2022/09/17 13:04:24 - mmengine - INFO - ------------------------------------------------------------ System environment: sys.platform: linux Python: 3.7.13 (default, Mar 29 2022, 02:18:16) [GCC 7.5.0] CUDA available: True numpy_random_seed: 897248524 GPU 0,1,2,3,4,5,6,7: NVIDIA A100-SXM4-80GB CUDA_HOME: /mnt/lustre/share/cuda-11.1 NVCC: Cuda compilation tools, release 11.1, V11.1.74 GCC: gcc (GCC) 5.4.0 PyTorch: 1.9.0+cu111 PyTorch compiling details: PyTorch built with: - GCC 7.3 - 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 v2.1.2 (Git Hash 98be7e8afa711dc9b66c8ff3504129cb82013cdb) - OpenMP 201511 (a.k.a. OpenMP 4.5) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 11.1 - 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 8.0.5 - Magma 2.5.2 - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.1, CUDNN_VERSION=8.0.5, CXX_COMPILER=/opt/rh/devtoolset-7/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 -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -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 -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.9.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, TorchVision: 0.10.0+cu111 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 ------------------------------------------------------------ 2022/09/17 13:04:25 - 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=1, save_best='coco/AP', rule='greater', max_keep_ckpts=1), 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=0.0005)) 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=512) codec = dict( type='MSRAHeatmap', input_size=(192, 256), heatmap_size=(48, 64), sigma=2) 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='ViPNAS_ResNet', depth=50), head=dict( type='ViPNASHead', in_channels=608, out_channels=17, loss=dict(type='KeypointMSELoss', use_target_weight=True), decoder=dict( type='MSRAHeatmap', input_size=(192, 256), heatmap_size=(48, 64), sigma=2)), test_cfg=dict(flip_test=True, flip_mode='heatmap', shift_heatmap=True)) 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', rotate_factor=60, scale_factor=(0.75, 1.25)), dict(type='TopdownAffine', input_size=(192, 256)), dict( type='GenerateTarget', target_type='heatmap', encoder=dict( type='MSRAHeatmap', input_size=(192, 256), heatmap_size=(48, 64), sigma=2)), dict(type='PackPoseInputs') ] test_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=64, num_workers=2, 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', rotate_factor=60, scale_factor=(0.75, 1.25)), dict(type='TopdownAffine', input_size=(192, 256)), dict( type='GenerateTarget', target_type='heatmap', encoder=dict( type='MSRAHeatmap', input_size=(192, 256), heatmap_size=(48, 64), sigma=2)), dict(type='PackPoseInputs') ])) val_dataloader = dict( batch_size=32, num_workers=2, 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=2, 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') test_evaluator = dict( type='CocoMetric', ann_file='data/coco/annotations/person_keypoints_val2017.json') launcher = 'slurm' work_dir = '/mnt/lustre/liqikai/work_dirs/20220917/vipnas_res50/' 2022/09/17 13:05:03 - 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. 2022/09/17 13:05:03 - 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. 2022/09/17 13:05:03 - 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. 2022/09/17 13:05:03 - 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. 2022/09/17 13:05:03 - 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. 2022/09/17 13:05:03 - 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. 2022/09/17 13:05:03 - 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. 2022/09/17 13:05:03 - 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. 2022/09/17 13:05:07 - 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. 2022/09/17 13:05:09 - 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. 2022/09/17 13:05:09 - 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. 2022/09/17 13:05:09 - 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. 2022/09/17 13:05:09 - 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.conv1.weight - torch.Size([48, 3, 7, 7]): NormalInit: mean=0, std=0.001, bias=0 backbone.bn1.weight - torch.Size([48]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.bn1.bias - torch.Size([48]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.0.conv1.weight - torch.Size([80, 48, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer1.0.bn1.weight - torch.Size([80]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.0.bn1.bias - torch.Size([80]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.0.conv2.weight - torch.Size([80, 5, 3, 3]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer1.0.bn2.weight - torch.Size([80]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.0.bn2.bias - torch.Size([80]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.0.conv3.weight - torch.Size([80, 80, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer1.0.bn3.weight - torch.Size([80]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.0.bn3.bias - torch.Size([80]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.0.attention.conv_mask.weight - torch.Size([1, 80, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer1.0.attention.conv_mask.bias - torch.Size([1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.0.attention.channel_add_conv.0.weight - torch.Size([16, 80, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer1.0.attention.channel_add_conv.0.bias - torch.Size([16]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer1.0.attention.channel_add_conv.1.weight - torch.Size([16, 1, 1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.0.attention.channel_add_conv.1.bias - torch.Size([16, 1, 1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.0.attention.channel_add_conv.3.weight - torch.Size([80, 16, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer1.0.attention.channel_add_conv.3.bias - torch.Size([80]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.0.downsample.0.weight - torch.Size([80, 48, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer1.0.downsample.1.weight - torch.Size([80]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.0.downsample.1.bias - torch.Size([80]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.1.conv1.weight - torch.Size([80, 80, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer1.1.bn1.weight - torch.Size([80]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.1.bn1.bias - torch.Size([80]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.1.conv2.weight - torch.Size([80, 5, 3, 3]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer1.1.bn2.weight - torch.Size([80]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.1.bn2.bias - torch.Size([80]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.1.conv3.weight - torch.Size([80, 80, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer1.1.bn3.weight - torch.Size([80]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.1.bn3.bias - torch.Size([80]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.1.attention.conv_mask.weight - torch.Size([1, 80, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer1.1.attention.conv_mask.bias - torch.Size([1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.1.attention.channel_add_conv.0.weight - torch.Size([16, 80, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer1.1.attention.channel_add_conv.0.bias - torch.Size([16]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer1.1.attention.channel_add_conv.1.weight - torch.Size([16, 1, 1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.1.attention.channel_add_conv.1.bias - torch.Size([16, 1, 1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.1.attention.channel_add_conv.3.weight - torch.Size([80, 16, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer1.1.attention.channel_add_conv.3.bias - torch.Size([80]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.2.conv1.weight - torch.Size([80, 80, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer1.2.bn1.weight - torch.Size([80]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.2.bn1.bias - torch.Size([80]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.2.conv2.weight - torch.Size([80, 5, 3, 3]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer1.2.bn2.weight - torch.Size([80]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.2.bn2.bias - torch.Size([80]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.2.conv3.weight - torch.Size([80, 80, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer1.2.bn3.weight - torch.Size([80]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.2.bn3.bias - torch.Size([80]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.2.attention.conv_mask.weight - torch.Size([1, 80, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer1.2.attention.conv_mask.bias - torch.Size([1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.2.attention.channel_add_conv.0.weight - torch.Size([16, 80, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer1.2.attention.channel_add_conv.0.bias - torch.Size([16]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer1.2.attention.channel_add_conv.1.weight - torch.Size([16, 1, 1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.2.attention.channel_add_conv.1.bias - torch.Size([16, 1, 1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.2.attention.channel_add_conv.3.weight - torch.Size([80, 16, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer1.2.attention.channel_add_conv.3.bias - torch.Size([80]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.3.conv1.weight - torch.Size([80, 80, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer1.3.bn1.weight - torch.Size([80]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.3.bn1.bias - torch.Size([80]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.3.conv2.weight - torch.Size([80, 5, 3, 3]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer1.3.bn2.weight - torch.Size([80]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.3.bn2.bias - torch.Size([80]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.3.conv3.weight - torch.Size([80, 80, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer1.3.bn3.weight - torch.Size([80]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.3.bn3.bias - torch.Size([80]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.3.attention.conv_mask.weight - torch.Size([1, 80, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer1.3.attention.conv_mask.bias - torch.Size([1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.3.attention.channel_add_conv.0.weight - torch.Size([16, 80, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer1.3.attention.channel_add_conv.0.bias - torch.Size([16]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer1.3.attention.channel_add_conv.1.weight - torch.Size([16, 1, 1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.3.attention.channel_add_conv.1.bias - torch.Size([16, 1, 1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer1.3.attention.channel_add_conv.3.weight - torch.Size([80, 16, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer1.3.attention.channel_add_conv.3.bias - torch.Size([80]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.0.conv1.weight - torch.Size([160, 80, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer2.0.bn1.weight - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.0.bn1.bias - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.0.conv2.weight - torch.Size([160, 10, 5, 5]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer2.0.bn2.weight - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.0.bn2.bias - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.0.conv3.weight - torch.Size([160, 160, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer2.0.bn3.weight - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.0.bn3.bias - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.0.downsample.0.weight - torch.Size([160, 80, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer2.0.downsample.1.weight - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.0.downsample.1.bias - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.1.conv1.weight - torch.Size([160, 160, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer2.1.bn1.weight - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.1.bn1.bias - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.1.conv2.weight - torch.Size([160, 10, 5, 5]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer2.1.bn2.weight - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.1.bn2.bias - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.1.conv3.weight - torch.Size([160, 160, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer2.1.bn3.weight - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.1.bn3.bias - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.2.conv1.weight - torch.Size([160, 160, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer2.2.bn1.weight - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.2.bn1.bias - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.2.conv2.weight - torch.Size([160, 10, 5, 5]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer2.2.bn2.weight - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.2.bn2.bias - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.2.conv3.weight - torch.Size([160, 160, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer2.2.bn3.weight - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.2.bn3.bias - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.3.conv1.weight - torch.Size([160, 160, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer2.3.bn1.weight - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.3.bn1.bias - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.3.conv2.weight - torch.Size([160, 10, 5, 5]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer2.3.bn2.weight - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.3.bn2.bias - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.3.conv3.weight - torch.Size([160, 160, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer2.3.bn3.weight - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.3.bn3.bias - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.4.conv1.weight - torch.Size([160, 160, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer2.4.bn1.weight - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.4.bn1.bias - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.4.conv2.weight - torch.Size([160, 10, 5, 5]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer2.4.bn2.weight - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.4.bn2.bias - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.4.conv3.weight - torch.Size([160, 160, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer2.4.bn3.weight - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.4.bn3.bias - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.5.conv1.weight - torch.Size([160, 160, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer2.5.bn1.weight - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.5.bn1.bias - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.5.conv2.weight - torch.Size([160, 10, 5, 5]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer2.5.bn2.weight - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.5.bn2.bias - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.5.conv3.weight - torch.Size([160, 160, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer2.5.bn3.weight - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer2.5.bn3.bias - torch.Size([160]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.0.conv1.weight - torch.Size([304, 160, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.0.bn1.weight - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.0.bn1.bias - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.0.conv2.weight - torch.Size([304, 19, 5, 5]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.0.bn2.weight - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.0.bn2.bias - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.0.conv3.weight - torch.Size([304, 304, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.0.bn3.weight - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.0.bn3.bias - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.0.attention.conv_mask.weight - torch.Size([1, 304, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.0.attention.conv_mask.bias - torch.Size([1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.0.attention.channel_add_conv.0.weight - torch.Size([19, 304, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.0.attention.channel_add_conv.0.bias - torch.Size([19]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.0.attention.channel_add_conv.1.weight - torch.Size([19, 1, 1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.0.attention.channel_add_conv.1.bias - torch.Size([19, 1, 1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.0.attention.channel_add_conv.3.weight - torch.Size([304, 19, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.0.attention.channel_add_conv.3.bias - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.0.downsample.0.weight - torch.Size([304, 160, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.0.downsample.1.weight - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.0.downsample.1.bias - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.1.conv1.weight - torch.Size([304, 304, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.1.bn1.weight - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.1.bn1.bias - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.1.conv2.weight - torch.Size([304, 19, 5, 5]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.1.bn2.weight - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.1.bn2.bias - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.1.conv3.weight - torch.Size([304, 304, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.1.bn3.weight - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.1.bn3.bias - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.1.attention.conv_mask.weight - torch.Size([1, 304, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.1.attention.conv_mask.bias - torch.Size([1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.1.attention.channel_add_conv.0.weight - torch.Size([19, 304, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.1.attention.channel_add_conv.0.bias - torch.Size([19]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.1.attention.channel_add_conv.1.weight - torch.Size([19, 1, 1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.1.attention.channel_add_conv.1.bias - torch.Size([19, 1, 1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.1.attention.channel_add_conv.3.weight - torch.Size([304, 19, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.1.attention.channel_add_conv.3.bias - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.2.conv1.weight - torch.Size([304, 304, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.2.bn1.weight - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.2.bn1.bias - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.2.conv2.weight - torch.Size([304, 19, 5, 5]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.2.bn2.weight - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.2.bn2.bias - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.2.conv3.weight - torch.Size([304, 304, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.2.bn3.weight - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.2.bn3.bias - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.2.attention.conv_mask.weight - torch.Size([1, 304, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.2.attention.conv_mask.bias - torch.Size([1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.2.attention.channel_add_conv.0.weight - torch.Size([19, 304, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.2.attention.channel_add_conv.0.bias - torch.Size([19]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.2.attention.channel_add_conv.1.weight - torch.Size([19, 1, 1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.2.attention.channel_add_conv.1.bias - torch.Size([19, 1, 1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.2.attention.channel_add_conv.3.weight - torch.Size([304, 19, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.2.attention.channel_add_conv.3.bias - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.3.conv1.weight - torch.Size([304, 304, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.3.bn1.weight - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.3.bn1.bias - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.3.conv2.weight - torch.Size([304, 19, 5, 5]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.3.bn2.weight - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.3.bn2.bias - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.3.conv3.weight - torch.Size([304, 304, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.3.bn3.weight - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.3.bn3.bias - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.3.attention.conv_mask.weight - torch.Size([1, 304, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.3.attention.conv_mask.bias - torch.Size([1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.3.attention.channel_add_conv.0.weight - torch.Size([19, 304, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.3.attention.channel_add_conv.0.bias - torch.Size([19]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.3.attention.channel_add_conv.1.weight - torch.Size([19, 1, 1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.3.attention.channel_add_conv.1.bias - torch.Size([19, 1, 1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.3.attention.channel_add_conv.3.weight - torch.Size([304, 19, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.3.attention.channel_add_conv.3.bias - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.4.conv1.weight - torch.Size([304, 304, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.4.bn1.weight - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.4.bn1.bias - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.4.conv2.weight - torch.Size([304, 19, 5, 5]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.4.bn2.weight - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.4.bn2.bias - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.4.conv3.weight - torch.Size([304, 304, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.4.bn3.weight - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.4.bn3.bias - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.4.attention.conv_mask.weight - torch.Size([1, 304, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.4.attention.conv_mask.bias - torch.Size([1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.4.attention.channel_add_conv.0.weight - torch.Size([19, 304, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.4.attention.channel_add_conv.0.bias - torch.Size([19]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.4.attention.channel_add_conv.1.weight - torch.Size([19, 1, 1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.4.attention.channel_add_conv.1.bias - torch.Size([19, 1, 1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.4.attention.channel_add_conv.3.weight - torch.Size([304, 19, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.4.attention.channel_add_conv.3.bias - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.5.conv1.weight - torch.Size([304, 304, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.5.bn1.weight - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.5.bn1.bias - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.5.conv2.weight - torch.Size([304, 19, 5, 5]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.5.bn2.weight - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.5.bn2.bias - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.5.conv3.weight - torch.Size([304, 304, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.5.bn3.weight - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.5.bn3.bias - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.5.attention.conv_mask.weight - torch.Size([1, 304, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.5.attention.conv_mask.bias - torch.Size([1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.5.attention.channel_add_conv.0.weight - torch.Size([19, 304, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.5.attention.channel_add_conv.0.bias - torch.Size([19]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.5.attention.channel_add_conv.1.weight - torch.Size([19, 1, 1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.5.attention.channel_add_conv.1.bias - torch.Size([19, 1, 1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.5.attention.channel_add_conv.3.weight - torch.Size([304, 19, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.5.attention.channel_add_conv.3.bias - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.6.conv1.weight - torch.Size([304, 304, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.6.bn1.weight - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.6.bn1.bias - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.6.conv2.weight - torch.Size([304, 19, 5, 5]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.6.bn2.weight - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.6.bn2.bias - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.6.conv3.weight - torch.Size([304, 304, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.6.bn3.weight - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.6.bn3.bias - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.6.attention.conv_mask.weight - torch.Size([1, 304, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.6.attention.conv_mask.bias - torch.Size([1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.6.attention.channel_add_conv.0.weight - torch.Size([19, 304, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.6.attention.channel_add_conv.0.bias - torch.Size([19]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.6.attention.channel_add_conv.1.weight - torch.Size([19, 1, 1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.6.attention.channel_add_conv.1.bias - torch.Size([19, 1, 1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer3.6.attention.channel_add_conv.3.weight - torch.Size([304, 19, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer3.6.attention.channel_add_conv.3.bias - torch.Size([304]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer4.0.conv1.weight - torch.Size([608, 304, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer4.0.bn1.weight - torch.Size([608]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer4.0.bn1.bias - torch.Size([608]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer4.0.conv2.weight - torch.Size([608, 38, 5, 5]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer4.0.bn2.weight - torch.Size([608]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer4.0.bn2.bias - torch.Size([608]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer4.0.conv3.weight - torch.Size([608, 608, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer4.0.bn3.weight - torch.Size([608]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer4.0.bn3.bias - torch.Size([608]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer4.0.attention.conv_mask.weight - torch.Size([1, 608, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer4.0.attention.conv_mask.bias - torch.Size([1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer4.0.attention.channel_add_conv.0.weight - torch.Size([38, 608, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer4.0.attention.channel_add_conv.0.bias - torch.Size([38]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer4.0.attention.channel_add_conv.1.weight - torch.Size([38, 1, 1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer4.0.attention.channel_add_conv.1.bias - torch.Size([38, 1, 1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer4.0.attention.channel_add_conv.3.weight - torch.Size([608, 38, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer4.0.attention.channel_add_conv.3.bias - torch.Size([608]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer4.0.downsample.0.weight - torch.Size([608, 304, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer4.0.downsample.1.weight - torch.Size([608]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer4.0.downsample.1.bias - torch.Size([608]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer4.1.conv1.weight - torch.Size([608, 608, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer4.1.bn1.weight - torch.Size([608]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer4.1.bn1.bias - torch.Size([608]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer4.1.conv2.weight - torch.Size([608, 38, 5, 5]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer4.1.bn2.weight - torch.Size([608]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer4.1.bn2.bias - torch.Size([608]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer4.1.conv3.weight - torch.Size([608, 608, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer4.1.bn3.weight - torch.Size([608]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer4.1.bn3.bias - torch.Size([608]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer4.1.attention.conv_mask.weight - torch.Size([1, 608, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer4.1.attention.conv_mask.bias - torch.Size([1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer4.1.attention.channel_add_conv.0.weight - torch.Size([38, 608, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer4.1.attention.channel_add_conv.0.bias - torch.Size([38]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer4.1.attention.channel_add_conv.1.weight - torch.Size([38, 1, 1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer4.1.attention.channel_add_conv.1.bias - torch.Size([38, 1, 1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer4.1.attention.channel_add_conv.3.weight - torch.Size([608, 38, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer4.1.attention.channel_add_conv.3.bias - torch.Size([608]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer4.2.conv1.weight - torch.Size([608, 608, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer4.2.bn1.weight - torch.Size([608]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer4.2.bn1.bias - torch.Size([608]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer4.2.conv2.weight - torch.Size([608, 38, 5, 5]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer4.2.bn2.weight - torch.Size([608]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer4.2.bn2.bias - torch.Size([608]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer4.2.conv3.weight - torch.Size([608, 608, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer4.2.bn3.weight - torch.Size([608]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer4.2.bn3.bias - torch.Size([608]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer4.2.attention.conv_mask.weight - torch.Size([1, 608, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer4.2.attention.conv_mask.bias - torch.Size([1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer4.2.attention.channel_add_conv.0.weight - torch.Size([38, 608, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer4.2.attention.channel_add_conv.0.bias - torch.Size([38]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer4.2.attention.channel_add_conv.1.weight - torch.Size([38, 1, 1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer4.2.attention.channel_add_conv.1.bias - torch.Size([38, 1, 1]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator backbone.layer4.2.attention.channel_add_conv.3.weight - torch.Size([608, 38, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 backbone.layer4.2.attention.channel_add_conv.3.bias - torch.Size([608]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.deconv_layers.0.weight - torch.Size([608, 9, 4, 4]): NormalInit: mean=0, std=0.001, bias=0 head.deconv_layers.1.weight - torch.Size([144]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.deconv_layers.1.bias - torch.Size([144]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.deconv_layers.3.weight - torch.Size([144, 9, 4, 4]): NormalInit: mean=0, std=0.001, bias=0 head.deconv_layers.4.weight - torch.Size([144]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.deconv_layers.4.bias - torch.Size([144]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.deconv_layers.6.weight - torch.Size([144, 9, 4, 4]): NormalInit: mean=0, std=0.001, bias=0 head.deconv_layers.7.weight - torch.Size([144]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.deconv_layers.7.bias - torch.Size([144]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.final_layer.weight - torch.Size([17, 144, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 head.final_layer.bias - torch.Size([17]): NormalInit: mean=0, std=0.001, bias=0 2022/09/17 13:05:09 - mmengine - INFO - Checkpoints will be saved to /mnt/lustre/liqikai/work_dirs/20220917/vipnas_res50 by HardDiskBackend. 2022/09/17 13:07:42 - mmengine - INFO - Epoch(train) [1][50/293] lr: 4.954910e-05 eta: 2 days, 4:21:37 time: 3.065991 data_time: 0.718500 memory: 5151 loss_kpt: 0.002333 acc_pose: 0.068202 loss: 0.002333 2022/09/17 13:08:50 - mmengine - INFO - Epoch(train) [1][100/293] lr: 9.959920e-05 eta: 1 day, 13:43:37 time: 1.355860 data_time: 0.220010 memory: 5151 loss_kpt: 0.002114 acc_pose: 0.189193 loss: 0.002114 2022/09/17 13:09:39 - mmengine - INFO - Epoch(train) [1][150/293] lr: 1.496493e-04 eta: 1 day, 6:39:36 time: 0.972913 data_time: 0.329677 memory: 5151 loss_kpt: 0.001956 acc_pose: 0.241687 loss: 0.001956 2022/09/17 13:10:22 - mmengine - INFO - Epoch(train) [1][200/293] lr: 1.996994e-04 eta: 1 day, 2:42:07 time: 0.874740 data_time: 0.117913 memory: 5151 loss_kpt: 0.001845 acc_pose: 0.344200 loss: 0.001845 2022/09/17 13:11:21 - mmengine - INFO - Epoch(train) [1][250/293] lr: 2.497495e-04 eta: 1 day, 1:21:16 time: 1.177965 data_time: 0.097946 memory: 5151 loss_kpt: 0.001718 acc_pose: 0.444753 loss: 0.001718 2022/09/17 13:11:56 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 13:11:56 - mmengine - INFO - Saving checkpoint at 1 epochs 2022/09/17 13:12:15 - mmengine - INFO - Epoch(train) [2][50/293] lr: 3.428427e-04 eta: 19:17:40 time: 0.340110 data_time: 0.064241 memory: 5151 loss_kpt: 0.001590 acc_pose: 0.454484 loss: 0.001590 2022/09/17 13:12:31 - mmengine - INFO - Epoch(train) [2][100/293] lr: 3.928928e-04 eta: 17:30:49 time: 0.318247 data_time: 0.052316 memory: 5151 loss_kpt: 0.001535 acc_pose: 0.468624 loss: 0.001535 2022/09/17 13:12:47 - mmengine - INFO - Epoch(train) [2][150/293] lr: 4.429429e-04 eta: 16:09:09 time: 0.328174 data_time: 0.067139 memory: 5151 loss_kpt: 0.001489 acc_pose: 0.476156 loss: 0.001489 2022/09/17 13:13:04 - mmengine - INFO - Epoch(train) [2][200/293] lr: 4.929930e-04 eta: 15:05:56 time: 0.346796 data_time: 0.064137 memory: 5151 loss_kpt: 0.001460 acc_pose: 0.472560 loss: 0.001460 2022/09/17 13:13:21 - mmengine - INFO - Epoch(train) [2][250/293] lr: 5.000000e-04 eta: 14:12:36 time: 0.328663 data_time: 0.065258 memory: 5151 loss_kpt: 0.001422 acc_pose: 0.547711 loss: 0.001422 2022/09/17 13:13:35 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 13:13:35 - mmengine - INFO - Saving checkpoint at 2 epochs 2022/09/17 13:13:55 - mmengine - INFO - Epoch(train) [3][50/293] lr: 5.000000e-04 eta: 12:35:09 time: 0.355055 data_time: 0.075981 memory: 5151 loss_kpt: 0.001351 acc_pose: 0.566500 loss: 0.001351 2022/09/17 13:14:12 - mmengine - INFO - Epoch(train) [3][100/293] lr: 5.000000e-04 eta: 12:04:32 time: 0.338375 data_time: 0.061439 memory: 5151 loss_kpt: 0.001336 acc_pose: 0.576125 loss: 0.001336 2022/09/17 13:14:29 - mmengine - INFO - Epoch(train) [3][150/293] lr: 5.000000e-04 eta: 11:37:51 time: 0.335353 data_time: 0.060181 memory: 5151 loss_kpt: 0.001325 acc_pose: 0.542710 loss: 0.001325 2022/09/17 13:14:45 - mmengine - INFO - Epoch(train) [3][200/293] lr: 5.000000e-04 eta: 11:13:54 time: 0.325713 data_time: 0.063702 memory: 5151 loss_kpt: 0.001275 acc_pose: 0.585345 loss: 0.001275 2022/09/17 13:15:02 - mmengine - INFO - Epoch(train) [3][250/293] lr: 5.000000e-04 eta: 10:53:02 time: 0.330052 data_time: 0.059592 memory: 5151 loss_kpt: 0.001243 acc_pose: 0.588552 loss: 0.001243 2022/09/17 13:15:15 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 13:15:15 - mmengine - INFO - Saving checkpoint at 3 epochs 2022/09/17 13:15:35 - mmengine - INFO - Epoch(train) [4][50/293] lr: 5.000000e-04 eta: 10:05:27 time: 0.343958 data_time: 0.067084 memory: 5151 loss_kpt: 0.001250 acc_pose: 0.586643 loss: 0.001250 2022/09/17 13:15:51 - mmengine - INFO - Epoch(train) [4][100/293] lr: 5.000000e-04 eta: 9:50:45 time: 0.323797 data_time: 0.060432 memory: 5151 loss_kpt: 0.001232 acc_pose: 0.588690 loss: 0.001232 2022/09/17 13:15:59 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 13:16:08 - mmengine - INFO - Epoch(train) [4][150/293] lr: 5.000000e-04 eta: 9:37:53 time: 0.332788 data_time: 0.057855 memory: 5151 loss_kpt: 0.001208 acc_pose: 0.597429 loss: 0.001208 2022/09/17 13:16:25 - mmengine - INFO - Epoch(train) [4][200/293] lr: 5.000000e-04 eta: 9:27:03 time: 0.351358 data_time: 0.067413 memory: 5151 loss_kpt: 0.001183 acc_pose: 0.520693 loss: 0.001183 2022/09/17 13:16:42 - mmengine - INFO - Epoch(train) [4][250/293] lr: 5.000000e-04 eta: 9:16:04 time: 0.326972 data_time: 0.064543 memory: 5151 loss_kpt: 0.001199 acc_pose: 0.637994 loss: 0.001199 2022/09/17 13:16:56 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 13:16:56 - mmengine - INFO - Saving checkpoint at 4 epochs 2022/09/17 13:17:15 - mmengine - INFO - Epoch(train) [5][50/293] lr: 5.000000e-04 eta: 8:47:02 time: 0.342384 data_time: 0.074643 memory: 5151 loss_kpt: 0.001148 acc_pose: 0.676009 loss: 0.001148 2022/09/17 13:17:32 - mmengine - INFO - Epoch(train) [5][100/293] lr: 5.000000e-04 eta: 8:39:06 time: 0.334222 data_time: 0.066820 memory: 5151 loss_kpt: 0.001184 acc_pose: 0.603566 loss: 0.001184 2022/09/17 13:17:49 - mmengine - INFO - Epoch(train) [5][150/293] lr: 5.000000e-04 eta: 8:31:43 time: 0.333669 data_time: 0.067825 memory: 5151 loss_kpt: 0.001139 acc_pose: 0.634621 loss: 0.001139 2022/09/17 13:18:05 - mmengine - INFO - Epoch(train) [5][200/293] lr: 5.000000e-04 eta: 8:24:34 time: 0.326022 data_time: 0.068812 memory: 5151 loss_kpt: 0.001134 acc_pose: 0.640626 loss: 0.001134 2022/09/17 13:18:22 - mmengine - INFO - Epoch(train) [5][250/293] lr: 5.000000e-04 eta: 8:18:17 time: 0.336906 data_time: 0.069434 memory: 5151 loss_kpt: 0.001136 acc_pose: 0.671956 loss: 0.001136 2022/09/17 13:18:37 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 13:18:37 - mmengine - INFO - Saving checkpoint at 5 epochs 2022/09/17 13:18:57 - mmengine - INFO - Epoch(train) [6][50/293] lr: 5.000000e-04 eta: 7:58:33 time: 0.350856 data_time: 0.080879 memory: 5151 loss_kpt: 0.001124 acc_pose: 0.636280 loss: 0.001124 2022/09/17 13:19:13 - mmengine - INFO - Epoch(train) [6][100/293] lr: 5.000000e-04 eta: 7:53:22 time: 0.328551 data_time: 0.063873 memory: 5151 loss_kpt: 0.001117 acc_pose: 0.614075 loss: 0.001117 2022/09/17 13:19:30 - mmengine - INFO - Epoch(train) [6][150/293] lr: 5.000000e-04 eta: 7:48:50 time: 0.339795 data_time: 0.064182 memory: 5151 loss_kpt: 0.001115 acc_pose: 0.679805 loss: 0.001115 2022/09/17 13:19:47 - mmengine - INFO - Epoch(train) [6][200/293] lr: 5.000000e-04 eta: 7:44:32 time: 0.338737 data_time: 0.062898 memory: 5151 loss_kpt: 0.001112 acc_pose: 0.682491 loss: 0.001112 2022/09/17 13:20:04 - mmengine - INFO - Epoch(train) [6][250/293] lr: 5.000000e-04 eta: 7:40:12 time: 0.329887 data_time: 0.064657 memory: 5151 loss_kpt: 0.001102 acc_pose: 0.652560 loss: 0.001102 2022/09/17 13:20:17 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 13:20:17 - mmengine - INFO - Saving checkpoint at 6 epochs 2022/09/17 13:20:37 - mmengine - INFO - Epoch(train) [7][50/293] lr: 5.000000e-04 eta: 7:25:15 time: 0.341407 data_time: 0.072540 memory: 5151 loss_kpt: 0.001086 acc_pose: 0.656273 loss: 0.001086 2022/09/17 13:20:53 - mmengine - INFO - Epoch(train) [7][100/293] lr: 5.000000e-04 eta: 7:21:37 time: 0.325732 data_time: 0.055075 memory: 5151 loss_kpt: 0.001088 acc_pose: 0.649357 loss: 0.001088 2022/09/17 13:21:09 - mmengine - INFO - Epoch(train) [7][150/293] lr: 5.000000e-04 eta: 7:18:17 time: 0.330405 data_time: 0.065400 memory: 5151 loss_kpt: 0.001075 acc_pose: 0.700243 loss: 0.001075 2022/09/17 13:21:26 - mmengine - INFO - Epoch(train) [7][200/293] lr: 5.000000e-04 eta: 7:15:08 time: 0.331384 data_time: 0.066017 memory: 5151 loss_kpt: 0.001071 acc_pose: 0.710533 loss: 0.001071 2022/09/17 13:21:40 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 13:21:42 - mmengine - INFO - Epoch(train) [7][250/293] lr: 5.000000e-04 eta: 7:12:06 time: 0.329735 data_time: 0.061113 memory: 5151 loss_kpt: 0.001057 acc_pose: 0.698811 loss: 0.001057 2022/09/17 13:21:57 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 13:21:57 - mmengine - INFO - Saving checkpoint at 7 epochs 2022/09/17 13:22:17 - mmengine - INFO - Epoch(train) [8][50/293] lr: 5.000000e-04 eta: 7:00:31 time: 0.347861 data_time: 0.063749 memory: 5151 loss_kpt: 0.001051 acc_pose: 0.635601 loss: 0.001051 2022/09/17 13:22:33 - mmengine - INFO - Epoch(train) [8][100/293] lr: 5.000000e-04 eta: 6:57:44 time: 0.318762 data_time: 0.058535 memory: 5151 loss_kpt: 0.001052 acc_pose: 0.756581 loss: 0.001052 2022/09/17 13:22:50 - mmengine - INFO - Epoch(train) [8][150/293] lr: 5.000000e-04 eta: 6:55:09 time: 0.322630 data_time: 0.058968 memory: 5151 loss_kpt: 0.001038 acc_pose: 0.737751 loss: 0.001038 2022/09/17 13:23:06 - mmengine - INFO - Epoch(train) [8][200/293] lr: 5.000000e-04 eta: 6:52:54 time: 0.333684 data_time: 0.068023 memory: 5151 loss_kpt: 0.001034 acc_pose: 0.654961 loss: 0.001034 2022/09/17 13:23:23 - mmengine - INFO - Epoch(train) [8][250/293] lr: 5.000000e-04 eta: 6:50:38 time: 0.328246 data_time: 0.062412 memory: 5151 loss_kpt: 0.001038 acc_pose: 0.663345 loss: 0.001038 2022/09/17 13:23:37 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 13:23:37 - mmengine - INFO - Saving checkpoint at 8 epochs 2022/09/17 13:23:56 - mmengine - INFO - Epoch(train) [9][50/293] lr: 5.000000e-04 eta: 6:41:03 time: 0.339848 data_time: 0.069671 memory: 5151 loss_kpt: 0.001039 acc_pose: 0.714182 loss: 0.001039 2022/09/17 13:24:13 - mmengine - INFO - Epoch(train) [9][100/293] lr: 5.000000e-04 eta: 6:39:23 time: 0.340338 data_time: 0.075492 memory: 5151 loss_kpt: 0.001033 acc_pose: 0.699506 loss: 0.001033 2022/09/17 13:24:29 - mmengine - INFO - Epoch(train) [9][150/293] lr: 5.000000e-04 eta: 6:37:32 time: 0.329153 data_time: 0.057851 memory: 5151 loss_kpt: 0.001024 acc_pose: 0.653559 loss: 0.001024 2022/09/17 13:24:46 - mmengine - INFO - Epoch(train) [9][200/293] lr: 5.000000e-04 eta: 6:35:50 time: 0.333407 data_time: 0.057985 memory: 5151 loss_kpt: 0.001004 acc_pose: 0.682271 loss: 0.001004 2022/09/17 13:25:03 - mmengine - INFO - Epoch(train) [9][250/293] lr: 5.000000e-04 eta: 6:34:07 time: 0.329678 data_time: 0.059074 memory: 5151 loss_kpt: 0.001024 acc_pose: 0.652870 loss: 0.001024 2022/09/17 13:25:17 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 13:25:17 - mmengine - INFO - Saving checkpoint at 9 epochs 2022/09/17 13:25:38 - mmengine - INFO - Epoch(train) [10][50/293] lr: 5.000000e-04 eta: 6:26:26 time: 0.359938 data_time: 0.071905 memory: 5151 loss_kpt: 0.001008 acc_pose: 0.667876 loss: 0.001008 2022/09/17 13:25:54 - mmengine - INFO - Epoch(train) [10][100/293] lr: 5.000000e-04 eta: 6:25:00 time: 0.331966 data_time: 0.062114 memory: 5151 loss_kpt: 0.000986 acc_pose: 0.701727 loss: 0.000986 2022/09/17 13:26:11 - mmengine - INFO - Epoch(train) [10][150/293] lr: 5.000000e-04 eta: 6:23:34 time: 0.330232 data_time: 0.070451 memory: 5151 loss_kpt: 0.000993 acc_pose: 0.702807 loss: 0.000993 2022/09/17 13:26:27 - mmengine - INFO - Epoch(train) [10][200/293] lr: 5.000000e-04 eta: 6:22:16 time: 0.335426 data_time: 0.060337 memory: 5151 loss_kpt: 0.000997 acc_pose: 0.680734 loss: 0.000997 2022/09/17 13:26:44 - mmengine - INFO - Epoch(train) [10][250/293] lr: 5.000000e-04 eta: 6:20:58 time: 0.332389 data_time: 0.059546 memory: 5151 loss_kpt: 0.001000 acc_pose: 0.689071 loss: 0.001000 2022/09/17 13:26:59 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 13:26:59 - mmengine - INFO - Saving checkpoint at 10 epochs 2022/09/17 13:27:13 - mmengine - INFO - Epoch(val) [10][50/407] eta: 0:01:29 time: 0.250309 data_time: 0.179144 memory: 5151 2022/09/17 13:27:20 - mmengine - INFO - Epoch(val) [10][100/407] eta: 0:00:37 time: 0.122548 data_time: 0.056509 memory: 331 2022/09/17 13:27:25 - mmengine - INFO - Epoch(val) [10][150/407] eta: 0:00:30 time: 0.118700 data_time: 0.049580 memory: 331 2022/09/17 13:27:31 - mmengine - INFO - Epoch(val) [10][200/407] eta: 0:00:23 time: 0.113382 data_time: 0.047536 memory: 331 2022/09/17 13:27:37 - mmengine - INFO - Epoch(val) [10][250/407] eta: 0:00:17 time: 0.114375 data_time: 0.047491 memory: 331 2022/09/17 13:27:43 - mmengine - INFO - Epoch(val) [10][300/407] eta: 0:00:12 time: 0.114019 data_time: 0.047135 memory: 331 2022/09/17 13:27:49 - mmengine - INFO - Epoch(val) [10][350/407] eta: 0:00:07 time: 0.134357 data_time: 0.060450 memory: 331 2022/09/17 13:27:55 - mmengine - INFO - Epoch(val) [10][400/407] eta: 0:00:00 time: 0.112415 data_time: 0.046803 memory: 331 2022/09/17 13:28:32 - mmengine - INFO - Evaluating CocoMetric... 2022/09/17 13:28:46 - mmengine - INFO - Epoch(val) [10][407/407] coco/AP: 0.559516 coco/AP .5: 0.820799 coco/AP .75: 0.616559 coco/AP (M): 0.536907 coco/AP (L): 0.610383 coco/AR: 0.626480 coco/AR .5: 0.870435 coco/AR .75: 0.685611 coco/AR (M): 0.592406 coco/AR (L): 0.675139 2022/09/17 13:28:48 - mmengine - INFO - The best checkpoint with 0.5595 coco/AP at 10 epoch is saved to best_coco/AP_epoch_10.pth. 2022/09/17 13:29:05 - mmengine - INFO - Epoch(train) [11][50/293] lr: 5.000000e-04 eta: 6:14:00 time: 0.336724 data_time: 0.067107 memory: 5151 loss_kpt: 0.000976 acc_pose: 0.757825 loss: 0.000976 2022/09/17 13:29:12 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 13:29:22 - mmengine - INFO - Epoch(train) [11][100/293] lr: 5.000000e-04 eta: 6:12:56 time: 0.337359 data_time: 0.059387 memory: 5151 loss_kpt: 0.000980 acc_pose: 0.718618 loss: 0.000980 2022/09/17 13:29:39 - mmengine - INFO - Epoch(train) [11][150/293] lr: 5.000000e-04 eta: 6:12:01 time: 0.343910 data_time: 0.070175 memory: 5151 loss_kpt: 0.000988 acc_pose: 0.754482 loss: 0.000988 2022/09/17 13:29:56 - mmengine - INFO - Epoch(train) [11][200/293] lr: 5.000000e-04 eta: 6:11:01 time: 0.338694 data_time: 0.064680 memory: 5151 loss_kpt: 0.000973 acc_pose: 0.709342 loss: 0.000973 2022/09/17 13:30:13 - mmengine - INFO - Epoch(train) [11][250/293] lr: 5.000000e-04 eta: 6:10:03 time: 0.338331 data_time: 0.062266 memory: 5151 loss_kpt: 0.000992 acc_pose: 0.672351 loss: 0.000992 2022/09/17 13:30:28 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 13:30:28 - mmengine - INFO - Saving checkpoint at 11 epochs 2022/09/17 13:30:47 - mmengine - INFO - Epoch(train) [12][50/293] lr: 5.000000e-04 eta: 6:03:52 time: 0.331024 data_time: 0.064520 memory: 5151 loss_kpt: 0.000970 acc_pose: 0.656711 loss: 0.000970 2022/09/17 13:31:03 - mmengine - INFO - Epoch(train) [12][100/293] lr: 5.000000e-04 eta: 6:02:56 time: 0.332420 data_time: 0.060208 memory: 5151 loss_kpt: 0.000969 acc_pose: 0.704175 loss: 0.000969 2022/09/17 13:31:20 - mmengine - INFO - Epoch(train) [12][150/293] lr: 5.000000e-04 eta: 6:01:57 time: 0.326521 data_time: 0.061070 memory: 5151 loss_kpt: 0.000969 acc_pose: 0.764186 loss: 0.000969 2022/09/17 13:31:36 - mmengine - INFO - Epoch(train) [12][200/293] lr: 5.000000e-04 eta: 6:01:06 time: 0.335245 data_time: 0.063265 memory: 5151 loss_kpt: 0.000949 acc_pose: 0.738159 loss: 0.000949 2022/09/17 13:31:53 - mmengine - INFO - Epoch(train) [12][250/293] lr: 5.000000e-04 eta: 6:00:12 time: 0.331345 data_time: 0.054659 memory: 5151 loss_kpt: 0.000976 acc_pose: 0.751240 loss: 0.000976 2022/09/17 13:32:08 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 13:32:08 - mmengine - INFO - Saving checkpoint at 12 epochs 2022/09/17 13:32:28 - mmengine - INFO - Epoch(train) [13][50/293] lr: 5.000000e-04 eta: 5:54:59 time: 0.349142 data_time: 0.070512 memory: 5151 loss_kpt: 0.000958 acc_pose: 0.718284 loss: 0.000958 2022/09/17 13:32:44 - mmengine - INFO - Epoch(train) [13][100/293] lr: 5.000000e-04 eta: 5:54:12 time: 0.331815 data_time: 0.068717 memory: 5151 loss_kpt: 0.000937 acc_pose: 0.726315 loss: 0.000937 2022/09/17 13:33:01 - mmengine - INFO - Epoch(train) [13][150/293] lr: 5.000000e-04 eta: 5:53:35 time: 0.344050 data_time: 0.064946 memory: 5151 loss_kpt: 0.000947 acc_pose: 0.690591 loss: 0.000947 2022/09/17 13:33:18 - mmengine - INFO - Epoch(train) [13][200/293] lr: 5.000000e-04 eta: 5:52:45 time: 0.325045 data_time: 0.064209 memory: 5151 loss_kpt: 0.000961 acc_pose: 0.731220 loss: 0.000961 2022/09/17 13:33:34 - mmengine - INFO - Epoch(train) [13][250/293] lr: 5.000000e-04 eta: 5:52:00 time: 0.332455 data_time: 0.072646 memory: 5151 loss_kpt: 0.000948 acc_pose: 0.752189 loss: 0.000948 2022/09/17 13:33:48 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 13:33:48 - mmengine - INFO - Saving checkpoint at 13 epochs 2022/09/17 13:34:07 - mmengine - INFO - Epoch(train) [14][50/293] lr: 5.000000e-04 eta: 5:47:14 time: 0.341635 data_time: 0.072702 memory: 5151 loss_kpt: 0.000963 acc_pose: 0.722035 loss: 0.000963 2022/09/17 13:34:24 - mmengine - INFO - Epoch(train) [14][100/293] lr: 5.000000e-04 eta: 5:46:29 time: 0.325443 data_time: 0.060939 memory: 5151 loss_kpt: 0.000948 acc_pose: 0.770946 loss: 0.000948 2022/09/17 13:34:40 - mmengine - INFO - Epoch(train) [14][150/293] lr: 5.000000e-04 eta: 5:45:51 time: 0.332546 data_time: 0.060591 memory: 5151 loss_kpt: 0.000944 acc_pose: 0.751646 loss: 0.000944 2022/09/17 13:34:54 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 13:34:57 - mmengine - INFO - Epoch(train) [14][200/293] lr: 5.000000e-04 eta: 5:45:09 time: 0.328260 data_time: 0.059548 memory: 5151 loss_kpt: 0.000955 acc_pose: 0.773075 loss: 0.000955 2022/09/17 13:35:14 - mmengine - INFO - Epoch(train) [14][250/293] lr: 5.000000e-04 eta: 5:44:41 time: 0.345929 data_time: 0.064606 memory: 5151 loss_kpt: 0.000940 acc_pose: 0.716132 loss: 0.000940 2022/09/17 13:35:29 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 13:35:29 - mmengine - INFO - Saving checkpoint at 14 epochs 2022/09/17 13:35:49 - mmengine - INFO - Epoch(train) [15][50/293] lr: 5.000000e-04 eta: 5:40:25 time: 0.347105 data_time: 0.074898 memory: 5151 loss_kpt: 0.000920 acc_pose: 0.757674 loss: 0.000920 2022/09/17 13:36:05 - mmengine - INFO - Epoch(train) [15][100/293] lr: 5.000000e-04 eta: 5:39:48 time: 0.326731 data_time: 0.059406 memory: 5151 loss_kpt: 0.000932 acc_pose: 0.764759 loss: 0.000932 2022/09/17 13:36:22 - mmengine - INFO - Epoch(train) [15][150/293] lr: 5.000000e-04 eta: 5:39:17 time: 0.337390 data_time: 0.068811 memory: 5151 loss_kpt: 0.000945 acc_pose: 0.721568 loss: 0.000945 2022/09/17 13:36:39 - mmengine - INFO - Epoch(train) [15][200/293] lr: 5.000000e-04 eta: 5:38:48 time: 0.337747 data_time: 0.066763 memory: 5151 loss_kpt: 0.000943 acc_pose: 0.697974 loss: 0.000943 2022/09/17 13:36:55 - mmengine - INFO - Epoch(train) [15][250/293] lr: 5.000000e-04 eta: 5:38:11 time: 0.326084 data_time: 0.058234 memory: 5151 loss_kpt: 0.000930 acc_pose: 0.740650 loss: 0.000930 2022/09/17 13:37:09 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 13:37:09 - mmengine - INFO - Saving checkpoint at 15 epochs 2022/09/17 13:37:29 - mmengine - INFO - Epoch(train) [16][50/293] lr: 5.000000e-04 eta: 5:34:21 time: 0.352675 data_time: 0.068668 memory: 5151 loss_kpt: 0.000937 acc_pose: 0.707214 loss: 0.000937 2022/09/17 13:37:46 - mmengine - INFO - Epoch(train) [16][100/293] lr: 5.000000e-04 eta: 5:33:53 time: 0.335310 data_time: 0.068267 memory: 5151 loss_kpt: 0.000924 acc_pose: 0.707588 loss: 0.000924 2022/09/17 13:38:03 - mmengine - INFO - Epoch(train) [16][150/293] lr: 5.000000e-04 eta: 5:33:24 time: 0.332692 data_time: 0.062607 memory: 5151 loss_kpt: 0.000918 acc_pose: 0.733058 loss: 0.000918 2022/09/17 13:38:19 - mmengine - INFO - Epoch(train) [16][200/293] lr: 5.000000e-04 eta: 5:32:49 time: 0.323401 data_time: 0.064862 memory: 5151 loss_kpt: 0.000917 acc_pose: 0.741896 loss: 0.000917 2022/09/17 13:38:35 - mmengine - INFO - Epoch(train) [16][250/293] lr: 5.000000e-04 eta: 5:32:16 time: 0.325464 data_time: 0.066777 memory: 5151 loss_kpt: 0.000925 acc_pose: 0.697194 loss: 0.000925 2022/09/17 13:38:49 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 13:38:49 - mmengine - INFO - Saving checkpoint at 16 epochs 2022/09/17 13:39:09 - mmengine - INFO - Epoch(train) [17][50/293] lr: 5.000000e-04 eta: 5:28:40 time: 0.345379 data_time: 0.070470 memory: 5151 loss_kpt: 0.000912 acc_pose: 0.735973 loss: 0.000912 2022/09/17 13:39:25 - mmengine - INFO - Epoch(train) [17][100/293] lr: 5.000000e-04 eta: 5:28:05 time: 0.317312 data_time: 0.057051 memory: 5151 loss_kpt: 0.000908 acc_pose: 0.727218 loss: 0.000908 2022/09/17 13:39:42 - mmengine - INFO - Epoch(train) [17][150/293] lr: 5.000000e-04 eta: 5:27:39 time: 0.332284 data_time: 0.059454 memory: 5151 loss_kpt: 0.000926 acc_pose: 0.774128 loss: 0.000926 2022/09/17 13:39:58 - mmengine - INFO - Epoch(train) [17][200/293] lr: 5.000000e-04 eta: 5:27:11 time: 0.329165 data_time: 0.057952 memory: 5151 loss_kpt: 0.000914 acc_pose: 0.735306 loss: 0.000914 2022/09/17 13:40:14 - mmengine - INFO - Epoch(train) [17][250/293] lr: 5.000000e-04 eta: 5:26:43 time: 0.327754 data_time: 0.060838 memory: 5151 loss_kpt: 0.000905 acc_pose: 0.748517 loss: 0.000905 2022/09/17 13:40:29 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 13:40:29 - mmengine - INFO - Saving checkpoint at 17 epochs 2022/09/17 13:40:38 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 13:40:48 - mmengine - INFO - Epoch(train) [18][50/293] lr: 5.000000e-04 eta: 5:23:17 time: 0.335646 data_time: 0.073442 memory: 5151 loss_kpt: 0.000907 acc_pose: 0.768997 loss: 0.000907 2022/09/17 13:41:04 - mmengine - INFO - Epoch(train) [18][100/293] lr: 5.000000e-04 eta: 5:22:49 time: 0.322703 data_time: 0.061332 memory: 5151 loss_kpt: 0.000910 acc_pose: 0.751499 loss: 0.000910 2022/09/17 13:41:21 - mmengine - INFO - Epoch(train) [18][150/293] lr: 5.000000e-04 eta: 5:22:26 time: 0.332500 data_time: 0.068231 memory: 5151 loss_kpt: 0.000912 acc_pose: 0.723167 loss: 0.000912 2022/09/17 13:41:37 - mmengine - INFO - Epoch(train) [18][200/293] lr: 5.000000e-04 eta: 5:21:57 time: 0.320735 data_time: 0.062466 memory: 5151 loss_kpt: 0.000918 acc_pose: 0.791693 loss: 0.000918 2022/09/17 13:41:53 - mmengine - INFO - Epoch(train) [18][250/293] lr: 5.000000e-04 eta: 5:21:27 time: 0.320319 data_time: 0.058792 memory: 5151 loss_kpt: 0.000919 acc_pose: 0.749330 loss: 0.000919 2022/09/17 13:42:07 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 13:42:07 - mmengine - INFO - Saving checkpoint at 18 epochs 2022/09/17 13:42:27 - mmengine - INFO - Epoch(train) [19][50/293] lr: 5.000000e-04 eta: 5:18:23 time: 0.348597 data_time: 0.075901 memory: 5151 loss_kpt: 0.000889 acc_pose: 0.761331 loss: 0.000889 2022/09/17 13:42:43 - mmengine - INFO - Epoch(train) [19][100/293] lr: 5.000000e-04 eta: 5:18:01 time: 0.329670 data_time: 0.060113 memory: 5151 loss_kpt: 0.000903 acc_pose: 0.705130 loss: 0.000903 2022/09/17 13:43:00 - mmengine - INFO - Epoch(train) [19][150/293] lr: 5.000000e-04 eta: 5:17:41 time: 0.333793 data_time: 0.058391 memory: 5151 loss_kpt: 0.000894 acc_pose: 0.719291 loss: 0.000894 2022/09/17 13:43:17 - mmengine - INFO - Epoch(train) [19][200/293] lr: 5.000000e-04 eta: 5:17:22 time: 0.335587 data_time: 0.067062 memory: 5151 loss_kpt: 0.000910 acc_pose: 0.727590 loss: 0.000910 2022/09/17 13:43:33 - mmengine - INFO - Epoch(train) [19][250/293] lr: 5.000000e-04 eta: 5:16:57 time: 0.324471 data_time: 0.058215 memory: 5151 loss_kpt: 0.000906 acc_pose: 0.739704 loss: 0.000906 2022/09/17 13:43:46 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 13:43:46 - mmengine - INFO - Saving checkpoint at 19 epochs 2022/09/17 13:44:06 - mmengine - INFO - Epoch(train) [20][50/293] lr: 5.000000e-04 eta: 5:13:59 time: 0.338229 data_time: 0.069996 memory: 5151 loss_kpt: 0.000895 acc_pose: 0.792767 loss: 0.000895 2022/09/17 13:44:22 - mmengine - INFO - Epoch(train) [20][100/293] lr: 5.000000e-04 eta: 5:13:37 time: 0.325337 data_time: 0.057908 memory: 5151 loss_kpt: 0.000893 acc_pose: 0.722610 loss: 0.000893 2022/09/17 13:44:39 - mmengine - INFO - Epoch(train) [20][150/293] lr: 5.000000e-04 eta: 5:13:20 time: 0.336303 data_time: 0.064753 memory: 5151 loss_kpt: 0.000889 acc_pose: 0.707827 loss: 0.000889 2022/09/17 13:44:56 - mmengine - INFO - Epoch(train) [20][200/293] lr: 5.000000e-04 eta: 5:13:07 time: 0.345641 data_time: 0.067698 memory: 5151 loss_kpt: 0.000898 acc_pose: 0.746662 loss: 0.000898 2022/09/17 13:45:12 - mmengine - INFO - Epoch(train) [20][250/293] lr: 5.000000e-04 eta: 5:12:46 time: 0.327575 data_time: 0.065076 memory: 5151 loss_kpt: 0.000889 acc_pose: 0.720506 loss: 0.000889 2022/09/17 13:45:26 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 13:45:27 - mmengine - INFO - Saving checkpoint at 20 epochs 2022/09/17 13:45:35 - mmengine - INFO - Epoch(val) [20][50/407] eta: 0:00:42 time: 0.120090 data_time: 0.052305 memory: 5151 2022/09/17 13:45:41 - mmengine - INFO - Epoch(val) [20][100/407] eta: 0:00:38 time: 0.124543 data_time: 0.052200 memory: 331 2022/09/17 13:45:47 - mmengine - INFO - Epoch(val) [20][150/407] eta: 0:00:30 time: 0.119117 data_time: 0.049526 memory: 331 2022/09/17 13:45:53 - mmengine - INFO - Epoch(val) [20][200/407] eta: 0:00:24 time: 0.118376 data_time: 0.050974 memory: 331 2022/09/17 13:45:59 - mmengine - INFO - Epoch(val) [20][250/407] eta: 0:00:18 time: 0.115851 data_time: 0.048413 memory: 331 2022/09/17 13:46:05 - mmengine - INFO - Epoch(val) [20][300/407] eta: 0:00:12 time: 0.117106 data_time: 0.051637 memory: 331 2022/09/17 13:46:11 - mmengine - INFO - Epoch(val) [20][350/407] eta: 0:00:06 time: 0.117661 data_time: 0.052555 memory: 331 2022/09/17 13:46:16 - mmengine - INFO - Epoch(val) [20][400/407] eta: 0:00:00 time: 0.107280 data_time: 0.044582 memory: 331 2022/09/17 13:46:53 - mmengine - INFO - Evaluating CocoMetric... 2022/09/17 13:47:07 - mmengine - INFO - Epoch(val) [20][407/407] coco/AP: 0.604376 coco/AP .5: 0.842862 coco/AP .75: 0.675332 coco/AP (M): 0.578687 coco/AP (L): 0.659762 coco/AR: 0.668136 coco/AR .5: 0.890113 coco/AR .75: 0.735989 coco/AR (M): 0.630210 coco/AR (L): 0.721925 2022/09/17 13:47:07 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220917/vipnas_res50/best_coco/AP_epoch_10.pth is removed 2022/09/17 13:47:09 - mmengine - INFO - The best checkpoint with 0.6044 coco/AP at 20 epoch is saved to best_coco/AP_epoch_20.pth. 2022/09/17 13:47:26 - mmengine - INFO - Epoch(train) [21][50/293] lr: 5.000000e-04 eta: 5:09:58 time: 0.337390 data_time: 0.068045 memory: 5151 loss_kpt: 0.000909 acc_pose: 0.751004 loss: 0.000909 2022/09/17 13:47:42 - mmengine - INFO - Epoch(train) [21][100/293] lr: 5.000000e-04 eta: 5:09:36 time: 0.322444 data_time: 0.063146 memory: 5151 loss_kpt: 0.000882 acc_pose: 0.723898 loss: 0.000882 2022/09/17 13:47:56 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 13:47:59 - mmengine - INFO - Epoch(train) [21][150/293] lr: 5.000000e-04 eta: 5:09:27 time: 0.351766 data_time: 0.065068 memory: 5151 loss_kpt: 0.000875 acc_pose: 0.707720 loss: 0.000875 2022/09/17 13:48:16 - mmengine - INFO - Epoch(train) [21][200/293] lr: 5.000000e-04 eta: 5:09:11 time: 0.335409 data_time: 0.065006 memory: 5151 loss_kpt: 0.000893 acc_pose: 0.766981 loss: 0.000893 2022/09/17 13:48:33 - mmengine - INFO - Epoch(train) [21][250/293] lr: 5.000000e-04 eta: 5:08:56 time: 0.337954 data_time: 0.073645 memory: 5151 loss_kpt: 0.000882 acc_pose: 0.757300 loss: 0.000882 2022/09/17 13:48:47 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 13:48:47 - mmengine - INFO - Saving checkpoint at 21 epochs 2022/09/17 13:49:06 - mmengine - INFO - Epoch(train) [22][50/293] lr: 5.000000e-04 eta: 5:06:15 time: 0.330073 data_time: 0.067563 memory: 5151 loss_kpt: 0.000887 acc_pose: 0.725163 loss: 0.000887 2022/09/17 13:49:23 - mmengine - INFO - Epoch(train) [22][100/293] lr: 5.000000e-04 eta: 5:06:02 time: 0.342198 data_time: 0.066252 memory: 5151 loss_kpt: 0.000902 acc_pose: 0.674505 loss: 0.000902 2022/09/17 13:49:40 - mmengine - INFO - Epoch(train) [22][150/293] lr: 5.000000e-04 eta: 5:05:49 time: 0.338637 data_time: 0.069923 memory: 5151 loss_kpt: 0.000866 acc_pose: 0.730774 loss: 0.000866 2022/09/17 13:49:57 - mmengine - INFO - Epoch(train) [22][200/293] lr: 5.000000e-04 eta: 5:05:38 time: 0.345303 data_time: 0.073576 memory: 5151 loss_kpt: 0.000879 acc_pose: 0.715965 loss: 0.000879 2022/09/17 13:50:14 - mmengine - INFO - Epoch(train) [22][250/293] lr: 5.000000e-04 eta: 5:05:23 time: 0.337327 data_time: 0.065622 memory: 5151 loss_kpt: 0.000884 acc_pose: 0.685564 loss: 0.000884 2022/09/17 13:50:29 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 13:50:29 - mmengine - INFO - Saving checkpoint at 22 epochs 2022/09/17 13:50:48 - mmengine - INFO - Epoch(train) [23][50/293] lr: 5.000000e-04 eta: 5:02:59 time: 0.351422 data_time: 0.070494 memory: 5151 loss_kpt: 0.000882 acc_pose: 0.717654 loss: 0.000882 2022/09/17 13:51:05 - mmengine - INFO - Epoch(train) [23][100/293] lr: 5.000000e-04 eta: 5:02:46 time: 0.337727 data_time: 0.063740 memory: 5151 loss_kpt: 0.000865 acc_pose: 0.740319 loss: 0.000865 2022/09/17 13:51:22 - mmengine - INFO - Epoch(train) [23][150/293] lr: 5.000000e-04 eta: 5:02:33 time: 0.339877 data_time: 0.061370 memory: 5151 loss_kpt: 0.000866 acc_pose: 0.723480 loss: 0.000866 2022/09/17 13:51:39 - mmengine - INFO - Epoch(train) [23][200/293] lr: 5.000000e-04 eta: 5:02:20 time: 0.337637 data_time: 0.060678 memory: 5151 loss_kpt: 0.000873 acc_pose: 0.747755 loss: 0.000873 2022/09/17 13:51:56 - mmengine - INFO - Epoch(train) [23][250/293] lr: 5.000000e-04 eta: 5:02:06 time: 0.337092 data_time: 0.069358 memory: 5151 loss_kpt: 0.000887 acc_pose: 0.766346 loss: 0.000887 2022/09/17 13:52:11 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 13:52:11 - mmengine - INFO - Saving checkpoint at 23 epochs 2022/09/17 13:52:30 - mmengine - INFO - Epoch(train) [24][50/293] lr: 5.000000e-04 eta: 4:59:44 time: 0.338880 data_time: 0.068569 memory: 5151 loss_kpt: 0.000873 acc_pose: 0.736340 loss: 0.000873 2022/09/17 13:52:47 - mmengine - INFO - Epoch(train) [24][100/293] lr: 5.000000e-04 eta: 4:59:29 time: 0.333243 data_time: 0.068549 memory: 5151 loss_kpt: 0.000864 acc_pose: 0.747582 loss: 0.000864 2022/09/17 13:53:04 - mmengine - INFO - Epoch(train) [24][150/293] lr: 5.000000e-04 eta: 4:59:19 time: 0.344782 data_time: 0.070663 memory: 5151 loss_kpt: 0.000860 acc_pose: 0.743599 loss: 0.000860 2022/09/17 13:53:21 - mmengine - INFO - Epoch(train) [24][200/293] lr: 5.000000e-04 eta: 4:59:09 time: 0.344919 data_time: 0.063081 memory: 5151 loss_kpt: 0.000884 acc_pose: 0.774831 loss: 0.000884 2022/09/17 13:53:38 - mmengine - INFO - Epoch(train) [24][250/293] lr: 5.000000e-04 eta: 4:58:56 time: 0.335796 data_time: 0.069160 memory: 5151 loss_kpt: 0.000864 acc_pose: 0.752096 loss: 0.000864 2022/09/17 13:53:42 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 13:53:52 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 13:53:52 - mmengine - INFO - Saving checkpoint at 24 epochs 2022/09/17 13:54:12 - mmengine - INFO - Epoch(train) [25][50/293] lr: 5.000000e-04 eta: 4:56:44 time: 0.349881 data_time: 0.076868 memory: 5151 loss_kpt: 0.000866 acc_pose: 0.704712 loss: 0.000866 2022/09/17 13:54:29 - mmengine - INFO - Epoch(train) [25][100/293] lr: 5.000000e-04 eta: 4:56:33 time: 0.339536 data_time: 0.064273 memory: 5151 loss_kpt: 0.000852 acc_pose: 0.790878 loss: 0.000852 2022/09/17 13:54:46 - mmengine - INFO - Epoch(train) [25][150/293] lr: 5.000000e-04 eta: 4:56:25 time: 0.349370 data_time: 0.079189 memory: 5151 loss_kpt: 0.000845 acc_pose: 0.831084 loss: 0.000845 2022/09/17 13:55:04 - mmengine - INFO - Epoch(train) [25][200/293] lr: 5.000000e-04 eta: 4:56:15 time: 0.343519 data_time: 0.069042 memory: 5151 loss_kpt: 0.000849 acc_pose: 0.752925 loss: 0.000849 2022/09/17 13:55:21 - mmengine - INFO - Epoch(train) [25][250/293] lr: 5.000000e-04 eta: 4:56:03 time: 0.341111 data_time: 0.068590 memory: 5151 loss_kpt: 0.000871 acc_pose: 0.772056 loss: 0.000871 2022/09/17 13:55:36 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 13:55:36 - mmengine - INFO - Saving checkpoint at 25 epochs 2022/09/17 13:55:56 - mmengine - INFO - Epoch(train) [26][50/293] lr: 5.000000e-04 eta: 4:53:59 time: 0.351879 data_time: 0.076902 memory: 5151 loss_kpt: 0.000864 acc_pose: 0.694840 loss: 0.000864 2022/09/17 13:56:13 - mmengine - INFO - Epoch(train) [26][100/293] lr: 5.000000e-04 eta: 4:53:46 time: 0.336404 data_time: 0.063567 memory: 5151 loss_kpt: 0.000866 acc_pose: 0.739633 loss: 0.000866 2022/09/17 13:56:29 - mmengine - INFO - Epoch(train) [26][150/293] lr: 5.000000e-04 eta: 4:53:32 time: 0.332073 data_time: 0.066188 memory: 5151 loss_kpt: 0.000864 acc_pose: 0.820788 loss: 0.000864 2022/09/17 13:56:46 - mmengine - INFO - Epoch(train) [26][200/293] lr: 5.000000e-04 eta: 4:53:21 time: 0.340425 data_time: 0.068655 memory: 5151 loss_kpt: 0.000858 acc_pose: 0.754199 loss: 0.000858 2022/09/17 13:57:03 - mmengine - INFO - Epoch(train) [26][250/293] lr: 5.000000e-04 eta: 4:53:08 time: 0.334227 data_time: 0.069603 memory: 5151 loss_kpt: 0.000853 acc_pose: 0.748420 loss: 0.000853 2022/09/17 13:57:17 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 13:57:17 - mmengine - INFO - Saving checkpoint at 26 epochs 2022/09/17 13:57:38 - mmengine - INFO - Epoch(train) [27][50/293] lr: 5.000000e-04 eta: 4:51:10 time: 0.357525 data_time: 0.079589 memory: 5151 loss_kpt: 0.000853 acc_pose: 0.745781 loss: 0.000853 2022/09/17 13:57:54 - mmengine - INFO - Epoch(train) [27][100/293] lr: 5.000000e-04 eta: 4:50:57 time: 0.333758 data_time: 0.067582 memory: 5151 loss_kpt: 0.000853 acc_pose: 0.782522 loss: 0.000853 2022/09/17 13:58:12 - mmengine - INFO - Epoch(train) [27][150/293] lr: 5.000000e-04 eta: 4:50:47 time: 0.341709 data_time: 0.068977 memory: 5151 loss_kpt: 0.000850 acc_pose: 0.815313 loss: 0.000850 2022/09/17 13:58:28 - mmengine - INFO - Epoch(train) [27][200/293] lr: 5.000000e-04 eta: 4:50:35 time: 0.337839 data_time: 0.065345 memory: 5151 loss_kpt: 0.000860 acc_pose: 0.744868 loss: 0.000860 2022/09/17 13:58:46 - mmengine - INFO - Epoch(train) [27][250/293] lr: 5.000000e-04 eta: 4:50:25 time: 0.341967 data_time: 0.071265 memory: 5151 loss_kpt: 0.000828 acc_pose: 0.782081 loss: 0.000828 2022/09/17 13:59:00 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 13:59:00 - mmengine - INFO - Saving checkpoint at 27 epochs 2022/09/17 13:59:20 - mmengine - INFO - Epoch(train) [28][50/293] lr: 5.000000e-04 eta: 4:48:27 time: 0.344809 data_time: 0.071909 memory: 5151 loss_kpt: 0.000865 acc_pose: 0.751708 loss: 0.000865 2022/09/17 13:59:33 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 13:59:36 - mmengine - INFO - Epoch(train) [28][100/293] lr: 5.000000e-04 eta: 4:48:14 time: 0.331553 data_time: 0.067425 memory: 5151 loss_kpt: 0.000841 acc_pose: 0.731987 loss: 0.000841 2022/09/17 13:59:53 - mmengine - INFO - Epoch(train) [28][150/293] lr: 5.000000e-04 eta: 4:48:05 time: 0.344183 data_time: 0.071688 memory: 5151 loss_kpt: 0.000832 acc_pose: 0.771934 loss: 0.000832 2022/09/17 14:00:11 - mmengine - INFO - Epoch(train) [28][200/293] lr: 5.000000e-04 eta: 4:47:56 time: 0.343769 data_time: 0.072037 memory: 5151 loss_kpt: 0.000845 acc_pose: 0.729013 loss: 0.000845 2022/09/17 14:00:28 - mmengine - INFO - Epoch(train) [28][250/293] lr: 5.000000e-04 eta: 4:47:46 time: 0.342304 data_time: 0.065509 memory: 5151 loss_kpt: 0.000858 acc_pose: 0.692780 loss: 0.000858 2022/09/17 14:00:42 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:00:42 - mmengine - INFO - Saving checkpoint at 28 epochs 2022/09/17 14:01:02 - mmengine - INFO - Epoch(train) [29][50/293] lr: 5.000000e-04 eta: 4:45:57 time: 0.357050 data_time: 0.075051 memory: 5151 loss_kpt: 0.000823 acc_pose: 0.766433 loss: 0.000823 2022/09/17 14:01:19 - mmengine - INFO - Epoch(train) [29][100/293] lr: 5.000000e-04 eta: 4:45:46 time: 0.338640 data_time: 0.067663 memory: 5151 loss_kpt: 0.000859 acc_pose: 0.778945 loss: 0.000859 2022/09/17 14:01:36 - mmengine - INFO - Epoch(train) [29][150/293] lr: 5.000000e-04 eta: 4:45:34 time: 0.337300 data_time: 0.075790 memory: 5151 loss_kpt: 0.000834 acc_pose: 0.750614 loss: 0.000834 2022/09/17 14:01:52 - mmengine - INFO - Epoch(train) [29][200/293] lr: 5.000000e-04 eta: 4:45:21 time: 0.332181 data_time: 0.063165 memory: 5151 loss_kpt: 0.000853 acc_pose: 0.746260 loss: 0.000853 2022/09/17 14:02:08 - mmengine - INFO - Epoch(train) [29][250/293] lr: 5.000000e-04 eta: 4:45:04 time: 0.318979 data_time: 0.061715 memory: 5151 loss_kpt: 0.000846 acc_pose: 0.802669 loss: 0.000846 2022/09/17 14:02:23 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:02:23 - mmengine - INFO - Saving checkpoint at 29 epochs 2022/09/17 14:02:43 - mmengine - INFO - Epoch(train) [30][50/293] lr: 5.000000e-04 eta: 4:43:18 time: 0.354440 data_time: 0.079323 memory: 5151 loss_kpt: 0.000834 acc_pose: 0.750657 loss: 0.000834 2022/09/17 14:02:59 - mmengine - INFO - Epoch(train) [30][100/293] lr: 5.000000e-04 eta: 4:43:05 time: 0.330640 data_time: 0.068115 memory: 5151 loss_kpt: 0.000830 acc_pose: 0.779298 loss: 0.000830 2022/09/17 14:03:16 - mmengine - INFO - Epoch(train) [30][150/293] lr: 5.000000e-04 eta: 4:42:55 time: 0.338305 data_time: 0.067784 memory: 5151 loss_kpt: 0.000832 acc_pose: 0.787423 loss: 0.000832 2022/09/17 14:03:32 - mmengine - INFO - Epoch(train) [30][200/293] lr: 5.000000e-04 eta: 4:42:39 time: 0.323202 data_time: 0.061418 memory: 5151 loss_kpt: 0.000834 acc_pose: 0.756675 loss: 0.000834 2022/09/17 14:03:49 - mmengine - INFO - Epoch(train) [30][250/293] lr: 5.000000e-04 eta: 4:42:26 time: 0.330246 data_time: 0.067609 memory: 5151 loss_kpt: 0.000845 acc_pose: 0.819754 loss: 0.000845 2022/09/17 14:04:03 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:04:03 - mmengine - INFO - Saving checkpoint at 30 epochs 2022/09/17 14:04:12 - mmengine - INFO - Epoch(val) [30][50/407] eta: 0:00:43 time: 0.122114 data_time: 0.053051 memory: 5151 2022/09/17 14:04:18 - mmengine - INFO - Epoch(val) [30][100/407] eta: 0:00:35 time: 0.114779 data_time: 0.047627 memory: 331 2022/09/17 14:04:24 - mmengine - INFO - Epoch(val) [30][150/407] eta: 0:00:31 time: 0.123265 data_time: 0.050573 memory: 331 2022/09/17 14:04:30 - mmengine - INFO - Epoch(val) [30][200/407] eta: 0:00:24 time: 0.117006 data_time: 0.049964 memory: 331 2022/09/17 14:04:35 - mmengine - INFO - Epoch(val) [30][250/407] eta: 0:00:18 time: 0.116369 data_time: 0.049563 memory: 331 2022/09/17 14:04:42 - mmengine - INFO - Epoch(val) [30][300/407] eta: 0:00:13 time: 0.121656 data_time: 0.054251 memory: 331 2022/09/17 14:04:47 - mmengine - INFO - Epoch(val) [30][350/407] eta: 0:00:06 time: 0.118712 data_time: 0.049872 memory: 331 2022/09/17 14:04:53 - mmengine - INFO - Epoch(val) [30][400/407] eta: 0:00:00 time: 0.109076 data_time: 0.040401 memory: 331 2022/09/17 14:05:30 - mmengine - INFO - Evaluating CocoMetric... 2022/09/17 14:05:44 - mmengine - INFO - Epoch(val) [30][407/407] coco/AP: 0.633526 coco/AP .5: 0.861085 coco/AP .75: 0.708426 coco/AP (M): 0.605829 coco/AP (L): 0.689504 coco/AR: 0.695120 coco/AR .5: 0.906171 coco/AR .75: 0.763854 coco/AR (M): 0.657143 coco/AR (L): 0.749275 2022/09/17 14:05:45 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220917/vipnas_res50/best_coco/AP_epoch_20.pth is removed 2022/09/17 14:05:47 - mmengine - INFO - The best checkpoint with 0.6335 coco/AP at 30 epoch is saved to best_coco/AP_epoch_30.pth. 2022/09/17 14:06:03 - mmengine - INFO - Epoch(train) [31][50/293] lr: 5.000000e-04 eta: 4:40:38 time: 0.334335 data_time: 0.070486 memory: 5151 loss_kpt: 0.000843 acc_pose: 0.751088 loss: 0.000843 2022/09/17 14:06:21 - mmengine - INFO - Epoch(train) [31][100/293] lr: 5.000000e-04 eta: 4:40:29 time: 0.343225 data_time: 0.066054 memory: 5151 loss_kpt: 0.000829 acc_pose: 0.759062 loss: 0.000829 2022/09/17 14:06:37 - mmengine - INFO - Epoch(train) [31][150/293] lr: 5.000000e-04 eta: 4:40:18 time: 0.336300 data_time: 0.071528 memory: 5151 loss_kpt: 0.000838 acc_pose: 0.778921 loss: 0.000838 2022/09/17 14:06:54 - mmengine - INFO - Epoch(train) [31][200/293] lr: 5.000000e-04 eta: 4:40:07 time: 0.339355 data_time: 0.067325 memory: 5151 loss_kpt: 0.000848 acc_pose: 0.759476 loss: 0.000848 2022/09/17 14:06:58 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:07:12 - mmengine - INFO - Epoch(train) [31][250/293] lr: 5.000000e-04 eta: 4:39:58 time: 0.343986 data_time: 0.068082 memory: 5151 loss_kpt: 0.000835 acc_pose: 0.751001 loss: 0.000835 2022/09/17 14:07:26 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:07:26 - mmengine - INFO - Saving checkpoint at 31 epochs 2022/09/17 14:07:47 - mmengine - INFO - Epoch(train) [32][50/293] lr: 5.000000e-04 eta: 4:38:15 time: 0.338418 data_time: 0.068995 memory: 5151 loss_kpt: 0.000839 acc_pose: 0.749047 loss: 0.000839 2022/09/17 14:08:03 - mmengine - INFO - Epoch(train) [32][100/293] lr: 5.000000e-04 eta: 4:38:04 time: 0.335400 data_time: 0.065011 memory: 5151 loss_kpt: 0.000843 acc_pose: 0.825815 loss: 0.000843 2022/09/17 14:08:21 - mmengine - INFO - Epoch(train) [32][150/293] lr: 5.000000e-04 eta: 4:37:54 time: 0.341669 data_time: 0.074758 memory: 5151 loss_kpt: 0.000835 acc_pose: 0.789813 loss: 0.000835 2022/09/17 14:08:37 - mmengine - INFO - Epoch(train) [32][200/293] lr: 5.000000e-04 eta: 4:37:43 time: 0.333158 data_time: 0.068752 memory: 5151 loss_kpt: 0.000821 acc_pose: 0.799389 loss: 0.000821 2022/09/17 14:08:54 - mmengine - INFO - Epoch(train) [32][250/293] lr: 5.000000e-04 eta: 4:37:32 time: 0.338531 data_time: 0.067893 memory: 5151 loss_kpt: 0.000829 acc_pose: 0.771393 loss: 0.000829 2022/09/17 14:09:09 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:09:09 - mmengine - INFO - Saving checkpoint at 32 epochs 2022/09/17 14:09:29 - mmengine - INFO - Epoch(train) [33][50/293] lr: 5.000000e-04 eta: 4:35:54 time: 0.346310 data_time: 0.075637 memory: 5151 loss_kpt: 0.000840 acc_pose: 0.748278 loss: 0.000840 2022/09/17 14:09:46 - mmengine - INFO - Epoch(train) [33][100/293] lr: 5.000000e-04 eta: 4:35:46 time: 0.347166 data_time: 0.081012 memory: 5151 loss_kpt: 0.000827 acc_pose: 0.751020 loss: 0.000827 2022/09/17 14:10:03 - mmengine - INFO - Epoch(train) [33][150/293] lr: 5.000000e-04 eta: 4:35:36 time: 0.339685 data_time: 0.078347 memory: 5151 loss_kpt: 0.000831 acc_pose: 0.824269 loss: 0.000831 2022/09/17 14:10:21 - mmengine - INFO - Epoch(train) [33][200/293] lr: 5.000000e-04 eta: 4:35:27 time: 0.342699 data_time: 0.074027 memory: 5151 loss_kpt: 0.000829 acc_pose: 0.785332 loss: 0.000829 2022/09/17 14:10:37 - mmengine - INFO - Epoch(train) [33][250/293] lr: 5.000000e-04 eta: 4:35:16 time: 0.334151 data_time: 0.070267 memory: 5151 loss_kpt: 0.000833 acc_pose: 0.777851 loss: 0.000833 2022/09/17 14:10:52 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:10:52 - mmengine - INFO - Saving checkpoint at 33 epochs 2022/09/17 14:11:12 - mmengine - INFO - Epoch(train) [34][50/293] lr: 5.000000e-04 eta: 4:33:44 time: 0.357722 data_time: 0.082991 memory: 5151 loss_kpt: 0.000832 acc_pose: 0.790769 loss: 0.000832 2022/09/17 14:11:29 - mmengine - INFO - Epoch(train) [34][100/293] lr: 5.000000e-04 eta: 4:33:31 time: 0.330456 data_time: 0.072699 memory: 5151 loss_kpt: 0.000824 acc_pose: 0.802451 loss: 0.000824 2022/09/17 14:11:46 - mmengine - INFO - Epoch(train) [34][150/293] lr: 5.000000e-04 eta: 4:33:23 time: 0.346517 data_time: 0.072528 memory: 5151 loss_kpt: 0.000813 acc_pose: 0.733935 loss: 0.000813 2022/09/17 14:12:03 - mmengine - INFO - Epoch(train) [34][200/293] lr: 5.000000e-04 eta: 4:33:13 time: 0.338873 data_time: 0.072329 memory: 5151 loss_kpt: 0.000823 acc_pose: 0.755000 loss: 0.000823 2022/09/17 14:12:19 - mmengine - INFO - Epoch(train) [34][250/293] lr: 5.000000e-04 eta: 4:32:58 time: 0.320634 data_time: 0.062801 memory: 5151 loss_kpt: 0.000820 acc_pose: 0.762940 loss: 0.000820 2022/09/17 14:12:33 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:12:33 - mmengine - INFO - Saving checkpoint at 34 epochs 2022/09/17 14:12:49 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:12:53 - mmengine - INFO - Epoch(train) [35][50/293] lr: 5.000000e-04 eta: 4:31:26 time: 0.349054 data_time: 0.089201 memory: 5151 loss_kpt: 0.000818 acc_pose: 0.747942 loss: 0.000818 2022/09/17 14:13:11 - mmengine - INFO - Epoch(train) [35][100/293] lr: 5.000000e-04 eta: 4:31:21 time: 0.356390 data_time: 0.062948 memory: 5151 loss_kpt: 0.000812 acc_pose: 0.754315 loss: 0.000812 2022/09/17 14:13:28 - mmengine - INFO - Epoch(train) [35][150/293] lr: 5.000000e-04 eta: 4:31:10 time: 0.335085 data_time: 0.067291 memory: 5151 loss_kpt: 0.000817 acc_pose: 0.830533 loss: 0.000817 2022/09/17 14:13:45 - mmengine - INFO - Epoch(train) [35][200/293] lr: 5.000000e-04 eta: 4:31:01 time: 0.342399 data_time: 0.071295 memory: 5151 loss_kpt: 0.000824 acc_pose: 0.702238 loss: 0.000824 2022/09/17 14:14:02 - mmengine - INFO - Epoch(train) [35][250/293] lr: 5.000000e-04 eta: 4:30:50 time: 0.337808 data_time: 0.070649 memory: 5151 loss_kpt: 0.000830 acc_pose: 0.817539 loss: 0.000830 2022/09/17 14:14:16 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:14:16 - mmengine - INFO - Saving checkpoint at 35 epochs 2022/09/17 14:14:36 - mmengine - INFO - Epoch(train) [36][50/293] lr: 5.000000e-04 eta: 4:29:21 time: 0.350556 data_time: 0.082004 memory: 5151 loss_kpt: 0.000828 acc_pose: 0.799366 loss: 0.000828 2022/09/17 14:14:54 - mmengine - INFO - Epoch(train) [36][100/293] lr: 5.000000e-04 eta: 4:29:13 time: 0.345386 data_time: 0.078469 memory: 5151 loss_kpt: 0.000822 acc_pose: 0.763565 loss: 0.000822 2022/09/17 14:15:11 - mmengine - INFO - Epoch(train) [36][150/293] lr: 5.000000e-04 eta: 4:29:06 time: 0.350150 data_time: 0.079806 memory: 5151 loss_kpt: 0.000813 acc_pose: 0.758480 loss: 0.000813 2022/09/17 14:15:28 - mmengine - INFO - Epoch(train) [36][200/293] lr: 5.000000e-04 eta: 4:28:55 time: 0.336698 data_time: 0.074405 memory: 5151 loss_kpt: 0.000822 acc_pose: 0.769650 loss: 0.000822 2022/09/17 14:15:45 - mmengine - INFO - Epoch(train) [36][250/293] lr: 5.000000e-04 eta: 4:28:45 time: 0.341648 data_time: 0.071055 memory: 5151 loss_kpt: 0.000829 acc_pose: 0.787324 loss: 0.000829 2022/09/17 14:15:59 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:15:59 - mmengine - INFO - Saving checkpoint at 36 epochs 2022/09/17 14:16:19 - mmengine - INFO - Epoch(train) [37][50/293] lr: 5.000000e-04 eta: 4:27:18 time: 0.345671 data_time: 0.075112 memory: 5151 loss_kpt: 0.000820 acc_pose: 0.788705 loss: 0.000820 2022/09/17 14:16:36 - mmengine - INFO - Epoch(train) [37][100/293] lr: 5.000000e-04 eta: 4:27:09 time: 0.344546 data_time: 0.076495 memory: 5151 loss_kpt: 0.000816 acc_pose: 0.762052 loss: 0.000816 2022/09/17 14:16:53 - mmengine - INFO - Epoch(train) [37][150/293] lr: 5.000000e-04 eta: 4:26:59 time: 0.337867 data_time: 0.069137 memory: 5151 loss_kpt: 0.000809 acc_pose: 0.757039 loss: 0.000809 2022/09/17 14:17:09 - mmengine - INFO - Epoch(train) [37][200/293] lr: 5.000000e-04 eta: 4:26:46 time: 0.325309 data_time: 0.064944 memory: 5151 loss_kpt: 0.000806 acc_pose: 0.738939 loss: 0.000806 2022/09/17 14:17:26 - mmengine - INFO - Epoch(train) [37][250/293] lr: 5.000000e-04 eta: 4:26:34 time: 0.332977 data_time: 0.069100 memory: 5151 loss_kpt: 0.000822 acc_pose: 0.765742 loss: 0.000822 2022/09/17 14:17:40 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:17:40 - mmengine - INFO - Saving checkpoint at 37 epochs 2022/09/17 14:18:01 - mmengine - INFO - Epoch(train) [38][50/293] lr: 5.000000e-04 eta: 4:25:12 time: 0.360053 data_time: 0.075254 memory: 5151 loss_kpt: 0.000811 acc_pose: 0.834563 loss: 0.000811 2022/09/17 14:18:17 - mmengine - INFO - Epoch(train) [38][100/293] lr: 5.000000e-04 eta: 4:25:02 time: 0.338734 data_time: 0.072756 memory: 5151 loss_kpt: 0.000806 acc_pose: 0.826435 loss: 0.000806 2022/09/17 14:18:35 - mmengine - INFO - Epoch(train) [38][150/293] lr: 5.000000e-04 eta: 4:24:53 time: 0.343764 data_time: 0.078853 memory: 5151 loss_kpt: 0.000817 acc_pose: 0.753147 loss: 0.000817 2022/09/17 14:18:38 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:18:52 - mmengine - INFO - Epoch(train) [38][200/293] lr: 5.000000e-04 eta: 4:24:44 time: 0.343497 data_time: 0.073191 memory: 5151 loss_kpt: 0.000801 acc_pose: 0.760277 loss: 0.000801 2022/09/17 14:19:09 - mmengine - INFO - Epoch(train) [38][250/293] lr: 5.000000e-04 eta: 4:24:34 time: 0.338911 data_time: 0.068753 memory: 5151 loss_kpt: 0.000813 acc_pose: 0.769507 loss: 0.000813 2022/09/17 14:19:24 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:19:24 - mmengine - INFO - Saving checkpoint at 38 epochs 2022/09/17 14:19:44 - mmengine - INFO - Epoch(train) [39][50/293] lr: 5.000000e-04 eta: 4:23:14 time: 0.359741 data_time: 0.080575 memory: 5151 loss_kpt: 0.000806 acc_pose: 0.757128 loss: 0.000806 2022/09/17 14:20:01 - mmengine - INFO - Epoch(train) [39][100/293] lr: 5.000000e-04 eta: 4:23:03 time: 0.334544 data_time: 0.065066 memory: 5151 loss_kpt: 0.000798 acc_pose: 0.743404 loss: 0.000798 2022/09/17 14:20:18 - mmengine - INFO - Epoch(train) [39][150/293] lr: 5.000000e-04 eta: 4:22:52 time: 0.336134 data_time: 0.064477 memory: 5151 loss_kpt: 0.000816 acc_pose: 0.773130 loss: 0.000816 2022/09/17 14:20:35 - mmengine - INFO - Epoch(train) [39][200/293] lr: 5.000000e-04 eta: 4:22:43 time: 0.343661 data_time: 0.066731 memory: 5151 loss_kpt: 0.000799 acc_pose: 0.813381 loss: 0.000799 2022/09/17 14:20:52 - mmengine - INFO - Epoch(train) [39][250/293] lr: 5.000000e-04 eta: 4:22:33 time: 0.341978 data_time: 0.072751 memory: 5151 loss_kpt: 0.000807 acc_pose: 0.748742 loss: 0.000807 2022/09/17 14:21:07 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:21:07 - mmengine - INFO - Saving checkpoint at 39 epochs 2022/09/17 14:21:27 - mmengine - INFO - Epoch(train) [40][50/293] lr: 5.000000e-04 eta: 4:21:14 time: 0.353546 data_time: 0.077438 memory: 5151 loss_kpt: 0.000804 acc_pose: 0.787221 loss: 0.000804 2022/09/17 14:21:44 - mmengine - INFO - Epoch(train) [40][100/293] lr: 5.000000e-04 eta: 4:21:04 time: 0.340222 data_time: 0.070419 memory: 5151 loss_kpt: 0.000814 acc_pose: 0.788655 loss: 0.000814 2022/09/17 14:22:01 - mmengine - INFO - Epoch(train) [40][150/293] lr: 5.000000e-04 eta: 4:20:51 time: 0.326553 data_time: 0.070759 memory: 5151 loss_kpt: 0.000804 acc_pose: 0.723851 loss: 0.000804 2022/09/17 14:22:18 - mmengine - INFO - Epoch(train) [40][200/293] lr: 5.000000e-04 eta: 4:20:42 time: 0.343352 data_time: 0.073915 memory: 5151 loss_kpt: 0.000797 acc_pose: 0.819273 loss: 0.000797 2022/09/17 14:22:35 - mmengine - INFO - Epoch(train) [40][250/293] lr: 5.000000e-04 eta: 4:20:32 time: 0.342283 data_time: 0.068842 memory: 5151 loss_kpt: 0.000793 acc_pose: 0.808601 loss: 0.000793 2022/09/17 14:22:50 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:22:50 - mmengine - INFO - Saving checkpoint at 40 epochs 2022/09/17 14:22:58 - mmengine - INFO - Epoch(val) [40][50/407] eta: 0:00:42 time: 0.119491 data_time: 0.049934 memory: 5151 2022/09/17 14:23:04 - mmengine - INFO - Epoch(val) [40][100/407] eta: 0:00:35 time: 0.115602 data_time: 0.047110 memory: 331 2022/09/17 14:23:10 - mmengine - INFO - Epoch(val) [40][150/407] eta: 0:00:30 time: 0.116986 data_time: 0.049518 memory: 331 2022/09/17 14:23:15 - mmengine - INFO - Epoch(val) [40][200/407] eta: 0:00:23 time: 0.114518 data_time: 0.047421 memory: 331 2022/09/17 14:23:21 - mmengine - INFO - Epoch(val) [40][250/407] eta: 0:00:18 time: 0.118355 data_time: 0.050732 memory: 331 2022/09/17 14:23:27 - mmengine - INFO - Epoch(val) [40][300/407] eta: 0:00:12 time: 0.114341 data_time: 0.046506 memory: 331 2022/09/17 14:23:33 - mmengine - INFO - Epoch(val) [40][350/407] eta: 0:00:07 time: 0.123716 data_time: 0.056684 memory: 331 2022/09/17 14:23:39 - mmengine - INFO - Epoch(val) [40][400/407] eta: 0:00:00 time: 0.111367 data_time: 0.042654 memory: 331 2022/09/17 14:24:15 - mmengine - INFO - Evaluating CocoMetric... 2022/09/17 14:24:29 - mmengine - INFO - Epoch(val) [40][407/407] coco/AP: 0.645674 coco/AP .5: 0.866323 coco/AP .75: 0.721156 coco/AP (M): 0.617540 coco/AP (L): 0.704451 coco/AR: 0.708722 coco/AR .5: 0.910422 coco/AR .75: 0.777078 coco/AR (M): 0.669435 coco/AR (L): 0.764326 2022/09/17 14:24:29 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220917/vipnas_res50/best_coco/AP_epoch_30.pth is removed 2022/09/17 14:24:31 - mmengine - INFO - The best checkpoint with 0.6457 coco/AP at 40 epoch is saved to best_coco/AP_epoch_40.pth. 2022/09/17 14:24:48 - mmengine - INFO - Epoch(train) [41][50/293] lr: 5.000000e-04 eta: 4:19:12 time: 0.342527 data_time: 0.072354 memory: 5151 loss_kpt: 0.000814 acc_pose: 0.810386 loss: 0.000814 2022/09/17 14:25:05 - mmengine - INFO - Epoch(train) [41][100/293] lr: 5.000000e-04 eta: 4:19:02 time: 0.336616 data_time: 0.069380 memory: 5151 loss_kpt: 0.000816 acc_pose: 0.779347 loss: 0.000816 2022/09/17 14:25:23 - mmengine - INFO - Epoch(train) [41][150/293] lr: 5.000000e-04 eta: 4:18:55 time: 0.352667 data_time: 0.076234 memory: 5151 loss_kpt: 0.000821 acc_pose: 0.781889 loss: 0.000821 2022/09/17 14:25:40 - mmengine - INFO - Epoch(train) [41][200/293] lr: 5.000000e-04 eta: 4:18:46 time: 0.345941 data_time: 0.073705 memory: 5151 loss_kpt: 0.000795 acc_pose: 0.781609 loss: 0.000795 2022/09/17 14:25:57 - mmengine - INFO - Epoch(train) [41][250/293] lr: 5.000000e-04 eta: 4:18:37 time: 0.345408 data_time: 0.067126 memory: 5151 loss_kpt: 0.000803 acc_pose: 0.795790 loss: 0.000803 2022/09/17 14:26:08 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:26:12 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:26:12 - mmengine - INFO - Saving checkpoint at 41 epochs 2022/09/17 14:26:32 - mmengine - INFO - Epoch(train) [42][50/293] lr: 5.000000e-04 eta: 4:17:19 time: 0.344688 data_time: 0.080711 memory: 5151 loss_kpt: 0.000791 acc_pose: 0.831737 loss: 0.000791 2022/09/17 14:26:48 - mmengine - INFO - Epoch(train) [42][100/293] lr: 5.000000e-04 eta: 4:17:07 time: 0.327695 data_time: 0.066332 memory: 5151 loss_kpt: 0.000794 acc_pose: 0.801315 loss: 0.000794 2022/09/17 14:27:05 - mmengine - INFO - Epoch(train) [42][150/293] lr: 5.000000e-04 eta: 4:16:57 time: 0.344456 data_time: 0.075509 memory: 5151 loss_kpt: 0.000798 acc_pose: 0.791587 loss: 0.000798 2022/09/17 14:27:23 - mmengine - INFO - Epoch(train) [42][200/293] lr: 5.000000e-04 eta: 4:16:49 time: 0.349512 data_time: 0.076288 memory: 5151 loss_kpt: 0.000816 acc_pose: 0.782803 loss: 0.000816 2022/09/17 14:27:40 - mmengine - INFO - Epoch(train) [42][250/293] lr: 5.000000e-04 eta: 4:16:38 time: 0.335294 data_time: 0.071845 memory: 5151 loss_kpt: 0.000802 acc_pose: 0.746689 loss: 0.000802 2022/09/17 14:27:55 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:27:55 - mmengine - INFO - Saving checkpoint at 42 epochs 2022/09/17 14:28:15 - mmengine - INFO - Epoch(train) [43][50/293] lr: 5.000000e-04 eta: 4:15:23 time: 0.350985 data_time: 0.077613 memory: 5151 loss_kpt: 0.000789 acc_pose: 0.813966 loss: 0.000789 2022/09/17 14:28:32 - mmengine - INFO - Epoch(train) [43][100/293] lr: 5.000000e-04 eta: 4:15:14 time: 0.340497 data_time: 0.065907 memory: 5151 loss_kpt: 0.000800 acc_pose: 0.793016 loss: 0.000800 2022/09/17 14:28:49 - mmengine - INFO - Epoch(train) [43][150/293] lr: 5.000000e-04 eta: 4:15:03 time: 0.337205 data_time: 0.065715 memory: 5151 loss_kpt: 0.000790 acc_pose: 0.781941 loss: 0.000790 2022/09/17 14:29:06 - mmengine - INFO - Epoch(train) [43][200/293] lr: 5.000000e-04 eta: 4:14:53 time: 0.339489 data_time: 0.078640 memory: 5151 loss_kpt: 0.000776 acc_pose: 0.780523 loss: 0.000776 2022/09/17 14:29:23 - mmengine - INFO - Epoch(train) [43][250/293] lr: 5.000000e-04 eta: 4:14:42 time: 0.336034 data_time: 0.065846 memory: 5151 loss_kpt: 0.000794 acc_pose: 0.761923 loss: 0.000794 2022/09/17 14:29:37 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:29:37 - mmengine - INFO - Saving checkpoint at 43 epochs 2022/09/17 14:29:57 - mmengine - INFO - Epoch(train) [44][50/293] lr: 5.000000e-04 eta: 4:13:28 time: 0.347583 data_time: 0.071783 memory: 5151 loss_kpt: 0.000808 acc_pose: 0.718309 loss: 0.000808 2022/09/17 14:30:14 - mmengine - INFO - Epoch(train) [44][100/293] lr: 5.000000e-04 eta: 4:13:17 time: 0.334183 data_time: 0.065551 memory: 5151 loss_kpt: 0.000786 acc_pose: 0.781269 loss: 0.000786 2022/09/17 14:30:32 - mmengine - INFO - Epoch(train) [44][150/293] lr: 5.000000e-04 eta: 4:13:08 time: 0.348138 data_time: 0.066124 memory: 5151 loss_kpt: 0.000807 acc_pose: 0.817978 loss: 0.000807 2022/09/17 14:30:48 - mmengine - INFO - Epoch(train) [44][200/293] lr: 5.000000e-04 eta: 4:12:56 time: 0.331072 data_time: 0.066070 memory: 5151 loss_kpt: 0.000799 acc_pose: 0.766960 loss: 0.000799 2022/09/17 14:31:05 - mmengine - INFO - Epoch(train) [44][250/293] lr: 5.000000e-04 eta: 4:12:47 time: 0.342197 data_time: 0.076306 memory: 5151 loss_kpt: 0.000802 acc_pose: 0.804563 loss: 0.000802 2022/09/17 14:31:20 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:31:20 - mmengine - INFO - Saving checkpoint at 44 epochs 2022/09/17 14:31:40 - mmengine - INFO - Epoch(train) [45][50/293] lr: 5.000000e-04 eta: 4:11:35 time: 0.349731 data_time: 0.082963 memory: 5151 loss_kpt: 0.000802 acc_pose: 0.756764 loss: 0.000802 2022/09/17 14:31:56 - mmengine - INFO - Epoch(train) [45][100/293] lr: 5.000000e-04 eta: 4:11:21 time: 0.321793 data_time: 0.068356 memory: 5151 loss_kpt: 0.000799 acc_pose: 0.747658 loss: 0.000799 2022/09/17 14:31:59 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:32:13 - mmengine - INFO - Epoch(train) [45][150/293] lr: 5.000000e-04 eta: 4:11:10 time: 0.334770 data_time: 0.062174 memory: 5151 loss_kpt: 0.000780 acc_pose: 0.795545 loss: 0.000780 2022/09/17 14:32:29 - mmengine - INFO - Epoch(train) [45][200/293] lr: 5.000000e-04 eta: 4:10:58 time: 0.328009 data_time: 0.065629 memory: 5151 loss_kpt: 0.000788 acc_pose: 0.811015 loss: 0.000788 2022/09/17 14:32:45 - mmengine - INFO - Epoch(train) [45][250/293] lr: 5.000000e-04 eta: 4:10:46 time: 0.329813 data_time: 0.065752 memory: 5151 loss_kpt: 0.000774 acc_pose: 0.838930 loss: 0.000774 2022/09/17 14:33:00 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:33:00 - mmengine - INFO - Saving checkpoint at 45 epochs 2022/09/17 14:33:20 - mmengine - INFO - Epoch(train) [46][50/293] lr: 5.000000e-04 eta: 4:09:35 time: 0.346726 data_time: 0.072734 memory: 5151 loss_kpt: 0.000786 acc_pose: 0.785656 loss: 0.000786 2022/09/17 14:33:37 - mmengine - INFO - Epoch(train) [46][100/293] lr: 5.000000e-04 eta: 4:09:24 time: 0.340129 data_time: 0.071496 memory: 5151 loss_kpt: 0.000801 acc_pose: 0.722820 loss: 0.000801 2022/09/17 14:33:53 - mmengine - INFO - Epoch(train) [46][150/293] lr: 5.000000e-04 eta: 4:09:12 time: 0.325335 data_time: 0.075707 memory: 5151 loss_kpt: 0.000782 acc_pose: 0.811120 loss: 0.000782 2022/09/17 14:34:10 - mmengine - INFO - Epoch(train) [46][200/293] lr: 5.000000e-04 eta: 4:09:03 time: 0.348464 data_time: 0.082844 memory: 5151 loss_kpt: 0.000795 acc_pose: 0.748304 loss: 0.000795 2022/09/17 14:34:27 - mmengine - INFO - Epoch(train) [46][250/293] lr: 5.000000e-04 eta: 4:08:52 time: 0.335806 data_time: 0.074564 memory: 5151 loss_kpt: 0.000793 acc_pose: 0.806197 loss: 0.000793 2022/09/17 14:34:42 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:34:42 - mmengine - INFO - Saving checkpoint at 46 epochs 2022/09/17 14:35:01 - mmengine - INFO - Epoch(train) [47][50/293] lr: 5.000000e-04 eta: 4:07:40 time: 0.332459 data_time: 0.065348 memory: 5151 loss_kpt: 0.000788 acc_pose: 0.762740 loss: 0.000788 2022/09/17 14:35:18 - mmengine - INFO - Epoch(train) [47][100/293] lr: 5.000000e-04 eta: 4:07:31 time: 0.345565 data_time: 0.074987 memory: 5151 loss_kpt: 0.000767 acc_pose: 0.782437 loss: 0.000767 2022/09/17 14:35:35 - mmengine - INFO - Epoch(train) [47][150/293] lr: 5.000000e-04 eta: 4:07:21 time: 0.343234 data_time: 0.076617 memory: 5151 loss_kpt: 0.000781 acc_pose: 0.792295 loss: 0.000781 2022/09/17 14:35:53 - mmengine - INFO - Epoch(train) [47][200/293] lr: 5.000000e-04 eta: 4:07:12 time: 0.346616 data_time: 0.086294 memory: 5151 loss_kpt: 0.000787 acc_pose: 0.743561 loss: 0.000787 2022/09/17 14:36:10 - mmengine - INFO - Epoch(train) [47][250/293] lr: 5.000000e-04 eta: 4:07:02 time: 0.341937 data_time: 0.075828 memory: 5151 loss_kpt: 0.000781 acc_pose: 0.846233 loss: 0.000781 2022/09/17 14:36:24 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:36:24 - mmengine - INFO - Saving checkpoint at 47 epochs 2022/09/17 14:36:44 - mmengine - INFO - Epoch(train) [48][50/293] lr: 5.000000e-04 eta: 4:05:54 time: 0.351597 data_time: 0.075295 memory: 5151 loss_kpt: 0.000779 acc_pose: 0.819907 loss: 0.000779 2022/09/17 14:37:01 - mmengine - INFO - Epoch(train) [48][100/293] lr: 5.000000e-04 eta: 4:05:46 time: 0.348788 data_time: 0.079718 memory: 5151 loss_kpt: 0.000787 acc_pose: 0.834768 loss: 0.000787 2022/09/17 14:37:18 - mmengine - INFO - Epoch(train) [48][150/293] lr: 5.000000e-04 eta: 4:05:34 time: 0.331587 data_time: 0.063271 memory: 5151 loss_kpt: 0.000778 acc_pose: 0.739505 loss: 0.000778 2022/09/17 14:37:36 - mmengine - INFO - Epoch(train) [48][200/293] lr: 5.000000e-04 eta: 4:05:27 time: 0.358456 data_time: 0.070362 memory: 5151 loss_kpt: 0.000789 acc_pose: 0.826191 loss: 0.000789 2022/09/17 14:37:46 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:37:53 - mmengine - INFO - Epoch(train) [48][250/293] lr: 5.000000e-04 eta: 4:05:17 time: 0.343887 data_time: 0.072907 memory: 5151 loss_kpt: 0.000781 acc_pose: 0.794557 loss: 0.000781 2022/09/17 14:38:07 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:38:07 - mmengine - INFO - Saving checkpoint at 48 epochs 2022/09/17 14:38:27 - mmengine - INFO - Epoch(train) [49][50/293] lr: 5.000000e-04 eta: 4:04:07 time: 0.330184 data_time: 0.069888 memory: 5151 loss_kpt: 0.000775 acc_pose: 0.753363 loss: 0.000775 2022/09/17 14:38:44 - mmengine - INFO - Epoch(train) [49][100/293] lr: 5.000000e-04 eta: 4:03:57 time: 0.341243 data_time: 0.074690 memory: 5151 loss_kpt: 0.000788 acc_pose: 0.741663 loss: 0.000788 2022/09/17 14:39:01 - mmengine - INFO - Epoch(train) [49][150/293] lr: 5.000000e-04 eta: 4:03:47 time: 0.341807 data_time: 0.065551 memory: 5151 loss_kpt: 0.000786 acc_pose: 0.774484 loss: 0.000786 2022/09/17 14:39:18 - mmengine - INFO - Epoch(train) [49][200/293] lr: 5.000000e-04 eta: 4:03:37 time: 0.344970 data_time: 0.077873 memory: 5151 loss_kpt: 0.000786 acc_pose: 0.828310 loss: 0.000786 2022/09/17 14:39:35 - mmengine - INFO - Epoch(train) [49][250/293] lr: 5.000000e-04 eta: 4:03:26 time: 0.332607 data_time: 0.069612 memory: 5151 loss_kpt: 0.000786 acc_pose: 0.783713 loss: 0.000786 2022/09/17 14:39:49 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:39:49 - mmengine - INFO - Saving checkpoint at 49 epochs 2022/09/17 14:40:09 - mmengine - INFO - Epoch(train) [50][50/293] lr: 5.000000e-04 eta: 4:02:19 time: 0.343715 data_time: 0.072537 memory: 5151 loss_kpt: 0.000783 acc_pose: 0.819842 loss: 0.000783 2022/09/17 14:40:26 - mmengine - INFO - Epoch(train) [50][100/293] lr: 5.000000e-04 eta: 4:02:10 time: 0.346538 data_time: 0.074041 memory: 5151 loss_kpt: 0.000776 acc_pose: 0.826251 loss: 0.000776 2022/09/17 14:40:43 - mmengine - INFO - Epoch(train) [50][150/293] lr: 5.000000e-04 eta: 4:01:59 time: 0.336716 data_time: 0.076460 memory: 5151 loss_kpt: 0.000784 acc_pose: 0.778914 loss: 0.000784 2022/09/17 14:40:59 - mmengine - INFO - Epoch(train) [50][200/293] lr: 5.000000e-04 eta: 4:01:48 time: 0.333429 data_time: 0.075800 memory: 5151 loss_kpt: 0.000763 acc_pose: 0.798261 loss: 0.000763 2022/09/17 14:41:17 - mmengine - INFO - Epoch(train) [50][250/293] lr: 5.000000e-04 eta: 4:01:38 time: 0.342271 data_time: 0.068520 memory: 5151 loss_kpt: 0.000800 acc_pose: 0.823103 loss: 0.000800 2022/09/17 14:41:31 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:41:31 - mmengine - INFO - Saving checkpoint at 50 epochs 2022/09/17 14:41:40 - mmengine - INFO - Epoch(val) [50][50/407] eta: 0:00:43 time: 0.121101 data_time: 0.052843 memory: 5151 2022/09/17 14:41:46 - mmengine - INFO - Epoch(val) [50][100/407] eta: 0:00:35 time: 0.116275 data_time: 0.047923 memory: 331 2022/09/17 14:41:52 - mmengine - INFO - Epoch(val) [50][150/407] eta: 0:00:30 time: 0.118088 data_time: 0.049988 memory: 331 2022/09/17 14:41:58 - mmengine - INFO - Epoch(val) [50][200/407] eta: 0:00:25 time: 0.122889 data_time: 0.055439 memory: 331 2022/09/17 14:42:04 - mmengine - INFO - Epoch(val) [50][250/407] eta: 0:00:18 time: 0.117420 data_time: 0.049945 memory: 331 2022/09/17 14:42:10 - mmengine - INFO - Epoch(val) [50][300/407] eta: 0:00:12 time: 0.120884 data_time: 0.053003 memory: 331 2022/09/17 14:42:16 - mmengine - INFO - Epoch(val) [50][350/407] eta: 0:00:06 time: 0.116451 data_time: 0.049387 memory: 331 2022/09/17 14:42:21 - mmengine - INFO - Epoch(val) [50][400/407] eta: 0:00:00 time: 0.105357 data_time: 0.040992 memory: 331 2022/09/17 14:42:57 - mmengine - INFO - Evaluating CocoMetric... 2022/09/17 14:43:11 - mmengine - INFO - Epoch(val) [50][407/407] coco/AP: 0.658940 coco/AP .5: 0.871932 coco/AP .75: 0.739379 coco/AP (M): 0.629139 coco/AP (L): 0.719488 coco/AR: 0.721174 coco/AR .5: 0.916719 coco/AR .75: 0.793766 coco/AR (M): 0.681207 coco/AR (L): 0.778187 2022/09/17 14:43:11 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220917/vipnas_res50/best_coco/AP_epoch_40.pth is removed 2022/09/17 14:43:13 - mmengine - INFO - The best checkpoint with 0.6589 coco/AP at 50 epoch is saved to best_coco/AP_epoch_50.pth. 2022/09/17 14:43:30 - mmengine - INFO - Epoch(train) [51][50/293] lr: 5.000000e-04 eta: 4:00:31 time: 0.339117 data_time: 0.070179 memory: 5151 loss_kpt: 0.000773 acc_pose: 0.803209 loss: 0.000773 2022/09/17 14:43:47 - mmengine - INFO - Epoch(train) [51][100/293] lr: 5.000000e-04 eta: 4:00:20 time: 0.332745 data_time: 0.065070 memory: 5151 loss_kpt: 0.000780 acc_pose: 0.784756 loss: 0.000780 2022/09/17 14:44:04 - mmengine - INFO - Epoch(train) [51][150/293] lr: 5.000000e-04 eta: 4:00:09 time: 0.339786 data_time: 0.062457 memory: 5151 loss_kpt: 0.000779 acc_pose: 0.785983 loss: 0.000779 2022/09/17 14:44:21 - mmengine - INFO - Epoch(train) [51][200/293] lr: 5.000000e-04 eta: 4:00:00 time: 0.344544 data_time: 0.067302 memory: 5151 loss_kpt: 0.000781 acc_pose: 0.787815 loss: 0.000781 2022/09/17 14:44:38 - mmengine - INFO - Epoch(train) [51][250/293] lr: 5.000000e-04 eta: 3:59:49 time: 0.337384 data_time: 0.069461 memory: 5151 loss_kpt: 0.000797 acc_pose: 0.755547 loss: 0.000797 2022/09/17 14:44:52 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:44:52 - mmengine - INFO - Saving checkpoint at 51 epochs 2022/09/17 14:45:12 - mmengine - INFO - Epoch(train) [52][50/293] lr: 5.000000e-04 eta: 3:58:44 time: 0.345133 data_time: 0.078769 memory: 5151 loss_kpt: 0.000763 acc_pose: 0.784402 loss: 0.000763 2022/09/17 14:45:15 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:45:30 - mmengine - INFO - Epoch(train) [52][100/293] lr: 5.000000e-04 eta: 3:58:36 time: 0.350621 data_time: 0.073884 memory: 5151 loss_kpt: 0.000766 acc_pose: 0.806117 loss: 0.000766 2022/09/17 14:45:46 - mmengine - INFO - Epoch(train) [52][150/293] lr: 5.000000e-04 eta: 3:58:24 time: 0.333386 data_time: 0.062924 memory: 5151 loss_kpt: 0.000779 acc_pose: 0.793176 loss: 0.000779 2022/09/17 14:46:03 - mmengine - INFO - Epoch(train) [52][200/293] lr: 5.000000e-04 eta: 3:58:13 time: 0.337583 data_time: 0.067589 memory: 5151 loss_kpt: 0.000771 acc_pose: 0.798919 loss: 0.000771 2022/09/17 14:46:21 - mmengine - INFO - Epoch(train) [52][250/293] lr: 5.000000e-04 eta: 3:58:04 time: 0.346184 data_time: 0.071178 memory: 5151 loss_kpt: 0.000778 acc_pose: 0.852613 loss: 0.000778 2022/09/17 14:46:37 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:46:37 - mmengine - INFO - Saving checkpoint at 52 epochs 2022/09/17 14:46:57 - mmengine - INFO - Epoch(train) [53][50/293] lr: 5.000000e-04 eta: 3:57:00 time: 0.344683 data_time: 0.072443 memory: 5151 loss_kpt: 0.000770 acc_pose: 0.789430 loss: 0.000770 2022/09/17 14:47:13 - mmengine - INFO - Epoch(train) [53][100/293] lr: 5.000000e-04 eta: 3:56:48 time: 0.326185 data_time: 0.062120 memory: 5151 loss_kpt: 0.000774 acc_pose: 0.797898 loss: 0.000774 2022/09/17 14:47:30 - mmengine - INFO - Epoch(train) [53][150/293] lr: 5.000000e-04 eta: 3:56:36 time: 0.330367 data_time: 0.067143 memory: 5151 loss_kpt: 0.000775 acc_pose: 0.801073 loss: 0.000775 2022/09/17 14:47:47 - mmengine - INFO - Epoch(train) [53][200/293] lr: 5.000000e-04 eta: 3:56:26 time: 0.346980 data_time: 0.083186 memory: 5151 loss_kpt: 0.000762 acc_pose: 0.783499 loss: 0.000762 2022/09/17 14:48:03 - mmengine - INFO - Epoch(train) [53][250/293] lr: 5.000000e-04 eta: 3:56:14 time: 0.326842 data_time: 0.069068 memory: 5151 loss_kpt: 0.000779 acc_pose: 0.787739 loss: 0.000779 2022/09/17 14:48:17 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:48:17 - mmengine - INFO - Saving checkpoint at 53 epochs 2022/09/17 14:48:38 - mmengine - INFO - Epoch(train) [54][50/293] lr: 5.000000e-04 eta: 3:55:14 time: 0.361407 data_time: 0.080758 memory: 5151 loss_kpt: 0.000764 acc_pose: 0.825454 loss: 0.000764 2022/09/17 14:48:54 - mmengine - INFO - Epoch(train) [54][100/293] lr: 5.000000e-04 eta: 3:55:02 time: 0.331010 data_time: 0.065546 memory: 5151 loss_kpt: 0.000777 acc_pose: 0.810457 loss: 0.000777 2022/09/17 14:49:11 - mmengine - INFO - Epoch(train) [54][150/293] lr: 5.000000e-04 eta: 3:54:51 time: 0.338178 data_time: 0.069979 memory: 5151 loss_kpt: 0.000780 acc_pose: 0.794921 loss: 0.000780 2022/09/17 14:49:28 - mmengine - INFO - Epoch(train) [54][200/293] lr: 5.000000e-04 eta: 3:54:40 time: 0.333477 data_time: 0.068218 memory: 5151 loss_kpt: 0.000780 acc_pose: 0.826814 loss: 0.000780 2022/09/17 14:49:45 - mmengine - INFO - Epoch(train) [54][250/293] lr: 5.000000e-04 eta: 3:54:29 time: 0.336635 data_time: 0.071492 memory: 5151 loss_kpt: 0.000774 acc_pose: 0.790111 loss: 0.000774 2022/09/17 14:49:59 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:49:59 - mmengine - INFO - Saving checkpoint at 54 epochs 2022/09/17 14:50:18 - mmengine - INFO - Epoch(train) [55][50/293] lr: 5.000000e-04 eta: 3:53:27 time: 0.341727 data_time: 0.076912 memory: 5151 loss_kpt: 0.000771 acc_pose: 0.792361 loss: 0.000771 2022/09/17 14:50:35 - mmengine - INFO - Epoch(train) [55][100/293] lr: 5.000000e-04 eta: 3:53:17 time: 0.341898 data_time: 0.075536 memory: 5151 loss_kpt: 0.000774 acc_pose: 0.791578 loss: 0.000774 2022/09/17 14:50:52 - mmengine - INFO - Epoch(train) [55][150/293] lr: 5.000000e-04 eta: 3:53:05 time: 0.332105 data_time: 0.075625 memory: 5151 loss_kpt: 0.000764 acc_pose: 0.766973 loss: 0.000764 2022/09/17 14:51:02 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:51:10 - mmengine - INFO - Epoch(train) [55][200/293] lr: 5.000000e-04 eta: 3:52:56 time: 0.352002 data_time: 0.078894 memory: 5151 loss_kpt: 0.000761 acc_pose: 0.819173 loss: 0.000761 2022/09/17 14:51:27 - mmengine - INFO - Epoch(train) [55][250/293] lr: 5.000000e-04 eta: 3:52:47 time: 0.348887 data_time: 0.076760 memory: 5151 loss_kpt: 0.000786 acc_pose: 0.783960 loss: 0.000786 2022/09/17 14:51:41 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:51:42 - mmengine - INFO - Saving checkpoint at 55 epochs 2022/09/17 14:52:01 - mmengine - INFO - Epoch(train) [56][50/293] lr: 5.000000e-04 eta: 3:51:46 time: 0.346777 data_time: 0.077076 memory: 5151 loss_kpt: 0.000754 acc_pose: 0.827567 loss: 0.000754 2022/09/17 14:52:19 - mmengine - INFO - Epoch(train) [56][100/293] lr: 5.000000e-04 eta: 3:51:36 time: 0.344972 data_time: 0.075494 memory: 5151 loss_kpt: 0.000764 acc_pose: 0.821505 loss: 0.000764 2022/09/17 14:52:36 - mmengine - INFO - Epoch(train) [56][150/293] lr: 5.000000e-04 eta: 3:51:27 time: 0.352155 data_time: 0.074348 memory: 5151 loss_kpt: 0.000769 acc_pose: 0.757570 loss: 0.000769 2022/09/17 14:52:53 - mmengine - INFO - Epoch(train) [56][200/293] lr: 5.000000e-04 eta: 3:51:17 time: 0.345501 data_time: 0.069799 memory: 5151 loss_kpt: 0.000746 acc_pose: 0.806588 loss: 0.000746 2022/09/17 14:53:11 - mmengine - INFO - Epoch(train) [56][250/293] lr: 5.000000e-04 eta: 3:51:08 time: 0.351643 data_time: 0.071122 memory: 5151 loss_kpt: 0.000772 acc_pose: 0.816322 loss: 0.000772 2022/09/17 14:53:26 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:53:26 - mmengine - INFO - Saving checkpoint at 56 epochs 2022/09/17 14:53:47 - mmengine - INFO - Epoch(train) [57][50/293] lr: 5.000000e-04 eta: 3:50:11 time: 0.358012 data_time: 0.071333 memory: 5151 loss_kpt: 0.000753 acc_pose: 0.817308 loss: 0.000753 2022/09/17 14:54:03 - mmengine - INFO - Epoch(train) [57][100/293] lr: 5.000000e-04 eta: 3:49:59 time: 0.330937 data_time: 0.068448 memory: 5151 loss_kpt: 0.000763 acc_pose: 0.744902 loss: 0.000763 2022/09/17 14:54:21 - mmengine - INFO - Epoch(train) [57][150/293] lr: 5.000000e-04 eta: 3:49:49 time: 0.351182 data_time: 0.066268 memory: 5151 loss_kpt: 0.000769 acc_pose: 0.803064 loss: 0.000769 2022/09/17 14:54:38 - mmengine - INFO - Epoch(train) [57][200/293] lr: 5.000000e-04 eta: 3:49:38 time: 0.334418 data_time: 0.070641 memory: 5151 loss_kpt: 0.000771 acc_pose: 0.786241 loss: 0.000771 2022/09/17 14:54:54 - mmengine - INFO - Epoch(train) [57][250/293] lr: 5.000000e-04 eta: 3:49:26 time: 0.331769 data_time: 0.070867 memory: 5151 loss_kpt: 0.000750 acc_pose: 0.838630 loss: 0.000750 2022/09/17 14:55:09 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:55:09 - mmengine - INFO - Saving checkpoint at 57 epochs 2022/09/17 14:55:29 - mmengine - INFO - Epoch(train) [58][50/293] lr: 5.000000e-04 eta: 3:48:29 time: 0.356780 data_time: 0.070782 memory: 5151 loss_kpt: 0.000759 acc_pose: 0.849551 loss: 0.000759 2022/09/17 14:55:45 - mmengine - INFO - Epoch(train) [58][100/293] lr: 5.000000e-04 eta: 3:48:16 time: 0.328024 data_time: 0.062161 memory: 5151 loss_kpt: 0.000773 acc_pose: 0.762985 loss: 0.000773 2022/09/17 14:56:03 - mmengine - INFO - Epoch(train) [58][150/293] lr: 5.000000e-04 eta: 3:48:06 time: 0.341733 data_time: 0.068932 memory: 5151 loss_kpt: 0.000773 acc_pose: 0.817594 loss: 0.000773 2022/09/17 14:56:20 - mmengine - INFO - Epoch(train) [58][200/293] lr: 5.000000e-04 eta: 3:47:57 time: 0.355585 data_time: 0.072180 memory: 5151 loss_kpt: 0.000766 acc_pose: 0.812454 loss: 0.000766 2022/09/17 14:56:37 - mmengine - INFO - Epoch(train) [58][250/293] lr: 5.000000e-04 eta: 3:47:46 time: 0.339689 data_time: 0.066679 memory: 5151 loss_kpt: 0.000772 acc_pose: 0.805510 loss: 0.000772 2022/09/17 14:56:52 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:56:52 - mmengine - INFO - Saving checkpoint at 58 epochs 2022/09/17 14:56:57 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:57:12 - mmengine - INFO - Epoch(train) [59][50/293] lr: 5.000000e-04 eta: 3:46:49 time: 0.352682 data_time: 0.073350 memory: 5151 loss_kpt: 0.000756 acc_pose: 0.810778 loss: 0.000756 2022/09/17 14:57:29 - mmengine - INFO - Epoch(train) [59][100/293] lr: 5.000000e-04 eta: 3:46:38 time: 0.340798 data_time: 0.068072 memory: 5151 loss_kpt: 0.000772 acc_pose: 0.791648 loss: 0.000772 2022/09/17 14:57:47 - mmengine - INFO - Epoch(train) [59][150/293] lr: 5.000000e-04 eta: 3:46:28 time: 0.345945 data_time: 0.071255 memory: 5151 loss_kpt: 0.000777 acc_pose: 0.809546 loss: 0.000777 2022/09/17 14:58:04 - mmengine - INFO - Epoch(train) [59][200/293] lr: 5.000000e-04 eta: 3:46:17 time: 0.340443 data_time: 0.067396 memory: 5151 loss_kpt: 0.000753 acc_pose: 0.851326 loss: 0.000753 2022/09/17 14:58:21 - mmengine - INFO - Epoch(train) [59][250/293] lr: 5.000000e-04 eta: 3:46:08 time: 0.350067 data_time: 0.062415 memory: 5151 loss_kpt: 0.000773 acc_pose: 0.796852 loss: 0.000773 2022/09/17 14:58:35 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 14:58:35 - mmengine - INFO - Saving checkpoint at 59 epochs 2022/09/17 14:58:54 - mmengine - INFO - Epoch(train) [60][50/293] lr: 5.000000e-04 eta: 3:45:10 time: 0.339557 data_time: 0.072085 memory: 5151 loss_kpt: 0.000759 acc_pose: 0.796864 loss: 0.000759 2022/09/17 14:59:11 - mmengine - INFO - Epoch(train) [60][100/293] lr: 5.000000e-04 eta: 3:44:57 time: 0.329682 data_time: 0.066217 memory: 5151 loss_kpt: 0.000762 acc_pose: 0.811173 loss: 0.000762 2022/09/17 14:59:28 - mmengine - INFO - Epoch(train) [60][150/293] lr: 5.000000e-04 eta: 3:44:47 time: 0.343122 data_time: 0.073105 memory: 5151 loss_kpt: 0.000775 acc_pose: 0.755587 loss: 0.000775 2022/09/17 14:59:45 - mmengine - INFO - Epoch(train) [60][200/293] lr: 5.000000e-04 eta: 3:44:36 time: 0.339365 data_time: 0.070222 memory: 5151 loss_kpt: 0.000757 acc_pose: 0.764298 loss: 0.000757 2022/09/17 15:00:02 - mmengine - INFO - Epoch(train) [60][250/293] lr: 5.000000e-04 eta: 3:44:24 time: 0.336976 data_time: 0.070205 memory: 5151 loss_kpt: 0.000757 acc_pose: 0.829754 loss: 0.000757 2022/09/17 15:00:16 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:00:16 - mmengine - INFO - Saving checkpoint at 60 epochs 2022/09/17 15:00:25 - mmengine - INFO - Epoch(val) [60][50/407] eta: 0:00:43 time: 0.122316 data_time: 0.050066 memory: 5151 2022/09/17 15:00:31 - mmengine - INFO - Epoch(val) [60][100/407] eta: 0:00:35 time: 0.114008 data_time: 0.047084 memory: 331 2022/09/17 15:00:37 - mmengine - INFO - Epoch(val) [60][150/407] eta: 0:00:30 time: 0.120543 data_time: 0.052862 memory: 331 2022/09/17 15:00:43 - mmengine - INFO - Epoch(val) [60][200/407] eta: 0:00:24 time: 0.118399 data_time: 0.050428 memory: 331 2022/09/17 15:00:49 - mmengine - INFO - Epoch(val) [60][250/407] eta: 0:00:18 time: 0.116625 data_time: 0.047740 memory: 331 2022/09/17 15:00:55 - mmengine - INFO - Epoch(val) [60][300/407] eta: 0:00:13 time: 0.127187 data_time: 0.052596 memory: 331 2022/09/17 15:01:01 - mmengine - INFO - Epoch(val) [60][350/407] eta: 0:00:06 time: 0.115738 data_time: 0.049977 memory: 331 2022/09/17 15:01:06 - mmengine - INFO - Epoch(val) [60][400/407] eta: 0:00:00 time: 0.109628 data_time: 0.045107 memory: 331 2022/09/17 15:01:42 - mmengine - INFO - Evaluating CocoMetric... 2022/09/17 15:01:56 - mmengine - INFO - Epoch(val) [60][407/407] coco/AP: 0.664723 coco/AP .5: 0.872903 coco/AP .75: 0.741273 coco/AP (M): 0.634710 coco/AP (L): 0.726437 coco/AR: 0.726039 coco/AR .5: 0.917034 coco/AR .75: 0.794710 coco/AR (M): 0.684731 coco/AR (L): 0.784615 2022/09/17 15:01:56 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220917/vipnas_res50/best_coco/AP_epoch_50.pth is removed 2022/09/17 15:01:59 - mmengine - INFO - The best checkpoint with 0.6647 coco/AP at 60 epoch is saved to best_coco/AP_epoch_60.pth. 2022/09/17 15:02:16 - mmengine - INFO - Epoch(train) [61][50/293] lr: 5.000000e-04 eta: 3:43:28 time: 0.346200 data_time: 0.082021 memory: 5151 loss_kpt: 0.000748 acc_pose: 0.841895 loss: 0.000748 2022/09/17 15:02:33 - mmengine - INFO - Epoch(train) [61][100/293] lr: 5.000000e-04 eta: 3:43:19 time: 0.350920 data_time: 0.073181 memory: 5151 loss_kpt: 0.000769 acc_pose: 0.789510 loss: 0.000769 2022/09/17 15:02:51 - mmengine - INFO - Epoch(train) [61][150/293] lr: 5.000000e-04 eta: 3:43:09 time: 0.348937 data_time: 0.073772 memory: 5151 loss_kpt: 0.000751 acc_pose: 0.788659 loss: 0.000751 2022/09/17 15:03:07 - mmengine - INFO - Epoch(train) [61][200/293] lr: 5.000000e-04 eta: 3:42:57 time: 0.332668 data_time: 0.067219 memory: 5151 loss_kpt: 0.000766 acc_pose: 0.801416 loss: 0.000766 2022/09/17 15:03:24 - mmengine - INFO - Epoch(train) [61][250/293] lr: 5.000000e-04 eta: 3:42:45 time: 0.331722 data_time: 0.059273 memory: 5151 loss_kpt: 0.000756 acc_pose: 0.762838 loss: 0.000756 2022/09/17 15:03:38 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:03:38 - mmengine - INFO - Saving checkpoint at 61 epochs 2022/09/17 15:03:58 - mmengine - INFO - Epoch(train) [62][50/293] lr: 5.000000e-04 eta: 3:41:50 time: 0.356656 data_time: 0.083824 memory: 5151 loss_kpt: 0.000763 acc_pose: 0.784437 loss: 0.000763 2022/09/17 15:04:15 - mmengine - INFO - Epoch(train) [62][100/293] lr: 5.000000e-04 eta: 3:41:39 time: 0.335602 data_time: 0.067235 memory: 5151 loss_kpt: 0.000757 acc_pose: 0.772573 loss: 0.000757 2022/09/17 15:04:24 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:04:32 - mmengine - INFO - Epoch(train) [62][150/293] lr: 5.000000e-04 eta: 3:41:27 time: 0.331612 data_time: 0.059601 memory: 5151 loss_kpt: 0.000771 acc_pose: 0.785550 loss: 0.000771 2022/09/17 15:04:49 - mmengine - INFO - Epoch(train) [62][200/293] lr: 5.000000e-04 eta: 3:41:17 time: 0.348707 data_time: 0.070727 memory: 5151 loss_kpt: 0.000756 acc_pose: 0.770942 loss: 0.000756 2022/09/17 15:05:06 - mmengine - INFO - Epoch(train) [62][250/293] lr: 5.000000e-04 eta: 3:41:05 time: 0.336830 data_time: 0.061327 memory: 5151 loss_kpt: 0.000765 acc_pose: 0.795161 loss: 0.000765 2022/09/17 15:05:20 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:05:20 - mmengine - INFO - Saving checkpoint at 62 epochs 2022/09/17 15:05:40 - mmengine - INFO - Epoch(train) [63][50/293] lr: 5.000000e-04 eta: 3:40:09 time: 0.339809 data_time: 0.073857 memory: 5151 loss_kpt: 0.000755 acc_pose: 0.800555 loss: 0.000755 2022/09/17 15:05:57 - mmengine - INFO - Epoch(train) [63][100/293] lr: 5.000000e-04 eta: 3:39:59 time: 0.344524 data_time: 0.065791 memory: 5151 loss_kpt: 0.000750 acc_pose: 0.833051 loss: 0.000750 2022/09/17 15:06:14 - mmengine - INFO - Epoch(train) [63][150/293] lr: 5.000000e-04 eta: 3:39:47 time: 0.331446 data_time: 0.071016 memory: 5151 loss_kpt: 0.000766 acc_pose: 0.813781 loss: 0.000766 2022/09/17 15:06:31 - mmengine - INFO - Epoch(train) [63][200/293] lr: 5.000000e-04 eta: 3:39:36 time: 0.345581 data_time: 0.067550 memory: 5151 loss_kpt: 0.000760 acc_pose: 0.849820 loss: 0.000760 2022/09/17 15:06:48 - mmengine - INFO - Epoch(train) [63][250/293] lr: 5.000000e-04 eta: 3:39:26 time: 0.349896 data_time: 0.073566 memory: 5151 loss_kpt: 0.000752 acc_pose: 0.821866 loss: 0.000752 2022/09/17 15:07:03 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:07:03 - mmengine - INFO - Saving checkpoint at 63 epochs 2022/09/17 15:07:23 - mmengine - INFO - Epoch(train) [64][50/293] lr: 5.000000e-04 eta: 3:38:32 time: 0.347046 data_time: 0.080966 memory: 5151 loss_kpt: 0.000755 acc_pose: 0.800947 loss: 0.000755 2022/09/17 15:07:40 - mmengine - INFO - Epoch(train) [64][100/293] lr: 5.000000e-04 eta: 3:38:21 time: 0.338077 data_time: 0.068488 memory: 5151 loss_kpt: 0.000770 acc_pose: 0.795982 loss: 0.000770 2022/09/17 15:07:58 - mmengine - INFO - Epoch(train) [64][150/293] lr: 5.000000e-04 eta: 3:38:10 time: 0.347090 data_time: 0.075730 memory: 5151 loss_kpt: 0.000756 acc_pose: 0.748739 loss: 0.000756 2022/09/17 15:08:14 - mmengine - INFO - Epoch(train) [64][200/293] lr: 5.000000e-04 eta: 3:37:58 time: 0.328998 data_time: 0.066471 memory: 5151 loss_kpt: 0.000743 acc_pose: 0.826630 loss: 0.000743 2022/09/17 15:08:31 - mmengine - INFO - Epoch(train) [64][250/293] lr: 5.000000e-04 eta: 3:37:46 time: 0.338956 data_time: 0.063774 memory: 5151 loss_kpt: 0.000753 acc_pose: 0.801992 loss: 0.000753 2022/09/17 15:08:45 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:08:45 - mmengine - INFO - Saving checkpoint at 64 epochs 2022/09/17 15:09:05 - mmengine - INFO - Epoch(train) [65][50/293] lr: 5.000000e-04 eta: 3:36:53 time: 0.348908 data_time: 0.076235 memory: 5151 loss_kpt: 0.000755 acc_pose: 0.804063 loss: 0.000755 2022/09/17 15:09:22 - mmengine - INFO - Epoch(train) [65][100/293] lr: 5.000000e-04 eta: 3:36:41 time: 0.331084 data_time: 0.066925 memory: 5151 loss_kpt: 0.000746 acc_pose: 0.802759 loss: 0.000746 2022/09/17 15:09:39 - mmengine - INFO - Epoch(train) [65][150/293] lr: 5.000000e-04 eta: 3:36:30 time: 0.343955 data_time: 0.073561 memory: 5151 loss_kpt: 0.000759 acc_pose: 0.753614 loss: 0.000759 2022/09/17 15:09:56 - mmengine - INFO - Epoch(train) [65][200/293] lr: 5.000000e-04 eta: 3:36:19 time: 0.339069 data_time: 0.069980 memory: 5151 loss_kpt: 0.000763 acc_pose: 0.765723 loss: 0.000763 2022/09/17 15:10:13 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:10:13 - mmengine - INFO - Epoch(train) [65][250/293] lr: 5.000000e-04 eta: 3:36:08 time: 0.344720 data_time: 0.072618 memory: 5151 loss_kpt: 0.000762 acc_pose: 0.828748 loss: 0.000762 2022/09/17 15:10:28 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:10:28 - mmengine - INFO - Saving checkpoint at 65 epochs 2022/09/17 15:10:47 - mmengine - INFO - Epoch(train) [66][50/293] lr: 5.000000e-04 eta: 3:35:16 time: 0.350087 data_time: 0.072322 memory: 5151 loss_kpt: 0.000737 acc_pose: 0.807845 loss: 0.000737 2022/09/17 15:11:04 - mmengine - INFO - Epoch(train) [66][100/293] lr: 5.000000e-04 eta: 3:35:03 time: 0.328935 data_time: 0.074486 memory: 5151 loss_kpt: 0.000741 acc_pose: 0.752788 loss: 0.000741 2022/09/17 15:11:21 - mmengine - INFO - Epoch(train) [66][150/293] lr: 5.000000e-04 eta: 3:34:52 time: 0.339429 data_time: 0.073109 memory: 5151 loss_kpt: 0.000747 acc_pose: 0.816788 loss: 0.000747 2022/09/17 15:11:39 - mmengine - INFO - Epoch(train) [66][200/293] lr: 5.000000e-04 eta: 3:34:42 time: 0.352660 data_time: 0.072129 memory: 5151 loss_kpt: 0.000764 acc_pose: 0.826117 loss: 0.000764 2022/09/17 15:11:56 - mmengine - INFO - Epoch(train) [66][250/293] lr: 5.000000e-04 eta: 3:34:31 time: 0.343976 data_time: 0.070034 memory: 5151 loss_kpt: 0.000762 acc_pose: 0.792257 loss: 0.000762 2022/09/17 15:12:10 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:12:10 - mmengine - INFO - Saving checkpoint at 66 epochs 2022/09/17 15:12:31 - mmengine - INFO - Epoch(train) [67][50/293] lr: 5.000000e-04 eta: 3:33:40 time: 0.355871 data_time: 0.072549 memory: 5151 loss_kpt: 0.000741 acc_pose: 0.759901 loss: 0.000741 2022/09/17 15:12:48 - mmengine - INFO - Epoch(train) [67][100/293] lr: 5.000000e-04 eta: 3:33:30 time: 0.352715 data_time: 0.068137 memory: 5151 loss_kpt: 0.000751 acc_pose: 0.815022 loss: 0.000751 2022/09/17 15:13:06 - mmengine - INFO - Epoch(train) [67][150/293] lr: 5.000000e-04 eta: 3:33:19 time: 0.346557 data_time: 0.069142 memory: 5151 loss_kpt: 0.000763 acc_pose: 0.806604 loss: 0.000763 2022/09/17 15:13:23 - mmengine - INFO - Epoch(train) [67][200/293] lr: 5.000000e-04 eta: 3:33:08 time: 0.346829 data_time: 0.077639 memory: 5151 loss_kpt: 0.000751 acc_pose: 0.791789 loss: 0.000751 2022/09/17 15:13:40 - mmengine - INFO - Epoch(train) [67][250/293] lr: 5.000000e-04 eta: 3:32:56 time: 0.333009 data_time: 0.063778 memory: 5151 loss_kpt: 0.000763 acc_pose: 0.796117 loss: 0.000763 2022/09/17 15:13:54 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:13:54 - mmengine - INFO - Saving checkpoint at 67 epochs 2022/09/17 15:14:13 - mmengine - INFO - Epoch(train) [68][50/293] lr: 5.000000e-04 eta: 3:32:04 time: 0.342556 data_time: 0.066134 memory: 5151 loss_kpt: 0.000737 acc_pose: 0.827265 loss: 0.000737 2022/09/17 15:14:31 - mmengine - INFO - Epoch(train) [68][100/293] lr: 5.000000e-04 eta: 3:31:54 time: 0.350532 data_time: 0.075164 memory: 5151 loss_kpt: 0.000752 acc_pose: 0.845247 loss: 0.000752 2022/09/17 15:14:48 - mmengine - INFO - Epoch(train) [68][150/293] lr: 5.000000e-04 eta: 3:31:43 time: 0.347842 data_time: 0.076767 memory: 5151 loss_kpt: 0.000743 acc_pose: 0.783976 loss: 0.000743 2022/09/17 15:15:05 - mmengine - INFO - Epoch(train) [68][200/293] lr: 5.000000e-04 eta: 3:31:31 time: 0.336641 data_time: 0.066767 memory: 5151 loss_kpt: 0.000752 acc_pose: 0.793155 loss: 0.000752 2022/09/17 15:15:22 - mmengine - INFO - Epoch(train) [68][250/293] lr: 5.000000e-04 eta: 3:31:20 time: 0.341068 data_time: 0.065881 memory: 5151 loss_kpt: 0.000751 acc_pose: 0.796605 loss: 0.000751 2022/09/17 15:15:36 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:15:36 - mmengine - INFO - Saving checkpoint at 68 epochs 2022/09/17 15:15:56 - mmengine - INFO - Epoch(train) [69][50/293] lr: 5.000000e-04 eta: 3:30:29 time: 0.346817 data_time: 0.073184 memory: 5151 loss_kpt: 0.000764 acc_pose: 0.788896 loss: 0.000764 2022/09/17 15:16:05 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:16:13 - mmengine - INFO - Epoch(train) [69][100/293] lr: 5.000000e-04 eta: 3:30:17 time: 0.337699 data_time: 0.070682 memory: 5151 loss_kpt: 0.000741 acc_pose: 0.831274 loss: 0.000741 2022/09/17 15:16:30 - mmengine - INFO - Epoch(train) [69][150/293] lr: 5.000000e-04 eta: 3:30:05 time: 0.338805 data_time: 0.068019 memory: 5151 loss_kpt: 0.000734 acc_pose: 0.768332 loss: 0.000734 2022/09/17 15:16:47 - mmengine - INFO - Epoch(train) [69][200/293] lr: 5.000000e-04 eta: 3:29:54 time: 0.340030 data_time: 0.072280 memory: 5151 loss_kpt: 0.000757 acc_pose: 0.822078 loss: 0.000757 2022/09/17 15:17:05 - mmengine - INFO - Epoch(train) [69][250/293] lr: 5.000000e-04 eta: 3:29:45 time: 0.363204 data_time: 0.075127 memory: 5151 loss_kpt: 0.000749 acc_pose: 0.785693 loss: 0.000749 2022/09/17 15:17:20 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:17:20 - mmengine - INFO - Saving checkpoint at 69 epochs 2022/09/17 15:17:40 - mmengine - INFO - Epoch(train) [70][50/293] lr: 5.000000e-04 eta: 3:28:55 time: 0.351154 data_time: 0.072470 memory: 5151 loss_kpt: 0.000734 acc_pose: 0.780552 loss: 0.000734 2022/09/17 15:17:57 - mmengine - INFO - Epoch(train) [70][100/293] lr: 5.000000e-04 eta: 3:28:43 time: 0.336837 data_time: 0.066689 memory: 5151 loss_kpt: 0.000747 acc_pose: 0.802174 loss: 0.000747 2022/09/17 15:18:13 - mmengine - INFO - Epoch(train) [70][150/293] lr: 5.000000e-04 eta: 3:28:30 time: 0.326634 data_time: 0.065033 memory: 5151 loss_kpt: 0.000737 acc_pose: 0.832246 loss: 0.000737 2022/09/17 15:18:30 - mmengine - INFO - Epoch(train) [70][200/293] lr: 5.000000e-04 eta: 3:28:18 time: 0.336328 data_time: 0.067442 memory: 5151 loss_kpt: 0.000736 acc_pose: 0.786111 loss: 0.000736 2022/09/17 15:18:47 - mmengine - INFO - Epoch(train) [70][250/293] lr: 5.000000e-04 eta: 3:28:06 time: 0.337668 data_time: 0.066766 memory: 5151 loss_kpt: 0.000749 acc_pose: 0.783111 loss: 0.000749 2022/09/17 15:19:00 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:19:00 - mmengine - INFO - Saving checkpoint at 70 epochs 2022/09/17 15:19:09 - mmengine - INFO - Epoch(val) [70][50/407] eta: 0:00:44 time: 0.123802 data_time: 0.053647 memory: 5151 2022/09/17 15:19:15 - mmengine - INFO - Epoch(val) [70][100/407] eta: 0:00:34 time: 0.113108 data_time: 0.045636 memory: 331 2022/09/17 15:19:21 - mmengine - INFO - Epoch(val) [70][150/407] eta: 0:00:30 time: 0.120322 data_time: 0.051181 memory: 331 2022/09/17 15:19:27 - mmengine - INFO - Epoch(val) [70][200/407] eta: 0:00:25 time: 0.122551 data_time: 0.054423 memory: 331 2022/09/17 15:19:33 - mmengine - INFO - Epoch(val) [70][250/407] eta: 0:00:18 time: 0.120631 data_time: 0.053502 memory: 331 2022/09/17 15:19:39 - mmengine - INFO - Epoch(val) [70][300/407] eta: 0:00:12 time: 0.117548 data_time: 0.049272 memory: 331 2022/09/17 15:19:45 - mmengine - INFO - Epoch(val) [70][350/407] eta: 0:00:06 time: 0.116982 data_time: 0.048145 memory: 331 2022/09/17 15:19:51 - mmengine - INFO - Epoch(val) [70][400/407] eta: 0:00:00 time: 0.119131 data_time: 0.053767 memory: 331 2022/09/17 15:20:27 - mmengine - INFO - Evaluating CocoMetric... 2022/09/17 15:20:41 - mmengine - INFO - Epoch(val) [70][407/407] coco/AP: 0.671354 coco/AP .5: 0.877831 coco/AP .75: 0.752477 coco/AP (M): 0.642313 coco/AP (L): 0.731094 coco/AR: 0.733076 coco/AR .5: 0.920812 coco/AR .75: 0.806203 coco/AR (M): 0.694482 coco/AR (L): 0.788369 2022/09/17 15:20:41 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220917/vipnas_res50/best_coco/AP_epoch_60.pth is removed 2022/09/17 15:20:44 - mmengine - INFO - The best checkpoint with 0.6714 coco/AP at 70 epoch is saved to best_coco/AP_epoch_70.pth. 2022/09/17 15:21:00 - mmengine - INFO - Epoch(train) [71][50/293] lr: 5.000000e-04 eta: 3:27:15 time: 0.339089 data_time: 0.067377 memory: 5151 loss_kpt: 0.000757 acc_pose: 0.742444 loss: 0.000757 2022/09/17 15:21:17 - mmengine - INFO - Epoch(train) [71][100/293] lr: 5.000000e-04 eta: 3:27:03 time: 0.330591 data_time: 0.062433 memory: 5151 loss_kpt: 0.000738 acc_pose: 0.801256 loss: 0.000738 2022/09/17 15:21:33 - mmengine - INFO - Epoch(train) [71][150/293] lr: 5.000000e-04 eta: 3:26:50 time: 0.328988 data_time: 0.061901 memory: 5151 loss_kpt: 0.000761 acc_pose: 0.825926 loss: 0.000761 2022/09/17 15:21:50 - mmengine - INFO - Epoch(train) [71][200/293] lr: 5.000000e-04 eta: 3:26:38 time: 0.331248 data_time: 0.064639 memory: 5151 loss_kpt: 0.000745 acc_pose: 0.790093 loss: 0.000745 2022/09/17 15:22:06 - mmengine - INFO - Epoch(train) [71][250/293] lr: 5.000000e-04 eta: 3:26:25 time: 0.328784 data_time: 0.062844 memory: 5151 loss_kpt: 0.000731 acc_pose: 0.778287 loss: 0.000731 2022/09/17 15:22:21 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:22:21 - mmengine - INFO - Saving checkpoint at 71 epochs 2022/09/17 15:22:41 - mmengine - INFO - Epoch(train) [72][50/293] lr: 5.000000e-04 eta: 3:25:35 time: 0.343234 data_time: 0.073403 memory: 5151 loss_kpt: 0.000747 acc_pose: 0.822274 loss: 0.000747 2022/09/17 15:22:58 - mmengine - INFO - Epoch(train) [72][100/293] lr: 5.000000e-04 eta: 3:25:23 time: 0.332858 data_time: 0.073374 memory: 5151 loss_kpt: 0.000750 acc_pose: 0.772747 loss: 0.000750 2022/09/17 15:23:14 - mmengine - INFO - Epoch(train) [72][150/293] lr: 5.000000e-04 eta: 3:25:10 time: 0.330653 data_time: 0.067106 memory: 5151 loss_kpt: 0.000742 acc_pose: 0.810616 loss: 0.000742 2022/09/17 15:23:30 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:23:31 - mmengine - INFO - Epoch(train) [72][200/293] lr: 5.000000e-04 eta: 3:24:59 time: 0.342215 data_time: 0.070043 memory: 5151 loss_kpt: 0.000746 acc_pose: 0.824569 loss: 0.000746 2022/09/17 15:23:48 - mmengine - INFO - Epoch(train) [72][250/293] lr: 5.000000e-04 eta: 3:24:47 time: 0.338504 data_time: 0.067326 memory: 5151 loss_kpt: 0.000743 acc_pose: 0.816287 loss: 0.000743 2022/09/17 15:24:02 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:24:02 - mmengine - INFO - Saving checkpoint at 72 epochs 2022/09/17 15:24:22 - mmengine - INFO - Epoch(train) [73][50/293] lr: 5.000000e-04 eta: 3:23:58 time: 0.350104 data_time: 0.075272 memory: 5151 loss_kpt: 0.000742 acc_pose: 0.766609 loss: 0.000742 2022/09/17 15:24:39 - mmengine - INFO - Epoch(train) [73][100/293] lr: 5.000000e-04 eta: 3:23:46 time: 0.335726 data_time: 0.066206 memory: 5151 loss_kpt: 0.000745 acc_pose: 0.827854 loss: 0.000745 2022/09/17 15:24:56 - mmengine - INFO - Epoch(train) [73][150/293] lr: 5.000000e-04 eta: 3:23:35 time: 0.348254 data_time: 0.073596 memory: 5151 loss_kpt: 0.000747 acc_pose: 0.822095 loss: 0.000747 2022/09/17 15:25:13 - mmengine - INFO - Epoch(train) [73][200/293] lr: 5.000000e-04 eta: 3:23:24 time: 0.343399 data_time: 0.082614 memory: 5151 loss_kpt: 0.000742 acc_pose: 0.838807 loss: 0.000742 2022/09/17 15:25:31 - mmengine - INFO - Epoch(train) [73][250/293] lr: 5.000000e-04 eta: 3:23:14 time: 0.354491 data_time: 0.075605 memory: 5151 loss_kpt: 0.000734 acc_pose: 0.845895 loss: 0.000734 2022/09/17 15:25:45 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:25:45 - mmengine - INFO - Saving checkpoint at 73 epochs 2022/09/17 15:26:06 - mmengine - INFO - Epoch(train) [74][50/293] lr: 5.000000e-04 eta: 3:22:25 time: 0.345967 data_time: 0.082603 memory: 5151 loss_kpt: 0.000729 acc_pose: 0.805897 loss: 0.000729 2022/09/17 15:26:23 - mmengine - INFO - Epoch(train) [74][100/293] lr: 5.000000e-04 eta: 3:22:13 time: 0.341182 data_time: 0.078699 memory: 5151 loss_kpt: 0.000748 acc_pose: 0.802949 loss: 0.000748 2022/09/17 15:26:41 - mmengine - INFO - Epoch(train) [74][150/293] lr: 5.000000e-04 eta: 3:22:03 time: 0.357359 data_time: 0.072944 memory: 5151 loss_kpt: 0.000744 acc_pose: 0.810108 loss: 0.000744 2022/09/17 15:26:58 - mmengine - INFO - Epoch(train) [74][200/293] lr: 5.000000e-04 eta: 3:21:52 time: 0.344621 data_time: 0.068796 memory: 5151 loss_kpt: 0.000728 acc_pose: 0.798539 loss: 0.000728 2022/09/17 15:27:15 - mmengine - INFO - Epoch(train) [74][250/293] lr: 5.000000e-04 eta: 3:21:39 time: 0.330515 data_time: 0.063602 memory: 5151 loss_kpt: 0.000737 acc_pose: 0.818185 loss: 0.000737 2022/09/17 15:27:29 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:27:29 - mmengine - INFO - Saving checkpoint at 74 epochs 2022/09/17 15:27:49 - mmengine - INFO - Epoch(train) [75][50/293] lr: 5.000000e-04 eta: 3:20:51 time: 0.347597 data_time: 0.073214 memory: 5151 loss_kpt: 0.000726 acc_pose: 0.837145 loss: 0.000726 2022/09/17 15:28:06 - mmengine - INFO - Epoch(train) [75][100/293] lr: 5.000000e-04 eta: 3:20:39 time: 0.338027 data_time: 0.063753 memory: 5151 loss_kpt: 0.000741 acc_pose: 0.797727 loss: 0.000741 2022/09/17 15:28:23 - mmengine - INFO - Epoch(train) [75][150/293] lr: 5.000000e-04 eta: 3:20:27 time: 0.337573 data_time: 0.062716 memory: 5151 loss_kpt: 0.000742 acc_pose: 0.830164 loss: 0.000742 2022/09/17 15:28:40 - mmengine - INFO - Epoch(train) [75][200/293] lr: 5.000000e-04 eta: 3:20:15 time: 0.339312 data_time: 0.067926 memory: 5151 loss_kpt: 0.000742 acc_pose: 0.856261 loss: 0.000742 2022/09/17 15:28:56 - mmengine - INFO - Epoch(train) [75][250/293] lr: 5.000000e-04 eta: 3:20:02 time: 0.326919 data_time: 0.058649 memory: 5151 loss_kpt: 0.000721 acc_pose: 0.790546 loss: 0.000721 2022/09/17 15:29:11 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:29:11 - mmengine - INFO - Saving checkpoint at 75 epochs 2022/09/17 15:29:22 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:29:30 - mmengine - INFO - Epoch(train) [76][50/293] lr: 5.000000e-04 eta: 3:19:14 time: 0.342307 data_time: 0.068097 memory: 5151 loss_kpt: 0.000733 acc_pose: 0.817053 loss: 0.000733 2022/09/17 15:29:46 - mmengine - INFO - Epoch(train) [76][100/293] lr: 5.000000e-04 eta: 3:19:01 time: 0.323678 data_time: 0.059901 memory: 5151 loss_kpt: 0.000731 acc_pose: 0.789166 loss: 0.000731 2022/09/17 15:30:03 - mmengine - INFO - Epoch(train) [76][150/293] lr: 5.000000e-04 eta: 3:18:48 time: 0.329465 data_time: 0.060037 memory: 5151 loss_kpt: 0.000739 acc_pose: 0.800628 loss: 0.000739 2022/09/17 15:30:19 - mmengine - INFO - Epoch(train) [76][200/293] lr: 5.000000e-04 eta: 3:18:36 time: 0.334564 data_time: 0.059446 memory: 5151 loss_kpt: 0.000727 acc_pose: 0.771180 loss: 0.000727 2022/09/17 15:30:36 - mmengine - INFO - Epoch(train) [76][250/293] lr: 5.000000e-04 eta: 3:18:24 time: 0.331963 data_time: 0.064963 memory: 5151 loss_kpt: 0.000730 acc_pose: 0.790968 loss: 0.000730 2022/09/17 15:30:50 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:30:50 - mmengine - INFO - Saving checkpoint at 76 epochs 2022/09/17 15:31:10 - mmengine - INFO - Epoch(train) [77][50/293] lr: 5.000000e-04 eta: 3:17:35 time: 0.336608 data_time: 0.072749 memory: 5151 loss_kpt: 0.000728 acc_pose: 0.820951 loss: 0.000728 2022/09/17 15:31:26 - mmengine - INFO - Epoch(train) [77][100/293] lr: 5.000000e-04 eta: 3:17:23 time: 0.330591 data_time: 0.065180 memory: 5151 loss_kpt: 0.000730 acc_pose: 0.839192 loss: 0.000730 2022/09/17 15:31:43 - mmengine - INFO - Epoch(train) [77][150/293] lr: 5.000000e-04 eta: 3:17:11 time: 0.340267 data_time: 0.064555 memory: 5151 loss_kpt: 0.000736 acc_pose: 0.755668 loss: 0.000736 2022/09/17 15:32:00 - mmengine - INFO - Epoch(train) [77][200/293] lr: 5.000000e-04 eta: 3:16:58 time: 0.331627 data_time: 0.063159 memory: 5151 loss_kpt: 0.000721 acc_pose: 0.779122 loss: 0.000721 2022/09/17 15:32:16 - mmengine - INFO - Epoch(train) [77][250/293] lr: 5.000000e-04 eta: 3:16:45 time: 0.327455 data_time: 0.062447 memory: 5151 loss_kpt: 0.000738 acc_pose: 0.798956 loss: 0.000738 2022/09/17 15:32:30 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:32:30 - mmengine - INFO - Saving checkpoint at 77 epochs 2022/09/17 15:32:50 - mmengine - INFO - Epoch(train) [78][50/293] lr: 5.000000e-04 eta: 3:15:59 time: 0.348414 data_time: 0.071441 memory: 5151 loss_kpt: 0.000724 acc_pose: 0.814918 loss: 0.000724 2022/09/17 15:33:06 - mmengine - INFO - Epoch(train) [78][100/293] lr: 5.000000e-04 eta: 3:15:46 time: 0.328474 data_time: 0.063827 memory: 5151 loss_kpt: 0.000731 acc_pose: 0.796491 loss: 0.000731 2022/09/17 15:33:23 - mmengine - INFO - Epoch(train) [78][150/293] lr: 5.000000e-04 eta: 3:15:34 time: 0.336531 data_time: 0.066447 memory: 5151 loss_kpt: 0.000733 acc_pose: 0.830952 loss: 0.000733 2022/09/17 15:33:40 - mmengine - INFO - Epoch(train) [78][200/293] lr: 5.000000e-04 eta: 3:15:22 time: 0.340170 data_time: 0.069063 memory: 5151 loss_kpt: 0.000727 acc_pose: 0.832918 loss: 0.000727 2022/09/17 15:33:57 - mmengine - INFO - Epoch(train) [78][250/293] lr: 5.000000e-04 eta: 3:15:09 time: 0.327113 data_time: 0.066547 memory: 5151 loss_kpt: 0.000737 acc_pose: 0.829695 loss: 0.000737 2022/09/17 15:34:11 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:34:11 - mmengine - INFO - Saving checkpoint at 78 epochs 2022/09/17 15:34:30 - mmengine - INFO - Epoch(train) [79][50/293] lr: 5.000000e-04 eta: 3:14:22 time: 0.337139 data_time: 0.073400 memory: 5151 loss_kpt: 0.000732 acc_pose: 0.833474 loss: 0.000732 2022/09/17 15:34:47 - mmengine - INFO - Epoch(train) [79][100/293] lr: 5.000000e-04 eta: 3:14:09 time: 0.330878 data_time: 0.065648 memory: 5151 loss_kpt: 0.000728 acc_pose: 0.793526 loss: 0.000728 2022/09/17 15:35:03 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:35:04 - mmengine - INFO - Epoch(train) [79][150/293] lr: 5.000000e-04 eta: 3:13:57 time: 0.341767 data_time: 0.068469 memory: 5151 loss_kpt: 0.000736 acc_pose: 0.827378 loss: 0.000736 2022/09/17 15:35:21 - mmengine - INFO - Epoch(train) [79][200/293] lr: 5.000000e-04 eta: 3:13:45 time: 0.339690 data_time: 0.064355 memory: 5151 loss_kpt: 0.000740 acc_pose: 0.792915 loss: 0.000740 2022/09/17 15:35:38 - mmengine - INFO - Epoch(train) [79][250/293] lr: 5.000000e-04 eta: 3:13:34 time: 0.350594 data_time: 0.066536 memory: 5151 loss_kpt: 0.000741 acc_pose: 0.816657 loss: 0.000741 2022/09/17 15:35:53 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:35:53 - mmengine - INFO - Saving checkpoint at 79 epochs 2022/09/17 15:36:13 - mmengine - INFO - Epoch(train) [80][50/293] lr: 5.000000e-04 eta: 3:12:48 time: 0.343972 data_time: 0.072983 memory: 5151 loss_kpt: 0.000726 acc_pose: 0.819734 loss: 0.000726 2022/09/17 15:36:30 - mmengine - INFO - Epoch(train) [80][100/293] lr: 5.000000e-04 eta: 3:12:36 time: 0.337300 data_time: 0.069181 memory: 5151 loss_kpt: 0.000735 acc_pose: 0.759545 loss: 0.000735 2022/09/17 15:36:47 - mmengine - INFO - Epoch(train) [80][150/293] lr: 5.000000e-04 eta: 3:12:24 time: 0.336325 data_time: 0.064886 memory: 5151 loss_kpt: 0.000725 acc_pose: 0.842159 loss: 0.000725 2022/09/17 15:37:04 - mmengine - INFO - Epoch(train) [80][200/293] lr: 5.000000e-04 eta: 3:12:12 time: 0.342638 data_time: 0.076733 memory: 5151 loss_kpt: 0.000731 acc_pose: 0.803115 loss: 0.000731 2022/09/17 15:37:21 - mmengine - INFO - Epoch(train) [80][250/293] lr: 5.000000e-04 eta: 3:12:00 time: 0.340833 data_time: 0.069392 memory: 5151 loss_kpt: 0.000733 acc_pose: 0.788387 loss: 0.000733 2022/09/17 15:37:35 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:37:35 - mmengine - INFO - Saving checkpoint at 80 epochs 2022/09/17 15:37:43 - mmengine - INFO - Epoch(val) [80][50/407] eta: 0:00:43 time: 0.122454 data_time: 0.054451 memory: 5151 2022/09/17 15:37:49 - mmengine - INFO - Epoch(val) [80][100/407] eta: 0:00:36 time: 0.119465 data_time: 0.051331 memory: 331 2022/09/17 15:37:55 - mmengine - INFO - Epoch(val) [80][150/407] eta: 0:00:29 time: 0.116315 data_time: 0.048510 memory: 331 2022/09/17 15:38:01 - mmengine - INFO - Epoch(val) [80][200/407] eta: 0:00:23 time: 0.115264 data_time: 0.047277 memory: 331 2022/09/17 15:38:07 - mmengine - INFO - Epoch(val) [80][250/407] eta: 0:00:18 time: 0.116485 data_time: 0.049307 memory: 331 2022/09/17 15:38:13 - mmengine - INFO - Epoch(val) [80][300/407] eta: 0:00:12 time: 0.120073 data_time: 0.053540 memory: 331 2022/09/17 15:38:19 - mmengine - INFO - Epoch(val) [80][350/407] eta: 0:00:06 time: 0.119571 data_time: 0.052857 memory: 331 2022/09/17 15:38:24 - mmengine - INFO - Epoch(val) [80][400/407] eta: 0:00:00 time: 0.112607 data_time: 0.043646 memory: 331 2022/09/17 15:39:00 - mmengine - INFO - Evaluating CocoMetric... 2022/09/17 15:39:14 - mmengine - INFO - Epoch(val) [80][407/407] coco/AP: 0.675066 coco/AP .5: 0.874553 coco/AP .75: 0.756961 coco/AP (M): 0.646522 coco/AP (L): 0.735852 coco/AR: 0.736508 coco/AR .5: 0.919238 coco/AR .75: 0.810139 coco/AR (M): 0.697487 coco/AR (L): 0.792939 2022/09/17 15:39:15 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220917/vipnas_res50/best_coco/AP_epoch_70.pth is removed 2022/09/17 15:39:17 - mmengine - INFO - The best checkpoint with 0.6751 coco/AP at 80 epoch is saved to best_coco/AP_epoch_80.pth. 2022/09/17 15:39:34 - mmengine - INFO - Epoch(train) [81][50/293] lr: 5.000000e-04 eta: 3:11:15 time: 0.348175 data_time: 0.074289 memory: 5151 loss_kpt: 0.000716 acc_pose: 0.854273 loss: 0.000716 2022/09/17 15:39:51 - mmengine - INFO - Epoch(train) [81][100/293] lr: 5.000000e-04 eta: 3:11:02 time: 0.333323 data_time: 0.069958 memory: 5151 loss_kpt: 0.000746 acc_pose: 0.800995 loss: 0.000746 2022/09/17 15:40:08 - mmengine - INFO - Epoch(train) [81][150/293] lr: 5.000000e-04 eta: 3:10:51 time: 0.349800 data_time: 0.069799 memory: 5151 loss_kpt: 0.000729 acc_pose: 0.760487 loss: 0.000729 2022/09/17 15:40:25 - mmengine - INFO - Epoch(train) [81][200/293] lr: 5.000000e-04 eta: 3:10:38 time: 0.333607 data_time: 0.072720 memory: 5151 loss_kpt: 0.000740 acc_pose: 0.820003 loss: 0.000740 2022/09/17 15:40:43 - mmengine - INFO - Epoch(train) [81][250/293] lr: 5.000000e-04 eta: 3:10:27 time: 0.351667 data_time: 0.070742 memory: 5151 loss_kpt: 0.000730 acc_pose: 0.734954 loss: 0.000730 2022/09/17 15:40:57 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:40:57 - mmengine - INFO - Saving checkpoint at 81 epochs 2022/09/17 15:41:17 - mmengine - INFO - Epoch(train) [82][50/293] lr: 5.000000e-04 eta: 3:09:43 time: 0.355941 data_time: 0.077126 memory: 5151 loss_kpt: 0.000730 acc_pose: 0.798788 loss: 0.000730 2022/09/17 15:41:34 - mmengine - INFO - Epoch(train) [82][100/293] lr: 5.000000e-04 eta: 3:09:31 time: 0.337827 data_time: 0.071384 memory: 5151 loss_kpt: 0.000730 acc_pose: 0.782039 loss: 0.000730 2022/09/17 15:41:51 - mmengine - INFO - Epoch(train) [82][150/293] lr: 5.000000e-04 eta: 3:09:18 time: 0.329730 data_time: 0.067429 memory: 5151 loss_kpt: 0.000733 acc_pose: 0.800023 loss: 0.000733 2022/09/17 15:42:07 - mmengine - INFO - Epoch(train) [82][200/293] lr: 5.000000e-04 eta: 3:09:05 time: 0.333962 data_time: 0.065084 memory: 5151 loss_kpt: 0.000730 acc_pose: 0.820379 loss: 0.000730 2022/09/17 15:42:25 - mmengine - INFO - Epoch(train) [82][250/293] lr: 5.000000e-04 eta: 3:08:54 time: 0.346846 data_time: 0.076157 memory: 5151 loss_kpt: 0.000722 acc_pose: 0.814269 loss: 0.000722 2022/09/17 15:42:30 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:42:39 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:42:39 - mmengine - INFO - Saving checkpoint at 82 epochs 2022/09/17 15:42:58 - mmengine - INFO - Epoch(train) [83][50/293] lr: 5.000000e-04 eta: 3:08:08 time: 0.338755 data_time: 0.070977 memory: 5151 loss_kpt: 0.000731 acc_pose: 0.793967 loss: 0.000731 2022/09/17 15:43:15 - mmengine - INFO - Epoch(train) [83][100/293] lr: 5.000000e-04 eta: 3:07:56 time: 0.334501 data_time: 0.065618 memory: 5151 loss_kpt: 0.000730 acc_pose: 0.823715 loss: 0.000730 2022/09/17 15:43:32 - mmengine - INFO - Epoch(train) [83][150/293] lr: 5.000000e-04 eta: 3:07:43 time: 0.332109 data_time: 0.064368 memory: 5151 loss_kpt: 0.000721 acc_pose: 0.820856 loss: 0.000721 2022/09/17 15:43:48 - mmengine - INFO - Epoch(train) [83][200/293] lr: 5.000000e-04 eta: 3:07:30 time: 0.327497 data_time: 0.069867 memory: 5151 loss_kpt: 0.000749 acc_pose: 0.851865 loss: 0.000749 2022/09/17 15:44:05 - mmengine - INFO - Epoch(train) [83][250/293] lr: 5.000000e-04 eta: 3:07:18 time: 0.341541 data_time: 0.071256 memory: 5151 loss_kpt: 0.000716 acc_pose: 0.800396 loss: 0.000716 2022/09/17 15:44:20 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:44:20 - mmengine - INFO - Saving checkpoint at 83 epochs 2022/09/17 15:44:40 - mmengine - INFO - Epoch(train) [84][50/293] lr: 5.000000e-04 eta: 3:06:33 time: 0.343964 data_time: 0.073142 memory: 5151 loss_kpt: 0.000725 acc_pose: 0.840377 loss: 0.000725 2022/09/17 15:44:57 - mmengine - INFO - Epoch(train) [84][100/293] lr: 5.000000e-04 eta: 3:06:22 time: 0.353587 data_time: 0.072295 memory: 5151 loss_kpt: 0.000714 acc_pose: 0.803474 loss: 0.000714 2022/09/17 15:45:14 - mmengine - INFO - Epoch(train) [84][150/293] lr: 5.000000e-04 eta: 3:06:09 time: 0.328506 data_time: 0.067130 memory: 5151 loss_kpt: 0.000719 acc_pose: 0.817781 loss: 0.000719 2022/09/17 15:45:31 - mmengine - INFO - Epoch(train) [84][200/293] lr: 5.000000e-04 eta: 3:05:58 time: 0.346694 data_time: 0.079383 memory: 5151 loss_kpt: 0.000730 acc_pose: 0.806105 loss: 0.000730 2022/09/17 15:45:48 - mmengine - INFO - Epoch(train) [84][250/293] lr: 5.000000e-04 eta: 3:05:46 time: 0.344870 data_time: 0.077573 memory: 5151 loss_kpt: 0.000724 acc_pose: 0.799265 loss: 0.000724 2022/09/17 15:46:03 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:46:03 - mmengine - INFO - Saving checkpoint at 84 epochs 2022/09/17 15:46:22 - mmengine - INFO - Epoch(train) [85][50/293] lr: 5.000000e-04 eta: 3:05:02 time: 0.344869 data_time: 0.072472 memory: 5151 loss_kpt: 0.000715 acc_pose: 0.837740 loss: 0.000715 2022/09/17 15:46:39 - mmengine - INFO - Epoch(train) [85][100/293] lr: 5.000000e-04 eta: 3:04:49 time: 0.329981 data_time: 0.061632 memory: 5151 loss_kpt: 0.000713 acc_pose: 0.791843 loss: 0.000713 2022/09/17 15:46:56 - mmengine - INFO - Epoch(train) [85][150/293] lr: 5.000000e-04 eta: 3:04:37 time: 0.349665 data_time: 0.076737 memory: 5151 loss_kpt: 0.000737 acc_pose: 0.792136 loss: 0.000737 2022/09/17 15:47:14 - mmengine - INFO - Epoch(train) [85][200/293] lr: 5.000000e-04 eta: 3:04:25 time: 0.343235 data_time: 0.064905 memory: 5151 loss_kpt: 0.000720 acc_pose: 0.800384 loss: 0.000720 2022/09/17 15:47:30 - mmengine - INFO - Epoch(train) [85][250/293] lr: 5.000000e-04 eta: 3:04:13 time: 0.334129 data_time: 0.073069 memory: 5151 loss_kpt: 0.000717 acc_pose: 0.824395 loss: 0.000717 2022/09/17 15:47:45 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:47:45 - mmengine - INFO - Saving checkpoint at 85 epochs 2022/09/17 15:48:05 - mmengine - INFO - Epoch(train) [86][50/293] lr: 5.000000e-04 eta: 3:03:29 time: 0.355128 data_time: 0.073762 memory: 5151 loss_kpt: 0.000704 acc_pose: 0.825066 loss: 0.000704 2022/09/17 15:48:20 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:48:22 - mmengine - INFO - Epoch(train) [86][100/293] lr: 5.000000e-04 eta: 3:03:18 time: 0.347835 data_time: 0.073708 memory: 5151 loss_kpt: 0.000723 acc_pose: 0.811885 loss: 0.000723 2022/09/17 15:48:39 - mmengine - INFO - Epoch(train) [86][150/293] lr: 5.000000e-04 eta: 3:03:06 time: 0.340815 data_time: 0.083022 memory: 5151 loss_kpt: 0.000716 acc_pose: 0.808283 loss: 0.000716 2022/09/17 15:48:56 - mmengine - INFO - Epoch(train) [86][200/293] lr: 5.000000e-04 eta: 3:02:54 time: 0.345260 data_time: 0.072048 memory: 5151 loss_kpt: 0.000711 acc_pose: 0.797330 loss: 0.000711 2022/09/17 15:49:13 - mmengine - INFO - Epoch(train) [86][250/293] lr: 5.000000e-04 eta: 3:02:41 time: 0.329124 data_time: 0.065447 memory: 5151 loss_kpt: 0.000730 acc_pose: 0.818689 loss: 0.000730 2022/09/17 15:49:27 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:49:27 - mmengine - INFO - Saving checkpoint at 86 epochs 2022/09/17 15:49:47 - mmengine - INFO - Epoch(train) [87][50/293] lr: 5.000000e-04 eta: 3:01:57 time: 0.339922 data_time: 0.070653 memory: 5151 loss_kpt: 0.000705 acc_pose: 0.824435 loss: 0.000705 2022/09/17 15:50:04 - mmengine - INFO - Epoch(train) [87][100/293] lr: 5.000000e-04 eta: 3:01:44 time: 0.334367 data_time: 0.067938 memory: 5151 loss_kpt: 0.000720 acc_pose: 0.789140 loss: 0.000720 2022/09/17 15:50:20 - mmengine - INFO - Epoch(train) [87][150/293] lr: 5.000000e-04 eta: 3:01:31 time: 0.333767 data_time: 0.070079 memory: 5151 loss_kpt: 0.000729 acc_pose: 0.857710 loss: 0.000729 2022/09/17 15:50:37 - mmengine - INFO - Epoch(train) [87][200/293] lr: 5.000000e-04 eta: 3:01:19 time: 0.336593 data_time: 0.071002 memory: 5151 loss_kpt: 0.000725 acc_pose: 0.797063 loss: 0.000725 2022/09/17 15:50:54 - mmengine - INFO - Epoch(train) [87][250/293] lr: 5.000000e-04 eta: 3:01:07 time: 0.341797 data_time: 0.078077 memory: 5151 loss_kpt: 0.000733 acc_pose: 0.829287 loss: 0.000733 2022/09/17 15:51:09 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:51:09 - mmengine - INFO - Saving checkpoint at 87 epochs 2022/09/17 15:51:30 - mmengine - INFO - Epoch(train) [88][50/293] lr: 5.000000e-04 eta: 3:00:24 time: 0.355906 data_time: 0.080104 memory: 5151 loss_kpt: 0.000709 acc_pose: 0.826642 loss: 0.000709 2022/09/17 15:51:47 - mmengine - INFO - Epoch(train) [88][100/293] lr: 5.000000e-04 eta: 3:00:13 time: 0.351772 data_time: 0.073102 memory: 5151 loss_kpt: 0.000728 acc_pose: 0.809807 loss: 0.000728 2022/09/17 15:52:05 - mmengine - INFO - Epoch(train) [88][150/293] lr: 5.000000e-04 eta: 3:00:01 time: 0.348996 data_time: 0.070524 memory: 5151 loss_kpt: 0.000720 acc_pose: 0.722825 loss: 0.000720 2022/09/17 15:52:21 - mmengine - INFO - Epoch(train) [88][200/293] lr: 5.000000e-04 eta: 2:59:48 time: 0.332951 data_time: 0.068002 memory: 5151 loss_kpt: 0.000718 acc_pose: 0.813750 loss: 0.000718 2022/09/17 15:52:38 - mmengine - INFO - Epoch(train) [88][250/293] lr: 5.000000e-04 eta: 2:59:36 time: 0.339277 data_time: 0.072243 memory: 5151 loss_kpt: 0.000737 acc_pose: 0.815988 loss: 0.000737 2022/09/17 15:52:52 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:52:52 - mmengine - INFO - Saving checkpoint at 88 epochs 2022/09/17 15:53:12 - mmengine - INFO - Epoch(train) [89][50/293] lr: 5.000000e-04 eta: 2:58:54 time: 0.350723 data_time: 0.078622 memory: 5151 loss_kpt: 0.000723 acc_pose: 0.822143 loss: 0.000723 2022/09/17 15:53:30 - mmengine - INFO - Epoch(train) [89][100/293] lr: 5.000000e-04 eta: 2:58:42 time: 0.346840 data_time: 0.077793 memory: 5151 loss_kpt: 0.000729 acc_pose: 0.792237 loss: 0.000729 2022/09/17 15:53:47 - mmengine - INFO - Epoch(train) [89][150/293] lr: 5.000000e-04 eta: 2:58:30 time: 0.342613 data_time: 0.072304 memory: 5151 loss_kpt: 0.000731 acc_pose: 0.805852 loss: 0.000731 2022/09/17 15:54:04 - mmengine - INFO - Epoch(train) [89][200/293] lr: 5.000000e-04 eta: 2:58:17 time: 0.335250 data_time: 0.071909 memory: 5151 loss_kpt: 0.000721 acc_pose: 0.835461 loss: 0.000721 2022/09/17 15:54:09 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:54:20 - mmengine - INFO - Epoch(train) [89][250/293] lr: 5.000000e-04 eta: 2:58:04 time: 0.331245 data_time: 0.066602 memory: 5151 loss_kpt: 0.000715 acc_pose: 0.795149 loss: 0.000715 2022/09/17 15:54:35 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:54:35 - mmengine - INFO - Saving checkpoint at 89 epochs 2022/09/17 15:54:55 - mmengine - INFO - Epoch(train) [90][50/293] lr: 5.000000e-04 eta: 2:57:21 time: 0.347236 data_time: 0.078814 memory: 5151 loss_kpt: 0.000715 acc_pose: 0.829285 loss: 0.000715 2022/09/17 15:55:12 - mmengine - INFO - Epoch(train) [90][100/293] lr: 5.000000e-04 eta: 2:57:10 time: 0.351602 data_time: 0.077788 memory: 5151 loss_kpt: 0.000712 acc_pose: 0.849828 loss: 0.000712 2022/09/17 15:55:29 - mmengine - INFO - Epoch(train) [90][150/293] lr: 5.000000e-04 eta: 2:56:57 time: 0.332141 data_time: 0.062728 memory: 5151 loss_kpt: 0.000718 acc_pose: 0.836955 loss: 0.000718 2022/09/17 15:55:46 - mmengine - INFO - Epoch(train) [90][200/293] lr: 5.000000e-04 eta: 2:56:45 time: 0.339785 data_time: 0.069399 memory: 5151 loss_kpt: 0.000734 acc_pose: 0.797095 loss: 0.000734 2022/09/17 15:56:03 - mmengine - INFO - Epoch(train) [90][250/293] lr: 5.000000e-04 eta: 2:56:32 time: 0.337978 data_time: 0.069756 memory: 5151 loss_kpt: 0.000720 acc_pose: 0.816371 loss: 0.000720 2022/09/17 15:56:17 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:56:17 - mmengine - INFO - Saving checkpoint at 90 epochs 2022/09/17 15:56:25 - mmengine - INFO - Epoch(val) [90][50/407] eta: 0:00:43 time: 0.120628 data_time: 0.051228 memory: 5151 2022/09/17 15:56:31 - mmengine - INFO - Epoch(val) [90][100/407] eta: 0:00:36 time: 0.120157 data_time: 0.050901 memory: 331 2022/09/17 15:56:37 - mmengine - INFO - Epoch(val) [90][150/407] eta: 0:00:29 time: 0.114492 data_time: 0.047044 memory: 331 2022/09/17 15:56:43 - mmengine - INFO - Epoch(val) [90][200/407] eta: 0:00:24 time: 0.117582 data_time: 0.049395 memory: 331 2022/09/17 15:56:49 - mmengine - INFO - Epoch(val) [90][250/407] eta: 0:00:18 time: 0.116834 data_time: 0.049952 memory: 331 2022/09/17 15:56:55 - mmengine - INFO - Epoch(val) [90][300/407] eta: 0:00:12 time: 0.120785 data_time: 0.051561 memory: 331 2022/09/17 15:57:01 - mmengine - INFO - Epoch(val) [90][350/407] eta: 0:00:06 time: 0.120673 data_time: 0.053325 memory: 331 2022/09/17 15:57:06 - mmengine - INFO - Epoch(val) [90][400/407] eta: 0:00:00 time: 0.106521 data_time: 0.040303 memory: 331 2022/09/17 15:57:42 - mmengine - INFO - Evaluating CocoMetric... 2022/09/17 15:57:56 - mmengine - INFO - Epoch(val) [90][407/407] coco/AP: 0.675551 coco/AP .5: 0.879548 coco/AP .75: 0.754026 coco/AP (M): 0.648305 coco/AP (L): 0.733956 coco/AR: 0.735941 coco/AR .5: 0.923331 coco/AR .75: 0.805888 coco/AR (M): 0.697951 coco/AR (L): 0.790561 2022/09/17 15:57:56 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220917/vipnas_res50/best_coco/AP_epoch_80.pth is removed 2022/09/17 15:57:58 - mmengine - INFO - The best checkpoint with 0.6756 coco/AP at 90 epoch is saved to best_coco/AP_epoch_90.pth. 2022/09/17 15:58:16 - mmengine - INFO - Epoch(train) [91][50/293] lr: 5.000000e-04 eta: 2:55:50 time: 0.346309 data_time: 0.069205 memory: 5151 loss_kpt: 0.000720 acc_pose: 0.860918 loss: 0.000720 2022/09/17 15:58:33 - mmengine - INFO - Epoch(train) [91][100/293] lr: 5.000000e-04 eta: 2:55:37 time: 0.338601 data_time: 0.069093 memory: 5151 loss_kpt: 0.000703 acc_pose: 0.825556 loss: 0.000703 2022/09/17 15:58:49 - mmengine - INFO - Epoch(train) [91][150/293] lr: 5.000000e-04 eta: 2:55:24 time: 0.329079 data_time: 0.062448 memory: 5151 loss_kpt: 0.000722 acc_pose: 0.822256 loss: 0.000722 2022/09/17 15:59:07 - mmengine - INFO - Epoch(train) [91][200/293] lr: 5.000000e-04 eta: 2:55:12 time: 0.346561 data_time: 0.073265 memory: 5151 loss_kpt: 0.000719 acc_pose: 0.796595 loss: 0.000719 2022/09/17 15:59:24 - mmengine - INFO - Epoch(train) [91][250/293] lr: 5.000000e-04 eta: 2:55:00 time: 0.341730 data_time: 0.080199 memory: 5151 loss_kpt: 0.000721 acc_pose: 0.812269 loss: 0.000721 2022/09/17 15:59:38 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 15:59:38 - mmengine - INFO - Saving checkpoint at 91 epochs 2022/09/17 15:59:58 - mmengine - INFO - Epoch(train) [92][50/293] lr: 5.000000e-04 eta: 2:54:19 time: 0.356332 data_time: 0.076741 memory: 5151 loss_kpt: 0.000716 acc_pose: 0.839296 loss: 0.000716 2022/09/17 16:00:15 - mmengine - INFO - Epoch(train) [92][100/293] lr: 5.000000e-04 eta: 2:54:06 time: 0.343404 data_time: 0.077851 memory: 5151 loss_kpt: 0.000718 acc_pose: 0.765644 loss: 0.000718 2022/09/17 16:00:32 - mmengine - INFO - Epoch(train) [92][150/293] lr: 5.000000e-04 eta: 2:53:53 time: 0.331072 data_time: 0.065248 memory: 5151 loss_kpt: 0.000737 acc_pose: 0.792842 loss: 0.000737 2022/09/17 16:00:48 - mmengine - INFO - Epoch(train) [92][200/293] lr: 5.000000e-04 eta: 2:53:40 time: 0.322484 data_time: 0.063854 memory: 5151 loss_kpt: 0.000733 acc_pose: 0.764776 loss: 0.000733 2022/09/17 16:01:06 - mmengine - INFO - Epoch(train) [92][250/293] lr: 5.000000e-04 eta: 2:53:28 time: 0.347522 data_time: 0.070930 memory: 5151 loss_kpt: 0.000713 acc_pose: 0.778394 loss: 0.000713 2022/09/17 16:01:20 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:01:20 - mmengine - INFO - Saving checkpoint at 92 epochs 2022/09/17 16:01:38 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:01:40 - mmengine - INFO - Epoch(train) [93][50/293] lr: 5.000000e-04 eta: 2:52:46 time: 0.345751 data_time: 0.071632 memory: 5151 loss_kpt: 0.000713 acc_pose: 0.800445 loss: 0.000713 2022/09/17 16:01:57 - mmengine - INFO - Epoch(train) [93][100/293] lr: 5.000000e-04 eta: 2:52:33 time: 0.336315 data_time: 0.063349 memory: 5151 loss_kpt: 0.000715 acc_pose: 0.761236 loss: 0.000715 2022/09/17 16:02:14 - mmengine - INFO - Epoch(train) [93][150/293] lr: 5.000000e-04 eta: 2:52:20 time: 0.333460 data_time: 0.062226 memory: 5151 loss_kpt: 0.000713 acc_pose: 0.829980 loss: 0.000713 2022/09/17 16:02:31 - mmengine - INFO - Epoch(train) [93][200/293] lr: 5.000000e-04 eta: 2:52:08 time: 0.346277 data_time: 0.067854 memory: 5151 loss_kpt: 0.000717 acc_pose: 0.853232 loss: 0.000717 2022/09/17 16:02:48 - mmengine - INFO - Epoch(train) [93][250/293] lr: 5.000000e-04 eta: 2:51:56 time: 0.335028 data_time: 0.069258 memory: 5151 loss_kpt: 0.000722 acc_pose: 0.819045 loss: 0.000722 2022/09/17 16:03:02 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:03:02 - mmengine - INFO - Saving checkpoint at 93 epochs 2022/09/17 16:03:22 - mmengine - INFO - Epoch(train) [94][50/293] lr: 5.000000e-04 eta: 2:51:14 time: 0.349731 data_time: 0.081457 memory: 5151 loss_kpt: 0.000724 acc_pose: 0.789117 loss: 0.000724 2022/09/17 16:03:39 - mmengine - INFO - Epoch(train) [94][100/293] lr: 5.000000e-04 eta: 2:51:02 time: 0.336246 data_time: 0.069531 memory: 5151 loss_kpt: 0.000714 acc_pose: 0.803461 loss: 0.000714 2022/09/17 16:03:57 - mmengine - INFO - Epoch(train) [94][150/293] lr: 5.000000e-04 eta: 2:50:51 time: 0.372535 data_time: 0.082110 memory: 5151 loss_kpt: 0.000715 acc_pose: 0.833096 loss: 0.000715 2022/09/17 16:04:14 - mmengine - INFO - Epoch(train) [94][200/293] lr: 5.000000e-04 eta: 2:50:38 time: 0.333705 data_time: 0.065071 memory: 5151 loss_kpt: 0.000710 acc_pose: 0.796314 loss: 0.000710 2022/09/17 16:04:31 - mmengine - INFO - Epoch(train) [94][250/293] lr: 5.000000e-04 eta: 2:50:26 time: 0.340382 data_time: 0.065481 memory: 5151 loss_kpt: 0.000715 acc_pose: 0.767988 loss: 0.000715 2022/09/17 16:04:45 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:04:45 - mmengine - INFO - Saving checkpoint at 94 epochs 2022/09/17 16:05:05 - mmengine - INFO - Epoch(train) [95][50/293] lr: 5.000000e-04 eta: 2:49:46 time: 0.360868 data_time: 0.080271 memory: 5151 loss_kpt: 0.000710 acc_pose: 0.794745 loss: 0.000710 2022/09/17 16:05:22 - mmengine - INFO - Epoch(train) [95][100/293] lr: 5.000000e-04 eta: 2:49:33 time: 0.341112 data_time: 0.072180 memory: 5151 loss_kpt: 0.000709 acc_pose: 0.808123 loss: 0.000709 2022/09/17 16:05:39 - mmengine - INFO - Epoch(train) [95][150/293] lr: 5.000000e-04 eta: 2:49:20 time: 0.338838 data_time: 0.068718 memory: 5151 loss_kpt: 0.000718 acc_pose: 0.799691 loss: 0.000718 2022/09/17 16:05:56 - mmengine - INFO - Epoch(train) [95][200/293] lr: 5.000000e-04 eta: 2:49:08 time: 0.338253 data_time: 0.070271 memory: 5151 loss_kpt: 0.000722 acc_pose: 0.791737 loss: 0.000722 2022/09/17 16:06:13 - mmengine - INFO - Epoch(train) [95][250/293] lr: 5.000000e-04 eta: 2:48:55 time: 0.337538 data_time: 0.069811 memory: 5151 loss_kpt: 0.000711 acc_pose: 0.798173 loss: 0.000711 2022/09/17 16:06:27 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:06:27 - mmengine - INFO - Saving checkpoint at 95 epochs 2022/09/17 16:06:48 - mmengine - INFO - Epoch(train) [96][50/293] lr: 5.000000e-04 eta: 2:48:16 time: 0.368858 data_time: 0.086496 memory: 5151 loss_kpt: 0.000695 acc_pose: 0.808334 loss: 0.000695 2022/09/17 16:07:05 - mmengine - INFO - Epoch(train) [96][100/293] lr: 5.000000e-04 eta: 2:48:02 time: 0.331010 data_time: 0.066883 memory: 5151 loss_kpt: 0.000706 acc_pose: 0.826223 loss: 0.000706 2022/09/17 16:07:22 - mmengine - INFO - Epoch(train) [96][150/293] lr: 5.000000e-04 eta: 2:47:50 time: 0.350191 data_time: 0.068721 memory: 5151 loss_kpt: 0.000721 acc_pose: 0.812612 loss: 0.000721 2022/09/17 16:07:27 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:07:39 - mmengine - INFO - Epoch(train) [96][200/293] lr: 5.000000e-04 eta: 2:47:37 time: 0.331090 data_time: 0.065040 memory: 5151 loss_kpt: 0.000719 acc_pose: 0.780918 loss: 0.000719 2022/09/17 16:07:56 - mmengine - INFO - Epoch(train) [96][250/293] lr: 5.000000e-04 eta: 2:47:24 time: 0.335607 data_time: 0.065682 memory: 5151 loss_kpt: 0.000723 acc_pose: 0.855998 loss: 0.000723 2022/09/17 16:08:10 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:08:10 - mmengine - INFO - Saving checkpoint at 96 epochs 2022/09/17 16:08:30 - mmengine - INFO - Epoch(train) [97][50/293] lr: 5.000000e-04 eta: 2:46:44 time: 0.350247 data_time: 0.076257 memory: 5151 loss_kpt: 0.000719 acc_pose: 0.773572 loss: 0.000719 2022/09/17 16:08:47 - mmengine - INFO - Epoch(train) [97][100/293] lr: 5.000000e-04 eta: 2:46:31 time: 0.337060 data_time: 0.066531 memory: 5151 loss_kpt: 0.000702 acc_pose: 0.795666 loss: 0.000702 2022/09/17 16:09:04 - mmengine - INFO - Epoch(train) [97][150/293] lr: 5.000000e-04 eta: 2:46:19 time: 0.343586 data_time: 0.066758 memory: 5151 loss_kpt: 0.000732 acc_pose: 0.818044 loss: 0.000732 2022/09/17 16:09:21 - mmengine - INFO - Epoch(train) [97][200/293] lr: 5.000000e-04 eta: 2:46:06 time: 0.344383 data_time: 0.074476 memory: 5151 loss_kpt: 0.000708 acc_pose: 0.820655 loss: 0.000708 2022/09/17 16:09:39 - mmengine - INFO - Epoch(train) [97][250/293] lr: 5.000000e-04 eta: 2:45:54 time: 0.344813 data_time: 0.074835 memory: 5151 loss_kpt: 0.000712 acc_pose: 0.821084 loss: 0.000712 2022/09/17 16:09:54 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:09:54 - mmengine - INFO - Saving checkpoint at 97 epochs 2022/09/17 16:10:13 - mmengine - INFO - Epoch(train) [98][50/293] lr: 5.000000e-04 eta: 2:45:14 time: 0.346266 data_time: 0.078056 memory: 5151 loss_kpt: 0.000711 acc_pose: 0.753845 loss: 0.000711 2022/09/17 16:10:30 - mmengine - INFO - Epoch(train) [98][100/293] lr: 5.000000e-04 eta: 2:45:01 time: 0.330133 data_time: 0.074014 memory: 5151 loss_kpt: 0.000709 acc_pose: 0.804490 loss: 0.000709 2022/09/17 16:10:47 - mmengine - INFO - Epoch(train) [98][150/293] lr: 5.000000e-04 eta: 2:44:48 time: 0.337984 data_time: 0.062985 memory: 5151 loss_kpt: 0.000708 acc_pose: 0.814003 loss: 0.000708 2022/09/17 16:11:03 - mmengine - INFO - Epoch(train) [98][200/293] lr: 5.000000e-04 eta: 2:44:35 time: 0.334853 data_time: 0.066408 memory: 5151 loss_kpt: 0.000708 acc_pose: 0.784192 loss: 0.000708 2022/09/17 16:11:20 - mmengine - INFO - Epoch(train) [98][250/293] lr: 5.000000e-04 eta: 2:44:22 time: 0.333651 data_time: 0.067926 memory: 5151 loss_kpt: 0.000709 acc_pose: 0.799269 loss: 0.000709 2022/09/17 16:11:34 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:11:34 - mmengine - INFO - Saving checkpoint at 98 epochs 2022/09/17 16:11:54 - mmengine - INFO - Epoch(train) [99][50/293] lr: 5.000000e-04 eta: 2:43:41 time: 0.342018 data_time: 0.076183 memory: 5151 loss_kpt: 0.000708 acc_pose: 0.864618 loss: 0.000708 2022/09/17 16:12:11 - mmengine - INFO - Epoch(train) [99][100/293] lr: 5.000000e-04 eta: 2:43:29 time: 0.338069 data_time: 0.071051 memory: 5151 loss_kpt: 0.000705 acc_pose: 0.819258 loss: 0.000705 2022/09/17 16:12:29 - mmengine - INFO - Epoch(train) [99][150/293] lr: 5.000000e-04 eta: 2:43:17 time: 0.351251 data_time: 0.075061 memory: 5151 loss_kpt: 0.000717 acc_pose: 0.798376 loss: 0.000717 2022/09/17 16:12:46 - mmengine - INFO - Epoch(train) [99][200/293] lr: 5.000000e-04 eta: 2:43:04 time: 0.350581 data_time: 0.070761 memory: 5151 loss_kpt: 0.000725 acc_pose: 0.823552 loss: 0.000725 2022/09/17 16:13:03 - mmengine - INFO - Epoch(train) [99][250/293] lr: 5.000000e-04 eta: 2:42:51 time: 0.337155 data_time: 0.070962 memory: 5151 loss_kpt: 0.000717 acc_pose: 0.781175 loss: 0.000717 2022/09/17 16:13:15 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:13:17 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:13:17 - mmengine - INFO - Saving checkpoint at 99 epochs 2022/09/17 16:13:37 - mmengine - INFO - Epoch(train) [100][50/293] lr: 5.000000e-04 eta: 2:42:12 time: 0.354417 data_time: 0.079692 memory: 5151 loss_kpt: 0.000698 acc_pose: 0.768075 loss: 0.000698 2022/09/17 16:13:55 - mmengine - INFO - Epoch(train) [100][100/293] lr: 5.000000e-04 eta: 2:42:00 time: 0.350209 data_time: 0.087257 memory: 5151 loss_kpt: 0.000710 acc_pose: 0.784372 loss: 0.000710 2022/09/17 16:14:12 - mmengine - INFO - Epoch(train) [100][150/293] lr: 5.000000e-04 eta: 2:41:48 time: 0.350405 data_time: 0.072623 memory: 5151 loss_kpt: 0.000715 acc_pose: 0.865385 loss: 0.000715 2022/09/17 16:14:29 - mmengine - INFO - Epoch(train) [100][200/293] lr: 5.000000e-04 eta: 2:41:35 time: 0.336135 data_time: 0.073845 memory: 5151 loss_kpt: 0.000712 acc_pose: 0.788676 loss: 0.000712 2022/09/17 16:14:46 - mmengine - INFO - Epoch(train) [100][250/293] lr: 5.000000e-04 eta: 2:41:22 time: 0.339280 data_time: 0.076194 memory: 5151 loss_kpt: 0.000706 acc_pose: 0.827001 loss: 0.000706 2022/09/17 16:15:00 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:15:01 - mmengine - INFO - Saving checkpoint at 100 epochs 2022/09/17 16:15:10 - mmengine - INFO - Epoch(val) [100][50/407] eta: 0:00:43 time: 0.122254 data_time: 0.054557 memory: 5151 2022/09/17 16:15:16 - mmengine - INFO - Epoch(val) [100][100/407] eta: 0:00:37 time: 0.122890 data_time: 0.055716 memory: 331 2022/09/17 16:15:22 - mmengine - INFO - Epoch(val) [100][150/407] eta: 0:00:30 time: 0.117499 data_time: 0.048160 memory: 331 2022/09/17 16:15:27 - mmengine - INFO - Epoch(val) [100][200/407] eta: 0:00:23 time: 0.113399 data_time: 0.044825 memory: 331 2022/09/17 16:15:33 - mmengine - INFO - Epoch(val) [100][250/407] eta: 0:00:18 time: 0.117493 data_time: 0.047901 memory: 331 2022/09/17 16:15:39 - mmengine - INFO - Epoch(val) [100][300/407] eta: 0:00:12 time: 0.115314 data_time: 0.046933 memory: 331 2022/09/17 16:15:45 - mmengine - INFO - Epoch(val) [100][350/407] eta: 0:00:06 time: 0.119465 data_time: 0.051892 memory: 331 2022/09/17 16:15:50 - mmengine - INFO - Epoch(val) [100][400/407] eta: 0:00:00 time: 0.107285 data_time: 0.042581 memory: 331 2022/09/17 16:16:26 - mmengine - INFO - Evaluating CocoMetric... 2022/09/17 16:16:40 - mmengine - INFO - Epoch(val) [100][407/407] coco/AP: 0.676452 coco/AP .5: 0.874560 coco/AP .75: 0.756211 coco/AP (M): 0.646231 coco/AP (L): 0.737793 coco/AR: 0.736713 coco/AR .5: 0.918766 coco/AR .75: 0.808879 coco/AR (M): 0.697105 coco/AR (L): 0.793906 2022/09/17 16:16:40 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220917/vipnas_res50/best_coco/AP_epoch_90.pth is removed 2022/09/17 16:16:42 - mmengine - INFO - The best checkpoint with 0.6765 coco/AP at 100 epoch is saved to best_coco/AP_epoch_100.pth. 2022/09/17 16:17:00 - mmengine - INFO - Epoch(train) [101][50/293] lr: 5.000000e-04 eta: 2:40:43 time: 0.350677 data_time: 0.079339 memory: 5151 loss_kpt: 0.000734 acc_pose: 0.791858 loss: 0.000734 2022/09/17 16:17:17 - mmengine - INFO - Epoch(train) [101][100/293] lr: 5.000000e-04 eta: 2:40:30 time: 0.347024 data_time: 0.068447 memory: 5151 loss_kpt: 0.000698 acc_pose: 0.873780 loss: 0.000698 2022/09/17 16:17:34 - mmengine - INFO - Epoch(train) [101][150/293] lr: 5.000000e-04 eta: 2:40:18 time: 0.347232 data_time: 0.071029 memory: 5151 loss_kpt: 0.000724 acc_pose: 0.784630 loss: 0.000724 2022/09/17 16:17:52 - mmengine - INFO - Epoch(train) [101][200/293] lr: 5.000000e-04 eta: 2:40:06 time: 0.357951 data_time: 0.078503 memory: 5151 loss_kpt: 0.000733 acc_pose: 0.808150 loss: 0.000733 2022/09/17 16:18:10 - mmengine - INFO - Epoch(train) [101][250/293] lr: 5.000000e-04 eta: 2:39:53 time: 0.342777 data_time: 0.072644 memory: 5151 loss_kpt: 0.000717 acc_pose: 0.839408 loss: 0.000717 2022/09/17 16:18:24 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:18:24 - mmengine - INFO - Saving checkpoint at 101 epochs 2022/09/17 16:18:44 - mmengine - INFO - Epoch(train) [102][50/293] lr: 5.000000e-04 eta: 2:39:14 time: 0.341698 data_time: 0.067775 memory: 5151 loss_kpt: 0.000708 acc_pose: 0.819639 loss: 0.000708 2022/09/17 16:19:01 - mmengine - INFO - Epoch(train) [102][100/293] lr: 5.000000e-04 eta: 2:39:01 time: 0.336658 data_time: 0.065591 memory: 5151 loss_kpt: 0.000716 acc_pose: 0.789416 loss: 0.000716 2022/09/17 16:19:17 - mmengine - INFO - Epoch(train) [102][150/293] lr: 5.000000e-04 eta: 2:38:47 time: 0.328181 data_time: 0.065401 memory: 5151 loss_kpt: 0.000689 acc_pose: 0.850753 loss: 0.000689 2022/09/17 16:19:34 - mmengine - INFO - Epoch(train) [102][200/293] lr: 5.000000e-04 eta: 2:38:34 time: 0.335805 data_time: 0.063426 memory: 5151 loss_kpt: 0.000724 acc_pose: 0.828126 loss: 0.000724 2022/09/17 16:19:51 - mmengine - INFO - Epoch(train) [102][250/293] lr: 5.000000e-04 eta: 2:38:21 time: 0.338306 data_time: 0.065652 memory: 5151 loss_kpt: 0.000711 acc_pose: 0.814289 loss: 0.000711 2022/09/17 16:20:05 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:20:05 - mmengine - INFO - Saving checkpoint at 102 epochs 2022/09/17 16:20:26 - mmengine - INFO - Epoch(train) [103][50/293] lr: 5.000000e-04 eta: 2:37:43 time: 0.352142 data_time: 0.081614 memory: 5151 loss_kpt: 0.000711 acc_pose: 0.821918 loss: 0.000711 2022/09/17 16:20:43 - mmengine - INFO - Epoch(train) [103][100/293] lr: 5.000000e-04 eta: 2:37:30 time: 0.351501 data_time: 0.067441 memory: 5151 loss_kpt: 0.000701 acc_pose: 0.851082 loss: 0.000701 2022/09/17 16:20:48 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:21:00 - mmengine - INFO - Epoch(train) [103][150/293] lr: 5.000000e-04 eta: 2:37:18 time: 0.339619 data_time: 0.068863 memory: 5151 loss_kpt: 0.000710 acc_pose: 0.772705 loss: 0.000710 2022/09/17 16:21:18 - mmengine - INFO - Epoch(train) [103][200/293] lr: 5.000000e-04 eta: 2:37:05 time: 0.346339 data_time: 0.073686 memory: 5151 loss_kpt: 0.000714 acc_pose: 0.800433 loss: 0.000714 2022/09/17 16:21:34 - mmengine - INFO - Epoch(train) [103][250/293] lr: 5.000000e-04 eta: 2:36:52 time: 0.328338 data_time: 0.065723 memory: 5151 loss_kpt: 0.000711 acc_pose: 0.823267 loss: 0.000711 2022/09/17 16:21:49 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:21:49 - mmengine - INFO - Saving checkpoint at 103 epochs 2022/09/17 16:22:08 - mmengine - INFO - Epoch(train) [104][50/293] lr: 5.000000e-04 eta: 2:36:13 time: 0.344238 data_time: 0.077957 memory: 5151 loss_kpt: 0.000713 acc_pose: 0.813299 loss: 0.000713 2022/09/17 16:22:26 - mmengine - INFO - Epoch(train) [104][100/293] lr: 5.000000e-04 eta: 2:36:00 time: 0.351627 data_time: 0.080548 memory: 5151 loss_kpt: 0.000698 acc_pose: 0.824529 loss: 0.000698 2022/09/17 16:22:43 - mmengine - INFO - Epoch(train) [104][150/293] lr: 5.000000e-04 eta: 2:35:47 time: 0.338220 data_time: 0.064765 memory: 5151 loss_kpt: 0.000710 acc_pose: 0.803716 loss: 0.000710 2022/09/17 16:22:59 - mmengine - INFO - Epoch(train) [104][200/293] lr: 5.000000e-04 eta: 2:35:34 time: 0.333086 data_time: 0.070118 memory: 5151 loss_kpt: 0.000699 acc_pose: 0.788641 loss: 0.000699 2022/09/17 16:23:16 - mmengine - INFO - Epoch(train) [104][250/293] lr: 5.000000e-04 eta: 2:35:21 time: 0.341704 data_time: 0.072921 memory: 5151 loss_kpt: 0.000718 acc_pose: 0.759418 loss: 0.000718 2022/09/17 16:23:30 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:23:30 - mmengine - INFO - Saving checkpoint at 104 epochs 2022/09/17 16:23:50 - mmengine - INFO - Epoch(train) [105][50/293] lr: 5.000000e-04 eta: 2:34:42 time: 0.340719 data_time: 0.071644 memory: 5151 loss_kpt: 0.000704 acc_pose: 0.823697 loss: 0.000704 2022/09/17 16:24:06 - mmengine - INFO - Epoch(train) [105][100/293] lr: 5.000000e-04 eta: 2:34:29 time: 0.329436 data_time: 0.059766 memory: 5151 loss_kpt: 0.000707 acc_pose: 0.860830 loss: 0.000707 2022/09/17 16:24:24 - mmengine - INFO - Epoch(train) [105][150/293] lr: 5.000000e-04 eta: 2:34:17 time: 0.351071 data_time: 0.078345 memory: 5151 loss_kpt: 0.000702 acc_pose: 0.803527 loss: 0.000702 2022/09/17 16:24:41 - mmengine - INFO - Epoch(train) [105][200/293] lr: 5.000000e-04 eta: 2:34:04 time: 0.341963 data_time: 0.073544 memory: 5151 loss_kpt: 0.000701 acc_pose: 0.852761 loss: 0.000701 2022/09/17 16:24:58 - mmengine - INFO - Epoch(train) [105][250/293] lr: 5.000000e-04 eta: 2:33:51 time: 0.340596 data_time: 0.067734 memory: 5151 loss_kpt: 0.000711 acc_pose: 0.802542 loss: 0.000711 2022/09/17 16:25:13 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:25:13 - mmengine - INFO - Saving checkpoint at 105 epochs 2022/09/17 16:25:32 - mmengine - INFO - Epoch(train) [106][50/293] lr: 5.000000e-04 eta: 2:33:12 time: 0.340864 data_time: 0.073384 memory: 5151 loss_kpt: 0.000691 acc_pose: 0.821618 loss: 0.000691 2022/09/17 16:25:49 - mmengine - INFO - Epoch(train) [106][100/293] lr: 5.000000e-04 eta: 2:32:59 time: 0.335217 data_time: 0.068460 memory: 5151 loss_kpt: 0.000703 acc_pose: 0.836441 loss: 0.000703 2022/09/17 16:26:06 - mmengine - INFO - Epoch(train) [106][150/293] lr: 5.000000e-04 eta: 2:32:46 time: 0.341854 data_time: 0.075090 memory: 5151 loss_kpt: 0.000710 acc_pose: 0.804327 loss: 0.000710 2022/09/17 16:26:23 - mmengine - INFO - Epoch(train) [106][200/293] lr: 5.000000e-04 eta: 2:32:34 time: 0.348609 data_time: 0.076531 memory: 5151 loss_kpt: 0.000708 acc_pose: 0.809146 loss: 0.000708 2022/09/17 16:26:36 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:26:41 - mmengine - INFO - Epoch(train) [106][250/293] lr: 5.000000e-04 eta: 2:32:21 time: 0.351970 data_time: 0.070828 memory: 5151 loss_kpt: 0.000716 acc_pose: 0.860893 loss: 0.000716 2022/09/17 16:26:56 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:26:56 - mmengine - INFO - Saving checkpoint at 106 epochs 2022/09/17 16:27:16 - mmengine - INFO - Epoch(train) [107][50/293] lr: 5.000000e-04 eta: 2:31:43 time: 0.352429 data_time: 0.082985 memory: 5151 loss_kpt: 0.000698 acc_pose: 0.828699 loss: 0.000698 2022/09/17 16:27:33 - mmengine - INFO - Epoch(train) [107][100/293] lr: 5.000000e-04 eta: 2:31:31 time: 0.347020 data_time: 0.079502 memory: 5151 loss_kpt: 0.000700 acc_pose: 0.886473 loss: 0.000700 2022/09/17 16:27:50 - mmengine - INFO - Epoch(train) [107][150/293] lr: 5.000000e-04 eta: 2:31:17 time: 0.331967 data_time: 0.067039 memory: 5151 loss_kpt: 0.000698 acc_pose: 0.822582 loss: 0.000698 2022/09/17 16:28:07 - mmengine - INFO - Epoch(train) [107][200/293] lr: 5.000000e-04 eta: 2:31:04 time: 0.342699 data_time: 0.076293 memory: 5151 loss_kpt: 0.000706 acc_pose: 0.783669 loss: 0.000706 2022/09/17 16:28:23 - mmengine - INFO - Epoch(train) [107][250/293] lr: 5.000000e-04 eta: 2:30:51 time: 0.335406 data_time: 0.071482 memory: 5151 loss_kpt: 0.000705 acc_pose: 0.838752 loss: 0.000705 2022/09/17 16:28:38 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:28:38 - mmengine - INFO - Saving checkpoint at 107 epochs 2022/09/17 16:28:58 - mmengine - INFO - Epoch(train) [108][50/293] lr: 5.000000e-04 eta: 2:30:14 time: 0.354990 data_time: 0.084271 memory: 5151 loss_kpt: 0.000700 acc_pose: 0.823016 loss: 0.000700 2022/09/17 16:29:16 - mmengine - INFO - Epoch(train) [108][100/293] lr: 5.000000e-04 eta: 2:30:01 time: 0.348094 data_time: 0.071134 memory: 5151 loss_kpt: 0.000700 acc_pose: 0.836249 loss: 0.000700 2022/09/17 16:29:32 - mmengine - INFO - Epoch(train) [108][150/293] lr: 5.000000e-04 eta: 2:29:47 time: 0.322868 data_time: 0.062941 memory: 5151 loss_kpt: 0.000696 acc_pose: 0.828887 loss: 0.000696 2022/09/17 16:29:48 - mmengine - INFO - Epoch(train) [108][200/293] lr: 5.000000e-04 eta: 2:29:34 time: 0.330728 data_time: 0.071533 memory: 5151 loss_kpt: 0.000710 acc_pose: 0.790464 loss: 0.000710 2022/09/17 16:30:06 - mmengine - INFO - Epoch(train) [108][250/293] lr: 5.000000e-04 eta: 2:29:21 time: 0.341619 data_time: 0.070192 memory: 5151 loss_kpt: 0.000714 acc_pose: 0.793781 loss: 0.000714 2022/09/17 16:30:20 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:30:20 - mmengine - INFO - Saving checkpoint at 108 epochs 2022/09/17 16:30:41 - mmengine - INFO - Epoch(train) [109][50/293] lr: 5.000000e-04 eta: 2:28:43 time: 0.349647 data_time: 0.081916 memory: 5151 loss_kpt: 0.000699 acc_pose: 0.835846 loss: 0.000699 2022/09/17 16:30:58 - mmengine - INFO - Epoch(train) [109][100/293] lr: 5.000000e-04 eta: 2:28:31 time: 0.355060 data_time: 0.073427 memory: 5151 loss_kpt: 0.000714 acc_pose: 0.803638 loss: 0.000714 2022/09/17 16:31:16 - mmengine - INFO - Epoch(train) [109][150/293] lr: 5.000000e-04 eta: 2:28:18 time: 0.351623 data_time: 0.083175 memory: 5151 loss_kpt: 0.000713 acc_pose: 0.835793 loss: 0.000713 2022/09/17 16:31:33 - mmengine - INFO - Epoch(train) [109][200/293] lr: 5.000000e-04 eta: 2:28:05 time: 0.337056 data_time: 0.064803 memory: 5151 loss_kpt: 0.000713 acc_pose: 0.817776 loss: 0.000713 2022/09/17 16:31:50 - mmengine - INFO - Epoch(train) [109][250/293] lr: 5.000000e-04 eta: 2:27:52 time: 0.336938 data_time: 0.069406 memory: 5151 loss_kpt: 0.000715 acc_pose: 0.820840 loss: 0.000715 2022/09/17 16:32:04 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:32:04 - mmengine - INFO - Saving checkpoint at 109 epochs 2022/09/17 16:32:24 - mmengine - INFO - Epoch(train) [110][50/293] lr: 5.000000e-04 eta: 2:27:14 time: 0.351157 data_time: 0.080563 memory: 5151 loss_kpt: 0.000696 acc_pose: 0.825962 loss: 0.000696 2022/09/17 16:32:29 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:32:41 - mmengine - INFO - Epoch(train) [110][100/293] lr: 5.000000e-04 eta: 2:27:01 time: 0.339015 data_time: 0.069522 memory: 5151 loss_kpt: 0.000696 acc_pose: 0.811546 loss: 0.000696 2022/09/17 16:32:59 - mmengine - INFO - Epoch(train) [110][150/293] lr: 5.000000e-04 eta: 2:26:49 time: 0.350868 data_time: 0.077425 memory: 5151 loss_kpt: 0.000706 acc_pose: 0.820772 loss: 0.000706 2022/09/17 16:33:16 - mmengine - INFO - Epoch(train) [110][200/293] lr: 5.000000e-04 eta: 2:26:36 time: 0.350063 data_time: 0.068762 memory: 5151 loss_kpt: 0.000700 acc_pose: 0.837805 loss: 0.000700 2022/09/17 16:33:34 - mmengine - INFO - Epoch(train) [110][250/293] lr: 5.000000e-04 eta: 2:26:23 time: 0.345015 data_time: 0.068798 memory: 5151 loss_kpt: 0.000708 acc_pose: 0.783016 loss: 0.000708 2022/09/17 16:33:47 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:33:48 - mmengine - INFO - Saving checkpoint at 110 epochs 2022/09/17 16:33:56 - mmengine - INFO - Epoch(val) [110][50/407] eta: 0:00:45 time: 0.127242 data_time: 0.055960 memory: 5151 2022/09/17 16:34:02 - mmengine - INFO - Epoch(val) [110][100/407] eta: 0:00:36 time: 0.117895 data_time: 0.050450 memory: 331 2022/09/17 16:34:08 - mmengine - INFO - Epoch(val) [110][150/407] eta: 0:00:29 time: 0.115496 data_time: 0.047166 memory: 331 2022/09/17 16:34:14 - mmengine - INFO - Epoch(val) [110][200/407] eta: 0:00:23 time: 0.115853 data_time: 0.048311 memory: 331 2022/09/17 16:34:20 - mmengine - INFO - Epoch(val) [110][250/407] eta: 0:00:18 time: 0.119643 data_time: 0.051935 memory: 331 2022/09/17 16:34:26 - mmengine - INFO - Epoch(val) [110][300/407] eta: 0:00:12 time: 0.118522 data_time: 0.051427 memory: 331 2022/09/17 16:34:32 - mmengine - INFO - Epoch(val) [110][350/407] eta: 0:00:06 time: 0.121903 data_time: 0.050927 memory: 331 2022/09/17 16:34:38 - mmengine - INFO - Epoch(val) [110][400/407] eta: 0:00:00 time: 0.114239 data_time: 0.049021 memory: 331 2022/09/17 16:35:14 - mmengine - INFO - Evaluating CocoMetric... 2022/09/17 16:35:27 - mmengine - INFO - Epoch(val) [110][407/407] coco/AP: 0.685092 coco/AP .5: 0.881432 coco/AP .75: 0.763621 coco/AP (M): 0.653592 coco/AP (L): 0.748926 coco/AR: 0.744978 coco/AR .5: 0.924433 coco/AR .75: 0.816908 coco/AR (M): 0.704043 coco/AR (L): 0.804013 2022/09/17 16:35:28 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220917/vipnas_res50/best_coco/AP_epoch_100.pth is removed 2022/09/17 16:35:30 - mmengine - INFO - The best checkpoint with 0.6851 coco/AP at 110 epoch is saved to best_coco/AP_epoch_110.pth. 2022/09/17 16:35:47 - mmengine - INFO - Epoch(train) [111][50/293] lr: 5.000000e-04 eta: 2:25:46 time: 0.351874 data_time: 0.073941 memory: 5151 loss_kpt: 0.000707 acc_pose: 0.806866 loss: 0.000707 2022/09/17 16:36:05 - mmengine - INFO - Epoch(train) [111][100/293] lr: 5.000000e-04 eta: 2:25:33 time: 0.349430 data_time: 0.071367 memory: 5151 loss_kpt: 0.000708 acc_pose: 0.839836 loss: 0.000708 2022/09/17 16:36:22 - mmengine - INFO - Epoch(train) [111][150/293] lr: 5.000000e-04 eta: 2:25:20 time: 0.336769 data_time: 0.064767 memory: 5151 loss_kpt: 0.000697 acc_pose: 0.804662 loss: 0.000697 2022/09/17 16:36:39 - mmengine - INFO - Epoch(train) [111][200/293] lr: 5.000000e-04 eta: 2:25:07 time: 0.343367 data_time: 0.068905 memory: 5151 loss_kpt: 0.000703 acc_pose: 0.823198 loss: 0.000703 2022/09/17 16:36:56 - mmengine - INFO - Epoch(train) [111][250/293] lr: 5.000000e-04 eta: 2:24:54 time: 0.336330 data_time: 0.064040 memory: 5151 loss_kpt: 0.000714 acc_pose: 0.829061 loss: 0.000714 2022/09/17 16:37:10 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:37:10 - mmengine - INFO - Saving checkpoint at 111 epochs 2022/09/17 16:37:31 - mmengine - INFO - Epoch(train) [112][50/293] lr: 5.000000e-04 eta: 2:24:17 time: 0.361608 data_time: 0.084979 memory: 5151 loss_kpt: 0.000693 acc_pose: 0.858383 loss: 0.000693 2022/09/17 16:37:48 - mmengine - INFO - Epoch(train) [112][100/293] lr: 5.000000e-04 eta: 2:24:05 time: 0.347434 data_time: 0.069460 memory: 5151 loss_kpt: 0.000722 acc_pose: 0.840072 loss: 0.000722 2022/09/17 16:38:06 - mmengine - INFO - Epoch(train) [112][150/293] lr: 5.000000e-04 eta: 2:23:52 time: 0.343650 data_time: 0.068518 memory: 5151 loss_kpt: 0.000701 acc_pose: 0.849815 loss: 0.000701 2022/09/17 16:38:22 - mmengine - INFO - Epoch(train) [112][200/293] lr: 5.000000e-04 eta: 2:23:38 time: 0.336798 data_time: 0.071732 memory: 5151 loss_kpt: 0.000696 acc_pose: 0.747649 loss: 0.000696 2022/09/17 16:38:39 - mmengine - INFO - Epoch(train) [112][250/293] lr: 5.000000e-04 eta: 2:23:25 time: 0.333227 data_time: 0.068453 memory: 5151 loss_kpt: 0.000705 acc_pose: 0.791843 loss: 0.000705 2022/09/17 16:38:53 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:38:53 - mmengine - INFO - Saving checkpoint at 112 epochs 2022/09/17 16:39:13 - mmengine - INFO - Epoch(train) [113][50/293] lr: 5.000000e-04 eta: 2:22:48 time: 0.347006 data_time: 0.068870 memory: 5151 loss_kpt: 0.000691 acc_pose: 0.813579 loss: 0.000691 2022/09/17 16:39:30 - mmengine - INFO - Epoch(train) [113][100/293] lr: 5.000000e-04 eta: 2:22:35 time: 0.343171 data_time: 0.067854 memory: 5151 loss_kpt: 0.000705 acc_pose: 0.844308 loss: 0.000705 2022/09/17 16:39:47 - mmengine - INFO - Epoch(train) [113][150/293] lr: 5.000000e-04 eta: 2:22:21 time: 0.327488 data_time: 0.063645 memory: 5151 loss_kpt: 0.000701 acc_pose: 0.796751 loss: 0.000701 2022/09/17 16:39:58 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:40:03 - mmengine - INFO - Epoch(train) [113][200/293] lr: 5.000000e-04 eta: 2:22:08 time: 0.337493 data_time: 0.060773 memory: 5151 loss_kpt: 0.000707 acc_pose: 0.816788 loss: 0.000707 2022/09/17 16:40:20 - mmengine - INFO - Epoch(train) [113][250/293] lr: 5.000000e-04 eta: 2:21:54 time: 0.329587 data_time: 0.066673 memory: 5151 loss_kpt: 0.000706 acc_pose: 0.796156 loss: 0.000706 2022/09/17 16:40:35 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:40:35 - mmengine - INFO - Saving checkpoint at 113 epochs 2022/09/17 16:40:54 - mmengine - INFO - Epoch(train) [114][50/293] lr: 5.000000e-04 eta: 2:21:17 time: 0.345242 data_time: 0.064175 memory: 5151 loss_kpt: 0.000696 acc_pose: 0.820922 loss: 0.000696 2022/09/17 16:41:12 - mmengine - INFO - Epoch(train) [114][100/293] lr: 5.000000e-04 eta: 2:21:04 time: 0.345065 data_time: 0.065693 memory: 5151 loss_kpt: 0.000684 acc_pose: 0.847854 loss: 0.000684 2022/09/17 16:41:28 - mmengine - INFO - Epoch(train) [114][150/293] lr: 5.000000e-04 eta: 2:20:50 time: 0.317889 data_time: 0.056278 memory: 5151 loss_kpt: 0.000697 acc_pose: 0.836932 loss: 0.000697 2022/09/17 16:41:44 - mmengine - INFO - Epoch(train) [114][200/293] lr: 5.000000e-04 eta: 2:20:37 time: 0.336837 data_time: 0.066152 memory: 5151 loss_kpt: 0.000707 acc_pose: 0.787843 loss: 0.000707 2022/09/17 16:42:01 - mmengine - INFO - Epoch(train) [114][250/293] lr: 5.000000e-04 eta: 2:20:24 time: 0.339225 data_time: 0.074197 memory: 5151 loss_kpt: 0.000703 acc_pose: 0.811294 loss: 0.000703 2022/09/17 16:42:16 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:42:16 - mmengine - INFO - Saving checkpoint at 114 epochs 2022/09/17 16:42:35 - mmengine - INFO - Epoch(train) [115][50/293] lr: 5.000000e-04 eta: 2:19:47 time: 0.335594 data_time: 0.070936 memory: 5151 loss_kpt: 0.000690 acc_pose: 0.796532 loss: 0.000690 2022/09/17 16:42:52 - mmengine - INFO - Epoch(train) [115][100/293] lr: 5.000000e-04 eta: 2:19:33 time: 0.336351 data_time: 0.062995 memory: 5151 loss_kpt: 0.000701 acc_pose: 0.774441 loss: 0.000701 2022/09/17 16:43:09 - mmengine - INFO - Epoch(train) [115][150/293] lr: 5.000000e-04 eta: 2:19:20 time: 0.342964 data_time: 0.063870 memory: 5151 loss_kpt: 0.000705 acc_pose: 0.747757 loss: 0.000705 2022/09/17 16:43:26 - mmengine - INFO - Epoch(train) [115][200/293] lr: 5.000000e-04 eta: 2:19:07 time: 0.333869 data_time: 0.065565 memory: 5151 loss_kpt: 0.000710 acc_pose: 0.805136 loss: 0.000710 2022/09/17 16:43:42 - mmengine - INFO - Epoch(train) [115][250/293] lr: 5.000000e-04 eta: 2:18:53 time: 0.335645 data_time: 0.059376 memory: 5151 loss_kpt: 0.000705 acc_pose: 0.813990 loss: 0.000705 2022/09/17 16:43:56 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:43:56 - mmengine - INFO - Saving checkpoint at 115 epochs 2022/09/17 16:44:16 - mmengine - INFO - Epoch(train) [116][50/293] lr: 5.000000e-04 eta: 2:18:17 time: 0.343524 data_time: 0.068366 memory: 5151 loss_kpt: 0.000706 acc_pose: 0.853445 loss: 0.000706 2022/09/17 16:44:32 - mmengine - INFO - Epoch(train) [116][100/293] lr: 5.000000e-04 eta: 2:18:03 time: 0.323477 data_time: 0.056669 memory: 5151 loss_kpt: 0.000694 acc_pose: 0.764468 loss: 0.000694 2022/09/17 16:44:49 - mmengine - INFO - Epoch(train) [116][150/293] lr: 5.000000e-04 eta: 2:17:49 time: 0.332240 data_time: 0.064263 memory: 5151 loss_kpt: 0.000690 acc_pose: 0.844132 loss: 0.000690 2022/09/17 16:45:06 - mmengine - INFO - Epoch(train) [116][200/293] lr: 5.000000e-04 eta: 2:17:36 time: 0.334306 data_time: 0.069050 memory: 5151 loss_kpt: 0.000708 acc_pose: 0.807843 loss: 0.000708 2022/09/17 16:45:22 - mmengine - INFO - Epoch(train) [116][250/293] lr: 5.000000e-04 eta: 2:17:22 time: 0.333234 data_time: 0.061584 memory: 5151 loss_kpt: 0.000699 acc_pose: 0.806095 loss: 0.000699 2022/09/17 16:45:37 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:45:37 - mmengine - INFO - Saving checkpoint at 116 epochs 2022/09/17 16:45:44 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:45:57 - mmengine - INFO - Epoch(train) [117][50/293] lr: 5.000000e-04 eta: 2:16:46 time: 0.347173 data_time: 0.071131 memory: 5151 loss_kpt: 0.000703 acc_pose: 0.827467 loss: 0.000703 2022/09/17 16:46:13 - mmengine - INFO - Epoch(train) [117][100/293] lr: 5.000000e-04 eta: 2:16:32 time: 0.331224 data_time: 0.063400 memory: 5151 loss_kpt: 0.000696 acc_pose: 0.795967 loss: 0.000696 2022/09/17 16:46:30 - mmengine - INFO - Epoch(train) [117][150/293] lr: 5.000000e-04 eta: 2:16:19 time: 0.335562 data_time: 0.073561 memory: 5151 loss_kpt: 0.000693 acc_pose: 0.775386 loss: 0.000693 2022/09/17 16:46:46 - mmengine - INFO - Epoch(train) [117][200/293] lr: 5.000000e-04 eta: 2:16:05 time: 0.328378 data_time: 0.061405 memory: 5151 loss_kpt: 0.000695 acc_pose: 0.830055 loss: 0.000695 2022/09/17 16:47:03 - mmengine - INFO - Epoch(train) [117][250/293] lr: 5.000000e-04 eta: 2:15:51 time: 0.327079 data_time: 0.064263 memory: 5151 loss_kpt: 0.000710 acc_pose: 0.826444 loss: 0.000710 2022/09/17 16:47:16 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:47:16 - mmengine - INFO - Saving checkpoint at 117 epochs 2022/09/17 16:47:36 - mmengine - INFO - Epoch(train) [118][50/293] lr: 5.000000e-04 eta: 2:15:16 time: 0.353314 data_time: 0.075570 memory: 5151 loss_kpt: 0.000703 acc_pose: 0.796965 loss: 0.000703 2022/09/17 16:47:53 - mmengine - INFO - Epoch(train) [118][100/293] lr: 5.000000e-04 eta: 2:15:02 time: 0.334913 data_time: 0.065619 memory: 5151 loss_kpt: 0.000715 acc_pose: 0.792329 loss: 0.000715 2022/09/17 16:48:10 - mmengine - INFO - Epoch(train) [118][150/293] lr: 5.000000e-04 eta: 2:14:49 time: 0.339207 data_time: 0.069792 memory: 5151 loss_kpt: 0.000685 acc_pose: 0.827925 loss: 0.000685 2022/09/17 16:48:27 - mmengine - INFO - Epoch(train) [118][200/293] lr: 5.000000e-04 eta: 2:14:35 time: 0.338758 data_time: 0.068313 memory: 5151 loss_kpt: 0.000711 acc_pose: 0.851245 loss: 0.000711 2022/09/17 16:48:44 - mmengine - INFO - Epoch(train) [118][250/293] lr: 5.000000e-04 eta: 2:14:22 time: 0.331108 data_time: 0.058196 memory: 5151 loss_kpt: 0.000706 acc_pose: 0.795570 loss: 0.000706 2022/09/17 16:48:58 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:48:58 - mmengine - INFO - Saving checkpoint at 118 epochs 2022/09/17 16:49:17 - mmengine - INFO - Epoch(train) [119][50/293] lr: 5.000000e-04 eta: 2:13:46 time: 0.345797 data_time: 0.073244 memory: 5151 loss_kpt: 0.000701 acc_pose: 0.833614 loss: 0.000701 2022/09/17 16:49:33 - mmengine - INFO - Epoch(train) [119][100/293] lr: 5.000000e-04 eta: 2:13:32 time: 0.323002 data_time: 0.063163 memory: 5151 loss_kpt: 0.000707 acc_pose: 0.835293 loss: 0.000707 2022/09/17 16:49:50 - mmengine - INFO - Epoch(train) [119][150/293] lr: 5.000000e-04 eta: 2:13:18 time: 0.333344 data_time: 0.056713 memory: 5151 loss_kpt: 0.000703 acc_pose: 0.849700 loss: 0.000703 2022/09/17 16:50:07 - mmengine - INFO - Epoch(train) [119][200/293] lr: 5.000000e-04 eta: 2:13:05 time: 0.333137 data_time: 0.061374 memory: 5151 loss_kpt: 0.000708 acc_pose: 0.838085 loss: 0.000708 2022/09/17 16:50:23 - mmengine - INFO - Epoch(train) [119][250/293] lr: 5.000000e-04 eta: 2:12:51 time: 0.326884 data_time: 0.059779 memory: 5151 loss_kpt: 0.000692 acc_pose: 0.844335 loss: 0.000692 2022/09/17 16:50:37 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:50:37 - mmengine - INFO - Saving checkpoint at 119 epochs 2022/09/17 16:50:57 - mmengine - INFO - Epoch(train) [120][50/293] lr: 5.000000e-04 eta: 2:12:15 time: 0.346180 data_time: 0.076528 memory: 5151 loss_kpt: 0.000683 acc_pose: 0.831334 loss: 0.000683 2022/09/17 16:51:14 - mmengine - INFO - Epoch(train) [120][100/293] lr: 5.000000e-04 eta: 2:12:02 time: 0.333301 data_time: 0.062813 memory: 5151 loss_kpt: 0.000705 acc_pose: 0.798156 loss: 0.000705 2022/09/17 16:51:25 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:51:30 - mmengine - INFO - Epoch(train) [120][150/293] lr: 5.000000e-04 eta: 2:11:48 time: 0.321984 data_time: 0.060223 memory: 5151 loss_kpt: 0.000701 acc_pose: 0.812682 loss: 0.000701 2022/09/17 16:51:47 - mmengine - INFO - Epoch(train) [120][200/293] lr: 5.000000e-04 eta: 2:11:35 time: 0.345268 data_time: 0.064933 memory: 5151 loss_kpt: 0.000692 acc_pose: 0.816901 loss: 0.000692 2022/09/17 16:52:04 - mmengine - INFO - Epoch(train) [120][250/293] lr: 5.000000e-04 eta: 2:11:21 time: 0.336405 data_time: 0.070048 memory: 5151 loss_kpt: 0.000705 acc_pose: 0.827378 loss: 0.000705 2022/09/17 16:52:18 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:52:18 - mmengine - INFO - Saving checkpoint at 120 epochs 2022/09/17 16:52:27 - mmengine - INFO - Epoch(val) [120][50/407] eta: 0:00:43 time: 0.122807 data_time: 0.054338 memory: 5151 2022/09/17 16:52:33 - mmengine - INFO - Epoch(val) [120][100/407] eta: 0:00:35 time: 0.116617 data_time: 0.047691 memory: 331 2022/09/17 16:52:39 - mmengine - INFO - Epoch(val) [120][150/407] eta: 0:00:32 time: 0.126925 data_time: 0.060438 memory: 331 2022/09/17 16:52:45 - mmengine - INFO - Epoch(val) [120][200/407] eta: 0:00:24 time: 0.117490 data_time: 0.049903 memory: 331 2022/09/17 16:52:51 - mmengine - INFO - Epoch(val) [120][250/407] eta: 0:00:19 time: 0.121885 data_time: 0.053325 memory: 331 2022/09/17 16:52:57 - mmengine - INFO - Epoch(val) [120][300/407] eta: 0:00:13 time: 0.122747 data_time: 0.053735 memory: 331 2022/09/17 16:53:03 - mmengine - INFO - Epoch(val) [120][350/407] eta: 0:00:06 time: 0.120010 data_time: 0.051384 memory: 331 2022/09/17 16:53:09 - mmengine - INFO - Epoch(val) [120][400/407] eta: 0:00:00 time: 0.113626 data_time: 0.046806 memory: 331 2022/09/17 16:53:46 - mmengine - INFO - Evaluating CocoMetric... 2022/09/17 16:54:00 - mmengine - INFO - Epoch(val) [120][407/407] coco/AP: 0.690758 coco/AP .5: 0.884575 coco/AP .75: 0.772110 coco/AP (M): 0.658454 coco/AP (L): 0.753568 coco/AR: 0.748064 coco/AR .5: 0.924748 coco/AR .75: 0.820372 coco/AR (M): 0.706719 coco/AR (L): 0.807507 2022/09/17 16:54:00 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220917/vipnas_res50/best_coco/AP_epoch_110.pth is removed 2022/09/17 16:54:02 - mmengine - INFO - The best checkpoint with 0.6908 coco/AP at 120 epoch is saved to best_coco/AP_epoch_120.pth. 2022/09/17 16:54:20 - mmengine - INFO - Epoch(train) [121][50/293] lr: 5.000000e-04 eta: 2:10:46 time: 0.360463 data_time: 0.081821 memory: 5151 loss_kpt: 0.000675 acc_pose: 0.848510 loss: 0.000675 2022/09/17 16:54:37 - mmengine - INFO - Epoch(train) [121][100/293] lr: 5.000000e-04 eta: 2:10:32 time: 0.333259 data_time: 0.067915 memory: 5151 loss_kpt: 0.000710 acc_pose: 0.784307 loss: 0.000710 2022/09/17 16:54:53 - mmengine - INFO - Epoch(train) [121][150/293] lr: 5.000000e-04 eta: 2:10:19 time: 0.332867 data_time: 0.066462 memory: 5151 loss_kpt: 0.000702 acc_pose: 0.827509 loss: 0.000702 2022/09/17 16:55:11 - mmengine - INFO - Epoch(train) [121][200/293] lr: 5.000000e-04 eta: 2:10:06 time: 0.346586 data_time: 0.071329 memory: 5151 loss_kpt: 0.000691 acc_pose: 0.841948 loss: 0.000691 2022/09/17 16:55:27 - mmengine - INFO - Epoch(train) [121][250/293] lr: 5.000000e-04 eta: 2:09:52 time: 0.328648 data_time: 0.069466 memory: 5151 loss_kpt: 0.000704 acc_pose: 0.806994 loss: 0.000704 2022/09/17 16:55:41 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:55:41 - mmengine - INFO - Saving checkpoint at 121 epochs 2022/09/17 16:56:01 - mmengine - INFO - Epoch(train) [122][50/293] lr: 5.000000e-04 eta: 2:09:16 time: 0.342927 data_time: 0.068344 memory: 5151 loss_kpt: 0.000695 acc_pose: 0.791405 loss: 0.000695 2022/09/17 16:56:18 - mmengine - INFO - Epoch(train) [122][100/293] lr: 5.000000e-04 eta: 2:09:03 time: 0.340745 data_time: 0.065862 memory: 5151 loss_kpt: 0.000703 acc_pose: 0.794532 loss: 0.000703 2022/09/17 16:56:34 - mmengine - INFO - Epoch(train) [122][150/293] lr: 5.000000e-04 eta: 2:08:49 time: 0.323204 data_time: 0.068385 memory: 5151 loss_kpt: 0.000700 acc_pose: 0.822603 loss: 0.000700 2022/09/17 16:56:51 - mmengine - INFO - Epoch(train) [122][200/293] lr: 5.000000e-04 eta: 2:08:36 time: 0.347284 data_time: 0.071284 memory: 5151 loss_kpt: 0.000696 acc_pose: 0.831387 loss: 0.000696 2022/09/17 16:57:08 - mmengine - INFO - Epoch(train) [122][250/293] lr: 5.000000e-04 eta: 2:08:22 time: 0.330115 data_time: 0.069544 memory: 5151 loss_kpt: 0.000689 acc_pose: 0.868122 loss: 0.000689 2022/09/17 16:57:23 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:57:23 - mmengine - INFO - Saving checkpoint at 122 epochs 2022/09/17 16:57:43 - mmengine - INFO - Epoch(train) [123][50/293] lr: 5.000000e-04 eta: 2:07:47 time: 0.352371 data_time: 0.076366 memory: 5151 loss_kpt: 0.000688 acc_pose: 0.802885 loss: 0.000688 2022/09/17 16:58:00 - mmengine - INFO - Epoch(train) [123][100/293] lr: 5.000000e-04 eta: 2:07:34 time: 0.346357 data_time: 0.071222 memory: 5151 loss_kpt: 0.000688 acc_pose: 0.818663 loss: 0.000688 2022/09/17 16:58:17 - mmengine - INFO - Epoch(train) [123][150/293] lr: 5.000000e-04 eta: 2:07:20 time: 0.334007 data_time: 0.064371 memory: 5151 loss_kpt: 0.000690 acc_pose: 0.839946 loss: 0.000690 2022/09/17 16:58:33 - mmengine - INFO - Epoch(train) [123][200/293] lr: 5.000000e-04 eta: 2:07:07 time: 0.332248 data_time: 0.069793 memory: 5151 loss_kpt: 0.000694 acc_pose: 0.817676 loss: 0.000694 2022/09/17 16:58:51 - mmengine - INFO - Epoch(train) [123][250/293] lr: 5.000000e-04 eta: 2:06:53 time: 0.346747 data_time: 0.075182 memory: 5151 loss_kpt: 0.000676 acc_pose: 0.799529 loss: 0.000676 2022/09/17 16:58:52 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:59:05 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 16:59:05 - mmengine - INFO - Saving checkpoint at 123 epochs 2022/09/17 16:59:25 - mmengine - INFO - Epoch(train) [124][50/293] lr: 5.000000e-04 eta: 2:06:19 time: 0.354255 data_time: 0.079261 memory: 5151 loss_kpt: 0.000713 acc_pose: 0.828157 loss: 0.000713 2022/09/17 16:59:42 - mmengine - INFO - Epoch(train) [124][100/293] lr: 5.000000e-04 eta: 2:06:05 time: 0.344877 data_time: 0.071875 memory: 5151 loss_kpt: 0.000684 acc_pose: 0.867251 loss: 0.000684 2022/09/17 16:59:59 - mmengine - INFO - Epoch(train) [124][150/293] lr: 5.000000e-04 eta: 2:05:52 time: 0.343376 data_time: 0.072947 memory: 5151 loss_kpt: 0.000686 acc_pose: 0.845492 loss: 0.000686 2022/09/17 17:00:17 - mmengine - INFO - Epoch(train) [124][200/293] lr: 5.000000e-04 eta: 2:05:39 time: 0.343634 data_time: 0.077580 memory: 5151 loss_kpt: 0.000700 acc_pose: 0.846771 loss: 0.000700 2022/09/17 17:00:33 - mmengine - INFO - Epoch(train) [124][250/293] lr: 5.000000e-04 eta: 2:05:25 time: 0.334851 data_time: 0.070533 memory: 5151 loss_kpt: 0.000698 acc_pose: 0.788820 loss: 0.000698 2022/09/17 17:00:48 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:00:48 - mmengine - INFO - Saving checkpoint at 124 epochs 2022/09/17 17:01:08 - mmengine - INFO - Epoch(train) [125][50/293] lr: 5.000000e-04 eta: 2:04:50 time: 0.340730 data_time: 0.071848 memory: 5151 loss_kpt: 0.000697 acc_pose: 0.854318 loss: 0.000697 2022/09/17 17:01:25 - mmengine - INFO - Epoch(train) [125][100/293] lr: 5.000000e-04 eta: 2:04:37 time: 0.344065 data_time: 0.074418 memory: 5151 loss_kpt: 0.000681 acc_pose: 0.825685 loss: 0.000681 2022/09/17 17:01:42 - mmengine - INFO - Epoch(train) [125][150/293] lr: 5.000000e-04 eta: 2:04:23 time: 0.338253 data_time: 0.066185 memory: 5151 loss_kpt: 0.000689 acc_pose: 0.835595 loss: 0.000689 2022/09/17 17:01:58 - mmengine - INFO - Epoch(train) [125][200/293] lr: 5.000000e-04 eta: 2:04:10 time: 0.333917 data_time: 0.072633 memory: 5151 loss_kpt: 0.000690 acc_pose: 0.833693 loss: 0.000690 2022/09/17 17:02:15 - mmengine - INFO - Epoch(train) [125][250/293] lr: 5.000000e-04 eta: 2:03:56 time: 0.337104 data_time: 0.075571 memory: 5151 loss_kpt: 0.000688 acc_pose: 0.835266 loss: 0.000688 2022/09/17 17:02:30 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:02:30 - mmengine - INFO - Saving checkpoint at 125 epochs 2022/09/17 17:02:50 - mmengine - INFO - Epoch(train) [126][50/293] lr: 5.000000e-04 eta: 2:03:22 time: 0.357811 data_time: 0.080537 memory: 5151 loss_kpt: 0.000708 acc_pose: 0.818037 loss: 0.000708 2022/09/17 17:03:07 - mmengine - INFO - Epoch(train) [126][100/293] lr: 5.000000e-04 eta: 2:03:08 time: 0.339495 data_time: 0.064168 memory: 5151 loss_kpt: 0.000684 acc_pose: 0.861396 loss: 0.000684 2022/09/17 17:03:23 - mmengine - INFO - Epoch(train) [126][150/293] lr: 5.000000e-04 eta: 2:02:54 time: 0.325532 data_time: 0.068206 memory: 5151 loss_kpt: 0.000702 acc_pose: 0.845799 loss: 0.000702 2022/09/17 17:03:40 - mmengine - INFO - Epoch(train) [126][200/293] lr: 5.000000e-04 eta: 2:02:41 time: 0.336657 data_time: 0.070502 memory: 5151 loss_kpt: 0.000697 acc_pose: 0.833114 loss: 0.000697 2022/09/17 17:03:57 - mmengine - INFO - Epoch(train) [126][250/293] lr: 5.000000e-04 eta: 2:02:27 time: 0.332992 data_time: 0.071679 memory: 5151 loss_kpt: 0.000696 acc_pose: 0.777639 loss: 0.000696 2022/09/17 17:04:12 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:04:12 - mmengine - INFO - Saving checkpoint at 126 epochs 2022/09/17 17:04:31 - mmengine - INFO - Epoch(train) [127][50/293] lr: 5.000000e-04 eta: 2:01:52 time: 0.349873 data_time: 0.081610 memory: 5151 loss_kpt: 0.000701 acc_pose: 0.873487 loss: 0.000701 2022/09/17 17:04:42 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:04:49 - mmengine - INFO - Epoch(train) [127][100/293] lr: 5.000000e-04 eta: 2:01:39 time: 0.347942 data_time: 0.074128 memory: 5151 loss_kpt: 0.000683 acc_pose: 0.813327 loss: 0.000683 2022/09/17 17:05:06 - mmengine - INFO - Epoch(train) [127][150/293] lr: 5.000000e-04 eta: 2:01:26 time: 0.348032 data_time: 0.067269 memory: 5151 loss_kpt: 0.000698 acc_pose: 0.834774 loss: 0.000698 2022/09/17 17:05:23 - mmengine - INFO - Epoch(train) [127][200/293] lr: 5.000000e-04 eta: 2:01:12 time: 0.334453 data_time: 0.066518 memory: 5151 loss_kpt: 0.000690 acc_pose: 0.845881 loss: 0.000690 2022/09/17 17:05:40 - mmengine - INFO - Epoch(train) [127][250/293] lr: 5.000000e-04 eta: 2:00:59 time: 0.335386 data_time: 0.062619 memory: 5151 loss_kpt: 0.000675 acc_pose: 0.812582 loss: 0.000675 2022/09/17 17:05:54 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:05:54 - mmengine - INFO - Saving checkpoint at 127 epochs 2022/09/17 17:06:14 - mmengine - INFO - Epoch(train) [128][50/293] lr: 5.000000e-04 eta: 2:00:24 time: 0.349497 data_time: 0.080360 memory: 5151 loss_kpt: 0.000684 acc_pose: 0.880638 loss: 0.000684 2022/09/17 17:06:31 - mmengine - INFO - Epoch(train) [128][100/293] lr: 5.000000e-04 eta: 2:00:11 time: 0.340705 data_time: 0.067780 memory: 5151 loss_kpt: 0.000687 acc_pose: 0.878499 loss: 0.000687 2022/09/17 17:06:48 - mmengine - INFO - Epoch(train) [128][150/293] lr: 5.000000e-04 eta: 1:59:57 time: 0.336327 data_time: 0.069793 memory: 5151 loss_kpt: 0.000690 acc_pose: 0.871021 loss: 0.000690 2022/09/17 17:07:04 - mmengine - INFO - Epoch(train) [128][200/293] lr: 5.000000e-04 eta: 1:59:43 time: 0.331895 data_time: 0.069578 memory: 5151 loss_kpt: 0.000684 acc_pose: 0.813306 loss: 0.000684 2022/09/17 17:07:22 - mmengine - INFO - Epoch(train) [128][250/293] lr: 5.000000e-04 eta: 1:59:30 time: 0.345785 data_time: 0.069793 memory: 5151 loss_kpt: 0.000690 acc_pose: 0.798492 loss: 0.000690 2022/09/17 17:07:37 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:07:37 - mmengine - INFO - Saving checkpoint at 128 epochs 2022/09/17 17:07:57 - mmengine - INFO - Epoch(train) [129][50/293] lr: 5.000000e-04 eta: 1:58:56 time: 0.352242 data_time: 0.079672 memory: 5151 loss_kpt: 0.000695 acc_pose: 0.837249 loss: 0.000695 2022/09/17 17:08:14 - mmengine - INFO - Epoch(train) [129][100/293] lr: 5.000000e-04 eta: 1:58:42 time: 0.344554 data_time: 0.076215 memory: 5151 loss_kpt: 0.000678 acc_pose: 0.780438 loss: 0.000678 2022/09/17 17:08:31 - mmengine - INFO - Epoch(train) [129][150/293] lr: 5.000000e-04 eta: 1:58:29 time: 0.344459 data_time: 0.071841 memory: 5151 loss_kpt: 0.000695 acc_pose: 0.822589 loss: 0.000695 2022/09/17 17:08:48 - mmengine - INFO - Epoch(train) [129][200/293] lr: 5.000000e-04 eta: 1:58:16 time: 0.342954 data_time: 0.073100 memory: 5151 loss_kpt: 0.000684 acc_pose: 0.842049 loss: 0.000684 2022/09/17 17:09:05 - mmengine - INFO - Epoch(train) [129][250/293] lr: 5.000000e-04 eta: 1:58:02 time: 0.340062 data_time: 0.072616 memory: 5151 loss_kpt: 0.000694 acc_pose: 0.787721 loss: 0.000694 2022/09/17 17:09:20 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:09:20 - mmengine - INFO - Saving checkpoint at 129 epochs 2022/09/17 17:09:40 - mmengine - INFO - Epoch(train) [130][50/293] lr: 5.000000e-04 eta: 1:57:28 time: 0.351159 data_time: 0.072743 memory: 5151 loss_kpt: 0.000677 acc_pose: 0.795565 loss: 0.000677 2022/09/17 17:09:57 - mmengine - INFO - Epoch(train) [130][100/293] lr: 5.000000e-04 eta: 1:57:14 time: 0.339340 data_time: 0.072313 memory: 5151 loss_kpt: 0.000693 acc_pose: 0.788721 loss: 0.000693 2022/09/17 17:10:14 - mmengine - INFO - Epoch(train) [130][150/293] lr: 5.000000e-04 eta: 1:57:01 time: 0.336174 data_time: 0.077098 memory: 5151 loss_kpt: 0.000698 acc_pose: 0.827810 loss: 0.000698 2022/09/17 17:10:30 - mmengine - INFO - Epoch(train) [130][200/293] lr: 5.000000e-04 eta: 1:56:47 time: 0.335238 data_time: 0.071878 memory: 5151 loss_kpt: 0.000695 acc_pose: 0.809705 loss: 0.000695 2022/09/17 17:10:31 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:10:47 - mmengine - INFO - Epoch(train) [130][250/293] lr: 5.000000e-04 eta: 1:56:33 time: 0.336998 data_time: 0.073154 memory: 5151 loss_kpt: 0.000696 acc_pose: 0.813598 loss: 0.000696 2022/09/17 17:11:02 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:11:02 - mmengine - INFO - Saving checkpoint at 130 epochs 2022/09/17 17:11:11 - mmengine - INFO - Epoch(val) [130][50/407] eta: 0:00:43 time: 0.121189 data_time: 0.052245 memory: 5151 2022/09/17 17:11:17 - mmengine - INFO - Epoch(val) [130][100/407] eta: 0:00:36 time: 0.117361 data_time: 0.047652 memory: 331 2022/09/17 17:11:23 - mmengine - INFO - Epoch(val) [130][150/407] eta: 0:00:32 time: 0.125764 data_time: 0.056421 memory: 331 2022/09/17 17:11:29 - mmengine - INFO - Epoch(val) [130][200/407] eta: 0:00:23 time: 0.112762 data_time: 0.043936 memory: 331 2022/09/17 17:11:34 - mmengine - INFO - Epoch(val) [130][250/407] eta: 0:00:17 time: 0.113033 data_time: 0.045996 memory: 331 2022/09/17 17:11:40 - mmengine - INFO - Epoch(val) [130][300/407] eta: 0:00:12 time: 0.118532 data_time: 0.050642 memory: 331 2022/09/17 17:11:46 - mmengine - INFO - Epoch(val) [130][350/407] eta: 0:00:06 time: 0.119933 data_time: 0.046557 memory: 331 2022/09/17 17:11:52 - mmengine - INFO - Epoch(val) [130][400/407] eta: 0:00:00 time: 0.107498 data_time: 0.042054 memory: 331 2022/09/17 17:12:29 - mmengine - INFO - Evaluating CocoMetric... 2022/09/17 17:12:43 - mmengine - INFO - Epoch(val) [130][407/407] coco/AP: 0.691201 coco/AP .5: 0.883122 coco/AP .75: 0.770755 coco/AP (M): 0.659322 coco/AP (L): 0.755530 coco/AR: 0.750520 coco/AR .5: 0.925063 coco/AR .75: 0.821788 coco/AR (M): 0.708440 coco/AR (L): 0.811483 2022/09/17 17:12:44 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220917/vipnas_res50/best_coco/AP_epoch_120.pth is removed 2022/09/17 17:12:46 - mmengine - INFO - The best checkpoint with 0.6912 coco/AP at 130 epoch is saved to best_coco/AP_epoch_130.pth. 2022/09/17 17:13:03 - mmengine - INFO - Epoch(train) [131][50/293] lr: 5.000000e-04 eta: 1:55:59 time: 0.351869 data_time: 0.081045 memory: 5151 loss_kpt: 0.000684 acc_pose: 0.846114 loss: 0.000684 2022/09/17 17:13:21 - mmengine - INFO - Epoch(train) [131][100/293] lr: 5.000000e-04 eta: 1:55:46 time: 0.344607 data_time: 0.075729 memory: 5151 loss_kpt: 0.000681 acc_pose: 0.825752 loss: 0.000681 2022/09/17 17:13:38 - mmengine - INFO - Epoch(train) [131][150/293] lr: 5.000000e-04 eta: 1:55:32 time: 0.338778 data_time: 0.068776 memory: 5151 loss_kpt: 0.000684 acc_pose: 0.838219 loss: 0.000684 2022/09/17 17:13:54 - mmengine - INFO - Epoch(train) [131][200/293] lr: 5.000000e-04 eta: 1:55:19 time: 0.335500 data_time: 0.075153 memory: 5151 loss_kpt: 0.000702 acc_pose: 0.820336 loss: 0.000702 2022/09/17 17:14:11 - mmengine - INFO - Epoch(train) [131][250/293] lr: 5.000000e-04 eta: 1:55:05 time: 0.339305 data_time: 0.076678 memory: 5151 loss_kpt: 0.000703 acc_pose: 0.821345 loss: 0.000703 2022/09/17 17:14:26 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:14:26 - mmengine - INFO - Saving checkpoint at 131 epochs 2022/09/17 17:14:46 - mmengine - INFO - Epoch(train) [132][50/293] lr: 5.000000e-04 eta: 1:54:31 time: 0.353183 data_time: 0.076970 memory: 5151 loss_kpt: 0.000691 acc_pose: 0.879305 loss: 0.000691 2022/09/17 17:15:04 - mmengine - INFO - Epoch(train) [132][100/293] lr: 5.000000e-04 eta: 1:54:18 time: 0.344206 data_time: 0.074548 memory: 5151 loss_kpt: 0.000686 acc_pose: 0.824368 loss: 0.000686 2022/09/17 17:15:20 - mmengine - INFO - Epoch(train) [132][150/293] lr: 5.000000e-04 eta: 1:54:04 time: 0.328704 data_time: 0.068942 memory: 5151 loss_kpt: 0.000684 acc_pose: 0.792246 loss: 0.000684 2022/09/17 17:15:37 - mmengine - INFO - Epoch(train) [132][200/293] lr: 5.000000e-04 eta: 1:53:50 time: 0.336453 data_time: 0.068186 memory: 5151 loss_kpt: 0.000703 acc_pose: 0.841606 loss: 0.000703 2022/09/17 17:15:54 - mmengine - INFO - Epoch(train) [132][250/293] lr: 5.000000e-04 eta: 1:53:37 time: 0.344159 data_time: 0.076294 memory: 5151 loss_kpt: 0.000686 acc_pose: 0.814002 loss: 0.000686 2022/09/17 17:16:08 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:16:08 - mmengine - INFO - Saving checkpoint at 132 epochs 2022/09/17 17:16:28 - mmengine - INFO - Epoch(train) [133][50/293] lr: 5.000000e-04 eta: 1:53:03 time: 0.344302 data_time: 0.070878 memory: 5151 loss_kpt: 0.000703 acc_pose: 0.751512 loss: 0.000703 2022/09/17 17:16:44 - mmengine - INFO - Epoch(train) [133][100/293] lr: 5.000000e-04 eta: 1:52:49 time: 0.334248 data_time: 0.070155 memory: 5151 loss_kpt: 0.000705 acc_pose: 0.806537 loss: 0.000705 2022/09/17 17:17:02 - mmengine - INFO - Epoch(train) [133][150/293] lr: 5.000000e-04 eta: 1:52:35 time: 0.348165 data_time: 0.072843 memory: 5151 loss_kpt: 0.000688 acc_pose: 0.800767 loss: 0.000688 2022/09/17 17:17:19 - mmengine - INFO - Epoch(train) [133][200/293] lr: 5.000000e-04 eta: 1:52:22 time: 0.337468 data_time: 0.072171 memory: 5151 loss_kpt: 0.000691 acc_pose: 0.809942 loss: 0.000691 2022/09/17 17:17:36 - mmengine - INFO - Epoch(train) [133][250/293] lr: 5.000000e-04 eta: 1:52:08 time: 0.337944 data_time: 0.074108 memory: 5151 loss_kpt: 0.000682 acc_pose: 0.835510 loss: 0.000682 2022/09/17 17:17:50 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:17:50 - mmengine - INFO - Saving checkpoint at 133 epochs 2022/09/17 17:18:04 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:18:11 - mmengine - INFO - Epoch(train) [134][50/293] lr: 5.000000e-04 eta: 1:51:35 time: 0.358695 data_time: 0.080085 memory: 5151 loss_kpt: 0.000679 acc_pose: 0.795809 loss: 0.000679 2022/09/17 17:18:28 - mmengine - INFO - Epoch(train) [134][100/293] lr: 5.000000e-04 eta: 1:51:21 time: 0.338965 data_time: 0.066581 memory: 5151 loss_kpt: 0.000682 acc_pose: 0.833703 loss: 0.000682 2022/09/17 17:18:44 - mmengine - INFO - Epoch(train) [134][150/293] lr: 5.000000e-04 eta: 1:51:07 time: 0.331946 data_time: 0.072317 memory: 5151 loss_kpt: 0.000685 acc_pose: 0.832078 loss: 0.000685 2022/09/17 17:19:02 - mmengine - INFO - Epoch(train) [134][200/293] lr: 5.000000e-04 eta: 1:50:54 time: 0.344278 data_time: 0.075499 memory: 5151 loss_kpt: 0.000701 acc_pose: 0.831264 loss: 0.000701 2022/09/17 17:19:19 - mmengine - INFO - Epoch(train) [134][250/293] lr: 5.000000e-04 eta: 1:50:40 time: 0.348566 data_time: 0.076717 memory: 5151 loss_kpt: 0.000690 acc_pose: 0.825805 loss: 0.000690 2022/09/17 17:19:33 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:19:33 - mmengine - INFO - Saving checkpoint at 134 epochs 2022/09/17 17:19:54 - mmengine - INFO - Epoch(train) [135][50/293] lr: 5.000000e-04 eta: 1:50:07 time: 0.359315 data_time: 0.088858 memory: 5151 loss_kpt: 0.000697 acc_pose: 0.830779 loss: 0.000697 2022/09/17 17:20:11 - mmengine - INFO - Epoch(train) [135][100/293] lr: 5.000000e-04 eta: 1:49:54 time: 0.345695 data_time: 0.069198 memory: 5151 loss_kpt: 0.000678 acc_pose: 0.847116 loss: 0.000678 2022/09/17 17:20:29 - mmengine - INFO - Epoch(train) [135][150/293] lr: 5.000000e-04 eta: 1:49:40 time: 0.350709 data_time: 0.080023 memory: 5151 loss_kpt: 0.000685 acc_pose: 0.831202 loss: 0.000685 2022/09/17 17:20:46 - mmengine - INFO - Epoch(train) [135][200/293] lr: 5.000000e-04 eta: 1:49:27 time: 0.341380 data_time: 0.069444 memory: 5151 loss_kpt: 0.000678 acc_pose: 0.825199 loss: 0.000678 2022/09/17 17:21:03 - mmengine - INFO - Epoch(train) [135][250/293] lr: 5.000000e-04 eta: 1:49:13 time: 0.332707 data_time: 0.067562 memory: 5151 loss_kpt: 0.000697 acc_pose: 0.820898 loss: 0.000697 2022/09/17 17:21:16 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:21:16 - mmengine - INFO - Saving checkpoint at 135 epochs 2022/09/17 17:21:36 - mmengine - INFO - Epoch(train) [136][50/293] lr: 5.000000e-04 eta: 1:48:39 time: 0.338398 data_time: 0.072397 memory: 5151 loss_kpt: 0.000687 acc_pose: 0.806106 loss: 0.000687 2022/09/17 17:21:53 - mmengine - INFO - Epoch(train) [136][100/293] lr: 5.000000e-04 eta: 1:48:25 time: 0.340179 data_time: 0.074696 memory: 5151 loss_kpt: 0.000696 acc_pose: 0.825342 loss: 0.000696 2022/09/17 17:22:10 - mmengine - INFO - Epoch(train) [136][150/293] lr: 5.000000e-04 eta: 1:48:12 time: 0.342379 data_time: 0.072191 memory: 5151 loss_kpt: 0.000688 acc_pose: 0.787313 loss: 0.000688 2022/09/17 17:22:27 - mmengine - INFO - Epoch(train) [136][200/293] lr: 5.000000e-04 eta: 1:47:58 time: 0.344320 data_time: 0.072200 memory: 5151 loss_kpt: 0.000683 acc_pose: 0.817224 loss: 0.000683 2022/09/17 17:22:44 - mmengine - INFO - Epoch(train) [136][250/293] lr: 5.000000e-04 eta: 1:47:44 time: 0.339710 data_time: 0.068631 memory: 5151 loss_kpt: 0.000680 acc_pose: 0.827919 loss: 0.000680 2022/09/17 17:22:59 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:22:59 - mmengine - INFO - Saving checkpoint at 136 epochs 2022/09/17 17:23:19 - mmengine - INFO - Epoch(train) [137][50/293] lr: 5.000000e-04 eta: 1:47:11 time: 0.341950 data_time: 0.074063 memory: 5151 loss_kpt: 0.000680 acc_pose: 0.806634 loss: 0.000680 2022/09/17 17:23:35 - mmengine - INFO - Epoch(train) [137][100/293] lr: 5.000000e-04 eta: 1:46:57 time: 0.328972 data_time: 0.062374 memory: 5151 loss_kpt: 0.000684 acc_pose: 0.833205 loss: 0.000684 2022/09/17 17:23:52 - mmengine - INFO - Epoch(train) [137][150/293] lr: 5.000000e-04 eta: 1:46:43 time: 0.344391 data_time: 0.064816 memory: 5151 loss_kpt: 0.000686 acc_pose: 0.848908 loss: 0.000686 2022/09/17 17:23:53 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:24:09 - mmengine - INFO - Epoch(train) [137][200/293] lr: 5.000000e-04 eta: 1:46:30 time: 0.341912 data_time: 0.076583 memory: 5151 loss_kpt: 0.000694 acc_pose: 0.807624 loss: 0.000694 2022/09/17 17:24:26 - mmengine - INFO - Epoch(train) [137][250/293] lr: 5.000000e-04 eta: 1:46:16 time: 0.330287 data_time: 0.064357 memory: 5151 loss_kpt: 0.000670 acc_pose: 0.832255 loss: 0.000670 2022/09/17 17:24:41 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:24:41 - mmengine - INFO - Saving checkpoint at 137 epochs 2022/09/17 17:25:02 - mmengine - INFO - Epoch(train) [138][50/293] lr: 5.000000e-04 eta: 1:45:43 time: 0.356161 data_time: 0.073429 memory: 5151 loss_kpt: 0.000684 acc_pose: 0.846348 loss: 0.000684 2022/09/17 17:25:18 - mmengine - INFO - Epoch(train) [138][100/293] lr: 5.000000e-04 eta: 1:45:29 time: 0.337431 data_time: 0.072720 memory: 5151 loss_kpt: 0.000680 acc_pose: 0.823358 loss: 0.000680 2022/09/17 17:25:35 - mmengine - INFO - Epoch(train) [138][150/293] lr: 5.000000e-04 eta: 1:45:15 time: 0.335442 data_time: 0.071599 memory: 5151 loss_kpt: 0.000684 acc_pose: 0.838195 loss: 0.000684 2022/09/17 17:25:52 - mmengine - INFO - Epoch(train) [138][200/293] lr: 5.000000e-04 eta: 1:45:01 time: 0.343219 data_time: 0.070372 memory: 5151 loss_kpt: 0.000692 acc_pose: 0.841432 loss: 0.000692 2022/09/17 17:26:09 - mmengine - INFO - Epoch(train) [138][250/293] lr: 5.000000e-04 eta: 1:44:47 time: 0.328664 data_time: 0.058697 memory: 5151 loss_kpt: 0.000685 acc_pose: 0.801912 loss: 0.000685 2022/09/17 17:26:23 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:26:23 - mmengine - INFO - Saving checkpoint at 138 epochs 2022/09/17 17:26:44 - mmengine - INFO - Epoch(train) [139][50/293] lr: 5.000000e-04 eta: 1:44:14 time: 0.342900 data_time: 0.067222 memory: 5151 loss_kpt: 0.000692 acc_pose: 0.787186 loss: 0.000692 2022/09/17 17:27:00 - mmengine - INFO - Epoch(train) [139][100/293] lr: 5.000000e-04 eta: 1:44:00 time: 0.334546 data_time: 0.065851 memory: 5151 loss_kpt: 0.000683 acc_pose: 0.837449 loss: 0.000683 2022/09/17 17:27:17 - mmengine - INFO - Epoch(train) [139][150/293] lr: 5.000000e-04 eta: 1:43:46 time: 0.334115 data_time: 0.068602 memory: 5151 loss_kpt: 0.000679 acc_pose: 0.824396 loss: 0.000679 2022/09/17 17:27:34 - mmengine - INFO - Epoch(train) [139][200/293] lr: 5.000000e-04 eta: 1:43:33 time: 0.339082 data_time: 0.071214 memory: 5151 loss_kpt: 0.000677 acc_pose: 0.876249 loss: 0.000677 2022/09/17 17:27:51 - mmengine - INFO - Epoch(train) [139][250/293] lr: 5.000000e-04 eta: 1:43:19 time: 0.344367 data_time: 0.069023 memory: 5151 loss_kpt: 0.000692 acc_pose: 0.831774 loss: 0.000692 2022/09/17 17:28:06 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:28:06 - mmengine - INFO - Saving checkpoint at 139 epochs 2022/09/17 17:28:27 - mmengine - INFO - Epoch(train) [140][50/293] lr: 5.000000e-04 eta: 1:42:46 time: 0.355068 data_time: 0.080309 memory: 5151 loss_kpt: 0.000688 acc_pose: 0.820709 loss: 0.000688 2022/09/17 17:28:44 - mmengine - INFO - Epoch(train) [140][100/293] lr: 5.000000e-04 eta: 1:42:33 time: 0.342494 data_time: 0.063164 memory: 5151 loss_kpt: 0.000688 acc_pose: 0.804671 loss: 0.000688 2022/09/17 17:29:01 - mmengine - INFO - Epoch(train) [140][150/293] lr: 5.000000e-04 eta: 1:42:19 time: 0.335966 data_time: 0.072834 memory: 5151 loss_kpt: 0.000684 acc_pose: 0.820302 loss: 0.000684 2022/09/17 17:29:18 - mmengine - INFO - Epoch(train) [140][200/293] lr: 5.000000e-04 eta: 1:42:05 time: 0.347393 data_time: 0.063690 memory: 5151 loss_kpt: 0.000663 acc_pose: 0.847667 loss: 0.000663 2022/09/17 17:29:35 - mmengine - INFO - Epoch(train) [140][250/293] lr: 5.000000e-04 eta: 1:41:51 time: 0.345296 data_time: 0.069132 memory: 5151 loss_kpt: 0.000691 acc_pose: 0.818157 loss: 0.000691 2022/09/17 17:29:43 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:29:50 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:29:50 - mmengine - INFO - Saving checkpoint at 140 epochs 2022/09/17 17:29:58 - mmengine - INFO - Epoch(val) [140][50/407] eta: 0:00:42 time: 0.120103 data_time: 0.051786 memory: 5151 2022/09/17 17:30:04 - mmengine - INFO - Epoch(val) [140][100/407] eta: 0:00:37 time: 0.121679 data_time: 0.050289 memory: 331 2022/09/17 17:30:10 - mmengine - INFO - Epoch(val) [140][150/407] eta: 0:00:29 time: 0.116502 data_time: 0.047688 memory: 331 2022/09/17 17:30:16 - mmengine - INFO - Epoch(val) [140][200/407] eta: 0:00:23 time: 0.115523 data_time: 0.049790 memory: 331 2022/09/17 17:30:22 - mmengine - INFO - Epoch(val) [140][250/407] eta: 0:00:20 time: 0.127806 data_time: 0.060421 memory: 331 2022/09/17 17:30:28 - mmengine - INFO - Epoch(val) [140][300/407] eta: 0:00:12 time: 0.115111 data_time: 0.048033 memory: 331 2022/09/17 17:30:34 - mmengine - INFO - Epoch(val) [140][350/407] eta: 0:00:06 time: 0.116412 data_time: 0.047084 memory: 331 2022/09/17 17:30:39 - mmengine - INFO - Epoch(val) [140][400/407] eta: 0:00:00 time: 0.108360 data_time: 0.041908 memory: 331 2022/09/17 17:31:16 - mmengine - INFO - Evaluating CocoMetric... 2022/09/17 17:31:30 - mmengine - INFO - Epoch(val) [140][407/407] coco/AP: 0.691828 coco/AP .5: 0.883682 coco/AP .75: 0.770974 coco/AP (M): 0.659922 coco/AP (L): 0.756336 coco/AR: 0.751448 coco/AR .5: 0.926637 coco/AR .75: 0.820844 coco/AR (M): 0.710298 coco/AR (L): 0.810888 2022/09/17 17:31:30 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220917/vipnas_res50/best_coco/AP_epoch_130.pth is removed 2022/09/17 17:31:32 - mmengine - INFO - The best checkpoint with 0.6918 coco/AP at 140 epoch is saved to best_coco/AP_epoch_140.pth. 2022/09/17 17:31:49 - mmengine - INFO - Epoch(train) [141][50/293] lr: 5.000000e-04 eta: 1:41:19 time: 0.349687 data_time: 0.086690 memory: 5151 loss_kpt: 0.000687 acc_pose: 0.834857 loss: 0.000687 2022/09/17 17:32:07 - mmengine - INFO - Epoch(train) [141][100/293] lr: 5.000000e-04 eta: 1:41:05 time: 0.346394 data_time: 0.067898 memory: 5151 loss_kpt: 0.000685 acc_pose: 0.859354 loss: 0.000685 2022/09/17 17:32:24 - mmengine - INFO - Epoch(train) [141][150/293] lr: 5.000000e-04 eta: 1:40:51 time: 0.340825 data_time: 0.069103 memory: 5151 loss_kpt: 0.000674 acc_pose: 0.838304 loss: 0.000674 2022/09/17 17:32:41 - mmengine - INFO - Epoch(train) [141][200/293] lr: 5.000000e-04 eta: 1:40:38 time: 0.349190 data_time: 0.074986 memory: 5151 loss_kpt: 0.000688 acc_pose: 0.818150 loss: 0.000688 2022/09/17 17:32:59 - mmengine - INFO - Epoch(train) [141][250/293] lr: 5.000000e-04 eta: 1:40:24 time: 0.349438 data_time: 0.074480 memory: 5151 loss_kpt: 0.000688 acc_pose: 0.860393 loss: 0.000688 2022/09/17 17:33:13 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:33:13 - mmengine - INFO - Saving checkpoint at 141 epochs 2022/09/17 17:33:33 - mmengine - INFO - Epoch(train) [142][50/293] lr: 5.000000e-04 eta: 1:39:51 time: 0.346962 data_time: 0.079269 memory: 5151 loss_kpt: 0.000693 acc_pose: 0.807161 loss: 0.000693 2022/09/17 17:33:50 - mmengine - INFO - Epoch(train) [142][100/293] lr: 5.000000e-04 eta: 1:39:38 time: 0.347824 data_time: 0.069013 memory: 5151 loss_kpt: 0.000685 acc_pose: 0.785127 loss: 0.000685 2022/09/17 17:34:07 - mmengine - INFO - Epoch(train) [142][150/293] lr: 5.000000e-04 eta: 1:39:24 time: 0.329113 data_time: 0.066870 memory: 5151 loss_kpt: 0.000685 acc_pose: 0.851632 loss: 0.000685 2022/09/17 17:34:23 - mmengine - INFO - Epoch(train) [142][200/293] lr: 5.000000e-04 eta: 1:39:10 time: 0.331377 data_time: 0.063496 memory: 5151 loss_kpt: 0.000682 acc_pose: 0.820636 loss: 0.000682 2022/09/17 17:34:41 - mmengine - INFO - Epoch(train) [142][250/293] lr: 5.000000e-04 eta: 1:38:56 time: 0.346334 data_time: 0.069598 memory: 5151 loss_kpt: 0.000691 acc_pose: 0.796992 loss: 0.000691 2022/09/17 17:34:55 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:34:55 - mmengine - INFO - Saving checkpoint at 142 epochs 2022/09/17 17:35:15 - mmengine - INFO - Epoch(train) [143][50/293] lr: 5.000000e-04 eta: 1:38:24 time: 0.354708 data_time: 0.081589 memory: 5151 loss_kpt: 0.000678 acc_pose: 0.820828 loss: 0.000678 2022/09/17 17:35:33 - mmengine - INFO - Epoch(train) [143][100/293] lr: 5.000000e-04 eta: 1:38:10 time: 0.348688 data_time: 0.074896 memory: 5151 loss_kpt: 0.000689 acc_pose: 0.840310 loss: 0.000689 2022/09/17 17:35:50 - mmengine - INFO - Epoch(train) [143][150/293] lr: 5.000000e-04 eta: 1:37:56 time: 0.351917 data_time: 0.084060 memory: 5151 loss_kpt: 0.000678 acc_pose: 0.840230 loss: 0.000678 2022/09/17 17:36:07 - mmengine - INFO - Epoch(train) [143][200/293] lr: 5.000000e-04 eta: 1:37:43 time: 0.337798 data_time: 0.069315 memory: 5151 loss_kpt: 0.000695 acc_pose: 0.849953 loss: 0.000695 2022/09/17 17:36:25 - mmengine - INFO - Epoch(train) [143][250/293] lr: 5.000000e-04 eta: 1:37:29 time: 0.344213 data_time: 0.075026 memory: 5151 loss_kpt: 0.000680 acc_pose: 0.848662 loss: 0.000680 2022/09/17 17:36:39 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:36:39 - mmengine - INFO - Saving checkpoint at 143 epochs 2022/09/17 17:36:59 - mmengine - INFO - Epoch(train) [144][50/293] lr: 5.000000e-04 eta: 1:36:56 time: 0.346991 data_time: 0.074454 memory: 5151 loss_kpt: 0.000683 acc_pose: 0.846992 loss: 0.000683 2022/09/17 17:37:16 - mmengine - INFO - Epoch(train) [144][100/293] lr: 5.000000e-04 eta: 1:36:43 time: 0.341720 data_time: 0.074472 memory: 5151 loss_kpt: 0.000673 acc_pose: 0.841093 loss: 0.000673 2022/09/17 17:37:16 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:37:33 - mmengine - INFO - Epoch(train) [144][150/293] lr: 5.000000e-04 eta: 1:36:29 time: 0.341810 data_time: 0.074919 memory: 5151 loss_kpt: 0.000686 acc_pose: 0.816337 loss: 0.000686 2022/09/17 17:37:49 - mmengine - INFO - Epoch(train) [144][200/293] lr: 5.000000e-04 eta: 1:36:15 time: 0.329733 data_time: 0.068980 memory: 5151 loss_kpt: 0.000693 acc_pose: 0.851436 loss: 0.000693 2022/09/17 17:38:07 - mmengine - INFO - Epoch(train) [144][250/293] lr: 5.000000e-04 eta: 1:36:01 time: 0.349941 data_time: 0.070147 memory: 5151 loss_kpt: 0.000695 acc_pose: 0.834148 loss: 0.000695 2022/09/17 17:38:21 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:38:21 - mmengine - INFO - Saving checkpoint at 144 epochs 2022/09/17 17:38:42 - mmengine - INFO - Epoch(train) [145][50/293] lr: 5.000000e-04 eta: 1:35:29 time: 0.356167 data_time: 0.088092 memory: 5151 loss_kpt: 0.000674 acc_pose: 0.835903 loss: 0.000674 2022/09/17 17:38:59 - mmengine - INFO - Epoch(train) [145][100/293] lr: 5.000000e-04 eta: 1:35:15 time: 0.348288 data_time: 0.069021 memory: 5151 loss_kpt: 0.000677 acc_pose: 0.836579 loss: 0.000677 2022/09/17 17:39:16 - mmengine - INFO - Epoch(train) [145][150/293] lr: 5.000000e-04 eta: 1:35:01 time: 0.340987 data_time: 0.071677 memory: 5151 loss_kpt: 0.000681 acc_pose: 0.813315 loss: 0.000681 2022/09/17 17:39:34 - mmengine - INFO - Epoch(train) [145][200/293] lr: 5.000000e-04 eta: 1:34:48 time: 0.353381 data_time: 0.072233 memory: 5151 loss_kpt: 0.000674 acc_pose: 0.819608 loss: 0.000674 2022/09/17 17:39:50 - mmengine - INFO - Epoch(train) [145][250/293] lr: 5.000000e-04 eta: 1:34:34 time: 0.328761 data_time: 0.064789 memory: 5151 loss_kpt: 0.000689 acc_pose: 0.816494 loss: 0.000689 2022/09/17 17:40:05 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:40:05 - mmengine - INFO - Saving checkpoint at 145 epochs 2022/09/17 17:40:25 - mmengine - INFO - Epoch(train) [146][50/293] lr: 5.000000e-04 eta: 1:34:01 time: 0.348076 data_time: 0.082780 memory: 5151 loss_kpt: 0.000668 acc_pose: 0.796767 loss: 0.000668 2022/09/17 17:40:43 - mmengine - INFO - Epoch(train) [146][100/293] lr: 5.000000e-04 eta: 1:33:48 time: 0.348062 data_time: 0.069051 memory: 5151 loss_kpt: 0.000679 acc_pose: 0.862073 loss: 0.000679 2022/09/17 17:40:59 - mmengine - INFO - Epoch(train) [146][150/293] lr: 5.000000e-04 eta: 1:33:34 time: 0.337039 data_time: 0.067542 memory: 5151 loss_kpt: 0.000684 acc_pose: 0.835749 loss: 0.000684 2022/09/17 17:41:16 - mmengine - INFO - Epoch(train) [146][200/293] lr: 5.000000e-04 eta: 1:33:20 time: 0.337969 data_time: 0.064070 memory: 5151 loss_kpt: 0.000686 acc_pose: 0.821600 loss: 0.000686 2022/09/17 17:41:34 - mmengine - INFO - Epoch(train) [146][250/293] lr: 5.000000e-04 eta: 1:33:06 time: 0.350908 data_time: 0.067955 memory: 5151 loss_kpt: 0.000690 acc_pose: 0.830508 loss: 0.000690 2022/09/17 17:41:49 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:41:49 - mmengine - INFO - Saving checkpoint at 146 epochs 2022/09/17 17:42:09 - mmengine - INFO - Epoch(train) [147][50/293] lr: 5.000000e-04 eta: 1:32:34 time: 0.349271 data_time: 0.078189 memory: 5151 loss_kpt: 0.000674 acc_pose: 0.832237 loss: 0.000674 2022/09/17 17:42:26 - mmengine - INFO - Epoch(train) [147][100/293] lr: 5.000000e-04 eta: 1:32:20 time: 0.340965 data_time: 0.079313 memory: 5151 loss_kpt: 0.000684 acc_pose: 0.786095 loss: 0.000684 2022/09/17 17:42:44 - mmengine - INFO - Epoch(train) [147][150/293] lr: 5.000000e-04 eta: 1:32:06 time: 0.351487 data_time: 0.072512 memory: 5151 loss_kpt: 0.000673 acc_pose: 0.865112 loss: 0.000673 2022/09/17 17:43:01 - mmengine - INFO - Epoch(train) [147][200/293] lr: 5.000000e-04 eta: 1:31:52 time: 0.337277 data_time: 0.072883 memory: 5151 loss_kpt: 0.000682 acc_pose: 0.798166 loss: 0.000682 2022/09/17 17:43:08 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:43:18 - mmengine - INFO - Epoch(train) [147][250/293] lr: 5.000000e-04 eta: 1:31:38 time: 0.335459 data_time: 0.071637 memory: 5151 loss_kpt: 0.000678 acc_pose: 0.815186 loss: 0.000678 2022/09/17 17:43:33 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:43:33 - mmengine - INFO - Saving checkpoint at 147 epochs 2022/09/17 17:43:53 - mmengine - INFO - Epoch(train) [148][50/293] lr: 5.000000e-04 eta: 1:31:07 time: 0.364849 data_time: 0.083999 memory: 5151 loss_kpt: 0.000674 acc_pose: 0.850305 loss: 0.000674 2022/09/17 17:44:10 - mmengine - INFO - Epoch(train) [148][100/293] lr: 5.000000e-04 eta: 1:30:53 time: 0.340261 data_time: 0.075239 memory: 5151 loss_kpt: 0.000674 acc_pose: 0.864913 loss: 0.000674 2022/09/17 17:44:28 - mmengine - INFO - Epoch(train) [148][150/293] lr: 5.000000e-04 eta: 1:30:39 time: 0.343355 data_time: 0.076272 memory: 5151 loss_kpt: 0.000684 acc_pose: 0.846012 loss: 0.000684 2022/09/17 17:44:45 - mmengine - INFO - Epoch(train) [148][200/293] lr: 5.000000e-04 eta: 1:30:25 time: 0.350099 data_time: 0.072380 memory: 5151 loss_kpt: 0.000666 acc_pose: 0.844114 loss: 0.000666 2022/09/17 17:45:02 - mmengine - INFO - Epoch(train) [148][250/293] lr: 5.000000e-04 eta: 1:30:11 time: 0.341935 data_time: 0.074497 memory: 5151 loss_kpt: 0.000685 acc_pose: 0.831662 loss: 0.000685 2022/09/17 17:45:16 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:45:16 - mmengine - INFO - Saving checkpoint at 148 epochs 2022/09/17 17:45:37 - mmengine - INFO - Epoch(train) [149][50/293] lr: 5.000000e-04 eta: 1:29:39 time: 0.353650 data_time: 0.081636 memory: 5151 loss_kpt: 0.000686 acc_pose: 0.802462 loss: 0.000686 2022/09/17 17:45:54 - mmengine - INFO - Epoch(train) [149][100/293] lr: 5.000000e-04 eta: 1:29:26 time: 0.349507 data_time: 0.073583 memory: 5151 loss_kpt: 0.000680 acc_pose: 0.867205 loss: 0.000680 2022/09/17 17:46:11 - mmengine - INFO - Epoch(train) [149][150/293] lr: 5.000000e-04 eta: 1:29:12 time: 0.339663 data_time: 0.073070 memory: 5151 loss_kpt: 0.000663 acc_pose: 0.846762 loss: 0.000663 2022/09/17 17:46:28 - mmengine - INFO - Epoch(train) [149][200/293] lr: 5.000000e-04 eta: 1:28:58 time: 0.334394 data_time: 0.067104 memory: 5151 loss_kpt: 0.000674 acc_pose: 0.852045 loss: 0.000674 2022/09/17 17:46:45 - mmengine - INFO - Epoch(train) [149][250/293] lr: 5.000000e-04 eta: 1:28:44 time: 0.338012 data_time: 0.067488 memory: 5151 loss_kpt: 0.000683 acc_pose: 0.835501 loss: 0.000683 2022/09/17 17:46:59 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:46:59 - mmengine - INFO - Saving checkpoint at 149 epochs 2022/09/17 17:47:19 - mmengine - INFO - Epoch(train) [150][50/293] lr: 5.000000e-04 eta: 1:28:12 time: 0.345149 data_time: 0.078516 memory: 5151 loss_kpt: 0.000692 acc_pose: 0.815857 loss: 0.000692 2022/09/17 17:47:36 - mmengine - INFO - Epoch(train) [150][100/293] lr: 5.000000e-04 eta: 1:27:58 time: 0.338984 data_time: 0.069252 memory: 5151 loss_kpt: 0.000689 acc_pose: 0.859757 loss: 0.000689 2022/09/17 17:47:53 - mmengine - INFO - Epoch(train) [150][150/293] lr: 5.000000e-04 eta: 1:27:44 time: 0.335639 data_time: 0.067236 memory: 5151 loss_kpt: 0.000678 acc_pose: 0.847045 loss: 0.000678 2022/09/17 17:48:10 - mmengine - INFO - Epoch(train) [150][200/293] lr: 5.000000e-04 eta: 1:27:30 time: 0.350680 data_time: 0.071662 memory: 5151 loss_kpt: 0.000694 acc_pose: 0.828285 loss: 0.000694 2022/09/17 17:48:27 - mmengine - INFO - Epoch(train) [150][250/293] lr: 5.000000e-04 eta: 1:27:16 time: 0.339320 data_time: 0.065794 memory: 5151 loss_kpt: 0.000664 acc_pose: 0.801385 loss: 0.000664 2022/09/17 17:48:41 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:48:41 - mmengine - INFO - Saving checkpoint at 150 epochs 2022/09/17 17:48:50 - mmengine - INFO - Epoch(val) [150][50/407] eta: 0:00:43 time: 0.121148 data_time: 0.052769 memory: 5151 2022/09/17 17:48:56 - mmengine - INFO - Epoch(val) [150][100/407] eta: 0:00:35 time: 0.115750 data_time: 0.047361 memory: 331 2022/09/17 17:49:02 - mmengine - INFO - Epoch(val) [150][150/407] eta: 0:00:30 time: 0.117984 data_time: 0.050284 memory: 331 2022/09/17 17:49:08 - mmengine - INFO - Epoch(val) [150][200/407] eta: 0:00:24 time: 0.116437 data_time: 0.045444 memory: 331 2022/09/17 17:49:14 - mmengine - INFO - Epoch(val) [150][250/407] eta: 0:00:18 time: 0.119435 data_time: 0.050754 memory: 331 2022/09/17 17:49:19 - mmengine - INFO - Epoch(val) [150][300/407] eta: 0:00:12 time: 0.114782 data_time: 0.046890 memory: 331 2022/09/17 17:49:25 - mmengine - INFO - Epoch(val) [150][350/407] eta: 0:00:07 time: 0.122959 data_time: 0.055754 memory: 331 2022/09/17 17:49:31 - mmengine - INFO - Epoch(val) [150][400/407] eta: 0:00:00 time: 0.106954 data_time: 0.039460 memory: 331 2022/09/17 17:50:08 - mmengine - INFO - Evaluating CocoMetric... 2022/09/17 17:50:22 - mmengine - INFO - Epoch(val) [150][407/407] coco/AP: 0.694877 coco/AP .5: 0.886643 coco/AP .75: 0.773040 coco/AP (M): 0.662415 coco/AP (L): 0.759864 coco/AR: 0.754581 coco/AR .5: 0.929156 coco/AR .75: 0.823363 coco/AR (M): 0.712456 coco/AR (L): 0.815831 2022/09/17 17:50:22 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220917/vipnas_res50/best_coco/AP_epoch_140.pth is removed 2022/09/17 17:50:24 - mmengine - INFO - The best checkpoint with 0.6949 coco/AP at 150 epoch is saved to best_coco/AP_epoch_150.pth. 2022/09/17 17:50:43 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:50:43 - mmengine - INFO - Epoch(train) [151][50/293] lr: 5.000000e-04 eta: 1:26:45 time: 0.366377 data_time: 0.083361 memory: 5151 loss_kpt: 0.000680 acc_pose: 0.843919 loss: 0.000680 2022/09/17 17:51:00 - mmengine - INFO - Epoch(train) [151][100/293] lr: 5.000000e-04 eta: 1:26:31 time: 0.345063 data_time: 0.074377 memory: 5151 loss_kpt: 0.000687 acc_pose: 0.848745 loss: 0.000687 2022/09/17 17:51:17 - mmengine - INFO - Epoch(train) [151][150/293] lr: 5.000000e-04 eta: 1:26:17 time: 0.346361 data_time: 0.075343 memory: 5151 loss_kpt: 0.000671 acc_pose: 0.815821 loss: 0.000671 2022/09/17 17:51:34 - mmengine - INFO - Epoch(train) [151][200/293] lr: 5.000000e-04 eta: 1:26:03 time: 0.338278 data_time: 0.065149 memory: 5151 loss_kpt: 0.000677 acc_pose: 0.838127 loss: 0.000677 2022/09/17 17:51:51 - mmengine - INFO - Epoch(train) [151][250/293] lr: 5.000000e-04 eta: 1:25:49 time: 0.337503 data_time: 0.067871 memory: 5151 loss_kpt: 0.000672 acc_pose: 0.869277 loss: 0.000672 2022/09/17 17:52:06 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:52:06 - mmengine - INFO - Saving checkpoint at 151 epochs 2022/09/17 17:52:26 - mmengine - INFO - Epoch(train) [152][50/293] lr: 5.000000e-04 eta: 1:25:17 time: 0.349062 data_time: 0.085476 memory: 5151 loss_kpt: 0.000677 acc_pose: 0.827611 loss: 0.000677 2022/09/17 17:52:43 - mmengine - INFO - Epoch(train) [152][100/293] lr: 5.000000e-04 eta: 1:25:03 time: 0.344730 data_time: 0.065638 memory: 5151 loss_kpt: 0.000681 acc_pose: 0.849457 loss: 0.000681 2022/09/17 17:53:00 - mmengine - INFO - Epoch(train) [152][150/293] lr: 5.000000e-04 eta: 1:24:49 time: 0.338954 data_time: 0.067268 memory: 5151 loss_kpt: 0.000691 acc_pose: 0.751156 loss: 0.000691 2022/09/17 17:53:17 - mmengine - INFO - Epoch(train) [152][200/293] lr: 5.000000e-04 eta: 1:24:35 time: 0.338189 data_time: 0.070723 memory: 5151 loss_kpt: 0.000697 acc_pose: 0.821929 loss: 0.000697 2022/09/17 17:53:34 - mmengine - INFO - Epoch(train) [152][250/293] lr: 5.000000e-04 eta: 1:24:21 time: 0.345585 data_time: 0.080951 memory: 5151 loss_kpt: 0.000669 acc_pose: 0.856088 loss: 0.000669 2022/09/17 17:53:49 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:53:49 - mmengine - INFO - Saving checkpoint at 152 epochs 2022/09/17 17:54:09 - mmengine - INFO - Epoch(train) [153][50/293] lr: 5.000000e-04 eta: 1:23:50 time: 0.347570 data_time: 0.079928 memory: 5151 loss_kpt: 0.000671 acc_pose: 0.827207 loss: 0.000671 2022/09/17 17:54:26 - mmengine - INFO - Epoch(train) [153][100/293] lr: 5.000000e-04 eta: 1:23:36 time: 0.343934 data_time: 0.064258 memory: 5151 loss_kpt: 0.000688 acc_pose: 0.815378 loss: 0.000688 2022/09/17 17:54:43 - mmengine - INFO - Epoch(train) [153][150/293] lr: 5.000000e-04 eta: 1:23:22 time: 0.337384 data_time: 0.081727 memory: 5151 loss_kpt: 0.000680 acc_pose: 0.872080 loss: 0.000680 2022/09/17 17:55:00 - mmengine - INFO - Epoch(train) [153][200/293] lr: 5.000000e-04 eta: 1:23:08 time: 0.345525 data_time: 0.069237 memory: 5151 loss_kpt: 0.000677 acc_pose: 0.794695 loss: 0.000677 2022/09/17 17:55:17 - mmengine - INFO - Epoch(train) [153][250/293] lr: 5.000000e-04 eta: 1:22:54 time: 0.336789 data_time: 0.074334 memory: 5151 loss_kpt: 0.000667 acc_pose: 0.815005 loss: 0.000667 2022/09/17 17:55:32 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:55:32 - mmengine - INFO - Saving checkpoint at 153 epochs 2022/09/17 17:55:53 - mmengine - INFO - Epoch(train) [154][50/293] lr: 5.000000e-04 eta: 1:22:22 time: 0.358232 data_time: 0.079980 memory: 5151 loss_kpt: 0.000665 acc_pose: 0.839348 loss: 0.000665 2022/09/17 17:56:10 - mmengine - INFO - Epoch(train) [154][100/293] lr: 5.000000e-04 eta: 1:22:08 time: 0.343121 data_time: 0.072735 memory: 5151 loss_kpt: 0.000671 acc_pose: 0.868137 loss: 0.000671 2022/09/17 17:56:27 - mmengine - INFO - Epoch(train) [154][150/293] lr: 5.000000e-04 eta: 1:21:54 time: 0.339075 data_time: 0.069028 memory: 5151 loss_kpt: 0.000671 acc_pose: 0.880612 loss: 0.000671 2022/09/17 17:56:34 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:56:44 - mmengine - INFO - Epoch(train) [154][200/293] lr: 5.000000e-04 eta: 1:21:40 time: 0.339769 data_time: 0.067436 memory: 5151 loss_kpt: 0.000693 acc_pose: 0.833479 loss: 0.000693 2022/09/17 17:57:01 - mmengine - INFO - Epoch(train) [154][250/293] lr: 5.000000e-04 eta: 1:21:26 time: 0.348004 data_time: 0.071959 memory: 5151 loss_kpt: 0.000673 acc_pose: 0.826405 loss: 0.000673 2022/09/17 17:57:15 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:57:15 - mmengine - INFO - Saving checkpoint at 154 epochs 2022/09/17 17:57:35 - mmengine - INFO - Epoch(train) [155][50/293] lr: 5.000000e-04 eta: 1:20:55 time: 0.344010 data_time: 0.076939 memory: 5151 loss_kpt: 0.000663 acc_pose: 0.803757 loss: 0.000663 2022/09/17 17:57:53 - mmengine - INFO - Epoch(train) [155][100/293] lr: 5.000000e-04 eta: 1:20:41 time: 0.350266 data_time: 0.072568 memory: 5151 loss_kpt: 0.000677 acc_pose: 0.803402 loss: 0.000677 2022/09/17 17:58:10 - mmengine - INFO - Epoch(train) [155][150/293] lr: 5.000000e-04 eta: 1:20:27 time: 0.340879 data_time: 0.066491 memory: 5151 loss_kpt: 0.000680 acc_pose: 0.841920 loss: 0.000680 2022/09/17 17:58:26 - mmengine - INFO - Epoch(train) [155][200/293] lr: 5.000000e-04 eta: 1:20:13 time: 0.330198 data_time: 0.068166 memory: 5151 loss_kpt: 0.000660 acc_pose: 0.853776 loss: 0.000660 2022/09/17 17:58:44 - mmengine - INFO - Epoch(train) [155][250/293] lr: 5.000000e-04 eta: 1:19:59 time: 0.344819 data_time: 0.083859 memory: 5151 loss_kpt: 0.000691 acc_pose: 0.852215 loss: 0.000691 2022/09/17 17:58:58 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 17:58:58 - mmengine - INFO - Saving checkpoint at 155 epochs 2022/09/17 17:59:19 - mmengine - INFO - Epoch(train) [156][50/293] lr: 5.000000e-04 eta: 1:19:28 time: 0.360413 data_time: 0.092673 memory: 5151 loss_kpt: 0.000668 acc_pose: 0.851507 loss: 0.000668 2022/09/17 17:59:35 - mmengine - INFO - Epoch(train) [156][100/293] lr: 5.000000e-04 eta: 1:19:13 time: 0.327659 data_time: 0.064325 memory: 5151 loss_kpt: 0.000673 acc_pose: 0.822751 loss: 0.000673 2022/09/17 17:59:52 - mmengine - INFO - Epoch(train) [156][150/293] lr: 5.000000e-04 eta: 1:18:59 time: 0.348791 data_time: 0.071510 memory: 5151 loss_kpt: 0.000678 acc_pose: 0.835631 loss: 0.000678 2022/09/17 18:00:13 - mmengine - INFO - Epoch(train) [156][200/293] lr: 5.000000e-04 eta: 1:18:47 time: 0.416483 data_time: 0.072126 memory: 5151 loss_kpt: 0.000673 acc_pose: 0.857620 loss: 0.000673 2022/09/17 18:00:31 - mmengine - INFO - Epoch(train) [156][250/293] lr: 5.000000e-04 eta: 1:18:33 time: 0.344302 data_time: 0.073494 memory: 5151 loss_kpt: 0.000681 acc_pose: 0.851363 loss: 0.000681 2022/09/17 18:00:45 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:00:45 - mmengine - INFO - Saving checkpoint at 156 epochs 2022/09/17 18:01:05 - mmengine - INFO - Epoch(train) [157][50/293] lr: 5.000000e-04 eta: 1:18:01 time: 0.344432 data_time: 0.075304 memory: 5151 loss_kpt: 0.000663 acc_pose: 0.880712 loss: 0.000663 2022/09/17 18:01:22 - mmengine - INFO - Epoch(train) [157][100/293] lr: 5.000000e-04 eta: 1:17:47 time: 0.336423 data_time: 0.074172 memory: 5151 loss_kpt: 0.000671 acc_pose: 0.802477 loss: 0.000671 2022/09/17 18:01:39 - mmengine - INFO - Epoch(train) [157][150/293] lr: 5.000000e-04 eta: 1:17:33 time: 0.332413 data_time: 0.067449 memory: 5151 loss_kpt: 0.000668 acc_pose: 0.812564 loss: 0.000668 2022/09/17 18:01:56 - mmengine - INFO - Epoch(train) [157][200/293] lr: 5.000000e-04 eta: 1:17:19 time: 0.342164 data_time: 0.069391 memory: 5151 loss_kpt: 0.000668 acc_pose: 0.812090 loss: 0.000668 2022/09/17 18:02:13 - mmengine - INFO - Epoch(train) [157][250/293] lr: 5.000000e-04 eta: 1:17:05 time: 0.350182 data_time: 0.072288 memory: 5151 loss_kpt: 0.000681 acc_pose: 0.809785 loss: 0.000681 2022/09/17 18:02:27 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:02:28 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:02:28 - mmengine - INFO - Saving checkpoint at 157 epochs 2022/09/17 18:02:47 - mmengine - INFO - Epoch(train) [158][50/293] lr: 5.000000e-04 eta: 1:16:34 time: 0.350986 data_time: 0.082741 memory: 5151 loss_kpt: 0.000669 acc_pose: 0.784726 loss: 0.000669 2022/09/17 18:03:05 - mmengine - INFO - Epoch(train) [158][100/293] lr: 5.000000e-04 eta: 1:16:20 time: 0.346247 data_time: 0.069548 memory: 5151 loss_kpt: 0.000670 acc_pose: 0.836562 loss: 0.000670 2022/09/17 18:03:21 - mmengine - INFO - Epoch(train) [158][150/293] lr: 5.000000e-04 eta: 1:16:06 time: 0.329099 data_time: 0.069847 memory: 5151 loss_kpt: 0.000658 acc_pose: 0.810940 loss: 0.000658 2022/09/17 18:03:38 - mmengine - INFO - Epoch(train) [158][200/293] lr: 5.000000e-04 eta: 1:15:52 time: 0.341769 data_time: 0.072546 memory: 5151 loss_kpt: 0.000656 acc_pose: 0.864640 loss: 0.000656 2022/09/17 18:03:55 - mmengine - INFO - Epoch(train) [158][250/293] lr: 5.000000e-04 eta: 1:15:37 time: 0.335069 data_time: 0.071114 memory: 5151 loss_kpt: 0.000682 acc_pose: 0.857316 loss: 0.000682 2022/09/17 18:04:10 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:04:10 - mmengine - INFO - Saving checkpoint at 158 epochs 2022/09/17 18:04:30 - mmengine - INFO - Epoch(train) [159][50/293] lr: 5.000000e-04 eta: 1:15:06 time: 0.343351 data_time: 0.076211 memory: 5151 loss_kpt: 0.000663 acc_pose: 0.829219 loss: 0.000663 2022/09/17 18:04:46 - mmengine - INFO - Epoch(train) [159][100/293] lr: 5.000000e-04 eta: 1:14:52 time: 0.334705 data_time: 0.077726 memory: 5151 loss_kpt: 0.000674 acc_pose: 0.849947 loss: 0.000674 2022/09/17 18:05:03 - mmengine - INFO - Epoch(train) [159][150/293] lr: 5.000000e-04 eta: 1:14:38 time: 0.340624 data_time: 0.073170 memory: 5151 loss_kpt: 0.000674 acc_pose: 0.867863 loss: 0.000674 2022/09/17 18:05:21 - mmengine - INFO - Epoch(train) [159][200/293] lr: 5.000000e-04 eta: 1:14:24 time: 0.344795 data_time: 0.075595 memory: 5151 loss_kpt: 0.000673 acc_pose: 0.855701 loss: 0.000673 2022/09/17 18:05:38 - mmengine - INFO - Epoch(train) [159][250/293] lr: 5.000000e-04 eta: 1:14:10 time: 0.337541 data_time: 0.074514 memory: 5151 loss_kpt: 0.000690 acc_pose: 0.830710 loss: 0.000690 2022/09/17 18:05:52 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:05:52 - mmengine - INFO - Saving checkpoint at 159 epochs 2022/09/17 18:06:13 - mmengine - INFO - Epoch(train) [160][50/293] lr: 5.000000e-04 eta: 1:13:39 time: 0.356521 data_time: 0.076662 memory: 5151 loss_kpt: 0.000673 acc_pose: 0.809394 loss: 0.000673 2022/09/17 18:06:30 - mmengine - INFO - Epoch(train) [160][100/293] lr: 5.000000e-04 eta: 1:13:25 time: 0.340292 data_time: 0.071802 memory: 5151 loss_kpt: 0.000674 acc_pose: 0.827580 loss: 0.000674 2022/09/17 18:06:47 - mmengine - INFO - Epoch(train) [160][150/293] lr: 5.000000e-04 eta: 1:13:11 time: 0.340895 data_time: 0.076542 memory: 5151 loss_kpt: 0.000669 acc_pose: 0.825129 loss: 0.000669 2022/09/17 18:07:03 - mmengine - INFO - Epoch(train) [160][200/293] lr: 5.000000e-04 eta: 1:12:56 time: 0.335880 data_time: 0.072192 memory: 5151 loss_kpt: 0.000668 acc_pose: 0.857701 loss: 0.000668 2022/09/17 18:07:21 - mmengine - INFO - Epoch(train) [160][250/293] lr: 5.000000e-04 eta: 1:12:42 time: 0.341325 data_time: 0.081355 memory: 5151 loss_kpt: 0.000688 acc_pose: 0.853912 loss: 0.000688 2022/09/17 18:07:35 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:07:35 - mmengine - INFO - Saving checkpoint at 160 epochs 2022/09/17 18:07:44 - mmengine - INFO - Epoch(val) [160][50/407] eta: 0:00:44 time: 0.125521 data_time: 0.055878 memory: 5151 2022/09/17 18:07:50 - mmengine - INFO - Epoch(val) [160][100/407] eta: 0:00:35 time: 0.115828 data_time: 0.048406 memory: 331 2022/09/17 18:07:56 - mmengine - INFO - Epoch(val) [160][150/407] eta: 0:00:31 time: 0.124448 data_time: 0.056375 memory: 331 2022/09/17 18:08:01 - mmengine - INFO - Epoch(val) [160][200/407] eta: 0:00:23 time: 0.112674 data_time: 0.043788 memory: 331 2022/09/17 18:08:07 - mmengine - INFO - Epoch(val) [160][250/407] eta: 0:00:18 time: 0.116267 data_time: 0.048038 memory: 331 2022/09/17 18:08:13 - mmengine - INFO - Epoch(val) [160][300/407] eta: 0:00:13 time: 0.121772 data_time: 0.053629 memory: 331 2022/09/17 18:08:19 - mmengine - INFO - Epoch(val) [160][350/407] eta: 0:00:06 time: 0.118179 data_time: 0.049879 memory: 331 2022/09/17 18:08:25 - mmengine - INFO - Epoch(val) [160][400/407] eta: 0:00:00 time: 0.115321 data_time: 0.049440 memory: 331 2022/09/17 18:09:01 - mmengine - INFO - Evaluating CocoMetric... 2022/09/17 18:09:15 - mmengine - INFO - Epoch(val) [160][407/407] coco/AP: 0.694717 coco/AP .5: 0.884123 coco/AP .75: 0.774261 coco/AP (M): 0.661936 coco/AP (L): 0.761535 coco/AR: 0.754125 coco/AR .5: 0.927582 coco/AR .75: 0.825252 coco/AR (M): 0.710680 coco/AR (L): 0.817094 2022/09/17 18:09:32 - mmengine - INFO - Epoch(train) [161][50/293] lr: 5.000000e-04 eta: 1:12:12 time: 0.352751 data_time: 0.080250 memory: 5151 loss_kpt: 0.000670 acc_pose: 0.841148 loss: 0.000670 2022/09/17 18:09:49 - mmengine - INFO - Epoch(train) [161][100/293] lr: 5.000000e-04 eta: 1:11:57 time: 0.333114 data_time: 0.069175 memory: 5151 loss_kpt: 0.000670 acc_pose: 0.815022 loss: 0.000670 2022/09/17 18:09:56 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:10:06 - mmengine - INFO - Epoch(train) [161][150/293] lr: 5.000000e-04 eta: 1:11:43 time: 0.338528 data_time: 0.060810 memory: 5151 loss_kpt: 0.000671 acc_pose: 0.837718 loss: 0.000671 2022/09/17 18:10:23 - mmengine - INFO - Epoch(train) [161][200/293] lr: 5.000000e-04 eta: 1:11:29 time: 0.333660 data_time: 0.064412 memory: 5151 loss_kpt: 0.000662 acc_pose: 0.869945 loss: 0.000662 2022/09/17 18:10:40 - mmengine - INFO - Epoch(train) [161][250/293] lr: 5.000000e-04 eta: 1:11:15 time: 0.341305 data_time: 0.066690 memory: 5151 loss_kpt: 0.000688 acc_pose: 0.846256 loss: 0.000688 2022/09/17 18:10:54 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:10:54 - mmengine - INFO - Saving checkpoint at 161 epochs 2022/09/17 18:11:14 - mmengine - INFO - Epoch(train) [162][50/293] lr: 5.000000e-04 eta: 1:10:44 time: 0.349356 data_time: 0.077686 memory: 5151 loss_kpt: 0.000683 acc_pose: 0.824174 loss: 0.000683 2022/09/17 18:11:31 - mmengine - INFO - Epoch(train) [162][100/293] lr: 5.000000e-04 eta: 1:10:30 time: 0.336929 data_time: 0.068221 memory: 5151 loss_kpt: 0.000668 acc_pose: 0.831850 loss: 0.000668 2022/09/17 18:11:48 - mmengine - INFO - Epoch(train) [162][150/293] lr: 5.000000e-04 eta: 1:10:16 time: 0.349448 data_time: 0.074177 memory: 5151 loss_kpt: 0.000676 acc_pose: 0.809072 loss: 0.000676 2022/09/17 18:12:06 - mmengine - INFO - Epoch(train) [162][200/293] lr: 5.000000e-04 eta: 1:10:02 time: 0.346253 data_time: 0.076212 memory: 5151 loss_kpt: 0.000648 acc_pose: 0.893470 loss: 0.000648 2022/09/17 18:12:22 - mmengine - INFO - Epoch(train) [162][250/293] lr: 5.000000e-04 eta: 1:09:47 time: 0.330624 data_time: 0.068102 memory: 5151 loss_kpt: 0.000669 acc_pose: 0.796007 loss: 0.000669 2022/09/17 18:12:37 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:12:37 - mmengine - INFO - Saving checkpoint at 162 epochs 2022/09/17 18:12:57 - mmengine - INFO - Epoch(train) [163][50/293] lr: 5.000000e-04 eta: 1:09:17 time: 0.347854 data_time: 0.073707 memory: 5151 loss_kpt: 0.000680 acc_pose: 0.856534 loss: 0.000680 2022/09/17 18:13:14 - mmengine - INFO - Epoch(train) [163][100/293] lr: 5.000000e-04 eta: 1:09:02 time: 0.336218 data_time: 0.071104 memory: 5151 loss_kpt: 0.000660 acc_pose: 0.817295 loss: 0.000660 2022/09/17 18:13:30 - mmengine - INFO - Epoch(train) [163][150/293] lr: 5.000000e-04 eta: 1:08:48 time: 0.329884 data_time: 0.065768 memory: 5151 loss_kpt: 0.000653 acc_pose: 0.810871 loss: 0.000653 2022/09/17 18:13:47 - mmengine - INFO - Epoch(train) [163][200/293] lr: 5.000000e-04 eta: 1:08:34 time: 0.341134 data_time: 0.069179 memory: 5151 loss_kpt: 0.000666 acc_pose: 0.885194 loss: 0.000666 2022/09/17 18:14:05 - mmengine - INFO - Epoch(train) [163][250/293] lr: 5.000000e-04 eta: 1:08:20 time: 0.352407 data_time: 0.070494 memory: 5151 loss_kpt: 0.000669 acc_pose: 0.810857 loss: 0.000669 2022/09/17 18:14:20 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:14:20 - mmengine - INFO - Saving checkpoint at 163 epochs 2022/09/17 18:14:39 - mmengine - INFO - Epoch(train) [164][50/293] lr: 5.000000e-04 eta: 1:07:49 time: 0.343590 data_time: 0.081122 memory: 5151 loss_kpt: 0.000672 acc_pose: 0.798644 loss: 0.000672 2022/09/17 18:14:56 - mmengine - INFO - Epoch(train) [164][100/293] lr: 5.000000e-04 eta: 1:07:35 time: 0.336759 data_time: 0.075227 memory: 5151 loss_kpt: 0.000666 acc_pose: 0.834838 loss: 0.000666 2022/09/17 18:15:13 - mmengine - INFO - Epoch(train) [164][150/293] lr: 5.000000e-04 eta: 1:07:21 time: 0.341794 data_time: 0.070259 memory: 5151 loss_kpt: 0.000658 acc_pose: 0.806297 loss: 0.000658 2022/09/17 18:15:30 - mmengine - INFO - Epoch(train) [164][200/293] lr: 5.000000e-04 eta: 1:07:07 time: 0.339201 data_time: 0.071216 memory: 5151 loss_kpt: 0.000663 acc_pose: 0.820499 loss: 0.000663 2022/09/17 18:15:45 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:15:47 - mmengine - INFO - Epoch(train) [164][250/293] lr: 5.000000e-04 eta: 1:06:52 time: 0.342545 data_time: 0.070653 memory: 5151 loss_kpt: 0.000677 acc_pose: 0.813605 loss: 0.000677 2022/09/17 18:16:02 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:16:02 - mmengine - INFO - Saving checkpoint at 164 epochs 2022/09/17 18:16:23 - mmengine - INFO - Epoch(train) [165][50/293] lr: 5.000000e-04 eta: 1:06:22 time: 0.356437 data_time: 0.075359 memory: 5151 loss_kpt: 0.000665 acc_pose: 0.830658 loss: 0.000665 2022/09/17 18:16:40 - mmengine - INFO - Epoch(train) [165][100/293] lr: 5.000000e-04 eta: 1:06:08 time: 0.337032 data_time: 0.065923 memory: 5151 loss_kpt: 0.000677 acc_pose: 0.868500 loss: 0.000677 2022/09/17 18:16:57 - mmengine - INFO - Epoch(train) [165][150/293] lr: 5.000000e-04 eta: 1:05:54 time: 0.338478 data_time: 0.067388 memory: 5151 loss_kpt: 0.000672 acc_pose: 0.839580 loss: 0.000672 2022/09/17 18:17:14 - mmengine - INFO - Epoch(train) [165][200/293] lr: 5.000000e-04 eta: 1:05:39 time: 0.342241 data_time: 0.072765 memory: 5151 loss_kpt: 0.000671 acc_pose: 0.846086 loss: 0.000671 2022/09/17 18:17:31 - mmengine - INFO - Epoch(train) [165][250/293] lr: 5.000000e-04 eta: 1:05:25 time: 0.343321 data_time: 0.066442 memory: 5151 loss_kpt: 0.000682 acc_pose: 0.848775 loss: 0.000682 2022/09/17 18:17:45 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:17:45 - mmengine - INFO - Saving checkpoint at 165 epochs 2022/09/17 18:18:06 - mmengine - INFO - Epoch(train) [166][50/293] lr: 5.000000e-04 eta: 1:04:55 time: 0.351548 data_time: 0.069728 memory: 5151 loss_kpt: 0.000672 acc_pose: 0.841468 loss: 0.000672 2022/09/17 18:18:23 - mmengine - INFO - Epoch(train) [166][100/293] lr: 5.000000e-04 eta: 1:04:41 time: 0.346809 data_time: 0.070180 memory: 5151 loss_kpt: 0.000665 acc_pose: 0.828900 loss: 0.000665 2022/09/17 18:18:41 - mmengine - INFO - Epoch(train) [166][150/293] lr: 5.000000e-04 eta: 1:04:27 time: 0.348626 data_time: 0.073464 memory: 5151 loss_kpt: 0.000661 acc_pose: 0.771651 loss: 0.000661 2022/09/17 18:18:58 - mmengine - INFO - Epoch(train) [166][200/293] lr: 5.000000e-04 eta: 1:04:12 time: 0.347092 data_time: 0.071372 memory: 5151 loss_kpt: 0.000659 acc_pose: 0.833781 loss: 0.000659 2022/09/17 18:19:16 - mmengine - INFO - Epoch(train) [166][250/293] lr: 5.000000e-04 eta: 1:03:58 time: 0.352374 data_time: 0.079576 memory: 5151 loss_kpt: 0.000692 acc_pose: 0.865520 loss: 0.000692 2022/09/17 18:19:31 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:19:31 - mmengine - INFO - Saving checkpoint at 166 epochs 2022/09/17 18:19:51 - mmengine - INFO - Epoch(train) [167][50/293] lr: 5.000000e-04 eta: 1:03:28 time: 0.351568 data_time: 0.081617 memory: 5151 loss_kpt: 0.000659 acc_pose: 0.830091 loss: 0.000659 2022/09/17 18:20:08 - mmengine - INFO - Epoch(train) [167][100/293] lr: 5.000000e-04 eta: 1:03:14 time: 0.336776 data_time: 0.071303 memory: 5151 loss_kpt: 0.000665 acc_pose: 0.856159 loss: 0.000665 2022/09/17 18:20:25 - mmengine - INFO - Epoch(train) [167][150/293] lr: 5.000000e-04 eta: 1:02:59 time: 0.335352 data_time: 0.069255 memory: 5151 loss_kpt: 0.000680 acc_pose: 0.802628 loss: 0.000680 2022/09/17 18:20:41 - mmengine - INFO - Epoch(train) [167][200/293] lr: 5.000000e-04 eta: 1:02:45 time: 0.330512 data_time: 0.066719 memory: 5151 loss_kpt: 0.000668 acc_pose: 0.811214 loss: 0.000668 2022/09/17 18:20:58 - mmengine - INFO - Epoch(train) [167][250/293] lr: 5.000000e-04 eta: 1:02:31 time: 0.331093 data_time: 0.064975 memory: 5151 loss_kpt: 0.000685 acc_pose: 0.861027 loss: 0.000685 2022/09/17 18:21:12 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:21:12 - mmengine - INFO - Saving checkpoint at 167 epochs 2022/09/17 18:21:33 - mmengine - INFO - Epoch(train) [168][50/293] lr: 5.000000e-04 eta: 1:02:00 time: 0.347829 data_time: 0.077476 memory: 5151 loss_kpt: 0.000670 acc_pose: 0.804371 loss: 0.000670 2022/09/17 18:21:39 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:21:49 - mmengine - INFO - Epoch(train) [168][100/293] lr: 5.000000e-04 eta: 1:01:46 time: 0.330022 data_time: 0.067287 memory: 5151 loss_kpt: 0.000659 acc_pose: 0.849607 loss: 0.000659 2022/09/17 18:22:07 - mmengine - INFO - Epoch(train) [168][150/293] lr: 5.000000e-04 eta: 1:01:32 time: 0.350520 data_time: 0.080762 memory: 5151 loss_kpt: 0.000667 acc_pose: 0.859645 loss: 0.000667 2022/09/17 18:22:24 - mmengine - INFO - Epoch(train) [168][200/293] lr: 5.000000e-04 eta: 1:01:18 time: 0.344803 data_time: 0.074399 memory: 5151 loss_kpt: 0.000677 acc_pose: 0.853214 loss: 0.000677 2022/09/17 18:22:40 - mmengine - INFO - Epoch(train) [168][250/293] lr: 5.000000e-04 eta: 1:01:03 time: 0.332334 data_time: 0.065723 memory: 5151 loss_kpt: 0.000687 acc_pose: 0.782275 loss: 0.000687 2022/09/17 18:22:55 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:22:55 - mmengine - INFO - Saving checkpoint at 168 epochs 2022/09/17 18:23:15 - mmengine - INFO - Epoch(train) [169][50/293] lr: 5.000000e-04 eta: 1:00:33 time: 0.348804 data_time: 0.078599 memory: 5151 loss_kpt: 0.000674 acc_pose: 0.827344 loss: 0.000674 2022/09/17 18:23:32 - mmengine - INFO - Epoch(train) [169][100/293] lr: 5.000000e-04 eta: 1:00:19 time: 0.341561 data_time: 0.067296 memory: 5151 loss_kpt: 0.000674 acc_pose: 0.863208 loss: 0.000674 2022/09/17 18:23:49 - mmengine - INFO - Epoch(train) [169][150/293] lr: 5.000000e-04 eta: 1:00:05 time: 0.340051 data_time: 0.070287 memory: 5151 loss_kpt: 0.000676 acc_pose: 0.854056 loss: 0.000676 2022/09/17 18:24:06 - mmengine - INFO - Epoch(train) [169][200/293] lr: 5.000000e-04 eta: 0:59:50 time: 0.341283 data_time: 0.073152 memory: 5151 loss_kpt: 0.000669 acc_pose: 0.819916 loss: 0.000669 2022/09/17 18:24:23 - mmengine - INFO - Epoch(train) [169][250/293] lr: 5.000000e-04 eta: 0:59:36 time: 0.335184 data_time: 0.067901 memory: 5151 loss_kpt: 0.000683 acc_pose: 0.823406 loss: 0.000683 2022/09/17 18:24:38 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:24:38 - mmengine - INFO - Saving checkpoint at 169 epochs 2022/09/17 18:24:58 - mmengine - INFO - Epoch(train) [170][50/293] lr: 5.000000e-04 eta: 0:59:06 time: 0.352962 data_time: 0.074206 memory: 5151 loss_kpt: 0.000651 acc_pose: 0.838866 loss: 0.000651 2022/09/17 18:25:16 - mmengine - INFO - Epoch(train) [170][100/293] lr: 5.000000e-04 eta: 0:58:52 time: 0.347978 data_time: 0.068350 memory: 5151 loss_kpt: 0.000667 acc_pose: 0.821794 loss: 0.000667 2022/09/17 18:25:33 - mmengine - INFO - Epoch(train) [170][150/293] lr: 5.000000e-04 eta: 0:58:37 time: 0.337779 data_time: 0.071843 memory: 5151 loss_kpt: 0.000663 acc_pose: 0.856288 loss: 0.000663 2022/09/17 18:25:50 - mmengine - INFO - Epoch(train) [170][200/293] lr: 5.000000e-04 eta: 0:58:23 time: 0.336552 data_time: 0.067578 memory: 5151 loss_kpt: 0.000670 acc_pose: 0.814092 loss: 0.000670 2022/09/17 18:26:07 - mmengine - INFO - Epoch(train) [170][250/293] lr: 5.000000e-04 eta: 0:58:09 time: 0.344594 data_time: 0.068990 memory: 5151 loss_kpt: 0.000665 acc_pose: 0.823328 loss: 0.000665 2022/09/17 18:26:21 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:26:21 - mmengine - INFO - Saving checkpoint at 170 epochs 2022/09/17 18:26:30 - mmengine - INFO - Epoch(val) [170][50/407] eta: 0:00:44 time: 0.123528 data_time: 0.054908 memory: 5151 2022/09/17 18:26:36 - mmengine - INFO - Epoch(val) [170][100/407] eta: 0:00:36 time: 0.119457 data_time: 0.049798 memory: 331 2022/09/17 18:26:42 - mmengine - INFO - Epoch(val) [170][150/407] eta: 0:00:30 time: 0.118272 data_time: 0.050959 memory: 331 2022/09/17 18:26:48 - mmengine - INFO - Epoch(val) [170][200/407] eta: 0:00:24 time: 0.116912 data_time: 0.049578 memory: 331 2022/09/17 18:26:54 - mmengine - INFO - Epoch(val) [170][250/407] eta: 0:00:18 time: 0.119734 data_time: 0.051891 memory: 331 2022/09/17 18:27:00 - mmengine - INFO - Epoch(val) [170][300/407] eta: 0:00:12 time: 0.114811 data_time: 0.046756 memory: 331 2022/09/17 18:27:06 - mmengine - INFO - Epoch(val) [170][350/407] eta: 0:00:06 time: 0.117831 data_time: 0.049946 memory: 331 2022/09/17 18:27:11 - mmengine - INFO - Epoch(val) [170][400/407] eta: 0:00:00 time: 0.106569 data_time: 0.041830 memory: 331 2022/09/17 18:27:46 - mmengine - INFO - Evaluating CocoMetric... 2022/09/17 18:28:00 - mmengine - INFO - Epoch(val) [170][407/407] coco/AP: 0.697698 coco/AP .5: 0.886353 coco/AP .75: 0.777162 coco/AP (M): 0.666708 coco/AP (L): 0.761610 coco/AR: 0.757415 coco/AR .5: 0.928999 coco/AR .75: 0.828873 coco/AR (M): 0.716089 coco/AR (L): 0.816908 2022/09/17 18:28:01 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220917/vipnas_res50/best_coco/AP_epoch_150.pth is removed 2022/09/17 18:28:03 - mmengine - INFO - The best checkpoint with 0.6977 coco/AP at 170 epoch is saved to best_coco/AP_epoch_170.pth. 2022/09/17 18:28:20 - mmengine - INFO - Epoch(train) [171][50/293] lr: 5.000000e-05 eta: 0:57:39 time: 0.341483 data_time: 0.078136 memory: 5151 loss_kpt: 0.000667 acc_pose: 0.825760 loss: 0.000667 2022/09/17 18:28:36 - mmengine - INFO - Epoch(train) [171][100/293] lr: 5.000000e-05 eta: 0:57:24 time: 0.333992 data_time: 0.069827 memory: 5151 loss_kpt: 0.000647 acc_pose: 0.848941 loss: 0.000647 2022/09/17 18:28:53 - mmengine - INFO - Epoch(train) [171][150/293] lr: 5.000000e-05 eta: 0:57:10 time: 0.341083 data_time: 0.070293 memory: 5151 loss_kpt: 0.000659 acc_pose: 0.843562 loss: 0.000659 2022/09/17 18:29:07 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:29:11 - mmengine - INFO - Epoch(train) [171][200/293] lr: 5.000000e-05 eta: 0:56:56 time: 0.345210 data_time: 0.067820 memory: 5151 loss_kpt: 0.000650 acc_pose: 0.871922 loss: 0.000650 2022/09/17 18:29:28 - mmengine - INFO - Epoch(train) [171][250/293] lr: 5.000000e-05 eta: 0:56:42 time: 0.350096 data_time: 0.071572 memory: 5151 loss_kpt: 0.000667 acc_pose: 0.837556 loss: 0.000667 2022/09/17 18:29:43 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:29:43 - mmengine - INFO - Saving checkpoint at 171 epochs 2022/09/17 18:30:04 - mmengine - INFO - Epoch(train) [172][50/293] lr: 5.000000e-05 eta: 0:56:12 time: 0.351104 data_time: 0.079931 memory: 5151 loss_kpt: 0.000646 acc_pose: 0.865062 loss: 0.000646 2022/09/17 18:30:21 - mmengine - INFO - Epoch(train) [172][100/293] lr: 5.000000e-05 eta: 0:55:58 time: 0.358421 data_time: 0.069387 memory: 5151 loss_kpt: 0.000654 acc_pose: 0.864638 loss: 0.000654 2022/09/17 18:30:39 - mmengine - INFO - Epoch(train) [172][150/293] lr: 5.000000e-05 eta: 0:55:43 time: 0.351172 data_time: 0.067247 memory: 5151 loss_kpt: 0.000648 acc_pose: 0.883515 loss: 0.000648 2022/09/17 18:30:56 - mmengine - INFO - Epoch(train) [172][200/293] lr: 5.000000e-05 eta: 0:55:29 time: 0.338849 data_time: 0.069218 memory: 5151 loss_kpt: 0.000652 acc_pose: 0.775460 loss: 0.000652 2022/09/17 18:31:13 - mmengine - INFO - Epoch(train) [172][250/293] lr: 5.000000e-05 eta: 0:55:15 time: 0.339792 data_time: 0.082715 memory: 5151 loss_kpt: 0.000647 acc_pose: 0.834024 loss: 0.000647 2022/09/17 18:31:27 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:31:27 - mmengine - INFO - Saving checkpoint at 172 epochs 2022/09/17 18:31:46 - mmengine - INFO - Epoch(train) [173][50/293] lr: 5.000000e-05 eta: 0:54:45 time: 0.335327 data_time: 0.070704 memory: 5151 loss_kpt: 0.000642 acc_pose: 0.847964 loss: 0.000642 2022/09/17 18:32:03 - mmengine - INFO - Epoch(train) [173][100/293] lr: 5.000000e-05 eta: 0:54:30 time: 0.338635 data_time: 0.072544 memory: 5151 loss_kpt: 0.000642 acc_pose: 0.842738 loss: 0.000642 2022/09/17 18:32:20 - mmengine - INFO - Epoch(train) [173][150/293] lr: 5.000000e-05 eta: 0:54:16 time: 0.339093 data_time: 0.065213 memory: 5151 loss_kpt: 0.000648 acc_pose: 0.799172 loss: 0.000648 2022/09/17 18:32:37 - mmengine - INFO - Epoch(train) [173][200/293] lr: 5.000000e-05 eta: 0:54:02 time: 0.332560 data_time: 0.070979 memory: 5151 loss_kpt: 0.000646 acc_pose: 0.858412 loss: 0.000646 2022/09/17 18:32:54 - mmengine - INFO - Epoch(train) [173][250/293] lr: 5.000000e-05 eta: 0:53:47 time: 0.337889 data_time: 0.069729 memory: 5151 loss_kpt: 0.000634 acc_pose: 0.851789 loss: 0.000634 2022/09/17 18:33:09 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:33:09 - mmengine - INFO - Saving checkpoint at 173 epochs 2022/09/17 18:33:28 - mmengine - INFO - Epoch(train) [174][50/293] lr: 5.000000e-05 eta: 0:53:17 time: 0.343488 data_time: 0.073699 memory: 5151 loss_kpt: 0.000649 acc_pose: 0.840230 loss: 0.000649 2022/09/17 18:33:44 - mmengine - INFO - Epoch(train) [174][100/293] lr: 5.000000e-05 eta: 0:53:03 time: 0.318602 data_time: 0.063224 memory: 5151 loss_kpt: 0.000648 acc_pose: 0.842507 loss: 0.000648 2022/09/17 18:34:01 - mmengine - INFO - Epoch(train) [174][150/293] lr: 5.000000e-05 eta: 0:52:48 time: 0.325356 data_time: 0.065838 memory: 5151 loss_kpt: 0.000641 acc_pose: 0.835962 loss: 0.000641 2022/09/17 18:34:18 - mmengine - INFO - Epoch(train) [174][200/293] lr: 5.000000e-05 eta: 0:52:34 time: 0.346718 data_time: 0.080391 memory: 5151 loss_kpt: 0.000636 acc_pose: 0.809263 loss: 0.000636 2022/09/17 18:34:35 - mmengine - INFO - Epoch(train) [174][250/293] lr: 5.000000e-05 eta: 0:52:20 time: 0.336023 data_time: 0.066298 memory: 5151 loss_kpt: 0.000650 acc_pose: 0.849763 loss: 0.000650 2022/09/17 18:34:49 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:34:49 - mmengine - INFO - Saving checkpoint at 174 epochs 2022/09/17 18:34:58 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:35:09 - mmengine - INFO - Epoch(train) [175][50/293] lr: 5.000000e-05 eta: 0:51:50 time: 0.351723 data_time: 0.076007 memory: 5151 loss_kpt: 0.000651 acc_pose: 0.865388 loss: 0.000651 2022/09/17 18:35:26 - mmengine - INFO - Epoch(train) [175][100/293] lr: 5.000000e-05 eta: 0:51:36 time: 0.342329 data_time: 0.073905 memory: 5151 loss_kpt: 0.000632 acc_pose: 0.801806 loss: 0.000632 2022/09/17 18:35:43 - mmengine - INFO - Epoch(train) [175][150/293] lr: 5.000000e-05 eta: 0:51:21 time: 0.330307 data_time: 0.072745 memory: 5151 loss_kpt: 0.000638 acc_pose: 0.839306 loss: 0.000638 2022/09/17 18:36:00 - mmengine - INFO - Epoch(train) [175][200/293] lr: 5.000000e-05 eta: 0:51:07 time: 0.340078 data_time: 0.071970 memory: 5151 loss_kpt: 0.000643 acc_pose: 0.874606 loss: 0.000643 2022/09/17 18:36:16 - mmengine - INFO - Epoch(train) [175][250/293] lr: 5.000000e-05 eta: 0:50:52 time: 0.334915 data_time: 0.063359 memory: 5151 loss_kpt: 0.000650 acc_pose: 0.837764 loss: 0.000650 2022/09/17 18:36:30 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:36:30 - mmengine - INFO - Saving checkpoint at 175 epochs 2022/09/17 18:36:50 - mmengine - INFO - Epoch(train) [176][50/293] lr: 5.000000e-05 eta: 0:50:23 time: 0.354078 data_time: 0.083454 memory: 5151 loss_kpt: 0.000636 acc_pose: 0.846685 loss: 0.000636 2022/09/17 18:37:07 - mmengine - INFO - Epoch(train) [176][100/293] lr: 5.000000e-05 eta: 0:50:08 time: 0.330259 data_time: 0.074243 memory: 5151 loss_kpt: 0.000632 acc_pose: 0.877047 loss: 0.000632 2022/09/17 18:37:23 - mmengine - INFO - Epoch(train) [176][150/293] lr: 5.000000e-05 eta: 0:49:54 time: 0.336134 data_time: 0.066394 memory: 5151 loss_kpt: 0.000635 acc_pose: 0.800947 loss: 0.000635 2022/09/17 18:37:40 - mmengine - INFO - Epoch(train) [176][200/293] lr: 5.000000e-05 eta: 0:49:40 time: 0.338910 data_time: 0.074820 memory: 5151 loss_kpt: 0.000653 acc_pose: 0.849424 loss: 0.000653 2022/09/17 18:37:57 - mmengine - INFO - Epoch(train) [176][250/293] lr: 5.000000e-05 eta: 0:49:25 time: 0.331404 data_time: 0.061515 memory: 5151 loss_kpt: 0.000635 acc_pose: 0.846867 loss: 0.000635 2022/09/17 18:38:11 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:38:11 - mmengine - INFO - Saving checkpoint at 176 epochs 2022/09/17 18:38:31 - mmengine - INFO - Epoch(train) [177][50/293] lr: 5.000000e-05 eta: 0:48:55 time: 0.335307 data_time: 0.067508 memory: 5151 loss_kpt: 0.000626 acc_pose: 0.840230 loss: 0.000626 2022/09/17 18:38:48 - mmengine - INFO - Epoch(train) [177][100/293] lr: 5.000000e-05 eta: 0:48:41 time: 0.333915 data_time: 0.064272 memory: 5151 loss_kpt: 0.000638 acc_pose: 0.824069 loss: 0.000638 2022/09/17 18:39:05 - mmengine - INFO - Epoch(train) [177][150/293] lr: 5.000000e-05 eta: 0:48:27 time: 0.339327 data_time: 0.071138 memory: 5151 loss_kpt: 0.000634 acc_pose: 0.852369 loss: 0.000634 2022/09/17 18:39:21 - mmengine - INFO - Epoch(train) [177][200/293] lr: 5.000000e-05 eta: 0:48:12 time: 0.333674 data_time: 0.067504 memory: 5151 loss_kpt: 0.000627 acc_pose: 0.865723 loss: 0.000627 2022/09/17 18:39:38 - mmengine - INFO - Epoch(train) [177][250/293] lr: 5.000000e-05 eta: 0:47:58 time: 0.324753 data_time: 0.057842 memory: 5151 loss_kpt: 0.000641 acc_pose: 0.812567 loss: 0.000641 2022/09/17 18:39:52 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:39:52 - mmengine - INFO - Saving checkpoint at 177 epochs 2022/09/17 18:40:12 - mmengine - INFO - Epoch(train) [178][50/293] lr: 5.000000e-05 eta: 0:47:28 time: 0.348994 data_time: 0.081457 memory: 5151 loss_kpt: 0.000629 acc_pose: 0.872475 loss: 0.000629 2022/09/17 18:40:29 - mmengine - INFO - Epoch(train) [178][100/293] lr: 5.000000e-05 eta: 0:47:14 time: 0.341518 data_time: 0.072583 memory: 5151 loss_kpt: 0.000630 acc_pose: 0.860342 loss: 0.000630 2022/09/17 18:40:42 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:40:46 - mmengine - INFO - Epoch(train) [178][150/293] lr: 5.000000e-05 eta: 0:46:59 time: 0.345122 data_time: 0.068208 memory: 5151 loss_kpt: 0.000630 acc_pose: 0.849220 loss: 0.000630 2022/09/17 18:41:03 - mmengine - INFO - Epoch(train) [178][200/293] lr: 5.000000e-05 eta: 0:46:45 time: 0.339149 data_time: 0.070316 memory: 5151 loss_kpt: 0.000637 acc_pose: 0.865035 loss: 0.000637 2022/09/17 18:41:20 - mmengine - INFO - Epoch(train) [178][250/293] lr: 5.000000e-05 eta: 0:46:31 time: 0.341245 data_time: 0.069687 memory: 5151 loss_kpt: 0.000630 acc_pose: 0.863645 loss: 0.000630 2022/09/17 18:41:34 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:41:34 - mmengine - INFO - Saving checkpoint at 178 epochs 2022/09/17 18:41:54 - mmengine - INFO - Epoch(train) [179][50/293] lr: 5.000000e-05 eta: 0:46:01 time: 0.339551 data_time: 0.074847 memory: 5151 loss_kpt: 0.000641 acc_pose: 0.878271 loss: 0.000641 2022/09/17 18:42:11 - mmengine - INFO - Epoch(train) [179][100/293] lr: 5.000000e-05 eta: 0:45:47 time: 0.335417 data_time: 0.072420 memory: 5151 loss_kpt: 0.000632 acc_pose: 0.811218 loss: 0.000632 2022/09/17 18:42:28 - mmengine - INFO - Epoch(train) [179][150/293] lr: 5.000000e-05 eta: 0:45:32 time: 0.340290 data_time: 0.071480 memory: 5151 loss_kpt: 0.000634 acc_pose: 0.865680 loss: 0.000634 2022/09/17 18:42:44 - mmengine - INFO - Epoch(train) [179][200/293] lr: 5.000000e-05 eta: 0:45:18 time: 0.327820 data_time: 0.065574 memory: 5151 loss_kpt: 0.000630 acc_pose: 0.825453 loss: 0.000630 2022/09/17 18:43:01 - mmengine - INFO - Epoch(train) [179][250/293] lr: 5.000000e-05 eta: 0:45:03 time: 0.339572 data_time: 0.068295 memory: 5151 loss_kpt: 0.000635 acc_pose: 0.818483 loss: 0.000635 2022/09/17 18:43:16 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:43:16 - mmengine - INFO - Saving checkpoint at 179 epochs 2022/09/17 18:43:35 - mmengine - INFO - Epoch(train) [180][50/293] lr: 5.000000e-05 eta: 0:44:34 time: 0.342244 data_time: 0.076003 memory: 5151 loss_kpt: 0.000639 acc_pose: 0.829765 loss: 0.000639 2022/09/17 18:43:52 - mmengine - INFO - Epoch(train) [180][100/293] lr: 5.000000e-05 eta: 0:44:19 time: 0.340144 data_time: 0.079667 memory: 5151 loss_kpt: 0.000623 acc_pose: 0.837600 loss: 0.000623 2022/09/17 18:44:09 - mmengine - INFO - Epoch(train) [180][150/293] lr: 5.000000e-05 eta: 0:44:05 time: 0.337696 data_time: 0.068275 memory: 5151 loss_kpt: 0.000635 acc_pose: 0.887846 loss: 0.000635 2022/09/17 18:44:26 - mmengine - INFO - Epoch(train) [180][200/293] lr: 5.000000e-05 eta: 0:43:51 time: 0.336097 data_time: 0.074105 memory: 5151 loss_kpt: 0.000625 acc_pose: 0.846220 loss: 0.000625 2022/09/17 18:44:43 - mmengine - INFO - Epoch(train) [180][250/293] lr: 5.000000e-05 eta: 0:43:36 time: 0.334634 data_time: 0.066911 memory: 5151 loss_kpt: 0.000641 acc_pose: 0.847321 loss: 0.000641 2022/09/17 18:44:57 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:44:57 - mmengine - INFO - Saving checkpoint at 180 epochs 2022/09/17 18:45:06 - mmengine - INFO - Epoch(val) [180][50/407] eta: 0:00:43 time: 0.122546 data_time: 0.053559 memory: 5151 2022/09/17 18:45:12 - mmengine - INFO - Epoch(val) [180][100/407] eta: 0:00:35 time: 0.115946 data_time: 0.045813 memory: 331 2022/09/17 18:45:18 - mmengine - INFO - Epoch(val) [180][150/407] eta: 0:00:31 time: 0.122308 data_time: 0.054948 memory: 331 2022/09/17 18:45:24 - mmengine - INFO - Epoch(val) [180][200/407] eta: 0:00:23 time: 0.113868 data_time: 0.047207 memory: 331 2022/09/17 18:45:29 - mmengine - INFO - Epoch(val) [180][250/407] eta: 0:00:18 time: 0.115223 data_time: 0.046206 memory: 331 2022/09/17 18:45:35 - mmengine - INFO - Epoch(val) [180][300/407] eta: 0:00:12 time: 0.115277 data_time: 0.047290 memory: 331 2022/09/17 18:45:42 - mmengine - INFO - Epoch(val) [180][350/407] eta: 0:00:07 time: 0.127230 data_time: 0.058560 memory: 331 2022/09/17 18:45:47 - mmengine - INFO - Epoch(val) [180][400/407] eta: 0:00:00 time: 0.110564 data_time: 0.045043 memory: 331 2022/09/17 18:46:23 - mmengine - INFO - Evaluating CocoMetric... 2022/09/17 18:46:36 - mmengine - INFO - Epoch(val) [180][407/407] coco/AP: 0.706861 coco/AP .5: 0.891152 coco/AP .75: 0.785949 coco/AP (M): 0.674180 coco/AP (L): 0.772577 coco/AR: 0.765145 coco/AR .5: 0.932777 coco/AR .75: 0.837531 coco/AR (M): 0.723026 coco/AR (L): 0.826124 2022/09/17 18:46:37 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220917/vipnas_res50/best_coco/AP_epoch_170.pth is removed 2022/09/17 18:46:39 - mmengine - INFO - The best checkpoint with 0.7069 coco/AP at 180 epoch is saved to best_coco/AP_epoch_180.pth. 2022/09/17 18:46:57 - mmengine - INFO - Epoch(train) [181][50/293] lr: 5.000000e-05 eta: 0:43:07 time: 0.358916 data_time: 0.082313 memory: 5151 loss_kpt: 0.000625 acc_pose: 0.850360 loss: 0.000625 2022/09/17 18:47:14 - mmengine - INFO - Epoch(train) [181][100/293] lr: 5.000000e-05 eta: 0:42:53 time: 0.347149 data_time: 0.071739 memory: 5151 loss_kpt: 0.000637 acc_pose: 0.856365 loss: 0.000637 2022/09/17 18:47:31 - mmengine - INFO - Epoch(train) [181][150/293] lr: 5.000000e-05 eta: 0:42:38 time: 0.347142 data_time: 0.072718 memory: 5151 loss_kpt: 0.000640 acc_pose: 0.875944 loss: 0.000640 2022/09/17 18:47:48 - mmengine - INFO - Epoch(train) [181][200/293] lr: 5.000000e-05 eta: 0:42:24 time: 0.340341 data_time: 0.067943 memory: 5151 loss_kpt: 0.000635 acc_pose: 0.863684 loss: 0.000635 2022/09/17 18:48:05 - mmengine - INFO - Epoch(train) [181][250/293] lr: 5.000000e-05 eta: 0:42:09 time: 0.332046 data_time: 0.067591 memory: 5151 loss_kpt: 0.000641 acc_pose: 0.864422 loss: 0.000641 2022/09/17 18:48:08 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:48:19 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:48:19 - mmengine - INFO - Saving checkpoint at 181 epochs 2022/09/17 18:48:40 - mmengine - INFO - Epoch(train) [182][50/293] lr: 5.000000e-05 eta: 0:41:40 time: 0.356091 data_time: 0.083705 memory: 5151 loss_kpt: 0.000627 acc_pose: 0.772167 loss: 0.000627 2022/09/17 18:48:57 - mmengine - INFO - Epoch(train) [182][100/293] lr: 5.000000e-05 eta: 0:41:26 time: 0.331980 data_time: 0.065249 memory: 5151 loss_kpt: 0.000648 acc_pose: 0.833712 loss: 0.000648 2022/09/17 18:49:13 - mmengine - INFO - Epoch(train) [182][150/293] lr: 5.000000e-05 eta: 0:41:11 time: 0.326317 data_time: 0.069416 memory: 5151 loss_kpt: 0.000635 acc_pose: 0.847640 loss: 0.000635 2022/09/17 18:49:30 - mmengine - INFO - Epoch(train) [182][200/293] lr: 5.000000e-05 eta: 0:40:56 time: 0.326087 data_time: 0.063744 memory: 5151 loss_kpt: 0.000626 acc_pose: 0.856353 loss: 0.000626 2022/09/17 18:49:46 - mmengine - INFO - Epoch(train) [182][250/293] lr: 5.000000e-05 eta: 0:40:42 time: 0.326252 data_time: 0.064496 memory: 5151 loss_kpt: 0.000642 acc_pose: 0.882453 loss: 0.000642 2022/09/17 18:50:00 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:50:00 - mmengine - INFO - Saving checkpoint at 182 epochs 2022/09/17 18:50:20 - mmengine - INFO - Epoch(train) [183][50/293] lr: 5.000000e-05 eta: 0:40:13 time: 0.352698 data_time: 0.080073 memory: 5151 loss_kpt: 0.000640 acc_pose: 0.825128 loss: 0.000640 2022/09/17 18:50:37 - mmengine - INFO - Epoch(train) [183][100/293] lr: 5.000000e-05 eta: 0:39:58 time: 0.337354 data_time: 0.072540 memory: 5151 loss_kpt: 0.000623 acc_pose: 0.830363 loss: 0.000623 2022/09/17 18:50:54 - mmengine - INFO - Epoch(train) [183][150/293] lr: 5.000000e-05 eta: 0:39:44 time: 0.341051 data_time: 0.071019 memory: 5151 loss_kpt: 0.000624 acc_pose: 0.856500 loss: 0.000624 2022/09/17 18:51:11 - mmengine - INFO - Epoch(train) [183][200/293] lr: 5.000000e-05 eta: 0:39:29 time: 0.338027 data_time: 0.072224 memory: 5151 loss_kpt: 0.000637 acc_pose: 0.802852 loss: 0.000637 2022/09/17 18:51:28 - mmengine - INFO - Epoch(train) [183][250/293] lr: 5.000000e-05 eta: 0:39:15 time: 0.338985 data_time: 0.071078 memory: 5151 loss_kpt: 0.000630 acc_pose: 0.864319 loss: 0.000630 2022/09/17 18:51:43 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:51:43 - mmengine - INFO - Saving checkpoint at 183 epochs 2022/09/17 18:52:03 - mmengine - INFO - Epoch(train) [184][50/293] lr: 5.000000e-05 eta: 0:38:46 time: 0.361572 data_time: 0.082123 memory: 5151 loss_kpt: 0.000640 acc_pose: 0.847966 loss: 0.000640 2022/09/17 18:52:21 - mmengine - INFO - Epoch(train) [184][100/293] lr: 5.000000e-05 eta: 0:38:32 time: 0.353642 data_time: 0.074245 memory: 5151 loss_kpt: 0.000635 acc_pose: 0.850828 loss: 0.000635 2022/09/17 18:52:37 - mmengine - INFO - Epoch(train) [184][150/293] lr: 5.000000e-05 eta: 0:38:17 time: 0.329125 data_time: 0.069186 memory: 5151 loss_kpt: 0.000638 acc_pose: 0.865458 loss: 0.000638 2022/09/17 18:52:55 - mmengine - INFO - Epoch(train) [184][200/293] lr: 5.000000e-05 eta: 0:38:03 time: 0.347290 data_time: 0.074779 memory: 5151 loss_kpt: 0.000638 acc_pose: 0.814634 loss: 0.000638 2022/09/17 18:53:11 - mmengine - INFO - Epoch(train) [184][250/293] lr: 5.000000e-05 eta: 0:37:48 time: 0.331392 data_time: 0.065478 memory: 5151 loss_kpt: 0.000638 acc_pose: 0.877185 loss: 0.000638 2022/09/17 18:53:26 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:53:26 - mmengine - INFO - Saving checkpoint at 184 epochs 2022/09/17 18:53:46 - mmengine - INFO - Epoch(train) [185][50/293] lr: 5.000000e-05 eta: 0:37:19 time: 0.338936 data_time: 0.070798 memory: 5151 loss_kpt: 0.000622 acc_pose: 0.800427 loss: 0.000622 2022/09/17 18:54:00 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:54:04 - mmengine - INFO - Epoch(train) [185][100/293] lr: 5.000000e-05 eta: 0:37:05 time: 0.351318 data_time: 0.078127 memory: 5151 loss_kpt: 0.000638 acc_pose: 0.873712 loss: 0.000638 2022/09/17 18:54:20 - mmengine - INFO - Epoch(train) [185][150/293] lr: 5.000000e-05 eta: 0:36:50 time: 0.337653 data_time: 0.067896 memory: 5151 loss_kpt: 0.000636 acc_pose: 0.826549 loss: 0.000636 2022/09/17 18:54:37 - mmengine - INFO - Epoch(train) [185][200/293] lr: 5.000000e-05 eta: 0:36:36 time: 0.334276 data_time: 0.072743 memory: 5151 loss_kpt: 0.000636 acc_pose: 0.860379 loss: 0.000636 2022/09/17 18:54:54 - mmengine - INFO - Epoch(train) [185][250/293] lr: 5.000000e-05 eta: 0:36:21 time: 0.330295 data_time: 0.066170 memory: 5151 loss_kpt: 0.000629 acc_pose: 0.841172 loss: 0.000629 2022/09/17 18:55:09 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:55:09 - mmengine - INFO - Saving checkpoint at 185 epochs 2022/09/17 18:55:29 - mmengine - INFO - Epoch(train) [186][50/293] lr: 5.000000e-05 eta: 0:35:52 time: 0.353876 data_time: 0.076555 memory: 5151 loss_kpt: 0.000635 acc_pose: 0.754503 loss: 0.000635 2022/09/17 18:55:46 - mmengine - INFO - Epoch(train) [186][100/293] lr: 5.000000e-05 eta: 0:35:38 time: 0.336629 data_time: 0.072537 memory: 5151 loss_kpt: 0.000630 acc_pose: 0.832319 loss: 0.000630 2022/09/17 18:56:02 - mmengine - INFO - Epoch(train) [186][150/293] lr: 5.000000e-05 eta: 0:35:23 time: 0.339051 data_time: 0.073598 memory: 5151 loss_kpt: 0.000630 acc_pose: 0.866273 loss: 0.000630 2022/09/17 18:56:20 - mmengine - INFO - Epoch(train) [186][200/293] lr: 5.000000e-05 eta: 0:35:09 time: 0.344364 data_time: 0.072245 memory: 5151 loss_kpt: 0.000633 acc_pose: 0.871803 loss: 0.000633 2022/09/17 18:56:36 - mmengine - INFO - Epoch(train) [186][250/293] lr: 5.000000e-05 eta: 0:34:54 time: 0.334801 data_time: 0.067199 memory: 5151 loss_kpt: 0.000630 acc_pose: 0.810024 loss: 0.000630 2022/09/17 18:56:51 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:56:51 - mmengine - INFO - Saving checkpoint at 186 epochs 2022/09/17 18:57:11 - mmengine - INFO - Epoch(train) [187][50/293] lr: 5.000000e-05 eta: 0:34:25 time: 0.359605 data_time: 0.084745 memory: 5151 loss_kpt: 0.000643 acc_pose: 0.869811 loss: 0.000643 2022/09/17 18:57:28 - mmengine - INFO - Epoch(train) [187][100/293] lr: 5.000000e-05 eta: 0:34:11 time: 0.338882 data_time: 0.071215 memory: 5151 loss_kpt: 0.000617 acc_pose: 0.871367 loss: 0.000617 2022/09/17 18:57:46 - mmengine - INFO - Epoch(train) [187][150/293] lr: 5.000000e-05 eta: 0:33:56 time: 0.346432 data_time: 0.070137 memory: 5151 loss_kpt: 0.000650 acc_pose: 0.853300 loss: 0.000650 2022/09/17 18:58:03 - mmengine - INFO - Epoch(train) [187][200/293] lr: 5.000000e-05 eta: 0:33:42 time: 0.350552 data_time: 0.075263 memory: 5151 loss_kpt: 0.000620 acc_pose: 0.858517 loss: 0.000620 2022/09/17 18:58:20 - mmengine - INFO - Epoch(train) [187][250/293] lr: 5.000000e-05 eta: 0:33:27 time: 0.334572 data_time: 0.070443 memory: 5151 loss_kpt: 0.000639 acc_pose: 0.844616 loss: 0.000639 2022/09/17 18:58:34 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 18:58:34 - mmengine - INFO - Saving checkpoint at 187 epochs 2022/09/17 18:58:55 - mmengine - INFO - Epoch(train) [188][50/293] lr: 5.000000e-05 eta: 0:32:59 time: 0.353512 data_time: 0.075380 memory: 5151 loss_kpt: 0.000618 acc_pose: 0.886479 loss: 0.000618 2022/09/17 18:59:12 - mmengine - INFO - Epoch(train) [188][100/293] lr: 5.000000e-05 eta: 0:32:44 time: 0.347337 data_time: 0.069507 memory: 5151 loss_kpt: 0.000619 acc_pose: 0.832526 loss: 0.000619 2022/09/17 18:59:28 - mmengine - INFO - Epoch(train) [188][150/293] lr: 5.000000e-05 eta: 0:32:29 time: 0.325416 data_time: 0.065755 memory: 5151 loss_kpt: 0.000620 acc_pose: 0.840354 loss: 0.000620 2022/09/17 18:59:45 - mmengine - INFO - Epoch(train) [188][200/293] lr: 5.000000e-05 eta: 0:32:15 time: 0.326327 data_time: 0.063918 memory: 5151 loss_kpt: 0.000622 acc_pose: 0.837729 loss: 0.000622 2022/09/17 18:59:48 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 19:00:01 - mmengine - INFO - Epoch(train) [188][250/293] lr: 5.000000e-05 eta: 0:32:00 time: 0.335760 data_time: 0.068360 memory: 5151 loss_kpt: 0.000629 acc_pose: 0.883976 loss: 0.000629 2022/09/17 19:00:16 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 19:00:16 - mmengine - INFO - Saving checkpoint at 188 epochs 2022/09/17 19:00:36 - mmengine - INFO - Epoch(train) [189][50/293] lr: 5.000000e-05 eta: 0:31:32 time: 0.349916 data_time: 0.075345 memory: 5151 loss_kpt: 0.000631 acc_pose: 0.821796 loss: 0.000631 2022/09/17 19:00:53 - mmengine - INFO - Epoch(train) [189][100/293] lr: 5.000000e-05 eta: 0:31:17 time: 0.337484 data_time: 0.072166 memory: 5151 loss_kpt: 0.000628 acc_pose: 0.866320 loss: 0.000628 2022/09/17 19:01:10 - mmengine - INFO - Epoch(train) [189][150/293] lr: 5.000000e-05 eta: 0:31:02 time: 0.339996 data_time: 0.069813 memory: 5151 loss_kpt: 0.000629 acc_pose: 0.873690 loss: 0.000629 2022/09/17 19:01:27 - mmengine - INFO - Epoch(train) [189][200/293] lr: 5.000000e-05 eta: 0:30:48 time: 0.338994 data_time: 0.073966 memory: 5151 loss_kpt: 0.000638 acc_pose: 0.881956 loss: 0.000638 2022/09/17 19:01:45 - mmengine - INFO - Epoch(train) [189][250/293] lr: 5.000000e-05 eta: 0:30:33 time: 0.350594 data_time: 0.080817 memory: 5151 loss_kpt: 0.000631 acc_pose: 0.815752 loss: 0.000631 2022/09/17 19:01:59 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 19:01:59 - mmengine - INFO - Saving checkpoint at 189 epochs 2022/09/17 19:02:18 - mmengine - INFO - Epoch(train) [190][50/293] lr: 5.000000e-05 eta: 0:30:05 time: 0.343620 data_time: 0.074974 memory: 5151 loss_kpt: 0.000632 acc_pose: 0.831102 loss: 0.000632 2022/09/17 19:02:36 - mmengine - INFO - Epoch(train) [190][100/293] lr: 5.000000e-05 eta: 0:29:50 time: 0.342671 data_time: 0.066064 memory: 5151 loss_kpt: 0.000629 acc_pose: 0.877719 loss: 0.000629 2022/09/17 19:02:53 - mmengine - INFO - Epoch(train) [190][150/293] lr: 5.000000e-05 eta: 0:29:36 time: 0.349194 data_time: 0.076634 memory: 5151 loss_kpt: 0.000627 acc_pose: 0.855592 loss: 0.000627 2022/09/17 19:03:10 - mmengine - INFO - Epoch(train) [190][200/293] lr: 5.000000e-05 eta: 0:29:21 time: 0.346124 data_time: 0.074090 memory: 5151 loss_kpt: 0.000630 acc_pose: 0.841319 loss: 0.000630 2022/09/17 19:03:27 - mmengine - INFO - Epoch(train) [190][250/293] lr: 5.000000e-05 eta: 0:29:07 time: 0.328919 data_time: 0.068535 memory: 5151 loss_kpt: 0.000635 acc_pose: 0.864866 loss: 0.000635 2022/09/17 19:03:42 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 19:03:42 - mmengine - INFO - Saving checkpoint at 190 epochs 2022/09/17 19:03:50 - mmengine - INFO - Epoch(val) [190][50/407] eta: 0:00:44 time: 0.125538 data_time: 0.056779 memory: 5151 2022/09/17 19:03:56 - mmengine - INFO - Epoch(val) [190][100/407] eta: 0:00:36 time: 0.119527 data_time: 0.049996 memory: 331 2022/09/17 19:04:02 - mmengine - INFO - Epoch(val) [190][150/407] eta: 0:00:29 time: 0.116568 data_time: 0.051619 memory: 331 2022/09/17 19:04:08 - mmengine - INFO - Epoch(val) [190][200/407] eta: 0:00:24 time: 0.119746 data_time: 0.054232 memory: 331 2022/09/17 19:04:14 - mmengine - INFO - Epoch(val) [190][250/407] eta: 0:00:17 time: 0.111550 data_time: 0.047441 memory: 331 2022/09/17 19:04:19 - mmengine - INFO - Epoch(val) [190][300/407] eta: 0:00:12 time: 0.115115 data_time: 0.047224 memory: 331 2022/09/17 19:04:25 - mmengine - INFO - Epoch(val) [190][350/407] eta: 0:00:06 time: 0.117959 data_time: 0.051852 memory: 331 2022/09/17 19:04:31 - mmengine - INFO - Epoch(val) [190][400/407] eta: 0:00:00 time: 0.116177 data_time: 0.043357 memory: 331 2022/09/17 19:05:08 - mmengine - INFO - Evaluating CocoMetric... 2022/09/17 19:05:23 - mmengine - INFO - Epoch(val) [190][407/407] coco/AP: 0.708917 coco/AP .5: 0.891942 coco/AP .75: 0.786733 coco/AP (M): 0.676312 coco/AP (L): 0.773458 coco/AR: 0.766719 coco/AR .5: 0.932147 coco/AR .75: 0.836429 coco/AR (M): 0.725212 coco/AR (L): 0.826719 2022/09/17 19:05:23 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220917/vipnas_res50/best_coco/AP_epoch_180.pth is removed 2022/09/17 19:05:25 - mmengine - INFO - The best checkpoint with 0.7089 coco/AP at 190 epoch is saved to best_coco/AP_epoch_190.pth. 2022/09/17 19:05:43 - mmengine - INFO - Epoch(train) [191][50/293] lr: 5.000000e-05 eta: 0:28:38 time: 0.353339 data_time: 0.073674 memory: 5151 loss_kpt: 0.000638 acc_pose: 0.864292 loss: 0.000638 2022/09/17 19:06:00 - mmengine - INFO - Epoch(train) [191][100/293] lr: 5.000000e-05 eta: 0:28:24 time: 0.347052 data_time: 0.065218 memory: 5151 loss_kpt: 0.000633 acc_pose: 0.823120 loss: 0.000633 2022/09/17 19:06:17 - mmengine - INFO - Epoch(train) [191][150/293] lr: 5.000000e-05 eta: 0:28:09 time: 0.341461 data_time: 0.072923 memory: 5151 loss_kpt: 0.000629 acc_pose: 0.866835 loss: 0.000629 2022/09/17 19:06:35 - mmengine - INFO - Epoch(train) [191][200/293] lr: 5.000000e-05 eta: 0:27:54 time: 0.357305 data_time: 0.076453 memory: 5151 loss_kpt: 0.000614 acc_pose: 0.889643 loss: 0.000614 2022/09/17 19:06:52 - mmengine - INFO - Epoch(train) [191][250/293] lr: 5.000000e-05 eta: 0:27:40 time: 0.336987 data_time: 0.066585 memory: 5151 loss_kpt: 0.000630 acc_pose: 0.869524 loss: 0.000630 2022/09/17 19:07:07 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 19:07:07 - mmengine - INFO - Saving checkpoint at 191 epochs 2022/09/17 19:07:22 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 19:07:27 - mmengine - INFO - Epoch(train) [192][50/293] lr: 5.000000e-05 eta: 0:27:11 time: 0.353372 data_time: 0.076364 memory: 5151 loss_kpt: 0.000612 acc_pose: 0.830825 loss: 0.000612 2022/09/17 19:07:44 - mmengine - INFO - Epoch(train) [192][100/293] lr: 5.000000e-05 eta: 0:26:57 time: 0.342165 data_time: 0.068962 memory: 5151 loss_kpt: 0.000626 acc_pose: 0.855010 loss: 0.000626 2022/09/17 19:08:02 - mmengine - INFO - Epoch(train) [192][150/293] lr: 5.000000e-05 eta: 0:26:42 time: 0.356102 data_time: 0.078374 memory: 5151 loss_kpt: 0.000625 acc_pose: 0.854131 loss: 0.000625 2022/09/17 19:08:19 - mmengine - INFO - Epoch(train) [192][200/293] lr: 5.000000e-05 eta: 0:26:28 time: 0.351768 data_time: 0.080462 memory: 5151 loss_kpt: 0.000612 acc_pose: 0.835018 loss: 0.000612 2022/09/17 19:08:37 - mmengine - INFO - Epoch(train) [192][250/293] lr: 5.000000e-05 eta: 0:26:13 time: 0.346313 data_time: 0.073045 memory: 5151 loss_kpt: 0.000638 acc_pose: 0.829001 loss: 0.000638 2022/09/17 19:08:51 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 19:08:51 - mmengine - INFO - Saving checkpoint at 192 epochs 2022/09/17 19:09:12 - mmengine - INFO - Epoch(train) [193][50/293] lr: 5.000000e-05 eta: 0:25:45 time: 0.361436 data_time: 0.082560 memory: 5151 loss_kpt: 0.000625 acc_pose: 0.816104 loss: 0.000625 2022/09/17 19:09:29 - mmengine - INFO - Epoch(train) [193][100/293] lr: 5.000000e-05 eta: 0:25:30 time: 0.346159 data_time: 0.074664 memory: 5151 loss_kpt: 0.000622 acc_pose: 0.875642 loss: 0.000622 2022/09/17 19:09:46 - mmengine - INFO - Epoch(train) [193][150/293] lr: 5.000000e-05 eta: 0:25:16 time: 0.335636 data_time: 0.067416 memory: 5151 loss_kpt: 0.000623 acc_pose: 0.876938 loss: 0.000623 2022/09/17 19:10:04 - mmengine - INFO - Epoch(train) [193][200/293] lr: 5.000000e-05 eta: 0:25:01 time: 0.348200 data_time: 0.076726 memory: 5151 loss_kpt: 0.000619 acc_pose: 0.822725 loss: 0.000619 2022/09/17 19:10:21 - mmengine - INFO - Epoch(train) [193][250/293] lr: 5.000000e-05 eta: 0:24:47 time: 0.354118 data_time: 0.084983 memory: 5151 loss_kpt: 0.000624 acc_pose: 0.856449 loss: 0.000624 2022/09/17 19:10:35 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 19:10:35 - mmengine - INFO - Saving checkpoint at 193 epochs 2022/09/17 19:10:56 - mmengine - INFO - Epoch(train) [194][50/293] lr: 5.000000e-05 eta: 0:24:18 time: 0.361043 data_time: 0.090148 memory: 5151 loss_kpt: 0.000634 acc_pose: 0.843833 loss: 0.000634 2022/09/17 19:11:13 - mmengine - INFO - Epoch(train) [194][100/293] lr: 5.000000e-05 eta: 0:24:04 time: 0.349365 data_time: 0.077539 memory: 5151 loss_kpt: 0.000600 acc_pose: 0.863186 loss: 0.000600 2022/09/17 19:11:30 - mmengine - INFO - Epoch(train) [194][150/293] lr: 5.000000e-05 eta: 0:23:49 time: 0.339230 data_time: 0.069465 memory: 5151 loss_kpt: 0.000626 acc_pose: 0.858036 loss: 0.000626 2022/09/17 19:11:48 - mmengine - INFO - Epoch(train) [194][200/293] lr: 5.000000e-05 eta: 0:23:34 time: 0.350245 data_time: 0.074865 memory: 5151 loss_kpt: 0.000619 acc_pose: 0.840643 loss: 0.000619 2022/09/17 19:12:05 - mmengine - INFO - Epoch(train) [194][250/293] lr: 5.000000e-05 eta: 0:23:20 time: 0.333400 data_time: 0.070510 memory: 5151 loss_kpt: 0.000624 acc_pose: 0.822805 loss: 0.000624 2022/09/17 19:12:19 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 19:12:19 - mmengine - INFO - Saving checkpoint at 194 epochs 2022/09/17 19:12:39 - mmengine - INFO - Epoch(train) [195][50/293] lr: 5.000000e-05 eta: 0:22:51 time: 0.346521 data_time: 0.070408 memory: 5151 loss_kpt: 0.000622 acc_pose: 0.853306 loss: 0.000622 2022/09/17 19:12:56 - mmengine - INFO - Epoch(train) [195][100/293] lr: 5.000000e-05 eta: 0:22:37 time: 0.337674 data_time: 0.066762 memory: 5151 loss_kpt: 0.000636 acc_pose: 0.830395 loss: 0.000636 2022/09/17 19:13:13 - mmengine - INFO - Epoch(train) [195][150/293] lr: 5.000000e-05 eta: 0:22:22 time: 0.340235 data_time: 0.072561 memory: 5151 loss_kpt: 0.000627 acc_pose: 0.853424 loss: 0.000627 2022/09/17 19:13:15 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 19:13:30 - mmengine - INFO - Epoch(train) [195][200/293] lr: 5.000000e-05 eta: 0:22:08 time: 0.344514 data_time: 0.075402 memory: 5151 loss_kpt: 0.000633 acc_pose: 0.856024 loss: 0.000633 2022/09/17 19:13:47 - mmengine - INFO - Epoch(train) [195][250/293] lr: 5.000000e-05 eta: 0:21:53 time: 0.344213 data_time: 0.078597 memory: 5151 loss_kpt: 0.000632 acc_pose: 0.836730 loss: 0.000632 2022/09/17 19:14:02 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 19:14:02 - mmengine - INFO - Saving checkpoint at 195 epochs 2022/09/17 19:14:22 - mmengine - INFO - Epoch(train) [196][50/293] lr: 5.000000e-05 eta: 0:21:25 time: 0.351445 data_time: 0.075464 memory: 5151 loss_kpt: 0.000630 acc_pose: 0.826566 loss: 0.000630 2022/09/17 19:14:39 - mmengine - INFO - Epoch(train) [196][100/293] lr: 5.000000e-05 eta: 0:21:10 time: 0.335335 data_time: 0.062038 memory: 5151 loss_kpt: 0.000624 acc_pose: 0.851622 loss: 0.000624 2022/09/17 19:14:56 - mmengine - INFO - Epoch(train) [196][150/293] lr: 5.000000e-05 eta: 0:20:55 time: 0.343622 data_time: 0.066208 memory: 5151 loss_kpt: 0.000622 acc_pose: 0.792545 loss: 0.000622 2022/09/17 19:15:13 - mmengine - INFO - Epoch(train) [196][200/293] lr: 5.000000e-05 eta: 0:20:41 time: 0.339583 data_time: 0.067786 memory: 5151 loss_kpt: 0.000635 acc_pose: 0.869034 loss: 0.000635 2022/09/17 19:15:29 - mmengine - INFO - Epoch(train) [196][250/293] lr: 5.000000e-05 eta: 0:20:26 time: 0.331640 data_time: 0.065938 memory: 5151 loss_kpt: 0.000630 acc_pose: 0.841670 loss: 0.000630 2022/09/17 19:15:44 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 19:15:44 - mmengine - INFO - Saving checkpoint at 196 epochs 2022/09/17 19:16:04 - mmengine - INFO - Epoch(train) [197][50/293] lr: 5.000000e-05 eta: 0:19:58 time: 0.361557 data_time: 0.080298 memory: 5151 loss_kpt: 0.000618 acc_pose: 0.852472 loss: 0.000618 2022/09/17 19:16:22 - mmengine - INFO - Epoch(train) [197][100/293] lr: 5.000000e-05 eta: 0:19:43 time: 0.343387 data_time: 0.070348 memory: 5151 loss_kpt: 0.000621 acc_pose: 0.835458 loss: 0.000621 2022/09/17 19:16:38 - mmengine - INFO - Epoch(train) [197][150/293] lr: 5.000000e-05 eta: 0:19:29 time: 0.333211 data_time: 0.066899 memory: 5151 loss_kpt: 0.000623 acc_pose: 0.836328 loss: 0.000623 2022/09/17 19:16:55 - mmengine - INFO - Epoch(train) [197][200/293] lr: 5.000000e-05 eta: 0:19:14 time: 0.332821 data_time: 0.065070 memory: 5151 loss_kpt: 0.000628 acc_pose: 0.880761 loss: 0.000628 2022/09/17 19:17:12 - mmengine - INFO - Epoch(train) [197][250/293] lr: 5.000000e-05 eta: 0:18:59 time: 0.347927 data_time: 0.075055 memory: 5151 loss_kpt: 0.000634 acc_pose: 0.856764 loss: 0.000634 2022/09/17 19:17:27 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 19:17:27 - mmengine - INFO - Saving checkpoint at 197 epochs 2022/09/17 19:17:47 - mmengine - INFO - Epoch(train) [198][50/293] lr: 5.000000e-05 eta: 0:18:31 time: 0.347652 data_time: 0.070891 memory: 5151 loss_kpt: 0.000633 acc_pose: 0.774972 loss: 0.000633 2022/09/17 19:18:03 - mmengine - INFO - Epoch(train) [198][100/293] lr: 5.000000e-05 eta: 0:18:17 time: 0.332867 data_time: 0.064643 memory: 5151 loss_kpt: 0.000625 acc_pose: 0.856371 loss: 0.000625 2022/09/17 19:18:20 - mmengine - INFO - Epoch(train) [198][150/293] lr: 5.000000e-05 eta: 0:18:02 time: 0.342132 data_time: 0.069923 memory: 5151 loss_kpt: 0.000618 acc_pose: 0.867944 loss: 0.000618 2022/09/17 19:18:37 - mmengine - INFO - Epoch(train) [198][200/293] lr: 5.000000e-05 eta: 0:17:47 time: 0.324917 data_time: 0.061824 memory: 5151 loss_kpt: 0.000622 acc_pose: 0.837589 loss: 0.000622 2022/09/17 19:18:53 - mmengine - INFO - Epoch(train) [198][250/293] lr: 5.000000e-05 eta: 0:17:33 time: 0.326351 data_time: 0.063414 memory: 5151 loss_kpt: 0.000625 acc_pose: 0.853466 loss: 0.000625 2022/09/17 19:19:03 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 19:19:08 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 19:19:08 - mmengine - INFO - Saving checkpoint at 198 epochs 2022/09/17 19:19:27 - mmengine - INFO - Epoch(train) [199][50/293] lr: 5.000000e-05 eta: 0:17:04 time: 0.343151 data_time: 0.065708 memory: 5151 loss_kpt: 0.000614 acc_pose: 0.835490 loss: 0.000614 2022/09/17 19:19:44 - mmengine - INFO - Epoch(train) [199][100/293] lr: 5.000000e-05 eta: 0:16:50 time: 0.332366 data_time: 0.060101 memory: 5151 loss_kpt: 0.000624 acc_pose: 0.873678 loss: 0.000624 2022/09/17 19:20:00 - mmengine - INFO - Epoch(train) [199][150/293] lr: 5.000000e-05 eta: 0:16:35 time: 0.330444 data_time: 0.066711 memory: 5151 loss_kpt: 0.000635 acc_pose: 0.832781 loss: 0.000635 2022/09/17 19:20:17 - mmengine - INFO - Epoch(train) [199][200/293] lr: 5.000000e-05 eta: 0:16:20 time: 0.332808 data_time: 0.066227 memory: 5151 loss_kpt: 0.000626 acc_pose: 0.861548 loss: 0.000626 2022/09/17 19:20:34 - mmengine - INFO - Epoch(train) [199][250/293] lr: 5.000000e-05 eta: 0:16:06 time: 0.336436 data_time: 0.068696 memory: 5151 loss_kpt: 0.000631 acc_pose: 0.859890 loss: 0.000631 2022/09/17 19:20:48 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 19:20:48 - mmengine - INFO - Saving checkpoint at 199 epochs 2022/09/17 19:21:08 - mmengine - INFO - Epoch(train) [200][50/293] lr: 5.000000e-05 eta: 0:15:38 time: 0.348779 data_time: 0.076109 memory: 5151 loss_kpt: 0.000625 acc_pose: 0.867115 loss: 0.000625 2022/09/17 19:21:25 - mmengine - INFO - Epoch(train) [200][100/293] lr: 5.000000e-05 eta: 0:15:23 time: 0.335373 data_time: 0.064047 memory: 5151 loss_kpt: 0.000625 acc_pose: 0.848638 loss: 0.000625 2022/09/17 19:21:41 - mmengine - INFO - Epoch(train) [200][150/293] lr: 5.000000e-05 eta: 0:15:08 time: 0.333730 data_time: 0.059091 memory: 5151 loss_kpt: 0.000628 acc_pose: 0.826283 loss: 0.000628 2022/09/17 19:21:58 - mmengine - INFO - Epoch(train) [200][200/293] lr: 5.000000e-05 eta: 0:14:54 time: 0.336703 data_time: 0.068612 memory: 5151 loss_kpt: 0.000628 acc_pose: 0.844553 loss: 0.000628 2022/09/17 19:22:16 - mmengine - INFO - Epoch(train) [200][250/293] lr: 5.000000e-05 eta: 0:14:39 time: 0.351265 data_time: 0.069595 memory: 5151 loss_kpt: 0.000636 acc_pose: 0.831653 loss: 0.000636 2022/09/17 19:22:30 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 19:22:30 - mmengine - INFO - Saving checkpoint at 200 epochs 2022/09/17 19:22:38 - mmengine - INFO - Epoch(val) [200][50/407] eta: 0:00:43 time: 0.120953 data_time: 0.052711 memory: 5151 2022/09/17 19:22:44 - mmengine - INFO - Epoch(val) [200][100/407] eta: 0:00:36 time: 0.117576 data_time: 0.050731 memory: 331 2022/09/17 19:22:50 - mmengine - INFO - Epoch(val) [200][150/407] eta: 0:00:30 time: 0.118740 data_time: 0.051777 memory: 331 2022/09/17 19:22:56 - mmengine - INFO - Epoch(val) [200][200/407] eta: 0:00:23 time: 0.111123 data_time: 0.043962 memory: 331 2022/09/17 19:23:02 - mmengine - INFO - Epoch(val) [200][250/407] eta: 0:00:18 time: 0.119054 data_time: 0.051551 memory: 331 2022/09/17 19:23:08 - mmengine - INFO - Epoch(val) [200][300/407] eta: 0:00:12 time: 0.118714 data_time: 0.050726 memory: 331 2022/09/17 19:23:14 - mmengine - INFO - Epoch(val) [200][350/407] eta: 0:00:06 time: 0.120265 data_time: 0.052674 memory: 331 2022/09/17 19:23:19 - mmengine - INFO - Epoch(val) [200][400/407] eta: 0:00:00 time: 0.108096 data_time: 0.043379 memory: 331 2022/09/17 19:23:55 - mmengine - INFO - Evaluating CocoMetric... 2022/09/17 19:24:09 - mmengine - INFO - Epoch(val) [200][407/407] coco/AP: 0.710535 coco/AP .5: 0.893346 coco/AP .75: 0.786862 coco/AP (M): 0.677707 coco/AP (L): 0.776388 coco/AR: 0.768467 coco/AR .5: 0.934666 coco/AR .75: 0.836587 coco/AR (M): 0.726441 coco/AR (L): 0.829208 2022/09/17 19:24:09 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220917/vipnas_res50/best_coco/AP_epoch_190.pth is removed 2022/09/17 19:24:11 - mmengine - INFO - The best checkpoint with 0.7105 coco/AP at 200 epoch is saved to best_coco/AP_epoch_200.pth. 2022/09/17 19:24:28 - mmengine - INFO - Epoch(train) [201][50/293] lr: 5.000000e-06 eta: 0:14:11 time: 0.343616 data_time: 0.067921 memory: 5151 loss_kpt: 0.000606 acc_pose: 0.863926 loss: 0.000606 2022/09/17 19:24:45 - mmengine - INFO - Epoch(train) [201][100/293] lr: 5.000000e-06 eta: 0:13:56 time: 0.332354 data_time: 0.065109 memory: 5151 loss_kpt: 0.000631 acc_pose: 0.840453 loss: 0.000631 2022/09/17 19:25:01 - mmengine - INFO - Epoch(train) [201][150/293] lr: 5.000000e-06 eta: 0:13:41 time: 0.324950 data_time: 0.062313 memory: 5151 loss_kpt: 0.000632 acc_pose: 0.806888 loss: 0.000632 2022/09/17 19:25:17 - mmengine - INFO - Epoch(train) [201][200/293] lr: 5.000000e-06 eta: 0:13:27 time: 0.323319 data_time: 0.058965 memory: 5151 loss_kpt: 0.000614 acc_pose: 0.855126 loss: 0.000614 2022/09/17 19:25:33 - mmengine - INFO - Epoch(train) [201][250/293] lr: 5.000000e-06 eta: 0:13:12 time: 0.318720 data_time: 0.057134 memory: 5151 loss_kpt: 0.000621 acc_pose: 0.841569 loss: 0.000621 2022/09/17 19:25:47 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 19:25:47 - mmengine - INFO - Saving checkpoint at 201 epochs 2022/09/17 19:26:07 - mmengine - INFO - Epoch(train) [202][50/293] lr: 5.000000e-06 eta: 0:12:44 time: 0.353733 data_time: 0.075971 memory: 5151 loss_kpt: 0.000621 acc_pose: 0.811671 loss: 0.000621 2022/09/17 19:26:24 - mmengine - INFO - Epoch(train) [202][100/293] lr: 5.000000e-06 eta: 0:12:29 time: 0.332819 data_time: 0.062983 memory: 5151 loss_kpt: 0.000625 acc_pose: 0.883714 loss: 0.000625 2022/09/17 19:26:26 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 19:26:40 - mmengine - INFO - Epoch(train) [202][150/293] lr: 5.000000e-06 eta: 0:12:15 time: 0.331933 data_time: 0.066182 memory: 5151 loss_kpt: 0.000626 acc_pose: 0.850809 loss: 0.000626 2022/09/17 19:26:57 - mmengine - INFO - Epoch(train) [202][200/293] lr: 5.000000e-06 eta: 0:12:00 time: 0.328045 data_time: 0.065749 memory: 5151 loss_kpt: 0.000624 acc_pose: 0.852900 loss: 0.000624 2022/09/17 19:27:13 - mmengine - INFO - Epoch(train) [202][250/293] lr: 5.000000e-06 eta: 0:11:45 time: 0.328656 data_time: 0.056592 memory: 5151 loss_kpt: 0.000625 acc_pose: 0.876596 loss: 0.000625 2022/09/17 19:27:27 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 19:27:27 - mmengine - INFO - Saving checkpoint at 202 epochs 2022/09/17 19:27:47 - mmengine - INFO - Epoch(train) [203][50/293] lr: 5.000000e-06 eta: 0:11:17 time: 0.338579 data_time: 0.067396 memory: 5151 loss_kpt: 0.000625 acc_pose: 0.837117 loss: 0.000625 2022/09/17 19:28:04 - mmengine - INFO - Epoch(train) [203][100/293] lr: 5.000000e-06 eta: 0:11:03 time: 0.339662 data_time: 0.065502 memory: 5151 loss_kpt: 0.000608 acc_pose: 0.838182 loss: 0.000608 2022/09/17 19:28:20 - mmengine - INFO - Epoch(train) [203][150/293] lr: 5.000000e-06 eta: 0:10:48 time: 0.326426 data_time: 0.061430 memory: 5151 loss_kpt: 0.000629 acc_pose: 0.824728 loss: 0.000629 2022/09/17 19:28:37 - mmengine - INFO - Epoch(train) [203][200/293] lr: 5.000000e-06 eta: 0:10:33 time: 0.332967 data_time: 0.062918 memory: 5151 loss_kpt: 0.000632 acc_pose: 0.868879 loss: 0.000632 2022/09/17 19:28:54 - mmengine - INFO - Epoch(train) [203][250/293] lr: 5.000000e-06 eta: 0:10:19 time: 0.337993 data_time: 0.066228 memory: 5151 loss_kpt: 0.000618 acc_pose: 0.858564 loss: 0.000618 2022/09/17 19:29:08 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 19:29:08 - mmengine - INFO - Saving checkpoint at 203 epochs 2022/09/17 19:29:28 - mmengine - INFO - Epoch(train) [204][50/293] lr: 5.000000e-06 eta: 0:09:51 time: 0.340254 data_time: 0.071765 memory: 5151 loss_kpt: 0.000622 acc_pose: 0.816747 loss: 0.000622 2022/09/17 19:29:45 - mmengine - INFO - Epoch(train) [204][100/293] lr: 5.000000e-06 eta: 0:09:36 time: 0.340743 data_time: 0.073287 memory: 5151 loss_kpt: 0.000622 acc_pose: 0.843241 loss: 0.000622 2022/09/17 19:30:01 - mmengine - INFO - Epoch(train) [204][150/293] lr: 5.000000e-06 eta: 0:09:21 time: 0.324340 data_time: 0.067685 memory: 5151 loss_kpt: 0.000634 acc_pose: 0.823918 loss: 0.000634 2022/09/17 19:30:17 - mmengine - INFO - Epoch(train) [204][200/293] lr: 5.000000e-06 eta: 0:09:07 time: 0.324152 data_time: 0.059508 memory: 5151 loss_kpt: 0.000627 acc_pose: 0.873863 loss: 0.000627 2022/09/17 19:30:33 - mmengine - INFO - Epoch(train) [204][250/293] lr: 5.000000e-06 eta: 0:08:52 time: 0.322216 data_time: 0.058913 memory: 5151 loss_kpt: 0.000622 acc_pose: 0.855727 loss: 0.000622 2022/09/17 19:30:48 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 19:30:48 - mmengine - INFO - Saving checkpoint at 204 epochs 2022/09/17 19:31:08 - mmengine - INFO - Epoch(train) [205][50/293] lr: 5.000000e-06 eta: 0:08:24 time: 0.354917 data_time: 0.084786 memory: 5151 loss_kpt: 0.000622 acc_pose: 0.833504 loss: 0.000622 2022/09/17 19:31:24 - mmengine - INFO - Epoch(train) [205][100/293] lr: 5.000000e-06 eta: 0:08:09 time: 0.328365 data_time: 0.066333 memory: 5151 loss_kpt: 0.000614 acc_pose: 0.861284 loss: 0.000614 2022/09/17 19:31:41 - mmengine - INFO - Epoch(train) [205][150/293] lr: 5.000000e-06 eta: 0:07:55 time: 0.334222 data_time: 0.064885 memory: 5151 loss_kpt: 0.000620 acc_pose: 0.844124 loss: 0.000620 2022/09/17 19:31:58 - mmengine - INFO - Epoch(train) [205][200/293] lr: 5.000000e-06 eta: 0:07:40 time: 0.337453 data_time: 0.068323 memory: 5151 loss_kpt: 0.000627 acc_pose: 0.828222 loss: 0.000627 2022/09/17 19:32:07 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 19:32:15 - mmengine - INFO - Epoch(train) [205][250/293] lr: 5.000000e-06 eta: 0:07:25 time: 0.337021 data_time: 0.062041 memory: 5151 loss_kpt: 0.000626 acc_pose: 0.863363 loss: 0.000626 2022/09/17 19:32:29 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 19:32:29 - mmengine - INFO - Saving checkpoint at 205 epochs 2022/09/17 19:32:48 - mmengine - INFO - Epoch(train) [206][50/293] lr: 5.000000e-06 eta: 0:06:57 time: 0.335069 data_time: 0.068723 memory: 5151 loss_kpt: 0.000627 acc_pose: 0.850607 loss: 0.000627 2022/09/17 19:33:05 - mmengine - INFO - Epoch(train) [206][100/293] lr: 5.000000e-06 eta: 0:06:43 time: 0.327757 data_time: 0.060530 memory: 5151 loss_kpt: 0.000629 acc_pose: 0.885293 loss: 0.000629 2022/09/17 19:33:22 - mmengine - INFO - Epoch(train) [206][150/293] lr: 5.000000e-06 eta: 0:06:28 time: 0.344908 data_time: 0.072871 memory: 5151 loss_kpt: 0.000620 acc_pose: 0.876861 loss: 0.000620 2022/09/17 19:33:38 - mmengine - INFO - Epoch(train) [206][200/293] lr: 5.000000e-06 eta: 0:06:13 time: 0.323553 data_time: 0.059516 memory: 5151 loss_kpt: 0.000624 acc_pose: 0.832485 loss: 0.000624 2022/09/17 19:33:55 - mmengine - INFO - Epoch(train) [206][250/293] lr: 5.000000e-06 eta: 0:05:59 time: 0.340695 data_time: 0.068951 memory: 5151 loss_kpt: 0.000614 acc_pose: 0.838588 loss: 0.000614 2022/09/17 19:34:10 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 19:34:10 - mmengine - INFO - Saving checkpoint at 206 epochs 2022/09/17 19:34:30 - mmengine - INFO - Epoch(train) [207][50/293] lr: 5.000000e-06 eta: 0:05:31 time: 0.340866 data_time: 0.073963 memory: 5151 loss_kpt: 0.000610 acc_pose: 0.819881 loss: 0.000610 2022/09/17 19:34:46 - mmengine - INFO - Epoch(train) [207][100/293] lr: 5.000000e-06 eta: 0:05:16 time: 0.338199 data_time: 0.068864 memory: 5151 loss_kpt: 0.000628 acc_pose: 0.879418 loss: 0.000628 2022/09/17 19:35:03 - mmengine - INFO - Epoch(train) [207][150/293] lr: 5.000000e-06 eta: 0:05:01 time: 0.338684 data_time: 0.065358 memory: 5151 loss_kpt: 0.000614 acc_pose: 0.888498 loss: 0.000614 2022/09/17 19:35:21 - mmengine - INFO - Epoch(train) [207][200/293] lr: 5.000000e-06 eta: 0:04:47 time: 0.348333 data_time: 0.069953 memory: 5151 loss_kpt: 0.000629 acc_pose: 0.847410 loss: 0.000629 2022/09/17 19:35:38 - mmengine - INFO - Epoch(train) [207][250/293] lr: 5.000000e-06 eta: 0:04:32 time: 0.336430 data_time: 0.063324 memory: 5151 loss_kpt: 0.000638 acc_pose: 0.867852 loss: 0.000638 2022/09/17 19:35:52 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 19:35:52 - mmengine - INFO - Saving checkpoint at 207 epochs 2022/09/17 19:36:12 - mmengine - INFO - Epoch(train) [208][50/293] lr: 5.000000e-06 eta: 0:04:04 time: 0.344157 data_time: 0.076353 memory: 5151 loss_kpt: 0.000618 acc_pose: 0.866201 loss: 0.000618 2022/09/17 19:36:29 - mmengine - INFO - Epoch(train) [208][100/293] lr: 5.000000e-06 eta: 0:03:50 time: 0.342875 data_time: 0.070442 memory: 5151 loss_kpt: 0.000630 acc_pose: 0.855927 loss: 0.000630 2022/09/17 19:36:46 - mmengine - INFO - Epoch(train) [208][150/293] lr: 5.000000e-06 eta: 0:03:35 time: 0.335045 data_time: 0.071994 memory: 5151 loss_kpt: 0.000607 acc_pose: 0.826291 loss: 0.000607 2022/09/17 19:37:02 - mmengine - INFO - Epoch(train) [208][200/293] lr: 5.000000e-06 eta: 0:03:20 time: 0.330284 data_time: 0.071359 memory: 5151 loss_kpt: 0.000624 acc_pose: 0.841554 loss: 0.000624 2022/09/17 19:37:19 - mmengine - INFO - Epoch(train) [208][250/293] lr: 5.000000e-06 eta: 0:03:05 time: 0.329661 data_time: 0.064681 memory: 5151 loss_kpt: 0.000630 acc_pose: 0.851570 loss: 0.000630 2022/09/17 19:37:34 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 19:37:34 - mmengine - INFO - Saving checkpoint at 208 epochs 2022/09/17 19:37:54 - mmengine - INFO - Epoch(train) [209][50/293] lr: 5.000000e-06 eta: 0:02:38 time: 0.349723 data_time: 0.072752 memory: 5151 loss_kpt: 0.000621 acc_pose: 0.817899 loss: 0.000621 2022/09/17 19:37:56 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 19:38:10 - mmengine - INFO - Epoch(train) [209][100/293] lr: 5.000000e-06 eta: 0:02:23 time: 0.335205 data_time: 0.065192 memory: 5151 loss_kpt: 0.000626 acc_pose: 0.832383 loss: 0.000626 2022/09/17 19:38:27 - mmengine - INFO - Epoch(train) [209][150/293] lr: 5.000000e-06 eta: 0:02:08 time: 0.340141 data_time: 0.062742 memory: 5151 loss_kpt: 0.000621 acc_pose: 0.842297 loss: 0.000621 2022/09/17 19:38:44 - mmengine - INFO - Epoch(train) [209][200/293] lr: 5.000000e-06 eta: 0:01:54 time: 0.342774 data_time: 0.066778 memory: 5151 loss_kpt: 0.000617 acc_pose: 0.840950 loss: 0.000617 2022/09/17 19:39:01 - mmengine - INFO - Epoch(train) [209][250/293] lr: 5.000000e-06 eta: 0:01:39 time: 0.335898 data_time: 0.062919 memory: 5151 loss_kpt: 0.000617 acc_pose: 0.865221 loss: 0.000617 2022/09/17 19:39:16 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 19:39:16 - mmengine - INFO - Saving checkpoint at 209 epochs 2022/09/17 19:39:35 - mmengine - INFO - Epoch(train) [210][50/293] lr: 5.000000e-06 eta: 0:01:11 time: 0.337225 data_time: 0.071864 memory: 5151 loss_kpt: 0.000620 acc_pose: 0.863715 loss: 0.000620 2022/09/17 19:39:52 - mmengine - INFO - Epoch(train) [210][100/293] lr: 5.000000e-06 eta: 0:00:56 time: 0.343738 data_time: 0.065093 memory: 5151 loss_kpt: 0.000628 acc_pose: 0.876324 loss: 0.000628 2022/09/17 19:40:09 - mmengine - INFO - Epoch(train) [210][150/293] lr: 5.000000e-06 eta: 0:00:42 time: 0.340738 data_time: 0.062608 memory: 5151 loss_kpt: 0.000611 acc_pose: 0.879894 loss: 0.000611 2022/09/17 19:40:27 - mmengine - INFO - Epoch(train) [210][200/293] lr: 5.000000e-06 eta: 0:00:27 time: 0.352637 data_time: 0.072953 memory: 5151 loss_kpt: 0.000623 acc_pose: 0.837194 loss: 0.000623 2022/09/17 19:40:44 - mmengine - INFO - Epoch(train) [210][250/293] lr: 5.000000e-06 eta: 0:00:12 time: 0.349947 data_time: 0.069572 memory: 5151 loss_kpt: 0.000622 acc_pose: 0.864726 loss: 0.000622 2022/09/17 19:40:59 - mmengine - INFO - Exp name: td-hm_vipnas-res50_8xb64-210e_coco-256x192_20220917_130414 2022/09/17 19:40:59 - mmengine - INFO - Saving checkpoint at 210 epochs 2022/09/17 19:41:08 - mmengine - INFO - Epoch(val) [210][50/407] eta: 0:00:42 time: 0.120360 data_time: 0.053646 memory: 5151 2022/09/17 19:41:14 - mmengine - INFO - Epoch(val) [210][100/407] eta: 0:00:36 time: 0.119626 data_time: 0.047921 memory: 331 2022/09/17 19:41:20 - mmengine - INFO - Epoch(val) [210][150/407] eta: 0:00:29 time: 0.115091 data_time: 0.048076 memory: 331 2022/09/17 19:41:25 - mmengine - INFO - Epoch(val) [210][200/407] eta: 0:00:23 time: 0.115703 data_time: 0.048915 memory: 331 2022/09/17 19:41:31 - mmengine - INFO - Epoch(val) [210][250/407] eta: 0:00:18 time: 0.117667 data_time: 0.050474 memory: 331 2022/09/17 19:41:37 - mmengine - INFO - Epoch(val) [210][300/407] eta: 0:00:12 time: 0.114193 data_time: 0.046421 memory: 331 2022/09/17 19:41:43 - mmengine - INFO - Epoch(val) [210][350/407] eta: 0:00:06 time: 0.118540 data_time: 0.051329 memory: 331 2022/09/17 19:41:48 - mmengine - INFO - Epoch(val) [210][400/407] eta: 0:00:00 time: 0.109580 data_time: 0.044312 memory: 331 2022/09/17 19:42:25 - mmengine - INFO - Evaluating CocoMetric... 2022/09/17 19:42:40 - mmengine - INFO - Epoch(val) [210][407/407] coco/AP: 0.711133 coco/AP .5: 0.893661 coco/AP .75: 0.786831 coco/AP (M): 0.677861 coco/AP (L): 0.776417 coco/AR: 0.768577 coco/AR .5: 0.934037 coco/AR .75: 0.835800 coco/AR (M): 0.726687 coco/AR (L): 0.829617 2022/09/17 19:42:40 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220917/vipnas_res50/best_coco/AP_epoch_200.pth is removed 2022/09/17 19:42:42 - mmengine - INFO - The best checkpoint with 0.7111 coco/AP at 210 epoch is saved to best_coco/AP_epoch_210.pth.