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: 1078105657 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 = [11, 9, 7, 5] codec = [ 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=1, 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=1, num_units=4, norm_cfg=dict(type='BN'), level_indices=[0, 1, 2, 3], 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) ], 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=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=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/rsn50/' 2022/10/12 11:02:53 - 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 11:02:53 - 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 11:02:53 - 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 11:02:53 - 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 11:02:53 - 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 11:02:53 - 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 11:02:53 - 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 11:02:53 - 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 11:02:57 - 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 11:02:59 - 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 11:02:59 - 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 11:02:59 - 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 11:02:59 - 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 11:02:59 - 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 11:02:59 - 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.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.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.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 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 2022/10/12 11:03:01 - mmengine - INFO - Checkpoints will be saved to /mnt/petrelfs/liqikai/openmmlab/pt112cu113py38/mmpose/work_dirs/20221012/rsn50 by HardDiskBackend. 2022/10/12 11:03:35 - mmengine - INFO - Epoch(train) [1][50/586] lr: 4.954910e-04 eta: 22:56:34 time: 0.671445 data_time: 0.229729 memory: 4465 loss_kpt: 152.620106 acc_pose: 0.050844 loss: 152.620106 2022/10/12 11:03:54 - mmengine - INFO - Epoch(train) [1][100/586] lr: 9.959920e-04 eta: 18:08:21 time: 0.390718 data_time: 0.068604 memory: 4465 loss_kpt: 152.194363 acc_pose: 0.047136 loss: 152.194363 2022/10/12 11:04:12 - mmengine - INFO - Epoch(train) [1][150/586] lr: 1.496493e-03 eta: 16:03:54 time: 0.349456 data_time: 0.057727 memory: 4465 loss_kpt: 152.137953 acc_pose: 0.088643 loss: 152.137953 2022/10/12 11:04:29 - mmengine - INFO - Epoch(train) [1][200/586] lr: 1.996994e-03 eta: 15:02:04 time: 0.350544 data_time: 0.050742 memory: 4465 loss_kpt: 150.388781 acc_pose: 0.069334 loss: 150.388781 2022/10/12 11:04:46 - mmengine - INFO - Epoch(train) [1][250/586] lr: 2.497495e-03 eta: 14:21:59 time: 0.343527 data_time: 0.049686 memory: 4465 loss_kpt: 151.386360 acc_pose: 0.149123 loss: 151.386360 2022/10/12 11:05:03 - mmengine - INFO - Epoch(train) [1][300/586] lr: 2.997996e-03 eta: 13:53:30 time: 0.338594 data_time: 0.048621 memory: 4465 loss_kpt: 150.419195 acc_pose: 0.115389 loss: 150.419195 2022/10/12 11:05:21 - mmengine - INFO - Epoch(train) [1][350/586] lr: 3.498497e-03 eta: 13:39:55 time: 0.362070 data_time: 0.051353 memory: 4465 loss_kpt: 148.102420 acc_pose: 0.114233 loss: 148.102420 2022/10/12 11:05:40 - mmengine - INFO - Epoch(train) [1][400/586] lr: 3.998998e-03 eta: 13:31:13 time: 0.368200 data_time: 0.052335 memory: 4465 loss_kpt: 147.260441 acc_pose: 0.158085 loss: 147.260441 2022/10/12 11:05:57 - mmengine - INFO - Epoch(train) [1][450/586] lr: 4.499499e-03 eta: 13:18:01 time: 0.340134 data_time: 0.053182 memory: 4465 loss_kpt: 146.681743 acc_pose: 0.231185 loss: 146.681743 2022/10/12 11:06:13 - mmengine - INFO - Epoch(train) [1][500/586] lr: 5.000000e-03 eta: 13:05:28 time: 0.330673 data_time: 0.046613 memory: 4465 loss_kpt: 145.550291 acc_pose: 0.193201 loss: 145.550291 2022/10/12 11:06:30 - mmengine - INFO - Epoch(train) [1][550/586] lr: 5.000000e-03 eta: 12:54:57 time: 0.329591 data_time: 0.050519 memory: 4465 loss_kpt: 144.141492 acc_pose: 0.219011 loss: 144.141492 2022/10/12 11:06:42 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:06:59 - mmengine - INFO - Epoch(train) [2][50/586] lr: 5.000000e-03 eta: 12:06:29 time: 0.354042 data_time: 0.060597 memory: 4465 loss_kpt: 142.764166 acc_pose: 0.203934 loss: 142.764166 2022/10/12 11:07:17 - mmengine - INFO - Epoch(train) [2][100/586] lr: 5.000000e-03 eta: 12:04:27 time: 0.344391 data_time: 0.052567 memory: 4465 loss_kpt: 144.819732 acc_pose: 0.275742 loss: 144.819732 2022/10/12 11:07:34 - mmengine - INFO - Epoch(train) [2][150/586] lr: 5.000000e-03 eta: 12:03:51 time: 0.353040 data_time: 0.052335 memory: 4465 loss_kpt: 143.484144 acc_pose: 0.208463 loss: 143.484144 2022/10/12 11:07:52 - mmengine - INFO - Epoch(train) [2][200/586] lr: 5.000000e-03 eta: 12:02:14 time: 0.344767 data_time: 0.055535 memory: 4465 loss_kpt: 140.673203 acc_pose: 0.210857 loss: 140.673203 2022/10/12 11:08:08 - mmengine - INFO - Epoch(train) [2][250/586] lr: 5.000000e-03 eta: 11:59:31 time: 0.334523 data_time: 0.049957 memory: 4465 loss_kpt: 137.736690 acc_pose: 0.334301 loss: 137.736690 2022/10/12 11:08:24 - mmengine - INFO - Epoch(train) [2][300/586] lr: 5.000000e-03 eta: 11:55:21 time: 0.319587 data_time: 0.049128 memory: 4465 loss_kpt: 137.040425 acc_pose: 0.400766 loss: 137.040425 2022/10/12 11:08:41 - mmengine - INFO - Epoch(train) [2][350/586] lr: 5.000000e-03 eta: 11:53:06 time: 0.333305 data_time: 0.052720 memory: 4465 loss_kpt: 135.303272 acc_pose: 0.293179 loss: 135.303272 2022/10/12 11:08:58 - mmengine - INFO - Epoch(train) [2][400/586] lr: 5.000000e-03 eta: 11:51:54 time: 0.341480 data_time: 0.056858 memory: 4465 loss_kpt: 136.924370 acc_pose: 0.336647 loss: 136.924370 2022/10/12 11:09:03 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:09:15 - mmengine - INFO - Epoch(train) [2][450/586] lr: 5.000000e-03 eta: 11:51:19 time: 0.347021 data_time: 0.057509 memory: 4465 loss_kpt: 133.803039 acc_pose: 0.377826 loss: 133.803039 2022/10/12 11:09:32 - mmengine - INFO - Epoch(train) [2][500/586] lr: 5.000000e-03 eta: 11:49:59 time: 0.338679 data_time: 0.053865 memory: 4465 loss_kpt: 132.566644 acc_pose: 0.369691 loss: 132.566644 2022/10/12 11:09:50 - mmengine - INFO - Epoch(train) [2][550/586] lr: 5.000000e-03 eta: 11:49:21 time: 0.345370 data_time: 0.053411 memory: 4465 loss_kpt: 130.949830 acc_pose: 0.448519 loss: 130.949830 2022/10/12 11:10:01 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:10:19 - mmengine - INFO - Epoch(train) [3][50/586] lr: 5.000000e-03 eta: 11:28:28 time: 0.355029 data_time: 0.058730 memory: 4465 loss_kpt: 131.990582 acc_pose: 0.363265 loss: 131.990582 2022/10/12 11:10:36 - mmengine - INFO - Epoch(train) [3][100/586] lr: 5.000000e-03 eta: 11:28:08 time: 0.338479 data_time: 0.051170 memory: 4465 loss_kpt: 130.511198 acc_pose: 0.436710 loss: 130.511198 2022/10/12 11:10:53 - mmengine - INFO - Epoch(train) [3][150/586] lr: 5.000000e-03 eta: 11:27:28 time: 0.334015 data_time: 0.046636 memory: 4465 loss_kpt: 130.913486 acc_pose: 0.480442 loss: 130.913486 2022/10/12 11:11:09 - mmengine - INFO - Epoch(train) [3][200/586] lr: 5.000000e-03 eta: 11:25:38 time: 0.317893 data_time: 0.049667 memory: 4465 loss_kpt: 128.334136 acc_pose: 0.554251 loss: 128.334136 2022/10/12 11:11:25 - mmengine - INFO - Epoch(train) [3][250/586] lr: 5.000000e-03 eta: 11:24:11 time: 0.321544 data_time: 0.050343 memory: 4465 loss_kpt: 126.089968 acc_pose: 0.471214 loss: 126.089968 2022/10/12 11:11:41 - mmengine - INFO - Epoch(train) [3][300/586] lr: 5.000000e-03 eta: 11:23:06 time: 0.326001 data_time: 0.046988 memory: 4465 loss_kpt: 126.038120 acc_pose: 0.473737 loss: 126.038120 2022/10/12 11:11:57 - mmengine - INFO - Epoch(train) [3][350/586] lr: 5.000000e-03 eta: 11:22:06 time: 0.326100 data_time: 0.050963 memory: 4465 loss_kpt: 125.927731 acc_pose: 0.491135 loss: 125.927731 2022/10/12 11:12:13 - mmengine - INFO - Epoch(train) [3][400/586] lr: 5.000000e-03 eta: 11:20:39 time: 0.318767 data_time: 0.050204 memory: 4465 loss_kpt: 127.709353 acc_pose: 0.490767 loss: 127.709353 2022/10/12 11:12:29 - mmengine - INFO - Epoch(train) [3][450/586] lr: 5.000000e-03 eta: 11:19:15 time: 0.318001 data_time: 0.047267 memory: 4465 loss_kpt: 124.103618 acc_pose: 0.496065 loss: 124.103618 2022/10/12 11:12:45 - mmengine - INFO - Epoch(train) [3][500/586] lr: 5.000000e-03 eta: 11:17:44 time: 0.315374 data_time: 0.051586 memory: 4465 loss_kpt: 122.939650 acc_pose: 0.463820 loss: 122.939650 2022/10/12 11:13:01 - mmengine - INFO - Epoch(train) [3][550/586] lr: 5.000000e-03 eta: 11:16:27 time: 0.317781 data_time: 0.051574 memory: 4465 loss_kpt: 122.479108 acc_pose: 0.548194 loss: 122.479108 2022/10/12 11:13:12 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:13:30 - mmengine - INFO - Epoch(train) [4][50/586] lr: 5.000000e-03 eta: 11:04:19 time: 0.366886 data_time: 0.064582 memory: 4465 loss_kpt: 124.130121 acc_pose: 0.478453 loss: 124.130121 2022/10/12 11:13:48 - mmengine - INFO - Epoch(train) [4][100/586] lr: 5.000000e-03 eta: 11:05:06 time: 0.348014 data_time: 0.047888 memory: 4465 loss_kpt: 123.094728 acc_pose: 0.438935 loss: 123.094728 2022/10/12 11:14:05 - mmengine - INFO - Epoch(train) [4][150/586] lr: 5.000000e-03 eta: 11:05:58 time: 0.350822 data_time: 0.051763 memory: 4465 loss_kpt: 124.640315 acc_pose: 0.481084 loss: 124.640315 2022/10/12 11:14:23 - mmengine - INFO - Epoch(train) [4][200/586] lr: 5.000000e-03 eta: 11:06:55 time: 0.353670 data_time: 0.046794 memory: 4465 loss_kpt: 119.021122 acc_pose: 0.487891 loss: 119.021122 2022/10/12 11:14:38 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:14:41 - mmengine - INFO - Epoch(train) [4][250/586] lr: 5.000000e-03 eta: 11:07:56 time: 0.356031 data_time: 0.054811 memory: 4465 loss_kpt: 122.312998 acc_pose: 0.417775 loss: 122.312998 2022/10/12 11:14:58 - mmengine - INFO - Epoch(train) [4][300/586] lr: 5.000000e-03 eta: 11:08:03 time: 0.339320 data_time: 0.046259 memory: 4465 loss_kpt: 122.539245 acc_pose: 0.539259 loss: 122.539245 2022/10/12 11:15:15 - mmengine - INFO - Epoch(train) [4][350/586] lr: 5.000000e-03 eta: 11:08:47 time: 0.352143 data_time: 0.053107 memory: 4465 loss_kpt: 119.490363 acc_pose: 0.514963 loss: 119.490363 2022/10/12 11:15:32 - mmengine - INFO - Epoch(train) [4][400/586] lr: 5.000000e-03 eta: 11:08:57 time: 0.341249 data_time: 0.046274 memory: 4465 loss_kpt: 119.172650 acc_pose: 0.592421 loss: 119.172650 2022/10/12 11:15:50 - mmengine - INFO - Epoch(train) [4][450/586] lr: 5.000000e-03 eta: 11:09:15 time: 0.344907 data_time: 0.055257 memory: 4465 loss_kpt: 120.623392 acc_pose: 0.633640 loss: 120.623392 2022/10/12 11:16:06 - mmengine - INFO - Epoch(train) [4][500/586] lr: 5.000000e-03 eta: 11:09:15 time: 0.338382 data_time: 0.046566 memory: 4465 loss_kpt: 119.139063 acc_pose: 0.475549 loss: 119.139063 2022/10/12 11:16:23 - mmengine - INFO - Epoch(train) [4][550/586] lr: 5.000000e-03 eta: 11:09:18 time: 0.340011 data_time: 0.055484 memory: 4465 loss_kpt: 117.642301 acc_pose: 0.545097 loss: 117.642301 2022/10/12 11:16:36 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:16:53 - mmengine - INFO - Epoch(train) [5][50/586] lr: 5.000000e-03 eta: 10:59:25 time: 0.347912 data_time: 0.059505 memory: 4465 loss_kpt: 120.172134 acc_pose: 0.519081 loss: 120.172134 2022/10/12 11:17:10 - mmengine - INFO - Epoch(train) [5][100/586] lr: 5.000000e-03 eta: 10:59:44 time: 0.342390 data_time: 0.049131 memory: 4465 loss_kpt: 120.009229 acc_pose: 0.520505 loss: 120.009229 2022/10/12 11:17:28 - mmengine - INFO - Epoch(train) [5][150/586] lr: 5.000000e-03 eta: 11:00:17 time: 0.348331 data_time: 0.049959 memory: 4465 loss_kpt: 117.164297 acc_pose: 0.614621 loss: 117.164297 2022/10/12 11:17:45 - mmengine - INFO - Epoch(train) [5][200/586] lr: 5.000000e-03 eta: 11:00:30 time: 0.341200 data_time: 0.046876 memory: 4465 loss_kpt: 119.765269 acc_pose: 0.493511 loss: 119.765269 2022/10/12 11:18:02 - mmengine - INFO - Epoch(train) [5][250/586] lr: 5.000000e-03 eta: 11:00:37 time: 0.338884 data_time: 0.050130 memory: 4465 loss_kpt: 119.044240 acc_pose: 0.423710 loss: 119.044240 2022/10/12 11:18:19 - mmengine - INFO - Epoch(train) [5][300/586] lr: 5.000000e-03 eta: 11:01:02 time: 0.347412 data_time: 0.045500 memory: 4465 loss_kpt: 117.678916 acc_pose: 0.559024 loss: 117.678916 2022/10/12 11:18:37 - mmengine - INFO - Epoch(train) [5][350/586] lr: 5.000000e-03 eta: 11:01:37 time: 0.352445 data_time: 0.049742 memory: 4465 loss_kpt: 118.112982 acc_pose: 0.535800 loss: 118.112982 2022/10/12 11:18:54 - mmengine - INFO - Epoch(train) [5][400/586] lr: 5.000000e-03 eta: 11:02:14 time: 0.354165 data_time: 0.048037 memory: 4465 loss_kpt: 118.449308 acc_pose: 0.625263 loss: 118.449308 2022/10/12 11:19:12 - mmengine - INFO - Epoch(train) [5][450/586] lr: 5.000000e-03 eta: 11:02:50 time: 0.354504 data_time: 0.049586 memory: 4465 loss_kpt: 117.338694 acc_pose: 0.564059 loss: 117.338694 2022/10/12 11:19:30 - mmengine - INFO - Epoch(train) [5][500/586] lr: 5.000000e-03 eta: 11:03:22 time: 0.353474 data_time: 0.048740 memory: 4465 loss_kpt: 117.125775 acc_pose: 0.579340 loss: 117.125775 2022/10/12 11:19:47 - mmengine - INFO - Epoch(train) [5][550/586] lr: 5.000000e-03 eta: 11:03:43 time: 0.349531 data_time: 0.045838 memory: 4465 loss_kpt: 117.419144 acc_pose: 0.543806 loss: 117.419144 2022/10/12 11:19:59 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:20:17 - mmengine - INFO - Epoch(train) [6][50/586] lr: 5.000000e-03 eta: 10:55:43 time: 0.345974 data_time: 0.062693 memory: 4465 loss_kpt: 116.252304 acc_pose: 0.611163 loss: 116.252304 2022/10/12 11:20:24 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:20:33 - mmengine - INFO - Epoch(train) [6][100/586] lr: 5.000000e-03 eta: 10:55:28 time: 0.328385 data_time: 0.049760 memory: 4465 loss_kpt: 114.941614 acc_pose: 0.511238 loss: 114.941614 2022/10/12 11:20:50 - mmengine - INFO - Epoch(train) [6][150/586] lr: 5.000000e-03 eta: 10:55:51 time: 0.347620 data_time: 0.051406 memory: 4465 loss_kpt: 113.978775 acc_pose: 0.607279 loss: 113.978775 2022/10/12 11:21:07 - mmengine - INFO - Epoch(train) [6][200/586] lr: 5.000000e-03 eta: 10:55:55 time: 0.338593 data_time: 0.050104 memory: 4465 loss_kpt: 116.336184 acc_pose: 0.659700 loss: 116.336184 2022/10/12 11:21:25 - mmengine - INFO - Epoch(train) [6][250/586] lr: 5.000000e-03 eta: 10:56:39 time: 0.360299 data_time: 0.053345 memory: 4465 loss_kpt: 116.416658 acc_pose: 0.596262 loss: 116.416658 2022/10/12 11:21:42 - mmengine - INFO - Epoch(train) [6][300/586] lr: 5.000000e-03 eta: 10:56:43 time: 0.339797 data_time: 0.046565 memory: 4465 loss_kpt: 114.983034 acc_pose: 0.646301 loss: 114.983034 2022/10/12 11:21:59 - mmengine - INFO - Epoch(train) [6][350/586] lr: 5.000000e-03 eta: 10:56:47 time: 0.339885 data_time: 0.051776 memory: 4465 loss_kpt: 113.472958 acc_pose: 0.611283 loss: 113.472958 2022/10/12 11:22:17 - mmengine - INFO - Epoch(train) [6][400/586] lr: 5.000000e-03 eta: 10:57:08 time: 0.349634 data_time: 0.053922 memory: 4465 loss_kpt: 115.936532 acc_pose: 0.504946 loss: 115.936532 2022/10/12 11:22:34 - mmengine - INFO - Epoch(train) [6][450/586] lr: 5.000000e-03 eta: 10:57:28 time: 0.349957 data_time: 0.055570 memory: 4465 loss_kpt: 116.382269 acc_pose: 0.556220 loss: 116.382269 2022/10/12 11:22:52 - mmengine - INFO - Epoch(train) [6][500/586] lr: 5.000000e-03 eta: 10:57:44 time: 0.348510 data_time: 0.049113 memory: 4465 loss_kpt: 113.591506 acc_pose: 0.635835 loss: 113.591506 2022/10/12 11:23:09 - mmengine - INFO - Epoch(train) [6][550/586] lr: 5.000000e-03 eta: 10:58:08 time: 0.353526 data_time: 0.054075 memory: 4465 loss_kpt: 113.889309 acc_pose: 0.615789 loss: 113.889309 2022/10/12 11:23:22 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:23:40 - mmengine - INFO - Epoch(train) [7][50/586] lr: 5.000000e-03 eta: 10:52:02 time: 0.366411 data_time: 0.061868 memory: 4465 loss_kpt: 113.553976 acc_pose: 0.649647 loss: 113.553976 2022/10/12 11:23:58 - mmengine - INFO - Epoch(train) [7][100/586] lr: 5.000000e-03 eta: 10:52:34 time: 0.356294 data_time: 0.055585 memory: 4465 loss_kpt: 112.051145 acc_pose: 0.652830 loss: 112.051145 2022/10/12 11:24:16 - mmengine - INFO - Epoch(train) [7][150/586] lr: 5.000000e-03 eta: 10:53:06 time: 0.357651 data_time: 0.054635 memory: 4465 loss_kpt: 114.401236 acc_pose: 0.681774 loss: 114.401236 2022/10/12 11:24:34 - mmengine - INFO - Epoch(train) [7][200/586] lr: 5.000000e-03 eta: 10:53:28 time: 0.352135 data_time: 0.054735 memory: 4465 loss_kpt: 113.168863 acc_pose: 0.645157 loss: 113.168863 2022/10/12 11:24:50 - mmengine - INFO - Epoch(train) [7][250/586] lr: 5.000000e-03 eta: 10:53:27 time: 0.338439 data_time: 0.052253 memory: 4465 loss_kpt: 113.094880 acc_pose: 0.604663 loss: 113.094880 2022/10/12 11:25:07 - mmengine - INFO - Epoch(train) [7][300/586] lr: 5.000000e-03 eta: 10:53:26 time: 0.338685 data_time: 0.050558 memory: 4465 loss_kpt: 113.434789 acc_pose: 0.539457 loss: 113.434789 2022/10/12 11:25:24 - mmengine - INFO - Epoch(train) [7][350/586] lr: 5.000000e-03 eta: 10:53:30 time: 0.341913 data_time: 0.053258 memory: 4465 loss_kpt: 114.253362 acc_pose: 0.517757 loss: 114.253362 2022/10/12 11:25:42 - mmengine - INFO - Epoch(train) [7][400/586] lr: 5.000000e-03 eta: 10:53:31 time: 0.340451 data_time: 0.048900 memory: 4465 loss_kpt: 110.686553 acc_pose: 0.601034 loss: 110.686553 2022/10/12 11:25:58 - mmengine - INFO - Epoch(train) [7][450/586] lr: 5.000000e-03 eta: 10:53:26 time: 0.336673 data_time: 0.051639 memory: 4465 loss_kpt: 111.207572 acc_pose: 0.572502 loss: 111.207572 2022/10/12 11:26:10 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:26:15 - mmengine - INFO - Epoch(train) [7][500/586] lr: 5.000000e-03 eta: 10:53:17 time: 0.334181 data_time: 0.051236 memory: 4465 loss_kpt: 110.836224 acc_pose: 0.685078 loss: 110.836224 2022/10/12 11:26:32 - mmengine - INFO - Epoch(train) [7][550/586] lr: 5.000000e-03 eta: 10:53:06 time: 0.332727 data_time: 0.052230 memory: 4465 loss_kpt: 109.057146 acc_pose: 0.592392 loss: 109.057146 2022/10/12 11:26:44 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:27:02 - mmengine - INFO - Epoch(train) [8][50/586] lr: 5.000000e-03 eta: 10:47:36 time: 0.356111 data_time: 0.064206 memory: 4465 loss_kpt: 113.912400 acc_pose: 0.660571 loss: 113.912400 2022/10/12 11:27:19 - mmengine - INFO - Epoch(train) [8][100/586] lr: 5.000000e-03 eta: 10:47:52 time: 0.349786 data_time: 0.051188 memory: 4465 loss_kpt: 110.762499 acc_pose: 0.716870 loss: 110.762499 2022/10/12 11:27:37 - mmengine - INFO - Epoch(train) [8][150/586] lr: 5.000000e-03 eta: 10:48:17 time: 0.356719 data_time: 0.054985 memory: 4465 loss_kpt: 111.471097 acc_pose: 0.557857 loss: 111.471097 2022/10/12 11:27:54 - mmengine - INFO - Epoch(train) [8][200/586] lr: 5.000000e-03 eta: 10:48:16 time: 0.338508 data_time: 0.048923 memory: 4465 loss_kpt: 111.155240 acc_pose: 0.575054 loss: 111.155240 2022/10/12 11:28:11 - mmengine - INFO - Epoch(train) [8][250/586] lr: 5.000000e-03 eta: 10:48:24 time: 0.345242 data_time: 0.056494 memory: 4465 loss_kpt: 113.122209 acc_pose: 0.656523 loss: 113.122209 2022/10/12 11:28:29 - mmengine - INFO - Epoch(train) [8][300/586] lr: 5.000000e-03 eta: 10:48:30 time: 0.343964 data_time: 0.051879 memory: 4465 loss_kpt: 109.794442 acc_pose: 0.568818 loss: 109.794442 2022/10/12 11:28:46 - mmengine - INFO - Epoch(train) [8][350/586] lr: 5.000000e-03 eta: 10:48:35 time: 0.344488 data_time: 0.054562 memory: 4465 loss_kpt: 112.672618 acc_pose: 0.659263 loss: 112.672618 2022/10/12 11:29:03 - mmengine - INFO - Epoch(train) [8][400/586] lr: 5.000000e-03 eta: 10:48:29 time: 0.335641 data_time: 0.052324 memory: 4465 loss_kpt: 110.447061 acc_pose: 0.646733 loss: 110.447061 2022/10/12 11:29:19 - mmengine - INFO - Epoch(train) [8][450/586] lr: 5.000000e-03 eta: 10:48:23 time: 0.336038 data_time: 0.054640 memory: 4465 loss_kpt: 111.109047 acc_pose: 0.573260 loss: 111.109047 2022/10/12 11:29:36 - mmengine - INFO - Epoch(train) [8][500/586] lr: 5.000000e-03 eta: 10:48:21 time: 0.339529 data_time: 0.048789 memory: 4465 loss_kpt: 109.747947 acc_pose: 0.648298 loss: 109.747947 2022/10/12 11:29:53 - mmengine - INFO - Epoch(train) [8][550/586] lr: 5.000000e-03 eta: 10:48:19 time: 0.339974 data_time: 0.060675 memory: 4465 loss_kpt: 111.395459 acc_pose: 0.587175 loss: 111.395459 2022/10/12 11:30:05 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:30:23 - mmengine - INFO - Epoch(train) [9][50/586] lr: 5.000000e-03 eta: 10:43:25 time: 0.351933 data_time: 0.061386 memory: 4465 loss_kpt: 113.233365 acc_pose: 0.649377 loss: 113.233365 2022/10/12 11:30:40 - mmengine - INFO - Epoch(train) [9][100/586] lr: 5.000000e-03 eta: 10:43:26 time: 0.341001 data_time: 0.046777 memory: 4465 loss_kpt: 110.378436 acc_pose: 0.706405 loss: 110.378436 2022/10/12 11:30:57 - mmengine - INFO - Epoch(train) [9][150/586] lr: 5.000000e-03 eta: 10:43:23 time: 0.336877 data_time: 0.049936 memory: 4465 loss_kpt: 112.211303 acc_pose: 0.685364 loss: 112.211303 2022/10/12 11:31:15 - mmengine - INFO - Epoch(train) [9][200/586] lr: 5.000000e-03 eta: 10:43:40 time: 0.353797 data_time: 0.051579 memory: 4465 loss_kpt: 108.990010 acc_pose: 0.597187 loss: 108.990010 2022/10/12 11:31:32 - mmengine - INFO - Epoch(train) [9][250/586] lr: 5.000000e-03 eta: 10:43:49 time: 0.348199 data_time: 0.052911 memory: 4465 loss_kpt: 111.673539 acc_pose: 0.635892 loss: 111.673539 2022/10/12 11:31:50 - mmengine - INFO - Epoch(train) [9][300/586] lr: 5.000000e-03 eta: 10:44:04 time: 0.353813 data_time: 0.050966 memory: 4465 loss_kpt: 110.109997 acc_pose: 0.595492 loss: 110.109997 2022/10/12 11:31:54 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:32:07 - mmengine - INFO - Epoch(train) [9][350/586] lr: 5.000000e-03 eta: 10:44:19 time: 0.354175 data_time: 0.049459 memory: 4465 loss_kpt: 109.406970 acc_pose: 0.587566 loss: 109.406970 2022/10/12 11:32:25 - mmengine - INFO - Epoch(train) [9][400/586] lr: 5.000000e-03 eta: 10:44:21 time: 0.343425 data_time: 0.051685 memory: 4465 loss_kpt: 109.165664 acc_pose: 0.569347 loss: 109.165664 2022/10/12 11:32:42 - mmengine - INFO - Epoch(train) [9][450/586] lr: 5.000000e-03 eta: 10:44:36 time: 0.354875 data_time: 0.049939 memory: 4465 loss_kpt: 108.885647 acc_pose: 0.640699 loss: 108.885647 2022/10/12 11:33:00 - mmengine - INFO - Epoch(train) [9][500/586] lr: 5.000000e-03 eta: 10:44:54 time: 0.357967 data_time: 0.054319 memory: 4465 loss_kpt: 109.478978 acc_pose: 0.676236 loss: 109.478978 2022/10/12 11:33:17 - mmengine - INFO - Epoch(train) [9][550/586] lr: 5.000000e-03 eta: 10:44:53 time: 0.342524 data_time: 0.051474 memory: 4465 loss_kpt: 106.761317 acc_pose: 0.630615 loss: 106.761317 2022/10/12 11:33:29 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:33:47 - mmengine - INFO - Epoch(train) [10][50/586] lr: 5.000000e-03 eta: 10:40:29 time: 0.351343 data_time: 0.062699 memory: 4465 loss_kpt: 111.195584 acc_pose: 0.631593 loss: 111.195584 2022/10/12 11:34:04 - mmengine - INFO - Epoch(train) [10][100/586] lr: 5.000000e-03 eta: 10:40:26 time: 0.338376 data_time: 0.054210 memory: 4465 loss_kpt: 108.814010 acc_pose: 0.582980 loss: 108.814010 2022/10/12 11:34:21 - mmengine - INFO - Epoch(train) [10][150/586] lr: 5.000000e-03 eta: 10:40:20 time: 0.335932 data_time: 0.050036 memory: 4465 loss_kpt: 107.635574 acc_pose: 0.675146 loss: 107.635574 2022/10/12 11:34:37 - mmengine - INFO - Epoch(train) [10][200/586] lr: 5.000000e-03 eta: 10:40:09 time: 0.332081 data_time: 0.053906 memory: 4465 loss_kpt: 108.324067 acc_pose: 0.686373 loss: 108.324067 2022/10/12 11:34:54 - mmengine - INFO - Epoch(train) [10][250/586] lr: 5.000000e-03 eta: 10:40:01 time: 0.334619 data_time: 0.054862 memory: 4465 loss_kpt: 108.758220 acc_pose: 0.510240 loss: 108.758220 2022/10/12 11:35:11 - mmengine - INFO - Epoch(train) [10][300/586] lr: 5.000000e-03 eta: 10:39:52 time: 0.332878 data_time: 0.051034 memory: 4465 loss_kpt: 109.856182 acc_pose: 0.579731 loss: 109.856182 2022/10/12 11:35:28 - mmengine - INFO - Epoch(train) [10][350/586] lr: 5.000000e-03 eta: 10:40:01 time: 0.351790 data_time: 0.055392 memory: 4465 loss_kpt: 109.683981 acc_pose: 0.657197 loss: 109.683981 2022/10/12 11:35:45 - mmengine - INFO - Epoch(train) [10][400/586] lr: 5.000000e-03 eta: 10:39:51 time: 0.332893 data_time: 0.053595 memory: 4465 loss_kpt: 107.757538 acc_pose: 0.611310 loss: 107.757538 2022/10/12 11:36:02 - mmengine - INFO - Epoch(train) [10][450/586] lr: 5.000000e-03 eta: 10:39:42 time: 0.334242 data_time: 0.056676 memory: 4465 loss_kpt: 109.108308 acc_pose: 0.642227 loss: 109.108308 2022/10/12 11:36:19 - mmengine - INFO - Epoch(train) [10][500/586] lr: 5.000000e-03 eta: 10:39:36 time: 0.337577 data_time: 0.052108 memory: 4465 loss_kpt: 108.588846 acc_pose: 0.657275 loss: 108.588846 2022/10/12 11:36:35 - mmengine - INFO - Epoch(train) [10][550/586] lr: 5.000000e-03 eta: 10:39:29 time: 0.336545 data_time: 0.052668 memory: 4465 loss_kpt: 107.551559 acc_pose: 0.690519 loss: 107.551559 2022/10/12 11:36:47 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:36:47 - mmengine - INFO - Saving checkpoint at 10 epochs 2022/10/12 11:37:00 - mmengine - INFO - Epoch(val) [10][50/407] eta: 0:01:17 time: 0.217368 data_time: 0.094544 memory: 4465 2022/10/12 11:37:07 - mmengine - INFO - Epoch(val) [10][100/407] eta: 0:00:39 time: 0.129591 data_time: 0.008552 memory: 1026 2022/10/12 11:37:14 - mmengine - INFO - Epoch(val) [10][150/407] eta: 0:00:34 time: 0.133698 data_time: 0.008928 memory: 1026 2022/10/12 11:37:20 - mmengine - INFO - Epoch(val) [10][200/407] eta: 0:00:27 time: 0.130740 data_time: 0.008424 memory: 1026 2022/10/12 11:37:27 - mmengine - INFO - Epoch(val) [10][250/407] eta: 0:00:21 time: 0.138290 data_time: 0.009160 memory: 1026 2022/10/12 11:37:34 - mmengine - INFO - Epoch(val) [10][300/407] eta: 0:00:13 time: 0.130197 data_time: 0.007953 memory: 1026 2022/10/12 11:37:40 - mmengine - INFO - Epoch(val) [10][350/407] eta: 0:00:07 time: 0.128709 data_time: 0.008262 memory: 1026 2022/10/12 11:37:47 - mmengine - INFO - Epoch(val) [10][400/407] eta: 0:00:00 time: 0.130060 data_time: 0.008734 memory: 1026 2022/10/12 11:38:00 - mmengine - INFO - Evaluating CocoMetric... 2022/10/12 11:38:15 - mmengine - INFO - Epoch(val) [10][407/407] coco/AP: 0.481294 coco/AP .5: 0.773942 coco/AP .75: 0.508592 coco/AP (M): 0.456681 coco/AP (L): 0.529612 coco/AR: 0.564200 coco/AR .5: 0.828558 coco/AR .75: 0.602487 coco/AR (M): 0.519339 coco/AR (L): 0.625604 2022/10/12 11:38:17 - mmengine - INFO - The best checkpoint with 0.4813 coco/AP at 10 epoch is saved to best_coco/AP_epoch_10.pth. 2022/10/12 11:38:36 - mmengine - INFO - Epoch(train) [11][50/586] lr: 5.000000e-03 eta: 10:35:54 time: 0.373980 data_time: 0.055559 memory: 4465 loss_kpt: 108.810691 acc_pose: 0.694307 loss: 108.810691 2022/10/12 11:38:54 - mmengine - INFO - Epoch(train) [11][100/586] lr: 5.000000e-03 eta: 10:36:06 time: 0.354431 data_time: 0.052040 memory: 4465 loss_kpt: 106.336004 acc_pose: 0.569707 loss: 106.336004 2022/10/12 11:39:07 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:39:11 - mmengine - INFO - Epoch(train) [11][150/586] lr: 5.000000e-03 eta: 10:36:13 time: 0.349848 data_time: 0.052413 memory: 4465 loss_kpt: 107.022038 acc_pose: 0.668002 loss: 107.022038 2022/10/12 11:39:28 - mmengine - INFO - Epoch(train) [11][200/586] lr: 5.000000e-03 eta: 10:36:12 time: 0.342078 data_time: 0.051300 memory: 4465 loss_kpt: 106.253135 acc_pose: 0.643318 loss: 106.253135 2022/10/12 11:39:45 - mmengine - INFO - Epoch(train) [11][250/586] lr: 5.000000e-03 eta: 10:36:12 time: 0.343613 data_time: 0.053090 memory: 4465 loss_kpt: 106.453456 acc_pose: 0.711422 loss: 106.453456 2022/10/12 11:40:02 - mmengine - INFO - Epoch(train) [11][300/586] lr: 5.000000e-03 eta: 10:36:06 time: 0.337365 data_time: 0.052719 memory: 4465 loss_kpt: 108.377555 acc_pose: 0.713802 loss: 108.377555 2022/10/12 11:40:19 - mmengine - INFO - Epoch(train) [11][350/586] lr: 5.000000e-03 eta: 10:35:59 time: 0.335578 data_time: 0.054020 memory: 4465 loss_kpt: 106.483228 acc_pose: 0.666617 loss: 106.483228 2022/10/12 11:40:36 - mmengine - INFO - Epoch(train) [11][400/586] lr: 5.000000e-03 eta: 10:35:48 time: 0.332765 data_time: 0.050713 memory: 4465 loss_kpt: 106.497593 acc_pose: 0.659327 loss: 106.497593 2022/10/12 11:40:53 - mmengine - INFO - Epoch(train) [11][450/586] lr: 5.000000e-03 eta: 10:35:43 time: 0.338723 data_time: 0.048665 memory: 4465 loss_kpt: 106.035479 acc_pose: 0.674983 loss: 106.035479 2022/10/12 11:41:09 - mmengine - INFO - Epoch(train) [11][500/586] lr: 5.000000e-03 eta: 10:35:28 time: 0.327738 data_time: 0.051358 memory: 4465 loss_kpt: 106.722560 acc_pose: 0.701215 loss: 106.722560 2022/10/12 11:41:26 - mmengine - INFO - Epoch(train) [11][550/586] lr: 5.000000e-03 eta: 10:35:20 time: 0.336152 data_time: 0.052774 memory: 4465 loss_kpt: 107.761891 acc_pose: 0.637188 loss: 107.761891 2022/10/12 11:41:37 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:41:55 - mmengine - INFO - Epoch(train) [12][50/586] lr: 5.000000e-03 eta: 10:31:47 time: 0.356613 data_time: 0.064391 memory: 4465 loss_kpt: 108.146747 acc_pose: 0.639268 loss: 108.146747 2022/10/12 11:42:12 - mmengine - INFO - Epoch(train) [12][100/586] lr: 5.000000e-03 eta: 10:31:45 time: 0.341208 data_time: 0.054128 memory: 4465 loss_kpt: 106.504118 acc_pose: 0.660623 loss: 106.504118 2022/10/12 11:42:30 - mmengine - INFO - Epoch(train) [12][150/586] lr: 5.000000e-03 eta: 10:31:54 time: 0.353471 data_time: 0.053044 memory: 4465 loss_kpt: 109.141388 acc_pose: 0.614171 loss: 109.141388 2022/10/12 11:42:47 - mmengine - INFO - Epoch(train) [12][200/586] lr: 5.000000e-03 eta: 10:31:55 time: 0.345982 data_time: 0.054995 memory: 4465 loss_kpt: 106.884295 acc_pose: 0.615605 loss: 106.884295 2022/10/12 11:43:04 - mmengine - INFO - Epoch(train) [12][250/586] lr: 5.000000e-03 eta: 10:31:57 time: 0.346602 data_time: 0.055797 memory: 4465 loss_kpt: 104.201488 acc_pose: 0.624883 loss: 104.201488 2022/10/12 11:43:20 - mmengine - INFO - Epoch(train) [12][300/586] lr: 5.000000e-03 eta: 10:31:38 time: 0.322509 data_time: 0.051424 memory: 4465 loss_kpt: 106.554879 acc_pose: 0.597802 loss: 106.554879 2022/10/12 11:43:37 - mmengine - INFO - Epoch(train) [12][350/586] lr: 5.000000e-03 eta: 10:31:24 time: 0.328083 data_time: 0.048403 memory: 4465 loss_kpt: 106.799048 acc_pose: 0.689750 loss: 106.799048 2022/10/12 11:43:54 - mmengine - INFO - Epoch(train) [12][400/586] lr: 5.000000e-03 eta: 10:31:20 time: 0.340918 data_time: 0.052246 memory: 4465 loss_kpt: 106.294455 acc_pose: 0.626303 loss: 106.294455 2022/10/12 11:44:11 - mmengine - INFO - Epoch(train) [12][450/586] lr: 5.000000e-03 eta: 10:31:15 time: 0.338829 data_time: 0.051797 memory: 4465 loss_kpt: 106.461311 acc_pose: 0.681067 loss: 106.461311 2022/10/12 11:44:28 - mmengine - INFO - Epoch(train) [12][500/586] lr: 5.000000e-03 eta: 10:31:05 time: 0.333208 data_time: 0.046301 memory: 4465 loss_kpt: 105.639976 acc_pose: 0.653174 loss: 105.639976 2022/10/12 11:44:45 - mmengine - INFO - Epoch(train) [12][550/586] lr: 5.000000e-03 eta: 10:31:02 time: 0.342919 data_time: 0.049093 memory: 4465 loss_kpt: 107.113616 acc_pose: 0.725805 loss: 107.113616 2022/10/12 11:44:46 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:44:57 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:45:15 - mmengine - INFO - Epoch(train) [13][50/586] lr: 5.000000e-03 eta: 10:27:45 time: 0.354525 data_time: 0.062572 memory: 4465 loss_kpt: 104.881161 acc_pose: 0.643074 loss: 104.881161 2022/10/12 11:45:32 - mmengine - INFO - Epoch(train) [13][100/586] lr: 5.000000e-03 eta: 10:27:48 time: 0.347907 data_time: 0.052333 memory: 4465 loss_kpt: 107.012002 acc_pose: 0.625145 loss: 107.012002 2022/10/12 11:45:49 - mmengine - INFO - Epoch(train) [13][150/586] lr: 5.000000e-03 eta: 10:27:48 time: 0.345338 data_time: 0.049796 memory: 4465 loss_kpt: 106.309130 acc_pose: 0.626948 loss: 106.309130 2022/10/12 11:46:06 - mmengine - INFO - Epoch(train) [13][200/586] lr: 5.000000e-03 eta: 10:27:44 time: 0.341065 data_time: 0.050948 memory: 4465 loss_kpt: 107.126321 acc_pose: 0.638337 loss: 107.126321 2022/10/12 11:46:24 - mmengine - INFO - Epoch(train) [13][250/586] lr: 5.000000e-03 eta: 10:27:50 time: 0.353285 data_time: 0.054754 memory: 4465 loss_kpt: 106.426647 acc_pose: 0.571579 loss: 106.426647 2022/10/12 11:46:41 - mmengine - INFO - Epoch(train) [13][300/586] lr: 5.000000e-03 eta: 10:27:42 time: 0.335829 data_time: 0.048279 memory: 4465 loss_kpt: 105.541368 acc_pose: 0.617771 loss: 105.541368 2022/10/12 11:46:58 - mmengine - INFO - Epoch(train) [13][350/586] lr: 5.000000e-03 eta: 10:27:47 time: 0.352358 data_time: 0.055299 memory: 4465 loss_kpt: 105.545422 acc_pose: 0.585557 loss: 105.545422 2022/10/12 11:47:16 - mmengine - INFO - Epoch(train) [13][400/586] lr: 5.000000e-03 eta: 10:27:55 time: 0.356383 data_time: 0.051546 memory: 4465 loss_kpt: 106.143761 acc_pose: 0.718230 loss: 106.143761 2022/10/12 11:47:34 - mmengine - INFO - Epoch(train) [13][450/586] lr: 5.000000e-03 eta: 10:27:55 time: 0.347194 data_time: 0.056907 memory: 4465 loss_kpt: 104.247824 acc_pose: 0.709698 loss: 104.247824 2022/10/12 11:47:52 - mmengine - INFO - Epoch(train) [13][500/586] lr: 5.000000e-03 eta: 10:28:11 time: 0.368448 data_time: 0.047882 memory: 4465 loss_kpt: 105.660126 acc_pose: 0.665422 loss: 105.660126 2022/10/12 11:48:09 - mmengine - INFO - Epoch(train) [13][550/586] lr: 5.000000e-03 eta: 10:28:08 time: 0.342767 data_time: 0.052318 memory: 4465 loss_kpt: 104.183156 acc_pose: 0.718153 loss: 104.183156 2022/10/12 11:48:22 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:48:40 - mmengine - INFO - Epoch(train) [14][50/586] lr: 5.000000e-03 eta: 10:25:09 time: 0.361460 data_time: 0.063785 memory: 4465 loss_kpt: 104.531460 acc_pose: 0.661755 loss: 104.531460 2022/10/12 11:48:57 - mmengine - INFO - Epoch(train) [14][100/586] lr: 5.000000e-03 eta: 10:25:08 time: 0.345278 data_time: 0.051692 memory: 4465 loss_kpt: 104.591158 acc_pose: 0.729486 loss: 104.591158 2022/10/12 11:49:14 - mmengine - INFO - Epoch(train) [14][150/586] lr: 5.000000e-03 eta: 10:25:03 time: 0.340134 data_time: 0.051217 memory: 4465 loss_kpt: 105.854811 acc_pose: 0.708985 loss: 105.854811 2022/10/12 11:49:31 - mmengine - INFO - Epoch(train) [14][200/586] lr: 5.000000e-03 eta: 10:24:59 time: 0.342406 data_time: 0.051296 memory: 4465 loss_kpt: 105.560982 acc_pose: 0.667740 loss: 105.560982 2022/10/12 11:49:48 - mmengine - INFO - Epoch(train) [14][250/586] lr: 5.000000e-03 eta: 10:24:50 time: 0.335076 data_time: 0.053708 memory: 4465 loss_kpt: 105.692101 acc_pose: 0.648325 loss: 105.692101 2022/10/12 11:50:05 - mmengine - INFO - Epoch(train) [14][300/586] lr: 5.000000e-03 eta: 10:24:38 time: 0.332017 data_time: 0.050644 memory: 4465 loss_kpt: 106.022097 acc_pose: 0.640247 loss: 106.022097 2022/10/12 11:50:21 - mmengine - INFO - Epoch(train) [14][350/586] lr: 5.000000e-03 eta: 10:24:24 time: 0.328389 data_time: 0.053322 memory: 4465 loss_kpt: 103.576590 acc_pose: 0.627564 loss: 103.576590 2022/10/12 11:50:31 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:50:37 - mmengine - INFO - Epoch(train) [14][400/586] lr: 5.000000e-03 eta: 10:24:10 time: 0.328221 data_time: 0.048015 memory: 4465 loss_kpt: 104.985446 acc_pose: 0.674408 loss: 104.985446 2022/10/12 11:50:54 - mmengine - INFO - Epoch(train) [14][450/586] lr: 5.000000e-03 eta: 10:24:01 time: 0.335299 data_time: 0.055017 memory: 4465 loss_kpt: 106.582875 acc_pose: 0.776409 loss: 106.582875 2022/10/12 11:51:11 - mmengine - INFO - Epoch(train) [14][500/586] lr: 5.000000e-03 eta: 10:23:57 time: 0.342936 data_time: 0.052236 memory: 4465 loss_kpt: 105.146384 acc_pose: 0.686096 loss: 105.146384 2022/10/12 11:51:28 - mmengine - INFO - Epoch(train) [14][550/586] lr: 5.000000e-03 eta: 10:23:52 time: 0.342506 data_time: 0.051824 memory: 4465 loss_kpt: 105.274859 acc_pose: 0.680158 loss: 105.274859 2022/10/12 11:51:40 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:51:57 - mmengine - INFO - Epoch(train) [15][50/586] lr: 5.000000e-03 eta: 10:20:50 time: 0.338629 data_time: 0.062873 memory: 4465 loss_kpt: 107.831310 acc_pose: 0.723829 loss: 107.831310 2022/10/12 11:52:14 - mmengine - INFO - Epoch(train) [15][100/586] lr: 5.000000e-03 eta: 10:20:37 time: 0.329273 data_time: 0.053658 memory: 4465 loss_kpt: 105.344083 acc_pose: 0.654578 loss: 105.344083 2022/10/12 11:52:30 - mmengine - INFO - Epoch(train) [15][150/586] lr: 5.000000e-03 eta: 10:20:24 time: 0.328625 data_time: 0.055789 memory: 4465 loss_kpt: 104.374321 acc_pose: 0.682185 loss: 104.374321 2022/10/12 11:52:47 - mmengine - INFO - Epoch(train) [15][200/586] lr: 5.000000e-03 eta: 10:20:13 time: 0.333221 data_time: 0.049503 memory: 4465 loss_kpt: 103.975388 acc_pose: 0.747870 loss: 103.975388 2022/10/12 11:53:03 - mmengine - INFO - Epoch(train) [15][250/586] lr: 5.000000e-03 eta: 10:19:59 time: 0.327581 data_time: 0.052885 memory: 4465 loss_kpt: 105.109527 acc_pose: 0.724138 loss: 105.109527 2022/10/12 11:53:21 - mmengine - INFO - Epoch(train) [15][300/586] lr: 5.000000e-03 eta: 10:19:56 time: 0.343564 data_time: 0.054046 memory: 4465 loss_kpt: 104.291923 acc_pose: 0.761152 loss: 104.291923 2022/10/12 11:53:38 - mmengine - INFO - Epoch(train) [15][350/586] lr: 5.000000e-03 eta: 10:19:55 time: 0.347744 data_time: 0.050954 memory: 4465 loss_kpt: 103.603721 acc_pose: 0.573941 loss: 103.603721 2022/10/12 11:53:55 - mmengine - INFO - Epoch(train) [15][400/586] lr: 5.000000e-03 eta: 10:19:48 time: 0.338710 data_time: 0.052592 memory: 4465 loss_kpt: 102.938505 acc_pose: 0.745315 loss: 102.938505 2022/10/12 11:54:12 - mmengine - INFO - Epoch(train) [15][450/586] lr: 5.000000e-03 eta: 10:19:49 time: 0.350689 data_time: 0.053040 memory: 4465 loss_kpt: 105.263198 acc_pose: 0.686771 loss: 105.263198 2022/10/12 11:54:29 - mmengine - INFO - Epoch(train) [15][500/586] lr: 5.000000e-03 eta: 10:19:41 time: 0.337880 data_time: 0.049054 memory: 4465 loss_kpt: 102.906291 acc_pose: 0.703293 loss: 102.906291 2022/10/12 11:54:46 - mmengine - INFO - Epoch(train) [15][550/586] lr: 5.000000e-03 eta: 10:19:28 time: 0.330866 data_time: 0.054191 memory: 4465 loss_kpt: 103.826612 acc_pose: 0.670456 loss: 103.826612 2022/10/12 11:54:57 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:55:15 - mmengine - INFO - Epoch(train) [16][50/586] lr: 5.000000e-03 eta: 10:16:47 time: 0.352918 data_time: 0.066663 memory: 4465 loss_kpt: 103.974141 acc_pose: 0.750427 loss: 103.974141 2022/10/12 11:55:33 - mmengine - INFO - Epoch(train) [16][100/586] lr: 5.000000e-03 eta: 10:16:48 time: 0.351150 data_time: 0.056431 memory: 4465 loss_kpt: 106.098802 acc_pose: 0.739768 loss: 106.098802 2022/10/12 11:55:49 - mmengine - INFO - Epoch(train) [16][150/586] lr: 5.000000e-03 eta: 10:16:38 time: 0.332770 data_time: 0.055369 memory: 4465 loss_kpt: 103.739664 acc_pose: 0.675666 loss: 103.739664 2022/10/12 11:56:05 - mmengine - INFO - Epoch(train) [16][200/586] lr: 5.000000e-03 eta: 10:16:22 time: 0.324638 data_time: 0.054647 memory: 4465 loss_kpt: 103.505156 acc_pose: 0.716624 loss: 103.505156 2022/10/12 11:56:09 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:56:23 - mmengine - INFO - Epoch(train) [16][250/586] lr: 5.000000e-03 eta: 10:16:16 time: 0.341635 data_time: 0.051765 memory: 4465 loss_kpt: 103.516756 acc_pose: 0.664347 loss: 103.516756 2022/10/12 11:56:39 - mmengine - INFO - Epoch(train) [16][300/586] lr: 5.000000e-03 eta: 10:16:07 time: 0.335361 data_time: 0.055193 memory: 4465 loss_kpt: 107.061242 acc_pose: 0.700795 loss: 107.061242 2022/10/12 11:56:56 - mmengine - INFO - Epoch(train) [16][350/586] lr: 5.000000e-03 eta: 10:16:01 time: 0.341089 data_time: 0.055229 memory: 4465 loss_kpt: 106.021131 acc_pose: 0.525697 loss: 106.021131 2022/10/12 11:57:13 - mmengine - INFO - Epoch(train) [16][400/586] lr: 5.000000e-03 eta: 10:15:54 time: 0.338091 data_time: 0.052008 memory: 4465 loss_kpt: 104.515542 acc_pose: 0.694459 loss: 104.515542 2022/10/12 11:57:30 - mmengine - INFO - Epoch(train) [16][450/586] lr: 5.000000e-03 eta: 10:15:49 time: 0.343149 data_time: 0.056048 memory: 4465 loss_kpt: 104.673086 acc_pose: 0.710392 loss: 104.673086 2022/10/12 11:57:48 - mmengine - INFO - Epoch(train) [16][500/586] lr: 5.000000e-03 eta: 10:15:43 time: 0.341265 data_time: 0.047089 memory: 4465 loss_kpt: 102.139999 acc_pose: 0.562591 loss: 102.139999 2022/10/12 11:58:04 - mmengine - INFO - Epoch(train) [16][550/586] lr: 5.000000e-03 eta: 10:15:34 time: 0.337638 data_time: 0.055663 memory: 4465 loss_kpt: 104.050908 acc_pose: 0.627777 loss: 104.050908 2022/10/12 11:58:16 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 11:58:34 - mmengine - INFO - Epoch(train) [17][50/586] lr: 5.000000e-03 eta: 10:13:06 time: 0.358891 data_time: 0.060661 memory: 4465 loss_kpt: 103.538477 acc_pose: 0.774223 loss: 103.538477 2022/10/12 11:58:52 - mmengine - INFO - Epoch(train) [17][100/586] lr: 5.000000e-03 eta: 10:13:09 time: 0.355862 data_time: 0.056878 memory: 4465 loss_kpt: 101.534753 acc_pose: 0.700025 loss: 101.534753 2022/10/12 11:59:10 - mmengine - INFO - Epoch(train) [17][150/586] lr: 5.000000e-03 eta: 10:13:08 time: 0.349676 data_time: 0.057142 memory: 4465 loss_kpt: 101.940501 acc_pose: 0.690242 loss: 101.940501 2022/10/12 11:59:26 - mmengine - INFO - Epoch(train) [17][200/586] lr: 5.000000e-03 eta: 10:12:56 time: 0.331096 data_time: 0.050450 memory: 4465 loss_kpt: 103.225173 acc_pose: 0.669840 loss: 103.225173 2022/10/12 11:59:43 - mmengine - INFO - Epoch(train) [17][250/586] lr: 5.000000e-03 eta: 10:12:42 time: 0.327811 data_time: 0.051371 memory: 4465 loss_kpt: 102.555176 acc_pose: 0.687391 loss: 102.555176 2022/10/12 11:59:59 - mmengine - INFO - Epoch(train) [17][300/586] lr: 5.000000e-03 eta: 10:12:28 time: 0.327730 data_time: 0.048071 memory: 4465 loss_kpt: 103.017621 acc_pose: 0.719681 loss: 103.017621 2022/10/12 12:00:16 - mmengine - INFO - Epoch(train) [17][350/586] lr: 5.000000e-03 eta: 10:12:18 time: 0.333730 data_time: 0.051641 memory: 4465 loss_kpt: 104.690844 acc_pose: 0.693802 loss: 104.690844 2022/10/12 12:00:32 - mmengine - INFO - Epoch(train) [17][400/586] lr: 5.000000e-03 eta: 10:12:06 time: 0.331579 data_time: 0.047773 memory: 4465 loss_kpt: 103.509619 acc_pose: 0.663961 loss: 103.509619 2022/10/12 12:00:49 - mmengine - INFO - Epoch(train) [17][450/586] lr: 5.000000e-03 eta: 10:11:56 time: 0.335181 data_time: 0.050441 memory: 4465 loss_kpt: 103.282383 acc_pose: 0.720885 loss: 103.282383 2022/10/12 12:01:05 - mmengine - INFO - Epoch(train) [17][500/586] lr: 5.000000e-03 eta: 10:11:40 time: 0.324596 data_time: 0.047700 memory: 4465 loss_kpt: 104.299312 acc_pose: 0.643241 loss: 104.299312 2022/10/12 12:01:21 - mmengine - INFO - Epoch(train) [17][550/586] lr: 5.000000e-03 eta: 10:11:20 time: 0.318866 data_time: 0.053027 memory: 4465 loss_kpt: 103.979839 acc_pose: 0.644140 loss: 103.979839 2022/10/12 12:01:32 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:01:46 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:01:50 - mmengine - INFO - Epoch(train) [18][50/586] lr: 5.000000e-03 eta: 10:08:56 time: 0.351915 data_time: 0.065043 memory: 4465 loss_kpt: 101.484522 acc_pose: 0.645549 loss: 101.484522 2022/10/12 12:02:07 - mmengine - INFO - Epoch(train) [18][100/586] lr: 5.000000e-03 eta: 10:08:49 time: 0.339538 data_time: 0.052704 memory: 4465 loss_kpt: 104.508747 acc_pose: 0.729140 loss: 104.508747 2022/10/12 12:02:24 - mmengine - INFO - Epoch(train) [18][150/586] lr: 5.000000e-03 eta: 10:08:40 time: 0.334526 data_time: 0.050921 memory: 4465 loss_kpt: 102.405819 acc_pose: 0.705651 loss: 102.405819 2022/10/12 12:02:41 - mmengine - INFO - Epoch(train) [18][200/586] lr: 5.000000e-03 eta: 10:08:31 time: 0.336911 data_time: 0.047424 memory: 4465 loss_kpt: 102.081947 acc_pose: 0.713572 loss: 102.081947 2022/10/12 12:02:57 - mmengine - INFO - Epoch(train) [18][250/586] lr: 5.000000e-03 eta: 10:08:20 time: 0.333008 data_time: 0.055118 memory: 4465 loss_kpt: 102.112244 acc_pose: 0.627385 loss: 102.112244 2022/10/12 12:03:14 - mmengine - INFO - Epoch(train) [18][300/586] lr: 5.000000e-03 eta: 10:08:13 time: 0.340686 data_time: 0.051134 memory: 4465 loss_kpt: 103.654258 acc_pose: 0.717904 loss: 103.654258 2022/10/12 12:03:31 - mmengine - INFO - Epoch(train) [18][350/586] lr: 5.000000e-03 eta: 10:08:00 time: 0.328833 data_time: 0.054501 memory: 4465 loss_kpt: 102.556045 acc_pose: 0.710106 loss: 102.556045 2022/10/12 12:03:47 - mmengine - INFO - Epoch(train) [18][400/586] lr: 5.000000e-03 eta: 10:07:45 time: 0.325942 data_time: 0.054367 memory: 4465 loss_kpt: 102.537532 acc_pose: 0.632248 loss: 102.537532 2022/10/12 12:04:04 - mmengine - INFO - Epoch(train) [18][450/586] lr: 5.000000e-03 eta: 10:07:36 time: 0.336087 data_time: 0.055786 memory: 4465 loss_kpt: 100.422739 acc_pose: 0.673672 loss: 100.422739 2022/10/12 12:04:21 - mmengine - INFO - Epoch(train) [18][500/586] lr: 5.000000e-03 eta: 10:07:29 time: 0.341849 data_time: 0.052715 memory: 4465 loss_kpt: 103.369059 acc_pose: 0.700931 loss: 103.369059 2022/10/12 12:04:38 - mmengine - INFO - Epoch(train) [18][550/586] lr: 5.000000e-03 eta: 10:07:26 time: 0.348385 data_time: 0.052293 memory: 4465 loss_kpt: 103.265379 acc_pose: 0.711112 loss: 103.265379 2022/10/12 12:04:50 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:05:08 - mmengine - INFO - Epoch(train) [19][50/586] lr: 5.000000e-03 eta: 10:05:14 time: 0.360425 data_time: 0.065357 memory: 4465 loss_kpt: 102.474730 acc_pose: 0.680378 loss: 102.474730 2022/10/12 12:05:25 - mmengine - INFO - Epoch(train) [19][100/586] lr: 5.000000e-03 eta: 10:05:09 time: 0.343569 data_time: 0.054431 memory: 4465 loss_kpt: 103.589246 acc_pose: 0.736851 loss: 103.589246 2022/10/12 12:05:43 - mmengine - INFO - Epoch(train) [19][150/586] lr: 5.000000e-03 eta: 10:05:06 time: 0.346999 data_time: 0.060214 memory: 4465 loss_kpt: 103.352019 acc_pose: 0.736383 loss: 103.352019 2022/10/12 12:06:00 - mmengine - INFO - Epoch(train) [19][200/586] lr: 5.000000e-03 eta: 10:04:59 time: 0.342192 data_time: 0.056214 memory: 4465 loss_kpt: 101.467236 acc_pose: 0.738852 loss: 101.467236 2022/10/12 12:06:17 - mmengine - INFO - Epoch(train) [19][250/586] lr: 5.000000e-03 eta: 10:04:55 time: 0.346040 data_time: 0.051551 memory: 4465 loss_kpt: 101.448267 acc_pose: 0.739997 loss: 101.448267 2022/10/12 12:06:35 - mmengine - INFO - Epoch(train) [19][300/586] lr: 5.000000e-03 eta: 10:04:53 time: 0.350787 data_time: 0.050092 memory: 4465 loss_kpt: 102.624295 acc_pose: 0.593090 loss: 102.624295 2022/10/12 12:06:52 - mmengine - INFO - Epoch(train) [19][350/586] lr: 5.000000e-03 eta: 10:04:49 time: 0.346806 data_time: 0.048742 memory: 4465 loss_kpt: 101.922598 acc_pose: 0.608844 loss: 101.922598 2022/10/12 12:07:08 - mmengine - INFO - Epoch(train) [19][400/586] lr: 5.000000e-03 eta: 10:04:37 time: 0.332043 data_time: 0.049642 memory: 4465 loss_kpt: 101.902335 acc_pose: 0.745520 loss: 101.902335 2022/10/12 12:07:25 - mmengine - INFO - Epoch(train) [19][450/586] lr: 5.000000e-03 eta: 10:04:27 time: 0.336010 data_time: 0.053314 memory: 4465 loss_kpt: 102.760782 acc_pose: 0.706636 loss: 102.760782 2022/10/12 12:07:26 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:07:42 - mmengine - INFO - Epoch(train) [19][500/586] lr: 5.000000e-03 eta: 10:04:15 time: 0.331779 data_time: 0.051453 memory: 4465 loss_kpt: 101.896004 acc_pose: 0.713260 loss: 101.896004 2022/10/12 12:07:58 - mmengine - INFO - Epoch(train) [19][550/586] lr: 5.000000e-03 eta: 10:04:03 time: 0.332035 data_time: 0.055578 memory: 4465 loss_kpt: 100.516716 acc_pose: 0.654483 loss: 100.516716 2022/10/12 12:08:10 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:08:28 - mmengine - INFO - Epoch(train) [20][50/586] lr: 5.000000e-03 eta: 10:01:54 time: 0.354898 data_time: 0.065716 memory: 4465 loss_kpt: 102.648099 acc_pose: 0.683292 loss: 102.648099 2022/10/12 12:08:45 - mmengine - INFO - Epoch(train) [20][100/586] lr: 5.000000e-03 eta: 10:01:44 time: 0.335184 data_time: 0.050709 memory: 4465 loss_kpt: 100.023557 acc_pose: 0.674395 loss: 100.023557 2022/10/12 12:09:02 - mmengine - INFO - Epoch(train) [20][150/586] lr: 5.000000e-03 eta: 10:01:37 time: 0.339940 data_time: 0.051630 memory: 4465 loss_kpt: 100.808599 acc_pose: 0.776117 loss: 100.808599 2022/10/12 12:09:19 - mmengine - INFO - Epoch(train) [20][200/586] lr: 5.000000e-03 eta: 10:01:26 time: 0.334095 data_time: 0.048483 memory: 4465 loss_kpt: 103.290249 acc_pose: 0.725164 loss: 103.290249 2022/10/12 12:09:36 - mmengine - INFO - Epoch(train) [20][250/586] lr: 5.000000e-03 eta: 10:01:19 time: 0.341742 data_time: 0.051674 memory: 4465 loss_kpt: 100.936548 acc_pose: 0.648512 loss: 100.936548 2022/10/12 12:09:52 - mmengine - INFO - Epoch(train) [20][300/586] lr: 5.000000e-03 eta: 10:01:06 time: 0.330017 data_time: 0.048408 memory: 4465 loss_kpt: 101.999139 acc_pose: 0.712115 loss: 101.999139 2022/10/12 12:10:10 - mmengine - INFO - Epoch(train) [20][350/586] lr: 5.000000e-03 eta: 10:01:05 time: 0.353186 data_time: 0.052638 memory: 4465 loss_kpt: 98.984132 acc_pose: 0.717266 loss: 98.984132 2022/10/12 12:10:27 - mmengine - INFO - Epoch(train) [20][400/586] lr: 5.000000e-03 eta: 10:00:54 time: 0.333774 data_time: 0.048370 memory: 4465 loss_kpt: 101.418739 acc_pose: 0.715601 loss: 101.418739 2022/10/12 12:10:44 - mmengine - INFO - Epoch(train) [20][450/586] lr: 5.000000e-03 eta: 10:00:54 time: 0.356472 data_time: 0.050744 memory: 4465 loss_kpt: 101.702098 acc_pose: 0.751080 loss: 101.702098 2022/10/12 12:11:01 - mmengine - INFO - Epoch(train) [20][500/586] lr: 5.000000e-03 eta: 10:00:43 time: 0.335557 data_time: 0.052828 memory: 4465 loss_kpt: 100.979869 acc_pose: 0.724442 loss: 100.979869 2022/10/12 12:11:18 - mmengine - INFO - Epoch(train) [20][550/586] lr: 5.000000e-03 eta: 10:00:36 time: 0.342178 data_time: 0.049228 memory: 4465 loss_kpt: 102.205463 acc_pose: 0.723693 loss: 102.205463 2022/10/12 12:11:31 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:11:31 - mmengine - INFO - Saving checkpoint at 20 epochs 2022/10/12 12:11:40 - mmengine - INFO - Epoch(val) [20][50/407] eta: 0:00:50 time: 0.142358 data_time: 0.013371 memory: 4465 2022/10/12 12:11:47 - mmengine - INFO - Epoch(val) [20][100/407] eta: 0:00:41 time: 0.134012 data_time: 0.008950 memory: 1026 2022/10/12 12:11:54 - mmengine - INFO - Epoch(val) [20][150/407] eta: 0:00:34 time: 0.132362 data_time: 0.008568 memory: 1026 2022/10/12 12:12:00 - mmengine - INFO - Epoch(val) [20][200/407] eta: 0:00:28 time: 0.137335 data_time: 0.009024 memory: 1026 2022/10/12 12:12:07 - mmengine - INFO - Epoch(val) [20][250/407] eta: 0:00:20 time: 0.132556 data_time: 0.008503 memory: 1026 2022/10/12 12:12:14 - mmengine - INFO - Epoch(val) [20][300/407] eta: 0:00:14 time: 0.133388 data_time: 0.009009 memory: 1026 2022/10/12 12:12:20 - mmengine - INFO - Epoch(val) [20][350/407] eta: 0:00:07 time: 0.130713 data_time: 0.008421 memory: 1026 2022/10/12 12:12:27 - mmengine - INFO - Epoch(val) [20][400/407] eta: 0:00:00 time: 0.125948 data_time: 0.007833 memory: 1026 2022/10/12 12:12:40 - mmengine - INFO - Evaluating CocoMetric... 2022/10/12 12:12:57 - mmengine - INFO - Epoch(val) [20][407/407] coco/AP: 0.557589 coco/AP .5: 0.816891 coco/AP .75: 0.610090 coco/AP (M): 0.536080 coco/AP (L): 0.603947 coco/AR: 0.640948 coco/AR .5: 0.872166 coco/AR .75: 0.695372 coco/AR (M): 0.601202 coco/AR (L): 0.695541 2022/10/12 12:12:57 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/liqikai/openmmlab/pt112cu113py38/mmpose/work_dirs/20221012/rsn50/best_coco/AP_epoch_10.pth is removed 2022/10/12 12:12:58 - mmengine - INFO - The best checkpoint with 0.5576 coco/AP at 20 epoch is saved to best_coco/AP_epoch_20.pth. 2022/10/12 12:13:15 - mmengine - INFO - Epoch(train) [21][50/586] lr: 5.000000e-03 eta: 9:58:26 time: 0.339850 data_time: 0.062271 memory: 4465 loss_kpt: 101.885103 acc_pose: 0.666654 loss: 101.885103 2022/10/12 12:13:32 - mmengine - INFO - Epoch(train) [21][100/586] lr: 5.000000e-03 eta: 9:58:16 time: 0.335309 data_time: 0.054345 memory: 4465 loss_kpt: 100.710201 acc_pose: 0.724601 loss: 100.710201 2022/10/12 12:13:48 - mmengine - INFO - Epoch(train) [21][150/586] lr: 5.000000e-03 eta: 9:58:00 time: 0.324831 data_time: 0.051133 memory: 4465 loss_kpt: 103.068780 acc_pose: 0.650053 loss: 103.068780 2022/10/12 12:14:05 - mmengine - INFO - Epoch(train) [21][200/586] lr: 5.000000e-03 eta: 9:57:49 time: 0.332596 data_time: 0.052162 memory: 4465 loss_kpt: 101.353083 acc_pose: 0.752284 loss: 101.353083 2022/10/12 12:14:21 - mmengine - INFO - Epoch(train) [21][250/586] lr: 5.000000e-03 eta: 9:57:33 time: 0.324182 data_time: 0.046941 memory: 4465 loss_kpt: 99.794010 acc_pose: 0.781488 loss: 99.794010 2022/10/12 12:14:32 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:14:38 - mmengine - INFO - Epoch(train) [21][300/586] lr: 5.000000e-03 eta: 9:57:23 time: 0.334814 data_time: 0.052524 memory: 4465 loss_kpt: 99.946268 acc_pose: 0.734834 loss: 99.946268 2022/10/12 12:14:55 - mmengine - INFO - Epoch(train) [21][350/586] lr: 5.000000e-03 eta: 9:57:10 time: 0.330158 data_time: 0.049090 memory: 4465 loss_kpt: 101.502600 acc_pose: 0.666360 loss: 101.502600 2022/10/12 12:15:11 - mmengine - INFO - Epoch(train) [21][400/586] lr: 5.000000e-03 eta: 9:56:57 time: 0.328604 data_time: 0.051128 memory: 4465 loss_kpt: 100.359851 acc_pose: 0.780216 loss: 100.359851 2022/10/12 12:15:28 - mmengine - INFO - Epoch(train) [21][450/586] lr: 5.000000e-03 eta: 9:56:45 time: 0.331963 data_time: 0.048434 memory: 4465 loss_kpt: 101.863085 acc_pose: 0.793440 loss: 101.863085 2022/10/12 12:15:44 - mmengine - INFO - Epoch(train) [21][500/586] lr: 5.000000e-03 eta: 9:56:32 time: 0.331495 data_time: 0.051609 memory: 4465 loss_kpt: 101.675192 acc_pose: 0.717665 loss: 101.675192 2022/10/12 12:16:01 - mmengine - INFO - Epoch(train) [21][550/586] lr: 5.000000e-03 eta: 9:56:21 time: 0.334578 data_time: 0.051460 memory: 4465 loss_kpt: 99.311320 acc_pose: 0.762096 loss: 99.311320 2022/10/12 12:16:12 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:16:30 - mmengine - INFO - Epoch(train) [22][50/586] lr: 5.000000e-03 eta: 9:54:27 time: 0.361111 data_time: 0.062326 memory: 4465 loss_kpt: 102.253760 acc_pose: 0.680500 loss: 102.253760 2022/10/12 12:16:48 - mmengine - INFO - Epoch(train) [22][100/586] lr: 5.000000e-03 eta: 9:54:22 time: 0.348871 data_time: 0.048780 memory: 4465 loss_kpt: 99.093949 acc_pose: 0.715315 loss: 99.093949 2022/10/12 12:17:05 - mmengine - INFO - Epoch(train) [22][150/586] lr: 5.000000e-03 eta: 9:54:11 time: 0.333549 data_time: 0.052873 memory: 4465 loss_kpt: 100.622903 acc_pose: 0.733572 loss: 100.622903 2022/10/12 12:17:21 - mmengine - INFO - Epoch(train) [22][200/586] lr: 5.000000e-03 eta: 9:53:59 time: 0.331297 data_time: 0.052782 memory: 4465 loss_kpt: 100.319015 acc_pose: 0.808654 loss: 100.319015 2022/10/12 12:17:37 - mmengine - INFO - Epoch(train) [22][250/586] lr: 5.000000e-03 eta: 9:53:45 time: 0.326660 data_time: 0.056010 memory: 4465 loss_kpt: 100.152102 acc_pose: 0.702429 loss: 100.152102 2022/10/12 12:17:54 - mmengine - INFO - Epoch(train) [22][300/586] lr: 5.000000e-03 eta: 9:53:30 time: 0.325839 data_time: 0.048034 memory: 4465 loss_kpt: 100.596354 acc_pose: 0.761955 loss: 100.596354 2022/10/12 12:18:10 - mmengine - INFO - Epoch(train) [22][350/586] lr: 5.000000e-03 eta: 9:53:19 time: 0.333934 data_time: 0.053004 memory: 4465 loss_kpt: 99.946745 acc_pose: 0.685423 loss: 99.946745 2022/10/12 12:18:27 - mmengine - INFO - Epoch(train) [22][400/586] lr: 5.000000e-03 eta: 9:53:10 time: 0.339120 data_time: 0.047791 memory: 4465 loss_kpt: 100.791454 acc_pose: 0.785880 loss: 100.791454 2022/10/12 12:18:44 - mmengine - INFO - Epoch(train) [22][450/586] lr: 5.000000e-03 eta: 9:52:55 time: 0.324135 data_time: 0.052582 memory: 4465 loss_kpt: 99.263632 acc_pose: 0.704001 loss: 99.263632 2022/10/12 12:19:00 - mmengine - INFO - Epoch(train) [22][500/586] lr: 5.000000e-03 eta: 9:52:43 time: 0.332329 data_time: 0.051357 memory: 4465 loss_kpt: 100.553608 acc_pose: 0.710282 loss: 100.553608 2022/10/12 12:19:17 - mmengine - INFO - Epoch(train) [22][550/586] lr: 5.000000e-03 eta: 9:52:31 time: 0.332215 data_time: 0.049442 memory: 4465 loss_kpt: 99.950391 acc_pose: 0.678279 loss: 99.950391 2022/10/12 12:19:28 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:19:46 - mmengine - INFO - Epoch(train) [23][50/586] lr: 5.000000e-03 eta: 9:50:39 time: 0.357295 data_time: 0.058613 memory: 4465 loss_kpt: 99.802418 acc_pose: 0.758094 loss: 99.802418 2022/10/12 12:20:04 - mmengine - INFO - Epoch(train) [23][100/586] lr: 5.000000e-03 eta: 9:50:36 time: 0.352166 data_time: 0.050052 memory: 4465 loss_kpt: 98.164436 acc_pose: 0.695798 loss: 98.164436 2022/10/12 12:20:07 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:20:21 - mmengine - INFO - Epoch(train) [23][150/586] lr: 5.000000e-03 eta: 9:50:25 time: 0.332960 data_time: 0.052579 memory: 4465 loss_kpt: 98.483598 acc_pose: 0.741426 loss: 98.483598 2022/10/12 12:20:37 - mmengine - INFO - Epoch(train) [23][200/586] lr: 5.000000e-03 eta: 9:50:10 time: 0.326469 data_time: 0.049618 memory: 4465 loss_kpt: 101.571401 acc_pose: 0.701958 loss: 101.571401 2022/10/12 12:20:53 - mmengine - INFO - Epoch(train) [23][250/586] lr: 5.000000e-03 eta: 9:49:58 time: 0.330114 data_time: 0.048402 memory: 4465 loss_kpt: 101.255617 acc_pose: 0.691667 loss: 101.255617 2022/10/12 12:21:10 - mmengine - INFO - Epoch(train) [23][300/586] lr: 5.000000e-03 eta: 9:49:49 time: 0.339376 data_time: 0.050382 memory: 4465 loss_kpt: 98.692212 acc_pose: 0.655513 loss: 98.692212 2022/10/12 12:21:27 - mmengine - INFO - Epoch(train) [23][350/586] lr: 5.000000e-03 eta: 9:49:37 time: 0.332344 data_time: 0.048399 memory: 4465 loss_kpt: 99.736256 acc_pose: 0.675340 loss: 99.736256 2022/10/12 12:21:44 - mmengine - INFO - Epoch(train) [23][400/586] lr: 5.000000e-03 eta: 9:49:28 time: 0.338751 data_time: 0.046151 memory: 4465 loss_kpt: 99.958549 acc_pose: 0.755602 loss: 99.958549 2022/10/12 12:22:02 - mmengine - INFO - Epoch(train) [23][450/586] lr: 5.000000e-03 eta: 9:49:24 time: 0.351518 data_time: 0.050326 memory: 4465 loss_kpt: 101.230286 acc_pose: 0.755856 loss: 101.230286 2022/10/12 12:22:19 - mmengine - INFO - Epoch(train) [23][500/586] lr: 5.000000e-03 eta: 9:49:16 time: 0.342170 data_time: 0.047070 memory: 4465 loss_kpt: 100.716832 acc_pose: 0.665411 loss: 100.716832 2022/10/12 12:22:36 - mmengine - INFO - Epoch(train) [23][550/586] lr: 5.000000e-03 eta: 9:49:09 time: 0.345005 data_time: 0.055392 memory: 4465 loss_kpt: 99.790497 acc_pose: 0.638982 loss: 99.790497 2022/10/12 12:22:48 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:23:06 - mmengine - INFO - Epoch(train) [24][50/586] lr: 5.000000e-03 eta: 9:47:18 time: 0.349776 data_time: 0.068119 memory: 4465 loss_kpt: 100.836285 acc_pose: 0.738161 loss: 100.836285 2022/10/12 12:23:23 - mmengine - INFO - Epoch(train) [24][100/586] lr: 5.000000e-03 eta: 9:47:10 time: 0.343009 data_time: 0.048499 memory: 4465 loss_kpt: 100.531116 acc_pose: 0.714560 loss: 100.531116 2022/10/12 12:23:40 - mmengine - INFO - Epoch(train) [24][150/586] lr: 5.000000e-03 eta: 9:47:04 time: 0.346430 data_time: 0.054514 memory: 4465 loss_kpt: 98.685001 acc_pose: 0.749159 loss: 98.685001 2022/10/12 12:23:57 - mmengine - INFO - Epoch(train) [24][200/586] lr: 5.000000e-03 eta: 9:46:56 time: 0.340415 data_time: 0.052598 memory: 4465 loss_kpt: 98.177850 acc_pose: 0.724412 loss: 98.177850 2022/10/12 12:24:14 - mmengine - INFO - Epoch(train) [24][250/586] lr: 5.000000e-03 eta: 9:46:46 time: 0.337134 data_time: 0.055180 memory: 4465 loss_kpt: 99.292003 acc_pose: 0.672349 loss: 99.292003 2022/10/12 12:24:30 - mmengine - INFO - Epoch(train) [24][300/586] lr: 5.000000e-03 eta: 9:46:31 time: 0.326385 data_time: 0.052780 memory: 4465 loss_kpt: 98.055816 acc_pose: 0.711586 loss: 98.055816 2022/10/12 12:24:47 - mmengine - INFO - Epoch(train) [24][350/586] lr: 5.000000e-03 eta: 9:46:22 time: 0.338509 data_time: 0.054475 memory: 4465 loss_kpt: 99.240238 acc_pose: 0.786673 loss: 99.240238 2022/10/12 12:25:04 - mmengine - INFO - Epoch(train) [24][400/586] lr: 5.000000e-03 eta: 9:46:10 time: 0.333312 data_time: 0.052599 memory: 4465 loss_kpt: 100.216304 acc_pose: 0.672943 loss: 100.216304 2022/10/12 12:25:20 - mmengine - INFO - Epoch(train) [24][450/586] lr: 5.000000e-03 eta: 9:45:58 time: 0.332160 data_time: 0.058322 memory: 4465 loss_kpt: 99.752392 acc_pose: 0.720052 loss: 99.752392 2022/10/12 12:25:37 - mmengine - INFO - Epoch(train) [24][500/586] lr: 5.000000e-03 eta: 9:45:44 time: 0.329330 data_time: 0.051340 memory: 4465 loss_kpt: 99.857797 acc_pose: 0.761211 loss: 99.857797 2022/10/12 12:25:44 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:25:54 - mmengine - INFO - Epoch(train) [24][550/586] lr: 5.000000e-03 eta: 9:45:32 time: 0.331605 data_time: 0.051789 memory: 4465 loss_kpt: 99.446411 acc_pose: 0.728127 loss: 99.446411 2022/10/12 12:26:05 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:26:23 - mmengine - INFO - Epoch(train) [25][50/586] lr: 5.000000e-03 eta: 9:43:45 time: 0.348165 data_time: 0.059460 memory: 4465 loss_kpt: 98.748648 acc_pose: 0.800905 loss: 98.748648 2022/10/12 12:26:40 - mmengine - INFO - Epoch(train) [25][100/586] lr: 5.000000e-03 eta: 9:43:37 time: 0.344491 data_time: 0.054147 memory: 4465 loss_kpt: 101.077830 acc_pose: 0.660951 loss: 101.077830 2022/10/12 12:26:57 - mmengine - INFO - Epoch(train) [25][150/586] lr: 5.000000e-03 eta: 9:43:28 time: 0.339024 data_time: 0.056390 memory: 4465 loss_kpt: 100.519463 acc_pose: 0.616995 loss: 100.519463 2022/10/12 12:27:14 - mmengine - INFO - Epoch(train) [25][200/586] lr: 5.000000e-03 eta: 9:43:16 time: 0.332162 data_time: 0.048995 memory: 4465 loss_kpt: 98.764917 acc_pose: 0.656841 loss: 98.764917 2022/10/12 12:27:31 - mmengine - INFO - Epoch(train) [25][250/586] lr: 5.000000e-03 eta: 9:43:07 time: 0.340712 data_time: 0.054099 memory: 4465 loss_kpt: 99.467915 acc_pose: 0.750162 loss: 99.467915 2022/10/12 12:27:47 - mmengine - INFO - Epoch(train) [25][300/586] lr: 5.000000e-03 eta: 9:42:56 time: 0.333732 data_time: 0.052766 memory: 4465 loss_kpt: 99.480111 acc_pose: 0.701876 loss: 99.480111 2022/10/12 12:28:04 - mmengine - INFO - Epoch(train) [25][350/586] lr: 5.000000e-03 eta: 9:42:44 time: 0.334320 data_time: 0.051829 memory: 4465 loss_kpt: 100.106264 acc_pose: 0.634268 loss: 100.106264 2022/10/12 12:28:21 - mmengine - INFO - Epoch(train) [25][400/586] lr: 5.000000e-03 eta: 9:42:32 time: 0.333058 data_time: 0.050711 memory: 4465 loss_kpt: 100.270564 acc_pose: 0.682977 loss: 100.270564 2022/10/12 12:28:38 - mmengine - INFO - Epoch(train) [25][450/586] lr: 5.000000e-03 eta: 9:42:22 time: 0.336510 data_time: 0.050268 memory: 4465 loss_kpt: 98.459932 acc_pose: 0.733974 loss: 98.459932 2022/10/12 12:28:55 - mmengine - INFO - Epoch(train) [25][500/586] lr: 5.000000e-03 eta: 9:42:13 time: 0.342610 data_time: 0.052743 memory: 4465 loss_kpt: 99.440174 acc_pose: 0.655972 loss: 99.440174 2022/10/12 12:29:11 - mmengine - INFO - Epoch(train) [25][550/586] lr: 5.000000e-03 eta: 9:42:02 time: 0.335793 data_time: 0.054258 memory: 4465 loss_kpt: 98.252719 acc_pose: 0.747305 loss: 98.252719 2022/10/12 12:29:23 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:29:41 - mmengine - INFO - Epoch(train) [26][50/586] lr: 5.000000e-03 eta: 9:40:23 time: 0.360407 data_time: 0.065736 memory: 4465 loss_kpt: 99.896223 acc_pose: 0.703195 loss: 99.896223 2022/10/12 12:29:58 - mmengine - INFO - Epoch(train) [26][100/586] lr: 5.000000e-03 eta: 9:40:14 time: 0.338663 data_time: 0.051108 memory: 4465 loss_kpt: 99.382922 acc_pose: 0.743551 loss: 99.382922 2022/10/12 12:30:15 - mmengine - INFO - Epoch(train) [26][150/586] lr: 5.000000e-03 eta: 9:40:04 time: 0.340250 data_time: 0.050305 memory: 4465 loss_kpt: 99.929378 acc_pose: 0.762602 loss: 99.929378 2022/10/12 12:30:32 - mmengine - INFO - Epoch(train) [26][200/586] lr: 5.000000e-03 eta: 9:39:56 time: 0.341498 data_time: 0.050620 memory: 4465 loss_kpt: 98.706582 acc_pose: 0.680709 loss: 98.706582 2022/10/12 12:30:49 - mmengine - INFO - Epoch(train) [26][250/586] lr: 5.000000e-03 eta: 9:39:44 time: 0.334583 data_time: 0.050280 memory: 4465 loss_kpt: 98.920516 acc_pose: 0.615903 loss: 98.920516 2022/10/12 12:31:06 - mmengine - INFO - Epoch(train) [26][300/586] lr: 5.000000e-03 eta: 9:39:35 time: 0.339055 data_time: 0.047465 memory: 4465 loss_kpt: 99.663467 acc_pose: 0.633466 loss: 99.663467 2022/10/12 12:31:23 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:31:23 - mmengine - INFO - Epoch(train) [26][350/586] lr: 5.000000e-03 eta: 9:39:24 time: 0.337542 data_time: 0.053652 memory: 4465 loss_kpt: 99.435941 acc_pose: 0.702668 loss: 99.435941 2022/10/12 12:31:40 - mmengine - INFO - Epoch(train) [26][400/586] lr: 5.000000e-03 eta: 9:39:14 time: 0.338695 data_time: 0.050457 memory: 4465 loss_kpt: 97.436272 acc_pose: 0.730356 loss: 97.436272 2022/10/12 12:31:57 - mmengine - INFO - Epoch(train) [26][450/586] lr: 5.000000e-03 eta: 9:39:07 time: 0.345265 data_time: 0.052420 memory: 4465 loss_kpt: 99.820737 acc_pose: 0.765884 loss: 99.820737 2022/10/12 12:32:13 - mmengine - INFO - Epoch(train) [26][500/586] lr: 5.000000e-03 eta: 9:38:53 time: 0.329595 data_time: 0.051164 memory: 4465 loss_kpt: 99.575069 acc_pose: 0.651936 loss: 99.575069 2022/10/12 12:32:30 - mmengine - INFO - Epoch(train) [26][550/586] lr: 5.000000e-03 eta: 9:38:42 time: 0.335464 data_time: 0.048218 memory: 4465 loss_kpt: 96.856551 acc_pose: 0.765765 loss: 96.856551 2022/10/12 12:32:41 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:33:00 - mmengine - INFO - Epoch(train) [27][50/586] lr: 5.000000e-03 eta: 9:37:07 time: 0.363933 data_time: 0.059000 memory: 4465 loss_kpt: 98.819749 acc_pose: 0.704239 loss: 98.819749 2022/10/12 12:33:17 - mmengine - INFO - Epoch(train) [27][100/586] lr: 5.000000e-03 eta: 9:36:59 time: 0.342798 data_time: 0.054038 memory: 4465 loss_kpt: 97.981595 acc_pose: 0.740647 loss: 97.981595 2022/10/12 12:33:34 - mmengine - INFO - Epoch(train) [27][150/586] lr: 5.000000e-03 eta: 9:36:54 time: 0.352900 data_time: 0.056623 memory: 4465 loss_kpt: 99.087235 acc_pose: 0.793913 loss: 99.087235 2022/10/12 12:33:52 - mmengine - INFO - Epoch(train) [27][200/586] lr: 5.000000e-03 eta: 9:36:48 time: 0.351926 data_time: 0.052542 memory: 4465 loss_kpt: 97.933736 acc_pose: 0.795270 loss: 97.933736 2022/10/12 12:34:10 - mmengine - INFO - Epoch(train) [27][250/586] lr: 5.000000e-03 eta: 9:36:44 time: 0.355860 data_time: 0.055111 memory: 4465 loss_kpt: 99.272430 acc_pose: 0.747200 loss: 99.272430 2022/10/12 12:34:27 - mmengine - INFO - Epoch(train) [27][300/586] lr: 5.000000e-03 eta: 9:36:36 time: 0.346015 data_time: 0.053556 memory: 4465 loss_kpt: 97.253198 acc_pose: 0.751977 loss: 97.253198 2022/10/12 12:34:45 - mmengine - INFO - Epoch(train) [27][350/586] lr: 5.000000e-03 eta: 9:36:31 time: 0.351186 data_time: 0.055194 memory: 4465 loss_kpt: 97.745172 acc_pose: 0.773617 loss: 97.745172 2022/10/12 12:35:02 - mmengine - INFO - Epoch(train) [27][400/586] lr: 5.000000e-03 eta: 9:36:22 time: 0.344334 data_time: 0.049894 memory: 4465 loss_kpt: 100.673441 acc_pose: 0.774139 loss: 100.673441 2022/10/12 12:35:19 - mmengine - INFO - Epoch(train) [27][450/586] lr: 5.000000e-03 eta: 9:36:16 time: 0.349831 data_time: 0.056004 memory: 4465 loss_kpt: 96.321247 acc_pose: 0.686021 loss: 96.321247 2022/10/12 12:35:36 - mmengine - INFO - Epoch(train) [27][500/586] lr: 5.000000e-03 eta: 9:36:05 time: 0.336803 data_time: 0.050818 memory: 4465 loss_kpt: 99.277425 acc_pose: 0.749379 loss: 99.277425 2022/10/12 12:35:53 - mmengine - INFO - Epoch(train) [27][550/586] lr: 5.000000e-03 eta: 9:35:54 time: 0.339085 data_time: 0.052025 memory: 4465 loss_kpt: 99.204383 acc_pose: 0.749736 loss: 99.204383 2022/10/12 12:36:05 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:36:23 - mmengine - INFO - Epoch(train) [28][50/586] lr: 5.000000e-03 eta: 9:34:19 time: 0.353736 data_time: 0.066457 memory: 4465 loss_kpt: 98.629906 acc_pose: 0.706143 loss: 98.629906 2022/10/12 12:36:40 - mmengine - INFO - Epoch(train) [28][100/586] lr: 5.000000e-03 eta: 9:34:08 time: 0.335749 data_time: 0.050339 memory: 4465 loss_kpt: 96.380571 acc_pose: 0.711234 loss: 96.380571 2022/10/12 12:36:57 - mmengine - INFO - Epoch(train) [28][150/586] lr: 5.000000e-03 eta: 9:33:56 time: 0.335216 data_time: 0.054409 memory: 4465 loss_kpt: 96.978764 acc_pose: 0.602075 loss: 96.978764 2022/10/12 12:37:06 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:37:14 - mmengine - INFO - Epoch(train) [28][200/586] lr: 5.000000e-03 eta: 9:33:49 time: 0.349628 data_time: 0.054387 memory: 4465 loss_kpt: 99.143276 acc_pose: 0.773695 loss: 99.143276 2022/10/12 12:37:31 - mmengine - INFO - Epoch(train) [28][250/586] lr: 5.000000e-03 eta: 9:33:36 time: 0.329633 data_time: 0.050486 memory: 4465 loss_kpt: 97.904753 acc_pose: 0.750546 loss: 97.904753 2022/10/12 12:37:47 - mmengine - INFO - Epoch(train) [28][300/586] lr: 5.000000e-03 eta: 9:33:24 time: 0.334021 data_time: 0.055229 memory: 4465 loss_kpt: 97.793161 acc_pose: 0.646297 loss: 97.793161 2022/10/12 12:38:04 - mmengine - INFO - Epoch(train) [28][350/586] lr: 5.000000e-03 eta: 9:33:12 time: 0.335467 data_time: 0.052598 memory: 4465 loss_kpt: 98.063138 acc_pose: 0.718537 loss: 98.063138 2022/10/12 12:38:21 - mmengine - INFO - Epoch(train) [28][400/586] lr: 5.000000e-03 eta: 9:33:00 time: 0.331217 data_time: 0.055131 memory: 4465 loss_kpt: 97.972548 acc_pose: 0.758811 loss: 97.972548 2022/10/12 12:38:37 - mmengine - INFO - Epoch(train) [28][450/586] lr: 5.000000e-03 eta: 9:32:45 time: 0.327788 data_time: 0.052627 memory: 4465 loss_kpt: 99.380512 acc_pose: 0.717564 loss: 99.380512 2022/10/12 12:38:54 - mmengine - INFO - Epoch(train) [28][500/586] lr: 5.000000e-03 eta: 9:32:32 time: 0.329435 data_time: 0.054935 memory: 4465 loss_kpt: 96.556389 acc_pose: 0.743161 loss: 96.556389 2022/10/12 12:39:10 - mmengine - INFO - Epoch(train) [28][550/586] lr: 5.000000e-03 eta: 9:32:18 time: 0.330092 data_time: 0.050285 memory: 4465 loss_kpt: 98.720146 acc_pose: 0.712711 loss: 98.720146 2022/10/12 12:39:21 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:39:39 - mmengine - INFO - Epoch(train) [29][50/586] lr: 5.000000e-03 eta: 9:30:44 time: 0.348573 data_time: 0.064331 memory: 4465 loss_kpt: 97.361013 acc_pose: 0.716205 loss: 97.361013 2022/10/12 12:39:55 - mmengine - INFO - Epoch(train) [29][100/586] lr: 5.000000e-03 eta: 9:30:31 time: 0.329649 data_time: 0.048232 memory: 4465 loss_kpt: 99.255528 acc_pose: 0.687666 loss: 99.255528 2022/10/12 12:40:12 - mmengine - INFO - Epoch(train) [29][150/586] lr: 5.000000e-03 eta: 9:30:18 time: 0.330361 data_time: 0.050956 memory: 4465 loss_kpt: 97.172068 acc_pose: 0.757818 loss: 97.172068 2022/10/12 12:40:29 - mmengine - INFO - Epoch(train) [29][200/586] lr: 5.000000e-03 eta: 9:30:09 time: 0.344244 data_time: 0.052742 memory: 4465 loss_kpt: 99.389595 acc_pose: 0.729639 loss: 99.389595 2022/10/12 12:40:46 - mmengine - INFO - Epoch(train) [29][250/586] lr: 5.000000e-03 eta: 9:29:58 time: 0.335373 data_time: 0.055239 memory: 4465 loss_kpt: 97.183476 acc_pose: 0.723246 loss: 97.183476 2022/10/12 12:41:03 - mmengine - INFO - Epoch(train) [29][300/586] lr: 5.000000e-03 eta: 9:29:50 time: 0.347971 data_time: 0.050225 memory: 4465 loss_kpt: 96.750121 acc_pose: 0.638207 loss: 96.750121 2022/10/12 12:41:20 - mmengine - INFO - Epoch(train) [29][350/586] lr: 5.000000e-03 eta: 9:29:40 time: 0.340100 data_time: 0.054895 memory: 4465 loss_kpt: 97.483188 acc_pose: 0.763758 loss: 97.483188 2022/10/12 12:41:37 - mmengine - INFO - Epoch(train) [29][400/586] lr: 5.000000e-03 eta: 9:29:27 time: 0.331155 data_time: 0.053446 memory: 4465 loss_kpt: 97.486555 acc_pose: 0.750029 loss: 97.486555 2022/10/12 12:41:54 - mmengine - INFO - Epoch(train) [29][450/586] lr: 5.000000e-03 eta: 9:29:17 time: 0.343058 data_time: 0.054289 memory: 4465 loss_kpt: 97.941207 acc_pose: 0.749986 loss: 97.941207 2022/10/12 12:42:11 - mmengine - INFO - Epoch(train) [29][500/586] lr: 5.000000e-03 eta: 9:29:10 time: 0.347955 data_time: 0.051276 memory: 4465 loss_kpt: 97.833172 acc_pose: 0.725967 loss: 97.833172 2022/10/12 12:42:29 - mmengine - INFO - Epoch(train) [29][550/586] lr: 5.000000e-03 eta: 9:29:04 time: 0.354291 data_time: 0.050821 memory: 4465 loss_kpt: 98.463154 acc_pose: 0.698860 loss: 98.463154 2022/10/12 12:42:42 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:42:44 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:42:59 - mmengine - INFO - Epoch(train) [30][50/586] lr: 5.000000e-03 eta: 9:27:30 time: 0.342229 data_time: 0.062436 memory: 4465 loss_kpt: 97.953692 acc_pose: 0.694713 loss: 97.953692 2022/10/12 12:43:15 - mmengine - INFO - Epoch(train) [30][100/586] lr: 5.000000e-03 eta: 9:27:18 time: 0.334584 data_time: 0.050536 memory: 4465 loss_kpt: 97.298415 acc_pose: 0.797551 loss: 97.298415 2022/10/12 12:43:33 - mmengine - INFO - Epoch(train) [30][150/586] lr: 5.000000e-03 eta: 9:27:12 time: 0.354065 data_time: 0.056561 memory: 4465 loss_kpt: 97.819633 acc_pose: 0.684953 loss: 97.819633 2022/10/12 12:43:50 - mmengine - INFO - Epoch(train) [30][200/586] lr: 5.000000e-03 eta: 9:27:00 time: 0.332752 data_time: 0.046707 memory: 4465 loss_kpt: 99.682630 acc_pose: 0.730153 loss: 99.682630 2022/10/12 12:44:06 - mmengine - INFO - Epoch(train) [30][250/586] lr: 5.000000e-03 eta: 9:26:46 time: 0.328414 data_time: 0.054694 memory: 4465 loss_kpt: 97.222924 acc_pose: 0.745991 loss: 97.222924 2022/10/12 12:44:22 - mmengine - INFO - Epoch(train) [30][300/586] lr: 5.000000e-03 eta: 9:26:32 time: 0.326627 data_time: 0.049149 memory: 4465 loss_kpt: 97.510423 acc_pose: 0.765007 loss: 97.510423 2022/10/12 12:44:39 - mmengine - INFO - Epoch(train) [30][350/586] lr: 5.000000e-03 eta: 9:26:18 time: 0.329731 data_time: 0.051583 memory: 4465 loss_kpt: 98.395988 acc_pose: 0.734391 loss: 98.395988 2022/10/12 12:44:56 - mmengine - INFO - Epoch(train) [30][400/586] lr: 5.000000e-03 eta: 9:26:10 time: 0.347738 data_time: 0.049756 memory: 4465 loss_kpt: 96.142143 acc_pose: 0.744819 loss: 96.142143 2022/10/12 12:45:14 - mmengine - INFO - Epoch(train) [30][450/586] lr: 5.000000e-03 eta: 9:26:01 time: 0.343595 data_time: 0.053231 memory: 4465 loss_kpt: 96.015704 acc_pose: 0.672611 loss: 96.015704 2022/10/12 12:45:31 - mmengine - INFO - Epoch(train) [30][500/586] lr: 5.000000e-03 eta: 9:25:54 time: 0.351912 data_time: 0.052856 memory: 4465 loss_kpt: 98.686675 acc_pose: 0.727883 loss: 98.686675 2022/10/12 12:45:48 - mmengine - INFO - Epoch(train) [30][550/586] lr: 5.000000e-03 eta: 9:25:42 time: 0.336608 data_time: 0.054405 memory: 4465 loss_kpt: 96.450580 acc_pose: 0.711063 loss: 96.450580 2022/10/12 12:46:00 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:46:00 - mmengine - INFO - Saving checkpoint at 30 epochs 2022/10/12 12:46:09 - mmengine - INFO - Epoch(val) [30][50/407] eta: 0:00:48 time: 0.136677 data_time: 0.013231 memory: 4465 2022/10/12 12:46:16 - mmengine - INFO - Epoch(val) [30][100/407] eta: 0:00:42 time: 0.137028 data_time: 0.009793 memory: 1026 2022/10/12 12:46:23 - mmengine - INFO - Epoch(val) [30][150/407] eta: 0:00:33 time: 0.131494 data_time: 0.008445 memory: 1026 2022/10/12 12:46:29 - mmengine - INFO - Epoch(val) [30][200/407] eta: 0:00:27 time: 0.134409 data_time: 0.011729 memory: 1026 2022/10/12 12:46:36 - mmengine - INFO - Epoch(val) [30][250/407] eta: 0:00:20 time: 0.133311 data_time: 0.008794 memory: 1026 2022/10/12 12:46:42 - mmengine - INFO - Epoch(val) [30][300/407] eta: 0:00:13 time: 0.129947 data_time: 0.008396 memory: 1026 2022/10/12 12:46:49 - mmengine - INFO - Epoch(val) [30][350/407] eta: 0:00:07 time: 0.132068 data_time: 0.008962 memory: 1026 2022/10/12 12:46:55 - mmengine - INFO - Epoch(val) [30][400/407] eta: 0:00:00 time: 0.125638 data_time: 0.007899 memory: 1026 2022/10/12 12:47:09 - mmengine - INFO - Evaluating CocoMetric... 2022/10/12 12:47:24 - mmengine - INFO - Epoch(val) [30][407/407] coco/AP: 0.611435 coco/AP .5: 0.846302 coco/AP .75: 0.676206 coco/AP (M): 0.583224 coco/AP (L): 0.667796 coco/AR: 0.689468 coco/AR .5: 0.894049 coco/AR .75: 0.750000 coco/AR (M): 0.644469 coco/AR (L): 0.751394 2022/10/12 12:47:24 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/liqikai/openmmlab/pt112cu113py38/mmpose/work_dirs/20221012/rsn50/best_coco/AP_epoch_20.pth is removed 2022/10/12 12:47:27 - mmengine - INFO - The best checkpoint with 0.6114 coco/AP at 30 epoch is saved to best_coco/AP_epoch_30.pth. 2022/10/12 12:47:44 - mmengine - INFO - Epoch(train) [31][50/586] lr: 5.000000e-03 eta: 9:24:15 time: 0.354169 data_time: 0.056652 memory: 4465 loss_kpt: 97.642233 acc_pose: 0.739160 loss: 97.642233 2022/10/12 12:48:01 - mmengine - INFO - Epoch(train) [31][100/586] lr: 5.000000e-03 eta: 9:24:03 time: 0.336138 data_time: 0.047115 memory: 4465 loss_kpt: 97.579970 acc_pose: 0.710072 loss: 97.579970 2022/10/12 12:48:18 - mmengine - INFO - Epoch(train) [31][150/586] lr: 5.000000e-03 eta: 9:23:51 time: 0.333667 data_time: 0.051931 memory: 4465 loss_kpt: 97.906288 acc_pose: 0.724085 loss: 97.906288 2022/10/12 12:48:35 - mmengine - INFO - Epoch(train) [31][200/586] lr: 5.000000e-03 eta: 9:23:39 time: 0.335059 data_time: 0.049003 memory: 4465 loss_kpt: 98.865820 acc_pose: 0.727846 loss: 98.865820 2022/10/12 12:48:51 - mmengine - INFO - Epoch(train) [31][250/586] lr: 5.000000e-03 eta: 9:23:28 time: 0.337141 data_time: 0.050282 memory: 4465 loss_kpt: 97.385149 acc_pose: 0.742207 loss: 97.385149 2022/10/12 12:49:08 - mmengine - INFO - Epoch(train) [31][300/586] lr: 5.000000e-03 eta: 9:23:17 time: 0.339391 data_time: 0.051029 memory: 4465 loss_kpt: 97.488388 acc_pose: 0.717104 loss: 97.488388 2022/10/12 12:49:25 - mmengine - INFO - Epoch(train) [31][350/586] lr: 5.000000e-03 eta: 9:23:03 time: 0.330415 data_time: 0.054428 memory: 4465 loss_kpt: 98.376770 acc_pose: 0.736082 loss: 98.376770 2022/10/12 12:49:41 - mmengine - INFO - Epoch(train) [31][400/586] lr: 5.000000e-03 eta: 9:22:50 time: 0.331482 data_time: 0.052361 memory: 4465 loss_kpt: 97.699628 acc_pose: 0.748938 loss: 97.699628 2022/10/12 12:49:48 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:49:58 - mmengine - INFO - Epoch(train) [31][450/586] lr: 5.000000e-03 eta: 9:22:38 time: 0.332441 data_time: 0.057140 memory: 4465 loss_kpt: 95.223287 acc_pose: 0.638804 loss: 95.223287 2022/10/12 12:50:15 - mmengine - INFO - Epoch(train) [31][500/586] lr: 5.000000e-03 eta: 9:22:25 time: 0.333170 data_time: 0.049935 memory: 4465 loss_kpt: 97.336953 acc_pose: 0.757812 loss: 97.336953 2022/10/12 12:50:32 - mmengine - INFO - Epoch(train) [31][550/586] lr: 5.000000e-03 eta: 9:22:14 time: 0.339227 data_time: 0.054535 memory: 4465 loss_kpt: 97.769108 acc_pose: 0.780516 loss: 97.769108 2022/10/12 12:50:44 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:51:02 - mmengine - INFO - Epoch(train) [32][50/586] lr: 5.000000e-03 eta: 9:20:50 time: 0.358159 data_time: 0.066413 memory: 4465 loss_kpt: 97.087871 acc_pose: 0.702191 loss: 97.087871 2022/10/12 12:51:19 - mmengine - INFO - Epoch(train) [32][100/586] lr: 5.000000e-03 eta: 9:20:39 time: 0.338894 data_time: 0.053130 memory: 4465 loss_kpt: 96.333484 acc_pose: 0.727882 loss: 96.333484 2022/10/12 12:51:36 - mmengine - INFO - Epoch(train) [32][150/586] lr: 5.000000e-03 eta: 9:20:29 time: 0.340953 data_time: 0.054106 memory: 4465 loss_kpt: 96.308551 acc_pose: 0.718733 loss: 96.308551 2022/10/12 12:51:53 - mmengine - INFO - Epoch(train) [32][200/586] lr: 5.000000e-03 eta: 9:20:18 time: 0.338213 data_time: 0.050910 memory: 4465 loss_kpt: 98.138496 acc_pose: 0.743440 loss: 98.138496 2022/10/12 12:52:10 - mmengine - INFO - Epoch(train) [32][250/586] lr: 5.000000e-03 eta: 9:20:11 time: 0.352068 data_time: 0.059823 memory: 4465 loss_kpt: 94.285108 acc_pose: 0.738448 loss: 94.285108 2022/10/12 12:52:28 - mmengine - INFO - Epoch(train) [32][300/586] lr: 5.000000e-03 eta: 9:20:02 time: 0.347018 data_time: 0.047252 memory: 4465 loss_kpt: 95.028720 acc_pose: 0.723701 loss: 95.028720 2022/10/12 12:52:45 - mmengine - INFO - Epoch(train) [32][350/586] lr: 5.000000e-03 eta: 9:19:52 time: 0.342940 data_time: 0.047966 memory: 4465 loss_kpt: 95.808557 acc_pose: 0.697290 loss: 95.808557 2022/10/12 12:53:02 - mmengine - INFO - Epoch(train) [32][400/586] lr: 5.000000e-03 eta: 9:19:42 time: 0.343993 data_time: 0.048856 memory: 4465 loss_kpt: 95.242372 acc_pose: 0.787722 loss: 95.242372 2022/10/12 12:53:19 - mmengine - INFO - Epoch(train) [32][450/586] lr: 5.000000e-03 eta: 9:19:32 time: 0.341550 data_time: 0.048562 memory: 4465 loss_kpt: 97.450517 acc_pose: 0.690401 loss: 97.450517 2022/10/12 12:53:36 - mmengine - INFO - Epoch(train) [32][500/586] lr: 5.000000e-03 eta: 9:19:20 time: 0.335456 data_time: 0.051584 memory: 4465 loss_kpt: 96.239345 acc_pose: 0.703147 loss: 96.239345 2022/10/12 12:53:53 - mmengine - INFO - Epoch(train) [32][550/586] lr: 5.000000e-03 eta: 9:19:08 time: 0.338295 data_time: 0.051183 memory: 4465 loss_kpt: 96.006331 acc_pose: 0.688837 loss: 96.006331 2022/10/12 12:54:04 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:54:22 - mmengine - INFO - Epoch(train) [33][50/586] lr: 5.000000e-03 eta: 9:17:44 time: 0.347644 data_time: 0.061044 memory: 4465 loss_kpt: 97.255315 acc_pose: 0.840502 loss: 97.255315 2022/10/12 12:54:39 - mmengine - INFO - Epoch(train) [33][100/586] lr: 5.000000e-03 eta: 9:17:31 time: 0.332947 data_time: 0.055151 memory: 4465 loss_kpt: 96.194228 acc_pose: 0.791486 loss: 96.194228 2022/10/12 12:54:55 - mmengine - INFO - Epoch(train) [33][150/586] lr: 5.000000e-03 eta: 9:17:19 time: 0.337780 data_time: 0.055195 memory: 4465 loss_kpt: 97.302584 acc_pose: 0.740539 loss: 97.302584 2022/10/12 12:55:12 - mmengine - INFO - Epoch(train) [33][200/586] lr: 5.000000e-03 eta: 9:17:07 time: 0.333628 data_time: 0.048337 memory: 4465 loss_kpt: 98.497491 acc_pose: 0.600555 loss: 98.497491 2022/10/12 12:55:29 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:55:29 - mmengine - INFO - Epoch(train) [33][250/586] lr: 5.000000e-03 eta: 9:16:57 time: 0.343757 data_time: 0.051737 memory: 4465 loss_kpt: 96.546301 acc_pose: 0.777454 loss: 96.546301 2022/10/12 12:55:46 - mmengine - INFO - Epoch(train) [33][300/586] lr: 5.000000e-03 eta: 9:16:47 time: 0.341919 data_time: 0.051848 memory: 4465 loss_kpt: 96.786017 acc_pose: 0.686931 loss: 96.786017 2022/10/12 12:56:04 - mmengine - INFO - Epoch(train) [33][350/586] lr: 5.000000e-03 eta: 9:16:38 time: 0.347192 data_time: 0.051051 memory: 4465 loss_kpt: 96.307380 acc_pose: 0.718467 loss: 96.307380 2022/10/12 12:56:21 - mmengine - INFO - Epoch(train) [33][400/586] lr: 5.000000e-03 eta: 9:16:26 time: 0.336256 data_time: 0.049568 memory: 4465 loss_kpt: 97.004907 acc_pose: 0.775544 loss: 97.004907 2022/10/12 12:56:37 - mmengine - INFO - Epoch(train) [33][450/586] lr: 5.000000e-03 eta: 9:16:14 time: 0.336909 data_time: 0.048332 memory: 4465 loss_kpt: 94.938344 acc_pose: 0.801778 loss: 94.938344 2022/10/12 12:56:54 - mmengine - INFO - Epoch(train) [33][500/586] lr: 5.000000e-03 eta: 9:16:01 time: 0.334092 data_time: 0.050709 memory: 4465 loss_kpt: 97.136382 acc_pose: 0.754235 loss: 97.136382 2022/10/12 12:57:11 - mmengine - INFO - Epoch(train) [33][550/586] lr: 5.000000e-03 eta: 9:15:48 time: 0.331638 data_time: 0.051492 memory: 4465 loss_kpt: 96.563966 acc_pose: 0.742609 loss: 96.563966 2022/10/12 12:57:23 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 12:57:40 - mmengine - INFO - Epoch(train) [34][50/586] lr: 5.000000e-03 eta: 9:14:27 time: 0.353006 data_time: 0.063182 memory: 4465 loss_kpt: 96.143439 acc_pose: 0.759580 loss: 96.143439 2022/10/12 12:57:57 - mmengine - INFO - Epoch(train) [34][100/586] lr: 5.000000e-03 eta: 9:14:16 time: 0.340359 data_time: 0.049765 memory: 4465 loss_kpt: 96.327079 acc_pose: 0.791521 loss: 96.327079 2022/10/12 12:58:15 - mmengine - INFO - Epoch(train) [34][150/586] lr: 5.000000e-03 eta: 9:14:08 time: 0.349577 data_time: 0.053492 memory: 4465 loss_kpt: 96.611560 acc_pose: 0.706101 loss: 96.611560 2022/10/12 12:58:32 - mmengine - INFO - Epoch(train) [34][200/586] lr: 5.000000e-03 eta: 9:13:58 time: 0.346414 data_time: 0.051922 memory: 4465 loss_kpt: 97.833370 acc_pose: 0.726728 loss: 97.833370 2022/10/12 12:58:50 - mmengine - INFO - Epoch(train) [34][250/586] lr: 5.000000e-03 eta: 9:13:50 time: 0.350148 data_time: 0.046207 memory: 4465 loss_kpt: 95.752241 acc_pose: 0.658591 loss: 95.752241 2022/10/12 12:59:07 - mmengine - INFO - Epoch(train) [34][300/586] lr: 5.000000e-03 eta: 9:13:38 time: 0.336173 data_time: 0.050507 memory: 4465 loss_kpt: 96.742651 acc_pose: 0.632371 loss: 96.742651 2022/10/12 12:59:23 - mmengine - INFO - Epoch(train) [34][350/586] lr: 5.000000e-03 eta: 9:13:24 time: 0.329606 data_time: 0.050432 memory: 4465 loss_kpt: 96.682855 acc_pose: 0.778286 loss: 96.682855 2022/10/12 12:59:40 - mmengine - INFO - Epoch(train) [34][400/586] lr: 5.000000e-03 eta: 9:13:12 time: 0.337444 data_time: 0.052580 memory: 4465 loss_kpt: 97.788922 acc_pose: 0.783453 loss: 97.788922 2022/10/12 12:59:56 - mmengine - INFO - Epoch(train) [34][450/586] lr: 5.000000e-03 eta: 9:12:56 time: 0.320295 data_time: 0.048528 memory: 4465 loss_kpt: 95.728741 acc_pose: 0.737779 loss: 95.728741 2022/10/12 13:00:13 - mmengine - INFO - Epoch(train) [34][500/586] lr: 5.000000e-03 eta: 9:12:43 time: 0.332190 data_time: 0.050917 memory: 4465 loss_kpt: 96.452551 acc_pose: 0.679028 loss: 96.452551 2022/10/12 13:00:29 - mmengine - INFO - Epoch(train) [34][550/586] lr: 5.000000e-03 eta: 9:12:30 time: 0.335422 data_time: 0.052283 memory: 4465 loss_kpt: 96.219888 acc_pose: 0.735330 loss: 96.219888 2022/10/12 13:00:41 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:01:01 - mmengine - INFO - Epoch(train) [35][50/586] lr: 5.000000e-03 eta: 9:11:19 time: 0.385935 data_time: 0.069043 memory: 4465 loss_kpt: 97.276663 acc_pose: 0.736607 loss: 97.276663 2022/10/12 13:01:10 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:01:19 - mmengine - INFO - Epoch(train) [35][100/586] lr: 5.000000e-03 eta: 9:11:16 time: 0.370627 data_time: 0.050552 memory: 4465 loss_kpt: 97.229479 acc_pose: 0.722512 loss: 97.229479 2022/10/12 13:01:37 - mmengine - INFO - Epoch(train) [35][150/586] lr: 5.000000e-03 eta: 9:11:08 time: 0.351122 data_time: 0.052379 memory: 4465 loss_kpt: 95.937145 acc_pose: 0.786747 loss: 95.937145 2022/10/12 13:01:54 - mmengine - INFO - Epoch(train) [35][200/586] lr: 5.000000e-03 eta: 9:11:01 time: 0.355792 data_time: 0.052376 memory: 4465 loss_kpt: 97.453311 acc_pose: 0.716273 loss: 97.453311 2022/10/12 13:02:11 - mmengine - INFO - Epoch(train) [35][250/586] lr: 5.000000e-03 eta: 9:10:49 time: 0.339257 data_time: 0.053108 memory: 4465 loss_kpt: 94.793700 acc_pose: 0.687328 loss: 94.793700 2022/10/12 13:02:28 - mmengine - INFO - Epoch(train) [35][300/586] lr: 5.000000e-03 eta: 9:10:36 time: 0.333600 data_time: 0.047873 memory: 4465 loss_kpt: 96.887509 acc_pose: 0.740998 loss: 96.887509 2022/10/12 13:02:45 - mmengine - INFO - Epoch(train) [35][350/586] lr: 5.000000e-03 eta: 9:10:25 time: 0.338671 data_time: 0.051656 memory: 4465 loss_kpt: 97.191074 acc_pose: 0.654585 loss: 97.191074 2022/10/12 13:03:01 - mmengine - INFO - Epoch(train) [35][400/586] lr: 5.000000e-03 eta: 9:10:10 time: 0.327740 data_time: 0.053002 memory: 4465 loss_kpt: 96.204539 acc_pose: 0.724069 loss: 96.204539 2022/10/12 13:03:18 - mmengine - INFO - Epoch(train) [35][450/586] lr: 5.000000e-03 eta: 9:09:56 time: 0.329795 data_time: 0.048666 memory: 4465 loss_kpt: 96.802957 acc_pose: 0.749570 loss: 96.802957 2022/10/12 13:03:35 - mmengine - INFO - Epoch(train) [35][500/586] lr: 5.000000e-03 eta: 9:09:43 time: 0.330994 data_time: 0.050998 memory: 4465 loss_kpt: 96.206068 acc_pose: 0.703803 loss: 96.206068 2022/10/12 13:03:51 - mmengine - INFO - Epoch(train) [35][550/586] lr: 5.000000e-03 eta: 9:09:29 time: 0.329024 data_time: 0.048455 memory: 4465 loss_kpt: 95.845101 acc_pose: 0.785315 loss: 95.845101 2022/10/12 13:04:02 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:04:20 - mmengine - INFO - Epoch(train) [36][50/586] lr: 5.000000e-03 eta: 9:08:13 time: 0.359442 data_time: 0.062029 memory: 4465 loss_kpt: 95.696239 acc_pose: 0.735389 loss: 95.696239 2022/10/12 13:04:38 - mmengine - INFO - Epoch(train) [36][100/586] lr: 5.000000e-03 eta: 9:08:05 time: 0.355909 data_time: 0.050359 memory: 4465 loss_kpt: 96.360567 acc_pose: 0.748020 loss: 96.360567 2022/10/12 13:04:55 - mmengine - INFO - Epoch(train) [36][150/586] lr: 5.000000e-03 eta: 9:07:56 time: 0.346368 data_time: 0.054579 memory: 4465 loss_kpt: 95.243292 acc_pose: 0.817594 loss: 95.243292 2022/10/12 13:05:13 - mmengine - INFO - Epoch(train) [36][200/586] lr: 5.000000e-03 eta: 9:07:45 time: 0.342881 data_time: 0.052561 memory: 4465 loss_kpt: 96.195808 acc_pose: 0.774158 loss: 96.195808 2022/10/12 13:05:30 - mmengine - INFO - Epoch(train) [36][250/586] lr: 5.000000e-03 eta: 9:07:35 time: 0.344239 data_time: 0.053118 memory: 4465 loss_kpt: 95.668146 acc_pose: 0.767806 loss: 95.668146 2022/10/12 13:05:47 - mmengine - INFO - Epoch(train) [36][300/586] lr: 5.000000e-03 eta: 9:07:25 time: 0.346155 data_time: 0.051455 memory: 4465 loss_kpt: 95.989051 acc_pose: 0.673828 loss: 95.989051 2022/10/12 13:06:04 - mmengine - INFO - Epoch(train) [36][350/586] lr: 5.000000e-03 eta: 9:07:15 time: 0.345480 data_time: 0.052286 memory: 4465 loss_kpt: 95.149561 acc_pose: 0.735335 loss: 95.149561 2022/10/12 13:06:21 - mmengine - INFO - Epoch(train) [36][400/586] lr: 5.000000e-03 eta: 9:07:02 time: 0.334349 data_time: 0.047150 memory: 4465 loss_kpt: 95.758326 acc_pose: 0.694696 loss: 95.758326 2022/10/12 13:06:38 - mmengine - INFO - Epoch(train) [36][450/586] lr: 5.000000e-03 eta: 9:06:49 time: 0.335696 data_time: 0.052942 memory: 4465 loss_kpt: 96.001964 acc_pose: 0.763343 loss: 96.001964 2022/10/12 13:06:51 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:06:55 - mmengine - INFO - Epoch(train) [36][500/586] lr: 5.000000e-03 eta: 9:06:36 time: 0.334972 data_time: 0.051176 memory: 4465 loss_kpt: 96.607030 acc_pose: 0.684622 loss: 96.607030 2022/10/12 13:07:12 - mmengine - INFO - Epoch(train) [36][550/586] lr: 5.000000e-03 eta: 9:06:24 time: 0.337921 data_time: 0.052385 memory: 4465 loss_kpt: 94.501157 acc_pose: 0.742803 loss: 94.501157 2022/10/12 13:07:23 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:07:41 - mmengine - INFO - Epoch(train) [37][50/586] lr: 5.000000e-03 eta: 9:05:07 time: 0.346098 data_time: 0.058336 memory: 4465 loss_kpt: 95.105360 acc_pose: 0.756597 loss: 95.105360 2022/10/12 13:07:57 - mmengine - INFO - Epoch(train) [37][100/586] lr: 5.000000e-03 eta: 9:04:52 time: 0.325782 data_time: 0.052164 memory: 4465 loss_kpt: 96.422576 acc_pose: 0.758306 loss: 96.422576 2022/10/12 13:08:14 - mmengine - INFO - Epoch(train) [37][150/586] lr: 5.000000e-03 eta: 9:04:42 time: 0.347817 data_time: 0.053300 memory: 4465 loss_kpt: 95.058553 acc_pose: 0.761333 loss: 95.058553 2022/10/12 13:08:31 - mmengine - INFO - Epoch(train) [37][200/586] lr: 5.000000e-03 eta: 9:04:29 time: 0.331473 data_time: 0.052336 memory: 4465 loss_kpt: 95.925310 acc_pose: 0.743210 loss: 95.925310 2022/10/12 13:08:47 - mmengine - INFO - Epoch(train) [37][250/586] lr: 5.000000e-03 eta: 9:04:15 time: 0.328454 data_time: 0.052791 memory: 4465 loss_kpt: 94.932911 acc_pose: 0.743457 loss: 94.932911 2022/10/12 13:09:04 - mmengine - INFO - Epoch(train) [37][300/586] lr: 5.000000e-03 eta: 9:04:02 time: 0.334509 data_time: 0.047565 memory: 4465 loss_kpt: 95.749470 acc_pose: 0.772878 loss: 95.749470 2022/10/12 13:09:21 - mmengine - INFO - Epoch(train) [37][350/586] lr: 5.000000e-03 eta: 9:03:47 time: 0.327537 data_time: 0.054318 memory: 4465 loss_kpt: 95.768082 acc_pose: 0.762404 loss: 95.768082 2022/10/12 13:09:37 - mmengine - INFO - Epoch(train) [37][400/586] lr: 5.000000e-03 eta: 9:03:33 time: 0.328121 data_time: 0.048069 memory: 4465 loss_kpt: 96.374692 acc_pose: 0.752805 loss: 96.374692 2022/10/12 13:09:53 - mmengine - INFO - Epoch(train) [37][450/586] lr: 5.000000e-03 eta: 9:03:19 time: 0.329373 data_time: 0.053076 memory: 4465 loss_kpt: 97.659224 acc_pose: 0.780304 loss: 97.659224 2022/10/12 13:10:10 - mmengine - INFO - Epoch(train) [37][500/586] lr: 5.000000e-03 eta: 9:03:03 time: 0.323131 data_time: 0.051774 memory: 4465 loss_kpt: 94.832355 acc_pose: 0.774093 loss: 94.832355 2022/10/12 13:10:26 - mmengine - INFO - Epoch(train) [37][550/586] lr: 5.000000e-03 eta: 9:02:47 time: 0.321384 data_time: 0.049707 memory: 4465 loss_kpt: 96.819398 acc_pose: 0.733736 loss: 96.819398 2022/10/12 13:10:38 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:10:55 - mmengine - INFO - Epoch(train) [38][50/586] lr: 5.000000e-03 eta: 9:01:34 time: 0.357068 data_time: 0.060972 memory: 4465 loss_kpt: 96.017133 acc_pose: 0.710407 loss: 96.017133 2022/10/12 13:11:12 - mmengine - INFO - Epoch(train) [38][100/586] lr: 5.000000e-03 eta: 9:01:22 time: 0.339817 data_time: 0.055236 memory: 4465 loss_kpt: 95.393466 acc_pose: 0.742635 loss: 95.393466 2022/10/12 13:11:30 - mmengine - INFO - Epoch(train) [38][150/586] lr: 5.000000e-03 eta: 9:01:13 time: 0.349803 data_time: 0.051721 memory: 4465 loss_kpt: 97.368021 acc_pose: 0.769547 loss: 97.368021 2022/10/12 13:11:47 - mmengine - INFO - Epoch(train) [38][200/586] lr: 5.000000e-03 eta: 9:01:02 time: 0.343754 data_time: 0.049855 memory: 4465 loss_kpt: 93.934273 acc_pose: 0.803433 loss: 93.934273 2022/10/12 13:12:04 - mmengine - INFO - Epoch(train) [38][250/586] lr: 5.000000e-03 eta: 9:00:52 time: 0.344850 data_time: 0.052682 memory: 4465 loss_kpt: 97.655540 acc_pose: 0.787522 loss: 97.655540 2022/10/12 13:12:22 - mmengine - INFO - Epoch(train) [38][300/586] lr: 5.000000e-03 eta: 9:00:41 time: 0.343776 data_time: 0.053199 memory: 4465 loss_kpt: 94.917829 acc_pose: 0.754591 loss: 94.917829 2022/10/12 13:12:28 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:12:38 - mmengine - INFO - Epoch(train) [38][350/586] lr: 5.000000e-03 eta: 9:00:27 time: 0.329600 data_time: 0.048492 memory: 4465 loss_kpt: 96.415307 acc_pose: 0.804812 loss: 96.415307 2022/10/12 13:12:54 - mmengine - INFO - Epoch(train) [38][400/586] lr: 5.000000e-03 eta: 9:00:12 time: 0.323995 data_time: 0.051353 memory: 4465 loss_kpt: 97.135905 acc_pose: 0.755115 loss: 97.135905 2022/10/12 13:13:11 - mmengine - INFO - Epoch(train) [38][450/586] lr: 5.000000e-03 eta: 8:59:57 time: 0.326674 data_time: 0.055026 memory: 4465 loss_kpt: 95.126346 acc_pose: 0.723900 loss: 95.126346 2022/10/12 13:13:27 - mmengine - INFO - Epoch(train) [38][500/586] lr: 5.000000e-03 eta: 8:59:41 time: 0.322784 data_time: 0.047615 memory: 4465 loss_kpt: 96.413989 acc_pose: 0.753884 loss: 96.413989 2022/10/12 13:13:43 - mmengine - INFO - Epoch(train) [38][550/586] lr: 5.000000e-03 eta: 8:59:28 time: 0.333436 data_time: 0.052117 memory: 4465 loss_kpt: 94.546662 acc_pose: 0.789951 loss: 94.546662 2022/10/12 13:13:55 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:14:12 - mmengine - INFO - Epoch(train) [39][50/586] lr: 5.000000e-03 eta: 8:58:15 time: 0.349691 data_time: 0.062413 memory: 4465 loss_kpt: 95.621564 acc_pose: 0.792062 loss: 95.621564 2022/10/12 13:14:29 - mmengine - INFO - Epoch(train) [39][100/586] lr: 5.000000e-03 eta: 8:58:03 time: 0.341423 data_time: 0.054207 memory: 4465 loss_kpt: 94.907995 acc_pose: 0.771072 loss: 94.907995 2022/10/12 13:14:46 - mmengine - INFO - Epoch(train) [39][150/586] lr: 5.000000e-03 eta: 8:57:52 time: 0.341989 data_time: 0.052491 memory: 4465 loss_kpt: 97.553236 acc_pose: 0.696594 loss: 97.553236 2022/10/12 13:15:03 - mmengine - INFO - Epoch(train) [39][200/586] lr: 5.000000e-03 eta: 8:57:38 time: 0.328394 data_time: 0.048054 memory: 4465 loss_kpt: 95.830151 acc_pose: 0.706037 loss: 95.830151 2022/10/12 13:15:20 - mmengine - INFO - Epoch(train) [39][250/586] lr: 5.000000e-03 eta: 8:57:26 time: 0.338962 data_time: 0.052754 memory: 4465 loss_kpt: 95.047510 acc_pose: 0.709980 loss: 95.047510 2022/10/12 13:15:36 - mmengine - INFO - Epoch(train) [39][300/586] lr: 5.000000e-03 eta: 8:57:12 time: 0.329638 data_time: 0.050098 memory: 4465 loss_kpt: 95.424071 acc_pose: 0.731922 loss: 95.424071 2022/10/12 13:15:53 - mmengine - INFO - Epoch(train) [39][350/586] lr: 5.000000e-03 eta: 8:56:59 time: 0.336010 data_time: 0.050545 memory: 4465 loss_kpt: 96.420770 acc_pose: 0.777192 loss: 96.420770 2022/10/12 13:16:10 - mmengine - INFO - Epoch(train) [39][400/586] lr: 5.000000e-03 eta: 8:56:48 time: 0.341188 data_time: 0.053048 memory: 4465 loss_kpt: 95.227591 acc_pose: 0.711922 loss: 95.227591 2022/10/12 13:16:27 - mmengine - INFO - Epoch(train) [39][450/586] lr: 5.000000e-03 eta: 8:56:35 time: 0.335478 data_time: 0.053670 memory: 4465 loss_kpt: 95.127825 acc_pose: 0.708609 loss: 95.127825 2022/10/12 13:16:44 - mmengine - INFO - Epoch(train) [39][500/586] lr: 5.000000e-03 eta: 8:56:25 time: 0.348636 data_time: 0.051899 memory: 4465 loss_kpt: 94.474918 acc_pose: 0.817007 loss: 94.474918 2022/10/12 13:17:01 - mmengine - INFO - Epoch(train) [39][550/586] lr: 5.000000e-03 eta: 8:56:14 time: 0.342592 data_time: 0.055545 memory: 4465 loss_kpt: 96.484862 acc_pose: 0.786722 loss: 96.484862 2022/10/12 13:17:14 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:17:31 - mmengine - INFO - Epoch(train) [40][50/586] lr: 5.000000e-03 eta: 8:55:01 time: 0.344667 data_time: 0.062579 memory: 4465 loss_kpt: 95.364278 acc_pose: 0.751123 loss: 95.364278 2022/10/12 13:17:48 - mmengine - INFO - Epoch(train) [40][100/586] lr: 5.000000e-03 eta: 8:54:50 time: 0.343933 data_time: 0.052343 memory: 4465 loss_kpt: 97.800118 acc_pose: 0.738043 loss: 97.800118 2022/10/12 13:18:04 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:18:06 - mmengine - INFO - Epoch(train) [40][150/586] lr: 5.000000e-03 eta: 8:54:41 time: 0.354403 data_time: 0.053571 memory: 4465 loss_kpt: 94.687746 acc_pose: 0.689759 loss: 94.687746 2022/10/12 13:18:23 - mmengine - INFO - Epoch(train) [40][200/586] lr: 5.000000e-03 eta: 8:54:31 time: 0.349576 data_time: 0.052317 memory: 4465 loss_kpt: 95.846536 acc_pose: 0.723257 loss: 95.846536 2022/10/12 13:18:41 - mmengine - INFO - Epoch(train) [40][250/586] lr: 5.000000e-03 eta: 8:54:22 time: 0.353722 data_time: 0.057181 memory: 4465 loss_kpt: 94.847129 acc_pose: 0.742928 loss: 94.847129 2022/10/12 13:18:58 - mmengine - INFO - Epoch(train) [40][300/586] lr: 5.000000e-03 eta: 8:54:12 time: 0.348069 data_time: 0.053491 memory: 4465 loss_kpt: 94.557224 acc_pose: 0.849862 loss: 94.557224 2022/10/12 13:19:15 - mmengine - INFO - Epoch(train) [40][350/586] lr: 5.000000e-03 eta: 8:54:00 time: 0.339375 data_time: 0.052733 memory: 4465 loss_kpt: 96.197143 acc_pose: 0.792106 loss: 96.197143 2022/10/12 13:19:32 - mmengine - INFO - Epoch(train) [40][400/586] lr: 5.000000e-03 eta: 8:53:48 time: 0.339924 data_time: 0.049556 memory: 4465 loss_kpt: 94.089665 acc_pose: 0.701100 loss: 94.089665 2022/10/12 13:19:49 - mmengine - INFO - Epoch(train) [40][450/586] lr: 5.000000e-03 eta: 8:53:36 time: 0.338403 data_time: 0.053849 memory: 4465 loss_kpt: 94.852377 acc_pose: 0.744010 loss: 94.852377 2022/10/12 13:20:05 - mmengine - INFO - Epoch(train) [40][500/586] lr: 5.000000e-03 eta: 8:53:19 time: 0.319015 data_time: 0.048656 memory: 4465 loss_kpt: 94.435649 acc_pose: 0.702154 loss: 94.435649 2022/10/12 13:20:22 - mmengine - INFO - Epoch(train) [40][550/586] lr: 5.000000e-03 eta: 8:53:06 time: 0.333087 data_time: 0.051713 memory: 4465 loss_kpt: 96.370043 acc_pose: 0.809355 loss: 96.370043 2022/10/12 13:20:34 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:20:34 - mmengine - INFO - Saving checkpoint at 40 epochs 2022/10/12 13:20:43 - mmengine - INFO - Epoch(val) [40][50/407] eta: 0:00:49 time: 0.137933 data_time: 0.013590 memory: 4465 2022/10/12 13:20:50 - mmengine - INFO - Epoch(val) [40][100/407] eta: 0:00:40 time: 0.132966 data_time: 0.008430 memory: 1026 2022/10/12 13:20:57 - mmengine - INFO - Epoch(val) [40][150/407] eta: 0:00:33 time: 0.132029 data_time: 0.008975 memory: 1026 2022/10/12 13:21:03 - mmengine - INFO - Epoch(val) [40][200/407] eta: 0:00:27 time: 0.133888 data_time: 0.008734 memory: 1026 2022/10/12 13:21:10 - mmengine - INFO - Epoch(val) [40][250/407] eta: 0:00:20 time: 0.132435 data_time: 0.008623 memory: 1026 2022/10/12 13:21:17 - mmengine - INFO - Epoch(val) [40][300/407] eta: 0:00:13 time: 0.130439 data_time: 0.008113 memory: 1026 2022/10/12 13:21:23 - mmengine - INFO - Epoch(val) [40][350/407] eta: 0:00:07 time: 0.130099 data_time: 0.008770 memory: 1026 2022/10/12 13:21:30 - mmengine - INFO - Epoch(val) [40][400/407] eta: 0:00:00 time: 0.130364 data_time: 0.008392 memory: 1026 2022/10/12 13:21:43 - mmengine - INFO - Evaluating CocoMetric... 2022/10/12 13:22:00 - mmengine - INFO - Epoch(val) [40][407/407] coco/AP: 0.635164 coco/AP .5: 0.863267 coco/AP .75: 0.704568 coco/AP (M): 0.603701 coco/AP (L): 0.693323 coco/AR: 0.708879 coco/AR .5: 0.905384 coco/AR .75: 0.770309 coco/AR (M): 0.662032 coco/AR (L): 0.773541 2022/10/12 13:22:00 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/liqikai/openmmlab/pt112cu113py38/mmpose/work_dirs/20221012/rsn50/best_coco/AP_epoch_30.pth is removed 2022/10/12 13:22:02 - mmengine - INFO - The best checkpoint with 0.6352 coco/AP at 40 epoch is saved to best_coco/AP_epoch_40.pth. 2022/10/12 13:22:20 - mmengine - INFO - Epoch(train) [41][50/586] lr: 5.000000e-03 eta: 8:51:58 time: 0.360767 data_time: 0.062438 memory: 4465 loss_kpt: 94.666907 acc_pose: 0.783637 loss: 94.666907 2022/10/12 13:22:37 - mmengine - INFO - Epoch(train) [41][100/586] lr: 5.000000e-03 eta: 8:51:47 time: 0.344138 data_time: 0.056620 memory: 4465 loss_kpt: 93.453868 acc_pose: 0.729466 loss: 93.453868 2022/10/12 13:22:54 - mmengine - INFO - Epoch(train) [41][150/586] lr: 5.000000e-03 eta: 8:51:37 time: 0.349427 data_time: 0.060055 memory: 4465 loss_kpt: 94.264013 acc_pose: 0.785356 loss: 94.264013 2022/10/12 13:23:12 - mmengine - INFO - Epoch(train) [41][200/586] lr: 5.000000e-03 eta: 8:51:28 time: 0.354437 data_time: 0.050486 memory: 4465 loss_kpt: 94.889077 acc_pose: 0.673196 loss: 94.889077 2022/10/12 13:23:29 - mmengine - INFO - Epoch(train) [41][250/586] lr: 5.000000e-03 eta: 8:51:15 time: 0.337010 data_time: 0.054830 memory: 4465 loss_kpt: 94.919996 acc_pose: 0.808746 loss: 94.919996 2022/10/12 13:23:46 - mmengine - INFO - Epoch(train) [41][300/586] lr: 5.000000e-03 eta: 8:51:04 time: 0.343423 data_time: 0.052189 memory: 4465 loss_kpt: 94.276610 acc_pose: 0.744329 loss: 94.276610 2022/10/12 13:24:03 - mmengine - INFO - Epoch(train) [41][350/586] lr: 5.000000e-03 eta: 8:50:53 time: 0.347105 data_time: 0.054708 memory: 4465 loss_kpt: 94.245301 acc_pose: 0.809353 loss: 94.245301 2022/10/12 13:24:20 - mmengine - INFO - Epoch(train) [41][400/586] lr: 5.000000e-03 eta: 8:50:40 time: 0.331023 data_time: 0.051360 memory: 4465 loss_kpt: 95.352357 acc_pose: 0.731159 loss: 95.352357 2022/10/12 13:24:37 - mmengine - INFO - Epoch(train) [41][450/586] lr: 5.000000e-03 eta: 8:50:27 time: 0.338892 data_time: 0.050600 memory: 4465 loss_kpt: 94.840105 acc_pose: 0.716931 loss: 94.840105 2022/10/12 13:24:53 - mmengine - INFO - Epoch(train) [41][500/586] lr: 5.000000e-03 eta: 8:50:12 time: 0.326355 data_time: 0.049241 memory: 4465 loss_kpt: 95.037656 acc_pose: 0.703919 loss: 95.037656 2022/10/12 13:25:10 - mmengine - INFO - Epoch(train) [41][550/586] lr: 5.000000e-03 eta: 8:50:00 time: 0.338082 data_time: 0.056476 memory: 4465 loss_kpt: 95.294940 acc_pose: 0.696387 loss: 95.294940 2022/10/12 13:25:13 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:25:22 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:25:40 - mmengine - INFO - Epoch(train) [42][50/586] lr: 5.000000e-03 eta: 8:48:50 time: 0.348839 data_time: 0.064432 memory: 4465 loss_kpt: 95.104603 acc_pose: 0.792594 loss: 95.104603 2022/10/12 13:25:56 - mmengine - INFO - Epoch(train) [42][100/586] lr: 5.000000e-03 eta: 8:48:36 time: 0.330975 data_time: 0.052277 memory: 4465 loss_kpt: 94.903513 acc_pose: 0.658224 loss: 94.903513 2022/10/12 13:26:13 - mmengine - INFO - Epoch(train) [42][150/586] lr: 5.000000e-03 eta: 8:48:23 time: 0.333346 data_time: 0.055587 memory: 4465 loss_kpt: 96.730461 acc_pose: 0.703692 loss: 96.730461 2022/10/12 13:26:30 - mmengine - INFO - Epoch(train) [42][200/586] lr: 5.000000e-03 eta: 8:48:10 time: 0.336144 data_time: 0.048700 memory: 4465 loss_kpt: 94.993790 acc_pose: 0.792060 loss: 94.993790 2022/10/12 13:26:46 - mmengine - INFO - Epoch(train) [42][250/586] lr: 5.000000e-03 eta: 8:47:55 time: 0.323588 data_time: 0.050355 memory: 4465 loss_kpt: 94.285829 acc_pose: 0.707853 loss: 94.285829 2022/10/12 13:27:03 - mmengine - INFO - Epoch(train) [42][300/586] lr: 5.000000e-03 eta: 8:47:43 time: 0.340518 data_time: 0.050803 memory: 4465 loss_kpt: 93.697327 acc_pose: 0.725680 loss: 93.697327 2022/10/12 13:27:20 - mmengine - INFO - Epoch(train) [42][350/586] lr: 5.000000e-03 eta: 8:47:29 time: 0.333065 data_time: 0.051517 memory: 4465 loss_kpt: 94.693518 acc_pose: 0.707856 loss: 94.693518 2022/10/12 13:27:36 - mmengine - INFO - Epoch(train) [42][400/586] lr: 5.000000e-03 eta: 8:47:15 time: 0.328779 data_time: 0.050241 memory: 4465 loss_kpt: 95.106614 acc_pose: 0.799667 loss: 95.106614 2022/10/12 13:27:53 - mmengine - INFO - Epoch(train) [42][450/586] lr: 5.000000e-03 eta: 8:47:01 time: 0.334102 data_time: 0.051630 memory: 4465 loss_kpt: 94.674049 acc_pose: 0.801735 loss: 94.674049 2022/10/12 13:28:09 - mmengine - INFO - Epoch(train) [42][500/586] lr: 5.000000e-03 eta: 8:46:48 time: 0.331825 data_time: 0.047490 memory: 4465 loss_kpt: 94.623840 acc_pose: 0.716809 loss: 94.623840 2022/10/12 13:28:26 - mmengine - INFO - Epoch(train) [42][550/586] lr: 5.000000e-03 eta: 8:46:33 time: 0.329569 data_time: 0.050688 memory: 4465 loss_kpt: 95.599061 acc_pose: 0.771786 loss: 95.599061 2022/10/12 13:28:38 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:28:55 - mmengine - INFO - Epoch(train) [43][50/586] lr: 5.000000e-03 eta: 8:45:25 time: 0.347623 data_time: 0.060788 memory: 4465 loss_kpt: 96.356468 acc_pose: 0.736608 loss: 96.356468 2022/10/12 13:29:12 - mmengine - INFO - Epoch(train) [43][100/586] lr: 5.000000e-03 eta: 8:45:12 time: 0.336648 data_time: 0.051233 memory: 4465 loss_kpt: 93.667963 acc_pose: 0.767653 loss: 93.667963 2022/10/12 13:29:29 - mmengine - INFO - Epoch(train) [43][150/586] lr: 5.000000e-03 eta: 8:45:02 time: 0.349283 data_time: 0.054909 memory: 4465 loss_kpt: 92.091874 acc_pose: 0.719946 loss: 92.091874 2022/10/12 13:29:46 - mmengine - INFO - Epoch(train) [43][200/586] lr: 5.000000e-03 eta: 8:44:50 time: 0.340170 data_time: 0.049613 memory: 4465 loss_kpt: 96.231986 acc_pose: 0.754058 loss: 96.231986 2022/10/12 13:30:03 - mmengine - INFO - Epoch(train) [43][250/586] lr: 5.000000e-03 eta: 8:44:38 time: 0.341744 data_time: 0.054230 memory: 4465 loss_kpt: 94.436697 acc_pose: 0.789854 loss: 94.436697 2022/10/12 13:30:20 - mmengine - INFO - Epoch(train) [43][300/586] lr: 5.000000e-03 eta: 8:44:25 time: 0.337474 data_time: 0.053104 memory: 4465 loss_kpt: 95.291092 acc_pose: 0.792612 loss: 95.291092 2022/10/12 13:30:37 - mmengine - INFO - Epoch(train) [43][350/586] lr: 5.000000e-03 eta: 8:44:12 time: 0.333843 data_time: 0.050023 memory: 4465 loss_kpt: 94.678458 acc_pose: 0.742071 loss: 94.678458 2022/10/12 13:30:50 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:30:53 - mmengine - INFO - Epoch(train) [43][400/586] lr: 5.000000e-03 eta: 8:43:57 time: 0.327773 data_time: 0.050478 memory: 4465 loss_kpt: 95.301555 acc_pose: 0.754655 loss: 95.301555 2022/10/12 13:31:10 - mmengine - INFO - Epoch(train) [43][450/586] lr: 5.000000e-03 eta: 8:43:44 time: 0.334076 data_time: 0.053494 memory: 4465 loss_kpt: 95.007806 acc_pose: 0.757399 loss: 95.007806 2022/10/12 13:31:27 - mmengine - INFO - Epoch(train) [43][500/586] lr: 5.000000e-03 eta: 8:43:32 time: 0.342655 data_time: 0.054927 memory: 4465 loss_kpt: 94.148309 acc_pose: 0.695145 loss: 94.148309 2022/10/12 13:31:44 - mmengine - INFO - Epoch(train) [43][550/586] lr: 5.000000e-03 eta: 8:43:18 time: 0.329972 data_time: 0.052980 memory: 4465 loss_kpt: 94.083994 acc_pose: 0.808023 loss: 94.083994 2022/10/12 13:31:55 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:32:14 - mmengine - INFO - Epoch(train) [44][50/586] lr: 5.000000e-03 eta: 8:42:14 time: 0.365093 data_time: 0.061208 memory: 4465 loss_kpt: 95.284237 acc_pose: 0.716559 loss: 95.284237 2022/10/12 13:32:31 - mmengine - INFO - Epoch(train) [44][100/586] lr: 5.000000e-03 eta: 8:42:04 time: 0.348783 data_time: 0.051336 memory: 4465 loss_kpt: 93.708242 acc_pose: 0.712777 loss: 93.708242 2022/10/12 13:32:49 - mmengine - INFO - Epoch(train) [44][150/586] lr: 5.000000e-03 eta: 8:41:54 time: 0.353768 data_time: 0.053354 memory: 4465 loss_kpt: 94.175179 acc_pose: 0.742123 loss: 94.175179 2022/10/12 13:33:06 - mmengine - INFO - Epoch(train) [44][200/586] lr: 5.000000e-03 eta: 8:41:44 time: 0.349707 data_time: 0.051045 memory: 4465 loss_kpt: 94.430165 acc_pose: 0.751089 loss: 94.430165 2022/10/12 13:33:24 - mmengine - INFO - Epoch(train) [44][250/586] lr: 5.000000e-03 eta: 8:41:34 time: 0.354544 data_time: 0.058227 memory: 4465 loss_kpt: 93.660771 acc_pose: 0.721828 loss: 93.660771 2022/10/12 13:33:41 - mmengine - INFO - Epoch(train) [44][300/586] lr: 5.000000e-03 eta: 8:41:22 time: 0.342901 data_time: 0.049087 memory: 4465 loss_kpt: 94.553692 acc_pose: 0.791809 loss: 94.553692 2022/10/12 13:33:59 - mmengine - INFO - Epoch(train) [44][350/586] lr: 5.000000e-03 eta: 8:41:12 time: 0.348748 data_time: 0.054588 memory: 4465 loss_kpt: 94.931214 acc_pose: 0.752940 loss: 94.931214 2022/10/12 13:34:16 - mmengine - INFO - Epoch(train) [44][400/586] lr: 5.000000e-03 eta: 8:41:00 time: 0.344045 data_time: 0.055163 memory: 4465 loss_kpt: 95.038008 acc_pose: 0.765923 loss: 95.038008 2022/10/12 13:34:33 - mmengine - INFO - Epoch(train) [44][450/586] lr: 5.000000e-03 eta: 8:40:49 time: 0.344524 data_time: 0.049373 memory: 4465 loss_kpt: 93.756539 acc_pose: 0.776516 loss: 93.756539 2022/10/12 13:34:50 - mmengine - INFO - Epoch(train) [44][500/586] lr: 5.000000e-03 eta: 8:40:37 time: 0.341659 data_time: 0.050918 memory: 4465 loss_kpt: 94.534199 acc_pose: 0.665772 loss: 94.534199 2022/10/12 13:35:08 - mmengine - INFO - Epoch(train) [44][550/586] lr: 5.000000e-03 eta: 8:40:26 time: 0.352072 data_time: 0.056816 memory: 4465 loss_kpt: 95.340596 acc_pose: 0.727755 loss: 95.340596 2022/10/12 13:35:20 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:35:37 - mmengine - INFO - Epoch(train) [45][50/586] lr: 5.000000e-03 eta: 8:39:21 time: 0.350088 data_time: 0.060609 memory: 4465 loss_kpt: 95.663432 acc_pose: 0.731680 loss: 95.663432 2022/10/12 13:35:55 - mmengine - INFO - Epoch(train) [45][100/586] lr: 5.000000e-03 eta: 8:39:11 time: 0.352908 data_time: 0.049170 memory: 4465 loss_kpt: 93.715048 acc_pose: 0.756537 loss: 93.715048 2022/10/12 13:36:13 - mmengine - INFO - Epoch(train) [45][150/586] lr: 5.000000e-03 eta: 8:39:03 time: 0.361577 data_time: 0.054609 memory: 4465 loss_kpt: 95.032973 acc_pose: 0.705581 loss: 95.032973 2022/10/12 13:36:31 - mmengine - INFO - Epoch(train) [45][200/586] lr: 5.000000e-03 eta: 8:38:55 time: 0.368473 data_time: 0.051482 memory: 4465 loss_kpt: 93.160005 acc_pose: 0.751687 loss: 93.160005 2022/10/12 13:36:37 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:36:49 - mmengine - INFO - Epoch(train) [45][250/586] lr: 5.000000e-03 eta: 8:38:45 time: 0.353079 data_time: 0.055535 memory: 4465 loss_kpt: 93.528776 acc_pose: 0.770545 loss: 93.528776 2022/10/12 13:37:07 - mmengine - INFO - Epoch(train) [45][300/586] lr: 5.000000e-03 eta: 8:38:35 time: 0.351402 data_time: 0.049255 memory: 4465 loss_kpt: 93.947878 acc_pose: 0.799845 loss: 93.947878 2022/10/12 13:37:24 - mmengine - INFO - Epoch(train) [45][350/586] lr: 5.000000e-03 eta: 8:38:23 time: 0.344662 data_time: 0.046178 memory: 4465 loss_kpt: 93.812508 acc_pose: 0.815821 loss: 93.812508 2022/10/12 13:37:41 - mmengine - INFO - Epoch(train) [45][400/586] lr: 5.000000e-03 eta: 8:38:12 time: 0.343311 data_time: 0.049165 memory: 4465 loss_kpt: 95.876579 acc_pose: 0.685883 loss: 95.876579 2022/10/12 13:37:58 - mmengine - INFO - Epoch(train) [45][450/586] lr: 5.000000e-03 eta: 8:37:59 time: 0.337982 data_time: 0.048233 memory: 4465 loss_kpt: 94.531702 acc_pose: 0.764307 loss: 94.531702 2022/10/12 13:38:14 - mmengine - INFO - Epoch(train) [45][500/586] lr: 5.000000e-03 eta: 8:37:44 time: 0.329684 data_time: 0.046184 memory: 4465 loss_kpt: 93.894799 acc_pose: 0.751859 loss: 93.894799 2022/10/12 13:38:31 - mmengine - INFO - Epoch(train) [45][550/586] lr: 5.000000e-03 eta: 8:37:30 time: 0.330333 data_time: 0.050666 memory: 4465 loss_kpt: 95.146682 acc_pose: 0.769232 loss: 95.146682 2022/10/12 13:38:43 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:39:01 - mmengine - INFO - Epoch(train) [46][50/586] lr: 5.000000e-03 eta: 8:36:28 time: 0.365616 data_time: 0.063756 memory: 4465 loss_kpt: 94.331077 acc_pose: 0.754914 loss: 94.331077 2022/10/12 13:39:18 - mmengine - INFO - Epoch(train) [46][100/586] lr: 5.000000e-03 eta: 8:36:16 time: 0.341309 data_time: 0.047918 memory: 4465 loss_kpt: 93.320916 acc_pose: 0.819641 loss: 93.320916 2022/10/12 13:39:36 - mmengine - INFO - Epoch(train) [46][150/586] lr: 5.000000e-03 eta: 8:36:04 time: 0.345715 data_time: 0.059004 memory: 4465 loss_kpt: 94.801315 acc_pose: 0.778618 loss: 94.801315 2022/10/12 13:39:52 - mmengine - INFO - Epoch(train) [46][200/586] lr: 5.000000e-03 eta: 8:35:51 time: 0.333696 data_time: 0.050945 memory: 4465 loss_kpt: 95.065440 acc_pose: 0.790529 loss: 95.065440 2022/10/12 13:40:10 - mmengine - INFO - Epoch(train) [46][250/586] lr: 5.000000e-03 eta: 8:35:40 time: 0.348185 data_time: 0.053496 memory: 4465 loss_kpt: 93.279637 acc_pose: 0.731039 loss: 93.279637 2022/10/12 13:40:26 - mmengine - INFO - Epoch(train) [46][300/586] lr: 5.000000e-03 eta: 8:35:26 time: 0.335093 data_time: 0.048869 memory: 4465 loss_kpt: 93.160341 acc_pose: 0.755312 loss: 93.160341 2022/10/12 13:40:44 - mmengine - INFO - Epoch(train) [46][350/586] lr: 5.000000e-03 eta: 8:35:14 time: 0.340225 data_time: 0.048073 memory: 4465 loss_kpt: 94.409710 acc_pose: 0.702189 loss: 94.409710 2022/10/12 13:41:01 - mmengine - INFO - Epoch(train) [46][400/586] lr: 5.000000e-03 eta: 8:35:01 time: 0.340330 data_time: 0.051075 memory: 4465 loss_kpt: 94.792040 acc_pose: 0.758857 loss: 94.792040 2022/10/12 13:41:18 - mmengine - INFO - Epoch(train) [46][450/586] lr: 5.000000e-03 eta: 8:34:48 time: 0.340047 data_time: 0.051457 memory: 4465 loss_kpt: 94.691588 acc_pose: 0.744544 loss: 94.691588 2022/10/12 13:41:34 - mmengine - INFO - Epoch(train) [46][500/586] lr: 5.000000e-03 eta: 8:34:34 time: 0.328278 data_time: 0.046695 memory: 4465 loss_kpt: 93.495121 acc_pose: 0.815315 loss: 93.495121 2022/10/12 13:41:51 - mmengine - INFO - Epoch(train) [46][550/586] lr: 5.000000e-03 eta: 8:34:20 time: 0.335220 data_time: 0.048902 memory: 4465 loss_kpt: 94.979215 acc_pose: 0.732036 loss: 94.979215 2022/10/12 13:42:03 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:42:20 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:42:22 - mmengine - INFO - Epoch(train) [47][50/586] lr: 5.000000e-03 eta: 8:33:22 time: 0.379267 data_time: 0.065304 memory: 4465 loss_kpt: 95.240154 acc_pose: 0.733571 loss: 95.240154 2022/10/12 13:42:40 - mmengine - INFO - Epoch(train) [47][100/586] lr: 5.000000e-03 eta: 8:33:16 time: 0.375898 data_time: 0.056033 memory: 4465 loss_kpt: 95.716622 acc_pose: 0.764210 loss: 95.716622 2022/10/12 13:42:59 - mmengine - INFO - Epoch(train) [47][150/586] lr: 5.000000e-03 eta: 8:33:07 time: 0.362510 data_time: 0.052889 memory: 4465 loss_kpt: 93.606536 acc_pose: 0.777128 loss: 93.606536 2022/10/12 13:43:16 - mmengine - INFO - Epoch(train) [47][200/586] lr: 5.000000e-03 eta: 8:32:57 time: 0.356726 data_time: 0.050298 memory: 4465 loss_kpt: 93.461370 acc_pose: 0.835627 loss: 93.461370 2022/10/12 13:43:34 - mmengine - INFO - Epoch(train) [47][250/586] lr: 5.000000e-03 eta: 8:32:47 time: 0.352688 data_time: 0.049764 memory: 4465 loss_kpt: 95.481061 acc_pose: 0.768235 loss: 95.481061 2022/10/12 13:43:51 - mmengine - INFO - Epoch(train) [47][300/586] lr: 5.000000e-03 eta: 8:32:35 time: 0.345958 data_time: 0.047576 memory: 4465 loss_kpt: 94.451162 acc_pose: 0.775855 loss: 94.451162 2022/10/12 13:44:08 - mmengine - INFO - Epoch(train) [47][350/586] lr: 5.000000e-03 eta: 8:32:22 time: 0.338095 data_time: 0.047744 memory: 4465 loss_kpt: 93.248727 acc_pose: 0.734475 loss: 93.248727 2022/10/12 13:44:26 - mmengine - INFO - Epoch(train) [47][400/586] lr: 5.000000e-03 eta: 8:32:11 time: 0.348970 data_time: 0.048206 memory: 4465 loss_kpt: 94.044922 acc_pose: 0.779362 loss: 94.044922 2022/10/12 13:44:44 - mmengine - INFO - Epoch(train) [47][450/586] lr: 5.000000e-03 eta: 8:32:03 time: 0.366400 data_time: 0.055761 memory: 4465 loss_kpt: 95.007075 acc_pose: 0.740807 loss: 95.007075 2022/10/12 13:45:02 - mmengine - INFO - Epoch(train) [47][500/586] lr: 5.000000e-03 eta: 8:31:55 time: 0.368295 data_time: 0.049915 memory: 4465 loss_kpt: 92.390852 acc_pose: 0.760642 loss: 92.390852 2022/10/12 13:45:21 - mmengine - INFO - Epoch(train) [47][550/586] lr: 5.000000e-03 eta: 8:31:47 time: 0.368939 data_time: 0.049021 memory: 4465 loss_kpt: 92.273562 acc_pose: 0.729523 loss: 92.273562 2022/10/12 13:45:33 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:45:50 - mmengine - INFO - Epoch(train) [48][50/586] lr: 5.000000e-03 eta: 8:30:42 time: 0.337622 data_time: 0.059708 memory: 4465 loss_kpt: 93.542143 acc_pose: 0.791814 loss: 93.542143 2022/10/12 13:46:07 - mmengine - INFO - Epoch(train) [48][100/586] lr: 5.000000e-03 eta: 8:30:28 time: 0.333746 data_time: 0.047683 memory: 4465 loss_kpt: 93.976653 acc_pose: 0.790200 loss: 93.976653 2022/10/12 13:46:23 - mmengine - INFO - Epoch(train) [48][150/586] lr: 5.000000e-03 eta: 8:30:14 time: 0.331206 data_time: 0.048783 memory: 4465 loss_kpt: 93.702746 acc_pose: 0.779085 loss: 93.702746 2022/10/12 13:46:40 - mmengine - INFO - Epoch(train) [48][200/586] lr: 5.000000e-03 eta: 8:29:58 time: 0.323054 data_time: 0.047627 memory: 4465 loss_kpt: 94.934936 acc_pose: 0.762596 loss: 94.934936 2022/10/12 13:46:57 - mmengine - INFO - Epoch(train) [48][250/586] lr: 5.000000e-03 eta: 8:29:46 time: 0.341824 data_time: 0.047813 memory: 4465 loss_kpt: 93.488495 acc_pose: 0.759456 loss: 93.488495 2022/10/12 13:47:13 - mmengine - INFO - Epoch(train) [48][300/586] lr: 5.000000e-03 eta: 8:29:30 time: 0.324334 data_time: 0.048137 memory: 4465 loss_kpt: 93.178239 acc_pose: 0.659861 loss: 93.178239 2022/10/12 13:47:29 - mmengine - INFO - Epoch(train) [48][350/586] lr: 5.000000e-03 eta: 8:29:16 time: 0.327960 data_time: 0.049618 memory: 4465 loss_kpt: 93.990911 acc_pose: 0.722863 loss: 93.990911 2022/10/12 13:47:47 - mmengine - INFO - Epoch(train) [48][400/586] lr: 5.000000e-03 eta: 8:29:04 time: 0.350083 data_time: 0.050752 memory: 4465 loss_kpt: 92.621616 acc_pose: 0.772125 loss: 92.621616 2022/10/12 13:48:05 - mmengine - INFO - Epoch(train) [48][450/586] lr: 5.000000e-03 eta: 8:28:54 time: 0.354030 data_time: 0.054058 memory: 4465 loss_kpt: 93.023488 acc_pose: 0.799060 loss: 93.023488 2022/10/12 13:48:08 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:48:22 - mmengine - INFO - Epoch(train) [48][500/586] lr: 5.000000e-03 eta: 8:28:41 time: 0.340544 data_time: 0.049608 memory: 4465 loss_kpt: 95.499028 acc_pose: 0.793945 loss: 95.499028 2022/10/12 13:48:38 - mmengine - INFO - Epoch(train) [48][550/586] lr: 5.000000e-03 eta: 8:28:28 time: 0.337331 data_time: 0.049130 memory: 4465 loss_kpt: 94.309438 acc_pose: 0.804714 loss: 94.309438 2022/10/12 13:48:50 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:49:08 - mmengine - INFO - Epoch(train) [49][50/586] lr: 5.000000e-03 eta: 8:27:28 time: 0.361155 data_time: 0.062050 memory: 4465 loss_kpt: 94.682994 acc_pose: 0.729127 loss: 94.682994 2022/10/12 13:49:25 - mmengine - INFO - Epoch(train) [49][100/586] lr: 5.000000e-03 eta: 8:27:15 time: 0.338827 data_time: 0.049375 memory: 4465 loss_kpt: 95.102233 acc_pose: 0.701707 loss: 95.102233 2022/10/12 13:49:42 - mmengine - INFO - Epoch(train) [49][150/586] lr: 5.000000e-03 eta: 8:27:02 time: 0.340224 data_time: 0.050745 memory: 4465 loss_kpt: 92.897027 acc_pose: 0.861100 loss: 92.897027 2022/10/12 13:50:00 - mmengine - INFO - Epoch(train) [49][200/586] lr: 5.000000e-03 eta: 8:26:51 time: 0.347323 data_time: 0.049967 memory: 4465 loss_kpt: 94.214619 acc_pose: 0.806292 loss: 94.214619 2022/10/12 13:50:17 - mmengine - INFO - Epoch(train) [49][250/586] lr: 5.000000e-03 eta: 8:26:38 time: 0.340230 data_time: 0.046626 memory: 4465 loss_kpt: 96.495887 acc_pose: 0.683610 loss: 96.495887 2022/10/12 13:50:33 - mmengine - INFO - Epoch(train) [49][300/586] lr: 5.000000e-03 eta: 8:26:23 time: 0.329829 data_time: 0.047912 memory: 4465 loss_kpt: 94.941713 acc_pose: 0.762940 loss: 94.941713 2022/10/12 13:50:50 - mmengine - INFO - Epoch(train) [49][350/586] lr: 5.000000e-03 eta: 8:26:09 time: 0.334814 data_time: 0.044779 memory: 4465 loss_kpt: 94.917473 acc_pose: 0.815234 loss: 94.917473 2022/10/12 13:51:06 - mmengine - INFO - Epoch(train) [49][400/586] lr: 5.000000e-03 eta: 8:25:55 time: 0.329831 data_time: 0.046105 memory: 4465 loss_kpt: 92.744702 acc_pose: 0.742346 loss: 92.744702 2022/10/12 13:51:24 - mmengine - INFO - Epoch(train) [49][450/586] lr: 5.000000e-03 eta: 8:25:42 time: 0.344307 data_time: 0.048675 memory: 4465 loss_kpt: 95.515052 acc_pose: 0.809646 loss: 95.515052 2022/10/12 13:51:41 - mmengine - INFO - Epoch(train) [49][500/586] lr: 5.000000e-03 eta: 8:25:30 time: 0.342034 data_time: 0.044003 memory: 4465 loss_kpt: 94.604444 acc_pose: 0.790271 loss: 94.604444 2022/10/12 13:51:58 - mmengine - INFO - Epoch(train) [49][550/586] lr: 5.000000e-03 eta: 8:25:18 time: 0.344104 data_time: 0.048624 memory: 4465 loss_kpt: 92.336765 acc_pose: 0.778353 loss: 92.336765 2022/10/12 13:52:10 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:52:28 - mmengine - INFO - Epoch(train) [50][50/586] lr: 5.000000e-03 eta: 8:24:17 time: 0.352407 data_time: 0.060853 memory: 4465 loss_kpt: 95.520465 acc_pose: 0.760450 loss: 95.520465 2022/10/12 13:52:45 - mmengine - INFO - Epoch(train) [50][100/586] lr: 5.000000e-03 eta: 8:24:05 time: 0.341638 data_time: 0.045114 memory: 4465 loss_kpt: 93.710535 acc_pose: 0.776892 loss: 93.710535 2022/10/12 13:53:02 - mmengine - INFO - Epoch(train) [50][150/586] lr: 5.000000e-03 eta: 8:23:52 time: 0.345266 data_time: 0.047714 memory: 4465 loss_kpt: 93.016765 acc_pose: 0.759124 loss: 93.016765 2022/10/12 13:53:19 - mmengine - INFO - Epoch(train) [50][200/586] lr: 5.000000e-03 eta: 8:23:41 time: 0.350450 data_time: 0.050876 memory: 4465 loss_kpt: 93.422921 acc_pose: 0.716355 loss: 93.422921 2022/10/12 13:53:36 - mmengine - INFO - Epoch(train) [50][250/586] lr: 5.000000e-03 eta: 8:23:28 time: 0.339199 data_time: 0.045314 memory: 4465 loss_kpt: 94.749881 acc_pose: 0.824370 loss: 94.749881 2022/10/12 13:53:49 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:53:54 - mmengine - INFO - Epoch(train) [50][300/586] lr: 5.000000e-03 eta: 8:23:16 time: 0.342678 data_time: 0.045459 memory: 4465 loss_kpt: 93.756709 acc_pose: 0.729823 loss: 93.756709 2022/10/12 13:54:11 - mmengine - INFO - Epoch(train) [50][350/586] lr: 5.000000e-03 eta: 8:23:05 time: 0.356920 data_time: 0.049355 memory: 4465 loss_kpt: 93.497068 acc_pose: 0.770789 loss: 93.497068 2022/10/12 13:54:28 - mmengine - INFO - Epoch(train) [50][400/586] lr: 5.000000e-03 eta: 8:22:52 time: 0.341293 data_time: 0.047651 memory: 4465 loss_kpt: 92.455499 acc_pose: 0.775735 loss: 92.455499 2022/10/12 13:54:45 - mmengine - INFO - Epoch(train) [50][450/586] lr: 5.000000e-03 eta: 8:22:39 time: 0.336988 data_time: 0.047160 memory: 4465 loss_kpt: 93.348451 acc_pose: 0.754708 loss: 93.348451 2022/10/12 13:55:02 - mmengine - INFO - Epoch(train) [50][500/586] lr: 5.000000e-03 eta: 8:22:26 time: 0.342966 data_time: 0.050525 memory: 4465 loss_kpt: 95.037921 acc_pose: 0.826287 loss: 95.037921 2022/10/12 13:55:20 - mmengine - INFO - Epoch(train) [50][550/586] lr: 5.000000e-03 eta: 8:22:14 time: 0.346318 data_time: 0.051244 memory: 4465 loss_kpt: 95.502179 acc_pose: 0.816797 loss: 95.502179 2022/10/12 13:55:32 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 13:55:32 - mmengine - INFO - Saving checkpoint at 50 epochs 2022/10/12 13:55:41 - mmengine - INFO - Epoch(val) [50][50/407] eta: 0:00:47 time: 0.133521 data_time: 0.013570 memory: 4465 2022/10/12 13:55:47 - mmengine - INFO - Epoch(val) [50][100/407] eta: 0:00:38 time: 0.126652 data_time: 0.008370 memory: 1026 2022/10/12 13:55:54 - mmengine - INFO - Epoch(val) [50][150/407] eta: 0:00:33 time: 0.131280 data_time: 0.012521 memory: 1026 2022/10/12 13:56:00 - mmengine - INFO - Epoch(val) [50][200/407] eta: 0:00:26 time: 0.126248 data_time: 0.008558 memory: 1026 2022/10/12 13:56:06 - mmengine - INFO - Epoch(val) [50][250/407] eta: 0:00:19 time: 0.124936 data_time: 0.008103 memory: 1026 2022/10/12 13:56:13 - mmengine - INFO - Epoch(val) [50][300/407] eta: 0:00:13 time: 0.126294 data_time: 0.008119 memory: 1026 2022/10/12 13:56:19 - mmengine - INFO - Epoch(val) [50][350/407] eta: 0:00:07 time: 0.126448 data_time: 0.008417 memory: 1026 2022/10/12 13:56:25 - mmengine - INFO - Epoch(val) [50][400/407] eta: 0:00:00 time: 0.125453 data_time: 0.008175 memory: 1026 2022/10/12 13:56:39 - mmengine - INFO - Evaluating CocoMetric... 2022/10/12 13:56:55 - mmengine - INFO - Epoch(val) [50][407/407] coco/AP: 0.652678 coco/AP .5: 0.866111 coco/AP .75: 0.726543 coco/AP (M): 0.625630 coco/AP (L): 0.706041 coco/AR: 0.725661 coco/AR .5: 0.909005 coco/AR .75: 0.791404 coco/AR (M): 0.681836 coco/AR (L): 0.786213 2022/10/12 13:56:55 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/liqikai/openmmlab/pt112cu113py38/mmpose/work_dirs/20221012/rsn50/best_coco/AP_epoch_40.pth is removed 2022/10/12 13:56:57 - mmengine - INFO - The best checkpoint with 0.6527 coco/AP at 50 epoch is saved to best_coco/AP_epoch_50.pth. 2022/10/12 13:57:14 - mmengine - INFO - Epoch(train) [51][50/586] lr: 5.000000e-03 eta: 8:21:15 time: 0.353327 data_time: 0.057369 memory: 4465 loss_kpt: 93.860738 acc_pose: 0.794891 loss: 93.860738 2022/10/12 13:57:32 - mmengine - INFO - Epoch(train) [51][100/586] lr: 5.000000e-03 eta: 8:21:03 time: 0.346498 data_time: 0.050789 memory: 4465 loss_kpt: 93.180246 acc_pose: 0.797550 loss: 93.180246 2022/10/12 13:57:49 - mmengine - INFO - Epoch(train) [51][150/586] lr: 5.000000e-03 eta: 8:20:50 time: 0.342979 data_time: 0.053035 memory: 4465 loss_kpt: 93.364056 acc_pose: 0.805940 loss: 93.364056 2022/10/12 13:58:06 - mmengine - INFO - Epoch(train) [51][200/586] lr: 5.000000e-03 eta: 8:20:37 time: 0.340462 data_time: 0.048098 memory: 4465 loss_kpt: 92.499638 acc_pose: 0.763653 loss: 92.499638 2022/10/12 13:58:23 - mmengine - INFO - Epoch(train) [51][250/586] lr: 5.000000e-03 eta: 8:20:25 time: 0.347109 data_time: 0.055519 memory: 4465 loss_kpt: 95.119555 acc_pose: 0.723848 loss: 95.119555 2022/10/12 13:58:41 - mmengine - INFO - Epoch(train) [51][300/586] lr: 5.000000e-03 eta: 8:20:13 time: 0.345194 data_time: 0.048035 memory: 4465 loss_kpt: 92.814672 acc_pose: 0.815986 loss: 92.814672 2022/10/12 13:58:58 - mmengine - INFO - Epoch(train) [51][350/586] lr: 5.000000e-03 eta: 8:20:02 time: 0.350417 data_time: 0.050763 memory: 4465 loss_kpt: 93.800840 acc_pose: 0.789750 loss: 93.800840 2022/10/12 13:59:15 - mmengine - INFO - Epoch(train) [51][400/586] lr: 5.000000e-03 eta: 8:19:50 time: 0.346260 data_time: 0.049403 memory: 4465 loss_kpt: 93.241861 acc_pose: 0.769192 loss: 93.241861 2022/10/12 13:59:33 - mmengine - INFO - Epoch(train) [51][450/586] lr: 5.000000e-03 eta: 8:19:38 time: 0.348427 data_time: 0.050188 memory: 4465 loss_kpt: 93.216742 acc_pose: 0.881800 loss: 93.216742 2022/10/12 13:59:50 - mmengine - INFO - Epoch(train) [51][500/586] lr: 5.000000e-03 eta: 8:19:26 time: 0.344865 data_time: 0.044559 memory: 4465 loss_kpt: 93.185497 acc_pose: 0.741248 loss: 93.185497 2022/10/12 14:00:08 - mmengine - INFO - Epoch(train) [51][550/586] lr: 5.000000e-03 eta: 8:19:15 time: 0.357882 data_time: 0.051809 memory: 4465 loss_kpt: 93.424844 acc_pose: 0.760171 loss: 93.424844 2022/10/12 14:00:20 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:00:38 - mmengine - INFO - Epoch(train) [52][50/586] lr: 5.000000e-03 eta: 8:18:15 time: 0.345013 data_time: 0.055557 memory: 4465 loss_kpt: 93.282874 acc_pose: 0.740353 loss: 93.282874 2022/10/12 14:00:54 - mmengine - INFO - Epoch(train) [52][100/586] lr: 5.000000e-03 eta: 8:18:00 time: 0.328832 data_time: 0.048228 memory: 4465 loss_kpt: 93.164725 acc_pose: 0.682842 loss: 93.164725 2022/10/12 14:00:59 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:01:12 - mmengine - INFO - Epoch(train) [52][150/586] lr: 5.000000e-03 eta: 8:17:51 time: 0.365704 data_time: 0.054043 memory: 4465 loss_kpt: 93.148753 acc_pose: 0.829395 loss: 93.148753 2022/10/12 14:01:30 - mmengine - INFO - Epoch(train) [52][200/586] lr: 5.000000e-03 eta: 8:17:40 time: 0.353071 data_time: 0.047054 memory: 4465 loss_kpt: 92.978414 acc_pose: 0.776764 loss: 92.978414 2022/10/12 14:01:47 - mmengine - INFO - Epoch(train) [52][250/586] lr: 5.000000e-03 eta: 8:17:27 time: 0.342338 data_time: 0.047052 memory: 4465 loss_kpt: 92.857917 acc_pose: 0.795058 loss: 92.857917 2022/10/12 14:02:04 - mmengine - INFO - Epoch(train) [52][300/586] lr: 5.000000e-03 eta: 8:17:14 time: 0.338825 data_time: 0.044134 memory: 4465 loss_kpt: 93.062601 acc_pose: 0.746817 loss: 93.062601 2022/10/12 14:02:21 - mmengine - INFO - Epoch(train) [52][350/586] lr: 5.000000e-03 eta: 8:17:02 time: 0.345985 data_time: 0.045168 memory: 4465 loss_kpt: 93.502982 acc_pose: 0.684125 loss: 93.502982 2022/10/12 14:02:39 - mmengine - INFO - Epoch(train) [52][400/586] lr: 5.000000e-03 eta: 8:16:50 time: 0.348272 data_time: 0.046590 memory: 4465 loss_kpt: 92.609102 acc_pose: 0.726570 loss: 92.609102 2022/10/12 14:02:56 - mmengine - INFO - Epoch(train) [52][450/586] lr: 5.000000e-03 eta: 8:16:37 time: 0.342354 data_time: 0.047378 memory: 4465 loss_kpt: 92.218691 acc_pose: 0.759455 loss: 92.218691 2022/10/12 14:03:12 - mmengine - INFO - Epoch(train) [52][500/586] lr: 5.000000e-03 eta: 8:16:21 time: 0.320966 data_time: 0.049157 memory: 4465 loss_kpt: 94.934647 acc_pose: 0.716978 loss: 94.934647 2022/10/12 14:03:29 - mmengine - INFO - Epoch(train) [52][550/586] lr: 5.000000e-03 eta: 8:16:08 time: 0.345092 data_time: 0.050626 memory: 4465 loss_kpt: 94.413227 acc_pose: 0.824466 loss: 94.413227 2022/10/12 14:03:41 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:04:00 - mmengine - INFO - Epoch(train) [53][50/586] lr: 5.000000e-03 eta: 8:15:14 time: 0.379177 data_time: 0.066360 memory: 4465 loss_kpt: 95.068240 acc_pose: 0.791703 loss: 95.068240 2022/10/12 14:04:18 - mmengine - INFO - Epoch(train) [53][100/586] lr: 5.000000e-03 eta: 8:15:02 time: 0.346907 data_time: 0.057881 memory: 4465 loss_kpt: 93.020106 acc_pose: 0.787431 loss: 93.020106 2022/10/12 14:04:35 - mmengine - INFO - Epoch(train) [53][150/586] lr: 5.000000e-03 eta: 8:14:50 time: 0.347829 data_time: 0.049558 memory: 4465 loss_kpt: 92.500108 acc_pose: 0.793194 loss: 92.500108 2022/10/12 14:04:52 - mmengine - INFO - Epoch(train) [53][200/586] lr: 5.000000e-03 eta: 8:14:36 time: 0.336551 data_time: 0.052354 memory: 4465 loss_kpt: 93.773996 acc_pose: 0.608756 loss: 93.773996 2022/10/12 14:05:09 - mmengine - INFO - Epoch(train) [53][250/586] lr: 5.000000e-03 eta: 8:14:22 time: 0.331870 data_time: 0.049980 memory: 4465 loss_kpt: 93.986177 acc_pose: 0.849608 loss: 93.986177 2022/10/12 14:05:25 - mmengine - INFO - Epoch(train) [53][300/586] lr: 5.000000e-03 eta: 8:14:06 time: 0.320127 data_time: 0.050249 memory: 4465 loss_kpt: 93.524632 acc_pose: 0.797171 loss: 93.524632 2022/10/12 14:05:41 - mmengine - INFO - Epoch(train) [53][350/586] lr: 5.000000e-03 eta: 8:13:50 time: 0.325978 data_time: 0.053502 memory: 4465 loss_kpt: 93.915853 acc_pose: 0.793041 loss: 93.915853 2022/10/12 14:05:57 - mmengine - INFO - Epoch(train) [53][400/586] lr: 5.000000e-03 eta: 8:13:34 time: 0.316445 data_time: 0.046227 memory: 4465 loss_kpt: 93.471993 acc_pose: 0.783162 loss: 93.471993 2022/10/12 14:06:14 - mmengine - INFO - Epoch(train) [53][450/586] lr: 5.000000e-03 eta: 8:13:20 time: 0.339653 data_time: 0.051493 memory: 4465 loss_kpt: 92.867585 acc_pose: 0.828725 loss: 92.867585 2022/10/12 14:06:31 - mmengine - INFO - Epoch(train) [53][500/586] lr: 5.000000e-03 eta: 8:13:07 time: 0.342769 data_time: 0.045734 memory: 4465 loss_kpt: 93.690291 acc_pose: 0.744717 loss: 93.690291 2022/10/12 14:06:41 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:06:48 - mmengine - INFO - Epoch(train) [53][550/586] lr: 5.000000e-03 eta: 8:12:54 time: 0.340925 data_time: 0.048822 memory: 4465 loss_kpt: 92.155116 acc_pose: 0.771542 loss: 92.155116 2022/10/12 14:07:00 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:07:17 - mmengine - INFO - Epoch(train) [54][50/586] lr: 5.000000e-03 eta: 8:11:56 time: 0.344935 data_time: 0.060066 memory: 4465 loss_kpt: 93.662027 acc_pose: 0.786458 loss: 93.662027 2022/10/12 14:07:33 - mmengine - INFO - Epoch(train) [54][100/586] lr: 5.000000e-03 eta: 8:11:40 time: 0.323853 data_time: 0.046065 memory: 4465 loss_kpt: 94.175051 acc_pose: 0.698074 loss: 94.175051 2022/10/12 14:07:50 - mmengine - INFO - Epoch(train) [54][150/586] lr: 5.000000e-03 eta: 8:11:25 time: 0.323646 data_time: 0.045664 memory: 4465 loss_kpt: 93.734582 acc_pose: 0.717574 loss: 93.734582 2022/10/12 14:08:06 - mmengine - INFO - Epoch(train) [54][200/586] lr: 5.000000e-03 eta: 8:11:09 time: 0.320527 data_time: 0.044832 memory: 4465 loss_kpt: 92.471495 acc_pose: 0.677088 loss: 92.471495 2022/10/12 14:08:22 - mmengine - INFO - Epoch(train) [54][250/586] lr: 5.000000e-03 eta: 8:10:55 time: 0.334868 data_time: 0.047648 memory: 4465 loss_kpt: 93.258346 acc_pose: 0.737434 loss: 93.258346 2022/10/12 14:08:39 - mmengine - INFO - Epoch(train) [54][300/586] lr: 5.000000e-03 eta: 8:10:40 time: 0.329792 data_time: 0.049477 memory: 4465 loss_kpt: 92.143648 acc_pose: 0.734606 loss: 92.143648 2022/10/12 14:08:55 - mmengine - INFO - Epoch(train) [54][350/586] lr: 5.000000e-03 eta: 8:10:25 time: 0.328323 data_time: 0.054117 memory: 4465 loss_kpt: 92.791939 acc_pose: 0.835504 loss: 92.791939 2022/10/12 14:09:12 - mmengine - INFO - Epoch(train) [54][400/586] lr: 5.000000e-03 eta: 8:10:10 time: 0.331975 data_time: 0.054926 memory: 4465 loss_kpt: 91.549825 acc_pose: 0.783705 loss: 91.549825 2022/10/12 14:09:29 - mmengine - INFO - Epoch(train) [54][450/586] lr: 5.000000e-03 eta: 8:09:57 time: 0.338526 data_time: 0.049557 memory: 4465 loss_kpt: 92.719051 acc_pose: 0.766328 loss: 92.719051 2022/10/12 14:09:47 - mmengine - INFO - Epoch(train) [54][500/586] lr: 5.000000e-03 eta: 8:09:46 time: 0.354534 data_time: 0.050476 memory: 4465 loss_kpt: 92.206902 acc_pose: 0.749430 loss: 92.206902 2022/10/12 14:10:04 - mmengine - INFO - Epoch(train) [54][550/586] lr: 5.000000e-03 eta: 8:09:33 time: 0.347060 data_time: 0.051969 memory: 4465 loss_kpt: 92.907645 acc_pose: 0.739577 loss: 92.907645 2022/10/12 14:10:16 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:10:33 - mmengine - INFO - Epoch(train) [55][50/586] lr: 5.000000e-03 eta: 8:08:36 time: 0.344389 data_time: 0.058348 memory: 4465 loss_kpt: 92.279567 acc_pose: 0.805125 loss: 92.279567 2022/10/12 14:10:50 - mmengine - INFO - Epoch(train) [55][100/586] lr: 5.000000e-03 eta: 8:08:21 time: 0.328729 data_time: 0.051286 memory: 4465 loss_kpt: 92.070989 acc_pose: 0.813165 loss: 92.070989 2022/10/12 14:11:07 - mmengine - INFO - Epoch(train) [55][150/586] lr: 5.000000e-03 eta: 8:08:09 time: 0.347553 data_time: 0.052795 memory: 4465 loss_kpt: 91.097067 acc_pose: 0.774788 loss: 91.097067 2022/10/12 14:11:24 - mmengine - INFO - Epoch(train) [55][200/586] lr: 5.000000e-03 eta: 8:07:55 time: 0.335688 data_time: 0.053619 memory: 4465 loss_kpt: 91.192750 acc_pose: 0.755538 loss: 91.192750 2022/10/12 14:11:40 - mmengine - INFO - Epoch(train) [55][250/586] lr: 5.000000e-03 eta: 8:07:40 time: 0.330220 data_time: 0.053755 memory: 4465 loss_kpt: 92.913314 acc_pose: 0.843880 loss: 92.913314 2022/10/12 14:11:57 - mmengine - INFO - Epoch(train) [55][300/586] lr: 5.000000e-03 eta: 8:07:27 time: 0.342375 data_time: 0.048656 memory: 4465 loss_kpt: 91.511193 acc_pose: 0.694577 loss: 91.511193 2022/10/12 14:12:14 - mmengine - INFO - Epoch(train) [55][350/586] lr: 5.000000e-03 eta: 8:07:13 time: 0.333353 data_time: 0.050105 memory: 4465 loss_kpt: 94.343010 acc_pose: 0.831663 loss: 94.343010 2022/10/12 14:12:16 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:12:31 - mmengine - INFO - Epoch(train) [55][400/586] lr: 5.000000e-03 eta: 8:06:58 time: 0.334714 data_time: 0.047213 memory: 4465 loss_kpt: 91.939295 acc_pose: 0.741481 loss: 91.939295 2022/10/12 14:12:47 - mmengine - INFO - Epoch(train) [55][450/586] lr: 5.000000e-03 eta: 8:06:44 time: 0.328738 data_time: 0.047608 memory: 4465 loss_kpt: 93.492162 acc_pose: 0.763057 loss: 93.492162 2022/10/12 14:13:04 - mmengine - INFO - Epoch(train) [55][500/586] lr: 5.000000e-03 eta: 8:06:29 time: 0.329651 data_time: 0.048939 memory: 4465 loss_kpt: 92.002383 acc_pose: 0.762715 loss: 92.002383 2022/10/12 14:13:20 - mmengine - INFO - Epoch(train) [55][550/586] lr: 5.000000e-03 eta: 8:06:14 time: 0.334095 data_time: 0.052354 memory: 4465 loss_kpt: 91.221693 acc_pose: 0.737810 loss: 91.221693 2022/10/12 14:13:33 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:13:50 - mmengine - INFO - Epoch(train) [56][50/586] lr: 5.000000e-03 eta: 8:05:17 time: 0.337854 data_time: 0.054142 memory: 4465 loss_kpt: 93.964466 acc_pose: 0.751103 loss: 93.964466 2022/10/12 14:14:06 - mmengine - INFO - Epoch(train) [56][100/586] lr: 5.000000e-03 eta: 8:05:02 time: 0.333193 data_time: 0.043443 memory: 4465 loss_kpt: 92.572540 acc_pose: 0.730992 loss: 92.572540 2022/10/12 14:14:23 - mmengine - INFO - Epoch(train) [56][150/586] lr: 5.000000e-03 eta: 8:04:47 time: 0.322383 data_time: 0.046250 memory: 4465 loss_kpt: 92.322146 acc_pose: 0.846840 loss: 92.322146 2022/10/12 14:14:39 - mmengine - INFO - Epoch(train) [56][200/586] lr: 5.000000e-03 eta: 8:04:31 time: 0.320946 data_time: 0.048103 memory: 4465 loss_kpt: 91.539134 acc_pose: 0.800210 loss: 91.539134 2022/10/12 14:14:55 - mmengine - INFO - Epoch(train) [56][250/586] lr: 5.000000e-03 eta: 8:04:17 time: 0.336336 data_time: 0.050722 memory: 4465 loss_kpt: 94.536808 acc_pose: 0.790564 loss: 94.536808 2022/10/12 14:15:12 - mmengine - INFO - Epoch(train) [56][300/586] lr: 5.000000e-03 eta: 8:04:02 time: 0.333520 data_time: 0.044111 memory: 4465 loss_kpt: 92.521832 acc_pose: 0.708271 loss: 92.521832 2022/10/12 14:15:28 - mmengine - INFO - Epoch(train) [56][350/586] lr: 5.000000e-03 eta: 8:03:46 time: 0.316825 data_time: 0.048711 memory: 4465 loss_kpt: 94.184523 acc_pose: 0.806912 loss: 94.184523 2022/10/12 14:15:44 - mmengine - INFO - Epoch(train) [56][400/586] lr: 5.000000e-03 eta: 8:03:31 time: 0.329350 data_time: 0.048878 memory: 4465 loss_kpt: 91.792750 acc_pose: 0.699634 loss: 91.792750 2022/10/12 14:16:01 - mmengine - INFO - Epoch(train) [56][450/586] lr: 5.000000e-03 eta: 8:03:16 time: 0.327376 data_time: 0.051054 memory: 4465 loss_kpt: 93.114747 acc_pose: 0.752538 loss: 93.114747 2022/10/12 14:16:17 - mmengine - INFO - Epoch(train) [56][500/586] lr: 5.000000e-03 eta: 8:03:00 time: 0.323524 data_time: 0.049570 memory: 4465 loss_kpt: 92.541725 acc_pose: 0.786479 loss: 92.541725 2022/10/12 14:16:33 - mmengine - INFO - Epoch(train) [56][550/586] lr: 5.000000e-03 eta: 8:02:45 time: 0.324340 data_time: 0.051620 memory: 4465 loss_kpt: 92.024407 acc_pose: 0.781641 loss: 92.024407 2022/10/12 14:16:44 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:17:03 - mmengine - INFO - Epoch(train) [57][50/586] lr: 5.000000e-03 eta: 8:01:52 time: 0.366836 data_time: 0.059776 memory: 4465 loss_kpt: 92.958893 acc_pose: 0.687267 loss: 92.958893 2022/10/12 14:17:20 - mmengine - INFO - Epoch(train) [57][100/586] lr: 5.000000e-03 eta: 8:01:39 time: 0.344459 data_time: 0.052837 memory: 4465 loss_kpt: 90.857004 acc_pose: 0.805316 loss: 90.857004 2022/10/12 14:17:38 - mmengine - INFO - Epoch(train) [57][150/586] lr: 5.000000e-03 eta: 8:01:27 time: 0.352294 data_time: 0.052427 memory: 4465 loss_kpt: 91.872645 acc_pose: 0.757215 loss: 91.872645 2022/10/12 14:17:49 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:17:55 - mmengine - INFO - Epoch(train) [57][200/586] lr: 5.000000e-03 eta: 8:01:14 time: 0.340044 data_time: 0.045457 memory: 4465 loss_kpt: 93.114910 acc_pose: 0.760737 loss: 93.114910 2022/10/12 14:18:12 - mmengine - INFO - Epoch(train) [57][250/586] lr: 5.000000e-03 eta: 8:01:00 time: 0.338795 data_time: 0.052405 memory: 4465 loss_kpt: 91.290294 acc_pose: 0.771926 loss: 91.290294 2022/10/12 14:18:29 - mmengine - INFO - Epoch(train) [57][300/586] lr: 5.000000e-03 eta: 8:00:47 time: 0.344456 data_time: 0.053434 memory: 4465 loss_kpt: 91.577593 acc_pose: 0.782731 loss: 91.577593 2022/10/12 14:18:46 - mmengine - INFO - Epoch(train) [57][350/586] lr: 5.000000e-03 eta: 8:00:35 time: 0.350113 data_time: 0.052138 memory: 4465 loss_kpt: 92.818011 acc_pose: 0.705500 loss: 92.818011 2022/10/12 14:19:03 - mmengine - INFO - Epoch(train) [57][400/586] lr: 5.000000e-03 eta: 8:00:22 time: 0.338813 data_time: 0.049484 memory: 4465 loss_kpt: 93.042121 acc_pose: 0.744728 loss: 93.042121 2022/10/12 14:19:21 - mmengine - INFO - Epoch(train) [57][450/586] lr: 5.000000e-03 eta: 8:00:09 time: 0.345035 data_time: 0.048768 memory: 4465 loss_kpt: 90.985466 acc_pose: 0.737872 loss: 90.985466 2022/10/12 14:19:37 - mmengine - INFO - Epoch(train) [57][500/586] lr: 5.000000e-03 eta: 7:59:55 time: 0.338054 data_time: 0.047307 memory: 4465 loss_kpt: 93.246917 acc_pose: 0.797304 loss: 93.246917 2022/10/12 14:19:55 - mmengine - INFO - Epoch(train) [57][550/586] lr: 5.000000e-03 eta: 7:59:42 time: 0.344948 data_time: 0.048833 memory: 4465 loss_kpt: 93.102142 acc_pose: 0.747811 loss: 93.102142 2022/10/12 14:20:07 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:20:25 - mmengine - INFO - Epoch(train) [58][50/586] lr: 5.000000e-03 eta: 7:58:50 time: 0.364807 data_time: 0.067891 memory: 4465 loss_kpt: 91.654844 acc_pose: 0.719505 loss: 91.654844 2022/10/12 14:20:43 - mmengine - INFO - Epoch(train) [58][100/586] lr: 5.000000e-03 eta: 7:58:38 time: 0.354064 data_time: 0.052297 memory: 4465 loss_kpt: 93.657473 acc_pose: 0.738316 loss: 93.657473 2022/10/12 14:21:00 - mmengine - INFO - Epoch(train) [58][150/586] lr: 5.000000e-03 eta: 7:58:25 time: 0.344434 data_time: 0.053699 memory: 4465 loss_kpt: 92.335951 acc_pose: 0.739266 loss: 92.335951 2022/10/12 14:21:17 - mmengine - INFO - Epoch(train) [58][200/586] lr: 5.000000e-03 eta: 7:58:13 time: 0.345515 data_time: 0.054815 memory: 4465 loss_kpt: 91.676536 acc_pose: 0.663554 loss: 91.676536 2022/10/12 14:21:34 - mmengine - INFO - Epoch(train) [58][250/586] lr: 5.000000e-03 eta: 7:58:00 time: 0.342721 data_time: 0.050348 memory: 4465 loss_kpt: 92.292102 acc_pose: 0.747855 loss: 92.292102 2022/10/12 14:21:52 - mmengine - INFO - Epoch(train) [58][300/586] lr: 5.000000e-03 eta: 7:57:47 time: 0.344091 data_time: 0.054631 memory: 4465 loss_kpt: 91.079766 acc_pose: 0.781363 loss: 91.079766 2022/10/12 14:22:09 - mmengine - INFO - Epoch(train) [58][350/586] lr: 5.000000e-03 eta: 7:57:34 time: 0.349302 data_time: 0.052243 memory: 4465 loss_kpt: 93.939905 acc_pose: 0.800465 loss: 93.939905 2022/10/12 14:22:26 - mmengine - INFO - Epoch(train) [58][400/586] lr: 5.000000e-03 eta: 7:57:21 time: 0.340884 data_time: 0.052346 memory: 4465 loss_kpt: 92.795723 acc_pose: 0.820118 loss: 92.795723 2022/10/12 14:22:43 - mmengine - INFO - Epoch(train) [58][450/586] lr: 5.000000e-03 eta: 7:57:07 time: 0.336636 data_time: 0.053310 memory: 4465 loss_kpt: 93.377813 acc_pose: 0.770613 loss: 93.377813 2022/10/12 14:23:00 - mmengine - INFO - Epoch(train) [58][500/586] lr: 5.000000e-03 eta: 7:56:53 time: 0.333384 data_time: 0.051311 memory: 4465 loss_kpt: 93.228957 acc_pose: 0.797772 loss: 93.228957 2022/10/12 14:23:16 - mmengine - INFO - Epoch(train) [58][550/586] lr: 5.000000e-03 eta: 7:56:38 time: 0.331864 data_time: 0.046874 memory: 4465 loss_kpt: 91.277004 acc_pose: 0.703000 loss: 91.277004 2022/10/12 14:23:28 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:23:32 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:23:45 - mmengine - INFO - Epoch(train) [59][50/586] lr: 5.000000e-03 eta: 7:55:44 time: 0.351302 data_time: 0.063031 memory: 4465 loss_kpt: 93.251749 acc_pose: 0.739703 loss: 93.251749 2022/10/12 14:24:02 - mmengine - INFO - Epoch(train) [59][100/586] lr: 5.000000e-03 eta: 7:55:31 time: 0.340252 data_time: 0.051879 memory: 4465 loss_kpt: 92.524961 acc_pose: 0.724369 loss: 92.524961 2022/10/12 14:24:20 - mmengine - INFO - Epoch(train) [59][150/586] lr: 5.000000e-03 eta: 7:55:18 time: 0.349501 data_time: 0.054231 memory: 4465 loss_kpt: 93.446428 acc_pose: 0.760992 loss: 93.446428 2022/10/12 14:24:38 - mmengine - INFO - Epoch(train) [59][200/586] lr: 5.000000e-03 eta: 7:55:07 time: 0.353482 data_time: 0.050472 memory: 4465 loss_kpt: 91.869623 acc_pose: 0.805060 loss: 91.869623 2022/10/12 14:24:55 - mmengine - INFO - Epoch(train) [59][250/586] lr: 5.000000e-03 eta: 7:54:55 time: 0.357683 data_time: 0.054046 memory: 4465 loss_kpt: 93.272686 acc_pose: 0.811576 loss: 93.272686 2022/10/12 14:25:12 - mmengine - INFO - Epoch(train) [59][300/586] lr: 5.000000e-03 eta: 7:54:41 time: 0.335773 data_time: 0.048648 memory: 4465 loss_kpt: 91.180641 acc_pose: 0.803942 loss: 91.180641 2022/10/12 14:25:30 - mmengine - INFO - Epoch(train) [59][350/586] lr: 5.000000e-03 eta: 7:54:28 time: 0.344823 data_time: 0.059102 memory: 4465 loss_kpt: 91.002692 acc_pose: 0.703359 loss: 91.002692 2022/10/12 14:25:47 - mmengine - INFO - Epoch(train) [59][400/586] lr: 5.000000e-03 eta: 7:54:15 time: 0.340391 data_time: 0.051642 memory: 4465 loss_kpt: 92.938633 acc_pose: 0.775398 loss: 92.938633 2022/10/12 14:26:03 - mmengine - INFO - Epoch(train) [59][450/586] lr: 5.000000e-03 eta: 7:54:01 time: 0.337782 data_time: 0.054471 memory: 4465 loss_kpt: 93.306886 acc_pose: 0.776362 loss: 93.306886 2022/10/12 14:26:20 - mmengine - INFO - Epoch(train) [59][500/586] lr: 5.000000e-03 eta: 7:53:46 time: 0.332488 data_time: 0.051650 memory: 4465 loss_kpt: 90.715397 acc_pose: 0.872467 loss: 90.715397 2022/10/12 14:26:37 - mmengine - INFO - Epoch(train) [59][550/586] lr: 5.000000e-03 eta: 7:53:34 time: 0.348060 data_time: 0.056805 memory: 4465 loss_kpt: 92.739362 acc_pose: 0.753273 loss: 92.739362 2022/10/12 14:26:50 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:27:08 - mmengine - INFO - Epoch(train) [60][50/586] lr: 5.000000e-03 eta: 7:52:42 time: 0.360855 data_time: 0.059451 memory: 4465 loss_kpt: 92.735031 acc_pose: 0.792185 loss: 92.735031 2022/10/12 14:27:25 - mmengine - INFO - Epoch(train) [60][100/586] lr: 5.000000e-03 eta: 7:52:29 time: 0.344015 data_time: 0.049326 memory: 4465 loss_kpt: 91.842667 acc_pose: 0.820885 loss: 91.842667 2022/10/12 14:27:43 - mmengine - INFO - Epoch(train) [60][150/586] lr: 5.000000e-03 eta: 7:52:17 time: 0.356402 data_time: 0.054345 memory: 4465 loss_kpt: 94.084377 acc_pose: 0.723849 loss: 94.084377 2022/10/12 14:28:00 - mmengine - INFO - Epoch(train) [60][200/586] lr: 5.000000e-03 eta: 7:52:04 time: 0.343905 data_time: 0.047728 memory: 4465 loss_kpt: 91.894163 acc_pose: 0.801586 loss: 91.894163 2022/10/12 14:28:17 - mmengine - INFO - Epoch(train) [60][250/586] lr: 5.000000e-03 eta: 7:51:50 time: 0.334204 data_time: 0.050965 memory: 4465 loss_kpt: 91.351252 acc_pose: 0.809256 loss: 91.351252 2022/10/12 14:28:34 - mmengine - INFO - Epoch(train) [60][300/586] lr: 5.000000e-03 eta: 7:51:37 time: 0.343380 data_time: 0.053085 memory: 4465 loss_kpt: 92.905515 acc_pose: 0.782442 loss: 92.905515 2022/10/12 14:28:51 - mmengine - INFO - Epoch(train) [60][350/586] lr: 5.000000e-03 eta: 7:51:23 time: 0.344720 data_time: 0.051193 memory: 4465 loss_kpt: 92.585817 acc_pose: 0.774203 loss: 92.585817 2022/10/12 14:29:07 - mmengine - INFO - Epoch(train) [60][400/586] lr: 5.000000e-03 eta: 7:51:08 time: 0.328145 data_time: 0.047192 memory: 4465 loss_kpt: 92.430375 acc_pose: 0.803229 loss: 92.430375 2022/10/12 14:29:16 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:29:24 - mmengine - INFO - Epoch(train) [60][450/586] lr: 5.000000e-03 eta: 7:50:53 time: 0.329003 data_time: 0.050292 memory: 4465 loss_kpt: 93.553411 acc_pose: 0.795161 loss: 93.553411 2022/10/12 14:29:40 - mmengine - INFO - Epoch(train) [60][500/586] lr: 5.000000e-03 eta: 7:50:38 time: 0.327189 data_time: 0.047712 memory: 4465 loss_kpt: 93.349956 acc_pose: 0.730974 loss: 93.349956 2022/10/12 14:29:56 - mmengine - INFO - Epoch(train) [60][550/586] lr: 5.000000e-03 eta: 7:50:22 time: 0.322275 data_time: 0.050452 memory: 4465 loss_kpt: 93.832739 acc_pose: 0.777337 loss: 93.832739 2022/10/12 14:30:08 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:30:08 - mmengine - INFO - Saving checkpoint at 60 epochs 2022/10/12 14:30:17 - mmengine - INFO - Epoch(val) [60][50/407] eta: 0:00:47 time: 0.132450 data_time: 0.013743 memory: 4465 2022/10/12 14:30:23 - mmengine - INFO - Epoch(val) [60][100/407] eta: 0:00:38 time: 0.125412 data_time: 0.008317 memory: 1026 2022/10/12 14:30:30 - mmengine - INFO - Epoch(val) [60][150/407] eta: 0:00:32 time: 0.126682 data_time: 0.008267 memory: 1026 2022/10/12 14:30:36 - mmengine - INFO - Epoch(val) [60][200/407] eta: 0:00:27 time: 0.131325 data_time: 0.008346 memory: 1026 2022/10/12 14:30:43 - mmengine - INFO - Epoch(val) [60][250/407] eta: 0:00:19 time: 0.127061 data_time: 0.008493 memory: 1026 2022/10/12 14:30:49 - mmengine - INFO - Epoch(val) [60][300/407] eta: 0:00:13 time: 0.127017 data_time: 0.008561 memory: 1026 2022/10/12 14:30:55 - mmengine - INFO - Epoch(val) [60][350/407] eta: 0:00:07 time: 0.126331 data_time: 0.008574 memory: 1026 2022/10/12 14:31:02 - mmengine - INFO - Epoch(val) [60][400/407] eta: 0:00:00 time: 0.126544 data_time: 0.008204 memory: 1026 2022/10/12 14:31:15 - mmengine - INFO - Evaluating CocoMetric... 2022/10/12 14:31:31 - mmengine - INFO - Epoch(val) [60][407/407] coco/AP: 0.653539 coco/AP .5: 0.866086 coco/AP .75: 0.725264 coco/AP (M): 0.622980 coco/AP (L): 0.711001 coco/AR: 0.726527 coco/AR .5: 0.909635 coco/AR .75: 0.791089 coco/AR (M): 0.680716 coco/AR (L): 0.789409 2022/10/12 14:31:31 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/liqikai/openmmlab/pt112cu113py38/mmpose/work_dirs/20221012/rsn50/best_coco/AP_epoch_50.pth is removed 2022/10/12 14:31:33 - mmengine - INFO - The best checkpoint with 0.6535 coco/AP at 60 epoch is saved to best_coco/AP_epoch_60.pth. 2022/10/12 14:31:50 - mmengine - INFO - Epoch(train) [61][50/586] lr: 5.000000e-03 eta: 7:49:28 time: 0.343002 data_time: 0.055878 memory: 4465 loss_kpt: 92.072992 acc_pose: 0.759267 loss: 92.072992 2022/10/12 14:32:07 - mmengine - INFO - Epoch(train) [61][100/586] lr: 5.000000e-03 eta: 7:49:15 time: 0.338565 data_time: 0.049236 memory: 4465 loss_kpt: 93.289675 acc_pose: 0.760223 loss: 93.289675 2022/10/12 14:32:24 - mmengine - INFO - Epoch(train) [61][150/586] lr: 5.000000e-03 eta: 7:49:02 time: 0.345624 data_time: 0.051324 memory: 4465 loss_kpt: 94.075138 acc_pose: 0.755421 loss: 94.075138 2022/10/12 14:32:42 - mmengine - INFO - Epoch(train) [61][200/586] lr: 5.000000e-03 eta: 7:48:49 time: 0.343358 data_time: 0.054604 memory: 4465 loss_kpt: 92.636316 acc_pose: 0.765252 loss: 92.636316 2022/10/12 14:32:59 - mmengine - INFO - Epoch(train) [61][250/586] lr: 5.000000e-03 eta: 7:48:37 time: 0.356833 data_time: 0.050565 memory: 4465 loss_kpt: 92.613967 acc_pose: 0.720247 loss: 92.613967 2022/10/12 14:33:17 - mmengine - INFO - Epoch(train) [61][300/586] lr: 5.000000e-03 eta: 7:48:25 time: 0.350282 data_time: 0.049543 memory: 4465 loss_kpt: 90.931564 acc_pose: 0.723228 loss: 90.931564 2022/10/12 14:33:34 - mmengine - INFO - Epoch(train) [61][350/586] lr: 5.000000e-03 eta: 7:48:12 time: 0.350951 data_time: 0.050443 memory: 4465 loss_kpt: 92.119361 acc_pose: 0.715127 loss: 92.119361 2022/10/12 14:33:51 - mmengine - INFO - Epoch(train) [61][400/586] lr: 5.000000e-03 eta: 7:47:58 time: 0.338673 data_time: 0.049009 memory: 4465 loss_kpt: 92.723203 acc_pose: 0.714937 loss: 92.723203 2022/10/12 14:34:08 - mmengine - INFO - Epoch(train) [61][450/586] lr: 5.000000e-03 eta: 7:47:45 time: 0.340661 data_time: 0.053970 memory: 4465 loss_kpt: 92.644382 acc_pose: 0.848037 loss: 92.644382 2022/10/12 14:34:25 - mmengine - INFO - Epoch(train) [61][500/586] lr: 5.000000e-03 eta: 7:47:29 time: 0.324633 data_time: 0.048637 memory: 4465 loss_kpt: 93.009613 acc_pose: 0.793922 loss: 93.009613 2022/10/12 14:34:41 - mmengine - INFO - Epoch(train) [61][550/586] lr: 5.000000e-03 eta: 7:47:14 time: 0.330982 data_time: 0.046576 memory: 4465 loss_kpt: 92.896046 acc_pose: 0.755738 loss: 92.896046 2022/10/12 14:34:53 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:35:11 - mmengine - INFO - Epoch(train) [62][50/586] lr: 5.000000e-03 eta: 7:46:23 time: 0.360231 data_time: 0.062254 memory: 4465 loss_kpt: 92.532517 acc_pose: 0.725298 loss: 92.532517 2022/10/12 14:35:28 - mmengine - INFO - Epoch(train) [62][100/586] lr: 5.000000e-03 eta: 7:46:10 time: 0.346348 data_time: 0.046886 memory: 4465 loss_kpt: 91.255816 acc_pose: 0.799619 loss: 91.255816 2022/10/12 14:35:45 - mmengine - INFO - Epoch(train) [62][150/586] lr: 5.000000e-03 eta: 7:45:57 time: 0.344240 data_time: 0.058223 memory: 4465 loss_kpt: 92.451595 acc_pose: 0.847098 loss: 92.451595 2022/10/12 14:36:02 - mmengine - INFO - Epoch(train) [62][200/586] lr: 5.000000e-03 eta: 7:45:43 time: 0.336319 data_time: 0.050777 memory: 4465 loss_kpt: 90.331267 acc_pose: 0.840180 loss: 90.331267 2022/10/12 14:36:20 - mmengine - INFO - Epoch(train) [62][250/586] lr: 5.000000e-03 eta: 7:45:31 time: 0.349231 data_time: 0.055289 memory: 4465 loss_kpt: 91.198969 acc_pose: 0.705694 loss: 91.198969 2022/10/12 14:36:21 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:36:37 - mmengine - INFO - Epoch(train) [62][300/586] lr: 5.000000e-03 eta: 7:45:17 time: 0.338013 data_time: 0.052683 memory: 4465 loss_kpt: 91.451991 acc_pose: 0.710972 loss: 91.451991 2022/10/12 14:36:53 - mmengine - INFO - Epoch(train) [62][350/586] lr: 5.000000e-03 eta: 7:45:02 time: 0.336789 data_time: 0.051153 memory: 4465 loss_kpt: 91.115389 acc_pose: 0.766823 loss: 91.115389 2022/10/12 14:37:11 - mmengine - INFO - Epoch(train) [62][400/586] lr: 5.000000e-03 eta: 7:44:49 time: 0.342057 data_time: 0.055260 memory: 4465 loss_kpt: 92.239441 acc_pose: 0.822601 loss: 92.239441 2022/10/12 14:37:27 - mmengine - INFO - Epoch(train) [62][450/586] lr: 5.000000e-03 eta: 7:44:35 time: 0.336340 data_time: 0.049020 memory: 4465 loss_kpt: 92.556696 acc_pose: 0.735684 loss: 92.556696 2022/10/12 14:37:45 - mmengine - INFO - Epoch(train) [62][500/586] lr: 5.000000e-03 eta: 7:44:22 time: 0.346341 data_time: 0.049930 memory: 4465 loss_kpt: 91.771623 acc_pose: 0.690234 loss: 91.771623 2022/10/12 14:38:02 - mmengine - INFO - Epoch(train) [62][550/586] lr: 5.000000e-03 eta: 7:44:09 time: 0.347231 data_time: 0.049502 memory: 4465 loss_kpt: 92.184165 acc_pose: 0.825059 loss: 92.184165 2022/10/12 14:38:14 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:38:31 - mmengine - INFO - Epoch(train) [63][50/586] lr: 5.000000e-03 eta: 7:43:17 time: 0.350306 data_time: 0.062210 memory: 4465 loss_kpt: 91.757649 acc_pose: 0.795516 loss: 91.757649 2022/10/12 14:38:48 - mmengine - INFO - Epoch(train) [63][100/586] lr: 5.000000e-03 eta: 7:43:02 time: 0.330857 data_time: 0.051567 memory: 4465 loss_kpt: 91.191680 acc_pose: 0.782737 loss: 91.191680 2022/10/12 14:39:05 - mmengine - INFO - Epoch(train) [63][150/586] lr: 5.000000e-03 eta: 7:42:50 time: 0.349461 data_time: 0.058977 memory: 4465 loss_kpt: 91.842793 acc_pose: 0.820662 loss: 91.842793 2022/10/12 14:39:22 - mmengine - INFO - Epoch(train) [63][200/586] lr: 5.000000e-03 eta: 7:42:35 time: 0.335585 data_time: 0.050938 memory: 4465 loss_kpt: 91.910103 acc_pose: 0.754628 loss: 91.910103 2022/10/12 14:39:39 - mmengine - INFO - Epoch(train) [63][250/586] lr: 5.000000e-03 eta: 7:42:21 time: 0.329854 data_time: 0.051802 memory: 4465 loss_kpt: 91.139271 acc_pose: 0.738168 loss: 91.139271 2022/10/12 14:39:56 - mmengine - INFO - Epoch(train) [63][300/586] lr: 5.000000e-03 eta: 7:42:06 time: 0.336273 data_time: 0.047610 memory: 4465 loss_kpt: 90.736193 acc_pose: 0.742782 loss: 90.736193 2022/10/12 14:40:12 - mmengine - INFO - Epoch(train) [63][350/586] lr: 5.000000e-03 eta: 7:41:50 time: 0.322633 data_time: 0.047400 memory: 4465 loss_kpt: 91.313405 acc_pose: 0.743551 loss: 91.313405 2022/10/12 14:40:28 - mmengine - INFO - Epoch(train) [63][400/586] lr: 5.000000e-03 eta: 7:41:35 time: 0.328735 data_time: 0.050061 memory: 4465 loss_kpt: 91.476709 acc_pose: 0.826459 loss: 91.476709 2022/10/12 14:40:45 - mmengine - INFO - Epoch(train) [63][450/586] lr: 5.000000e-03 eta: 7:41:20 time: 0.327546 data_time: 0.049879 memory: 4465 loss_kpt: 91.634814 acc_pose: 0.801748 loss: 91.634814 2022/10/12 14:41:01 - mmengine - INFO - Epoch(train) [63][500/586] lr: 5.000000e-03 eta: 7:41:05 time: 0.324599 data_time: 0.050403 memory: 4465 loss_kpt: 92.604161 acc_pose: 0.778042 loss: 92.604161 2022/10/12 14:41:17 - mmengine - INFO - Epoch(train) [63][550/586] lr: 5.000000e-03 eta: 7:40:48 time: 0.319963 data_time: 0.051145 memory: 4465 loss_kpt: 92.475764 acc_pose: 0.795205 loss: 92.475764 2022/10/12 14:41:28 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:41:46 - mmengine - INFO - Epoch(train) [64][50/586] lr: 5.000000e-03 eta: 7:39:58 time: 0.356061 data_time: 0.064879 memory: 4465 loss_kpt: 92.537062 acc_pose: 0.751524 loss: 92.537062 2022/10/12 14:41:57 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:42:02 - mmengine - INFO - Epoch(train) [64][100/586] lr: 5.000000e-03 eta: 7:39:43 time: 0.331459 data_time: 0.052550 memory: 4465 loss_kpt: 90.637517 acc_pose: 0.712545 loss: 90.637517 2022/10/12 14:42:19 - mmengine - INFO - Epoch(train) [64][150/586] lr: 5.000000e-03 eta: 7:39:29 time: 0.332332 data_time: 0.051558 memory: 4465 loss_kpt: 91.228249 acc_pose: 0.822827 loss: 91.228249 2022/10/12 14:42:36 - mmengine - INFO - Epoch(train) [64][200/586] lr: 5.000000e-03 eta: 7:39:14 time: 0.330812 data_time: 0.054982 memory: 4465 loss_kpt: 90.601424 acc_pose: 0.830154 loss: 90.601424 2022/10/12 14:42:53 - mmengine - INFO - Epoch(train) [64][250/586] lr: 5.000000e-03 eta: 7:39:00 time: 0.339736 data_time: 0.052713 memory: 4465 loss_kpt: 91.879546 acc_pose: 0.760415 loss: 91.879546 2022/10/12 14:43:09 - mmengine - INFO - Epoch(train) [64][300/586] lr: 5.000000e-03 eta: 7:38:44 time: 0.319164 data_time: 0.047870 memory: 4465 loss_kpt: 90.918530 acc_pose: 0.782805 loss: 90.918530 2022/10/12 14:43:25 - mmengine - INFO - Epoch(train) [64][350/586] lr: 5.000000e-03 eta: 7:38:29 time: 0.336684 data_time: 0.052631 memory: 4465 loss_kpt: 92.061524 acc_pose: 0.750517 loss: 92.061524 2022/10/12 14:43:42 - mmengine - INFO - Epoch(train) [64][400/586] lr: 5.000000e-03 eta: 7:38:15 time: 0.331345 data_time: 0.050471 memory: 4465 loss_kpt: 91.181962 acc_pose: 0.800576 loss: 91.181962 2022/10/12 14:43:59 - mmengine - INFO - Epoch(train) [64][450/586] lr: 5.000000e-03 eta: 7:38:00 time: 0.331993 data_time: 0.052235 memory: 4465 loss_kpt: 93.301142 acc_pose: 0.842142 loss: 93.301142 2022/10/12 14:44:15 - mmengine - INFO - Epoch(train) [64][500/586] lr: 5.000000e-03 eta: 7:37:45 time: 0.326207 data_time: 0.052563 memory: 4465 loss_kpt: 92.059496 acc_pose: 0.736777 loss: 92.059496 2022/10/12 14:44:31 - mmengine - INFO - Epoch(train) [64][550/586] lr: 5.000000e-03 eta: 7:37:29 time: 0.323724 data_time: 0.052341 memory: 4465 loss_kpt: 91.919332 acc_pose: 0.778459 loss: 91.919332 2022/10/12 14:44:43 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:45:01 - mmengine - INFO - Epoch(train) [65][50/586] lr: 5.000000e-03 eta: 7:36:40 time: 0.363102 data_time: 0.066188 memory: 4465 loss_kpt: 93.257139 acc_pose: 0.698840 loss: 93.257139 2022/10/12 14:45:18 - mmengine - INFO - Epoch(train) [65][100/586] lr: 5.000000e-03 eta: 7:36:26 time: 0.335993 data_time: 0.048629 memory: 4465 loss_kpt: 91.672867 acc_pose: 0.708079 loss: 91.672867 2022/10/12 14:45:35 - mmengine - INFO - Epoch(train) [65][150/586] lr: 5.000000e-03 eta: 7:36:11 time: 0.335953 data_time: 0.050069 memory: 4465 loss_kpt: 92.710329 acc_pose: 0.771878 loss: 92.710329 2022/10/12 14:45:52 - mmengine - INFO - Epoch(train) [65][200/586] lr: 5.000000e-03 eta: 7:35:57 time: 0.339662 data_time: 0.051770 memory: 4465 loss_kpt: 93.785968 acc_pose: 0.813065 loss: 93.785968 2022/10/12 14:46:09 - mmengine - INFO - Epoch(train) [65][250/586] lr: 5.000000e-03 eta: 7:35:46 time: 0.359025 data_time: 0.051903 memory: 4465 loss_kpt: 90.496645 acc_pose: 0.691735 loss: 90.496645 2022/10/12 14:46:28 - mmengine - INFO - Epoch(train) [65][300/586] lr: 5.000000e-03 eta: 7:35:35 time: 0.364695 data_time: 0.047723 memory: 4465 loss_kpt: 91.367875 acc_pose: 0.769807 loss: 91.367875 2022/10/12 14:46:46 - mmengine - INFO - Epoch(train) [65][350/586] lr: 5.000000e-03 eta: 7:35:23 time: 0.355408 data_time: 0.053336 memory: 4465 loss_kpt: 94.084792 acc_pose: 0.791252 loss: 94.084792 2022/10/12 14:47:03 - mmengine - INFO - Epoch(train) [65][400/586] lr: 5.000000e-03 eta: 7:35:10 time: 0.352891 data_time: 0.050389 memory: 4465 loss_kpt: 91.568349 acc_pose: 0.751690 loss: 91.568349 2022/10/12 14:47:20 - mmengine - INFO - Epoch(train) [65][450/586] lr: 5.000000e-03 eta: 7:34:57 time: 0.345696 data_time: 0.046360 memory: 4465 loss_kpt: 89.958657 acc_pose: 0.836254 loss: 89.958657 2022/10/12 14:47:36 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:47:37 - mmengine - INFO - Epoch(train) [65][500/586] lr: 5.000000e-03 eta: 7:34:43 time: 0.339829 data_time: 0.049693 memory: 4465 loss_kpt: 91.298403 acc_pose: 0.754870 loss: 91.298403 2022/10/12 14:47:55 - mmengine - INFO - Epoch(train) [65][550/586] lr: 5.000000e-03 eta: 7:34:31 time: 0.357025 data_time: 0.053796 memory: 4465 loss_kpt: 91.162630 acc_pose: 0.757151 loss: 91.162630 2022/10/12 14:48:08 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:48:26 - mmengine - INFO - Epoch(train) [66][50/586] lr: 5.000000e-03 eta: 7:33:42 time: 0.356441 data_time: 0.059872 memory: 4465 loss_kpt: 92.924276 acc_pose: 0.758129 loss: 92.924276 2022/10/12 14:48:43 - mmengine - INFO - Epoch(train) [66][100/586] lr: 5.000000e-03 eta: 7:33:28 time: 0.340909 data_time: 0.052856 memory: 4465 loss_kpt: 91.648170 acc_pose: 0.705749 loss: 91.648170 2022/10/12 14:48:59 - mmengine - INFO - Epoch(train) [66][150/586] lr: 5.000000e-03 eta: 7:33:13 time: 0.329555 data_time: 0.050878 memory: 4465 loss_kpt: 92.960747 acc_pose: 0.796527 loss: 92.960747 2022/10/12 14:49:16 - mmengine - INFO - Epoch(train) [66][200/586] lr: 5.000000e-03 eta: 7:32:58 time: 0.329776 data_time: 0.052101 memory: 4465 loss_kpt: 91.157970 acc_pose: 0.797630 loss: 91.157970 2022/10/12 14:49:32 - mmengine - INFO - Epoch(train) [66][250/586] lr: 5.000000e-03 eta: 7:32:43 time: 0.333041 data_time: 0.053079 memory: 4465 loss_kpt: 91.379953 acc_pose: 0.725335 loss: 91.379953 2022/10/12 14:49:48 - mmengine - INFO - Epoch(train) [66][300/586] lr: 5.000000e-03 eta: 7:32:26 time: 0.311169 data_time: 0.055286 memory: 4465 loss_kpt: 91.660924 acc_pose: 0.804158 loss: 91.660924 2022/10/12 14:50:04 - mmengine - INFO - Epoch(train) [66][350/586] lr: 5.000000e-03 eta: 7:32:11 time: 0.328720 data_time: 0.050850 memory: 4465 loss_kpt: 92.677692 acc_pose: 0.759986 loss: 92.677692 2022/10/12 14:50:21 - mmengine - INFO - Epoch(train) [66][400/586] lr: 5.000000e-03 eta: 7:31:55 time: 0.324866 data_time: 0.052113 memory: 4465 loss_kpt: 93.239153 acc_pose: 0.710633 loss: 93.239153 2022/10/12 14:50:36 - mmengine - INFO - Epoch(train) [66][450/586] lr: 5.000000e-03 eta: 7:31:39 time: 0.317300 data_time: 0.048345 memory: 4465 loss_kpt: 92.316948 acc_pose: 0.824517 loss: 92.316948 2022/10/12 14:50:52 - mmengine - INFO - Epoch(train) [66][500/586] lr: 5.000000e-03 eta: 7:31:23 time: 0.315770 data_time: 0.053029 memory: 4465 loss_kpt: 92.789805 acc_pose: 0.749770 loss: 92.789805 2022/10/12 14:51:08 - mmengine - INFO - Epoch(train) [66][550/586] lr: 5.000000e-03 eta: 7:31:06 time: 0.316928 data_time: 0.052485 memory: 4465 loss_kpt: 90.476676 acc_pose: 0.779065 loss: 90.476676 2022/10/12 14:51:20 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:51:38 - mmengine - INFO - Epoch(train) [67][50/586] lr: 5.000000e-03 eta: 7:30:19 time: 0.368765 data_time: 0.063031 memory: 4465 loss_kpt: 90.911249 acc_pose: 0.826684 loss: 90.911249 2022/10/12 14:51:56 - mmengine - INFO - Epoch(train) [67][100/586] lr: 5.000000e-03 eta: 7:30:05 time: 0.345969 data_time: 0.053673 memory: 4465 loss_kpt: 93.609436 acc_pose: 0.816718 loss: 93.609436 2022/10/12 14:52:13 - mmengine - INFO - Epoch(train) [67][150/586] lr: 5.000000e-03 eta: 7:29:52 time: 0.342629 data_time: 0.051952 memory: 4465 loss_kpt: 92.026776 acc_pose: 0.702935 loss: 92.026776 2022/10/12 14:52:30 - mmengine - INFO - Epoch(train) [67][200/586] lr: 5.000000e-03 eta: 7:29:38 time: 0.339917 data_time: 0.052215 memory: 4465 loss_kpt: 92.534017 acc_pose: 0.787368 loss: 92.534017 2022/10/12 14:52:46 - mmengine - INFO - Epoch(train) [67][250/586] lr: 5.000000e-03 eta: 7:29:23 time: 0.332967 data_time: 0.053333 memory: 4465 loss_kpt: 92.119939 acc_pose: 0.799996 loss: 92.119939 2022/10/12 14:53:03 - mmengine - INFO - Epoch(train) [67][300/586] lr: 5.000000e-03 eta: 7:29:09 time: 0.337730 data_time: 0.050546 memory: 4465 loss_kpt: 92.586864 acc_pose: 0.895043 loss: 92.586864 2022/10/12 14:53:11 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:53:20 - mmengine - INFO - Epoch(train) [67][350/586] lr: 5.000000e-03 eta: 7:28:54 time: 0.327346 data_time: 0.051206 memory: 4465 loss_kpt: 91.362488 acc_pose: 0.762398 loss: 91.362488 2022/10/12 14:53:36 - mmengine - INFO - Epoch(train) [67][400/586] lr: 5.000000e-03 eta: 7:28:39 time: 0.334263 data_time: 0.048421 memory: 4465 loss_kpt: 91.477452 acc_pose: 0.808144 loss: 91.477452 2022/10/12 14:53:54 - mmengine - INFO - Epoch(train) [67][450/586] lr: 5.000000e-03 eta: 7:28:26 time: 0.349672 data_time: 0.051664 memory: 4465 loss_kpt: 91.281663 acc_pose: 0.847117 loss: 91.281663 2022/10/12 14:54:11 - mmengine - INFO - Epoch(train) [67][500/586] lr: 5.000000e-03 eta: 7:28:13 time: 0.350845 data_time: 0.056993 memory: 4465 loss_kpt: 91.350349 acc_pose: 0.798848 loss: 91.350349 2022/10/12 14:54:29 - mmengine - INFO - Epoch(train) [67][550/586] lr: 5.000000e-03 eta: 7:28:01 time: 0.356425 data_time: 0.048276 memory: 4465 loss_kpt: 91.124946 acc_pose: 0.723605 loss: 91.124946 2022/10/12 14:54:41 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:54:58 - mmengine - INFO - Epoch(train) [68][50/586] lr: 5.000000e-03 eta: 7:27:12 time: 0.347794 data_time: 0.064078 memory: 4465 loss_kpt: 91.350334 acc_pose: 0.757004 loss: 91.350334 2022/10/12 14:55:15 - mmengine - INFO - Epoch(train) [68][100/586] lr: 5.000000e-03 eta: 7:26:57 time: 0.332392 data_time: 0.050300 memory: 4465 loss_kpt: 91.891050 acc_pose: 0.719452 loss: 91.891050 2022/10/12 14:55:31 - mmengine - INFO - Epoch(train) [68][150/586] lr: 5.000000e-03 eta: 7:26:42 time: 0.326317 data_time: 0.050856 memory: 4465 loss_kpt: 92.264820 acc_pose: 0.803566 loss: 92.264820 2022/10/12 14:55:48 - mmengine - INFO - Epoch(train) [68][200/586] lr: 5.000000e-03 eta: 7:26:27 time: 0.334744 data_time: 0.046818 memory: 4465 loss_kpt: 89.979465 acc_pose: 0.834366 loss: 89.979465 2022/10/12 14:56:05 - mmengine - INFO - Epoch(train) [68][250/586] lr: 5.000000e-03 eta: 7:26:13 time: 0.336993 data_time: 0.049578 memory: 4465 loss_kpt: 92.805674 acc_pose: 0.780339 loss: 92.805674 2022/10/12 14:56:21 - mmengine - INFO - Epoch(train) [68][300/586] lr: 5.000000e-03 eta: 7:25:57 time: 0.322469 data_time: 0.051770 memory: 4465 loss_kpt: 92.310105 acc_pose: 0.783961 loss: 92.310105 2022/10/12 14:56:37 - mmengine - INFO - Epoch(train) [68][350/586] lr: 5.000000e-03 eta: 7:25:42 time: 0.323394 data_time: 0.046750 memory: 4465 loss_kpt: 92.836052 acc_pose: 0.701422 loss: 92.836052 2022/10/12 14:56:53 - mmengine - INFO - Epoch(train) [68][400/586] lr: 5.000000e-03 eta: 7:25:25 time: 0.320121 data_time: 0.048819 memory: 4465 loss_kpt: 92.054621 acc_pose: 0.826762 loss: 92.054621 2022/10/12 14:57:09 - mmengine - INFO - Epoch(train) [68][450/586] lr: 5.000000e-03 eta: 7:25:10 time: 0.322565 data_time: 0.046215 memory: 4465 loss_kpt: 91.517633 acc_pose: 0.729608 loss: 91.517633 2022/10/12 14:57:26 - mmengine - INFO - Epoch(train) [68][500/586] lr: 5.000000e-03 eta: 7:24:55 time: 0.328942 data_time: 0.049763 memory: 4465 loss_kpt: 91.722547 acc_pose: 0.784660 loss: 91.722547 2022/10/12 14:57:42 - mmengine - INFO - Epoch(train) [68][550/586] lr: 5.000000e-03 eta: 7:24:38 time: 0.312154 data_time: 0.046694 memory: 4465 loss_kpt: 91.989766 acc_pose: 0.805188 loss: 91.989766 2022/10/12 14:57:53 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:58:11 - mmengine - INFO - Epoch(train) [69][50/586] lr: 5.000000e-03 eta: 7:23:51 time: 0.365346 data_time: 0.066517 memory: 4465 loss_kpt: 91.101037 acc_pose: 0.751485 loss: 91.101037 2022/10/12 14:58:28 - mmengine - INFO - Epoch(train) [69][100/586] lr: 5.000000e-03 eta: 7:23:37 time: 0.340164 data_time: 0.052940 memory: 4465 loss_kpt: 90.536764 acc_pose: 0.775608 loss: 90.536764 2022/10/12 14:58:45 - mmengine - INFO - Epoch(train) [69][150/586] lr: 5.000000e-03 eta: 7:23:23 time: 0.341859 data_time: 0.055791 memory: 4465 loss_kpt: 91.682527 acc_pose: 0.740067 loss: 91.682527 2022/10/12 14:58:46 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 14:59:02 - mmengine - INFO - Epoch(train) [69][200/586] lr: 5.000000e-03 eta: 7:23:09 time: 0.336313 data_time: 0.047014 memory: 4465 loss_kpt: 90.233042 acc_pose: 0.775660 loss: 90.233042 2022/10/12 14:59:19 - mmengine - INFO - Epoch(train) [69][250/586] lr: 5.000000e-03 eta: 7:22:54 time: 0.334545 data_time: 0.046399 memory: 4465 loss_kpt: 89.914876 acc_pose: 0.729053 loss: 89.914876 2022/10/12 14:59:35 - mmengine - INFO - Epoch(train) [69][300/586] lr: 5.000000e-03 eta: 7:22:38 time: 0.322780 data_time: 0.050157 memory: 4465 loss_kpt: 91.178434 acc_pose: 0.701587 loss: 91.178434 2022/10/12 14:59:51 - mmengine - INFO - Epoch(train) [69][350/586] lr: 5.000000e-03 eta: 7:22:22 time: 0.321529 data_time: 0.050829 memory: 4465 loss_kpt: 91.121455 acc_pose: 0.730802 loss: 91.121455 2022/10/12 15:00:07 - mmengine - INFO - Epoch(train) [69][400/586] lr: 5.000000e-03 eta: 7:22:07 time: 0.322586 data_time: 0.048618 memory: 4465 loss_kpt: 92.486783 acc_pose: 0.678349 loss: 92.486783 2022/10/12 15:00:24 - mmengine - INFO - Epoch(train) [69][450/586] lr: 5.000000e-03 eta: 7:21:52 time: 0.332720 data_time: 0.051463 memory: 4465 loss_kpt: 90.900229 acc_pose: 0.851138 loss: 90.900229 2022/10/12 15:00:41 - mmengine - INFO - Epoch(train) [69][500/586] lr: 5.000000e-03 eta: 7:21:37 time: 0.333918 data_time: 0.049613 memory: 4465 loss_kpt: 91.883254 acc_pose: 0.774767 loss: 91.883254 2022/10/12 15:00:57 - mmengine - INFO - Epoch(train) [69][550/586] lr: 5.000000e-03 eta: 7:21:22 time: 0.326616 data_time: 0.047500 memory: 4465 loss_kpt: 89.412304 acc_pose: 0.725548 loss: 89.412304 2022/10/12 15:01:09 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:01:26 - mmengine - INFO - Epoch(train) [70][50/586] lr: 5.000000e-03 eta: 7:20:34 time: 0.349997 data_time: 0.064458 memory: 4465 loss_kpt: 91.888364 acc_pose: 0.790201 loss: 91.888364 2022/10/12 15:01:44 - mmengine - INFO - Epoch(train) [70][100/586] lr: 5.000000e-03 eta: 7:20:21 time: 0.346352 data_time: 0.050138 memory: 4465 loss_kpt: 91.404342 acc_pose: 0.774295 loss: 91.404342 2022/10/12 15:02:01 - mmengine - INFO - Epoch(train) [70][150/586] lr: 5.000000e-03 eta: 7:20:08 time: 0.350630 data_time: 0.053186 memory: 4465 loss_kpt: 91.407822 acc_pose: 0.695676 loss: 91.407822 2022/10/12 15:02:19 - mmengine - INFO - Epoch(train) [70][200/586] lr: 5.000000e-03 eta: 7:19:55 time: 0.350971 data_time: 0.050363 memory: 4465 loss_kpt: 90.534427 acc_pose: 0.783195 loss: 90.534427 2022/10/12 15:02:36 - mmengine - INFO - Epoch(train) [70][250/586] lr: 5.000000e-03 eta: 7:19:41 time: 0.344736 data_time: 0.051425 memory: 4465 loss_kpt: 90.216617 acc_pose: 0.800779 loss: 90.216617 2022/10/12 15:02:53 - mmengine - INFO - Epoch(train) [70][300/586] lr: 5.000000e-03 eta: 7:19:27 time: 0.333422 data_time: 0.052235 memory: 4465 loss_kpt: 92.088984 acc_pose: 0.790059 loss: 92.088984 2022/10/12 15:03:09 - mmengine - INFO - Epoch(train) [70][350/586] lr: 5.000000e-03 eta: 7:19:12 time: 0.334427 data_time: 0.051990 memory: 4465 loss_kpt: 90.384473 acc_pose: 0.808645 loss: 90.384473 2022/10/12 15:03:26 - mmengine - INFO - Epoch(train) [70][400/586] lr: 5.000000e-03 eta: 7:18:57 time: 0.333458 data_time: 0.047195 memory: 4465 loss_kpt: 91.344926 acc_pose: 0.793129 loss: 91.344926 2022/10/12 15:03:43 - mmengine - INFO - Epoch(train) [70][450/586] lr: 5.000000e-03 eta: 7:18:43 time: 0.335428 data_time: 0.050534 memory: 4465 loss_kpt: 91.040293 acc_pose: 0.698823 loss: 91.040293 2022/10/12 15:03:59 - mmengine - INFO - Epoch(train) [70][500/586] lr: 5.000000e-03 eta: 7:18:28 time: 0.330070 data_time: 0.049823 memory: 4465 loss_kpt: 92.097897 acc_pose: 0.797010 loss: 92.097897 2022/10/12 15:04:17 - mmengine - INFO - Epoch(train) [70][550/586] lr: 5.000000e-03 eta: 7:18:14 time: 0.345808 data_time: 0.045641 memory: 4465 loss_kpt: 92.185122 acc_pose: 0.766211 loss: 92.185122 2022/10/12 15:04:22 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:04:29 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:04:29 - mmengine - INFO - Saving checkpoint at 70 epochs 2022/10/12 15:04:38 - mmengine - INFO - Epoch(val) [70][50/407] eta: 0:00:47 time: 0.132043 data_time: 0.012706 memory: 4465 2022/10/12 15:04:44 - mmengine - INFO - Epoch(val) [70][100/407] eta: 0:00:40 time: 0.132565 data_time: 0.008572 memory: 1026 2022/10/12 15:04:51 - mmengine - INFO - Epoch(val) [70][150/407] eta: 0:00:32 time: 0.126553 data_time: 0.008156 memory: 1026 2022/10/12 15:04:57 - mmengine - INFO - Epoch(val) [70][200/407] eta: 0:00:26 time: 0.126644 data_time: 0.008778 memory: 1026 2022/10/12 15:05:03 - mmengine - INFO - Epoch(val) [70][250/407] eta: 0:00:19 time: 0.127349 data_time: 0.008095 memory: 1026 2022/10/12 15:05:10 - mmengine - INFO - Epoch(val) [70][300/407] eta: 0:00:13 time: 0.125919 data_time: 0.008297 memory: 1026 2022/10/12 15:05:16 - mmengine - INFO - Epoch(val) [70][350/407] eta: 0:00:07 time: 0.125713 data_time: 0.008039 memory: 1026 2022/10/12 15:05:22 - mmengine - INFO - Epoch(val) [70][400/407] eta: 0:00:00 time: 0.125111 data_time: 0.008234 memory: 1026 2022/10/12 15:05:36 - mmengine - INFO - Evaluating CocoMetric... 2022/10/12 15:05:52 - mmengine - INFO - Epoch(val) [70][407/407] coco/AP: 0.670989 coco/AP .5: 0.873712 coco/AP .75: 0.744575 coco/AP (M): 0.641605 coco/AP (L): 0.727647 coco/AR: 0.741247 coco/AR .5: 0.916404 coco/AR .75: 0.804471 coco/AR (M): 0.696750 coco/AR (L): 0.802378 2022/10/12 15:05:52 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/liqikai/openmmlab/pt112cu113py38/mmpose/work_dirs/20221012/rsn50/best_coco/AP_epoch_60.pth is removed 2022/10/12 15:05:54 - mmengine - INFO - The best checkpoint with 0.6710 coco/AP at 70 epoch is saved to best_coco/AP_epoch_70.pth. 2022/10/12 15:06:11 - mmengine - INFO - Epoch(train) [71][50/586] lr: 5.000000e-03 eta: 7:17:27 time: 0.354941 data_time: 0.058427 memory: 4465 loss_kpt: 91.388476 acc_pose: 0.789337 loss: 91.388476 2022/10/12 15:06:29 - mmengine - INFO - Epoch(train) [71][100/586] lr: 5.000000e-03 eta: 7:17:13 time: 0.343618 data_time: 0.047450 memory: 4465 loss_kpt: 90.645305 acc_pose: 0.768130 loss: 90.645305 2022/10/12 15:06:46 - mmengine - INFO - Epoch(train) [71][150/586] lr: 5.000000e-03 eta: 7:17:00 time: 0.345292 data_time: 0.052002 memory: 4465 loss_kpt: 91.287533 acc_pose: 0.824188 loss: 91.287533 2022/10/12 15:07:03 - mmengine - INFO - Epoch(train) [71][200/586] lr: 5.000000e-03 eta: 7:16:46 time: 0.339909 data_time: 0.049213 memory: 4465 loss_kpt: 90.055886 acc_pose: 0.728654 loss: 90.055886 2022/10/12 15:07:20 - mmengine - INFO - Epoch(train) [71][250/586] lr: 5.000000e-03 eta: 7:16:32 time: 0.346122 data_time: 0.048447 memory: 4465 loss_kpt: 90.076559 acc_pose: 0.803969 loss: 90.076559 2022/10/12 15:07:38 - mmengine - INFO - Epoch(train) [71][300/586] lr: 5.000000e-03 eta: 7:16:19 time: 0.347552 data_time: 0.050369 memory: 4465 loss_kpt: 89.836470 acc_pose: 0.708023 loss: 89.836470 2022/10/12 15:07:55 - mmengine - INFO - Epoch(train) [71][350/586] lr: 5.000000e-03 eta: 7:16:05 time: 0.339628 data_time: 0.053256 memory: 4465 loss_kpt: 90.476910 acc_pose: 0.734120 loss: 90.476910 2022/10/12 15:08:11 - mmengine - INFO - Epoch(train) [71][400/586] lr: 5.000000e-03 eta: 7:15:51 time: 0.335504 data_time: 0.056840 memory: 4465 loss_kpt: 89.885005 acc_pose: 0.805983 loss: 89.885005 2022/10/12 15:08:28 - mmengine - INFO - Epoch(train) [71][450/586] lr: 5.000000e-03 eta: 7:15:36 time: 0.330585 data_time: 0.052028 memory: 4465 loss_kpt: 89.975088 acc_pose: 0.780755 loss: 89.975088 2022/10/12 15:08:45 - mmengine - INFO - Epoch(train) [71][500/586] lr: 5.000000e-03 eta: 7:15:21 time: 0.332372 data_time: 0.052303 memory: 4465 loss_kpt: 93.756268 acc_pose: 0.777356 loss: 93.756268 2022/10/12 15:09:01 - mmengine - INFO - Epoch(train) [71][550/586] lr: 5.000000e-03 eta: 7:15:06 time: 0.334701 data_time: 0.055031 memory: 4465 loss_kpt: 91.054938 acc_pose: 0.796364 loss: 91.054938 2022/10/12 15:09:13 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:09:31 - mmengine - INFO - Epoch(train) [72][50/586] lr: 5.000000e-03 eta: 7:14:19 time: 0.353230 data_time: 0.061725 memory: 4465 loss_kpt: 90.717113 acc_pose: 0.767877 loss: 90.717113 2022/10/12 15:09:48 - mmengine - INFO - Epoch(train) [72][100/586] lr: 5.000000e-03 eta: 7:14:06 time: 0.353218 data_time: 0.058557 memory: 4465 loss_kpt: 90.859292 acc_pose: 0.788061 loss: 90.859292 2022/10/12 15:10:07 - mmengine - INFO - Epoch(train) [72][150/586] lr: 5.000000e-03 eta: 7:13:55 time: 0.363446 data_time: 0.056421 memory: 4465 loss_kpt: 90.942131 acc_pose: 0.806471 loss: 90.942131 2022/10/12 15:10:24 - mmengine - INFO - Epoch(train) [72][200/586] lr: 5.000000e-03 eta: 7:13:42 time: 0.351097 data_time: 0.055307 memory: 4465 loss_kpt: 91.017810 acc_pose: 0.753257 loss: 91.017810 2022/10/12 15:10:42 - mmengine - INFO - Epoch(train) [72][250/586] lr: 5.000000e-03 eta: 7:13:30 time: 0.362925 data_time: 0.053136 memory: 4465 loss_kpt: 91.193121 acc_pose: 0.816535 loss: 91.193121 2022/10/12 15:11:00 - mmengine - INFO - Epoch(train) [72][300/586] lr: 5.000000e-03 eta: 7:13:16 time: 0.344187 data_time: 0.053903 memory: 4465 loss_kpt: 89.607171 acc_pose: 0.805641 loss: 89.607171 2022/10/12 15:11:17 - mmengine - INFO - Epoch(train) [72][350/586] lr: 5.000000e-03 eta: 7:13:04 time: 0.356916 data_time: 0.052263 memory: 4465 loss_kpt: 90.491229 acc_pose: 0.852578 loss: 90.491229 2022/10/12 15:11:33 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:11:35 - mmengine - INFO - Epoch(train) [72][400/586] lr: 5.000000e-03 eta: 7:12:51 time: 0.357281 data_time: 0.056899 memory: 4465 loss_kpt: 91.444022 acc_pose: 0.775074 loss: 91.444022 2022/10/12 15:11:53 - mmengine - INFO - Epoch(train) [72][450/586] lr: 5.000000e-03 eta: 7:12:38 time: 0.347059 data_time: 0.053353 memory: 4465 loss_kpt: 90.455815 acc_pose: 0.805256 loss: 90.455815 2022/10/12 15:12:10 - mmengine - INFO - Epoch(train) [72][500/586] lr: 5.000000e-03 eta: 7:12:25 time: 0.352808 data_time: 0.056350 memory: 4465 loss_kpt: 92.098900 acc_pose: 0.849510 loss: 92.098900 2022/10/12 15:12:27 - mmengine - INFO - Epoch(train) [72][550/586] lr: 5.000000e-03 eta: 7:12:10 time: 0.337943 data_time: 0.052422 memory: 4465 loss_kpt: 91.840001 acc_pose: 0.695959 loss: 91.840001 2022/10/12 15:12:39 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:12:56 - mmengine - INFO - Epoch(train) [73][50/586] lr: 5.000000e-03 eta: 7:11:24 time: 0.351732 data_time: 0.059120 memory: 4465 loss_kpt: 90.656664 acc_pose: 0.744762 loss: 90.656664 2022/10/12 15:13:13 - mmengine - INFO - Epoch(train) [73][100/586] lr: 5.000000e-03 eta: 7:11:09 time: 0.337400 data_time: 0.051890 memory: 4465 loss_kpt: 90.599433 acc_pose: 0.800094 loss: 90.599433 2022/10/12 15:13:30 - mmengine - INFO - Epoch(train) [73][150/586] lr: 5.000000e-03 eta: 7:10:54 time: 0.328949 data_time: 0.050625 memory: 4465 loss_kpt: 93.033817 acc_pose: 0.851436 loss: 93.033817 2022/10/12 15:13:47 - mmengine - INFO - Epoch(train) [73][200/586] lr: 5.000000e-03 eta: 7:10:40 time: 0.339949 data_time: 0.051372 memory: 4465 loss_kpt: 90.807229 acc_pose: 0.755896 loss: 90.807229 2022/10/12 15:14:04 - mmengine - INFO - Epoch(train) [73][250/586] lr: 5.000000e-03 eta: 7:10:26 time: 0.346574 data_time: 0.055099 memory: 4465 loss_kpt: 90.391115 acc_pose: 0.765341 loss: 90.391115 2022/10/12 15:14:21 - mmengine - INFO - Epoch(train) [73][300/586] lr: 5.000000e-03 eta: 7:10:12 time: 0.338510 data_time: 0.050517 memory: 4465 loss_kpt: 91.725994 acc_pose: 0.771148 loss: 91.725994 2022/10/12 15:14:38 - mmengine - INFO - Epoch(train) [73][350/586] lr: 5.000000e-03 eta: 7:09:58 time: 0.337200 data_time: 0.049286 memory: 4465 loss_kpt: 91.414504 acc_pose: 0.753756 loss: 91.414504 2022/10/12 15:14:55 - mmengine - INFO - Epoch(train) [73][400/586] lr: 5.000000e-03 eta: 7:09:43 time: 0.335491 data_time: 0.047952 memory: 4465 loss_kpt: 90.915981 acc_pose: 0.808325 loss: 90.915981 2022/10/12 15:15:11 - mmengine - INFO - Epoch(train) [73][450/586] lr: 5.000000e-03 eta: 7:09:28 time: 0.329609 data_time: 0.052210 memory: 4465 loss_kpt: 91.282190 acc_pose: 0.794738 loss: 91.282190 2022/10/12 15:15:28 - mmengine - INFO - Epoch(train) [73][500/586] lr: 5.000000e-03 eta: 7:09:13 time: 0.335914 data_time: 0.055713 memory: 4465 loss_kpt: 91.913350 acc_pose: 0.811677 loss: 91.913350 2022/10/12 15:15:45 - mmengine - INFO - Epoch(train) [73][550/586] lr: 5.000000e-03 eta: 7:08:58 time: 0.331382 data_time: 0.053363 memory: 4465 loss_kpt: 90.346373 acc_pose: 0.768197 loss: 90.346373 2022/10/12 15:15:56 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:16:14 - mmengine - INFO - Epoch(train) [74][50/586] lr: 5.000000e-03 eta: 7:08:13 time: 0.359440 data_time: 0.066764 memory: 4465 loss_kpt: 90.496120 acc_pose: 0.692971 loss: 90.496120 2022/10/12 15:16:31 - mmengine - INFO - Epoch(train) [74][100/586] lr: 5.000000e-03 eta: 7:07:58 time: 0.330585 data_time: 0.051373 memory: 4465 loss_kpt: 91.584455 acc_pose: 0.780720 loss: 91.584455 2022/10/12 15:16:48 - mmengine - INFO - Epoch(train) [74][150/586] lr: 5.000000e-03 eta: 7:07:44 time: 0.346061 data_time: 0.055996 memory: 4465 loss_kpt: 91.121317 acc_pose: 0.795186 loss: 91.121317 2022/10/12 15:17:06 - mmengine - INFO - Epoch(train) [74][200/586] lr: 5.000000e-03 eta: 7:07:31 time: 0.353746 data_time: 0.052921 memory: 4465 loss_kpt: 89.523332 acc_pose: 0.767385 loss: 89.523332 2022/10/12 15:17:14 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:17:25 - mmengine - INFO - Epoch(train) [74][250/586] lr: 5.000000e-03 eta: 7:07:20 time: 0.373438 data_time: 0.054549 memory: 4465 loss_kpt: 90.549705 acc_pose: 0.724628 loss: 90.549705 2022/10/12 15:17:43 - mmengine - INFO - Epoch(train) [74][300/586] lr: 5.000000e-03 eta: 7:07:08 time: 0.361337 data_time: 0.054030 memory: 4465 loss_kpt: 92.618071 acc_pose: 0.779899 loss: 92.618071 2022/10/12 15:18:01 - mmengine - INFO - Epoch(train) [74][350/586] lr: 5.000000e-03 eta: 7:06:56 time: 0.362226 data_time: 0.056918 memory: 4465 loss_kpt: 91.519548 acc_pose: 0.751259 loss: 91.519548 2022/10/12 15:18:18 - mmengine - INFO - Epoch(train) [74][400/586] lr: 5.000000e-03 eta: 7:06:43 time: 0.353942 data_time: 0.051645 memory: 4465 loss_kpt: 91.625288 acc_pose: 0.791010 loss: 91.625288 2022/10/12 15:18:35 - mmengine - INFO - Epoch(train) [74][450/586] lr: 5.000000e-03 eta: 7:06:29 time: 0.340143 data_time: 0.055161 memory: 4465 loss_kpt: 91.274207 acc_pose: 0.759121 loss: 91.274207 2022/10/12 15:18:53 - mmengine - INFO - Epoch(train) [74][500/586] lr: 5.000000e-03 eta: 7:06:15 time: 0.343836 data_time: 0.049121 memory: 4465 loss_kpt: 88.800295 acc_pose: 0.838248 loss: 88.800295 2022/10/12 15:19:11 - mmengine - INFO - Epoch(train) [74][550/586] lr: 5.000000e-03 eta: 7:06:03 time: 0.362304 data_time: 0.049831 memory: 4465 loss_kpt: 90.155347 acc_pose: 0.787595 loss: 90.155347 2022/10/12 15:19:23 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:19:41 - mmengine - INFO - Epoch(train) [75][50/586] lr: 5.000000e-03 eta: 7:05:16 time: 0.347106 data_time: 0.063664 memory: 4465 loss_kpt: 91.801064 acc_pose: 0.829716 loss: 91.801064 2022/10/12 15:19:57 - mmengine - INFO - Epoch(train) [75][100/586] lr: 5.000000e-03 eta: 7:05:01 time: 0.326136 data_time: 0.047914 memory: 4465 loss_kpt: 90.091255 acc_pose: 0.796779 loss: 90.091255 2022/10/12 15:20:14 - mmengine - INFO - Epoch(train) [75][150/586] lr: 5.000000e-03 eta: 7:04:46 time: 0.336691 data_time: 0.047843 memory: 4465 loss_kpt: 89.954499 acc_pose: 0.782147 loss: 89.954499 2022/10/12 15:20:31 - mmengine - INFO - Epoch(train) [75][200/586] lr: 5.000000e-03 eta: 7:04:32 time: 0.336280 data_time: 0.045618 memory: 4465 loss_kpt: 90.121714 acc_pose: 0.842214 loss: 90.121714 2022/10/12 15:20:47 - mmengine - INFO - Epoch(train) [75][250/586] lr: 5.000000e-03 eta: 7:04:16 time: 0.324767 data_time: 0.050594 memory: 4465 loss_kpt: 91.900161 acc_pose: 0.726197 loss: 91.900161 2022/10/12 15:21:04 - mmengine - INFO - Epoch(train) [75][300/586] lr: 5.000000e-03 eta: 7:04:02 time: 0.337472 data_time: 0.051022 memory: 4465 loss_kpt: 90.417339 acc_pose: 0.741709 loss: 90.417339 2022/10/12 15:21:20 - mmengine - INFO - Epoch(train) [75][350/586] lr: 5.000000e-03 eta: 7:03:46 time: 0.323123 data_time: 0.046803 memory: 4465 loss_kpt: 91.151911 acc_pose: 0.789532 loss: 91.151911 2022/10/12 15:21:37 - mmengine - INFO - Epoch(train) [75][400/586] lr: 5.000000e-03 eta: 7:03:31 time: 0.331781 data_time: 0.051802 memory: 4465 loss_kpt: 92.414406 acc_pose: 0.808285 loss: 92.414406 2022/10/12 15:21:53 - mmengine - INFO - Epoch(train) [75][450/586] lr: 5.000000e-03 eta: 7:03:16 time: 0.329522 data_time: 0.048795 memory: 4465 loss_kpt: 92.346580 acc_pose: 0.847633 loss: 92.346580 2022/10/12 15:22:10 - mmengine - INFO - Epoch(train) [75][500/586] lr: 5.000000e-03 eta: 7:03:01 time: 0.329186 data_time: 0.052486 memory: 4465 loss_kpt: 90.806109 acc_pose: 0.748537 loss: 90.806109 2022/10/12 15:22:26 - mmengine - INFO - Epoch(train) [75][550/586] lr: 5.000000e-03 eta: 7:02:45 time: 0.329135 data_time: 0.047706 memory: 4465 loss_kpt: 91.209982 acc_pose: 0.810058 loss: 91.209982 2022/10/12 15:22:38 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:22:55 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:22:55 - mmengine - INFO - Epoch(train) [76][50/586] lr: 5.000000e-03 eta: 7:01:59 time: 0.346338 data_time: 0.057814 memory: 4465 loss_kpt: 90.439656 acc_pose: 0.784983 loss: 90.439656 2022/10/12 15:23:12 - mmengine - INFO - Epoch(train) [76][100/586] lr: 5.000000e-03 eta: 7:01:44 time: 0.328456 data_time: 0.050772 memory: 4465 loss_kpt: 90.725459 acc_pose: 0.813109 loss: 90.725459 2022/10/12 15:23:28 - mmengine - INFO - Epoch(train) [76][150/586] lr: 5.000000e-03 eta: 7:01:28 time: 0.324196 data_time: 0.050718 memory: 4465 loss_kpt: 90.350049 acc_pose: 0.742072 loss: 90.350049 2022/10/12 15:23:44 - mmengine - INFO - Epoch(train) [76][200/586] lr: 5.000000e-03 eta: 7:01:13 time: 0.326017 data_time: 0.050216 memory: 4465 loss_kpt: 91.271650 acc_pose: 0.827349 loss: 91.271650 2022/10/12 15:24:00 - mmengine - INFO - Epoch(train) [76][250/586] lr: 5.000000e-03 eta: 7:00:57 time: 0.321087 data_time: 0.049639 memory: 4465 loss_kpt: 91.413962 acc_pose: 0.837497 loss: 91.413962 2022/10/12 15:24:17 - mmengine - INFO - Epoch(train) [76][300/586] lr: 5.000000e-03 eta: 7:00:42 time: 0.329560 data_time: 0.055529 memory: 4465 loss_kpt: 90.744592 acc_pose: 0.762574 loss: 90.744592 2022/10/12 15:24:33 - mmengine - INFO - Epoch(train) [76][350/586] lr: 5.000000e-03 eta: 7:00:26 time: 0.324481 data_time: 0.052333 memory: 4465 loss_kpt: 91.359236 acc_pose: 0.728296 loss: 91.359236 2022/10/12 15:24:49 - mmengine - INFO - Epoch(train) [76][400/586] lr: 5.000000e-03 eta: 7:00:11 time: 0.329963 data_time: 0.057895 memory: 4465 loss_kpt: 91.043509 acc_pose: 0.710137 loss: 91.043509 2022/10/12 15:25:07 - mmengine - INFO - Epoch(train) [76][450/586] lr: 5.000000e-03 eta: 6:59:57 time: 0.341845 data_time: 0.057743 memory: 4465 loss_kpt: 90.957965 acc_pose: 0.781677 loss: 90.957965 2022/10/12 15:25:23 - mmengine - INFO - Epoch(train) [76][500/586] lr: 5.000000e-03 eta: 6:59:42 time: 0.337596 data_time: 0.056196 memory: 4465 loss_kpt: 90.884319 acc_pose: 0.827900 loss: 90.884319 2022/10/12 15:25:40 - mmengine - INFO - Epoch(train) [76][550/586] lr: 5.000000e-03 eta: 6:59:28 time: 0.340986 data_time: 0.059236 memory: 4465 loss_kpt: 89.965323 acc_pose: 0.791267 loss: 89.965323 2022/10/12 15:25:52 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:26:11 - mmengine - INFO - Epoch(train) [77][50/586] lr: 5.000000e-03 eta: 6:58:45 time: 0.372855 data_time: 0.071054 memory: 4465 loss_kpt: 90.377909 acc_pose: 0.761681 loss: 90.377909 2022/10/12 15:26:29 - mmengine - INFO - Epoch(train) [77][100/586] lr: 5.000000e-03 eta: 6:58:32 time: 0.358445 data_time: 0.048769 memory: 4465 loss_kpt: 91.365688 acc_pose: 0.803412 loss: 91.365688 2022/10/12 15:26:46 - mmengine - INFO - Epoch(train) [77][150/586] lr: 5.000000e-03 eta: 6:58:19 time: 0.355891 data_time: 0.057600 memory: 4465 loss_kpt: 90.826510 acc_pose: 0.753386 loss: 90.826510 2022/10/12 15:27:04 - mmengine - INFO - Epoch(train) [77][200/586] lr: 5.000000e-03 eta: 6:58:06 time: 0.353600 data_time: 0.051589 memory: 4465 loss_kpt: 91.454022 acc_pose: 0.807850 loss: 91.454022 2022/10/12 15:27:21 - mmengine - INFO - Epoch(train) [77][250/586] lr: 5.000000e-03 eta: 6:57:53 time: 0.347484 data_time: 0.051198 memory: 4465 loss_kpt: 91.869069 acc_pose: 0.703363 loss: 91.869069 2022/10/12 15:27:39 - mmengine - INFO - Epoch(train) [77][300/586] lr: 5.000000e-03 eta: 6:57:40 time: 0.358588 data_time: 0.051564 memory: 4465 loss_kpt: 91.388097 acc_pose: 0.800336 loss: 91.388097 2022/10/12 15:27:56 - mmengine - INFO - Epoch(train) [77][350/586] lr: 5.000000e-03 eta: 6:57:26 time: 0.340399 data_time: 0.052656 memory: 4465 loss_kpt: 90.561735 acc_pose: 0.822012 loss: 90.561735 2022/10/12 15:28:13 - mmengine - INFO - Epoch(train) [77][400/586] lr: 5.000000e-03 eta: 6:57:11 time: 0.332352 data_time: 0.050281 memory: 4465 loss_kpt: 91.614197 acc_pose: 0.783866 loss: 91.614197 2022/10/12 15:28:30 - mmengine - INFO - Epoch(train) [77][450/586] lr: 5.000000e-03 eta: 6:56:56 time: 0.333238 data_time: 0.057906 memory: 4465 loss_kpt: 90.216540 acc_pose: 0.727488 loss: 90.216540 2022/10/12 15:28:35 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:28:46 - mmengine - INFO - Epoch(train) [77][500/586] lr: 5.000000e-03 eta: 6:56:41 time: 0.336816 data_time: 0.054051 memory: 4465 loss_kpt: 91.197917 acc_pose: 0.765399 loss: 91.197917 2022/10/12 15:29:03 - mmengine - INFO - Epoch(train) [77][550/586] lr: 5.000000e-03 eta: 6:56:26 time: 0.332872 data_time: 0.055228 memory: 4465 loss_kpt: 89.045533 acc_pose: 0.829422 loss: 89.045533 2022/10/12 15:29:15 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:29:32 - mmengine - INFO - Epoch(train) [78][50/586] lr: 5.000000e-03 eta: 6:55:41 time: 0.345020 data_time: 0.062619 memory: 4465 loss_kpt: 89.779316 acc_pose: 0.799673 loss: 89.779316 2022/10/12 15:29:50 - mmengine - INFO - Epoch(train) [78][100/586] lr: 5.000000e-03 eta: 6:55:27 time: 0.345163 data_time: 0.053636 memory: 4465 loss_kpt: 91.991339 acc_pose: 0.798592 loss: 91.991339 2022/10/12 15:30:06 - mmengine - INFO - Epoch(train) [78][150/586] lr: 5.000000e-03 eta: 6:55:12 time: 0.335207 data_time: 0.055542 memory: 4465 loss_kpt: 92.422152 acc_pose: 0.743278 loss: 92.422152 2022/10/12 15:30:23 - mmengine - INFO - Epoch(train) [78][200/586] lr: 5.000000e-03 eta: 6:54:57 time: 0.323106 data_time: 0.049744 memory: 4465 loss_kpt: 90.778809 acc_pose: 0.826865 loss: 90.778809 2022/10/12 15:30:39 - mmengine - INFO - Epoch(train) [78][250/586] lr: 5.000000e-03 eta: 6:54:41 time: 0.322956 data_time: 0.050445 memory: 4465 loss_kpt: 91.182692 acc_pose: 0.694669 loss: 91.182692 2022/10/12 15:30:56 - mmengine - INFO - Epoch(train) [78][300/586] lr: 5.000000e-03 eta: 6:54:26 time: 0.337875 data_time: 0.050623 memory: 4465 loss_kpt: 90.019715 acc_pose: 0.763604 loss: 90.019715 2022/10/12 15:31:13 - mmengine - INFO - Epoch(train) [78][350/586] lr: 5.000000e-03 eta: 6:54:12 time: 0.338158 data_time: 0.055767 memory: 4465 loss_kpt: 89.663371 acc_pose: 0.815105 loss: 89.663371 2022/10/12 15:31:29 - mmengine - INFO - Epoch(train) [78][400/586] lr: 5.000000e-03 eta: 6:53:57 time: 0.331388 data_time: 0.051668 memory: 4465 loss_kpt: 91.626926 acc_pose: 0.779659 loss: 91.626926 2022/10/12 15:31:46 - mmengine - INFO - Epoch(train) [78][450/586] lr: 5.000000e-03 eta: 6:53:42 time: 0.339845 data_time: 0.056993 memory: 4465 loss_kpt: 90.253649 acc_pose: 0.802700 loss: 90.253649 2022/10/12 15:32:03 - mmengine - INFO - Epoch(train) [78][500/586] lr: 5.000000e-03 eta: 6:53:28 time: 0.344244 data_time: 0.056230 memory: 4465 loss_kpt: 92.445189 acc_pose: 0.772133 loss: 92.445189 2022/10/12 15:32:21 - mmengine - INFO - Epoch(train) [78][550/586] lr: 5.000000e-03 eta: 6:53:15 time: 0.349818 data_time: 0.058118 memory: 4465 loss_kpt: 91.000912 acc_pose: 0.843674 loss: 91.000912 2022/10/12 15:32:33 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:32:51 - mmengine - INFO - Epoch(train) [79][50/586] lr: 5.000000e-03 eta: 6:52:31 time: 0.352688 data_time: 0.069016 memory: 4465 loss_kpt: 90.315916 acc_pose: 0.706046 loss: 90.315916 2022/10/12 15:33:07 - mmengine - INFO - Epoch(train) [79][100/586] lr: 5.000000e-03 eta: 6:52:15 time: 0.329652 data_time: 0.050697 memory: 4465 loss_kpt: 88.779891 acc_pose: 0.760041 loss: 88.779891 2022/10/12 15:33:24 - mmengine - INFO - Epoch(train) [79][150/586] lr: 5.000000e-03 eta: 6:52:01 time: 0.335819 data_time: 0.053639 memory: 4465 loss_kpt: 91.000297 acc_pose: 0.782670 loss: 91.000297 2022/10/12 15:33:41 - mmengine - INFO - Epoch(train) [79][200/586] lr: 5.000000e-03 eta: 6:51:45 time: 0.330577 data_time: 0.049760 memory: 4465 loss_kpt: 89.349701 acc_pose: 0.786268 loss: 89.349701 2022/10/12 15:33:57 - mmengine - INFO - Epoch(train) [79][250/586] lr: 5.000000e-03 eta: 6:51:30 time: 0.330363 data_time: 0.052807 memory: 4465 loss_kpt: 91.691740 acc_pose: 0.770295 loss: 91.691740 2022/10/12 15:34:11 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:34:14 - mmengine - INFO - Epoch(train) [79][300/586] lr: 5.000000e-03 eta: 6:51:16 time: 0.342688 data_time: 0.053187 memory: 4465 loss_kpt: 90.600579 acc_pose: 0.795869 loss: 90.600579 2022/10/12 15:34:31 - mmengine - INFO - Epoch(train) [79][350/586] lr: 5.000000e-03 eta: 6:51:01 time: 0.331723 data_time: 0.051468 memory: 4465 loss_kpt: 88.741302 acc_pose: 0.844292 loss: 88.741302 2022/10/12 15:34:47 - mmengine - INFO - Epoch(train) [79][400/586] lr: 5.000000e-03 eta: 6:50:46 time: 0.333678 data_time: 0.054288 memory: 4465 loss_kpt: 91.633933 acc_pose: 0.757640 loss: 91.633933 2022/10/12 15:35:04 - mmengine - INFO - Epoch(train) [79][450/586] lr: 5.000000e-03 eta: 6:50:31 time: 0.331898 data_time: 0.055192 memory: 4465 loss_kpt: 90.741024 acc_pose: 0.732949 loss: 90.741024 2022/10/12 15:35:21 - mmengine - INFO - Epoch(train) [79][500/586] lr: 5.000000e-03 eta: 6:50:16 time: 0.330912 data_time: 0.050390 memory: 4465 loss_kpt: 90.555179 acc_pose: 0.837780 loss: 90.555179 2022/10/12 15:35:37 - mmengine - INFO - Epoch(train) [79][550/586] lr: 5.000000e-03 eta: 6:50:01 time: 0.330412 data_time: 0.053805 memory: 4465 loss_kpt: 91.477820 acc_pose: 0.720986 loss: 91.477820 2022/10/12 15:35:49 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:36:07 - mmengine - INFO - Epoch(train) [80][50/586] lr: 5.000000e-03 eta: 6:49:17 time: 0.350164 data_time: 0.066350 memory: 4465 loss_kpt: 90.817454 acc_pose: 0.717718 loss: 90.817454 2022/10/12 15:36:23 - mmengine - INFO - Epoch(train) [80][100/586] lr: 5.000000e-03 eta: 6:49:02 time: 0.331741 data_time: 0.051769 memory: 4465 loss_kpt: 92.083487 acc_pose: 0.799425 loss: 92.083487 2022/10/12 15:36:41 - mmengine - INFO - Epoch(train) [80][150/586] lr: 5.000000e-03 eta: 6:48:48 time: 0.345315 data_time: 0.056571 memory: 4465 loss_kpt: 89.985547 acc_pose: 0.780724 loss: 89.985547 2022/10/12 15:36:58 - mmengine - INFO - Epoch(train) [80][200/586] lr: 5.000000e-03 eta: 6:48:33 time: 0.338876 data_time: 0.055399 memory: 4465 loss_kpt: 90.706660 acc_pose: 0.829299 loss: 90.706660 2022/10/12 15:37:15 - mmengine - INFO - Epoch(train) [80][250/586] lr: 5.000000e-03 eta: 6:48:19 time: 0.341170 data_time: 0.055921 memory: 4465 loss_kpt: 90.511020 acc_pose: 0.813065 loss: 90.511020 2022/10/12 15:37:31 - mmengine - INFO - Epoch(train) [80][300/586] lr: 5.000000e-03 eta: 6:48:04 time: 0.336448 data_time: 0.054568 memory: 4465 loss_kpt: 90.838893 acc_pose: 0.789061 loss: 90.838893 2022/10/12 15:37:49 - mmengine - INFO - Epoch(train) [80][350/586] lr: 5.000000e-03 eta: 6:47:51 time: 0.354706 data_time: 0.054117 memory: 4465 loss_kpt: 89.984324 acc_pose: 0.778865 loss: 89.984324 2022/10/12 15:38:07 - mmengine - INFO - Epoch(train) [80][400/586] lr: 5.000000e-03 eta: 6:47:38 time: 0.351941 data_time: 0.051248 memory: 4465 loss_kpt: 90.939534 acc_pose: 0.752635 loss: 90.939534 2022/10/12 15:38:24 - mmengine - INFO - Epoch(train) [80][450/586] lr: 5.000000e-03 eta: 6:47:24 time: 0.345490 data_time: 0.050749 memory: 4465 loss_kpt: 91.074558 acc_pose: 0.746176 loss: 91.074558 2022/10/12 15:38:41 - mmengine - INFO - Epoch(train) [80][500/586] lr: 5.000000e-03 eta: 6:47:09 time: 0.341305 data_time: 0.052402 memory: 4465 loss_kpt: 90.662570 acc_pose: 0.778427 loss: 90.662570 2022/10/12 15:38:59 - mmengine - INFO - Epoch(train) [80][550/586] lr: 5.000000e-03 eta: 6:46:56 time: 0.349443 data_time: 0.049378 memory: 4465 loss_kpt: 89.131209 acc_pose: 0.769367 loss: 89.131209 2022/10/12 15:39:11 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:39:11 - mmengine - INFO - Saving checkpoint at 80 epochs 2022/10/12 15:39:20 - mmengine - INFO - Epoch(val) [80][50/407] eta: 0:00:48 time: 0.134966 data_time: 0.016939 memory: 4465 2022/10/12 15:39:27 - mmengine - INFO - Epoch(val) [80][100/407] eta: 0:00:38 time: 0.125627 data_time: 0.008232 memory: 1026 2022/10/12 15:39:33 - mmengine - INFO - Epoch(val) [80][150/407] eta: 0:00:32 time: 0.126692 data_time: 0.007811 memory: 1026 2022/10/12 15:39:39 - mmengine - INFO - Epoch(val) [80][200/407] eta: 0:00:26 time: 0.128170 data_time: 0.008680 memory: 1026 2022/10/12 15:39:46 - mmengine - INFO - Epoch(val) [80][250/407] eta: 0:00:19 time: 0.126329 data_time: 0.008062 memory: 1026 2022/10/12 15:39:52 - mmengine - INFO - Epoch(val) [80][300/407] eta: 0:00:13 time: 0.128895 data_time: 0.008475 memory: 1026 2022/10/12 15:39:58 - mmengine - INFO - Epoch(val) [80][350/407] eta: 0:00:07 time: 0.126618 data_time: 0.008314 memory: 1026 2022/10/12 15:40:05 - mmengine - INFO - Epoch(val) [80][400/407] eta: 0:00:00 time: 0.125131 data_time: 0.007745 memory: 1026 2022/10/12 15:40:18 - mmengine - INFO - Evaluating CocoMetric... 2022/10/12 15:40:34 - mmengine - INFO - Epoch(val) [80][407/407] coco/AP: 0.682338 coco/AP .5: 0.882189 coco/AP .75: 0.757411 coco/AP (M): 0.650040 coco/AP (L): 0.741797 coco/AR: 0.752535 coco/AR .5: 0.921757 coco/AR .75: 0.816751 coco/AR (M): 0.707020 coco/AR (L): 0.815236 2022/10/12 15:40:34 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/liqikai/openmmlab/pt112cu113py38/mmpose/work_dirs/20221012/rsn50/best_coco/AP_epoch_70.pth is removed 2022/10/12 15:40:36 - mmengine - INFO - The best checkpoint with 0.6823 coco/AP at 80 epoch is saved to best_coco/AP_epoch_80.pth. 2022/10/12 15:40:54 - mmengine - INFO - Epoch(train) [81][50/586] lr: 5.000000e-03 eta: 6:46:13 time: 0.357056 data_time: 0.058562 memory: 4465 loss_kpt: 90.126369 acc_pose: 0.820369 loss: 90.126369 2022/10/12 15:41:11 - mmengine - INFO - Epoch(train) [81][100/586] lr: 5.000000e-03 eta: 6:45:58 time: 0.337275 data_time: 0.048853 memory: 4465 loss_kpt: 90.706976 acc_pose: 0.741858 loss: 90.706976 2022/10/12 15:41:18 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:41:27 - mmengine - INFO - Epoch(train) [81][150/586] lr: 5.000000e-03 eta: 6:45:43 time: 0.335148 data_time: 0.054788 memory: 4465 loss_kpt: 91.010388 acc_pose: 0.661084 loss: 91.010388 2022/10/12 15:41:43 - mmengine - INFO - Epoch(train) [81][200/586] lr: 5.000000e-03 eta: 6:45:27 time: 0.319412 data_time: 0.049490 memory: 4465 loss_kpt: 91.822047 acc_pose: 0.828145 loss: 91.822047 2022/10/12 15:42:00 - mmengine - INFO - Epoch(train) [81][250/586] lr: 5.000000e-03 eta: 6:45:12 time: 0.330109 data_time: 0.052200 memory: 4465 loss_kpt: 90.740179 acc_pose: 0.678558 loss: 90.740179 2022/10/12 15:42:16 - mmengine - INFO - Epoch(train) [81][300/586] lr: 5.000000e-03 eta: 6:44:56 time: 0.324360 data_time: 0.051414 memory: 4465 loss_kpt: 89.113089 acc_pose: 0.829017 loss: 89.113089 2022/10/12 15:42:32 - mmengine - INFO - Epoch(train) [81][350/586] lr: 5.000000e-03 eta: 6:44:41 time: 0.328261 data_time: 0.052171 memory: 4465 loss_kpt: 89.130065 acc_pose: 0.716164 loss: 89.130065 2022/10/12 15:42:49 - mmengine - INFO - Epoch(train) [81][400/586] lr: 5.000000e-03 eta: 6:44:25 time: 0.326035 data_time: 0.051460 memory: 4465 loss_kpt: 91.144418 acc_pose: 0.771413 loss: 91.144418 2022/10/12 15:43:05 - mmengine - INFO - Epoch(train) [81][450/586] lr: 5.000000e-03 eta: 6:44:10 time: 0.326798 data_time: 0.051717 memory: 4465 loss_kpt: 91.349716 acc_pose: 0.767294 loss: 91.349716 2022/10/12 15:43:21 - mmengine - INFO - Epoch(train) [81][500/586] lr: 5.000000e-03 eta: 6:43:54 time: 0.319904 data_time: 0.049108 memory: 4465 loss_kpt: 90.139561 acc_pose: 0.751653 loss: 90.139561 2022/10/12 15:43:37 - mmengine - INFO - Epoch(train) [81][550/586] lr: 5.000000e-03 eta: 6:43:37 time: 0.314730 data_time: 0.052311 memory: 4465 loss_kpt: 90.900754 acc_pose: 0.719829 loss: 90.900754 2022/10/12 15:43:48 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:44:06 - mmengine - INFO - Epoch(train) [82][50/586] lr: 5.000000e-03 eta: 6:42:54 time: 0.356139 data_time: 0.067925 memory: 4465 loss_kpt: 90.864445 acc_pose: 0.690393 loss: 90.864445 2022/10/12 15:44:23 - mmengine - INFO - Epoch(train) [82][100/586] lr: 5.000000e-03 eta: 6:42:39 time: 0.333089 data_time: 0.052494 memory: 4465 loss_kpt: 90.630069 acc_pose: 0.807519 loss: 90.630069 2022/10/12 15:44:40 - mmengine - INFO - Epoch(train) [82][150/586] lr: 5.000000e-03 eta: 6:42:25 time: 0.341518 data_time: 0.053929 memory: 4465 loss_kpt: 90.784194 acc_pose: 0.804896 loss: 90.784194 2022/10/12 15:44:57 - mmengine - INFO - Epoch(train) [82][200/586] lr: 5.000000e-03 eta: 6:42:10 time: 0.336379 data_time: 0.054428 memory: 4465 loss_kpt: 89.964165 acc_pose: 0.743043 loss: 89.964165 2022/10/12 15:45:14 - mmengine - INFO - Epoch(train) [82][250/586] lr: 5.000000e-03 eta: 6:41:57 time: 0.352649 data_time: 0.054417 memory: 4465 loss_kpt: 90.990219 acc_pose: 0.757353 loss: 90.990219 2022/10/12 15:45:31 - mmengine - INFO - Epoch(train) [82][300/586] lr: 5.000000e-03 eta: 6:41:42 time: 0.340317 data_time: 0.055787 memory: 4465 loss_kpt: 89.633347 acc_pose: 0.760222 loss: 89.633347 2022/10/12 15:45:48 - mmengine - INFO - Epoch(train) [82][350/586] lr: 5.000000e-03 eta: 6:41:27 time: 0.331608 data_time: 0.050740 memory: 4465 loss_kpt: 90.312875 acc_pose: 0.788763 loss: 90.312875 2022/10/12 15:46:04 - mmengine - INFO - Epoch(train) [82][400/586] lr: 5.000000e-03 eta: 6:41:12 time: 0.325694 data_time: 0.049712 memory: 4465 loss_kpt: 90.438236 acc_pose: 0.844220 loss: 90.438236 2022/10/12 15:46:21 - mmengine - INFO - Epoch(train) [82][450/586] lr: 5.000000e-03 eta: 6:40:56 time: 0.328624 data_time: 0.052939 memory: 4465 loss_kpt: 90.048504 acc_pose: 0.828115 loss: 90.048504 2022/10/12 15:46:37 - mmengine - INFO - Epoch(train) [82][500/586] lr: 5.000000e-03 eta: 6:40:41 time: 0.329304 data_time: 0.049442 memory: 4465 loss_kpt: 90.336315 acc_pose: 0.787172 loss: 90.336315 2022/10/12 15:46:48 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:46:54 - mmengine - INFO - Epoch(train) [82][550/586] lr: 5.000000e-03 eta: 6:40:26 time: 0.329995 data_time: 0.053387 memory: 4465 loss_kpt: 89.949637 acc_pose: 0.815785 loss: 89.949637 2022/10/12 15:47:05 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:47:23 - mmengine - INFO - Epoch(train) [83][50/586] lr: 5.000000e-03 eta: 6:39:43 time: 0.350570 data_time: 0.057604 memory: 4465 loss_kpt: 91.806553 acc_pose: 0.748552 loss: 91.806553 2022/10/12 15:47:40 - mmengine - INFO - Epoch(train) [83][100/586] lr: 5.000000e-03 eta: 6:39:28 time: 0.340390 data_time: 0.054424 memory: 4465 loss_kpt: 90.244237 acc_pose: 0.808635 loss: 90.244237 2022/10/12 15:47:57 - mmengine - INFO - Epoch(train) [83][150/586] lr: 5.000000e-03 eta: 6:39:15 time: 0.354013 data_time: 0.053530 memory: 4465 loss_kpt: 90.390959 acc_pose: 0.808937 loss: 90.390959 2022/10/12 15:48:15 - mmengine - INFO - Epoch(train) [83][200/586] lr: 5.000000e-03 eta: 6:39:01 time: 0.344055 data_time: 0.052052 memory: 4465 loss_kpt: 91.043484 acc_pose: 0.850397 loss: 91.043484 2022/10/12 15:48:32 - mmengine - INFO - Epoch(train) [83][250/586] lr: 5.000000e-03 eta: 6:38:47 time: 0.352008 data_time: 0.054143 memory: 4465 loss_kpt: 90.869122 acc_pose: 0.750530 loss: 90.869122 2022/10/12 15:48:49 - mmengine - INFO - Epoch(train) [83][300/586] lr: 5.000000e-03 eta: 6:38:33 time: 0.346531 data_time: 0.052785 memory: 4465 loss_kpt: 91.573547 acc_pose: 0.768824 loss: 91.573547 2022/10/12 15:49:07 - mmengine - INFO - Epoch(train) [83][350/586] lr: 5.000000e-03 eta: 6:38:20 time: 0.351805 data_time: 0.057530 memory: 4465 loss_kpt: 90.854179 acc_pose: 0.716438 loss: 90.854179 2022/10/12 15:49:24 - mmengine - INFO - Epoch(train) [83][400/586] lr: 5.000000e-03 eta: 6:38:06 time: 0.346527 data_time: 0.052436 memory: 4465 loss_kpt: 89.732384 acc_pose: 0.791468 loss: 89.732384 2022/10/12 15:49:42 - mmengine - INFO - Epoch(train) [83][450/586] lr: 5.000000e-03 eta: 6:37:52 time: 0.342695 data_time: 0.051234 memory: 4465 loss_kpt: 90.518422 acc_pose: 0.735156 loss: 90.518422 2022/10/12 15:49:59 - mmengine - INFO - Epoch(train) [83][500/586] lr: 5.000000e-03 eta: 6:37:37 time: 0.345013 data_time: 0.056572 memory: 4465 loss_kpt: 89.950877 acc_pose: 0.814835 loss: 89.950877 2022/10/12 15:50:16 - mmengine - INFO - Epoch(train) [83][550/586] lr: 5.000000e-03 eta: 6:37:23 time: 0.336281 data_time: 0.053570 memory: 4465 loss_kpt: 91.279609 acc_pose: 0.814556 loss: 91.279609 2022/10/12 15:50:28 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:50:45 - mmengine - INFO - Epoch(train) [84][50/586] lr: 5.000000e-03 eta: 6:36:40 time: 0.347395 data_time: 0.058187 memory: 4465 loss_kpt: 88.068291 acc_pose: 0.762245 loss: 88.068291 2022/10/12 15:51:02 - mmengine - INFO - Epoch(train) [84][100/586] lr: 5.000000e-03 eta: 6:36:25 time: 0.343922 data_time: 0.049077 memory: 4465 loss_kpt: 87.850518 acc_pose: 0.750233 loss: 87.850518 2022/10/12 15:51:19 - mmengine - INFO - Epoch(train) [84][150/586] lr: 5.000000e-03 eta: 6:36:11 time: 0.336827 data_time: 0.048923 memory: 4465 loss_kpt: 88.862001 acc_pose: 0.763245 loss: 88.862001 2022/10/12 15:51:36 - mmengine - INFO - Epoch(train) [84][200/586] lr: 5.000000e-03 eta: 6:35:56 time: 0.339650 data_time: 0.059527 memory: 4465 loss_kpt: 89.179887 acc_pose: 0.819303 loss: 89.179887 2022/10/12 15:51:53 - mmengine - INFO - Epoch(train) [84][250/586] lr: 5.000000e-03 eta: 6:35:41 time: 0.331352 data_time: 0.052294 memory: 4465 loss_kpt: 89.623114 acc_pose: 0.823583 loss: 89.623114 2022/10/12 15:52:09 - mmengine - INFO - Epoch(train) [84][300/586] lr: 5.000000e-03 eta: 6:35:26 time: 0.332809 data_time: 0.050446 memory: 4465 loss_kpt: 89.279482 acc_pose: 0.735559 loss: 89.279482 2022/10/12 15:52:26 - mmengine - INFO - Epoch(train) [84][350/586] lr: 5.000000e-03 eta: 6:35:11 time: 0.331215 data_time: 0.053042 memory: 4465 loss_kpt: 90.258725 acc_pose: 0.754259 loss: 90.258725 2022/10/12 15:52:30 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:52:42 - mmengine - INFO - Epoch(train) [84][400/586] lr: 5.000000e-03 eta: 6:34:55 time: 0.322451 data_time: 0.050562 memory: 4465 loss_kpt: 90.938255 acc_pose: 0.761247 loss: 90.938255 2022/10/12 15:52:58 - mmengine - INFO - Epoch(train) [84][450/586] lr: 5.000000e-03 eta: 6:34:39 time: 0.323239 data_time: 0.050268 memory: 4465 loss_kpt: 90.002233 acc_pose: 0.820282 loss: 90.002233 2022/10/12 15:53:15 - mmengine - INFO - Epoch(train) [84][500/586] lr: 5.000000e-03 eta: 6:34:25 time: 0.339533 data_time: 0.052735 memory: 4465 loss_kpt: 91.389073 acc_pose: 0.759578 loss: 91.389073 2022/10/12 15:53:32 - mmengine - INFO - Epoch(train) [84][550/586] lr: 5.000000e-03 eta: 6:34:10 time: 0.330954 data_time: 0.052343 memory: 4465 loss_kpt: 90.769024 acc_pose: 0.787231 loss: 90.769024 2022/10/12 15:53:44 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:54:01 - mmengine - INFO - Epoch(train) [85][50/586] lr: 5.000000e-03 eta: 6:33:27 time: 0.347701 data_time: 0.065861 memory: 4465 loss_kpt: 92.129694 acc_pose: 0.727935 loss: 92.129694 2022/10/12 15:54:17 - mmengine - INFO - Epoch(train) [85][100/586] lr: 5.000000e-03 eta: 6:33:11 time: 0.327653 data_time: 0.050645 memory: 4465 loss_kpt: 89.926098 acc_pose: 0.786533 loss: 89.926098 2022/10/12 15:54:34 - mmengine - INFO - Epoch(train) [85][150/586] lr: 5.000000e-03 eta: 6:32:56 time: 0.330558 data_time: 0.052412 memory: 4465 loss_kpt: 89.893956 acc_pose: 0.763703 loss: 89.893956 2022/10/12 15:54:50 - mmengine - INFO - Epoch(train) [85][200/586] lr: 5.000000e-03 eta: 6:32:41 time: 0.325904 data_time: 0.053883 memory: 4465 loss_kpt: 89.659383 acc_pose: 0.761324 loss: 89.659383 2022/10/12 15:55:07 - mmengine - INFO - Epoch(train) [85][250/586] lr: 5.000000e-03 eta: 6:32:25 time: 0.329221 data_time: 0.056362 memory: 4465 loss_kpt: 91.093542 acc_pose: 0.795336 loss: 91.093542 2022/10/12 15:55:22 - mmengine - INFO - Epoch(train) [85][300/586] lr: 5.000000e-03 eta: 6:32:09 time: 0.317006 data_time: 0.051009 memory: 4465 loss_kpt: 91.120563 acc_pose: 0.784071 loss: 91.120563 2022/10/12 15:55:38 - mmengine - INFO - Epoch(train) [85][350/586] lr: 5.000000e-03 eta: 6:31:53 time: 0.316237 data_time: 0.050476 memory: 4465 loss_kpt: 91.601394 acc_pose: 0.730667 loss: 91.601394 2022/10/12 15:55:54 - mmengine - INFO - Epoch(train) [85][400/586] lr: 5.000000e-03 eta: 6:31:37 time: 0.320005 data_time: 0.050469 memory: 4465 loss_kpt: 89.540382 acc_pose: 0.762087 loss: 89.540382 2022/10/12 15:56:11 - mmengine - INFO - Epoch(train) [85][450/586] lr: 5.000000e-03 eta: 6:31:22 time: 0.334987 data_time: 0.051144 memory: 4465 loss_kpt: 90.085517 acc_pose: 0.801401 loss: 90.085517 2022/10/12 15:56:27 - mmengine - INFO - Epoch(train) [85][500/586] lr: 5.000000e-03 eta: 6:31:06 time: 0.325999 data_time: 0.050067 memory: 4465 loss_kpt: 90.101728 acc_pose: 0.753325 loss: 90.101728 2022/10/12 15:56:44 - mmengine - INFO - Epoch(train) [85][550/586] lr: 5.000000e-03 eta: 6:30:52 time: 0.341507 data_time: 0.047663 memory: 4465 loss_kpt: 90.131955 acc_pose: 0.796467 loss: 90.131955 2022/10/12 15:56:57 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:57:14 - mmengine - INFO - Epoch(train) [86][50/586] lr: 5.000000e-03 eta: 6:30:10 time: 0.347810 data_time: 0.061114 memory: 4465 loss_kpt: 91.106048 acc_pose: 0.719196 loss: 91.106048 2022/10/12 15:57:30 - mmengine - INFO - Epoch(train) [86][100/586] lr: 5.000000e-03 eta: 6:29:54 time: 0.327691 data_time: 0.049405 memory: 4465 loss_kpt: 88.548215 acc_pose: 0.793060 loss: 88.548215 2022/10/12 15:57:47 - mmengine - INFO - Epoch(train) [86][150/586] lr: 5.000000e-03 eta: 6:29:39 time: 0.337443 data_time: 0.048213 memory: 4465 loss_kpt: 91.198740 acc_pose: 0.768405 loss: 91.198740 2022/10/12 15:58:01 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 15:58:04 - mmengine - INFO - Epoch(train) [86][200/586] lr: 5.000000e-03 eta: 6:29:24 time: 0.331501 data_time: 0.049755 memory: 4465 loss_kpt: 89.034144 acc_pose: 0.817085 loss: 89.034144 2022/10/12 15:58:21 - mmengine - INFO - Epoch(train) [86][250/586] lr: 5.000000e-03 eta: 6:29:10 time: 0.341352 data_time: 0.053216 memory: 4465 loss_kpt: 88.908158 acc_pose: 0.799237 loss: 88.908158 2022/10/12 15:58:38 - mmengine - INFO - Epoch(train) [86][300/586] lr: 5.000000e-03 eta: 6:28:55 time: 0.340940 data_time: 0.047579 memory: 4465 loss_kpt: 90.936045 acc_pose: 0.772780 loss: 90.936045 2022/10/12 15:58:55 - mmengine - INFO - Epoch(train) [86][350/586] lr: 5.000000e-03 eta: 6:28:41 time: 0.336632 data_time: 0.052340 memory: 4465 loss_kpt: 91.026975 acc_pose: 0.734358 loss: 91.026975 2022/10/12 15:59:11 - mmengine - INFO - Epoch(train) [86][400/586] lr: 5.000000e-03 eta: 6:28:25 time: 0.330624 data_time: 0.046977 memory: 4465 loss_kpt: 92.505650 acc_pose: 0.803047 loss: 92.505650 2022/10/12 15:59:28 - mmengine - INFO - Epoch(train) [86][450/586] lr: 5.000000e-03 eta: 6:28:11 time: 0.334992 data_time: 0.047039 memory: 4465 loss_kpt: 91.648853 acc_pose: 0.842168 loss: 91.648853 2022/10/12 15:59:45 - mmengine - INFO - Epoch(train) [86][500/586] lr: 5.000000e-03 eta: 6:27:55 time: 0.329344 data_time: 0.048850 memory: 4465 loss_kpt: 90.970622 acc_pose: 0.774362 loss: 90.970622 2022/10/12 16:00:01 - mmengine - INFO - Epoch(train) [86][550/586] lr: 5.000000e-03 eta: 6:27:40 time: 0.327084 data_time: 0.047067 memory: 4465 loss_kpt: 89.762740 acc_pose: 0.848643 loss: 89.762740 2022/10/12 16:00:13 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:00:30 - mmengine - INFO - Epoch(train) [87][50/586] lr: 5.000000e-03 eta: 6:26:58 time: 0.349641 data_time: 0.061335 memory: 4465 loss_kpt: 88.138369 acc_pose: 0.787810 loss: 88.138369 2022/10/12 16:00:47 - mmengine - INFO - Epoch(train) [87][100/586] lr: 5.000000e-03 eta: 6:26:43 time: 0.338720 data_time: 0.048473 memory: 4465 loss_kpt: 90.546631 acc_pose: 0.798314 loss: 90.546631 2022/10/12 16:01:04 - mmengine - INFO - Epoch(train) [87][150/586] lr: 5.000000e-03 eta: 6:26:28 time: 0.337760 data_time: 0.050188 memory: 4465 loss_kpt: 90.305894 acc_pose: 0.716414 loss: 90.305894 2022/10/12 16:01:21 - mmengine - INFO - Epoch(train) [87][200/586] lr: 5.000000e-03 eta: 6:26:14 time: 0.338717 data_time: 0.046489 memory: 4465 loss_kpt: 90.964617 acc_pose: 0.796811 loss: 90.964617 2022/10/12 16:01:38 - mmengine - INFO - Epoch(train) [87][250/586] lr: 5.000000e-03 eta: 6:25:59 time: 0.340939 data_time: 0.052045 memory: 4465 loss_kpt: 90.724217 acc_pose: 0.821529 loss: 90.724217 2022/10/12 16:01:55 - mmengine - INFO - Epoch(train) [87][300/586] lr: 5.000000e-03 eta: 6:25:44 time: 0.330626 data_time: 0.052845 memory: 4465 loss_kpt: 89.395787 acc_pose: 0.775235 loss: 89.395787 2022/10/12 16:02:11 - mmengine - INFO - Epoch(train) [87][350/586] lr: 5.000000e-03 eta: 6:25:29 time: 0.328953 data_time: 0.057927 memory: 4465 loss_kpt: 90.520959 acc_pose: 0.759884 loss: 90.520959 2022/10/12 16:02:27 - mmengine - INFO - Epoch(train) [87][400/586] lr: 5.000000e-03 eta: 6:25:13 time: 0.328261 data_time: 0.046366 memory: 4465 loss_kpt: 90.412794 acc_pose: 0.822561 loss: 90.412794 2022/10/12 16:02:44 - mmengine - INFO - Epoch(train) [87][450/586] lr: 5.000000e-03 eta: 6:24:58 time: 0.331509 data_time: 0.049631 memory: 4465 loss_kpt: 90.515429 acc_pose: 0.754191 loss: 90.515429 2022/10/12 16:03:00 - mmengine - INFO - Epoch(train) [87][500/586] lr: 5.000000e-03 eta: 6:24:42 time: 0.322836 data_time: 0.046791 memory: 4465 loss_kpt: 90.294959 acc_pose: 0.758634 loss: 90.294959 2022/10/12 16:03:17 - mmengine - INFO - Epoch(train) [87][550/586] lr: 5.000000e-03 eta: 6:24:27 time: 0.330898 data_time: 0.050043 memory: 4465 loss_kpt: 90.792324 acc_pose: 0.746560 loss: 90.792324 2022/10/12 16:03:28 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:03:35 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:03:45 - mmengine - INFO - Epoch(train) [88][50/586] lr: 5.000000e-03 eta: 6:23:45 time: 0.343832 data_time: 0.059833 memory: 4465 loss_kpt: 90.295617 acc_pose: 0.858538 loss: 90.295617 2022/10/12 16:04:03 - mmengine - INFO - Epoch(train) [88][100/586] lr: 5.000000e-03 eta: 6:23:31 time: 0.347809 data_time: 0.049378 memory: 4465 loss_kpt: 91.115066 acc_pose: 0.664850 loss: 91.115066 2022/10/12 16:04:20 - mmengine - INFO - Epoch(train) [88][150/586] lr: 5.000000e-03 eta: 6:23:17 time: 0.344670 data_time: 0.054316 memory: 4465 loss_kpt: 88.567665 acc_pose: 0.859130 loss: 88.567665 2022/10/12 16:04:37 - mmengine - INFO - Epoch(train) [88][200/586] lr: 5.000000e-03 eta: 6:23:02 time: 0.339391 data_time: 0.047552 memory: 4465 loss_kpt: 89.968957 acc_pose: 0.797891 loss: 89.968957 2022/10/12 16:04:54 - mmengine - INFO - Epoch(train) [88][250/586] lr: 5.000000e-03 eta: 6:22:48 time: 0.345238 data_time: 0.052099 memory: 4465 loss_kpt: 89.372104 acc_pose: 0.737218 loss: 89.372104 2022/10/12 16:05:11 - mmengine - INFO - Epoch(train) [88][300/586] lr: 5.000000e-03 eta: 6:22:34 time: 0.341843 data_time: 0.048151 memory: 4465 loss_kpt: 89.479238 acc_pose: 0.741889 loss: 89.479238 2022/10/12 16:05:29 - mmengine - INFO - Epoch(train) [88][350/586] lr: 5.000000e-03 eta: 6:22:20 time: 0.350761 data_time: 0.049443 memory: 4465 loss_kpt: 89.077139 acc_pose: 0.839272 loss: 89.077139 2022/10/12 16:05:46 - mmengine - INFO - Epoch(train) [88][400/586] lr: 5.000000e-03 eta: 6:22:05 time: 0.340041 data_time: 0.045935 memory: 4465 loss_kpt: 90.037300 acc_pose: 0.798023 loss: 90.037300 2022/10/12 16:06:03 - mmengine - INFO - Epoch(train) [88][450/586] lr: 5.000000e-03 eta: 6:21:51 time: 0.338852 data_time: 0.049388 memory: 4465 loss_kpt: 91.096056 acc_pose: 0.795559 loss: 91.096056 2022/10/12 16:06:20 - mmengine - INFO - Epoch(train) [88][500/586] lr: 5.000000e-03 eta: 6:21:36 time: 0.344101 data_time: 0.044765 memory: 4465 loss_kpt: 89.167093 acc_pose: 0.777970 loss: 89.167093 2022/10/12 16:06:37 - mmengine - INFO - Epoch(train) [88][550/586] lr: 5.000000e-03 eta: 6:21:21 time: 0.334950 data_time: 0.046761 memory: 4465 loss_kpt: 90.239687 acc_pose: 0.738851 loss: 90.239687 2022/10/12 16:06:49 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:07:07 - mmengine - INFO - Epoch(train) [89][50/586] lr: 5.000000e-03 eta: 6:20:40 time: 0.353539 data_time: 0.057806 memory: 4465 loss_kpt: 89.833887 acc_pose: 0.769587 loss: 89.833887 2022/10/12 16:07:23 - mmengine - INFO - Epoch(train) [89][100/586] lr: 5.000000e-03 eta: 6:20:25 time: 0.333661 data_time: 0.051988 memory: 4465 loss_kpt: 88.868961 acc_pose: 0.739845 loss: 88.868961 2022/10/12 16:07:40 - mmengine - INFO - Epoch(train) [89][150/586] lr: 5.000000e-03 eta: 6:20:10 time: 0.336062 data_time: 0.052215 memory: 4465 loss_kpt: 90.193798 acc_pose: 0.804281 loss: 90.193798 2022/10/12 16:07:57 - mmengine - INFO - Epoch(train) [89][200/586] lr: 5.000000e-03 eta: 6:19:55 time: 0.335152 data_time: 0.049050 memory: 4465 loss_kpt: 89.432456 acc_pose: 0.801346 loss: 89.432456 2022/10/12 16:08:14 - mmengine - INFO - Epoch(train) [89][250/586] lr: 5.000000e-03 eta: 6:19:40 time: 0.334100 data_time: 0.050231 memory: 4465 loss_kpt: 90.135379 acc_pose: 0.797164 loss: 90.135379 2022/10/12 16:08:31 - mmengine - INFO - Epoch(train) [89][300/586] lr: 5.000000e-03 eta: 6:19:26 time: 0.339956 data_time: 0.047461 memory: 4465 loss_kpt: 89.265252 acc_pose: 0.758632 loss: 89.265252 2022/10/12 16:08:47 - mmengine - INFO - Epoch(train) [89][350/586] lr: 5.000000e-03 eta: 6:19:11 time: 0.333842 data_time: 0.053802 memory: 4465 loss_kpt: 89.117590 acc_pose: 0.834724 loss: 89.117590 2022/10/12 16:09:04 - mmengine - INFO - Epoch(train) [89][400/586] lr: 5.000000e-03 eta: 6:18:56 time: 0.338278 data_time: 0.052417 memory: 4465 loss_kpt: 89.680861 acc_pose: 0.792989 loss: 89.680861 2022/10/12 16:09:15 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:09:21 - mmengine - INFO - Epoch(train) [89][450/586] lr: 5.000000e-03 eta: 6:18:40 time: 0.325669 data_time: 0.049824 memory: 4465 loss_kpt: 90.334838 acc_pose: 0.773167 loss: 90.334838 2022/10/12 16:09:37 - mmengine - INFO - Epoch(train) [89][500/586] lr: 5.000000e-03 eta: 6:18:25 time: 0.324066 data_time: 0.051599 memory: 4465 loss_kpt: 91.757187 acc_pose: 0.806169 loss: 91.757187 2022/10/12 16:09:54 - mmengine - INFO - Epoch(train) [89][550/586] lr: 5.000000e-03 eta: 6:18:10 time: 0.344054 data_time: 0.052699 memory: 4465 loss_kpt: 90.110222 acc_pose: 0.786926 loss: 90.110222 2022/10/12 16:10:06 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:10:24 - mmengine - INFO - Epoch(train) [90][50/586] lr: 5.000000e-03 eta: 6:17:29 time: 0.347685 data_time: 0.058699 memory: 4465 loss_kpt: 89.904729 acc_pose: 0.791466 loss: 89.904729 2022/10/12 16:10:41 - mmengine - INFO - Epoch(train) [90][100/586] lr: 5.000000e-03 eta: 6:17:14 time: 0.337359 data_time: 0.048842 memory: 4465 loss_kpt: 92.095158 acc_pose: 0.759060 loss: 92.095158 2022/10/12 16:10:57 - mmengine - INFO - Epoch(train) [90][150/586] lr: 5.000000e-03 eta: 6:16:59 time: 0.327944 data_time: 0.047866 memory: 4465 loss_kpt: 88.450586 acc_pose: 0.780140 loss: 88.450586 2022/10/12 16:11:13 - mmengine - INFO - Epoch(train) [90][200/586] lr: 5.000000e-03 eta: 6:16:43 time: 0.326679 data_time: 0.049108 memory: 4465 loss_kpt: 89.893443 acc_pose: 0.806736 loss: 89.893443 2022/10/12 16:11:30 - mmengine - INFO - Epoch(train) [90][250/586] lr: 5.000000e-03 eta: 6:16:28 time: 0.329475 data_time: 0.050491 memory: 4465 loss_kpt: 89.833007 acc_pose: 0.809087 loss: 89.833007 2022/10/12 16:11:47 - mmengine - INFO - Epoch(train) [90][300/586] lr: 5.000000e-03 eta: 6:16:13 time: 0.335124 data_time: 0.044864 memory: 4465 loss_kpt: 90.863750 acc_pose: 0.735080 loss: 90.863750 2022/10/12 16:12:03 - mmengine - INFO - Epoch(train) [90][350/586] lr: 5.000000e-03 eta: 6:15:58 time: 0.331712 data_time: 0.050881 memory: 4465 loss_kpt: 88.962234 acc_pose: 0.708319 loss: 88.962234 2022/10/12 16:12:19 - mmengine - INFO - Epoch(train) [90][400/586] lr: 5.000000e-03 eta: 6:15:42 time: 0.319623 data_time: 0.052055 memory: 4465 loss_kpt: 89.012168 acc_pose: 0.749719 loss: 89.012168 2022/10/12 16:12:35 - mmengine - INFO - Epoch(train) [90][450/586] lr: 5.000000e-03 eta: 6:15:26 time: 0.315804 data_time: 0.048514 memory: 4465 loss_kpt: 89.936494 acc_pose: 0.744884 loss: 89.936494 2022/10/12 16:12:51 - mmengine - INFO - Epoch(train) [90][500/586] lr: 5.000000e-03 eta: 6:15:10 time: 0.320649 data_time: 0.048069 memory: 4465 loss_kpt: 89.592929 acc_pose: 0.814658 loss: 89.592929 2022/10/12 16:13:07 - mmengine - INFO - Epoch(train) [90][550/586] lr: 5.000000e-03 eta: 6:14:54 time: 0.323899 data_time: 0.046343 memory: 4465 loss_kpt: 89.315089 acc_pose: 0.794752 loss: 89.315089 2022/10/12 16:13:19 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:13:19 - mmengine - INFO - Saving checkpoint at 90 epochs 2022/10/12 16:13:28 - mmengine - INFO - Epoch(val) [90][50/407] eta: 0:00:47 time: 0.133458 data_time: 0.012980 memory: 4465 2022/10/12 16:13:35 - mmengine - INFO - Epoch(val) [90][100/407] eta: 0:00:39 time: 0.128155 data_time: 0.008347 memory: 1026 2022/10/12 16:13:41 - mmengine - INFO - Epoch(val) [90][150/407] eta: 0:00:32 time: 0.127633 data_time: 0.008157 memory: 1026 2022/10/12 16:13:48 - mmengine - INFO - Epoch(val) [90][200/407] eta: 0:00:26 time: 0.126708 data_time: 0.008085 memory: 1026 2022/10/12 16:13:54 - mmengine - INFO - Epoch(val) [90][250/407] eta: 0:00:19 time: 0.126080 data_time: 0.007956 memory: 1026 2022/10/12 16:14:00 - mmengine - INFO - Epoch(val) [90][300/407] eta: 0:00:14 time: 0.131867 data_time: 0.012086 memory: 1026 2022/10/12 16:14:07 - mmengine - INFO - Epoch(val) [90][350/407] eta: 0:00:07 time: 0.127534 data_time: 0.008235 memory: 1026 2022/10/12 16:14:13 - mmengine - INFO - Epoch(val) [90][400/407] eta: 0:00:00 time: 0.124394 data_time: 0.007838 memory: 1026 2022/10/12 16:14:27 - mmengine - INFO - Evaluating CocoMetric... 2022/10/12 16:14:43 - mmengine - INFO - Epoch(val) [90][407/407] coco/AP: 0.679046 coco/AP .5: 0.871886 coco/AP .75: 0.753377 coco/AP (M): 0.646392 coco/AP (L): 0.740767 coco/AR: 0.751763 coco/AR .5: 0.915775 coco/AR .75: 0.815334 coco/AR (M): 0.705736 coco/AR (L): 0.814939 2022/10/12 16:15:00 - mmengine - INFO - Epoch(train) [91][50/586] lr: 5.000000e-03 eta: 6:14:13 time: 0.345615 data_time: 0.056201 memory: 4465 loss_kpt: 88.292060 acc_pose: 0.833741 loss: 88.292060 2022/10/12 16:15:16 - mmengine - INFO - Epoch(train) [91][100/586] lr: 5.000000e-03 eta: 6:13:57 time: 0.323208 data_time: 0.048292 memory: 4465 loss_kpt: 90.644347 acc_pose: 0.735443 loss: 90.644347 2022/10/12 16:15:32 - mmengine - INFO - Epoch(train) [91][150/586] lr: 5.000000e-03 eta: 6:13:41 time: 0.319567 data_time: 0.051659 memory: 4465 loss_kpt: 88.211292 acc_pose: 0.796758 loss: 88.211292 2022/10/12 16:15:49 - mmengine - INFO - Epoch(train) [91][200/586] lr: 5.000000e-03 eta: 6:13:26 time: 0.327830 data_time: 0.051479 memory: 4465 loss_kpt: 89.958932 acc_pose: 0.772480 loss: 89.958932 2022/10/12 16:16:05 - mmengine - INFO - Epoch(train) [91][250/586] lr: 5.000000e-03 eta: 6:13:10 time: 0.323011 data_time: 0.050703 memory: 4465 loss_kpt: 89.506259 acc_pose: 0.854878 loss: 89.506259 2022/10/12 16:16:08 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:16:21 - mmengine - INFO - Epoch(train) [91][300/586] lr: 5.000000e-03 eta: 6:12:54 time: 0.321875 data_time: 0.050013 memory: 4465 loss_kpt: 90.654079 acc_pose: 0.742079 loss: 90.654079 2022/10/12 16:16:37 - mmengine - INFO - Epoch(train) [91][350/586] lr: 5.000000e-03 eta: 6:12:39 time: 0.322334 data_time: 0.049388 memory: 4465 loss_kpt: 90.468021 acc_pose: 0.726631 loss: 90.468021 2022/10/12 16:16:53 - mmengine - INFO - Epoch(train) [91][400/586] lr: 5.000000e-03 eta: 6:12:23 time: 0.331131 data_time: 0.046977 memory: 4465 loss_kpt: 90.897067 acc_pose: 0.739973 loss: 90.897067 2022/10/12 16:17:10 - mmengine - INFO - Epoch(train) [91][450/586] lr: 5.000000e-03 eta: 6:12:08 time: 0.323210 data_time: 0.048279 memory: 4465 loss_kpt: 89.202680 acc_pose: 0.712884 loss: 89.202680 2022/10/12 16:17:27 - mmengine - INFO - Epoch(train) [91][500/586] lr: 5.000000e-03 eta: 6:11:53 time: 0.343829 data_time: 0.049870 memory: 4465 loss_kpt: 89.002049 acc_pose: 0.814537 loss: 89.002049 2022/10/12 16:17:44 - mmengine - INFO - Epoch(train) [91][550/586] lr: 5.000000e-03 eta: 6:11:39 time: 0.344400 data_time: 0.047211 memory: 4465 loss_kpt: 89.829457 acc_pose: 0.787857 loss: 89.829457 2022/10/12 16:17:56 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:18:14 - mmengine - INFO - Epoch(train) [92][50/586] lr: 5.000000e-03 eta: 6:10:58 time: 0.347641 data_time: 0.059987 memory: 4465 loss_kpt: 90.596237 acc_pose: 0.834130 loss: 90.596237 2022/10/12 16:18:30 - mmengine - INFO - Epoch(train) [92][100/586] lr: 5.000000e-03 eta: 6:10:43 time: 0.328843 data_time: 0.046664 memory: 4465 loss_kpt: 90.319926 acc_pose: 0.714186 loss: 90.319926 2022/10/12 16:18:48 - mmengine - INFO - Epoch(train) [92][150/586] lr: 5.000000e-03 eta: 6:10:29 time: 0.354163 data_time: 0.051432 memory: 4465 loss_kpt: 90.689677 acc_pose: 0.846320 loss: 90.689677 2022/10/12 16:19:05 - mmengine - INFO - Epoch(train) [92][200/586] lr: 5.000000e-03 eta: 6:10:15 time: 0.342155 data_time: 0.044695 memory: 4465 loss_kpt: 88.801324 acc_pose: 0.756694 loss: 88.801324 2022/10/12 16:19:22 - mmengine - INFO - Epoch(train) [92][250/586] lr: 5.000000e-03 eta: 6:10:00 time: 0.342401 data_time: 0.055133 memory: 4465 loss_kpt: 88.727098 acc_pose: 0.778270 loss: 88.727098 2022/10/12 16:19:39 - mmengine - INFO - Epoch(train) [92][300/586] lr: 5.000000e-03 eta: 6:09:46 time: 0.346298 data_time: 0.044784 memory: 4465 loss_kpt: 88.851369 acc_pose: 0.773808 loss: 88.851369 2022/10/12 16:19:57 - mmengine - INFO - Epoch(train) [92][350/586] lr: 5.000000e-03 eta: 6:09:32 time: 0.354605 data_time: 0.050323 memory: 4465 loss_kpt: 88.760344 acc_pose: 0.784408 loss: 88.760344 2022/10/12 16:20:14 - mmengine - INFO - Epoch(train) [92][400/586] lr: 5.000000e-03 eta: 6:09:17 time: 0.336747 data_time: 0.045394 memory: 4465 loss_kpt: 90.151218 acc_pose: 0.722716 loss: 90.151218 2022/10/12 16:20:31 - mmengine - INFO - Epoch(train) [92][450/586] lr: 5.000000e-03 eta: 6:09:02 time: 0.336105 data_time: 0.046802 memory: 4465 loss_kpt: 89.434319 acc_pose: 0.761280 loss: 89.434319 2022/10/12 16:20:47 - mmengine - INFO - Epoch(train) [92][500/586] lr: 5.000000e-03 eta: 6:08:47 time: 0.330793 data_time: 0.048254 memory: 4465 loss_kpt: 90.246902 acc_pose: 0.893010 loss: 90.246902 2022/10/12 16:21:04 - mmengine - INFO - Epoch(train) [92][550/586] lr: 5.000000e-03 eta: 6:08:32 time: 0.332030 data_time: 0.046635 memory: 4465 loss_kpt: 89.318924 acc_pose: 0.904108 loss: 89.318924 2022/10/12 16:21:15 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:21:33 - mmengine - INFO - Epoch(train) [93][50/586] lr: 5.000000e-03 eta: 6:07:52 time: 0.350769 data_time: 0.057269 memory: 4465 loss_kpt: 88.344058 acc_pose: 0.773044 loss: 88.344058 2022/10/12 16:21:46 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:21:50 - mmengine - INFO - Epoch(train) [93][100/586] lr: 5.000000e-03 eta: 6:07:37 time: 0.334584 data_time: 0.046202 memory: 4465 loss_kpt: 88.681001 acc_pose: 0.786241 loss: 88.681001 2022/10/12 16:22:06 - mmengine - INFO - Epoch(train) [93][150/586] lr: 5.000000e-03 eta: 6:07:22 time: 0.333537 data_time: 0.048955 memory: 4465 loss_kpt: 90.313351 acc_pose: 0.783835 loss: 90.313351 2022/10/12 16:22:23 - mmengine - INFO - Epoch(train) [93][200/586] lr: 5.000000e-03 eta: 6:07:07 time: 0.339083 data_time: 0.053798 memory: 4465 loss_kpt: 89.565845 acc_pose: 0.783598 loss: 89.565845 2022/10/12 16:22:40 - mmengine - INFO - Epoch(train) [93][250/586] lr: 5.000000e-03 eta: 6:06:52 time: 0.341076 data_time: 0.046552 memory: 4465 loss_kpt: 90.569016 acc_pose: 0.775824 loss: 90.569016 2022/10/12 16:22:57 - mmengine - INFO - Epoch(train) [93][300/586] lr: 5.000000e-03 eta: 6:06:37 time: 0.335014 data_time: 0.050213 memory: 4465 loss_kpt: 89.843933 acc_pose: 0.785945 loss: 89.843933 2022/10/12 16:23:13 - mmengine - INFO - Epoch(train) [93][350/586] lr: 5.000000e-03 eta: 6:06:22 time: 0.322420 data_time: 0.047669 memory: 4465 loss_kpt: 89.359604 acc_pose: 0.801347 loss: 89.359604 2022/10/12 16:23:30 - mmengine - INFO - Epoch(train) [93][400/586] lr: 5.000000e-03 eta: 6:06:06 time: 0.332320 data_time: 0.046228 memory: 4465 loss_kpt: 90.011057 acc_pose: 0.788971 loss: 90.011057 2022/10/12 16:23:47 - mmengine - INFO - Epoch(train) [93][450/586] lr: 5.000000e-03 eta: 6:05:51 time: 0.335327 data_time: 0.049214 memory: 4465 loss_kpt: 87.078012 acc_pose: 0.795013 loss: 87.078012 2022/10/12 16:24:04 - mmengine - INFO - Epoch(train) [93][500/586] lr: 5.000000e-03 eta: 6:05:37 time: 0.341106 data_time: 0.050046 memory: 4465 loss_kpt: 89.586236 acc_pose: 0.791560 loss: 89.586236 2022/10/12 16:24:20 - mmengine - INFO - Epoch(train) [93][550/586] lr: 5.000000e-03 eta: 6:05:22 time: 0.332457 data_time: 0.047455 memory: 4465 loss_kpt: 90.538173 acc_pose: 0.759022 loss: 90.538173 2022/10/12 16:24:32 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:24:50 - mmengine - INFO - Epoch(train) [94][50/586] lr: 5.000000e-03 eta: 6:04:41 time: 0.345427 data_time: 0.056894 memory: 4465 loss_kpt: 88.661839 acc_pose: 0.840389 loss: 88.661839 2022/10/12 16:25:07 - mmengine - INFO - Epoch(train) [94][100/586] lr: 5.000000e-03 eta: 6:04:27 time: 0.341875 data_time: 0.051208 memory: 4465 loss_kpt: 90.185385 acc_pose: 0.799207 loss: 90.185385 2022/10/12 16:25:24 - mmengine - INFO - Epoch(train) [94][150/586] lr: 5.000000e-03 eta: 6:04:13 time: 0.352674 data_time: 0.051592 memory: 4465 loss_kpt: 90.016825 acc_pose: 0.826306 loss: 90.016825 2022/10/12 16:25:43 - mmengine - INFO - Epoch(train) [94][200/586] lr: 5.000000e-03 eta: 6:03:59 time: 0.361851 data_time: 0.053120 memory: 4465 loss_kpt: 90.833223 acc_pose: 0.800952 loss: 90.833223 2022/10/12 16:26:00 - mmengine - INFO - Epoch(train) [94][250/586] lr: 5.000000e-03 eta: 6:03:45 time: 0.345265 data_time: 0.049085 memory: 4465 loss_kpt: 90.174890 acc_pose: 0.832536 loss: 90.174890 2022/10/12 16:26:17 - mmengine - INFO - Epoch(train) [94][300/586] lr: 5.000000e-03 eta: 6:03:30 time: 0.335878 data_time: 0.055228 memory: 4465 loss_kpt: 90.248380 acc_pose: 0.821410 loss: 90.248380 2022/10/12 16:26:33 - mmengine - INFO - Epoch(train) [94][350/586] lr: 5.000000e-03 eta: 6:03:14 time: 0.321755 data_time: 0.051658 memory: 4465 loss_kpt: 90.475986 acc_pose: 0.794012 loss: 90.475986 2022/10/12 16:26:49 - mmengine - INFO - Epoch(train) [94][400/586] lr: 5.000000e-03 eta: 6:02:59 time: 0.329930 data_time: 0.047389 memory: 4465 loss_kpt: 89.498557 acc_pose: 0.794419 loss: 89.498557 2022/10/12 16:27:06 - mmengine - INFO - Epoch(train) [94][450/586] lr: 5.000000e-03 eta: 6:02:44 time: 0.335573 data_time: 0.051664 memory: 4465 loss_kpt: 89.454709 acc_pose: 0.778576 loss: 89.454709 2022/10/12 16:27:22 - mmengine - INFO - Epoch(train) [94][500/586] lr: 5.000000e-03 eta: 6:02:29 time: 0.328720 data_time: 0.050787 memory: 4465 loss_kpt: 90.804563 acc_pose: 0.796537 loss: 90.804563 2022/10/12 16:27:23 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:27:40 - mmengine - INFO - Epoch(train) [94][550/586] lr: 5.000000e-03 eta: 6:02:14 time: 0.342807 data_time: 0.052011 memory: 4465 loss_kpt: 89.131769 acc_pose: 0.792342 loss: 89.131769 2022/10/12 16:27:51 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:28:10 - mmengine - INFO - Epoch(train) [95][50/586] lr: 5.000000e-03 eta: 6:01:35 time: 0.361094 data_time: 0.057350 memory: 4465 loss_kpt: 88.306723 acc_pose: 0.786317 loss: 88.306723 2022/10/12 16:28:26 - mmengine - INFO - Epoch(train) [95][100/586] lr: 5.000000e-03 eta: 6:01:20 time: 0.328947 data_time: 0.045019 memory: 4465 loss_kpt: 88.864070 acc_pose: 0.809047 loss: 88.864070 2022/10/12 16:28:42 - mmengine - INFO - Epoch(train) [95][150/586] lr: 5.000000e-03 eta: 6:01:04 time: 0.322454 data_time: 0.048084 memory: 4465 loss_kpt: 89.982771 acc_pose: 0.765560 loss: 89.982771 2022/10/12 16:28:58 - mmengine - INFO - Epoch(train) [95][200/586] lr: 5.000000e-03 eta: 6:00:48 time: 0.320006 data_time: 0.044823 memory: 4465 loss_kpt: 88.456231 acc_pose: 0.845206 loss: 88.456231 2022/10/12 16:29:14 - mmengine - INFO - Epoch(train) [95][250/586] lr: 5.000000e-03 eta: 6:00:32 time: 0.322314 data_time: 0.047466 memory: 4465 loss_kpt: 89.047122 acc_pose: 0.733758 loss: 89.047122 2022/10/12 16:29:30 - mmengine - INFO - Epoch(train) [95][300/586] lr: 5.000000e-03 eta: 6:00:16 time: 0.316837 data_time: 0.045750 memory: 4465 loss_kpt: 89.871106 acc_pose: 0.801760 loss: 89.871106 2022/10/12 16:29:46 - mmengine - INFO - Epoch(train) [95][350/586] lr: 5.000000e-03 eta: 6:00:00 time: 0.323947 data_time: 0.047695 memory: 4465 loss_kpt: 88.401114 acc_pose: 0.819409 loss: 88.401114 2022/10/12 16:30:03 - mmengine - INFO - Epoch(train) [95][400/586] lr: 5.000000e-03 eta: 5:59:45 time: 0.328161 data_time: 0.048309 memory: 4465 loss_kpt: 89.888086 acc_pose: 0.805222 loss: 89.888086 2022/10/12 16:30:19 - mmengine - INFO - Epoch(train) [95][450/586] lr: 5.000000e-03 eta: 5:59:29 time: 0.323794 data_time: 0.046198 memory: 4465 loss_kpt: 89.918563 acc_pose: 0.779504 loss: 89.918563 2022/10/12 16:30:35 - mmengine - INFO - Epoch(train) [95][500/586] lr: 5.000000e-03 eta: 5:59:14 time: 0.328231 data_time: 0.049167 memory: 4465 loss_kpt: 89.882556 acc_pose: 0.763042 loss: 89.882556 2022/10/12 16:30:52 - mmengine - INFO - Epoch(train) [95][550/586] lr: 5.000000e-03 eta: 5:58:58 time: 0.331823 data_time: 0.047888 memory: 4465 loss_kpt: 88.700871 acc_pose: 0.788562 loss: 88.700871 2022/10/12 16:31:04 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:31:21 - mmengine - INFO - Epoch(train) [96][50/586] lr: 5.000000e-03 eta: 5:58:18 time: 0.339472 data_time: 0.056360 memory: 4465 loss_kpt: 89.101950 acc_pose: 0.812438 loss: 89.101950 2022/10/12 16:31:37 - mmengine - INFO - Epoch(train) [96][100/586] lr: 5.000000e-03 eta: 5:58:03 time: 0.327694 data_time: 0.050319 memory: 4465 loss_kpt: 90.940790 acc_pose: 0.769797 loss: 90.940790 2022/10/12 16:31:54 - mmengine - INFO - Epoch(train) [96][150/586] lr: 5.000000e-03 eta: 5:57:47 time: 0.323907 data_time: 0.046491 memory: 4465 loss_kpt: 89.703572 acc_pose: 0.787776 loss: 89.703572 2022/10/12 16:32:10 - mmengine - INFO - Epoch(train) [96][200/586] lr: 5.000000e-03 eta: 5:57:31 time: 0.323667 data_time: 0.050884 memory: 4465 loss_kpt: 87.645378 acc_pose: 0.753524 loss: 87.645378 2022/10/12 16:32:26 - mmengine - INFO - Epoch(train) [96][250/586] lr: 5.000000e-03 eta: 5:57:16 time: 0.326018 data_time: 0.054849 memory: 4465 loss_kpt: 90.545145 acc_pose: 0.737041 loss: 90.545145 2022/10/12 16:32:42 - mmengine - INFO - Epoch(train) [96][300/586] lr: 5.000000e-03 eta: 5:57:00 time: 0.319782 data_time: 0.046609 memory: 4465 loss_kpt: 90.035780 acc_pose: 0.777673 loss: 90.035780 2022/10/12 16:32:53 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:33:00 - mmengine - INFO - Epoch(train) [96][350/586] lr: 5.000000e-03 eta: 5:56:46 time: 0.353228 data_time: 0.052906 memory: 4465 loss_kpt: 90.553009 acc_pose: 0.831477 loss: 90.553009 2022/10/12 16:33:16 - mmengine - INFO - Epoch(train) [96][400/586] lr: 5.000000e-03 eta: 5:56:30 time: 0.325776 data_time: 0.055380 memory: 4465 loss_kpt: 89.443209 acc_pose: 0.825460 loss: 89.443209 2022/10/12 16:33:33 - mmengine - INFO - Epoch(train) [96][450/586] lr: 5.000000e-03 eta: 5:56:15 time: 0.331056 data_time: 0.050860 memory: 4465 loss_kpt: 89.418643 acc_pose: 0.786446 loss: 89.418643 2022/10/12 16:33:49 - mmengine - INFO - Epoch(train) [96][500/586] lr: 5.000000e-03 eta: 5:56:00 time: 0.335185 data_time: 0.053772 memory: 4465 loss_kpt: 90.646367 acc_pose: 0.722698 loss: 90.646367 2022/10/12 16:34:06 - mmengine - INFO - Epoch(train) [96][550/586] lr: 5.000000e-03 eta: 5:55:45 time: 0.328593 data_time: 0.050491 memory: 4465 loss_kpt: 89.162204 acc_pose: 0.842200 loss: 89.162204 2022/10/12 16:34:18 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:34:35 - mmengine - INFO - Epoch(train) [97][50/586] lr: 5.000000e-03 eta: 5:55:06 time: 0.355258 data_time: 0.063099 memory: 4465 loss_kpt: 89.028189 acc_pose: 0.758117 loss: 89.028189 2022/10/12 16:34:52 - mmengine - INFO - Epoch(train) [97][100/586] lr: 5.000000e-03 eta: 5:54:51 time: 0.339487 data_time: 0.053956 memory: 4465 loss_kpt: 90.539967 acc_pose: 0.828144 loss: 90.539967 2022/10/12 16:35:09 - mmengine - INFO - Epoch(train) [97][150/586] lr: 5.000000e-03 eta: 5:54:36 time: 0.341937 data_time: 0.051483 memory: 4465 loss_kpt: 88.691326 acc_pose: 0.809460 loss: 88.691326 2022/10/12 16:35:26 - mmengine - INFO - Epoch(train) [97][200/586] lr: 5.000000e-03 eta: 5:54:22 time: 0.339910 data_time: 0.051191 memory: 4465 loss_kpt: 88.647777 acc_pose: 0.776802 loss: 88.647777 2022/10/12 16:35:43 - mmengine - INFO - Epoch(train) [97][250/586] lr: 5.000000e-03 eta: 5:54:07 time: 0.334398 data_time: 0.048353 memory: 4465 loss_kpt: 89.774978 acc_pose: 0.775174 loss: 89.774978 2022/10/12 16:36:00 - mmengine - INFO - Epoch(train) [97][300/586] lr: 5.000000e-03 eta: 5:53:52 time: 0.342475 data_time: 0.050736 memory: 4465 loss_kpt: 89.558907 acc_pose: 0.753908 loss: 89.558907 2022/10/12 16:36:17 - mmengine - INFO - Epoch(train) [97][350/586] lr: 5.000000e-03 eta: 5:53:37 time: 0.341399 data_time: 0.056281 memory: 4465 loss_kpt: 90.207995 acc_pose: 0.795976 loss: 90.207995 2022/10/12 16:36:34 - mmengine - INFO - Epoch(train) [97][400/586] lr: 5.000000e-03 eta: 5:53:22 time: 0.333560 data_time: 0.049842 memory: 4465 loss_kpt: 90.079760 acc_pose: 0.780775 loss: 90.079760 2022/10/12 16:36:51 - mmengine - INFO - Epoch(train) [97][450/586] lr: 5.000000e-03 eta: 5:53:07 time: 0.331964 data_time: 0.048695 memory: 4465 loss_kpt: 87.440427 acc_pose: 0.860928 loss: 87.440427 2022/10/12 16:37:07 - mmengine - INFO - Epoch(train) [97][500/586] lr: 5.000000e-03 eta: 5:52:52 time: 0.330681 data_time: 0.047192 memory: 4465 loss_kpt: 88.760899 acc_pose: 0.743617 loss: 88.760899 2022/10/12 16:37:24 - mmengine - INFO - Epoch(train) [97][550/586] lr: 5.000000e-03 eta: 5:52:37 time: 0.333476 data_time: 0.053740 memory: 4465 loss_kpt: 87.439686 acc_pose: 0.809907 loss: 87.439686 2022/10/12 16:37:36 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:37:53 - mmengine - INFO - Epoch(train) [98][50/586] lr: 5.000000e-03 eta: 5:51:58 time: 0.353635 data_time: 0.067241 memory: 4465 loss_kpt: 89.697990 acc_pose: 0.823662 loss: 89.697990 2022/10/12 16:38:10 - mmengine - INFO - Epoch(train) [98][100/586] lr: 5.000000e-03 eta: 5:51:43 time: 0.334259 data_time: 0.053970 memory: 4465 loss_kpt: 88.323381 acc_pose: 0.826087 loss: 88.323381 2022/10/12 16:38:28 - mmengine - INFO - Epoch(train) [98][150/586] lr: 5.000000e-03 eta: 5:51:28 time: 0.348819 data_time: 0.054067 memory: 4465 loss_kpt: 88.956068 acc_pose: 0.766626 loss: 88.956068 2022/10/12 16:38:30 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:38:45 - mmengine - INFO - Epoch(train) [98][200/586] lr: 5.000000e-03 eta: 5:51:14 time: 0.345800 data_time: 0.054197 memory: 4465 loss_kpt: 88.018971 acc_pose: 0.834306 loss: 88.018971 2022/10/12 16:39:03 - mmengine - INFO - Epoch(train) [98][250/586] lr: 5.000000e-03 eta: 5:51:00 time: 0.351989 data_time: 0.056660 memory: 4465 loss_kpt: 91.068002 acc_pose: 0.832772 loss: 91.068002 2022/10/12 16:39:21 - mmengine - INFO - Epoch(train) [98][300/586] lr: 5.000000e-03 eta: 5:50:46 time: 0.360117 data_time: 0.056648 memory: 4465 loss_kpt: 87.789933 acc_pose: 0.855278 loss: 87.789933 2022/10/12 16:39:39 - mmengine - INFO - Epoch(train) [98][350/586] lr: 5.000000e-03 eta: 5:50:33 time: 0.358913 data_time: 0.053320 memory: 4465 loss_kpt: 89.293541 acc_pose: 0.834090 loss: 89.293541 2022/10/12 16:39:57 - mmengine - INFO - Epoch(train) [98][400/586] lr: 5.000000e-03 eta: 5:50:19 time: 0.362850 data_time: 0.065384 memory: 4465 loss_kpt: 88.361140 acc_pose: 0.818410 loss: 88.361140 2022/10/12 16:40:14 - mmengine - INFO - Epoch(train) [98][450/586] lr: 5.000000e-03 eta: 5:50:05 time: 0.354023 data_time: 0.055094 memory: 4465 loss_kpt: 89.091225 acc_pose: 0.823814 loss: 89.091225 2022/10/12 16:40:31 - mmengine - INFO - Epoch(train) [98][500/586] lr: 5.000000e-03 eta: 5:49:50 time: 0.339014 data_time: 0.049265 memory: 4465 loss_kpt: 89.431331 acc_pose: 0.783651 loss: 89.431331 2022/10/12 16:40:48 - mmengine - INFO - Epoch(train) [98][550/586] lr: 5.000000e-03 eta: 5:49:36 time: 0.342747 data_time: 0.053845 memory: 4465 loss_kpt: 89.517388 acc_pose: 0.842862 loss: 89.517388 2022/10/12 16:41:00 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:41:18 - mmengine - INFO - Epoch(train) [99][50/586] lr: 5.000000e-03 eta: 5:48:57 time: 0.354044 data_time: 0.056565 memory: 4465 loss_kpt: 90.300312 acc_pose: 0.766737 loss: 90.300312 2022/10/12 16:41:35 - mmengine - INFO - Epoch(train) [99][100/586] lr: 5.000000e-03 eta: 5:48:42 time: 0.341929 data_time: 0.046327 memory: 4465 loss_kpt: 88.893728 acc_pose: 0.736917 loss: 88.893728 2022/10/12 16:41:53 - mmengine - INFO - Epoch(train) [99][150/586] lr: 5.000000e-03 eta: 5:48:29 time: 0.357041 data_time: 0.049388 memory: 4465 loss_kpt: 89.768465 acc_pose: 0.802649 loss: 89.768465 2022/10/12 16:42:11 - mmengine - INFO - Epoch(train) [99][200/586] lr: 5.000000e-03 eta: 5:48:14 time: 0.349005 data_time: 0.050266 memory: 4465 loss_kpt: 89.734515 acc_pose: 0.790672 loss: 89.734515 2022/10/12 16:42:28 - mmengine - INFO - Epoch(train) [99][250/586] lr: 5.000000e-03 eta: 5:48:00 time: 0.351591 data_time: 0.051003 memory: 4465 loss_kpt: 88.516202 acc_pose: 0.811059 loss: 88.516202 2022/10/12 16:42:46 - mmengine - INFO - Epoch(train) [99][300/586] lr: 5.000000e-03 eta: 5:47:46 time: 0.358211 data_time: 0.049064 memory: 4465 loss_kpt: 89.559283 acc_pose: 0.827842 loss: 89.559283 2022/10/12 16:43:03 - mmengine - INFO - Epoch(train) [99][350/586] lr: 5.000000e-03 eta: 5:47:32 time: 0.339309 data_time: 0.047666 memory: 4465 loss_kpt: 87.587709 acc_pose: 0.823339 loss: 87.587709 2022/10/12 16:43:20 - mmengine - INFO - Epoch(train) [99][400/586] lr: 5.000000e-03 eta: 5:47:17 time: 0.339490 data_time: 0.043608 memory: 4465 loss_kpt: 88.966115 acc_pose: 0.794011 loss: 88.966115 2022/10/12 16:43:37 - mmengine - INFO - Epoch(train) [99][450/586] lr: 5.000000e-03 eta: 5:47:02 time: 0.338686 data_time: 0.051767 memory: 4465 loss_kpt: 91.687489 acc_pose: 0.801288 loss: 91.687489 2022/10/12 16:43:53 - mmengine - INFO - Epoch(train) [99][500/586] lr: 5.000000e-03 eta: 5:46:46 time: 0.326758 data_time: 0.047050 memory: 4465 loss_kpt: 87.661040 acc_pose: 0.770965 loss: 87.661040 2022/10/12 16:44:09 - mmengine - INFO - Epoch(train) [99][550/586] lr: 5.000000e-03 eta: 5:46:30 time: 0.322492 data_time: 0.050492 memory: 4465 loss_kpt: 88.597303 acc_pose: 0.777668 loss: 88.597303 2022/10/12 16:44:17 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:44:21 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:44:39 - mmengine - INFO - Epoch(train) [100][50/586] lr: 5.000000e-03 eta: 5:45:52 time: 0.360797 data_time: 0.063754 memory: 4465 loss_kpt: 89.258058 acc_pose: 0.841330 loss: 89.258058 2022/10/12 16:44:56 - mmengine - INFO - Epoch(train) [100][100/586] lr: 5.000000e-03 eta: 5:45:37 time: 0.337543 data_time: 0.051308 memory: 4465 loss_kpt: 87.882829 acc_pose: 0.753514 loss: 87.882829 2022/10/12 16:45:13 - mmengine - INFO - Epoch(train) [100][150/586] lr: 5.000000e-03 eta: 5:45:23 time: 0.344531 data_time: 0.051883 memory: 4465 loss_kpt: 88.368404 acc_pose: 0.754980 loss: 88.368404 2022/10/12 16:45:30 - mmengine - INFO - Epoch(train) [100][200/586] lr: 5.000000e-03 eta: 5:45:08 time: 0.340699 data_time: 0.056188 memory: 4465 loss_kpt: 87.071779 acc_pose: 0.787845 loss: 87.071779 2022/10/12 16:45:47 - mmengine - INFO - Epoch(train) [100][250/586] lr: 5.000000e-03 eta: 5:44:54 time: 0.344990 data_time: 0.053271 memory: 4465 loss_kpt: 89.265094 acc_pose: 0.800306 loss: 89.265094 2022/10/12 16:46:04 - mmengine - INFO - Epoch(train) [100][300/586] lr: 5.000000e-03 eta: 5:44:38 time: 0.329629 data_time: 0.050653 memory: 4465 loss_kpt: 90.346924 acc_pose: 0.760026 loss: 90.346924 2022/10/12 16:46:20 - mmengine - INFO - Epoch(train) [100][350/586] lr: 5.000000e-03 eta: 5:44:23 time: 0.333458 data_time: 0.052018 memory: 4465 loss_kpt: 89.117913 acc_pose: 0.760514 loss: 89.117913 2022/10/12 16:46:37 - mmengine - INFO - Epoch(train) [100][400/586] lr: 5.000000e-03 eta: 5:44:08 time: 0.333470 data_time: 0.052329 memory: 4465 loss_kpt: 89.827785 acc_pose: 0.801019 loss: 89.827785 2022/10/12 16:46:54 - mmengine - INFO - Epoch(train) [100][450/586] lr: 5.000000e-03 eta: 5:43:53 time: 0.333016 data_time: 0.053727 memory: 4465 loss_kpt: 90.185855 acc_pose: 0.812975 loss: 90.185855 2022/10/12 16:47:11 - mmengine - INFO - Epoch(train) [100][500/586] lr: 5.000000e-03 eta: 5:43:38 time: 0.337497 data_time: 0.049029 memory: 4465 loss_kpt: 87.927805 acc_pose: 0.735483 loss: 87.927805 2022/10/12 16:47:27 - mmengine - INFO - Epoch(train) [100][550/586] lr: 5.000000e-03 eta: 5:43:23 time: 0.336142 data_time: 0.055081 memory: 4465 loss_kpt: 89.014139 acc_pose: 0.789123 loss: 89.014139 2022/10/12 16:47:39 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:47:39 - mmengine - INFO - Saving checkpoint at 100 epochs 2022/10/12 16:47:49 - mmengine - INFO - Epoch(val) [100][50/407] eta: 0:00:48 time: 0.135385 data_time: 0.013964 memory: 4465 2022/10/12 16:47:55 - mmengine - INFO - Epoch(val) [100][100/407] eta: 0:00:38 time: 0.126846 data_time: 0.008492 memory: 1026 2022/10/12 16:48:01 - mmengine - INFO - Epoch(val) [100][150/407] eta: 0:00:32 time: 0.127334 data_time: 0.008309 memory: 1026 2022/10/12 16:48:08 - mmengine - INFO - Epoch(val) [100][200/407] eta: 0:00:28 time: 0.137453 data_time: 0.018247 memory: 1026 2022/10/12 16:48:15 - mmengine - INFO - Epoch(val) [100][250/407] eta: 0:00:20 time: 0.127795 data_time: 0.008618 memory: 1026 2022/10/12 16:48:21 - mmengine - INFO - Epoch(val) [100][300/407] eta: 0:00:13 time: 0.127904 data_time: 0.008330 memory: 1026 2022/10/12 16:48:27 - mmengine - INFO - Epoch(val) [100][350/407] eta: 0:00:07 time: 0.127771 data_time: 0.008583 memory: 1026 2022/10/12 16:48:34 - mmengine - INFO - Epoch(val) [100][400/407] eta: 0:00:00 time: 0.124189 data_time: 0.007926 memory: 1026 2022/10/12 16:48:47 - mmengine - INFO - Evaluating CocoMetric... 2022/10/12 16:49:03 - mmengine - INFO - Epoch(val) [100][407/407] coco/AP: 0.686280 coco/AP .5: 0.881232 coco/AP .75: 0.760657 coco/AP (M): 0.655449 coco/AP (L): 0.745066 coco/AR: 0.755841 coco/AR .5: 0.922387 coco/AR .75: 0.819427 coco/AR (M): 0.710926 coco/AR (L): 0.817577 2022/10/12 16:49:03 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/liqikai/openmmlab/pt112cu113py38/mmpose/work_dirs/20221012/rsn50/best_coco/AP_epoch_80.pth is removed 2022/10/12 16:49:04 - mmengine - INFO - The best checkpoint with 0.6863 coco/AP at 100 epoch is saved to best_coco/AP_epoch_100.pth. 2022/10/12 16:49:22 - mmengine - INFO - Epoch(train) [101][50/586] lr: 5.000000e-03 eta: 5:42:44 time: 0.353917 data_time: 0.067092 memory: 4465 loss_kpt: 89.650884 acc_pose: 0.684002 loss: 89.650884 2022/10/12 16:49:39 - mmengine - INFO - Epoch(train) [101][100/586] lr: 5.000000e-03 eta: 5:42:29 time: 0.332109 data_time: 0.048372 memory: 4465 loss_kpt: 89.993212 acc_pose: 0.857022 loss: 89.993212 2022/10/12 16:49:56 - mmengine - INFO - Epoch(train) [101][150/586] lr: 5.000000e-03 eta: 5:42:14 time: 0.337999 data_time: 0.048744 memory: 4465 loss_kpt: 89.065932 acc_pose: 0.782023 loss: 89.065932 2022/10/12 16:50:12 - mmengine - INFO - Epoch(train) [101][200/586] lr: 5.000000e-03 eta: 5:41:59 time: 0.334417 data_time: 0.048163 memory: 4465 loss_kpt: 89.027248 acc_pose: 0.798727 loss: 89.027248 2022/10/12 16:50:30 - mmengine - INFO - Epoch(train) [101][250/586] lr: 5.000000e-03 eta: 5:41:45 time: 0.345921 data_time: 0.049197 memory: 4465 loss_kpt: 89.293176 acc_pose: 0.752594 loss: 89.293176 2022/10/12 16:50:46 - mmengine - INFO - Epoch(train) [101][300/586] lr: 5.000000e-03 eta: 5:41:29 time: 0.331376 data_time: 0.046134 memory: 4465 loss_kpt: 90.063199 acc_pose: 0.773876 loss: 90.063199 2022/10/12 16:51:03 - mmengine - INFO - Epoch(train) [101][350/586] lr: 5.000000e-03 eta: 5:41:14 time: 0.331029 data_time: 0.052305 memory: 4465 loss_kpt: 87.650117 acc_pose: 0.775509 loss: 87.650117 2022/10/12 16:51:20 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:51:20 - mmengine - INFO - Epoch(train) [101][400/586] lr: 5.000000e-03 eta: 5:40:59 time: 0.335171 data_time: 0.046800 memory: 4465 loss_kpt: 89.230160 acc_pose: 0.740839 loss: 89.230160 2022/10/12 16:51:37 - mmengine - INFO - Epoch(train) [101][450/586] lr: 5.000000e-03 eta: 5:40:44 time: 0.342205 data_time: 0.050571 memory: 4465 loss_kpt: 88.803752 acc_pose: 0.803507 loss: 88.803752 2022/10/12 16:51:53 - mmengine - INFO - Epoch(train) [101][500/586] lr: 5.000000e-03 eta: 5:40:29 time: 0.333161 data_time: 0.048593 memory: 4465 loss_kpt: 89.161921 acc_pose: 0.784268 loss: 89.161921 2022/10/12 16:52:10 - mmengine - INFO - Epoch(train) [101][550/586] lr: 5.000000e-03 eta: 5:40:13 time: 0.331335 data_time: 0.049368 memory: 4465 loss_kpt: 88.978513 acc_pose: 0.808032 loss: 88.978513 2022/10/12 16:52:21 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:52:39 - mmengine - INFO - Epoch(train) [102][50/586] lr: 5.000000e-03 eta: 5:39:36 time: 0.355277 data_time: 0.061136 memory: 4465 loss_kpt: 88.779380 acc_pose: 0.860148 loss: 88.779380 2022/10/12 16:52:56 - mmengine - INFO - Epoch(train) [102][100/586] lr: 5.000000e-03 eta: 5:39:21 time: 0.344323 data_time: 0.050284 memory: 4465 loss_kpt: 88.750854 acc_pose: 0.844681 loss: 88.750854 2022/10/12 16:53:14 - mmengine - INFO - Epoch(train) [102][150/586] lr: 5.000000e-03 eta: 5:39:07 time: 0.348982 data_time: 0.052082 memory: 4465 loss_kpt: 90.253975 acc_pose: 0.770819 loss: 90.253975 2022/10/12 16:53:32 - mmengine - INFO - Epoch(train) [102][200/586] lr: 5.000000e-03 eta: 5:38:52 time: 0.354473 data_time: 0.048227 memory: 4465 loss_kpt: 89.718184 acc_pose: 0.794291 loss: 89.718184 2022/10/12 16:53:49 - mmengine - INFO - Epoch(train) [102][250/586] lr: 5.000000e-03 eta: 5:38:38 time: 0.344964 data_time: 0.049121 memory: 4465 loss_kpt: 88.625742 acc_pose: 0.856971 loss: 88.625742 2022/10/12 16:54:06 - mmengine - INFO - Epoch(train) [102][300/586] lr: 5.000000e-03 eta: 5:38:23 time: 0.336936 data_time: 0.052549 memory: 4465 loss_kpt: 89.407937 acc_pose: 0.778957 loss: 89.407937 2022/10/12 16:54:23 - mmengine - INFO - Epoch(train) [102][350/586] lr: 5.000000e-03 eta: 5:38:08 time: 0.346927 data_time: 0.051786 memory: 4465 loss_kpt: 89.992582 acc_pose: 0.873460 loss: 89.992582 2022/10/12 16:54:40 - mmengine - INFO - Epoch(train) [102][400/586] lr: 5.000000e-03 eta: 5:37:54 time: 0.343290 data_time: 0.050512 memory: 4465 loss_kpt: 89.249183 acc_pose: 0.825561 loss: 89.249183 2022/10/12 16:54:58 - mmengine - INFO - Epoch(train) [102][450/586] lr: 5.000000e-03 eta: 5:37:39 time: 0.351535 data_time: 0.053105 memory: 4465 loss_kpt: 89.117632 acc_pose: 0.714157 loss: 89.117632 2022/10/12 16:55:15 - mmengine - INFO - Epoch(train) [102][500/586] lr: 5.000000e-03 eta: 5:37:25 time: 0.345359 data_time: 0.050346 memory: 4465 loss_kpt: 88.631987 acc_pose: 0.759084 loss: 88.631987 2022/10/12 16:55:32 - mmengine - INFO - Epoch(train) [102][550/586] lr: 5.000000e-03 eta: 5:37:10 time: 0.340637 data_time: 0.050641 memory: 4465 loss_kpt: 89.830299 acc_pose: 0.841982 loss: 89.830299 2022/10/12 16:55:44 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:56:02 - mmengine - INFO - Epoch(train) [103][50/586] lr: 5.000000e-03 eta: 5:36:32 time: 0.352739 data_time: 0.064024 memory: 4465 loss_kpt: 88.606842 acc_pose: 0.813152 loss: 88.606842 2022/10/12 16:56:19 - mmengine - INFO - Epoch(train) [103][100/586] lr: 5.000000e-03 eta: 5:36:17 time: 0.338083 data_time: 0.050232 memory: 4465 loss_kpt: 87.871885 acc_pose: 0.835891 loss: 87.871885 2022/10/12 16:56:36 - mmengine - INFO - Epoch(train) [103][150/586] lr: 5.000000e-03 eta: 5:36:03 time: 0.348234 data_time: 0.054809 memory: 4465 loss_kpt: 88.297209 acc_pose: 0.805855 loss: 88.297209 2022/10/12 16:56:53 - mmengine - INFO - Epoch(train) [103][200/586] lr: 5.000000e-03 eta: 5:35:48 time: 0.338151 data_time: 0.054269 memory: 4465 loss_kpt: 88.983115 acc_pose: 0.850475 loss: 88.983115 2022/10/12 16:57:02 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:57:10 - mmengine - INFO - Epoch(train) [103][250/586] lr: 5.000000e-03 eta: 5:35:33 time: 0.336742 data_time: 0.050672 memory: 4465 loss_kpt: 89.623812 acc_pose: 0.725435 loss: 89.623812 2022/10/12 16:57:26 - mmengine - INFO - Epoch(train) [103][300/586] lr: 5.000000e-03 eta: 5:35:17 time: 0.333050 data_time: 0.054159 memory: 4465 loss_kpt: 90.523983 acc_pose: 0.785756 loss: 90.523983 2022/10/12 16:57:43 - mmengine - INFO - Epoch(train) [103][350/586] lr: 5.000000e-03 eta: 5:35:02 time: 0.330136 data_time: 0.052708 memory: 4465 loss_kpt: 88.797907 acc_pose: 0.776407 loss: 88.797907 2022/10/12 16:57:59 - mmengine - INFO - Epoch(train) [103][400/586] lr: 5.000000e-03 eta: 5:34:46 time: 0.325631 data_time: 0.048151 memory: 4465 loss_kpt: 89.363676 acc_pose: 0.787143 loss: 89.363676 2022/10/12 16:58:15 - mmengine - INFO - Epoch(train) [103][450/586] lr: 5.000000e-03 eta: 5:34:31 time: 0.323430 data_time: 0.050264 memory: 4465 loss_kpt: 88.324709 acc_pose: 0.821704 loss: 88.324709 2022/10/12 16:58:32 - mmengine - INFO - Epoch(train) [103][500/586] lr: 5.000000e-03 eta: 5:34:15 time: 0.328750 data_time: 0.046844 memory: 4465 loss_kpt: 88.819639 acc_pose: 0.777782 loss: 88.819639 2022/10/12 16:58:49 - mmengine - INFO - Epoch(train) [103][550/586] lr: 5.000000e-03 eta: 5:34:00 time: 0.337873 data_time: 0.050777 memory: 4465 loss_kpt: 89.741626 acc_pose: 0.727699 loss: 89.741626 2022/10/12 16:59:01 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 16:59:18 - mmengine - INFO - Epoch(train) [104][50/586] lr: 5.000000e-03 eta: 5:33:22 time: 0.351815 data_time: 0.059695 memory: 4465 loss_kpt: 89.656423 acc_pose: 0.818062 loss: 89.656423 2022/10/12 16:59:35 - mmengine - INFO - Epoch(train) [104][100/586] lr: 5.000000e-03 eta: 5:33:08 time: 0.340582 data_time: 0.050268 memory: 4465 loss_kpt: 88.436017 acc_pose: 0.752112 loss: 88.436017 2022/10/12 16:59:53 - mmengine - INFO - Epoch(train) [104][150/586] lr: 5.000000e-03 eta: 5:32:53 time: 0.352640 data_time: 0.053135 memory: 4465 loss_kpt: 88.180958 acc_pose: 0.834189 loss: 88.180958 2022/10/12 17:00:11 - mmengine - INFO - Epoch(train) [104][200/586] lr: 5.000000e-03 eta: 5:32:39 time: 0.351986 data_time: 0.051185 memory: 4465 loss_kpt: 88.697388 acc_pose: 0.802537 loss: 88.697388 2022/10/12 17:00:28 - mmengine - INFO - Epoch(train) [104][250/586] lr: 5.000000e-03 eta: 5:32:25 time: 0.354174 data_time: 0.056664 memory: 4465 loss_kpt: 87.248935 acc_pose: 0.739109 loss: 87.248935 2022/10/12 17:00:46 - mmengine - INFO - Epoch(train) [104][300/586] lr: 5.000000e-03 eta: 5:32:10 time: 0.348479 data_time: 0.052424 memory: 4465 loss_kpt: 87.675987 acc_pose: 0.851291 loss: 87.675987 2022/10/12 17:01:03 - mmengine - INFO - Epoch(train) [104][350/586] lr: 5.000000e-03 eta: 5:31:56 time: 0.345782 data_time: 0.049794 memory: 4465 loss_kpt: 88.061530 acc_pose: 0.776603 loss: 88.061530 2022/10/12 17:01:20 - mmengine - INFO - Epoch(train) [104][400/586] lr: 5.000000e-03 eta: 5:31:41 time: 0.343140 data_time: 0.049384 memory: 4465 loss_kpt: 89.171264 acc_pose: 0.705960 loss: 89.171264 2022/10/12 17:01:38 - mmengine - INFO - Epoch(train) [104][450/586] lr: 5.000000e-03 eta: 5:31:26 time: 0.346837 data_time: 0.054267 memory: 4465 loss_kpt: 88.351298 acc_pose: 0.831428 loss: 88.351298 2022/10/12 17:01:55 - mmengine - INFO - Epoch(train) [104][500/586] lr: 5.000000e-03 eta: 5:31:12 time: 0.344622 data_time: 0.053311 memory: 4465 loss_kpt: 88.420887 acc_pose: 0.755669 loss: 88.420887 2022/10/12 17:02:12 - mmengine - INFO - Epoch(train) [104][550/586] lr: 5.000000e-03 eta: 5:30:57 time: 0.350223 data_time: 0.055926 memory: 4465 loss_kpt: 89.533445 acc_pose: 0.837911 loss: 89.533445 2022/10/12 17:02:25 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:02:43 - mmengine - INFO - Epoch(train) [105][50/586] lr: 5.000000e-03 eta: 5:30:20 time: 0.355047 data_time: 0.062011 memory: 4465 loss_kpt: 88.521205 acc_pose: 0.712076 loss: 88.521205 2022/10/12 17:02:45 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:03:00 - mmengine - INFO - Epoch(train) [105][100/586] lr: 5.000000e-03 eta: 5:30:05 time: 0.344781 data_time: 0.052223 memory: 4465 loss_kpt: 89.796317 acc_pose: 0.858906 loss: 89.796317 2022/10/12 17:03:17 - mmengine - INFO - Epoch(train) [105][150/586] lr: 5.000000e-03 eta: 5:29:51 time: 0.346348 data_time: 0.050709 memory: 4465 loss_kpt: 89.127598 acc_pose: 0.781157 loss: 89.127598 2022/10/12 17:03:34 - mmengine - INFO - Epoch(train) [105][200/586] lr: 5.000000e-03 eta: 5:29:35 time: 0.332531 data_time: 0.050025 memory: 4465 loss_kpt: 88.611680 acc_pose: 0.816359 loss: 88.611680 2022/10/12 17:03:51 - mmengine - INFO - Epoch(train) [105][250/586] lr: 5.000000e-03 eta: 5:29:21 time: 0.342825 data_time: 0.051326 memory: 4465 loss_kpt: 87.838509 acc_pose: 0.805039 loss: 87.838509 2022/10/12 17:04:09 - mmengine - INFO - Epoch(train) [105][300/586] lr: 5.000000e-03 eta: 5:29:07 time: 0.358361 data_time: 0.046360 memory: 4465 loss_kpt: 87.996691 acc_pose: 0.831952 loss: 87.996691 2022/10/12 17:04:27 - mmengine - INFO - Epoch(train) [105][350/586] lr: 5.000000e-03 eta: 5:28:52 time: 0.355744 data_time: 0.053147 memory: 4465 loss_kpt: 89.195740 acc_pose: 0.858908 loss: 89.195740 2022/10/12 17:04:45 - mmengine - INFO - Epoch(train) [105][400/586] lr: 5.000000e-03 eta: 5:28:39 time: 0.361644 data_time: 0.051603 memory: 4465 loss_kpt: 88.476146 acc_pose: 0.787015 loss: 88.476146 2022/10/12 17:05:03 - mmengine - INFO - Epoch(train) [105][450/586] lr: 5.000000e-03 eta: 5:28:25 time: 0.358161 data_time: 0.049058 memory: 4465 loss_kpt: 88.410770 acc_pose: 0.771692 loss: 88.410770 2022/10/12 17:05:20 - mmengine - INFO - Epoch(train) [105][500/586] lr: 5.000000e-03 eta: 5:28:10 time: 0.354214 data_time: 0.048971 memory: 4465 loss_kpt: 88.190058 acc_pose: 0.813143 loss: 88.190058 2022/10/12 17:05:39 - mmengine - INFO - Epoch(train) [105][550/586] lr: 5.000000e-03 eta: 5:27:57 time: 0.374159 data_time: 0.055334 memory: 4465 loss_kpt: 88.077962 acc_pose: 0.811851 loss: 88.077962 2022/10/12 17:05:51 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:06:09 - mmengine - INFO - Epoch(train) [106][50/586] lr: 5.000000e-03 eta: 5:27:20 time: 0.351412 data_time: 0.062597 memory: 4465 loss_kpt: 87.997801 acc_pose: 0.780191 loss: 87.997801 2022/10/12 17:06:26 - mmengine - INFO - Epoch(train) [106][100/586] lr: 5.000000e-03 eta: 5:27:05 time: 0.346837 data_time: 0.049875 memory: 4465 loss_kpt: 87.645775 acc_pose: 0.837915 loss: 87.645775 2022/10/12 17:06:44 - mmengine - INFO - Epoch(train) [106][150/586] lr: 5.000000e-03 eta: 5:26:51 time: 0.348236 data_time: 0.056371 memory: 4465 loss_kpt: 88.868564 acc_pose: 0.831561 loss: 88.868564 2022/10/12 17:07:01 - mmengine - INFO - Epoch(train) [106][200/586] lr: 5.000000e-03 eta: 5:26:36 time: 0.349710 data_time: 0.050949 memory: 4465 loss_kpt: 88.667917 acc_pose: 0.824800 loss: 88.667917 2022/10/12 17:07:19 - mmengine - INFO - Epoch(train) [106][250/586] lr: 5.000000e-03 eta: 5:26:21 time: 0.347510 data_time: 0.054712 memory: 4465 loss_kpt: 87.880140 acc_pose: 0.795367 loss: 87.880140 2022/10/12 17:07:35 - mmengine - INFO - Epoch(train) [106][300/586] lr: 5.000000e-03 eta: 5:26:06 time: 0.335459 data_time: 0.049152 memory: 4465 loss_kpt: 87.714434 acc_pose: 0.843968 loss: 87.714434 2022/10/12 17:07:52 - mmengine - INFO - Epoch(train) [106][350/586] lr: 5.000000e-03 eta: 5:25:51 time: 0.334971 data_time: 0.054237 memory: 4465 loss_kpt: 88.671355 acc_pose: 0.821115 loss: 88.671355 2022/10/12 17:08:09 - mmengine - INFO - Epoch(train) [106][400/586] lr: 5.000000e-03 eta: 5:25:36 time: 0.330234 data_time: 0.053141 memory: 4465 loss_kpt: 89.164854 acc_pose: 0.834150 loss: 89.164854 2022/10/12 17:08:25 - mmengine - INFO - Epoch(train) [106][450/586] lr: 5.000000e-03 eta: 5:25:20 time: 0.326837 data_time: 0.052513 memory: 4465 loss_kpt: 89.281938 acc_pose: 0.730211 loss: 89.281938 2022/10/12 17:08:32 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:08:41 - mmengine - INFO - Epoch(train) [106][500/586] lr: 5.000000e-03 eta: 5:25:04 time: 0.328120 data_time: 0.052751 memory: 4465 loss_kpt: 88.521805 acc_pose: 0.838751 loss: 88.521805 2022/10/12 17:08:58 - mmengine - INFO - Epoch(train) [106][550/586] lr: 5.000000e-03 eta: 5:24:49 time: 0.326165 data_time: 0.047255 memory: 4465 loss_kpt: 89.830743 acc_pose: 0.708092 loss: 89.830743 2022/10/12 17:09:09 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:09:27 - mmengine - INFO - Epoch(train) [107][50/586] lr: 5.000000e-03 eta: 5:24:11 time: 0.346938 data_time: 0.056779 memory: 4465 loss_kpt: 88.145664 acc_pose: 0.708573 loss: 88.145664 2022/10/12 17:09:44 - mmengine - INFO - Epoch(train) [107][100/586] lr: 5.000000e-03 eta: 5:23:57 time: 0.346152 data_time: 0.051866 memory: 4465 loss_kpt: 89.532282 acc_pose: 0.757707 loss: 89.532282 2022/10/12 17:10:01 - mmengine - INFO - Epoch(train) [107][150/586] lr: 5.000000e-03 eta: 5:23:42 time: 0.350200 data_time: 0.052744 memory: 4465 loss_kpt: 86.784040 acc_pose: 0.842312 loss: 86.784040 2022/10/12 17:10:18 - mmengine - INFO - Epoch(train) [107][200/586] lr: 5.000000e-03 eta: 5:23:27 time: 0.339248 data_time: 0.044854 memory: 4465 loss_kpt: 89.973770 acc_pose: 0.677032 loss: 89.973770 2022/10/12 17:10:35 - mmengine - INFO - Epoch(train) [107][250/586] lr: 5.000000e-03 eta: 5:23:12 time: 0.341696 data_time: 0.048395 memory: 4465 loss_kpt: 87.971918 acc_pose: 0.738842 loss: 87.971918 2022/10/12 17:10:52 - mmengine - INFO - Epoch(train) [107][300/586] lr: 5.000000e-03 eta: 5:22:57 time: 0.335499 data_time: 0.045821 memory: 4465 loss_kpt: 89.087517 acc_pose: 0.786777 loss: 89.087517 2022/10/12 17:11:09 - mmengine - INFO - Epoch(train) [107][350/586] lr: 5.000000e-03 eta: 5:22:42 time: 0.336960 data_time: 0.048861 memory: 4465 loss_kpt: 89.703216 acc_pose: 0.794618 loss: 89.703216 2022/10/12 17:11:25 - mmengine - INFO - Epoch(train) [107][400/586] lr: 5.000000e-03 eta: 5:22:26 time: 0.327511 data_time: 0.049930 memory: 4465 loss_kpt: 88.676399 acc_pose: 0.827511 loss: 88.676399 2022/10/12 17:11:42 - mmengine - INFO - Epoch(train) [107][450/586] lr: 5.000000e-03 eta: 5:22:11 time: 0.334561 data_time: 0.049144 memory: 4465 loss_kpt: 90.196052 acc_pose: 0.764237 loss: 90.196052 2022/10/12 17:11:59 - mmengine - INFO - Epoch(train) [107][500/586] lr: 5.000000e-03 eta: 5:21:56 time: 0.341159 data_time: 0.049699 memory: 4465 loss_kpt: 88.926367 acc_pose: 0.882527 loss: 88.926367 2022/10/12 17:12:16 - mmengine - INFO - Epoch(train) [107][550/586] lr: 5.000000e-03 eta: 5:21:41 time: 0.338722 data_time: 0.056218 memory: 4465 loss_kpt: 89.336472 acc_pose: 0.784284 loss: 89.336472 2022/10/12 17:12:28 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:12:47 - mmengine - INFO - Epoch(train) [108][50/586] lr: 5.000000e-03 eta: 5:21:05 time: 0.366128 data_time: 0.062138 memory: 4465 loss_kpt: 89.311820 acc_pose: 0.751156 loss: 89.311820 2022/10/12 17:13:03 - mmengine - INFO - Epoch(train) [108][100/586] lr: 5.000000e-03 eta: 5:20:50 time: 0.338937 data_time: 0.050863 memory: 4465 loss_kpt: 90.126483 acc_pose: 0.802395 loss: 90.126483 2022/10/12 17:13:21 - mmengine - INFO - Epoch(train) [108][150/586] lr: 5.000000e-03 eta: 5:20:35 time: 0.340224 data_time: 0.049166 memory: 4465 loss_kpt: 88.097688 acc_pose: 0.822345 loss: 88.097688 2022/10/12 17:13:37 - mmengine - INFO - Epoch(train) [108][200/586] lr: 5.000000e-03 eta: 5:20:20 time: 0.334113 data_time: 0.050996 memory: 4465 loss_kpt: 88.375270 acc_pose: 0.775429 loss: 88.375270 2022/10/12 17:13:54 - mmengine - INFO - Epoch(train) [108][250/586] lr: 5.000000e-03 eta: 5:20:04 time: 0.336596 data_time: 0.059804 memory: 4465 loss_kpt: 88.700739 acc_pose: 0.797717 loss: 88.700739 2022/10/12 17:14:11 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:14:11 - mmengine - INFO - Epoch(train) [108][300/586] lr: 5.000000e-03 eta: 5:19:50 time: 0.343043 data_time: 0.052170 memory: 4465 loss_kpt: 87.948175 acc_pose: 0.728722 loss: 87.948175 2022/10/12 17:14:28 - mmengine - INFO - Epoch(train) [108][350/586] lr: 5.000000e-03 eta: 5:19:35 time: 0.342576 data_time: 0.050169 memory: 4465 loss_kpt: 89.630642 acc_pose: 0.802487 loss: 89.630642 2022/10/12 17:14:45 - mmengine - INFO - Epoch(train) [108][400/586] lr: 5.000000e-03 eta: 5:19:19 time: 0.328506 data_time: 0.046175 memory: 4465 loss_kpt: 87.912739 acc_pose: 0.850972 loss: 87.912739 2022/10/12 17:15:01 - mmengine - INFO - Epoch(train) [108][450/586] lr: 5.000000e-03 eta: 5:19:04 time: 0.329292 data_time: 0.047686 memory: 4465 loss_kpt: 88.128168 acc_pose: 0.849682 loss: 88.128168 2022/10/12 17:15:18 - mmengine - INFO - Epoch(train) [108][500/586] lr: 5.000000e-03 eta: 5:18:48 time: 0.326854 data_time: 0.048834 memory: 4465 loss_kpt: 88.054946 acc_pose: 0.845623 loss: 88.054946 2022/10/12 17:15:34 - mmengine - INFO - Epoch(train) [108][550/586] lr: 5.000000e-03 eta: 5:18:32 time: 0.330150 data_time: 0.046270 memory: 4465 loss_kpt: 88.713116 acc_pose: 0.807556 loss: 88.713116 2022/10/12 17:15:46 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:16:04 - mmengine - INFO - Epoch(train) [109][50/586] lr: 5.000000e-03 eta: 5:17:56 time: 0.357106 data_time: 0.057106 memory: 4465 loss_kpt: 88.688827 acc_pose: 0.774012 loss: 88.688827 2022/10/12 17:16:21 - mmengine - INFO - Epoch(train) [109][100/586] lr: 5.000000e-03 eta: 5:17:41 time: 0.352582 data_time: 0.050932 memory: 4465 loss_kpt: 88.707919 acc_pose: 0.808893 loss: 88.707919 2022/10/12 17:16:39 - mmengine - INFO - Epoch(train) [109][150/586] lr: 5.000000e-03 eta: 5:17:27 time: 0.352858 data_time: 0.053948 memory: 4465 loss_kpt: 88.847255 acc_pose: 0.822821 loss: 88.847255 2022/10/12 17:16:57 - mmengine - INFO - Epoch(train) [109][200/586] lr: 5.000000e-03 eta: 5:17:12 time: 0.347330 data_time: 0.057885 memory: 4465 loss_kpt: 89.031775 acc_pose: 0.772526 loss: 89.031775 2022/10/12 17:17:14 - mmengine - INFO - Epoch(train) [109][250/586] lr: 5.000000e-03 eta: 5:16:57 time: 0.340783 data_time: 0.048128 memory: 4465 loss_kpt: 88.118197 acc_pose: 0.782692 loss: 88.118197 2022/10/12 17:17:30 - mmengine - INFO - Epoch(train) [109][300/586] lr: 5.000000e-03 eta: 5:16:42 time: 0.336980 data_time: 0.051193 memory: 4465 loss_kpt: 88.459853 acc_pose: 0.809554 loss: 88.459853 2022/10/12 17:17:48 - mmengine - INFO - Epoch(train) [109][350/586] lr: 5.000000e-03 eta: 5:16:27 time: 0.342418 data_time: 0.053698 memory: 4465 loss_kpt: 86.888424 acc_pose: 0.830581 loss: 86.888424 2022/10/12 17:18:04 - mmengine - INFO - Epoch(train) [109][400/586] lr: 5.000000e-03 eta: 5:16:12 time: 0.336732 data_time: 0.055299 memory: 4465 loss_kpt: 88.590358 acc_pose: 0.777084 loss: 88.590358 2022/10/12 17:18:21 - mmengine - INFO - Epoch(train) [109][450/586] lr: 5.000000e-03 eta: 5:15:56 time: 0.324233 data_time: 0.052967 memory: 4465 loss_kpt: 87.385307 acc_pose: 0.844970 loss: 87.385307 2022/10/12 17:18:37 - mmengine - INFO - Epoch(train) [109][500/586] lr: 5.000000e-03 eta: 5:15:41 time: 0.331118 data_time: 0.060109 memory: 4465 loss_kpt: 87.378766 acc_pose: 0.769609 loss: 87.378766 2022/10/12 17:18:54 - mmengine - INFO - Epoch(train) [109][550/586] lr: 5.000000e-03 eta: 5:15:26 time: 0.330256 data_time: 0.055344 memory: 4465 loss_kpt: 87.696538 acc_pose: 0.816611 loss: 87.696538 2022/10/12 17:19:05 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:19:23 - mmengine - INFO - Epoch(train) [110][50/586] lr: 5.000000e-03 eta: 5:14:49 time: 0.352220 data_time: 0.061426 memory: 4465 loss_kpt: 88.367280 acc_pose: 0.837184 loss: 88.367280 2022/10/12 17:19:41 - mmengine - INFO - Epoch(train) [110][100/586] lr: 5.000000e-03 eta: 5:14:35 time: 0.360497 data_time: 0.055436 memory: 4465 loss_kpt: 89.022158 acc_pose: 0.818248 loss: 89.022158 2022/10/12 17:19:50 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:19:59 - mmengine - INFO - Epoch(train) [110][150/586] lr: 5.000000e-03 eta: 5:14:20 time: 0.352806 data_time: 0.053232 memory: 4465 loss_kpt: 87.626784 acc_pose: 0.752074 loss: 87.626784 2022/10/12 17:20:17 - mmengine - INFO - Epoch(train) [110][200/586] lr: 5.000000e-03 eta: 5:14:07 time: 0.364886 data_time: 0.053034 memory: 4465 loss_kpt: 88.168440 acc_pose: 0.783908 loss: 88.168440 2022/10/12 17:20:35 - mmengine - INFO - Epoch(train) [110][250/586] lr: 5.000000e-03 eta: 5:13:53 time: 0.365327 data_time: 0.054216 memory: 4465 loss_kpt: 89.980495 acc_pose: 0.815568 loss: 89.980495 2022/10/12 17:20:53 - mmengine - INFO - Epoch(train) [110][300/586] lr: 5.000000e-03 eta: 5:13:38 time: 0.346487 data_time: 0.055183 memory: 4465 loss_kpt: 88.400108 acc_pose: 0.770743 loss: 88.400108 2022/10/12 17:21:09 - mmengine - INFO - Epoch(train) [110][350/586] lr: 5.000000e-03 eta: 5:13:23 time: 0.334080 data_time: 0.048495 memory: 4465 loss_kpt: 87.106886 acc_pose: 0.786257 loss: 87.106886 2022/10/12 17:21:26 - mmengine - INFO - Epoch(train) [110][400/586] lr: 5.000000e-03 eta: 5:13:07 time: 0.335886 data_time: 0.053555 memory: 4465 loss_kpt: 87.804402 acc_pose: 0.794767 loss: 87.804402 2022/10/12 17:21:43 - mmengine - INFO - Epoch(train) [110][450/586] lr: 5.000000e-03 eta: 5:12:52 time: 0.333243 data_time: 0.049167 memory: 4465 loss_kpt: 88.587466 acc_pose: 0.781065 loss: 88.587466 2022/10/12 17:22:00 - mmengine - INFO - Epoch(train) [110][500/586] lr: 5.000000e-03 eta: 5:12:37 time: 0.340952 data_time: 0.048883 memory: 4465 loss_kpt: 89.842876 acc_pose: 0.809396 loss: 89.842876 2022/10/12 17:22:18 - mmengine - INFO - Epoch(train) [110][550/586] lr: 5.000000e-03 eta: 5:12:23 time: 0.359028 data_time: 0.052120 memory: 4465 loss_kpt: 88.377083 acc_pose: 0.768004 loss: 88.377083 2022/10/12 17:22:31 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:22:31 - mmengine - INFO - Saving checkpoint at 110 epochs 2022/10/12 17:22:40 - mmengine - INFO - Epoch(val) [110][50/407] eta: 0:00:47 time: 0.131974 data_time: 0.013081 memory: 4465 2022/10/12 17:22:46 - mmengine - INFO - Epoch(val) [110][100/407] eta: 0:00:39 time: 0.127477 data_time: 0.008015 memory: 1026 2022/10/12 17:22:53 - mmengine - INFO - Epoch(val) [110][150/407] eta: 0:00:32 time: 0.127257 data_time: 0.008069 memory: 1026 2022/10/12 17:22:59 - mmengine - INFO - Epoch(val) [110][200/407] eta: 0:00:26 time: 0.125614 data_time: 0.008431 memory: 1026 2022/10/12 17:23:06 - mmengine - INFO - Epoch(val) [110][250/407] eta: 0:00:20 time: 0.129462 data_time: 0.008581 memory: 1026 2022/10/12 17:23:12 - mmengine - INFO - Epoch(val) [110][300/407] eta: 0:00:13 time: 0.128028 data_time: 0.008376 memory: 1026 2022/10/12 17:23:18 - mmengine - INFO - Epoch(val) [110][350/407] eta: 0:00:07 time: 0.125866 data_time: 0.007793 memory: 1026 2022/10/12 17:23:24 - mmengine - INFO - Epoch(val) [110][400/407] eta: 0:00:00 time: 0.124622 data_time: 0.007858 memory: 1026 2022/10/12 17:23:38 - mmengine - INFO - Evaluating CocoMetric... 2022/10/12 17:23:54 - mmengine - INFO - Epoch(val) [110][407/407] coco/AP: 0.693046 coco/AP .5: 0.883980 coco/AP .75: 0.770330 coco/AP (M): 0.660521 coco/AP (L): 0.754727 coco/AR: 0.762610 coco/AR .5: 0.925693 coco/AR .75: 0.828873 coco/AR (M): 0.717154 coco/AR (L): 0.825418 2022/10/12 17:23:54 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/liqikai/openmmlab/pt112cu113py38/mmpose/work_dirs/20221012/rsn50/best_coco/AP_epoch_100.pth is removed 2022/10/12 17:23:56 - mmengine - INFO - The best checkpoint with 0.6930 coco/AP at 110 epoch is saved to best_coco/AP_epoch_110.pth. 2022/10/12 17:24:13 - mmengine - INFO - Epoch(train) [111][50/586] lr: 5.000000e-03 eta: 5:11:46 time: 0.347402 data_time: 0.057397 memory: 4465 loss_kpt: 89.282854 acc_pose: 0.809523 loss: 89.282854 2022/10/12 17:24:30 - mmengine - INFO - Epoch(train) [111][100/586] lr: 5.000000e-03 eta: 5:11:31 time: 0.340810 data_time: 0.049767 memory: 4465 loss_kpt: 88.527228 acc_pose: 0.797560 loss: 88.527228 2022/10/12 17:24:48 - mmengine - INFO - Epoch(train) [111][150/586] lr: 5.000000e-03 eta: 5:11:16 time: 0.346990 data_time: 0.056257 memory: 4465 loss_kpt: 90.279945 acc_pose: 0.854447 loss: 90.279945 2022/10/12 17:25:05 - mmengine - INFO - Epoch(train) [111][200/586] lr: 5.000000e-03 eta: 5:11:02 time: 0.343873 data_time: 0.057711 memory: 4465 loss_kpt: 88.361293 acc_pose: 0.848082 loss: 88.361293 2022/10/12 17:25:22 - mmengine - INFO - Epoch(train) [111][250/586] lr: 5.000000e-03 eta: 5:10:47 time: 0.349201 data_time: 0.060845 memory: 4465 loss_kpt: 89.264562 acc_pose: 0.793561 loss: 89.264562 2022/10/12 17:25:39 - mmengine - INFO - Epoch(train) [111][300/586] lr: 5.000000e-03 eta: 5:10:32 time: 0.340051 data_time: 0.050597 memory: 4465 loss_kpt: 90.085411 acc_pose: 0.772090 loss: 90.085411 2022/10/12 17:25:57 - mmengine - INFO - Epoch(train) [111][350/586] lr: 5.000000e-03 eta: 5:10:17 time: 0.345160 data_time: 0.056220 memory: 4465 loss_kpt: 88.890623 acc_pose: 0.791905 loss: 88.890623 2022/10/12 17:26:14 - mmengine - INFO - Epoch(train) [111][400/586] lr: 5.000000e-03 eta: 5:10:02 time: 0.338491 data_time: 0.054418 memory: 4465 loss_kpt: 88.111881 acc_pose: 0.775648 loss: 88.111881 2022/10/12 17:26:30 - mmengine - INFO - Epoch(train) [111][450/586] lr: 5.000000e-03 eta: 5:09:47 time: 0.336773 data_time: 0.048769 memory: 4465 loss_kpt: 88.943621 acc_pose: 0.777122 loss: 88.943621 2022/10/12 17:26:48 - mmengine - INFO - Epoch(train) [111][500/586] lr: 5.000000e-03 eta: 5:09:32 time: 0.352689 data_time: 0.060655 memory: 4465 loss_kpt: 88.870890 acc_pose: 0.827296 loss: 88.870890 2022/10/12 17:27:01 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:27:05 - mmengine - INFO - Epoch(train) [111][550/586] lr: 5.000000e-03 eta: 5:09:17 time: 0.334345 data_time: 0.048371 memory: 4465 loss_kpt: 89.313760 acc_pose: 0.873991 loss: 89.313760 2022/10/12 17:27:17 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:27:35 - mmengine - INFO - Epoch(train) [112][50/586] lr: 5.000000e-03 eta: 5:08:41 time: 0.358084 data_time: 0.060183 memory: 4465 loss_kpt: 87.863826 acc_pose: 0.750376 loss: 87.863826 2022/10/12 17:27:52 - mmengine - INFO - Epoch(train) [112][100/586] lr: 5.000000e-03 eta: 5:08:26 time: 0.343708 data_time: 0.050142 memory: 4465 loss_kpt: 88.566143 acc_pose: 0.841074 loss: 88.566143 2022/10/12 17:28:09 - mmengine - INFO - Epoch(train) [112][150/586] lr: 5.000000e-03 eta: 5:08:11 time: 0.344247 data_time: 0.049109 memory: 4465 loss_kpt: 88.952124 acc_pose: 0.792829 loss: 88.952124 2022/10/12 17:28:26 - mmengine - INFO - Epoch(train) [112][200/586] lr: 5.000000e-03 eta: 5:07:56 time: 0.341215 data_time: 0.047676 memory: 4465 loss_kpt: 88.983136 acc_pose: 0.837793 loss: 88.983136 2022/10/12 17:28:43 - mmengine - INFO - Epoch(train) [112][250/586] lr: 5.000000e-03 eta: 5:07:41 time: 0.336659 data_time: 0.049118 memory: 4465 loss_kpt: 89.732445 acc_pose: 0.762730 loss: 89.732445 2022/10/12 17:29:00 - mmengine - INFO - Epoch(train) [112][300/586] lr: 5.000000e-03 eta: 5:07:25 time: 0.333986 data_time: 0.051327 memory: 4465 loss_kpt: 87.722104 acc_pose: 0.828451 loss: 87.722104 2022/10/12 17:29:17 - mmengine - INFO - Epoch(train) [112][350/586] lr: 5.000000e-03 eta: 5:07:10 time: 0.337406 data_time: 0.051193 memory: 4465 loss_kpt: 88.114962 acc_pose: 0.756304 loss: 88.114962 2022/10/12 17:29:34 - mmengine - INFO - Epoch(train) [112][400/586] lr: 5.000000e-03 eta: 5:06:55 time: 0.341963 data_time: 0.049626 memory: 4465 loss_kpt: 89.066239 acc_pose: 0.781657 loss: 89.066239 2022/10/12 17:29:50 - mmengine - INFO - Epoch(train) [112][450/586] lr: 5.000000e-03 eta: 5:06:40 time: 0.329371 data_time: 0.050376 memory: 4465 loss_kpt: 87.786634 acc_pose: 0.758101 loss: 87.786634 2022/10/12 17:30:07 - mmengine - INFO - Epoch(train) [112][500/586] lr: 5.000000e-03 eta: 5:06:24 time: 0.330247 data_time: 0.055181 memory: 4465 loss_kpt: 87.720842 acc_pose: 0.819976 loss: 87.720842 2022/10/12 17:30:23 - mmengine - INFO - Epoch(train) [112][550/586] lr: 5.000000e-03 eta: 5:06:08 time: 0.323909 data_time: 0.053346 memory: 4465 loss_kpt: 87.584121 acc_pose: 0.780475 loss: 87.584121 2022/10/12 17:30:35 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:30:52 - mmengine - INFO - Epoch(train) [113][50/586] lr: 5.000000e-03 eta: 5:05:32 time: 0.349910 data_time: 0.067209 memory: 4465 loss_kpt: 87.846619 acc_pose: 0.823966 loss: 87.846619 2022/10/12 17:31:09 - mmengine - INFO - Epoch(train) [113][100/586] lr: 5.000000e-03 eta: 5:05:17 time: 0.341347 data_time: 0.051061 memory: 4465 loss_kpt: 88.023854 acc_pose: 0.762912 loss: 88.023854 2022/10/12 17:31:26 - mmengine - INFO - Epoch(train) [113][150/586] lr: 5.000000e-03 eta: 5:05:02 time: 0.335195 data_time: 0.048434 memory: 4465 loss_kpt: 88.922997 acc_pose: 0.816289 loss: 88.922997 2022/10/12 17:31:43 - mmengine - INFO - Epoch(train) [113][200/586] lr: 5.000000e-03 eta: 5:04:47 time: 0.341575 data_time: 0.052008 memory: 4465 loss_kpt: 87.803226 acc_pose: 0.818531 loss: 87.803226 2022/10/12 17:32:00 - mmengine - INFO - Epoch(train) [113][250/586] lr: 5.000000e-03 eta: 5:04:31 time: 0.329651 data_time: 0.056779 memory: 4465 loss_kpt: 87.417781 acc_pose: 0.804855 loss: 87.417781 2022/10/12 17:32:16 - mmengine - INFO - Epoch(train) [113][300/586] lr: 5.000000e-03 eta: 5:04:16 time: 0.334898 data_time: 0.050257 memory: 4465 loss_kpt: 88.203982 acc_pose: 0.866452 loss: 88.203982 2022/10/12 17:32:33 - mmengine - INFO - Epoch(train) [113][350/586] lr: 5.000000e-03 eta: 5:04:01 time: 0.332621 data_time: 0.052692 memory: 4465 loss_kpt: 87.573853 acc_pose: 0.819827 loss: 87.573853 2022/10/12 17:32:39 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:32:49 - mmengine - INFO - Epoch(train) [113][400/586] lr: 5.000000e-03 eta: 5:03:45 time: 0.327615 data_time: 0.050120 memory: 4465 loss_kpt: 88.438974 acc_pose: 0.852550 loss: 88.438974 2022/10/12 17:33:06 - mmengine - INFO - Epoch(train) [113][450/586] lr: 5.000000e-03 eta: 5:03:29 time: 0.328669 data_time: 0.052641 memory: 4465 loss_kpt: 88.949065 acc_pose: 0.776993 loss: 88.949065 2022/10/12 17:33:23 - mmengine - INFO - Epoch(train) [113][500/586] lr: 5.000000e-03 eta: 5:03:14 time: 0.336794 data_time: 0.049945 memory: 4465 loss_kpt: 87.248423 acc_pose: 0.782408 loss: 87.248423 2022/10/12 17:33:40 - mmengine - INFO - Epoch(train) [113][550/586] lr: 5.000000e-03 eta: 5:02:59 time: 0.348720 data_time: 0.053340 memory: 4465 loss_kpt: 89.659247 acc_pose: 0.725829 loss: 89.659247 2022/10/12 17:33:52 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:34:09 - mmengine - INFO - Epoch(train) [114][50/586] lr: 5.000000e-03 eta: 5:02:23 time: 0.344475 data_time: 0.063181 memory: 4465 loss_kpt: 88.638402 acc_pose: 0.781050 loss: 88.638402 2022/10/12 17:34:26 - mmengine - INFO - Epoch(train) [114][100/586] lr: 5.000000e-03 eta: 5:02:08 time: 0.330741 data_time: 0.052826 memory: 4465 loss_kpt: 88.370405 acc_pose: 0.797215 loss: 88.370405 2022/10/12 17:34:42 - mmengine - INFO - Epoch(train) [114][150/586] lr: 5.000000e-03 eta: 5:01:52 time: 0.322558 data_time: 0.053694 memory: 4465 loss_kpt: 88.431508 acc_pose: 0.805258 loss: 88.431508 2022/10/12 17:34:59 - mmengine - INFO - Epoch(train) [114][200/586] lr: 5.000000e-03 eta: 5:01:37 time: 0.352268 data_time: 0.051083 memory: 4465 loss_kpt: 88.089482 acc_pose: 0.847114 loss: 88.089482 2022/10/12 17:35:16 - mmengine - INFO - Epoch(train) [114][250/586] lr: 5.000000e-03 eta: 5:01:22 time: 0.339580 data_time: 0.054154 memory: 4465 loss_kpt: 88.203536 acc_pose: 0.796935 loss: 88.203536 2022/10/12 17:35:34 - mmengine - INFO - Epoch(train) [114][300/586] lr: 5.000000e-03 eta: 5:01:07 time: 0.344056 data_time: 0.051712 memory: 4465 loss_kpt: 88.308815 acc_pose: 0.805374 loss: 88.308815 2022/10/12 17:35:50 - mmengine - INFO - Epoch(train) [114][350/586] lr: 5.000000e-03 eta: 5:00:52 time: 0.334247 data_time: 0.054039 memory: 4465 loss_kpt: 88.181069 acc_pose: 0.856560 loss: 88.181069 2022/10/12 17:36:07 - mmengine - INFO - Epoch(train) [114][400/586] lr: 5.000000e-03 eta: 5:00:36 time: 0.329284 data_time: 0.049226 memory: 4465 loss_kpt: 86.134066 acc_pose: 0.790418 loss: 86.134066 2022/10/12 17:36:23 - mmengine - INFO - Epoch(train) [114][450/586] lr: 5.000000e-03 eta: 5:00:21 time: 0.329670 data_time: 0.052815 memory: 4465 loss_kpt: 88.619434 acc_pose: 0.801761 loss: 88.619434 2022/10/12 17:36:40 - mmengine - INFO - Epoch(train) [114][500/586] lr: 5.000000e-03 eta: 5:00:05 time: 0.335590 data_time: 0.052672 memory: 4465 loss_kpt: 87.432768 acc_pose: 0.860565 loss: 87.432768 2022/10/12 17:36:57 - mmengine - INFO - Epoch(train) [114][550/586] lr: 5.000000e-03 eta: 4:59:50 time: 0.326747 data_time: 0.050523 memory: 4465 loss_kpt: 87.987510 acc_pose: 0.861235 loss: 87.987510 2022/10/12 17:37:08 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:37:26 - mmengine - INFO - Epoch(train) [115][50/586] lr: 5.000000e-03 eta: 4:59:14 time: 0.356612 data_time: 0.060473 memory: 4465 loss_kpt: 87.792325 acc_pose: 0.812282 loss: 87.792325 2022/10/12 17:37:43 - mmengine - INFO - Epoch(train) [115][100/586] lr: 5.000000e-03 eta: 4:58:59 time: 0.350406 data_time: 0.053358 memory: 4465 loss_kpt: 89.474972 acc_pose: 0.780720 loss: 89.474972 2022/10/12 17:38:00 - mmengine - INFO - Epoch(train) [115][150/586] lr: 5.000000e-03 eta: 4:58:44 time: 0.332155 data_time: 0.049302 memory: 4465 loss_kpt: 89.278172 acc_pose: 0.823225 loss: 89.278172 2022/10/12 17:38:16 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:38:17 - mmengine - INFO - Epoch(train) [115][200/586] lr: 5.000000e-03 eta: 4:58:29 time: 0.340301 data_time: 0.050894 memory: 4465 loss_kpt: 88.020100 acc_pose: 0.802559 loss: 88.020100 2022/10/12 17:38:34 - mmengine - INFO - Epoch(train) [115][250/586] lr: 5.000000e-03 eta: 4:58:14 time: 0.345201 data_time: 0.051386 memory: 4465 loss_kpt: 87.414898 acc_pose: 0.826145 loss: 87.414898 2022/10/12 17:38:51 - mmengine - INFO - Epoch(train) [115][300/586] lr: 5.000000e-03 eta: 4:57:59 time: 0.337374 data_time: 0.047080 memory: 4465 loss_kpt: 89.326183 acc_pose: 0.778025 loss: 89.326183 2022/10/12 17:39:08 - mmengine - INFO - Epoch(train) [115][350/586] lr: 5.000000e-03 eta: 4:57:44 time: 0.339103 data_time: 0.052048 memory: 4465 loss_kpt: 87.822670 acc_pose: 0.772188 loss: 87.822670 2022/10/12 17:39:26 - mmengine - INFO - Epoch(train) [115][400/586] lr: 5.000000e-03 eta: 4:57:29 time: 0.348190 data_time: 0.048912 memory: 4465 loss_kpt: 88.388862 acc_pose: 0.796251 loss: 88.388862 2022/10/12 17:39:42 - mmengine - INFO - Epoch(train) [115][450/586] lr: 5.000000e-03 eta: 4:57:13 time: 0.324229 data_time: 0.046209 memory: 4465 loss_kpt: 87.438886 acc_pose: 0.721165 loss: 87.438886 2022/10/12 17:39:58 - mmengine - INFO - Epoch(train) [115][500/586] lr: 5.000000e-03 eta: 4:56:57 time: 0.332428 data_time: 0.045470 memory: 4465 loss_kpt: 88.381640 acc_pose: 0.836986 loss: 88.381640 2022/10/12 17:40:15 - mmengine - INFO - Epoch(train) [115][550/586] lr: 5.000000e-03 eta: 4:56:42 time: 0.336477 data_time: 0.051475 memory: 4465 loss_kpt: 89.376773 acc_pose: 0.847209 loss: 89.376773 2022/10/12 17:40:27 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:40:45 - mmengine - INFO - Epoch(train) [116][50/586] lr: 5.000000e-03 eta: 4:56:07 time: 0.356716 data_time: 0.057334 memory: 4465 loss_kpt: 87.665434 acc_pose: 0.774005 loss: 87.665434 2022/10/12 17:41:02 - mmengine - INFO - Epoch(train) [116][100/586] lr: 5.000000e-03 eta: 4:55:52 time: 0.344350 data_time: 0.051755 memory: 4465 loss_kpt: 88.393333 acc_pose: 0.773423 loss: 88.393333 2022/10/12 17:41:19 - mmengine - INFO - Epoch(train) [116][150/586] lr: 5.000000e-03 eta: 4:55:37 time: 0.338059 data_time: 0.049580 memory: 4465 loss_kpt: 88.537306 acc_pose: 0.791374 loss: 88.537306 2022/10/12 17:41:35 - mmengine - INFO - Epoch(train) [116][200/586] lr: 5.000000e-03 eta: 4:55:21 time: 0.326357 data_time: 0.050018 memory: 4465 loss_kpt: 89.295936 acc_pose: 0.705042 loss: 89.295936 2022/10/12 17:41:52 - mmengine - INFO - Epoch(train) [116][250/586] lr: 5.000000e-03 eta: 4:55:05 time: 0.330727 data_time: 0.047823 memory: 4465 loss_kpt: 88.158368 acc_pose: 0.779100 loss: 88.158368 2022/10/12 17:42:08 - mmengine - INFO - Epoch(train) [116][300/586] lr: 5.000000e-03 eta: 4:54:50 time: 0.324168 data_time: 0.046413 memory: 4465 loss_kpt: 89.192836 acc_pose: 0.805058 loss: 89.192836 2022/10/12 17:42:24 - mmengine - INFO - Epoch(train) [116][350/586] lr: 5.000000e-03 eta: 4:54:34 time: 0.316313 data_time: 0.050704 memory: 4465 loss_kpt: 88.821905 acc_pose: 0.821960 loss: 88.821905 2022/10/12 17:42:40 - mmengine - INFO - Epoch(train) [116][400/586] lr: 5.000000e-03 eta: 4:54:18 time: 0.327181 data_time: 0.050116 memory: 4465 loss_kpt: 87.931416 acc_pose: 0.846458 loss: 87.931416 2022/10/12 17:42:57 - mmengine - INFO - Epoch(train) [116][450/586] lr: 5.000000e-03 eta: 4:54:02 time: 0.333997 data_time: 0.053220 memory: 4465 loss_kpt: 88.278133 acc_pose: 0.809142 loss: 88.278133 2022/10/12 17:43:14 - mmengine - INFO - Epoch(train) [116][500/586] lr: 5.000000e-03 eta: 4:53:47 time: 0.330224 data_time: 0.049517 memory: 4465 loss_kpt: 88.178829 acc_pose: 0.827861 loss: 88.178829 2022/10/12 17:43:30 - mmengine - INFO - Epoch(train) [116][550/586] lr: 5.000000e-03 eta: 4:53:31 time: 0.327945 data_time: 0.051742 memory: 4465 loss_kpt: 88.127014 acc_pose: 0.821404 loss: 88.127014 2022/10/12 17:43:42 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:43:51 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:44:00 - mmengine - INFO - Epoch(train) [117][50/586] lr: 5.000000e-03 eta: 4:52:56 time: 0.350923 data_time: 0.061513 memory: 4465 loss_kpt: 87.125266 acc_pose: 0.731559 loss: 87.125266 2022/10/12 17:44:17 - mmengine - INFO - Epoch(train) [117][100/586] lr: 5.000000e-03 eta: 4:52:40 time: 0.333305 data_time: 0.049613 memory: 4465 loss_kpt: 88.470739 acc_pose: 0.820855 loss: 88.470739 2022/10/12 17:44:33 - mmengine - INFO - Epoch(train) [117][150/586] lr: 5.000000e-03 eta: 4:52:25 time: 0.326584 data_time: 0.054341 memory: 4465 loss_kpt: 88.896967 acc_pose: 0.818991 loss: 88.896967 2022/10/12 17:44:49 - mmengine - INFO - Epoch(train) [117][200/586] lr: 5.000000e-03 eta: 4:52:09 time: 0.327804 data_time: 0.048035 memory: 4465 loss_kpt: 88.425087 acc_pose: 0.752024 loss: 88.425087 2022/10/12 17:45:06 - mmengine - INFO - Epoch(train) [117][250/586] lr: 5.000000e-03 eta: 4:51:54 time: 0.341483 data_time: 0.051225 memory: 4465 loss_kpt: 86.980973 acc_pose: 0.808925 loss: 86.980973 2022/10/12 17:45:23 - mmengine - INFO - Epoch(train) [117][300/586] lr: 5.000000e-03 eta: 4:51:39 time: 0.340293 data_time: 0.050671 memory: 4465 loss_kpt: 89.107413 acc_pose: 0.768907 loss: 89.107413 2022/10/12 17:45:40 - mmengine - INFO - Epoch(train) [117][350/586] lr: 5.000000e-03 eta: 4:51:23 time: 0.330409 data_time: 0.053055 memory: 4465 loss_kpt: 86.617313 acc_pose: 0.755300 loss: 86.617313 2022/10/12 17:45:57 - mmengine - INFO - Epoch(train) [117][400/586] lr: 5.000000e-03 eta: 4:51:08 time: 0.338935 data_time: 0.052419 memory: 4465 loss_kpt: 87.766626 acc_pose: 0.763908 loss: 87.766626 2022/10/12 17:46:14 - mmengine - INFO - Epoch(train) [117][450/586] lr: 5.000000e-03 eta: 4:50:53 time: 0.331972 data_time: 0.052939 memory: 4465 loss_kpt: 89.292526 acc_pose: 0.838924 loss: 89.292526 2022/10/12 17:46:30 - mmengine - INFO - Epoch(train) [117][500/586] lr: 5.000000e-03 eta: 4:50:37 time: 0.337902 data_time: 0.052318 memory: 4465 loss_kpt: 88.584771 acc_pose: 0.839238 loss: 88.584771 2022/10/12 17:46:47 - mmengine - INFO - Epoch(train) [117][550/586] lr: 5.000000e-03 eta: 4:50:22 time: 0.335461 data_time: 0.047879 memory: 4465 loss_kpt: 88.216245 acc_pose: 0.771110 loss: 88.216245 2022/10/12 17:46:59 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:47:17 - mmengine - INFO - Epoch(train) [118][50/586] lr: 5.000000e-03 eta: 4:49:47 time: 0.360216 data_time: 0.059386 memory: 4465 loss_kpt: 87.597596 acc_pose: 0.777454 loss: 87.597596 2022/10/12 17:47:35 - mmengine - INFO - Epoch(train) [118][100/586] lr: 5.000000e-03 eta: 4:49:33 time: 0.355006 data_time: 0.055844 memory: 4465 loss_kpt: 89.013753 acc_pose: 0.795570 loss: 89.013753 2022/10/12 17:47:52 - mmengine - INFO - Epoch(train) [118][150/586] lr: 5.000000e-03 eta: 4:49:18 time: 0.343266 data_time: 0.055794 memory: 4465 loss_kpt: 87.258935 acc_pose: 0.745893 loss: 87.258935 2022/10/12 17:48:10 - mmengine - INFO - Epoch(train) [118][200/586] lr: 5.000000e-03 eta: 4:49:03 time: 0.356494 data_time: 0.049960 memory: 4465 loss_kpt: 88.176756 acc_pose: 0.812545 loss: 88.176756 2022/10/12 17:48:27 - mmengine - INFO - Epoch(train) [118][250/586] lr: 5.000000e-03 eta: 4:48:48 time: 0.335381 data_time: 0.049617 memory: 4465 loss_kpt: 88.760810 acc_pose: 0.724786 loss: 88.760810 2022/10/12 17:48:44 - mmengine - INFO - Epoch(train) [118][300/586] lr: 5.000000e-03 eta: 4:48:33 time: 0.343718 data_time: 0.050960 memory: 4465 loss_kpt: 88.644451 acc_pose: 0.768288 loss: 88.644451 2022/10/12 17:49:01 - mmengine - INFO - Epoch(train) [118][350/586] lr: 5.000000e-03 eta: 4:48:18 time: 0.341381 data_time: 0.051372 memory: 4465 loss_kpt: 88.166454 acc_pose: 0.758679 loss: 88.166454 2022/10/12 17:49:18 - mmengine - INFO - Epoch(train) [118][400/586] lr: 5.000000e-03 eta: 4:48:03 time: 0.344585 data_time: 0.047704 memory: 4465 loss_kpt: 88.678017 acc_pose: 0.861311 loss: 88.678017 2022/10/12 17:49:31 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:49:36 - mmengine - INFO - Epoch(train) [118][450/586] lr: 5.000000e-03 eta: 4:47:48 time: 0.350791 data_time: 0.047909 memory: 4465 loss_kpt: 88.966555 acc_pose: 0.780524 loss: 88.966555 2022/10/12 17:49:53 - mmengine - INFO - Epoch(train) [118][500/586] lr: 5.000000e-03 eta: 4:47:33 time: 0.354322 data_time: 0.053815 memory: 4465 loss_kpt: 87.095751 acc_pose: 0.771133 loss: 87.095751 2022/10/12 17:50:11 - mmengine - INFO - Epoch(train) [118][550/586] lr: 5.000000e-03 eta: 4:47:19 time: 0.355491 data_time: 0.048253 memory: 4465 loss_kpt: 87.594256 acc_pose: 0.737709 loss: 87.594256 2022/10/12 17:50:24 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:50:41 - mmengine - INFO - Epoch(train) [119][50/586] lr: 5.000000e-03 eta: 4:46:43 time: 0.348454 data_time: 0.069214 memory: 4465 loss_kpt: 88.290952 acc_pose: 0.755899 loss: 88.290952 2022/10/12 17:50:58 - mmengine - INFO - Epoch(train) [119][100/586] lr: 5.000000e-03 eta: 4:46:28 time: 0.330296 data_time: 0.050174 memory: 4465 loss_kpt: 88.323648 acc_pose: 0.778135 loss: 88.323648 2022/10/12 17:51:15 - mmengine - INFO - Epoch(train) [119][150/586] lr: 5.000000e-03 eta: 4:46:13 time: 0.341780 data_time: 0.052667 memory: 4465 loss_kpt: 89.135337 acc_pose: 0.795416 loss: 89.135337 2022/10/12 17:51:31 - mmengine - INFO - Epoch(train) [119][200/586] lr: 5.000000e-03 eta: 4:45:57 time: 0.329444 data_time: 0.051619 memory: 4465 loss_kpt: 88.987098 acc_pose: 0.784732 loss: 88.987098 2022/10/12 17:51:48 - mmengine - INFO - Epoch(train) [119][250/586] lr: 5.000000e-03 eta: 4:45:42 time: 0.335513 data_time: 0.053420 memory: 4465 loss_kpt: 87.386119 acc_pose: 0.842692 loss: 87.386119 2022/10/12 17:52:05 - mmengine - INFO - Epoch(train) [119][300/586] lr: 5.000000e-03 eta: 4:45:26 time: 0.329182 data_time: 0.045734 memory: 4465 loss_kpt: 87.827185 acc_pose: 0.754567 loss: 87.827185 2022/10/12 17:52:21 - mmengine - INFO - Epoch(train) [119][350/586] lr: 5.000000e-03 eta: 4:45:11 time: 0.335301 data_time: 0.051541 memory: 4465 loss_kpt: 89.150271 acc_pose: 0.789978 loss: 89.150271 2022/10/12 17:52:38 - mmengine - INFO - Epoch(train) [119][400/586] lr: 5.000000e-03 eta: 4:44:55 time: 0.324249 data_time: 0.053321 memory: 4465 loss_kpt: 88.346895 acc_pose: 0.799849 loss: 88.346895 2022/10/12 17:52:54 - mmengine - INFO - Epoch(train) [119][450/586] lr: 5.000000e-03 eta: 4:44:39 time: 0.328597 data_time: 0.048777 memory: 4465 loss_kpt: 88.071027 acc_pose: 0.835429 loss: 88.071027 2022/10/12 17:53:10 - mmengine - INFO - Epoch(train) [119][500/586] lr: 5.000000e-03 eta: 4:44:23 time: 0.320339 data_time: 0.050955 memory: 4465 loss_kpt: 87.894417 acc_pose: 0.811922 loss: 87.894417 2022/10/12 17:53:27 - mmengine - INFO - Epoch(train) [119][550/586] lr: 5.000000e-03 eta: 4:44:08 time: 0.330932 data_time: 0.046437 memory: 4465 loss_kpt: 87.651033 acc_pose: 0.837135 loss: 87.651033 2022/10/12 17:53:38 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:53:56 - mmengine - INFO - Epoch(train) [120][50/586] lr: 5.000000e-03 eta: 4:43:33 time: 0.352508 data_time: 0.059336 memory: 4465 loss_kpt: 87.261212 acc_pose: 0.736143 loss: 87.261212 2022/10/12 17:54:13 - mmengine - INFO - Epoch(train) [120][100/586] lr: 5.000000e-03 eta: 4:43:18 time: 0.342626 data_time: 0.053730 memory: 4465 loss_kpt: 88.388523 acc_pose: 0.836520 loss: 88.388523 2022/10/12 17:54:30 - mmengine - INFO - Epoch(train) [120][150/586] lr: 5.000000e-03 eta: 4:43:03 time: 0.346062 data_time: 0.054582 memory: 4465 loss_kpt: 87.432551 acc_pose: 0.827230 loss: 87.432551 2022/10/12 17:54:48 - mmengine - INFO - Epoch(train) [120][200/586] lr: 5.000000e-03 eta: 4:42:48 time: 0.342569 data_time: 0.050845 memory: 4465 loss_kpt: 89.001266 acc_pose: 0.800952 loss: 89.001266 2022/10/12 17:55:05 - mmengine - INFO - Epoch(train) [120][250/586] lr: 5.000000e-03 eta: 4:42:33 time: 0.352865 data_time: 0.050058 memory: 4465 loss_kpt: 86.822460 acc_pose: 0.833704 loss: 86.822460 2022/10/12 17:55:11 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:55:23 - mmengine - INFO - Epoch(train) [120][300/586] lr: 5.000000e-03 eta: 4:42:18 time: 0.349070 data_time: 0.056004 memory: 4465 loss_kpt: 88.610208 acc_pose: 0.869313 loss: 88.610208 2022/10/12 17:55:40 - mmengine - INFO - Epoch(train) [120][350/586] lr: 5.000000e-03 eta: 4:42:03 time: 0.345721 data_time: 0.051142 memory: 4465 loss_kpt: 86.930536 acc_pose: 0.784542 loss: 86.930536 2022/10/12 17:55:57 - mmengine - INFO - Epoch(train) [120][400/586] lr: 5.000000e-03 eta: 4:41:48 time: 0.343562 data_time: 0.047924 memory: 4465 loss_kpt: 87.325992 acc_pose: 0.857575 loss: 87.325992 2022/10/12 17:56:15 - mmengine - INFO - Epoch(train) [120][450/586] lr: 5.000000e-03 eta: 4:41:33 time: 0.352555 data_time: 0.048784 memory: 4465 loss_kpt: 88.265513 acc_pose: 0.787935 loss: 88.265513 2022/10/12 17:56:32 - mmengine - INFO - Epoch(train) [120][500/586] lr: 5.000000e-03 eta: 4:41:18 time: 0.341243 data_time: 0.051488 memory: 4465 loss_kpt: 87.892309 acc_pose: 0.804037 loss: 87.892309 2022/10/12 17:56:48 - mmengine - INFO - Epoch(train) [120][550/586] lr: 5.000000e-03 eta: 4:41:03 time: 0.324243 data_time: 0.054400 memory: 4465 loss_kpt: 89.617526 acc_pose: 0.892022 loss: 89.617526 2022/10/12 17:57:00 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 17:57:00 - mmengine - INFO - Saving checkpoint at 120 epochs 2022/10/12 17:57:09 - mmengine - INFO - Epoch(val) [120][50/407] eta: 0:00:47 time: 0.133681 data_time: 0.013296 memory: 4465 2022/10/12 17:57:15 - mmengine - INFO - Epoch(val) [120][100/407] eta: 0:00:39 time: 0.127116 data_time: 0.008300 memory: 1026 2022/10/12 17:57:22 - mmengine - INFO - Epoch(val) [120][150/407] eta: 0:00:32 time: 0.125337 data_time: 0.008198 memory: 1026 2022/10/12 17:57:28 - mmengine - INFO - Epoch(val) [120][200/407] eta: 0:00:26 time: 0.127110 data_time: 0.008167 memory: 1026 2022/10/12 17:57:35 - mmengine - INFO - Epoch(val) [120][250/407] eta: 0:00:20 time: 0.128997 data_time: 0.008611 memory: 1026 2022/10/12 17:57:41 - mmengine - INFO - Epoch(val) [120][300/407] eta: 0:00:13 time: 0.126790 data_time: 0.008241 memory: 1026 2022/10/12 17:57:47 - mmengine - INFO - Epoch(val) [120][350/407] eta: 0:00:07 time: 0.129957 data_time: 0.008938 memory: 1026 2022/10/12 17:57:54 - mmengine - INFO - Epoch(val) [120][400/407] eta: 0:00:00 time: 0.127483 data_time: 0.011257 memory: 1026 2022/10/12 17:58:07 - mmengine - INFO - Evaluating CocoMetric... 2022/10/12 17:58:23 - mmengine - INFO - Epoch(val) [120][407/407] coco/AP: 0.696640 coco/AP .5: 0.886790 coco/AP .75: 0.771351 coco/AP (M): 0.663149 coco/AP (L): 0.759395 coco/AR: 0.765822 coco/AR .5: 0.927110 coco/AR .75: 0.829345 coco/AR (M): 0.719366 coco/AR (L): 0.830137 2022/10/12 17:58:23 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/liqikai/openmmlab/pt112cu113py38/mmpose/work_dirs/20221012/rsn50/best_coco/AP_epoch_110.pth is removed 2022/10/12 17:58:25 - mmengine - INFO - The best checkpoint with 0.6966 coco/AP at 120 epoch is saved to best_coco/AP_epoch_120.pth. 2022/10/12 17:58:42 - mmengine - INFO - Epoch(train) [121][50/586] lr: 5.000000e-03 eta: 4:40:27 time: 0.342214 data_time: 0.058871 memory: 4465 loss_kpt: 89.336772 acc_pose: 0.793782 loss: 89.336772 2022/10/12 17:58:59 - mmengine - INFO - Epoch(train) [121][100/586] lr: 5.000000e-03 eta: 4:40:12 time: 0.334264 data_time: 0.049122 memory: 4465 loss_kpt: 87.501915 acc_pose: 0.812279 loss: 87.501915 2022/10/12 17:59:16 - mmengine - INFO - Epoch(train) [121][150/586] lr: 5.000000e-03 eta: 4:39:57 time: 0.337203 data_time: 0.048138 memory: 4465 loss_kpt: 88.635877 acc_pose: 0.825370 loss: 88.635877 2022/10/12 17:59:33 - mmengine - INFO - Epoch(train) [121][200/586] lr: 5.000000e-03 eta: 4:39:42 time: 0.344246 data_time: 0.048660 memory: 4465 loss_kpt: 89.036741 acc_pose: 0.789946 loss: 89.036741 2022/10/12 17:59:50 - mmengine - INFO - Epoch(train) [121][250/586] lr: 5.000000e-03 eta: 4:39:26 time: 0.343389 data_time: 0.048917 memory: 4465 loss_kpt: 87.042845 acc_pose: 0.832764 loss: 87.042845 2022/10/12 18:00:07 - mmengine - INFO - Epoch(train) [121][300/586] lr: 5.000000e-03 eta: 4:39:11 time: 0.342473 data_time: 0.050660 memory: 4465 loss_kpt: 87.921131 acc_pose: 0.760908 loss: 87.921131 2022/10/12 18:00:24 - mmengine - INFO - Epoch(train) [121][350/586] lr: 5.000000e-03 eta: 4:38:56 time: 0.336361 data_time: 0.049602 memory: 4465 loss_kpt: 87.428441 acc_pose: 0.863203 loss: 87.428441 2022/10/12 18:00:41 - mmengine - INFO - Epoch(train) [121][400/586] lr: 5.000000e-03 eta: 4:38:40 time: 0.329209 data_time: 0.045538 memory: 4465 loss_kpt: 88.705400 acc_pose: 0.794841 loss: 88.705400 2022/10/12 18:00:58 - mmengine - INFO - Epoch(train) [121][450/586] lr: 5.000000e-03 eta: 4:38:25 time: 0.339930 data_time: 0.048575 memory: 4465 loss_kpt: 87.883237 acc_pose: 0.780347 loss: 87.883237 2022/10/12 18:01:14 - mmengine - INFO - Epoch(train) [121][500/586] lr: 5.000000e-03 eta: 4:38:09 time: 0.326419 data_time: 0.048308 memory: 4465 loss_kpt: 86.484520 acc_pose: 0.845740 loss: 86.484520 2022/10/12 18:01:31 - mmengine - INFO - Epoch(train) [121][550/586] lr: 5.000000e-03 eta: 4:37:55 time: 0.349973 data_time: 0.045741 memory: 4465 loss_kpt: 87.000609 acc_pose: 0.831232 loss: 87.000609 2022/10/12 18:01:44 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:02:01 - mmengine - INFO - Epoch(train) [122][50/586] lr: 5.000000e-03 eta: 4:37:20 time: 0.350975 data_time: 0.064122 memory: 4465 loss_kpt: 86.588923 acc_pose: 0.838961 loss: 86.588923 2022/10/12 18:02:16 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:02:18 - mmengine - INFO - Epoch(train) [122][100/586] lr: 5.000000e-03 eta: 4:37:05 time: 0.344872 data_time: 0.052192 memory: 4465 loss_kpt: 88.053784 acc_pose: 0.799344 loss: 88.053784 2022/10/12 18:02:36 - mmengine - INFO - Epoch(train) [122][150/586] lr: 5.000000e-03 eta: 4:36:50 time: 0.349677 data_time: 0.059951 memory: 4465 loss_kpt: 88.187424 acc_pose: 0.836639 loss: 88.187424 2022/10/12 18:02:53 - mmengine - INFO - Epoch(train) [122][200/586] lr: 5.000000e-03 eta: 4:36:35 time: 0.339426 data_time: 0.053433 memory: 4465 loss_kpt: 89.206510 acc_pose: 0.855609 loss: 89.206510 2022/10/12 18:03:10 - mmengine - INFO - Epoch(train) [122][250/586] lr: 5.000000e-03 eta: 4:36:19 time: 0.336020 data_time: 0.052035 memory: 4465 loss_kpt: 87.397009 acc_pose: 0.807386 loss: 87.397009 2022/10/12 18:03:26 - mmengine - INFO - Epoch(train) [122][300/586] lr: 5.000000e-03 eta: 4:36:03 time: 0.324142 data_time: 0.051843 memory: 4465 loss_kpt: 88.407339 acc_pose: 0.816292 loss: 88.407339 2022/10/12 18:03:42 - mmengine - INFO - Epoch(train) [122][350/586] lr: 5.000000e-03 eta: 4:35:48 time: 0.320013 data_time: 0.056274 memory: 4465 loss_kpt: 88.664689 acc_pose: 0.790897 loss: 88.664689 2022/10/12 18:03:58 - mmengine - INFO - Epoch(train) [122][400/586] lr: 5.000000e-03 eta: 4:35:32 time: 0.321206 data_time: 0.052123 memory: 4465 loss_kpt: 88.356544 acc_pose: 0.820350 loss: 88.356544 2022/10/12 18:04:14 - mmengine - INFO - Epoch(train) [122][450/586] lr: 5.000000e-03 eta: 4:35:16 time: 0.319101 data_time: 0.054966 memory: 4465 loss_kpt: 88.795457 acc_pose: 0.741237 loss: 88.795457 2022/10/12 18:04:31 - mmengine - INFO - Epoch(train) [122][500/586] lr: 5.000000e-03 eta: 4:35:00 time: 0.339302 data_time: 0.057077 memory: 4465 loss_kpt: 88.382258 acc_pose: 0.818163 loss: 88.382258 2022/10/12 18:04:47 - mmengine - INFO - Epoch(train) [122][550/586] lr: 5.000000e-03 eta: 4:34:45 time: 0.325944 data_time: 0.056844 memory: 4465 loss_kpt: 87.603289 acc_pose: 0.739038 loss: 87.603289 2022/10/12 18:04:59 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:05:16 - mmengine - INFO - Epoch(train) [123][50/586] lr: 5.000000e-03 eta: 4:34:10 time: 0.343447 data_time: 0.060647 memory: 4465 loss_kpt: 88.575069 acc_pose: 0.818917 loss: 88.575069 2022/10/12 18:05:32 - mmengine - INFO - Epoch(train) [123][100/586] lr: 5.000000e-03 eta: 4:33:54 time: 0.331296 data_time: 0.051344 memory: 4465 loss_kpt: 87.769661 acc_pose: 0.777601 loss: 87.769661 2022/10/12 18:05:49 - mmengine - INFO - Epoch(train) [123][150/586] lr: 5.000000e-03 eta: 4:33:39 time: 0.338449 data_time: 0.049359 memory: 4465 loss_kpt: 88.510834 acc_pose: 0.767483 loss: 88.510834 2022/10/12 18:06:06 - mmengine - INFO - Epoch(train) [123][200/586] lr: 5.000000e-03 eta: 4:33:24 time: 0.339567 data_time: 0.052698 memory: 4465 loss_kpt: 87.873149 acc_pose: 0.878005 loss: 87.873149 2022/10/12 18:06:23 - mmengine - INFO - Epoch(train) [123][250/586] lr: 5.000000e-03 eta: 4:33:08 time: 0.337939 data_time: 0.047781 memory: 4465 loss_kpt: 87.033502 acc_pose: 0.786745 loss: 87.033502 2022/10/12 18:06:41 - mmengine - INFO - Epoch(train) [123][300/586] lr: 5.000000e-03 eta: 4:32:54 time: 0.350258 data_time: 0.052047 memory: 4465 loss_kpt: 88.444567 acc_pose: 0.794121 loss: 88.444567 2022/10/12 18:06:58 - mmengine - INFO - Epoch(train) [123][350/586] lr: 5.000000e-03 eta: 4:32:38 time: 0.344181 data_time: 0.050470 memory: 4465 loss_kpt: 86.505317 acc_pose: 0.840260 loss: 86.505317 2022/10/12 18:07:16 - mmengine - INFO - Epoch(train) [123][400/586] lr: 5.000000e-03 eta: 4:32:24 time: 0.349969 data_time: 0.056439 memory: 4465 loss_kpt: 87.860521 acc_pose: 0.804696 loss: 87.860521 2022/10/12 18:07:32 - mmengine - INFO - Epoch(train) [123][450/586] lr: 5.000000e-03 eta: 4:32:08 time: 0.333783 data_time: 0.047976 memory: 4465 loss_kpt: 89.285191 acc_pose: 0.783540 loss: 89.285191 2022/10/12 18:07:49 - mmengine - INFO - Epoch(train) [123][500/586] lr: 5.000000e-03 eta: 4:31:52 time: 0.326869 data_time: 0.047045 memory: 4465 loss_kpt: 87.471755 acc_pose: 0.770457 loss: 87.471755 2022/10/12 18:07:51 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:08:05 - mmengine - INFO - Epoch(train) [123][550/586] lr: 5.000000e-03 eta: 4:31:37 time: 0.336421 data_time: 0.048518 memory: 4465 loss_kpt: 90.662394 acc_pose: 0.827421 loss: 90.662394 2022/10/12 18:08:17 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:08:35 - mmengine - INFO - Epoch(train) [124][50/586] lr: 5.000000e-03 eta: 4:31:02 time: 0.349153 data_time: 0.059494 memory: 4465 loss_kpt: 87.545378 acc_pose: 0.848830 loss: 87.545378 2022/10/12 18:08:52 - mmengine - INFO - Epoch(train) [124][100/586] lr: 5.000000e-03 eta: 4:30:47 time: 0.344023 data_time: 0.054162 memory: 4465 loss_kpt: 88.692857 acc_pose: 0.731831 loss: 88.692857 2022/10/12 18:09:08 - mmengine - INFO - Epoch(train) [124][150/586] lr: 5.000000e-03 eta: 4:30:32 time: 0.325493 data_time: 0.048688 memory: 4465 loss_kpt: 88.087099 acc_pose: 0.817695 loss: 88.087099 2022/10/12 18:09:25 - mmengine - INFO - Epoch(train) [124][200/586] lr: 5.000000e-03 eta: 4:30:16 time: 0.327447 data_time: 0.048557 memory: 4465 loss_kpt: 87.962805 acc_pose: 0.795468 loss: 87.962805 2022/10/12 18:09:41 - mmengine - INFO - Epoch(train) [124][250/586] lr: 5.000000e-03 eta: 4:30:00 time: 0.331918 data_time: 0.045002 memory: 4465 loss_kpt: 87.174238 acc_pose: 0.781230 loss: 87.174238 2022/10/12 18:09:58 - mmengine - INFO - Epoch(train) [124][300/586] lr: 5.000000e-03 eta: 4:29:45 time: 0.329261 data_time: 0.050002 memory: 4465 loss_kpt: 87.818426 acc_pose: 0.786579 loss: 87.818426 2022/10/12 18:10:14 - mmengine - INFO - Epoch(train) [124][350/586] lr: 5.000000e-03 eta: 4:29:29 time: 0.332043 data_time: 0.047445 memory: 4465 loss_kpt: 88.829663 acc_pose: 0.799300 loss: 88.829663 2022/10/12 18:10:30 - mmengine - INFO - Epoch(train) [124][400/586] lr: 5.000000e-03 eta: 4:29:13 time: 0.321348 data_time: 0.048600 memory: 4465 loss_kpt: 86.523049 acc_pose: 0.891350 loss: 86.523049 2022/10/12 18:10:47 - mmengine - INFO - Epoch(train) [124][450/586] lr: 5.000000e-03 eta: 4:28:58 time: 0.331423 data_time: 0.051242 memory: 4465 loss_kpt: 88.542697 acc_pose: 0.724413 loss: 88.542697 2022/10/12 18:11:03 - mmengine - INFO - Epoch(train) [124][500/586] lr: 5.000000e-03 eta: 4:28:42 time: 0.330543 data_time: 0.050367 memory: 4465 loss_kpt: 88.226608 acc_pose: 0.784168 loss: 88.226608 2022/10/12 18:11:20 - mmengine - INFO - Epoch(train) [124][550/586] lr: 5.000000e-03 eta: 4:28:27 time: 0.326669 data_time: 0.057908 memory: 4465 loss_kpt: 89.232545 acc_pose: 0.809101 loss: 89.232545 2022/10/12 18:11:32 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:11:49 - mmengine - INFO - Epoch(train) [125][50/586] lr: 5.000000e-03 eta: 4:27:52 time: 0.351208 data_time: 0.055991 memory: 4465 loss_kpt: 87.832220 acc_pose: 0.818292 loss: 87.832220 2022/10/12 18:12:06 - mmengine - INFO - Epoch(train) [125][100/586] lr: 5.000000e-03 eta: 4:27:37 time: 0.345579 data_time: 0.051012 memory: 4465 loss_kpt: 89.186334 acc_pose: 0.823417 loss: 89.186334 2022/10/12 18:12:24 - mmengine - INFO - Epoch(train) [125][150/586] lr: 5.000000e-03 eta: 4:27:22 time: 0.344502 data_time: 0.046778 memory: 4465 loss_kpt: 88.868187 acc_pose: 0.794594 loss: 88.868187 2022/10/12 18:12:41 - mmengine - INFO - Epoch(train) [125][200/586] lr: 5.000000e-03 eta: 4:27:07 time: 0.342578 data_time: 0.050422 memory: 4465 loss_kpt: 88.062579 acc_pose: 0.755838 loss: 88.062579 2022/10/12 18:12:58 - mmengine - INFO - Epoch(train) [125][250/586] lr: 5.000000e-03 eta: 4:26:52 time: 0.344723 data_time: 0.050200 memory: 4465 loss_kpt: 88.219798 acc_pose: 0.852711 loss: 88.219798 2022/10/12 18:13:15 - mmengine - INFO - Epoch(train) [125][300/586] lr: 5.000000e-03 eta: 4:26:37 time: 0.339987 data_time: 0.046853 memory: 4465 loss_kpt: 88.867422 acc_pose: 0.778440 loss: 88.867422 2022/10/12 18:13:27 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:13:32 - mmengine - INFO - Epoch(train) [125][350/586] lr: 5.000000e-03 eta: 4:26:21 time: 0.334272 data_time: 0.051236 memory: 4465 loss_kpt: 86.828522 acc_pose: 0.799040 loss: 86.828522 2022/10/12 18:13:48 - mmengine - INFO - Epoch(train) [125][400/586] lr: 5.000000e-03 eta: 4:26:05 time: 0.325957 data_time: 0.048140 memory: 4465 loss_kpt: 87.865522 acc_pose: 0.785638 loss: 87.865522 2022/10/12 18:14:04 - mmengine - INFO - Epoch(train) [125][450/586] lr: 5.000000e-03 eta: 4:25:50 time: 0.326961 data_time: 0.046381 memory: 4465 loss_kpt: 86.824603 acc_pose: 0.728965 loss: 86.824603 2022/10/12 18:14:22 - mmengine - INFO - Epoch(train) [125][500/586] lr: 5.000000e-03 eta: 4:25:34 time: 0.340694 data_time: 0.048732 memory: 4465 loss_kpt: 89.212022 acc_pose: 0.791214 loss: 89.212022 2022/10/12 18:14:38 - mmengine - INFO - Epoch(train) [125][550/586] lr: 5.000000e-03 eta: 4:25:19 time: 0.336630 data_time: 0.047832 memory: 4465 loss_kpt: 88.127635 acc_pose: 0.780901 loss: 88.127635 2022/10/12 18:14:50 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:15:08 - mmengine - INFO - Epoch(train) [126][50/586] lr: 5.000000e-03 eta: 4:24:45 time: 0.369469 data_time: 0.057948 memory: 4465 loss_kpt: 88.477479 acc_pose: 0.802256 loss: 88.477479 2022/10/12 18:15:25 - mmengine - INFO - Epoch(train) [126][100/586] lr: 5.000000e-03 eta: 4:24:30 time: 0.331980 data_time: 0.049340 memory: 4465 loss_kpt: 89.223187 acc_pose: 0.759137 loss: 89.223187 2022/10/12 18:15:41 - mmengine - INFO - Epoch(train) [126][150/586] lr: 5.000000e-03 eta: 4:24:14 time: 0.331462 data_time: 0.047594 memory: 4465 loss_kpt: 88.605688 acc_pose: 0.770371 loss: 88.605688 2022/10/12 18:15:58 - mmengine - INFO - Epoch(train) [126][200/586] lr: 5.000000e-03 eta: 4:23:59 time: 0.336479 data_time: 0.047892 memory: 4465 loss_kpt: 87.424844 acc_pose: 0.787428 loss: 87.424844 2022/10/12 18:16:15 - mmengine - INFO - Epoch(train) [126][250/586] lr: 5.000000e-03 eta: 4:23:43 time: 0.331706 data_time: 0.050960 memory: 4465 loss_kpt: 88.367500 acc_pose: 0.863068 loss: 88.367500 2022/10/12 18:16:32 - mmengine - INFO - Epoch(train) [126][300/586] lr: 5.000000e-03 eta: 4:23:28 time: 0.337080 data_time: 0.045966 memory: 4465 loss_kpt: 87.089495 acc_pose: 0.794401 loss: 87.089495 2022/10/12 18:16:48 - mmengine - INFO - Epoch(train) [126][350/586] lr: 5.000000e-03 eta: 4:23:13 time: 0.333654 data_time: 0.048837 memory: 4465 loss_kpt: 86.344304 acc_pose: 0.709149 loss: 86.344304 2022/10/12 18:17:05 - mmengine - INFO - Epoch(train) [126][400/586] lr: 5.000000e-03 eta: 4:22:57 time: 0.326861 data_time: 0.045425 memory: 4465 loss_kpt: 87.515968 acc_pose: 0.787920 loss: 87.515968 2022/10/12 18:17:22 - mmengine - INFO - Epoch(train) [126][450/586] lr: 5.000000e-03 eta: 4:22:41 time: 0.333953 data_time: 0.046227 memory: 4465 loss_kpt: 86.560375 acc_pose: 0.785832 loss: 86.560375 2022/10/12 18:17:38 - mmengine - INFO - Epoch(train) [126][500/586] lr: 5.000000e-03 eta: 4:22:26 time: 0.335098 data_time: 0.051158 memory: 4465 loss_kpt: 87.539046 acc_pose: 0.806791 loss: 87.539046 2022/10/12 18:17:55 - mmengine - INFO - Epoch(train) [126][550/586] lr: 5.000000e-03 eta: 4:22:10 time: 0.325377 data_time: 0.045728 memory: 4465 loss_kpt: 87.327597 acc_pose: 0.849570 loss: 87.327597 2022/10/12 18:18:06 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:18:24 - mmengine - INFO - Epoch(train) [127][50/586] lr: 5.000000e-03 eta: 4:21:36 time: 0.354534 data_time: 0.061993 memory: 4465 loss_kpt: 88.555597 acc_pose: 0.767736 loss: 88.555597 2022/10/12 18:18:41 - mmengine - INFO - Epoch(train) [127][100/586] lr: 5.000000e-03 eta: 4:21:21 time: 0.332050 data_time: 0.047626 memory: 4465 loss_kpt: 88.393546 acc_pose: 0.813725 loss: 88.393546 2022/10/12 18:18:58 - mmengine - INFO - Epoch(train) [127][150/586] lr: 5.000000e-03 eta: 4:21:06 time: 0.341468 data_time: 0.051888 memory: 4465 loss_kpt: 88.344294 acc_pose: 0.761712 loss: 88.344294 2022/10/12 18:19:02 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:19:14 - mmengine - INFO - Epoch(train) [127][200/586] lr: 5.000000e-03 eta: 4:20:50 time: 0.328208 data_time: 0.049508 memory: 4465 loss_kpt: 86.703821 acc_pose: 0.766292 loss: 86.703821 2022/10/12 18:19:31 - mmengine - INFO - Epoch(train) [127][250/586] lr: 5.000000e-03 eta: 4:20:34 time: 0.326298 data_time: 0.052462 memory: 4465 loss_kpt: 88.652381 acc_pose: 0.843921 loss: 88.652381 2022/10/12 18:19:47 - mmengine - INFO - Epoch(train) [127][300/586] lr: 5.000000e-03 eta: 4:20:19 time: 0.330110 data_time: 0.053388 memory: 4465 loss_kpt: 88.791722 acc_pose: 0.769296 loss: 88.791722 2022/10/12 18:20:04 - mmengine - INFO - Epoch(train) [127][350/586] lr: 5.000000e-03 eta: 4:20:03 time: 0.338533 data_time: 0.051833 memory: 4465 loss_kpt: 87.788944 acc_pose: 0.806496 loss: 87.788944 2022/10/12 18:20:21 - mmengine - INFO - Epoch(train) [127][400/586] lr: 5.000000e-03 eta: 4:19:48 time: 0.333958 data_time: 0.047074 memory: 4465 loss_kpt: 90.317993 acc_pose: 0.793337 loss: 90.317993 2022/10/12 18:20:38 - mmengine - INFO - Epoch(train) [127][450/586] lr: 5.000000e-03 eta: 4:19:33 time: 0.341701 data_time: 0.056084 memory: 4465 loss_kpt: 86.495589 acc_pose: 0.682186 loss: 86.495589 2022/10/12 18:20:54 - mmengine - INFO - Epoch(train) [127][500/586] lr: 5.000000e-03 eta: 4:19:17 time: 0.325789 data_time: 0.052048 memory: 4465 loss_kpt: 87.186526 acc_pose: 0.836201 loss: 87.186526 2022/10/12 18:21:11 - mmengine - INFO - Epoch(train) [127][550/586] lr: 5.000000e-03 eta: 4:19:01 time: 0.333420 data_time: 0.049606 memory: 4465 loss_kpt: 87.531789 acc_pose: 0.859295 loss: 87.531789 2022/10/12 18:21:22 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:21:40 - mmengine - INFO - Epoch(train) [128][50/586] lr: 5.000000e-03 eta: 4:18:27 time: 0.349662 data_time: 0.058247 memory: 4465 loss_kpt: 86.495401 acc_pose: 0.770272 loss: 86.495401 2022/10/12 18:21:57 - mmengine - INFO - Epoch(train) [128][100/586] lr: 5.000000e-03 eta: 4:18:12 time: 0.332879 data_time: 0.050735 memory: 4465 loss_kpt: 88.781672 acc_pose: 0.828411 loss: 88.781672 2022/10/12 18:22:13 - mmengine - INFO - Epoch(train) [128][150/586] lr: 5.000000e-03 eta: 4:17:56 time: 0.328095 data_time: 0.049498 memory: 4465 loss_kpt: 88.256614 acc_pose: 0.797777 loss: 88.256614 2022/10/12 18:22:30 - mmengine - INFO - Epoch(train) [128][200/586] lr: 5.000000e-03 eta: 4:17:41 time: 0.335081 data_time: 0.048956 memory: 4465 loss_kpt: 88.405254 acc_pose: 0.793813 loss: 88.405254 2022/10/12 18:22:46 - mmengine - INFO - Epoch(train) [128][250/586] lr: 5.000000e-03 eta: 4:17:25 time: 0.333713 data_time: 0.045937 memory: 4465 loss_kpt: 85.862859 acc_pose: 0.833019 loss: 85.862859 2022/10/12 18:23:03 - mmengine - INFO - Epoch(train) [128][300/586] lr: 5.000000e-03 eta: 4:17:10 time: 0.339358 data_time: 0.049510 memory: 4465 loss_kpt: 88.547676 acc_pose: 0.808618 loss: 88.547676 2022/10/12 18:23:20 - mmengine - INFO - Epoch(train) [128][350/586] lr: 5.000000e-03 eta: 4:16:54 time: 0.328673 data_time: 0.049641 memory: 4465 loss_kpt: 89.038788 acc_pose: 0.806253 loss: 89.038788 2022/10/12 18:23:37 - mmengine - INFO - Epoch(train) [128][400/586] lr: 5.000000e-03 eta: 4:16:39 time: 0.341244 data_time: 0.045487 memory: 4465 loss_kpt: 88.716548 acc_pose: 0.836001 loss: 88.716548 2022/10/12 18:23:54 - mmengine - INFO - Epoch(train) [128][450/586] lr: 5.000000e-03 eta: 4:16:23 time: 0.334682 data_time: 0.049679 memory: 4465 loss_kpt: 88.103568 acc_pose: 0.782493 loss: 88.103568 2022/10/12 18:24:10 - mmengine - INFO - Epoch(train) [128][500/586] lr: 5.000000e-03 eta: 4:16:08 time: 0.331804 data_time: 0.047981 memory: 4465 loss_kpt: 86.679362 acc_pose: 0.809558 loss: 86.679362 2022/10/12 18:24:27 - mmengine - INFO - Epoch(train) [128][550/586] lr: 5.000000e-03 eta: 4:15:53 time: 0.342118 data_time: 0.045102 memory: 4465 loss_kpt: 89.851804 acc_pose: 0.851811 loss: 89.851804 2022/10/12 18:24:37 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:24:39 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:24:57 - mmengine - INFO - Epoch(train) [129][50/586] lr: 5.000000e-03 eta: 4:15:19 time: 0.359568 data_time: 0.059408 memory: 4465 loss_kpt: 87.404945 acc_pose: 0.839030 loss: 87.404945 2022/10/12 18:25:15 - mmengine - INFO - Epoch(train) [129][100/586] lr: 5.000000e-03 eta: 4:15:04 time: 0.347872 data_time: 0.052451 memory: 4465 loss_kpt: 89.416960 acc_pose: 0.737988 loss: 89.416960 2022/10/12 18:25:32 - mmengine - INFO - Epoch(train) [129][150/586] lr: 5.000000e-03 eta: 4:14:49 time: 0.339556 data_time: 0.048476 memory: 4465 loss_kpt: 87.296868 acc_pose: 0.759083 loss: 87.296868 2022/10/12 18:25:48 - mmengine - INFO - Epoch(train) [129][200/586] lr: 5.000000e-03 eta: 4:14:33 time: 0.320235 data_time: 0.047113 memory: 4465 loss_kpt: 86.937169 acc_pose: 0.861626 loss: 86.937169 2022/10/12 18:26:04 - mmengine - INFO - Epoch(train) [129][250/586] lr: 5.000000e-03 eta: 4:14:17 time: 0.326088 data_time: 0.046735 memory: 4465 loss_kpt: 88.086246 acc_pose: 0.707965 loss: 88.086246 2022/10/12 18:26:21 - mmengine - INFO - Epoch(train) [129][300/586] lr: 5.000000e-03 eta: 4:14:02 time: 0.331648 data_time: 0.050877 memory: 4465 loss_kpt: 87.985067 acc_pose: 0.831695 loss: 87.985067 2022/10/12 18:26:37 - mmengine - INFO - Epoch(train) [129][350/586] lr: 5.000000e-03 eta: 4:13:46 time: 0.335465 data_time: 0.050967 memory: 4465 loss_kpt: 88.228563 acc_pose: 0.808575 loss: 88.228563 2022/10/12 18:26:54 - mmengine - INFO - Epoch(train) [129][400/586] lr: 5.000000e-03 eta: 4:13:31 time: 0.339886 data_time: 0.049334 memory: 4465 loss_kpt: 86.773198 acc_pose: 0.834093 loss: 86.773198 2022/10/12 18:27:11 - mmengine - INFO - Epoch(train) [129][450/586] lr: 5.000000e-03 eta: 4:13:15 time: 0.335360 data_time: 0.049038 memory: 4465 loss_kpt: 87.767527 acc_pose: 0.793686 loss: 87.767527 2022/10/12 18:27:27 - mmengine - INFO - Epoch(train) [129][500/586] lr: 5.000000e-03 eta: 4:13:00 time: 0.324598 data_time: 0.049221 memory: 4465 loss_kpt: 89.094621 acc_pose: 0.837206 loss: 89.094621 2022/10/12 18:27:44 - mmengine - INFO - Epoch(train) [129][550/586] lr: 5.000000e-03 eta: 4:12:44 time: 0.334975 data_time: 0.054112 memory: 4465 loss_kpt: 89.031606 acc_pose: 0.753708 loss: 89.031606 2022/10/12 18:27:56 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:28:13 - mmengine - INFO - Epoch(train) [130][50/586] lr: 5.000000e-03 eta: 4:12:10 time: 0.350732 data_time: 0.063539 memory: 4465 loss_kpt: 86.483620 acc_pose: 0.846828 loss: 86.483620 2022/10/12 18:28:31 - mmengine - INFO - Epoch(train) [130][100/586] lr: 5.000000e-03 eta: 4:11:55 time: 0.342342 data_time: 0.049348 memory: 4465 loss_kpt: 86.822785 acc_pose: 0.786108 loss: 86.822785 2022/10/12 18:28:48 - mmengine - INFO - Epoch(train) [130][150/586] lr: 5.000000e-03 eta: 4:11:40 time: 0.340711 data_time: 0.060136 memory: 4465 loss_kpt: 88.963170 acc_pose: 0.758177 loss: 88.963170 2022/10/12 18:29:04 - mmengine - INFO - Epoch(train) [130][200/586] lr: 5.000000e-03 eta: 4:11:24 time: 0.332288 data_time: 0.045769 memory: 4465 loss_kpt: 85.990945 acc_pose: 0.808096 loss: 85.990945 2022/10/12 18:29:21 - mmengine - INFO - Epoch(train) [130][250/586] lr: 5.000000e-03 eta: 4:11:09 time: 0.338446 data_time: 0.059464 memory: 4465 loss_kpt: 87.094175 acc_pose: 0.720840 loss: 87.094175 2022/10/12 18:29:38 - mmengine - INFO - Epoch(train) [130][300/586] lr: 5.000000e-03 eta: 4:10:54 time: 0.332499 data_time: 0.054410 memory: 4465 loss_kpt: 87.737543 acc_pose: 0.791405 loss: 87.737543 2022/10/12 18:29:54 - mmengine - INFO - Epoch(train) [130][350/586] lr: 5.000000e-03 eta: 4:10:38 time: 0.331809 data_time: 0.058352 memory: 4465 loss_kpt: 90.008425 acc_pose: 0.752249 loss: 90.008425 2022/10/12 18:30:11 - mmengine - INFO - Epoch(train) [130][400/586] lr: 5.000000e-03 eta: 4:10:22 time: 0.324828 data_time: 0.050499 memory: 4465 loss_kpt: 87.206884 acc_pose: 0.800844 loss: 87.206884 2022/10/12 18:30:13 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:30:27 - mmengine - INFO - Epoch(train) [130][450/586] lr: 5.000000e-03 eta: 4:10:06 time: 0.325632 data_time: 0.054833 memory: 4465 loss_kpt: 87.722742 acc_pose: 0.851567 loss: 87.722742 2022/10/12 18:30:44 - mmengine - INFO - Epoch(train) [130][500/586] lr: 5.000000e-03 eta: 4:09:51 time: 0.332411 data_time: 0.046838 memory: 4465 loss_kpt: 87.131833 acc_pose: 0.793714 loss: 87.131833 2022/10/12 18:31:00 - mmengine - INFO - Epoch(train) [130][550/586] lr: 5.000000e-03 eta: 4:09:35 time: 0.324853 data_time: 0.050845 memory: 4465 loss_kpt: 88.219789 acc_pose: 0.826730 loss: 88.219789 2022/10/12 18:31:12 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:31:12 - mmengine - INFO - Saving checkpoint at 130 epochs 2022/10/12 18:31:21 - mmengine - INFO - Epoch(val) [130][50/407] eta: 0:00:48 time: 0.134538 data_time: 0.013709 memory: 4465 2022/10/12 18:31:28 - mmengine - INFO - Epoch(val) [130][100/407] eta: 0:00:38 time: 0.126386 data_time: 0.008039 memory: 1026 2022/10/12 18:31:34 - mmengine - INFO - Epoch(val) [130][150/407] eta: 0:00:33 time: 0.131915 data_time: 0.011691 memory: 1026 2022/10/12 18:31:41 - mmengine - INFO - Epoch(val) [130][200/407] eta: 0:00:26 time: 0.127578 data_time: 0.007994 memory: 1026 2022/10/12 18:31:47 - mmengine - INFO - Epoch(val) [130][250/407] eta: 0:00:19 time: 0.125571 data_time: 0.008198 memory: 1026 2022/10/12 18:31:53 - mmengine - INFO - Epoch(val) [130][300/407] eta: 0:00:13 time: 0.127047 data_time: 0.008082 memory: 1026 2022/10/12 18:32:00 - mmengine - INFO - Epoch(val) [130][350/407] eta: 0:00:07 time: 0.128333 data_time: 0.008388 memory: 1026 2022/10/12 18:32:06 - mmengine - INFO - Epoch(val) [130][400/407] eta: 0:00:00 time: 0.125482 data_time: 0.007982 memory: 1026 2022/10/12 18:32:19 - mmengine - INFO - Evaluating CocoMetric... 2022/10/12 18:32:35 - mmengine - INFO - Epoch(val) [130][407/407] coco/AP: 0.695567 coco/AP .5: 0.883955 coco/AP .75: 0.770253 coco/AP (M): 0.664504 coco/AP (L): 0.754502 coco/AR: 0.765696 coco/AR .5: 0.925693 coco/AR .75: 0.828401 coco/AR (M): 0.721934 coco/AR (L): 0.826161 2022/10/12 18:32:52 - mmengine - INFO - Epoch(train) [131][50/586] lr: 5.000000e-03 eta: 4:09:01 time: 0.338871 data_time: 0.056922 memory: 4465 loss_kpt: 88.248337 acc_pose: 0.882410 loss: 88.248337 2022/10/12 18:33:09 - mmengine - INFO - Epoch(train) [131][100/586] lr: 5.000000e-03 eta: 4:08:46 time: 0.339719 data_time: 0.050070 memory: 4465 loss_kpt: 87.665057 acc_pose: 0.865514 loss: 87.665057 2022/10/12 18:33:26 - mmengine - INFO - Epoch(train) [131][150/586] lr: 5.000000e-03 eta: 4:08:31 time: 0.347006 data_time: 0.051197 memory: 4465 loss_kpt: 86.503218 acc_pose: 0.762699 loss: 86.503218 2022/10/12 18:33:43 - mmengine - INFO - Epoch(train) [131][200/586] lr: 5.000000e-03 eta: 4:08:16 time: 0.345818 data_time: 0.056692 memory: 4465 loss_kpt: 87.566158 acc_pose: 0.830117 loss: 87.566158 2022/10/12 18:34:01 - mmengine - INFO - Epoch(train) [131][250/586] lr: 5.000000e-03 eta: 4:08:00 time: 0.340670 data_time: 0.046140 memory: 4465 loss_kpt: 87.746627 acc_pose: 0.818199 loss: 87.746627 2022/10/12 18:34:18 - mmengine - INFO - Epoch(train) [131][300/586] lr: 5.000000e-03 eta: 4:07:45 time: 0.345799 data_time: 0.050053 memory: 4465 loss_kpt: 87.808405 acc_pose: 0.813936 loss: 87.808405 2022/10/12 18:34:35 - mmengine - INFO - Epoch(train) [131][350/586] lr: 5.000000e-03 eta: 4:07:30 time: 0.346442 data_time: 0.053709 memory: 4465 loss_kpt: 86.920740 acc_pose: 0.740546 loss: 86.920740 2022/10/12 18:34:52 - mmengine - INFO - Epoch(train) [131][400/586] lr: 5.000000e-03 eta: 4:07:15 time: 0.340279 data_time: 0.053271 memory: 4465 loss_kpt: 86.634082 acc_pose: 0.812602 loss: 86.634082 2022/10/12 18:35:10 - mmengine - INFO - Epoch(train) [131][450/586] lr: 5.000000e-03 eta: 4:07:00 time: 0.345772 data_time: 0.054709 memory: 4465 loss_kpt: 87.815300 acc_pose: 0.875367 loss: 87.815300 2022/10/12 18:35:27 - mmengine - INFO - Epoch(train) [131][500/586] lr: 5.000000e-03 eta: 4:06:44 time: 0.345449 data_time: 0.053124 memory: 4465 loss_kpt: 88.515914 acc_pose: 0.827298 loss: 88.515914 2022/10/12 18:35:44 - mmengine - INFO - Epoch(train) [131][550/586] lr: 5.000000e-03 eta: 4:06:29 time: 0.335480 data_time: 0.053730 memory: 4465 loss_kpt: 88.582652 acc_pose: 0.839239 loss: 88.582652 2022/10/12 18:35:56 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:36:14 - mmengine - INFO - Epoch(train) [132][50/586] lr: 5.000000e-03 eta: 4:05:56 time: 0.360730 data_time: 0.064305 memory: 4465 loss_kpt: 86.222475 acc_pose: 0.800835 loss: 86.222475 2022/10/12 18:36:31 - mmengine - INFO - Epoch(train) [132][100/586] lr: 5.000000e-03 eta: 4:05:41 time: 0.348267 data_time: 0.050748 memory: 4465 loss_kpt: 87.183216 acc_pose: 0.842176 loss: 87.183216 2022/10/12 18:36:48 - mmengine - INFO - Epoch(train) [132][150/586] lr: 5.000000e-03 eta: 4:05:26 time: 0.347877 data_time: 0.053845 memory: 4465 loss_kpt: 89.058430 acc_pose: 0.824134 loss: 89.058430 2022/10/12 18:37:06 - mmengine - INFO - Epoch(train) [132][200/586] lr: 5.000000e-03 eta: 4:05:11 time: 0.358316 data_time: 0.053246 memory: 4465 loss_kpt: 85.760879 acc_pose: 0.857902 loss: 85.760879 2022/10/12 18:37:18 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:37:23 - mmengine - INFO - Epoch(train) [132][250/586] lr: 5.000000e-03 eta: 4:04:55 time: 0.336350 data_time: 0.047508 memory: 4465 loss_kpt: 88.065401 acc_pose: 0.841008 loss: 88.065401 2022/10/12 18:37:40 - mmengine - INFO - Epoch(train) [132][300/586] lr: 5.000000e-03 eta: 4:04:40 time: 0.334773 data_time: 0.050057 memory: 4465 loss_kpt: 86.641802 acc_pose: 0.832135 loss: 86.641802 2022/10/12 18:37:57 - mmengine - INFO - Epoch(train) [132][350/586] lr: 5.000000e-03 eta: 4:04:24 time: 0.332733 data_time: 0.051170 memory: 4465 loss_kpt: 87.549122 acc_pose: 0.829446 loss: 87.549122 2022/10/12 18:38:13 - mmengine - INFO - Epoch(train) [132][400/586] lr: 5.000000e-03 eta: 4:04:08 time: 0.322401 data_time: 0.048997 memory: 4465 loss_kpt: 87.110793 acc_pose: 0.850469 loss: 87.110793 2022/10/12 18:38:29 - mmengine - INFO - Epoch(train) [132][450/586] lr: 5.000000e-03 eta: 4:03:53 time: 0.327863 data_time: 0.052021 memory: 4465 loss_kpt: 89.972937 acc_pose: 0.813310 loss: 89.972937 2022/10/12 18:38:46 - mmengine - INFO - Epoch(train) [132][500/586] lr: 5.000000e-03 eta: 4:03:37 time: 0.332538 data_time: 0.054380 memory: 4465 loss_kpt: 87.066200 acc_pose: 0.807100 loss: 87.066200 2022/10/12 18:39:02 - mmengine - INFO - Epoch(train) [132][550/586] lr: 5.000000e-03 eta: 4:03:21 time: 0.324653 data_time: 0.048676 memory: 4465 loss_kpt: 87.356684 acc_pose: 0.792354 loss: 87.356684 2022/10/12 18:39:14 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:39:31 - mmengine - INFO - Epoch(train) [133][50/586] lr: 5.000000e-03 eta: 4:02:48 time: 0.352730 data_time: 0.066481 memory: 4465 loss_kpt: 88.774970 acc_pose: 0.813185 loss: 88.774970 2022/10/12 18:39:48 - mmengine - INFO - Epoch(train) [133][100/586] lr: 5.000000e-03 eta: 4:02:33 time: 0.333947 data_time: 0.050123 memory: 4465 loss_kpt: 86.241593 acc_pose: 0.874292 loss: 86.241593 2022/10/12 18:40:04 - mmengine - INFO - Epoch(train) [133][150/586] lr: 5.000000e-03 eta: 4:02:17 time: 0.326539 data_time: 0.053801 memory: 4465 loss_kpt: 87.744794 acc_pose: 0.840841 loss: 87.744794 2022/10/12 18:40:20 - mmengine - INFO - Epoch(train) [133][200/586] lr: 5.000000e-03 eta: 4:02:01 time: 0.322128 data_time: 0.052529 memory: 4465 loss_kpt: 86.837807 acc_pose: 0.803963 loss: 86.837807 2022/10/12 18:40:37 - mmengine - INFO - Epoch(train) [133][250/586] lr: 5.000000e-03 eta: 4:01:45 time: 0.320264 data_time: 0.051578 memory: 4465 loss_kpt: 86.612721 acc_pose: 0.761846 loss: 86.612721 2022/10/12 18:40:53 - mmengine - INFO - Epoch(train) [133][300/586] lr: 5.000000e-03 eta: 4:01:30 time: 0.331517 data_time: 0.050906 memory: 4465 loss_kpt: 87.557719 acc_pose: 0.788932 loss: 87.557719 2022/10/12 18:41:10 - mmengine - INFO - Epoch(train) [133][350/586] lr: 5.000000e-03 eta: 4:01:14 time: 0.334964 data_time: 0.052779 memory: 4465 loss_kpt: 88.926633 acc_pose: 0.807380 loss: 88.926633 2022/10/12 18:41:27 - mmengine - INFO - Epoch(train) [133][400/586] lr: 5.000000e-03 eta: 4:00:59 time: 0.337884 data_time: 0.052210 memory: 4465 loss_kpt: 87.792772 acc_pose: 0.836875 loss: 87.792772 2022/10/12 18:41:43 - mmengine - INFO - Epoch(train) [133][450/586] lr: 5.000000e-03 eta: 4:00:43 time: 0.330898 data_time: 0.052733 memory: 4465 loss_kpt: 87.782595 acc_pose: 0.802736 loss: 87.782595 2022/10/12 18:42:00 - mmengine - INFO - Epoch(train) [133][500/586] lr: 5.000000e-03 eta: 4:00:28 time: 0.341981 data_time: 0.053490 memory: 4465 loss_kpt: 87.683288 acc_pose: 0.852967 loss: 87.683288 2022/10/12 18:42:17 - mmengine - INFO - Epoch(train) [133][550/586] lr: 5.000000e-03 eta: 4:00:12 time: 0.329550 data_time: 0.054176 memory: 4465 loss_kpt: 87.009410 acc_pose: 0.817425 loss: 87.009410 2022/10/12 18:42:28 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:42:46 - mmengine - INFO - Epoch(train) [134][50/586] lr: 5.000000e-03 eta: 3:59:39 time: 0.352915 data_time: 0.065813 memory: 4465 loss_kpt: 88.162430 acc_pose: 0.767906 loss: 88.162430 2022/10/12 18:42:50 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:43:03 - mmengine - INFO - Epoch(train) [134][100/586] lr: 5.000000e-03 eta: 3:59:23 time: 0.330220 data_time: 0.048917 memory: 4465 loss_kpt: 88.926403 acc_pose: 0.799084 loss: 88.926403 2022/10/12 18:43:20 - mmengine - INFO - Epoch(train) [134][150/586] lr: 5.000000e-03 eta: 3:59:08 time: 0.343410 data_time: 0.052625 memory: 4465 loss_kpt: 87.577419 acc_pose: 0.779512 loss: 87.577419 2022/10/12 18:43:36 - mmengine - INFO - Epoch(train) [134][200/586] lr: 5.000000e-03 eta: 3:58:52 time: 0.330475 data_time: 0.052294 memory: 4465 loss_kpt: 86.367053 acc_pose: 0.804849 loss: 86.367053 2022/10/12 18:43:53 - mmengine - INFO - Epoch(train) [134][250/586] lr: 5.000000e-03 eta: 3:58:37 time: 0.333382 data_time: 0.051366 memory: 4465 loss_kpt: 87.038920 acc_pose: 0.786688 loss: 87.038920 2022/10/12 18:44:09 - mmengine - INFO - Epoch(train) [134][300/586] lr: 5.000000e-03 eta: 3:58:21 time: 0.325092 data_time: 0.048313 memory: 4465 loss_kpt: 87.627774 acc_pose: 0.869467 loss: 87.627774 2022/10/12 18:44:26 - mmengine - INFO - Epoch(train) [134][350/586] lr: 5.000000e-03 eta: 3:58:06 time: 0.333780 data_time: 0.054975 memory: 4465 loss_kpt: 86.384982 acc_pose: 0.792563 loss: 86.384982 2022/10/12 18:44:43 - mmengine - INFO - Epoch(train) [134][400/586] lr: 5.000000e-03 eta: 3:57:50 time: 0.344199 data_time: 0.049930 memory: 4465 loss_kpt: 88.173202 acc_pose: 0.838536 loss: 88.173202 2022/10/12 18:45:00 - mmengine - INFO - Epoch(train) [134][450/586] lr: 5.000000e-03 eta: 3:57:35 time: 0.336941 data_time: 0.052936 memory: 4465 loss_kpt: 87.362689 acc_pose: 0.884725 loss: 87.362689 2022/10/12 18:45:16 - mmengine - INFO - Epoch(train) [134][500/586] lr: 5.000000e-03 eta: 3:57:19 time: 0.325804 data_time: 0.045973 memory: 4465 loss_kpt: 87.042560 acc_pose: 0.814973 loss: 87.042560 2022/10/12 18:45:33 - mmengine - INFO - Epoch(train) [134][550/586] lr: 5.000000e-03 eta: 3:57:04 time: 0.332064 data_time: 0.050886 memory: 4465 loss_kpt: 87.333525 acc_pose: 0.857765 loss: 87.333525 2022/10/12 18:45:45 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:46:03 - mmengine - INFO - Epoch(train) [135][50/586] lr: 5.000000e-03 eta: 3:56:31 time: 0.352751 data_time: 0.061593 memory: 4465 loss_kpt: 86.951404 acc_pose: 0.826202 loss: 86.951404 2022/10/12 18:46:20 - mmengine - INFO - Epoch(train) [135][100/586] lr: 5.000000e-03 eta: 3:56:15 time: 0.343461 data_time: 0.047791 memory: 4465 loss_kpt: 88.171325 acc_pose: 0.829620 loss: 88.171325 2022/10/12 18:46:37 - mmengine - INFO - Epoch(train) [135][150/586] lr: 5.000000e-03 eta: 3:56:00 time: 0.343828 data_time: 0.051818 memory: 4465 loss_kpt: 87.069786 acc_pose: 0.850160 loss: 87.069786 2022/10/12 18:46:54 - mmengine - INFO - Epoch(train) [135][200/586] lr: 5.000000e-03 eta: 3:55:45 time: 0.337610 data_time: 0.047650 memory: 4465 loss_kpt: 86.037350 acc_pose: 0.855512 loss: 86.037350 2022/10/12 18:47:11 - mmengine - INFO - Epoch(train) [135][250/586] lr: 5.000000e-03 eta: 3:55:29 time: 0.339399 data_time: 0.057083 memory: 4465 loss_kpt: 88.104628 acc_pose: 0.818859 loss: 88.104628 2022/10/12 18:47:28 - mmengine - INFO - Epoch(train) [135][300/586] lr: 5.000000e-03 eta: 3:55:14 time: 0.333596 data_time: 0.053840 memory: 4465 loss_kpt: 87.217573 acc_pose: 0.797556 loss: 87.217573 2022/10/12 18:47:44 - mmengine - INFO - Epoch(train) [135][350/586] lr: 5.000000e-03 eta: 3:54:58 time: 0.336173 data_time: 0.048538 memory: 4465 loss_kpt: 87.503356 acc_pose: 0.703458 loss: 87.503356 2022/10/12 18:48:01 - mmengine - INFO - Epoch(train) [135][400/586] lr: 5.000000e-03 eta: 3:54:43 time: 0.331661 data_time: 0.052772 memory: 4465 loss_kpt: 87.014179 acc_pose: 0.783119 loss: 87.014179 2022/10/12 18:48:17 - mmengine - INFO - Epoch(train) [135][450/586] lr: 5.000000e-03 eta: 3:54:26 time: 0.311535 data_time: 0.047571 memory: 4465 loss_kpt: 88.350652 acc_pose: 0.810156 loss: 88.350652 2022/10/12 18:48:25 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:48:33 - mmengine - INFO - Epoch(train) [135][500/586] lr: 5.000000e-03 eta: 3:54:11 time: 0.333322 data_time: 0.049562 memory: 4465 loss_kpt: 86.238441 acc_pose: 0.889114 loss: 86.238441 2022/10/12 18:48:50 - mmengine - INFO - Epoch(train) [135][550/586] lr: 5.000000e-03 eta: 3:53:55 time: 0.332431 data_time: 0.048948 memory: 4465 loss_kpt: 86.528713 acc_pose: 0.791518 loss: 86.528713 2022/10/12 18:49:02 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:49:20 - mmengine - INFO - Epoch(train) [136][50/586] lr: 5.000000e-03 eta: 3:53:22 time: 0.353663 data_time: 0.060338 memory: 4465 loss_kpt: 86.824438 acc_pose: 0.877236 loss: 86.824438 2022/10/12 18:49:37 - mmengine - INFO - Epoch(train) [136][100/586] lr: 5.000000e-03 eta: 3:53:07 time: 0.352709 data_time: 0.054726 memory: 4465 loss_kpt: 87.036433 acc_pose: 0.782156 loss: 87.036433 2022/10/12 18:49:55 - mmengine - INFO - Epoch(train) [136][150/586] lr: 5.000000e-03 eta: 3:52:53 time: 0.356305 data_time: 0.052290 memory: 4465 loss_kpt: 87.483582 acc_pose: 0.795235 loss: 87.483582 2022/10/12 18:50:12 - mmengine - INFO - Epoch(train) [136][200/586] lr: 5.000000e-03 eta: 3:52:37 time: 0.338388 data_time: 0.048012 memory: 4465 loss_kpt: 86.309692 acc_pose: 0.744474 loss: 86.309692 2022/10/12 18:50:30 - mmengine - INFO - Epoch(train) [136][250/586] lr: 5.000000e-03 eta: 3:52:22 time: 0.352509 data_time: 0.056578 memory: 4465 loss_kpt: 87.394674 acc_pose: 0.861440 loss: 87.394674 2022/10/12 18:50:47 - mmengine - INFO - Epoch(train) [136][300/586] lr: 5.000000e-03 eta: 3:52:07 time: 0.354360 data_time: 0.050997 memory: 4465 loss_kpt: 85.767378 acc_pose: 0.789914 loss: 85.767378 2022/10/12 18:51:05 - mmengine - INFO - Epoch(train) [136][350/586] lr: 5.000000e-03 eta: 3:51:52 time: 0.345583 data_time: 0.052341 memory: 4465 loss_kpt: 88.239167 acc_pose: 0.726244 loss: 88.239167 2022/10/12 18:51:22 - mmengine - INFO - Epoch(train) [136][400/586] lr: 5.000000e-03 eta: 3:51:37 time: 0.346375 data_time: 0.052957 memory: 4465 loss_kpt: 87.791821 acc_pose: 0.828394 loss: 87.791821 2022/10/12 18:51:40 - mmengine - INFO - Epoch(train) [136][450/586] lr: 5.000000e-03 eta: 3:51:22 time: 0.353017 data_time: 0.052772 memory: 4465 loss_kpt: 88.093532 acc_pose: 0.824265 loss: 88.093532 2022/10/12 18:51:57 - mmengine - INFO - Epoch(train) [136][500/586] lr: 5.000000e-03 eta: 3:51:06 time: 0.345383 data_time: 0.051147 memory: 4465 loss_kpt: 88.267935 acc_pose: 0.822188 loss: 88.267935 2022/10/12 18:52:14 - mmengine - INFO - Epoch(train) [136][550/586] lr: 5.000000e-03 eta: 3:50:51 time: 0.342484 data_time: 0.049469 memory: 4465 loss_kpt: 87.547593 acc_pose: 0.813907 loss: 87.547593 2022/10/12 18:52:26 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:52:44 - mmengine - INFO - Epoch(train) [137][50/586] lr: 5.000000e-03 eta: 3:50:19 time: 0.359660 data_time: 0.063197 memory: 4465 loss_kpt: 87.045800 acc_pose: 0.881109 loss: 87.045800 2022/10/12 18:53:01 - mmengine - INFO - Epoch(train) [137][100/586] lr: 5.000000e-03 eta: 3:50:03 time: 0.338860 data_time: 0.055307 memory: 4465 loss_kpt: 87.668584 acc_pose: 0.806954 loss: 87.668584 2022/10/12 18:53:17 - mmengine - INFO - Epoch(train) [137][150/586] lr: 5.000000e-03 eta: 3:49:47 time: 0.321965 data_time: 0.049633 memory: 4465 loss_kpt: 87.346414 acc_pose: 0.834329 loss: 87.346414 2022/10/12 18:53:33 - mmengine - INFO - Epoch(train) [137][200/586] lr: 5.000000e-03 eta: 3:49:31 time: 0.316942 data_time: 0.048662 memory: 4465 loss_kpt: 86.906105 acc_pose: 0.859327 loss: 86.906105 2022/10/12 18:53:50 - mmengine - INFO - Epoch(train) [137][250/586] lr: 5.000000e-03 eta: 3:49:16 time: 0.330630 data_time: 0.045983 memory: 4465 loss_kpt: 88.305353 acc_pose: 0.822493 loss: 88.305353 2022/10/12 18:54:06 - mmengine - INFO - Epoch(train) [137][300/586] lr: 5.000000e-03 eta: 3:49:00 time: 0.320278 data_time: 0.050558 memory: 4465 loss_kpt: 85.134405 acc_pose: 0.812801 loss: 85.134405 2022/10/12 18:54:07 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:54:22 - mmengine - INFO - Epoch(train) [137][350/586] lr: 5.000000e-03 eta: 3:48:44 time: 0.332321 data_time: 0.047743 memory: 4465 loss_kpt: 86.260558 acc_pose: 0.814281 loss: 86.260558 2022/10/12 18:54:39 - mmengine - INFO - Epoch(train) [137][400/586] lr: 5.000000e-03 eta: 3:48:28 time: 0.329793 data_time: 0.045276 memory: 4465 loss_kpt: 86.578380 acc_pose: 0.843521 loss: 86.578380 2022/10/12 18:54:55 - mmengine - INFO - Epoch(train) [137][450/586] lr: 5.000000e-03 eta: 3:48:13 time: 0.325544 data_time: 0.048033 memory: 4465 loss_kpt: 87.115641 acc_pose: 0.787323 loss: 87.115641 2022/10/12 18:55:11 - mmengine - INFO - Epoch(train) [137][500/586] lr: 5.000000e-03 eta: 3:47:57 time: 0.325334 data_time: 0.049024 memory: 4465 loss_kpt: 86.650573 acc_pose: 0.796489 loss: 86.650573 2022/10/12 18:55:28 - mmengine - INFO - Epoch(train) [137][550/586] lr: 5.000000e-03 eta: 3:47:41 time: 0.340400 data_time: 0.050780 memory: 4465 loss_kpt: 88.588276 acc_pose: 0.766208 loss: 88.588276 2022/10/12 18:55:40 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:55:58 - mmengine - INFO - Epoch(train) [138][50/586] lr: 5.000000e-03 eta: 3:47:09 time: 0.344893 data_time: 0.063263 memory: 4465 loss_kpt: 87.717563 acc_pose: 0.764734 loss: 87.717563 2022/10/12 18:56:15 - mmengine - INFO - Epoch(train) [138][100/586] lr: 5.000000e-03 eta: 3:46:53 time: 0.342252 data_time: 0.048114 memory: 4465 loss_kpt: 86.991975 acc_pose: 0.873344 loss: 86.991975 2022/10/12 18:56:31 - mmengine - INFO - Epoch(train) [138][150/586] lr: 5.000000e-03 eta: 3:46:38 time: 0.330261 data_time: 0.049921 memory: 4465 loss_kpt: 87.825325 acc_pose: 0.724113 loss: 87.825325 2022/10/12 18:56:48 - mmengine - INFO - Epoch(train) [138][200/586] lr: 5.000000e-03 eta: 3:46:22 time: 0.339642 data_time: 0.047664 memory: 4465 loss_kpt: 86.057090 acc_pose: 0.868302 loss: 86.057090 2022/10/12 18:57:06 - mmengine - INFO - Epoch(train) [138][250/586] lr: 5.000000e-03 eta: 3:46:07 time: 0.349064 data_time: 0.049950 memory: 4465 loss_kpt: 87.667387 acc_pose: 0.824758 loss: 87.667387 2022/10/12 18:57:23 - mmengine - INFO - Epoch(train) [138][300/586] lr: 5.000000e-03 eta: 3:45:52 time: 0.352492 data_time: 0.045671 memory: 4465 loss_kpt: 86.431348 acc_pose: 0.807558 loss: 86.431348 2022/10/12 18:57:41 - mmengine - INFO - Epoch(train) [138][350/586] lr: 5.000000e-03 eta: 3:45:37 time: 0.343787 data_time: 0.051441 memory: 4465 loss_kpt: 86.501172 acc_pose: 0.832911 loss: 86.501172 2022/10/12 18:57:57 - mmengine - INFO - Epoch(train) [138][400/586] lr: 5.000000e-03 eta: 3:45:21 time: 0.334731 data_time: 0.044914 memory: 4465 loss_kpt: 88.234991 acc_pose: 0.863496 loss: 88.234991 2022/10/12 18:58:14 - mmengine - INFO - Epoch(train) [138][450/586] lr: 5.000000e-03 eta: 3:45:06 time: 0.337290 data_time: 0.045661 memory: 4465 loss_kpt: 86.424802 acc_pose: 0.867823 loss: 86.424802 2022/10/12 18:58:32 - mmengine - INFO - Epoch(train) [138][500/586] lr: 5.000000e-03 eta: 3:44:51 time: 0.351034 data_time: 0.046090 memory: 4465 loss_kpt: 87.912388 acc_pose: 0.846094 loss: 87.912388 2022/10/12 18:58:49 - mmengine - INFO - Epoch(train) [138][550/586] lr: 5.000000e-03 eta: 3:44:35 time: 0.344456 data_time: 0.055104 memory: 4465 loss_kpt: 88.034879 acc_pose: 0.793508 loss: 88.034879 2022/10/12 18:59:02 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:59:19 - mmengine - INFO - Epoch(train) [139][50/586] lr: 5.000000e-03 eta: 3:44:02 time: 0.341806 data_time: 0.066803 memory: 4465 loss_kpt: 87.029255 acc_pose: 0.843669 loss: 87.029255 2022/10/12 18:59:35 - mmengine - INFO - Epoch(train) [139][100/586] lr: 5.000000e-03 eta: 3:43:47 time: 0.327084 data_time: 0.049012 memory: 4465 loss_kpt: 86.261683 acc_pose: 0.776462 loss: 86.261683 2022/10/12 18:59:46 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 18:59:52 - mmengine - INFO - Epoch(train) [139][150/586] lr: 5.000000e-03 eta: 3:43:31 time: 0.348252 data_time: 0.050064 memory: 4465 loss_kpt: 87.059559 acc_pose: 0.826713 loss: 87.059559 2022/10/12 19:00:10 - mmengine - INFO - Epoch(train) [139][200/586] lr: 5.000000e-03 eta: 3:43:16 time: 0.346773 data_time: 0.050205 memory: 4465 loss_kpt: 87.260897 acc_pose: 0.871202 loss: 87.260897 2022/10/12 19:00:27 - mmengine - INFO - Epoch(train) [139][250/586] lr: 5.000000e-03 eta: 3:43:01 time: 0.338817 data_time: 0.050555 memory: 4465 loss_kpt: 86.545403 acc_pose: 0.769551 loss: 86.545403 2022/10/12 19:00:44 - mmengine - INFO - Epoch(train) [139][300/586] lr: 5.000000e-03 eta: 3:42:46 time: 0.347483 data_time: 0.046811 memory: 4465 loss_kpt: 86.022376 acc_pose: 0.794684 loss: 86.022376 2022/10/12 19:01:02 - mmengine - INFO - Epoch(train) [139][350/586] lr: 5.000000e-03 eta: 3:42:30 time: 0.351503 data_time: 0.046637 memory: 4465 loss_kpt: 86.807158 acc_pose: 0.749342 loss: 86.807158 2022/10/12 19:01:19 - mmengine - INFO - Epoch(train) [139][400/586] lr: 5.000000e-03 eta: 3:42:15 time: 0.338950 data_time: 0.049873 memory: 4465 loss_kpt: 87.640558 acc_pose: 0.792943 loss: 87.640558 2022/10/12 19:01:36 - mmengine - INFO - Epoch(train) [139][450/586] lr: 5.000000e-03 eta: 3:42:00 time: 0.340996 data_time: 0.048532 memory: 4465 loss_kpt: 86.390641 acc_pose: 0.902466 loss: 86.390641 2022/10/12 19:01:53 - mmengine - INFO - Epoch(train) [139][500/586] lr: 5.000000e-03 eta: 3:41:44 time: 0.343574 data_time: 0.049361 memory: 4465 loss_kpt: 87.207382 acc_pose: 0.817660 loss: 87.207382 2022/10/12 19:02:10 - mmengine - INFO - Epoch(train) [139][550/586] lr: 5.000000e-03 eta: 3:41:29 time: 0.331855 data_time: 0.047831 memory: 4465 loss_kpt: 87.547463 acc_pose: 0.769849 loss: 87.547463 2022/10/12 19:02:21 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:02:39 - mmengine - INFO - Epoch(train) [140][50/586] lr: 5.000000e-03 eta: 3:40:56 time: 0.354478 data_time: 0.055432 memory: 4465 loss_kpt: 89.186755 acc_pose: 0.765206 loss: 89.186755 2022/10/12 19:02:56 - mmengine - INFO - Epoch(train) [140][100/586] lr: 5.000000e-03 eta: 3:40:41 time: 0.341620 data_time: 0.049664 memory: 4465 loss_kpt: 86.812840 acc_pose: 0.761804 loss: 86.812840 2022/10/12 19:03:13 - mmengine - INFO - Epoch(train) [140][150/586] lr: 5.000000e-03 eta: 3:40:25 time: 0.339010 data_time: 0.050857 memory: 4465 loss_kpt: 86.881943 acc_pose: 0.831936 loss: 86.881943 2022/10/12 19:03:30 - mmengine - INFO - Epoch(train) [140][200/586] lr: 5.000000e-03 eta: 3:40:10 time: 0.334109 data_time: 0.046889 memory: 4465 loss_kpt: 86.729096 acc_pose: 0.819163 loss: 86.729096 2022/10/12 19:03:47 - mmengine - INFO - Epoch(train) [140][250/586] lr: 5.000000e-03 eta: 3:39:54 time: 0.338767 data_time: 0.048477 memory: 4465 loss_kpt: 87.241490 acc_pose: 0.810421 loss: 87.241490 2022/10/12 19:04:03 - mmengine - INFO - Epoch(train) [140][300/586] lr: 5.000000e-03 eta: 3:39:39 time: 0.329537 data_time: 0.049957 memory: 4465 loss_kpt: 87.527276 acc_pose: 0.731785 loss: 87.527276 2022/10/12 19:04:20 - mmengine - INFO - Epoch(train) [140][350/586] lr: 5.000000e-03 eta: 3:39:23 time: 0.336542 data_time: 0.052859 memory: 4465 loss_kpt: 87.979728 acc_pose: 0.824067 loss: 87.979728 2022/10/12 19:04:37 - mmengine - INFO - Epoch(train) [140][400/586] lr: 5.000000e-03 eta: 3:39:08 time: 0.341070 data_time: 0.049812 memory: 4465 loss_kpt: 87.883267 acc_pose: 0.820775 loss: 87.883267 2022/10/12 19:04:54 - mmengine - INFO - Epoch(train) [140][450/586] lr: 5.000000e-03 eta: 3:38:52 time: 0.336991 data_time: 0.048547 memory: 4465 loss_kpt: 87.931304 acc_pose: 0.759914 loss: 87.931304 2022/10/12 19:05:11 - mmengine - INFO - Epoch(train) [140][500/586] lr: 5.000000e-03 eta: 3:38:37 time: 0.342171 data_time: 0.049999 memory: 4465 loss_kpt: 87.310016 acc_pose: 0.742530 loss: 87.310016 2022/10/12 19:05:27 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:05:28 - mmengine - INFO - Epoch(train) [140][550/586] lr: 5.000000e-03 eta: 3:38:22 time: 0.342881 data_time: 0.049259 memory: 4465 loss_kpt: 86.836185 acc_pose: 0.809564 loss: 86.836185 2022/10/12 19:05:41 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:05:41 - mmengine - INFO - Saving checkpoint at 140 epochs 2022/10/12 19:05:50 - mmengine - INFO - Epoch(val) [140][50/407] eta: 0:00:48 time: 0.134723 data_time: 0.015386 memory: 4465 2022/10/12 19:05:56 - mmengine - INFO - Epoch(val) [140][100/407] eta: 0:00:38 time: 0.126651 data_time: 0.008280 memory: 1026 2022/10/12 19:06:02 - mmengine - INFO - Epoch(val) [140][150/407] eta: 0:00:32 time: 0.127680 data_time: 0.008389 memory: 1026 2022/10/12 19:06:09 - mmengine - INFO - Epoch(val) [140][200/407] eta: 0:00:26 time: 0.129048 data_time: 0.008164 memory: 1026 2022/10/12 19:06:16 - mmengine - INFO - Epoch(val) [140][250/407] eta: 0:00:20 time: 0.131592 data_time: 0.011977 memory: 1026 2022/10/12 19:06:22 - mmengine - INFO - Epoch(val) [140][300/407] eta: 0:00:13 time: 0.126792 data_time: 0.008270 memory: 1026 2022/10/12 19:06:28 - mmengine - INFO - Epoch(val) [140][350/407] eta: 0:00:07 time: 0.126226 data_time: 0.008328 memory: 1026 2022/10/12 19:06:34 - mmengine - INFO - Epoch(val) [140][400/407] eta: 0:00:00 time: 0.126334 data_time: 0.007741 memory: 1026 2022/10/12 19:06:48 - mmengine - INFO - Evaluating CocoMetric... 2022/10/12 19:07:03 - mmengine - INFO - Epoch(val) [140][407/407] coco/AP: 0.697688 coco/AP .5: 0.887198 coco/AP .75: 0.771833 coco/AP (M): 0.665688 coco/AP (L): 0.759111 coco/AR: 0.766814 coco/AR .5: 0.928999 coco/AR .75: 0.828401 coco/AR (M): 0.720541 coco/AR (L): 0.830732 2022/10/12 19:07:03 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/liqikai/openmmlab/pt112cu113py38/mmpose/work_dirs/20221012/rsn50/best_coco/AP_epoch_120.pth is removed 2022/10/12 19:07:05 - mmengine - INFO - The best checkpoint with 0.6977 coco/AP at 140 epoch is saved to best_coco/AP_epoch_140.pth. 2022/10/12 19:07:23 - mmengine - INFO - Epoch(train) [141][50/586] lr: 5.000000e-03 eta: 3:37:49 time: 0.353939 data_time: 0.066674 memory: 4465 loss_kpt: 87.289795 acc_pose: 0.834790 loss: 87.289795 2022/10/12 19:07:40 - mmengine - INFO - Epoch(train) [141][100/586] lr: 5.000000e-03 eta: 3:37:34 time: 0.351135 data_time: 0.046883 memory: 4465 loss_kpt: 86.792478 acc_pose: 0.838678 loss: 86.792478 2022/10/12 19:07:58 - mmengine - INFO - Epoch(train) [141][150/586] lr: 5.000000e-03 eta: 3:37:19 time: 0.352672 data_time: 0.049504 memory: 4465 loss_kpt: 86.386555 acc_pose: 0.824158 loss: 86.386555 2022/10/12 19:08:16 - mmengine - INFO - Epoch(train) [141][200/586] lr: 5.000000e-03 eta: 3:37:04 time: 0.357488 data_time: 0.049650 memory: 4465 loss_kpt: 87.531662 acc_pose: 0.701419 loss: 87.531662 2022/10/12 19:08:34 - mmengine - INFO - Epoch(train) [141][250/586] lr: 5.000000e-03 eta: 3:36:49 time: 0.350644 data_time: 0.046332 memory: 4465 loss_kpt: 86.888683 acc_pose: 0.771281 loss: 86.888683 2022/10/12 19:08:51 - mmengine - INFO - Epoch(train) [141][300/586] lr: 5.000000e-03 eta: 3:36:34 time: 0.345192 data_time: 0.049671 memory: 4465 loss_kpt: 87.548833 acc_pose: 0.765504 loss: 87.548833 2022/10/12 19:09:08 - mmengine - INFO - Epoch(train) [141][350/586] lr: 5.000000e-03 eta: 3:36:18 time: 0.341503 data_time: 0.049250 memory: 4465 loss_kpt: 87.333638 acc_pose: 0.776409 loss: 87.333638 2022/10/12 19:09:25 - mmengine - INFO - Epoch(train) [141][400/586] lr: 5.000000e-03 eta: 3:36:03 time: 0.336124 data_time: 0.046981 memory: 4465 loss_kpt: 86.809868 acc_pose: 0.745384 loss: 86.809868 2022/10/12 19:09:41 - mmengine - INFO - Epoch(train) [141][450/586] lr: 5.000000e-03 eta: 3:35:47 time: 0.333338 data_time: 0.045367 memory: 4465 loss_kpt: 86.988767 acc_pose: 0.803956 loss: 86.988767 2022/10/12 19:09:58 - mmengine - INFO - Epoch(train) [141][500/586] lr: 5.000000e-03 eta: 3:35:31 time: 0.330128 data_time: 0.050735 memory: 4465 loss_kpt: 87.461959 acc_pose: 0.803054 loss: 87.461959 2022/10/12 19:10:14 - mmengine - INFO - Epoch(train) [141][550/586] lr: 5.000000e-03 eta: 3:35:16 time: 0.330422 data_time: 0.049925 memory: 4465 loss_kpt: 86.820862 acc_pose: 0.715537 loss: 86.820862 2022/10/12 19:10:26 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:10:44 - mmengine - INFO - Epoch(train) [142][50/586] lr: 5.000000e-03 eta: 3:34:43 time: 0.355224 data_time: 0.063343 memory: 4465 loss_kpt: 86.558636 acc_pose: 0.784649 loss: 86.558636 2022/10/12 19:11:01 - mmengine - INFO - Epoch(train) [142][100/586] lr: 5.000000e-03 eta: 3:34:28 time: 0.345407 data_time: 0.053632 memory: 4465 loss_kpt: 87.814052 acc_pose: 0.864284 loss: 87.814052 2022/10/12 19:11:18 - mmengine - INFO - Epoch(train) [142][150/586] lr: 5.000000e-03 eta: 3:34:13 time: 0.342299 data_time: 0.050324 memory: 4465 loss_kpt: 87.719208 acc_pose: 0.815899 loss: 87.719208 2022/10/12 19:11:36 - mmengine - INFO - Epoch(train) [142][200/586] lr: 5.000000e-03 eta: 3:33:57 time: 0.343693 data_time: 0.051352 memory: 4465 loss_kpt: 87.239205 acc_pose: 0.867353 loss: 87.239205 2022/10/12 19:11:53 - mmengine - INFO - Epoch(train) [142][250/586] lr: 5.000000e-03 eta: 3:33:42 time: 0.342774 data_time: 0.051254 memory: 4465 loss_kpt: 86.900125 acc_pose: 0.845553 loss: 86.900125 2022/10/12 19:12:10 - mmengine - INFO - Epoch(train) [142][300/586] lr: 5.000000e-03 eta: 3:33:27 time: 0.340808 data_time: 0.056383 memory: 4465 loss_kpt: 86.861848 acc_pose: 0.796268 loss: 86.861848 2022/10/12 19:12:27 - mmengine - INFO - Epoch(train) [142][350/586] lr: 5.000000e-03 eta: 3:33:11 time: 0.340400 data_time: 0.054058 memory: 4465 loss_kpt: 87.346841 acc_pose: 0.747097 loss: 87.346841 2022/10/12 19:12:35 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:12:44 - mmengine - INFO - Epoch(train) [142][400/586] lr: 5.000000e-03 eta: 3:32:56 time: 0.334669 data_time: 0.053159 memory: 4465 loss_kpt: 86.514389 acc_pose: 0.807783 loss: 86.514389 2022/10/12 19:13:00 - mmengine - INFO - Epoch(train) [142][450/586] lr: 5.000000e-03 eta: 3:32:40 time: 0.323944 data_time: 0.052014 memory: 4465 loss_kpt: 87.835905 acc_pose: 0.860234 loss: 87.835905 2022/10/12 19:13:16 - mmengine - INFO - Epoch(train) [142][500/586] lr: 5.000000e-03 eta: 3:32:24 time: 0.322111 data_time: 0.055023 memory: 4465 loss_kpt: 86.769963 acc_pose: 0.806516 loss: 86.769963 2022/10/12 19:13:33 - mmengine - INFO - Epoch(train) [142][550/586] lr: 5.000000e-03 eta: 3:32:08 time: 0.339161 data_time: 0.051185 memory: 4465 loss_kpt: 85.840898 acc_pose: 0.754245 loss: 85.840898 2022/10/12 19:13:45 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:14:03 - mmengine - INFO - Epoch(train) [143][50/586] lr: 5.000000e-03 eta: 3:31:36 time: 0.353344 data_time: 0.065622 memory: 4465 loss_kpt: 87.866435 acc_pose: 0.805172 loss: 87.866435 2022/10/12 19:14:19 - mmengine - INFO - Epoch(train) [143][100/586] lr: 5.000000e-03 eta: 3:31:21 time: 0.329454 data_time: 0.050849 memory: 4465 loss_kpt: 86.225546 acc_pose: 0.815319 loss: 86.225546 2022/10/12 19:14:36 - mmengine - INFO - Epoch(train) [143][150/586] lr: 5.000000e-03 eta: 3:31:05 time: 0.335228 data_time: 0.053913 memory: 4465 loss_kpt: 89.306502 acc_pose: 0.762464 loss: 89.306502 2022/10/12 19:14:53 - mmengine - INFO - Epoch(train) [143][200/586] lr: 5.000000e-03 eta: 3:30:49 time: 0.337896 data_time: 0.049712 memory: 4465 loss_kpt: 87.385685 acc_pose: 0.824995 loss: 87.385685 2022/10/12 19:15:09 - mmengine - INFO - Epoch(train) [143][250/586] lr: 5.000000e-03 eta: 3:30:34 time: 0.330413 data_time: 0.055081 memory: 4465 loss_kpt: 87.947582 acc_pose: 0.800948 loss: 87.947582 2022/10/12 19:15:26 - mmengine - INFO - Epoch(train) [143][300/586] lr: 5.000000e-03 eta: 3:30:18 time: 0.336571 data_time: 0.052287 memory: 4465 loss_kpt: 86.902211 acc_pose: 0.821675 loss: 86.902211 2022/10/12 19:15:43 - mmengine - INFO - Epoch(train) [143][350/586] lr: 5.000000e-03 eta: 3:30:03 time: 0.334432 data_time: 0.054952 memory: 4465 loss_kpt: 85.569076 acc_pose: 0.747770 loss: 85.569076 2022/10/12 19:16:00 - mmengine - INFO - Epoch(train) [143][400/586] lr: 5.000000e-03 eta: 3:29:47 time: 0.334645 data_time: 0.047628 memory: 4465 loss_kpt: 87.516651 acc_pose: 0.785991 loss: 87.516651 2022/10/12 19:16:16 - mmengine - INFO - Epoch(train) [143][450/586] lr: 5.000000e-03 eta: 3:29:31 time: 0.334111 data_time: 0.052423 memory: 4465 loss_kpt: 87.689550 acc_pose: 0.840974 loss: 87.689550 2022/10/12 19:16:33 - mmengine - INFO - Epoch(train) [143][500/586] lr: 5.000000e-03 eta: 3:29:16 time: 0.328265 data_time: 0.046839 memory: 4465 loss_kpt: 86.764541 acc_pose: 0.807585 loss: 86.764541 2022/10/12 19:16:50 - mmengine - INFO - Epoch(train) [143][550/586] lr: 5.000000e-03 eta: 3:29:00 time: 0.335022 data_time: 0.050431 memory: 4465 loss_kpt: 88.153385 acc_pose: 0.766347 loss: 88.153385 2022/10/12 19:17:01 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:17:19 - mmengine - INFO - Epoch(train) [144][50/586] lr: 5.000000e-03 eta: 3:28:28 time: 0.362867 data_time: 0.062213 memory: 4465 loss_kpt: 86.822832 acc_pose: 0.727814 loss: 86.822832 2022/10/12 19:17:37 - mmengine - INFO - Epoch(train) [144][100/586] lr: 5.000000e-03 eta: 3:28:13 time: 0.348799 data_time: 0.051004 memory: 4465 loss_kpt: 88.174458 acc_pose: 0.788784 loss: 88.174458 2022/10/12 19:17:53 - mmengine - INFO - Epoch(train) [144][150/586] lr: 5.000000e-03 eta: 3:27:58 time: 0.336250 data_time: 0.049392 memory: 4465 loss_kpt: 85.035515 acc_pose: 0.769287 loss: 85.035515 2022/10/12 19:18:11 - mmengine - INFO - Epoch(train) [144][200/586] lr: 5.000000e-03 eta: 3:27:42 time: 0.350361 data_time: 0.047561 memory: 4465 loss_kpt: 84.842614 acc_pose: 0.777059 loss: 84.842614 2022/10/12 19:18:12 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:18:29 - mmengine - INFO - Epoch(train) [144][250/586] lr: 5.000000e-03 eta: 3:27:27 time: 0.352926 data_time: 0.049407 memory: 4465 loss_kpt: 88.005768 acc_pose: 0.816016 loss: 88.005768 2022/10/12 19:18:46 - mmengine - INFO - Epoch(train) [144][300/586] lr: 5.000000e-03 eta: 3:27:12 time: 0.350016 data_time: 0.049895 memory: 4465 loss_kpt: 86.924200 acc_pose: 0.787702 loss: 86.924200 2022/10/12 19:19:04 - mmengine - INFO - Epoch(train) [144][350/586] lr: 5.000000e-03 eta: 3:26:57 time: 0.349921 data_time: 0.048130 memory: 4465 loss_kpt: 87.696048 acc_pose: 0.805727 loss: 87.696048 2022/10/12 19:19:21 - mmengine - INFO - Epoch(train) [144][400/586] lr: 5.000000e-03 eta: 3:26:42 time: 0.354510 data_time: 0.045495 memory: 4465 loss_kpt: 88.460848 acc_pose: 0.861693 loss: 88.460848 2022/10/12 19:19:38 - mmengine - INFO - Epoch(train) [144][450/586] lr: 5.000000e-03 eta: 3:26:26 time: 0.332395 data_time: 0.048664 memory: 4465 loss_kpt: 86.792396 acc_pose: 0.802127 loss: 86.792396 2022/10/12 19:19:54 - mmengine - INFO - Epoch(train) [144][500/586] lr: 5.000000e-03 eta: 3:26:10 time: 0.330636 data_time: 0.047299 memory: 4465 loss_kpt: 86.521602 acc_pose: 0.868347 loss: 86.521602 2022/10/12 19:20:11 - mmengine - INFO - Epoch(train) [144][550/586] lr: 5.000000e-03 eta: 3:25:55 time: 0.336503 data_time: 0.054100 memory: 4465 loss_kpt: 85.982912 acc_pose: 0.832109 loss: 85.982912 2022/10/12 19:20:23 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:20:41 - mmengine - INFO - Epoch(train) [145][50/586] lr: 5.000000e-03 eta: 3:25:23 time: 0.352492 data_time: 0.061195 memory: 4465 loss_kpt: 89.007867 acc_pose: 0.775994 loss: 89.007867 2022/10/12 19:20:58 - mmengine - INFO - Epoch(train) [145][100/586] lr: 5.000000e-03 eta: 3:25:07 time: 0.350852 data_time: 0.050779 memory: 4465 loss_kpt: 85.579601 acc_pose: 0.791308 loss: 85.579601 2022/10/12 19:21:16 - mmengine - INFO - Epoch(train) [145][150/586] lr: 5.000000e-03 eta: 3:24:52 time: 0.344459 data_time: 0.056094 memory: 4465 loss_kpt: 87.507502 acc_pose: 0.803599 loss: 87.507502 2022/10/12 19:21:33 - mmengine - INFO - Epoch(train) [145][200/586] lr: 5.000000e-03 eta: 3:24:37 time: 0.338796 data_time: 0.049829 memory: 4465 loss_kpt: 86.901846 acc_pose: 0.859943 loss: 86.901846 2022/10/12 19:21:51 - mmengine - INFO - Epoch(train) [145][250/586] lr: 5.000000e-03 eta: 3:24:22 time: 0.360137 data_time: 0.055069 memory: 4465 loss_kpt: 86.235475 acc_pose: 0.836551 loss: 86.235475 2022/10/12 19:22:08 - mmengine - INFO - Epoch(train) [145][300/586] lr: 5.000000e-03 eta: 3:24:06 time: 0.346152 data_time: 0.052021 memory: 4465 loss_kpt: 86.260064 acc_pose: 0.844860 loss: 86.260064 2022/10/12 19:22:25 - mmengine - INFO - Epoch(train) [145][350/586] lr: 5.000000e-03 eta: 3:23:51 time: 0.333425 data_time: 0.049942 memory: 4465 loss_kpt: 86.039981 acc_pose: 0.838003 loss: 86.039981 2022/10/12 19:22:42 - mmengine - INFO - Epoch(train) [145][400/586] lr: 5.000000e-03 eta: 3:23:35 time: 0.343557 data_time: 0.051623 memory: 4465 loss_kpt: 86.661099 acc_pose: 0.828410 loss: 86.661099 2022/10/12 19:22:59 - mmengine - INFO - Epoch(train) [145][450/586] lr: 5.000000e-03 eta: 3:23:20 time: 0.338824 data_time: 0.054404 memory: 4465 loss_kpt: 86.805836 acc_pose: 0.843892 loss: 86.805836 2022/10/12 19:23:15 - mmengine - INFO - Epoch(train) [145][500/586] lr: 5.000000e-03 eta: 3:23:04 time: 0.333133 data_time: 0.053721 memory: 4465 loss_kpt: 86.869546 acc_pose: 0.835266 loss: 86.869546 2022/10/12 19:23:32 - mmengine - INFO - Epoch(train) [145][550/586] lr: 5.000000e-03 eta: 3:22:48 time: 0.329272 data_time: 0.050309 memory: 4465 loss_kpt: 87.923291 acc_pose: 0.838432 loss: 87.923291 2022/10/12 19:23:44 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:23:54 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:24:01 - mmengine - INFO - Epoch(train) [146][50/586] lr: 5.000000e-03 eta: 3:22:16 time: 0.350278 data_time: 0.066134 memory: 4465 loss_kpt: 88.391234 acc_pose: 0.814024 loss: 88.391234 2022/10/12 19:24:18 - mmengine - INFO - Epoch(train) [146][100/586] lr: 5.000000e-03 eta: 3:22:01 time: 0.340883 data_time: 0.055693 memory: 4465 loss_kpt: 86.246342 acc_pose: 0.824677 loss: 86.246342 2022/10/12 19:24:36 - mmengine - INFO - Epoch(train) [146][150/586] lr: 5.000000e-03 eta: 3:21:46 time: 0.349145 data_time: 0.054544 memory: 4465 loss_kpt: 87.152409 acc_pose: 0.807881 loss: 87.152409 2022/10/12 19:24:53 - mmengine - INFO - Epoch(train) [146][200/586] lr: 5.000000e-03 eta: 3:21:30 time: 0.352796 data_time: 0.060412 memory: 4465 loss_kpt: 87.134488 acc_pose: 0.866993 loss: 87.134488 2022/10/12 19:25:10 - mmengine - INFO - Epoch(train) [146][250/586] lr: 5.000000e-03 eta: 3:21:15 time: 0.339818 data_time: 0.051839 memory: 4465 loss_kpt: 86.011756 acc_pose: 0.830509 loss: 86.011756 2022/10/12 19:25:28 - mmengine - INFO - Epoch(train) [146][300/586] lr: 5.000000e-03 eta: 3:21:00 time: 0.344727 data_time: 0.054323 memory: 4465 loss_kpt: 86.521019 acc_pose: 0.860981 loss: 86.521019 2022/10/12 19:25:46 - mmengine - INFO - Epoch(train) [146][350/586] lr: 5.000000e-03 eta: 3:20:45 time: 0.361492 data_time: 0.052242 memory: 4465 loss_kpt: 85.996488 acc_pose: 0.795369 loss: 85.996488 2022/10/12 19:26:03 - mmengine - INFO - Epoch(train) [146][400/586] lr: 5.000000e-03 eta: 3:20:29 time: 0.353017 data_time: 0.053998 memory: 4465 loss_kpt: 86.584277 acc_pose: 0.789387 loss: 86.584277 2022/10/12 19:26:21 - mmengine - INFO - Epoch(train) [146][450/586] lr: 5.000000e-03 eta: 3:20:14 time: 0.347891 data_time: 0.049624 memory: 4465 loss_kpt: 85.160654 acc_pose: 0.839441 loss: 85.160654 2022/10/12 19:26:38 - mmengine - INFO - Epoch(train) [146][500/586] lr: 5.000000e-03 eta: 3:19:59 time: 0.344752 data_time: 0.053842 memory: 4465 loss_kpt: 88.763993 acc_pose: 0.793625 loss: 88.763993 2022/10/12 19:26:55 - mmengine - INFO - Epoch(train) [146][550/586] lr: 5.000000e-03 eta: 3:19:43 time: 0.343676 data_time: 0.052820 memory: 4465 loss_kpt: 86.653484 acc_pose: 0.795914 loss: 86.653484 2022/10/12 19:27:07 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:27:25 - mmengine - INFO - Epoch(train) [147][50/586] lr: 5.000000e-03 eta: 3:19:12 time: 0.361027 data_time: 0.061871 memory: 4465 loss_kpt: 87.928192 acc_pose: 0.854910 loss: 87.928192 2022/10/12 19:27:42 - mmengine - INFO - Epoch(train) [147][100/586] lr: 5.000000e-03 eta: 3:18:56 time: 0.343984 data_time: 0.054364 memory: 4465 loss_kpt: 86.819396 acc_pose: 0.814470 loss: 86.819396 2022/10/12 19:28:00 - mmengine - INFO - Epoch(train) [147][150/586] lr: 5.000000e-03 eta: 3:18:41 time: 0.346873 data_time: 0.054950 memory: 4465 loss_kpt: 87.679229 acc_pose: 0.737102 loss: 87.679229 2022/10/12 19:28:17 - mmengine - INFO - Epoch(train) [147][200/586] lr: 5.000000e-03 eta: 3:18:25 time: 0.337824 data_time: 0.051614 memory: 4465 loss_kpt: 86.700394 acc_pose: 0.801877 loss: 86.700394 2022/10/12 19:28:34 - mmengine - INFO - Epoch(train) [147][250/586] lr: 5.000000e-03 eta: 3:18:10 time: 0.343188 data_time: 0.054014 memory: 4465 loss_kpt: 87.010387 acc_pose: 0.832071 loss: 87.010387 2022/10/12 19:28:51 - mmengine - INFO - Epoch(train) [147][300/586] lr: 5.000000e-03 eta: 3:17:54 time: 0.340327 data_time: 0.055162 memory: 4465 loss_kpt: 85.443889 acc_pose: 0.776218 loss: 85.443889 2022/10/12 19:29:08 - mmengine - INFO - Epoch(train) [147][350/586] lr: 5.000000e-03 eta: 3:17:39 time: 0.334032 data_time: 0.050106 memory: 4465 loss_kpt: 86.866044 acc_pose: 0.785197 loss: 86.866044 2022/10/12 19:29:25 - mmengine - INFO - Epoch(train) [147][400/586] lr: 5.000000e-03 eta: 3:17:23 time: 0.349789 data_time: 0.047598 memory: 4465 loss_kpt: 85.230556 acc_pose: 0.755963 loss: 85.230556 2022/10/12 19:29:41 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:29:43 - mmengine - INFO - Epoch(train) [147][450/586] lr: 5.000000e-03 eta: 3:17:08 time: 0.347886 data_time: 0.052865 memory: 4465 loss_kpt: 86.764421 acc_pose: 0.694725 loss: 86.764421 2022/10/12 19:30:01 - mmengine - INFO - Epoch(train) [147][500/586] lr: 5.000000e-03 eta: 3:16:53 time: 0.359552 data_time: 0.051369 memory: 4465 loss_kpt: 86.170029 acc_pose: 0.788771 loss: 86.170029 2022/10/12 19:30:18 - mmengine - INFO - Epoch(train) [147][550/586] lr: 5.000000e-03 eta: 3:16:38 time: 0.349720 data_time: 0.054148 memory: 4465 loss_kpt: 86.061715 acc_pose: 0.824397 loss: 86.061715 2022/10/12 19:30:31 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:30:48 - mmengine - INFO - Epoch(train) [148][50/586] lr: 5.000000e-03 eta: 3:16:06 time: 0.348263 data_time: 0.066784 memory: 4465 loss_kpt: 87.055952 acc_pose: 0.718232 loss: 87.055952 2022/10/12 19:31:05 - mmengine - INFO - Epoch(train) [148][100/586] lr: 5.000000e-03 eta: 3:15:50 time: 0.329520 data_time: 0.046105 memory: 4465 loss_kpt: 86.840571 acc_pose: 0.802278 loss: 86.840571 2022/10/12 19:31:21 - mmengine - INFO - Epoch(train) [148][150/586] lr: 5.000000e-03 eta: 3:15:34 time: 0.330280 data_time: 0.052005 memory: 4465 loss_kpt: 87.333367 acc_pose: 0.862273 loss: 87.333367 2022/10/12 19:31:38 - mmengine - INFO - Epoch(train) [148][200/586] lr: 5.000000e-03 eta: 3:15:19 time: 0.335090 data_time: 0.045764 memory: 4465 loss_kpt: 87.437939 acc_pose: 0.833692 loss: 87.437939 2022/10/12 19:31:54 - mmengine - INFO - Epoch(train) [148][250/586] lr: 5.000000e-03 eta: 3:15:03 time: 0.332118 data_time: 0.047956 memory: 4465 loss_kpt: 86.625219 acc_pose: 0.807840 loss: 86.625219 2022/10/12 19:32:12 - mmengine - INFO - Epoch(train) [148][300/586] lr: 5.000000e-03 eta: 3:14:48 time: 0.342121 data_time: 0.056224 memory: 4465 loss_kpt: 86.540873 acc_pose: 0.783783 loss: 86.540873 2022/10/12 19:32:29 - mmengine - INFO - Epoch(train) [148][350/586] lr: 5.000000e-03 eta: 3:14:32 time: 0.339437 data_time: 0.049390 memory: 4465 loss_kpt: 88.737178 acc_pose: 0.814920 loss: 88.737178 2022/10/12 19:32:46 - mmengine - INFO - Epoch(train) [148][400/586] lr: 5.000000e-03 eta: 3:14:17 time: 0.347777 data_time: 0.054245 memory: 4465 loss_kpt: 85.441823 acc_pose: 0.868352 loss: 85.441823 2022/10/12 19:33:03 - mmengine - INFO - Epoch(train) [148][450/586] lr: 5.000000e-03 eta: 3:14:01 time: 0.343096 data_time: 0.052397 memory: 4465 loss_kpt: 87.291935 acc_pose: 0.784585 loss: 87.291935 2022/10/12 19:33:20 - mmengine - INFO - Epoch(train) [148][500/586] lr: 5.000000e-03 eta: 3:13:46 time: 0.336658 data_time: 0.055333 memory: 4465 loss_kpt: 87.013478 acc_pose: 0.786123 loss: 87.013478 2022/10/12 19:33:37 - mmengine - INFO - Epoch(train) [148][550/586] lr: 5.000000e-03 eta: 3:13:30 time: 0.340740 data_time: 0.051801 memory: 4465 loss_kpt: 87.935257 acc_pose: 0.778880 loss: 87.935257 2022/10/12 19:33:49 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:34:06 - mmengine - INFO - Epoch(train) [149][50/586] lr: 5.000000e-03 eta: 3:12:58 time: 0.342194 data_time: 0.061542 memory: 4465 loss_kpt: 86.122805 acc_pose: 0.786074 loss: 86.122805 2022/10/12 19:34:23 - mmengine - INFO - Epoch(train) [149][100/586] lr: 5.000000e-03 eta: 3:12:43 time: 0.333598 data_time: 0.045923 memory: 4465 loss_kpt: 89.369861 acc_pose: 0.784968 loss: 89.369861 2022/10/12 19:34:40 - mmengine - INFO - Epoch(train) [149][150/586] lr: 5.000000e-03 eta: 3:12:27 time: 0.339651 data_time: 0.047572 memory: 4465 loss_kpt: 87.695796 acc_pose: 0.800813 loss: 87.695796 2022/10/12 19:34:57 - mmengine - INFO - Epoch(train) [149][200/586] lr: 5.000000e-03 eta: 3:12:12 time: 0.336215 data_time: 0.046967 memory: 4465 loss_kpt: 86.828948 acc_pose: 0.854065 loss: 86.828948 2022/10/12 19:35:14 - mmengine - INFO - Epoch(train) [149][250/586] lr: 5.000000e-03 eta: 3:11:56 time: 0.341716 data_time: 0.049144 memory: 4465 loss_kpt: 88.204493 acc_pose: 0.772620 loss: 88.204493 2022/10/12 19:35:22 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:35:31 - mmengine - INFO - Epoch(train) [149][300/586] lr: 5.000000e-03 eta: 3:11:41 time: 0.350276 data_time: 0.052906 memory: 4465 loss_kpt: 86.830057 acc_pose: 0.836721 loss: 86.830057 2022/10/12 19:35:49 - mmengine - INFO - Epoch(train) [149][350/586] lr: 5.000000e-03 eta: 3:11:25 time: 0.341648 data_time: 0.049159 memory: 4465 loss_kpt: 86.257127 acc_pose: 0.826513 loss: 86.257127 2022/10/12 19:36:06 - mmengine - INFO - Epoch(train) [149][400/586] lr: 5.000000e-03 eta: 3:11:10 time: 0.341882 data_time: 0.053939 memory: 4465 loss_kpt: 87.552957 acc_pose: 0.785385 loss: 87.552957 2022/10/12 19:36:22 - mmengine - INFO - Epoch(train) [149][450/586] lr: 5.000000e-03 eta: 3:10:54 time: 0.332128 data_time: 0.050432 memory: 4465 loss_kpt: 87.291436 acc_pose: 0.839417 loss: 87.291436 2022/10/12 19:36:39 - mmengine - INFO - Epoch(train) [149][500/586] lr: 5.000000e-03 eta: 3:10:38 time: 0.332591 data_time: 0.051433 memory: 4465 loss_kpt: 86.900825 acc_pose: 0.846031 loss: 86.900825 2022/10/12 19:36:56 - mmengine - INFO - Epoch(train) [149][550/586] lr: 5.000000e-03 eta: 3:10:23 time: 0.335844 data_time: 0.051082 memory: 4465 loss_kpt: 87.061198 acc_pose: 0.795593 loss: 87.061198 2022/10/12 19:37:08 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:37:26 - mmengine - INFO - Epoch(train) [150][50/586] lr: 5.000000e-03 eta: 3:09:52 time: 0.358718 data_time: 0.061018 memory: 4465 loss_kpt: 86.692025 acc_pose: 0.741291 loss: 86.692025 2022/10/12 19:37:42 - mmengine - INFO - Epoch(train) [150][100/586] lr: 5.000000e-03 eta: 3:09:36 time: 0.324083 data_time: 0.049271 memory: 4465 loss_kpt: 87.566124 acc_pose: 0.713854 loss: 87.566124 2022/10/12 19:37:59 - mmengine - INFO - Epoch(train) [150][150/586] lr: 5.000000e-03 eta: 3:09:20 time: 0.342203 data_time: 0.050566 memory: 4465 loss_kpt: 87.781569 acc_pose: 0.818510 loss: 87.781569 2022/10/12 19:38:16 - mmengine - INFO - Epoch(train) [150][200/586] lr: 5.000000e-03 eta: 3:09:05 time: 0.341951 data_time: 0.047954 memory: 4465 loss_kpt: 86.956587 acc_pose: 0.839523 loss: 86.956587 2022/10/12 19:38:33 - mmengine - INFO - Epoch(train) [150][250/586] lr: 5.000000e-03 eta: 3:08:49 time: 0.335937 data_time: 0.050845 memory: 4465 loss_kpt: 85.564826 acc_pose: 0.869699 loss: 85.564826 2022/10/12 19:38:50 - mmengine - INFO - Epoch(train) [150][300/586] lr: 5.000000e-03 eta: 3:08:33 time: 0.332751 data_time: 0.047351 memory: 4465 loss_kpt: 86.311952 acc_pose: 0.786203 loss: 86.311952 2022/10/12 19:39:06 - mmengine - INFO - Epoch(train) [150][350/586] lr: 5.000000e-03 eta: 3:08:18 time: 0.325913 data_time: 0.048337 memory: 4465 loss_kpt: 87.268700 acc_pose: 0.751852 loss: 87.268700 2022/10/12 19:39:23 - mmengine - INFO - Epoch(train) [150][400/586] lr: 5.000000e-03 eta: 3:08:02 time: 0.330588 data_time: 0.044673 memory: 4465 loss_kpt: 87.484476 acc_pose: 0.845755 loss: 87.484476 2022/10/12 19:39:40 - mmengine - INFO - Epoch(train) [150][450/586] lr: 5.000000e-03 eta: 3:07:46 time: 0.338940 data_time: 0.049185 memory: 4465 loss_kpt: 88.727185 acc_pose: 0.793131 loss: 88.727185 2022/10/12 19:39:56 - mmengine - INFO - Epoch(train) [150][500/586] lr: 5.000000e-03 eta: 3:07:31 time: 0.332998 data_time: 0.048203 memory: 4465 loss_kpt: 87.092206 acc_pose: 0.864673 loss: 87.092206 2022/10/12 19:40:13 - mmengine - INFO - Epoch(train) [150][550/586] lr: 5.000000e-03 eta: 3:07:15 time: 0.339606 data_time: 0.045370 memory: 4465 loss_kpt: 87.101419 acc_pose: 0.786184 loss: 87.101419 2022/10/12 19:40:26 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:40:26 - mmengine - INFO - Saving checkpoint at 150 epochs 2022/10/12 19:40:35 - mmengine - INFO - Epoch(val) [150][50/407] eta: 0:00:48 time: 0.136514 data_time: 0.012759 memory: 4465 2022/10/12 19:40:41 - mmengine - INFO - Epoch(val) [150][100/407] eta: 0:00:39 time: 0.127665 data_time: 0.008037 memory: 1026 2022/10/12 19:40:48 - mmengine - INFO - Epoch(val) [150][150/407] eta: 0:00:33 time: 0.129235 data_time: 0.008342 memory: 1026 2022/10/12 19:40:54 - mmengine - INFO - Epoch(val) [150][200/407] eta: 0:00:26 time: 0.127643 data_time: 0.008693 memory: 1026 2022/10/12 19:41:00 - mmengine - INFO - Epoch(val) [150][250/407] eta: 0:00:20 time: 0.127526 data_time: 0.008285 memory: 1026 2022/10/12 19:41:07 - mmengine - INFO - Epoch(val) [150][300/407] eta: 0:00:13 time: 0.127315 data_time: 0.008591 memory: 1026 2022/10/12 19:41:13 - mmengine - INFO - Epoch(val) [150][350/407] eta: 0:00:07 time: 0.126395 data_time: 0.007881 memory: 1026 2022/10/12 19:41:19 - mmengine - INFO - Epoch(val) [150][400/407] eta: 0:00:00 time: 0.123973 data_time: 0.008201 memory: 1026 2022/10/12 19:41:33 - mmengine - INFO - Evaluating CocoMetric... 2022/10/12 19:41:49 - mmengine - INFO - Epoch(val) [150][407/407] coco/AP: 0.702411 coco/AP .5: 0.885591 coco/AP .75: 0.780265 coco/AP (M): 0.669703 coco/AP (L): 0.763377 coco/AR: 0.771080 coco/AR .5: 0.926322 coco/AR .75: 0.833753 coco/AR (M): 0.725266 coco/AR (L): 0.834262 2022/10/12 19:41:49 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/liqikai/openmmlab/pt112cu113py38/mmpose/work_dirs/20221012/rsn50/best_coco/AP_epoch_140.pth is removed 2022/10/12 19:41:50 - mmengine - INFO - The best checkpoint with 0.7024 coco/AP at 150 epoch is saved to best_coco/AP_epoch_150.pth. 2022/10/12 19:42:07 - mmengine - INFO - Epoch(train) [151][50/586] lr: 5.000000e-03 eta: 3:06:43 time: 0.327147 data_time: 0.055676 memory: 4465 loss_kpt: 86.908661 acc_pose: 0.763231 loss: 86.908661 2022/10/12 19:42:23 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:42:23 - mmengine - INFO - Epoch(train) [151][100/586] lr: 5.000000e-03 eta: 3:06:27 time: 0.327059 data_time: 0.050318 memory: 4465 loss_kpt: 87.431233 acc_pose: 0.806620 loss: 87.431233 2022/10/12 19:42:41 - mmengine - INFO - Epoch(train) [151][150/586] lr: 5.000000e-03 eta: 3:06:12 time: 0.348833 data_time: 0.052205 memory: 4465 loss_kpt: 87.203503 acc_pose: 0.833875 loss: 87.203503 2022/10/12 19:42:58 - mmengine - INFO - Epoch(train) [151][200/586] lr: 5.000000e-03 eta: 3:05:57 time: 0.343519 data_time: 0.049228 memory: 4465 loss_kpt: 87.886506 acc_pose: 0.797349 loss: 87.886506 2022/10/12 19:43:15 - mmengine - INFO - Epoch(train) [151][250/586] lr: 5.000000e-03 eta: 3:05:41 time: 0.340309 data_time: 0.055610 memory: 4465 loss_kpt: 85.397800 acc_pose: 0.770985 loss: 85.397800 2022/10/12 19:43:32 - mmengine - INFO - Epoch(train) [151][300/586] lr: 5.000000e-03 eta: 3:05:25 time: 0.342147 data_time: 0.050558 memory: 4465 loss_kpt: 86.143138 acc_pose: 0.804082 loss: 86.143138 2022/10/12 19:43:49 - mmengine - INFO - Epoch(train) [151][350/586] lr: 5.000000e-03 eta: 3:05:10 time: 0.334707 data_time: 0.048981 memory: 4465 loss_kpt: 86.629202 acc_pose: 0.798811 loss: 86.629202 2022/10/12 19:44:06 - mmengine - INFO - Epoch(train) [151][400/586] lr: 5.000000e-03 eta: 3:04:54 time: 0.344528 data_time: 0.052151 memory: 4465 loss_kpt: 85.726403 acc_pose: 0.786256 loss: 85.726403 2022/10/12 19:44:23 - mmengine - INFO - Epoch(train) [151][450/586] lr: 5.000000e-03 eta: 3:04:39 time: 0.348636 data_time: 0.047146 memory: 4465 loss_kpt: 86.136483 acc_pose: 0.790881 loss: 86.136483 2022/10/12 19:44:41 - mmengine - INFO - Epoch(train) [151][500/586] lr: 5.000000e-03 eta: 3:04:24 time: 0.346076 data_time: 0.050211 memory: 4465 loss_kpt: 87.919487 acc_pose: 0.795857 loss: 87.919487 2022/10/12 19:44:58 - mmengine - INFO - Epoch(train) [151][550/586] lr: 5.000000e-03 eta: 3:04:08 time: 0.340713 data_time: 0.052491 memory: 4465 loss_kpt: 86.332750 acc_pose: 0.730983 loss: 86.332750 2022/10/12 19:45:10 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:45:27 - mmengine - INFO - Epoch(train) [152][50/586] lr: 5.000000e-03 eta: 3:03:36 time: 0.340509 data_time: 0.056766 memory: 4465 loss_kpt: 87.097502 acc_pose: 0.839458 loss: 87.097502 2022/10/12 19:45:44 - mmengine - INFO - Epoch(train) [152][100/586] lr: 5.000000e-03 eta: 3:03:21 time: 0.343055 data_time: 0.053290 memory: 4465 loss_kpt: 87.255400 acc_pose: 0.813913 loss: 87.255400 2022/10/12 19:46:00 - mmengine - INFO - Epoch(train) [152][150/586] lr: 5.000000e-03 eta: 3:03:05 time: 0.327067 data_time: 0.048764 memory: 4465 loss_kpt: 86.690582 acc_pose: 0.769872 loss: 86.690582 2022/10/12 19:46:17 - mmengine - INFO - Epoch(train) [152][200/586] lr: 5.000000e-03 eta: 3:02:50 time: 0.333525 data_time: 0.049431 memory: 4465 loss_kpt: 88.152476 acc_pose: 0.821751 loss: 88.152476 2022/10/12 19:46:33 - mmengine - INFO - Epoch(train) [152][250/586] lr: 5.000000e-03 eta: 3:02:34 time: 0.327812 data_time: 0.051353 memory: 4465 loss_kpt: 86.967015 acc_pose: 0.752065 loss: 86.967015 2022/10/12 19:46:50 - mmengine - INFO - Epoch(train) [152][300/586] lr: 5.000000e-03 eta: 3:02:18 time: 0.328440 data_time: 0.047580 memory: 4465 loss_kpt: 86.511014 acc_pose: 0.835011 loss: 86.511014 2022/10/12 19:47:07 - mmengine - INFO - Epoch(train) [152][350/586] lr: 5.000000e-03 eta: 3:02:02 time: 0.345933 data_time: 0.055808 memory: 4465 loss_kpt: 86.376040 acc_pose: 0.805119 loss: 86.376040 2022/10/12 19:47:24 - mmengine - INFO - Epoch(train) [152][400/586] lr: 5.000000e-03 eta: 3:01:47 time: 0.345337 data_time: 0.050025 memory: 4465 loss_kpt: 88.290886 acc_pose: 0.789319 loss: 88.290886 2022/10/12 19:47:41 - mmengine - INFO - Epoch(train) [152][450/586] lr: 5.000000e-03 eta: 3:01:31 time: 0.330745 data_time: 0.050180 memory: 4465 loss_kpt: 88.400358 acc_pose: 0.856269 loss: 88.400358 2022/10/12 19:47:58 - mmengine - INFO - Epoch(train) [152][500/586] lr: 5.000000e-03 eta: 3:01:16 time: 0.338270 data_time: 0.049801 memory: 4465 loss_kpt: 87.807318 acc_pose: 0.835730 loss: 87.807318 2022/10/12 19:48:03 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:48:15 - mmengine - INFO - Epoch(train) [152][550/586] lr: 5.000000e-03 eta: 3:01:00 time: 0.339737 data_time: 0.049238 memory: 4465 loss_kpt: 86.830867 acc_pose: 0.703249 loss: 86.830867 2022/10/12 19:48:27 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:48:44 - mmengine - INFO - Epoch(train) [153][50/586] lr: 5.000000e-03 eta: 3:00:29 time: 0.356331 data_time: 0.065638 memory: 4465 loss_kpt: 87.987529 acc_pose: 0.833016 loss: 87.987529 2022/10/12 19:49:02 - mmengine - INFO - Epoch(train) [153][100/586] lr: 5.000000e-03 eta: 3:00:14 time: 0.344508 data_time: 0.052085 memory: 4465 loss_kpt: 86.257469 acc_pose: 0.833343 loss: 86.257469 2022/10/12 19:49:19 - mmengine - INFO - Epoch(train) [153][150/586] lr: 5.000000e-03 eta: 2:59:58 time: 0.346432 data_time: 0.051818 memory: 4465 loss_kpt: 86.354373 acc_pose: 0.830379 loss: 86.354373 2022/10/12 19:49:36 - mmengine - INFO - Epoch(train) [153][200/586] lr: 5.000000e-03 eta: 2:59:42 time: 0.333398 data_time: 0.048116 memory: 4465 loss_kpt: 85.495964 acc_pose: 0.790548 loss: 85.495964 2022/10/12 19:49:52 - mmengine - INFO - Epoch(train) [153][250/586] lr: 5.000000e-03 eta: 2:59:27 time: 0.330577 data_time: 0.050185 memory: 4465 loss_kpt: 86.084985 acc_pose: 0.816318 loss: 86.084985 2022/10/12 19:50:09 - mmengine - INFO - Epoch(train) [153][300/586] lr: 5.000000e-03 eta: 2:59:11 time: 0.326920 data_time: 0.046450 memory: 4465 loss_kpt: 85.363313 acc_pose: 0.694662 loss: 85.363313 2022/10/12 19:50:25 - mmengine - INFO - Epoch(train) [153][350/586] lr: 5.000000e-03 eta: 2:58:55 time: 0.325743 data_time: 0.048652 memory: 4465 loss_kpt: 87.128915 acc_pose: 0.814884 loss: 87.128915 2022/10/12 19:50:41 - mmengine - INFO - Epoch(train) [153][400/586] lr: 5.000000e-03 eta: 2:58:39 time: 0.328575 data_time: 0.047964 memory: 4465 loss_kpt: 86.943066 acc_pose: 0.809682 loss: 86.943066 2022/10/12 19:50:58 - mmengine - INFO - Epoch(train) [153][450/586] lr: 5.000000e-03 eta: 2:58:24 time: 0.329454 data_time: 0.049013 memory: 4465 loss_kpt: 86.606317 acc_pose: 0.791812 loss: 86.606317 2022/10/12 19:51:14 - mmengine - INFO - Epoch(train) [153][500/586] lr: 5.000000e-03 eta: 2:58:08 time: 0.329855 data_time: 0.050228 memory: 4465 loss_kpt: 85.882447 acc_pose: 0.765270 loss: 85.882447 2022/10/12 19:51:31 - mmengine - INFO - Epoch(train) [153][550/586] lr: 5.000000e-03 eta: 2:57:52 time: 0.324274 data_time: 0.050326 memory: 4465 loss_kpt: 87.125278 acc_pose: 0.841732 loss: 87.125278 2022/10/12 19:51:43 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:52:00 - mmengine - INFO - Epoch(train) [154][50/586] lr: 5.000000e-03 eta: 2:57:21 time: 0.351714 data_time: 0.066060 memory: 4465 loss_kpt: 87.551382 acc_pose: 0.751849 loss: 87.551382 2022/10/12 19:52:17 - mmengine - INFO - Epoch(train) [154][100/586] lr: 5.000000e-03 eta: 2:57:05 time: 0.328162 data_time: 0.053029 memory: 4465 loss_kpt: 86.754215 acc_pose: 0.724295 loss: 86.754215 2022/10/12 19:52:33 - mmengine - INFO - Epoch(train) [154][150/586] lr: 5.000000e-03 eta: 2:56:49 time: 0.332758 data_time: 0.052929 memory: 4465 loss_kpt: 87.088897 acc_pose: 0.775822 loss: 87.088897 2022/10/12 19:52:49 - mmengine - INFO - Epoch(train) [154][200/586] lr: 5.000000e-03 eta: 2:56:33 time: 0.319519 data_time: 0.050994 memory: 4465 loss_kpt: 85.713177 acc_pose: 0.850783 loss: 85.713177 2022/10/12 19:53:05 - mmengine - INFO - Epoch(train) [154][250/586] lr: 5.000000e-03 eta: 2:56:17 time: 0.320242 data_time: 0.052421 memory: 4465 loss_kpt: 87.310196 acc_pose: 0.826928 loss: 87.310196 2022/10/12 19:53:22 - mmengine - INFO - Epoch(train) [154][300/586] lr: 5.000000e-03 eta: 2:56:02 time: 0.327433 data_time: 0.056118 memory: 4465 loss_kpt: 86.148569 acc_pose: 0.846726 loss: 86.148569 2022/10/12 19:53:35 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:53:38 - mmengine - INFO - Epoch(train) [154][350/586] lr: 5.000000e-03 eta: 2:55:46 time: 0.316227 data_time: 0.054717 memory: 4465 loss_kpt: 87.372001 acc_pose: 0.876510 loss: 87.372001 2022/10/12 19:53:54 - mmengine - INFO - Epoch(train) [154][400/586] lr: 5.000000e-03 eta: 2:55:30 time: 0.331367 data_time: 0.054897 memory: 4465 loss_kpt: 86.057048 acc_pose: 0.757121 loss: 86.057048 2022/10/12 19:54:11 - mmengine - INFO - Epoch(train) [154][450/586] lr: 5.000000e-03 eta: 2:55:14 time: 0.336202 data_time: 0.054179 memory: 4465 loss_kpt: 86.633465 acc_pose: 0.840540 loss: 86.633465 2022/10/12 19:54:28 - mmengine - INFO - Epoch(train) [154][500/586] lr: 5.000000e-03 eta: 2:54:59 time: 0.338039 data_time: 0.050180 memory: 4465 loss_kpt: 87.569248 acc_pose: 0.809747 loss: 87.569248 2022/10/12 19:54:45 - mmengine - INFO - Epoch(train) [154][550/586] lr: 5.000000e-03 eta: 2:54:43 time: 0.335388 data_time: 0.047283 memory: 4465 loss_kpt: 86.492985 acc_pose: 0.796929 loss: 86.492985 2022/10/12 19:54:57 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:55:14 - mmengine - INFO - Epoch(train) [155][50/586] lr: 5.000000e-03 eta: 2:54:12 time: 0.346423 data_time: 0.054664 memory: 4465 loss_kpt: 87.107479 acc_pose: 0.835085 loss: 87.107479 2022/10/12 19:55:31 - mmengine - INFO - Epoch(train) [155][100/586] lr: 5.000000e-03 eta: 2:53:56 time: 0.330265 data_time: 0.050872 memory: 4465 loss_kpt: 86.094456 acc_pose: 0.862599 loss: 86.094456 2022/10/12 19:55:47 - mmengine - INFO - Epoch(train) [155][150/586] lr: 5.000000e-03 eta: 2:53:40 time: 0.327514 data_time: 0.055959 memory: 4465 loss_kpt: 86.427089 acc_pose: 0.834533 loss: 86.427089 2022/10/12 19:56:03 - mmengine - INFO - Epoch(train) [155][200/586] lr: 5.000000e-03 eta: 2:53:25 time: 0.328227 data_time: 0.049994 memory: 4465 loss_kpt: 85.720159 acc_pose: 0.749749 loss: 85.720159 2022/10/12 19:56:20 - mmengine - INFO - Epoch(train) [155][250/586] lr: 5.000000e-03 eta: 2:53:09 time: 0.337785 data_time: 0.050522 memory: 4465 loss_kpt: 87.010652 acc_pose: 0.850692 loss: 87.010652 2022/10/12 19:56:37 - mmengine - INFO - Epoch(train) [155][300/586] lr: 5.000000e-03 eta: 2:52:53 time: 0.335934 data_time: 0.049472 memory: 4465 loss_kpt: 87.676192 acc_pose: 0.809462 loss: 87.676192 2022/10/12 19:56:53 - mmengine - INFO - Epoch(train) [155][350/586] lr: 5.000000e-03 eta: 2:52:37 time: 0.321012 data_time: 0.051611 memory: 4465 loss_kpt: 86.902215 acc_pose: 0.768383 loss: 86.902215 2022/10/12 19:57:10 - mmengine - INFO - Epoch(train) [155][400/586] lr: 5.000000e-03 eta: 2:52:22 time: 0.329529 data_time: 0.051190 memory: 4465 loss_kpt: 86.159012 acc_pose: 0.837066 loss: 86.159012 2022/10/12 19:57:26 - mmengine - INFO - Epoch(train) [155][450/586] lr: 5.000000e-03 eta: 2:52:06 time: 0.321490 data_time: 0.051725 memory: 4465 loss_kpt: 87.123284 acc_pose: 0.771718 loss: 87.123284 2022/10/12 19:57:41 - mmengine - INFO - Epoch(train) [155][500/586] lr: 5.000000e-03 eta: 2:51:50 time: 0.314247 data_time: 0.054102 memory: 4465 loss_kpt: 86.042475 acc_pose: 0.844625 loss: 86.042475 2022/10/12 19:57:58 - mmengine - INFO - Epoch(train) [155][550/586] lr: 5.000000e-03 eta: 2:51:34 time: 0.325336 data_time: 0.052260 memory: 4465 loss_kpt: 87.023802 acc_pose: 0.862319 loss: 87.023802 2022/10/12 19:58:09 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:58:27 - mmengine - INFO - Epoch(train) [156][50/586] lr: 5.000000e-03 eta: 2:51:03 time: 0.348529 data_time: 0.059599 memory: 4465 loss_kpt: 87.796703 acc_pose: 0.843220 loss: 87.796703 2022/10/12 19:58:43 - mmengine - INFO - Epoch(train) [156][100/586] lr: 5.000000e-03 eta: 2:50:47 time: 0.338368 data_time: 0.055746 memory: 4465 loss_kpt: 88.801244 acc_pose: 0.776559 loss: 88.801244 2022/10/12 19:59:01 - mmengine - INFO - Epoch(train) [156][150/586] lr: 5.000000e-03 eta: 2:50:32 time: 0.347825 data_time: 0.052323 memory: 4465 loss_kpt: 86.980344 acc_pose: 0.794840 loss: 86.980344 2022/10/12 19:59:07 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 19:59:18 - mmengine - INFO - Epoch(train) [156][200/586] lr: 5.000000e-03 eta: 2:50:16 time: 0.340626 data_time: 0.052038 memory: 4465 loss_kpt: 86.741152 acc_pose: 0.771834 loss: 86.741152 2022/10/12 19:59:35 - mmengine - INFO - Epoch(train) [156][250/586] lr: 5.000000e-03 eta: 2:50:01 time: 0.333531 data_time: 0.053582 memory: 4465 loss_kpt: 86.202142 acc_pose: 0.771492 loss: 86.202142 2022/10/12 19:59:51 - mmengine - INFO - Epoch(train) [156][300/586] lr: 5.000000e-03 eta: 2:49:45 time: 0.334848 data_time: 0.051023 memory: 4465 loss_kpt: 85.196953 acc_pose: 0.828716 loss: 85.196953 2022/10/12 20:00:08 - mmengine - INFO - Epoch(train) [156][350/586] lr: 5.000000e-03 eta: 2:49:29 time: 0.330622 data_time: 0.055283 memory: 4465 loss_kpt: 86.540964 acc_pose: 0.766651 loss: 86.540964 2022/10/12 20:00:24 - mmengine - INFO - Epoch(train) [156][400/586] lr: 5.000000e-03 eta: 2:49:13 time: 0.321853 data_time: 0.048938 memory: 4465 loss_kpt: 87.551116 acc_pose: 0.828871 loss: 87.551116 2022/10/12 20:00:41 - mmengine - INFO - Epoch(train) [156][450/586] lr: 5.000000e-03 eta: 2:48:58 time: 0.334769 data_time: 0.049665 memory: 4465 loss_kpt: 86.421615 acc_pose: 0.790191 loss: 86.421615 2022/10/12 20:00:57 - mmengine - INFO - Epoch(train) [156][500/586] lr: 5.000000e-03 eta: 2:48:42 time: 0.327679 data_time: 0.049784 memory: 4465 loss_kpt: 86.747997 acc_pose: 0.727482 loss: 86.747997 2022/10/12 20:01:13 - mmengine - INFO - Epoch(train) [156][550/586] lr: 5.000000e-03 eta: 2:48:26 time: 0.326309 data_time: 0.052669 memory: 4465 loss_kpt: 86.498962 acc_pose: 0.825281 loss: 86.498962 2022/10/12 20:01:25 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:01:43 - mmengine - INFO - Epoch(train) [157][50/586] lr: 5.000000e-03 eta: 2:47:55 time: 0.359391 data_time: 0.066591 memory: 4465 loss_kpt: 87.017678 acc_pose: 0.829472 loss: 87.017678 2022/10/12 20:02:01 - mmengine - INFO - Epoch(train) [157][100/586] lr: 5.000000e-03 eta: 2:47:40 time: 0.346994 data_time: 0.053582 memory: 4465 loss_kpt: 84.507493 acc_pose: 0.805809 loss: 84.507493 2022/10/12 20:02:19 - mmengine - INFO - Epoch(train) [157][150/586] lr: 5.000000e-03 eta: 2:47:25 time: 0.364503 data_time: 0.053317 memory: 4465 loss_kpt: 86.225806 acc_pose: 0.778955 loss: 86.225806 2022/10/12 20:02:36 - mmengine - INFO - Epoch(train) [157][200/586] lr: 5.000000e-03 eta: 2:47:09 time: 0.348944 data_time: 0.047964 memory: 4465 loss_kpt: 86.561743 acc_pose: 0.762623 loss: 86.561743 2022/10/12 20:02:54 - mmengine - INFO - Epoch(train) [157][250/586] lr: 5.000000e-03 eta: 2:46:54 time: 0.359268 data_time: 0.052082 memory: 4465 loss_kpt: 86.831554 acc_pose: 0.809809 loss: 86.831554 2022/10/12 20:03:12 - mmengine - INFO - Epoch(train) [157][300/586] lr: 5.000000e-03 eta: 2:46:38 time: 0.349692 data_time: 0.053790 memory: 4465 loss_kpt: 87.201105 acc_pose: 0.842952 loss: 87.201105 2022/10/12 20:03:28 - mmengine - INFO - Epoch(train) [157][350/586] lr: 5.000000e-03 eta: 2:46:23 time: 0.333586 data_time: 0.051377 memory: 4465 loss_kpt: 86.587192 acc_pose: 0.834046 loss: 86.587192 2022/10/12 20:03:45 - mmengine - INFO - Epoch(train) [157][400/586] lr: 5.000000e-03 eta: 2:46:07 time: 0.324839 data_time: 0.049863 memory: 4465 loss_kpt: 87.142760 acc_pose: 0.817553 loss: 87.142760 2022/10/12 20:04:01 - mmengine - INFO - Epoch(train) [157][450/586] lr: 5.000000e-03 eta: 2:45:51 time: 0.332670 data_time: 0.052674 memory: 4465 loss_kpt: 87.382423 acc_pose: 0.706849 loss: 87.382423 2022/10/12 20:04:18 - mmengine - INFO - Epoch(train) [157][500/586] lr: 5.000000e-03 eta: 2:45:35 time: 0.335209 data_time: 0.052862 memory: 4465 loss_kpt: 85.920030 acc_pose: 0.709348 loss: 85.920030 2022/10/12 20:04:35 - mmengine - INFO - Epoch(train) [157][550/586] lr: 5.000000e-03 eta: 2:45:20 time: 0.335826 data_time: 0.054050 memory: 4465 loss_kpt: 86.257242 acc_pose: 0.807557 loss: 86.257242 2022/10/12 20:04:46 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:04:47 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:05:05 - mmengine - INFO - Epoch(train) [158][50/586] lr: 5.000000e-03 eta: 2:44:49 time: 0.363328 data_time: 0.060383 memory: 4465 loss_kpt: 86.767304 acc_pose: 0.794221 loss: 86.767304 2022/10/12 20:05:21 - mmengine - INFO - Epoch(train) [158][100/586] lr: 5.000000e-03 eta: 2:44:33 time: 0.325770 data_time: 0.051378 memory: 4465 loss_kpt: 86.630060 acc_pose: 0.823309 loss: 86.630060 2022/10/12 20:05:39 - mmengine - INFO - Epoch(train) [158][150/586] lr: 5.000000e-03 eta: 2:44:18 time: 0.344361 data_time: 0.051647 memory: 4465 loss_kpt: 86.879505 acc_pose: 0.874970 loss: 86.879505 2022/10/12 20:05:56 - mmengine - INFO - Epoch(train) [158][200/586] lr: 5.000000e-03 eta: 2:44:02 time: 0.340563 data_time: 0.049985 memory: 4465 loss_kpt: 86.660448 acc_pose: 0.823950 loss: 86.660448 2022/10/12 20:06:13 - mmengine - INFO - Epoch(train) [158][250/586] lr: 5.000000e-03 eta: 2:43:47 time: 0.348250 data_time: 0.051395 memory: 4465 loss_kpt: 88.432614 acc_pose: 0.805691 loss: 88.432614 2022/10/12 20:06:31 - mmengine - INFO - Epoch(train) [158][300/586] lr: 5.000000e-03 eta: 2:43:31 time: 0.352744 data_time: 0.050315 memory: 4465 loss_kpt: 86.967895 acc_pose: 0.838697 loss: 86.967895 2022/10/12 20:06:47 - mmengine - INFO - Epoch(train) [158][350/586] lr: 5.000000e-03 eta: 2:43:16 time: 0.335438 data_time: 0.050288 memory: 4465 loss_kpt: 86.483197 acc_pose: 0.847183 loss: 86.483197 2022/10/12 20:07:04 - mmengine - INFO - Epoch(train) [158][400/586] lr: 5.000000e-03 eta: 2:43:00 time: 0.336965 data_time: 0.052014 memory: 4465 loss_kpt: 87.938906 acc_pose: 0.809270 loss: 87.938906 2022/10/12 20:07:21 - mmengine - INFO - Epoch(train) [158][450/586] lr: 5.000000e-03 eta: 2:42:44 time: 0.331552 data_time: 0.051008 memory: 4465 loss_kpt: 87.220972 acc_pose: 0.777583 loss: 87.220972 2022/10/12 20:07:38 - mmengine - INFO - Epoch(train) [158][500/586] lr: 5.000000e-03 eta: 2:42:29 time: 0.339895 data_time: 0.050634 memory: 4465 loss_kpt: 84.879160 acc_pose: 0.794361 loss: 84.879160 2022/10/12 20:07:55 - mmengine - INFO - Epoch(train) [158][550/586] lr: 5.000000e-03 eta: 2:42:13 time: 0.340843 data_time: 0.058363 memory: 4465 loss_kpt: 86.811275 acc_pose: 0.726083 loss: 86.811275 2022/10/12 20:08:07 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:08:26 - mmengine - INFO - Epoch(train) [159][50/586] lr: 5.000000e-03 eta: 2:41:43 time: 0.368279 data_time: 0.066036 memory: 4465 loss_kpt: 86.954820 acc_pose: 0.770565 loss: 86.954820 2022/10/12 20:08:43 - mmengine - INFO - Epoch(train) [159][100/586] lr: 5.000000e-03 eta: 2:41:27 time: 0.344220 data_time: 0.049663 memory: 4465 loss_kpt: 87.590982 acc_pose: 0.788977 loss: 87.590982 2022/10/12 20:09:00 - mmengine - INFO - Epoch(train) [159][150/586] lr: 5.000000e-03 eta: 2:41:12 time: 0.347188 data_time: 0.051029 memory: 4465 loss_kpt: 85.392635 acc_pose: 0.825037 loss: 85.392635 2022/10/12 20:09:17 - mmengine - INFO - Epoch(train) [159][200/586] lr: 5.000000e-03 eta: 2:40:56 time: 0.342934 data_time: 0.047032 memory: 4465 loss_kpt: 86.551339 acc_pose: 0.825866 loss: 86.551339 2022/10/12 20:09:36 - mmengine - INFO - Epoch(train) [159][250/586] lr: 5.000000e-03 eta: 2:40:41 time: 0.360470 data_time: 0.055761 memory: 4465 loss_kpt: 86.600843 acc_pose: 0.830875 loss: 86.600843 2022/10/12 20:09:52 - mmengine - INFO - Epoch(train) [159][300/586] lr: 5.000000e-03 eta: 2:40:25 time: 0.329994 data_time: 0.047835 memory: 4465 loss_kpt: 86.508601 acc_pose: 0.839030 loss: 86.508601 2022/10/12 20:10:09 - mmengine - INFO - Epoch(train) [159][350/586] lr: 5.000000e-03 eta: 2:40:10 time: 0.337838 data_time: 0.048165 memory: 4465 loss_kpt: 86.726146 acc_pose: 0.764833 loss: 86.726146 2022/10/12 20:10:25 - mmengine - INFO - Epoch(train) [159][400/586] lr: 5.000000e-03 eta: 2:39:54 time: 0.327662 data_time: 0.048497 memory: 4465 loss_kpt: 86.464275 acc_pose: 0.868529 loss: 86.464275 2022/10/12 20:10:29 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:10:42 - mmengine - INFO - Epoch(train) [159][450/586] lr: 5.000000e-03 eta: 2:39:38 time: 0.335263 data_time: 0.046010 memory: 4465 loss_kpt: 87.241359 acc_pose: 0.853110 loss: 87.241359 2022/10/12 20:10:58 - mmengine - INFO - Epoch(train) [159][500/586] lr: 5.000000e-03 eta: 2:39:22 time: 0.321777 data_time: 0.050460 memory: 4465 loss_kpt: 88.104209 acc_pose: 0.831642 loss: 88.104209 2022/10/12 20:11:14 - mmengine - INFO - Epoch(train) [159][550/586] lr: 5.000000e-03 eta: 2:39:06 time: 0.321311 data_time: 0.049795 memory: 4465 loss_kpt: 85.738170 acc_pose: 0.810875 loss: 85.738170 2022/10/12 20:11:26 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:11:43 - mmengine - INFO - Epoch(train) [160][50/586] lr: 5.000000e-03 eta: 2:38:35 time: 0.344291 data_time: 0.066342 memory: 4465 loss_kpt: 84.848276 acc_pose: 0.813647 loss: 84.848276 2022/10/12 20:12:00 - mmengine - INFO - Epoch(train) [160][100/586] lr: 5.000000e-03 eta: 2:38:20 time: 0.336683 data_time: 0.052213 memory: 4465 loss_kpt: 86.359542 acc_pose: 0.783484 loss: 86.359542 2022/10/12 20:12:17 - mmengine - INFO - Epoch(train) [160][150/586] lr: 5.000000e-03 eta: 2:38:04 time: 0.351259 data_time: 0.056213 memory: 4465 loss_kpt: 88.036603 acc_pose: 0.833271 loss: 88.036603 2022/10/12 20:12:34 - mmengine - INFO - Epoch(train) [160][200/586] lr: 5.000000e-03 eta: 2:37:49 time: 0.340016 data_time: 0.055212 memory: 4465 loss_kpt: 86.452437 acc_pose: 0.817271 loss: 86.452437 2022/10/12 20:12:51 - mmengine - INFO - Epoch(train) [160][250/586] lr: 5.000000e-03 eta: 2:37:33 time: 0.339599 data_time: 0.058641 memory: 4465 loss_kpt: 85.205636 acc_pose: 0.764435 loss: 85.205636 2022/10/12 20:13:08 - mmengine - INFO - Epoch(train) [160][300/586] lr: 5.000000e-03 eta: 2:37:17 time: 0.325996 data_time: 0.052419 memory: 4465 loss_kpt: 85.155393 acc_pose: 0.904515 loss: 85.155393 2022/10/12 20:13:24 - mmengine - INFO - Epoch(train) [160][350/586] lr: 5.000000e-03 eta: 2:37:02 time: 0.331972 data_time: 0.053613 memory: 4465 loss_kpt: 86.972531 acc_pose: 0.800379 loss: 86.972531 2022/10/12 20:13:41 - mmengine - INFO - Epoch(train) [160][400/586] lr: 5.000000e-03 eta: 2:36:46 time: 0.328780 data_time: 0.052264 memory: 4465 loss_kpt: 86.033639 acc_pose: 0.853790 loss: 86.033639 2022/10/12 20:13:57 - mmengine - INFO - Epoch(train) [160][450/586] lr: 5.000000e-03 eta: 2:36:30 time: 0.323364 data_time: 0.048322 memory: 4465 loss_kpt: 86.338125 acc_pose: 0.842100 loss: 86.338125 2022/10/12 20:14:13 - mmengine - INFO - Epoch(train) [160][500/586] lr: 5.000000e-03 eta: 2:36:14 time: 0.327582 data_time: 0.053706 memory: 4465 loss_kpt: 86.791114 acc_pose: 0.786104 loss: 86.791114 2022/10/12 20:14:31 - mmengine - INFO - Epoch(train) [160][550/586] lr: 5.000000e-03 eta: 2:35:59 time: 0.344072 data_time: 0.057787 memory: 4465 loss_kpt: 86.978156 acc_pose: 0.857840 loss: 86.978156 2022/10/12 20:14:43 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:14:43 - mmengine - INFO - Saving checkpoint at 160 epochs 2022/10/12 20:14:52 - mmengine - INFO - Epoch(val) [160][50/407] eta: 0:00:46 time: 0.131432 data_time: 0.012823 memory: 4465 2022/10/12 20:14:58 - mmengine - INFO - Epoch(val) [160][100/407] eta: 0:00:39 time: 0.129086 data_time: 0.008962 memory: 1026 2022/10/12 20:15:05 - mmengine - INFO - Epoch(val) [160][150/407] eta: 0:00:33 time: 0.129547 data_time: 0.008208 memory: 1026 2022/10/12 20:15:11 - mmengine - INFO - Epoch(val) [160][200/407] eta: 0:00:27 time: 0.132730 data_time: 0.007801 memory: 1026 2022/10/12 20:15:18 - mmengine - INFO - Epoch(val) [160][250/407] eta: 0:00:20 time: 0.128631 data_time: 0.008801 memory: 1026 2022/10/12 20:15:24 - mmengine - INFO - Epoch(val) [160][300/407] eta: 0:00:13 time: 0.126787 data_time: 0.008478 memory: 1026 2022/10/12 20:15:30 - mmengine - INFO - Epoch(val) [160][350/407] eta: 0:00:07 time: 0.126586 data_time: 0.008244 memory: 1026 2022/10/12 20:15:37 - mmengine - INFO - Epoch(val) [160][400/407] eta: 0:00:00 time: 0.124144 data_time: 0.007914 memory: 1026 2022/10/12 20:15:50 - mmengine - INFO - Evaluating CocoMetric... 2022/10/12 20:16:06 - mmengine - INFO - Epoch(val) [160][407/407] coco/AP: 0.705712 coco/AP .5: 0.887696 coco/AP .75: 0.781856 coco/AP (M): 0.671297 coco/AP (L): 0.767939 coco/AR: 0.773410 coco/AR .5: 0.926637 coco/AR .75: 0.838476 coco/AR (M): 0.727533 coco/AR (L): 0.836529 2022/10/12 20:16:06 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/liqikai/openmmlab/pt112cu113py38/mmpose/work_dirs/20221012/rsn50/best_coco/AP_epoch_150.pth is removed 2022/10/12 20:16:08 - mmengine - INFO - The best checkpoint with 0.7057 coco/AP at 160 epoch is saved to best_coco/AP_epoch_160.pth. 2022/10/12 20:16:25 - mmengine - INFO - Epoch(train) [161][50/586] lr: 5.000000e-03 eta: 2:35:28 time: 0.334605 data_time: 0.061136 memory: 4465 loss_kpt: 87.420237 acc_pose: 0.787422 loss: 87.420237 2022/10/12 20:16:41 - mmengine - INFO - Epoch(train) [161][100/586] lr: 5.000000e-03 eta: 2:35:12 time: 0.325685 data_time: 0.048826 memory: 4465 loss_kpt: 85.689321 acc_pose: 0.829184 loss: 85.689321 2022/10/12 20:16:57 - mmengine - INFO - Epoch(train) [161][150/586] lr: 5.000000e-03 eta: 2:34:56 time: 0.328330 data_time: 0.053602 memory: 4465 loss_kpt: 86.732753 acc_pose: 0.831574 loss: 86.732753 2022/10/12 20:17:14 - mmengine - INFO - Epoch(train) [161][200/586] lr: 5.000000e-03 eta: 2:34:40 time: 0.336963 data_time: 0.053312 memory: 4465 loss_kpt: 85.404960 acc_pose: 0.757665 loss: 85.404960 2022/10/12 20:17:28 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:17:32 - mmengine - INFO - Epoch(train) [161][250/586] lr: 5.000000e-03 eta: 2:34:25 time: 0.349011 data_time: 0.057676 memory: 4465 loss_kpt: 87.185393 acc_pose: 0.832239 loss: 87.185393 2022/10/12 20:17:49 - mmengine - INFO - Epoch(train) [161][300/586] lr: 5.000000e-03 eta: 2:34:09 time: 0.342345 data_time: 0.049172 memory: 4465 loss_kpt: 85.656329 acc_pose: 0.860126 loss: 85.656329 2022/10/12 20:18:06 - mmengine - INFO - Epoch(train) [161][350/586] lr: 5.000000e-03 eta: 2:33:54 time: 0.344895 data_time: 0.053827 memory: 4465 loss_kpt: 87.382239 acc_pose: 0.835076 loss: 87.382239 2022/10/12 20:18:23 - mmengine - INFO - Epoch(train) [161][400/586] lr: 5.000000e-03 eta: 2:33:38 time: 0.343945 data_time: 0.046900 memory: 4465 loss_kpt: 88.426354 acc_pose: 0.829040 loss: 88.426354 2022/10/12 20:18:41 - mmengine - INFO - Epoch(train) [161][450/586] lr: 5.000000e-03 eta: 2:33:23 time: 0.355700 data_time: 0.054838 memory: 4465 loss_kpt: 86.977580 acc_pose: 0.836309 loss: 86.977580 2022/10/12 20:18:58 - mmengine - INFO - Epoch(train) [161][500/586] lr: 5.000000e-03 eta: 2:33:07 time: 0.337785 data_time: 0.054141 memory: 4465 loss_kpt: 86.194622 acc_pose: 0.826764 loss: 86.194622 2022/10/12 20:19:14 - mmengine - INFO - Epoch(train) [161][550/586] lr: 5.000000e-03 eta: 2:32:51 time: 0.326701 data_time: 0.049552 memory: 4465 loss_kpt: 86.442731 acc_pose: 0.820269 loss: 86.442731 2022/10/12 20:19:26 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:19:43 - mmengine - INFO - Epoch(train) [162][50/586] lr: 5.000000e-03 eta: 2:32:21 time: 0.347531 data_time: 0.072804 memory: 4465 loss_kpt: 86.189163 acc_pose: 0.776094 loss: 86.189163 2022/10/12 20:20:00 - mmengine - INFO - Epoch(train) [162][100/586] lr: 5.000000e-03 eta: 2:32:05 time: 0.333798 data_time: 0.049246 memory: 4465 loss_kpt: 87.078448 acc_pose: 0.822512 loss: 87.078448 2022/10/12 20:20:17 - mmengine - INFO - Epoch(train) [162][150/586] lr: 5.000000e-03 eta: 2:31:49 time: 0.336957 data_time: 0.054570 memory: 4465 loss_kpt: 86.866707 acc_pose: 0.831155 loss: 86.866707 2022/10/12 20:20:34 - mmengine - INFO - Epoch(train) [162][200/586] lr: 5.000000e-03 eta: 2:31:34 time: 0.334559 data_time: 0.051679 memory: 4465 loss_kpt: 86.089736 acc_pose: 0.827505 loss: 86.089736 2022/10/12 20:20:51 - mmengine - INFO - Epoch(train) [162][250/586] lr: 5.000000e-03 eta: 2:31:18 time: 0.336975 data_time: 0.052219 memory: 4465 loss_kpt: 85.142555 acc_pose: 0.793088 loss: 85.142555 2022/10/12 20:21:07 - mmengine - INFO - Epoch(train) [162][300/586] lr: 5.000000e-03 eta: 2:31:02 time: 0.330731 data_time: 0.051830 memory: 4465 loss_kpt: 85.435601 acc_pose: 0.788211 loss: 85.435601 2022/10/12 20:21:23 - mmengine - INFO - Epoch(train) [162][350/586] lr: 5.000000e-03 eta: 2:30:46 time: 0.326249 data_time: 0.049958 memory: 4465 loss_kpt: 87.194197 acc_pose: 0.808217 loss: 87.194197 2022/10/12 20:21:40 - mmengine - INFO - Epoch(train) [162][400/586] lr: 5.000000e-03 eta: 2:30:31 time: 0.331806 data_time: 0.051052 memory: 4465 loss_kpt: 87.367684 acc_pose: 0.769090 loss: 87.367684 2022/10/12 20:21:57 - mmengine - INFO - Epoch(train) [162][450/586] lr: 5.000000e-03 eta: 2:30:15 time: 0.328120 data_time: 0.054795 memory: 4465 loss_kpt: 86.219787 acc_pose: 0.775069 loss: 86.219787 2022/10/12 20:22:13 - mmengine - INFO - Epoch(train) [162][500/586] lr: 5.000000e-03 eta: 2:29:59 time: 0.327168 data_time: 0.049029 memory: 4465 loss_kpt: 86.656859 acc_pose: 0.841614 loss: 86.656859 2022/10/12 20:22:30 - mmengine - INFO - Epoch(train) [162][550/586] lr: 5.000000e-03 eta: 2:29:43 time: 0.333818 data_time: 0.057084 memory: 4465 loss_kpt: 86.056781 acc_pose: 0.844230 loss: 86.056781 2022/10/12 20:22:41 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:22:59 - mmengine - INFO - Epoch(train) [163][50/586] lr: 5.000000e-03 eta: 2:29:13 time: 0.347087 data_time: 0.068209 memory: 4465 loss_kpt: 86.323425 acc_pose: 0.773380 loss: 86.323425 2022/10/12 20:23:05 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:23:15 - mmengine - INFO - Epoch(train) [163][100/586] lr: 5.000000e-03 eta: 2:28:57 time: 0.327563 data_time: 0.055410 memory: 4465 loss_kpt: 86.837494 acc_pose: 0.824048 loss: 86.837494 2022/10/12 20:23:31 - mmengine - INFO - Epoch(train) [163][150/586] lr: 5.000000e-03 eta: 2:28:41 time: 0.324011 data_time: 0.053249 memory: 4465 loss_kpt: 85.264066 acc_pose: 0.824803 loss: 85.264066 2022/10/12 20:23:48 - mmengine - INFO - Epoch(train) [163][200/586] lr: 5.000000e-03 eta: 2:28:25 time: 0.326518 data_time: 0.049658 memory: 4465 loss_kpt: 87.265130 acc_pose: 0.840707 loss: 87.265130 2022/10/12 20:24:04 - mmengine - INFO - Epoch(train) [163][250/586] lr: 5.000000e-03 eta: 2:28:10 time: 0.323370 data_time: 0.048617 memory: 4465 loss_kpt: 87.259132 acc_pose: 0.797511 loss: 87.259132 2022/10/12 20:24:20 - mmengine - INFO - Epoch(train) [163][300/586] lr: 5.000000e-03 eta: 2:27:54 time: 0.320317 data_time: 0.053005 memory: 4465 loss_kpt: 86.396718 acc_pose: 0.766916 loss: 86.396718 2022/10/12 20:24:36 - mmengine - INFO - Epoch(train) [163][350/586] lr: 5.000000e-03 eta: 2:27:38 time: 0.325706 data_time: 0.051135 memory: 4465 loss_kpt: 87.295376 acc_pose: 0.768754 loss: 87.295376 2022/10/12 20:24:52 - mmengine - INFO - Epoch(train) [163][400/586] lr: 5.000000e-03 eta: 2:27:22 time: 0.315018 data_time: 0.047083 memory: 4465 loss_kpt: 86.899726 acc_pose: 0.857415 loss: 86.899726 2022/10/12 20:25:09 - mmengine - INFO - Epoch(train) [163][450/586] lr: 5.000000e-03 eta: 2:27:06 time: 0.332270 data_time: 0.052540 memory: 4465 loss_kpt: 86.817005 acc_pose: 0.786780 loss: 86.817005 2022/10/12 20:25:25 - mmengine - INFO - Epoch(train) [163][500/586] lr: 5.000000e-03 eta: 2:26:50 time: 0.322151 data_time: 0.050315 memory: 4465 loss_kpt: 85.577374 acc_pose: 0.813255 loss: 85.577374 2022/10/12 20:25:41 - mmengine - INFO - Epoch(train) [163][550/586] lr: 5.000000e-03 eta: 2:26:34 time: 0.318950 data_time: 0.047946 memory: 4465 loss_kpt: 86.431004 acc_pose: 0.810525 loss: 86.431004 2022/10/12 20:25:52 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:26:09 - mmengine - INFO - Epoch(train) [164][50/586] lr: 5.000000e-03 eta: 2:26:04 time: 0.339340 data_time: 0.061100 memory: 4465 loss_kpt: 85.004789 acc_pose: 0.834430 loss: 85.004789 2022/10/12 20:26:25 - mmengine - INFO - Epoch(train) [164][100/586] lr: 5.000000e-03 eta: 2:25:48 time: 0.322610 data_time: 0.053791 memory: 4465 loss_kpt: 85.920456 acc_pose: 0.831581 loss: 85.920456 2022/10/12 20:26:42 - mmengine - INFO - Epoch(train) [164][150/586] lr: 5.000000e-03 eta: 2:25:32 time: 0.342791 data_time: 0.055324 memory: 4465 loss_kpt: 84.600063 acc_pose: 0.860450 loss: 84.600063 2022/10/12 20:26:59 - mmengine - INFO - Epoch(train) [164][200/586] lr: 5.000000e-03 eta: 2:25:17 time: 0.336743 data_time: 0.054262 memory: 4465 loss_kpt: 86.635388 acc_pose: 0.772916 loss: 86.635388 2022/10/12 20:27:16 - mmengine - INFO - Epoch(train) [164][250/586] lr: 5.000000e-03 eta: 2:25:01 time: 0.341293 data_time: 0.054031 memory: 4465 loss_kpt: 86.799362 acc_pose: 0.792381 loss: 86.799362 2022/10/12 20:27:33 - mmengine - INFO - Epoch(train) [164][300/586] lr: 5.000000e-03 eta: 2:24:45 time: 0.338594 data_time: 0.050798 memory: 4465 loss_kpt: 86.919999 acc_pose: 0.783758 loss: 86.919999 2022/10/12 20:27:51 - mmengine - INFO - Epoch(train) [164][350/586] lr: 5.000000e-03 eta: 2:24:30 time: 0.346442 data_time: 0.054847 memory: 4465 loss_kpt: 87.680631 acc_pose: 0.661789 loss: 87.680631 2022/10/12 20:28:08 - mmengine - INFO - Epoch(train) [164][400/586] lr: 5.000000e-03 eta: 2:24:14 time: 0.343983 data_time: 0.050779 memory: 4465 loss_kpt: 85.867829 acc_pose: 0.782502 loss: 85.867829 2022/10/12 20:28:25 - mmengine - INFO - Epoch(train) [164][450/586] lr: 5.000000e-03 eta: 2:23:59 time: 0.340925 data_time: 0.052454 memory: 4465 loss_kpt: 85.718219 acc_pose: 0.879646 loss: 85.718219 2022/10/12 20:28:36 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:28:42 - mmengine - INFO - Epoch(train) [164][500/586] lr: 5.000000e-03 eta: 2:23:43 time: 0.336264 data_time: 0.051273 memory: 4465 loss_kpt: 86.043237 acc_pose: 0.824372 loss: 86.043237 2022/10/12 20:28:59 - mmengine - INFO - Epoch(train) [164][550/586] lr: 5.000000e-03 eta: 2:23:27 time: 0.338279 data_time: 0.050587 memory: 4465 loss_kpt: 84.927247 acc_pose: 0.872012 loss: 84.927247 2022/10/12 20:29:10 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:29:28 - mmengine - INFO - Epoch(train) [165][50/586] lr: 5.000000e-03 eta: 2:22:57 time: 0.353274 data_time: 0.056498 memory: 4465 loss_kpt: 88.617459 acc_pose: 0.768668 loss: 88.617459 2022/10/12 20:29:45 - mmengine - INFO - Epoch(train) [165][100/586] lr: 5.000000e-03 eta: 2:22:41 time: 0.339229 data_time: 0.052073 memory: 4465 loss_kpt: 86.065379 acc_pose: 0.749863 loss: 86.065379 2022/10/12 20:30:02 - mmengine - INFO - Epoch(train) [165][150/586] lr: 5.000000e-03 eta: 2:22:26 time: 0.341169 data_time: 0.048259 memory: 4465 loss_kpt: 85.732050 acc_pose: 0.772875 loss: 85.732050 2022/10/12 20:30:19 - mmengine - INFO - Epoch(train) [165][200/586] lr: 5.000000e-03 eta: 2:22:10 time: 0.330945 data_time: 0.049282 memory: 4465 loss_kpt: 86.690233 acc_pose: 0.816140 loss: 86.690233 2022/10/12 20:30:36 - mmengine - INFO - Epoch(train) [165][250/586] lr: 5.000000e-03 eta: 2:21:54 time: 0.344452 data_time: 0.049472 memory: 4465 loss_kpt: 86.971561 acc_pose: 0.758401 loss: 86.971561 2022/10/12 20:30:53 - mmengine - INFO - Epoch(train) [165][300/586] lr: 5.000000e-03 eta: 2:21:39 time: 0.341910 data_time: 0.047498 memory: 4465 loss_kpt: 87.790375 acc_pose: 0.810635 loss: 87.790375 2022/10/12 20:31:10 - mmengine - INFO - Epoch(train) [165][350/586] lr: 5.000000e-03 eta: 2:21:23 time: 0.333789 data_time: 0.049494 memory: 4465 loss_kpt: 86.273792 acc_pose: 0.819993 loss: 86.273792 2022/10/12 20:31:27 - mmengine - INFO - Epoch(train) [165][400/586] lr: 5.000000e-03 eta: 2:21:07 time: 0.343066 data_time: 0.051092 memory: 4465 loss_kpt: 88.085372 acc_pose: 0.864545 loss: 88.085372 2022/10/12 20:31:44 - mmengine - INFO - Epoch(train) [165][450/586] lr: 5.000000e-03 eta: 2:20:52 time: 0.347923 data_time: 0.046819 memory: 4465 loss_kpt: 86.353405 acc_pose: 0.729746 loss: 86.353405 2022/10/12 20:32:01 - mmengine - INFO - Epoch(train) [165][500/586] lr: 5.000000e-03 eta: 2:20:36 time: 0.336725 data_time: 0.051838 memory: 4465 loss_kpt: 85.406239 acc_pose: 0.860371 loss: 85.406239 2022/10/12 20:32:18 - mmengine - INFO - Epoch(train) [165][550/586] lr: 5.000000e-03 eta: 2:20:20 time: 0.336471 data_time: 0.048834 memory: 4465 loss_kpt: 87.671950 acc_pose: 0.714225 loss: 87.671950 2022/10/12 20:32:30 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:32:47 - mmengine - INFO - Epoch(train) [166][50/586] lr: 5.000000e-03 eta: 2:19:50 time: 0.345105 data_time: 0.060373 memory: 4465 loss_kpt: 85.801565 acc_pose: 0.770104 loss: 85.801565 2022/10/12 20:33:04 - mmengine - INFO - Epoch(train) [166][100/586] lr: 5.000000e-03 eta: 2:19:35 time: 0.337486 data_time: 0.053972 memory: 4465 loss_kpt: 86.993558 acc_pose: 0.766082 loss: 86.993558 2022/10/12 20:33:21 - mmengine - INFO - Epoch(train) [166][150/586] lr: 5.000000e-03 eta: 2:19:19 time: 0.334479 data_time: 0.054105 memory: 4465 loss_kpt: 86.752060 acc_pose: 0.856952 loss: 86.752060 2022/10/12 20:33:37 - mmengine - INFO - Epoch(train) [166][200/586] lr: 5.000000e-03 eta: 2:19:03 time: 0.327213 data_time: 0.051956 memory: 4465 loss_kpt: 86.414261 acc_pose: 0.797517 loss: 86.414261 2022/10/12 20:33:54 - mmengine - INFO - Epoch(train) [166][250/586] lr: 5.000000e-03 eta: 2:18:47 time: 0.326288 data_time: 0.047564 memory: 4465 loss_kpt: 85.568278 acc_pose: 0.808117 loss: 85.568278 2022/10/12 20:34:11 - mmengine - INFO - Epoch(train) [166][300/586] lr: 5.000000e-03 eta: 2:18:32 time: 0.346286 data_time: 0.054263 memory: 4465 loss_kpt: 86.849829 acc_pose: 0.778442 loss: 86.849829 2022/10/12 20:34:14 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:34:28 - mmengine - INFO - Epoch(train) [166][350/586] lr: 5.000000e-03 eta: 2:18:16 time: 0.342613 data_time: 0.048756 memory: 4465 loss_kpt: 85.842177 acc_pose: 0.754597 loss: 85.842177 2022/10/12 20:34:46 - mmengine - INFO - Epoch(train) [166][400/586] lr: 5.000000e-03 eta: 2:18:01 time: 0.356869 data_time: 0.053552 memory: 4465 loss_kpt: 86.318095 acc_pose: 0.789925 loss: 86.318095 2022/10/12 20:35:03 - mmengine - INFO - Epoch(train) [166][450/586] lr: 5.000000e-03 eta: 2:17:45 time: 0.351189 data_time: 0.049762 memory: 4465 loss_kpt: 85.008124 acc_pose: 0.840893 loss: 85.008124 2022/10/12 20:35:21 - mmengine - INFO - Epoch(train) [166][500/586] lr: 5.000000e-03 eta: 2:17:29 time: 0.347832 data_time: 0.053105 memory: 4465 loss_kpt: 86.338391 acc_pose: 0.887391 loss: 86.338391 2022/10/12 20:35:38 - mmengine - INFO - Epoch(train) [166][550/586] lr: 5.000000e-03 eta: 2:17:14 time: 0.343862 data_time: 0.054751 memory: 4465 loss_kpt: 86.576552 acc_pose: 0.857077 loss: 86.576552 2022/10/12 20:35:50 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:36:07 - mmengine - INFO - Epoch(train) [167][50/586] lr: 5.000000e-03 eta: 2:16:44 time: 0.341403 data_time: 0.061053 memory: 4465 loss_kpt: 86.648291 acc_pose: 0.768328 loss: 86.648291 2022/10/12 20:36:24 - mmengine - INFO - Epoch(train) [167][100/586] lr: 5.000000e-03 eta: 2:16:28 time: 0.333634 data_time: 0.051659 memory: 4465 loss_kpt: 86.547173 acc_pose: 0.805050 loss: 86.547173 2022/10/12 20:36:41 - mmengine - INFO - Epoch(train) [167][150/586] lr: 5.000000e-03 eta: 2:16:12 time: 0.336738 data_time: 0.047638 memory: 4465 loss_kpt: 86.368286 acc_pose: 0.787910 loss: 86.368286 2022/10/12 20:36:57 - mmengine - INFO - Epoch(train) [167][200/586] lr: 5.000000e-03 eta: 2:15:56 time: 0.331174 data_time: 0.051442 memory: 4465 loss_kpt: 85.692456 acc_pose: 0.777693 loss: 85.692456 2022/10/12 20:37:14 - mmengine - INFO - Epoch(train) [167][250/586] lr: 5.000000e-03 eta: 2:15:41 time: 0.341762 data_time: 0.048043 memory: 4465 loss_kpt: 87.060000 acc_pose: 0.822914 loss: 87.060000 2022/10/12 20:37:31 - mmengine - INFO - Epoch(train) [167][300/586] lr: 5.000000e-03 eta: 2:15:25 time: 0.343883 data_time: 0.049240 memory: 4465 loss_kpt: 85.443724 acc_pose: 0.876110 loss: 85.443724 2022/10/12 20:37:48 - mmengine - INFO - Epoch(train) [167][350/586] lr: 5.000000e-03 eta: 2:15:10 time: 0.337693 data_time: 0.051773 memory: 4465 loss_kpt: 86.812641 acc_pose: 0.781868 loss: 86.812641 2022/10/12 20:38:05 - mmengine - INFO - Epoch(train) [167][400/586] lr: 5.000000e-03 eta: 2:14:54 time: 0.342293 data_time: 0.052418 memory: 4465 loss_kpt: 85.947554 acc_pose: 0.748364 loss: 85.947554 2022/10/12 20:38:22 - mmengine - INFO - Epoch(train) [167][450/586] lr: 5.000000e-03 eta: 2:14:38 time: 0.333973 data_time: 0.052178 memory: 4465 loss_kpt: 85.651592 acc_pose: 0.851612 loss: 85.651592 2022/10/12 20:38:39 - mmengine - INFO - Epoch(train) [167][500/586] lr: 5.000000e-03 eta: 2:14:22 time: 0.335607 data_time: 0.048945 memory: 4465 loss_kpt: 86.148285 acc_pose: 0.867950 loss: 86.148285 2022/10/12 20:38:55 - mmengine - INFO - Epoch(train) [167][550/586] lr: 5.000000e-03 eta: 2:14:07 time: 0.328309 data_time: 0.050841 memory: 4465 loss_kpt: 87.226234 acc_pose: 0.738830 loss: 87.226234 2022/10/12 20:39:07 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:39:25 - mmengine - INFO - Epoch(train) [168][50/586] lr: 5.000000e-03 eta: 2:13:37 time: 0.352874 data_time: 0.065006 memory: 4465 loss_kpt: 86.595048 acc_pose: 0.764902 loss: 86.595048 2022/10/12 20:39:42 - mmengine - INFO - Epoch(train) [168][100/586] lr: 5.000000e-03 eta: 2:13:21 time: 0.339016 data_time: 0.054237 memory: 4465 loss_kpt: 86.024805 acc_pose: 0.816741 loss: 86.024805 2022/10/12 20:39:55 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:39:59 - mmengine - INFO - Epoch(train) [168][150/586] lr: 5.000000e-03 eta: 2:13:05 time: 0.339469 data_time: 0.051198 memory: 4465 loss_kpt: 85.989453 acc_pose: 0.820013 loss: 85.989453 2022/10/12 20:40:16 - mmengine - INFO - Epoch(train) [168][200/586] lr: 5.000000e-03 eta: 2:12:50 time: 0.337540 data_time: 0.054875 memory: 4465 loss_kpt: 85.496275 acc_pose: 0.860945 loss: 85.496275 2022/10/12 20:40:33 - mmengine - INFO - Epoch(train) [168][250/586] lr: 5.000000e-03 eta: 2:12:34 time: 0.345838 data_time: 0.052639 memory: 4465 loss_kpt: 86.604275 acc_pose: 0.814415 loss: 86.604275 2022/10/12 20:40:49 - mmengine - INFO - Epoch(train) [168][300/586] lr: 5.000000e-03 eta: 2:12:18 time: 0.324782 data_time: 0.050850 memory: 4465 loss_kpt: 85.253284 acc_pose: 0.851098 loss: 85.253284 2022/10/12 20:41:07 - mmengine - INFO - Epoch(train) [168][350/586] lr: 5.000000e-03 eta: 2:12:03 time: 0.350260 data_time: 0.056571 memory: 4465 loss_kpt: 87.789534 acc_pose: 0.836134 loss: 87.789534 2022/10/12 20:41:24 - mmengine - INFO - Epoch(train) [168][400/586] lr: 5.000000e-03 eta: 2:11:47 time: 0.343419 data_time: 0.054242 memory: 4465 loss_kpt: 86.622560 acc_pose: 0.858409 loss: 86.622560 2022/10/12 20:41:41 - mmengine - INFO - Epoch(train) [168][450/586] lr: 5.000000e-03 eta: 2:11:31 time: 0.340964 data_time: 0.054495 memory: 4465 loss_kpt: 86.244077 acc_pose: 0.824055 loss: 86.244077 2022/10/12 20:41:58 - mmengine - INFO - Epoch(train) [168][500/586] lr: 5.000000e-03 eta: 2:11:16 time: 0.333535 data_time: 0.053217 memory: 4465 loss_kpt: 85.849642 acc_pose: 0.902168 loss: 85.849642 2022/10/12 20:42:15 - mmengine - INFO - Epoch(train) [168][550/586] lr: 5.000000e-03 eta: 2:11:00 time: 0.336184 data_time: 0.055040 memory: 4465 loss_kpt: 86.059803 acc_pose: 0.848319 loss: 86.059803 2022/10/12 20:42:27 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:42:45 - mmengine - INFO - Epoch(train) [169][50/586] lr: 5.000000e-03 eta: 2:10:30 time: 0.369317 data_time: 0.067369 memory: 4465 loss_kpt: 86.171411 acc_pose: 0.835800 loss: 86.171411 2022/10/12 20:43:02 - mmengine - INFO - Epoch(train) [169][100/586] lr: 5.000000e-03 eta: 2:10:14 time: 0.340813 data_time: 0.048923 memory: 4465 loss_kpt: 86.851207 acc_pose: 0.876160 loss: 86.851207 2022/10/12 20:43:19 - mmengine - INFO - Epoch(train) [169][150/586] lr: 5.000000e-03 eta: 2:09:59 time: 0.340012 data_time: 0.059657 memory: 4465 loss_kpt: 86.457224 acc_pose: 0.767886 loss: 86.457224 2022/10/12 20:43:38 - mmengine - INFO - Epoch(train) [169][200/586] lr: 5.000000e-03 eta: 2:09:43 time: 0.367492 data_time: 0.051549 memory: 4465 loss_kpt: 86.072415 acc_pose: 0.859698 loss: 86.072415 2022/10/12 20:43:56 - mmengine - INFO - Epoch(train) [169][250/586] lr: 5.000000e-03 eta: 2:09:28 time: 0.357259 data_time: 0.047162 memory: 4465 loss_kpt: 85.330596 acc_pose: 0.848462 loss: 85.330596 2022/10/12 20:44:13 - mmengine - INFO - Epoch(train) [169][300/586] lr: 5.000000e-03 eta: 2:09:12 time: 0.355864 data_time: 0.050034 memory: 4465 loss_kpt: 87.054653 acc_pose: 0.801783 loss: 87.054653 2022/10/12 20:44:31 - mmengine - INFO - Epoch(train) [169][350/586] lr: 5.000000e-03 eta: 2:08:57 time: 0.355034 data_time: 0.048601 memory: 4465 loss_kpt: 87.837021 acc_pose: 0.758309 loss: 87.837021 2022/10/12 20:44:49 - mmengine - INFO - Epoch(train) [169][400/586] lr: 5.000000e-03 eta: 2:08:41 time: 0.348596 data_time: 0.047209 memory: 4465 loss_kpt: 86.352951 acc_pose: 0.817447 loss: 86.352951 2022/10/12 20:45:06 - mmengine - INFO - Epoch(train) [169][450/586] lr: 5.000000e-03 eta: 2:08:26 time: 0.347001 data_time: 0.046833 memory: 4465 loss_kpt: 86.548717 acc_pose: 0.754164 loss: 86.548717 2022/10/12 20:45:23 - mmengine - INFO - Epoch(train) [169][500/586] lr: 5.000000e-03 eta: 2:08:10 time: 0.347421 data_time: 0.049596 memory: 4465 loss_kpt: 86.775275 acc_pose: 0.829942 loss: 86.775275 2022/10/12 20:45:41 - mmengine - INFO - Epoch(train) [169][550/586] lr: 5.000000e-03 eta: 2:07:55 time: 0.348649 data_time: 0.047362 memory: 4465 loss_kpt: 87.027170 acc_pose: 0.831396 loss: 87.027170 2022/10/12 20:45:41 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:45:53 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:46:11 - mmengine - INFO - Epoch(train) [170][50/586] lr: 5.000000e-03 eta: 2:07:25 time: 0.367950 data_time: 0.064865 memory: 4465 loss_kpt: 85.053151 acc_pose: 0.817596 loss: 85.053151 2022/10/12 20:46:28 - mmengine - INFO - Epoch(train) [170][100/586] lr: 5.000000e-03 eta: 2:07:09 time: 0.341103 data_time: 0.048779 memory: 4465 loss_kpt: 86.991554 acc_pose: 0.832190 loss: 86.991554 2022/10/12 20:46:46 - mmengine - INFO - Epoch(train) [170][150/586] lr: 5.000000e-03 eta: 2:06:54 time: 0.342251 data_time: 0.056044 memory: 4465 loss_kpt: 86.262649 acc_pose: 0.822573 loss: 86.262649 2022/10/12 20:47:03 - mmengine - INFO - Epoch(train) [170][200/586] lr: 5.000000e-03 eta: 2:06:38 time: 0.352721 data_time: 0.049370 memory: 4465 loss_kpt: 86.916187 acc_pose: 0.751394 loss: 86.916187 2022/10/12 20:47:21 - mmengine - INFO - Epoch(train) [170][250/586] lr: 5.000000e-03 eta: 2:06:23 time: 0.353844 data_time: 0.053866 memory: 4465 loss_kpt: 87.507678 acc_pose: 0.769870 loss: 87.507678 2022/10/12 20:47:38 - mmengine - INFO - Epoch(train) [170][300/586] lr: 5.000000e-03 eta: 2:06:07 time: 0.335126 data_time: 0.048894 memory: 4465 loss_kpt: 86.112887 acc_pose: 0.833766 loss: 86.112887 2022/10/12 20:47:54 - mmengine - INFO - Epoch(train) [170][350/586] lr: 5.000000e-03 eta: 2:05:51 time: 0.333567 data_time: 0.052626 memory: 4465 loss_kpt: 86.998772 acc_pose: 0.820334 loss: 86.998772 2022/10/12 20:48:11 - mmengine - INFO - Epoch(train) [170][400/586] lr: 5.000000e-03 eta: 2:05:35 time: 0.329278 data_time: 0.051764 memory: 4465 loss_kpt: 87.066801 acc_pose: 0.783101 loss: 87.066801 2022/10/12 20:48:28 - mmengine - INFO - Epoch(train) [170][450/586] lr: 5.000000e-03 eta: 2:05:20 time: 0.341095 data_time: 0.052613 memory: 4465 loss_kpt: 86.422542 acc_pose: 0.746316 loss: 86.422542 2022/10/12 20:48:45 - mmengine - INFO - Epoch(train) [170][500/586] lr: 5.000000e-03 eta: 2:05:04 time: 0.341396 data_time: 0.049859 memory: 4465 loss_kpt: 85.210633 acc_pose: 0.781666 loss: 85.210633 2022/10/12 20:49:02 - mmengine - INFO - Epoch(train) [170][550/586] lr: 5.000000e-03 eta: 2:04:48 time: 0.345047 data_time: 0.046947 memory: 4465 loss_kpt: 85.269447 acc_pose: 0.837062 loss: 85.269447 2022/10/12 20:49:15 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:49:15 - mmengine - INFO - Saving checkpoint at 170 epochs 2022/10/12 20:49:24 - mmengine - INFO - Epoch(val) [170][50/407] eta: 0:00:47 time: 0.133167 data_time: 0.013468 memory: 4465 2022/10/12 20:49:31 - mmengine - INFO - Epoch(val) [170][100/407] eta: 0:00:38 time: 0.127028 data_time: 0.008322 memory: 1026 2022/10/12 20:49:37 - mmengine - INFO - Epoch(val) [170][150/407] eta: 0:00:33 time: 0.129064 data_time: 0.008096 memory: 1026 2022/10/12 20:49:43 - mmengine - INFO - Epoch(val) [170][200/407] eta: 0:00:26 time: 0.126741 data_time: 0.007863 memory: 1026 2022/10/12 20:49:50 - mmengine - INFO - Epoch(val) [170][250/407] eta: 0:00:20 time: 0.128511 data_time: 0.008405 memory: 1026 2022/10/12 20:49:56 - mmengine - INFO - Epoch(val) [170][300/407] eta: 0:00:13 time: 0.128902 data_time: 0.008522 memory: 1026 2022/10/12 20:50:03 - mmengine - INFO - Epoch(val) [170][350/407] eta: 0:00:07 time: 0.127977 data_time: 0.008590 memory: 1026 2022/10/12 20:50:09 - mmengine - INFO - Epoch(val) [170][400/407] eta: 0:00:00 time: 0.125110 data_time: 0.007654 memory: 1026 2022/10/12 20:50:22 - mmengine - INFO - Evaluating CocoMetric... 2022/10/12 20:50:38 - mmengine - INFO - Epoch(val) [170][407/407] coco/AP: 0.704282 coco/AP .5: 0.887412 coco/AP .75: 0.778296 coco/AP (M): 0.671518 coco/AP (L): 0.766462 coco/AR: 0.772796 coco/AR .5: 0.929471 coco/AR .75: 0.833596 coco/AR (M): 0.727042 coco/AR (L): 0.835897 2022/10/12 20:50:55 - mmengine - INFO - Epoch(train) [171][50/586] lr: 5.000000e-04 eta: 2:04:18 time: 0.344337 data_time: 0.059762 memory: 4465 loss_kpt: 85.232489 acc_pose: 0.842249 loss: 85.232489 2022/10/12 20:51:12 - mmengine - INFO - Epoch(train) [171][100/586] lr: 5.000000e-04 eta: 2:04:03 time: 0.333804 data_time: 0.051522 memory: 4465 loss_kpt: 85.055208 acc_pose: 0.790210 loss: 85.055208 2022/10/12 20:51:29 - mmengine - INFO - Epoch(train) [171][150/586] lr: 5.000000e-04 eta: 2:03:47 time: 0.347378 data_time: 0.056459 memory: 4465 loss_kpt: 84.278951 acc_pose: 0.801919 loss: 84.278951 2022/10/12 20:51:46 - mmengine - INFO - Epoch(train) [171][200/586] lr: 5.000000e-04 eta: 2:03:31 time: 0.336820 data_time: 0.052474 memory: 4465 loss_kpt: 84.791205 acc_pose: 0.860528 loss: 84.791205 2022/10/12 20:52:03 - mmengine - INFO - Epoch(train) [171][250/586] lr: 5.000000e-04 eta: 2:03:16 time: 0.343357 data_time: 0.049539 memory: 4465 loss_kpt: 84.844293 acc_pose: 0.864564 loss: 84.844293 2022/10/12 20:52:20 - mmengine - INFO - Epoch(train) [171][300/586] lr: 5.000000e-04 eta: 2:03:00 time: 0.338672 data_time: 0.051864 memory: 4465 loss_kpt: 86.262580 acc_pose: 0.821239 loss: 86.262580 2022/10/12 20:52:38 - mmengine - INFO - Epoch(train) [171][350/586] lr: 5.000000e-04 eta: 2:02:44 time: 0.343662 data_time: 0.048077 memory: 4465 loss_kpt: 83.923567 acc_pose: 0.763900 loss: 83.923567 2022/10/12 20:52:48 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:52:54 - mmengine - INFO - Epoch(train) [171][400/586] lr: 5.000000e-04 eta: 2:02:28 time: 0.336425 data_time: 0.053604 memory: 4465 loss_kpt: 84.454351 acc_pose: 0.799623 loss: 84.454351 2022/10/12 20:53:11 - mmengine - INFO - Epoch(train) [171][450/586] lr: 5.000000e-04 eta: 2:02:13 time: 0.339124 data_time: 0.049183 memory: 4465 loss_kpt: 85.296070 acc_pose: 0.833388 loss: 85.296070 2022/10/12 20:53:28 - mmengine - INFO - Epoch(train) [171][500/586] lr: 5.000000e-04 eta: 2:01:57 time: 0.328273 data_time: 0.050220 memory: 4465 loss_kpt: 86.152781 acc_pose: 0.789662 loss: 86.152781 2022/10/12 20:53:44 - mmengine - INFO - Epoch(train) [171][550/586] lr: 5.000000e-04 eta: 2:01:41 time: 0.330364 data_time: 0.053158 memory: 4465 loss_kpt: 84.506162 acc_pose: 0.769760 loss: 84.506162 2022/10/12 20:53:56 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:54:13 - mmengine - INFO - Epoch(train) [172][50/586] lr: 5.000000e-04 eta: 2:01:11 time: 0.340009 data_time: 0.061250 memory: 4465 loss_kpt: 84.480927 acc_pose: 0.845751 loss: 84.480927 2022/10/12 20:54:30 - mmengine - INFO - Epoch(train) [172][100/586] lr: 5.000000e-04 eta: 2:00:55 time: 0.326318 data_time: 0.049220 memory: 4465 loss_kpt: 85.127958 acc_pose: 0.822434 loss: 85.127958 2022/10/12 20:54:46 - mmengine - INFO - Epoch(train) [172][150/586] lr: 5.000000e-04 eta: 2:00:40 time: 0.333531 data_time: 0.055171 memory: 4465 loss_kpt: 85.382915 acc_pose: 0.736724 loss: 85.382915 2022/10/12 20:55:03 - mmengine - INFO - Epoch(train) [172][200/586] lr: 5.000000e-04 eta: 2:00:24 time: 0.328338 data_time: 0.052892 memory: 4465 loss_kpt: 83.486012 acc_pose: 0.772978 loss: 83.486012 2022/10/12 20:55:20 - mmengine - INFO - Epoch(train) [172][250/586] lr: 5.000000e-04 eta: 2:00:08 time: 0.339814 data_time: 0.053267 memory: 4465 loss_kpt: 85.449154 acc_pose: 0.846208 loss: 85.449154 2022/10/12 20:55:37 - mmengine - INFO - Epoch(train) [172][300/586] lr: 5.000000e-04 eta: 1:59:52 time: 0.340550 data_time: 0.048874 memory: 4465 loss_kpt: 85.266910 acc_pose: 0.810668 loss: 85.266910 2022/10/12 20:55:54 - mmengine - INFO - Epoch(train) [172][350/586] lr: 5.000000e-04 eta: 1:59:37 time: 0.339573 data_time: 0.052807 memory: 4465 loss_kpt: 85.538475 acc_pose: 0.790599 loss: 85.538475 2022/10/12 20:56:11 - mmengine - INFO - Epoch(train) [172][400/586] lr: 5.000000e-04 eta: 1:59:21 time: 0.334398 data_time: 0.050932 memory: 4465 loss_kpt: 84.463486 acc_pose: 0.838857 loss: 84.463486 2022/10/12 20:56:28 - mmengine - INFO - Epoch(train) [172][450/586] lr: 5.000000e-04 eta: 1:59:05 time: 0.348374 data_time: 0.054453 memory: 4465 loss_kpt: 84.208216 acc_pose: 0.806662 loss: 84.208216 2022/10/12 20:56:45 - mmengine - INFO - Epoch(train) [172][500/586] lr: 5.000000e-04 eta: 1:58:50 time: 0.346120 data_time: 0.052254 memory: 4465 loss_kpt: 83.934265 acc_pose: 0.837165 loss: 83.934265 2022/10/12 20:57:02 - mmengine - INFO - Epoch(train) [172][550/586] lr: 5.000000e-04 eta: 1:58:34 time: 0.340650 data_time: 0.051584 memory: 4465 loss_kpt: 85.355349 acc_pose: 0.847384 loss: 85.355349 2022/10/12 20:57:14 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:57:32 - mmengine - INFO - Epoch(train) [173][50/586] lr: 5.000000e-04 eta: 1:58:04 time: 0.357982 data_time: 0.063891 memory: 4465 loss_kpt: 85.530028 acc_pose: 0.828183 loss: 85.530028 2022/10/12 20:57:50 - mmengine - INFO - Epoch(train) [173][100/586] lr: 5.000000e-04 eta: 1:57:49 time: 0.343690 data_time: 0.057846 memory: 4465 loss_kpt: 83.595126 acc_pose: 0.858744 loss: 83.595126 2022/10/12 20:58:06 - mmengine - INFO - Epoch(train) [173][150/586] lr: 5.000000e-04 eta: 1:57:33 time: 0.329258 data_time: 0.053137 memory: 4465 loss_kpt: 84.412185 acc_pose: 0.814596 loss: 84.412185 2022/10/12 20:58:23 - mmengine - INFO - Epoch(train) [173][200/586] lr: 5.000000e-04 eta: 1:57:17 time: 0.344325 data_time: 0.051081 memory: 4465 loss_kpt: 83.753761 acc_pose: 0.799785 loss: 83.753761 2022/10/12 20:58:26 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 20:58:40 - mmengine - INFO - Epoch(train) [173][250/586] lr: 5.000000e-04 eta: 1:57:02 time: 0.340278 data_time: 0.055524 memory: 4465 loss_kpt: 83.871136 acc_pose: 0.817368 loss: 83.871136 2022/10/12 20:58:57 - mmengine - INFO - Epoch(train) [173][300/586] lr: 5.000000e-04 eta: 1:56:46 time: 0.334297 data_time: 0.053771 memory: 4465 loss_kpt: 84.543228 acc_pose: 0.747013 loss: 84.543228 2022/10/12 20:59:14 - mmengine - INFO - Epoch(train) [173][350/586] lr: 5.000000e-04 eta: 1:56:30 time: 0.331743 data_time: 0.055179 memory: 4465 loss_kpt: 83.325903 acc_pose: 0.845603 loss: 83.325903 2022/10/12 20:59:31 - mmengine - INFO - Epoch(train) [173][400/586] lr: 5.000000e-04 eta: 1:56:14 time: 0.337519 data_time: 0.054738 memory: 4465 loss_kpt: 84.985193 acc_pose: 0.864910 loss: 84.985193 2022/10/12 20:59:47 - mmengine - INFO - Epoch(train) [173][450/586] lr: 5.000000e-04 eta: 1:55:58 time: 0.323572 data_time: 0.048976 memory: 4465 loss_kpt: 85.425283 acc_pose: 0.888472 loss: 85.425283 2022/10/12 21:00:03 - mmengine - INFO - Epoch(train) [173][500/586] lr: 5.000000e-04 eta: 1:55:42 time: 0.326734 data_time: 0.056020 memory: 4465 loss_kpt: 85.300757 acc_pose: 0.772944 loss: 85.300757 2022/10/12 21:00:19 - mmengine - INFO - Epoch(train) [173][550/586] lr: 5.000000e-04 eta: 1:55:27 time: 0.321712 data_time: 0.050037 memory: 4465 loss_kpt: 85.495729 acc_pose: 0.851415 loss: 85.495729 2022/10/12 21:00:31 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:00:48 - mmengine - INFO - Epoch(train) [174][50/586] lr: 5.000000e-04 eta: 1:54:57 time: 0.344444 data_time: 0.060993 memory: 4465 loss_kpt: 84.386194 acc_pose: 0.807973 loss: 84.386194 2022/10/12 21:01:04 - mmengine - INFO - Epoch(train) [174][100/586] lr: 5.000000e-04 eta: 1:54:41 time: 0.331207 data_time: 0.047904 memory: 4465 loss_kpt: 85.153499 acc_pose: 0.816715 loss: 85.153499 2022/10/12 21:01:21 - mmengine - INFO - Epoch(train) [174][150/586] lr: 5.000000e-04 eta: 1:54:25 time: 0.330774 data_time: 0.046673 memory: 4465 loss_kpt: 85.493352 acc_pose: 0.934964 loss: 85.493352 2022/10/12 21:01:37 - mmengine - INFO - Epoch(train) [174][200/586] lr: 5.000000e-04 eta: 1:54:09 time: 0.323415 data_time: 0.046901 memory: 4465 loss_kpt: 84.057749 acc_pose: 0.861295 loss: 84.057749 2022/10/12 21:01:53 - mmengine - INFO - Epoch(train) [174][250/586] lr: 5.000000e-04 eta: 1:53:54 time: 0.324045 data_time: 0.048586 memory: 4465 loss_kpt: 85.400079 acc_pose: 0.825886 loss: 85.400079 2022/10/12 21:02:10 - mmengine - INFO - Epoch(train) [174][300/586] lr: 5.000000e-04 eta: 1:53:38 time: 0.324722 data_time: 0.048382 memory: 4465 loss_kpt: 82.757354 acc_pose: 0.860786 loss: 82.757354 2022/10/12 21:02:26 - mmengine - INFO - Epoch(train) [174][350/586] lr: 5.000000e-04 eta: 1:53:22 time: 0.329511 data_time: 0.055569 memory: 4465 loss_kpt: 85.450878 acc_pose: 0.812200 loss: 85.450878 2022/10/12 21:02:42 - mmengine - INFO - Epoch(train) [174][400/586] lr: 5.000000e-04 eta: 1:53:06 time: 0.324328 data_time: 0.052388 memory: 4465 loss_kpt: 84.825358 acc_pose: 0.819415 loss: 84.825358 2022/10/12 21:02:58 - mmengine - INFO - Epoch(train) [174][450/586] lr: 5.000000e-04 eta: 1:52:50 time: 0.320749 data_time: 0.050970 memory: 4465 loss_kpt: 83.711793 acc_pose: 0.862089 loss: 83.711793 2022/10/12 21:03:14 - mmengine - INFO - Epoch(train) [174][500/586] lr: 5.000000e-04 eta: 1:52:34 time: 0.314856 data_time: 0.049217 memory: 4465 loss_kpt: 84.058673 acc_pose: 0.833029 loss: 84.058673 2022/10/12 21:03:30 - mmengine - INFO - Epoch(train) [174][550/586] lr: 5.000000e-04 eta: 1:52:18 time: 0.319185 data_time: 0.049877 memory: 4465 loss_kpt: 84.106215 acc_pose: 0.776390 loss: 84.106215 2022/10/12 21:03:42 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:03:55 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:04:00 - mmengine - INFO - Epoch(train) [175][50/586] lr: 5.000000e-04 eta: 1:51:49 time: 0.365764 data_time: 0.062032 memory: 4465 loss_kpt: 85.517106 acc_pose: 0.896699 loss: 85.517106 2022/10/12 21:04:17 - mmengine - INFO - Epoch(train) [175][100/586] lr: 5.000000e-04 eta: 1:51:33 time: 0.335326 data_time: 0.051603 memory: 4465 loss_kpt: 84.091671 acc_pose: 0.836187 loss: 84.091671 2022/10/12 21:04:34 - mmengine - INFO - Epoch(train) [175][150/586] lr: 5.000000e-04 eta: 1:51:17 time: 0.345855 data_time: 0.055070 memory: 4465 loss_kpt: 84.594516 acc_pose: 0.872194 loss: 84.594516 2022/10/12 21:04:51 - mmengine - INFO - Epoch(train) [175][200/586] lr: 5.000000e-04 eta: 1:51:02 time: 0.335115 data_time: 0.054249 memory: 4465 loss_kpt: 83.421740 acc_pose: 0.764779 loss: 83.421740 2022/10/12 21:05:08 - mmengine - INFO - Epoch(train) [175][250/586] lr: 5.000000e-04 eta: 1:50:46 time: 0.334897 data_time: 0.051836 memory: 4465 loss_kpt: 84.333869 acc_pose: 0.809605 loss: 84.333869 2022/10/12 21:05:24 - mmengine - INFO - Epoch(train) [175][300/586] lr: 5.000000e-04 eta: 1:50:30 time: 0.332656 data_time: 0.052952 memory: 4465 loss_kpt: 84.025022 acc_pose: 0.859147 loss: 84.025022 2022/10/12 21:05:41 - mmengine - INFO - Epoch(train) [175][350/586] lr: 5.000000e-04 eta: 1:50:14 time: 0.336493 data_time: 0.056033 memory: 4465 loss_kpt: 83.936726 acc_pose: 0.844369 loss: 83.936726 2022/10/12 21:05:58 - mmengine - INFO - Epoch(train) [175][400/586] lr: 5.000000e-04 eta: 1:49:58 time: 0.331283 data_time: 0.058118 memory: 4465 loss_kpt: 85.340064 acc_pose: 0.828118 loss: 85.340064 2022/10/12 21:06:14 - mmengine - INFO - Epoch(train) [175][450/586] lr: 5.000000e-04 eta: 1:49:43 time: 0.331955 data_time: 0.056407 memory: 4465 loss_kpt: 84.404428 acc_pose: 0.863454 loss: 84.404428 2022/10/12 21:06:31 - mmengine - INFO - Epoch(train) [175][500/586] lr: 5.000000e-04 eta: 1:49:27 time: 0.332345 data_time: 0.053053 memory: 4465 loss_kpt: 83.833468 acc_pose: 0.838713 loss: 83.833468 2022/10/12 21:06:48 - mmengine - INFO - Epoch(train) [175][550/586] lr: 5.000000e-04 eta: 1:49:11 time: 0.343020 data_time: 0.057511 memory: 4465 loss_kpt: 84.754606 acc_pose: 0.807811 loss: 84.754606 2022/10/12 21:07:00 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:07:18 - mmengine - INFO - Epoch(train) [176][50/586] lr: 5.000000e-04 eta: 1:48:42 time: 0.350119 data_time: 0.058860 memory: 4465 loss_kpt: 84.112707 acc_pose: 0.839990 loss: 84.112707 2022/10/12 21:07:35 - mmengine - INFO - Epoch(train) [176][100/586] lr: 5.000000e-04 eta: 1:48:26 time: 0.349875 data_time: 0.050826 memory: 4465 loss_kpt: 83.858190 acc_pose: 0.861463 loss: 83.858190 2022/10/12 21:07:52 - mmengine - INFO - Epoch(train) [176][150/586] lr: 5.000000e-04 eta: 1:48:10 time: 0.335691 data_time: 0.054468 memory: 4465 loss_kpt: 84.369694 acc_pose: 0.840407 loss: 84.369694 2022/10/12 21:08:09 - mmengine - INFO - Epoch(train) [176][200/586] lr: 5.000000e-04 eta: 1:47:54 time: 0.332571 data_time: 0.053106 memory: 4465 loss_kpt: 83.905705 acc_pose: 0.800812 loss: 83.905705 2022/10/12 21:08:26 - mmengine - INFO - Epoch(train) [176][250/586] lr: 5.000000e-04 eta: 1:47:39 time: 0.337665 data_time: 0.053738 memory: 4465 loss_kpt: 83.943791 acc_pose: 0.892678 loss: 83.943791 2022/10/12 21:08:42 - mmengine - INFO - Epoch(train) [176][300/586] lr: 5.000000e-04 eta: 1:47:23 time: 0.330701 data_time: 0.053797 memory: 4465 loss_kpt: 84.367190 acc_pose: 0.877905 loss: 84.367190 2022/10/12 21:08:59 - mmengine - INFO - Epoch(train) [176][350/586] lr: 5.000000e-04 eta: 1:47:07 time: 0.335464 data_time: 0.053981 memory: 4465 loss_kpt: 86.331066 acc_pose: 0.744229 loss: 86.331066 2022/10/12 21:09:16 - mmengine - INFO - Epoch(train) [176][400/586] lr: 5.000000e-04 eta: 1:46:51 time: 0.341396 data_time: 0.050479 memory: 4465 loss_kpt: 84.889997 acc_pose: 0.798005 loss: 84.889997 2022/10/12 21:09:33 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:09:33 - mmengine - INFO - Epoch(train) [176][450/586] lr: 5.000000e-04 eta: 1:46:36 time: 0.344904 data_time: 0.050501 memory: 4465 loss_kpt: 84.811289 acc_pose: 0.813369 loss: 84.811289 2022/10/12 21:09:51 - mmengine - INFO - Epoch(train) [176][500/586] lr: 5.000000e-04 eta: 1:46:20 time: 0.350312 data_time: 0.051667 memory: 4465 loss_kpt: 84.958441 acc_pose: 0.846557 loss: 84.958441 2022/10/12 21:10:08 - mmengine - INFO - Epoch(train) [176][550/586] lr: 5.000000e-04 eta: 1:46:04 time: 0.351749 data_time: 0.053148 memory: 4465 loss_kpt: 85.022278 acc_pose: 0.791589 loss: 85.022278 2022/10/12 21:10:21 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:10:38 - mmengine - INFO - Epoch(train) [177][50/586] lr: 5.000000e-04 eta: 1:45:35 time: 0.345940 data_time: 0.059170 memory: 4465 loss_kpt: 82.974316 acc_pose: 0.846851 loss: 82.974316 2022/10/12 21:10:55 - mmengine - INFO - Epoch(train) [177][100/586] lr: 5.000000e-04 eta: 1:45:19 time: 0.344997 data_time: 0.056532 memory: 4465 loss_kpt: 84.083854 acc_pose: 0.827205 loss: 84.083854 2022/10/12 21:11:13 - mmengine - INFO - Epoch(train) [177][150/586] lr: 5.000000e-04 eta: 1:45:04 time: 0.353001 data_time: 0.055722 memory: 4465 loss_kpt: 86.245091 acc_pose: 0.891759 loss: 86.245091 2022/10/12 21:11:31 - mmengine - INFO - Epoch(train) [177][200/586] lr: 5.000000e-04 eta: 1:44:48 time: 0.354333 data_time: 0.052254 memory: 4465 loss_kpt: 84.090116 acc_pose: 0.865264 loss: 84.090116 2022/10/12 21:11:48 - mmengine - INFO - Epoch(train) [177][250/586] lr: 5.000000e-04 eta: 1:44:33 time: 0.349626 data_time: 0.051413 memory: 4465 loss_kpt: 82.694771 acc_pose: 0.853741 loss: 82.694771 2022/10/12 21:12:05 - mmengine - INFO - Epoch(train) [177][300/586] lr: 5.000000e-04 eta: 1:44:17 time: 0.334871 data_time: 0.048647 memory: 4465 loss_kpt: 85.440129 acc_pose: 0.777092 loss: 85.440129 2022/10/12 21:12:22 - mmengine - INFO - Epoch(train) [177][350/586] lr: 5.000000e-04 eta: 1:44:01 time: 0.345873 data_time: 0.051123 memory: 4465 loss_kpt: 83.734400 acc_pose: 0.881168 loss: 83.734400 2022/10/12 21:12:39 - mmengine - INFO - Epoch(train) [177][400/586] lr: 5.000000e-04 eta: 1:43:45 time: 0.335144 data_time: 0.045161 memory: 4465 loss_kpt: 83.543238 acc_pose: 0.836710 loss: 83.543238 2022/10/12 21:12:56 - mmengine - INFO - Epoch(train) [177][450/586] lr: 5.000000e-04 eta: 1:43:29 time: 0.337251 data_time: 0.047915 memory: 4465 loss_kpt: 84.105704 acc_pose: 0.831637 loss: 84.105704 2022/10/12 21:13:13 - mmengine - INFO - Epoch(train) [177][500/586] lr: 5.000000e-04 eta: 1:43:14 time: 0.339144 data_time: 0.046360 memory: 4465 loss_kpt: 83.600264 acc_pose: 0.882263 loss: 83.600264 2022/10/12 21:13:30 - mmengine - INFO - Epoch(train) [177][550/586] lr: 5.000000e-04 eta: 1:42:58 time: 0.337764 data_time: 0.049914 memory: 4465 loss_kpt: 84.654154 acc_pose: 0.831876 loss: 84.654154 2022/10/12 21:13:42 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:14:00 - mmengine - INFO - Epoch(train) [178][50/586] lr: 5.000000e-04 eta: 1:42:29 time: 0.351455 data_time: 0.064042 memory: 4465 loss_kpt: 84.019845 acc_pose: 0.877407 loss: 84.019845 2022/10/12 21:14:17 - mmengine - INFO - Epoch(train) [178][100/586] lr: 5.000000e-04 eta: 1:42:13 time: 0.346684 data_time: 0.051717 memory: 4465 loss_kpt: 84.939754 acc_pose: 0.836073 loss: 84.939754 2022/10/12 21:14:34 - mmengine - INFO - Epoch(train) [178][150/586] lr: 5.000000e-04 eta: 1:41:57 time: 0.334921 data_time: 0.054150 memory: 4465 loss_kpt: 86.158512 acc_pose: 0.857608 loss: 86.158512 2022/10/12 21:14:50 - mmengine - INFO - Epoch(train) [178][200/586] lr: 5.000000e-04 eta: 1:41:41 time: 0.333906 data_time: 0.046895 memory: 4465 loss_kpt: 84.065362 acc_pose: 0.829784 loss: 84.065362 2022/10/12 21:15:08 - mmengine - INFO - Epoch(train) [178][250/586] lr: 5.000000e-04 eta: 1:41:26 time: 0.354338 data_time: 0.055306 memory: 4465 loss_kpt: 86.403048 acc_pose: 0.808772 loss: 86.403048 2022/10/12 21:15:18 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:15:25 - mmengine - INFO - Epoch(train) [178][300/586] lr: 5.000000e-04 eta: 1:41:10 time: 0.342390 data_time: 0.051209 memory: 4465 loss_kpt: 85.290411 acc_pose: 0.841865 loss: 85.290411 2022/10/12 21:15:42 - mmengine - INFO - Epoch(train) [178][350/586] lr: 5.000000e-04 eta: 1:40:54 time: 0.333927 data_time: 0.052896 memory: 4465 loss_kpt: 83.357789 acc_pose: 0.824339 loss: 83.357789 2022/10/12 21:15:58 - mmengine - INFO - Epoch(train) [178][400/586] lr: 5.000000e-04 eta: 1:40:38 time: 0.327343 data_time: 0.045967 memory: 4465 loss_kpt: 83.793127 acc_pose: 0.833896 loss: 83.793127 2022/10/12 21:16:15 - mmengine - INFO - Epoch(train) [178][450/586] lr: 5.000000e-04 eta: 1:40:23 time: 0.331358 data_time: 0.050084 memory: 4465 loss_kpt: 84.952144 acc_pose: 0.780193 loss: 84.952144 2022/10/12 21:16:32 - mmengine - INFO - Epoch(train) [178][500/586] lr: 5.000000e-04 eta: 1:40:07 time: 0.332593 data_time: 0.049926 memory: 4465 loss_kpt: 84.702481 acc_pose: 0.831354 loss: 84.702481 2022/10/12 21:16:48 - mmengine - INFO - Epoch(train) [178][550/586] lr: 5.000000e-04 eta: 1:39:51 time: 0.325657 data_time: 0.051068 memory: 4465 loss_kpt: 82.491932 acc_pose: 0.859777 loss: 82.491932 2022/10/12 21:17:00 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:17:17 - mmengine - INFO - Epoch(train) [179][50/586] lr: 5.000000e-04 eta: 1:39:22 time: 0.347823 data_time: 0.059862 memory: 4465 loss_kpt: 84.225286 acc_pose: 0.850482 loss: 84.225286 2022/10/12 21:17:34 - mmengine - INFO - Epoch(train) [179][100/586] lr: 5.000000e-04 eta: 1:39:06 time: 0.336117 data_time: 0.052752 memory: 4465 loss_kpt: 83.946076 acc_pose: 0.758538 loss: 83.946076 2022/10/12 21:17:51 - mmengine - INFO - Epoch(train) [179][150/586] lr: 5.000000e-04 eta: 1:38:50 time: 0.344264 data_time: 0.048757 memory: 4465 loss_kpt: 84.525385 acc_pose: 0.883417 loss: 84.525385 2022/10/12 21:18:08 - mmengine - INFO - Epoch(train) [179][200/586] lr: 5.000000e-04 eta: 1:38:34 time: 0.327662 data_time: 0.046309 memory: 4465 loss_kpt: 83.846864 acc_pose: 0.818872 loss: 83.846864 2022/10/12 21:18:25 - mmengine - INFO - Epoch(train) [179][250/586] lr: 5.000000e-04 eta: 1:38:19 time: 0.348735 data_time: 0.050824 memory: 4465 loss_kpt: 82.541940 acc_pose: 0.766188 loss: 82.541940 2022/10/12 21:18:42 - mmengine - INFO - Epoch(train) [179][300/586] lr: 5.000000e-04 eta: 1:38:03 time: 0.333438 data_time: 0.048454 memory: 4465 loss_kpt: 83.013094 acc_pose: 0.908286 loss: 83.013094 2022/10/12 21:18:59 - mmengine - INFO - Epoch(train) [179][350/586] lr: 5.000000e-04 eta: 1:37:47 time: 0.341296 data_time: 0.046957 memory: 4465 loss_kpt: 83.248363 acc_pose: 0.794571 loss: 83.248363 2022/10/12 21:19:16 - mmengine - INFO - Epoch(train) [179][400/586] lr: 5.000000e-04 eta: 1:37:31 time: 0.335512 data_time: 0.049294 memory: 4465 loss_kpt: 84.558495 acc_pose: 0.783379 loss: 84.558495 2022/10/12 21:19:32 - mmengine - INFO - Epoch(train) [179][450/586] lr: 5.000000e-04 eta: 1:37:15 time: 0.335392 data_time: 0.049733 memory: 4465 loss_kpt: 84.854691 acc_pose: 0.753134 loss: 84.854691 2022/10/12 21:19:49 - mmengine - INFO - Epoch(train) [179][500/586] lr: 5.000000e-04 eta: 1:37:00 time: 0.333334 data_time: 0.046797 memory: 4465 loss_kpt: 83.813143 acc_pose: 0.781085 loss: 83.813143 2022/10/12 21:20:06 - mmengine - INFO - Epoch(train) [179][550/586] lr: 5.000000e-04 eta: 1:36:44 time: 0.344252 data_time: 0.050324 memory: 4465 loss_kpt: 83.844446 acc_pose: 0.862272 loss: 83.844446 2022/10/12 21:20:18 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:20:36 - mmengine - INFO - Epoch(train) [180][50/586] lr: 5.000000e-04 eta: 1:36:15 time: 0.356138 data_time: 0.060019 memory: 4465 loss_kpt: 83.544611 acc_pose: 0.839558 loss: 83.544611 2022/10/12 21:20:53 - mmengine - INFO - Epoch(train) [180][100/586] lr: 5.000000e-04 eta: 1:35:59 time: 0.341337 data_time: 0.050829 memory: 4465 loss_kpt: 84.181657 acc_pose: 0.773536 loss: 84.181657 2022/10/12 21:20:55 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:21:10 - mmengine - INFO - Epoch(train) [180][150/586] lr: 5.000000e-04 eta: 1:35:43 time: 0.334927 data_time: 0.047844 memory: 4465 loss_kpt: 84.417384 acc_pose: 0.882683 loss: 84.417384 2022/10/12 21:21:26 - mmengine - INFO - Epoch(train) [180][200/586] lr: 5.000000e-04 eta: 1:35:27 time: 0.333418 data_time: 0.048043 memory: 4465 loss_kpt: 83.468739 acc_pose: 0.816205 loss: 83.468739 2022/10/12 21:21:43 - mmengine - INFO - Epoch(train) [180][250/586] lr: 5.000000e-04 eta: 1:35:12 time: 0.330586 data_time: 0.046624 memory: 4465 loss_kpt: 84.258241 acc_pose: 0.873603 loss: 84.258241 2022/10/12 21:21:59 - mmengine - INFO - Epoch(train) [180][300/586] lr: 5.000000e-04 eta: 1:34:56 time: 0.325859 data_time: 0.049720 memory: 4465 loss_kpt: 82.340286 acc_pose: 0.852548 loss: 82.340286 2022/10/12 21:22:16 - mmengine - INFO - Epoch(train) [180][350/586] lr: 5.000000e-04 eta: 1:34:40 time: 0.334048 data_time: 0.048224 memory: 4465 loss_kpt: 86.226421 acc_pose: 0.825844 loss: 86.226421 2022/10/12 21:22:33 - mmengine - INFO - Epoch(train) [180][400/586] lr: 5.000000e-04 eta: 1:34:24 time: 0.341801 data_time: 0.049242 memory: 4465 loss_kpt: 84.702511 acc_pose: 0.838700 loss: 84.702511 2022/10/12 21:22:50 - mmengine - INFO - Epoch(train) [180][450/586] lr: 5.000000e-04 eta: 1:34:08 time: 0.344505 data_time: 0.051535 memory: 4465 loss_kpt: 83.529448 acc_pose: 0.846351 loss: 83.529448 2022/10/12 21:23:07 - mmengine - INFO - Epoch(train) [180][500/586] lr: 5.000000e-04 eta: 1:33:53 time: 0.333559 data_time: 0.049728 memory: 4465 loss_kpt: 84.379888 acc_pose: 0.853589 loss: 84.379888 2022/10/12 21:23:24 - mmengine - INFO - Epoch(train) [180][550/586] lr: 5.000000e-04 eta: 1:33:37 time: 0.340737 data_time: 0.051429 memory: 4465 loss_kpt: 84.091625 acc_pose: 0.753055 loss: 84.091625 2022/10/12 21:23:36 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:23:36 - mmengine - INFO - Saving checkpoint at 180 epochs 2022/10/12 21:23:45 - mmengine - INFO - Epoch(val) [180][50/407] eta: 0:00:47 time: 0.131961 data_time: 0.012698 memory: 4465 2022/10/12 21:23:51 - mmengine - INFO - Epoch(val) [180][100/407] eta: 0:00:39 time: 0.128174 data_time: 0.008252 memory: 1026 2022/10/12 21:23:58 - mmengine - INFO - Epoch(val) [180][150/407] eta: 0:00:32 time: 0.127997 data_time: 0.008233 memory: 1026 2022/10/12 21:24:04 - mmengine - INFO - Epoch(val) [180][200/407] eta: 0:00:26 time: 0.127919 data_time: 0.008357 memory: 1026 2022/10/12 21:24:10 - mmengine - INFO - Epoch(val) [180][250/407] eta: 0:00:19 time: 0.125651 data_time: 0.008077 memory: 1026 2022/10/12 21:24:17 - mmengine - INFO - Epoch(val) [180][300/407] eta: 0:00:13 time: 0.126642 data_time: 0.008121 memory: 1026 2022/10/12 21:24:23 - mmengine - INFO - Epoch(val) [180][350/407] eta: 0:00:07 time: 0.126329 data_time: 0.008028 memory: 1026 2022/10/12 21:24:29 - mmengine - INFO - Epoch(val) [180][400/407] eta: 0:00:00 time: 0.128815 data_time: 0.007643 memory: 1026 2022/10/12 21:24:43 - mmengine - INFO - Evaluating CocoMetric... 2022/10/12 21:24:59 - mmengine - INFO - Epoch(val) [180][407/407] coco/AP: 0.720857 coco/AP .5: 0.893091 coco/AP .75: 0.793531 coco/AP (M): 0.688124 coco/AP (L): 0.782603 coco/AR: 0.786524 coco/AR .5: 0.933092 coco/AR .75: 0.847292 coco/AR (M): 0.742502 coco/AR (L): 0.847566 2022/10/12 21:24:59 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/liqikai/openmmlab/pt112cu113py38/mmpose/work_dirs/20221012/rsn50/best_coco/AP_epoch_160.pth is removed 2022/10/12 21:25:00 - mmengine - INFO - The best checkpoint with 0.7209 coco/AP at 180 epoch is saved to best_coco/AP_epoch_180.pth. 2022/10/12 21:25:18 - mmengine - INFO - Epoch(train) [181][50/586] lr: 5.000000e-04 eta: 1:33:08 time: 0.350418 data_time: 0.057526 memory: 4465 loss_kpt: 83.865703 acc_pose: 0.858740 loss: 83.865703 2022/10/12 21:25:34 - mmengine - INFO - Epoch(train) [181][100/586] lr: 5.000000e-04 eta: 1:32:52 time: 0.322310 data_time: 0.050181 memory: 4465 loss_kpt: 83.853468 acc_pose: 0.765973 loss: 83.853468 2022/10/12 21:25:50 - mmengine - INFO - Epoch(train) [181][150/586] lr: 5.000000e-04 eta: 1:32:36 time: 0.321324 data_time: 0.046804 memory: 4465 loss_kpt: 85.202075 acc_pose: 0.842757 loss: 85.202075 2022/10/12 21:26:06 - mmengine - INFO - Epoch(train) [181][200/586] lr: 5.000000e-04 eta: 1:32:20 time: 0.323541 data_time: 0.050282 memory: 4465 loss_kpt: 84.354402 acc_pose: 0.822682 loss: 84.354402 2022/10/12 21:26:23 - mmengine - INFO - Epoch(train) [181][250/586] lr: 5.000000e-04 eta: 1:32:04 time: 0.331944 data_time: 0.048356 memory: 4465 loss_kpt: 85.296351 acc_pose: 0.842143 loss: 85.296351 2022/10/12 21:26:39 - mmengine - INFO - Epoch(train) [181][300/586] lr: 5.000000e-04 eta: 1:31:48 time: 0.320825 data_time: 0.046730 memory: 4465 loss_kpt: 84.343104 acc_pose: 0.807339 loss: 84.343104 2022/10/12 21:26:55 - mmengine - INFO - Epoch(train) [181][350/586] lr: 5.000000e-04 eta: 1:31:32 time: 0.325808 data_time: 0.050076 memory: 4465 loss_kpt: 84.746293 acc_pose: 0.753175 loss: 84.746293 2022/10/12 21:27:11 - mmengine - INFO - Epoch(train) [181][400/586] lr: 5.000000e-04 eta: 1:31:17 time: 0.320874 data_time: 0.050503 memory: 4465 loss_kpt: 84.065157 acc_pose: 0.772490 loss: 84.065157 2022/10/12 21:27:28 - mmengine - INFO - Epoch(train) [181][450/586] lr: 5.000000e-04 eta: 1:31:01 time: 0.323873 data_time: 0.047370 memory: 4465 loss_kpt: 83.147213 acc_pose: 0.834072 loss: 83.147213 2022/10/12 21:27:44 - mmengine - INFO - Epoch(train) [181][500/586] lr: 5.000000e-04 eta: 1:30:45 time: 0.320794 data_time: 0.049304 memory: 4465 loss_kpt: 83.005455 acc_pose: 0.804919 loss: 83.005455 2022/10/12 21:27:50 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:28:00 - mmengine - INFO - Epoch(train) [181][550/586] lr: 5.000000e-04 eta: 1:30:29 time: 0.323428 data_time: 0.045211 memory: 4465 loss_kpt: 84.233795 acc_pose: 0.894374 loss: 84.233795 2022/10/12 21:28:11 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:28:29 - mmengine - INFO - Epoch(train) [182][50/586] lr: 5.000000e-04 eta: 1:30:00 time: 0.349033 data_time: 0.063543 memory: 4465 loss_kpt: 84.809464 acc_pose: 0.801034 loss: 84.809464 2022/10/12 21:28:46 - mmengine - INFO - Epoch(train) [182][100/586] lr: 5.000000e-04 eta: 1:29:44 time: 0.341647 data_time: 0.052707 memory: 4465 loss_kpt: 84.674344 acc_pose: 0.825221 loss: 84.674344 2022/10/12 21:29:03 - mmengine - INFO - Epoch(train) [182][150/586] lr: 5.000000e-04 eta: 1:29:28 time: 0.335991 data_time: 0.048837 memory: 4465 loss_kpt: 84.386084 acc_pose: 0.842127 loss: 84.386084 2022/10/12 21:29:19 - mmengine - INFO - Epoch(train) [182][200/586] lr: 5.000000e-04 eta: 1:29:12 time: 0.330046 data_time: 0.054755 memory: 4465 loss_kpt: 84.041107 acc_pose: 0.876328 loss: 84.041107 2022/10/12 21:29:36 - mmengine - INFO - Epoch(train) [182][250/586] lr: 5.000000e-04 eta: 1:28:57 time: 0.330154 data_time: 0.050937 memory: 4465 loss_kpt: 84.033703 acc_pose: 0.845412 loss: 84.033703 2022/10/12 21:29:53 - mmengine - INFO - Epoch(train) [182][300/586] lr: 5.000000e-04 eta: 1:28:41 time: 0.352713 data_time: 0.046241 memory: 4465 loss_kpt: 82.335374 acc_pose: 0.778784 loss: 82.335374 2022/10/12 21:30:11 - mmengine - INFO - Epoch(train) [182][350/586] lr: 5.000000e-04 eta: 1:28:25 time: 0.350964 data_time: 0.050592 memory: 4465 loss_kpt: 83.605972 acc_pose: 0.883900 loss: 83.605972 2022/10/12 21:30:28 - mmengine - INFO - Epoch(train) [182][400/586] lr: 5.000000e-04 eta: 1:28:09 time: 0.347057 data_time: 0.045825 memory: 4465 loss_kpt: 84.740595 acc_pose: 0.856798 loss: 84.740595 2022/10/12 21:30:46 - mmengine - INFO - Epoch(train) [182][450/586] lr: 5.000000e-04 eta: 1:27:54 time: 0.343983 data_time: 0.048223 memory: 4465 loss_kpt: 83.838181 acc_pose: 0.894164 loss: 83.838181 2022/10/12 21:31:03 - mmengine - INFO - Epoch(train) [182][500/586] lr: 5.000000e-04 eta: 1:27:38 time: 0.340577 data_time: 0.051706 memory: 4465 loss_kpt: 84.481321 acc_pose: 0.784595 loss: 84.481321 2022/10/12 21:31:19 - mmengine - INFO - Epoch(train) [182][550/586] lr: 5.000000e-04 eta: 1:27:22 time: 0.335553 data_time: 0.047680 memory: 4465 loss_kpt: 82.480503 acc_pose: 0.811748 loss: 82.480503 2022/10/12 21:31:31 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:31:49 - mmengine - INFO - Epoch(train) [183][50/586] lr: 5.000000e-04 eta: 1:26:53 time: 0.354558 data_time: 0.054291 memory: 4465 loss_kpt: 83.623429 acc_pose: 0.848656 loss: 83.623429 2022/10/12 21:32:07 - mmengine - INFO - Epoch(train) [183][100/586] lr: 5.000000e-04 eta: 1:26:37 time: 0.346032 data_time: 0.051399 memory: 4465 loss_kpt: 84.897611 acc_pose: 0.842741 loss: 84.897611 2022/10/12 21:32:24 - mmengine - INFO - Epoch(train) [183][150/586] lr: 5.000000e-04 eta: 1:26:22 time: 0.344145 data_time: 0.052182 memory: 4465 loss_kpt: 82.145406 acc_pose: 0.854606 loss: 82.145406 2022/10/12 21:32:41 - mmengine - INFO - Epoch(train) [183][200/586] lr: 5.000000e-04 eta: 1:26:06 time: 0.338333 data_time: 0.050079 memory: 4465 loss_kpt: 84.812113 acc_pose: 0.883672 loss: 84.812113 2022/10/12 21:32:57 - mmengine - INFO - Epoch(train) [183][250/586] lr: 5.000000e-04 eta: 1:25:50 time: 0.327786 data_time: 0.052152 memory: 4465 loss_kpt: 84.337066 acc_pose: 0.818513 loss: 84.337066 2022/10/12 21:33:14 - mmengine - INFO - Epoch(train) [183][300/586] lr: 5.000000e-04 eta: 1:25:34 time: 0.332851 data_time: 0.050888 memory: 4465 loss_kpt: 82.921873 acc_pose: 0.835599 loss: 82.921873 2022/10/12 21:33:30 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:33:30 - mmengine - INFO - Epoch(train) [183][350/586] lr: 5.000000e-04 eta: 1:25:18 time: 0.332982 data_time: 0.047751 memory: 4465 loss_kpt: 83.458175 acc_pose: 0.830723 loss: 83.458175 2022/10/12 21:33:48 - mmengine - INFO - Epoch(train) [183][400/586] lr: 5.000000e-04 eta: 1:25:03 time: 0.340853 data_time: 0.054669 memory: 4465 loss_kpt: 82.623002 acc_pose: 0.792458 loss: 82.623002 2022/10/12 21:34:05 - mmengine - INFO - Epoch(train) [183][450/586] lr: 5.000000e-04 eta: 1:24:47 time: 0.343496 data_time: 0.054625 memory: 4465 loss_kpt: 84.653034 acc_pose: 0.805086 loss: 84.653034 2022/10/12 21:34:22 - mmengine - INFO - Epoch(train) [183][500/586] lr: 5.000000e-04 eta: 1:24:31 time: 0.341695 data_time: 0.046741 memory: 4465 loss_kpt: 83.502323 acc_pose: 0.820939 loss: 83.502323 2022/10/12 21:34:39 - mmengine - INFO - Epoch(train) [183][550/586] lr: 5.000000e-04 eta: 1:24:15 time: 0.344693 data_time: 0.048496 memory: 4465 loss_kpt: 83.015944 acc_pose: 0.873984 loss: 83.015944 2022/10/12 21:34:51 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:35:09 - mmengine - INFO - Epoch(train) [184][50/586] lr: 5.000000e-04 eta: 1:23:46 time: 0.348644 data_time: 0.058369 memory: 4465 loss_kpt: 82.974545 acc_pose: 0.848872 loss: 82.974545 2022/10/12 21:35:25 - mmengine - INFO - Epoch(train) [184][100/586] lr: 5.000000e-04 eta: 1:23:31 time: 0.331620 data_time: 0.047620 memory: 4465 loss_kpt: 83.093167 acc_pose: 0.869298 loss: 83.093167 2022/10/12 21:35:42 - mmengine - INFO - Epoch(train) [184][150/586] lr: 5.000000e-04 eta: 1:23:15 time: 0.341193 data_time: 0.050907 memory: 4465 loss_kpt: 83.245185 acc_pose: 0.770225 loss: 83.245185 2022/10/12 21:35:59 - mmengine - INFO - Epoch(train) [184][200/586] lr: 5.000000e-04 eta: 1:22:59 time: 0.337453 data_time: 0.045674 memory: 4465 loss_kpt: 83.897582 acc_pose: 0.825390 loss: 83.897582 2022/10/12 21:36:16 - mmengine - INFO - Epoch(train) [184][250/586] lr: 5.000000e-04 eta: 1:22:43 time: 0.338039 data_time: 0.050064 memory: 4465 loss_kpt: 84.330487 acc_pose: 0.871659 loss: 84.330487 2022/10/12 21:36:33 - mmengine - INFO - Epoch(train) [184][300/586] lr: 5.000000e-04 eta: 1:22:27 time: 0.335533 data_time: 0.050444 memory: 4465 loss_kpt: 83.606688 acc_pose: 0.841014 loss: 83.606688 2022/10/12 21:36:50 - mmengine - INFO - Epoch(train) [184][350/586] lr: 5.000000e-04 eta: 1:22:12 time: 0.347589 data_time: 0.052297 memory: 4465 loss_kpt: 85.050510 acc_pose: 0.817103 loss: 85.050510 2022/10/12 21:37:07 - mmengine - INFO - Epoch(train) [184][400/586] lr: 5.000000e-04 eta: 1:21:56 time: 0.339271 data_time: 0.045626 memory: 4465 loss_kpt: 84.155630 acc_pose: 0.869883 loss: 84.155630 2022/10/12 21:37:24 - mmengine - INFO - Epoch(train) [184][450/586] lr: 5.000000e-04 eta: 1:21:40 time: 0.338381 data_time: 0.051544 memory: 4465 loss_kpt: 83.959651 acc_pose: 0.820437 loss: 83.959651 2022/10/12 21:37:41 - mmengine - INFO - Epoch(train) [184][500/586] lr: 5.000000e-04 eta: 1:21:24 time: 0.330397 data_time: 0.050292 memory: 4465 loss_kpt: 84.131661 acc_pose: 0.862245 loss: 84.131661 2022/10/12 21:37:58 - mmengine - INFO - Epoch(train) [184][550/586] lr: 5.000000e-04 eta: 1:21:08 time: 0.335232 data_time: 0.051452 memory: 4465 loss_kpt: 83.500716 acc_pose: 0.803001 loss: 83.500716 2022/10/12 21:38:09 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:38:26 - mmengine - INFO - Epoch(train) [185][50/586] lr: 5.000000e-04 eta: 1:20:40 time: 0.343951 data_time: 0.058089 memory: 4465 loss_kpt: 84.603884 acc_pose: 0.765857 loss: 84.603884 2022/10/12 21:38:43 - mmengine - INFO - Epoch(train) [185][100/586] lr: 5.000000e-04 eta: 1:20:24 time: 0.335769 data_time: 0.053861 memory: 4465 loss_kpt: 84.703730 acc_pose: 0.833079 loss: 84.703730 2022/10/12 21:39:01 - mmengine - INFO - Epoch(train) [185][150/586] lr: 5.000000e-04 eta: 1:20:08 time: 0.355806 data_time: 0.054351 memory: 4465 loss_kpt: 84.887188 acc_pose: 0.867658 loss: 84.887188 2022/10/12 21:39:10 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:39:18 - mmengine - INFO - Epoch(train) [185][200/586] lr: 5.000000e-04 eta: 1:19:52 time: 0.345722 data_time: 0.053700 memory: 4465 loss_kpt: 83.363935 acc_pose: 0.672936 loss: 83.363935 2022/10/12 21:39:36 - mmengine - INFO - Epoch(train) [185][250/586] lr: 5.000000e-04 eta: 1:19:37 time: 0.347561 data_time: 0.051639 memory: 4465 loss_kpt: 83.093154 acc_pose: 0.809190 loss: 83.093154 2022/10/12 21:39:53 - mmengine - INFO - Epoch(train) [185][300/586] lr: 5.000000e-04 eta: 1:19:21 time: 0.347000 data_time: 0.051292 memory: 4465 loss_kpt: 82.633642 acc_pose: 0.854810 loss: 82.633642 2022/10/12 21:40:10 - mmengine - INFO - Epoch(train) [185][350/586] lr: 5.000000e-04 eta: 1:19:05 time: 0.346062 data_time: 0.053002 memory: 4465 loss_kpt: 84.365466 acc_pose: 0.812490 loss: 84.365466 2022/10/12 21:40:28 - mmengine - INFO - Epoch(train) [185][400/586] lr: 5.000000e-04 eta: 1:18:49 time: 0.348003 data_time: 0.052836 memory: 4465 loss_kpt: 83.535945 acc_pose: 0.870089 loss: 83.535945 2022/10/12 21:40:45 - mmengine - INFO - Epoch(train) [185][450/586] lr: 5.000000e-04 eta: 1:18:34 time: 0.344485 data_time: 0.050602 memory: 4465 loss_kpt: 83.886703 acc_pose: 0.822916 loss: 83.886703 2022/10/12 21:41:02 - mmengine - INFO - Epoch(train) [185][500/586] lr: 5.000000e-04 eta: 1:18:18 time: 0.343677 data_time: 0.052959 memory: 4465 loss_kpt: 83.912762 acc_pose: 0.814259 loss: 83.912762 2022/10/12 21:41:20 - mmengine - INFO - Epoch(train) [185][550/586] lr: 5.000000e-04 eta: 1:18:02 time: 0.355484 data_time: 0.055522 memory: 4465 loss_kpt: 82.925660 acc_pose: 0.837087 loss: 82.925660 2022/10/12 21:41:32 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:41:49 - mmengine - INFO - Epoch(train) [186][50/586] lr: 5.000000e-04 eta: 1:17:33 time: 0.353113 data_time: 0.058513 memory: 4465 loss_kpt: 84.136327 acc_pose: 0.850544 loss: 84.136327 2022/10/12 21:42:06 - mmengine - INFO - Epoch(train) [186][100/586] lr: 5.000000e-04 eta: 1:17:18 time: 0.337926 data_time: 0.050066 memory: 4465 loss_kpt: 84.046632 acc_pose: 0.883412 loss: 84.046632 2022/10/12 21:42:24 - mmengine - INFO - Epoch(train) [186][150/586] lr: 5.000000e-04 eta: 1:17:02 time: 0.346359 data_time: 0.051290 memory: 4465 loss_kpt: 83.482038 acc_pose: 0.739199 loss: 83.482038 2022/10/12 21:42:41 - mmengine - INFO - Epoch(train) [186][200/586] lr: 5.000000e-04 eta: 1:16:46 time: 0.349942 data_time: 0.046755 memory: 4465 loss_kpt: 83.961417 acc_pose: 0.863733 loss: 83.961417 2022/10/12 21:42:58 - mmengine - INFO - Epoch(train) [186][250/586] lr: 5.000000e-04 eta: 1:16:30 time: 0.346721 data_time: 0.052521 memory: 4465 loss_kpt: 84.013015 acc_pose: 0.826551 loss: 84.013015 2022/10/12 21:43:15 - mmengine - INFO - Epoch(train) [186][300/586] lr: 5.000000e-04 eta: 1:16:15 time: 0.337805 data_time: 0.047536 memory: 4465 loss_kpt: 83.135617 acc_pose: 0.836447 loss: 83.135617 2022/10/12 21:43:32 - mmengine - INFO - Epoch(train) [186][350/586] lr: 5.000000e-04 eta: 1:15:59 time: 0.338353 data_time: 0.047875 memory: 4465 loss_kpt: 82.001821 acc_pose: 0.912605 loss: 82.001821 2022/10/12 21:43:49 - mmengine - INFO - Epoch(train) [186][400/586] lr: 5.000000e-04 eta: 1:15:43 time: 0.330497 data_time: 0.047914 memory: 4465 loss_kpt: 85.702216 acc_pose: 0.870312 loss: 85.702216 2022/10/12 21:44:06 - mmengine - INFO - Epoch(train) [186][450/586] lr: 5.000000e-04 eta: 1:15:27 time: 0.337950 data_time: 0.051778 memory: 4465 loss_kpt: 83.584401 acc_pose: 0.833841 loss: 83.584401 2022/10/12 21:44:23 - mmengine - INFO - Epoch(train) [186][500/586] lr: 5.000000e-04 eta: 1:15:11 time: 0.343095 data_time: 0.047396 memory: 4465 loss_kpt: 82.494348 acc_pose: 0.744367 loss: 82.494348 2022/10/12 21:44:40 - mmengine - INFO - Epoch(train) [186][550/586] lr: 5.000000e-04 eta: 1:14:56 time: 0.347013 data_time: 0.048842 memory: 4465 loss_kpt: 83.515773 acc_pose: 0.837890 loss: 83.515773 2022/10/12 21:44:52 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:44:54 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:45:11 - mmengine - INFO - Epoch(train) [187][50/586] lr: 5.000000e-04 eta: 1:14:27 time: 0.364580 data_time: 0.063351 memory: 4465 loss_kpt: 82.330884 acc_pose: 0.891637 loss: 82.330884 2022/10/12 21:45:27 - mmengine - INFO - Epoch(train) [187][100/586] lr: 5.000000e-04 eta: 1:14:11 time: 0.336426 data_time: 0.049605 memory: 4465 loss_kpt: 83.782031 acc_pose: 0.842638 loss: 83.782031 2022/10/12 21:45:45 - mmengine - INFO - Epoch(train) [187][150/586] lr: 5.000000e-04 eta: 1:13:55 time: 0.343852 data_time: 0.051340 memory: 4465 loss_kpt: 83.563665 acc_pose: 0.834543 loss: 83.563665 2022/10/12 21:46:02 - mmengine - INFO - Epoch(train) [187][200/586] lr: 5.000000e-04 eta: 1:13:39 time: 0.339295 data_time: 0.049948 memory: 4465 loss_kpt: 83.842324 acc_pose: 0.824352 loss: 83.842324 2022/10/12 21:46:19 - mmengine - INFO - Epoch(train) [187][250/586] lr: 5.000000e-04 eta: 1:13:24 time: 0.351766 data_time: 0.054472 memory: 4465 loss_kpt: 83.838354 acc_pose: 0.797129 loss: 83.838354 2022/10/12 21:46:36 - mmengine - INFO - Epoch(train) [187][300/586] lr: 5.000000e-04 eta: 1:13:08 time: 0.333650 data_time: 0.048483 memory: 4465 loss_kpt: 82.943712 acc_pose: 0.793551 loss: 82.943712 2022/10/12 21:46:53 - mmengine - INFO - Epoch(train) [187][350/586] lr: 5.000000e-04 eta: 1:12:52 time: 0.340799 data_time: 0.050936 memory: 4465 loss_kpt: 84.230257 acc_pose: 0.825678 loss: 84.230257 2022/10/12 21:47:10 - mmengine - INFO - Epoch(train) [187][400/586] lr: 5.000000e-04 eta: 1:12:36 time: 0.335929 data_time: 0.047893 memory: 4465 loss_kpt: 85.509859 acc_pose: 0.793835 loss: 85.509859 2022/10/12 21:47:27 - mmengine - INFO - Epoch(train) [187][450/586] lr: 5.000000e-04 eta: 1:12:20 time: 0.339977 data_time: 0.050767 memory: 4465 loss_kpt: 82.914174 acc_pose: 0.841911 loss: 82.914174 2022/10/12 21:47:44 - mmengine - INFO - Epoch(train) [187][500/586] lr: 5.000000e-04 eta: 1:12:05 time: 0.338226 data_time: 0.048474 memory: 4465 loss_kpt: 83.329837 acc_pose: 0.847737 loss: 83.329837 2022/10/12 21:48:00 - mmengine - INFO - Epoch(train) [187][550/586] lr: 5.000000e-04 eta: 1:11:49 time: 0.332562 data_time: 0.047851 memory: 4465 loss_kpt: 83.509518 acc_pose: 0.794156 loss: 83.509518 2022/10/12 21:48:12 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:48:29 - mmengine - INFO - Epoch(train) [188][50/586] lr: 5.000000e-04 eta: 1:11:20 time: 0.345286 data_time: 0.063191 memory: 4465 loss_kpt: 84.040074 acc_pose: 0.824839 loss: 84.040074 2022/10/12 21:48:46 - mmengine - INFO - Epoch(train) [188][100/586] lr: 5.000000e-04 eta: 1:11:04 time: 0.341494 data_time: 0.052599 memory: 4465 loss_kpt: 83.435972 acc_pose: 0.880458 loss: 83.435972 2022/10/12 21:49:04 - mmengine - INFO - Epoch(train) [188][150/586] lr: 5.000000e-04 eta: 1:10:49 time: 0.358652 data_time: 0.054446 memory: 4465 loss_kpt: 84.670469 acc_pose: 0.816303 loss: 84.670469 2022/10/12 21:49:21 - mmengine - INFO - Epoch(train) [188][200/586] lr: 5.000000e-04 eta: 1:10:33 time: 0.334807 data_time: 0.047037 memory: 4465 loss_kpt: 82.774508 acc_pose: 0.903460 loss: 82.774508 2022/10/12 21:49:37 - mmengine - INFO - Epoch(train) [188][250/586] lr: 5.000000e-04 eta: 1:10:17 time: 0.327461 data_time: 0.049033 memory: 4465 loss_kpt: 84.546515 acc_pose: 0.879962 loss: 84.546515 2022/10/12 21:49:55 - mmengine - INFO - Epoch(train) [188][300/586] lr: 5.000000e-04 eta: 1:10:01 time: 0.350754 data_time: 0.050468 memory: 4465 loss_kpt: 83.803421 acc_pose: 0.821152 loss: 83.803421 2022/10/12 21:50:12 - mmengine - INFO - Epoch(train) [188][350/586] lr: 5.000000e-04 eta: 1:09:45 time: 0.344015 data_time: 0.046644 memory: 4465 loss_kpt: 83.637374 acc_pose: 0.846206 loss: 83.637374 2022/10/12 21:50:29 - mmengine - INFO - Epoch(train) [188][400/586] lr: 5.000000e-04 eta: 1:09:30 time: 0.339853 data_time: 0.049084 memory: 4465 loss_kpt: 83.913706 acc_pose: 0.780179 loss: 83.913706 2022/10/12 21:50:35 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:50:46 - mmengine - INFO - Epoch(train) [188][450/586] lr: 5.000000e-04 eta: 1:09:14 time: 0.338917 data_time: 0.052467 memory: 4465 loss_kpt: 84.305429 acc_pose: 0.874908 loss: 84.305429 2022/10/12 21:51:03 - mmengine - INFO - Epoch(train) [188][500/586] lr: 5.000000e-04 eta: 1:08:58 time: 0.335504 data_time: 0.047104 memory: 4465 loss_kpt: 84.083941 acc_pose: 0.802631 loss: 84.083941 2022/10/12 21:51:20 - mmengine - INFO - Epoch(train) [188][550/586] lr: 5.000000e-04 eta: 1:08:42 time: 0.341175 data_time: 0.052059 memory: 4465 loss_kpt: 82.348518 acc_pose: 0.821733 loss: 82.348518 2022/10/12 21:51:31 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:51:50 - mmengine - INFO - Epoch(train) [189][50/586] lr: 5.000000e-04 eta: 1:08:14 time: 0.363826 data_time: 0.058984 memory: 4465 loss_kpt: 83.844622 acc_pose: 0.825424 loss: 83.844622 2022/10/12 21:52:08 - mmengine - INFO - Epoch(train) [189][100/586] lr: 5.000000e-04 eta: 1:07:58 time: 0.365607 data_time: 0.053985 memory: 4465 loss_kpt: 83.411384 acc_pose: 0.751941 loss: 83.411384 2022/10/12 21:52:26 - mmengine - INFO - Epoch(train) [189][150/586] lr: 5.000000e-04 eta: 1:07:42 time: 0.371744 data_time: 0.050521 memory: 4465 loss_kpt: 84.564298 acc_pose: 0.812223 loss: 84.564298 2022/10/12 21:52:45 - mmengine - INFO - Epoch(train) [189][200/586] lr: 5.000000e-04 eta: 1:07:27 time: 0.374818 data_time: 0.054940 memory: 4465 loss_kpt: 82.611715 acc_pose: 0.840287 loss: 82.611715 2022/10/12 21:53:04 - mmengine - INFO - Epoch(train) [189][250/586] lr: 5.000000e-04 eta: 1:07:11 time: 0.370695 data_time: 0.052591 memory: 4465 loss_kpt: 84.696727 acc_pose: 0.821560 loss: 84.696727 2022/10/12 21:53:21 - mmengine - INFO - Epoch(train) [189][300/586] lr: 5.000000e-04 eta: 1:06:55 time: 0.346512 data_time: 0.049420 memory: 4465 loss_kpt: 82.719100 acc_pose: 0.871657 loss: 82.719100 2022/10/12 21:53:37 - mmengine - INFO - Epoch(train) [189][350/586] lr: 5.000000e-04 eta: 1:06:39 time: 0.325304 data_time: 0.047122 memory: 4465 loss_kpt: 83.487037 acc_pose: 0.850213 loss: 83.487037 2022/10/12 21:53:54 - mmengine - INFO - Epoch(train) [189][400/586] lr: 5.000000e-04 eta: 1:06:23 time: 0.341145 data_time: 0.054254 memory: 4465 loss_kpt: 84.926351 acc_pose: 0.794337 loss: 84.926351 2022/10/12 21:54:11 - mmengine - INFO - Epoch(train) [189][450/586] lr: 5.000000e-04 eta: 1:06:08 time: 0.333289 data_time: 0.046903 memory: 4465 loss_kpt: 84.898958 acc_pose: 0.874002 loss: 84.898958 2022/10/12 21:54:29 - mmengine - INFO - Epoch(train) [189][500/586] lr: 5.000000e-04 eta: 1:05:52 time: 0.355336 data_time: 0.052053 memory: 4465 loss_kpt: 82.151054 acc_pose: 0.865272 loss: 82.151054 2022/10/12 21:54:47 - mmengine - INFO - Epoch(train) [189][550/586] lr: 5.000000e-04 eta: 1:05:36 time: 0.358044 data_time: 0.051193 memory: 4465 loss_kpt: 82.924130 acc_pose: 0.884582 loss: 82.924130 2022/10/12 21:54:59 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:55:17 - mmengine - INFO - Epoch(train) [190][50/586] lr: 5.000000e-04 eta: 1:05:08 time: 0.354359 data_time: 0.070058 memory: 4465 loss_kpt: 82.976310 acc_pose: 0.825861 loss: 82.976310 2022/10/12 21:55:34 - mmengine - INFO - Epoch(train) [190][100/586] lr: 5.000000e-04 eta: 1:04:52 time: 0.333617 data_time: 0.049957 memory: 4465 loss_kpt: 83.512753 acc_pose: 0.774624 loss: 83.512753 2022/10/12 21:55:51 - mmengine - INFO - Epoch(train) [190][150/586] lr: 5.000000e-04 eta: 1:04:36 time: 0.347822 data_time: 0.053440 memory: 4465 loss_kpt: 85.057659 acc_pose: 0.847329 loss: 85.057659 2022/10/12 21:56:08 - mmengine - INFO - Epoch(train) [190][200/586] lr: 5.000000e-04 eta: 1:04:20 time: 0.343499 data_time: 0.050920 memory: 4465 loss_kpt: 84.217384 acc_pose: 0.861120 loss: 84.217384 2022/10/12 21:56:24 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:56:25 - mmengine - INFO - Epoch(train) [190][250/586] lr: 5.000000e-04 eta: 1:04:04 time: 0.340894 data_time: 0.053307 memory: 4465 loss_kpt: 83.223131 acc_pose: 0.845756 loss: 83.223131 2022/10/12 21:56:43 - mmengine - INFO - Epoch(train) [190][300/586] lr: 5.000000e-04 eta: 1:03:49 time: 0.346099 data_time: 0.049665 memory: 4465 loss_kpt: 84.620174 acc_pose: 0.817873 loss: 84.620174 2022/10/12 21:57:00 - mmengine - INFO - Epoch(train) [190][350/586] lr: 5.000000e-04 eta: 1:03:33 time: 0.349772 data_time: 0.050704 memory: 4465 loss_kpt: 83.099739 acc_pose: 0.842558 loss: 83.099739 2022/10/12 21:57:18 - mmengine - INFO - Epoch(train) [190][400/586] lr: 5.000000e-04 eta: 1:03:17 time: 0.345742 data_time: 0.050420 memory: 4465 loss_kpt: 83.723702 acc_pose: 0.827643 loss: 83.723702 2022/10/12 21:57:34 - mmengine - INFO - Epoch(train) [190][450/586] lr: 5.000000e-04 eta: 1:03:01 time: 0.335529 data_time: 0.052187 memory: 4465 loss_kpt: 83.121070 acc_pose: 0.830158 loss: 83.121070 2022/10/12 21:57:51 - mmengine - INFO - Epoch(train) [190][500/586] lr: 5.000000e-04 eta: 1:02:45 time: 0.336500 data_time: 0.050777 memory: 4465 loss_kpt: 84.079823 acc_pose: 0.862783 loss: 84.079823 2022/10/12 21:58:08 - mmengine - INFO - Epoch(train) [190][550/586] lr: 5.000000e-04 eta: 1:02:29 time: 0.328859 data_time: 0.050109 memory: 4465 loss_kpt: 84.357172 acc_pose: 0.803272 loss: 84.357172 2022/10/12 21:58:19 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 21:58:19 - mmengine - INFO - Saving checkpoint at 190 epochs 2022/10/12 21:58:28 - mmengine - INFO - Epoch(val) [190][50/407] eta: 0:00:48 time: 0.135155 data_time: 0.013166 memory: 4465 2022/10/12 21:58:35 - mmengine - INFO - Epoch(val) [190][100/407] eta: 0:00:39 time: 0.127039 data_time: 0.007734 memory: 1026 2022/10/12 21:58:41 - mmengine - INFO - Epoch(val) [190][150/407] eta: 0:00:32 time: 0.127629 data_time: 0.007900 memory: 1026 2022/10/12 21:58:47 - mmengine - INFO - Epoch(val) [190][200/407] eta: 0:00:25 time: 0.124941 data_time: 0.007957 memory: 1026 2022/10/12 21:58:54 - mmengine - INFO - Epoch(val) [190][250/407] eta: 0:00:20 time: 0.128193 data_time: 0.007935 memory: 1026 2022/10/12 21:59:00 - mmengine - INFO - Epoch(val) [190][300/407] eta: 0:00:13 time: 0.129709 data_time: 0.008517 memory: 1026 2022/10/12 21:59:07 - mmengine - INFO - Epoch(val) [190][350/407] eta: 0:00:07 time: 0.128525 data_time: 0.008697 memory: 1026 2022/10/12 21:59:13 - mmengine - INFO - Epoch(val) [190][400/407] eta: 0:00:00 time: 0.126020 data_time: 0.007976 memory: 1026 2022/10/12 21:59:27 - mmengine - INFO - Evaluating CocoMetric... 2022/10/12 21:59:43 - mmengine - INFO - Epoch(val) [190][407/407] coco/AP: 0.722228 coco/AP .5: 0.893123 coco/AP .75: 0.795025 coco/AP (M): 0.689449 coco/AP (L): 0.784055 coco/AR: 0.788586 coco/AR .5: 0.933722 coco/AR .75: 0.849339 coco/AR (M): 0.743868 coco/AR (L): 0.850465 2022/10/12 21:59:43 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/liqikai/openmmlab/pt112cu113py38/mmpose/work_dirs/20221012/rsn50/best_coco/AP_epoch_180.pth is removed 2022/10/12 21:59:45 - mmengine - INFO - The best checkpoint with 0.7222 coco/AP at 190 epoch is saved to best_coco/AP_epoch_190.pth. 2022/10/12 22:00:02 - mmengine - INFO - Epoch(train) [191][50/586] lr: 5.000000e-04 eta: 1:02:01 time: 0.342700 data_time: 0.057712 memory: 4465 loss_kpt: 83.302604 acc_pose: 0.839506 loss: 83.302604 2022/10/12 22:00:19 - mmengine - INFO - Epoch(train) [191][100/586] lr: 5.000000e-04 eta: 1:01:45 time: 0.338258 data_time: 0.050535 memory: 4465 loss_kpt: 83.191133 acc_pose: 0.849945 loss: 83.191133 2022/10/12 22:00:37 - mmengine - INFO - Epoch(train) [191][150/586] lr: 5.000000e-04 eta: 1:01:29 time: 0.358964 data_time: 0.055988 memory: 4465 loss_kpt: 83.042148 acc_pose: 0.871538 loss: 83.042148 2022/10/12 22:00:54 - mmengine - INFO - Epoch(train) [191][200/586] lr: 5.000000e-04 eta: 1:01:13 time: 0.352064 data_time: 0.053247 memory: 4465 loss_kpt: 84.359807 acc_pose: 0.787312 loss: 84.359807 2022/10/12 22:01:12 - mmengine - INFO - Epoch(train) [191][250/586] lr: 5.000000e-04 eta: 1:00:58 time: 0.360013 data_time: 0.053046 memory: 4465 loss_kpt: 84.276902 acc_pose: 0.845777 loss: 84.276902 2022/10/12 22:01:29 - mmengine - INFO - Epoch(train) [191][300/586] lr: 5.000000e-04 eta: 1:00:42 time: 0.340633 data_time: 0.056679 memory: 4465 loss_kpt: 82.638136 acc_pose: 0.774325 loss: 82.638136 2022/10/12 22:01:47 - mmengine - INFO - Epoch(train) [191][350/586] lr: 5.000000e-04 eta: 1:00:26 time: 0.351509 data_time: 0.057898 memory: 4465 loss_kpt: 84.633460 acc_pose: 0.765028 loss: 84.633460 2022/10/12 22:02:04 - mmengine - INFO - Epoch(train) [191][400/586] lr: 5.000000e-04 eta: 1:00:10 time: 0.348839 data_time: 0.056507 memory: 4465 loss_kpt: 84.188377 acc_pose: 0.845845 loss: 84.188377 2022/10/12 22:02:21 - mmengine - INFO - Epoch(train) [191][450/586] lr: 5.000000e-04 eta: 0:59:54 time: 0.340432 data_time: 0.052879 memory: 4465 loss_kpt: 83.650153 acc_pose: 0.874674 loss: 83.650153 2022/10/12 22:02:38 - mmengine - INFO - Epoch(train) [191][500/586] lr: 5.000000e-04 eta: 0:59:39 time: 0.330177 data_time: 0.047086 memory: 4465 loss_kpt: 83.307650 acc_pose: 0.822008 loss: 83.307650 2022/10/12 22:02:54 - mmengine - INFO - Epoch(train) [191][550/586] lr: 5.000000e-04 eta: 0:59:23 time: 0.329228 data_time: 0.055999 memory: 4465 loss_kpt: 83.451569 acc_pose: 0.825509 loss: 83.451569 2022/10/12 22:03:06 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:03:24 - mmengine - INFO - Epoch(train) [192][50/586] lr: 5.000000e-04 eta: 0:58:54 time: 0.357072 data_time: 0.058227 memory: 4465 loss_kpt: 83.121903 acc_pose: 0.845304 loss: 83.121903 2022/10/12 22:03:32 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:03:41 - mmengine - INFO - Epoch(train) [192][100/586] lr: 5.000000e-04 eta: 0:58:38 time: 0.343597 data_time: 0.048938 memory: 4465 loss_kpt: 83.303188 acc_pose: 0.849582 loss: 83.303188 2022/10/12 22:03:58 - mmengine - INFO - Epoch(train) [192][150/586] lr: 5.000000e-04 eta: 0:58:23 time: 0.349607 data_time: 0.051684 memory: 4465 loss_kpt: 83.728531 acc_pose: 0.844007 loss: 83.728531 2022/10/12 22:04:16 - mmengine - INFO - Epoch(train) [192][200/586] lr: 5.000000e-04 eta: 0:58:07 time: 0.356413 data_time: 0.052760 memory: 4465 loss_kpt: 84.115415 acc_pose: 0.776667 loss: 84.115415 2022/10/12 22:04:34 - mmengine - INFO - Epoch(train) [192][250/586] lr: 5.000000e-04 eta: 0:57:51 time: 0.356258 data_time: 0.052537 memory: 4465 loss_kpt: 83.947425 acc_pose: 0.802244 loss: 83.947425 2022/10/12 22:04:52 - mmengine - INFO - Epoch(train) [192][300/586] lr: 5.000000e-04 eta: 0:57:35 time: 0.356090 data_time: 0.049108 memory: 4465 loss_kpt: 83.769833 acc_pose: 0.874936 loss: 83.769833 2022/10/12 22:05:10 - mmengine - INFO - Epoch(train) [192][350/586] lr: 5.000000e-04 eta: 0:57:20 time: 0.359553 data_time: 0.056237 memory: 4465 loss_kpt: 83.575794 acc_pose: 0.816842 loss: 83.575794 2022/10/12 22:05:27 - mmengine - INFO - Epoch(train) [192][400/586] lr: 5.000000e-04 eta: 0:57:04 time: 0.347700 data_time: 0.047301 memory: 4465 loss_kpt: 84.412912 acc_pose: 0.843450 loss: 84.412912 2022/10/12 22:05:44 - mmengine - INFO - Epoch(train) [192][450/586] lr: 5.000000e-04 eta: 0:56:48 time: 0.341237 data_time: 0.050088 memory: 4465 loss_kpt: 82.806596 acc_pose: 0.888979 loss: 82.806596 2022/10/12 22:06:01 - mmengine - INFO - Epoch(train) [192][500/586] lr: 5.000000e-04 eta: 0:56:32 time: 0.335830 data_time: 0.045791 memory: 4465 loss_kpt: 85.241341 acc_pose: 0.899304 loss: 85.241341 2022/10/12 22:06:18 - mmengine - INFO - Epoch(train) [192][550/586] lr: 5.000000e-04 eta: 0:56:16 time: 0.344860 data_time: 0.046858 memory: 4465 loss_kpt: 83.016617 acc_pose: 0.815819 loss: 83.016617 2022/10/12 22:06:30 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:06:48 - mmengine - INFO - Epoch(train) [193][50/586] lr: 5.000000e-04 eta: 0:55:48 time: 0.354037 data_time: 0.059465 memory: 4465 loss_kpt: 84.438162 acc_pose: 0.860300 loss: 84.438162 2022/10/12 22:07:05 - mmengine - INFO - Epoch(train) [193][100/586] lr: 5.000000e-04 eta: 0:55:32 time: 0.342446 data_time: 0.053089 memory: 4465 loss_kpt: 84.868217 acc_pose: 0.816323 loss: 84.868217 2022/10/12 22:07:23 - mmengine - INFO - Epoch(train) [193][150/586] lr: 5.000000e-04 eta: 0:55:16 time: 0.349185 data_time: 0.053221 memory: 4465 loss_kpt: 84.149342 acc_pose: 0.849000 loss: 84.149342 2022/10/12 22:07:40 - mmengine - INFO - Epoch(train) [193][200/586] lr: 5.000000e-04 eta: 0:55:00 time: 0.343854 data_time: 0.049213 memory: 4465 loss_kpt: 81.967440 acc_pose: 0.805440 loss: 81.967440 2022/10/12 22:07:57 - mmengine - INFO - Epoch(train) [193][250/586] lr: 5.000000e-04 eta: 0:54:45 time: 0.348965 data_time: 0.051320 memory: 4465 loss_kpt: 85.409386 acc_pose: 0.811071 loss: 85.409386 2022/10/12 22:08:14 - mmengine - INFO - Epoch(train) [193][300/586] lr: 5.000000e-04 eta: 0:54:29 time: 0.340502 data_time: 0.049515 memory: 4465 loss_kpt: 85.135309 acc_pose: 0.892674 loss: 85.135309 2022/10/12 22:08:31 - mmengine - INFO - Epoch(train) [193][350/586] lr: 5.000000e-04 eta: 0:54:13 time: 0.331160 data_time: 0.047547 memory: 4465 loss_kpt: 82.721152 acc_pose: 0.845370 loss: 82.721152 2022/10/12 22:08:48 - mmengine - INFO - Epoch(train) [193][400/586] lr: 5.000000e-04 eta: 0:53:57 time: 0.335484 data_time: 0.055413 memory: 4465 loss_kpt: 84.712725 acc_pose: 0.827533 loss: 84.712725 2022/10/12 22:09:05 - mmengine - INFO - Epoch(train) [193][450/586] lr: 5.000000e-04 eta: 0:53:41 time: 0.336283 data_time: 0.050934 memory: 4465 loss_kpt: 84.330036 acc_pose: 0.841706 loss: 84.330036 2022/10/12 22:09:18 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:09:22 - mmengine - INFO - Epoch(train) [193][500/586] lr: 5.000000e-04 eta: 0:53:25 time: 0.345210 data_time: 0.049761 memory: 4465 loss_kpt: 83.906985 acc_pose: 0.773122 loss: 83.906985 2022/10/12 22:09:39 - mmengine - INFO - Epoch(train) [193][550/586] lr: 5.000000e-04 eta: 0:53:09 time: 0.338180 data_time: 0.054319 memory: 4465 loss_kpt: 84.214405 acc_pose: 0.888251 loss: 84.214405 2022/10/12 22:09:51 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:10:08 - mmengine - INFO - Epoch(train) [194][50/586] lr: 5.000000e-04 eta: 0:52:41 time: 0.351167 data_time: 0.059414 memory: 4465 loss_kpt: 82.912345 acc_pose: 0.878807 loss: 82.912345 2022/10/12 22:10:25 - mmengine - INFO - Epoch(train) [194][100/586] lr: 5.000000e-04 eta: 0:52:25 time: 0.339630 data_time: 0.049965 memory: 4465 loss_kpt: 85.056484 acc_pose: 0.885580 loss: 85.056484 2022/10/12 22:10:42 - mmengine - INFO - Epoch(train) [194][150/586] lr: 5.000000e-04 eta: 0:52:09 time: 0.339630 data_time: 0.053955 memory: 4465 loss_kpt: 83.751392 acc_pose: 0.840437 loss: 83.751392 2022/10/12 22:11:00 - mmengine - INFO - Epoch(train) [194][200/586] lr: 5.000000e-04 eta: 0:51:54 time: 0.341106 data_time: 0.051527 memory: 4465 loss_kpt: 83.298400 acc_pose: 0.829237 loss: 83.298400 2022/10/12 22:11:17 - mmengine - INFO - Epoch(train) [194][250/586] lr: 5.000000e-04 eta: 0:51:38 time: 0.347622 data_time: 0.056691 memory: 4465 loss_kpt: 82.412500 acc_pose: 0.812246 loss: 82.412500 2022/10/12 22:11:35 - mmengine - INFO - Epoch(train) [194][300/586] lr: 5.000000e-04 eta: 0:51:22 time: 0.352775 data_time: 0.052716 memory: 4465 loss_kpt: 83.460701 acc_pose: 0.909880 loss: 83.460701 2022/10/12 22:11:52 - mmengine - INFO - Epoch(train) [194][350/586] lr: 5.000000e-04 eta: 0:51:06 time: 0.345976 data_time: 0.053876 memory: 4465 loss_kpt: 83.085231 acc_pose: 0.846360 loss: 83.085231 2022/10/12 22:12:10 - mmengine - INFO - Epoch(train) [194][400/586] lr: 5.000000e-04 eta: 0:50:50 time: 0.354104 data_time: 0.045894 memory: 4465 loss_kpt: 84.842617 acc_pose: 0.816361 loss: 84.842617 2022/10/12 22:12:27 - mmengine - INFO - Epoch(train) [194][450/586] lr: 5.000000e-04 eta: 0:50:34 time: 0.347592 data_time: 0.053711 memory: 4465 loss_kpt: 84.371809 acc_pose: 0.887653 loss: 84.371809 2022/10/12 22:12:44 - mmengine - INFO - Epoch(train) [194][500/586] lr: 5.000000e-04 eta: 0:50:19 time: 0.345232 data_time: 0.050131 memory: 4465 loss_kpt: 84.687321 acc_pose: 0.785350 loss: 84.687321 2022/10/12 22:13:01 - mmengine - INFO - Epoch(train) [194][550/586] lr: 5.000000e-04 eta: 0:50:03 time: 0.342010 data_time: 0.052807 memory: 4465 loss_kpt: 81.988749 acc_pose: 0.847391 loss: 81.988749 2022/10/12 22:13:13 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:13:31 - mmengine - INFO - Epoch(train) [195][50/586] lr: 5.000000e-04 eta: 0:49:34 time: 0.351914 data_time: 0.064817 memory: 4465 loss_kpt: 84.117839 acc_pose: 0.838459 loss: 84.117839 2022/10/12 22:13:48 - mmengine - INFO - Epoch(train) [195][100/586] lr: 5.000000e-04 eta: 0:49:19 time: 0.349696 data_time: 0.049964 memory: 4465 loss_kpt: 83.615058 acc_pose: 0.805332 loss: 83.615058 2022/10/12 22:14:06 - mmengine - INFO - Epoch(train) [195][150/586] lr: 5.000000e-04 eta: 0:49:03 time: 0.357666 data_time: 0.050174 memory: 4465 loss_kpt: 85.062096 acc_pose: 0.887801 loss: 85.062096 2022/10/12 22:14:23 - mmengine - INFO - Epoch(train) [195][200/586] lr: 5.000000e-04 eta: 0:48:47 time: 0.334674 data_time: 0.052887 memory: 4465 loss_kpt: 83.346623 acc_pose: 0.822988 loss: 83.346623 2022/10/12 22:14:40 - mmengine - INFO - Epoch(train) [195][250/586] lr: 5.000000e-04 eta: 0:48:31 time: 0.343280 data_time: 0.049421 memory: 4465 loss_kpt: 81.709856 acc_pose: 0.808008 loss: 81.709856 2022/10/12 22:14:57 - mmengine - INFO - Epoch(train) [195][300/586] lr: 5.000000e-04 eta: 0:48:15 time: 0.339750 data_time: 0.053058 memory: 4465 loss_kpt: 84.614985 acc_pose: 0.879172 loss: 84.614985 2022/10/12 22:15:02 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:15:14 - mmengine - INFO - Epoch(train) [195][350/586] lr: 5.000000e-04 eta: 0:47:59 time: 0.340328 data_time: 0.054751 memory: 4465 loss_kpt: 82.222561 acc_pose: 0.869883 loss: 82.222561 2022/10/12 22:15:30 - mmengine - INFO - Epoch(train) [195][400/586] lr: 5.000000e-04 eta: 0:47:43 time: 0.331144 data_time: 0.054008 memory: 4465 loss_kpt: 84.894541 acc_pose: 0.829166 loss: 84.894541 2022/10/12 22:15:47 - mmengine - INFO - Epoch(train) [195][450/586] lr: 5.000000e-04 eta: 0:47:28 time: 0.332932 data_time: 0.053257 memory: 4465 loss_kpt: 83.151108 acc_pose: 0.777203 loss: 83.151108 2022/10/12 22:16:04 - mmengine - INFO - Epoch(train) [195][500/586] lr: 5.000000e-04 eta: 0:47:12 time: 0.334861 data_time: 0.051698 memory: 4465 loss_kpt: 82.697142 acc_pose: 0.817269 loss: 82.697142 2022/10/12 22:16:21 - mmengine - INFO - Epoch(train) [195][550/586] lr: 5.000000e-04 eta: 0:46:56 time: 0.339103 data_time: 0.059338 memory: 4465 loss_kpt: 83.662820 acc_pose: 0.793232 loss: 83.662820 2022/10/12 22:16:33 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:16:51 - mmengine - INFO - Epoch(train) [196][50/586] lr: 5.000000e-04 eta: 0:46:28 time: 0.361741 data_time: 0.064607 memory: 4465 loss_kpt: 85.395905 acc_pose: 0.743269 loss: 85.395905 2022/10/12 22:17:08 - mmengine - INFO - Epoch(train) [196][100/586] lr: 5.000000e-04 eta: 0:46:12 time: 0.335477 data_time: 0.054444 memory: 4465 loss_kpt: 84.670310 acc_pose: 0.797640 loss: 84.670310 2022/10/12 22:17:24 - mmengine - INFO - Epoch(train) [196][150/586] lr: 5.000000e-04 eta: 0:45:56 time: 0.333545 data_time: 0.055529 memory: 4465 loss_kpt: 82.293079 acc_pose: 0.841737 loss: 82.293079 2022/10/12 22:17:42 - mmengine - INFO - Epoch(train) [196][200/586] lr: 5.000000e-04 eta: 0:45:40 time: 0.342647 data_time: 0.050386 memory: 4465 loss_kpt: 83.149665 acc_pose: 0.827357 loss: 83.149665 2022/10/12 22:17:59 - mmengine - INFO - Epoch(train) [196][250/586] lr: 5.000000e-04 eta: 0:45:24 time: 0.344236 data_time: 0.055347 memory: 4465 loss_kpt: 83.122201 acc_pose: 0.863740 loss: 83.122201 2022/10/12 22:18:16 - mmengine - INFO - Epoch(train) [196][300/586] lr: 5.000000e-04 eta: 0:45:08 time: 0.338097 data_time: 0.050625 memory: 4465 loss_kpt: 84.805450 acc_pose: 0.898807 loss: 84.805450 2022/10/12 22:18:33 - mmengine - INFO - Epoch(train) [196][350/586] lr: 5.000000e-04 eta: 0:44:52 time: 0.341026 data_time: 0.050570 memory: 4465 loss_kpt: 82.629916 acc_pose: 0.789440 loss: 82.629916 2022/10/12 22:18:50 - mmengine - INFO - Epoch(train) [196][400/586] lr: 5.000000e-04 eta: 0:44:37 time: 0.345988 data_time: 0.052039 memory: 4465 loss_kpt: 84.088244 acc_pose: 0.847571 loss: 84.088244 2022/10/12 22:19:08 - mmengine - INFO - Epoch(train) [196][450/586] lr: 5.000000e-04 eta: 0:44:21 time: 0.359135 data_time: 0.053581 memory: 4465 loss_kpt: 84.126636 acc_pose: 0.745257 loss: 84.126636 2022/10/12 22:19:26 - mmengine - INFO - Epoch(train) [196][500/586] lr: 5.000000e-04 eta: 0:44:05 time: 0.349122 data_time: 0.053314 memory: 4465 loss_kpt: 82.615395 acc_pose: 0.687783 loss: 82.615395 2022/10/12 22:19:43 - mmengine - INFO - Epoch(train) [196][550/586] lr: 5.000000e-04 eta: 0:43:49 time: 0.346537 data_time: 0.052990 memory: 4465 loss_kpt: 83.374789 acc_pose: 0.846899 loss: 83.374789 2022/10/12 22:19:55 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:20:13 - mmengine - INFO - Epoch(train) [197][50/586] lr: 5.000000e-04 eta: 0:43:21 time: 0.345320 data_time: 0.061650 memory: 4465 loss_kpt: 82.632622 acc_pose: 0.860276 loss: 82.632622 2022/10/12 22:20:30 - mmengine - INFO - Epoch(train) [197][100/586] lr: 5.000000e-04 eta: 0:43:05 time: 0.335244 data_time: 0.053972 memory: 4465 loss_kpt: 83.266548 acc_pose: 0.809207 loss: 83.266548 2022/10/12 22:20:44 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:20:46 - mmengine - INFO - Epoch(train) [197][150/586] lr: 5.000000e-04 eta: 0:42:49 time: 0.337876 data_time: 0.054018 memory: 4465 loss_kpt: 82.219025 acc_pose: 0.873644 loss: 82.219025 2022/10/12 22:21:04 - mmengine - INFO - Epoch(train) [197][200/586] lr: 5.000000e-04 eta: 0:42:33 time: 0.347605 data_time: 0.052954 memory: 4465 loss_kpt: 83.159298 acc_pose: 0.843683 loss: 83.159298 2022/10/12 22:21:21 - mmengine - INFO - Epoch(train) [197][250/586] lr: 5.000000e-04 eta: 0:42:17 time: 0.351346 data_time: 0.055589 memory: 4465 loss_kpt: 84.484596 acc_pose: 0.827044 loss: 84.484596 2022/10/12 22:21:39 - mmengine - INFO - Epoch(train) [197][300/586] lr: 5.000000e-04 eta: 0:42:02 time: 0.343342 data_time: 0.053453 memory: 4465 loss_kpt: 83.959761 acc_pose: 0.886366 loss: 83.959761 2022/10/12 22:21:56 - mmengine - INFO - Epoch(train) [197][350/586] lr: 5.000000e-04 eta: 0:41:46 time: 0.352214 data_time: 0.058558 memory: 4465 loss_kpt: 84.944528 acc_pose: 0.807189 loss: 84.944528 2022/10/12 22:22:14 - mmengine - INFO - Epoch(train) [197][400/586] lr: 5.000000e-04 eta: 0:41:30 time: 0.352704 data_time: 0.046524 memory: 4465 loss_kpt: 83.150213 acc_pose: 0.809929 loss: 83.150213 2022/10/12 22:22:31 - mmengine - INFO - Epoch(train) [197][450/586] lr: 5.000000e-04 eta: 0:41:14 time: 0.345173 data_time: 0.053717 memory: 4465 loss_kpt: 83.398952 acc_pose: 0.825104 loss: 83.398952 2022/10/12 22:22:48 - mmengine - INFO - Epoch(train) [197][500/586] lr: 5.000000e-04 eta: 0:40:58 time: 0.336708 data_time: 0.050489 memory: 4465 loss_kpt: 83.366784 acc_pose: 0.807775 loss: 83.366784 2022/10/12 22:23:05 - mmengine - INFO - Epoch(train) [197][550/586] lr: 5.000000e-04 eta: 0:40:42 time: 0.337641 data_time: 0.051706 memory: 4465 loss_kpt: 81.790044 acc_pose: 0.803280 loss: 81.790044 2022/10/12 22:23:17 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:23:35 - mmengine - INFO - Epoch(train) [198][50/586] lr: 5.000000e-04 eta: 0:40:14 time: 0.358031 data_time: 0.061236 memory: 4465 loss_kpt: 83.662915 acc_pose: 0.814701 loss: 83.662915 2022/10/12 22:23:52 - mmengine - INFO - Epoch(train) [198][100/586] lr: 5.000000e-04 eta: 0:39:58 time: 0.343758 data_time: 0.053519 memory: 4465 loss_kpt: 82.821744 acc_pose: 0.855583 loss: 82.821744 2022/10/12 22:24:09 - mmengine - INFO - Epoch(train) [198][150/586] lr: 5.000000e-04 eta: 0:39:42 time: 0.345590 data_time: 0.050943 memory: 4465 loss_kpt: 83.451857 acc_pose: 0.834362 loss: 83.451857 2022/10/12 22:24:26 - mmengine - INFO - Epoch(train) [198][200/586] lr: 5.000000e-04 eta: 0:39:26 time: 0.343499 data_time: 0.053805 memory: 4465 loss_kpt: 83.787166 acc_pose: 0.804703 loss: 83.787166 2022/10/12 22:24:43 - mmengine - INFO - Epoch(train) [198][250/586] lr: 5.000000e-04 eta: 0:39:11 time: 0.338710 data_time: 0.056943 memory: 4465 loss_kpt: 85.134883 acc_pose: 0.757763 loss: 85.134883 2022/10/12 22:25:00 - mmengine - INFO - Epoch(train) [198][300/586] lr: 5.000000e-04 eta: 0:38:55 time: 0.337055 data_time: 0.055881 memory: 4465 loss_kpt: 82.836644 acc_pose: 0.866537 loss: 82.836644 2022/10/12 22:25:17 - mmengine - INFO - Epoch(train) [198][350/586] lr: 5.000000e-04 eta: 0:38:39 time: 0.341893 data_time: 0.054948 memory: 4465 loss_kpt: 82.940241 acc_pose: 0.854515 loss: 82.940241 2022/10/12 22:25:34 - mmengine - INFO - Epoch(train) [198][400/586] lr: 5.000000e-04 eta: 0:38:23 time: 0.340168 data_time: 0.053319 memory: 4465 loss_kpt: 84.626915 acc_pose: 0.794691 loss: 84.626915 2022/10/12 22:25:51 - mmengine - INFO - Epoch(train) [198][450/586] lr: 5.000000e-04 eta: 0:38:07 time: 0.337570 data_time: 0.051654 memory: 4465 loss_kpt: 83.730476 acc_pose: 0.836625 loss: 83.730476 2022/10/12 22:26:08 - mmengine - INFO - Epoch(train) [198][500/586] lr: 5.000000e-04 eta: 0:37:51 time: 0.342185 data_time: 0.055309 memory: 4465 loss_kpt: 83.777702 acc_pose: 0.764946 loss: 83.777702 2022/10/12 22:26:25 - mmengine - INFO - Epoch(train) [198][550/586] lr: 5.000000e-04 eta: 0:37:35 time: 0.336687 data_time: 0.053025 memory: 4465 loss_kpt: 83.806027 acc_pose: 0.863173 loss: 83.806027 2022/10/12 22:26:28 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:26:38 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:26:55 - mmengine - INFO - Epoch(train) [199][50/586] lr: 5.000000e-04 eta: 0:37:07 time: 0.347279 data_time: 0.060408 memory: 4465 loss_kpt: 83.400317 acc_pose: 0.861483 loss: 83.400317 2022/10/12 22:27:12 - mmengine - INFO - Epoch(train) [199][100/586] lr: 5.000000e-04 eta: 0:36:51 time: 0.340926 data_time: 0.045071 memory: 4465 loss_kpt: 83.590041 acc_pose: 0.856989 loss: 83.590041 2022/10/12 22:27:29 - mmengine - INFO - Epoch(train) [199][150/586] lr: 5.000000e-04 eta: 0:36:35 time: 0.330443 data_time: 0.049331 memory: 4465 loss_kpt: 85.013165 acc_pose: 0.744505 loss: 85.013165 2022/10/12 22:27:45 - mmengine - INFO - Epoch(train) [199][200/586] lr: 5.000000e-04 eta: 0:36:19 time: 0.331219 data_time: 0.051571 memory: 4465 loss_kpt: 84.224901 acc_pose: 0.864013 loss: 84.224901 2022/10/12 22:28:02 - mmengine - INFO - Epoch(train) [199][250/586] lr: 5.000000e-04 eta: 0:36:04 time: 0.334382 data_time: 0.047577 memory: 4465 loss_kpt: 84.419245 acc_pose: 0.860609 loss: 84.419245 2022/10/12 22:28:18 - mmengine - INFO - Epoch(train) [199][300/586] lr: 5.000000e-04 eta: 0:35:48 time: 0.329668 data_time: 0.046934 memory: 4465 loss_kpt: 82.947534 acc_pose: 0.806301 loss: 82.947534 2022/10/12 22:28:35 - mmengine - INFO - Epoch(train) [199][350/586] lr: 5.000000e-04 eta: 0:35:32 time: 0.334127 data_time: 0.051678 memory: 4465 loss_kpt: 82.306221 acc_pose: 0.849013 loss: 82.306221 2022/10/12 22:28:52 - mmengine - INFO - Epoch(train) [199][400/586] lr: 5.000000e-04 eta: 0:35:16 time: 0.331939 data_time: 0.049597 memory: 4465 loss_kpt: 83.154359 acc_pose: 0.886729 loss: 83.154359 2022/10/12 22:29:08 - mmengine - INFO - Epoch(train) [199][450/586] lr: 5.000000e-04 eta: 0:35:00 time: 0.330786 data_time: 0.046356 memory: 4465 loss_kpt: 84.160171 acc_pose: 0.755784 loss: 84.160171 2022/10/12 22:29:25 - mmengine - INFO - Epoch(train) [199][500/586] lr: 5.000000e-04 eta: 0:34:44 time: 0.329327 data_time: 0.053658 memory: 4465 loss_kpt: 85.022519 acc_pose: 0.827239 loss: 85.022519 2022/10/12 22:29:42 - mmengine - INFO - Epoch(train) [199][550/586] lr: 5.000000e-04 eta: 0:34:28 time: 0.334674 data_time: 0.052386 memory: 4465 loss_kpt: 83.869629 acc_pose: 0.850458 loss: 83.869629 2022/10/12 22:29:53 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:30:12 - mmengine - INFO - Epoch(train) [200][50/586] lr: 5.000000e-04 eta: 0:34:00 time: 0.379049 data_time: 0.064091 memory: 4465 loss_kpt: 83.230907 acc_pose: 0.848156 loss: 83.230907 2022/10/12 22:30:30 - mmengine - INFO - Epoch(train) [200][100/586] lr: 5.000000e-04 eta: 0:33:44 time: 0.358760 data_time: 0.051915 memory: 4465 loss_kpt: 82.399520 acc_pose: 0.698444 loss: 82.399520 2022/10/12 22:30:48 - mmengine - INFO - Epoch(train) [200][150/586] lr: 5.000000e-04 eta: 0:33:28 time: 0.357151 data_time: 0.053279 memory: 4465 loss_kpt: 84.207271 acc_pose: 0.850724 loss: 84.207271 2022/10/12 22:31:06 - mmengine - INFO - Epoch(train) [200][200/586] lr: 5.000000e-04 eta: 0:33:13 time: 0.363103 data_time: 0.058791 memory: 4465 loss_kpt: 84.151312 acc_pose: 0.833127 loss: 84.151312 2022/10/12 22:31:24 - mmengine - INFO - Epoch(train) [200][250/586] lr: 5.000000e-04 eta: 0:32:57 time: 0.362499 data_time: 0.051468 memory: 4465 loss_kpt: 82.549681 acc_pose: 0.787932 loss: 82.549681 2022/10/12 22:31:43 - mmengine - INFO - Epoch(train) [200][300/586] lr: 5.000000e-04 eta: 0:32:41 time: 0.364566 data_time: 0.054921 memory: 4465 loss_kpt: 83.407189 acc_pose: 0.806804 loss: 83.407189 2022/10/12 22:32:01 - mmengine - INFO - Epoch(train) [200][350/586] lr: 5.000000e-04 eta: 0:32:25 time: 0.366166 data_time: 0.054149 memory: 4465 loss_kpt: 84.304378 acc_pose: 0.876501 loss: 84.304378 2022/10/12 22:32:13 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:32:18 - mmengine - INFO - Epoch(train) [200][400/586] lr: 5.000000e-04 eta: 0:32:09 time: 0.347486 data_time: 0.051402 memory: 4465 loss_kpt: 82.484916 acc_pose: 0.850553 loss: 82.484916 2022/10/12 22:32:36 - mmengine - INFO - Epoch(train) [200][450/586] lr: 5.000000e-04 eta: 0:31:53 time: 0.348733 data_time: 0.054384 memory: 4465 loss_kpt: 83.327317 acc_pose: 0.807426 loss: 83.327317 2022/10/12 22:32:53 - mmengine - INFO - Epoch(train) [200][500/586] lr: 5.000000e-04 eta: 0:31:37 time: 0.344058 data_time: 0.048624 memory: 4465 loss_kpt: 84.175869 acc_pose: 0.855137 loss: 84.175869 2022/10/12 22:33:10 - mmengine - INFO - Epoch(train) [200][550/586] lr: 5.000000e-04 eta: 0:31:22 time: 0.346273 data_time: 0.050715 memory: 4465 loss_kpt: 81.851889 acc_pose: 0.874530 loss: 81.851889 2022/10/12 22:33:22 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:33:22 - mmengine - INFO - Saving checkpoint at 200 epochs 2022/10/12 22:33:32 - mmengine - INFO - Epoch(val) [200][50/407] eta: 0:00:47 time: 0.131656 data_time: 0.013010 memory: 4465 2022/10/12 22:33:38 - mmengine - INFO - Epoch(val) [200][100/407] eta: 0:00:39 time: 0.128465 data_time: 0.008196 memory: 1026 2022/10/12 22:33:45 - mmengine - INFO - Epoch(val) [200][150/407] eta: 0:00:34 time: 0.133208 data_time: 0.009028 memory: 1026 2022/10/12 22:33:51 - mmengine - INFO - Epoch(val) [200][200/407] eta: 0:00:26 time: 0.127909 data_time: 0.008404 memory: 1026 2022/10/12 22:33:58 - mmengine - INFO - Epoch(val) [200][250/407] eta: 0:00:20 time: 0.130371 data_time: 0.011580 memory: 1026 2022/10/12 22:34:04 - mmengine - INFO - Epoch(val) [200][300/407] eta: 0:00:13 time: 0.127926 data_time: 0.008269 memory: 1026 2022/10/12 22:34:10 - mmengine - INFO - Epoch(val) [200][350/407] eta: 0:00:07 time: 0.128315 data_time: 0.008348 memory: 1026 2022/10/12 22:34:17 - mmengine - INFO - Epoch(val) [200][400/407] eta: 0:00:00 time: 0.123149 data_time: 0.007775 memory: 1026 2022/10/12 22:34:30 - mmengine - INFO - Evaluating CocoMetric... 2022/10/12 22:34:46 - mmengine - INFO - Epoch(val) [200][407/407] coco/AP: 0.724002 coco/AP .5: 0.895250 coco/AP .75: 0.799647 coco/AP (M): 0.690184 coco/AP (L): 0.786795 coco/AR: 0.790444 coco/AR .5: 0.935768 coco/AR .75: 0.852802 coco/AR (M): 0.746244 coco/AR (L): 0.851579 2022/10/12 22:34:46 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/liqikai/openmmlab/pt112cu113py38/mmpose/work_dirs/20221012/rsn50/best_coco/AP_epoch_190.pth is removed 2022/10/12 22:34:48 - mmengine - INFO - The best checkpoint with 0.7240 coco/AP at 200 epoch is saved to best_coco/AP_epoch_200.pth. 2022/10/12 22:35:05 - mmengine - INFO - Epoch(train) [201][50/586] lr: 5.000000e-05 eta: 0:30:54 time: 0.351263 data_time: 0.059388 memory: 4465 loss_kpt: 83.447171 acc_pose: 0.858308 loss: 83.447171 2022/10/12 22:35:22 - mmengine - INFO - Epoch(train) [201][100/586] lr: 5.000000e-05 eta: 0:30:38 time: 0.338317 data_time: 0.045467 memory: 4465 loss_kpt: 83.562323 acc_pose: 0.819895 loss: 83.562323 2022/10/12 22:35:40 - mmengine - INFO - Epoch(train) [201][150/586] lr: 5.000000e-05 eta: 0:30:22 time: 0.355151 data_time: 0.059264 memory: 4465 loss_kpt: 84.663851 acc_pose: 0.872818 loss: 84.663851 2022/10/12 22:35:58 - mmengine - INFO - Epoch(train) [201][200/586] lr: 5.000000e-05 eta: 0:30:06 time: 0.360996 data_time: 0.046965 memory: 4465 loss_kpt: 83.673685 acc_pose: 0.773669 loss: 83.673685 2022/10/12 22:36:16 - mmengine - INFO - Epoch(train) [201][250/586] lr: 5.000000e-05 eta: 0:29:50 time: 0.359086 data_time: 0.052194 memory: 4465 loss_kpt: 84.559186 acc_pose: 0.791266 loss: 84.559186 2022/10/12 22:36:33 - mmengine - INFO - Epoch(train) [201][300/586] lr: 5.000000e-05 eta: 0:29:34 time: 0.339366 data_time: 0.048619 memory: 4465 loss_kpt: 82.691300 acc_pose: 0.834659 loss: 82.691300 2022/10/12 22:36:50 - mmengine - INFO - Epoch(train) [201][350/586] lr: 5.000000e-05 eta: 0:29:18 time: 0.337410 data_time: 0.048764 memory: 4465 loss_kpt: 83.823486 acc_pose: 0.870879 loss: 83.823486 2022/10/12 22:37:07 - mmengine - INFO - Epoch(train) [201][400/586] lr: 5.000000e-05 eta: 0:29:02 time: 0.347142 data_time: 0.050371 memory: 4465 loss_kpt: 82.240594 acc_pose: 0.843992 loss: 82.240594 2022/10/12 22:37:25 - mmengine - INFO - Epoch(train) [201][450/586] lr: 5.000000e-05 eta: 0:28:46 time: 0.352775 data_time: 0.047833 memory: 4465 loss_kpt: 83.362680 acc_pose: 0.815446 loss: 83.362680 2022/10/12 22:37:43 - mmengine - INFO - Epoch(train) [201][500/586] lr: 5.000000e-05 eta: 0:28:31 time: 0.368093 data_time: 0.051985 memory: 4465 loss_kpt: 82.650079 acc_pose: 0.857636 loss: 82.650079 2022/10/12 22:38:01 - mmengine - INFO - Epoch(train) [201][550/586] lr: 5.000000e-05 eta: 0:28:15 time: 0.352987 data_time: 0.052451 memory: 4465 loss_kpt: 84.052296 acc_pose: 0.855206 loss: 84.052296 2022/10/12 22:38:13 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:38:31 - mmengine - INFO - Epoch(train) [202][50/586] lr: 5.000000e-05 eta: 0:27:47 time: 0.355069 data_time: 0.063011 memory: 4465 loss_kpt: 83.225815 acc_pose: 0.772723 loss: 83.225815 2022/10/12 22:38:49 - mmengine - INFO - Epoch(train) [202][100/586] lr: 5.000000e-05 eta: 0:27:31 time: 0.349686 data_time: 0.050200 memory: 4465 loss_kpt: 84.243601 acc_pose: 0.810732 loss: 84.243601 2022/10/12 22:39:06 - mmengine - INFO - Epoch(train) [202][150/586] lr: 5.000000e-05 eta: 0:27:15 time: 0.350930 data_time: 0.054729 memory: 4465 loss_kpt: 82.919872 acc_pose: 0.866496 loss: 82.919872 2022/10/12 22:39:23 - mmengine - INFO - Epoch(train) [202][200/586] lr: 5.000000e-05 eta: 0:26:59 time: 0.341345 data_time: 0.049537 memory: 4465 loss_kpt: 81.654899 acc_pose: 0.830803 loss: 81.654899 2022/10/12 22:39:28 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:39:40 - mmengine - INFO - Epoch(train) [202][250/586] lr: 5.000000e-05 eta: 0:26:43 time: 0.343185 data_time: 0.052880 memory: 4465 loss_kpt: 82.160808 acc_pose: 0.873886 loss: 82.160808 2022/10/12 22:39:58 - mmengine - INFO - Epoch(train) [202][300/586] lr: 5.000000e-05 eta: 0:26:27 time: 0.350895 data_time: 0.051182 memory: 4465 loss_kpt: 83.051698 acc_pose: 0.854396 loss: 83.051698 2022/10/12 22:40:16 - mmengine - INFO - Epoch(train) [202][350/586] lr: 5.000000e-05 eta: 0:26:11 time: 0.353464 data_time: 0.059538 memory: 4465 loss_kpt: 82.273857 acc_pose: 0.832893 loss: 82.273857 2022/10/12 22:40:33 - mmengine - INFO - Epoch(train) [202][400/586] lr: 5.000000e-05 eta: 0:25:56 time: 0.350972 data_time: 0.052375 memory: 4465 loss_kpt: 85.245323 acc_pose: 0.880011 loss: 85.245323 2022/10/12 22:40:50 - mmengine - INFO - Epoch(train) [202][450/586] lr: 5.000000e-05 eta: 0:25:40 time: 0.343447 data_time: 0.050683 memory: 4465 loss_kpt: 84.084988 acc_pose: 0.793918 loss: 84.084988 2022/10/12 22:41:08 - mmengine - INFO - Epoch(train) [202][500/586] lr: 5.000000e-05 eta: 0:25:24 time: 0.352290 data_time: 0.047360 memory: 4465 loss_kpt: 82.159760 acc_pose: 0.882076 loss: 82.159760 2022/10/12 22:41:26 - mmengine - INFO - Epoch(train) [202][550/586] lr: 5.000000e-05 eta: 0:25:08 time: 0.356128 data_time: 0.053278 memory: 4465 loss_kpt: 82.912022 acc_pose: 0.800383 loss: 82.912022 2022/10/12 22:41:39 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:41:56 - mmengine - INFO - Epoch(train) [203][50/586] lr: 5.000000e-05 eta: 0:24:40 time: 0.342441 data_time: 0.057949 memory: 4465 loss_kpt: 83.832353 acc_pose: 0.795499 loss: 83.832353 2022/10/12 22:42:13 - mmengine - INFO - Epoch(train) [203][100/586] lr: 5.000000e-05 eta: 0:24:24 time: 0.340840 data_time: 0.052947 memory: 4465 loss_kpt: 82.516283 acc_pose: 0.762865 loss: 82.516283 2022/10/12 22:42:30 - mmengine - INFO - Epoch(train) [203][150/586] lr: 5.000000e-05 eta: 0:24:08 time: 0.344191 data_time: 0.050158 memory: 4465 loss_kpt: 84.060864 acc_pose: 0.822446 loss: 84.060864 2022/10/12 22:42:47 - mmengine - INFO - Epoch(train) [203][200/586] lr: 5.000000e-05 eta: 0:23:52 time: 0.338648 data_time: 0.054801 memory: 4465 loss_kpt: 82.358814 acc_pose: 0.847465 loss: 82.358814 2022/10/12 22:43:05 - mmengine - INFO - Epoch(train) [203][250/586] lr: 5.000000e-05 eta: 0:23:36 time: 0.356233 data_time: 0.051863 memory: 4465 loss_kpt: 84.936790 acc_pose: 0.784615 loss: 84.936790 2022/10/12 22:43:23 - mmengine - INFO - Epoch(train) [203][300/586] lr: 5.000000e-05 eta: 0:23:20 time: 0.362150 data_time: 0.054190 memory: 4465 loss_kpt: 81.759483 acc_pose: 0.829303 loss: 81.759483 2022/10/12 22:43:40 - mmengine - INFO - Epoch(train) [203][350/586] lr: 5.000000e-05 eta: 0:23:05 time: 0.341484 data_time: 0.047009 memory: 4465 loss_kpt: 82.886502 acc_pose: 0.848983 loss: 82.886502 2022/10/12 22:43:57 - mmengine - INFO - Epoch(train) [203][400/586] lr: 5.000000e-05 eta: 0:22:49 time: 0.349707 data_time: 0.051651 memory: 4465 loss_kpt: 84.637274 acc_pose: 0.862590 loss: 84.637274 2022/10/12 22:44:15 - mmengine - INFO - Epoch(train) [203][450/586] lr: 5.000000e-05 eta: 0:22:33 time: 0.348951 data_time: 0.052186 memory: 4465 loss_kpt: 83.599691 acc_pose: 0.778492 loss: 83.599691 2022/10/12 22:44:32 - mmengine - INFO - Epoch(train) [203][500/586] lr: 5.000000e-05 eta: 0:22:17 time: 0.349928 data_time: 0.049022 memory: 4465 loss_kpt: 82.716858 acc_pose: 0.850997 loss: 82.716858 2022/10/12 22:44:49 - mmengine - INFO - Epoch(train) [203][550/586] lr: 5.000000e-05 eta: 0:22:01 time: 0.332667 data_time: 0.047727 memory: 4465 loss_kpt: 83.287986 acc_pose: 0.814277 loss: 83.287986 2022/10/12 22:45:01 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:45:17 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:45:19 - mmengine - INFO - Epoch(train) [204][50/586] lr: 5.000000e-05 eta: 0:21:33 time: 0.358756 data_time: 0.067286 memory: 4465 loss_kpt: 83.255682 acc_pose: 0.840797 loss: 83.255682 2022/10/12 22:45:36 - mmengine - INFO - Epoch(train) [204][100/586] lr: 5.000000e-05 eta: 0:21:17 time: 0.337150 data_time: 0.050496 memory: 4465 loss_kpt: 83.639653 acc_pose: 0.712168 loss: 83.639653 2022/10/12 22:45:53 - mmengine - INFO - Epoch(train) [204][150/586] lr: 5.000000e-05 eta: 0:21:01 time: 0.329955 data_time: 0.052167 memory: 4465 loss_kpt: 84.739651 acc_pose: 0.843266 loss: 84.739651 2022/10/12 22:46:10 - mmengine - INFO - Epoch(train) [204][200/586] lr: 5.000000e-05 eta: 0:20:45 time: 0.333437 data_time: 0.051899 memory: 4465 loss_kpt: 82.940159 acc_pose: 0.815374 loss: 82.940159 2022/10/12 22:46:27 - mmengine - INFO - Epoch(train) [204][250/586] lr: 5.000000e-05 eta: 0:20:29 time: 0.340449 data_time: 0.056095 memory: 4465 loss_kpt: 83.290257 acc_pose: 0.801259 loss: 83.290257 2022/10/12 22:46:43 - mmengine - INFO - Epoch(train) [204][300/586] lr: 5.000000e-05 eta: 0:20:13 time: 0.331516 data_time: 0.049823 memory: 4465 loss_kpt: 84.678101 acc_pose: 0.853732 loss: 84.678101 2022/10/12 22:47:00 - mmengine - INFO - Epoch(train) [204][350/586] lr: 5.000000e-05 eta: 0:19:57 time: 0.335974 data_time: 0.053875 memory: 4465 loss_kpt: 81.686125 acc_pose: 0.850259 loss: 81.686125 2022/10/12 22:47:17 - mmengine - INFO - Epoch(train) [204][400/586] lr: 5.000000e-05 eta: 0:19:42 time: 0.330455 data_time: 0.046466 memory: 4465 loss_kpt: 82.766295 acc_pose: 0.836760 loss: 82.766295 2022/10/12 22:47:33 - mmengine - INFO - Epoch(train) [204][450/586] lr: 5.000000e-05 eta: 0:19:26 time: 0.336227 data_time: 0.054533 memory: 4465 loss_kpt: 82.028177 acc_pose: 0.828542 loss: 82.028177 2022/10/12 22:47:50 - mmengine - INFO - Epoch(train) [204][500/586] lr: 5.000000e-05 eta: 0:19:10 time: 0.325380 data_time: 0.047354 memory: 4465 loss_kpt: 82.707591 acc_pose: 0.848056 loss: 82.707591 2022/10/12 22:48:06 - mmengine - INFO - Epoch(train) [204][550/586] lr: 5.000000e-05 eta: 0:18:54 time: 0.334403 data_time: 0.051112 memory: 4465 loss_kpt: 82.450011 acc_pose: 0.858517 loss: 82.450011 2022/10/12 22:48:18 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:48:36 - mmengine - INFO - Epoch(train) [205][50/586] lr: 5.000000e-05 eta: 0:18:26 time: 0.358713 data_time: 0.060937 memory: 4465 loss_kpt: 84.034778 acc_pose: 0.804508 loss: 84.034778 2022/10/12 22:48:54 - mmengine - INFO - Epoch(train) [205][100/586] lr: 5.000000e-05 eta: 0:18:10 time: 0.349859 data_time: 0.045931 memory: 4465 loss_kpt: 83.488629 acc_pose: 0.865379 loss: 83.488629 2022/10/12 22:49:12 - mmengine - INFO - Epoch(train) [205][150/586] lr: 5.000000e-05 eta: 0:17:54 time: 0.361815 data_time: 0.058238 memory: 4465 loss_kpt: 84.731507 acc_pose: 0.804580 loss: 84.731507 2022/10/12 22:49:30 - mmengine - INFO - Epoch(train) [205][200/586] lr: 5.000000e-05 eta: 0:17:38 time: 0.359274 data_time: 0.048033 memory: 4465 loss_kpt: 81.507130 acc_pose: 0.788253 loss: 81.507130 2022/10/12 22:49:48 - mmengine - INFO - Epoch(train) [205][250/586] lr: 5.000000e-05 eta: 0:17:22 time: 0.368746 data_time: 0.059118 memory: 4465 loss_kpt: 83.211930 acc_pose: 0.861155 loss: 83.211930 2022/10/12 22:50:06 - mmengine - INFO - Epoch(train) [205][300/586] lr: 5.000000e-05 eta: 0:17:06 time: 0.350735 data_time: 0.048389 memory: 4465 loss_kpt: 84.215763 acc_pose: 0.806008 loss: 84.215763 2022/10/12 22:50:23 - mmengine - INFO - Epoch(train) [205][350/586] lr: 5.000000e-05 eta: 0:16:50 time: 0.347722 data_time: 0.054233 memory: 4465 loss_kpt: 82.391407 acc_pose: 0.836859 loss: 82.391407 2022/10/12 22:50:40 - mmengine - INFO - Epoch(train) [205][400/586] lr: 5.000000e-05 eta: 0:16:35 time: 0.337598 data_time: 0.050574 memory: 4465 loss_kpt: 84.137569 acc_pose: 0.843965 loss: 84.137569 2022/10/12 22:50:57 - mmengine - INFO - Epoch(train) [205][450/586] lr: 5.000000e-05 eta: 0:16:19 time: 0.340939 data_time: 0.054852 memory: 4465 loss_kpt: 84.741320 acc_pose: 0.813292 loss: 84.741320 2022/10/12 22:50:59 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:51:14 - mmengine - INFO - Epoch(train) [205][500/586] lr: 5.000000e-05 eta: 0:16:03 time: 0.338806 data_time: 0.051485 memory: 4465 loss_kpt: 82.825793 acc_pose: 0.877606 loss: 82.825793 2022/10/12 22:51:31 - mmengine - INFO - Epoch(train) [205][550/586] lr: 5.000000e-05 eta: 0:15:47 time: 0.342204 data_time: 0.053550 memory: 4465 loss_kpt: 83.860396 acc_pose: 0.871824 loss: 83.860396 2022/10/12 22:51:43 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:52:00 - mmengine - INFO - Epoch(train) [206][50/586] lr: 5.000000e-05 eta: 0:15:19 time: 0.348863 data_time: 0.059966 memory: 4465 loss_kpt: 82.893999 acc_pose: 0.802792 loss: 82.893999 2022/10/12 22:52:17 - mmengine - INFO - Epoch(train) [206][100/586] lr: 5.000000e-05 eta: 0:15:03 time: 0.335120 data_time: 0.053626 memory: 4465 loss_kpt: 83.223167 acc_pose: 0.898248 loss: 83.223167 2022/10/12 22:52:34 - mmengine - INFO - Epoch(train) [206][150/586] lr: 5.000000e-05 eta: 0:14:47 time: 0.340736 data_time: 0.057771 memory: 4465 loss_kpt: 83.102258 acc_pose: 0.871148 loss: 83.102258 2022/10/12 22:52:51 - mmengine - INFO - Epoch(train) [206][200/586] lr: 5.000000e-05 eta: 0:14:31 time: 0.330461 data_time: 0.049880 memory: 4465 loss_kpt: 83.151124 acc_pose: 0.878984 loss: 83.151124 2022/10/12 22:53:09 - mmengine - INFO - Epoch(train) [206][250/586] lr: 5.000000e-05 eta: 0:14:15 time: 0.357066 data_time: 0.052447 memory: 4465 loss_kpt: 84.158359 acc_pose: 0.801674 loss: 84.158359 2022/10/12 22:53:26 - mmengine - INFO - Epoch(train) [206][300/586] lr: 5.000000e-05 eta: 0:13:59 time: 0.351844 data_time: 0.048262 memory: 4465 loss_kpt: 83.541087 acc_pose: 0.844929 loss: 83.541087 2022/10/12 22:53:44 - mmengine - INFO - Epoch(train) [206][350/586] lr: 5.000000e-05 eta: 0:13:43 time: 0.351030 data_time: 0.053588 memory: 4465 loss_kpt: 83.926563 acc_pose: 0.821687 loss: 83.926563 2022/10/12 22:54:00 - mmengine - INFO - Epoch(train) [206][400/586] lr: 5.000000e-05 eta: 0:13:27 time: 0.331871 data_time: 0.050261 memory: 4465 loss_kpt: 83.045260 acc_pose: 0.805298 loss: 83.045260 2022/10/12 22:54:17 - mmengine - INFO - Epoch(train) [206][450/586] lr: 5.000000e-05 eta: 0:13:11 time: 0.333345 data_time: 0.052393 memory: 4465 loss_kpt: 83.000025 acc_pose: 0.838966 loss: 83.000025 2022/10/12 22:54:34 - mmengine - INFO - Epoch(train) [206][500/586] lr: 5.000000e-05 eta: 0:12:56 time: 0.330785 data_time: 0.046314 memory: 4465 loss_kpt: 83.805899 acc_pose: 0.814228 loss: 83.805899 2022/10/12 22:54:50 - mmengine - INFO - Epoch(train) [206][550/586] lr: 5.000000e-05 eta: 0:12:40 time: 0.330801 data_time: 0.050487 memory: 4465 loss_kpt: 83.001024 acc_pose: 0.777457 loss: 83.001024 2022/10/12 22:55:02 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:55:19 - mmengine - INFO - Epoch(train) [207][50/586] lr: 5.000000e-05 eta: 0:12:12 time: 0.347631 data_time: 0.064849 memory: 4465 loss_kpt: 82.973036 acc_pose: 0.841461 loss: 82.973036 2022/10/12 22:55:36 - mmengine - INFO - Epoch(train) [207][100/586] lr: 5.000000e-05 eta: 0:11:56 time: 0.334850 data_time: 0.056660 memory: 4465 loss_kpt: 83.745733 acc_pose: 0.842807 loss: 83.745733 2022/10/12 22:55:53 - mmengine - INFO - Epoch(train) [207][150/586] lr: 5.000000e-05 eta: 0:11:40 time: 0.335273 data_time: 0.051443 memory: 4465 loss_kpt: 82.921310 acc_pose: 0.783367 loss: 82.921310 2022/10/12 22:56:10 - mmengine - INFO - Epoch(train) [207][200/586] lr: 5.000000e-05 eta: 0:11:24 time: 0.335583 data_time: 0.049922 memory: 4465 loss_kpt: 82.393037 acc_pose: 0.847075 loss: 82.393037 2022/10/12 22:56:26 - mmengine - INFO - Epoch(train) [207][250/586] lr: 5.000000e-05 eta: 0:11:08 time: 0.335537 data_time: 0.051095 memory: 4465 loss_kpt: 83.873466 acc_pose: 0.851506 loss: 83.873466 2022/10/12 22:56:38 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:56:44 - mmengine - INFO - Epoch(train) [207][300/586] lr: 5.000000e-05 eta: 0:10:52 time: 0.342630 data_time: 0.049861 memory: 4465 loss_kpt: 82.467730 acc_pose: 0.823380 loss: 82.467730 2022/10/12 22:57:01 - mmengine - INFO - Epoch(train) [207][350/586] lr: 5.000000e-05 eta: 0:10:36 time: 0.346148 data_time: 0.055040 memory: 4465 loss_kpt: 82.032515 acc_pose: 0.845138 loss: 82.032515 2022/10/12 22:57:17 - mmengine - INFO - Epoch(train) [207][400/586] lr: 5.000000e-05 eta: 0:10:20 time: 0.318529 data_time: 0.049494 memory: 4465 loss_kpt: 82.247947 acc_pose: 0.861372 loss: 82.247947 2022/10/12 22:57:33 - mmengine - INFO - Epoch(train) [207][450/586] lr: 5.000000e-05 eta: 0:10:04 time: 0.324388 data_time: 0.051253 memory: 4465 loss_kpt: 82.469228 acc_pose: 0.857452 loss: 82.469228 2022/10/12 22:57:49 - mmengine - INFO - Epoch(train) [207][500/586] lr: 5.000000e-05 eta: 0:09:48 time: 0.323154 data_time: 0.048474 memory: 4465 loss_kpt: 84.824986 acc_pose: 0.832631 loss: 84.824986 2022/10/12 22:58:06 - mmengine - INFO - Epoch(train) [207][550/586] lr: 5.000000e-05 eta: 0:09:32 time: 0.328152 data_time: 0.049037 memory: 4465 loss_kpt: 82.526630 acc_pose: 0.823452 loss: 82.526630 2022/10/12 22:58:17 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 22:58:35 - mmengine - INFO - Epoch(train) [208][50/586] lr: 5.000000e-05 eta: 0:09:05 time: 0.351632 data_time: 0.066644 memory: 4465 loss_kpt: 83.299017 acc_pose: 0.869784 loss: 83.299017 2022/10/12 22:58:51 - mmengine - INFO - Epoch(train) [208][100/586] lr: 5.000000e-05 eta: 0:08:49 time: 0.331171 data_time: 0.050770 memory: 4465 loss_kpt: 84.218419 acc_pose: 0.754629 loss: 84.218419 2022/10/12 22:59:08 - mmengine - INFO - Epoch(train) [208][150/586] lr: 5.000000e-05 eta: 0:08:33 time: 0.332824 data_time: 0.051797 memory: 4465 loss_kpt: 82.403645 acc_pose: 0.796846 loss: 82.403645 2022/10/12 22:59:25 - mmengine - INFO - Epoch(train) [208][200/586] lr: 5.000000e-05 eta: 0:08:17 time: 0.338951 data_time: 0.051265 memory: 4465 loss_kpt: 82.715308 acc_pose: 0.853181 loss: 82.715308 2022/10/12 22:59:42 - mmengine - INFO - Epoch(train) [208][250/586] lr: 5.000000e-05 eta: 0:08:01 time: 0.344502 data_time: 0.052912 memory: 4465 loss_kpt: 82.878001 acc_pose: 0.794276 loss: 82.878001 2022/10/12 22:59:59 - mmengine - INFO - Epoch(train) [208][300/586] lr: 5.000000e-05 eta: 0:07:45 time: 0.344508 data_time: 0.052377 memory: 4465 loss_kpt: 82.827663 acc_pose: 0.846907 loss: 82.827663 2022/10/12 23:00:17 - mmengine - INFO - Epoch(train) [208][350/586] lr: 5.000000e-05 eta: 0:07:29 time: 0.345138 data_time: 0.057354 memory: 4465 loss_kpt: 83.980368 acc_pose: 0.811845 loss: 83.980368 2022/10/12 23:00:33 - mmengine - INFO - Epoch(train) [208][400/586] lr: 5.000000e-05 eta: 0:07:13 time: 0.334109 data_time: 0.055147 memory: 4465 loss_kpt: 82.354384 acc_pose: 0.839945 loss: 82.354384 2022/10/12 23:00:50 - mmengine - INFO - Epoch(train) [208][450/586] lr: 5.000000e-05 eta: 0:06:57 time: 0.333655 data_time: 0.049506 memory: 4465 loss_kpt: 82.878795 acc_pose: 0.769444 loss: 82.878795 2022/10/12 23:01:07 - mmengine - INFO - Epoch(train) [208][500/586] lr: 5.000000e-05 eta: 0:06:41 time: 0.343361 data_time: 0.053515 memory: 4465 loss_kpt: 82.464010 acc_pose: 0.839883 loss: 82.464010 2022/10/12 23:01:25 - mmengine - INFO - Epoch(train) [208][550/586] lr: 5.000000e-05 eta: 0:06:25 time: 0.357540 data_time: 0.053398 memory: 4465 loss_kpt: 85.538254 acc_pose: 0.865585 loss: 85.538254 2022/10/12 23:01:38 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 23:01:55 - mmengine - INFO - Epoch(train) [209][50/586] lr: 5.000000e-05 eta: 0:05:58 time: 0.350609 data_time: 0.064988 memory: 4465 loss_kpt: 82.817933 acc_pose: 0.799523 loss: 82.817933 2022/10/12 23:02:13 - mmengine - INFO - Epoch(train) [209][100/586] lr: 5.000000e-05 eta: 0:05:42 time: 0.345714 data_time: 0.055003 memory: 4465 loss_kpt: 83.285036 acc_pose: 0.834249 loss: 83.285036 2022/10/12 23:02:17 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 23:02:30 - mmengine - INFO - Epoch(train) [209][150/586] lr: 5.000000e-05 eta: 0:05:26 time: 0.349868 data_time: 0.052700 memory: 4465 loss_kpt: 83.060736 acc_pose: 0.838163 loss: 83.060736 2022/10/12 23:02:47 - mmengine - INFO - Epoch(train) [209][200/586] lr: 5.000000e-05 eta: 0:05:10 time: 0.334584 data_time: 0.049343 memory: 4465 loss_kpt: 85.055466 acc_pose: 0.831420 loss: 85.055466 2022/10/12 23:03:04 - mmengine - INFO - Epoch(train) [209][250/586] lr: 5.000000e-05 eta: 0:04:54 time: 0.333634 data_time: 0.047476 memory: 4465 loss_kpt: 84.109839 acc_pose: 0.804865 loss: 84.109839 2022/10/12 23:03:21 - mmengine - INFO - Epoch(train) [209][300/586] lr: 5.000000e-05 eta: 0:04:38 time: 0.346752 data_time: 0.059909 memory: 4465 loss_kpt: 83.400477 acc_pose: 0.833986 loss: 83.400477 2022/10/12 23:03:38 - mmengine - INFO - Epoch(train) [209][350/586] lr: 5.000000e-05 eta: 0:04:22 time: 0.348874 data_time: 0.051483 memory: 4465 loss_kpt: 82.715470 acc_pose: 0.833575 loss: 82.715470 2022/10/12 23:03:56 - mmengine - INFO - Epoch(train) [209][400/586] lr: 5.000000e-05 eta: 0:04:06 time: 0.346099 data_time: 0.052355 memory: 4465 loss_kpt: 83.805460 acc_pose: 0.825161 loss: 83.805460 2022/10/12 23:04:14 - mmengine - INFO - Epoch(train) [209][450/586] lr: 5.000000e-05 eta: 0:03:50 time: 0.360822 data_time: 0.045392 memory: 4465 loss_kpt: 84.683696 acc_pose: 0.868973 loss: 84.683696 2022/10/12 23:04:31 - mmengine - INFO - Epoch(train) [209][500/586] lr: 5.000000e-05 eta: 0:03:34 time: 0.338484 data_time: 0.049909 memory: 4465 loss_kpt: 83.986051 acc_pose: 0.859923 loss: 83.986051 2022/10/12 23:04:48 - mmengine - INFO - Epoch(train) [209][550/586] lr: 5.000000e-05 eta: 0:03:18 time: 0.338477 data_time: 0.050903 memory: 4465 loss_kpt: 82.950451 acc_pose: 0.801045 loss: 82.950451 2022/10/12 23:05:00 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 23:05:16 - mmengine - INFO - Epoch(train) [210][50/586] lr: 5.000000e-05 eta: 0:02:51 time: 0.333123 data_time: 0.063479 memory: 4465 loss_kpt: 83.154169 acc_pose: 0.873360 loss: 83.154169 2022/10/12 23:05:34 - mmengine - INFO - Epoch(train) [210][100/586] lr: 5.000000e-05 eta: 0:02:35 time: 0.341134 data_time: 0.049429 memory: 4465 loss_kpt: 83.321221 acc_pose: 0.830687 loss: 83.321221 2022/10/12 23:05:51 - mmengine - INFO - Epoch(train) [210][150/586] lr: 5.000000e-05 eta: 0:02:19 time: 0.338931 data_time: 0.049075 memory: 4465 loss_kpt: 82.777076 acc_pose: 0.849670 loss: 82.777076 2022/10/12 23:06:08 - mmengine - INFO - Epoch(train) [210][200/586] lr: 5.000000e-05 eta: 0:02:03 time: 0.341501 data_time: 0.049035 memory: 4465 loss_kpt: 83.710001 acc_pose: 0.902684 loss: 83.710001 2022/10/12 23:06:25 - mmengine - INFO - Epoch(train) [210][250/586] lr: 5.000000e-05 eta: 0:01:47 time: 0.352917 data_time: 0.057032 memory: 4465 loss_kpt: 84.686047 acc_pose: 0.820713 loss: 84.686047 2022/10/12 23:06:43 - mmengine - INFO - Epoch(train) [210][300/586] lr: 5.000000e-05 eta: 0:01:31 time: 0.345272 data_time: 0.058735 memory: 4465 loss_kpt: 81.953479 acc_pose: 0.757124 loss: 81.953479 2022/10/12 23:07:00 - mmengine - INFO - Epoch(train) [210][350/586] lr: 5.000000e-05 eta: 0:01:15 time: 0.347692 data_time: 0.053044 memory: 4465 loss_kpt: 85.086707 acc_pose: 0.761619 loss: 85.086707 2022/10/12 23:07:17 - mmengine - INFO - Epoch(train) [210][400/586] lr: 5.000000e-05 eta: 0:00:59 time: 0.338846 data_time: 0.050364 memory: 4465 loss_kpt: 83.308345 acc_pose: 0.844057 loss: 83.308345 2022/10/12 23:07:34 - mmengine - INFO - Epoch(train) [210][450/586] lr: 5.000000e-05 eta: 0:00:43 time: 0.345426 data_time: 0.053058 memory: 4465 loss_kpt: 81.809340 acc_pose: 0.864026 loss: 81.809340 2022/10/12 23:07:51 - mmengine - INFO - Epoch(train) [210][500/586] lr: 5.000000e-05 eta: 0:00:27 time: 0.342730 data_time: 0.046323 memory: 4465 loss_kpt: 83.624012 acc_pose: 0.823231 loss: 83.624012 2022/10/12 23:08:00 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 23:08:09 - mmengine - INFO - Epoch(train) [210][550/586] lr: 5.000000e-05 eta: 0:00:11 time: 0.346598 data_time: 0.055921 memory: 4465 loss_kpt: 83.133861 acc_pose: 0.898739 loss: 83.133861 2022/10/12 23:08:21 - mmengine - INFO - Exp name: td-hm_rsn50_8xb32-210e_coco-256x192_20221012_110214 2022/10/12 23:08:21 - mmengine - INFO - Saving checkpoint at 210 epochs 2022/10/12 23:08:31 - mmengine - INFO - Epoch(val) [210][50/407] eta: 0:00:48 time: 0.134729 data_time: 0.012980 memory: 4465 2022/10/12 23:08:37 - mmengine - INFO - Epoch(val) [210][100/407] eta: 0:00:39 time: 0.128020 data_time: 0.008666 memory: 1026 2022/10/12 23:08:43 - mmengine - INFO - Epoch(val) [210][150/407] eta: 0:00:33 time: 0.129026 data_time: 0.008428 memory: 1026 2022/10/12 23:08:50 - mmengine - INFO - Epoch(val) [210][200/407] eta: 0:00:26 time: 0.128355 data_time: 0.008322 memory: 1026 2022/10/12 23:08:56 - mmengine - INFO - Epoch(val) [210][250/407] eta: 0:00:20 time: 0.127878 data_time: 0.008817 memory: 1026 2022/10/12 23:09:03 - mmengine - INFO - Epoch(val) [210][300/407] eta: 0:00:13 time: 0.130460 data_time: 0.011871 memory: 1026 2022/10/12 23:09:09 - mmengine - INFO - Epoch(val) [210][350/407] eta: 0:00:07 time: 0.127528 data_time: 0.008403 memory: 1026 2022/10/12 23:09:15 - mmengine - INFO - Epoch(val) [210][400/407] eta: 0:00:00 time: 0.125669 data_time: 0.008305 memory: 1026 2022/10/12 23:09:29 - mmengine - INFO - Evaluating CocoMetric... 2022/10/12 23:09:45 - mmengine - INFO - Epoch(val) [210][407/407] coco/AP: 0.724076 coco/AP .5: 0.894278 coco/AP .75: 0.798023 coco/AP (M): 0.689843 coco/AP (L): 0.787294 coco/AR: 0.790775 coco/AR .5: 0.934824 coco/AR .75: 0.851228 coco/AR (M): 0.746053 coco/AR (L): 0.852657 2022/10/12 23:09:45 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/liqikai/openmmlab/pt112cu113py38/mmpose/work_dirs/20221012/rsn50/best_coco/AP_epoch_200.pth is removed 2022/10/12 23:09:47 - mmengine - INFO - The best checkpoint with 0.7241 coco/AP at 210 epoch is saved to best_coco/AP_epoch_210.pth.