713 loss_kpt: 206.480708 acc_pose: 0.775169 loss: 206.480708 2022/10/12 23:34:30 - mmengine - INFO - Epoch(train) [142][250/586] lr: 5.000000e-03 eta: 5:30:18 time: 0.530253 data_time: 0.063626 memory: 8713 loss_kpt: 202.998281 acc_pose: 0.817520 loss: 202.998281 2022/10/12 23:34:57 - mmengine - INFO - Epoch(train) [142][300/586] lr: 5.000000e-03 eta: 5:29:54 time: 0.530518 data_time: 0.066825 memory: 8713 loss_kpt: 205.743969 acc_pose: 0.841909 loss: 205.743969 2022/10/12 23:35:24 - mmengine - INFO - Epoch(train) [142][350/586] lr: 5.000000e-03 eta: 5:29:31 time: 0.547474 data_time: 0.063074 memory: 8713 loss_kpt: 206.275360 acc_pose: 0.806683 loss: 206.275360 2022/10/12 23:35:37 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 23:35:51 - mmengine - INFO - Epoch(train) [142][400/586] lr: 5.000000e-03 eta: 5:29:07 time: 0.545509 data_time: 0.060203 memory: 8713 loss_kpt: 203.083059 acc_pose: 0.866892 loss: 203.083059 2022/10/12 23:36:20 - mmengine - INFO - Epoch(train) [142][450/586] lr: 5.000000e-03 eta: 5:28:44 time: 0.563418 data_time: 0.058573 memory: 8713 loss_kpt: 201.930725 acc_pose: 0.838896 loss: 201.930725 2022/10/12 23:36:47 - mmengine - INFO - Epoch(train) [142][500/586] lr: 5.000000e-03 eta: 5:28:21 time: 0.547385 data_time: 0.056924 memory: 8713 loss_kpt: 200.737976 acc_pose: 0.830118 loss: 200.737976 2022/10/12 23:37:14 - mmengine - INFO - Epoch(train) [142][550/586] lr: 5.000000e-03 eta: 5:27:58 time: 0.543140 data_time: 0.065995 memory: 8713 loss_kpt: 202.995414 acc_pose: 0.870755 loss: 202.995414 2022/10/12 23:37:33 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 23:38:00 - mmengine - INFO - Epoch(train) [143][50/586] lr: 5.000000e-03 eta: 5:27:08 time: 0.538641 data_time: 0.076648 memory: 8713 loss_kpt: 206.550329 acc_pose: 0.718493 loss: 206.550329 2022/10/12 23:38:26 - mmengine - INFO - Epoch(train) [143][100/586] lr: 5.000000e-03 eta: 5:26:44 time: 0.523170 data_time: 0.060762 memory: 8713 loss_kpt: 206.047105 acc_pose: 0.869266 loss: 206.047105 2022/10/12 23:38:53 - mmengine - INFO - Epoch(train) [143][150/586] lr: 5.000000e-03 eta: 5:26:20 time: 0.531488 data_time: 0.064673 memory: 8713 loss_kpt: 204.702932 acc_pose: 0.884591 loss: 204.702932 2022/10/12 23:39:19 - mmengine - INFO - Epoch(train) [143][200/586] lr: 5.000000e-03 eta: 5:25:56 time: 0.525821 data_time: 0.060799 memory: 8713 loss_kpt: 203.897441 acc_pose: 0.785787 loss: 203.897441 2022/10/12 23:39:46 - mmengine - INFO - Epoch(train) [143][250/586] lr: 5.000000e-03 eta: 5:25:32 time: 0.535102 data_time: 0.065802 memory: 8713 loss_kpt: 207.596761 acc_pose: 0.800102 loss: 207.596761 2022/10/12 23:40:12 - mmengine - INFO - Epoch(train) [143][300/586] lr: 5.000000e-03 eta: 5:25:09 time: 0.526987 data_time: 0.063959 memory: 8713 loss_kpt: 204.857238 acc_pose: 0.831714 loss: 204.857238 2022/10/12 23:40:39 - mmengine - INFO - Epoch(train) [143][350/586] lr: 5.000000e-03 eta: 5:24:45 time: 0.529344 data_time: 0.059819 memory: 8713 loss_kpt: 202.801989 acc_pose: 0.826084 loss: 202.801989 2022/10/12 23:41:05 - mmengine - INFO - Epoch(train) [143][400/586] lr: 5.000000e-03 eta: 5:24:21 time: 0.536366 data_time: 0.061830 memory: 8713 loss_kpt: 202.131277 acc_pose: 0.821474 loss: 202.131277 2022/10/12 23:41:32 - mmengine - INFO - Epoch(train) [143][450/586] lr: 5.000000e-03 eta: 5:23:58 time: 0.539488 data_time: 0.064493 memory: 8713 loss_kpt: 200.376930 acc_pose: 0.795084 loss: 200.376930 2022/10/12 23:41:59 - mmengine - INFO - Epoch(train) [143][500/586] lr: 5.000000e-03 eta: 5:23:34 time: 0.531469 data_time: 0.059633 memory: 8713 loss_kpt: 205.606429 acc_pose: 0.815543 loss: 205.606429 2022/10/12 23:42:26 - mmengine - INFO - Epoch(train) [143][550/586] lr: 5.000000e-03 eta: 5:23:10 time: 0.540837 data_time: 0.071352 memory: 8713 loss_kpt: 201.408272 acc_pose: 0.848833 loss: 201.408272 2022/10/12 23:42:45 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 23:43:12 - mmengine - INFO - Epoch(train) [144][50/586] lr: 5.000000e-03 eta: 5:22:20 time: 0.535776 data_time: 0.077076 memory: 8713 loss_kpt: 202.991482 acc_pose: 0.896493 loss: 202.991482 2022/10/12 23:43:38 - mmengine - INFO - Epoch(train) [144][100/586] lr: 5.000000e-03 eta: 5:21:57 time: 0.524838 data_time: 0.070292 memory: 8713 loss_kpt: 203.860469 acc_pose: 0.852818 loss: 203.860469 2022/10/12 23:44:05 - mmengine - INFO - Epoch(train) [144][150/586] lr: 5.000000e-03 eta: 5:21:33 time: 0.528590 data_time: 0.064256 memory: 8713 loss_kpt: 205.029223 acc_pose: 0.882999 loss: 205.029223 2022/10/12 23:44:31 - mmengine - INFO - Epoch(train) [144][200/586] lr: 5.000000e-03 eta: 5:21:09 time: 0.519472 data_time: 0.061025 memory: 8713 loss_kpt: 204.002940 acc_pose: 0.800542 loss: 204.002940 2022/10/12 23:44:32 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 23:44:57 - mmengine - INFO - Epoch(train) [144][250/586] lr: 5.000000e-03 eta: 5:20:45 time: 0.521357 data_time: 0.062967 memory: 8713 loss_kpt: 204.800089 acc_pose: 0.810701 loss: 204.800089 2022/10/12 23:45:23 - mmengine - INFO - Epoch(train) [144][300/586] lr: 5.000000e-03 eta: 5:20:21 time: 0.523963 data_time: 0.064059 memory: 8713 loss_kpt: 202.903538 acc_pose: 0.831867 loss: 202.903538 2022/10/12 23:45:49 - mmengine - INFO - Epoch(train) [144][350/586] lr: 5.000000e-03 eta: 5:19:57 time: 0.529920 data_time: 0.062684 memory: 8713 loss_kpt: 205.728235 acc_pose: 0.858123 loss: 205.728235 2022/10/12 23:46:16 - mmengine - INFO - Epoch(train) [144][400/586] lr: 5.000000e-03 eta: 5:19:33 time: 0.526732 data_time: 0.066781 memory: 8713 loss_kpt: 202.209526 acc_pose: 0.835183 loss: 202.209526 2022/10/12 23:46:42 - mmengine - INFO - Epoch(train) [144][450/586] lr: 5.000000e-03 eta: 5:19:09 time: 0.526428 data_time: 0.061173 memory: 8713 loss_kpt: 200.754277 acc_pose: 0.893458 loss: 200.754277 2022/10/12 23:47:09 - mmengine - INFO - Epoch(train) [144][500/586] lr: 5.000000e-03 eta: 5:18:45 time: 0.534910 data_time: 0.064274 memory: 8713 loss_kpt: 201.073908 acc_pose: 0.818845 loss: 201.073908 2022/10/12 23:47:35 - mmengine - INFO - Epoch(train) [144][550/586] lr: 5.000000e-03 eta: 5:18:21 time: 0.524987 data_time: 0.061938 memory: 8713 loss_kpt: 201.541418 acc_pose: 0.873628 loss: 201.541418 2022/10/12 23:47:54 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 23:48:20 - mmengine - INFO - Epoch(train) [145][50/586] lr: 5.000000e-03 eta: 5:17:31 time: 0.518865 data_time: 0.072450 memory: 8713 loss_kpt: 202.722863 acc_pose: 0.830919 loss: 202.722863 2022/10/12 23:48:46 - mmengine - INFO - Epoch(train) [145][100/586] lr: 5.000000e-03 eta: 5:17:07 time: 0.515538 data_time: 0.068977 memory: 8713 loss_kpt: 207.134052 acc_pose: 0.818349 loss: 207.134052 2022/10/12 23:49:12 - mmengine - INFO - Epoch(train) [145][150/586] lr: 5.000000e-03 eta: 5:16:44 time: 0.532001 data_time: 0.059729 memory: 8713 loss_kpt: 202.844525 acc_pose: 0.889966 loss: 202.844525 2022/10/12 23:49:38 - mmengine - INFO - Epoch(train) [145][200/586] lr: 5.000000e-03 eta: 5:16:19 time: 0.517527 data_time: 0.064071 memory: 8713 loss_kpt: 202.308723 acc_pose: 0.847507 loss: 202.308723 2022/10/12 23:50:05 - mmengine - INFO - Epoch(train) [145][250/586] lr: 5.000000e-03 eta: 5:15:55 time: 0.523288 data_time: 0.063353 memory: 8713 loss_kpt: 201.979818 acc_pose: 0.799624 loss: 201.979818 2022/10/12 23:50:31 - mmengine - INFO - Epoch(train) [145][300/586] lr: 5.000000e-03 eta: 5:15:32 time: 0.527904 data_time: 0.059305 memory: 8713 loss_kpt: 205.949705 acc_pose: 0.850874 loss: 205.949705 2022/10/12 23:50:58 - mmengine - INFO - Epoch(train) [145][350/586] lr: 5.000000e-03 eta: 5:15:08 time: 0.536892 data_time: 0.061090 memory: 8713 loss_kpt: 205.749769 acc_pose: 0.818487 loss: 205.749769 2022/10/12 23:51:25 - mmengine - INFO - Epoch(train) [145][400/586] lr: 5.000000e-03 eta: 5:14:44 time: 0.550966 data_time: 0.056200 memory: 8713 loss_kpt: 204.051021 acc_pose: 0.850686 loss: 204.051021 2022/10/12 23:51:52 - mmengine - INFO - Epoch(train) [145][450/586] lr: 5.000000e-03 eta: 5:14:21 time: 0.531054 data_time: 0.056053 memory: 8713 loss_kpt: 203.729239 acc_pose: 0.789630 loss: 203.729239 2022/10/12 23:52:19 - mmengine - INFO - Epoch(train) [145][500/586] lr: 5.000000e-03 eta: 5:13:57 time: 0.540126 data_time: 0.058277 memory: 8713 loss_kpt: 198.984807 acc_pose: 0.811405 loss: 198.984807 2022/10/12 23:52:46 - mmengine - INFO - Epoch(train) [145][550/586] lr: 5.000000e-03 eta: 5:13:34 time: 0.548816 data_time: 0.055117 memory: 8713 loss_kpt: 204.024203 acc_pose: 0.875711 loss: 204.024203 2022/10/12 23:53:06 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 23:53:23 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 23:53:33 - mmengine - INFO - Epoch(train) [146][50/586] lr: 5.000000e-03 eta: 5:12:45 time: 0.550540 data_time: 0.070885 memory: 8713 loss_kpt: 206.842096 acc_pose: 0.890685 loss: 206.842096 2022/10/12 23:54:00 - mmengine - INFO - Epoch(train) [146][100/586] lr: 5.000000e-03 eta: 5:12:21 time: 0.541107 data_time: 0.058887 memory: 8713 loss_kpt: 204.983414 acc_pose: 0.814345 loss: 204.983414 2022/10/12 23:54:27 - mmengine - INFO - Epoch(train) [146][150/586] lr: 5.000000e-03 eta: 5:11:57 time: 0.536120 data_time: 0.058397 memory: 8713 loss_kpt: 202.911860 acc_pose: 0.821525 loss: 202.911860 2022/10/12 23:54:54 - mmengine - INFO - Epoch(train) [146][200/586] lr: 5.000000e-03 eta: 5:11:33 time: 0.535569 data_time: 0.065569 memory: 8713 loss_kpt: 204.885215 acc_pose: 0.861691 loss: 204.885215 2022/10/12 23:55:21 - mmengine - INFO - Epoch(train) [146][250/586] lr: 5.000000e-03 eta: 5:11:10 time: 0.534578 data_time: 0.059384 memory: 8713 loss_kpt: 205.859244 acc_pose: 0.876072 loss: 205.859244 2022/10/12 23:55:48 - mmengine - INFO - Epoch(train) [146][300/586] lr: 5.000000e-03 eta: 5:10:46 time: 0.543458 data_time: 0.058795 memory: 8713 loss_kpt: 205.389909 acc_pose: 0.837361 loss: 205.389909 2022/10/12 23:56:15 - mmengine - INFO - Epoch(train) [146][350/586] lr: 5.000000e-03 eta: 5:10:23 time: 0.542610 data_time: 0.065826 memory: 8713 loss_kpt: 208.553238 acc_pose: 0.853178 loss: 208.553238 2022/10/12 23:56:42 - mmengine - INFO - Epoch(train) [146][400/586] lr: 5.000000e-03 eta: 5:09:59 time: 0.542304 data_time: 0.059559 memory: 8713 loss_kpt: 202.314421 acc_pose: 0.796134 loss: 202.314421 2022/10/12 23:57:10 - mmengine - INFO - Epoch(train) [146][450/586] lr: 5.000000e-03 eta: 5:09:36 time: 0.558078 data_time: 0.064261 memory: 8713 loss_kpt: 204.437707 acc_pose: 0.866417 loss: 204.437707 2022/10/12 23:57:37 - mmengine - INFO - Epoch(train) [146][500/586] lr: 5.000000e-03 eta: 5:09:12 time: 0.538904 data_time: 0.058323 memory: 8713 loss_kpt: 203.320811 acc_pose: 0.852682 loss: 203.320811 2022/10/12 23:58:04 - mmengine - INFO - Epoch(train) [146][550/586] lr: 5.000000e-03 eta: 5:08:48 time: 0.537567 data_time: 0.059090 memory: 8713 loss_kpt: 201.182672 acc_pose: 0.834769 loss: 201.182672 2022/10/12 23:58:23 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 23:58:50 - mmengine - INFO - Epoch(train) [147][50/586] lr: 5.000000e-03 eta: 5:07:59 time: 0.530418 data_time: 0.072974 memory: 8713 loss_kpt: 199.069505 acc_pose: 0.804961 loss: 199.069505 2022/10/12 23:59:16 - mmengine - INFO - Epoch(train) [147][100/586] lr: 5.000000e-03 eta: 5:07:35 time: 0.525991 data_time: 0.059194 memory: 8713 loss_kpt: 205.622187 acc_pose: 0.842704 loss: 205.622187 2022/10/12 23:59:42 - mmengine - INFO - Epoch(train) [147][150/586] lr: 5.000000e-03 eta: 5:07:11 time: 0.528529 data_time: 0.058949 memory: 8713 loss_kpt: 202.749709 acc_pose: 0.834030 loss: 202.749709 2022/10/13 00:00:08 - mmengine - INFO - Epoch(train) [147][200/586] lr: 5.000000e-03 eta: 5:06:47 time: 0.516047 data_time: 0.059139 memory: 8713 loss_kpt: 203.924815 acc_pose: 0.879707 loss: 203.924815 2022/10/13 00:00:35 - mmengine - INFO - Epoch(train) [147][250/586] lr: 5.000000e-03 eta: 5:06:23 time: 0.531557 data_time: 0.059037 memory: 8713 loss_kpt: 205.034498 acc_pose: 0.843309 loss: 205.034498 2022/10/13 00:01:01 - mmengine - INFO - Epoch(train) [147][300/586] lr: 5.000000e-03 eta: 5:05:59 time: 0.524093 data_time: 0.062100 memory: 8713 loss_kpt: 206.710241 acc_pose: 0.828380 loss: 206.710241 2022/10/13 00:01:27 - mmengine - INFO - Epoch(train) [147][350/586] lr: 5.000000e-03 eta: 5:05:35 time: 0.519434 data_time: 0.060960 memory: 8713 loss_kpt: 205.838999 acc_pose: 0.800452 loss: 205.838999 2022/10/13 00:01:53 - mmengine - INFO - Epoch(train) [147][400/586] lr: 5.000000e-03 eta: 5:05:11 time: 0.522881 data_time: 0.058069 memory: 8713 loss_kpt: 203.839681 acc_pose: 0.801620 loss: 203.839681 2022/10/13 00:02:16 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 00:02:19 - mmengine - INFO - Epoch(train) [147][450/586] lr: 5.000000e-03 eta: 5:04:47 time: 0.527047 data_time: 0.062519 memory: 8713 loss_kpt: 204.021265 acc_pose: 0.825052 loss: 204.021265 2022/10/13 00:02:46 - mmengine - INFO - Epoch(train) [147][500/586] lr: 5.000000e-03 eta: 5:04:23 time: 0.533254 data_time: 0.059967 memory: 8713 loss_kpt: 202.074246 acc_pose: 0.853237 loss: 202.074246 2022/10/13 00:03:13 - mmengine - INFO - Epoch(train) [147][550/586] lr: 5.000000e-03 eta: 5:03:59 time: 0.529829 data_time: 0.058511 memory: 8713 loss_kpt: 201.826097 acc_pose: 0.870811 loss: 201.826097 2022/10/13 00:03:31 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 00:03:58 - mmengine - INFO - Epoch(train) [148][50/586] lr: 5.000000e-03 eta: 5:03:10 time: 0.535054 data_time: 0.076081 memory: 8713 loss_kpt: 201.707514 acc_pose: 0.806879 loss: 201.707514 2022/10/13 00:04:24 - mmengine - INFO - Epoch(train) [148][100/586] lr: 5.000000e-03 eta: 5:02:46 time: 0.522618 data_time: 0.062466 memory: 8713 loss_kpt: 202.029724 acc_pose: 0.883536 loss: 202.029724 2022/10/13 00:04:51 - mmengine - INFO - Epoch(train) [148][150/586] lr: 5.000000e-03 eta: 5:02:22 time: 0.526898 data_time: 0.059838 memory: 8713 loss_kpt: 205.588037 acc_pose: 0.866717 loss: 205.588037 2022/10/13 00:05:17 - mmengine - INFO - Epoch(train) [148][200/586] lr: 5.000000e-03 eta: 5:01:58 time: 0.529371 data_time: 0.058167 memory: 8713 loss_kpt: 200.770790 acc_pose: 0.805800 loss: 200.770790 2022/10/13 00:05:44 - mmengine - INFO - Epoch(train) [148][250/586] lr: 5.000000e-03 eta: 5:01:34 time: 0.526747 data_time: 0.062145 memory: 8713 loss_kpt: 200.560171 acc_pose: 0.875057 loss: 200.560171 2022/10/13 00:06:10 - mmengine - INFO - Epoch(train) [148][300/586] lr: 5.000000e-03 eta: 5:01:10 time: 0.533718 data_time: 0.057423 memory: 8713 loss_kpt: 201.360748 acc_pose: 0.842217 loss: 201.360748 2022/10/13 00:06:38 - mmengine - INFO - Epoch(train) [148][350/586] lr: 5.000000e-03 eta: 5:00:47 time: 0.560208 data_time: 0.059421 memory: 8713 loss_kpt: 199.942336 acc_pose: 0.839371 loss: 199.942336 2022/10/13 00:07:06 - mmengine - INFO - Epoch(train) [148][400/586] lr: 5.000000e-03 eta: 5:00:24 time: 0.549034 data_time: 0.065381 memory: 8713 loss_kpt: 200.780088 acc_pose: 0.851631 loss: 200.780088 2022/10/13 00:07:33 - mmengine - INFO - Epoch(train) [148][450/586] lr: 5.000000e-03 eta: 5:00:00 time: 0.535947 data_time: 0.065418 memory: 8713 loss_kpt: 201.895159 acc_pose: 0.844598 loss: 201.895159 2022/10/13 00:08:00 - mmengine - INFO - Epoch(train) [148][500/586] lr: 5.000000e-03 eta: 4:59:36 time: 0.544918 data_time: 0.064520 memory: 8713 loss_kpt: 205.969024 acc_pose: 0.800142 loss: 205.969024 2022/10/13 00:08:28 - mmengine - INFO - Epoch(train) [148][550/586] lr: 5.000000e-03 eta: 4:59:13 time: 0.558820 data_time: 0.065734 memory: 8713 loss_kpt: 203.444998 acc_pose: 0.839335 loss: 203.444998 2022/10/13 00:08:47 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 00:09:14 - mmengine - INFO - Epoch(train) [149][50/586] lr: 5.000000e-03 eta: 4:58:24 time: 0.536884 data_time: 0.070433 memory: 8713 loss_kpt: 204.183055 acc_pose: 0.834695 loss: 204.183055 2022/10/13 00:09:40 - mmengine - INFO - Epoch(train) [149][100/586] lr: 5.000000e-03 eta: 4:58:00 time: 0.519927 data_time: 0.060850 memory: 8713 loss_kpt: 198.125149 acc_pose: 0.826009 loss: 198.125149 2022/10/13 00:10:06 - mmengine - INFO - Epoch(train) [149][150/586] lr: 5.000000e-03 eta: 4:57:36 time: 0.517352 data_time: 0.066375 memory: 8713 loss_kpt: 203.299503 acc_pose: 0.876723 loss: 203.299503 2022/10/13 00:10:32 - mmengine - INFO - Epoch(train) [149][200/586] lr: 5.000000e-03 eta: 4:57:11 time: 0.511719 data_time: 0.062450 memory: 8713 loss_kpt: 200.913572 acc_pose: 0.866625 loss: 200.913572 2022/10/13 00:10:58 - mmengine - INFO - Epoch(train) [149][250/586] lr: 5.000000e-03 eta: 4:56:47 time: 0.533061 data_time: 0.064548 memory: 8713 loss_kpt: 205.373997 acc_pose: 0.816891 loss: 205.373997 2022/10/13 00:11:09 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 00:11:24 - mmengine - INFO - Epoch(train) [149][300/586] lr: 5.000000e-03 eta: 4:56:23 time: 0.511982 data_time: 0.059898 memory: 8713 loss_kpt: 203.261927 acc_pose: 0.853860 loss: 203.261927 2022/10/13 00:11:49 - mmengine - INFO - Epoch(train) [149][350/586] lr: 5.000000e-03 eta: 4:55:59 time: 0.511645 data_time: 0.060276 memory: 8713 loss_kpt: 205.683741 acc_pose: 0.803484 loss: 205.683741 2022/10/13 00:12:15 - mmengine - INFO - Epoch(train) [149][400/586] lr: 5.000000e-03 eta: 4:55:35 time: 0.519842 data_time: 0.061830 memory: 8713 loss_kpt: 202.464757 acc_pose: 0.780626 loss: 202.464757 2022/10/13 00:12:41 - mmengine - INFO - Epoch(train) [149][450/586] lr: 5.000000e-03 eta: 4:55:10 time: 0.513836 data_time: 0.061416 memory: 8713 loss_kpt: 202.398196 acc_pose: 0.870956 loss: 202.398196 2022/10/13 00:13:07 - mmengine - INFO - Epoch(train) [149][500/586] lr: 5.000000e-03 eta: 4:54:46 time: 0.510466 data_time: 0.060013 memory: 8713 loss_kpt: 204.908025 acc_pose: 0.825133 loss: 204.908025 2022/10/13 00:13:33 - mmengine - INFO - Epoch(train) [149][550/586] lr: 5.000000e-03 eta: 4:54:22 time: 0.515591 data_time: 0.060672 memory: 8713 loss_kpt: 197.456382 acc_pose: 0.863138 loss: 197.456382 2022/10/13 00:13:51 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 00:14:18 - mmengine - INFO - Epoch(train) [150][50/586] lr: 5.000000e-03 eta: 4:53:33 time: 0.542537 data_time: 0.071180 memory: 8713 loss_kpt: 204.293381 acc_pose: 0.745874 loss: 204.293381 2022/10/13 00:14:45 - mmengine - INFO - Epoch(train) [150][100/586] lr: 5.000000e-03 eta: 4:53:09 time: 0.526864 data_time: 0.057047 memory: 8713 loss_kpt: 203.160643 acc_pose: 0.810906 loss: 203.160643 2022/10/13 00:15:11 - mmengine - INFO - Epoch(train) [150][150/586] lr: 5.000000e-03 eta: 4:52:45 time: 0.529329 data_time: 0.056518 memory: 8713 loss_kpt: 200.719060 acc_pose: 0.824566 loss: 200.719060 2022/10/13 00:15:38 - mmengine - INFO - Epoch(train) [150][200/586] lr: 5.000000e-03 eta: 4:52:22 time: 0.545125 data_time: 0.057078 memory: 8713 loss_kpt: 199.629030 acc_pose: 0.815505 loss: 199.629030 2022/10/13 00:16:05 - mmengine - INFO - Epoch(train) [150][250/586] lr: 5.000000e-03 eta: 4:51:58 time: 0.539731 data_time: 0.055298 memory: 8713 loss_kpt: 205.614499 acc_pose: 0.838662 loss: 205.614499 2022/10/13 00:16:32 - mmengine - INFO - Epoch(train) [150][300/586] lr: 5.000000e-03 eta: 4:51:34 time: 0.535037 data_time: 0.055143 memory: 8713 loss_kpt: 203.674312 acc_pose: 0.802707 loss: 203.674312 2022/10/13 00:17:00 - mmengine - INFO - Epoch(train) [150][350/586] lr: 5.000000e-03 eta: 4:51:10 time: 0.549174 data_time: 0.057636 memory: 8713 loss_kpt: 203.717699 acc_pose: 0.867202 loss: 203.717699 2022/10/13 00:17:26 - mmengine - INFO - Epoch(train) [150][400/586] lr: 5.000000e-03 eta: 4:50:46 time: 0.528612 data_time: 0.057461 memory: 8713 loss_kpt: 208.602576 acc_pose: 0.809803 loss: 208.602576 2022/10/13 00:17:53 - mmengine - INFO - Epoch(train) [150][450/586] lr: 5.000000e-03 eta: 4:50:23 time: 0.539194 data_time: 0.063619 memory: 8713 loss_kpt: 203.226568 acc_pose: 0.814588 loss: 203.226568 2022/10/13 00:18:20 - mmengine - INFO - Epoch(train) [150][500/586] lr: 5.000000e-03 eta: 4:49:59 time: 0.530128 data_time: 0.061728 memory: 8713 loss_kpt: 201.951422 acc_pose: 0.848908 loss: 201.951422 2022/10/13 00:18:46 - mmengine - INFO - Epoch(train) [150][550/586] lr: 5.000000e-03 eta: 4:49:35 time: 0.529119 data_time: 0.060837 memory: 8713 loss_kpt: 201.220060 acc_pose: 0.812743 loss: 201.220060 2022/10/13 00:19:05 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 00:19:05 - mmengine - INFO - Saving checkpoint at 150 epochs 2022/10/13 00:19:19 - mmengine - INFO - Epoch(val) [150][50/407] eta: 0:01:10 time: 0.198170 data_time: 0.012453 memory: 8713 2022/10/13 00:19:28 - mmengine - INFO - Epoch(val) [150][100/407] eta: 0:00:59 time: 0.192206 data_time: 0.007827 memory: 1759 2022/10/13 00:19:38 - mmengine - INFO - Epoch(val) [150][150/407] eta: 0:00:49 time: 0.193103 data_time: 0.008090 memory: 1759 2022/10/13 00:19:47 - mmengine - INFO - Epoch(val) [150][200/407] eta: 0:00:39 time: 0.192809 data_time: 0.008526 memory: 1759 2022/10/13 00:19:57 - mmengine - INFO - Epoch(val) [150][250/407] eta: 0:00:30 time: 0.196440 data_time: 0.011932 memory: 1759 2022/10/13 00:20:07 - mmengine - INFO - Epoch(val) [150][300/407] eta: 0:00:20 time: 0.191004 data_time: 0.007921 memory: 1759 2022/10/13 00:20:17 - mmengine - INFO - Epoch(val) [150][350/407] eta: 0:00:11 time: 0.193931 data_time: 0.007795 memory: 1759 2022/10/13 00:20:26 - mmengine - INFO - Epoch(val) [150][400/407] eta: 0:00:01 time: 0.191098 data_time: 0.008092 memory: 1759 2022/10/13 00:20:40 - mmengine - INFO - Evaluating CocoMetric... 2022/10/13 00:20:56 - mmengine - INFO - Epoch(val) [150][407/407] coco/AP: 0.728495 coco/AP .5: 0.893984 coco/AP .75: 0.801540 coco/AP (M): 0.696969 coco/AP (L): 0.788688 coco/AR: 0.793703 coco/AR .5: 0.934351 coco/AR .75: 0.854849 coco/AR (M): 0.750997 coco/AR (L): 0.852657 2022/10/13 00:20:56 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/liqikai/openmmlab/pt112cu113py38/mmpose/work_dirs/20221012/rsn2x/best_coco/AP_epoch_140.pth is removed 2022/10/13 00:20:59 - mmengine - INFO - The best checkpoint with 0.7285 coco/AP at 150 epoch is saved to best_coco/AP_epoch_150.pth. 2022/10/13 00:21:25 - mmengine - INFO - Epoch(train) [151][50/586] lr: 5.000000e-03 eta: 4:48:46 time: 0.534543 data_time: 0.072273 memory: 8713 loss_kpt: 206.463964 acc_pose: 0.792269 loss: 206.463964 2022/10/13 00:21:51 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 00:21:51 - mmengine - INFO - Epoch(train) [151][100/586] lr: 5.000000e-03 eta: 4:48:22 time: 0.520778 data_time: 0.064006 memory: 8713 loss_kpt: 201.201131 acc_pose: 0.889639 loss: 201.201131 2022/10/13 00:22:18 - mmengine - INFO - Epoch(train) [151][150/586] lr: 5.000000e-03 eta: 4:47:58 time: 0.529066 data_time: 0.058350 memory: 8713 loss_kpt: 204.348120 acc_pose: 0.893010 loss: 204.348120 2022/10/13 00:22:44 - mmengine - INFO - Epoch(train) [151][200/586] lr: 5.000000e-03 eta: 4:47:34 time: 0.523778 data_time: 0.057800 memory: 8713 loss_kpt: 200.345487 acc_pose: 0.874534 loss: 200.345487 2022/10/13 00:23:10 - mmengine - INFO - Epoch(train) [151][250/586] lr: 5.000000e-03 eta: 4:47:10 time: 0.522085 data_time: 0.055776 memory: 8713 loss_kpt: 201.283995 acc_pose: 0.840320 loss: 201.283995 2022/10/13 00:23:36 - mmengine - INFO - Epoch(train) [151][300/586] lr: 5.000000e-03 eta: 4:46:46 time: 0.516301 data_time: 0.060356 memory: 8713 loss_kpt: 201.060064 acc_pose: 0.883564 loss: 201.060064 2022/10/13 00:24:02 - mmengine - INFO - Epoch(train) [151][350/586] lr: 5.000000e-03 eta: 4:46:22 time: 0.526889 data_time: 0.058880 memory: 8713 loss_kpt: 203.612976 acc_pose: 0.845190 loss: 203.612976 2022/10/13 00:24:29 - mmengine - INFO - Epoch(train) [151][400/586] lr: 5.000000e-03 eta: 4:45:57 time: 0.525831 data_time: 0.054953 memory: 8713 loss_kpt: 195.946515 acc_pose: 0.782299 loss: 195.946515 2022/10/13 00:24:55 - mmengine - INFO - Epoch(train) [151][450/586] lr: 5.000000e-03 eta: 4:45:33 time: 0.519429 data_time: 0.058533 memory: 8713 loss_kpt: 205.001991 acc_pose: 0.844150 loss: 205.001991 2022/10/13 00:25:21 - mmengine - INFO - Epoch(train) [151][500/586] lr: 5.000000e-03 eta: 4:45:09 time: 0.522590 data_time: 0.054037 memory: 8713 loss_kpt: 204.052049 acc_pose: 0.908574 loss: 204.052049 2022/10/13 00:25:47 - mmengine - INFO - Epoch(train) [151][550/586] lr: 5.000000e-03 eta: 4:44:45 time: 0.519123 data_time: 0.056753 memory: 8713 loss_kpt: 203.197449 acc_pose: 0.857175 loss: 203.197449 2022/10/13 00:26:05 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 00:26:32 - mmengine - INFO - Epoch(train) [152][50/586] lr: 5.000000e-03 eta: 4:43:57 time: 0.544866 data_time: 0.074190 memory: 8713 loss_kpt: 204.974026 acc_pose: 0.879097 loss: 204.974026 2022/10/13 00:26:58 - mmengine - INFO - Epoch(train) [152][100/586] lr: 5.000000e-03 eta: 4:43:33 time: 0.524698 data_time: 0.054208 memory: 8713 loss_kpt: 204.764196 acc_pose: 0.830520 loss: 204.764196 2022/10/13 00:27:25 - mmengine - INFO - Epoch(train) [152][150/586] lr: 5.000000e-03 eta: 4:43:09 time: 0.534067 data_time: 0.059734 memory: 8713 loss_kpt: 206.073626 acc_pose: 0.855843 loss: 206.073626 2022/10/13 00:27:52 - mmengine - INFO - Epoch(train) [152][200/586] lr: 5.000000e-03 eta: 4:42:45 time: 0.535159 data_time: 0.053859 memory: 8713 loss_kpt: 198.878047 acc_pose: 0.732295 loss: 198.878047 2022/10/13 00:28:19 - mmengine - INFO - Epoch(train) [152][250/586] lr: 5.000000e-03 eta: 4:42:21 time: 0.539600 data_time: 0.060169 memory: 8713 loss_kpt: 199.942529 acc_pose: 0.900968 loss: 199.942529 2022/10/13 00:28:45 - mmengine - INFO - Epoch(train) [152][300/586] lr: 5.000000e-03 eta: 4:41:57 time: 0.531858 data_time: 0.059203 memory: 8713 loss_kpt: 199.002957 acc_pose: 0.778918 loss: 199.002957 2022/10/13 00:29:14 - mmengine - INFO - Epoch(train) [152][350/586] lr: 5.000000e-03 eta: 4:41:34 time: 0.561586 data_time: 0.059371 memory: 8713 loss_kpt: 201.416951 acc_pose: 0.864919 loss: 201.416951 2022/10/13 00:29:41 - mmengine - INFO - Epoch(train) [152][400/586] lr: 5.000000e-03 eta: 4:41:10 time: 0.557054 data_time: 0.062158 memory: 8713 loss_kpt: 199.333639 acc_pose: 0.851340 loss: 199.333639 2022/10/13 00:30:11 - mmengine - INFO - Epoch(train) [152][450/586] lr: 5.000000e-03 eta: 4:40:47 time: 0.584899 data_time: 0.062318 memory: 8713 loss_kpt: 206.519219 acc_pose: 0.867994 loss: 206.519219 2022/10/13 00:30:39 - mmengine - INFO - Epoch(train) [152][500/586] lr: 5.000000e-03 eta: 4:40:24 time: 0.562334 data_time: 0.057780 memory: 8713 loss_kpt: 204.220607 acc_pose: 0.841544 loss: 204.220607 2022/10/13 00:30:47 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 00:31:07 - mmengine - INFO - Epoch(train) [152][550/586] lr: 5.000000e-03 eta: 4:40:01 time: 0.570887 data_time: 0.066549 memory: 8713 loss_kpt: 203.785636 acc_pose: 0.862295 loss: 203.785636 2022/10/13 00:31:27 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 00:31:54 - mmengine - INFO - Epoch(train) [153][50/586] lr: 5.000000e-03 eta: 4:39:12 time: 0.535276 data_time: 0.065788 memory: 8713 loss_kpt: 200.879148 acc_pose: 0.831828 loss: 200.879148 2022/10/13 00:32:20 - mmengine - INFO - Epoch(train) [153][100/586] lr: 5.000000e-03 eta: 4:38:48 time: 0.526161 data_time: 0.058207 memory: 8713 loss_kpt: 201.993757 acc_pose: 0.876654 loss: 201.993757 2022/10/13 00:32:47 - mmengine - INFO - Epoch(train) [153][150/586] lr: 5.000000e-03 eta: 4:38:24 time: 0.540536 data_time: 0.058131 memory: 8713 loss_kpt: 199.443293 acc_pose: 0.802705 loss: 199.443293 2022/10/13 00:33:14 - mmengine - INFO - Epoch(train) [153][200/586] lr: 5.000000e-03 eta: 4:38:01 time: 0.536634 data_time: 0.058232 memory: 8713 loss_kpt: 202.504528 acc_pose: 0.867339 loss: 202.504528 2022/10/13 00:33:41 - mmengine - INFO - Epoch(train) [153][250/586] lr: 5.000000e-03 eta: 4:37:37 time: 0.544649 data_time: 0.054903 memory: 8713 loss_kpt: 203.878628 acc_pose: 0.869217 loss: 203.878628 2022/10/13 00:34:08 - mmengine - INFO - Epoch(train) [153][300/586] lr: 5.000000e-03 eta: 4:37:13 time: 0.533779 data_time: 0.055820 memory: 8713 loss_kpt: 207.322619 acc_pose: 0.706148 loss: 207.322619 2022/10/13 00:34:35 - mmengine - INFO - Epoch(train) [153][350/586] lr: 5.000000e-03 eta: 4:36:49 time: 0.546215 data_time: 0.054822 memory: 8713 loss_kpt: 203.263559 acc_pose: 0.855648 loss: 203.263559 2022/10/13 00:35:03 - mmengine - INFO - Epoch(train) [153][400/586] lr: 5.000000e-03 eta: 4:36:26 time: 0.546785 data_time: 0.054108 memory: 8713 loss_kpt: 202.624798 acc_pose: 0.829083 loss: 202.624798 2022/10/13 00:35:29 - mmengine - INFO - Epoch(train) [153][450/586] lr: 5.000000e-03 eta: 4:36:01 time: 0.529591 data_time: 0.059096 memory: 8713 loss_kpt: 201.320845 acc_pose: 0.829861 loss: 201.320845 2022/10/13 00:35:56 - mmengine - INFO - Epoch(train) [153][500/586] lr: 5.000000e-03 eta: 4:35:38 time: 0.533964 data_time: 0.059021 memory: 8713 loss_kpt: 203.044647 acc_pose: 0.781306 loss: 203.044647 2022/10/13 00:36:22 - mmengine - INFO - Epoch(train) [153][550/586] lr: 5.000000e-03 eta: 4:35:13 time: 0.522749 data_time: 0.056837 memory: 8713 loss_kpt: 203.206183 acc_pose: 0.891381 loss: 203.206183 2022/10/13 00:36:40 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 00:37:07 - mmengine - INFO - Epoch(train) [154][50/586] lr: 5.000000e-03 eta: 4:34:25 time: 0.538411 data_time: 0.064270 memory: 8713 loss_kpt: 200.607772 acc_pose: 0.888232 loss: 200.607772 2022/10/13 00:37:33 - mmengine - INFO - Epoch(train) [154][100/586] lr: 5.000000e-03 eta: 4:34:01 time: 0.518584 data_time: 0.053894 memory: 8713 loss_kpt: 203.329207 acc_pose: 0.846046 loss: 203.329207 2022/10/13 00:37:59 - mmengine - INFO - Epoch(train) [154][150/586] lr: 5.000000e-03 eta: 4:33:37 time: 0.526636 data_time: 0.057184 memory: 8713 loss_kpt: 202.624467 acc_pose: 0.839014 loss: 202.624467 2022/10/13 00:38:26 - mmengine - INFO - Epoch(train) [154][200/586] lr: 5.000000e-03 eta: 4:33:13 time: 0.529421 data_time: 0.055082 memory: 8713 loss_kpt: 197.186599 acc_pose: 0.904635 loss: 197.186599 2022/10/13 00:38:52 - mmengine - INFO - Epoch(train) [154][250/586] lr: 5.000000e-03 eta: 4:32:49 time: 0.521798 data_time: 0.053998 memory: 8713 loss_kpt: 196.079024 acc_pose: 0.828125 loss: 196.079024 2022/10/13 00:39:18 - mmengine - INFO - Epoch(train) [154][300/586] lr: 5.000000e-03 eta: 4:32:24 time: 0.519512 data_time: 0.057130 memory: 8713 loss_kpt: 201.094029 acc_pose: 0.866605 loss: 201.094029 2022/10/13 00:39:40 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 00:39:44 - mmengine - INFO - Epoch(train) [154][350/586] lr: 5.000000e-03 eta: 4:32:00 time: 0.518573 data_time: 0.057006 memory: 8713 loss_kpt: 199.703742 acc_pose: 0.817491 loss: 199.703742 2022/10/13 00:40:10 - mmengine - INFO - Epoch(train) [154][400/586] lr: 5.000000e-03 eta: 4:31:36 time: 0.516464 data_time: 0.052377 memory: 8713 loss_kpt: 203.189013 acc_pose: 0.822643 loss: 203.189013 2022/10/13 00:40:35 - mmengine - INFO - Epoch(train) [154][450/586] lr: 5.000000e-03 eta: 4:31:12 time: 0.515201 data_time: 0.060402 memory: 8713 loss_kpt: 202.155109 acc_pose: 0.785341 loss: 202.155109 2022/10/13 00:41:01 - mmengine - INFO - Epoch(train) [154][500/586] lr: 5.000000e-03 eta: 4:30:47 time: 0.519378 data_time: 0.054473 memory: 8713 loss_kpt: 200.505986 acc_pose: 0.837524 loss: 200.505986 2022/10/13 00:41:27 - mmengine - INFO - Epoch(train) [154][550/586] lr: 5.000000e-03 eta: 4:30:23 time: 0.519998 data_time: 0.058456 memory: 8713 loss_kpt: 205.347805 acc_pose: 0.901260 loss: 205.347805 2022/10/13 00:41:46 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 00:42:12 - mmengine - INFO - Epoch(train) [155][50/586] lr: 5.000000e-03 eta: 4:29:35 time: 0.523699 data_time: 0.067924 memory: 8713 loss_kpt: 201.650728 acc_pose: 0.771747 loss: 201.650728 2022/10/13 00:42:39 - mmengine - INFO - Epoch(train) [155][100/586] lr: 5.000000e-03 eta: 4:29:11 time: 0.524319 data_time: 0.053664 memory: 8713 loss_kpt: 204.122846 acc_pose: 0.810782 loss: 204.122846 2022/10/13 00:43:05 - mmengine - INFO - Epoch(train) [155][150/586] lr: 5.000000e-03 eta: 4:28:47 time: 0.534386 data_time: 0.063248 memory: 8713 loss_kpt: 202.590883 acc_pose: 0.897732 loss: 202.590883 2022/10/13 00:43:32 - mmengine - INFO - Epoch(train) [155][200/586] lr: 5.000000e-03 eta: 4:28:23 time: 0.539663 data_time: 0.061237 memory: 8713 loss_kpt: 201.476012 acc_pose: 0.889997 loss: 201.476012 2022/10/13 00:44:00 - mmengine - INFO - Epoch(train) [155][250/586] lr: 5.000000e-03 eta: 4:27:59 time: 0.547720 data_time: 0.058733 memory: 8713 loss_kpt: 202.985123 acc_pose: 0.820111 loss: 202.985123 2022/10/13 00:44:27 - mmengine - INFO - Epoch(train) [155][300/586] lr: 5.000000e-03 eta: 4:27:35 time: 0.543394 data_time: 0.056715 memory: 8713 loss_kpt: 201.659413 acc_pose: 0.873869 loss: 201.659413 2022/10/13 00:44:54 - mmengine - INFO - Epoch(train) [155][350/586] lr: 5.000000e-03 eta: 4:27:11 time: 0.536357 data_time: 0.055020 memory: 8713 loss_kpt: 200.032537 acc_pose: 0.830270 loss: 200.032537 2022/10/13 00:45:21 - mmengine - INFO - Epoch(train) [155][400/586] lr: 5.000000e-03 eta: 4:26:47 time: 0.534101 data_time: 0.056511 memory: 8713 loss_kpt: 199.404185 acc_pose: 0.865306 loss: 199.404185 2022/10/13 00:45:48 - mmengine - INFO - Epoch(train) [155][450/586] lr: 5.000000e-03 eta: 4:26:24 time: 0.542738 data_time: 0.059976 memory: 8713 loss_kpt: 200.950557 acc_pose: 0.809072 loss: 200.950557 2022/10/13 00:46:15 - mmengine - INFO - Epoch(train) [155][500/586] lr: 5.000000e-03 eta: 4:26:00 time: 0.542325 data_time: 0.056526 memory: 8713 loss_kpt: 203.286510 acc_pose: 0.921344 loss: 203.286510 2022/10/13 00:46:41 - mmengine - INFO - Epoch(train) [155][550/586] lr: 5.000000e-03 eta: 4:25:36 time: 0.532446 data_time: 0.054328 memory: 8713 loss_kpt: 202.276728 acc_pose: 0.846203 loss: 202.276728 2022/10/13 00:47:01 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 00:47:28 - mmengine - INFO - Epoch(train) [156][50/586] lr: 5.000000e-03 eta: 4:24:48 time: 0.539652 data_time: 0.072509 memory: 8713 loss_kpt: 200.748433 acc_pose: 0.839568 loss: 200.748433 2022/10/13 00:47:54 - mmengine - INFO - Epoch(train) [156][100/586] lr: 5.000000e-03 eta: 4:24:24 time: 0.533415 data_time: 0.056446 memory: 8713 loss_kpt: 205.702157 acc_pose: 0.829308 loss: 205.702157 2022/10/13 00:48:21 - mmengine - INFO - Epoch(train) [156][150/586] lr: 5.000000e-03 eta: 4:24:00 time: 0.541213 data_time: 0.060419 memory: 8713 loss_kpt: 201.628619 acc_pose: 0.832044 loss: 201.628619 2022/10/13 00:48:32 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 00:48:48 - mmengine - INFO - Epoch(train) [156][200/586] lr: 5.000000e-03 eta: 4:23:36 time: 0.533148 data_time: 0.059204 memory: 8713 loss_kpt: 204.650497 acc_pose: 0.776717 loss: 204.650497 2022/10/13 00:49:15 - mmengine - INFO - Epoch(train) [156][250/586] lr: 5.000000e-03 eta: 4:23:12 time: 0.541897 data_time: 0.060406 memory: 8713 loss_kpt: 203.067104 acc_pose: 0.863381 loss: 203.067104 2022/10/13 00:49:42 - mmengine - INFO - Epoch(train) [156][300/586] lr: 5.000000e-03 eta: 4:22:48 time: 0.526695 data_time: 0.055832 memory: 8713 loss_kpt: 202.542437 acc_pose: 0.723308 loss: 202.542437 2022/10/13 00:50:09 - mmengine - INFO - Epoch(train) [156][350/586] lr: 5.000000e-03 eta: 4:22:24 time: 0.547395 data_time: 0.062398 memory: 8713 loss_kpt: 203.287795 acc_pose: 0.820353 loss: 203.287795 2022/10/13 00:50:36 - mmengine - INFO - Epoch(train) [156][400/586] lr: 5.000000e-03 eta: 4:22:00 time: 0.539231 data_time: 0.059424 memory: 8713 loss_kpt: 204.180258 acc_pose: 0.767295 loss: 204.180258 2022/10/13 00:51:03 - mmengine - INFO - Epoch(train) [156][450/586] lr: 5.000000e-03 eta: 4:21:37 time: 0.546208 data_time: 0.058439 memory: 8713 loss_kpt: 203.176572 acc_pose: 0.799203 loss: 203.176572 2022/10/13 00:51:30 - mmengine - INFO - Epoch(train) [156][500/586] lr: 5.000000e-03 eta: 4:21:13 time: 0.537763 data_time: 0.056771 memory: 8713 loss_kpt: 202.040272 acc_pose: 0.853083 loss: 202.040272 2022/10/13 00:51:57 - mmengine - INFO - Epoch(train) [156][550/586] lr: 5.000000e-03 eta: 4:20:49 time: 0.540144 data_time: 0.059443 memory: 8713 loss_kpt: 202.703979 acc_pose: 0.808735 loss: 202.703979 2022/10/13 00:52:16 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 00:52:43 - mmengine - INFO - Epoch(train) [157][50/586] lr: 5.000000e-03 eta: 4:20:01 time: 0.541195 data_time: 0.064628 memory: 8713 loss_kpt: 202.527667 acc_pose: 0.837464 loss: 202.527667 2022/10/13 00:53:10 - mmengine - INFO - Epoch(train) [157][100/586] lr: 5.000000e-03 eta: 4:19:37 time: 0.527186 data_time: 0.057297 memory: 8713 loss_kpt: 204.081663 acc_pose: 0.842043 loss: 204.081663 2022/10/13 00:53:37 - mmengine - INFO - Epoch(train) [157][150/586] lr: 5.000000e-03 eta: 4:19:13 time: 0.540697 data_time: 0.059948 memory: 8713 loss_kpt: 201.084543 acc_pose: 0.841350 loss: 201.084543 2022/10/13 00:54:03 - mmengine - INFO - Epoch(train) [157][200/586] lr: 5.000000e-03 eta: 4:18:49 time: 0.530257 data_time: 0.057012 memory: 8713 loss_kpt: 200.210868 acc_pose: 0.876131 loss: 200.210868 2022/10/13 00:54:30 - mmengine - INFO - Epoch(train) [157][250/586] lr: 5.000000e-03 eta: 4:18:25 time: 0.527520 data_time: 0.062122 memory: 8713 loss_kpt: 204.487279 acc_pose: 0.867077 loss: 204.487279 2022/10/13 00:54:56 - mmengine - INFO - Epoch(train) [157][300/586] lr: 5.000000e-03 eta: 4:18:01 time: 0.531341 data_time: 0.059832 memory: 8713 loss_kpt: 205.003175 acc_pose: 0.866314 loss: 205.003175 2022/10/13 00:55:23 - mmengine - INFO - Epoch(train) [157][350/586] lr: 5.000000e-03 eta: 4:17:37 time: 0.536658 data_time: 0.056896 memory: 8713 loss_kpt: 202.380273 acc_pose: 0.842074 loss: 202.380273 2022/10/13 00:55:50 - mmengine - INFO - Epoch(train) [157][400/586] lr: 5.000000e-03 eta: 4:17:13 time: 0.533659 data_time: 0.059138 memory: 8713 loss_kpt: 202.653401 acc_pose: 0.791180 loss: 202.653401 2022/10/13 00:56:17 - mmengine - INFO - Epoch(train) [157][450/586] lr: 5.000000e-03 eta: 4:16:49 time: 0.542588 data_time: 0.059331 memory: 8713 loss_kpt: 200.652285 acc_pose: 0.857786 loss: 200.652285 2022/10/13 00:56:45 - mmengine - INFO - Epoch(train) [157][500/586] lr: 5.000000e-03 eta: 4:16:25 time: 0.554047 data_time: 0.056659 memory: 8713 loss_kpt: 202.173384 acc_pose: 0.843902 loss: 202.173384 2022/10/13 00:57:11 - mmengine - INFO - Epoch(train) [157][550/586] lr: 5.000000e-03 eta: 4:16:01 time: 0.534404 data_time: 0.055896 memory: 8713 loss_kpt: 201.229677 acc_pose: 0.857367 loss: 201.229677 2022/10/13 00:57:30 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 00:57:30 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 00:57:57 - mmengine - INFO - Epoch(train) [158][50/586] lr: 5.000000e-03 eta: 4:15:13 time: 0.537191 data_time: 0.070005 memory: 8713 loss_kpt: 202.451670 acc_pose: 0.757224 loss: 202.451670 2022/10/13 00:58:24 - mmengine - INFO - Epoch(train) [158][100/586] lr: 5.000000e-03 eta: 4:14:49 time: 0.539414 data_time: 0.058094 memory: 8713 loss_kpt: 200.842638 acc_pose: 0.889183 loss: 200.842638 2022/10/13 00:58:51 - mmengine - INFO - Epoch(train) [158][150/586] lr: 5.000000e-03 eta: 4:14:25 time: 0.535989 data_time: 0.058069 memory: 8713 loss_kpt: 203.158362 acc_pose: 0.857615 loss: 203.158362 2022/10/13 00:59:17 - mmengine - INFO - Epoch(train) [158][200/586] lr: 5.000000e-03 eta: 4:14:01 time: 0.522215 data_time: 0.058498 memory: 8713 loss_kpt: 199.098778 acc_pose: 0.827863 loss: 199.098778 2022/10/13 00:59:44 - mmengine - INFO - Epoch(train) [158][250/586] lr: 5.000000e-03 eta: 4:13:37 time: 0.534271 data_time: 0.057930 memory: 8713 loss_kpt: 201.644713 acc_pose: 0.815188 loss: 201.644713 2022/10/13 01:00:10 - mmengine - INFO - Epoch(train) [158][300/586] lr: 5.000000e-03 eta: 4:13:13 time: 0.526524 data_time: 0.055936 memory: 8713 loss_kpt: 202.552550 acc_pose: 0.888588 loss: 202.552550 2022/10/13 01:00:37 - mmengine - INFO - Epoch(train) [158][350/586] lr: 5.000000e-03 eta: 4:12:49 time: 0.528555 data_time: 0.063447 memory: 8713 loss_kpt: 201.825374 acc_pose: 0.845407 loss: 201.825374 2022/10/13 01:01:04 - mmengine - INFO - Epoch(train) [158][400/586] lr: 5.000000e-03 eta: 4:12:25 time: 0.537023 data_time: 0.059337 memory: 8713 loss_kpt: 201.517570 acc_pose: 0.847662 loss: 201.517570 2022/10/13 01:01:30 - mmengine - INFO - Epoch(train) [158][450/586] lr: 5.000000e-03 eta: 4:12:01 time: 0.536539 data_time: 0.061321 memory: 8713 loss_kpt: 199.956494 acc_pose: 0.832580 loss: 199.956494 2022/10/13 01:01:58 - mmengine - INFO - Epoch(train) [158][500/586] lr: 5.000000e-03 eta: 4:11:37 time: 0.547057 data_time: 0.058821 memory: 8713 loss_kpt: 200.086263 acc_pose: 0.761525 loss: 200.086263 2022/10/13 01:02:25 - mmengine - INFO - Epoch(train) [158][550/586] lr: 5.000000e-03 eta: 4:11:13 time: 0.538042 data_time: 0.063938 memory: 8713 loss_kpt: 206.437784 acc_pose: 0.866373 loss: 206.437784 2022/10/13 01:02:44 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 01:03:12 - mmengine - INFO - Epoch(train) [159][50/586] lr: 5.000000e-03 eta: 4:10:26 time: 0.552356 data_time: 0.070978 memory: 8713 loss_kpt: 203.770759 acc_pose: 0.862359 loss: 203.770759 2022/10/13 01:03:38 - mmengine - INFO - Epoch(train) [159][100/586] lr: 5.000000e-03 eta: 4:10:02 time: 0.529497 data_time: 0.062656 memory: 8713 loss_kpt: 201.203857 acc_pose: 0.823970 loss: 201.203857 2022/10/13 01:04:04 - mmengine - INFO - Epoch(train) [159][150/586] lr: 5.000000e-03 eta: 4:09:37 time: 0.523585 data_time: 0.060549 memory: 8713 loss_kpt: 200.847920 acc_pose: 0.801956 loss: 200.847920 2022/10/13 01:04:31 - mmengine - INFO - Epoch(train) [159][200/586] lr: 5.000000e-03 eta: 4:09:14 time: 0.538138 data_time: 0.058662 memory: 8713 loss_kpt: 197.680661 acc_pose: 0.865534 loss: 197.680661 2022/10/13 01:04:58 - mmengine - INFO - Epoch(train) [159][250/586] lr: 5.000000e-03 eta: 4:08:50 time: 0.537912 data_time: 0.056269 memory: 8713 loss_kpt: 203.370221 acc_pose: 0.711337 loss: 203.370221 2022/10/13 01:05:25 - mmengine - INFO - Epoch(train) [159][300/586] lr: 5.000000e-03 eta: 4:08:25 time: 0.532085 data_time: 0.061884 memory: 8713 loss_kpt: 206.896384 acc_pose: 0.839108 loss: 206.896384 2022/10/13 01:05:51 - mmengine - INFO - Epoch(train) [159][350/586] lr: 5.000000e-03 eta: 4:08:01 time: 0.532468 data_time: 0.060862 memory: 8713 loss_kpt: 206.384164 acc_pose: 0.822953 loss: 206.384164 2022/10/13 01:06:18 - mmengine - INFO - Epoch(train) [159][400/586] lr: 5.000000e-03 eta: 4:07:37 time: 0.533291 data_time: 0.065989 memory: 8713 loss_kpt: 206.711008 acc_pose: 0.842210 loss: 206.711008 2022/10/13 01:06:25 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 01:06:45 - mmengine - INFO - Epoch(train) [159][450/586] lr: 5.000000e-03 eta: 4:07:13 time: 0.536761 data_time: 0.058956 memory: 8713 loss_kpt: 200.078976 acc_pose: 0.848268 loss: 200.078976 2022/10/13 01:07:12 - mmengine - INFO - Epoch(train) [159][500/586] lr: 5.000000e-03 eta: 4:06:49 time: 0.532303 data_time: 0.056896 memory: 8713 loss_kpt: 200.945522 acc_pose: 0.865123 loss: 200.945522 2022/10/13 01:07:38 - mmengine - INFO - Epoch(train) [159][550/586] lr: 5.000000e-03 eta: 4:06:25 time: 0.531564 data_time: 0.058283 memory: 8713 loss_kpt: 198.330756 acc_pose: 0.854697 loss: 198.330756 2022/10/13 01:07:57 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 01:08:24 - mmengine - INFO - Epoch(train) [160][50/586] lr: 5.000000e-03 eta: 4:05:38 time: 0.546607 data_time: 0.067083 memory: 8713 loss_kpt: 205.009697 acc_pose: 0.885570 loss: 205.009697 2022/10/13 01:08:51 - mmengine - INFO - Epoch(train) [160][100/586] lr: 5.000000e-03 eta: 4:05:14 time: 0.532283 data_time: 0.058475 memory: 8713 loss_kpt: 202.075438 acc_pose: 0.860264 loss: 202.075438 2022/10/13 01:09:17 - mmengine - INFO - Epoch(train) [160][150/586] lr: 5.000000e-03 eta: 4:04:50 time: 0.530441 data_time: 0.060192 memory: 8713 loss_kpt: 197.227665 acc_pose: 0.803588 loss: 197.227665 2022/10/13 01:09:44 - mmengine - INFO - Epoch(train) [160][200/586] lr: 5.000000e-03 eta: 4:04:25 time: 0.534185 data_time: 0.060491 memory: 8713 loss_kpt: 200.295596 acc_pose: 0.821924 loss: 200.295596 2022/10/13 01:10:11 - mmengine - INFO - Epoch(train) [160][250/586] lr: 5.000000e-03 eta: 4:04:01 time: 0.533453 data_time: 0.062565 memory: 8713 loss_kpt: 202.859337 acc_pose: 0.684849 loss: 202.859337 2022/10/13 01:10:37 - mmengine - INFO - Epoch(train) [160][300/586] lr: 5.000000e-03 eta: 4:03:37 time: 0.527107 data_time: 0.059970 memory: 8713 loss_kpt: 201.290113 acc_pose: 0.793309 loss: 201.290113 2022/10/13 01:11:04 - mmengine - INFO - Epoch(train) [160][350/586] lr: 5.000000e-03 eta: 4:03:13 time: 0.530404 data_time: 0.060890 memory: 8713 loss_kpt: 202.100289 acc_pose: 0.807957 loss: 202.100289 2022/10/13 01:11:30 - mmengine - INFO - Epoch(train) [160][400/586] lr: 5.000000e-03 eta: 4:02:49 time: 0.527760 data_time: 0.058503 memory: 8713 loss_kpt: 198.143068 acc_pose: 0.770322 loss: 198.143068 2022/10/13 01:11:56 - mmengine - INFO - Epoch(train) [160][450/586] lr: 5.000000e-03 eta: 4:02:25 time: 0.525820 data_time: 0.057015 memory: 8713 loss_kpt: 203.012618 acc_pose: 0.786077 loss: 203.012618 2022/10/13 01:12:23 - mmengine - INFO - Epoch(train) [160][500/586] lr: 5.000000e-03 eta: 4:02:01 time: 0.537625 data_time: 0.057844 memory: 8713 loss_kpt: 202.395028 acc_pose: 0.840969 loss: 202.395028 2022/10/13 01:12:50 - mmengine - INFO - Epoch(train) [160][550/586] lr: 5.000000e-03 eta: 4:01:37 time: 0.547118 data_time: 0.058053 memory: 8713 loss_kpt: 202.128874 acc_pose: 0.797091 loss: 202.128874 2022/10/13 01:13:09 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 01:13:09 - mmengine - INFO - Saving checkpoint at 160 epochs 2022/10/13 01:13:23 - mmengine - INFO - Epoch(val) [160][50/407] eta: 0:01:10 time: 0.198598 data_time: 0.013429 memory: 8713 2022/10/13 01:13:33 - mmengine - INFO - Epoch(val) [160][100/407] eta: 0:01:00 time: 0.195883 data_time: 0.007882 memory: 1759 2022/10/13 01:13:42 - mmengine - INFO - Epoch(val) [160][150/407] eta: 0:00:49 time: 0.194447 data_time: 0.008031 memory: 1759 2022/10/13 01:13:52 - mmengine - INFO - Epoch(val) [160][200/407] eta: 0:00:40 time: 0.197551 data_time: 0.008292 memory: 1759 2022/10/13 01:14:02 - mmengine - INFO - Epoch(val) [160][250/407] eta: 0:00:30 time: 0.195045 data_time: 0.008231 memory: 1759 2022/10/13 01:14:12 - mmengine - INFO - Epoch(val) [160][300/407] eta: 0:00:20 time: 0.193171 data_time: 0.007941 memory: 1759 2022/10/13 01:14:21 - mmengine - INFO - Epoch(val) [160][350/407] eta: 0:00:11 time: 0.194245 data_time: 0.008423 memory: 1759 2022/10/13 01:14:31 - mmengine - INFO - Epoch(val) [160][400/407] eta: 0:00:01 time: 0.191612 data_time: 0.008189 memory: 1759 2022/10/13 01:14:45 - mmengine - INFO - Evaluating CocoMetric... 2022/10/13 01:15:00 - mmengine - INFO - Epoch(val) [160][407/407] coco/AP: 0.729078 coco/AP .5: 0.894343 coco/AP .75: 0.799959 coco/AP (M): 0.696409 coco/AP (L): 0.792371 coco/AR: 0.794962 coco/AR .5: 0.935611 coco/AR .75: 0.855479 coco/AR (M): 0.750423 coco/AR (L): 0.856447 2022/10/13 01:15:00 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/liqikai/openmmlab/pt112cu113py38/mmpose/work_dirs/20221012/rsn2x/best_coco/AP_epoch_150.pth is removed 2022/10/13 01:15:02 - mmengine - INFO - The best checkpoint with 0.7291 coco/AP at 160 epoch is saved to best_coco/AP_epoch_160.pth. 2022/10/13 01:15:29 - mmengine - INFO - Epoch(train) [161][50/586] lr: 5.000000e-03 eta: 4:00:49 time: 0.525309 data_time: 0.063199 memory: 8713 loss_kpt: 205.754128 acc_pose: 0.814524 loss: 205.754128 2022/10/13 01:15:54 - mmengine - INFO - Epoch(train) [161][100/586] lr: 5.000000e-03 eta: 4:00:25 time: 0.512689 data_time: 0.056472 memory: 8713 loss_kpt: 207.264185 acc_pose: 0.848572 loss: 207.264185 2022/10/13 01:16:21 - mmengine - INFO - Epoch(train) [161][150/586] lr: 5.000000e-03 eta: 4:00:01 time: 0.524752 data_time: 0.055145 memory: 8713 loss_kpt: 200.786442 acc_pose: 0.905213 loss: 200.786442 2022/10/13 01:16:47 - mmengine - INFO - Epoch(train) [161][200/586] lr: 5.000000e-03 eta: 3:59:36 time: 0.528314 data_time: 0.061919 memory: 8713 loss_kpt: 199.710568 acc_pose: 0.882719 loss: 199.710568 2022/10/13 01:17:08 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 01:17:13 - mmengine - INFO - Epoch(train) [161][250/586] lr: 5.000000e-03 eta: 3:59:12 time: 0.515221 data_time: 0.057963 memory: 8713 loss_kpt: 201.172731 acc_pose: 0.857718 loss: 201.172731 2022/10/13 01:17:39 - mmengine - INFO - Epoch(train) [161][300/586] lr: 5.000000e-03 eta: 3:58:48 time: 0.515874 data_time: 0.054507 memory: 8713 loss_kpt: 202.923063 acc_pose: 0.797641 loss: 202.923063 2022/10/13 01:18:05 - mmengine - INFO - Epoch(train) [161][350/586] lr: 5.000000e-03 eta: 3:58:23 time: 0.522212 data_time: 0.056389 memory: 8713 loss_kpt: 199.149961 acc_pose: 0.841309 loss: 199.149961 2022/10/13 01:18:31 - mmengine - INFO - Epoch(train) [161][400/586] lr: 5.000000e-03 eta: 3:57:59 time: 0.521433 data_time: 0.058090 memory: 8713 loss_kpt: 203.128086 acc_pose: 0.868966 loss: 203.128086 2022/10/13 01:18:57 - mmengine - INFO - Epoch(train) [161][450/586] lr: 5.000000e-03 eta: 3:57:35 time: 0.525554 data_time: 0.057758 memory: 8713 loss_kpt: 199.893409 acc_pose: 0.769217 loss: 199.893409 2022/10/13 01:19:23 - mmengine - INFO - Epoch(train) [161][500/586] lr: 5.000000e-03 eta: 3:57:11 time: 0.517110 data_time: 0.057156 memory: 8713 loss_kpt: 206.063019 acc_pose: 0.829853 loss: 206.063019 2022/10/13 01:19:49 - mmengine - INFO - Epoch(train) [161][550/586] lr: 5.000000e-03 eta: 3:56:46 time: 0.508695 data_time: 0.057370 memory: 8713 loss_kpt: 204.540398 acc_pose: 0.749090 loss: 204.540398 2022/10/13 01:20:07 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 01:20:33 - mmengine - INFO - Epoch(train) [162][50/586] lr: 5.000000e-03 eta: 3:55:59 time: 0.532207 data_time: 0.066928 memory: 8713 loss_kpt: 201.490740 acc_pose: 0.855762 loss: 201.490740 2022/10/13 01:20:59 - mmengine - INFO - Epoch(train) [162][100/586] lr: 5.000000e-03 eta: 3:55:34 time: 0.519444 data_time: 0.062071 memory: 8713 loss_kpt: 202.936757 acc_pose: 0.879704 loss: 202.936757 2022/10/13 01:21:25 - mmengine - INFO - Epoch(train) [162][150/586] lr: 5.000000e-03 eta: 3:55:10 time: 0.523222 data_time: 0.054966 memory: 8713 loss_kpt: 201.394074 acc_pose: 0.885690 loss: 201.394074 2022/10/13 01:21:51 - mmengine - INFO - Epoch(train) [162][200/586] lr: 5.000000e-03 eta: 3:54:46 time: 0.521189 data_time: 0.056439 memory: 8713 loss_kpt: 199.542471 acc_pose: 0.858557 loss: 199.542471 2022/10/13 01:22:17 - mmengine - INFO - Epoch(train) [162][250/586] lr: 5.000000e-03 eta: 3:54:21 time: 0.506973 data_time: 0.057939 memory: 8713 loss_kpt: 198.906310 acc_pose: 0.850214 loss: 198.906310 2022/10/13 01:22:43 - mmengine - INFO - Epoch(train) [162][300/586] lr: 5.000000e-03 eta: 3:53:57 time: 0.525314 data_time: 0.054150 memory: 8713 loss_kpt: 200.999646 acc_pose: 0.857971 loss: 200.999646 2022/10/13 01:23:10 - mmengine - INFO - Epoch(train) [162][350/586] lr: 5.000000e-03 eta: 3:53:33 time: 0.535146 data_time: 0.056393 memory: 8713 loss_kpt: 203.507346 acc_pose: 0.771551 loss: 203.507346 2022/10/13 01:23:36 - mmengine - INFO - Epoch(train) [162][400/586] lr: 5.000000e-03 eta: 3:53:09 time: 0.518428 data_time: 0.057431 memory: 8713 loss_kpt: 203.219958 acc_pose: 0.824545 loss: 203.219958 2022/10/13 01:24:02 - mmengine - INFO - Epoch(train) [162][450/586] lr: 5.000000e-03 eta: 3:52:44 time: 0.517253 data_time: 0.056934 memory: 8713 loss_kpt: 201.998934 acc_pose: 0.751076 loss: 201.998934 2022/10/13 01:24:28 - mmengine - INFO - Epoch(train) [162][500/586] lr: 5.000000e-03 eta: 3:52:20 time: 0.516547 data_time: 0.058580 memory: 8713 loss_kpt: 199.545340 acc_pose: 0.849777 loss: 199.545340 2022/10/13 01:24:54 - mmengine - INFO - Epoch(train) [162][550/586] lr: 5.000000e-03 eta: 3:51:56 time: 0.530914 data_time: 0.054806 memory: 8713 loss_kpt: 200.598401 acc_pose: 0.933923 loss: 200.598401 2022/10/13 01:25:12 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 01:25:39 - mmengine - INFO - Epoch(train) [163][50/586] lr: 5.000000e-03 eta: 3:51:09 time: 0.542134 data_time: 0.068258 memory: 8713 loss_kpt: 201.740890 acc_pose: 0.858835 loss: 201.740890 2022/10/13 01:25:48 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 01:26:05 - mmengine - INFO - Epoch(train) [163][100/586] lr: 5.000000e-03 eta: 3:50:44 time: 0.519270 data_time: 0.054051 memory: 8713 loss_kpt: 204.437711 acc_pose: 0.837893 loss: 204.437711 2022/10/13 01:26:31 - mmengine - INFO - Epoch(train) [163][150/586] lr: 5.000000e-03 eta: 3:50:20 time: 0.524656 data_time: 0.060541 memory: 8713 loss_kpt: 200.055644 acc_pose: 0.813378 loss: 200.055644 2022/10/13 01:26:57 - mmengine - INFO - Epoch(train) [163][200/586] lr: 5.000000e-03 eta: 3:49:56 time: 0.515958 data_time: 0.055793 memory: 8713 loss_kpt: 205.285608 acc_pose: 0.791866 loss: 205.285608 2022/10/13 01:27:23 - mmengine - INFO - Epoch(train) [163][250/586] lr: 5.000000e-03 eta: 3:49:31 time: 0.517551 data_time: 0.057704 memory: 8713 loss_kpt: 199.421071 acc_pose: 0.801425 loss: 199.421071 2022/10/13 01:27:49 - mmengine - INFO - Epoch(train) [163][300/586] lr: 5.000000e-03 eta: 3:49:07 time: 0.515578 data_time: 0.062502 memory: 8713 loss_kpt: 198.560750 acc_pose: 0.765264 loss: 198.560750 2022/10/13 01:28:15 - mmengine - INFO - Epoch(train) [163][350/586] lr: 5.000000e-03 eta: 3:48:43 time: 0.511726 data_time: 0.058270 memory: 8713 loss_kpt: 203.959492 acc_pose: 0.860087 loss: 203.959492 2022/10/13 01:28:40 - mmengine - INFO - Epoch(train) [163][400/586] lr: 5.000000e-03 eta: 3:48:18 time: 0.505034 data_time: 0.055376 memory: 8713 loss_kpt: 201.663334 acc_pose: 0.897040 loss: 201.663334 2022/10/13 01:29:05 - mmengine - INFO - Epoch(train) [163][450/586] lr: 5.000000e-03 eta: 3:47:54 time: 0.504077 data_time: 0.056617 memory: 8713 loss_kpt: 200.899172 acc_pose: 0.849643 loss: 200.899172 2022/10/13 01:29:30 - mmengine - INFO - Epoch(train) [163][500/586] lr: 5.000000e-03 eta: 3:47:29 time: 0.501016 data_time: 0.056091 memory: 8713 loss_kpt: 197.898177 acc_pose: 0.862667 loss: 197.898177 2022/10/13 01:29:55 - mmengine - INFO - Epoch(train) [163][550/586] lr: 5.000000e-03 eta: 3:47:04 time: 0.502011 data_time: 0.057976 memory: 8713 loss_kpt: 205.104702 acc_pose: 0.816062 loss: 205.104702 2022/10/13 01:30:13 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 01:30:39 - mmengine - INFO - Epoch(train) [164][50/586] lr: 5.000000e-03 eta: 3:46:17 time: 0.522994 data_time: 0.069379 memory: 8713 loss_kpt: 201.802187 acc_pose: 0.888451 loss: 201.802187 2022/10/13 01:31:05 - mmengine - INFO - Epoch(train) [164][100/586] lr: 5.000000e-03 eta: 3:45:53 time: 0.518311 data_time: 0.056832 memory: 8713 loss_kpt: 199.939492 acc_pose: 0.848334 loss: 199.939492 2022/10/13 01:31:31 - mmengine - INFO - Epoch(train) [164][150/586] lr: 5.000000e-03 eta: 3:45:28 time: 0.513502 data_time: 0.055450 memory: 8713 loss_kpt: 202.876038 acc_pose: 0.897967 loss: 202.876038 2022/10/13 01:31:57 - mmengine - INFO - Epoch(train) [164][200/586] lr: 5.000000e-03 eta: 3:45:04 time: 0.517248 data_time: 0.061325 memory: 8713 loss_kpt: 202.580452 acc_pose: 0.881518 loss: 202.580452 2022/10/13 01:32:22 - mmengine - INFO - Epoch(train) [164][250/586] lr: 5.000000e-03 eta: 3:44:40 time: 0.510772 data_time: 0.056365 memory: 8713 loss_kpt: 198.787349 acc_pose: 0.811768 loss: 198.787349 2022/10/13 01:32:47 - mmengine - INFO - Epoch(train) [164][300/586] lr: 5.000000e-03 eta: 3:44:15 time: 0.505859 data_time: 0.050794 memory: 8713 loss_kpt: 201.395944 acc_pose: 0.808649 loss: 201.395944 2022/10/13 01:33:14 - mmengine - INFO - Epoch(train) [164][350/586] lr: 5.000000e-03 eta: 3:43:51 time: 0.521356 data_time: 0.059604 memory: 8713 loss_kpt: 207.142593 acc_pose: 0.875511 loss: 207.142593 2022/10/13 01:33:40 - mmengine - INFO - Epoch(train) [164][400/586] lr: 5.000000e-03 eta: 3:43:27 time: 0.528284 data_time: 0.056411 memory: 8713 loss_kpt: 200.677383 acc_pose: 0.819074 loss: 200.677383 2022/10/13 01:34:06 - mmengine - INFO - Epoch(train) [164][450/586] lr: 5.000000e-03 eta: 3:43:02 time: 0.516940 data_time: 0.056147 memory: 8713 loss_kpt: 202.913741 acc_pose: 0.861955 loss: 202.913741 2022/10/13 01:34:23 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 01:34:32 - mmengine - INFO - Epoch(train) [164][500/586] lr: 5.000000e-03 eta: 3:42:38 time: 0.520639 data_time: 0.056470 memory: 8713 loss_kpt: 203.886495 acc_pose: 0.869802 loss: 203.886495 2022/10/13 01:34:58 - mmengine - INFO - Epoch(train) [164][550/586] lr: 5.000000e-03 eta: 3:42:14 time: 0.530636 data_time: 0.060419 memory: 8713 loss_kpt: 204.476360 acc_pose: 0.841221 loss: 204.476360 2022/10/13 01:35:17 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 01:35:44 - mmengine - INFO - Epoch(train) [165][50/586] lr: 5.000000e-03 eta: 3:41:27 time: 0.536168 data_time: 0.070468 memory: 8713 loss_kpt: 203.272184 acc_pose: 0.836162 loss: 203.272184 2022/10/13 01:36:10 - mmengine - INFO - Epoch(train) [165][100/586] lr: 5.000000e-03 eta: 3:41:03 time: 0.521543 data_time: 0.060566 memory: 8713 loss_kpt: 198.225706 acc_pose: 0.797999 loss: 198.225706 2022/10/13 01:36:36 - mmengine - INFO - Epoch(train) [165][150/586] lr: 5.000000e-03 eta: 3:40:38 time: 0.520371 data_time: 0.061047 memory: 8713 loss_kpt: 201.076298 acc_pose: 0.823586 loss: 201.076298 2022/10/13 01:37:02 - mmengine - INFO - Epoch(train) [165][200/586] lr: 5.000000e-03 eta: 3:40:14 time: 0.513708 data_time: 0.052204 memory: 8713 loss_kpt: 202.118069 acc_pose: 0.846212 loss: 202.118069 2022/10/13 01:37:28 - mmengine - INFO - Epoch(train) [165][250/586] lr: 5.000000e-03 eta: 3:39:49 time: 0.521061 data_time: 0.061673 memory: 8713 loss_kpt: 198.407829 acc_pose: 0.870377 loss: 198.407829 2022/10/13 01:37:55 - mmengine - INFO - Epoch(train) [165][300/586] lr: 5.000000e-03 eta: 3:39:26 time: 0.549002 data_time: 0.059089 memory: 8713 loss_kpt: 202.047500 acc_pose: 0.785261 loss: 202.047500 2022/10/13 01:38:22 - mmengine - INFO - Epoch(train) [165][350/586] lr: 5.000000e-03 eta: 3:39:02 time: 0.543380 data_time: 0.056855 memory: 8713 loss_kpt: 201.255334 acc_pose: 0.827522 loss: 201.255334 2022/10/13 01:38:49 - mmengine - INFO - Epoch(train) [165][400/586] lr: 5.000000e-03 eta: 3:38:37 time: 0.523071 data_time: 0.056593 memory: 8713 loss_kpt: 200.744678 acc_pose: 0.831013 loss: 200.744678 2022/10/13 01:39:16 - mmengine - INFO - Epoch(train) [165][450/586] lr: 5.000000e-03 eta: 3:38:13 time: 0.539201 data_time: 0.061373 memory: 8713 loss_kpt: 201.256480 acc_pose: 0.787146 loss: 201.256480 2022/10/13 01:39:42 - mmengine - INFO - Epoch(train) [165][500/586] lr: 5.000000e-03 eta: 3:37:49 time: 0.523683 data_time: 0.054446 memory: 8713 loss_kpt: 201.396367 acc_pose: 0.829908 loss: 201.396367 2022/10/13 01:40:09 - mmengine - INFO - Epoch(train) [165][550/586] lr: 5.000000e-03 eta: 3:37:25 time: 0.535808 data_time: 0.058702 memory: 8713 loss_kpt: 200.562060 acc_pose: 0.846672 loss: 200.562060 2022/10/13 01:40:27 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 01:40:54 - mmengine - INFO - Epoch(train) [166][50/586] lr: 5.000000e-03 eta: 3:36:38 time: 0.550938 data_time: 0.070527 memory: 8713 loss_kpt: 203.562005 acc_pose: 0.878823 loss: 203.562005 2022/10/13 01:41:21 - mmengine - INFO - Epoch(train) [166][100/586] lr: 5.000000e-03 eta: 3:36:14 time: 0.533990 data_time: 0.059320 memory: 8713 loss_kpt: 199.716429 acc_pose: 0.872544 loss: 199.716429 2022/10/13 01:41:48 - mmengine - INFO - Epoch(train) [166][150/586] lr: 5.000000e-03 eta: 3:35:50 time: 0.540591 data_time: 0.061206 memory: 8713 loss_kpt: 202.310992 acc_pose: 0.851281 loss: 202.310992 2022/10/13 01:42:14 - mmengine - INFO - Epoch(train) [166][200/586] lr: 5.000000e-03 eta: 3:35:26 time: 0.526494 data_time: 0.060615 memory: 8713 loss_kpt: 202.924402 acc_pose: 0.856251 loss: 202.924402 2022/10/13 01:42:41 - mmengine - INFO - Epoch(train) [166][250/586] lr: 5.000000e-03 eta: 3:35:01 time: 0.527468 data_time: 0.057964 memory: 8713 loss_kpt: 199.029823 acc_pose: 0.839172 loss: 199.029823 2022/10/13 01:43:07 - mmengine - INFO - Epoch(train) [166][300/586] lr: 5.000000e-03 eta: 3:34:37 time: 0.520962 data_time: 0.056488 memory: 8713 loss_kpt: 202.556362 acc_pose: 0.877894 loss: 202.556362 2022/10/13 01:43:12 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 01:43:33 - mmengine - INFO - Epoch(train) [166][350/586] lr: 5.000000e-03 eta: 3:34:13 time: 0.522335 data_time: 0.060021 memory: 8713 loss_kpt: 198.551994 acc_pose: 0.819118 loss: 198.551994 2022/10/13 01:43:59 - mmengine - INFO - Epoch(train) [166][400/586] lr: 5.000000e-03 eta: 3:33:48 time: 0.512994 data_time: 0.057019 memory: 8713 loss_kpt: 199.638120 acc_pose: 0.850597 loss: 199.638120 2022/10/13 01:44:25 - mmengine - INFO - Epoch(train) [166][450/586] lr: 5.000000e-03 eta: 3:33:24 time: 0.520396 data_time: 0.061646 memory: 8713 loss_kpt: 202.747720 acc_pose: 0.883506 loss: 202.747720 2022/10/13 01:44:50 - mmengine - INFO - Epoch(train) [166][500/586] lr: 5.000000e-03 eta: 3:33:00 time: 0.510940 data_time: 0.053751 memory: 8713 loss_kpt: 203.149821 acc_pose: 0.769978 loss: 203.149821 2022/10/13 01:45:16 - mmengine - INFO - Epoch(train) [166][550/586] lr: 5.000000e-03 eta: 3:32:35 time: 0.521092 data_time: 0.058691 memory: 8713 loss_kpt: 202.524057 acc_pose: 0.773114 loss: 202.524057 2022/10/13 01:45:34 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 01:46:01 - mmengine - INFO - Epoch(train) [167][50/586] lr: 5.000000e-03 eta: 3:31:48 time: 0.530678 data_time: 0.073959 memory: 8713 loss_kpt: 205.804565 acc_pose: 0.854573 loss: 205.804565 2022/10/13 01:46:26 - mmengine - INFO - Epoch(train) [167][100/586] lr: 5.000000e-03 eta: 3:31:24 time: 0.507619 data_time: 0.056225 memory: 8713 loss_kpt: 199.492935 acc_pose: 0.809377 loss: 199.492935 2022/10/13 01:46:52 - mmengine - INFO - Epoch(train) [167][150/586] lr: 5.000000e-03 eta: 3:30:59 time: 0.509486 data_time: 0.059238 memory: 8713 loss_kpt: 199.314669 acc_pose: 0.863958 loss: 199.314669 2022/10/13 01:47:17 - mmengine - INFO - Epoch(train) [167][200/586] lr: 5.000000e-03 eta: 3:30:35 time: 0.504971 data_time: 0.056405 memory: 8713 loss_kpt: 200.944796 acc_pose: 0.852637 loss: 200.944796 2022/10/13 01:47:43 - mmengine - INFO - Epoch(train) [167][250/586] lr: 5.000000e-03 eta: 3:30:11 time: 0.520440 data_time: 0.055427 memory: 8713 loss_kpt: 197.229554 acc_pose: 0.764365 loss: 197.229554 2022/10/13 01:48:09 - mmengine - INFO - Epoch(train) [167][300/586] lr: 5.000000e-03 eta: 3:29:46 time: 0.528306 data_time: 0.053927 memory: 8713 loss_kpt: 199.418033 acc_pose: 0.877277 loss: 199.418033 2022/10/13 01:48:36 - mmengine - INFO - Epoch(train) [167][350/586] lr: 5.000000e-03 eta: 3:29:22 time: 0.528537 data_time: 0.057722 memory: 8713 loss_kpt: 198.676346 acc_pose: 0.863557 loss: 198.676346 2022/10/13 01:49:02 - mmengine - INFO - Epoch(train) [167][400/586] lr: 5.000000e-03 eta: 3:28:58 time: 0.517458 data_time: 0.054462 memory: 8713 loss_kpt: 205.874683 acc_pose: 0.864050 loss: 205.874683 2022/10/13 01:49:28 - mmengine - INFO - Epoch(train) [167][450/586] lr: 5.000000e-03 eta: 3:28:33 time: 0.520236 data_time: 0.059580 memory: 8713 loss_kpt: 201.024154 acc_pose: 0.770907 loss: 201.024154 2022/10/13 01:49:54 - mmengine - INFO - Epoch(train) [167][500/586] lr: 5.000000e-03 eta: 3:28:09 time: 0.516645 data_time: 0.056595 memory: 8713 loss_kpt: 199.394040 acc_pose: 0.867221 loss: 199.394040 2022/10/13 01:50:20 - mmengine - INFO - Epoch(train) [167][550/586] lr: 5.000000e-03 eta: 3:27:45 time: 0.519213 data_time: 0.056476 memory: 8713 loss_kpt: 200.512945 acc_pose: 0.826433 loss: 200.512945 2022/10/13 01:50:38 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 01:51:05 - mmengine - INFO - Epoch(train) [168][50/586] lr: 5.000000e-03 eta: 3:26:58 time: 0.538796 data_time: 0.073125 memory: 8713 loss_kpt: 199.771077 acc_pose: 0.807707 loss: 199.771077 2022/10/13 01:51:31 - mmengine - INFO - Epoch(train) [168][100/586] lr: 5.000000e-03 eta: 3:26:34 time: 0.522571 data_time: 0.056680 memory: 8713 loss_kpt: 204.239292 acc_pose: 0.840193 loss: 204.239292 2022/10/13 01:51:52 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 01:51:59 - mmengine - INFO - Epoch(train) [168][150/586] lr: 5.000000e-03 eta: 3:26:10 time: 0.559098 data_time: 0.061387 memory: 8713 loss_kpt: 196.918181 acc_pose: 0.827673 loss: 196.918181 2022/10/13 01:52:26 - mmengine - INFO - Epoch(train) [168][200/586] lr: 5.000000e-03 eta: 3:25:46 time: 0.537333 data_time: 0.056595 memory: 8713 loss_kpt: 198.594114 acc_pose: 0.849817 loss: 198.594114 2022/10/13 01:52:52 - mmengine - INFO - Epoch(train) [168][250/586] lr: 5.000000e-03 eta: 3:25:22 time: 0.533974 data_time: 0.059068 memory: 8713 loss_kpt: 203.444336 acc_pose: 0.902582 loss: 203.444336 2022/10/13 01:53:19 - mmengine - INFO - Epoch(train) [168][300/586] lr: 5.000000e-03 eta: 3:24:57 time: 0.539269 data_time: 0.058158 memory: 8713 loss_kpt: 202.504210 acc_pose: 0.857760 loss: 202.504210 2022/10/13 01:53:47 - mmengine - INFO - Epoch(train) [168][350/586] lr: 5.000000e-03 eta: 3:24:34 time: 0.554628 data_time: 0.060700 memory: 8713 loss_kpt: 202.238098 acc_pose: 0.838281 loss: 202.238098 2022/10/13 01:54:14 - mmengine - INFO - Epoch(train) [168][400/586] lr: 5.000000e-03 eta: 3:24:09 time: 0.544890 data_time: 0.057486 memory: 8713 loss_kpt: 197.884642 acc_pose: 0.870700 loss: 197.884642 2022/10/13 01:54:42 - mmengine - INFO - Epoch(train) [168][450/586] lr: 5.000000e-03 eta: 3:23:45 time: 0.548336 data_time: 0.061273 memory: 8713 loss_kpt: 201.918998 acc_pose: 0.871415 loss: 201.918998 2022/10/13 01:55:10 - mmengine - INFO - Epoch(train) [168][500/586] lr: 5.000000e-03 eta: 3:23:22 time: 0.555774 data_time: 0.058958 memory: 8713 loss_kpt: 201.419358 acc_pose: 0.782433 loss: 201.419358 2022/10/13 01:55:37 - mmengine - INFO - Epoch(train) [168][550/586] lr: 5.000000e-03 eta: 3:22:58 time: 0.553070 data_time: 0.062461 memory: 8713 loss_kpt: 201.888420 acc_pose: 0.839618 loss: 201.888420 2022/10/13 01:55:56 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 01:56:23 - mmengine - INFO - Epoch(train) [169][50/586] lr: 5.000000e-03 eta: 3:22:11 time: 0.535975 data_time: 0.070051 memory: 8713 loss_kpt: 202.515338 acc_pose: 0.894163 loss: 202.515338 2022/10/13 01:56:49 - mmengine - INFO - Epoch(train) [169][100/586] lr: 5.000000e-03 eta: 3:21:47 time: 0.510410 data_time: 0.051785 memory: 8713 loss_kpt: 205.291449 acc_pose: 0.857420 loss: 205.291449 2022/10/13 01:57:15 - mmengine - INFO - Epoch(train) [169][150/586] lr: 5.000000e-03 eta: 3:21:22 time: 0.521628 data_time: 0.061102 memory: 8713 loss_kpt: 202.062683 acc_pose: 0.798785 loss: 202.062683 2022/10/13 01:57:41 - mmengine - INFO - Epoch(train) [169][200/586] lr: 5.000000e-03 eta: 3:20:58 time: 0.518298 data_time: 0.055644 memory: 8713 loss_kpt: 195.355345 acc_pose: 0.825863 loss: 195.355345 2022/10/13 01:58:07 - mmengine - INFO - Epoch(train) [169][250/586] lr: 5.000000e-03 eta: 3:20:34 time: 0.523819 data_time: 0.058458 memory: 8713 loss_kpt: 200.937218 acc_pose: 0.846819 loss: 200.937218 2022/10/13 01:58:33 - mmengine - INFO - Epoch(train) [169][300/586] lr: 5.000000e-03 eta: 3:20:09 time: 0.511243 data_time: 0.055404 memory: 8713 loss_kpt: 200.596893 acc_pose: 0.808982 loss: 200.596893 2022/10/13 01:58:59 - mmengine - INFO - Epoch(train) [169][350/586] lr: 5.000000e-03 eta: 3:19:45 time: 0.523375 data_time: 0.072416 memory: 8713 loss_kpt: 199.647606 acc_pose: 0.848415 loss: 199.647606 2022/10/13 01:59:24 - mmengine - INFO - Epoch(train) [169][400/586] lr: 5.000000e-03 eta: 3:19:20 time: 0.509619 data_time: 0.062327 memory: 8713 loss_kpt: 203.939659 acc_pose: 0.854844 loss: 203.939659 2022/10/13 01:59:51 - mmengine - INFO - Epoch(train) [169][450/586] lr: 5.000000e-03 eta: 3:18:56 time: 0.538663 data_time: 0.065487 memory: 8713 loss_kpt: 202.133974 acc_pose: 0.808265 loss: 202.133974 2022/10/13 02:00:17 - mmengine - INFO - Epoch(train) [169][500/586] lr: 5.000000e-03 eta: 3:18:32 time: 0.517698 data_time: 0.060525 memory: 8713 loss_kpt: 197.064249 acc_pose: 0.803010 loss: 197.064249 2022/10/13 02:00:43 - mmengine - INFO - Epoch(train) [169][550/586] lr: 5.000000e-03 eta: 3:18:07 time: 0.524062 data_time: 0.060531 memory: 8713 loss_kpt: 197.956640 acc_pose: 0.820505 loss: 197.956640 2022/10/13 02:00:44 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 02:01:02 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 02:01:29 - mmengine - INFO - Epoch(train) [170][50/586] lr: 5.000000e-03 eta: 3:17:21 time: 0.531411 data_time: 0.075522 memory: 8713 loss_kpt: 199.353249 acc_pose: 0.896751 loss: 199.353249 2022/10/13 02:01:55 - mmengine - INFO - Epoch(train) [170][100/586] lr: 5.000000e-03 eta: 3:16:57 time: 0.522060 data_time: 0.064050 memory: 8713 loss_kpt: 202.075226 acc_pose: 0.851529 loss: 202.075226 2022/10/13 02:02:22 - mmengine - INFO - Epoch(train) [170][150/586] lr: 5.000000e-03 eta: 3:16:33 time: 0.545275 data_time: 0.063493 memory: 8713 loss_kpt: 200.484557 acc_pose: 0.804294 loss: 200.484557 2022/10/13 02:02:49 - mmengine - INFO - Epoch(train) [170][200/586] lr: 5.000000e-03 eta: 3:16:08 time: 0.535980 data_time: 0.060835 memory: 8713 loss_kpt: 200.617247 acc_pose: 0.869483 loss: 200.617247 2022/10/13 02:03:16 - mmengine - INFO - Epoch(train) [170][250/586] lr: 5.000000e-03 eta: 3:15:44 time: 0.543477 data_time: 0.062678 memory: 8713 loss_kpt: 199.743619 acc_pose: 0.821017 loss: 199.743619 2022/10/13 02:03:43 - mmengine - INFO - Epoch(train) [170][300/586] lr: 5.000000e-03 eta: 3:15:20 time: 0.538706 data_time: 0.055726 memory: 8713 loss_kpt: 200.048112 acc_pose: 0.825381 loss: 200.048112 2022/10/13 02:04:10 - mmengine - INFO - Epoch(train) [170][350/586] lr: 5.000000e-03 eta: 3:14:56 time: 0.538980 data_time: 0.067320 memory: 8713 loss_kpt: 204.241376 acc_pose: 0.862750 loss: 204.241376 2022/10/13 02:04:37 - mmengine - INFO - Epoch(train) [170][400/586] lr: 5.000000e-03 eta: 3:14:32 time: 0.540061 data_time: 0.052784 memory: 8713 loss_kpt: 201.242525 acc_pose: 0.886420 loss: 201.242525 2022/10/13 02:05:03 - mmengine - INFO - Epoch(train) [170][450/586] lr: 5.000000e-03 eta: 3:14:07 time: 0.521279 data_time: 0.056291 memory: 8713 loss_kpt: 202.946763 acc_pose: 0.864271 loss: 202.946763 2022/10/13 02:05:29 - mmengine - INFO - Epoch(train) [170][500/586] lr: 5.000000e-03 eta: 3:13:43 time: 0.529290 data_time: 0.061810 memory: 8713 loss_kpt: 202.186055 acc_pose: 0.845651 loss: 202.186055 2022/10/13 02:05:56 - mmengine - INFO - Epoch(train) [170][550/586] lr: 5.000000e-03 eta: 3:13:19 time: 0.525208 data_time: 0.058882 memory: 8713 loss_kpt: 201.707281 acc_pose: 0.795160 loss: 201.707281 2022/10/13 02:06:14 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 02:06:14 - mmengine - INFO - Saving checkpoint at 170 epochs 2022/10/13 02:06:28 - mmengine - INFO - Epoch(val) [170][50/407] eta: 0:01:10 time: 0.198842 data_time: 0.013312 memory: 8713 2022/10/13 02:06:37 - mmengine - INFO - Epoch(val) [170][100/407] eta: 0:00:59 time: 0.193106 data_time: 0.007937 memory: 1759 2022/10/13 02:06:47 - mmengine - INFO - Epoch(val) [170][150/407] eta: 0:00:49 time: 0.191838 data_time: 0.008491 memory: 1759 2022/10/13 02:06:57 - mmengine - INFO - Epoch(val) [170][200/407] eta: 0:00:39 time: 0.192230 data_time: 0.007668 memory: 1759 2022/10/13 02:07:06 - mmengine - INFO - Epoch(val) [170][250/407] eta: 0:00:30 time: 0.193243 data_time: 0.007767 memory: 1759 2022/10/13 02:07:16 - mmengine - INFO - Epoch(val) [170][300/407] eta: 0:00:20 time: 0.192906 data_time: 0.008214 memory: 1759 2022/10/13 02:07:26 - mmengine - INFO - Epoch(val) [170][350/407] eta: 0:00:11 time: 0.194035 data_time: 0.008181 memory: 1759 2022/10/13 02:07:35 - mmengine - INFO - Epoch(val) [170][400/407] eta: 0:00:01 time: 0.194638 data_time: 0.011358 memory: 1759 2022/10/13 02:07:50 - mmengine - INFO - Evaluating CocoMetric... 2022/10/13 02:08:06 - mmengine - INFO - Epoch(val) [170][407/407] coco/AP: 0.727667 coco/AP .5: 0.893694 coco/AP .75: 0.798818 coco/AP (M): 0.693871 coco/AP (L): 0.790922 coco/AR: 0.792695 coco/AR .5: 0.935296 coco/AR .75: 0.851543 coco/AR (M): 0.748074 coco/AR (L): 0.854404 2022/10/13 02:08:33 - mmengine - INFO - Epoch(train) [171][50/586] lr: 5.000000e-04 eta: 3:12:33 time: 0.545027 data_time: 0.070972 memory: 8713 loss_kpt: 201.782863 acc_pose: 0.857612 loss: 201.782863 2022/10/13 02:09:00 - mmengine - INFO - Epoch(train) [171][100/586] lr: 5.000000e-04 eta: 3:12:09 time: 0.543878 data_time: 0.062379 memory: 8713 loss_kpt: 199.829679 acc_pose: 0.813901 loss: 199.829679 2022/10/13 02:09:27 - mmengine - INFO - Epoch(train) [171][150/586] lr: 5.000000e-04 eta: 3:11:44 time: 0.538632 data_time: 0.057747 memory: 8713 loss_kpt: 197.572139 acc_pose: 0.879117 loss: 197.572139 2022/10/13 02:09:54 - mmengine - INFO - Epoch(train) [171][200/586] lr: 5.000000e-04 eta: 3:11:20 time: 0.542367 data_time: 0.056003 memory: 8713 loss_kpt: 200.240535 acc_pose: 0.789597 loss: 200.240535 2022/10/13 02:10:22 - mmengine - INFO - Epoch(train) [171][250/586] lr: 5.000000e-04 eta: 3:10:56 time: 0.550306 data_time: 0.063979 memory: 8713 loss_kpt: 198.700541 acc_pose: 0.860093 loss: 198.700541 2022/10/13 02:10:48 - mmengine - INFO - Epoch(train) [171][300/586] lr: 5.000000e-04 eta: 3:10:32 time: 0.529598 data_time: 0.060600 memory: 8713 loss_kpt: 197.914919 acc_pose: 0.857997 loss: 197.914919 2022/10/13 02:11:15 - mmengine - INFO - Epoch(train) [171][350/586] lr: 5.000000e-04 eta: 3:10:08 time: 0.537122 data_time: 0.059891 memory: 8713 loss_kpt: 198.102161 acc_pose: 0.854458 loss: 198.102161 2022/10/13 02:11:31 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 02:11:42 - mmengine - INFO - Epoch(train) [171][400/586] lr: 5.000000e-04 eta: 3:09:44 time: 0.536153 data_time: 0.057109 memory: 8713 loss_kpt: 198.630605 acc_pose: 0.823873 loss: 198.630605 2022/10/13 02:12:09 - mmengine - INFO - Epoch(train) [171][450/586] lr: 5.000000e-04 eta: 3:09:19 time: 0.534494 data_time: 0.059715 memory: 8713 loss_kpt: 196.243664 acc_pose: 0.801579 loss: 196.243664 2022/10/13 02:12:35 - mmengine - INFO - Epoch(train) [171][500/586] lr: 5.000000e-04 eta: 3:08:55 time: 0.528398 data_time: 0.059154 memory: 8713 loss_kpt: 194.257664 acc_pose: 0.847153 loss: 194.257664 2022/10/13 02:13:03 - mmengine - INFO - Epoch(train) [171][550/586] lr: 5.000000e-04 eta: 3:08:31 time: 0.550003 data_time: 0.060353 memory: 8713 loss_kpt: 193.873411 acc_pose: 0.874323 loss: 193.873411 2022/10/13 02:13:22 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 02:13:49 - mmengine - INFO - Epoch(train) [172][50/586] lr: 5.000000e-04 eta: 3:07:45 time: 0.525972 data_time: 0.070431 memory: 8713 loss_kpt: 201.475520 acc_pose: 0.901991 loss: 201.475520 2022/10/13 02:14:15 - mmengine - INFO - Epoch(train) [172][100/586] lr: 5.000000e-04 eta: 3:07:20 time: 0.528462 data_time: 0.057798 memory: 8713 loss_kpt: 194.221009 acc_pose: 0.839647 loss: 194.221009 2022/10/13 02:14:42 - mmengine - INFO - Epoch(train) [172][150/586] lr: 5.000000e-04 eta: 3:06:56 time: 0.539920 data_time: 0.059149 memory: 8713 loss_kpt: 195.699035 acc_pose: 0.805604 loss: 195.699035 2022/10/13 02:15:08 - mmengine - INFO - Epoch(train) [172][200/586] lr: 5.000000e-04 eta: 3:06:32 time: 0.524500 data_time: 0.057326 memory: 8713 loss_kpt: 200.444250 acc_pose: 0.877761 loss: 200.444250 2022/10/13 02:15:35 - mmengine - INFO - Epoch(train) [172][250/586] lr: 5.000000e-04 eta: 3:06:08 time: 0.527385 data_time: 0.061302 memory: 8713 loss_kpt: 197.666037 acc_pose: 0.888299 loss: 197.666037 2022/10/13 02:16:01 - mmengine - INFO - Epoch(train) [172][300/586] lr: 5.000000e-04 eta: 3:05:43 time: 0.513269 data_time: 0.061104 memory: 8713 loss_kpt: 197.513843 acc_pose: 0.832803 loss: 197.513843 2022/10/13 02:16:27 - mmengine - INFO - Epoch(train) [172][350/586] lr: 5.000000e-04 eta: 3:05:19 time: 0.530524 data_time: 0.060515 memory: 8713 loss_kpt: 193.247085 acc_pose: 0.844431 loss: 193.247085 2022/10/13 02:16:53 - mmengine - INFO - Epoch(train) [172][400/586] lr: 5.000000e-04 eta: 3:04:54 time: 0.527724 data_time: 0.060084 memory: 8713 loss_kpt: 199.777144 acc_pose: 0.811587 loss: 199.777144 2022/10/13 02:17:20 - mmengine - INFO - Epoch(train) [172][450/586] lr: 5.000000e-04 eta: 3:04:30 time: 0.534201 data_time: 0.056933 memory: 8713 loss_kpt: 195.136379 acc_pose: 0.848423 loss: 195.136379 2022/10/13 02:17:47 - mmengine - INFO - Epoch(train) [172][500/586] lr: 5.000000e-04 eta: 3:04:06 time: 0.536072 data_time: 0.060328 memory: 8713 loss_kpt: 195.953952 acc_pose: 0.903309 loss: 195.953952 2022/10/13 02:18:14 - mmengine - INFO - Epoch(train) [172][550/586] lr: 5.000000e-04 eta: 3:03:42 time: 0.533968 data_time: 0.060760 memory: 8713 loss_kpt: 194.731691 acc_pose: 0.855300 loss: 194.731691 2022/10/13 02:18:33 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 02:18:59 - mmengine - INFO - Epoch(train) [173][50/586] lr: 5.000000e-04 eta: 3:02:56 time: 0.520348 data_time: 0.067627 memory: 8713 loss_kpt: 193.986383 acc_pose: 0.839249 loss: 193.986383 2022/10/13 02:19:24 - mmengine - INFO - Epoch(train) [173][100/586] lr: 5.000000e-04 eta: 3:02:31 time: 0.504779 data_time: 0.057885 memory: 8713 loss_kpt: 195.889753 acc_pose: 0.888621 loss: 195.889753 2022/10/13 02:19:49 - mmengine - INFO - Epoch(train) [173][150/586] lr: 5.000000e-04 eta: 3:02:06 time: 0.503025 data_time: 0.060481 memory: 8713 loss_kpt: 198.299473 acc_pose: 0.901321 loss: 198.299473 2022/10/13 02:20:15 - mmengine - INFO - Epoch(train) [173][200/586] lr: 5.000000e-04 eta: 3:01:42 time: 0.508662 data_time: 0.056359 memory: 8713 loss_kpt: 192.114725 acc_pose: 0.757676 loss: 192.114725 2022/10/13 02:20:19 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 02:20:41 - mmengine - INFO - Epoch(train) [173][250/586] lr: 5.000000e-04 eta: 3:01:17 time: 0.518271 data_time: 0.059842 memory: 8713 loss_kpt: 195.793169 acc_pose: 0.857026 loss: 195.793169 2022/10/13 02:21:06 - mmengine - INFO - Epoch(train) [173][300/586] lr: 5.000000e-04 eta: 3:00:53 time: 0.507497 data_time: 0.057926 memory: 8713 loss_kpt: 195.103186 acc_pose: 0.829119 loss: 195.103186 2022/10/13 02:21:32 - mmengine - INFO - Epoch(train) [173][350/586] lr: 5.000000e-04 eta: 3:00:28 time: 0.517358 data_time: 0.058431 memory: 8713 loss_kpt: 193.964736 acc_pose: 0.833559 loss: 193.964736 2022/10/13 02:21:58 - mmengine - INFO - Epoch(train) [173][400/586] lr: 5.000000e-04 eta: 3:00:04 time: 0.518613 data_time: 0.057046 memory: 8713 loss_kpt: 193.959073 acc_pose: 0.853574 loss: 193.959073 2022/10/13 02:22:24 - mmengine - INFO - Epoch(train) [173][450/586] lr: 5.000000e-04 eta: 2:59:39 time: 0.516080 data_time: 0.060714 memory: 8713 loss_kpt: 195.592732 acc_pose: 0.823865 loss: 195.592732 2022/10/13 02:22:50 - mmengine - INFO - Epoch(train) [173][500/586] lr: 5.000000e-04 eta: 2:59:15 time: 0.517102 data_time: 0.060934 memory: 8713 loss_kpt: 195.462108 acc_pose: 0.846045 loss: 195.462108 2022/10/13 02:23:16 - mmengine - INFO - Epoch(train) [173][550/586] lr: 5.000000e-04 eta: 2:58:51 time: 0.516423 data_time: 0.059468 memory: 8713 loss_kpt: 195.400511 acc_pose: 0.901490 loss: 195.400511 2022/10/13 02:23:34 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 02:24:01 - mmengine - INFO - Epoch(train) [174][50/586] lr: 5.000000e-04 eta: 2:58:05 time: 0.543889 data_time: 0.071040 memory: 8713 loss_kpt: 195.661649 acc_pose: 0.835090 loss: 195.661649 2022/10/13 02:24:27 - mmengine - INFO - Epoch(train) [174][100/586] lr: 5.000000e-04 eta: 2:57:40 time: 0.519292 data_time: 0.050477 memory: 8713 loss_kpt: 193.097923 acc_pose: 0.864483 loss: 193.097923 2022/10/13 02:24:54 - mmengine - INFO - Epoch(train) [174][150/586] lr: 5.000000e-04 eta: 2:57:16 time: 0.531121 data_time: 0.059438 memory: 8713 loss_kpt: 195.437034 acc_pose: 0.896892 loss: 195.437034 2022/10/13 02:25:19 - mmengine - INFO - Epoch(train) [174][200/586] lr: 5.000000e-04 eta: 2:56:52 time: 0.508762 data_time: 0.055046 memory: 8713 loss_kpt: 201.221112 acc_pose: 0.869390 loss: 201.221112 2022/10/13 02:25:45 - mmengine - INFO - Epoch(train) [174][250/586] lr: 5.000000e-04 eta: 2:56:27 time: 0.503755 data_time: 0.059530 memory: 8713 loss_kpt: 193.259082 acc_pose: 0.877297 loss: 193.259082 2022/10/13 02:26:10 - mmengine - INFO - Epoch(train) [174][300/586] lr: 5.000000e-04 eta: 2:56:02 time: 0.513922 data_time: 0.054802 memory: 8713 loss_kpt: 194.751047 acc_pose: 0.838686 loss: 194.751047 2022/10/13 02:26:36 - mmengine - INFO - Epoch(train) [174][350/586] lr: 5.000000e-04 eta: 2:55:38 time: 0.518062 data_time: 0.061337 memory: 8713 loss_kpt: 193.435941 acc_pose: 0.849434 loss: 193.435941 2022/10/13 02:27:02 - mmengine - INFO - Epoch(train) [174][400/586] lr: 5.000000e-04 eta: 2:55:14 time: 0.513689 data_time: 0.055750 memory: 8713 loss_kpt: 200.632805 acc_pose: 0.813161 loss: 200.632805 2022/10/13 02:27:28 - mmengine - INFO - Epoch(train) [174][450/586] lr: 5.000000e-04 eta: 2:54:49 time: 0.514882 data_time: 0.058843 memory: 8713 loss_kpt: 198.102792 acc_pose: 0.804847 loss: 198.102792 2022/10/13 02:27:53 - mmengine - INFO - Epoch(train) [174][500/586] lr: 5.000000e-04 eta: 2:54:24 time: 0.504712 data_time: 0.055138 memory: 8713 loss_kpt: 198.435103 acc_pose: 0.899920 loss: 198.435103 2022/10/13 02:28:19 - mmengine - INFO - Epoch(train) [174][550/586] lr: 5.000000e-04 eta: 2:54:00 time: 0.517490 data_time: 0.058142 memory: 8713 loss_kpt: 193.526115 acc_pose: 0.858573 loss: 193.526115 2022/10/13 02:28:37 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 02:28:56 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 02:29:04 - mmengine - INFO - Epoch(train) [175][50/586] lr: 5.000000e-04 eta: 2:53:14 time: 0.541238 data_time: 0.078737 memory: 8713 loss_kpt: 197.674931 acc_pose: 0.824880 loss: 197.674931 2022/10/13 02:29:30 - mmengine - INFO - Epoch(train) [175][100/586] lr: 5.000000e-04 eta: 2:52:50 time: 0.522235 data_time: 0.056358 memory: 8713 loss_kpt: 195.159879 acc_pose: 0.867888 loss: 195.159879 2022/10/13 02:29:56 - mmengine - INFO - Epoch(train) [175][150/586] lr: 5.000000e-04 eta: 2:52:25 time: 0.518317 data_time: 0.059397 memory: 8713 loss_kpt: 194.579771 acc_pose: 0.901565 loss: 194.579771 2022/10/13 02:30:22 - mmengine - INFO - Epoch(train) [175][200/586] lr: 5.000000e-04 eta: 2:52:01 time: 0.518856 data_time: 0.059834 memory: 8713 loss_kpt: 195.619965 acc_pose: 0.895528 loss: 195.619965 2022/10/13 02:30:49 - mmengine - INFO - Epoch(train) [175][250/586] lr: 5.000000e-04 eta: 2:51:37 time: 0.529742 data_time: 0.060074 memory: 8713 loss_kpt: 193.762433 acc_pose: 0.837657 loss: 193.762433 2022/10/13 02:31:16 - mmengine - INFO - Epoch(train) [175][300/586] lr: 5.000000e-04 eta: 2:51:12 time: 0.541060 data_time: 0.059117 memory: 8713 loss_kpt: 193.705493 acc_pose: 0.849609 loss: 193.705493 2022/10/13 02:31:43 - mmengine - INFO - Epoch(train) [175][350/586] lr: 5.000000e-04 eta: 2:50:48 time: 0.544718 data_time: 0.059508 memory: 8713 loss_kpt: 197.221428 acc_pose: 0.864947 loss: 197.221428 2022/10/13 02:32:09 - mmengine - INFO - Epoch(train) [175][400/586] lr: 5.000000e-04 eta: 2:50:24 time: 0.532507 data_time: 0.055945 memory: 8713 loss_kpt: 194.361648 acc_pose: 0.850009 loss: 194.361648 2022/10/13 02:32:36 - mmengine - INFO - Epoch(train) [175][450/586] lr: 5.000000e-04 eta: 2:50:00 time: 0.528428 data_time: 0.060421 memory: 8713 loss_kpt: 196.482866 acc_pose: 0.924635 loss: 196.482866 2022/10/13 02:33:02 - mmengine - INFO - Epoch(train) [175][500/586] lr: 5.000000e-04 eta: 2:49:35 time: 0.520399 data_time: 0.056222 memory: 8713 loss_kpt: 195.980196 acc_pose: 0.808968 loss: 195.980196 2022/10/13 02:33:29 - mmengine - INFO - Epoch(train) [175][550/586] lr: 5.000000e-04 eta: 2:49:11 time: 0.530934 data_time: 0.059313 memory: 8713 loss_kpt: 197.202815 acc_pose: 0.895234 loss: 197.202815 2022/10/13 02:33:47 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 02:34:14 - mmengine - INFO - Epoch(train) [176][50/586] lr: 5.000000e-04 eta: 2:48:25 time: 0.525205 data_time: 0.070569 memory: 8713 loss_kpt: 198.427489 acc_pose: 0.809110 loss: 198.427489 2022/10/13 02:34:40 - mmengine - INFO - Epoch(train) [176][100/586] lr: 5.000000e-04 eta: 2:48:01 time: 0.515010 data_time: 0.060187 memory: 8713 loss_kpt: 196.481543 acc_pose: 0.861781 loss: 196.481543 2022/10/13 02:35:05 - mmengine - INFO - Epoch(train) [176][150/586] lr: 5.000000e-04 eta: 2:47:36 time: 0.512945 data_time: 0.063915 memory: 8713 loss_kpt: 193.658256 acc_pose: 0.860526 loss: 193.658256 2022/10/13 02:35:31 - mmengine - INFO - Epoch(train) [176][200/586] lr: 5.000000e-04 eta: 2:47:12 time: 0.519383 data_time: 0.060332 memory: 8713 loss_kpt: 195.865349 acc_pose: 0.833209 loss: 195.865349 2022/10/13 02:35:57 - mmengine - INFO - Epoch(train) [176][250/586] lr: 5.000000e-04 eta: 2:46:47 time: 0.508921 data_time: 0.065575 memory: 8713 loss_kpt: 199.035712 acc_pose: 0.890034 loss: 199.035712 2022/10/13 02:36:22 - mmengine - INFO - Epoch(train) [176][300/586] lr: 5.000000e-04 eta: 2:46:23 time: 0.508431 data_time: 0.058518 memory: 8713 loss_kpt: 195.884544 acc_pose: 0.846065 loss: 195.884544 2022/10/13 02:36:48 - mmengine - INFO - Epoch(train) [176][350/586] lr: 5.000000e-04 eta: 2:45:58 time: 0.510449 data_time: 0.059233 memory: 8713 loss_kpt: 195.761897 acc_pose: 0.833648 loss: 195.761897 2022/10/13 02:37:13 - mmengine - INFO - Epoch(train) [176][400/586] lr: 5.000000e-04 eta: 2:45:34 time: 0.517310 data_time: 0.057861 memory: 8713 loss_kpt: 189.590168 acc_pose: 0.830237 loss: 189.590168 2022/10/13 02:37:39 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 02:37:39 - mmengine - INFO - Epoch(train) [176][450/586] lr: 5.000000e-04 eta: 2:45:09 time: 0.515523 data_time: 0.057322 memory: 8713 loss_kpt: 192.805394 acc_pose: 0.861628 loss: 192.805394 2022/10/13 02:38:05 - mmengine - INFO - Epoch(train) [176][500/586] lr: 5.000000e-04 eta: 2:44:44 time: 0.507187 data_time: 0.055830 memory: 8713 loss_kpt: 198.477855 acc_pose: 0.840833 loss: 198.477855 2022/10/13 02:38:31 - mmengine - INFO - Epoch(train) [176][550/586] lr: 5.000000e-04 eta: 2:44:20 time: 0.533136 data_time: 0.060103 memory: 8713 loss_kpt: 193.475351 acc_pose: 0.830016 loss: 193.475351 2022/10/13 02:38:50 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 02:39:17 - mmengine - INFO - Epoch(train) [177][50/586] lr: 5.000000e-04 eta: 2:43:35 time: 0.538489 data_time: 0.074656 memory: 8713 loss_kpt: 194.137531 acc_pose: 0.877466 loss: 194.137531 2022/10/13 02:39:43 - mmengine - INFO - Epoch(train) [177][100/586] lr: 5.000000e-04 eta: 2:43:10 time: 0.526586 data_time: 0.058178 memory: 8713 loss_kpt: 194.530048 acc_pose: 0.780131 loss: 194.530048 2022/10/13 02:40:10 - mmengine - INFO - Epoch(train) [177][150/586] lr: 5.000000e-04 eta: 2:42:46 time: 0.533031 data_time: 0.060739 memory: 8713 loss_kpt: 193.045740 acc_pose: 0.831055 loss: 193.045740 2022/10/13 02:40:36 - mmengine - INFO - Epoch(train) [177][200/586] lr: 5.000000e-04 eta: 2:42:22 time: 0.529707 data_time: 0.058742 memory: 8713 loss_kpt: 191.848277 acc_pose: 0.891900 loss: 191.848277 2022/10/13 02:41:04 - mmengine - INFO - Epoch(train) [177][250/586] lr: 5.000000e-04 eta: 2:41:57 time: 0.547846 data_time: 0.060812 memory: 8713 loss_kpt: 193.430605 acc_pose: 0.839105 loss: 193.430605 2022/10/13 02:41:31 - mmengine - INFO - Epoch(train) [177][300/586] lr: 5.000000e-04 eta: 2:41:33 time: 0.541401 data_time: 0.055025 memory: 8713 loss_kpt: 193.665182 acc_pose: 0.849856 loss: 193.665182 2022/10/13 02:41:59 - mmengine - INFO - Epoch(train) [177][350/586] lr: 5.000000e-04 eta: 2:41:09 time: 0.565605 data_time: 0.061171 memory: 8713 loss_kpt: 192.824295 acc_pose: 0.908954 loss: 192.824295 2022/10/13 02:42:27 - mmengine - INFO - Epoch(train) [177][400/586] lr: 5.000000e-04 eta: 2:40:45 time: 0.557000 data_time: 0.055806 memory: 8713 loss_kpt: 194.575536 acc_pose: 0.936631 loss: 194.575536 2022/10/13 02:42:55 - mmengine - INFO - Epoch(train) [177][450/586] lr: 5.000000e-04 eta: 2:40:21 time: 0.560611 data_time: 0.062867 memory: 8713 loss_kpt: 191.928777 acc_pose: 0.831436 loss: 191.928777 2022/10/13 02:43:23 - mmengine - INFO - Epoch(train) [177][500/586] lr: 5.000000e-04 eta: 2:39:57 time: 0.556324 data_time: 0.055266 memory: 8713 loss_kpt: 195.003351 acc_pose: 0.813695 loss: 195.003351 2022/10/13 02:43:50 - mmengine - INFO - Epoch(train) [177][550/586] lr: 5.000000e-04 eta: 2:39:33 time: 0.545975 data_time: 0.059872 memory: 8713 loss_kpt: 192.987008 acc_pose: 0.940171 loss: 192.987008 2022/10/13 02:44:10 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 02:44:36 - mmengine - INFO - Epoch(train) [178][50/586] lr: 5.000000e-04 eta: 2:38:47 time: 0.531269 data_time: 0.064720 memory: 8713 loss_kpt: 193.559497 acc_pose: 0.875573 loss: 193.559497 2022/10/13 02:45:03 - mmengine - INFO - Epoch(train) [178][100/586] lr: 5.000000e-04 eta: 2:38:23 time: 0.528952 data_time: 0.061351 memory: 8713 loss_kpt: 193.871234 acc_pose: 0.861582 loss: 193.871234 2022/10/13 02:45:29 - mmengine - INFO - Epoch(train) [178][150/586] lr: 5.000000e-04 eta: 2:37:58 time: 0.528402 data_time: 0.060627 memory: 8713 loss_kpt: 193.206135 acc_pose: 0.881162 loss: 193.206135 2022/10/13 02:45:55 - mmengine - INFO - Epoch(train) [178][200/586] lr: 5.000000e-04 eta: 2:37:34 time: 0.517074 data_time: 0.058479 memory: 8713 loss_kpt: 192.564747 acc_pose: 0.835256 loss: 192.564747 2022/10/13 02:46:21 - mmengine - INFO - Epoch(train) [178][250/586] lr: 5.000000e-04 eta: 2:37:10 time: 0.524352 data_time: 0.057911 memory: 8713 loss_kpt: 192.779359 acc_pose: 0.858132 loss: 192.779359 2022/10/13 02:46:36 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 02:46:48 - mmengine - INFO - Epoch(train) [178][300/586] lr: 5.000000e-04 eta: 2:36:45 time: 0.528291 data_time: 0.058238 memory: 8713 loss_kpt: 190.123210 acc_pose: 0.818241 loss: 190.123210 2022/10/13 02:47:14 - mmengine - INFO - Epoch(train) [178][350/586] lr: 5.000000e-04 eta: 2:36:21 time: 0.523294 data_time: 0.055937 memory: 8713 loss_kpt: 191.858043 acc_pose: 0.900009 loss: 191.858043 2022/10/13 02:47:39 - mmengine - INFO - Epoch(train) [178][400/586] lr: 5.000000e-04 eta: 2:35:56 time: 0.510668 data_time: 0.053052 memory: 8713 loss_kpt: 195.743547 acc_pose: 0.828654 loss: 195.743547 2022/10/13 02:48:05 - mmengine - INFO - Epoch(train) [178][450/586] lr: 5.000000e-04 eta: 2:35:32 time: 0.521339 data_time: 0.059706 memory: 8713 loss_kpt: 197.032502 acc_pose: 0.877276 loss: 197.032502 2022/10/13 02:48:32 - mmengine - INFO - Epoch(train) [178][500/586] lr: 5.000000e-04 eta: 2:35:07 time: 0.529934 data_time: 0.058506 memory: 8713 loss_kpt: 192.942069 acc_pose: 0.895572 loss: 192.942069 2022/10/13 02:48:58 - mmengine - INFO - Epoch(train) [178][550/586] lr: 5.000000e-04 eta: 2:34:43 time: 0.529634 data_time: 0.061621 memory: 8713 loss_kpt: 195.734094 acc_pose: 0.862216 loss: 195.734094 2022/10/13 02:49:17 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 02:49:45 - mmengine - INFO - Epoch(train) [179][50/586] lr: 5.000000e-04 eta: 2:33:58 time: 0.548231 data_time: 0.073828 memory: 8713 loss_kpt: 190.565309 acc_pose: 0.857112 loss: 190.565309 2022/10/13 02:50:11 - mmengine - INFO - Epoch(train) [179][100/586] lr: 5.000000e-04 eta: 2:33:33 time: 0.525405 data_time: 0.052260 memory: 8713 loss_kpt: 196.438136 acc_pose: 0.863996 loss: 196.438136 2022/10/13 02:50:38 - mmengine - INFO - Epoch(train) [179][150/586] lr: 5.000000e-04 eta: 2:33:09 time: 0.530123 data_time: 0.061364 memory: 8713 loss_kpt: 196.188050 acc_pose: 0.875377 loss: 196.188050 2022/10/13 02:51:04 - mmengine - INFO - Epoch(train) [179][200/586] lr: 5.000000e-04 eta: 2:32:45 time: 0.528661 data_time: 0.056282 memory: 8713 loss_kpt: 196.742828 acc_pose: 0.800486 loss: 196.742828 2022/10/13 02:51:31 - mmengine - INFO - Epoch(train) [179][250/586] lr: 5.000000e-04 eta: 2:32:20 time: 0.534741 data_time: 0.057618 memory: 8713 loss_kpt: 192.708687 acc_pose: 0.847278 loss: 192.708687 2022/10/13 02:51:57 - mmengine - INFO - Epoch(train) [179][300/586] lr: 5.000000e-04 eta: 2:31:56 time: 0.517480 data_time: 0.058220 memory: 8713 loss_kpt: 190.396067 acc_pose: 0.761380 loss: 190.396067 2022/10/13 02:52:23 - mmengine - INFO - Epoch(train) [179][350/586] lr: 5.000000e-04 eta: 2:31:31 time: 0.530311 data_time: 0.061509 memory: 8713 loss_kpt: 193.187672 acc_pose: 0.852766 loss: 193.187672 2022/10/13 02:52:50 - mmengine - INFO - Epoch(train) [179][400/586] lr: 5.000000e-04 eta: 2:31:07 time: 0.534248 data_time: 0.064815 memory: 8713 loss_kpt: 194.035189 acc_pose: 0.864986 loss: 194.035189 2022/10/13 02:53:17 - mmengine - INFO - Epoch(train) [179][450/586] lr: 5.000000e-04 eta: 2:30:43 time: 0.536977 data_time: 0.062959 memory: 8713 loss_kpt: 195.612308 acc_pose: 0.853073 loss: 195.612308 2022/10/13 02:53:43 - mmengine - INFO - Epoch(train) [179][500/586] lr: 5.000000e-04 eta: 2:30:18 time: 0.528475 data_time: 0.057192 memory: 8713 loss_kpt: 197.743030 acc_pose: 0.900547 loss: 197.743030 2022/10/13 02:54:10 - mmengine - INFO - Epoch(train) [179][550/586] lr: 5.000000e-04 eta: 2:29:54 time: 0.526469 data_time: 0.063506 memory: 8713 loss_kpt: 197.644871 acc_pose: 0.856108 loss: 197.644871 2022/10/13 02:54:28 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 02:54:55 - mmengine - INFO - Epoch(train) [180][50/586] lr: 5.000000e-04 eta: 2:29:09 time: 0.540673 data_time: 0.073452 memory: 8713 loss_kpt: 195.145678 acc_pose: 0.870364 loss: 195.145678 2022/10/13 02:55:21 - mmengine - INFO - Epoch(train) [180][100/586] lr: 5.000000e-04 eta: 2:28:44 time: 0.525328 data_time: 0.058667 memory: 8713 loss_kpt: 191.292666 acc_pose: 0.868970 loss: 191.292666 2022/10/13 02:55:25 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 02:55:48 - mmengine - INFO - Epoch(train) [180][150/586] lr: 5.000000e-04 eta: 2:28:20 time: 0.535399 data_time: 0.065012 memory: 8713 loss_kpt: 192.948391 acc_pose: 0.902969 loss: 192.948391 2022/10/13 02:56:14 - mmengine - INFO - Epoch(train) [180][200/586] lr: 5.000000e-04 eta: 2:27:55 time: 0.527673 data_time: 0.066748 memory: 8713 loss_kpt: 192.401075 acc_pose: 0.882137 loss: 192.401075 2022/10/13 02:56:41 - mmengine - INFO - Epoch(train) [180][250/586] lr: 5.000000e-04 eta: 2:27:31 time: 0.535416 data_time: 0.069169 memory: 8713 loss_kpt: 191.460982 acc_pose: 0.864304 loss: 191.460982 2022/10/13 02:57:08 - mmengine - INFO - Epoch(train) [180][300/586] lr: 5.000000e-04 eta: 2:27:07 time: 0.525750 data_time: 0.057974 memory: 8713 loss_kpt: 197.588660 acc_pose: 0.824137 loss: 197.588660 2022/10/13 02:57:34 - mmengine - INFO - Epoch(train) [180][350/586] lr: 5.000000e-04 eta: 2:26:42 time: 0.535729 data_time: 0.060012 memory: 8713 loss_kpt: 192.485923 acc_pose: 0.847672 loss: 192.485923 2022/10/13 02:58:01 - mmengine - INFO - Epoch(train) [180][400/586] lr: 5.000000e-04 eta: 2:26:18 time: 0.536970 data_time: 0.064471 memory: 8713 loss_kpt: 193.036936 acc_pose: 0.865589 loss: 193.036936 2022/10/13 02:58:28 - mmengine - INFO - Epoch(train) [180][450/586] lr: 5.000000e-04 eta: 2:25:54 time: 0.540145 data_time: 0.066257 memory: 8713 loss_kpt: 193.700071 acc_pose: 0.836450 loss: 193.700071 2022/10/13 02:58:54 - mmengine - INFO - Epoch(train) [180][500/586] lr: 5.000000e-04 eta: 2:25:29 time: 0.520686 data_time: 0.059157 memory: 8713 loss_kpt: 195.415975 acc_pose: 0.845386 loss: 195.415975 2022/10/13 02:59:22 - mmengine - INFO - Epoch(train) [180][550/586] lr: 5.000000e-04 eta: 2:25:05 time: 0.550541 data_time: 0.065768 memory: 8713 loss_kpt: 195.300018 acc_pose: 0.892024 loss: 195.300018 2022/10/13 02:59:41 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 02:59:41 - mmengine - INFO - Saving checkpoint at 180 epochs 2022/10/13 02:59:54 - mmengine - INFO - Epoch(val) [180][50/407] eta: 0:01:12 time: 0.203881 data_time: 0.013182 memory: 8713 2022/10/13 03:00:04 - mmengine - INFO - Epoch(val) [180][100/407] eta: 0:00:59 time: 0.194987 data_time: 0.008103 memory: 1759 2022/10/13 03:00:14 - mmengine - INFO - Epoch(val) [180][150/407] eta: 0:00:50 time: 0.194970 data_time: 0.008210 memory: 1759 2022/10/13 03:00:24 - mmengine - INFO - Epoch(val) [180][200/407] eta: 0:00:40 time: 0.195472 data_time: 0.009258 memory: 1759 2022/10/13 03:00:33 - mmengine - INFO - Epoch(val) [180][250/407] eta: 0:00:30 time: 0.194692 data_time: 0.007687 memory: 1759 2022/10/13 03:00:43 - mmengine - INFO - Epoch(val) [180][300/407] eta: 0:00:20 time: 0.193460 data_time: 0.007951 memory: 1759 2022/10/13 03:00:53 - mmengine - INFO - Epoch(val) [180][350/407] eta: 0:00:11 time: 0.193566 data_time: 0.007707 memory: 1759 2022/10/13 03:01:02 - mmengine - INFO - Epoch(val) [180][400/407] eta: 0:00:01 time: 0.188591 data_time: 0.007934 memory: 1759 2022/10/13 03:01:16 - mmengine - INFO - Evaluating CocoMetric... 2022/10/13 03:01:33 - mmengine - INFO - Epoch(val) [180][407/407] coco/AP: 0.744241 coco/AP .5: 0.897925 coco/AP .75: 0.817734 coco/AP (M): 0.709503 coco/AP (L): 0.808599 coco/AR: 0.807872 coco/AR .5: 0.938602 coco/AR .75: 0.868545 coco/AR (M): 0.763753 coco/AR (L): 0.869008 2022/10/13 03:01:33 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/liqikai/openmmlab/pt112cu113py38/mmpose/work_dirs/20221012/rsn2x/best_coco/AP_epoch_160.pth is removed 2022/10/13 03:01:35 - mmengine - INFO - The best checkpoint with 0.7442 coco/AP at 180 epoch is saved to best_coco/AP_epoch_180.pth. 2022/10/13 03:02:02 - mmengine - INFO - Epoch(train) [181][50/586] lr: 5.000000e-04 eta: 2:24:20 time: 0.544097 data_time: 0.075084 memory: 8713 loss_kpt: 190.900532 acc_pose: 0.866244 loss: 190.900532 2022/10/13 03:02:30 - mmengine - INFO - Epoch(train) [181][100/586] lr: 5.000000e-04 eta: 2:23:56 time: 0.553859 data_time: 0.060143 memory: 8713 loss_kpt: 194.477337 acc_pose: 0.849621 loss: 194.477337 2022/10/13 03:02:57 - mmengine - INFO - Epoch(train) [181][150/586] lr: 5.000000e-04 eta: 2:23:31 time: 0.544955 data_time: 0.064747 memory: 8713 loss_kpt: 197.143142 acc_pose: 0.895690 loss: 197.143142 2022/10/13 03:03:25 - mmengine - INFO - Epoch(train) [181][200/586] lr: 5.000000e-04 eta: 2:23:07 time: 0.557869 data_time: 0.063935 memory: 8713 loss_kpt: 195.040906 acc_pose: 0.858775 loss: 195.040906 2022/10/13 03:03:52 - mmengine - INFO - Epoch(train) [181][250/586] lr: 5.000000e-04 eta: 2:22:43 time: 0.547423 data_time: 0.063826 memory: 8713 loss_kpt: 195.798198 acc_pose: 0.863408 loss: 195.798198 2022/10/13 03:04:20 - mmengine - INFO - Epoch(train) [181][300/586] lr: 5.000000e-04 eta: 2:22:19 time: 0.554697 data_time: 0.064425 memory: 8713 loss_kpt: 191.004789 acc_pose: 0.869428 loss: 191.004789 2022/10/13 03:04:47 - mmengine - INFO - Epoch(train) [181][350/586] lr: 5.000000e-04 eta: 2:21:54 time: 0.547039 data_time: 0.057660 memory: 8713 loss_kpt: 192.069490 acc_pose: 0.866743 loss: 192.069490 2022/10/13 03:05:15 - mmengine - INFO - Epoch(train) [181][400/586] lr: 5.000000e-04 eta: 2:21:30 time: 0.553418 data_time: 0.060700 memory: 8713 loss_kpt: 194.862896 acc_pose: 0.789274 loss: 194.862896 2022/10/13 03:05:43 - mmengine - INFO - Epoch(train) [181][450/586] lr: 5.000000e-04 eta: 2:21:06 time: 0.562875 data_time: 0.060035 memory: 8713 loss_kpt: 198.301115 acc_pose: 0.848897 loss: 198.301115 2022/10/13 03:06:10 - mmengine - INFO - Epoch(train) [181][500/586] lr: 5.000000e-04 eta: 2:20:42 time: 0.540995 data_time: 0.059516 memory: 8713 loss_kpt: 195.341805 acc_pose: 0.906189 loss: 195.341805 2022/10/13 03:06:21 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 03:06:37 - mmengine - INFO - Epoch(train) [181][550/586] lr: 5.000000e-04 eta: 2:20:17 time: 0.538380 data_time: 0.064392 memory: 8713 loss_kpt: 194.704966 acc_pose: 0.816756 loss: 194.704966 2022/10/13 03:06:56 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 03:07:23 - mmengine - INFO - Epoch(train) [182][50/586] lr: 5.000000e-04 eta: 2:19:32 time: 0.533534 data_time: 0.071059 memory: 8713 loss_kpt: 193.793088 acc_pose: 0.895865 loss: 193.793088 2022/10/13 03:07:50 - mmengine - INFO - Epoch(train) [182][100/586] lr: 5.000000e-04 eta: 2:19:08 time: 0.546741 data_time: 0.061210 memory: 8713 loss_kpt: 192.587245 acc_pose: 0.847302 loss: 192.587245 2022/10/13 03:08:18 - mmengine - INFO - Epoch(train) [182][150/586] lr: 5.000000e-04 eta: 2:18:44 time: 0.549859 data_time: 0.063707 memory: 8713 loss_kpt: 195.003781 acc_pose: 0.875597 loss: 195.003781 2022/10/13 03:08:45 - mmengine - INFO - Epoch(train) [182][200/586] lr: 5.000000e-04 eta: 2:18:19 time: 0.542649 data_time: 0.062170 memory: 8713 loss_kpt: 193.857232 acc_pose: 0.877628 loss: 193.857232 2022/10/13 03:09:11 - mmengine - INFO - Epoch(train) [182][250/586] lr: 5.000000e-04 eta: 2:17:55 time: 0.528565 data_time: 0.059740 memory: 8713 loss_kpt: 191.735818 acc_pose: 0.830061 loss: 191.735818 2022/10/13 03:09:38 - mmengine - INFO - Epoch(train) [182][300/586] lr: 5.000000e-04 eta: 2:17:31 time: 0.530349 data_time: 0.064256 memory: 8713 loss_kpt: 198.027802 acc_pose: 0.867437 loss: 198.027802 2022/10/13 03:10:05 - mmengine - INFO - Epoch(train) [182][350/586] lr: 5.000000e-04 eta: 2:17:06 time: 0.554257 data_time: 0.067706 memory: 8713 loss_kpt: 196.353238 acc_pose: 0.903464 loss: 196.353238 2022/10/13 03:10:34 - mmengine - INFO - Epoch(train) [182][400/586] lr: 5.000000e-04 eta: 2:16:42 time: 0.563418 data_time: 0.058098 memory: 8713 loss_kpt: 192.080113 acc_pose: 0.857679 loss: 192.080113 2022/10/13 03:11:01 - mmengine - INFO - Epoch(train) [182][450/586] lr: 5.000000e-04 eta: 2:16:18 time: 0.551990 data_time: 0.063569 memory: 8713 loss_kpt: 190.770746 acc_pose: 0.834441 loss: 190.770746 2022/10/13 03:11:29 - mmengine - INFO - Epoch(train) [182][500/586] lr: 5.000000e-04 eta: 2:15:54 time: 0.560569 data_time: 0.058092 memory: 8713 loss_kpt: 193.888900 acc_pose: 0.844784 loss: 193.888900 2022/10/13 03:11:57 - mmengine - INFO - Epoch(train) [182][550/586] lr: 5.000000e-04 eta: 2:15:29 time: 0.556596 data_time: 0.064985 memory: 8713 loss_kpt: 191.916063 acc_pose: 0.927289 loss: 191.916063 2022/10/13 03:12:17 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 03:12:44 - mmengine - INFO - Epoch(train) [183][50/586] lr: 5.000000e-04 eta: 2:14:45 time: 0.539918 data_time: 0.080193 memory: 8713 loss_kpt: 193.139805 acc_pose: 0.859724 loss: 193.139805 2022/10/13 03:13:10 - mmengine - INFO - Epoch(train) [183][100/586] lr: 5.000000e-04 eta: 2:14:20 time: 0.511677 data_time: 0.059173 memory: 8713 loss_kpt: 192.750185 acc_pose: 0.834041 loss: 192.750185 2022/10/13 03:13:36 - mmengine - INFO - Epoch(train) [183][150/586] lr: 5.000000e-04 eta: 2:13:55 time: 0.515308 data_time: 0.064129 memory: 8713 loss_kpt: 195.321322 acc_pose: 0.855922 loss: 195.321322 2022/10/13 03:14:01 - mmengine - INFO - Epoch(train) [183][200/586] lr: 5.000000e-04 eta: 2:13:31 time: 0.508169 data_time: 0.060863 memory: 8713 loss_kpt: 194.752750 acc_pose: 0.815476 loss: 194.752750 2022/10/13 03:14:27 - mmengine - INFO - Epoch(train) [183][250/586] lr: 5.000000e-04 eta: 2:13:06 time: 0.521163 data_time: 0.064294 memory: 8713 loss_kpt: 195.969423 acc_pose: 0.902481 loss: 195.969423 2022/10/13 03:14:52 - mmengine - INFO - Epoch(train) [183][300/586] lr: 5.000000e-04 eta: 2:12:42 time: 0.500984 data_time: 0.064643 memory: 8713 loss_kpt: 193.630127 acc_pose: 0.880157 loss: 193.630127 2022/10/13 03:15:16 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 03:15:18 - mmengine - INFO - Epoch(train) [183][350/586] lr: 5.000000e-04 eta: 2:12:17 time: 0.502490 data_time: 0.061389 memory: 8713 loss_kpt: 192.411003 acc_pose: 0.846228 loss: 192.411003 2022/10/13 03:15:43 - mmengine - INFO - Epoch(train) [183][400/586] lr: 5.000000e-04 eta: 2:11:52 time: 0.510061 data_time: 0.062769 memory: 8713 loss_kpt: 193.072305 acc_pose: 0.833109 loss: 193.072305 2022/10/13 03:16:09 - mmengine - INFO - Epoch(train) [183][450/586] lr: 5.000000e-04 eta: 2:11:28 time: 0.513479 data_time: 0.071501 memory: 8713 loss_kpt: 194.885477 acc_pose: 0.803117 loss: 194.885477 2022/10/13 03:16:35 - mmengine - INFO - Epoch(train) [183][500/586] lr: 5.000000e-04 eta: 2:11:03 time: 0.518792 data_time: 0.067684 memory: 8713 loss_kpt: 195.754021 acc_pose: 0.883987 loss: 195.754021 2022/10/13 03:17:01 - mmengine - INFO - Epoch(train) [183][550/586] lr: 5.000000e-04 eta: 2:10:39 time: 0.528087 data_time: 0.067855 memory: 8713 loss_kpt: 192.572144 acc_pose: 0.902197 loss: 192.572144 2022/10/13 03:17:19 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 03:17:46 - mmengine - INFO - Epoch(train) [184][50/586] lr: 5.000000e-04 eta: 2:09:54 time: 0.539314 data_time: 0.077901 memory: 8713 loss_kpt: 194.827829 acc_pose: 0.845569 loss: 194.827829 2022/10/13 03:18:13 - mmengine - INFO - Epoch(train) [184][100/586] lr: 5.000000e-04 eta: 2:09:30 time: 0.529801 data_time: 0.062993 memory: 8713 loss_kpt: 192.592085 acc_pose: 0.861699 loss: 192.592085 2022/10/13 03:18:40 - mmengine - INFO - Epoch(train) [184][150/586] lr: 5.000000e-04 eta: 2:09:05 time: 0.533730 data_time: 0.062460 memory: 8713 loss_kpt: 194.404135 acc_pose: 0.872514 loss: 194.404135 2022/10/13 03:19:06 - mmengine - INFO - Epoch(train) [184][200/586] lr: 5.000000e-04 eta: 2:08:41 time: 0.526668 data_time: 0.064134 memory: 8713 loss_kpt: 191.245950 acc_pose: 0.880049 loss: 191.245950 2022/10/13 03:19:32 - mmengine - INFO - Epoch(train) [184][250/586] lr: 5.000000e-04 eta: 2:08:16 time: 0.513204 data_time: 0.060870 memory: 8713 loss_kpt: 193.913370 acc_pose: 0.805923 loss: 193.913370 2022/10/13 03:19:58 - mmengine - INFO - Epoch(train) [184][300/586] lr: 5.000000e-04 eta: 2:07:52 time: 0.528892 data_time: 0.060367 memory: 8713 loss_kpt: 194.396217 acc_pose: 0.862516 loss: 194.396217 2022/10/13 03:20:25 - mmengine - INFO - Epoch(train) [184][350/586] lr: 5.000000e-04 eta: 2:07:27 time: 0.530585 data_time: 0.061277 memory: 8713 loss_kpt: 194.304962 acc_pose: 0.894155 loss: 194.304962 2022/10/13 03:20:50 - mmengine - INFO - Epoch(train) [184][400/586] lr: 5.000000e-04 eta: 2:07:03 time: 0.511838 data_time: 0.057433 memory: 8713 loss_kpt: 195.732721 acc_pose: 0.847391 loss: 195.732721 2022/10/13 03:21:17 - mmengine - INFO - Epoch(train) [184][450/586] lr: 5.000000e-04 eta: 2:06:38 time: 0.525748 data_time: 0.059903 memory: 8713 loss_kpt: 194.877484 acc_pose: 0.863054 loss: 194.877484 2022/10/13 03:21:43 - mmengine - INFO - Epoch(train) [184][500/586] lr: 5.000000e-04 eta: 2:06:14 time: 0.527231 data_time: 0.065564 memory: 8713 loss_kpt: 192.370961 acc_pose: 0.890210 loss: 192.370961 2022/10/13 03:22:10 - mmengine - INFO - Epoch(train) [184][550/586] lr: 5.000000e-04 eta: 2:05:49 time: 0.534886 data_time: 0.068706 memory: 8713 loss_kpt: 191.501323 acc_pose: 0.861742 loss: 191.501323 2022/10/13 03:22:29 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 03:22:55 - mmengine - INFO - Epoch(train) [185][50/586] lr: 5.000000e-04 eta: 2:05:04 time: 0.517316 data_time: 0.072731 memory: 8713 loss_kpt: 191.652225 acc_pose: 0.885406 loss: 191.652225 2022/10/13 03:23:21 - mmengine - INFO - Epoch(train) [185][100/586] lr: 5.000000e-04 eta: 2:04:40 time: 0.523056 data_time: 0.059797 memory: 8713 loss_kpt: 192.385651 acc_pose: 0.845659 loss: 192.385651 2022/10/13 03:23:47 - mmengine - INFO - Epoch(train) [185][150/586] lr: 5.000000e-04 eta: 2:04:15 time: 0.517156 data_time: 0.062162 memory: 8713 loss_kpt: 191.430641 acc_pose: 0.896088 loss: 191.430641 2022/10/13 03:24:00 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 03:24:12 - mmengine - INFO - Epoch(train) [185][200/586] lr: 5.000000e-04 eta: 2:03:51 time: 0.512622 data_time: 0.059786 memory: 8713 loss_kpt: 191.916048 acc_pose: 0.831002 loss: 191.916048 2022/10/13 03:24:38 - mmengine - INFO - Epoch(train) [185][250/586] lr: 5.000000e-04 eta: 2:03:26 time: 0.521347 data_time: 0.058991 memory: 8713 loss_kpt: 188.228303 acc_pose: 0.894705 loss: 188.228303 2022/10/13 03:25:05 - mmengine - INFO - Epoch(train) [185][300/586] lr: 5.000000e-04 eta: 2:03:02 time: 0.525737 data_time: 0.059951 memory: 8713 loss_kpt: 197.295092 acc_pose: 0.821856 loss: 197.295092 2022/10/13 03:25:31 - mmengine - INFO - Epoch(train) [185][350/586] lr: 5.000000e-04 eta: 2:02:37 time: 0.526998 data_time: 0.063474 memory: 8713 loss_kpt: 194.692112 acc_pose: 0.824466 loss: 194.692112 2022/10/13 03:25:57 - mmengine - INFO - Epoch(train) [185][400/586] lr: 5.000000e-04 eta: 2:02:13 time: 0.520761 data_time: 0.060281 memory: 8713 loss_kpt: 191.705292 acc_pose: 0.849130 loss: 191.705292 2022/10/13 03:26:23 - mmengine - INFO - Epoch(train) [185][450/586] lr: 5.000000e-04 eta: 2:01:48 time: 0.521570 data_time: 0.063576 memory: 8713 loss_kpt: 192.417694 acc_pose: 0.817230 loss: 192.417694 2022/10/13 03:26:49 - mmengine - INFO - Epoch(train) [185][500/586] lr: 5.000000e-04 eta: 2:01:24 time: 0.518626 data_time: 0.066576 memory: 8713 loss_kpt: 192.784703 acc_pose: 0.830633 loss: 192.784703 2022/10/13 03:27:15 - mmengine - INFO - Epoch(train) [185][550/586] lr: 5.000000e-04 eta: 2:00:59 time: 0.515127 data_time: 0.060335 memory: 8713 loss_kpt: 192.692953 acc_pose: 0.826664 loss: 192.692953 2022/10/13 03:27:33 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 03:28:00 - mmengine - INFO - Epoch(train) [186][50/586] lr: 5.000000e-04 eta: 2:00:14 time: 0.525165 data_time: 0.071303 memory: 8713 loss_kpt: 193.624753 acc_pose: 0.841216 loss: 193.624753 2022/10/13 03:28:26 - mmengine - INFO - Epoch(train) [186][100/586] lr: 5.000000e-04 eta: 1:59:50 time: 0.522199 data_time: 0.063038 memory: 8713 loss_kpt: 189.445464 acc_pose: 0.863279 loss: 189.445464 2022/10/13 03:28:53 - mmengine - INFO - Epoch(train) [186][150/586] lr: 5.000000e-04 eta: 1:59:25 time: 0.536948 data_time: 0.064126 memory: 8713 loss_kpt: 194.827245 acc_pose: 0.841542 loss: 194.827245 2022/10/13 03:29:20 - mmengine - INFO - Epoch(train) [186][200/586] lr: 5.000000e-04 eta: 1:59:01 time: 0.544828 data_time: 0.058347 memory: 8713 loss_kpt: 192.165655 acc_pose: 0.856708 loss: 192.165655 2022/10/13 03:29:47 - mmengine - INFO - Epoch(train) [186][250/586] lr: 5.000000e-04 eta: 1:58:37 time: 0.532973 data_time: 0.069328 memory: 8713 loss_kpt: 194.363993 acc_pose: 0.819296 loss: 194.363993 2022/10/13 03:30:13 - mmengine - INFO - Epoch(train) [186][300/586] lr: 5.000000e-04 eta: 1:58:12 time: 0.530636 data_time: 0.060917 memory: 8713 loss_kpt: 192.488481 acc_pose: 0.849923 loss: 192.488481 2022/10/13 03:30:41 - mmengine - INFO - Epoch(train) [186][350/586] lr: 5.000000e-04 eta: 1:57:48 time: 0.548094 data_time: 0.062682 memory: 8713 loss_kpt: 193.585497 acc_pose: 0.867732 loss: 193.585497 2022/10/13 03:31:08 - mmengine - INFO - Epoch(train) [186][400/586] lr: 5.000000e-04 eta: 1:57:23 time: 0.545383 data_time: 0.060889 memory: 8713 loss_kpt: 196.924610 acc_pose: 0.907728 loss: 196.924610 2022/10/13 03:31:35 - mmengine - INFO - Epoch(train) [186][450/586] lr: 5.000000e-04 eta: 1:56:59 time: 0.543549 data_time: 0.057308 memory: 8713 loss_kpt: 194.494572 acc_pose: 0.818567 loss: 194.494572 2022/10/13 03:32:02 - mmengine - INFO - Epoch(train) [186][500/586] lr: 5.000000e-04 eta: 1:56:35 time: 0.538886 data_time: 0.060101 memory: 8713 loss_kpt: 192.265490 acc_pose: 0.907076 loss: 192.265490 2022/10/13 03:32:29 - mmengine - INFO - Epoch(train) [186][550/586] lr: 5.000000e-04 eta: 1:56:10 time: 0.543113 data_time: 0.064440 memory: 8713 loss_kpt: 192.326784 acc_pose: 0.803282 loss: 192.326784 2022/10/13 03:32:48 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 03:32:51 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 03:33:16 - mmengine - INFO - Epoch(train) [187][50/586] lr: 5.000000e-04 eta: 1:55:26 time: 0.547235 data_time: 0.072633 memory: 8713 loss_kpt: 193.980410 acc_pose: 0.858378 loss: 193.980410 2022/10/13 03:33:42 - mmengine - INFO - Epoch(train) [187][100/586] lr: 5.000000e-04 eta: 1:55:01 time: 0.528158 data_time: 0.058450 memory: 8713 loss_kpt: 192.726268 acc_pose: 0.877551 loss: 192.726268 2022/10/13 03:34:08 - mmengine - INFO - Epoch(train) [187][150/586] lr: 5.000000e-04 eta: 1:54:37 time: 0.526181 data_time: 0.061587 memory: 8713 loss_kpt: 191.400703 acc_pose: 0.824927 loss: 191.400703 2022/10/13 03:34:35 - mmengine - INFO - Epoch(train) [187][200/586] lr: 5.000000e-04 eta: 1:54:12 time: 0.526620 data_time: 0.060025 memory: 8713 loss_kpt: 193.183368 acc_pose: 0.886912 loss: 193.183368 2022/10/13 03:35:01 - mmengine - INFO - Epoch(train) [187][250/586] lr: 5.000000e-04 eta: 1:53:48 time: 0.530668 data_time: 0.068382 memory: 8713 loss_kpt: 193.675576 acc_pose: 0.835525 loss: 193.675576 2022/10/13 03:35:27 - mmengine - INFO - Epoch(train) [187][300/586] lr: 5.000000e-04 eta: 1:53:23 time: 0.522246 data_time: 0.058395 memory: 8713 loss_kpt: 192.347516 acc_pose: 0.868533 loss: 192.347516 2022/10/13 03:35:54 - mmengine - INFO - Epoch(train) [187][350/586] lr: 5.000000e-04 eta: 1:52:59 time: 0.537789 data_time: 0.065192 memory: 8713 loss_kpt: 191.992943 acc_pose: 0.857822 loss: 191.992943 2022/10/13 03:36:21 - mmengine - INFO - Epoch(train) [187][400/586] lr: 5.000000e-04 eta: 1:52:34 time: 0.535724 data_time: 0.060932 memory: 8713 loss_kpt: 194.191188 acc_pose: 0.857256 loss: 194.191188 2022/10/13 03:36:48 - mmengine - INFO - Epoch(train) [187][450/586] lr: 5.000000e-04 eta: 1:52:10 time: 0.543627 data_time: 0.064627 memory: 8713 loss_kpt: 191.518207 acc_pose: 0.843671 loss: 191.518207 2022/10/13 03:37:15 - mmengine - INFO - Epoch(train) [187][500/586] lr: 5.000000e-04 eta: 1:51:45 time: 0.537630 data_time: 0.061595 memory: 8713 loss_kpt: 193.196399 acc_pose: 0.867071 loss: 193.196399 2022/10/13 03:37:42 - mmengine - INFO - Epoch(train) [187][550/586] lr: 5.000000e-04 eta: 1:51:21 time: 0.543702 data_time: 0.064034 memory: 8713 loss_kpt: 197.545061 acc_pose: 0.875273 loss: 197.545061 2022/10/13 03:38:02 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 03:38:28 - mmengine - INFO - Epoch(train) [188][50/586] lr: 5.000000e-04 eta: 1:50:36 time: 0.529709 data_time: 0.074736 memory: 8713 loss_kpt: 193.835721 acc_pose: 0.800392 loss: 193.835721 2022/10/13 03:38:54 - mmengine - INFO - Epoch(train) [188][100/586] lr: 5.000000e-04 eta: 1:50:12 time: 0.516914 data_time: 0.061883 memory: 8713 loss_kpt: 194.567995 acc_pose: 0.868844 loss: 194.567995 2022/10/13 03:39:20 - mmengine - INFO - Epoch(train) [188][150/586] lr: 5.000000e-04 eta: 1:49:47 time: 0.518839 data_time: 0.060770 memory: 8713 loss_kpt: 186.943474 acc_pose: 0.860190 loss: 186.943474 2022/10/13 03:39:46 - mmengine - INFO - Epoch(train) [188][200/586] lr: 5.000000e-04 eta: 1:49:23 time: 0.517456 data_time: 0.054226 memory: 8713 loss_kpt: 192.879884 acc_pose: 0.852846 loss: 192.879884 2022/10/13 03:40:12 - mmengine - INFO - Epoch(train) [188][250/586] lr: 5.000000e-04 eta: 1:48:58 time: 0.522256 data_time: 0.063173 memory: 8713 loss_kpt: 192.297688 acc_pose: 0.862242 loss: 192.297688 2022/10/13 03:40:37 - mmengine - INFO - Epoch(train) [188][300/586] lr: 5.000000e-04 eta: 1:48:34 time: 0.507147 data_time: 0.061159 memory: 8713 loss_kpt: 193.283052 acc_pose: 0.801077 loss: 193.283052 2022/10/13 03:41:03 - mmengine - INFO - Epoch(train) [188][350/586] lr: 5.000000e-04 eta: 1:48:09 time: 0.516169 data_time: 0.065529 memory: 8713 loss_kpt: 194.829568 acc_pose: 0.863103 loss: 194.829568 2022/10/13 03:41:29 - mmengine - INFO - Epoch(train) [188][400/586] lr: 5.000000e-04 eta: 1:47:44 time: 0.513379 data_time: 0.066077 memory: 8713 loss_kpt: 190.407439 acc_pose: 0.775015 loss: 190.407439 2022/10/13 03:41:38 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 03:41:55 - mmengine - INFO - Epoch(train) [188][450/586] lr: 5.000000e-04 eta: 1:47:20 time: 0.528848 data_time: 0.061912 memory: 8713 loss_kpt: 190.955771 acc_pose: 0.887481 loss: 190.955771 2022/10/13 03:42:21 - mmengine - INFO - Epoch(train) [188][500/586] lr: 5.000000e-04 eta: 1:46:55 time: 0.510282 data_time: 0.056509 memory: 8713 loss_kpt: 192.945890 acc_pose: 0.804145 loss: 192.945890 2022/10/13 03:42:47 - mmengine - INFO - Epoch(train) [188][550/586] lr: 5.000000e-04 eta: 1:46:31 time: 0.514081 data_time: 0.065558 memory: 8713 loss_kpt: 194.038863 acc_pose: 0.852184 loss: 194.038863 2022/10/13 03:43:05 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 03:43:32 - mmengine - INFO - Epoch(train) [189][50/586] lr: 5.000000e-04 eta: 1:45:46 time: 0.527251 data_time: 0.076324 memory: 8713 loss_kpt: 190.202144 acc_pose: 0.837412 loss: 190.202144 2022/10/13 03:43:58 - mmengine - INFO - Epoch(train) [189][100/586] lr: 5.000000e-04 eta: 1:45:22 time: 0.524766 data_time: 0.059780 memory: 8713 loss_kpt: 196.399002 acc_pose: 0.836204 loss: 196.399002 2022/10/13 03:44:25 - mmengine - INFO - Epoch(train) [189][150/586] lr: 5.000000e-04 eta: 1:44:57 time: 0.529337 data_time: 0.059447 memory: 8713 loss_kpt: 190.448564 acc_pose: 0.837948 loss: 190.448564 2022/10/13 03:44:51 - mmengine - INFO - Epoch(train) [189][200/586] lr: 5.000000e-04 eta: 1:44:33 time: 0.519619 data_time: 0.060152 memory: 8713 loss_kpt: 194.035158 acc_pose: 0.849175 loss: 194.035158 2022/10/13 03:45:17 - mmengine - INFO - Epoch(train) [189][250/586] lr: 5.000000e-04 eta: 1:44:08 time: 0.532830 data_time: 0.060512 memory: 8713 loss_kpt: 192.411377 acc_pose: 0.857571 loss: 192.411377 2022/10/13 03:45:44 - mmengine - INFO - Epoch(train) [189][300/586] lr: 5.000000e-04 eta: 1:43:44 time: 0.532966 data_time: 0.055066 memory: 8713 loss_kpt: 190.639045 acc_pose: 0.904990 loss: 190.639045 2022/10/13 03:46:10 - mmengine - INFO - Epoch(train) [189][350/586] lr: 5.000000e-04 eta: 1:43:19 time: 0.526541 data_time: 0.064070 memory: 8713 loss_kpt: 193.038464 acc_pose: 0.834615 loss: 193.038464 2022/10/13 03:46:36 - mmengine - INFO - Epoch(train) [189][400/586] lr: 5.000000e-04 eta: 1:42:55 time: 0.521979 data_time: 0.056186 memory: 8713 loss_kpt: 194.651272 acc_pose: 0.903188 loss: 194.651272 2022/10/13 03:47:03 - mmengine - INFO - Epoch(train) [189][450/586] lr: 5.000000e-04 eta: 1:42:30 time: 0.530705 data_time: 0.062362 memory: 8713 loss_kpt: 194.913776 acc_pose: 0.846349 loss: 194.913776 2022/10/13 03:47:29 - mmengine - INFO - Epoch(train) [189][500/586] lr: 5.000000e-04 eta: 1:42:06 time: 0.525938 data_time: 0.056640 memory: 8713 loss_kpt: 196.736235 acc_pose: 0.836784 loss: 196.736235 2022/10/13 03:47:56 - mmengine - INFO - Epoch(train) [189][550/586] lr: 5.000000e-04 eta: 1:41:41 time: 0.525453 data_time: 0.057655 memory: 8713 loss_kpt: 191.855256 acc_pose: 0.908985 loss: 191.855256 2022/10/13 03:48:14 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 03:48:41 - mmengine - INFO - Epoch(train) [190][50/586] lr: 5.000000e-04 eta: 1:40:57 time: 0.552229 data_time: 0.071707 memory: 8713 loss_kpt: 195.381464 acc_pose: 0.862664 loss: 195.381464 2022/10/13 03:49:08 - mmengine - INFO - Epoch(train) [190][100/586] lr: 5.000000e-04 eta: 1:40:32 time: 0.538489 data_time: 0.059073 memory: 8713 loss_kpt: 196.197574 acc_pose: 0.878821 loss: 196.197574 2022/10/13 03:49:35 - mmengine - INFO - Epoch(train) [190][150/586] lr: 5.000000e-04 eta: 1:40:08 time: 0.539261 data_time: 0.067556 memory: 8713 loss_kpt: 189.009167 acc_pose: 0.911710 loss: 189.009167 2022/10/13 03:50:02 - mmengine - INFO - Epoch(train) [190][200/586] lr: 5.000000e-04 eta: 1:39:43 time: 0.531161 data_time: 0.056601 memory: 8713 loss_kpt: 192.633151 acc_pose: 0.821046 loss: 192.633151 2022/10/13 03:50:27 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 03:50:29 - mmengine - INFO - Epoch(train) [190][250/586] lr: 5.000000e-04 eta: 1:39:19 time: 0.539735 data_time: 0.064082 memory: 8713 loss_kpt: 192.529401 acc_pose: 0.904938 loss: 192.529401 2022/10/13 03:50:55 - mmengine - INFO - Epoch(train) [190][300/586] lr: 5.000000e-04 eta: 1:38:54 time: 0.529012 data_time: 0.061416 memory: 8713 loss_kpt: 192.291661 acc_pose: 0.883524 loss: 192.291661 2022/10/13 03:51:23 - mmengine - INFO - Epoch(train) [190][350/586] lr: 5.000000e-04 eta: 1:38:30 time: 0.541666 data_time: 0.064432 memory: 8713 loss_kpt: 194.319593 acc_pose: 0.898327 loss: 194.319593 2022/10/13 03:51:50 - mmengine - INFO - Epoch(train) [190][400/586] lr: 5.000000e-04 eta: 1:38:05 time: 0.544954 data_time: 0.059060 memory: 8713 loss_kpt: 192.216681 acc_pose: 0.848596 loss: 192.216681 2022/10/13 03:52:17 - mmengine - INFO - Epoch(train) [190][450/586] lr: 5.000000e-04 eta: 1:37:41 time: 0.550252 data_time: 0.065120 memory: 8713 loss_kpt: 188.877281 acc_pose: 0.870826 loss: 188.877281 2022/10/13 03:52:45 - mmengine - INFO - Epoch(train) [190][500/586] lr: 5.000000e-04 eta: 1:37:17 time: 0.543389 data_time: 0.062300 memory: 8713 loss_kpt: 193.597849 acc_pose: 0.881322 loss: 193.597849 2022/10/13 03:53:12 - mmengine - INFO - Epoch(train) [190][550/586] lr: 5.000000e-04 eta: 1:36:52 time: 0.544517 data_time: 0.063113 memory: 8713 loss_kpt: 191.724852 acc_pose: 0.824144 loss: 191.724852 2022/10/13 03:53:31 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 03:53:31 - mmengine - INFO - Saving checkpoint at 190 epochs 2022/10/13 03:53:44 - mmengine - INFO - Epoch(val) [190][50/407] eta: 0:01:11 time: 0.201004 data_time: 0.012813 memory: 8713 2022/10/13 03:53:54 - mmengine - INFO - Epoch(val) [190][100/407] eta: 0:00:59 time: 0.192288 data_time: 0.007900 memory: 1759 2022/10/13 03:54:04 - mmengine - INFO - Epoch(val) [190][150/407] eta: 0:00:50 time: 0.195299 data_time: 0.008426 memory: 1759 2022/10/13 03:54:13 - mmengine - INFO - Epoch(val) [190][200/407] eta: 0:00:39 time: 0.193114 data_time: 0.007682 memory: 1759 2022/10/13 03:54:23 - mmengine - INFO - Epoch(val) [190][250/407] eta: 0:00:30 time: 0.193288 data_time: 0.008139 memory: 1759 2022/10/13 03:54:33 - mmengine - INFO - Epoch(val) [190][300/407] eta: 0:00:20 time: 0.191021 data_time: 0.007573 memory: 1759 2022/10/13 03:54:42 - mmengine - INFO - Epoch(val) [190][350/407] eta: 0:00:11 time: 0.195963 data_time: 0.008541 memory: 1759 2022/10/13 03:54:52 - mmengine - INFO - Epoch(val) [190][400/407] eta: 0:00:01 time: 0.190090 data_time: 0.007783 memory: 1759 2022/10/13 03:55:06 - mmengine - INFO - Evaluating CocoMetric... 2022/10/13 03:55:22 - mmengine - INFO - Epoch(val) [190][407/407] coco/AP: 0.745927 coco/AP .5: 0.898723 coco/AP .75: 0.818531 coco/AP (M): 0.711183 coco/AP (L): 0.809766 coco/AR: 0.809084 coco/AR .5: 0.938917 coco/AR .75: 0.869175 coco/AR (M): 0.765419 coco/AR (L): 0.869305 2022/10/13 03:55:22 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/liqikai/openmmlab/pt112cu113py38/mmpose/work_dirs/20221012/rsn2x/best_coco/AP_epoch_180.pth is removed 2022/10/13 03:55:24 - mmengine - INFO - The best checkpoint with 0.7459 coco/AP at 190 epoch is saved to best_coco/AP_epoch_190.pth. 2022/10/13 03:55:50 - mmengine - INFO - Epoch(train) [191][50/586] lr: 5.000000e-04 eta: 1:36:08 time: 0.511656 data_time: 0.067819 memory: 8713 loss_kpt: 190.580138 acc_pose: 0.852082 loss: 190.580138 2022/10/13 03:56:15 - mmengine - INFO - Epoch(train) [191][100/586] lr: 5.000000e-04 eta: 1:35:43 time: 0.505893 data_time: 0.060905 memory: 8713 loss_kpt: 192.495160 acc_pose: 0.830363 loss: 192.495160 2022/10/13 03:56:41 - mmengine - INFO - Epoch(train) [191][150/586] lr: 5.000000e-04 eta: 1:35:19 time: 0.520433 data_time: 0.058623 memory: 8713 loss_kpt: 188.731406 acc_pose: 0.856506 loss: 188.731406 2022/10/13 03:57:07 - mmengine - INFO - Epoch(train) [191][200/586] lr: 5.000000e-04 eta: 1:34:54 time: 0.514099 data_time: 0.061746 memory: 8713 loss_kpt: 192.402032 acc_pose: 0.819694 loss: 192.402032 2022/10/13 03:57:32 - mmengine - INFO - Epoch(train) [191][250/586] lr: 5.000000e-04 eta: 1:34:29 time: 0.503409 data_time: 0.056572 memory: 8713 loss_kpt: 191.018865 acc_pose: 0.816400 loss: 191.018865 2022/10/13 03:57:58 - mmengine - INFO - Epoch(train) [191][300/586] lr: 5.000000e-04 eta: 1:34:05 time: 0.511450 data_time: 0.056809 memory: 8713 loss_kpt: 194.259383 acc_pose: 0.894494 loss: 194.259383 2022/10/13 03:58:24 - mmengine - INFO - Epoch(train) [191][350/586] lr: 5.000000e-04 eta: 1:33:40 time: 0.517856 data_time: 0.055238 memory: 8713 loss_kpt: 190.383469 acc_pose: 0.856699 loss: 190.383469 2022/10/13 03:58:49 - mmengine - INFO - Epoch(train) [191][400/586] lr: 5.000000e-04 eta: 1:33:15 time: 0.512732 data_time: 0.056035 memory: 8713 loss_kpt: 192.191680 acc_pose: 0.874579 loss: 192.191680 2022/10/13 03:59:15 - mmengine - INFO - Epoch(train) [191][450/586] lr: 5.000000e-04 eta: 1:32:51 time: 0.522065 data_time: 0.061861 memory: 8713 loss_kpt: 193.868121 acc_pose: 0.810012 loss: 193.868121 2022/10/13 03:59:41 - mmengine - INFO - Epoch(train) [191][500/586] lr: 5.000000e-04 eta: 1:32:26 time: 0.514389 data_time: 0.055193 memory: 8713 loss_kpt: 193.075020 acc_pose: 0.928858 loss: 193.075020 2022/10/13 04:00:07 - mmengine - INFO - Epoch(train) [191][550/586] lr: 5.000000e-04 eta: 1:32:02 time: 0.514346 data_time: 0.057006 memory: 8713 loss_kpt: 195.023386 acc_pose: 0.848431 loss: 195.023386 2022/10/13 04:00:25 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 04:00:52 - mmengine - INFO - Epoch(train) [192][50/586] lr: 5.000000e-04 eta: 1:31:18 time: 0.531936 data_time: 0.073719 memory: 8713 loss_kpt: 195.471695 acc_pose: 0.896306 loss: 195.471695 2022/10/13 04:01:04 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 04:01:18 - mmengine - INFO - Epoch(train) [192][100/586] lr: 5.000000e-04 eta: 1:30:53 time: 0.519063 data_time: 0.055736 memory: 8713 loss_kpt: 194.286070 acc_pose: 0.853055 loss: 194.286070 2022/10/13 04:01:44 - mmengine - INFO - Epoch(train) [192][150/586] lr: 5.000000e-04 eta: 1:30:28 time: 0.518275 data_time: 0.056637 memory: 8713 loss_kpt: 194.259483 acc_pose: 0.821358 loss: 194.259483 2022/10/13 04:02:10 - mmengine - INFO - Epoch(train) [192][200/586] lr: 5.000000e-04 eta: 1:30:04 time: 0.523754 data_time: 0.051872 memory: 8713 loss_kpt: 190.322898 acc_pose: 0.928678 loss: 190.322898 2022/10/13 04:02:36 - mmengine - INFO - Epoch(train) [192][250/586] lr: 5.000000e-04 eta: 1:29:39 time: 0.528106 data_time: 0.063050 memory: 8713 loss_kpt: 191.462100 acc_pose: 0.847458 loss: 191.462100 2022/10/13 04:03:02 - mmengine - INFO - Epoch(train) [192][300/586] lr: 5.000000e-04 eta: 1:29:15 time: 0.516189 data_time: 0.053768 memory: 8713 loss_kpt: 195.531604 acc_pose: 0.880843 loss: 195.531604 2022/10/13 04:03:29 - mmengine - INFO - Epoch(train) [192][350/586] lr: 5.000000e-04 eta: 1:28:50 time: 0.529850 data_time: 0.060094 memory: 8713 loss_kpt: 189.776568 acc_pose: 0.862466 loss: 189.776568 2022/10/13 04:03:55 - mmengine - INFO - Epoch(train) [192][400/586] lr: 5.000000e-04 eta: 1:28:26 time: 0.522123 data_time: 0.056823 memory: 8713 loss_kpt: 194.558706 acc_pose: 0.837905 loss: 194.558706 2022/10/13 04:04:21 - mmengine - INFO - Epoch(train) [192][450/586] lr: 5.000000e-04 eta: 1:28:01 time: 0.528015 data_time: 0.059781 memory: 8713 loss_kpt: 195.130976 acc_pose: 0.887412 loss: 195.130976 2022/10/13 04:04:47 - mmengine - INFO - Epoch(train) [192][500/586] lr: 5.000000e-04 eta: 1:27:36 time: 0.519528 data_time: 0.056198 memory: 8713 loss_kpt: 194.637385 acc_pose: 0.840481 loss: 194.637385 2022/10/13 04:05:13 - mmengine - INFO - Epoch(train) [192][550/586] lr: 5.000000e-04 eta: 1:27:12 time: 0.518066 data_time: 0.060358 memory: 8713 loss_kpt: 195.660016 acc_pose: 0.889496 loss: 195.660016 2022/10/13 04:05:32 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 04:05:58 - mmengine - INFO - Epoch(train) [193][50/586] lr: 5.000000e-04 eta: 1:26:28 time: 0.521999 data_time: 0.066788 memory: 8713 loss_kpt: 199.716981 acc_pose: 0.843017 loss: 199.716981 2022/10/13 04:06:23 - mmengine - INFO - Epoch(train) [193][100/586] lr: 5.000000e-04 eta: 1:26:03 time: 0.509870 data_time: 0.054957 memory: 8713 loss_kpt: 193.660909 acc_pose: 0.887579 loss: 193.660909 2022/10/13 04:06:49 - mmengine - INFO - Epoch(train) [193][150/586] lr: 5.000000e-04 eta: 1:25:38 time: 0.517629 data_time: 0.060598 memory: 8713 loss_kpt: 191.823044 acc_pose: 0.938526 loss: 191.823044 2022/10/13 04:07:15 - mmengine - INFO - Epoch(train) [193][200/586] lr: 5.000000e-04 eta: 1:25:14 time: 0.515083 data_time: 0.056825 memory: 8713 loss_kpt: 192.396424 acc_pose: 0.849153 loss: 192.396424 2022/10/13 04:07:40 - mmengine - INFO - Epoch(train) [193][250/586] lr: 5.000000e-04 eta: 1:24:49 time: 0.507998 data_time: 0.058099 memory: 8713 loss_kpt: 193.647821 acc_pose: 0.899880 loss: 193.647821 2022/10/13 04:08:06 - mmengine - INFO - Epoch(train) [193][300/586] lr: 5.000000e-04 eta: 1:24:25 time: 0.507726 data_time: 0.051911 memory: 8713 loss_kpt: 192.270132 acc_pose: 0.840754 loss: 192.270132 2022/10/13 04:08:31 - mmengine - INFO - Epoch(train) [193][350/586] lr: 5.000000e-04 eta: 1:24:00 time: 0.510062 data_time: 0.056003 memory: 8713 loss_kpt: 191.583017 acc_pose: 0.874505 loss: 191.583017 2022/10/13 04:08:57 - mmengine - INFO - Epoch(train) [193][400/586] lr: 5.000000e-04 eta: 1:23:35 time: 0.510484 data_time: 0.054714 memory: 8713 loss_kpt: 193.499709 acc_pose: 0.840158 loss: 193.499709 2022/10/13 04:09:23 - mmengine - INFO - Epoch(train) [193][450/586] lr: 5.000000e-04 eta: 1:23:11 time: 0.513935 data_time: 0.056710 memory: 8713 loss_kpt: 191.973002 acc_pose: 0.896446 loss: 191.973002 2022/10/13 04:09:42 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 04:09:48 - mmengine - INFO - Epoch(train) [193][500/586] lr: 5.000000e-04 eta: 1:22:46 time: 0.502825 data_time: 0.055258 memory: 8713 loss_kpt: 194.455083 acc_pose: 0.896027 loss: 194.455083 2022/10/13 04:10:13 - mmengine - INFO - Epoch(train) [193][550/586] lr: 5.000000e-04 eta: 1:22:21 time: 0.511502 data_time: 0.052439 memory: 8713 loss_kpt: 192.339774 acc_pose: 0.909622 loss: 192.339774 2022/10/13 04:10:32 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 04:10:58 - mmengine - INFO - Epoch(train) [194][50/586] lr: 5.000000e-04 eta: 1:21:37 time: 0.519041 data_time: 0.066246 memory: 8713 loss_kpt: 185.982182 acc_pose: 0.834421 loss: 185.982182 2022/10/13 04:11:23 - mmengine - INFO - Epoch(train) [194][100/586] lr: 5.000000e-04 eta: 1:21:13 time: 0.502526 data_time: 0.056521 memory: 8713 loss_kpt: 191.452498 acc_pose: 0.874055 loss: 191.452498 2022/10/13 04:11:48 - mmengine - INFO - Epoch(train) [194][150/586] lr: 5.000000e-04 eta: 1:20:48 time: 0.514071 data_time: 0.058855 memory: 8713 loss_kpt: 194.891972 acc_pose: 0.844522 loss: 194.891972 2022/10/13 04:12:13 - mmengine - INFO - Epoch(train) [194][200/586] lr: 5.000000e-04 eta: 1:20:23 time: 0.498843 data_time: 0.053730 memory: 8713 loss_kpt: 191.376852 acc_pose: 0.911776 loss: 191.376852 2022/10/13 04:12:38 - mmengine - INFO - Epoch(train) [194][250/586] lr: 5.000000e-04 eta: 1:19:59 time: 0.501719 data_time: 0.055416 memory: 8713 loss_kpt: 194.147645 acc_pose: 0.848779 loss: 194.147645 2022/10/13 04:13:03 - mmengine - INFO - Epoch(train) [194][300/586] lr: 5.000000e-04 eta: 1:19:34 time: 0.495164 data_time: 0.056240 memory: 8713 loss_kpt: 195.927214 acc_pose: 0.813715 loss: 195.927214 2022/10/13 04:13:28 - mmengine - INFO - Epoch(train) [194][350/586] lr: 5.000000e-04 eta: 1:19:09 time: 0.502085 data_time: 0.058306 memory: 8713 loss_kpt: 193.320063 acc_pose: 0.864151 loss: 193.320063 2022/10/13 04:13:54 - mmengine - INFO - Epoch(train) [194][400/586] lr: 5.000000e-04 eta: 1:18:45 time: 0.503370 data_time: 0.057731 memory: 8713 loss_kpt: 188.964655 acc_pose: 0.869364 loss: 188.964655 2022/10/13 04:14:19 - mmengine - INFO - Epoch(train) [194][450/586] lr: 5.000000e-04 eta: 1:18:20 time: 0.501485 data_time: 0.053641 memory: 8713 loss_kpt: 190.231018 acc_pose: 0.785406 loss: 190.231018 2022/10/13 04:14:44 - mmengine - INFO - Epoch(train) [194][500/586] lr: 5.000000e-04 eta: 1:17:55 time: 0.500039 data_time: 0.056179 memory: 8713 loss_kpt: 190.714148 acc_pose: 0.844424 loss: 190.714148 2022/10/13 04:15:09 - mmengine - INFO - Epoch(train) [194][550/586] lr: 5.000000e-04 eta: 1:17:31 time: 0.507032 data_time: 0.059020 memory: 8713 loss_kpt: 193.082531 acc_pose: 0.825259 loss: 193.082531 2022/10/13 04:15:27 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 04:15:55 - mmengine - INFO - Epoch(train) [195][50/586] lr: 5.000000e-04 eta: 1:16:47 time: 0.552529 data_time: 0.069272 memory: 8713 loss_kpt: 196.659594 acc_pose: 0.917465 loss: 196.659594 2022/10/13 04:16:21 - mmengine - INFO - Epoch(train) [195][100/586] lr: 5.000000e-04 eta: 1:16:22 time: 0.535151 data_time: 0.058287 memory: 8713 loss_kpt: 191.113209 acc_pose: 0.855624 loss: 191.113209 2022/10/13 04:16:48 - mmengine - INFO - Epoch(train) [195][150/586] lr: 5.000000e-04 eta: 1:15:58 time: 0.535053 data_time: 0.060403 memory: 8713 loss_kpt: 197.732552 acc_pose: 0.817390 loss: 197.732552 2022/10/13 04:17:15 - mmengine - INFO - Epoch(train) [195][200/586] lr: 5.000000e-04 eta: 1:15:33 time: 0.533858 data_time: 0.053850 memory: 8713 loss_kpt: 191.573360 acc_pose: 0.869800 loss: 191.573360 2022/10/13 04:17:41 - mmengine - INFO - Epoch(train) [195][250/586] lr: 5.000000e-04 eta: 1:15:09 time: 0.533283 data_time: 0.057404 memory: 8713 loss_kpt: 192.730736 acc_pose: 0.857859 loss: 192.730736 2022/10/13 04:18:08 - mmengine - INFO - Epoch(train) [195][300/586] lr: 5.000000e-04 eta: 1:14:44 time: 0.530957 data_time: 0.057821 memory: 8713 loss_kpt: 189.920340 acc_pose: 0.816631 loss: 189.920340 2022/10/13 04:18:16 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 04:18:34 - mmengine - INFO - Epoch(train) [195][350/586] lr: 5.000000e-04 eta: 1:14:20 time: 0.515504 data_time: 0.054044 memory: 8713 loss_kpt: 192.951920 acc_pose: 0.876019 loss: 192.951920 2022/10/13 04:19:00 - mmengine - INFO - Epoch(train) [195][400/586] lr: 5.000000e-04 eta: 1:13:55 time: 0.519792 data_time: 0.059761 memory: 8713 loss_kpt: 191.422355 acc_pose: 0.869761 loss: 191.422355 2022/10/13 04:19:26 - mmengine - INFO - Epoch(train) [195][450/586] lr: 5.000000e-04 eta: 1:13:30 time: 0.520815 data_time: 0.057785 memory: 8713 loss_kpt: 186.615724 acc_pose: 0.884163 loss: 186.615724 2022/10/13 04:19:51 - mmengine - INFO - Epoch(train) [195][500/586] lr: 5.000000e-04 eta: 1:13:06 time: 0.507313 data_time: 0.055005 memory: 8713 loss_kpt: 188.285927 acc_pose: 0.877955 loss: 188.285927 2022/10/13 04:20:17 - mmengine - INFO - Epoch(train) [195][550/586] lr: 5.000000e-04 eta: 1:12:41 time: 0.514217 data_time: 0.052849 memory: 8713 loss_kpt: 192.331920 acc_pose: 0.881818 loss: 192.331920 2022/10/13 04:20:35 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 04:21:01 - mmengine - INFO - Epoch(train) [196][50/586] lr: 5.000000e-04 eta: 1:11:57 time: 0.520572 data_time: 0.071707 memory: 8713 loss_kpt: 193.561842 acc_pose: 0.884624 loss: 193.561842 2022/10/13 04:21:27 - mmengine - INFO - Epoch(train) [196][100/586] lr: 5.000000e-04 eta: 1:11:33 time: 0.510299 data_time: 0.056304 memory: 8713 loss_kpt: 194.420849 acc_pose: 0.904450 loss: 194.420849 2022/10/13 04:21:52 - mmengine - INFO - Epoch(train) [196][150/586] lr: 5.000000e-04 eta: 1:11:08 time: 0.507770 data_time: 0.059897 memory: 8713 loss_kpt: 190.222497 acc_pose: 0.856228 loss: 190.222497 2022/10/13 04:22:17 - mmengine - INFO - Epoch(train) [196][200/586] lr: 5.000000e-04 eta: 1:10:43 time: 0.497872 data_time: 0.055191 memory: 8713 loss_kpt: 191.687933 acc_pose: 0.866244 loss: 191.687933 2022/10/13 04:22:43 - mmengine - INFO - Epoch(train) [196][250/586] lr: 5.000000e-04 eta: 1:10:19 time: 0.514642 data_time: 0.061166 memory: 8713 loss_kpt: 192.403763 acc_pose: 0.851680 loss: 192.403763 2022/10/13 04:23:08 - mmengine - INFO - Epoch(train) [196][300/586] lr: 5.000000e-04 eta: 1:09:54 time: 0.502071 data_time: 0.055147 memory: 8713 loss_kpt: 190.791514 acc_pose: 0.892920 loss: 190.791514 2022/10/13 04:23:33 - mmengine - INFO - Epoch(train) [196][350/586] lr: 5.000000e-04 eta: 1:09:29 time: 0.507045 data_time: 0.061726 memory: 8713 loss_kpt: 186.109350 acc_pose: 0.897002 loss: 186.109350 2022/10/13 04:23:59 - mmengine - INFO - Epoch(train) [196][400/586] lr: 5.000000e-04 eta: 1:09:05 time: 0.508091 data_time: 0.057274 memory: 8713 loss_kpt: 192.817967 acc_pose: 0.883998 loss: 192.817967 2022/10/13 04:24:24 - mmengine - INFO - Epoch(train) [196][450/586] lr: 5.000000e-04 eta: 1:08:40 time: 0.509970 data_time: 0.058510 memory: 8713 loss_kpt: 191.741341 acc_pose: 0.872723 loss: 191.741341 2022/10/13 04:24:49 - mmengine - INFO - Epoch(train) [196][500/586] lr: 5.000000e-04 eta: 1:08:15 time: 0.500675 data_time: 0.053330 memory: 8713 loss_kpt: 191.706893 acc_pose: 0.855781 loss: 191.706893 2022/10/13 04:25:15 - mmengine - INFO - Epoch(train) [196][550/586] lr: 5.000000e-04 eta: 1:07:51 time: 0.505681 data_time: 0.059370 memory: 8713 loss_kpt: 194.795138 acc_pose: 0.847411 loss: 194.795138 2022/10/13 04:25:33 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 04:25:59 - mmengine - INFO - Epoch(train) [197][50/586] lr: 5.000000e-04 eta: 1:07:07 time: 0.523866 data_time: 0.073606 memory: 8713 loss_kpt: 191.935719 acc_pose: 0.860997 loss: 191.935719 2022/10/13 04:26:25 - mmengine - INFO - Epoch(train) [197][100/586] lr: 5.000000e-04 eta: 1:06:43 time: 0.516522 data_time: 0.053669 memory: 8713 loss_kpt: 194.636919 acc_pose: 0.878642 loss: 194.636919 2022/10/13 04:26:48 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 04:26:51 - mmengine - INFO - Epoch(train) [197][150/586] lr: 5.000000e-04 eta: 1:06:18 time: 0.525009 data_time: 0.060882 memory: 8713 loss_kpt: 189.588603 acc_pose: 0.873689 loss: 189.588603 2022/10/13 04:27:17 - mmengine - INFO - Epoch(train) [197][200/586] lr: 5.000000e-04 eta: 1:05:53 time: 0.522151 data_time: 0.057547 memory: 8713 loss_kpt: 192.670976 acc_pose: 0.857515 loss: 192.670976 2022/10/13 04:27:43 - mmengine - INFO - Epoch(train) [197][250/586] lr: 5.000000e-04 eta: 1:05:29 time: 0.525267 data_time: 0.064962 memory: 8713 loss_kpt: 195.284725 acc_pose: 0.835274 loss: 195.284725 2022/10/13 04:28:09 - mmengine - INFO - Epoch(train) [197][300/586] lr: 5.000000e-04 eta: 1:05:04 time: 0.522220 data_time: 0.054557 memory: 8713 loss_kpt: 192.854958 acc_pose: 0.855549 loss: 192.854958 2022/10/13 04:28:35 - mmengine - INFO - Epoch(train) [197][350/586] lr: 5.000000e-04 eta: 1:04:40 time: 0.517383 data_time: 0.061199 memory: 8713 loss_kpt: 192.604030 acc_pose: 0.805129 loss: 192.604030 2022/10/13 04:29:02 - mmengine - INFO - Epoch(train) [197][400/586] lr: 5.000000e-04 eta: 1:04:15 time: 0.533123 data_time: 0.059297 memory: 8713 loss_kpt: 191.673592 acc_pose: 0.779198 loss: 191.673592 2022/10/13 04:29:29 - mmengine - INFO - Epoch(train) [197][450/586] lr: 5.000000e-04 eta: 1:03:50 time: 0.534313 data_time: 0.057266 memory: 8713 loss_kpt: 191.142758 acc_pose: 0.772288 loss: 191.142758 2022/10/13 04:29:55 - mmengine - INFO - Epoch(train) [197][500/586] lr: 5.000000e-04 eta: 1:03:26 time: 0.531759 data_time: 0.055878 memory: 8713 loss_kpt: 190.824938 acc_pose: 0.746125 loss: 190.824938 2022/10/13 04:30:22 - mmengine - INFO - Epoch(train) [197][550/586] lr: 5.000000e-04 eta: 1:03:01 time: 0.540505 data_time: 0.064055 memory: 8713 loss_kpt: 191.929097 acc_pose: 0.915448 loss: 191.929097 2022/10/13 04:30:41 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 04:31:08 - mmengine - INFO - Epoch(train) [198][50/586] lr: 5.000000e-04 eta: 1:02:18 time: 0.537727 data_time: 0.073912 memory: 8713 loss_kpt: 190.424629 acc_pose: 0.844071 loss: 190.424629 2022/10/13 04:31:34 - mmengine - INFO - Epoch(train) [198][100/586] lr: 5.000000e-04 eta: 1:01:53 time: 0.515979 data_time: 0.056211 memory: 8713 loss_kpt: 193.226607 acc_pose: 0.863096 loss: 193.226607 2022/10/13 04:31:59 - mmengine - INFO - Epoch(train) [198][150/586] lr: 5.000000e-04 eta: 1:01:28 time: 0.510020 data_time: 0.055876 memory: 8713 loss_kpt: 196.246115 acc_pose: 0.837945 loss: 196.246115 2022/10/13 04:32:25 - mmengine - INFO - Epoch(train) [198][200/586] lr: 5.000000e-04 eta: 1:01:04 time: 0.505382 data_time: 0.057788 memory: 8713 loss_kpt: 195.594417 acc_pose: 0.909460 loss: 195.594417 2022/10/13 04:32:50 - mmengine - INFO - Epoch(train) [198][250/586] lr: 5.000000e-04 eta: 1:00:39 time: 0.511670 data_time: 0.052923 memory: 8713 loss_kpt: 193.213681 acc_pose: 0.857129 loss: 193.213681 2022/10/13 04:33:16 - mmengine - INFO - Epoch(train) [198][300/586] lr: 5.000000e-04 eta: 1:00:15 time: 0.518571 data_time: 0.058233 memory: 8713 loss_kpt: 192.736776 acc_pose: 0.778902 loss: 192.736776 2022/10/13 04:33:42 - mmengine - INFO - Epoch(train) [198][350/586] lr: 5.000000e-04 eta: 0:59:50 time: 0.506446 data_time: 0.058455 memory: 8713 loss_kpt: 190.953380 acc_pose: 0.868220 loss: 190.953380 2022/10/13 04:34:07 - mmengine - INFO - Epoch(train) [198][400/586] lr: 5.000000e-04 eta: 0:59:25 time: 0.500730 data_time: 0.052057 memory: 8713 loss_kpt: 194.117553 acc_pose: 0.909266 loss: 194.117553 2022/10/13 04:34:32 - mmengine - INFO - Epoch(train) [198][450/586] lr: 5.000000e-04 eta: 0:59:01 time: 0.505234 data_time: 0.058430 memory: 8713 loss_kpt: 194.564832 acc_pose: 0.872717 loss: 194.564832 2022/10/13 04:34:57 - mmengine - INFO - Epoch(train) [198][500/586] lr: 5.000000e-04 eta: 0:58:36 time: 0.502897 data_time: 0.055521 memory: 8713 loss_kpt: 193.419286 acc_pose: 0.814129 loss: 193.419286 2022/10/13 04:35:23 - mmengine - INFO - Epoch(train) [198][550/586] lr: 5.000000e-04 eta: 0:58:11 time: 0.521440 data_time: 0.061803 memory: 8713 loss_kpt: 192.300816 acc_pose: 0.838898 loss: 192.300816 2022/10/13 04:35:27 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 04:35:41 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 04:36:07 - mmengine - INFO - Epoch(train) [199][50/586] lr: 5.000000e-04 eta: 0:57:28 time: 0.526230 data_time: 0.071164 memory: 8713 loss_kpt: 192.364121 acc_pose: 0.746438 loss: 192.364121 2022/10/13 04:36:33 - mmengine - INFO - Epoch(train) [199][100/586] lr: 5.000000e-04 eta: 0:57:03 time: 0.525210 data_time: 0.054622 memory: 8713 loss_kpt: 191.107148 acc_pose: 0.853254 loss: 191.107148 2022/10/13 04:36:59 - mmengine - INFO - Epoch(train) [199][150/586] lr: 5.000000e-04 eta: 0:56:39 time: 0.508422 data_time: 0.053447 memory: 8713 loss_kpt: 190.151560 acc_pose: 0.862773 loss: 190.151560 2022/10/13 04:37:25 - mmengine - INFO - Epoch(train) [199][200/586] lr: 5.000000e-04 eta: 0:56:14 time: 0.516708 data_time: 0.057553 memory: 8713 loss_kpt: 193.828808 acc_pose: 0.793951 loss: 193.828808 2022/10/13 04:37:51 - mmengine - INFO - Epoch(train) [199][250/586] lr: 5.000000e-04 eta: 0:55:49 time: 0.527444 data_time: 0.055087 memory: 8713 loss_kpt: 195.135784 acc_pose: 0.862005 loss: 195.135784 2022/10/13 04:38:17 - mmengine - INFO - Epoch(train) [199][300/586] lr: 5.000000e-04 eta: 0:55:25 time: 0.527168 data_time: 0.056746 memory: 8713 loss_kpt: 193.642122 acc_pose: 0.835868 loss: 193.642122 2022/10/13 04:38:43 - mmengine - INFO - Epoch(train) [199][350/586] lr: 5.000000e-04 eta: 0:55:00 time: 0.511743 data_time: 0.059394 memory: 8713 loss_kpt: 191.869317 acc_pose: 0.802012 loss: 191.869317 2022/10/13 04:39:09 - mmengine - INFO - Epoch(train) [199][400/586] lr: 5.000000e-04 eta: 0:54:35 time: 0.527118 data_time: 0.054466 memory: 8713 loss_kpt: 194.156758 acc_pose: 0.887522 loss: 194.156758 2022/10/13 04:39:36 - mmengine - INFO - Epoch(train) [199][450/586] lr: 5.000000e-04 eta: 0:54:11 time: 0.526650 data_time: 0.058247 memory: 8713 loss_kpt: 192.902232 acc_pose: 0.858324 loss: 192.902232 2022/10/13 04:40:02 - mmengine - INFO - Epoch(train) [199][500/586] lr: 5.000000e-04 eta: 0:53:46 time: 0.524388 data_time: 0.057991 memory: 8713 loss_kpt: 191.995854 acc_pose: 0.827430 loss: 191.995854 2022/10/13 04:40:28 - mmengine - INFO - Epoch(train) [199][550/586] lr: 5.000000e-04 eta: 0:53:22 time: 0.513647 data_time: 0.062123 memory: 8713 loss_kpt: 187.164499 acc_pose: 0.801780 loss: 187.164499 2022/10/13 04:40:46 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 04:41:13 - mmengine - INFO - Epoch(train) [200][50/586] lr: 5.000000e-04 eta: 0:52:38 time: 0.536947 data_time: 0.073989 memory: 8713 loss_kpt: 190.262785 acc_pose: 0.866470 loss: 190.262785 2022/10/13 04:41:39 - mmengine - INFO - Epoch(train) [200][100/586] lr: 5.000000e-04 eta: 0:52:14 time: 0.521826 data_time: 0.056479 memory: 8713 loss_kpt: 193.365708 acc_pose: 0.828316 loss: 193.365708 2022/10/13 04:42:05 - mmengine - INFO - Epoch(train) [200][150/586] lr: 5.000000e-04 eta: 0:51:49 time: 0.513837 data_time: 0.063170 memory: 8713 loss_kpt: 192.521246 acc_pose: 0.847535 loss: 192.521246 2022/10/13 04:42:31 - mmengine - INFO - Epoch(train) [200][200/586] lr: 5.000000e-04 eta: 0:51:24 time: 0.518253 data_time: 0.064782 memory: 8713 loss_kpt: 189.930551 acc_pose: 0.876736 loss: 189.930551 2022/10/13 04:42:57 - mmengine - INFO - Epoch(train) [200][250/586] lr: 5.000000e-04 eta: 0:51:00 time: 0.522438 data_time: 0.060663 memory: 8713 loss_kpt: 194.713228 acc_pose: 0.862895 loss: 194.713228 2022/10/13 04:43:24 - mmengine - INFO - Epoch(train) [200][300/586] lr: 5.000000e-04 eta: 0:50:35 time: 0.527296 data_time: 0.060250 memory: 8713 loss_kpt: 195.431273 acc_pose: 0.817701 loss: 195.431273 2022/10/13 04:43:50 - mmengine - INFO - Epoch(train) [200][350/586] lr: 5.000000e-04 eta: 0:50:11 time: 0.526199 data_time: 0.054187 memory: 8713 loss_kpt: 188.431182 acc_pose: 0.841293 loss: 188.431182 2022/10/13 04:44:09 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 04:44:16 - mmengine - INFO - Epoch(train) [200][400/586] lr: 5.000000e-04 eta: 0:49:46 time: 0.525561 data_time: 0.062924 memory: 8713 loss_kpt: 189.146647 acc_pose: 0.860922 loss: 189.146647 2022/10/13 04:44:42 - mmengine - INFO - Epoch(train) [200][450/586] lr: 5.000000e-04 eta: 0:49:21 time: 0.521659 data_time: 0.057919 memory: 8713 loss_kpt: 190.668628 acc_pose: 0.839327 loss: 190.668628 2022/10/13 04:45:08 - mmengine - INFO - Epoch(train) [200][500/586] lr: 5.000000e-04 eta: 0:48:57 time: 0.517995 data_time: 0.058579 memory: 8713 loss_kpt: 196.115130 acc_pose: 0.894632 loss: 196.115130 2022/10/13 04:45:34 - mmengine - INFO - Epoch(train) [200][550/586] lr: 5.000000e-04 eta: 0:48:32 time: 0.518110 data_time: 0.057836 memory: 8713 loss_kpt: 192.017628 acc_pose: 0.878859 loss: 192.017628 2022/10/13 04:45:52 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 04:45:52 - mmengine - INFO - Saving checkpoint at 200 epochs 2022/10/13 04:46:06 - mmengine - INFO - Epoch(val) [200][50/407] eta: 0:01:12 time: 0.202218 data_time: 0.013365 memory: 8713 2022/10/13 04:46:16 - mmengine - INFO - Epoch(val) [200][100/407] eta: 0:00:59 time: 0.192684 data_time: 0.008201 memory: 1759 2022/10/13 04:46:26 - mmengine - INFO - Epoch(val) [200][150/407] eta: 0:00:52 time: 0.202610 data_time: 0.011843 memory: 1759 2022/10/13 04:46:35 - mmengine - INFO - Epoch(val) [200][200/407] eta: 0:00:40 time: 0.194353 data_time: 0.008044 memory: 1759 2022/10/13 04:46:45 - mmengine - INFO - Epoch(val) [200][250/407] eta: 0:00:30 time: 0.192760 data_time: 0.008044 memory: 1759 2022/10/13 04:46:55 - mmengine - INFO - Epoch(val) [200][300/407] eta: 0:00:20 time: 0.194957 data_time: 0.008024 memory: 1759 2022/10/13 04:47:05 - mmengine - INFO - Epoch(val) [200][350/407] eta: 0:00:11 time: 0.194836 data_time: 0.007967 memory: 1759 2022/10/13 04:47:14 - mmengine - INFO - Epoch(val) [200][400/407] eta: 0:00:01 time: 0.190365 data_time: 0.007978 memory: 1759 2022/10/13 04:47:28 - mmengine - INFO - Evaluating CocoMetric... 2022/10/13 04:47:44 - mmengine - INFO - Epoch(val) [200][407/407] coco/AP: 0.746062 coco/AP .5: 0.899098 coco/AP .75: 0.821157 coco/AP (M): 0.712927 coco/AP (L): 0.809481 coco/AR: 0.809336 coco/AR .5: 0.939232 coco/AR .75: 0.870749 coco/AR (M): 0.765310 coco/AR (L): 0.870197 2022/10/13 04:47:44 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/liqikai/openmmlab/pt112cu113py38/mmpose/work_dirs/20221012/rsn2x/best_coco/AP_epoch_190.pth is removed 2022/10/13 04:47:46 - mmengine - INFO - The best checkpoint with 0.7461 coco/AP at 200 epoch is saved to best_coco/AP_epoch_200.pth. 2022/10/13 04:48:13 - mmengine - INFO - Epoch(train) [201][50/586] lr: 5.000000e-05 eta: 0:47:49 time: 0.531582 data_time: 0.065764 memory: 8713 loss_kpt: 189.628652 acc_pose: 0.830377 loss: 189.628652 2022/10/13 04:48:38 - mmengine - INFO - Epoch(train) [201][100/586] lr: 5.000000e-05 eta: 0:47:24 time: 0.512770 data_time: 0.056292 memory: 8713 loss_kpt: 195.344937 acc_pose: 0.836888 loss: 195.344937 2022/10/13 04:49:04 - mmengine - INFO - Epoch(train) [201][150/586] lr: 5.000000e-05 eta: 0:46:59 time: 0.522699 data_time: 0.060704 memory: 8713 loss_kpt: 192.903612 acc_pose: 0.901976 loss: 192.903612 2022/10/13 04:49:31 - mmengine - INFO - Epoch(train) [201][200/586] lr: 5.000000e-05 eta: 0:46:35 time: 0.522710 data_time: 0.062470 memory: 8713 loss_kpt: 191.131060 acc_pose: 0.855374 loss: 191.131060 2022/10/13 04:49:57 - mmengine - INFO - Epoch(train) [201][250/586] lr: 5.000000e-05 eta: 0:46:10 time: 0.526258 data_time: 0.060759 memory: 8713 loss_kpt: 190.392816 acc_pose: 0.897900 loss: 190.392816 2022/10/13 04:50:22 - mmengine - INFO - Epoch(train) [201][300/586] lr: 5.000000e-05 eta: 0:45:46 time: 0.510566 data_time: 0.054799 memory: 8713 loss_kpt: 192.053353 acc_pose: 0.874775 loss: 192.053353 2022/10/13 04:50:48 - mmengine - INFO - Epoch(train) [201][350/586] lr: 5.000000e-05 eta: 0:45:21 time: 0.507615 data_time: 0.053996 memory: 8713 loss_kpt: 192.045712 acc_pose: 0.880726 loss: 192.045712 2022/10/13 04:51:13 - mmengine - INFO - Epoch(train) [201][400/586] lr: 5.000000e-05 eta: 0:44:56 time: 0.504423 data_time: 0.055396 memory: 8713 loss_kpt: 192.008140 acc_pose: 0.870744 loss: 192.008140 2022/10/13 04:51:38 - mmengine - INFO - Epoch(train) [201][450/586] lr: 5.000000e-05 eta: 0:44:32 time: 0.507348 data_time: 0.057910 memory: 8713 loss_kpt: 193.995042 acc_pose: 0.894571 loss: 193.995042 2022/10/13 04:52:03 - mmengine - INFO - Epoch(train) [201][500/586] lr: 5.000000e-05 eta: 0:44:07 time: 0.500284 data_time: 0.058330 memory: 8713 loss_kpt: 192.793101 acc_pose: 0.902248 loss: 192.793101 2022/10/13 04:52:29 - mmengine - INFO - Epoch(train) [201][550/586] lr: 5.000000e-05 eta: 0:43:42 time: 0.507147 data_time: 0.057660 memory: 8713 loss_kpt: 191.063335 acc_pose: 0.877694 loss: 191.063335 2022/10/13 04:52:47 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 04:53:14 - mmengine - INFO - Epoch(train) [202][50/586] lr: 5.000000e-05 eta: 0:42:59 time: 0.542533 data_time: 0.064136 memory: 8713 loss_kpt: 194.112826 acc_pose: 0.812421 loss: 194.112826 2022/10/13 04:53:40 - mmengine - INFO - Epoch(train) [202][100/586] lr: 5.000000e-05 eta: 0:42:34 time: 0.518831 data_time: 0.060233 memory: 8713 loss_kpt: 194.379606 acc_pose: 0.830022 loss: 194.379606 2022/10/13 04:54:06 - mmengine - INFO - Epoch(train) [202][150/586] lr: 5.000000e-05 eta: 0:42:10 time: 0.512978 data_time: 0.053790 memory: 8713 loss_kpt: 191.269914 acc_pose: 0.873409 loss: 191.269914 2022/10/13 04:54:32 - mmengine - INFO - Epoch(train) [202][200/586] lr: 5.000000e-05 eta: 0:41:45 time: 0.513602 data_time: 0.056678 memory: 8713 loss_kpt: 190.919419 acc_pose: 0.830150 loss: 190.919419 2022/10/13 04:54:39 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 04:54:57 - mmengine - INFO - Epoch(train) [202][250/586] lr: 5.000000e-05 eta: 0:41:20 time: 0.515366 data_time: 0.059147 memory: 8713 loss_kpt: 192.026943 acc_pose: 0.861920 loss: 192.026943 2022/10/13 04:55:23 - mmengine - INFO - Epoch(train) [202][300/586] lr: 5.000000e-05 eta: 0:40:56 time: 0.521864 data_time: 0.056763 memory: 8713 loss_kpt: 188.664198 acc_pose: 0.879590 loss: 188.664198 2022/10/13 04:55:51 - mmengine - INFO - Epoch(train) [202][350/586] lr: 5.000000e-05 eta: 0:40:31 time: 0.542671 data_time: 0.059005 memory: 8713 loss_kpt: 191.126798 acc_pose: 0.898148 loss: 191.126798 2022/10/13 04:56:18 - mmengine - INFO - Epoch(train) [202][400/586] lr: 5.000000e-05 eta: 0:40:07 time: 0.538695 data_time: 0.054138 memory: 8713 loss_kpt: 191.598660 acc_pose: 0.822274 loss: 191.598660 2022/10/13 04:56:45 - mmengine - INFO - Epoch(train) [202][450/586] lr: 5.000000e-05 eta: 0:39:42 time: 0.542188 data_time: 0.058799 memory: 8713 loss_kpt: 194.717910 acc_pose: 0.851322 loss: 194.717910 2022/10/13 04:57:11 - mmengine - INFO - Epoch(train) [202][500/586] lr: 5.000000e-05 eta: 0:39:17 time: 0.532868 data_time: 0.062194 memory: 8713 loss_kpt: 193.873213 acc_pose: 0.913589 loss: 193.873213 2022/10/13 04:57:38 - mmengine - INFO - Epoch(train) [202][550/586] lr: 5.000000e-05 eta: 0:38:53 time: 0.527531 data_time: 0.058520 memory: 8713 loss_kpt: 191.342259 acc_pose: 0.903624 loss: 191.342259 2022/10/13 04:57:56 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 04:58:23 - mmengine - INFO - Epoch(train) [203][50/586] lr: 5.000000e-05 eta: 0:38:10 time: 0.540384 data_time: 0.069427 memory: 8713 loss_kpt: 189.771982 acc_pose: 0.921042 loss: 189.771982 2022/10/13 04:58:50 - mmengine - INFO - Epoch(train) [203][100/586] lr: 5.000000e-05 eta: 0:37:45 time: 0.537049 data_time: 0.056538 memory: 8713 loss_kpt: 191.293583 acc_pose: 0.857147 loss: 191.293583 2022/10/13 04:59:18 - mmengine - INFO - Epoch(train) [203][150/586] lr: 5.000000e-05 eta: 0:37:21 time: 0.553543 data_time: 0.059564 memory: 8713 loss_kpt: 186.294164 acc_pose: 0.867413 loss: 186.294164 2022/10/13 04:59:45 - mmengine - INFO - Epoch(train) [203][200/586] lr: 5.000000e-05 eta: 0:36:56 time: 0.545768 data_time: 0.057751 memory: 8713 loss_kpt: 191.506806 acc_pose: 0.883558 loss: 191.506806 2022/10/13 05:00:13 - mmengine - INFO - Epoch(train) [203][250/586] lr: 5.000000e-05 eta: 0:36:31 time: 0.547185 data_time: 0.057104 memory: 8713 loss_kpt: 187.499529 acc_pose: 0.863061 loss: 187.499529 2022/10/13 05:00:41 - mmengine - INFO - Epoch(train) [203][300/586] lr: 5.000000e-05 eta: 0:36:07 time: 0.561128 data_time: 0.060743 memory: 8713 loss_kpt: 192.801512 acc_pose: 0.885253 loss: 192.801512 2022/10/13 05:01:09 - mmengine - INFO - Epoch(train) [203][350/586] lr: 5.000000e-05 eta: 0:35:42 time: 0.556742 data_time: 0.060077 memory: 8713 loss_kpt: 192.959659 acc_pose: 0.866376 loss: 192.959659 2022/10/13 05:01:37 - mmengine - INFO - Epoch(train) [203][400/586] lr: 5.000000e-05 eta: 0:35:18 time: 0.567068 data_time: 0.060968 memory: 8713 loss_kpt: 194.846186 acc_pose: 0.897730 loss: 194.846186 2022/10/13 05:02:05 - mmengine - INFO - Epoch(train) [203][450/586] lr: 5.000000e-05 eta: 0:34:53 time: 0.571334 data_time: 0.059426 memory: 8713 loss_kpt: 188.754194 acc_pose: 0.848559 loss: 188.754194 2022/10/13 05:02:34 - mmengine - INFO - Epoch(train) [203][500/586] lr: 5.000000e-05 eta: 0:34:29 time: 0.570695 data_time: 0.062237 memory: 8713 loss_kpt: 192.494679 acc_pose: 0.862781 loss: 192.494679 2022/10/13 05:03:02 - mmengine - INFO - Epoch(train) [203][550/586] lr: 5.000000e-05 eta: 0:34:04 time: 0.565256 data_time: 0.060110 memory: 8713 loss_kpt: 194.087857 acc_pose: 0.863832 loss: 194.087857 2022/10/13 05:03:22 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 05:03:45 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 05:03:49 - mmengine - INFO - Epoch(train) [204][50/586] lr: 5.000000e-05 eta: 0:33:21 time: 0.542475 data_time: 0.068188 memory: 8713 loss_kpt: 193.001776 acc_pose: 0.873880 loss: 193.001776 2022/10/13 05:04:17 - mmengine - INFO - Epoch(train) [204][100/586] lr: 5.000000e-05 eta: 0:32:56 time: 0.543403 data_time: 0.059472 memory: 8713 loss_kpt: 193.419140 acc_pose: 0.895456 loss: 193.419140 2022/10/13 05:04:44 - mmengine - INFO - Epoch(train) [204][150/586] lr: 5.000000e-05 eta: 0:32:32 time: 0.547167 data_time: 0.053932 memory: 8713 loss_kpt: 190.512162 acc_pose: 0.810729 loss: 190.512162 2022/10/13 05:05:11 - mmengine - INFO - Epoch(train) [204][200/586] lr: 5.000000e-05 eta: 0:32:07 time: 0.543098 data_time: 0.061917 memory: 8713 loss_kpt: 192.655226 acc_pose: 0.753804 loss: 192.655226 2022/10/13 05:05:39 - mmengine - INFO - Epoch(train) [204][250/586] lr: 5.000000e-05 eta: 0:31:42 time: 0.549976 data_time: 0.059325 memory: 8713 loss_kpt: 188.196983 acc_pose: 0.868270 loss: 188.196983 2022/10/13 05:06:06 - mmengine - INFO - Epoch(train) [204][300/586] lr: 5.000000e-05 eta: 0:31:18 time: 0.541947 data_time: 0.060936 memory: 8713 loss_kpt: 187.003354 acc_pose: 0.914503 loss: 187.003354 2022/10/13 05:06:33 - mmengine - INFO - Epoch(train) [204][350/586] lr: 5.000000e-05 eta: 0:30:53 time: 0.545777 data_time: 0.058339 memory: 8713 loss_kpt: 192.088327 acc_pose: 0.857787 loss: 192.088327 2022/10/13 05:06:59 - mmengine - INFO - Epoch(train) [204][400/586] lr: 5.000000e-05 eta: 0:30:29 time: 0.528656 data_time: 0.061760 memory: 8713 loss_kpt: 187.141610 acc_pose: 0.854760 loss: 187.141610 2022/10/13 05:07:26 - mmengine - INFO - Epoch(train) [204][450/586] lr: 5.000000e-05 eta: 0:30:04 time: 0.529002 data_time: 0.060511 memory: 8713 loss_kpt: 196.122729 acc_pose: 0.877748 loss: 196.122729 2022/10/13 05:07:52 - mmengine - INFO - Epoch(train) [204][500/586] lr: 5.000000e-05 eta: 0:29:39 time: 0.520586 data_time: 0.061137 memory: 8713 loss_kpt: 192.502414 acc_pose: 0.874225 loss: 192.502414 2022/10/13 05:08:18 - mmengine - INFO - Epoch(train) [204][550/586] lr: 5.000000e-05 eta: 0:29:15 time: 0.521899 data_time: 0.060524 memory: 8713 loss_kpt: 194.000424 acc_pose: 0.810206 loss: 194.000424 2022/10/13 05:08:36 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 05:09:03 - mmengine - INFO - Epoch(train) [205][50/586] lr: 5.000000e-05 eta: 0:28:32 time: 0.529394 data_time: 0.070747 memory: 8713 loss_kpt: 192.524844 acc_pose: 0.831983 loss: 192.524844 2022/10/13 05:09:29 - mmengine - INFO - Epoch(train) [205][100/586] lr: 5.000000e-05 eta: 0:28:07 time: 0.519983 data_time: 0.064485 memory: 8713 loss_kpt: 194.172973 acc_pose: 0.897265 loss: 194.172973 2022/10/13 05:09:55 - mmengine - INFO - Epoch(train) [205][150/586] lr: 5.000000e-05 eta: 0:27:42 time: 0.529204 data_time: 0.061023 memory: 8713 loss_kpt: 191.930555 acc_pose: 0.866697 loss: 191.930555 2022/10/13 05:10:22 - mmengine - INFO - Epoch(train) [205][200/586] lr: 5.000000e-05 eta: 0:27:18 time: 0.537063 data_time: 0.063145 memory: 8713 loss_kpt: 190.745625 acc_pose: 0.876756 loss: 190.745625 2022/10/13 05:10:49 - mmengine - INFO - Epoch(train) [205][250/586] lr: 5.000000e-05 eta: 0:26:53 time: 0.531560 data_time: 0.058374 memory: 8713 loss_kpt: 194.042757 acc_pose: 0.877275 loss: 194.042757 2022/10/13 05:11:15 - mmengine - INFO - Epoch(train) [205][300/586] lr: 5.000000e-05 eta: 0:26:28 time: 0.521643 data_time: 0.054207 memory: 8713 loss_kpt: 191.541508 acc_pose: 0.857282 loss: 191.541508 2022/10/13 05:11:41 - mmengine - INFO - Epoch(train) [205][350/586] lr: 5.000000e-05 eta: 0:26:04 time: 0.531351 data_time: 0.057045 memory: 8713 loss_kpt: 189.878553 acc_pose: 0.877175 loss: 189.878553 2022/10/13 05:12:07 - mmengine - INFO - Epoch(train) [205][400/586] lr: 5.000000e-05 eta: 0:25:39 time: 0.522287 data_time: 0.056735 memory: 8713 loss_kpt: 192.958042 acc_pose: 0.854179 loss: 192.958042 2022/10/13 05:12:34 - mmengine - INFO - Epoch(train) [205][450/586] lr: 5.000000e-05 eta: 0:25:14 time: 0.538249 data_time: 0.057477 memory: 8713 loss_kpt: 190.581414 acc_pose: 0.892533 loss: 190.581414 2022/10/13 05:12:38 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 05:13:01 - mmengine - INFO - Epoch(train) [205][500/586] lr: 5.000000e-05 eta: 0:24:50 time: 0.532395 data_time: 0.056764 memory: 8713 loss_kpt: 195.158120 acc_pose: 0.933387 loss: 195.158120 2022/10/13 05:13:28 - mmengine - INFO - Epoch(train) [205][550/586] lr: 5.000000e-05 eta: 0:24:25 time: 0.538078 data_time: 0.059012 memory: 8713 loss_kpt: 191.357849 acc_pose: 0.891490 loss: 191.357849 2022/10/13 05:13:47 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 05:14:14 - mmengine - INFO - Epoch(train) [206][50/586] lr: 5.000000e-05 eta: 0:23:42 time: 0.542082 data_time: 0.065673 memory: 8713 loss_kpt: 193.275924 acc_pose: 0.892778 loss: 193.275924 2022/10/13 05:14:40 - mmengine - INFO - Epoch(train) [206][100/586] lr: 5.000000e-05 eta: 0:23:18 time: 0.518481 data_time: 0.058336 memory: 8713 loss_kpt: 194.368563 acc_pose: 0.900360 loss: 194.368563 2022/10/13 05:15:06 - mmengine - INFO - Epoch(train) [206][150/586] lr: 5.000000e-05 eta: 0:22:53 time: 0.514430 data_time: 0.055146 memory: 8713 loss_kpt: 190.977122 acc_pose: 0.884002 loss: 190.977122 2022/10/13 05:15:32 - mmengine - INFO - Epoch(train) [206][200/586] lr: 5.000000e-05 eta: 0:22:28 time: 0.516964 data_time: 0.060790 memory: 8713 loss_kpt: 190.944561 acc_pose: 0.899121 loss: 190.944561 2022/10/13 05:15:58 - mmengine - INFO - Epoch(train) [206][250/586] lr: 5.000000e-05 eta: 0:22:04 time: 0.519723 data_time: 0.057568 memory: 8713 loss_kpt: 189.880247 acc_pose: 0.895769 loss: 189.880247 2022/10/13 05:16:23 - mmengine - INFO - Epoch(train) [206][300/586] lr: 5.000000e-05 eta: 0:21:39 time: 0.509352 data_time: 0.056702 memory: 8713 loss_kpt: 196.535312 acc_pose: 0.887443 loss: 196.535312 2022/10/13 05:16:49 - mmengine - INFO - Epoch(train) [206][350/586] lr: 5.000000e-05 eta: 0:21:14 time: 0.520373 data_time: 0.056371 memory: 8713 loss_kpt: 191.326424 acc_pose: 0.868309 loss: 191.326424 2022/10/13 05:17:15 - mmengine - INFO - Epoch(train) [206][400/586] lr: 5.000000e-05 eta: 0:20:50 time: 0.519538 data_time: 0.054947 memory: 8713 loss_kpt: 190.211169 acc_pose: 0.850271 loss: 190.211169 2022/10/13 05:17:42 - mmengine - INFO - Epoch(train) [206][450/586] lr: 5.000000e-05 eta: 0:20:25 time: 0.525149 data_time: 0.063280 memory: 8713 loss_kpt: 187.213794 acc_pose: 0.844312 loss: 187.213794 2022/10/13 05:18:07 - mmengine - INFO - Epoch(train) [206][500/586] lr: 5.000000e-05 eta: 0:20:00 time: 0.517790 data_time: 0.057816 memory: 8713 loss_kpt: 194.340229 acc_pose: 0.899462 loss: 194.340229 2022/10/13 05:18:34 - mmengine - INFO - Epoch(train) [206][550/586] lr: 5.000000e-05 eta: 0:19:35 time: 0.523243 data_time: 0.062132 memory: 8713 loss_kpt: 193.334551 acc_pose: 0.803487 loss: 193.334551 2022/10/13 05:18:52 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 05:19:20 - mmengine - INFO - Epoch(train) [207][50/586] lr: 5.000000e-05 eta: 0:18:53 time: 0.546108 data_time: 0.072568 memory: 8713 loss_kpt: 193.209331 acc_pose: 0.893377 loss: 193.209331 2022/10/13 05:19:46 - mmengine - INFO - Epoch(train) [207][100/586] lr: 5.000000e-05 eta: 0:18:28 time: 0.533713 data_time: 0.055817 memory: 8713 loss_kpt: 189.541887 acc_pose: 0.877238 loss: 189.541887 2022/10/13 05:20:13 - mmengine - INFO - Epoch(train) [207][150/586] lr: 5.000000e-05 eta: 0:18:03 time: 0.541135 data_time: 0.063421 memory: 8713 loss_kpt: 194.387014 acc_pose: 0.869464 loss: 194.387014 2022/10/13 05:20:40 - mmengine - INFO - Epoch(train) [207][200/586] lr: 5.000000e-05 eta: 0:17:39 time: 0.536531 data_time: 0.052901 memory: 8713 loss_kpt: 187.813301 acc_pose: 0.872855 loss: 187.813301 2022/10/13 05:21:07 - mmengine - INFO - Epoch(train) [207][250/586] lr: 5.000000e-05 eta: 0:17:14 time: 0.539860 data_time: 0.059726 memory: 8713 loss_kpt: 192.729340 acc_pose: 0.926859 loss: 192.729340 2022/10/13 05:21:25 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 05:21:34 - mmengine - INFO - Epoch(train) [207][300/586] lr: 5.000000e-05 eta: 0:16:49 time: 0.532403 data_time: 0.056430 memory: 8713 loss_kpt: 196.550371 acc_pose: 0.819508 loss: 196.550371 2022/10/13 05:22:01 - mmengine - INFO - Epoch(train) [207][350/586] lr: 5.000000e-05 eta: 0:16:25 time: 0.534853 data_time: 0.057998 memory: 8713 loss_kpt: 192.006460 acc_pose: 0.896753 loss: 192.006460 2022/10/13 05:22:27 - mmengine - INFO - Epoch(train) [207][400/586] lr: 5.000000e-05 eta: 0:16:00 time: 0.533524 data_time: 0.055813 memory: 8713 loss_kpt: 191.162370 acc_pose: 0.870156 loss: 191.162370 2022/10/13 05:22:54 - mmengine - INFO - Epoch(train) [207][450/586] lr: 5.000000e-05 eta: 0:15:35 time: 0.537667 data_time: 0.060741 memory: 8713 loss_kpt: 188.312635 acc_pose: 0.890876 loss: 188.312635 2022/10/13 05:23:20 - mmengine - INFO - Epoch(train) [207][500/586] lr: 5.000000e-05 eta: 0:15:11 time: 0.522662 data_time: 0.060633 memory: 8713 loss_kpt: 192.265413 acc_pose: 0.861401 loss: 192.265413 2022/10/13 05:23:47 - mmengine - INFO - Epoch(train) [207][550/586] lr: 5.000000e-05 eta: 0:14:46 time: 0.525163 data_time: 0.056526 memory: 8713 loss_kpt: 192.367835 acc_pose: 0.809839 loss: 192.367835 2022/10/13 05:24:06 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 05:24:32 - mmengine - INFO - Epoch(train) [208][50/586] lr: 5.000000e-05 eta: 0:14:03 time: 0.529481 data_time: 0.065969 memory: 8713 loss_kpt: 193.127473 acc_pose: 0.883394 loss: 193.127473 2022/10/13 05:24:59 - mmengine - INFO - Epoch(train) [208][100/586] lr: 5.000000e-05 eta: 0:13:39 time: 0.536016 data_time: 0.058797 memory: 8713 loss_kpt: 192.879234 acc_pose: 0.872388 loss: 192.879234 2022/10/13 05:25:26 - mmengine - INFO - Epoch(train) [208][150/586] lr: 5.000000e-05 eta: 0:13:14 time: 0.538497 data_time: 0.060430 memory: 8713 loss_kpt: 193.798653 acc_pose: 0.929201 loss: 193.798653 2022/10/13 05:25:52 - mmengine - INFO - Epoch(train) [208][200/586] lr: 5.000000e-05 eta: 0:12:49 time: 0.519646 data_time: 0.051813 memory: 8713 loss_kpt: 189.947776 acc_pose: 0.861993 loss: 189.947776 2022/10/13 05:26:19 - mmengine - INFO - Epoch(train) [208][250/586] lr: 5.000000e-05 eta: 0:12:25 time: 0.533569 data_time: 0.059914 memory: 8713 loss_kpt: 193.247097 acc_pose: 0.904650 loss: 193.247097 2022/10/13 05:26:45 - mmengine - INFO - Epoch(train) [208][300/586] lr: 5.000000e-05 eta: 0:12:00 time: 0.536768 data_time: 0.054818 memory: 8713 loss_kpt: 192.714898 acc_pose: 0.859685 loss: 192.714898 2022/10/13 05:27:15 - mmengine - INFO - Epoch(train) [208][350/586] lr: 5.000000e-05 eta: 0:11:35 time: 0.583875 data_time: 0.065938 memory: 8713 loss_kpt: 190.225662 acc_pose: 0.810267 loss: 190.225662 2022/10/13 05:27:43 - mmengine - INFO - Epoch(train) [208][400/586] lr: 5.000000e-05 eta: 0:11:11 time: 0.568497 data_time: 0.057515 memory: 8713 loss_kpt: 190.616104 acc_pose: 0.837495 loss: 190.616104 2022/10/13 05:28:12 - mmengine - INFO - Epoch(train) [208][450/586] lr: 5.000000e-05 eta: 0:10:46 time: 0.586973 data_time: 0.063026 memory: 8713 loss_kpt: 190.277855 acc_pose: 0.867615 loss: 190.277855 2022/10/13 05:28:41 - mmengine - INFO - Epoch(train) [208][500/586] lr: 5.000000e-05 eta: 0:10:21 time: 0.577807 data_time: 0.058992 memory: 8713 loss_kpt: 191.135632 acc_pose: 0.866059 loss: 191.135632 2022/10/13 05:29:10 - mmengine - INFO - Epoch(train) [208][550/586] lr: 5.000000e-05 eta: 0:09:57 time: 0.572775 data_time: 0.064574 memory: 8713 loss_kpt: 196.140967 acc_pose: 0.732528 loss: 196.140967 2022/10/13 05:29:30 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 05:29:56 - mmengine - INFO - Epoch(train) [209][50/586] lr: 5.000000e-05 eta: 0:09:14 time: 0.525203 data_time: 0.073409 memory: 8713 loss_kpt: 194.540909 acc_pose: 0.813937 loss: 194.540909 2022/10/13 05:30:21 - mmengine - INFO - Epoch(train) [209][100/586] lr: 5.000000e-05 eta: 0:08:49 time: 0.506586 data_time: 0.056618 memory: 8713 loss_kpt: 187.361660 acc_pose: 0.906327 loss: 187.361660 2022/10/13 05:30:28 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 05:30:47 - mmengine - INFO - Epoch(train) [209][150/586] lr: 5.000000e-05 eta: 0:08:25 time: 0.517032 data_time: 0.062157 memory: 8713 loss_kpt: 192.338822 acc_pose: 0.855302 loss: 192.338822 2022/10/13 05:31:13 - mmengine - INFO - Epoch(train) [209][200/586] lr: 5.000000e-05 eta: 0:08:00 time: 0.503551 data_time: 0.049987 memory: 8713 loss_kpt: 191.788905 acc_pose: 0.844494 loss: 191.788905 2022/10/13 05:31:38 - mmengine - INFO - Epoch(train) [209][250/586] lr: 5.000000e-05 eta: 0:07:35 time: 0.511034 data_time: 0.054319 memory: 8713 loss_kpt: 192.427744 acc_pose: 0.892318 loss: 192.427744 2022/10/13 05:32:03 - mmengine - INFO - Epoch(train) [209][300/586] lr: 5.000000e-05 eta: 0:07:10 time: 0.495677 data_time: 0.055899 memory: 8713 loss_kpt: 192.113434 acc_pose: 0.855460 loss: 192.113434 2022/10/13 05:32:28 - mmengine - INFO - Epoch(train) [209][350/586] lr: 5.000000e-05 eta: 0:06:46 time: 0.496705 data_time: 0.059359 memory: 8713 loss_kpt: 190.915429 acc_pose: 0.922431 loss: 190.915429 2022/10/13 05:32:53 - mmengine - INFO - Epoch(train) [209][400/586] lr: 5.000000e-05 eta: 0:06:21 time: 0.505981 data_time: 0.053254 memory: 8713 loss_kpt: 193.075756 acc_pose: 0.859860 loss: 193.075756 2022/10/13 05:33:19 - mmengine - INFO - Epoch(train) [209][450/586] lr: 5.000000e-05 eta: 0:05:56 time: 0.512663 data_time: 0.056654 memory: 8713 loss_kpt: 192.739190 acc_pose: 0.895144 loss: 192.739190 2022/10/13 05:33:44 - mmengine - INFO - Epoch(train) [209][500/586] lr: 5.000000e-05 eta: 0:05:32 time: 0.512904 data_time: 0.056342 memory: 8713 loss_kpt: 197.345777 acc_pose: 0.832646 loss: 197.345777 2022/10/13 05:34:10 - mmengine - INFO - Epoch(train) [209][550/586] lr: 5.000000e-05 eta: 0:05:07 time: 0.510150 data_time: 0.059513 memory: 8713 loss_kpt: 192.864324 acc_pose: 0.896245 loss: 192.864324 2022/10/13 05:34:28 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 05:34:55 - mmengine - INFO - Epoch(train) [210][50/586] lr: 5.000000e-05 eta: 0:04:24 time: 0.534146 data_time: 0.072779 memory: 8713 loss_kpt: 193.706259 acc_pose: 0.882120 loss: 193.706259 2022/10/13 05:35:21 - mmengine - INFO - Epoch(train) [210][100/586] lr: 5.000000e-05 eta: 0:04:00 time: 0.526638 data_time: 0.057652 memory: 8713 loss_kpt: 191.963331 acc_pose: 0.889200 loss: 191.963331 2022/10/13 05:35:48 - mmengine - INFO - Epoch(train) [210][150/586] lr: 5.000000e-05 eta: 0:03:35 time: 0.543674 data_time: 0.065150 memory: 8713 loss_kpt: 193.283166 acc_pose: 0.928874 loss: 193.283166 2022/10/13 05:36:15 - mmengine - INFO - Epoch(train) [210][200/586] lr: 5.000000e-05 eta: 0:03:10 time: 0.538198 data_time: 0.052711 memory: 8713 loss_kpt: 192.513591 acc_pose: 0.791198 loss: 192.513591 2022/10/13 05:36:42 - mmengine - INFO - Epoch(train) [210][250/586] lr: 5.000000e-05 eta: 0:02:46 time: 0.541565 data_time: 0.063390 memory: 8713 loss_kpt: 195.066107 acc_pose: 0.835994 loss: 195.066107 2022/10/13 05:37:10 - mmengine - INFO - Epoch(train) [210][300/586] lr: 5.000000e-05 eta: 0:02:21 time: 0.550948 data_time: 0.059146 memory: 8713 loss_kpt: 191.618631 acc_pose: 0.822697 loss: 191.618631 2022/10/13 05:37:37 - mmengine - INFO - Epoch(train) [210][350/586] lr: 5.000000e-05 eta: 0:01:56 time: 0.551457 data_time: 0.060605 memory: 8713 loss_kpt: 190.631162 acc_pose: 0.863144 loss: 190.631162 2022/10/13 05:38:05 - mmengine - INFO - Epoch(train) [210][400/586] lr: 5.000000e-05 eta: 0:01:31 time: 0.549962 data_time: 0.053443 memory: 8713 loss_kpt: 190.219105 acc_pose: 0.860755 loss: 190.219105 2022/10/13 05:38:33 - mmengine - INFO - Epoch(train) [210][450/586] lr: 5.000000e-05 eta: 0:01:07 time: 0.556169 data_time: 0.059603 memory: 8713 loss_kpt: 193.315399 acc_pose: 0.872760 loss: 193.315399 2022/10/13 05:39:00 - mmengine - INFO - Epoch(train) [210][500/586] lr: 5.000000e-05 eta: 0:00:42 time: 0.542542 data_time: 0.056917 memory: 8713 loss_kpt: 191.716512 acc_pose: 0.826198 loss: 191.716512 2022/10/13 05:39:14 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 05:39:27 - mmengine - INFO - Epoch(train) [210][550/586] lr: 5.000000e-05 eta: 0:00:17 time: 0.537863 data_time: 0.062200 memory: 8713 loss_kpt: 191.846158 acc_pose: 0.783557 loss: 191.846158 2022/10/13 05:39:46 - mmengine - INFO - Exp name: td-hm_2xrsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/13 05:39:46 - mmengine - INFO - Saving checkpoint at 210 epochs 2022/10/13 05:40:00 - mmengine - INFO - Epoch(val) [210][50/407] eta: 0:01:11 time: 0.201048 data_time: 0.012819 memory: 8713 2022/10/13 05:40:10 - mmengine - INFO - Epoch(val) [210][100/407] eta: 0:01:00 time: 0.197167 data_time: 0.007927 memory: 1759 2022/10/13 05:40:20 - mmengine - INFO - Epoch(val) [210][150/407] eta: 0:00:51 time: 0.201692 data_time: 0.013068 memory: 1759 2022/10/13 05:40:29 - mmengine - INFO - Epoch(val) [210][200/407] eta: 0:00:40 time: 0.196019 data_time: 0.007613 memory: 1759 2022/10/13 05:40:39 - mmengine - INFO - Epoch(val) [210][250/407] eta: 0:00:31 time: 0.197701 data_time: 0.008361 memory: 1759 2022/10/13 05:40:49 - mmengine - INFO - Epoch(val) [210][300/407] eta: 0:00:20 time: 0.189359 data_time: 0.007898 memory: 1759 2022/10/13 05:40:58 - mmengine - INFO - Epoch(val) [210][350/407] eta: 0:00:11 time: 0.194490 data_time: 0.008517 memory: 1759 2022/10/13 05:41:08 - mmengine - INFO - Epoch(val) [210][400/407] eta: 0:00:01 time: 0.188555 data_time: 0.007663 memory: 1759 2022/10/13 05:41:22 - mmengine - INFO - Evaluating CocoMetric... 2022/10/13 05:41:37 - mmengine - INFO - Epoch(val) [210][407/407] coco/AP: 0.747538 coco/AP .5: 0.899571 coco/AP .75: 0.821138 coco/AP (M): 0.713451 coco/AP (L): 0.811427 coco/AR: 0.810107 coco/AR .5: 0.938917 coco/AR .75: 0.871537 coco/AR (M): 0.766485 coco/AR (L): 0.870420 2022/10/13 05:41:37 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/liqikai/openmmlab/pt112cu113py38/mmpose/work_dirs/20221012/rsn2x/best_coco/AP_epoch_200.pth is removed 2022/10/13 05:41:40 - mmengine - INFO - The best checkpoint with 0.7475 coco/AP at 210 epoch is saved to best_coco/AP_epoch_210.pth.