2022/09/08 12:36:55 - 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: 2006828410 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 ------------------------------------------------------------ 2022/09/08 12:36:57 - 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='HRNet', in_channels=3, extra=dict( stage1=dict( num_modules=1, num_branches=1, block='BOTTLENECK', num_blocks=(4, ), num_channels=(64, )), stage2=dict( num_modules=1, num_branches=2, block='BASIC', num_blocks=(4, 4), num_channels=(32, 64)), stage3=dict( num_modules=4, num_branches=3, block='BASIC', num_blocks=(4, 4, 4), num_channels=(32, 64, 128)), stage4=dict( num_modules=3, num_branches=4, block='BASIC', num_blocks=(4, 4, 4, 4), num_channels=(32, 64, 128, 256))), init_cfg=dict( type='Pretrained', checkpoint= 'https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth' )), head=dict( type='HeatmapHead', in_channels=32, out_channels=17, deconv_out_channels=None, 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'), 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'), 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/20220908/hrnet_w32_256/' 2022/09/08 12:37:32 - 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. 2022/09/08 12:37:32 - 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. 2022/09/08 12:37:32 - 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. 2022/09/08 12:37:32 - 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. 2022/09/08 12:37:32 - 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. 2022/09/08 12:37:32 - 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. 2022/09/08 12:37:32 - 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. 2022/09/08 12:37:32 - 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. 2022/09/08 12:37:36 - 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. 2022/09/08 12:37:38 - 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. 2022/09/08 12:37:40 - 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. 2022/09/08 12:37:40 - 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([64, 3, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.0.conv1.weight - torch.Size([64, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.0.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.0.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.0.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.0.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.0.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.0.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.0.bn3.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.0.bn3.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.0.downsample.0.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.0.downsample.1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.0.downsample.1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.1.conv1.weight - torch.Size([64, 256, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.1.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.1.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.1.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.1.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.1.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.1.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.1.bn3.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.1.bn3.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.2.conv1.weight - torch.Size([64, 256, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.2.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.2.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.2.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.2.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.2.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.2.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.2.bn3.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.2.bn3.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.3.conv1.weight - torch.Size([64, 256, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.3.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.3.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.3.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.3.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.3.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.3.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.3.bn3.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.3.bn3.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.transition1.0.0.weight - torch.Size([32, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.transition1.0.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.transition1.0.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.transition1.1.0.0.weight - torch.Size([64, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.transition1.1.0.1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.transition1.1.0.1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.0.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.0.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.0.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.0.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.0.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.0.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.1.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.1.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.1.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.1.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.1.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.1.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.2.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.2.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.2.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.2.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.2.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.2.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.3.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.3.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.3.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.3.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.3.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.3.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.0.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.0.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.0.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.0.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.0.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.0.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.1.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.1.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.1.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.1.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.1.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.1.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.2.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.2.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.2.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.2.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.2.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.2.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.3.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.3.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.3.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.3.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.3.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.3.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.fuse_layers.0.1.0.weight - torch.Size([32, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.fuse_layers.0.1.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.fuse_layers.0.1.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.fuse_layers.1.0.0.0.weight - torch.Size([64, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.fuse_layers.1.0.0.1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.fuse_layers.1.0.0.1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.transition2.2.0.0.weight - torch.Size([128, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.transition2.2.0.1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.transition2.2.0.1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.0.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.0.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.0.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.0.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.0.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.0.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.1.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.1.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.1.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.1.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.1.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.1.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.2.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.2.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.2.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.2.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.2.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.2.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.3.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.3.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.3.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.3.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.3.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.3.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.0.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.0.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.0.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.0.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.0.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.0.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.1.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.1.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.1.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.1.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.1.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.1.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.2.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.2.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.2.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.2.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.2.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.2.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.3.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.3.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.3.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.3.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.3.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.3.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.0.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.0.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.0.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.0.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.0.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.0.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.1.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.1.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.1.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.1.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.1.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.1.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.2.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.2.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.2.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.2.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.2.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.2.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.3.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.3.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.3.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.3.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.3.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.3.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.0.1.0.weight - torch.Size([32, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.0.1.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.0.1.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.0.2.0.weight - torch.Size([32, 128, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.0.2.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.0.2.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.1.0.0.0.weight - torch.Size([64, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.1.0.0.1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.1.0.0.1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.1.2.0.weight - torch.Size([64, 128, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.1.2.1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.1.2.1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.2.0.0.0.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.2.0.0.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.2.0.0.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.2.0.1.0.weight - torch.Size([128, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.2.0.1.1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.2.0.1.1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.2.1.0.0.weight - torch.Size([128, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.2.1.0.1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.2.1.0.1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.0.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.0.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.0.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.0.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.0.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.0.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.1.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.1.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.1.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.1.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.1.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.1.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.2.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.2.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.2.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.2.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.2.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.2.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.3.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.3.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.3.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.3.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.3.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.3.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.0.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.0.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.0.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.0.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.0.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.0.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.1.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.1.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.1.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.1.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.1.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.1.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.2.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.2.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.2.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.2.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.2.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.2.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.3.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.3.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.3.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.3.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.3.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.3.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.0.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.0.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.0.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.0.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.0.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.0.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.1.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.1.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.1.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.1.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.1.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.1.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.2.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.2.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.2.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.2.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.2.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.2.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.3.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.3.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.3.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.3.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.3.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.3.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.0.1.0.weight - torch.Size([32, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.0.1.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.0.1.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.0.2.0.weight - torch.Size([32, 128, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.0.2.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.0.2.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.1.0.0.0.weight - torch.Size([64, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.1.0.0.1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.1.0.0.1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.1.2.0.weight - torch.Size([64, 128, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.1.2.1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.1.2.1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.2.0.0.0.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.2.0.0.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.2.0.0.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.2.0.1.0.weight - torch.Size([128, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.2.0.1.1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.2.0.1.1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.2.1.0.0.weight - torch.Size([128, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.2.1.0.1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.2.1.0.1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.0.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.0.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.0.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.0.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.0.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.0.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.1.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.1.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.1.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.1.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.1.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.1.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.2.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.2.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.2.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.2.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.2.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.2.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.3.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.3.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.3.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.3.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.3.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.3.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.0.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.0.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.0.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.0.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.0.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.0.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.1.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.1.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.1.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.1.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.1.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.1.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.2.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.2.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.2.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.2.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.2.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.2.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.3.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.3.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.3.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.3.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.3.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.3.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.0.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.0.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.0.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.0.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.0.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.0.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.1.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.1.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.1.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.1.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.1.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.1.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.2.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.2.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.2.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.2.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.2.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.2.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.3.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.3.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.3.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.3.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.3.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.3.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.0.1.0.weight - torch.Size([32, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.0.1.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.0.1.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.0.2.0.weight - torch.Size([32, 128, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.0.2.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.0.2.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.1.0.0.0.weight - torch.Size([64, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.1.0.0.1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.1.0.0.1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.1.2.0.weight - torch.Size([64, 128, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.1.2.1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.1.2.1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.2.0.0.0.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.2.0.0.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.2.0.0.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.2.0.1.0.weight - torch.Size([128, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.2.0.1.1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.2.0.1.1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.2.1.0.0.weight - torch.Size([128, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.2.1.0.1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.2.1.0.1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.0.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.0.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.0.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.0.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.0.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.0.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.1.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.1.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.1.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.1.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.1.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.1.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.2.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.2.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.2.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.2.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.2.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.2.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.3.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.3.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.3.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.3.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.3.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.3.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.0.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.0.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.0.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.0.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.0.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.0.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.1.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.1.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.1.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.1.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.1.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.1.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.2.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.2.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.2.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.2.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.2.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.2.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.3.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.3.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.3.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.3.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.3.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.3.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.0.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.0.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.0.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.0.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.0.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.0.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.1.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.1.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.1.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.1.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.1.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.1.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.2.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.2.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.2.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.2.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.2.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.2.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.3.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.3.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.3.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.3.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.3.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.3.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.0.1.0.weight - torch.Size([32, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.0.1.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.0.1.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.0.2.0.weight - torch.Size([32, 128, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.0.2.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.0.2.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.1.0.0.0.weight - torch.Size([64, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.1.0.0.1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.1.0.0.1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.1.2.0.weight - torch.Size([64, 128, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.1.2.1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.1.2.1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.2.0.0.0.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.2.0.0.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.2.0.0.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.2.0.1.0.weight - torch.Size([128, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.2.0.1.1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.2.0.1.1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.2.1.0.0.weight - torch.Size([128, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.2.1.0.1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.2.1.0.1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.transition3.3.0.0.weight - torch.Size([256, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.transition3.3.0.1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.transition3.3.0.1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.0.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.0.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.0.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.0.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.0.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.0.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.1.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.1.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.1.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.1.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.1.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.1.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.2.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.2.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.2.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.2.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.2.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.2.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.3.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.3.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.3.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.3.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.3.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.3.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.0.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.0.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.0.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.0.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.0.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.0.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.1.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.1.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.1.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.1.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.1.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.1.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.2.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.2.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.2.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.2.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.2.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.2.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.3.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.3.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.3.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.3.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.3.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.3.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.0.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.0.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.0.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.0.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.0.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.0.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.1.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.1.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.1.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.1.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.1.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.1.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.2.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.2.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.2.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.2.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.2.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.2.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.3.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.3.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.3.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.3.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.3.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.3.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.0.conv1.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.0.bn1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.0.bn1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.0.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.0.bn2.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.0.bn2.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.1.conv1.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.1.bn1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.1.bn1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.1.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.1.bn2.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.1.bn2.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.2.conv1.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.2.bn1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.2.bn1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.2.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.2.bn2.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.2.bn2.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.3.conv1.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.3.bn1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.3.bn1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.3.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.3.bn2.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.3.bn2.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.0.1.0.weight - torch.Size([32, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.0.1.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.0.1.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.0.2.0.weight - torch.Size([32, 128, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.0.2.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.0.2.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.0.3.0.weight - torch.Size([32, 256, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.0.3.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.0.3.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.1.0.0.0.weight - torch.Size([64, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.1.0.0.1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.1.0.0.1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.1.2.0.weight - torch.Size([64, 128, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.1.2.1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.1.2.1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.1.3.0.weight - torch.Size([64, 256, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.1.3.1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.1.3.1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.2.0.0.0.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.2.0.0.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.2.0.0.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.2.0.1.0.weight - torch.Size([128, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.2.0.1.1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.2.0.1.1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.2.1.0.0.weight - torch.Size([128, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.2.1.0.1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.2.1.0.1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.2.3.0.weight - torch.Size([128, 256, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.2.3.1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.2.3.1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.3.0.0.0.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.3.0.0.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.3.0.0.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.3.0.1.0.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.3.0.1.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.3.0.1.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.3.0.2.0.weight - torch.Size([256, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.3.0.2.1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.3.0.2.1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.3.1.0.0.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.3.1.0.1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.3.1.0.1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.3.1.1.0.weight - torch.Size([256, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.3.1.1.1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.3.1.1.1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.3.2.0.0.weight - torch.Size([256, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.3.2.0.1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.3.2.0.1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.0.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.0.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.0.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.0.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.0.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.0.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.1.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.1.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.1.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.1.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.1.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.1.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.2.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.2.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.2.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.2.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.2.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.2.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.3.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.3.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.3.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.3.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.3.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.3.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.0.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.0.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.0.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.0.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.0.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.0.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.1.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.1.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.1.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.1.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.1.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.1.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.2.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.2.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.2.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.2.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.2.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.2.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.3.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.3.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.3.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.3.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.3.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.3.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.0.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.0.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.0.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.0.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.0.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.0.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.1.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.1.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.1.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.1.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.1.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.1.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.2.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.2.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.2.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.2.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.2.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.2.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.3.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.3.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.3.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.3.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.3.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.3.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.0.conv1.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.0.bn1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.0.bn1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.0.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.0.bn2.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.0.bn2.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.1.conv1.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.1.bn1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.1.bn1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.1.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.1.bn2.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.1.bn2.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.2.conv1.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.2.bn1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.2.bn1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.2.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.2.bn2.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.2.bn2.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.3.conv1.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.3.bn1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.3.bn1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.3.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.3.bn2.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.3.bn2.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.0.1.0.weight - torch.Size([32, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.0.1.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.0.1.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.0.2.0.weight - torch.Size([32, 128, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.0.2.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.0.2.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.0.3.0.weight - torch.Size([32, 256, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.0.3.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.0.3.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.1.0.0.0.weight - torch.Size([64, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.1.0.0.1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.1.0.0.1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.1.2.0.weight - torch.Size([64, 128, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.1.2.1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.1.2.1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.1.3.0.weight - torch.Size([64, 256, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.1.3.1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.1.3.1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.2.0.0.0.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.2.0.0.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.2.0.0.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.2.0.1.0.weight - torch.Size([128, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.2.0.1.1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.2.0.1.1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.2.1.0.0.weight - torch.Size([128, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.2.1.0.1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.2.1.0.1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.2.3.0.weight - torch.Size([128, 256, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.2.3.1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.2.3.1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.3.0.0.0.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.3.0.0.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.3.0.0.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.3.0.1.0.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.3.0.1.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.3.0.1.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.3.0.2.0.weight - torch.Size([256, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.3.0.2.1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.3.0.2.1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.3.1.0.0.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.3.1.0.1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.3.1.0.1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.3.1.1.0.weight - torch.Size([256, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.3.1.1.1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.3.1.1.1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.3.2.0.0.weight - torch.Size([256, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.3.2.0.1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.3.2.0.1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.0.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.0.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.0.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.0.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.0.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.0.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.1.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.1.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.1.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.1.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.1.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.1.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.2.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.2.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.2.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.2.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.2.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.2.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.3.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.3.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.3.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.3.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.3.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.3.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.0.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.0.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.0.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.0.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.0.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.0.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.1.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.1.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.1.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.1.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.1.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.1.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.2.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.2.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.2.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.2.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.2.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.2.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.3.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.3.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.3.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.3.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.3.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.3.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.0.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.0.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.0.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.0.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.0.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.0.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.1.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.1.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.1.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.1.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.1.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.1.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.2.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.2.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.2.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.2.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.2.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.2.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.3.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.3.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.3.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.3.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.3.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.3.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.0.conv1.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.0.bn1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.0.bn1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.0.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.0.bn2.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.0.bn2.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.1.conv1.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.1.bn1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.1.bn1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.1.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.1.bn2.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.1.bn2.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.2.conv1.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.2.bn1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.2.bn1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.2.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.2.bn2.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.2.bn2.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.3.conv1.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.3.bn1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.3.bn1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.3.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.3.bn2.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.3.bn2.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.fuse_layers.0.1.0.weight - torch.Size([32, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.fuse_layers.0.1.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.fuse_layers.0.1.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.fuse_layers.0.2.0.weight - torch.Size([32, 128, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.fuse_layers.0.2.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.fuse_layers.0.2.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.fuse_layers.0.3.0.weight - torch.Size([32, 256, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.fuse_layers.0.3.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.fuse_layers.0.3.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth head.final_layer.weight - torch.Size([17, 32, 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 2022/09/08 12:37:55 - mmengine - INFO - Checkpoints will be saved to /mnt/lustre/liqikai/work_dirs/20220908/hrnet_w32_256 by HardDiskBackend. 2022/09/08 12:38:57 - mmengine - INFO - Epoch(train) [1][50/293] lr: 4.954910e-05 eta: 21:08:44 time: 1.238197 data_time: 0.450790 memory: 9871 loss_kpt: 0.002195 acc_pose: 0.116425 loss: 0.002195 2022/09/08 12:39:46 - mmengine - INFO - Epoch(train) [1][100/293] lr: 9.959920e-05 eta: 19:02:58 time: 0.994538 data_time: 0.169134 memory: 9871 loss_kpt: 0.001901 acc_pose: 0.351052 loss: 0.001901 2022/09/08 12:40:31 - mmengine - INFO - Epoch(train) [1][150/293] lr: 1.496493e-04 eta: 17:47:35 time: 0.898025 data_time: 0.087048 memory: 9871 loss_kpt: 0.001635 acc_pose: 0.416844 loss: 0.001635 2022/09/08 12:40:56 - mmengine - INFO - Epoch(train) [1][200/293] lr: 1.996994e-04 eta: 15:24:15 time: 0.486080 data_time: 0.073822 memory: 9871 loss_kpt: 0.001428 acc_pose: 0.535879 loss: 0.001428 2022/09/08 12:41:37 - mmengine - INFO - Epoch(train) [1][250/293] lr: 2.497495e-04 eta: 15:07:52 time: 0.827735 data_time: 0.070270 memory: 9871 loss_kpt: 0.001300 acc_pose: 0.545446 loss: 0.001300 2022/09/08 12:41:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 12:41:59 - mmengine - INFO - Saving checkpoint at 1 epochs 2022/09/08 12:42:29 - mmengine - INFO - Epoch(train) [2][50/293] lr: 3.428427e-04 eta: 12:15:05 time: 0.500276 data_time: 0.080773 memory: 9871 loss_kpt: 0.001198 acc_pose: 0.597114 loss: 0.001198 2022/09/08 12:42:53 - mmengine - INFO - Epoch(train) [2][100/293] lr: 3.928928e-04 eta: 11:43:47 time: 0.484110 data_time: 0.071045 memory: 9871 loss_kpt: 0.001154 acc_pose: 0.666083 loss: 0.001154 2022/09/08 12:43:18 - mmengine - INFO - Epoch(train) [2][150/293] lr: 4.429429e-04 eta: 11:21:09 time: 0.498726 data_time: 0.073274 memory: 9871 loss_kpt: 0.001148 acc_pose: 0.641547 loss: 0.001148 2022/09/08 12:43:43 - mmengine - INFO - Epoch(train) [2][200/293] lr: 4.929930e-04 eta: 11:02:28 time: 0.493290 data_time: 0.073146 memory: 9871 loss_kpt: 0.001119 acc_pose: 0.675142 loss: 0.001119 2022/09/08 12:44:08 - mmengine - INFO - Epoch(train) [2][250/293] lr: 5.000000e-04 eta: 10:47:55 time: 0.501594 data_time: 0.076936 memory: 9871 loss_kpt: 0.001109 acc_pose: 0.583844 loss: 0.001109 2022/09/08 12:44:28 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 12:44:28 - mmengine - INFO - Saving checkpoint at 2 epochs 2022/09/08 12:44:59 - mmengine - INFO - Epoch(train) [3][50/293] lr: 5.000000e-04 eta: 9:52:50 time: 0.507682 data_time: 0.084962 memory: 9871 loss_kpt: 0.001080 acc_pose: 0.674843 loss: 0.001080 2022/09/08 12:45:24 - mmengine - INFO - Epoch(train) [3][100/293] lr: 5.000000e-04 eta: 9:46:40 time: 0.507317 data_time: 0.075191 memory: 9871 loss_kpt: 0.001045 acc_pose: 0.679100 loss: 0.001045 2022/09/08 12:45:48 - mmengine - INFO - Epoch(train) [3][150/293] lr: 5.000000e-04 eta: 9:39:41 time: 0.484146 data_time: 0.075727 memory: 9871 loss_kpt: 0.001009 acc_pose: 0.679501 loss: 0.001009 2022/09/08 12:46:13 - mmengine - INFO - Epoch(train) [3][200/293] lr: 5.000000e-04 eta: 9:34:46 time: 0.503149 data_time: 0.071090 memory: 9871 loss_kpt: 0.001014 acc_pose: 0.633057 loss: 0.001014 2022/09/08 12:46:38 - mmengine - INFO - Epoch(train) [3][250/293] lr: 5.000000e-04 eta: 9:29:59 time: 0.496351 data_time: 0.075880 memory: 9871 loss_kpt: 0.001001 acc_pose: 0.723261 loss: 0.001001 2022/09/08 12:46:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 12:46:59 - mmengine - INFO - Saving checkpoint at 3 epochs 2022/09/08 12:47:29 - mmengine - INFO - Epoch(train) [4][50/293] lr: 5.000000e-04 eta: 8:59:21 time: 0.500825 data_time: 0.079953 memory: 9871 loss_kpt: 0.001009 acc_pose: 0.679492 loss: 0.001009 2022/09/08 12:47:54 - mmengine - INFO - Epoch(train) [4][100/293] lr: 5.000000e-04 eta: 8:56:28 time: 0.486433 data_time: 0.074906 memory: 9871 loss_kpt: 0.000966 acc_pose: 0.715505 loss: 0.000966 2022/09/08 12:48:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 12:48:19 - mmengine - INFO - Epoch(train) [4][150/293] lr: 5.000000e-04 eta: 8:54:31 time: 0.501083 data_time: 0.071175 memory: 9871 loss_kpt: 0.000959 acc_pose: 0.717888 loss: 0.000959 2022/09/08 12:48:43 - mmengine - INFO - Epoch(train) [4][200/293] lr: 5.000000e-04 eta: 8:52:19 time: 0.492443 data_time: 0.078866 memory: 9871 loss_kpt: 0.000977 acc_pose: 0.689083 loss: 0.000977 2022/09/08 12:49:08 - mmengine - INFO - Epoch(train) [4][250/293] lr: 5.000000e-04 eta: 8:50:22 time: 0.494379 data_time: 0.077353 memory: 9871 loss_kpt: 0.000948 acc_pose: 0.714463 loss: 0.000948 2022/09/08 12:49:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 12:49:30 - mmengine - INFO - Saving checkpoint at 4 epochs 2022/09/08 12:50:00 - mmengine - INFO - Epoch(train) [5][50/293] lr: 5.000000e-04 eta: 8:30:21 time: 0.513049 data_time: 0.086408 memory: 9871 loss_kpt: 0.000927 acc_pose: 0.731968 loss: 0.000927 2022/09/08 12:50:24 - mmengine - INFO - Epoch(train) [5][100/293] lr: 5.000000e-04 eta: 8:29:24 time: 0.494419 data_time: 0.070419 memory: 9871 loss_kpt: 0.000950 acc_pose: 0.714939 loss: 0.000950 2022/09/08 12:50:49 - mmengine - INFO - Epoch(train) [5][150/293] lr: 5.000000e-04 eta: 8:28:44 time: 0.500821 data_time: 0.072008 memory: 9871 loss_kpt: 0.000920 acc_pose: 0.641027 loss: 0.000920 2022/09/08 12:51:14 - mmengine - INFO - Epoch(train) [5][200/293] lr: 5.000000e-04 eta: 8:27:51 time: 0.494575 data_time: 0.075749 memory: 9871 loss_kpt: 0.000906 acc_pose: 0.743803 loss: 0.000906 2022/09/08 12:51:39 - mmengine - INFO - Epoch(train) [5][250/293] lr: 5.000000e-04 eta: 8:26:57 time: 0.492606 data_time: 0.072112 memory: 9871 loss_kpt: 0.000911 acc_pose: 0.745978 loss: 0.000911 2022/09/08 12:52:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 12:52:00 - mmengine - INFO - Saving checkpoint at 5 epochs 2022/09/08 12:52:30 - mmengine - INFO - Epoch(train) [6][50/293] lr: 5.000000e-04 eta: 8:11:47 time: 0.505768 data_time: 0.079918 memory: 9871 loss_kpt: 0.000904 acc_pose: 0.755679 loss: 0.000904 2022/09/08 12:52:55 - mmengine - INFO - Epoch(train) [6][100/293] lr: 5.000000e-04 eta: 8:11:49 time: 0.505569 data_time: 0.079480 memory: 9871 loss_kpt: 0.000905 acc_pose: 0.714000 loss: 0.000905 2022/09/08 12:53:20 - mmengine - INFO - Epoch(train) [6][150/293] lr: 5.000000e-04 eta: 8:11:24 time: 0.491736 data_time: 0.072076 memory: 9871 loss_kpt: 0.000884 acc_pose: 0.706718 loss: 0.000884 2022/09/08 12:53:45 - mmengine - INFO - Epoch(train) [6][200/293] lr: 5.000000e-04 eta: 8:11:16 time: 0.501171 data_time: 0.079540 memory: 9871 loss_kpt: 0.000878 acc_pose: 0.712594 loss: 0.000878 2022/09/08 12:54:10 - mmengine - INFO - Epoch(train) [6][250/293] lr: 5.000000e-04 eta: 8:10:57 time: 0.495670 data_time: 0.070947 memory: 9871 loss_kpt: 0.000889 acc_pose: 0.754083 loss: 0.000889 2022/09/08 12:54:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 12:54:30 - mmengine - INFO - Saving checkpoint at 6 epochs 2022/09/08 12:55:01 - mmengine - INFO - Epoch(train) [7][50/293] lr: 5.000000e-04 eta: 7:59:04 time: 0.512371 data_time: 0.081177 memory: 9871 loss_kpt: 0.000891 acc_pose: 0.652182 loss: 0.000891 2022/09/08 12:55:25 - mmengine - INFO - Epoch(train) [7][100/293] lr: 5.000000e-04 eta: 7:58:55 time: 0.490590 data_time: 0.074857 memory: 9871 loss_kpt: 0.000877 acc_pose: 0.728523 loss: 0.000877 2022/09/08 12:55:51 - mmengine - INFO - Epoch(train) [7][150/293] lr: 5.000000e-04 eta: 7:59:15 time: 0.509686 data_time: 0.076948 memory: 9871 loss_kpt: 0.000862 acc_pose: 0.710055 loss: 0.000862 2022/09/08 12:56:16 - mmengine - INFO - Epoch(train) [7][200/293] lr: 5.000000e-04 eta: 7:59:24 time: 0.503790 data_time: 0.072475 memory: 9871 loss_kpt: 0.000878 acc_pose: 0.719014 loss: 0.000878 2022/09/08 12:56:36 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 12:56:40 - mmengine - INFO - Epoch(train) [7][250/293] lr: 5.000000e-04 eta: 7:59:04 time: 0.486178 data_time: 0.070945 memory: 9871 loss_kpt: 0.000861 acc_pose: 0.769976 loss: 0.000861 2022/09/08 12:57:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 12:57:02 - mmengine - INFO - Saving checkpoint at 7 epochs 2022/09/08 12:57:32 - mmengine - INFO - Epoch(train) [8][50/293] lr: 5.000000e-04 eta: 7:48:58 time: 0.501033 data_time: 0.083294 memory: 9871 loss_kpt: 0.000855 acc_pose: 0.690552 loss: 0.000855 2022/09/08 12:57:56 - mmengine - INFO - Epoch(train) [8][100/293] lr: 5.000000e-04 eta: 7:48:55 time: 0.488444 data_time: 0.075194 memory: 9871 loss_kpt: 0.000864 acc_pose: 0.736610 loss: 0.000864 2022/09/08 12:58:22 - mmengine - INFO - Epoch(train) [8][150/293] lr: 5.000000e-04 eta: 7:49:16 time: 0.507083 data_time: 0.076637 memory: 9871 loss_kpt: 0.000854 acc_pose: 0.749938 loss: 0.000854 2022/09/08 12:58:47 - mmengine - INFO - Epoch(train) [8][200/293] lr: 5.000000e-04 eta: 7:49:30 time: 0.503591 data_time: 0.074926 memory: 9871 loss_kpt: 0.000867 acc_pose: 0.722563 loss: 0.000867 2022/09/08 12:59:12 - mmengine - INFO - Epoch(train) [8][250/293] lr: 5.000000e-04 eta: 7:49:30 time: 0.493356 data_time: 0.075334 memory: 9871 loss_kpt: 0.000855 acc_pose: 0.756971 loss: 0.000855 2022/09/08 12:59:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 12:59:32 - mmengine - INFO - Saving checkpoint at 8 epochs 2022/09/08 13:00:02 - mmengine - INFO - Epoch(train) [9][50/293] lr: 5.000000e-04 eta: 7:41:03 time: 0.510305 data_time: 0.083221 memory: 9871 loss_kpt: 0.000846 acc_pose: 0.684177 loss: 0.000846 2022/09/08 13:00:27 - mmengine - INFO - Epoch(train) [9][100/293] lr: 5.000000e-04 eta: 7:41:15 time: 0.496929 data_time: 0.075387 memory: 9871 loss_kpt: 0.000841 acc_pose: 0.698404 loss: 0.000841 2022/09/08 13:00:53 - mmengine - INFO - Epoch(train) [9][150/293] lr: 5.000000e-04 eta: 7:41:49 time: 0.516671 data_time: 0.077580 memory: 9871 loss_kpt: 0.000833 acc_pose: 0.703162 loss: 0.000833 2022/09/08 13:01:18 - mmengine - INFO - Epoch(train) [9][200/293] lr: 5.000000e-04 eta: 7:41:57 time: 0.496409 data_time: 0.074990 memory: 9871 loss_kpt: 0.000841 acc_pose: 0.679101 loss: 0.000841 2022/09/08 13:01:43 - mmengine - INFO - Epoch(train) [9][250/293] lr: 5.000000e-04 eta: 7:42:04 time: 0.496912 data_time: 0.076185 memory: 9871 loss_kpt: 0.000833 acc_pose: 0.762707 loss: 0.000833 2022/09/08 13:02:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 13:02:04 - mmengine - INFO - Saving checkpoint at 9 epochs 2022/09/08 13:02:33 - mmengine - INFO - Epoch(train) [10][50/293] lr: 5.000000e-04 eta: 7:34:41 time: 0.510145 data_time: 0.087105 memory: 9871 loss_kpt: 0.000821 acc_pose: 0.761601 loss: 0.000821 2022/09/08 13:02:58 - mmengine - INFO - Epoch(train) [10][100/293] lr: 5.000000e-04 eta: 7:34:52 time: 0.495396 data_time: 0.075144 memory: 9871 loss_kpt: 0.000844 acc_pose: 0.781185 loss: 0.000844 2022/09/08 13:03:23 - mmengine - INFO - Epoch(train) [10][150/293] lr: 5.000000e-04 eta: 7:34:50 time: 0.484619 data_time: 0.071489 memory: 9871 loss_kpt: 0.000822 acc_pose: 0.778997 loss: 0.000822 2022/09/08 13:03:48 - mmengine - INFO - Epoch(train) [10][200/293] lr: 5.000000e-04 eta: 7:35:09 time: 0.505852 data_time: 0.082981 memory: 9871 loss_kpt: 0.000835 acc_pose: 0.732867 loss: 0.000835 2022/09/08 13:04:12 - mmengine - INFO - Epoch(train) [10][250/293] lr: 5.000000e-04 eta: 7:35:14 time: 0.492477 data_time: 0.074738 memory: 9871 loss_kpt: 0.000820 acc_pose: 0.792643 loss: 0.000820 2022/09/08 13:04:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 13:04:33 - mmengine - INFO - Saving checkpoint at 10 epochs 2022/09/08 13:04:52 - mmengine - INFO - Epoch(val) [10][50/407] eta: 0:01:38 time: 0.276851 data_time: 0.170879 memory: 9871 2022/09/08 13:05:05 - mmengine - INFO - Epoch(val) [10][100/407] eta: 0:01:18 time: 0.254575 data_time: 0.147999 memory: 920 2022/09/08 13:05:11 - mmengine - INFO - Epoch(val) [10][150/407] eta: 0:00:29 time: 0.113270 data_time: 0.009739 memory: 920 2022/09/08 13:05:22 - mmengine - INFO - Epoch(val) [10][200/407] eta: 0:00:44 time: 0.216212 data_time: 0.109428 memory: 920 2022/09/08 13:05:27 - mmengine - INFO - Epoch(val) [10][250/407] eta: 0:00:17 time: 0.113914 data_time: 0.009354 memory: 920 2022/09/08 13:05:33 - mmengine - INFO - Epoch(val) [10][300/407] eta: 0:00:12 time: 0.117011 data_time: 0.010244 memory: 920 2022/09/08 13:05:40 - mmengine - INFO - Epoch(val) [10][350/407] eta: 0:00:07 time: 0.130013 data_time: 0.025080 memory: 920 2022/09/08 13:05:46 - mmengine - INFO - Epoch(val) [10][400/407] eta: 0:00:00 time: 0.130066 data_time: 0.024446 memory: 920 2022/09/08 13:06:25 - mmengine - INFO - Evaluating CocoMetric... 2022/09/08 13:06:39 - mmengine - INFO - Epoch(val) [10][407/407] coco/AP: 0.654481 coco/AP .5: 0.870461 coco/AP .75: 0.726068 coco/AP (M): 0.619507 coco/AP (L): 0.719410 coco/AR: 0.718136 coco/AR .5: 0.913256 coco/AR .75: 0.786209 coco/AR (M): 0.673614 coco/AR (L): 0.781085 2022/09/08 13:06:42 - mmengine - INFO - The best checkpoint with 0.6545 coco/AP at 10 epoch is saved to best_coco/AP_epoch_10.pth. 2022/09/08 13:07:07 - mmengine - INFO - Epoch(train) [11][50/293] lr: 5.000000e-04 eta: 7:28:29 time: 0.498837 data_time: 0.082566 memory: 9871 loss_kpt: 0.000819 acc_pose: 0.759368 loss: 0.000819 2022/09/08 13:07:17 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 13:07:32 - mmengine - INFO - Epoch(train) [11][100/293] lr: 5.000000e-04 eta: 7:28:45 time: 0.500104 data_time: 0.071105 memory: 9871 loss_kpt: 0.000822 acc_pose: 0.783819 loss: 0.000822 2022/09/08 13:07:57 - mmengine - INFO - Epoch(train) [11][150/293] lr: 5.000000e-04 eta: 7:29:09 time: 0.509043 data_time: 0.078681 memory: 9871 loss_kpt: 0.000804 acc_pose: 0.756295 loss: 0.000804 2022/09/08 13:08:22 - mmengine - INFO - Epoch(train) [11][200/293] lr: 5.000000e-04 eta: 7:29:22 time: 0.500325 data_time: 0.079457 memory: 9871 loss_kpt: 0.000815 acc_pose: 0.759089 loss: 0.000815 2022/09/08 13:08:47 - mmengine - INFO - Epoch(train) [11][250/293] lr: 5.000000e-04 eta: 7:29:40 time: 0.506107 data_time: 0.071518 memory: 9871 loss_kpt: 0.000819 acc_pose: 0.746320 loss: 0.000819 2022/09/08 13:09:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 13:09:09 - mmengine - INFO - Saving checkpoint at 11 epochs 2022/09/08 13:09:39 - mmengine - INFO - Epoch(train) [12][50/293] lr: 5.000000e-04 eta: 7:23:55 time: 0.521106 data_time: 0.088814 memory: 9871 loss_kpt: 0.000813 acc_pose: 0.769119 loss: 0.000813 2022/09/08 13:10:04 - mmengine - INFO - Epoch(train) [12][100/293] lr: 5.000000e-04 eta: 7:24:16 time: 0.506438 data_time: 0.082357 memory: 9871 loss_kpt: 0.000832 acc_pose: 0.792399 loss: 0.000832 2022/09/08 13:10:29 - mmengine - INFO - Epoch(train) [12][150/293] lr: 5.000000e-04 eta: 7:24:30 time: 0.500853 data_time: 0.071240 memory: 9871 loss_kpt: 0.000816 acc_pose: 0.732322 loss: 0.000816 2022/09/08 13:10:54 - mmengine - INFO - Epoch(train) [12][200/293] lr: 5.000000e-04 eta: 7:24:31 time: 0.487699 data_time: 0.075167 memory: 9871 loss_kpt: 0.000804 acc_pose: 0.770168 loss: 0.000804 2022/09/08 13:11:18 - mmengine - INFO - Epoch(train) [12][250/293] lr: 5.000000e-04 eta: 7:24:34 time: 0.489511 data_time: 0.075030 memory: 9871 loss_kpt: 0.000805 acc_pose: 0.706721 loss: 0.000805 2022/09/08 13:11:39 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 13:11:39 - mmengine - INFO - Saving checkpoint at 12 epochs 2022/09/08 13:12:09 - mmengine - INFO - Epoch(train) [13][50/293] lr: 5.000000e-04 eta: 7:19:02 time: 0.499031 data_time: 0.081703 memory: 9871 loss_kpt: 0.000824 acc_pose: 0.717249 loss: 0.000824 2022/09/08 13:12:34 - mmengine - INFO - Epoch(train) [13][100/293] lr: 5.000000e-04 eta: 7:19:18 time: 0.502257 data_time: 0.077799 memory: 9871 loss_kpt: 0.000799 acc_pose: 0.753033 loss: 0.000799 2022/09/08 13:12:58 - mmengine - INFO - Epoch(train) [13][150/293] lr: 5.000000e-04 eta: 7:19:24 time: 0.492264 data_time: 0.074334 memory: 9871 loss_kpt: 0.000826 acc_pose: 0.749547 loss: 0.000826 2022/09/08 13:13:23 - mmengine - INFO - Epoch(train) [13][200/293] lr: 5.000000e-04 eta: 7:19:34 time: 0.497315 data_time: 0.076852 memory: 9871 loss_kpt: 0.000803 acc_pose: 0.764551 loss: 0.000803 2022/09/08 13:13:48 - mmengine - INFO - Epoch(train) [13][250/293] lr: 5.000000e-04 eta: 7:19:37 time: 0.489373 data_time: 0.075613 memory: 9871 loss_kpt: 0.000783 acc_pose: 0.764421 loss: 0.000783 2022/09/08 13:14:09 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 13:14:09 - mmengine - INFO - Saving checkpoint at 13 epochs 2022/09/08 13:14:39 - mmengine - INFO - Epoch(train) [14][50/293] lr: 5.000000e-04 eta: 7:14:36 time: 0.504473 data_time: 0.086086 memory: 9871 loss_kpt: 0.000795 acc_pose: 0.773258 loss: 0.000795 2022/09/08 13:15:04 - mmengine - INFO - Epoch(train) [14][100/293] lr: 5.000000e-04 eta: 7:14:59 time: 0.514001 data_time: 0.077839 memory: 9871 loss_kpt: 0.000792 acc_pose: 0.763879 loss: 0.000792 2022/09/08 13:15:29 - mmengine - INFO - Epoch(train) [14][150/293] lr: 5.000000e-04 eta: 7:15:06 time: 0.493523 data_time: 0.076106 memory: 9871 loss_kpt: 0.000798 acc_pose: 0.704576 loss: 0.000798 2022/09/08 13:15:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 13:15:54 - mmengine - INFO - Epoch(train) [14][200/293] lr: 5.000000e-04 eta: 7:15:23 time: 0.508059 data_time: 0.075683 memory: 9871 loss_kpt: 0.000803 acc_pose: 0.756645 loss: 0.000803 2022/09/08 13:16:19 - mmengine - INFO - Epoch(train) [14][250/293] lr: 5.000000e-04 eta: 7:15:31 time: 0.497527 data_time: 0.078675 memory: 9871 loss_kpt: 0.000791 acc_pose: 0.775273 loss: 0.000791 2022/09/08 13:16:40 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 13:16:40 - mmengine - INFO - Saving checkpoint at 14 epochs 2022/09/08 13:17:10 - mmengine - INFO - Epoch(train) [15][50/293] lr: 5.000000e-04 eta: 7:10:59 time: 0.512945 data_time: 0.086505 memory: 9871 loss_kpt: 0.000796 acc_pose: 0.710826 loss: 0.000796 2022/09/08 13:17:35 - mmengine - INFO - Epoch(train) [15][100/293] lr: 5.000000e-04 eta: 7:11:05 time: 0.492872 data_time: 0.072083 memory: 9871 loss_kpt: 0.000786 acc_pose: 0.723287 loss: 0.000786 2022/09/08 13:18:00 - mmengine - INFO - Epoch(train) [15][150/293] lr: 5.000000e-04 eta: 7:11:17 time: 0.502937 data_time: 0.077365 memory: 9871 loss_kpt: 0.000781 acc_pose: 0.787827 loss: 0.000781 2022/09/08 13:18:25 - mmengine - INFO - Epoch(train) [15][200/293] lr: 5.000000e-04 eta: 7:11:20 time: 0.490673 data_time: 0.072327 memory: 9871 loss_kpt: 0.000797 acc_pose: 0.773345 loss: 0.000797 2022/09/08 13:18:49 - mmengine - INFO - Epoch(train) [15][250/293] lr: 5.000000e-04 eta: 7:11:24 time: 0.492238 data_time: 0.078735 memory: 9871 loss_kpt: 0.000773 acc_pose: 0.760244 loss: 0.000773 2022/09/08 13:19:10 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 13:19:10 - mmengine - INFO - Saving checkpoint at 15 epochs 2022/09/08 13:19:40 - mmengine - INFO - Epoch(train) [16][50/293] lr: 5.000000e-04 eta: 7:07:03 time: 0.500739 data_time: 0.086765 memory: 9871 loss_kpt: 0.000786 acc_pose: 0.777047 loss: 0.000786 2022/09/08 13:20:05 - mmengine - INFO - Epoch(train) [16][100/293] lr: 5.000000e-04 eta: 7:07:11 time: 0.497891 data_time: 0.075201 memory: 9871 loss_kpt: 0.000777 acc_pose: 0.748259 loss: 0.000777 2022/09/08 13:20:30 - mmengine - INFO - Epoch(train) [16][150/293] lr: 5.000000e-04 eta: 7:07:17 time: 0.494367 data_time: 0.074899 memory: 9871 loss_kpt: 0.000775 acc_pose: 0.733764 loss: 0.000775 2022/09/08 13:20:55 - mmengine - INFO - Epoch(train) [16][200/293] lr: 5.000000e-04 eta: 7:07:28 time: 0.503962 data_time: 0.072349 memory: 9871 loss_kpt: 0.000792 acc_pose: 0.731328 loss: 0.000792 2022/09/08 13:21:19 - mmengine - INFO - Epoch(train) [16][250/293] lr: 5.000000e-04 eta: 7:07:31 time: 0.491872 data_time: 0.076148 memory: 9871 loss_kpt: 0.000772 acc_pose: 0.726033 loss: 0.000772 2022/09/08 13:21:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 13:21:41 - mmengine - INFO - Saving checkpoint at 16 epochs 2022/09/08 13:22:11 - mmengine - INFO - Epoch(train) [17][50/293] lr: 5.000000e-04 eta: 7:03:33 time: 0.511677 data_time: 0.088617 memory: 9871 loss_kpt: 0.000769 acc_pose: 0.709091 loss: 0.000769 2022/09/08 13:22:36 - mmengine - INFO - Epoch(train) [17][100/293] lr: 5.000000e-04 eta: 7:03:35 time: 0.488985 data_time: 0.072499 memory: 9871 loss_kpt: 0.000777 acc_pose: 0.763979 loss: 0.000777 2022/09/08 13:23:00 - mmengine - INFO - Epoch(train) [17][150/293] lr: 5.000000e-04 eta: 7:03:40 time: 0.493688 data_time: 0.074877 memory: 9871 loss_kpt: 0.000769 acc_pose: 0.733899 loss: 0.000769 2022/09/08 13:23:25 - mmengine - INFO - Epoch(train) [17][200/293] lr: 5.000000e-04 eta: 7:03:41 time: 0.490071 data_time: 0.071878 memory: 9871 loss_kpt: 0.000764 acc_pose: 0.765278 loss: 0.000764 2022/09/08 13:23:50 - mmengine - INFO - Epoch(train) [17][250/293] lr: 5.000000e-04 eta: 7:03:44 time: 0.493119 data_time: 0.071942 memory: 9871 loss_kpt: 0.000787 acc_pose: 0.724359 loss: 0.000787 2022/09/08 13:24:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 13:24:11 - mmengine - INFO - Saving checkpoint at 17 epochs 2022/09/08 13:24:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 13:24:41 - mmengine - INFO - Epoch(train) [18][50/293] lr: 5.000000e-04 eta: 6:59:59 time: 0.509169 data_time: 0.082831 memory: 9871 loss_kpt: 0.000769 acc_pose: 0.758091 loss: 0.000769 2022/09/08 13:25:06 - mmengine - INFO - Epoch(train) [18][100/293] lr: 5.000000e-04 eta: 7:00:04 time: 0.495387 data_time: 0.075557 memory: 9871 loss_kpt: 0.000765 acc_pose: 0.750152 loss: 0.000765 2022/09/08 13:25:30 - mmengine - INFO - Epoch(train) [18][150/293] lr: 5.000000e-04 eta: 7:00:06 time: 0.489719 data_time: 0.075111 memory: 9871 loss_kpt: 0.000767 acc_pose: 0.781623 loss: 0.000767 2022/09/08 13:25:55 - mmengine - INFO - Epoch(train) [18][200/293] lr: 5.000000e-04 eta: 7:00:09 time: 0.493577 data_time: 0.080742 memory: 9871 loss_kpt: 0.000773 acc_pose: 0.691068 loss: 0.000773 2022/09/08 13:26:19 - mmengine - INFO - Epoch(train) [18][250/293] lr: 5.000000e-04 eta: 7:00:09 time: 0.489125 data_time: 0.080408 memory: 9871 loss_kpt: 0.000782 acc_pose: 0.740425 loss: 0.000782 2022/09/08 13:26:40 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 13:26:40 - mmengine - INFO - Saving checkpoint at 18 epochs 2022/09/08 13:27:10 - mmengine - INFO - Epoch(train) [19][50/293] lr: 5.000000e-04 eta: 6:56:36 time: 0.508556 data_time: 0.081574 memory: 9871 loss_kpt: 0.000757 acc_pose: 0.756833 loss: 0.000757 2022/09/08 13:27:35 - mmengine - INFO - Epoch(train) [19][100/293] lr: 5.000000e-04 eta: 6:56:41 time: 0.496798 data_time: 0.074146 memory: 9871 loss_kpt: 0.000749 acc_pose: 0.751194 loss: 0.000749 2022/09/08 13:28:00 - mmengine - INFO - Epoch(train) [19][150/293] lr: 5.000000e-04 eta: 6:56:46 time: 0.497949 data_time: 0.080810 memory: 9871 loss_kpt: 0.000773 acc_pose: 0.737261 loss: 0.000773 2022/09/08 13:28:25 - mmengine - INFO - Epoch(train) [19][200/293] lr: 5.000000e-04 eta: 6:56:54 time: 0.503998 data_time: 0.075711 memory: 9871 loss_kpt: 0.000770 acc_pose: 0.769212 loss: 0.000770 2022/09/08 13:28:50 - mmengine - INFO - Epoch(train) [19][250/293] lr: 5.000000e-04 eta: 6:56:57 time: 0.497592 data_time: 0.071360 memory: 9871 loss_kpt: 0.000774 acc_pose: 0.735606 loss: 0.000774 2022/09/08 13:29:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 13:29:11 - mmengine - INFO - Saving checkpoint at 19 epochs 2022/09/08 13:29:41 - mmengine - INFO - Epoch(train) [20][50/293] lr: 5.000000e-04 eta: 6:53:34 time: 0.505699 data_time: 0.078006 memory: 9871 loss_kpt: 0.000760 acc_pose: 0.770522 loss: 0.000760 2022/09/08 13:30:06 - mmengine - INFO - Epoch(train) [20][100/293] lr: 5.000000e-04 eta: 6:53:40 time: 0.502017 data_time: 0.076134 memory: 9871 loss_kpt: 0.000767 acc_pose: 0.695543 loss: 0.000767 2022/09/08 13:30:31 - mmengine - INFO - Epoch(train) [20][150/293] lr: 5.000000e-04 eta: 6:53:42 time: 0.493690 data_time: 0.079207 memory: 9871 loss_kpt: 0.000751 acc_pose: 0.781946 loss: 0.000751 2022/09/08 13:30:56 - mmengine - INFO - Epoch(train) [20][200/293] lr: 5.000000e-04 eta: 6:53:46 time: 0.497617 data_time: 0.071395 memory: 9871 loss_kpt: 0.000757 acc_pose: 0.757513 loss: 0.000757 2022/09/08 13:31:20 - mmengine - INFO - Epoch(train) [20][250/293] lr: 5.000000e-04 eta: 6:53:43 time: 0.486392 data_time: 0.077016 memory: 9871 loss_kpt: 0.000759 acc_pose: 0.780841 loss: 0.000759 2022/09/08 13:31:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 13:31:41 - mmengine - INFO - Saving checkpoint at 20 epochs 2022/09/08 13:31:52 - mmengine - INFO - Epoch(val) [20][50/407] eta: 0:00:44 time: 0.124031 data_time: 0.014714 memory: 9871 2022/09/08 13:31:58 - mmengine - INFO - Epoch(val) [20][100/407] eta: 0:00:36 time: 0.119862 data_time: 0.010045 memory: 920 2022/09/08 13:32:04 - mmengine - INFO - Epoch(val) [20][150/407] eta: 0:00:31 time: 0.123647 data_time: 0.013308 memory: 920 2022/09/08 13:32:10 - mmengine - INFO - Epoch(val) [20][200/407] eta: 0:00:24 time: 0.119164 data_time: 0.009713 memory: 920 2022/09/08 13:32:16 - mmengine - INFO - Epoch(val) [20][250/407] eta: 0:00:18 time: 0.120439 data_time: 0.011802 memory: 920 2022/09/08 13:32:23 - mmengine - INFO - Epoch(val) [20][300/407] eta: 0:00:13 time: 0.121667 data_time: 0.013477 memory: 920 2022/09/08 13:32:29 - mmengine - INFO - Epoch(val) [20][350/407] eta: 0:00:06 time: 0.121899 data_time: 0.013510 memory: 920 2022/09/08 13:32:34 - mmengine - INFO - Epoch(val) [20][400/407] eta: 0:00:00 time: 0.111155 data_time: 0.008221 memory: 920 2022/09/08 13:33:09 - mmengine - INFO - Evaluating CocoMetric... 2022/09/08 13:33:22 - mmengine - INFO - Epoch(val) [20][407/407] coco/AP: 0.684027 coco/AP .5: 0.882582 coco/AP .75: 0.759019 coco/AP (M): 0.649410 coco/AP (L): 0.749203 coco/AR: 0.744065 coco/AR .5: 0.923961 coco/AR .75: 0.811555 coco/AR (M): 0.700847 coco/AR (L): 0.805686 2022/09/08 13:33:22 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220908/hrnet_w32_256/best_coco/AP_epoch_10.pth is removed 2022/09/08 13:33:25 - mmengine - INFO - The best checkpoint with 0.6840 coco/AP at 20 epoch is saved to best_coco/AP_epoch_20.pth. 2022/09/08 13:33:51 - mmengine - INFO - Epoch(train) [21][50/293] lr: 5.000000e-04 eta: 6:50:34 time: 0.515362 data_time: 0.077235 memory: 9871 loss_kpt: 0.000758 acc_pose: 0.775188 loss: 0.000758 2022/09/08 13:34:16 - mmengine - INFO - Epoch(train) [21][100/293] lr: 5.000000e-04 eta: 6:50:41 time: 0.505088 data_time: 0.074555 memory: 9871 loss_kpt: 0.000762 acc_pose: 0.819282 loss: 0.000762 2022/09/08 13:34:36 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 13:34:41 - mmengine - INFO - Epoch(train) [21][150/293] lr: 5.000000e-04 eta: 6:50:45 time: 0.499770 data_time: 0.083817 memory: 9871 loss_kpt: 0.000736 acc_pose: 0.747927 loss: 0.000736 2022/09/08 13:35:06 - mmengine - INFO - Epoch(train) [21][200/293] lr: 5.000000e-04 eta: 6:50:46 time: 0.494080 data_time: 0.075540 memory: 9871 loss_kpt: 0.000761 acc_pose: 0.797160 loss: 0.000761 2022/09/08 13:35:30 - mmengine - INFO - Epoch(train) [21][250/293] lr: 5.000000e-04 eta: 6:50:45 time: 0.492200 data_time: 0.074084 memory: 9871 loss_kpt: 0.000760 acc_pose: 0.755027 loss: 0.000760 2022/09/08 13:35:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 13:35:52 - mmengine - INFO - Saving checkpoint at 21 epochs 2022/09/08 13:36:21 - mmengine - INFO - Epoch(train) [22][50/293] lr: 5.000000e-04 eta: 6:47:36 time: 0.494974 data_time: 0.083440 memory: 9871 loss_kpt: 0.000761 acc_pose: 0.740410 loss: 0.000761 2022/09/08 13:36:45 - mmengine - INFO - Epoch(train) [22][100/293] lr: 5.000000e-04 eta: 6:47:37 time: 0.494845 data_time: 0.071661 memory: 9871 loss_kpt: 0.000752 acc_pose: 0.785215 loss: 0.000752 2022/09/08 13:37:10 - mmengine - INFO - Epoch(train) [22][150/293] lr: 5.000000e-04 eta: 6:47:39 time: 0.497820 data_time: 0.075973 memory: 9871 loss_kpt: 0.000747 acc_pose: 0.729360 loss: 0.000747 2022/09/08 13:37:36 - mmengine - INFO - Epoch(train) [22][200/293] lr: 5.000000e-04 eta: 6:47:48 time: 0.513858 data_time: 0.071916 memory: 9871 loss_kpt: 0.000751 acc_pose: 0.794239 loss: 0.000751 2022/09/08 13:38:01 - mmengine - INFO - Epoch(train) [22][250/293] lr: 5.000000e-04 eta: 6:47:49 time: 0.497673 data_time: 0.072304 memory: 9871 loss_kpt: 0.000748 acc_pose: 0.774529 loss: 0.000748 2022/09/08 13:38:22 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 13:38:22 - mmengine - INFO - Saving checkpoint at 22 epochs 2022/09/08 13:38:51 - mmengine - INFO - Epoch(train) [23][50/293] lr: 5.000000e-04 eta: 6:44:49 time: 0.498372 data_time: 0.082579 memory: 9871 loss_kpt: 0.000747 acc_pose: 0.771216 loss: 0.000747 2022/09/08 13:39:16 - mmengine - INFO - Epoch(train) [23][100/293] lr: 5.000000e-04 eta: 6:44:50 time: 0.497027 data_time: 0.080029 memory: 9871 loss_kpt: 0.000757 acc_pose: 0.787710 loss: 0.000757 2022/09/08 13:39:41 - mmengine - INFO - Epoch(train) [23][150/293] lr: 5.000000e-04 eta: 6:44:48 time: 0.490328 data_time: 0.074187 memory: 9871 loss_kpt: 0.000746 acc_pose: 0.778993 loss: 0.000746 2022/09/08 13:40:06 - mmengine - INFO - Epoch(train) [23][200/293] lr: 5.000000e-04 eta: 6:44:53 time: 0.507701 data_time: 0.075653 memory: 9871 loss_kpt: 0.000746 acc_pose: 0.791251 loss: 0.000746 2022/09/08 13:40:31 - mmengine - INFO - Epoch(train) [23][250/293] lr: 5.000000e-04 eta: 6:44:53 time: 0.494591 data_time: 0.074437 memory: 9871 loss_kpt: 0.000748 acc_pose: 0.806524 loss: 0.000748 2022/09/08 13:40:52 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 13:40:52 - mmengine - INFO - Saving checkpoint at 23 epochs 2022/09/08 13:41:22 - mmengine - INFO - Epoch(train) [24][50/293] lr: 5.000000e-04 eta: 6:42:03 time: 0.505493 data_time: 0.085469 memory: 9871 loss_kpt: 0.000744 acc_pose: 0.755823 loss: 0.000744 2022/09/08 13:41:47 - mmengine - INFO - Epoch(train) [24][100/293] lr: 5.000000e-04 eta: 6:42:05 time: 0.501779 data_time: 0.078989 memory: 9871 loss_kpt: 0.000754 acc_pose: 0.812164 loss: 0.000754 2022/09/08 13:42:12 - mmengine - INFO - Epoch(train) [24][150/293] lr: 5.000000e-04 eta: 6:42:06 time: 0.498812 data_time: 0.075325 memory: 9871 loss_kpt: 0.000736 acc_pose: 0.798674 loss: 0.000736 2022/09/08 13:42:37 - mmengine - INFO - Epoch(train) [24][200/293] lr: 5.000000e-04 eta: 6:42:04 time: 0.492484 data_time: 0.074247 memory: 9871 loss_kpt: 0.000741 acc_pose: 0.797921 loss: 0.000741 2022/09/08 13:43:02 - mmengine - INFO - Epoch(train) [24][250/293] lr: 5.000000e-04 eta: 6:42:02 time: 0.493626 data_time: 0.079739 memory: 9871 loss_kpt: 0.000748 acc_pose: 0.819981 loss: 0.000748 2022/09/08 13:43:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 13:43:23 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 13:43:23 - mmengine - INFO - Saving checkpoint at 24 epochs 2022/09/08 13:43:53 - mmengine - INFO - Epoch(train) [25][50/293] lr: 5.000000e-04 eta: 6:39:19 time: 0.504117 data_time: 0.083603 memory: 9871 loss_kpt: 0.000733 acc_pose: 0.782779 loss: 0.000733 2022/09/08 13:44:18 - mmengine - INFO - Epoch(train) [25][100/293] lr: 5.000000e-04 eta: 6:39:17 time: 0.494423 data_time: 0.074215 memory: 9871 loss_kpt: 0.000732 acc_pose: 0.743162 loss: 0.000732 2022/09/08 13:44:43 - mmengine - INFO - Epoch(train) [25][150/293] lr: 5.000000e-04 eta: 6:39:24 time: 0.517328 data_time: 0.083116 memory: 9871 loss_kpt: 0.000724 acc_pose: 0.779717 loss: 0.000724 2022/09/08 13:45:08 - mmengine - INFO - Epoch(train) [25][200/293] lr: 5.000000e-04 eta: 6:39:21 time: 0.491378 data_time: 0.072419 memory: 9871 loss_kpt: 0.000758 acc_pose: 0.709568 loss: 0.000758 2022/09/08 13:45:33 - mmengine - INFO - Epoch(train) [25][250/293] lr: 5.000000e-04 eta: 6:39:19 time: 0.493189 data_time: 0.075071 memory: 9871 loss_kpt: 0.000737 acc_pose: 0.802896 loss: 0.000737 2022/09/08 13:45:54 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 13:45:54 - mmengine - INFO - Saving checkpoint at 25 epochs 2022/09/08 13:46:23 - mmengine - INFO - Epoch(train) [26][50/293] lr: 5.000000e-04 eta: 6:36:41 time: 0.502853 data_time: 0.085411 memory: 9871 loss_kpt: 0.000734 acc_pose: 0.740446 loss: 0.000734 2022/09/08 13:46:48 - mmengine - INFO - Epoch(train) [26][100/293] lr: 5.000000e-04 eta: 6:36:39 time: 0.495325 data_time: 0.071890 memory: 9871 loss_kpt: 0.000737 acc_pose: 0.784823 loss: 0.000737 2022/09/08 13:47:13 - mmengine - INFO - Epoch(train) [26][150/293] lr: 5.000000e-04 eta: 6:36:37 time: 0.494276 data_time: 0.079232 memory: 9871 loss_kpt: 0.000732 acc_pose: 0.754073 loss: 0.000732 2022/09/08 13:47:37 - mmengine - INFO - Epoch(train) [26][200/293] lr: 5.000000e-04 eta: 6:36:33 time: 0.490664 data_time: 0.070994 memory: 9871 loss_kpt: 0.000765 acc_pose: 0.811589 loss: 0.000765 2022/09/08 13:48:02 - mmengine - INFO - Epoch(train) [26][250/293] lr: 5.000000e-04 eta: 6:36:31 time: 0.499069 data_time: 0.079014 memory: 9871 loss_kpt: 0.000736 acc_pose: 0.785024 loss: 0.000736 2022/09/08 13:48:23 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 13:48:23 - mmengine - INFO - Saving checkpoint at 26 epochs 2022/09/08 13:48:53 - mmengine - INFO - Epoch(train) [27][50/293] lr: 5.000000e-04 eta: 6:34:00 time: 0.505515 data_time: 0.079004 memory: 9871 loss_kpt: 0.000746 acc_pose: 0.819000 loss: 0.000746 2022/09/08 13:49:18 - mmengine - INFO - Epoch(train) [27][100/293] lr: 5.000000e-04 eta: 6:33:56 time: 0.490007 data_time: 0.076587 memory: 9871 loss_kpt: 0.000737 acc_pose: 0.745796 loss: 0.000737 2022/09/08 13:49:43 - mmengine - INFO - Epoch(train) [27][150/293] lr: 5.000000e-04 eta: 6:33:57 time: 0.507169 data_time: 0.072025 memory: 9871 loss_kpt: 0.000728 acc_pose: 0.767470 loss: 0.000728 2022/09/08 13:50:08 - mmengine - INFO - Epoch(train) [27][200/293] lr: 5.000000e-04 eta: 6:33:59 time: 0.507411 data_time: 0.074163 memory: 9871 loss_kpt: 0.000718 acc_pose: 0.854796 loss: 0.000718 2022/09/08 13:50:33 - mmengine - INFO - Epoch(train) [27][250/293] lr: 5.000000e-04 eta: 6:33:56 time: 0.496978 data_time: 0.071195 memory: 9871 loss_kpt: 0.000730 acc_pose: 0.785641 loss: 0.000730 2022/09/08 13:50:54 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 13:50:54 - mmengine - INFO - Saving checkpoint at 27 epochs 2022/09/08 13:51:24 - mmengine - INFO - Epoch(train) [28][50/293] lr: 5.000000e-04 eta: 6:31:30 time: 0.505989 data_time: 0.082935 memory: 9871 loss_kpt: 0.000740 acc_pose: 0.782726 loss: 0.000740 2022/09/08 13:51:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 13:51:50 - mmengine - INFO - Epoch(train) [28][100/293] lr: 5.000000e-04 eta: 6:31:30 time: 0.506295 data_time: 0.072528 memory: 9871 loss_kpt: 0.000722 acc_pose: 0.815791 loss: 0.000722 2022/09/08 13:52:15 - mmengine - INFO - Epoch(train) [28][150/293] lr: 5.000000e-04 eta: 6:31:31 time: 0.507358 data_time: 0.079599 memory: 9871 loss_kpt: 0.000723 acc_pose: 0.800046 loss: 0.000723 2022/09/08 13:52:40 - mmengine - INFO - Epoch(train) [28][200/293] lr: 5.000000e-04 eta: 6:31:28 time: 0.496140 data_time: 0.075519 memory: 9871 loss_kpt: 0.000735 acc_pose: 0.823380 loss: 0.000735 2022/09/08 13:53:05 - mmengine - INFO - Epoch(train) [28][250/293] lr: 5.000000e-04 eta: 6:31:29 time: 0.510399 data_time: 0.074781 memory: 9871 loss_kpt: 0.000729 acc_pose: 0.807140 loss: 0.000729 2022/09/08 13:53:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 13:53:27 - mmengine - INFO - Saving checkpoint at 28 epochs 2022/09/08 13:53:57 - mmengine - INFO - Epoch(train) [29][50/293] lr: 5.000000e-04 eta: 6:29:07 time: 0.506958 data_time: 0.083289 memory: 9871 loss_kpt: 0.000711 acc_pose: 0.781925 loss: 0.000711 2022/09/08 13:54:22 - mmengine - INFO - Epoch(train) [29][100/293] lr: 5.000000e-04 eta: 6:29:03 time: 0.491822 data_time: 0.072267 memory: 9871 loss_kpt: 0.000730 acc_pose: 0.761685 loss: 0.000730 2022/09/08 13:54:47 - mmengine - INFO - Epoch(train) [29][150/293] lr: 5.000000e-04 eta: 6:29:03 time: 0.508467 data_time: 0.079476 memory: 9871 loss_kpt: 0.000720 acc_pose: 0.766219 loss: 0.000720 2022/09/08 13:55:12 - mmengine - INFO - Epoch(train) [29][200/293] lr: 5.000000e-04 eta: 6:29:01 time: 0.500765 data_time: 0.075267 memory: 9871 loss_kpt: 0.000725 acc_pose: 0.826662 loss: 0.000725 2022/09/08 13:55:37 - mmengine - INFO - Epoch(train) [29][250/293] lr: 5.000000e-04 eta: 6:28:57 time: 0.496781 data_time: 0.078749 memory: 9871 loss_kpt: 0.000732 acc_pose: 0.777511 loss: 0.000732 2022/09/08 13:55:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 13:55:59 - mmengine - INFO - Saving checkpoint at 29 epochs 2022/09/08 13:56:28 - mmengine - INFO - Epoch(train) [30][50/293] lr: 5.000000e-04 eta: 6:26:38 time: 0.502089 data_time: 0.079011 memory: 9871 loss_kpt: 0.000733 acc_pose: 0.830047 loss: 0.000733 2022/09/08 13:56:53 - mmengine - INFO - Epoch(train) [30][100/293] lr: 5.000000e-04 eta: 6:26:34 time: 0.497669 data_time: 0.074563 memory: 9871 loss_kpt: 0.000711 acc_pose: 0.826711 loss: 0.000711 2022/09/08 13:57:18 - mmengine - INFO - Epoch(train) [30][150/293] lr: 5.000000e-04 eta: 6:26:31 time: 0.499476 data_time: 0.072679 memory: 9871 loss_kpt: 0.000711 acc_pose: 0.817930 loss: 0.000711 2022/09/08 13:57:43 - mmengine - INFO - Epoch(train) [30][200/293] lr: 5.000000e-04 eta: 6:26:25 time: 0.491241 data_time: 0.071789 memory: 9871 loss_kpt: 0.000729 acc_pose: 0.840088 loss: 0.000729 2022/09/08 13:58:08 - mmengine - INFO - Epoch(train) [30][250/293] lr: 5.000000e-04 eta: 6:26:25 time: 0.511581 data_time: 0.071604 memory: 9871 loss_kpt: 0.000708 acc_pose: 0.799458 loss: 0.000708 2022/09/08 13:58:29 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 13:58:29 - mmengine - INFO - Saving checkpoint at 30 epochs 2022/09/08 13:58:40 - mmengine - INFO - Epoch(val) [30][50/407] eta: 0:00:45 time: 0.127920 data_time: 0.016954 memory: 9871 2022/09/08 13:58:46 - mmengine - INFO - Epoch(val) [30][100/407] eta: 0:00:36 time: 0.119566 data_time: 0.010837 memory: 920 2022/09/08 13:58:52 - mmengine - INFO - Epoch(val) [30][150/407] eta: 0:00:30 time: 0.120057 data_time: 0.010465 memory: 920 2022/09/08 13:58:58 - mmengine - INFO - Epoch(val) [30][200/407] eta: 0:00:24 time: 0.117963 data_time: 0.009497 memory: 920 2022/09/08 13:59:04 - mmengine - INFO - Epoch(val) [30][250/407] eta: 0:00:19 time: 0.122337 data_time: 0.014146 memory: 920 2022/09/08 13:59:10 - mmengine - INFO - Epoch(val) [30][300/407] eta: 0:00:12 time: 0.118438 data_time: 0.010536 memory: 920 2022/09/08 13:59:16 - mmengine - INFO - Epoch(val) [30][350/407] eta: 0:00:06 time: 0.121922 data_time: 0.011274 memory: 920 2022/09/08 13:59:21 - mmengine - INFO - Epoch(val) [30][400/407] eta: 0:00:00 time: 0.106953 data_time: 0.006928 memory: 920 2022/09/08 13:59:56 - mmengine - INFO - Evaluating CocoMetric... 2022/09/08 14:00:09 - mmengine - INFO - Epoch(val) [30][407/407] coco/AP: 0.694351 coco/AP .5: 0.884730 coco/AP .75: 0.768948 coco/AP (M): 0.657540 coco/AP (L): 0.763546 coco/AR: 0.752582 coco/AR .5: 0.925220 coco/AR .75: 0.820372 coco/AR (M): 0.708113 coco/AR (L): 0.816054 2022/09/08 14:00:09 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220908/hrnet_w32_256/best_coco/AP_epoch_20.pth is removed 2022/09/08 14:00:12 - mmengine - INFO - The best checkpoint with 0.6944 coco/AP at 30 epoch is saved to best_coco/AP_epoch_30.pth. 2022/09/08 14:00:38 - mmengine - INFO - Epoch(train) [31][50/293] lr: 5.000000e-04 eta: 6:24:15 time: 0.516279 data_time: 0.084615 memory: 9871 loss_kpt: 0.000713 acc_pose: 0.846619 loss: 0.000713 2022/09/08 14:01:03 - mmengine - INFO - Epoch(train) [31][100/293] lr: 5.000000e-04 eta: 6:24:12 time: 0.502674 data_time: 0.073163 memory: 9871 loss_kpt: 0.000732 acc_pose: 0.742841 loss: 0.000732 2022/09/08 14:01:28 - mmengine - INFO - Epoch(train) [31][150/293] lr: 5.000000e-04 eta: 6:24:08 time: 0.499164 data_time: 0.075102 memory: 9871 loss_kpt: 0.000744 acc_pose: 0.799143 loss: 0.000744 2022/09/08 14:01:54 - mmengine - INFO - Epoch(train) [31][200/293] lr: 5.000000e-04 eta: 6:24:08 time: 0.511477 data_time: 0.075078 memory: 9871 loss_kpt: 0.000735 acc_pose: 0.786822 loss: 0.000735 2022/09/08 14:01:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 14:02:19 - mmengine - INFO - Epoch(train) [31][250/293] lr: 5.000000e-04 eta: 6:24:04 time: 0.502351 data_time: 0.075028 memory: 9871 loss_kpt: 0.000716 acc_pose: 0.785221 loss: 0.000716 2022/09/08 14:02:40 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 14:02:40 - mmengine - INFO - Saving checkpoint at 31 epochs 2022/09/08 14:03:10 - mmengine - INFO - Epoch(train) [32][50/293] lr: 5.000000e-04 eta: 6:21:56 time: 0.511444 data_time: 0.082616 memory: 9871 loss_kpt: 0.000716 acc_pose: 0.816228 loss: 0.000716 2022/09/08 14:03:35 - mmengine - INFO - Epoch(train) [32][100/293] lr: 5.000000e-04 eta: 6:21:51 time: 0.494933 data_time: 0.072662 memory: 9871 loss_kpt: 0.000712 acc_pose: 0.818854 loss: 0.000712 2022/09/08 14:04:00 - mmengine - INFO - Epoch(train) [32][150/293] lr: 5.000000e-04 eta: 6:21:46 time: 0.497422 data_time: 0.080338 memory: 9871 loss_kpt: 0.000724 acc_pose: 0.793682 loss: 0.000724 2022/09/08 14:04:25 - mmengine - INFO - Epoch(train) [32][200/293] lr: 5.000000e-04 eta: 6:21:40 time: 0.496548 data_time: 0.069224 memory: 9871 loss_kpt: 0.000719 acc_pose: 0.800198 loss: 0.000719 2022/09/08 14:04:49 - mmengine - INFO - Epoch(train) [32][250/293] lr: 5.000000e-04 eta: 6:21:33 time: 0.491857 data_time: 0.072482 memory: 9871 loss_kpt: 0.000712 acc_pose: 0.818872 loss: 0.000712 2022/09/08 14:05:10 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 14:05:10 - mmengine - INFO - Saving checkpoint at 32 epochs 2022/09/08 14:05:40 - mmengine - INFO - Epoch(train) [33][50/293] lr: 5.000000e-04 eta: 6:19:28 time: 0.508840 data_time: 0.085636 memory: 9871 loss_kpt: 0.000728 acc_pose: 0.778869 loss: 0.000728 2022/09/08 14:06:05 - mmengine - INFO - Epoch(train) [33][100/293] lr: 5.000000e-04 eta: 6:19:19 time: 0.486246 data_time: 0.078684 memory: 9871 loss_kpt: 0.000710 acc_pose: 0.772001 loss: 0.000710 2022/09/08 14:06:29 - mmengine - INFO - Epoch(train) [33][150/293] lr: 5.000000e-04 eta: 6:19:12 time: 0.489184 data_time: 0.074184 memory: 9871 loss_kpt: 0.000731 acc_pose: 0.737002 loss: 0.000731 2022/09/08 14:06:54 - mmengine - INFO - Epoch(train) [33][200/293] lr: 5.000000e-04 eta: 6:19:05 time: 0.492052 data_time: 0.084069 memory: 9871 loss_kpt: 0.000715 acc_pose: 0.832953 loss: 0.000715 2022/09/08 14:07:19 - mmengine - INFO - Epoch(train) [33][250/293] lr: 5.000000e-04 eta: 6:19:02 time: 0.510572 data_time: 0.078572 memory: 9871 loss_kpt: 0.000724 acc_pose: 0.741041 loss: 0.000724 2022/09/08 14:07:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 14:07:41 - mmengine - INFO - Saving checkpoint at 33 epochs 2022/09/08 14:08:10 - mmengine - INFO - Epoch(train) [34][50/293] lr: 5.000000e-04 eta: 6:16:56 time: 0.495412 data_time: 0.081098 memory: 9871 loss_kpt: 0.000735 acc_pose: 0.744621 loss: 0.000735 2022/09/08 14:08:35 - mmengine - INFO - Epoch(train) [34][100/293] lr: 5.000000e-04 eta: 6:16:50 time: 0.494584 data_time: 0.074246 memory: 9871 loss_kpt: 0.000713 acc_pose: 0.783233 loss: 0.000713 2022/09/08 14:09:00 - mmengine - INFO - Epoch(train) [34][150/293] lr: 5.000000e-04 eta: 6:16:45 time: 0.501428 data_time: 0.074596 memory: 9871 loss_kpt: 0.000699 acc_pose: 0.804365 loss: 0.000699 2022/09/08 14:09:25 - mmengine - INFO - Epoch(train) [34][200/293] lr: 5.000000e-04 eta: 6:16:39 time: 0.496679 data_time: 0.074921 memory: 9871 loss_kpt: 0.000719 acc_pose: 0.784805 loss: 0.000719 2022/09/08 14:09:50 - mmengine - INFO - Epoch(train) [34][250/293] lr: 5.000000e-04 eta: 6:16:31 time: 0.491840 data_time: 0.072985 memory: 9871 loss_kpt: 0.000686 acc_pose: 0.731664 loss: 0.000686 2022/09/08 14:10:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 14:10:11 - mmengine - INFO - Saving checkpoint at 34 epochs 2022/09/08 14:10:34 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 14:10:41 - mmengine - INFO - Epoch(train) [35][50/293] lr: 5.000000e-04 eta: 6:14:32 time: 0.509358 data_time: 0.080683 memory: 9871 loss_kpt: 0.000701 acc_pose: 0.755274 loss: 0.000701 2022/09/08 14:11:05 - mmengine - INFO - Epoch(train) [35][100/293] lr: 5.000000e-04 eta: 6:14:24 time: 0.491502 data_time: 0.074859 memory: 9871 loss_kpt: 0.000709 acc_pose: 0.744473 loss: 0.000709 2022/09/08 14:11:31 - mmengine - INFO - Epoch(train) [35][150/293] lr: 5.000000e-04 eta: 6:14:22 time: 0.514676 data_time: 0.072620 memory: 9871 loss_kpt: 0.000706 acc_pose: 0.788918 loss: 0.000706 2022/09/08 14:11:56 - mmengine - INFO - Epoch(train) [35][200/293] lr: 5.000000e-04 eta: 6:14:15 time: 0.493826 data_time: 0.082815 memory: 9871 loss_kpt: 0.000690 acc_pose: 0.815638 loss: 0.000690 2022/09/08 14:12:20 - mmengine - INFO - Epoch(train) [35][250/293] lr: 5.000000e-04 eta: 6:14:05 time: 0.485735 data_time: 0.075705 memory: 9871 loss_kpt: 0.000697 acc_pose: 0.816214 loss: 0.000697 2022/09/08 14:12:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 14:12:41 - mmengine - INFO - Saving checkpoint at 35 epochs 2022/09/08 14:13:12 - mmengine - INFO - Epoch(train) [36][50/293] lr: 5.000000e-04 eta: 6:12:12 time: 0.519685 data_time: 0.089180 memory: 9871 loss_kpt: 0.000713 acc_pose: 0.783028 loss: 0.000713 2022/09/08 14:13:37 - mmengine - INFO - Epoch(train) [36][100/293] lr: 5.000000e-04 eta: 6:12:05 time: 0.497153 data_time: 0.074976 memory: 9871 loss_kpt: 0.000691 acc_pose: 0.776415 loss: 0.000691 2022/09/08 14:14:02 - mmengine - INFO - Epoch(train) [36][150/293] lr: 5.000000e-04 eta: 6:12:00 time: 0.504082 data_time: 0.073443 memory: 9871 loss_kpt: 0.000712 acc_pose: 0.769782 loss: 0.000712 2022/09/08 14:14:27 - mmengine - INFO - Epoch(train) [36][200/293] lr: 5.000000e-04 eta: 6:11:52 time: 0.495763 data_time: 0.071827 memory: 9871 loss_kpt: 0.000729 acc_pose: 0.766954 loss: 0.000729 2022/09/08 14:14:51 - mmengine - INFO - Epoch(train) [36][250/293] lr: 5.000000e-04 eta: 6:11:45 time: 0.494937 data_time: 0.075587 memory: 9871 loss_kpt: 0.000709 acc_pose: 0.781582 loss: 0.000709 2022/09/08 14:15:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 14:15:13 - mmengine - INFO - Saving checkpoint at 36 epochs 2022/09/08 14:15:42 - mmengine - INFO - Epoch(train) [37][50/293] lr: 5.000000e-04 eta: 6:09:50 time: 0.506513 data_time: 0.091783 memory: 9871 loss_kpt: 0.000709 acc_pose: 0.805795 loss: 0.000709 2022/09/08 14:16:07 - mmengine - INFO - Epoch(train) [37][100/293] lr: 5.000000e-04 eta: 6:09:45 time: 0.504279 data_time: 0.070790 memory: 9871 loss_kpt: 0.000692 acc_pose: 0.839721 loss: 0.000692 2022/09/08 14:16:32 - mmengine - INFO - Epoch(train) [37][150/293] lr: 5.000000e-04 eta: 6:09:38 time: 0.498370 data_time: 0.078316 memory: 9871 loss_kpt: 0.000713 acc_pose: 0.812909 loss: 0.000713 2022/09/08 14:16:57 - mmengine - INFO - Epoch(train) [37][200/293] lr: 5.000000e-04 eta: 6:09:30 time: 0.495579 data_time: 0.079890 memory: 9871 loss_kpt: 0.000706 acc_pose: 0.776386 loss: 0.000706 2022/09/08 14:17:21 - mmengine - INFO - Epoch(train) [37][250/293] lr: 5.000000e-04 eta: 6:09:20 time: 0.485262 data_time: 0.071493 memory: 9871 loss_kpt: 0.000707 acc_pose: 0.762536 loss: 0.000707 2022/09/08 14:17:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 14:17:42 - mmengine - INFO - Saving checkpoint at 37 epochs 2022/09/08 14:18:13 - mmengine - INFO - Epoch(train) [38][50/293] lr: 5.000000e-04 eta: 6:07:32 time: 0.524812 data_time: 0.084254 memory: 9871 loss_kpt: 0.000695 acc_pose: 0.804851 loss: 0.000695 2022/09/08 14:18:38 - mmengine - INFO - Epoch(train) [38][100/293] lr: 5.000000e-04 eta: 6:07:23 time: 0.491930 data_time: 0.070857 memory: 9871 loss_kpt: 0.000707 acc_pose: 0.831655 loss: 0.000707 2022/09/08 14:19:03 - mmengine - INFO - Epoch(train) [38][150/293] lr: 5.000000e-04 eta: 6:07:17 time: 0.500850 data_time: 0.078762 memory: 9871 loss_kpt: 0.000702 acc_pose: 0.816711 loss: 0.000702 2022/09/08 14:19:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 14:19:28 - mmengine - INFO - Epoch(train) [38][200/293] lr: 5.000000e-04 eta: 6:07:10 time: 0.500849 data_time: 0.072083 memory: 9871 loss_kpt: 0.000716 acc_pose: 0.763748 loss: 0.000716 2022/09/08 14:19:52 - mmengine - INFO - Epoch(train) [38][250/293] lr: 5.000000e-04 eta: 6:07:01 time: 0.495309 data_time: 0.071320 memory: 9871 loss_kpt: 0.000691 acc_pose: 0.820958 loss: 0.000691 2022/09/08 14:20:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 14:20:13 - mmengine - INFO - Saving checkpoint at 38 epochs 2022/09/08 14:20:43 - mmengine - INFO - Epoch(train) [39][50/293] lr: 5.000000e-04 eta: 6:05:11 time: 0.503334 data_time: 0.084283 memory: 9871 loss_kpt: 0.000678 acc_pose: 0.828873 loss: 0.000678 2022/09/08 14:21:08 - mmengine - INFO - Epoch(train) [39][100/293] lr: 5.000000e-04 eta: 6:05:05 time: 0.504898 data_time: 0.080914 memory: 9871 loss_kpt: 0.000705 acc_pose: 0.806420 loss: 0.000705 2022/09/08 14:21:33 - mmengine - INFO - Epoch(train) [39][150/293] lr: 5.000000e-04 eta: 6:04:57 time: 0.497570 data_time: 0.075376 memory: 9871 loss_kpt: 0.000715 acc_pose: 0.807136 loss: 0.000715 2022/09/08 14:21:58 - mmengine - INFO - Epoch(train) [39][200/293] lr: 5.000000e-04 eta: 6:04:50 time: 0.502410 data_time: 0.072271 memory: 9871 loss_kpt: 0.000706 acc_pose: 0.805237 loss: 0.000706 2022/09/08 14:22:22 - mmengine - INFO - Epoch(train) [39][250/293] lr: 5.000000e-04 eta: 6:04:39 time: 0.485744 data_time: 0.078343 memory: 9871 loss_kpt: 0.000698 acc_pose: 0.805745 loss: 0.000698 2022/09/08 14:22:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 14:22:43 - mmengine - INFO - Saving checkpoint at 39 epochs 2022/09/08 14:23:13 - mmengine - INFO - Epoch(train) [40][50/293] lr: 5.000000e-04 eta: 6:02:52 time: 0.505561 data_time: 0.085473 memory: 9871 loss_kpt: 0.000711 acc_pose: 0.792357 loss: 0.000711 2022/09/08 14:23:39 - mmengine - INFO - Epoch(train) [40][100/293] lr: 5.000000e-04 eta: 6:02:46 time: 0.510883 data_time: 0.078269 memory: 9871 loss_kpt: 0.000712 acc_pose: 0.861964 loss: 0.000712 2022/09/08 14:24:03 - mmengine - INFO - Epoch(train) [40][150/293] lr: 5.000000e-04 eta: 6:02:37 time: 0.493617 data_time: 0.079650 memory: 9871 loss_kpt: 0.000715 acc_pose: 0.795852 loss: 0.000715 2022/09/08 14:24:28 - mmengine - INFO - Epoch(train) [40][200/293] lr: 5.000000e-04 eta: 6:02:29 time: 0.498863 data_time: 0.072866 memory: 9871 loss_kpt: 0.000692 acc_pose: 0.850026 loss: 0.000692 2022/09/08 14:24:53 - mmengine - INFO - Epoch(train) [40][250/293] lr: 5.000000e-04 eta: 6:02:20 time: 0.494780 data_time: 0.073310 memory: 9871 loss_kpt: 0.000699 acc_pose: 0.796996 loss: 0.000699 2022/09/08 14:25:14 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 14:25:14 - mmengine - INFO - Saving checkpoint at 40 epochs 2022/09/08 14:25:27 - mmengine - INFO - Epoch(val) [40][50/407] eta: 0:00:44 time: 0.124238 data_time: 0.014726 memory: 9871 2022/09/08 14:25:33 - mmengine - INFO - Epoch(val) [40][100/407] eta: 0:00:37 time: 0.123521 data_time: 0.012408 memory: 920 2022/09/08 14:25:39 - mmengine - INFO - Epoch(val) [40][150/407] eta: 0:00:30 time: 0.120369 data_time: 0.010792 memory: 920 2022/09/08 14:25:45 - mmengine - INFO - Epoch(val) [40][200/407] eta: 0:00:24 time: 0.118469 data_time: 0.009587 memory: 920 2022/09/08 14:25:51 - mmengine - INFO - Epoch(val) [40][250/407] eta: 0:00:18 time: 0.116620 data_time: 0.009306 memory: 920 2022/09/08 14:25:57 - mmengine - INFO - Epoch(val) [40][300/407] eta: 0:00:12 time: 0.118749 data_time: 0.009405 memory: 920 2022/09/08 14:26:03 - mmengine - INFO - Epoch(val) [40][350/407] eta: 0:00:06 time: 0.119209 data_time: 0.010339 memory: 920 2022/09/08 14:26:08 - mmengine - INFO - Epoch(val) [40][400/407] eta: 0:00:00 time: 0.107536 data_time: 0.007537 memory: 920 2022/09/08 14:26:43 - mmengine - INFO - Evaluating CocoMetric... 2022/09/08 14:26:56 - mmengine - INFO - Epoch(val) [40][407/407] coco/AP: 0.705335 coco/AP .5: 0.888642 coco/AP .75: 0.777640 coco/AP (M): 0.670972 coco/AP (L): 0.770703 coco/AR: 0.762248 coco/AR .5: 0.928999 coco/AR .75: 0.827141 coco/AR (M): 0.720650 coco/AR (L): 0.822334 2022/09/08 14:26:56 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220908/hrnet_w32_256/best_coco/AP_epoch_30.pth is removed 2022/09/08 14:26:59 - mmengine - INFO - The best checkpoint with 0.7053 coco/AP at 40 epoch is saved to best_coco/AP_epoch_40.pth. 2022/09/08 14:27:24 - mmengine - INFO - Epoch(train) [41][50/293] lr: 5.000000e-04 eta: 6:00:35 time: 0.505135 data_time: 0.079776 memory: 9871 loss_kpt: 0.000699 acc_pose: 0.763939 loss: 0.000699 2022/09/08 14:27:50 - mmengine - INFO - Epoch(train) [41][100/293] lr: 5.000000e-04 eta: 6:00:28 time: 0.508425 data_time: 0.076036 memory: 9871 loss_kpt: 0.000708 acc_pose: 0.780839 loss: 0.000708 2022/09/08 14:28:14 - mmengine - INFO - Epoch(train) [41][150/293] lr: 5.000000e-04 eta: 6:00:19 time: 0.491959 data_time: 0.077386 memory: 9871 loss_kpt: 0.000706 acc_pose: 0.773255 loss: 0.000706 2022/09/08 14:28:39 - mmengine - INFO - Epoch(train) [41][200/293] lr: 5.000000e-04 eta: 6:00:09 time: 0.493684 data_time: 0.076049 memory: 9871 loss_kpt: 0.000700 acc_pose: 0.787968 loss: 0.000700 2022/09/08 14:29:04 - mmengine - INFO - Epoch(train) [41][250/293] lr: 5.000000e-04 eta: 6:00:01 time: 0.500283 data_time: 0.085621 memory: 9871 loss_kpt: 0.000700 acc_pose: 0.797786 loss: 0.000700 2022/09/08 14:29:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 14:29:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 14:29:26 - mmengine - INFO - Saving checkpoint at 41 epochs 2022/09/08 14:29:56 - mmengine - INFO - Epoch(train) [42][50/293] lr: 5.000000e-04 eta: 5:58:18 time: 0.507844 data_time: 0.080111 memory: 9871 loss_kpt: 0.000710 acc_pose: 0.755105 loss: 0.000710 2022/09/08 14:30:21 - mmengine - INFO - Epoch(train) [42][100/293] lr: 5.000000e-04 eta: 5:58:11 time: 0.508403 data_time: 0.071206 memory: 9871 loss_kpt: 0.000700 acc_pose: 0.845071 loss: 0.000700 2022/09/08 14:30:46 - mmengine - INFO - Epoch(train) [42][150/293] lr: 5.000000e-04 eta: 5:58:00 time: 0.488166 data_time: 0.070262 memory: 9871 loss_kpt: 0.000711 acc_pose: 0.814408 loss: 0.000711 2022/09/08 14:31:10 - mmengine - INFO - Epoch(train) [42][200/293] lr: 5.000000e-04 eta: 5:57:50 time: 0.494171 data_time: 0.071392 memory: 9871 loss_kpt: 0.000686 acc_pose: 0.798088 loss: 0.000686 2022/09/08 14:31:35 - mmengine - INFO - Epoch(train) [42][250/293] lr: 5.000000e-04 eta: 5:57:42 time: 0.500819 data_time: 0.071042 memory: 9871 loss_kpt: 0.000696 acc_pose: 0.809249 loss: 0.000696 2022/09/08 14:31:57 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 14:31:57 - mmengine - INFO - Saving checkpoint at 42 epochs 2022/09/08 14:32:27 - mmengine - INFO - Epoch(train) [43][50/293] lr: 5.000000e-04 eta: 5:56:01 time: 0.508796 data_time: 0.083040 memory: 9871 loss_kpt: 0.000699 acc_pose: 0.780502 loss: 0.000699 2022/09/08 14:32:52 - mmengine - INFO - Epoch(train) [43][100/293] lr: 5.000000e-04 eta: 5:55:52 time: 0.496925 data_time: 0.076059 memory: 9871 loss_kpt: 0.000691 acc_pose: 0.726411 loss: 0.000691 2022/09/08 14:33:17 - mmengine - INFO - Epoch(train) [43][150/293] lr: 5.000000e-04 eta: 5:55:43 time: 0.498950 data_time: 0.071376 memory: 9871 loss_kpt: 0.000695 acc_pose: 0.730848 loss: 0.000695 2022/09/08 14:33:42 - mmengine - INFO - Epoch(train) [43][200/293] lr: 5.000000e-04 eta: 5:55:35 time: 0.505041 data_time: 0.079195 memory: 9871 loss_kpt: 0.000697 acc_pose: 0.795435 loss: 0.000697 2022/09/08 14:34:07 - mmengine - INFO - Epoch(train) [43][250/293] lr: 5.000000e-04 eta: 5:55:26 time: 0.500513 data_time: 0.074150 memory: 9871 loss_kpt: 0.000696 acc_pose: 0.787033 loss: 0.000696 2022/09/08 14:34:28 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 14:34:28 - mmengine - INFO - Saving checkpoint at 43 epochs 2022/09/08 14:34:58 - mmengine - INFO - Epoch(train) [44][50/293] lr: 5.000000e-04 eta: 5:53:47 time: 0.509898 data_time: 0.078937 memory: 9871 loss_kpt: 0.000695 acc_pose: 0.841269 loss: 0.000695 2022/09/08 14:35:23 - mmengine - INFO - Epoch(train) [44][100/293] lr: 5.000000e-04 eta: 5:53:37 time: 0.494414 data_time: 0.069697 memory: 9871 loss_kpt: 0.000705 acc_pose: 0.782212 loss: 0.000705 2022/09/08 14:35:49 - mmengine - INFO - Epoch(train) [44][150/293] lr: 5.000000e-04 eta: 5:53:32 time: 0.518005 data_time: 0.075325 memory: 9871 loss_kpt: 0.000688 acc_pose: 0.712628 loss: 0.000688 2022/09/08 14:36:14 - mmengine - INFO - Epoch(train) [44][200/293] lr: 5.000000e-04 eta: 5:53:20 time: 0.489672 data_time: 0.071223 memory: 9871 loss_kpt: 0.000686 acc_pose: 0.784952 loss: 0.000686 2022/09/08 14:36:38 - mmengine - INFO - Epoch(train) [44][250/293] lr: 5.000000e-04 eta: 5:53:10 time: 0.495742 data_time: 0.075638 memory: 9871 loss_kpt: 0.000679 acc_pose: 0.787999 loss: 0.000679 2022/09/08 14:36:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 14:36:59 - mmengine - INFO - Saving checkpoint at 44 epochs 2022/09/08 14:37:28 - mmengine - INFO - Epoch(train) [45][50/293] lr: 5.000000e-04 eta: 5:51:32 time: 0.501017 data_time: 0.084323 memory: 9871 loss_kpt: 0.000681 acc_pose: 0.811829 loss: 0.000681 2022/09/08 14:37:53 - mmengine - INFO - Epoch(train) [45][100/293] lr: 5.000000e-04 eta: 5:51:21 time: 0.494539 data_time: 0.075705 memory: 9871 loss_kpt: 0.000693 acc_pose: 0.807682 loss: 0.000693 2022/09/08 14:37:58 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 14:38:18 - mmengine - INFO - Epoch(train) [45][150/293] lr: 5.000000e-04 eta: 5:51:12 time: 0.503336 data_time: 0.083037 memory: 9871 loss_kpt: 0.000695 acc_pose: 0.790231 loss: 0.000695 2022/09/08 14:38:43 - mmengine - INFO - Epoch(train) [45][200/293] lr: 5.000000e-04 eta: 5:51:02 time: 0.495696 data_time: 0.078050 memory: 9871 loss_kpt: 0.000705 acc_pose: 0.824013 loss: 0.000705 2022/09/08 14:39:08 - mmengine - INFO - Epoch(train) [45][250/293] lr: 5.000000e-04 eta: 5:50:53 time: 0.506042 data_time: 0.080778 memory: 9871 loss_kpt: 0.000683 acc_pose: 0.798832 loss: 0.000683 2022/09/08 14:39:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 14:39:30 - mmengine - INFO - Saving checkpoint at 45 epochs 2022/09/08 14:40:00 - mmengine - INFO - Epoch(train) [46][50/293] lr: 5.000000e-04 eta: 5:49:19 time: 0.514938 data_time: 0.083398 memory: 9871 loss_kpt: 0.000678 acc_pose: 0.773986 loss: 0.000678 2022/09/08 14:40:25 - mmengine - INFO - Epoch(train) [46][100/293] lr: 5.000000e-04 eta: 5:49:09 time: 0.498488 data_time: 0.074958 memory: 9871 loss_kpt: 0.000684 acc_pose: 0.822554 loss: 0.000684 2022/09/08 14:40:50 - mmengine - INFO - Epoch(train) [46][150/293] lr: 5.000000e-04 eta: 5:48:58 time: 0.494990 data_time: 0.074054 memory: 9871 loss_kpt: 0.000698 acc_pose: 0.762450 loss: 0.000698 2022/09/08 14:41:14 - mmengine - INFO - Epoch(train) [46][200/293] lr: 5.000000e-04 eta: 5:48:48 time: 0.496240 data_time: 0.078451 memory: 9871 loss_kpt: 0.000695 acc_pose: 0.808346 loss: 0.000695 2022/09/08 14:41:39 - mmengine - INFO - Epoch(train) [46][250/293] lr: 5.000000e-04 eta: 5:48:36 time: 0.489493 data_time: 0.074671 memory: 9871 loss_kpt: 0.000681 acc_pose: 0.781032 loss: 0.000681 2022/09/08 14:42:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 14:42:00 - mmengine - INFO - Saving checkpoint at 46 epochs 2022/09/08 14:42:30 - mmengine - INFO - Epoch(train) [47][50/293] lr: 5.000000e-04 eta: 5:47:02 time: 0.507575 data_time: 0.085629 memory: 9871 loss_kpt: 0.000684 acc_pose: 0.838462 loss: 0.000684 2022/09/08 14:42:55 - mmengine - INFO - Epoch(train) [47][100/293] lr: 5.000000e-04 eta: 5:46:51 time: 0.492809 data_time: 0.071991 memory: 9871 loss_kpt: 0.000689 acc_pose: 0.766648 loss: 0.000689 2022/09/08 14:43:20 - mmengine - INFO - Epoch(train) [47][150/293] lr: 5.000000e-04 eta: 5:46:41 time: 0.503911 data_time: 0.078068 memory: 9871 loss_kpt: 0.000682 acc_pose: 0.811385 loss: 0.000682 2022/09/08 14:43:45 - mmengine - INFO - Epoch(train) [47][200/293] lr: 5.000000e-04 eta: 5:46:31 time: 0.502284 data_time: 0.076028 memory: 9871 loss_kpt: 0.000672 acc_pose: 0.838433 loss: 0.000672 2022/09/08 14:44:11 - mmengine - INFO - Epoch(train) [47][250/293] lr: 5.000000e-04 eta: 5:46:23 time: 0.511515 data_time: 0.078314 memory: 9871 loss_kpt: 0.000692 acc_pose: 0.802214 loss: 0.000692 2022/09/08 14:44:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 14:44:32 - mmengine - INFO - Saving checkpoint at 47 epochs 2022/09/08 14:45:01 - mmengine - INFO - Epoch(train) [48][50/293] lr: 5.000000e-04 eta: 5:44:50 time: 0.502564 data_time: 0.082009 memory: 9871 loss_kpt: 0.000688 acc_pose: 0.769959 loss: 0.000688 2022/09/08 14:45:26 - mmengine - INFO - Epoch(train) [48][100/293] lr: 5.000000e-04 eta: 5:44:37 time: 0.488480 data_time: 0.070551 memory: 9871 loss_kpt: 0.000688 acc_pose: 0.847000 loss: 0.000688 2022/09/08 14:45:51 - mmengine - INFO - Epoch(train) [48][150/293] lr: 5.000000e-04 eta: 5:44:27 time: 0.501846 data_time: 0.078049 memory: 9871 loss_kpt: 0.000695 acc_pose: 0.780740 loss: 0.000695 2022/09/08 14:46:16 - mmengine - INFO - Epoch(train) [48][200/293] lr: 5.000000e-04 eta: 5:44:17 time: 0.499655 data_time: 0.075058 memory: 9871 loss_kpt: 0.000684 acc_pose: 0.765017 loss: 0.000684 2022/09/08 14:46:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 14:46:41 - mmengine - INFO - Epoch(train) [48][250/293] lr: 5.000000e-04 eta: 5:44:06 time: 0.498128 data_time: 0.078617 memory: 9871 loss_kpt: 0.000692 acc_pose: 0.771890 loss: 0.000692 2022/09/08 14:47:01 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 14:47:01 - mmengine - INFO - Saving checkpoint at 48 epochs 2022/09/08 14:47:31 - mmengine - INFO - Epoch(train) [49][50/293] lr: 5.000000e-04 eta: 5:42:35 time: 0.508520 data_time: 0.082086 memory: 9871 loss_kpt: 0.000684 acc_pose: 0.779880 loss: 0.000684 2022/09/08 14:47:57 - mmengine - INFO - Epoch(train) [49][100/293] lr: 5.000000e-04 eta: 5:42:25 time: 0.503831 data_time: 0.077367 memory: 9871 loss_kpt: 0.000703 acc_pose: 0.734347 loss: 0.000703 2022/09/08 14:48:22 - mmengine - INFO - Epoch(train) [49][150/293] lr: 5.000000e-04 eta: 5:42:17 time: 0.515822 data_time: 0.077357 memory: 9871 loss_kpt: 0.000684 acc_pose: 0.809197 loss: 0.000684 2022/09/08 14:48:48 - mmengine - INFO - Epoch(train) [49][200/293] lr: 5.000000e-04 eta: 5:42:07 time: 0.505966 data_time: 0.075330 memory: 9871 loss_kpt: 0.000679 acc_pose: 0.819555 loss: 0.000679 2022/09/08 14:49:12 - mmengine - INFO - Epoch(train) [49][250/293] lr: 5.000000e-04 eta: 5:41:54 time: 0.486812 data_time: 0.074804 memory: 9871 loss_kpt: 0.000681 acc_pose: 0.778794 loss: 0.000681 2022/09/08 14:49:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 14:49:33 - mmengine - INFO - Saving checkpoint at 49 epochs 2022/09/08 14:50:03 - mmengine - INFO - Epoch(train) [50][50/293] lr: 5.000000e-04 eta: 5:40:24 time: 0.502868 data_time: 0.081141 memory: 9871 loss_kpt: 0.000679 acc_pose: 0.796528 loss: 0.000679 2022/09/08 14:50:28 - mmengine - INFO - Epoch(train) [50][100/293] lr: 5.000000e-04 eta: 5:40:13 time: 0.500353 data_time: 0.073922 memory: 9871 loss_kpt: 0.000702 acc_pose: 0.801941 loss: 0.000702 2022/09/08 14:50:53 - mmengine - INFO - Epoch(train) [50][150/293] lr: 5.000000e-04 eta: 5:40:03 time: 0.502248 data_time: 0.079011 memory: 9871 loss_kpt: 0.000685 acc_pose: 0.800496 loss: 0.000685 2022/09/08 14:51:18 - mmengine - INFO - Epoch(train) [50][200/293] lr: 5.000000e-04 eta: 5:39:50 time: 0.492442 data_time: 0.073901 memory: 9871 loss_kpt: 0.000690 acc_pose: 0.804895 loss: 0.000690 2022/09/08 14:51:42 - mmengine - INFO - Epoch(train) [50][250/293] lr: 5.000000e-04 eta: 5:39:38 time: 0.492114 data_time: 0.070219 memory: 9871 loss_kpt: 0.000679 acc_pose: 0.816689 loss: 0.000679 2022/09/08 14:52:03 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 14:52:03 - mmengine - INFO - Saving checkpoint at 50 epochs 2022/09/08 14:52:15 - mmengine - INFO - Epoch(val) [50][50/407] eta: 0:00:46 time: 0.128980 data_time: 0.018646 memory: 9871 2022/09/08 14:52:21 - mmengine - INFO - Epoch(val) [50][100/407] eta: 0:00:38 time: 0.126289 data_time: 0.012558 memory: 920 2022/09/08 14:52:27 - mmengine - INFO - Epoch(val) [50][150/407] eta: 0:00:30 time: 0.117235 data_time: 0.009519 memory: 920 2022/09/08 14:52:33 - mmengine - INFO - Epoch(val) [50][200/407] eta: 0:00:24 time: 0.118340 data_time: 0.009732 memory: 920 2022/09/08 14:52:39 - mmengine - INFO - Epoch(val) [50][250/407] eta: 0:00:19 time: 0.121226 data_time: 0.011756 memory: 920 2022/09/08 14:52:45 - mmengine - INFO - Epoch(val) [50][300/407] eta: 0:00:12 time: 0.118960 data_time: 0.009417 memory: 920 2022/09/08 14:52:51 - mmengine - INFO - Epoch(val) [50][350/407] eta: 0:00:06 time: 0.119163 data_time: 0.010069 memory: 920 2022/09/08 14:52:56 - mmengine - INFO - Epoch(val) [50][400/407] eta: 0:00:00 time: 0.107791 data_time: 0.007351 memory: 920 2022/09/08 14:53:31 - mmengine - INFO - Evaluating CocoMetric... 2022/09/08 14:53:44 - mmengine - INFO - Epoch(val) [50][407/407] coco/AP: 0.711801 coco/AP .5: 0.893349 coco/AP .75: 0.787319 coco/AP (M): 0.675051 coco/AP (L): 0.778376 coco/AR: 0.767979 coco/AR .5: 0.932777 coco/AR .75: 0.836272 coco/AR (M): 0.725458 coco/AR (L): 0.828651 2022/09/08 14:53:44 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220908/hrnet_w32_256/best_coco/AP_epoch_40.pth is removed 2022/09/08 14:53:47 - mmengine - INFO - The best checkpoint with 0.7118 coco/AP at 50 epoch is saved to best_coco/AP_epoch_50.pth. 2022/09/08 14:54:14 - mmengine - INFO - Epoch(train) [51][50/293] lr: 5.000000e-04 eta: 5:38:12 time: 0.521858 data_time: 0.081053 memory: 9871 loss_kpt: 0.000659 acc_pose: 0.813944 loss: 0.000659 2022/09/08 14:54:39 - mmengine - INFO - Epoch(train) [51][100/293] lr: 5.000000e-04 eta: 5:38:01 time: 0.499261 data_time: 0.076352 memory: 9871 loss_kpt: 0.000686 acc_pose: 0.838726 loss: 0.000686 2022/09/08 14:55:03 - mmengine - INFO - Epoch(train) [51][150/293] lr: 5.000000e-04 eta: 5:37:49 time: 0.497778 data_time: 0.084591 memory: 9871 loss_kpt: 0.000679 acc_pose: 0.797280 loss: 0.000679 2022/09/08 14:55:28 - mmengine - INFO - Epoch(train) [51][200/293] lr: 5.000000e-04 eta: 5:37:38 time: 0.498629 data_time: 0.075684 memory: 9871 loss_kpt: 0.000684 acc_pose: 0.775602 loss: 0.000684 2022/09/08 14:55:53 - mmengine - INFO - Epoch(train) [51][250/293] lr: 5.000000e-04 eta: 5:37:27 time: 0.500595 data_time: 0.075825 memory: 9871 loss_kpt: 0.000683 acc_pose: 0.832383 loss: 0.000683 2022/09/08 14:56:14 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 14:56:14 - mmengine - INFO - Saving checkpoint at 51 epochs 2022/09/08 14:56:44 - mmengine - INFO - Epoch(train) [52][50/293] lr: 5.000000e-04 eta: 5:36:00 time: 0.509296 data_time: 0.079423 memory: 9871 loss_kpt: 0.000685 acc_pose: 0.764113 loss: 0.000685 2022/09/08 14:56:48 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 14:57:09 - mmengine - INFO - Epoch(train) [52][100/293] lr: 5.000000e-04 eta: 5:35:48 time: 0.498147 data_time: 0.070662 memory: 9871 loss_kpt: 0.000678 acc_pose: 0.833629 loss: 0.000678 2022/09/08 14:57:34 - mmengine - INFO - Epoch(train) [52][150/293] lr: 5.000000e-04 eta: 5:35:37 time: 0.501977 data_time: 0.077306 memory: 9871 loss_kpt: 0.000675 acc_pose: 0.837733 loss: 0.000675 2022/09/08 14:57:59 - mmengine - INFO - Epoch(train) [52][200/293] lr: 5.000000e-04 eta: 5:35:26 time: 0.500306 data_time: 0.070672 memory: 9871 loss_kpt: 0.000685 acc_pose: 0.809666 loss: 0.000685 2022/09/08 14:58:24 - mmengine - INFO - Epoch(train) [52][250/293] lr: 5.000000e-04 eta: 5:35:13 time: 0.494844 data_time: 0.071365 memory: 9871 loss_kpt: 0.000679 acc_pose: 0.801349 loss: 0.000679 2022/09/08 14:58:45 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 14:58:45 - mmengine - INFO - Saving checkpoint at 52 epochs 2022/09/08 14:59:15 - mmengine - INFO - Epoch(train) [53][50/293] lr: 5.000000e-04 eta: 5:33:49 time: 0.520133 data_time: 0.088881 memory: 9871 loss_kpt: 0.000677 acc_pose: 0.780633 loss: 0.000677 2022/09/08 14:59:40 - mmengine - INFO - Epoch(train) [53][100/293] lr: 5.000000e-04 eta: 5:33:37 time: 0.495055 data_time: 0.075677 memory: 9871 loss_kpt: 0.000678 acc_pose: 0.806625 loss: 0.000678 2022/09/08 15:00:05 - mmengine - INFO - Epoch(train) [53][150/293] lr: 5.000000e-04 eta: 5:33:26 time: 0.503591 data_time: 0.075546 memory: 9871 loss_kpt: 0.000686 acc_pose: 0.768180 loss: 0.000686 2022/09/08 15:00:30 - mmengine - INFO - Epoch(train) [53][200/293] lr: 5.000000e-04 eta: 5:33:14 time: 0.495512 data_time: 0.074667 memory: 9871 loss_kpt: 0.000674 acc_pose: 0.745979 loss: 0.000674 2022/09/08 15:00:56 - mmengine - INFO - Epoch(train) [53][250/293] lr: 5.000000e-04 eta: 5:33:04 time: 0.512257 data_time: 0.076635 memory: 9871 loss_kpt: 0.000685 acc_pose: 0.830490 loss: 0.000685 2022/09/08 15:01:18 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 15:01:18 - mmengine - INFO - Saving checkpoint at 53 epochs 2022/09/08 15:01:48 - mmengine - INFO - Epoch(train) [54][50/293] lr: 5.000000e-04 eta: 5:31:41 time: 0.518962 data_time: 0.086483 memory: 9871 loss_kpt: 0.000672 acc_pose: 0.821390 loss: 0.000672 2022/09/08 15:02:13 - mmengine - INFO - Epoch(train) [54][100/293] lr: 5.000000e-04 eta: 5:31:30 time: 0.504658 data_time: 0.074757 memory: 9871 loss_kpt: 0.000671 acc_pose: 0.798774 loss: 0.000671 2022/09/08 15:02:38 - mmengine - INFO - Epoch(train) [54][150/293] lr: 5.000000e-04 eta: 5:31:17 time: 0.495151 data_time: 0.081411 memory: 9871 loss_kpt: 0.000681 acc_pose: 0.793372 loss: 0.000681 2022/09/08 15:03:03 - mmengine - INFO - Epoch(train) [54][200/293] lr: 5.000000e-04 eta: 5:31:04 time: 0.492809 data_time: 0.077444 memory: 9871 loss_kpt: 0.000677 acc_pose: 0.788015 loss: 0.000677 2022/09/08 15:03:27 - mmengine - INFO - Epoch(train) [54][250/293] lr: 5.000000e-04 eta: 5:30:50 time: 0.490531 data_time: 0.077427 memory: 9871 loss_kpt: 0.000678 acc_pose: 0.813905 loss: 0.000678 2022/09/08 15:03:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 15:03:49 - mmengine - INFO - Saving checkpoint at 54 epochs 2022/09/08 15:04:18 - mmengine - INFO - Epoch(train) [55][50/293] lr: 5.000000e-04 eta: 5:29:26 time: 0.499735 data_time: 0.078212 memory: 9871 loss_kpt: 0.000655 acc_pose: 0.758298 loss: 0.000655 2022/09/08 15:04:43 - mmengine - INFO - Epoch(train) [55][100/293] lr: 5.000000e-04 eta: 5:29:12 time: 0.486422 data_time: 0.074894 memory: 9871 loss_kpt: 0.000673 acc_pose: 0.791078 loss: 0.000673 2022/09/08 15:05:09 - mmengine - INFO - Epoch(train) [55][150/293] lr: 5.000000e-04 eta: 5:29:03 time: 0.521942 data_time: 0.078973 memory: 9871 loss_kpt: 0.000673 acc_pose: 0.808139 loss: 0.000673 2022/09/08 15:05:22 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 15:05:33 - mmengine - INFO - Epoch(train) [55][200/293] lr: 5.000000e-04 eta: 5:28:50 time: 0.493640 data_time: 0.072890 memory: 9871 loss_kpt: 0.000679 acc_pose: 0.830441 loss: 0.000679 2022/09/08 15:05:58 - mmengine - INFO - Epoch(train) [55][250/293] lr: 5.000000e-04 eta: 5:28:36 time: 0.489335 data_time: 0.077569 memory: 9871 loss_kpt: 0.000677 acc_pose: 0.826973 loss: 0.000677 2022/09/08 15:06:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 15:06:19 - mmengine - INFO - Saving checkpoint at 55 epochs 2022/09/08 15:06:49 - mmengine - INFO - Epoch(train) [56][50/293] lr: 5.000000e-04 eta: 5:27:13 time: 0.505529 data_time: 0.083179 memory: 9871 loss_kpt: 0.000664 acc_pose: 0.790345 loss: 0.000664 2022/09/08 15:07:14 - mmengine - INFO - Epoch(train) [56][100/293] lr: 5.000000e-04 eta: 5:27:01 time: 0.500406 data_time: 0.080721 memory: 9871 loss_kpt: 0.000672 acc_pose: 0.780098 loss: 0.000672 2022/09/08 15:07:39 - mmengine - INFO - Epoch(train) [56][150/293] lr: 5.000000e-04 eta: 5:26:49 time: 0.500355 data_time: 0.079967 memory: 9871 loss_kpt: 0.000682 acc_pose: 0.807719 loss: 0.000682 2022/09/08 15:08:03 - mmengine - INFO - Epoch(train) [56][200/293] lr: 5.000000e-04 eta: 5:26:36 time: 0.492832 data_time: 0.083072 memory: 9871 loss_kpt: 0.000670 acc_pose: 0.800265 loss: 0.000670 2022/09/08 15:08:29 - mmengine - INFO - Epoch(train) [56][250/293] lr: 5.000000e-04 eta: 5:26:24 time: 0.507868 data_time: 0.085556 memory: 9871 loss_kpt: 0.000670 acc_pose: 0.827252 loss: 0.000670 2022/09/08 15:08:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 15:08:49 - mmengine - INFO - Saving checkpoint at 56 epochs 2022/09/08 15:09:19 - mmengine - INFO - Epoch(train) [57][50/293] lr: 5.000000e-04 eta: 5:25:03 time: 0.506209 data_time: 0.089588 memory: 9871 loss_kpt: 0.000672 acc_pose: 0.824022 loss: 0.000672 2022/09/08 15:09:44 - mmengine - INFO - Epoch(train) [57][100/293] lr: 5.000000e-04 eta: 5:24:49 time: 0.490848 data_time: 0.075900 memory: 9871 loss_kpt: 0.000669 acc_pose: 0.799921 loss: 0.000669 2022/09/08 15:10:09 - mmengine - INFO - Epoch(train) [57][150/293] lr: 5.000000e-04 eta: 5:24:36 time: 0.496147 data_time: 0.077322 memory: 9871 loss_kpt: 0.000655 acc_pose: 0.820082 loss: 0.000655 2022/09/08 15:10:33 - mmengine - INFO - Epoch(train) [57][200/293] lr: 5.000000e-04 eta: 5:24:22 time: 0.490175 data_time: 0.079662 memory: 9871 loss_kpt: 0.000680 acc_pose: 0.775885 loss: 0.000680 2022/09/08 15:10:58 - mmengine - INFO - Epoch(train) [57][250/293] lr: 5.000000e-04 eta: 5:24:09 time: 0.498000 data_time: 0.080331 memory: 9871 loss_kpt: 0.000674 acc_pose: 0.780694 loss: 0.000674 2022/09/08 15:11:20 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 15:11:20 - mmengine - INFO - Saving checkpoint at 57 epochs 2022/09/08 15:11:50 - mmengine - INFO - Epoch(train) [58][50/293] lr: 5.000000e-04 eta: 5:22:51 time: 0.520253 data_time: 0.081394 memory: 9871 loss_kpt: 0.000671 acc_pose: 0.843086 loss: 0.000671 2022/09/08 15:12:15 - mmengine - INFO - Epoch(train) [58][100/293] lr: 5.000000e-04 eta: 5:22:37 time: 0.495971 data_time: 0.076669 memory: 9871 loss_kpt: 0.000665 acc_pose: 0.774715 loss: 0.000665 2022/09/08 15:12:40 - mmengine - INFO - Epoch(train) [58][150/293] lr: 5.000000e-04 eta: 5:22:24 time: 0.493913 data_time: 0.076589 memory: 9871 loss_kpt: 0.000675 acc_pose: 0.787254 loss: 0.000675 2022/09/08 15:13:05 - mmengine - INFO - Epoch(train) [58][200/293] lr: 5.000000e-04 eta: 5:22:12 time: 0.505885 data_time: 0.080431 memory: 9871 loss_kpt: 0.000662 acc_pose: 0.834198 loss: 0.000662 2022/09/08 15:13:30 - mmengine - INFO - Epoch(train) [58][250/293] lr: 5.000000e-04 eta: 5:21:59 time: 0.502809 data_time: 0.072687 memory: 9871 loss_kpt: 0.000663 acc_pose: 0.764744 loss: 0.000663 2022/09/08 15:13:52 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 15:13:52 - mmengine - INFO - Saving checkpoint at 58 epochs 2022/09/08 15:13:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 15:14:21 - mmengine - INFO - Epoch(train) [59][50/293] lr: 5.000000e-04 eta: 5:20:40 time: 0.507590 data_time: 0.080424 memory: 9871 loss_kpt: 0.000680 acc_pose: 0.809583 loss: 0.000680 2022/09/08 15:14:46 - mmengine - INFO - Epoch(train) [59][100/293] lr: 5.000000e-04 eta: 5:20:26 time: 0.487651 data_time: 0.076739 memory: 9871 loss_kpt: 0.000671 acc_pose: 0.830540 loss: 0.000671 2022/09/08 15:15:11 - mmengine - INFO - Epoch(train) [59][150/293] lr: 5.000000e-04 eta: 5:20:13 time: 0.501468 data_time: 0.076818 memory: 9871 loss_kpt: 0.000684 acc_pose: 0.812335 loss: 0.000684 2022/09/08 15:15:36 - mmengine - INFO - Epoch(train) [59][200/293] lr: 5.000000e-04 eta: 5:19:59 time: 0.496343 data_time: 0.085243 memory: 9871 loss_kpt: 0.000661 acc_pose: 0.771823 loss: 0.000661 2022/09/08 15:16:00 - mmengine - INFO - Epoch(train) [59][250/293] lr: 5.000000e-04 eta: 5:19:46 time: 0.494856 data_time: 0.077374 memory: 9871 loss_kpt: 0.000678 acc_pose: 0.852554 loss: 0.000678 2022/09/08 15:16:21 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 15:16:21 - mmengine - INFO - Saving checkpoint at 59 epochs 2022/09/08 15:16:51 - mmengine - INFO - Epoch(train) [60][50/293] lr: 5.000000e-04 eta: 5:18:27 time: 0.502246 data_time: 0.080255 memory: 9871 loss_kpt: 0.000660 acc_pose: 0.783083 loss: 0.000660 2022/09/08 15:17:16 - mmengine - INFO - Epoch(train) [60][100/293] lr: 5.000000e-04 eta: 5:18:14 time: 0.501379 data_time: 0.079683 memory: 9871 loss_kpt: 0.000685 acc_pose: 0.790049 loss: 0.000685 2022/09/08 15:17:41 - mmengine - INFO - Epoch(train) [60][150/293] lr: 5.000000e-04 eta: 5:18:01 time: 0.499747 data_time: 0.079825 memory: 9871 loss_kpt: 0.000663 acc_pose: 0.812059 loss: 0.000663 2022/09/08 15:18:06 - mmengine - INFO - Epoch(train) [60][200/293] lr: 5.000000e-04 eta: 5:17:47 time: 0.498267 data_time: 0.074361 memory: 9871 loss_kpt: 0.000666 acc_pose: 0.846696 loss: 0.000666 2022/09/08 15:18:31 - mmengine - INFO - Epoch(train) [60][250/293] lr: 5.000000e-04 eta: 5:17:34 time: 0.501908 data_time: 0.074361 memory: 9871 loss_kpt: 0.000695 acc_pose: 0.819646 loss: 0.000695 2022/09/08 15:18:52 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 15:18:52 - mmengine - INFO - Saving checkpoint at 60 epochs 2022/09/08 15:19:02 - mmengine - INFO - Epoch(val) [60][50/407] eta: 0:00:42 time: 0.118455 data_time: 0.014068 memory: 9871 2022/09/08 15:19:08 - mmengine - INFO - Epoch(val) [60][100/407] eta: 0:00:36 time: 0.119705 data_time: 0.009315 memory: 920 2022/09/08 15:19:14 - mmengine - INFO - Epoch(val) [60][150/407] eta: 0:00:30 time: 0.119145 data_time: 0.011621 memory: 920 2022/09/08 15:19:20 - mmengine - INFO - Epoch(val) [60][200/407] eta: 0:00:23 time: 0.114986 data_time: 0.009515 memory: 920 2022/09/08 15:19:26 - mmengine - INFO - Epoch(val) [60][250/407] eta: 0:00:17 time: 0.113285 data_time: 0.009172 memory: 920 2022/09/08 15:19:31 - mmengine - INFO - Epoch(val) [60][300/407] eta: 0:00:11 time: 0.112062 data_time: 0.008595 memory: 920 2022/09/08 15:19:37 - mmengine - INFO - Epoch(val) [60][350/407] eta: 0:00:06 time: 0.119701 data_time: 0.015744 memory: 920 2022/09/08 15:19:43 - mmengine - INFO - Epoch(val) [60][400/407] eta: 0:00:00 time: 0.109513 data_time: 0.007955 memory: 920 2022/09/08 15:20:18 - mmengine - INFO - Evaluating CocoMetric... 2022/09/08 15:20:32 - mmengine - INFO - Epoch(val) [60][407/407] coco/AP: 0.715939 coco/AP .5: 0.891054 coco/AP .75: 0.793481 coco/AP (M): 0.679319 coco/AP (L): 0.782863 coco/AR: 0.771048 coco/AR .5: 0.929156 coco/AR .75: 0.841152 coco/AR (M): 0.728162 coco/AR (L): 0.832516 2022/09/08 15:20:32 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220908/hrnet_w32_256/best_coco/AP_epoch_50.pth is removed 2022/09/08 15:20:35 - mmengine - INFO - The best checkpoint with 0.7159 coco/AP at 60 epoch is saved to best_coco/AP_epoch_60.pth. 2022/09/08 15:21:00 - mmengine - INFO - Epoch(train) [61][50/293] lr: 5.000000e-04 eta: 5:16:17 time: 0.512163 data_time: 0.083536 memory: 9871 loss_kpt: 0.000675 acc_pose: 0.811072 loss: 0.000675 2022/09/08 15:21:26 - mmengine - INFO - Epoch(train) [61][100/293] lr: 5.000000e-04 eta: 5:16:06 time: 0.514366 data_time: 0.084813 memory: 9871 loss_kpt: 0.000656 acc_pose: 0.837769 loss: 0.000656 2022/09/08 15:21:51 - mmengine - INFO - Epoch(train) [61][150/293] lr: 5.000000e-04 eta: 5:15:53 time: 0.502457 data_time: 0.076833 memory: 9871 loss_kpt: 0.000651 acc_pose: 0.821736 loss: 0.000651 2022/09/08 15:22:16 - mmengine - INFO - Epoch(train) [61][200/293] lr: 5.000000e-04 eta: 5:15:40 time: 0.505346 data_time: 0.076610 memory: 9871 loss_kpt: 0.000663 acc_pose: 0.820283 loss: 0.000663 2022/09/08 15:22:41 - mmengine - INFO - Epoch(train) [61][250/293] lr: 5.000000e-04 eta: 5:15:26 time: 0.493729 data_time: 0.078810 memory: 9871 loss_kpt: 0.000676 acc_pose: 0.777137 loss: 0.000676 2022/09/08 15:23:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 15:23:02 - mmengine - INFO - Saving checkpoint at 61 epochs 2022/09/08 15:23:33 - mmengine - INFO - Epoch(train) [62][50/293] lr: 5.000000e-04 eta: 5:14:11 time: 0.522887 data_time: 0.096192 memory: 9871 loss_kpt: 0.000667 acc_pose: 0.798258 loss: 0.000667 2022/09/08 15:23:58 - mmengine - INFO - Epoch(train) [62][100/293] lr: 5.000000e-04 eta: 5:13:58 time: 0.497939 data_time: 0.074450 memory: 9871 loss_kpt: 0.000656 acc_pose: 0.800034 loss: 0.000656 2022/09/08 15:24:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 15:24:22 - mmengine - INFO - Epoch(train) [62][150/293] lr: 5.000000e-04 eta: 5:13:43 time: 0.488779 data_time: 0.077887 memory: 9871 loss_kpt: 0.000670 acc_pose: 0.811047 loss: 0.000670 2022/09/08 15:24:48 - mmengine - INFO - Epoch(train) [62][200/293] lr: 5.000000e-04 eta: 5:13:30 time: 0.508410 data_time: 0.073366 memory: 9871 loss_kpt: 0.000664 acc_pose: 0.744241 loss: 0.000664 2022/09/08 15:25:13 - mmengine - INFO - Epoch(train) [62][250/293] lr: 5.000000e-04 eta: 5:13:19 time: 0.513840 data_time: 0.081468 memory: 9871 loss_kpt: 0.000689 acc_pose: 0.820090 loss: 0.000689 2022/09/08 15:25:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 15:25:35 - mmengine - INFO - Saving checkpoint at 62 epochs 2022/09/08 15:26:05 - mmengine - INFO - Epoch(train) [63][50/293] lr: 5.000000e-04 eta: 5:12:03 time: 0.513191 data_time: 0.081372 memory: 9871 loss_kpt: 0.000662 acc_pose: 0.792760 loss: 0.000662 2022/09/08 15:26:29 - mmengine - INFO - Epoch(train) [63][100/293] lr: 5.000000e-04 eta: 5:11:49 time: 0.489845 data_time: 0.076497 memory: 9871 loss_kpt: 0.000664 acc_pose: 0.809042 loss: 0.000664 2022/09/08 15:26:54 - mmengine - INFO - Epoch(train) [63][150/293] lr: 5.000000e-04 eta: 5:11:35 time: 0.499100 data_time: 0.088901 memory: 9871 loss_kpt: 0.000659 acc_pose: 0.755120 loss: 0.000659 2022/09/08 15:27:19 - mmengine - INFO - Epoch(train) [63][200/293] lr: 5.000000e-04 eta: 5:11:21 time: 0.493894 data_time: 0.079248 memory: 9871 loss_kpt: 0.000661 acc_pose: 0.816565 loss: 0.000661 2022/09/08 15:27:44 - mmengine - INFO - Epoch(train) [63][250/293] lr: 5.000000e-04 eta: 5:11:07 time: 0.498073 data_time: 0.073788 memory: 9871 loss_kpt: 0.000672 acc_pose: 0.845438 loss: 0.000672 2022/09/08 15:28:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 15:28:05 - mmengine - INFO - Saving checkpoint at 63 epochs 2022/09/08 15:28:35 - mmengine - INFO - Epoch(train) [64][50/293] lr: 5.000000e-04 eta: 5:09:51 time: 0.504544 data_time: 0.085881 memory: 9871 loss_kpt: 0.000671 acc_pose: 0.840830 loss: 0.000671 2022/09/08 15:29:00 - mmengine - INFO - Epoch(train) [64][100/293] lr: 5.000000e-04 eta: 5:09:36 time: 0.485306 data_time: 0.078571 memory: 9871 loss_kpt: 0.000667 acc_pose: 0.761672 loss: 0.000667 2022/09/08 15:29:25 - mmengine - INFO - Epoch(train) [64][150/293] lr: 5.000000e-04 eta: 5:09:23 time: 0.511405 data_time: 0.077256 memory: 9871 loss_kpt: 0.000664 acc_pose: 0.843145 loss: 0.000664 2022/09/08 15:29:50 - mmengine - INFO - Epoch(train) [64][200/293] lr: 5.000000e-04 eta: 5:09:09 time: 0.494818 data_time: 0.078164 memory: 9871 loss_kpt: 0.000662 acc_pose: 0.818602 loss: 0.000662 2022/09/08 15:30:15 - mmengine - INFO - Epoch(train) [64][250/293] lr: 5.000000e-04 eta: 5:08:54 time: 0.494853 data_time: 0.080907 memory: 9871 loss_kpt: 0.000654 acc_pose: 0.821920 loss: 0.000654 2022/09/08 15:30:36 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 15:30:36 - mmengine - INFO - Saving checkpoint at 64 epochs 2022/09/08 15:31:06 - mmengine - INFO - Epoch(train) [65][50/293] lr: 5.000000e-04 eta: 5:07:39 time: 0.496996 data_time: 0.079765 memory: 9871 loss_kpt: 0.000671 acc_pose: 0.860252 loss: 0.000671 2022/09/08 15:31:31 - mmengine - INFO - Epoch(train) [65][100/293] lr: 5.000000e-04 eta: 5:07:26 time: 0.504120 data_time: 0.076630 memory: 9871 loss_kpt: 0.000669 acc_pose: 0.795996 loss: 0.000669 2022/09/08 15:31:56 - mmengine - INFO - Epoch(train) [65][150/293] lr: 5.000000e-04 eta: 5:07:11 time: 0.498354 data_time: 0.073577 memory: 9871 loss_kpt: 0.000664 acc_pose: 0.839036 loss: 0.000664 2022/09/08 15:32:21 - mmengine - INFO - Epoch(train) [65][200/293] lr: 5.000000e-04 eta: 5:06:57 time: 0.499086 data_time: 0.072534 memory: 9871 loss_kpt: 0.000661 acc_pose: 0.766593 loss: 0.000661 2022/09/08 15:32:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 15:32:45 - mmengine - INFO - Epoch(train) [65][250/293] lr: 5.000000e-04 eta: 5:06:42 time: 0.492663 data_time: 0.072403 memory: 9871 loss_kpt: 0.000667 acc_pose: 0.830039 loss: 0.000667 2022/09/08 15:33:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 15:33:07 - mmengine - INFO - Saving checkpoint at 65 epochs 2022/09/08 15:33:36 - mmengine - INFO - Epoch(train) [66][50/293] lr: 5.000000e-04 eta: 5:05:29 time: 0.507226 data_time: 0.092887 memory: 9871 loss_kpt: 0.000666 acc_pose: 0.818543 loss: 0.000666 2022/09/08 15:34:01 - mmengine - INFO - Epoch(train) [66][100/293] lr: 5.000000e-04 eta: 5:05:15 time: 0.495712 data_time: 0.075694 memory: 9871 loss_kpt: 0.000673 acc_pose: 0.768728 loss: 0.000673 2022/09/08 15:34:26 - mmengine - INFO - Epoch(train) [66][150/293] lr: 5.000000e-04 eta: 5:05:00 time: 0.498115 data_time: 0.081697 memory: 9871 loss_kpt: 0.000649 acc_pose: 0.838682 loss: 0.000649 2022/09/08 15:34:51 - mmengine - INFO - Epoch(train) [66][200/293] lr: 5.000000e-04 eta: 5:04:45 time: 0.493097 data_time: 0.075074 memory: 9871 loss_kpt: 0.000661 acc_pose: 0.843202 loss: 0.000661 2022/09/08 15:35:16 - mmengine - INFO - Epoch(train) [66][250/293] lr: 5.000000e-04 eta: 5:04:31 time: 0.497708 data_time: 0.075636 memory: 9871 loss_kpt: 0.000673 acc_pose: 0.827968 loss: 0.000673 2022/09/08 15:35:37 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 15:35:37 - mmengine - INFO - Saving checkpoint at 66 epochs 2022/09/08 15:36:07 - mmengine - INFO - Epoch(train) [67][50/293] lr: 5.000000e-04 eta: 5:03:18 time: 0.506347 data_time: 0.095836 memory: 9871 loss_kpt: 0.000650 acc_pose: 0.780460 loss: 0.000650 2022/09/08 15:36:31 - mmengine - INFO - Epoch(train) [67][100/293] lr: 5.000000e-04 eta: 5:03:04 time: 0.499026 data_time: 0.074764 memory: 9871 loss_kpt: 0.000655 acc_pose: 0.815852 loss: 0.000655 2022/09/08 15:36:57 - mmengine - INFO - Epoch(train) [67][150/293] lr: 5.000000e-04 eta: 5:02:50 time: 0.500550 data_time: 0.076389 memory: 9871 loss_kpt: 0.000656 acc_pose: 0.819167 loss: 0.000656 2022/09/08 15:37:21 - mmengine - INFO - Epoch(train) [67][200/293] lr: 5.000000e-04 eta: 5:02:35 time: 0.495891 data_time: 0.076629 memory: 9871 loss_kpt: 0.000675 acc_pose: 0.838758 loss: 0.000675 2022/09/08 15:37:46 - mmengine - INFO - Epoch(train) [67][250/293] lr: 5.000000e-04 eta: 5:02:20 time: 0.497646 data_time: 0.081977 memory: 9871 loss_kpt: 0.000642 acc_pose: 0.840166 loss: 0.000642 2022/09/08 15:38:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 15:38:07 - mmengine - INFO - Saving checkpoint at 67 epochs 2022/09/08 15:38:37 - mmengine - INFO - Epoch(train) [68][50/293] lr: 5.000000e-04 eta: 5:01:08 time: 0.506090 data_time: 0.084822 memory: 9871 loss_kpt: 0.000664 acc_pose: 0.866783 loss: 0.000664 2022/09/08 15:39:02 - mmengine - INFO - Epoch(train) [68][100/293] lr: 5.000000e-04 eta: 5:00:54 time: 0.498159 data_time: 0.072061 memory: 9871 loss_kpt: 0.000641 acc_pose: 0.818599 loss: 0.000641 2022/09/08 15:39:26 - mmengine - INFO - Epoch(train) [68][150/293] lr: 5.000000e-04 eta: 5:00:38 time: 0.487229 data_time: 0.076574 memory: 9871 loss_kpt: 0.000675 acc_pose: 0.804678 loss: 0.000675 2022/09/08 15:39:50 - mmengine - INFO - Epoch(train) [68][200/293] lr: 5.000000e-04 eta: 5:00:22 time: 0.480377 data_time: 0.076520 memory: 9871 loss_kpt: 0.000656 acc_pose: 0.788347 loss: 0.000656 2022/09/08 15:40:15 - mmengine - INFO - Epoch(train) [68][250/293] lr: 5.000000e-04 eta: 5:00:07 time: 0.496790 data_time: 0.083856 memory: 9871 loss_kpt: 0.000667 acc_pose: 0.802084 loss: 0.000667 2022/09/08 15:40:36 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 15:40:36 - mmengine - INFO - Saving checkpoint at 68 epochs 2022/09/08 15:41:06 - mmengine - INFO - Epoch(train) [69][50/293] lr: 5.000000e-04 eta: 4:58:55 time: 0.505615 data_time: 0.083926 memory: 9871 loss_kpt: 0.000657 acc_pose: 0.801164 loss: 0.000657 2022/09/08 15:41:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 15:41:31 - mmengine - INFO - Epoch(train) [69][100/293] lr: 5.000000e-04 eta: 4:58:40 time: 0.493553 data_time: 0.076080 memory: 9871 loss_kpt: 0.000653 acc_pose: 0.862802 loss: 0.000653 2022/09/08 15:41:56 - mmengine - INFO - Epoch(train) [69][150/293] lr: 5.000000e-04 eta: 4:58:26 time: 0.504434 data_time: 0.078409 memory: 9871 loss_kpt: 0.000678 acc_pose: 0.816924 loss: 0.000678 2022/09/08 15:42:21 - mmengine - INFO - Epoch(train) [69][200/293] lr: 5.000000e-04 eta: 4:58:12 time: 0.502551 data_time: 0.074677 memory: 9871 loss_kpt: 0.000671 acc_pose: 0.877365 loss: 0.000671 2022/09/08 15:42:46 - mmengine - INFO - Epoch(train) [69][250/293] lr: 5.000000e-04 eta: 4:57:58 time: 0.505268 data_time: 0.079684 memory: 9871 loss_kpt: 0.000673 acc_pose: 0.794023 loss: 0.000673 2022/09/08 15:43:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 15:43:07 - mmengine - INFO - Saving checkpoint at 69 epochs 2022/09/08 15:43:38 - mmengine - INFO - Epoch(train) [70][50/293] lr: 5.000000e-04 eta: 4:56:49 time: 0.521205 data_time: 0.097356 memory: 9871 loss_kpt: 0.000659 acc_pose: 0.799373 loss: 0.000659 2022/09/08 15:44:03 - mmengine - INFO - Epoch(train) [70][100/293] lr: 5.000000e-04 eta: 4:56:34 time: 0.501558 data_time: 0.076498 memory: 9871 loss_kpt: 0.000646 acc_pose: 0.854414 loss: 0.000646 2022/09/08 15:44:28 - mmengine - INFO - Epoch(train) [70][150/293] lr: 5.000000e-04 eta: 4:56:20 time: 0.509002 data_time: 0.077055 memory: 9871 loss_kpt: 0.000652 acc_pose: 0.795406 loss: 0.000652 2022/09/08 15:44:54 - mmengine - INFO - Epoch(train) [70][200/293] lr: 5.000000e-04 eta: 4:56:06 time: 0.502109 data_time: 0.081334 memory: 9871 loss_kpt: 0.000662 acc_pose: 0.818708 loss: 0.000662 2022/09/08 15:45:19 - mmengine - INFO - Epoch(train) [70][250/293] lr: 5.000000e-04 eta: 4:55:52 time: 0.509653 data_time: 0.073427 memory: 9871 loss_kpt: 0.000651 acc_pose: 0.849721 loss: 0.000651 2022/09/08 15:45:40 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 15:45:40 - mmengine - INFO - Saving checkpoint at 70 epochs 2022/09/08 15:45:51 - mmengine - INFO - Epoch(val) [70][50/407] eta: 0:00:44 time: 0.124513 data_time: 0.015462 memory: 9871 2022/09/08 15:45:57 - mmengine - INFO - Epoch(val) [70][100/407] eta: 0:00:36 time: 0.118868 data_time: 0.009690 memory: 920 2022/09/08 15:46:03 - mmengine - INFO - Epoch(val) [70][150/407] eta: 0:00:30 time: 0.116766 data_time: 0.010437 memory: 920 2022/09/08 15:46:09 - mmengine - INFO - Epoch(val) [70][200/407] eta: 0:00:24 time: 0.118832 data_time: 0.016138 memory: 920 2022/09/08 15:46:14 - mmengine - INFO - Epoch(val) [70][250/407] eta: 0:00:17 time: 0.112445 data_time: 0.009138 memory: 920 2022/09/08 15:46:20 - mmengine - INFO - Epoch(val) [70][300/407] eta: 0:00:12 time: 0.114794 data_time: 0.010077 memory: 920 2022/09/08 15:46:26 - mmengine - INFO - Epoch(val) [70][350/407] eta: 0:00:06 time: 0.116686 data_time: 0.012901 memory: 920 2022/09/08 15:46:31 - mmengine - INFO - Epoch(val) [70][400/407] eta: 0:00:00 time: 0.110611 data_time: 0.008234 memory: 920 2022/09/08 15:47:06 - mmengine - INFO - Evaluating CocoMetric... 2022/09/08 15:47:20 - mmengine - INFO - Epoch(val) [70][407/407] coco/AP: 0.721864 coco/AP .5: 0.894375 coco/AP .75: 0.797975 coco/AP (M): 0.688156 coco/AP (L): 0.787100 coco/AR: 0.778652 coco/AR .5: 0.935296 coco/AR .75: 0.847450 coco/AR (M): 0.737695 coco/AR (L): 0.837644 2022/09/08 15:47:20 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220908/hrnet_w32_256/best_coco/AP_epoch_60.pth is removed 2022/09/08 15:47:22 - mmengine - INFO - The best checkpoint with 0.7219 coco/AP at 70 epoch is saved to best_coco/AP_epoch_70.pth. 2022/09/08 15:47:48 - mmengine - INFO - Epoch(train) [71][50/293] lr: 5.000000e-04 eta: 4:54:42 time: 0.505984 data_time: 0.082895 memory: 9871 loss_kpt: 0.000644 acc_pose: 0.807798 loss: 0.000644 2022/09/08 15:48:12 - mmengine - INFO - Epoch(train) [71][100/293] lr: 5.000000e-04 eta: 4:54:26 time: 0.490157 data_time: 0.077641 memory: 9871 loss_kpt: 0.000670 acc_pose: 0.807409 loss: 0.000670 2022/09/08 15:48:38 - mmengine - INFO - Epoch(train) [71][150/293] lr: 5.000000e-04 eta: 4:54:12 time: 0.505908 data_time: 0.079812 memory: 9871 loss_kpt: 0.000663 acc_pose: 0.793433 loss: 0.000663 2022/09/08 15:49:02 - mmengine - INFO - Epoch(train) [71][200/293] lr: 5.000000e-04 eta: 4:53:57 time: 0.497099 data_time: 0.072049 memory: 9871 loss_kpt: 0.000662 acc_pose: 0.847657 loss: 0.000662 2022/09/08 15:49:27 - mmengine - INFO - Epoch(train) [71][250/293] lr: 5.000000e-04 eta: 4:53:42 time: 0.496223 data_time: 0.078428 memory: 9871 loss_kpt: 0.000650 acc_pose: 0.753997 loss: 0.000650 2022/09/08 15:49:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 15:49:49 - mmengine - INFO - Saving checkpoint at 71 epochs 2022/09/08 15:50:18 - mmengine - INFO - Epoch(train) [72][50/293] lr: 5.000000e-04 eta: 4:52:33 time: 0.507735 data_time: 0.080435 memory: 9871 loss_kpt: 0.000647 acc_pose: 0.787629 loss: 0.000647 2022/09/08 15:50:43 - mmengine - INFO - Epoch(train) [72][100/293] lr: 5.000000e-04 eta: 4:52:18 time: 0.499397 data_time: 0.072451 memory: 9871 loss_kpt: 0.000661 acc_pose: 0.840505 loss: 0.000661 2022/09/08 15:51:09 - mmengine - INFO - Epoch(train) [72][150/293] lr: 5.000000e-04 eta: 4:52:04 time: 0.509827 data_time: 0.077403 memory: 9871 loss_kpt: 0.000656 acc_pose: 0.791732 loss: 0.000656 2022/09/08 15:51:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 15:51:34 - mmengine - INFO - Epoch(train) [72][200/293] lr: 5.000000e-04 eta: 4:51:48 time: 0.499067 data_time: 0.073694 memory: 9871 loss_kpt: 0.000669 acc_pose: 0.753332 loss: 0.000669 2022/09/08 15:51:58 - mmengine - INFO - Epoch(train) [72][250/293] lr: 5.000000e-04 eta: 4:51:32 time: 0.482312 data_time: 0.072127 memory: 9871 loss_kpt: 0.000650 acc_pose: 0.848353 loss: 0.000650 2022/09/08 15:52:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 15:52:19 - mmengine - INFO - Saving checkpoint at 72 epochs 2022/09/08 15:52:48 - mmengine - INFO - Epoch(train) [73][50/293] lr: 5.000000e-04 eta: 4:50:24 time: 0.511321 data_time: 0.087247 memory: 9871 loss_kpt: 0.000650 acc_pose: 0.811625 loss: 0.000650 2022/09/08 15:53:13 - mmengine - INFO - Epoch(train) [73][100/293] lr: 5.000000e-04 eta: 4:50:08 time: 0.491202 data_time: 0.075894 memory: 9871 loss_kpt: 0.000658 acc_pose: 0.836952 loss: 0.000658 2022/09/08 15:53:38 - mmengine - INFO - Epoch(train) [73][150/293] lr: 5.000000e-04 eta: 4:49:52 time: 0.498586 data_time: 0.081030 memory: 9871 loss_kpt: 0.000676 acc_pose: 0.784238 loss: 0.000676 2022/09/08 15:54:03 - mmengine - INFO - Epoch(train) [73][200/293] lr: 5.000000e-04 eta: 4:49:38 time: 0.509207 data_time: 0.077521 memory: 9871 loss_kpt: 0.000653 acc_pose: 0.818340 loss: 0.000653 2022/09/08 15:54:28 - mmengine - INFO - Epoch(train) [73][250/293] lr: 5.000000e-04 eta: 4:49:23 time: 0.498416 data_time: 0.081981 memory: 9871 loss_kpt: 0.000668 acc_pose: 0.805907 loss: 0.000668 2022/09/08 15:54:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 15:54:50 - mmengine - INFO - Saving checkpoint at 73 epochs 2022/09/08 15:55:19 - mmengine - INFO - Epoch(train) [74][50/293] lr: 5.000000e-04 eta: 4:48:15 time: 0.512929 data_time: 0.087019 memory: 9871 loss_kpt: 0.000653 acc_pose: 0.818368 loss: 0.000653 2022/09/08 15:55:44 - mmengine - INFO - Epoch(train) [74][100/293] lr: 5.000000e-04 eta: 4:48:00 time: 0.494337 data_time: 0.079083 memory: 9871 loss_kpt: 0.000652 acc_pose: 0.801298 loss: 0.000652 2022/09/08 15:56:09 - mmengine - INFO - Epoch(train) [74][150/293] lr: 5.000000e-04 eta: 4:47:44 time: 0.499040 data_time: 0.076377 memory: 9871 loss_kpt: 0.000658 acc_pose: 0.761420 loss: 0.000658 2022/09/08 15:56:34 - mmengine - INFO - Epoch(train) [74][200/293] lr: 5.000000e-04 eta: 4:47:28 time: 0.492365 data_time: 0.076741 memory: 9871 loss_kpt: 0.000648 acc_pose: 0.838750 loss: 0.000648 2022/09/08 15:56:59 - mmengine - INFO - Epoch(train) [74][250/293] lr: 5.000000e-04 eta: 4:47:13 time: 0.501789 data_time: 0.076182 memory: 9871 loss_kpt: 0.000649 acc_pose: 0.811191 loss: 0.000649 2022/09/08 15:57:21 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 15:57:21 - mmengine - INFO - Saving checkpoint at 74 epochs 2022/09/08 15:57:50 - mmengine - INFO - Epoch(train) [75][50/293] lr: 5.000000e-04 eta: 4:46:06 time: 0.507555 data_time: 0.090810 memory: 9871 loss_kpt: 0.000658 acc_pose: 0.826648 loss: 0.000658 2022/09/08 15:58:16 - mmengine - INFO - Epoch(train) [75][100/293] lr: 5.000000e-04 eta: 4:45:52 time: 0.511160 data_time: 0.081685 memory: 9871 loss_kpt: 0.000665 acc_pose: 0.769222 loss: 0.000665 2022/09/08 15:58:41 - mmengine - INFO - Epoch(train) [75][150/293] lr: 5.000000e-04 eta: 4:45:36 time: 0.491763 data_time: 0.074264 memory: 9871 loss_kpt: 0.000640 acc_pose: 0.810663 loss: 0.000640 2022/09/08 15:59:06 - mmengine - INFO - Epoch(train) [75][200/293] lr: 5.000000e-04 eta: 4:45:20 time: 0.500209 data_time: 0.075008 memory: 9871 loss_kpt: 0.000663 acc_pose: 0.833133 loss: 0.000663 2022/09/08 15:59:31 - mmengine - INFO - Epoch(train) [75][250/293] lr: 5.000000e-04 eta: 4:45:05 time: 0.502961 data_time: 0.076883 memory: 9871 loss_kpt: 0.000651 acc_pose: 0.840629 loss: 0.000651 2022/09/08 15:59:52 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 15:59:52 - mmengine - INFO - Saving checkpoint at 75 epochs 2022/09/08 16:00:09 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 16:00:21 - mmengine - INFO - Epoch(train) [76][50/293] lr: 5.000000e-04 eta: 4:43:58 time: 0.500262 data_time: 0.079908 memory: 9871 loss_kpt: 0.000647 acc_pose: 0.820281 loss: 0.000647 2022/09/08 16:00:47 - mmengine - INFO - Epoch(train) [76][100/293] lr: 5.000000e-04 eta: 4:43:44 time: 0.514249 data_time: 0.084985 memory: 9871 loss_kpt: 0.000654 acc_pose: 0.851213 loss: 0.000654 2022/09/08 16:01:12 - mmengine - INFO - Epoch(train) [76][150/293] lr: 5.000000e-04 eta: 4:43:29 time: 0.505766 data_time: 0.083587 memory: 9871 loss_kpt: 0.000640 acc_pose: 0.792662 loss: 0.000640 2022/09/08 16:01:37 - mmengine - INFO - Epoch(train) [76][200/293] lr: 5.000000e-04 eta: 4:43:13 time: 0.496134 data_time: 0.081745 memory: 9871 loss_kpt: 0.000657 acc_pose: 0.800486 loss: 0.000657 2022/09/08 16:02:02 - mmengine - INFO - Epoch(train) [76][250/293] lr: 5.000000e-04 eta: 4:42:58 time: 0.507148 data_time: 0.072709 memory: 9871 loss_kpt: 0.000650 acc_pose: 0.814492 loss: 0.000650 2022/09/08 16:02:24 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 16:02:24 - mmengine - INFO - Saving checkpoint at 76 epochs 2022/09/08 16:02:54 - mmengine - INFO - Epoch(train) [77][50/293] lr: 5.000000e-04 eta: 4:41:53 time: 0.517250 data_time: 0.083928 memory: 9871 loss_kpt: 0.000639 acc_pose: 0.802424 loss: 0.000639 2022/09/08 16:03:19 - mmengine - INFO - Epoch(train) [77][100/293] lr: 5.000000e-04 eta: 4:41:37 time: 0.504782 data_time: 0.079924 memory: 9871 loss_kpt: 0.000649 acc_pose: 0.824497 loss: 0.000649 2022/09/08 16:03:45 - mmengine - INFO - Epoch(train) [77][150/293] lr: 5.000000e-04 eta: 4:41:22 time: 0.502430 data_time: 0.078483 memory: 9871 loss_kpt: 0.000655 acc_pose: 0.779879 loss: 0.000655 2022/09/08 16:04:09 - mmengine - INFO - Epoch(train) [77][200/293] lr: 5.000000e-04 eta: 4:41:06 time: 0.498544 data_time: 0.076321 memory: 9871 loss_kpt: 0.000643 acc_pose: 0.814734 loss: 0.000643 2022/09/08 16:04:35 - mmengine - INFO - Epoch(train) [77][250/293] lr: 5.000000e-04 eta: 4:40:51 time: 0.503888 data_time: 0.071295 memory: 9871 loss_kpt: 0.000644 acc_pose: 0.792845 loss: 0.000644 2022/09/08 16:04:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 16:04:55 - mmengine - INFO - Saving checkpoint at 77 epochs 2022/09/08 16:05:25 - mmengine - INFO - Epoch(train) [78][50/293] lr: 5.000000e-04 eta: 4:39:45 time: 0.507828 data_time: 0.089993 memory: 9871 loss_kpt: 0.000653 acc_pose: 0.831870 loss: 0.000653 2022/09/08 16:05:50 - mmengine - INFO - Epoch(train) [78][100/293] lr: 5.000000e-04 eta: 4:39:29 time: 0.496233 data_time: 0.077371 memory: 9871 loss_kpt: 0.000643 acc_pose: 0.819926 loss: 0.000643 2022/09/08 16:06:14 - mmengine - INFO - Epoch(train) [78][150/293] lr: 5.000000e-04 eta: 4:39:12 time: 0.483003 data_time: 0.079672 memory: 9871 loss_kpt: 0.000649 acc_pose: 0.832095 loss: 0.000649 2022/09/08 16:06:39 - mmengine - INFO - Epoch(train) [78][200/293] lr: 5.000000e-04 eta: 4:38:56 time: 0.493282 data_time: 0.076465 memory: 9871 loss_kpt: 0.000651 acc_pose: 0.794629 loss: 0.000651 2022/09/08 16:07:04 - mmengine - INFO - Epoch(train) [78][250/293] lr: 5.000000e-04 eta: 4:38:40 time: 0.494618 data_time: 0.077296 memory: 9871 loss_kpt: 0.000645 acc_pose: 0.805275 loss: 0.000645 2022/09/08 16:07:25 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 16:07:25 - mmengine - INFO - Saving checkpoint at 78 epochs 2022/09/08 16:07:56 - mmengine - INFO - Epoch(train) [79][50/293] lr: 5.000000e-04 eta: 4:37:35 time: 0.516624 data_time: 0.085065 memory: 9871 loss_kpt: 0.000655 acc_pose: 0.804474 loss: 0.000655 2022/09/08 16:08:21 - mmengine - INFO - Epoch(train) [79][100/293] lr: 5.000000e-04 eta: 4:37:19 time: 0.493659 data_time: 0.075329 memory: 9871 loss_kpt: 0.000653 acc_pose: 0.817627 loss: 0.000653 2022/09/08 16:08:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 16:08:45 - mmengine - INFO - Epoch(train) [79][150/293] lr: 5.000000e-04 eta: 4:37:02 time: 0.488974 data_time: 0.071868 memory: 9871 loss_kpt: 0.000648 acc_pose: 0.832151 loss: 0.000648 2022/09/08 16:09:10 - mmengine - INFO - Epoch(train) [79][200/293] lr: 5.000000e-04 eta: 4:36:46 time: 0.497301 data_time: 0.074931 memory: 9871 loss_kpt: 0.000647 acc_pose: 0.834153 loss: 0.000647 2022/09/08 16:09:35 - mmengine - INFO - Epoch(train) [79][250/293] lr: 5.000000e-04 eta: 4:36:29 time: 0.491273 data_time: 0.076083 memory: 9871 loss_kpt: 0.000649 acc_pose: 0.832670 loss: 0.000649 2022/09/08 16:09:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 16:09:56 - mmengine - INFO - Saving checkpoint at 79 epochs 2022/09/08 16:10:25 - mmengine - INFO - Epoch(train) [80][50/293] lr: 5.000000e-04 eta: 4:35:25 time: 0.504404 data_time: 0.080352 memory: 9871 loss_kpt: 0.000660 acc_pose: 0.769027 loss: 0.000660 2022/09/08 16:10:50 - mmengine - INFO - Epoch(train) [80][100/293] lr: 5.000000e-04 eta: 4:35:08 time: 0.491051 data_time: 0.076557 memory: 9871 loss_kpt: 0.000659 acc_pose: 0.818847 loss: 0.000659 2022/09/08 16:11:15 - mmengine - INFO - Epoch(train) [80][150/293] lr: 5.000000e-04 eta: 4:34:53 time: 0.506390 data_time: 0.077890 memory: 9871 loss_kpt: 0.000647 acc_pose: 0.831687 loss: 0.000647 2022/09/08 16:11:40 - mmengine - INFO - Epoch(train) [80][200/293] lr: 5.000000e-04 eta: 4:34:36 time: 0.496216 data_time: 0.079122 memory: 9871 loss_kpt: 0.000652 acc_pose: 0.834913 loss: 0.000652 2022/09/08 16:12:05 - mmengine - INFO - Epoch(train) [80][250/293] lr: 5.000000e-04 eta: 4:34:20 time: 0.496947 data_time: 0.070616 memory: 9871 loss_kpt: 0.000657 acc_pose: 0.811967 loss: 0.000657 2022/09/08 16:12:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 16:12:26 - mmengine - INFO - Saving checkpoint at 80 epochs 2022/09/08 16:12:37 - mmengine - INFO - Epoch(val) [80][50/407] eta: 0:00:45 time: 0.128837 data_time: 0.017043 memory: 9871 2022/09/08 16:12:43 - mmengine - INFO - Epoch(val) [80][100/407] eta: 0:00:36 time: 0.119962 data_time: 0.009905 memory: 920 2022/09/08 16:12:49 - mmengine - INFO - Epoch(val) [80][150/407] eta: 0:00:30 time: 0.120544 data_time: 0.011361 memory: 920 2022/09/08 16:12:55 - mmengine - INFO - Epoch(val) [80][200/407] eta: 0:00:25 time: 0.121094 data_time: 0.014521 memory: 920 2022/09/08 16:13:01 - mmengine - INFO - Epoch(val) [80][250/407] eta: 0:00:19 time: 0.121918 data_time: 0.011979 memory: 920 2022/09/08 16:13:07 - mmengine - INFO - Epoch(val) [80][300/407] eta: 0:00:12 time: 0.117368 data_time: 0.009144 memory: 920 2022/09/08 16:13:13 - mmengine - INFO - Epoch(val) [80][350/407] eta: 0:00:06 time: 0.118223 data_time: 0.010146 memory: 920 2022/09/08 16:13:19 - mmengine - INFO - Epoch(val) [80][400/407] eta: 0:00:00 time: 0.114894 data_time: 0.010299 memory: 920 2022/09/08 16:13:53 - mmengine - INFO - Evaluating CocoMetric... 2022/09/08 16:14:06 - mmengine - INFO - Epoch(val) [80][407/407] coco/AP: 0.722930 coco/AP .5: 0.896546 coco/AP .75: 0.797747 coco/AP (M): 0.688162 coco/AP (L): 0.789327 coco/AR: 0.778920 coco/AR .5: 0.937343 coco/AR .75: 0.844616 coco/AR (M): 0.736930 coco/AR (L): 0.839056 2022/09/08 16:14:07 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220908/hrnet_w32_256/best_coco/AP_epoch_70.pth is removed 2022/09/08 16:14:10 - mmengine - INFO - The best checkpoint with 0.7229 coco/AP at 80 epoch is saved to best_coco/AP_epoch_80.pth. 2022/09/08 16:14:35 - mmengine - INFO - Epoch(train) [81][50/293] lr: 5.000000e-04 eta: 4:33:16 time: 0.502374 data_time: 0.079007 memory: 9871 loss_kpt: 0.000646 acc_pose: 0.850030 loss: 0.000646 2022/09/08 16:15:00 - mmengine - INFO - Epoch(train) [81][100/293] lr: 5.000000e-04 eta: 4:33:00 time: 0.498882 data_time: 0.084141 memory: 9871 loss_kpt: 0.000639 acc_pose: 0.807625 loss: 0.000639 2022/09/08 16:15:25 - mmengine - INFO - Epoch(train) [81][150/293] lr: 5.000000e-04 eta: 4:32:44 time: 0.502985 data_time: 0.074677 memory: 9871 loss_kpt: 0.000646 acc_pose: 0.796301 loss: 0.000646 2022/09/08 16:15:51 - mmengine - INFO - Epoch(train) [81][200/293] lr: 5.000000e-04 eta: 4:32:28 time: 0.508283 data_time: 0.080193 memory: 9871 loss_kpt: 0.000652 acc_pose: 0.816084 loss: 0.000652 2022/09/08 16:16:16 - mmengine - INFO - Epoch(train) [81][250/293] lr: 5.000000e-04 eta: 4:32:13 time: 0.505689 data_time: 0.072453 memory: 9871 loss_kpt: 0.000654 acc_pose: 0.879785 loss: 0.000654 2022/09/08 16:16:37 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 16:16:37 - mmengine - INFO - Saving checkpoint at 81 epochs 2022/09/08 16:17:07 - mmengine - INFO - Epoch(train) [82][50/293] lr: 5.000000e-04 eta: 4:31:09 time: 0.505864 data_time: 0.090094 memory: 9871 loss_kpt: 0.000650 acc_pose: 0.841442 loss: 0.000650 2022/09/08 16:17:31 - mmengine - INFO - Epoch(train) [82][100/293] lr: 5.000000e-04 eta: 4:30:53 time: 0.497575 data_time: 0.076323 memory: 9871 loss_kpt: 0.000644 acc_pose: 0.841187 loss: 0.000644 2022/09/08 16:17:56 - mmengine - INFO - Epoch(train) [82][150/293] lr: 5.000000e-04 eta: 4:30:36 time: 0.497236 data_time: 0.074349 memory: 9871 loss_kpt: 0.000654 acc_pose: 0.776907 loss: 0.000654 2022/09/08 16:18:21 - mmengine - INFO - Epoch(train) [82][200/293] lr: 5.000000e-04 eta: 4:30:20 time: 0.496530 data_time: 0.075468 memory: 9871 loss_kpt: 0.000643 acc_pose: 0.778345 loss: 0.000643 2022/09/08 16:18:46 - mmengine - INFO - Epoch(train) [82][250/293] lr: 5.000000e-04 eta: 4:30:04 time: 0.506631 data_time: 0.076436 memory: 9871 loss_kpt: 0.000640 acc_pose: 0.770902 loss: 0.000640 2022/09/08 16:18:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 16:19:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 16:19:08 - mmengine - INFO - Saving checkpoint at 82 epochs 2022/09/08 16:19:38 - mmengine - INFO - Epoch(train) [83][50/293] lr: 5.000000e-04 eta: 4:29:01 time: 0.504907 data_time: 0.079890 memory: 9871 loss_kpt: 0.000642 acc_pose: 0.798738 loss: 0.000642 2022/09/08 16:20:03 - mmengine - INFO - Epoch(train) [83][100/293] lr: 5.000000e-04 eta: 4:28:45 time: 0.498063 data_time: 0.080050 memory: 9871 loss_kpt: 0.000653 acc_pose: 0.836223 loss: 0.000653 2022/09/08 16:20:28 - mmengine - INFO - Epoch(train) [83][150/293] lr: 5.000000e-04 eta: 4:28:29 time: 0.502707 data_time: 0.076552 memory: 9871 loss_kpt: 0.000643 acc_pose: 0.822293 loss: 0.000643 2022/09/08 16:20:53 - mmengine - INFO - Epoch(train) [83][200/293] lr: 5.000000e-04 eta: 4:28:12 time: 0.500560 data_time: 0.077618 memory: 9871 loss_kpt: 0.000644 acc_pose: 0.823871 loss: 0.000644 2022/09/08 16:21:17 - mmengine - INFO - Epoch(train) [83][250/293] lr: 5.000000e-04 eta: 4:27:56 time: 0.495696 data_time: 0.072602 memory: 9871 loss_kpt: 0.000649 acc_pose: 0.770024 loss: 0.000649 2022/09/08 16:21:39 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 16:21:39 - mmengine - INFO - Saving checkpoint at 83 epochs 2022/09/08 16:22:08 - mmengine - INFO - Epoch(train) [84][50/293] lr: 5.000000e-04 eta: 4:26:52 time: 0.498686 data_time: 0.086896 memory: 9871 loss_kpt: 0.000653 acc_pose: 0.772733 loss: 0.000653 2022/09/08 16:22:33 - mmengine - INFO - Epoch(train) [84][100/293] lr: 5.000000e-04 eta: 4:26:36 time: 0.502419 data_time: 0.078106 memory: 9871 loss_kpt: 0.000645 acc_pose: 0.794611 loss: 0.000645 2022/09/08 16:22:58 - mmengine - INFO - Epoch(train) [84][150/293] lr: 5.000000e-04 eta: 4:26:20 time: 0.503435 data_time: 0.076924 memory: 9871 loss_kpt: 0.000637 acc_pose: 0.822515 loss: 0.000637 2022/09/08 16:23:23 - mmengine - INFO - Epoch(train) [84][200/293] lr: 5.000000e-04 eta: 4:26:03 time: 0.492411 data_time: 0.077541 memory: 9871 loss_kpt: 0.000643 acc_pose: 0.813543 loss: 0.000643 2022/09/08 16:23:48 - mmengine - INFO - Epoch(train) [84][250/293] lr: 5.000000e-04 eta: 4:25:46 time: 0.492551 data_time: 0.076635 memory: 9871 loss_kpt: 0.000647 acc_pose: 0.798033 loss: 0.000647 2022/09/08 16:24:09 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 16:24:09 - mmengine - INFO - Saving checkpoint at 84 epochs 2022/09/08 16:24:39 - mmengine - INFO - Epoch(train) [85][50/293] lr: 5.000000e-04 eta: 4:24:44 time: 0.506080 data_time: 0.087468 memory: 9871 loss_kpt: 0.000641 acc_pose: 0.847476 loss: 0.000641 2022/09/08 16:25:03 - mmengine - INFO - Epoch(train) [85][100/293] lr: 5.000000e-04 eta: 4:24:27 time: 0.485974 data_time: 0.072572 memory: 9871 loss_kpt: 0.000633 acc_pose: 0.790591 loss: 0.000633 2022/09/08 16:25:29 - mmengine - INFO - Epoch(train) [85][150/293] lr: 5.000000e-04 eta: 4:24:11 time: 0.512653 data_time: 0.075345 memory: 9871 loss_kpt: 0.000645 acc_pose: 0.826744 loss: 0.000645 2022/09/08 16:25:54 - mmengine - INFO - Epoch(train) [85][200/293] lr: 5.000000e-04 eta: 4:23:54 time: 0.494728 data_time: 0.077546 memory: 9871 loss_kpt: 0.000655 acc_pose: 0.848579 loss: 0.000655 2022/09/08 16:26:19 - mmengine - INFO - Epoch(train) [85][250/293] lr: 5.000000e-04 eta: 4:23:39 time: 0.515699 data_time: 0.079761 memory: 9871 loss_kpt: 0.000629 acc_pose: 0.770979 loss: 0.000629 2022/09/08 16:26:40 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 16:26:40 - mmengine - INFO - Saving checkpoint at 85 epochs 2022/09/08 16:27:11 - mmengine - INFO - Epoch(train) [86][50/293] lr: 5.000000e-04 eta: 4:22:38 time: 0.518049 data_time: 0.084146 memory: 9871 loss_kpt: 0.000634 acc_pose: 0.856313 loss: 0.000634 2022/09/08 16:27:34 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 16:27:36 - mmengine - INFO - Epoch(train) [86][100/293] lr: 5.000000e-04 eta: 4:22:22 time: 0.504564 data_time: 0.071909 memory: 9871 loss_kpt: 0.000640 acc_pose: 0.805543 loss: 0.000640 2022/09/08 16:28:01 - mmengine - INFO - Epoch(train) [86][150/293] lr: 5.000000e-04 eta: 4:22:05 time: 0.501904 data_time: 0.080036 memory: 9871 loss_kpt: 0.000621 acc_pose: 0.800247 loss: 0.000621 2022/09/08 16:28:26 - mmengine - INFO - Epoch(train) [86][200/293] lr: 5.000000e-04 eta: 4:21:48 time: 0.491992 data_time: 0.081137 memory: 9871 loss_kpt: 0.000652 acc_pose: 0.826265 loss: 0.000652 2022/09/08 16:28:51 - mmengine - INFO - Epoch(train) [86][250/293] lr: 5.000000e-04 eta: 4:21:32 time: 0.503162 data_time: 0.075891 memory: 9871 loss_kpt: 0.000648 acc_pose: 0.810313 loss: 0.000648 2022/09/08 16:29:12 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 16:29:12 - mmengine - INFO - Saving checkpoint at 86 epochs 2022/09/08 16:29:42 - mmengine - INFO - Epoch(train) [87][50/293] lr: 5.000000e-04 eta: 4:20:30 time: 0.501225 data_time: 0.082040 memory: 9871 loss_kpt: 0.000645 acc_pose: 0.812690 loss: 0.000645 2022/09/08 16:30:06 - mmengine - INFO - Epoch(train) [87][100/293] lr: 5.000000e-04 eta: 4:20:13 time: 0.492980 data_time: 0.083515 memory: 9871 loss_kpt: 0.000649 acc_pose: 0.796232 loss: 0.000649 2022/09/08 16:30:31 - mmengine - INFO - Epoch(train) [87][150/293] lr: 5.000000e-04 eta: 4:19:57 time: 0.500879 data_time: 0.076001 memory: 9871 loss_kpt: 0.000636 acc_pose: 0.848734 loss: 0.000636 2022/09/08 16:30:57 - mmengine - INFO - Epoch(train) [87][200/293] lr: 5.000000e-04 eta: 4:19:40 time: 0.507709 data_time: 0.076492 memory: 9871 loss_kpt: 0.000654 acc_pose: 0.824462 loss: 0.000654 2022/09/08 16:31:21 - mmengine - INFO - Epoch(train) [87][250/293] lr: 5.000000e-04 eta: 4:19:22 time: 0.480366 data_time: 0.076361 memory: 9871 loss_kpt: 0.000627 acc_pose: 0.828483 loss: 0.000627 2022/09/08 16:31:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 16:31:42 - mmengine - INFO - Saving checkpoint at 87 epochs 2022/09/08 16:32:12 - mmengine - INFO - Epoch(train) [88][50/293] lr: 5.000000e-04 eta: 4:18:21 time: 0.507406 data_time: 0.078938 memory: 9871 loss_kpt: 0.000639 acc_pose: 0.854544 loss: 0.000639 2022/09/08 16:32:37 - mmengine - INFO - Epoch(train) [88][100/293] lr: 5.000000e-04 eta: 4:18:05 time: 0.503850 data_time: 0.077254 memory: 9871 loss_kpt: 0.000641 acc_pose: 0.826197 loss: 0.000641 2022/09/08 16:33:03 - mmengine - INFO - Epoch(train) [88][150/293] lr: 5.000000e-04 eta: 4:17:49 time: 0.513563 data_time: 0.080454 memory: 9871 loss_kpt: 0.000642 acc_pose: 0.823839 loss: 0.000642 2022/09/08 16:33:28 - mmengine - INFO - Epoch(train) [88][200/293] lr: 5.000000e-04 eta: 4:17:32 time: 0.495445 data_time: 0.073580 memory: 9871 loss_kpt: 0.000651 acc_pose: 0.801194 loss: 0.000651 2022/09/08 16:33:53 - mmengine - INFO - Epoch(train) [88][250/293] lr: 5.000000e-04 eta: 4:17:16 time: 0.508095 data_time: 0.075354 memory: 9871 loss_kpt: 0.000669 acc_pose: 0.838604 loss: 0.000669 2022/09/08 16:34:14 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 16:34:14 - mmengine - INFO - Saving checkpoint at 88 epochs 2022/09/08 16:34:44 - mmengine - INFO - Epoch(train) [89][50/293] lr: 5.000000e-04 eta: 4:16:15 time: 0.500054 data_time: 0.079226 memory: 9871 loss_kpt: 0.000626 acc_pose: 0.785269 loss: 0.000626 2022/09/08 16:35:08 - mmengine - INFO - Epoch(train) [89][100/293] lr: 5.000000e-04 eta: 4:15:58 time: 0.489735 data_time: 0.080655 memory: 9871 loss_kpt: 0.000640 acc_pose: 0.823321 loss: 0.000640 2022/09/08 16:35:34 - mmengine - INFO - Epoch(train) [89][150/293] lr: 5.000000e-04 eta: 4:15:41 time: 0.508464 data_time: 0.075117 memory: 9871 loss_kpt: 0.000655 acc_pose: 0.773064 loss: 0.000655 2022/09/08 16:35:59 - mmengine - INFO - Epoch(train) [89][200/293] lr: 5.000000e-04 eta: 4:15:25 time: 0.505759 data_time: 0.082228 memory: 9871 loss_kpt: 0.000652 acc_pose: 0.828634 loss: 0.000652 2022/09/08 16:36:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 16:36:24 - mmengine - INFO - Epoch(train) [89][250/293] lr: 5.000000e-04 eta: 4:15:08 time: 0.492384 data_time: 0.072477 memory: 9871 loss_kpt: 0.000637 acc_pose: 0.828143 loss: 0.000637 2022/09/08 16:36:45 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 16:36:45 - mmengine - INFO - Saving checkpoint at 89 epochs 2022/09/08 16:37:14 - mmengine - INFO - Epoch(train) [90][50/293] lr: 5.000000e-04 eta: 4:14:07 time: 0.504730 data_time: 0.086825 memory: 9871 loss_kpt: 0.000646 acc_pose: 0.799396 loss: 0.000646 2022/09/08 16:37:39 - mmengine - INFO - Epoch(train) [90][100/293] lr: 5.000000e-04 eta: 4:13:50 time: 0.498740 data_time: 0.079459 memory: 9871 loss_kpt: 0.000632 acc_pose: 0.826388 loss: 0.000632 2022/09/08 16:38:05 - mmengine - INFO - Epoch(train) [90][150/293] lr: 5.000000e-04 eta: 4:13:34 time: 0.514129 data_time: 0.079064 memory: 9871 loss_kpt: 0.000635 acc_pose: 0.799375 loss: 0.000635 2022/09/08 16:38:30 - mmengine - INFO - Epoch(train) [90][200/293] lr: 5.000000e-04 eta: 4:13:18 time: 0.507633 data_time: 0.078850 memory: 9871 loss_kpt: 0.000642 acc_pose: 0.874045 loss: 0.000642 2022/09/08 16:38:55 - mmengine - INFO - Epoch(train) [90][250/293] lr: 5.000000e-04 eta: 4:13:01 time: 0.495846 data_time: 0.070915 memory: 9871 loss_kpt: 0.000646 acc_pose: 0.792302 loss: 0.000646 2022/09/08 16:39:16 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 16:39:16 - mmengine - INFO - Saving checkpoint at 90 epochs 2022/09/08 16:39:27 - mmengine - INFO - Epoch(val) [90][50/407] eta: 0:00:47 time: 0.133439 data_time: 0.017978 memory: 9871 2022/09/08 16:39:33 - mmengine - INFO - Epoch(val) [90][100/407] eta: 0:00:38 time: 0.125983 data_time: 0.013811 memory: 920 2022/09/08 16:39:39 - mmengine - INFO - Epoch(val) [90][150/407] eta: 0:00:30 time: 0.119172 data_time: 0.012944 memory: 920 2022/09/08 16:39:45 - mmengine - INFO - Epoch(val) [90][200/407] eta: 0:00:24 time: 0.120661 data_time: 0.010432 memory: 920 2022/09/08 16:39:52 - mmengine - INFO - Epoch(val) [90][250/407] eta: 0:00:19 time: 0.123226 data_time: 0.010119 memory: 920 2022/09/08 16:39:58 - mmengine - INFO - Epoch(val) [90][300/407] eta: 0:00:12 time: 0.118028 data_time: 0.009627 memory: 920 2022/09/08 16:40:04 - mmengine - INFO - Epoch(val) [90][350/407] eta: 0:00:06 time: 0.120043 data_time: 0.011989 memory: 920 2022/09/08 16:40:09 - mmengine - INFO - Epoch(val) [90][400/407] eta: 0:00:00 time: 0.107898 data_time: 0.007437 memory: 920 2022/09/08 16:40:43 - mmengine - INFO - Evaluating CocoMetric... 2022/09/08 16:40:56 - mmengine - INFO - Epoch(val) [90][407/407] coco/AP: 0.724820 coco/AP .5: 0.896591 coco/AP .75: 0.797828 coco/AP (M): 0.691169 coco/AP (L): 0.790283 coco/AR: 0.782179 coco/AR .5: 0.937972 coco/AR .75: 0.848552 coco/AR (M): 0.741573 coco/AR (L): 0.840654 2022/09/08 16:40:57 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220908/hrnet_w32_256/best_coco/AP_epoch_80.pth is removed 2022/09/08 16:41:00 - mmengine - INFO - The best checkpoint with 0.7248 coco/AP at 90 epoch is saved to best_coco/AP_epoch_90.pth. 2022/09/08 16:41:26 - mmengine - INFO - Epoch(train) [91][50/293] lr: 5.000000e-04 eta: 4:12:02 time: 0.520962 data_time: 0.086681 memory: 9871 loss_kpt: 0.000633 acc_pose: 0.806304 loss: 0.000633 2022/09/08 16:41:50 - mmengine - INFO - Epoch(train) [91][100/293] lr: 5.000000e-04 eta: 4:11:45 time: 0.497886 data_time: 0.076424 memory: 9871 loss_kpt: 0.000647 acc_pose: 0.849423 loss: 0.000647 2022/09/08 16:42:15 - mmengine - INFO - Epoch(train) [91][150/293] lr: 5.000000e-04 eta: 4:11:27 time: 0.493193 data_time: 0.074917 memory: 9871 loss_kpt: 0.000641 acc_pose: 0.810681 loss: 0.000641 2022/09/08 16:42:40 - mmengine - INFO - Epoch(train) [91][200/293] lr: 5.000000e-04 eta: 4:11:10 time: 0.493700 data_time: 0.076596 memory: 9871 loss_kpt: 0.000634 acc_pose: 0.829492 loss: 0.000634 2022/09/08 16:43:04 - mmengine - INFO - Epoch(train) [91][250/293] lr: 5.000000e-04 eta: 4:10:53 time: 0.492433 data_time: 0.074065 memory: 9871 loss_kpt: 0.000624 acc_pose: 0.832299 loss: 0.000624 2022/09/08 16:43:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 16:43:26 - mmengine - INFO - Saving checkpoint at 91 epochs 2022/09/08 16:43:56 - mmengine - INFO - Epoch(train) [92][50/293] lr: 5.000000e-04 eta: 4:09:53 time: 0.500561 data_time: 0.087890 memory: 9871 loss_kpt: 0.000640 acc_pose: 0.834727 loss: 0.000640 2022/09/08 16:44:21 - mmengine - INFO - Epoch(train) [92][100/293] lr: 5.000000e-04 eta: 4:09:36 time: 0.507478 data_time: 0.070524 memory: 9871 loss_kpt: 0.000633 acc_pose: 0.851902 loss: 0.000633 2022/09/08 16:44:46 - mmengine - INFO - Epoch(train) [92][150/293] lr: 5.000000e-04 eta: 4:09:19 time: 0.498447 data_time: 0.076106 memory: 9871 loss_kpt: 0.000641 acc_pose: 0.865185 loss: 0.000641 2022/09/08 16:45:12 - mmengine - INFO - Epoch(train) [92][200/293] lr: 5.000000e-04 eta: 4:09:03 time: 0.511510 data_time: 0.075289 memory: 9871 loss_kpt: 0.000632 acc_pose: 0.852092 loss: 0.000632 2022/09/08 16:45:37 - mmengine - INFO - Epoch(train) [92][250/293] lr: 5.000000e-04 eta: 4:08:46 time: 0.510111 data_time: 0.074767 memory: 9871 loss_kpt: 0.000643 acc_pose: 0.753852 loss: 0.000643 2022/09/08 16:45:58 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 16:45:58 - mmengine - INFO - Saving checkpoint at 92 epochs 2022/09/08 16:46:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 16:46:29 - mmengine - INFO - Epoch(train) [93][50/293] lr: 5.000000e-04 eta: 4:07:48 time: 0.517038 data_time: 0.080169 memory: 9871 loss_kpt: 0.000642 acc_pose: 0.792720 loss: 0.000642 2022/09/08 16:46:53 - mmengine - INFO - Epoch(train) [93][100/293] lr: 5.000000e-04 eta: 4:07:30 time: 0.492986 data_time: 0.079310 memory: 9871 loss_kpt: 0.000634 acc_pose: 0.809283 loss: 0.000634 2022/09/08 16:47:18 - mmengine - INFO - Epoch(train) [93][150/293] lr: 5.000000e-04 eta: 4:07:12 time: 0.487005 data_time: 0.075041 memory: 9871 loss_kpt: 0.000630 acc_pose: 0.763426 loss: 0.000630 2022/09/08 16:47:43 - mmengine - INFO - Epoch(train) [93][200/293] lr: 5.000000e-04 eta: 4:06:56 time: 0.504630 data_time: 0.078847 memory: 9871 loss_kpt: 0.000634 acc_pose: 0.813969 loss: 0.000634 2022/09/08 16:48:08 - mmengine - INFO - Epoch(train) [93][250/293] lr: 5.000000e-04 eta: 4:06:39 time: 0.504298 data_time: 0.073981 memory: 9871 loss_kpt: 0.000648 acc_pose: 0.845708 loss: 0.000648 2022/09/08 16:48:29 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 16:48:29 - mmengine - INFO - Saving checkpoint at 93 epochs 2022/09/08 16:49:00 - mmengine - INFO - Epoch(train) [94][50/293] lr: 5.000000e-04 eta: 4:05:41 time: 0.515300 data_time: 0.082894 memory: 9871 loss_kpt: 0.000633 acc_pose: 0.851521 loss: 0.000633 2022/09/08 16:49:25 - mmengine - INFO - Epoch(train) [94][100/293] lr: 5.000000e-04 eta: 4:05:23 time: 0.495795 data_time: 0.076380 memory: 9871 loss_kpt: 0.000640 acc_pose: 0.884682 loss: 0.000640 2022/09/08 16:49:50 - mmengine - INFO - Epoch(train) [94][150/293] lr: 5.000000e-04 eta: 4:05:06 time: 0.499201 data_time: 0.074955 memory: 9871 loss_kpt: 0.000661 acc_pose: 0.866210 loss: 0.000661 2022/09/08 16:50:15 - mmengine - INFO - Epoch(train) [94][200/293] lr: 5.000000e-04 eta: 4:04:49 time: 0.503793 data_time: 0.079288 memory: 9871 loss_kpt: 0.000627 acc_pose: 0.841534 loss: 0.000627 2022/09/08 16:50:40 - mmengine - INFO - Epoch(train) [94][250/293] lr: 5.000000e-04 eta: 4:04:31 time: 0.497754 data_time: 0.076052 memory: 9871 loss_kpt: 0.000633 acc_pose: 0.837805 loss: 0.000633 2022/09/08 16:51:01 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 16:51:01 - mmengine - INFO - Saving checkpoint at 94 epochs 2022/09/08 16:51:31 - mmengine - INFO - Epoch(train) [95][50/293] lr: 5.000000e-04 eta: 4:03:34 time: 0.513889 data_time: 0.090424 memory: 9871 loss_kpt: 0.000633 acc_pose: 0.804356 loss: 0.000633 2022/09/08 16:51:56 - mmengine - INFO - Epoch(train) [95][100/293] lr: 5.000000e-04 eta: 4:03:17 time: 0.507415 data_time: 0.071735 memory: 9871 loss_kpt: 0.000645 acc_pose: 0.848095 loss: 0.000645 2022/09/08 16:52:21 - mmengine - INFO - Epoch(train) [95][150/293] lr: 5.000000e-04 eta: 4:02:59 time: 0.496570 data_time: 0.076307 memory: 9871 loss_kpt: 0.000637 acc_pose: 0.842750 loss: 0.000637 2022/09/08 16:52:46 - mmengine - INFO - Epoch(train) [95][200/293] lr: 5.000000e-04 eta: 4:02:41 time: 0.491919 data_time: 0.070779 memory: 9871 loss_kpt: 0.000640 acc_pose: 0.828815 loss: 0.000640 2022/09/08 16:53:11 - mmengine - INFO - Epoch(train) [95][250/293] lr: 5.000000e-04 eta: 4:02:25 time: 0.507912 data_time: 0.071687 memory: 9871 loss_kpt: 0.000617 acc_pose: 0.849957 loss: 0.000617 2022/09/08 16:53:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 16:53:33 - mmengine - INFO - Saving checkpoint at 95 epochs 2022/09/08 16:54:02 - mmengine - INFO - Epoch(train) [96][50/293] lr: 5.000000e-04 eta: 4:01:26 time: 0.497879 data_time: 0.084348 memory: 9871 loss_kpt: 0.000633 acc_pose: 0.793312 loss: 0.000633 2022/09/08 16:54:28 - mmengine - INFO - Epoch(train) [96][100/293] lr: 5.000000e-04 eta: 4:01:09 time: 0.502898 data_time: 0.080200 memory: 9871 loss_kpt: 0.000644 acc_pose: 0.837579 loss: 0.000644 2022/09/08 16:54:53 - mmengine - INFO - Epoch(train) [96][150/293] lr: 5.000000e-04 eta: 4:00:52 time: 0.513391 data_time: 0.072453 memory: 9871 loss_kpt: 0.000642 acc_pose: 0.840998 loss: 0.000642 2022/09/08 16:55:01 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 16:55:19 - mmengine - INFO - Epoch(train) [96][200/293] lr: 5.000000e-04 eta: 4:00:35 time: 0.505339 data_time: 0.080528 memory: 9871 loss_kpt: 0.000645 acc_pose: 0.832679 loss: 0.000645 2022/09/08 16:55:44 - mmengine - INFO - Epoch(train) [96][250/293] lr: 5.000000e-04 eta: 4:00:18 time: 0.500813 data_time: 0.075683 memory: 9871 loss_kpt: 0.000630 acc_pose: 0.852601 loss: 0.000630 2022/09/08 16:56:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 16:56:05 - mmengine - INFO - Saving checkpoint at 96 epochs 2022/09/08 16:56:35 - mmengine - INFO - Epoch(train) [97][50/293] lr: 5.000000e-04 eta: 3:59:20 time: 0.510151 data_time: 0.082473 memory: 9871 loss_kpt: 0.000631 acc_pose: 0.833487 loss: 0.000631 2022/09/08 16:57:00 - mmengine - INFO - Epoch(train) [97][100/293] lr: 5.000000e-04 eta: 3:59:03 time: 0.500146 data_time: 0.074105 memory: 9871 loss_kpt: 0.000631 acc_pose: 0.852569 loss: 0.000631 2022/09/08 16:57:25 - mmengine - INFO - Epoch(train) [97][150/293] lr: 5.000000e-04 eta: 3:58:46 time: 0.499038 data_time: 0.079535 memory: 9871 loss_kpt: 0.000639 acc_pose: 0.861679 loss: 0.000639 2022/09/08 16:57:50 - mmengine - INFO - Epoch(train) [97][200/293] lr: 5.000000e-04 eta: 3:58:28 time: 0.502164 data_time: 0.078436 memory: 9871 loss_kpt: 0.000661 acc_pose: 0.781367 loss: 0.000661 2022/09/08 16:58:15 - mmengine - INFO - Epoch(train) [97][250/293] lr: 5.000000e-04 eta: 3:58:11 time: 0.500572 data_time: 0.076098 memory: 9871 loss_kpt: 0.000618 acc_pose: 0.821544 loss: 0.000618 2022/09/08 16:58:36 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 16:58:36 - mmengine - INFO - Saving checkpoint at 97 epochs 2022/09/08 16:59:06 - mmengine - INFO - Epoch(train) [98][50/293] lr: 5.000000e-04 eta: 3:57:14 time: 0.508594 data_time: 0.082405 memory: 9871 loss_kpt: 0.000635 acc_pose: 0.833037 loss: 0.000635 2022/09/08 16:59:31 - mmengine - INFO - Epoch(train) [98][100/293] lr: 5.000000e-04 eta: 3:56:56 time: 0.497623 data_time: 0.074936 memory: 9871 loss_kpt: 0.000624 acc_pose: 0.848031 loss: 0.000624 2022/09/08 16:59:56 - mmengine - INFO - Epoch(train) [98][150/293] lr: 5.000000e-04 eta: 3:56:38 time: 0.499808 data_time: 0.071465 memory: 9871 loss_kpt: 0.000626 acc_pose: 0.849308 loss: 0.000626 2022/09/08 17:00:21 - mmengine - INFO - Epoch(train) [98][200/293] lr: 5.000000e-04 eta: 3:56:21 time: 0.497477 data_time: 0.082133 memory: 9871 loss_kpt: 0.000645 acc_pose: 0.831058 loss: 0.000645 2022/09/08 17:00:45 - mmengine - INFO - Epoch(train) [98][250/293] lr: 5.000000e-04 eta: 3:56:03 time: 0.493720 data_time: 0.076545 memory: 9871 loss_kpt: 0.000643 acc_pose: 0.783432 loss: 0.000643 2022/09/08 17:01:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 17:01:06 - mmengine - INFO - Saving checkpoint at 98 epochs 2022/09/08 17:01:36 - mmengine - INFO - Epoch(train) [99][50/293] lr: 5.000000e-04 eta: 3:55:06 time: 0.507001 data_time: 0.086722 memory: 9871 loss_kpt: 0.000640 acc_pose: 0.804267 loss: 0.000640 2022/09/08 17:02:01 - mmengine - INFO - Epoch(train) [99][100/293] lr: 5.000000e-04 eta: 3:54:49 time: 0.510886 data_time: 0.072656 memory: 9871 loss_kpt: 0.000635 acc_pose: 0.849109 loss: 0.000635 2022/09/08 17:02:26 - mmengine - INFO - Epoch(train) [99][150/293] lr: 5.000000e-04 eta: 3:54:31 time: 0.492962 data_time: 0.078356 memory: 9871 loss_kpt: 0.000630 acc_pose: 0.859720 loss: 0.000630 2022/09/08 17:02:51 - mmengine - INFO - Epoch(train) [99][200/293] lr: 5.000000e-04 eta: 3:54:13 time: 0.503610 data_time: 0.074185 memory: 9871 loss_kpt: 0.000619 acc_pose: 0.800450 loss: 0.000619 2022/09/08 17:03:16 - mmengine - INFO - Epoch(train) [99][250/293] lr: 5.000000e-04 eta: 3:53:56 time: 0.500713 data_time: 0.074471 memory: 9871 loss_kpt: 0.000621 acc_pose: 0.842277 loss: 0.000621 2022/09/08 17:03:34 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 17:03:38 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 17:03:38 - mmengine - INFO - Saving checkpoint at 99 epochs 2022/09/08 17:04:08 - mmengine - INFO - Epoch(train) [100][50/293] lr: 5.000000e-04 eta: 3:53:00 time: 0.514427 data_time: 0.087741 memory: 9871 loss_kpt: 0.000629 acc_pose: 0.832608 loss: 0.000629 2022/09/08 17:04:32 - mmengine - INFO - Epoch(train) [100][100/293] lr: 5.000000e-04 eta: 3:52:41 time: 0.487483 data_time: 0.076274 memory: 9871 loss_kpt: 0.000642 acc_pose: 0.808299 loss: 0.000642 2022/09/08 17:04:57 - mmengine - INFO - Epoch(train) [100][150/293] lr: 5.000000e-04 eta: 3:52:24 time: 0.498218 data_time: 0.074865 memory: 9871 loss_kpt: 0.000630 acc_pose: 0.820415 loss: 0.000630 2022/09/08 17:05:23 - mmengine - INFO - Epoch(train) [100][200/293] lr: 5.000000e-04 eta: 3:52:06 time: 0.508057 data_time: 0.075967 memory: 9871 loss_kpt: 0.000644 acc_pose: 0.775260 loss: 0.000644 2022/09/08 17:05:48 - mmengine - INFO - Epoch(train) [100][250/293] lr: 5.000000e-04 eta: 3:51:49 time: 0.499406 data_time: 0.080252 memory: 9871 loss_kpt: 0.000642 acc_pose: 0.818947 loss: 0.000642 2022/09/08 17:06:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 17:06:08 - mmengine - INFO - Saving checkpoint at 100 epochs 2022/09/08 17:06:19 - mmengine - INFO - Epoch(val) [100][50/407] eta: 0:00:44 time: 0.123939 data_time: 0.015246 memory: 9871 2022/09/08 17:06:25 - mmengine - INFO - Epoch(val) [100][100/407] eta: 0:00:36 time: 0.119107 data_time: 0.010886 memory: 920 2022/09/08 17:06:31 - mmengine - INFO - Epoch(val) [100][150/407] eta: 0:00:31 time: 0.121343 data_time: 0.012262 memory: 920 2022/09/08 17:06:38 - mmengine - INFO - Epoch(val) [100][200/407] eta: 0:00:25 time: 0.122170 data_time: 0.011493 memory: 920 2022/09/08 17:06:44 - mmengine - INFO - Epoch(val) [100][250/407] eta: 0:00:19 time: 0.123342 data_time: 0.009763 memory: 920 2022/09/08 17:06:50 - mmengine - INFO - Epoch(val) [100][300/407] eta: 0:00:12 time: 0.117925 data_time: 0.009817 memory: 920 2022/09/08 17:06:56 - mmengine - INFO - Epoch(val) [100][350/407] eta: 0:00:06 time: 0.119847 data_time: 0.010934 memory: 920 2022/09/08 17:07:01 - mmengine - INFO - Epoch(val) [100][400/407] eta: 0:00:00 time: 0.112238 data_time: 0.010467 memory: 920 2022/09/08 17:07:35 - mmengine - INFO - Evaluating CocoMetric... 2022/09/08 17:07:49 - mmengine - INFO - Epoch(val) [100][407/407] coco/AP: 0.722258 coco/AP .5: 0.894547 coco/AP .75: 0.795099 coco/AP (M): 0.686329 coco/AP (L): 0.791949 coco/AR: 0.779676 coco/AR .5: 0.936713 coco/AR .75: 0.844144 coco/AR (M): 0.736739 coco/AR (L): 0.841509 2022/09/08 17:08:14 - mmengine - INFO - Epoch(train) [101][50/293] lr: 5.000000e-04 eta: 3:50:52 time: 0.504611 data_time: 0.083416 memory: 9871 loss_kpt: 0.000637 acc_pose: 0.850001 loss: 0.000637 2022/09/08 17:08:39 - mmengine - INFO - Epoch(train) [101][100/293] lr: 5.000000e-04 eta: 3:50:35 time: 0.505446 data_time: 0.071927 memory: 9871 loss_kpt: 0.000618 acc_pose: 0.849089 loss: 0.000618 2022/09/08 17:09:05 - mmengine - INFO - Epoch(train) [101][150/293] lr: 5.000000e-04 eta: 3:50:17 time: 0.508035 data_time: 0.075475 memory: 9871 loss_kpt: 0.000640 acc_pose: 0.846817 loss: 0.000640 2022/09/08 17:09:30 - mmengine - INFO - Epoch(train) [101][200/293] lr: 5.000000e-04 eta: 3:50:00 time: 0.501724 data_time: 0.071984 memory: 9871 loss_kpt: 0.000629 acc_pose: 0.825943 loss: 0.000629 2022/09/08 17:09:55 - mmengine - INFO - Epoch(train) [101][250/293] lr: 5.000000e-04 eta: 3:49:43 time: 0.512349 data_time: 0.077550 memory: 9871 loss_kpt: 0.000627 acc_pose: 0.779229 loss: 0.000627 2022/09/08 17:10:16 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 17:10:16 - mmengine - INFO - Saving checkpoint at 101 epochs 2022/09/08 17:10:47 - mmengine - INFO - Epoch(train) [102][50/293] lr: 5.000000e-04 eta: 3:48:47 time: 0.508866 data_time: 0.083477 memory: 9871 loss_kpt: 0.000636 acc_pose: 0.804136 loss: 0.000636 2022/09/08 17:11:11 - mmengine - INFO - Epoch(train) [102][100/293] lr: 5.000000e-04 eta: 3:48:28 time: 0.490470 data_time: 0.076478 memory: 9871 loss_kpt: 0.000632 acc_pose: 0.846280 loss: 0.000632 2022/09/08 17:11:37 - mmengine - INFO - Epoch(train) [102][150/293] lr: 5.000000e-04 eta: 3:48:12 time: 0.515737 data_time: 0.079378 memory: 9871 loss_kpt: 0.000643 acc_pose: 0.821170 loss: 0.000643 2022/09/08 17:12:01 - mmengine - INFO - Epoch(train) [102][200/293] lr: 5.000000e-04 eta: 3:47:53 time: 0.486289 data_time: 0.076814 memory: 9871 loss_kpt: 0.000621 acc_pose: 0.827269 loss: 0.000621 2022/09/08 17:12:26 - mmengine - INFO - Epoch(train) [102][250/293] lr: 5.000000e-04 eta: 3:47:35 time: 0.501000 data_time: 0.076207 memory: 9871 loss_kpt: 0.000634 acc_pose: 0.799840 loss: 0.000634 2022/09/08 17:12:47 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 17:12:47 - mmengine - INFO - Saving checkpoint at 102 epochs 2022/09/08 17:13:17 - mmengine - INFO - Epoch(train) [103][50/293] lr: 5.000000e-04 eta: 3:46:39 time: 0.504019 data_time: 0.081498 memory: 9871 loss_kpt: 0.000625 acc_pose: 0.807301 loss: 0.000625 2022/09/08 17:13:42 - mmengine - INFO - Epoch(train) [103][100/293] lr: 5.000000e-04 eta: 3:46:21 time: 0.500466 data_time: 0.076734 memory: 9871 loss_kpt: 0.000633 acc_pose: 0.858958 loss: 0.000633 2022/09/08 17:13:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 17:14:07 - mmengine - INFO - Epoch(train) [103][150/293] lr: 5.000000e-04 eta: 3:46:03 time: 0.493127 data_time: 0.071616 memory: 9871 loss_kpt: 0.000637 acc_pose: 0.808745 loss: 0.000637 2022/09/08 17:14:31 - mmengine - INFO - Epoch(train) [103][200/293] lr: 5.000000e-04 eta: 3:45:45 time: 0.492442 data_time: 0.071755 memory: 9871 loss_kpt: 0.000629 acc_pose: 0.811906 loss: 0.000629 2022/09/08 17:14:56 - mmengine - INFO - Epoch(train) [103][250/293] lr: 5.000000e-04 eta: 3:45:27 time: 0.496982 data_time: 0.071166 memory: 9871 loss_kpt: 0.000624 acc_pose: 0.834859 loss: 0.000624 2022/09/08 17:15:17 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 17:15:17 - mmengine - INFO - Saving checkpoint at 103 epochs 2022/09/08 17:15:47 - mmengine - INFO - Epoch(train) [104][50/293] lr: 5.000000e-04 eta: 3:44:31 time: 0.505982 data_time: 0.085587 memory: 9871 loss_kpt: 0.000623 acc_pose: 0.824544 loss: 0.000623 2022/09/08 17:16:12 - mmengine - INFO - Epoch(train) [104][100/293] lr: 5.000000e-04 eta: 3:44:14 time: 0.499039 data_time: 0.073157 memory: 9871 loss_kpt: 0.000629 acc_pose: 0.806150 loss: 0.000629 2022/09/08 17:16:37 - mmengine - INFO - Epoch(train) [104][150/293] lr: 5.000000e-04 eta: 3:43:55 time: 0.493071 data_time: 0.074804 memory: 9871 loss_kpt: 0.000627 acc_pose: 0.809495 loss: 0.000627 2022/09/08 17:17:02 - mmengine - INFO - Epoch(train) [104][200/293] lr: 5.000000e-04 eta: 3:43:37 time: 0.499264 data_time: 0.078220 memory: 9871 loss_kpt: 0.000615 acc_pose: 0.825246 loss: 0.000615 2022/09/08 17:17:28 - mmengine - INFO - Epoch(train) [104][250/293] lr: 5.000000e-04 eta: 3:43:20 time: 0.523131 data_time: 0.073775 memory: 9871 loss_kpt: 0.000640 acc_pose: 0.809179 loss: 0.000640 2022/09/08 17:17:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 17:17:49 - mmengine - INFO - Saving checkpoint at 104 epochs 2022/09/08 17:18:19 - mmengine - INFO - Epoch(train) [105][50/293] lr: 5.000000e-04 eta: 3:42:25 time: 0.509394 data_time: 0.084348 memory: 9871 loss_kpt: 0.000617 acc_pose: 0.864789 loss: 0.000617 2022/09/08 17:18:45 - mmengine - INFO - Epoch(train) [105][100/293] lr: 5.000000e-04 eta: 3:42:08 time: 0.506904 data_time: 0.073127 memory: 9871 loss_kpt: 0.000635 acc_pose: 0.832900 loss: 0.000635 2022/09/08 17:19:09 - mmengine - INFO - Epoch(train) [105][150/293] lr: 5.000000e-04 eta: 3:41:50 time: 0.496359 data_time: 0.075227 memory: 9871 loss_kpt: 0.000631 acc_pose: 0.845987 loss: 0.000631 2022/09/08 17:19:35 - mmengine - INFO - Epoch(train) [105][200/293] lr: 5.000000e-04 eta: 3:41:32 time: 0.502924 data_time: 0.075056 memory: 9871 loss_kpt: 0.000626 acc_pose: 0.853378 loss: 0.000626 2022/09/08 17:19:59 - mmengine - INFO - Epoch(train) [105][250/293] lr: 5.000000e-04 eta: 3:41:13 time: 0.486872 data_time: 0.074946 memory: 9871 loss_kpt: 0.000628 acc_pose: 0.837452 loss: 0.000628 2022/09/08 17:20:20 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 17:20:20 - mmengine - INFO - Saving checkpoint at 105 epochs 2022/09/08 17:20:50 - mmengine - INFO - Epoch(train) [106][50/293] lr: 5.000000e-04 eta: 3:40:18 time: 0.502072 data_time: 0.087210 memory: 9871 loss_kpt: 0.000626 acc_pose: 0.833219 loss: 0.000626 2022/09/08 17:21:15 - mmengine - INFO - Epoch(train) [106][100/293] lr: 5.000000e-04 eta: 3:40:00 time: 0.503392 data_time: 0.075001 memory: 9871 loss_kpt: 0.000617 acc_pose: 0.840040 loss: 0.000617 2022/09/08 17:21:40 - mmengine - INFO - Epoch(train) [106][150/293] lr: 5.000000e-04 eta: 3:39:42 time: 0.501449 data_time: 0.075113 memory: 9871 loss_kpt: 0.000626 acc_pose: 0.804878 loss: 0.000626 2022/09/08 17:22:05 - mmengine - INFO - Epoch(train) [106][200/293] lr: 5.000000e-04 eta: 3:39:24 time: 0.500363 data_time: 0.079638 memory: 9871 loss_kpt: 0.000631 acc_pose: 0.839839 loss: 0.000631 2022/09/08 17:22:23 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 17:22:31 - mmengine - INFO - Epoch(train) [106][250/293] lr: 5.000000e-04 eta: 3:39:06 time: 0.501010 data_time: 0.076379 memory: 9871 loss_kpt: 0.000630 acc_pose: 0.837433 loss: 0.000630 2022/09/08 17:22:52 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 17:22:52 - mmengine - INFO - Saving checkpoint at 106 epochs 2022/09/08 17:23:22 - mmengine - INFO - Epoch(train) [107][50/293] lr: 5.000000e-04 eta: 3:38:12 time: 0.520456 data_time: 0.084826 memory: 9871 loss_kpt: 0.000636 acc_pose: 0.819640 loss: 0.000636 2022/09/08 17:23:48 - mmengine - INFO - Epoch(train) [107][100/293] lr: 5.000000e-04 eta: 3:37:55 time: 0.509880 data_time: 0.071919 memory: 9871 loss_kpt: 0.000635 acc_pose: 0.831735 loss: 0.000635 2022/09/08 17:24:13 - mmengine - INFO - Epoch(train) [107][150/293] lr: 5.000000e-04 eta: 3:37:36 time: 0.500489 data_time: 0.082454 memory: 9871 loss_kpt: 0.000619 acc_pose: 0.770761 loss: 0.000619 2022/09/08 17:24:37 - mmengine - INFO - Epoch(train) [107][200/293] lr: 5.000000e-04 eta: 3:37:18 time: 0.489289 data_time: 0.075246 memory: 9871 loss_kpt: 0.000618 acc_pose: 0.876268 loss: 0.000618 2022/09/08 17:25:02 - mmengine - INFO - Epoch(train) [107][250/293] lr: 5.000000e-04 eta: 3:36:59 time: 0.497788 data_time: 0.076883 memory: 9871 loss_kpt: 0.000632 acc_pose: 0.775110 loss: 0.000632 2022/09/08 17:25:24 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 17:25:24 - mmengine - INFO - Saving checkpoint at 107 epochs 2022/09/08 17:25:54 - mmengine - INFO - Epoch(train) [108][50/293] lr: 5.000000e-04 eta: 3:36:05 time: 0.505249 data_time: 0.086534 memory: 9871 loss_kpt: 0.000632 acc_pose: 0.806669 loss: 0.000632 2022/09/08 17:26:19 - mmengine - INFO - Epoch(train) [108][100/293] lr: 5.000000e-04 eta: 3:35:47 time: 0.499374 data_time: 0.075028 memory: 9871 loss_kpt: 0.000624 acc_pose: 0.821041 loss: 0.000624 2022/09/08 17:26:44 - mmengine - INFO - Epoch(train) [108][150/293] lr: 5.000000e-04 eta: 3:35:29 time: 0.498691 data_time: 0.073159 memory: 9871 loss_kpt: 0.000621 acc_pose: 0.825771 loss: 0.000621 2022/09/08 17:27:09 - mmengine - INFO - Epoch(train) [108][200/293] lr: 5.000000e-04 eta: 3:35:10 time: 0.499394 data_time: 0.076610 memory: 9871 loss_kpt: 0.000624 acc_pose: 0.786020 loss: 0.000624 2022/09/08 17:27:34 - mmengine - INFO - Epoch(train) [108][250/293] lr: 5.000000e-04 eta: 3:34:52 time: 0.496413 data_time: 0.080157 memory: 9871 loss_kpt: 0.000620 acc_pose: 0.830295 loss: 0.000620 2022/09/08 17:27:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 17:27:55 - mmengine - INFO - Saving checkpoint at 108 epochs 2022/09/08 17:28:28 - mmengine - INFO - Epoch(train) [109][50/293] lr: 5.000000e-04 eta: 3:33:58 time: 0.499943 data_time: 0.083111 memory: 9871 loss_kpt: 0.000622 acc_pose: 0.791603 loss: 0.000622 2022/09/08 17:28:52 - mmengine - INFO - Epoch(train) [109][100/293] lr: 5.000000e-04 eta: 3:33:39 time: 0.493178 data_time: 0.075876 memory: 9871 loss_kpt: 0.000624 acc_pose: 0.828549 loss: 0.000624 2022/09/08 17:29:17 - mmengine - INFO - Epoch(train) [109][150/293] lr: 5.000000e-04 eta: 3:33:21 time: 0.500107 data_time: 0.078464 memory: 9871 loss_kpt: 0.000609 acc_pose: 0.848679 loss: 0.000609 2022/09/08 17:29:43 - mmengine - INFO - Epoch(train) [109][200/293] lr: 5.000000e-04 eta: 3:33:03 time: 0.503793 data_time: 0.077434 memory: 9871 loss_kpt: 0.000629 acc_pose: 0.837051 loss: 0.000629 2022/09/08 17:30:08 - mmengine - INFO - Epoch(train) [109][250/293] lr: 5.000000e-04 eta: 3:32:45 time: 0.500904 data_time: 0.081022 memory: 9871 loss_kpt: 0.000628 acc_pose: 0.858394 loss: 0.000628 2022/09/08 17:30:29 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 17:30:29 - mmengine - INFO - Saving checkpoint at 109 epochs 2022/09/08 17:30:59 - mmengine - INFO - Epoch(train) [110][50/293] lr: 5.000000e-04 eta: 3:31:51 time: 0.511798 data_time: 0.079296 memory: 9871 loss_kpt: 0.000633 acc_pose: 0.794216 loss: 0.000633 2022/09/08 17:31:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 17:31:24 - mmengine - INFO - Epoch(train) [110][100/293] lr: 5.000000e-04 eta: 3:31:32 time: 0.489957 data_time: 0.083061 memory: 9871 loss_kpt: 0.000629 acc_pose: 0.832153 loss: 0.000629 2022/09/08 17:31:50 - mmengine - INFO - Epoch(train) [110][150/293] lr: 5.000000e-04 eta: 3:31:15 time: 0.511351 data_time: 0.078694 memory: 9871 loss_kpt: 0.000632 acc_pose: 0.801697 loss: 0.000632 2022/09/08 17:32:14 - mmengine - INFO - Epoch(train) [110][200/293] lr: 5.000000e-04 eta: 3:30:56 time: 0.499212 data_time: 0.076900 memory: 9871 loss_kpt: 0.000620 acc_pose: 0.829858 loss: 0.000620 2022/09/08 17:32:39 - mmengine - INFO - Epoch(train) [110][250/293] lr: 5.000000e-04 eta: 3:30:37 time: 0.490864 data_time: 0.075207 memory: 9871 loss_kpt: 0.000629 acc_pose: 0.829909 loss: 0.000629 2022/09/08 17:33:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 17:33:00 - mmengine - INFO - Saving checkpoint at 110 epochs 2022/09/08 17:33:12 - mmengine - INFO - Epoch(val) [110][50/407] eta: 0:00:44 time: 0.125239 data_time: 0.014558 memory: 9871 2022/09/08 17:33:18 - mmengine - INFO - Epoch(val) [110][100/407] eta: 0:00:39 time: 0.127682 data_time: 0.012974 memory: 920 2022/09/08 17:33:24 - mmengine - INFO - Epoch(val) [110][150/407] eta: 0:00:30 time: 0.118625 data_time: 0.009814 memory: 920 2022/09/08 17:33:30 - mmengine - INFO - Epoch(val) [110][200/407] eta: 0:00:24 time: 0.118459 data_time: 0.009714 memory: 920 2022/09/08 17:33:36 - mmengine - INFO - Epoch(val) [110][250/407] eta: 0:00:18 time: 0.119772 data_time: 0.009524 memory: 920 2022/09/08 17:33:42 - mmengine - INFO - Epoch(val) [110][300/407] eta: 0:00:13 time: 0.128758 data_time: 0.020934 memory: 920 2022/09/08 17:33:49 - mmengine - INFO - Epoch(val) [110][350/407] eta: 0:00:07 time: 0.125653 data_time: 0.016245 memory: 920 2022/09/08 17:33:54 - mmengine - INFO - Epoch(val) [110][400/407] eta: 0:00:00 time: 0.114137 data_time: 0.013537 memory: 920 2022/09/08 17:34:29 - mmengine - INFO - Evaluating CocoMetric... 2022/09/08 17:34:42 - mmengine - INFO - Epoch(val) [110][407/407] coco/AP: 0.730044 coco/AP .5: 0.899447 coco/AP .75: 0.806087 coco/AP (M): 0.694886 coco/AP (L): 0.794756 coco/AR: 0.784194 coco/AR .5: 0.937972 coco/AR .75: 0.851385 coco/AR (M): 0.742939 coco/AR (L): 0.843627 2022/09/08 17:34:42 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220908/hrnet_w32_256/best_coco/AP_epoch_90.pth is removed 2022/09/08 17:34:45 - mmengine - INFO - The best checkpoint with 0.7300 coco/AP at 110 epoch is saved to best_coco/AP_epoch_110.pth. 2022/09/08 17:35:11 - mmengine - INFO - Epoch(train) [111][50/293] lr: 5.000000e-04 eta: 3:29:44 time: 0.510165 data_time: 0.079559 memory: 9871 loss_kpt: 0.000617 acc_pose: 0.856727 loss: 0.000617 2022/09/08 17:35:36 - mmengine - INFO - Epoch(train) [111][100/293] lr: 5.000000e-04 eta: 3:29:26 time: 0.499360 data_time: 0.074652 memory: 9871 loss_kpt: 0.000633 acc_pose: 0.824778 loss: 0.000633 2022/09/08 17:36:01 - mmengine - INFO - Epoch(train) [111][150/293] lr: 5.000000e-04 eta: 3:29:08 time: 0.503314 data_time: 0.075434 memory: 9871 loss_kpt: 0.000625 acc_pose: 0.791314 loss: 0.000625 2022/09/08 17:36:27 - mmengine - INFO - Epoch(train) [111][200/293] lr: 5.000000e-04 eta: 3:28:50 time: 0.511308 data_time: 0.072524 memory: 9871 loss_kpt: 0.000630 acc_pose: 0.838204 loss: 0.000630 2022/09/08 17:36:52 - mmengine - INFO - Epoch(train) [111][250/293] lr: 5.000000e-04 eta: 3:28:31 time: 0.498574 data_time: 0.070818 memory: 9871 loss_kpt: 0.000630 acc_pose: 0.850184 loss: 0.000630 2022/09/08 17:37:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 17:37:13 - mmengine - INFO - Saving checkpoint at 111 epochs 2022/09/08 17:37:43 - mmengine - INFO - Epoch(train) [112][50/293] lr: 5.000000e-04 eta: 3:27:38 time: 0.508803 data_time: 0.084145 memory: 9871 loss_kpt: 0.000631 acc_pose: 0.807771 loss: 0.000631 2022/09/08 17:38:08 - mmengine - INFO - Epoch(train) [112][100/293] lr: 5.000000e-04 eta: 3:27:20 time: 0.501556 data_time: 0.075437 memory: 9871 loss_kpt: 0.000629 acc_pose: 0.855194 loss: 0.000629 2022/09/08 17:38:33 - mmengine - INFO - Epoch(train) [112][150/293] lr: 5.000000e-04 eta: 3:27:01 time: 0.495817 data_time: 0.070429 memory: 9871 loss_kpt: 0.000628 acc_pose: 0.830006 loss: 0.000628 2022/09/08 17:38:58 - mmengine - INFO - Epoch(train) [112][200/293] lr: 5.000000e-04 eta: 3:26:43 time: 0.503517 data_time: 0.071085 memory: 9871 loss_kpt: 0.000626 acc_pose: 0.833738 loss: 0.000626 2022/09/08 17:39:24 - mmengine - INFO - Epoch(train) [112][250/293] lr: 5.000000e-04 eta: 3:26:25 time: 0.508544 data_time: 0.073028 memory: 9871 loss_kpt: 0.000629 acc_pose: 0.849424 loss: 0.000629 2022/09/08 17:39:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 17:39:46 - mmengine - INFO - Saving checkpoint at 112 epochs 2022/09/08 17:40:15 - mmengine - INFO - Epoch(train) [113][50/293] lr: 5.000000e-04 eta: 3:25:32 time: 0.505138 data_time: 0.082819 memory: 9871 loss_kpt: 0.000615 acc_pose: 0.802153 loss: 0.000615 2022/09/08 17:40:41 - mmengine - INFO - Epoch(train) [113][100/293] lr: 5.000000e-04 eta: 3:25:14 time: 0.509223 data_time: 0.077685 memory: 9871 loss_kpt: 0.000616 acc_pose: 0.824003 loss: 0.000616 2022/09/08 17:41:06 - mmengine - INFO - Epoch(train) [113][150/293] lr: 5.000000e-04 eta: 3:24:55 time: 0.501327 data_time: 0.076308 memory: 9871 loss_kpt: 0.000617 acc_pose: 0.816244 loss: 0.000617 2022/09/08 17:41:23 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 17:41:31 - mmengine - INFO - Epoch(train) [113][200/293] lr: 5.000000e-04 eta: 3:24:37 time: 0.504786 data_time: 0.073649 memory: 9871 loss_kpt: 0.000632 acc_pose: 0.840577 loss: 0.000632 2022/09/08 17:41:56 - mmengine - INFO - Epoch(train) [113][250/293] lr: 5.000000e-04 eta: 3:24:18 time: 0.497606 data_time: 0.075094 memory: 9871 loss_kpt: 0.000620 acc_pose: 0.828487 loss: 0.000620 2022/09/08 17:42:17 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 17:42:17 - mmengine - INFO - Saving checkpoint at 113 epochs 2022/09/08 17:42:47 - mmengine - INFO - Epoch(train) [114][50/293] lr: 5.000000e-04 eta: 3:23:25 time: 0.502858 data_time: 0.083635 memory: 9871 loss_kpt: 0.000624 acc_pose: 0.830101 loss: 0.000624 2022/09/08 17:43:12 - mmengine - INFO - Epoch(train) [114][100/293] lr: 5.000000e-04 eta: 3:23:07 time: 0.502959 data_time: 0.076739 memory: 9871 loss_kpt: 0.000623 acc_pose: 0.820350 loss: 0.000623 2022/09/08 17:43:37 - mmengine - INFO - Epoch(train) [114][150/293] lr: 5.000000e-04 eta: 3:22:48 time: 0.498469 data_time: 0.077072 memory: 9871 loss_kpt: 0.000627 acc_pose: 0.811532 loss: 0.000627 2022/09/08 17:44:02 - mmengine - INFO - Epoch(train) [114][200/293] lr: 5.000000e-04 eta: 3:22:30 time: 0.498525 data_time: 0.075186 memory: 9871 loss_kpt: 0.000607 acc_pose: 0.829690 loss: 0.000607 2022/09/08 17:44:27 - mmengine - INFO - Epoch(train) [114][250/293] lr: 5.000000e-04 eta: 3:22:11 time: 0.502599 data_time: 0.072607 memory: 9871 loss_kpt: 0.000631 acc_pose: 0.816959 loss: 0.000631 2022/09/08 17:44:48 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 17:44:48 - mmengine - INFO - Saving checkpoint at 114 epochs 2022/09/08 17:45:19 - mmengine - INFO - Epoch(train) [115][50/293] lr: 5.000000e-04 eta: 3:21:19 time: 0.512749 data_time: 0.082280 memory: 9871 loss_kpt: 0.000620 acc_pose: 0.800537 loss: 0.000620 2022/09/08 17:45:43 - mmengine - INFO - Epoch(train) [115][100/293] lr: 5.000000e-04 eta: 3:21:00 time: 0.493046 data_time: 0.080354 memory: 9871 loss_kpt: 0.000628 acc_pose: 0.811402 loss: 0.000628 2022/09/08 17:46:08 - mmengine - INFO - Epoch(train) [115][150/293] lr: 5.000000e-04 eta: 3:20:41 time: 0.495983 data_time: 0.076277 memory: 9871 loss_kpt: 0.000612 acc_pose: 0.784658 loss: 0.000612 2022/09/08 17:46:33 - mmengine - INFO - Epoch(train) [115][200/293] lr: 5.000000e-04 eta: 3:20:23 time: 0.503243 data_time: 0.075912 memory: 9871 loss_kpt: 0.000625 acc_pose: 0.833610 loss: 0.000625 2022/09/08 17:46:58 - mmengine - INFO - Epoch(train) [115][250/293] lr: 5.000000e-04 eta: 3:20:04 time: 0.500603 data_time: 0.076195 memory: 9871 loss_kpt: 0.000628 acc_pose: 0.840051 loss: 0.000628 2022/09/08 17:47:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 17:47:19 - mmengine - INFO - Saving checkpoint at 115 epochs 2022/09/08 17:47:49 - mmengine - INFO - Epoch(train) [116][50/293] lr: 5.000000e-04 eta: 3:19:12 time: 0.506321 data_time: 0.081413 memory: 9871 loss_kpt: 0.000628 acc_pose: 0.868064 loss: 0.000628 2022/09/08 17:48:14 - mmengine - INFO - Epoch(train) [116][100/293] lr: 5.000000e-04 eta: 3:18:54 time: 0.502256 data_time: 0.079306 memory: 9871 loss_kpt: 0.000624 acc_pose: 0.832844 loss: 0.000624 2022/09/08 17:48:40 - mmengine - INFO - Epoch(train) [116][150/293] lr: 5.000000e-04 eta: 3:18:35 time: 0.507368 data_time: 0.077154 memory: 9871 loss_kpt: 0.000622 acc_pose: 0.813979 loss: 0.000622 2022/09/08 17:49:04 - mmengine - INFO - Epoch(train) [116][200/293] lr: 5.000000e-04 eta: 3:18:16 time: 0.487795 data_time: 0.076217 memory: 9871 loss_kpt: 0.000630 acc_pose: 0.857612 loss: 0.000630 2022/09/08 17:49:28 - mmengine - INFO - Epoch(train) [116][250/293] lr: 5.000000e-04 eta: 3:17:57 time: 0.488189 data_time: 0.071029 memory: 9871 loss_kpt: 0.000624 acc_pose: 0.858435 loss: 0.000624 2022/09/08 17:49:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 17:49:50 - mmengine - INFO - Saving checkpoint at 116 epochs 2022/09/08 17:50:01 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 17:50:19 - mmengine - INFO - Epoch(train) [117][50/293] lr: 5.000000e-04 eta: 3:17:05 time: 0.503988 data_time: 0.085275 memory: 9871 loss_kpt: 0.000612 acc_pose: 0.830690 loss: 0.000612 2022/09/08 17:50:45 - mmengine - INFO - Epoch(train) [117][100/293] lr: 5.000000e-04 eta: 3:16:46 time: 0.507742 data_time: 0.074165 memory: 9871 loss_kpt: 0.000612 acc_pose: 0.854754 loss: 0.000612 2022/09/08 17:51:10 - mmengine - INFO - Epoch(train) [117][150/293] lr: 5.000000e-04 eta: 3:16:28 time: 0.495874 data_time: 0.074691 memory: 9871 loss_kpt: 0.000637 acc_pose: 0.770329 loss: 0.000637 2022/09/08 17:51:35 - mmengine - INFO - Epoch(train) [117][200/293] lr: 5.000000e-04 eta: 3:16:09 time: 0.496988 data_time: 0.074442 memory: 9871 loss_kpt: 0.000615 acc_pose: 0.844666 loss: 0.000615 2022/09/08 17:51:59 - mmengine - INFO - Epoch(train) [117][250/293] lr: 5.000000e-04 eta: 3:15:50 time: 0.491113 data_time: 0.079543 memory: 9871 loss_kpt: 0.000624 acc_pose: 0.865674 loss: 0.000624 2022/09/08 17:52:21 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 17:52:21 - mmengine - INFO - Saving checkpoint at 117 epochs 2022/09/08 17:52:51 - mmengine - INFO - Epoch(train) [118][50/293] lr: 5.000000e-04 eta: 3:14:58 time: 0.513012 data_time: 0.082185 memory: 9871 loss_kpt: 0.000622 acc_pose: 0.823109 loss: 0.000622 2022/09/08 17:53:15 - mmengine - INFO - Epoch(train) [118][100/293] lr: 5.000000e-04 eta: 3:14:39 time: 0.490995 data_time: 0.078254 memory: 9871 loss_kpt: 0.000611 acc_pose: 0.819186 loss: 0.000611 2022/09/08 17:53:40 - mmengine - INFO - Epoch(train) [118][150/293] lr: 5.000000e-04 eta: 3:14:20 time: 0.500440 data_time: 0.074101 memory: 9871 loss_kpt: 0.000614 acc_pose: 0.871204 loss: 0.000614 2022/09/08 17:54:05 - mmengine - INFO - Epoch(train) [118][200/293] lr: 5.000000e-04 eta: 3:14:01 time: 0.496792 data_time: 0.070028 memory: 9871 loss_kpt: 0.000631 acc_pose: 0.855153 loss: 0.000631 2022/09/08 17:54:30 - mmengine - INFO - Epoch(train) [118][250/293] lr: 5.000000e-04 eta: 3:13:42 time: 0.487897 data_time: 0.073899 memory: 9871 loss_kpt: 0.000613 acc_pose: 0.842096 loss: 0.000613 2022/09/08 17:54:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 17:54:51 - mmengine - INFO - Saving checkpoint at 118 epochs 2022/09/08 17:55:21 - mmengine - INFO - Epoch(train) [119][50/293] lr: 5.000000e-04 eta: 3:12:51 time: 0.512385 data_time: 0.081432 memory: 9871 loss_kpt: 0.000620 acc_pose: 0.836147 loss: 0.000620 2022/09/08 17:55:47 - mmengine - INFO - Epoch(train) [119][100/293] lr: 5.000000e-04 eta: 3:12:32 time: 0.504967 data_time: 0.079555 memory: 9871 loss_kpt: 0.000625 acc_pose: 0.819516 loss: 0.000625 2022/09/08 17:56:12 - mmengine - INFO - Epoch(train) [119][150/293] lr: 5.000000e-04 eta: 3:12:14 time: 0.503394 data_time: 0.076668 memory: 9871 loss_kpt: 0.000616 acc_pose: 0.843504 loss: 0.000616 2022/09/08 17:56:37 - mmengine - INFO - Epoch(train) [119][200/293] lr: 5.000000e-04 eta: 3:11:55 time: 0.498538 data_time: 0.075735 memory: 9871 loss_kpt: 0.000627 acc_pose: 0.829614 loss: 0.000627 2022/09/08 17:57:01 - mmengine - INFO - Epoch(train) [119][250/293] lr: 5.000000e-04 eta: 3:11:36 time: 0.489227 data_time: 0.071214 memory: 9871 loss_kpt: 0.000625 acc_pose: 0.793773 loss: 0.000625 2022/09/08 17:57:22 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 17:57:22 - mmengine - INFO - Saving checkpoint at 119 epochs 2022/09/08 17:57:52 - mmengine - INFO - Epoch(train) [120][50/293] lr: 5.000000e-04 eta: 3:10:44 time: 0.507751 data_time: 0.091611 memory: 9871 loss_kpt: 0.000619 acc_pose: 0.814008 loss: 0.000619 2022/09/08 17:58:18 - mmengine - INFO - Epoch(train) [120][100/293] lr: 5.000000e-04 eta: 3:10:26 time: 0.509149 data_time: 0.078184 memory: 9871 loss_kpt: 0.000618 acc_pose: 0.802276 loss: 0.000618 2022/09/08 17:58:34 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 17:58:42 - mmengine - INFO - Epoch(train) [120][150/293] lr: 5.000000e-04 eta: 3:10:07 time: 0.489871 data_time: 0.079106 memory: 9871 loss_kpt: 0.000628 acc_pose: 0.777528 loss: 0.000628 2022/09/08 17:59:07 - mmengine - INFO - Epoch(train) [120][200/293] lr: 5.000000e-04 eta: 3:09:47 time: 0.494392 data_time: 0.075923 memory: 9871 loss_kpt: 0.000618 acc_pose: 0.848780 loss: 0.000618 2022/09/08 17:59:33 - mmengine - INFO - Epoch(train) [120][250/293] lr: 5.000000e-04 eta: 3:09:29 time: 0.515203 data_time: 0.079746 memory: 9871 loss_kpt: 0.000633 acc_pose: 0.835296 loss: 0.000633 2022/09/08 17:59:54 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 17:59:54 - mmengine - INFO - Saving checkpoint at 120 epochs 2022/09/08 18:00:06 - mmengine - INFO - Epoch(val) [120][50/407] eta: 0:00:56 time: 0.158328 data_time: 0.014387 memory: 9871 2022/09/08 18:00:13 - mmengine - INFO - Epoch(val) [120][100/407] eta: 0:00:37 time: 0.123242 data_time: 0.010270 memory: 920 2022/09/08 18:00:19 - mmengine - INFO - Epoch(val) [120][150/407] eta: 0:00:31 time: 0.122519 data_time: 0.009621 memory: 920 2022/09/08 18:00:25 - mmengine - INFO - Epoch(val) [120][200/407] eta: 0:00:24 time: 0.118152 data_time: 0.009327 memory: 920 2022/09/08 18:00:31 - mmengine - INFO - Epoch(val) [120][250/407] eta: 0:00:20 time: 0.127579 data_time: 0.019234 memory: 920 2022/09/08 18:00:37 - mmengine - INFO - Epoch(val) [120][300/407] eta: 0:00:12 time: 0.118295 data_time: 0.009999 memory: 920 2022/09/08 18:00:43 - mmengine - INFO - Epoch(val) [120][350/407] eta: 0:00:07 time: 0.122879 data_time: 0.013237 memory: 920 2022/09/08 18:00:49 - mmengine - INFO - Epoch(val) [120][400/407] eta: 0:00:00 time: 0.113548 data_time: 0.010133 memory: 920 2022/09/08 18:01:24 - mmengine - INFO - Evaluating CocoMetric... 2022/09/08 18:01:37 - mmengine - INFO - Epoch(val) [120][407/407] coco/AP: 0.730545 coco/AP .5: 0.896979 coco/AP .75: 0.805682 coco/AP (M): 0.693870 coco/AP (L): 0.799723 coco/AR: 0.786949 coco/AR .5: 0.938602 coco/AR .75: 0.852645 coco/AR (M): 0.743813 coco/AR (L): 0.848792 2022/09/08 18:01:37 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220908/hrnet_w32_256/best_coco/AP_epoch_110.pth is removed 2022/09/08 18:01:40 - mmengine - INFO - The best checkpoint with 0.7305 coco/AP at 120 epoch is saved to best_coco/AP_epoch_120.pth. 2022/09/08 18:02:06 - mmengine - INFO - Epoch(train) [121][50/293] lr: 5.000000e-04 eta: 3:08:38 time: 0.508533 data_time: 0.081659 memory: 9871 loss_kpt: 0.000605 acc_pose: 0.859931 loss: 0.000605 2022/09/08 18:02:31 - mmengine - INFO - Epoch(train) [121][100/293] lr: 5.000000e-04 eta: 3:08:19 time: 0.501433 data_time: 0.077163 memory: 9871 loss_kpt: 0.000613 acc_pose: 0.781080 loss: 0.000613 2022/09/08 18:02:56 - mmengine - INFO - Epoch(train) [121][150/293] lr: 5.000000e-04 eta: 3:08:01 time: 0.508872 data_time: 0.080870 memory: 9871 loss_kpt: 0.000620 acc_pose: 0.807658 loss: 0.000620 2022/09/08 18:03:22 - mmengine - INFO - Epoch(train) [121][200/293] lr: 5.000000e-04 eta: 3:07:42 time: 0.517062 data_time: 0.076029 memory: 9871 loss_kpt: 0.000613 acc_pose: 0.823221 loss: 0.000613 2022/09/08 18:03:47 - mmengine - INFO - Epoch(train) [121][250/293] lr: 5.000000e-04 eta: 3:07:23 time: 0.496589 data_time: 0.075464 memory: 9871 loss_kpt: 0.000621 acc_pose: 0.815518 loss: 0.000621 2022/09/08 18:04:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 18:04:08 - mmengine - INFO - Saving checkpoint at 121 epochs 2022/09/08 18:04:38 - mmengine - INFO - Epoch(train) [122][50/293] lr: 5.000000e-04 eta: 3:06:32 time: 0.495967 data_time: 0.082629 memory: 9871 loss_kpt: 0.000619 acc_pose: 0.805684 loss: 0.000619 2022/09/08 18:05:04 - mmengine - INFO - Epoch(train) [122][100/293] lr: 5.000000e-04 eta: 3:06:14 time: 0.514089 data_time: 0.084226 memory: 9871 loss_kpt: 0.000612 acc_pose: 0.837505 loss: 0.000612 2022/09/08 18:05:29 - mmengine - INFO - Epoch(train) [122][150/293] lr: 5.000000e-04 eta: 3:05:55 time: 0.507410 data_time: 0.086341 memory: 9871 loss_kpt: 0.000611 acc_pose: 0.811004 loss: 0.000611 2022/09/08 18:05:54 - mmengine - INFO - Epoch(train) [122][200/293] lr: 5.000000e-04 eta: 3:05:36 time: 0.491564 data_time: 0.078295 memory: 9871 loss_kpt: 0.000612 acc_pose: 0.770878 loss: 0.000612 2022/09/08 18:06:18 - mmengine - INFO - Epoch(train) [122][250/293] lr: 5.000000e-04 eta: 3:05:17 time: 0.493497 data_time: 0.073380 memory: 9871 loss_kpt: 0.000615 acc_pose: 0.795860 loss: 0.000615 2022/09/08 18:06:40 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 18:06:40 - mmengine - INFO - Saving checkpoint at 122 epochs 2022/09/08 18:07:10 - mmengine - INFO - Epoch(train) [123][50/293] lr: 5.000000e-04 eta: 3:04:26 time: 0.503689 data_time: 0.079684 memory: 9871 loss_kpt: 0.000620 acc_pose: 0.814223 loss: 0.000620 2022/09/08 18:07:34 - mmengine - INFO - Epoch(train) [123][100/293] lr: 5.000000e-04 eta: 3:04:07 time: 0.493123 data_time: 0.080832 memory: 9871 loss_kpt: 0.000622 acc_pose: 0.807845 loss: 0.000622 2022/09/08 18:08:00 - mmengine - INFO - Epoch(train) [123][150/293] lr: 5.000000e-04 eta: 3:03:48 time: 0.507347 data_time: 0.085343 memory: 9871 loss_kpt: 0.000631 acc_pose: 0.853008 loss: 0.000631 2022/09/08 18:08:25 - mmengine - INFO - Epoch(train) [123][200/293] lr: 5.000000e-04 eta: 3:03:29 time: 0.497862 data_time: 0.073151 memory: 9871 loss_kpt: 0.000601 acc_pose: 0.851561 loss: 0.000601 2022/09/08 18:08:49 - mmengine - INFO - Epoch(train) [123][250/293] lr: 5.000000e-04 eta: 3:03:09 time: 0.494182 data_time: 0.073936 memory: 9871 loss_kpt: 0.000622 acc_pose: 0.832956 loss: 0.000622 2022/09/08 18:08:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 18:09:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 18:09:11 - mmengine - INFO - Saving checkpoint at 123 epochs 2022/09/08 18:09:41 - mmengine - INFO - Epoch(train) [124][50/293] lr: 5.000000e-04 eta: 3:02:20 time: 0.522460 data_time: 0.086955 memory: 9871 loss_kpt: 0.000618 acc_pose: 0.798777 loss: 0.000618 2022/09/08 18:10:06 - mmengine - INFO - Epoch(train) [124][100/293] lr: 5.000000e-04 eta: 3:02:01 time: 0.500096 data_time: 0.072670 memory: 9871 loss_kpt: 0.000624 acc_pose: 0.829551 loss: 0.000624 2022/09/08 18:10:31 - mmengine - INFO - Epoch(train) [124][150/293] lr: 5.000000e-04 eta: 3:01:41 time: 0.494502 data_time: 0.074717 memory: 9871 loss_kpt: 0.000627 acc_pose: 0.820573 loss: 0.000627 2022/09/08 18:10:56 - mmengine - INFO - Epoch(train) [124][200/293] lr: 5.000000e-04 eta: 3:01:22 time: 0.491976 data_time: 0.075798 memory: 9871 loss_kpt: 0.000626 acc_pose: 0.801670 loss: 0.000626 2022/09/08 18:11:22 - mmengine - INFO - Epoch(train) [124][250/293] lr: 5.000000e-04 eta: 3:01:04 time: 0.517781 data_time: 0.074605 memory: 9871 loss_kpt: 0.000621 acc_pose: 0.854142 loss: 0.000621 2022/09/08 18:11:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 18:11:43 - mmengine - INFO - Saving checkpoint at 124 epochs 2022/09/08 18:12:14 - mmengine - INFO - Epoch(train) [125][50/293] lr: 5.000000e-04 eta: 3:00:14 time: 0.516337 data_time: 0.087537 memory: 9871 loss_kpt: 0.000618 acc_pose: 0.785975 loss: 0.000618 2022/09/08 18:12:38 - mmengine - INFO - Epoch(train) [125][100/293] lr: 5.000000e-04 eta: 2:59:54 time: 0.490707 data_time: 0.072463 memory: 9871 loss_kpt: 0.000614 acc_pose: 0.819687 loss: 0.000614 2022/09/08 18:13:04 - mmengine - INFO - Epoch(train) [125][150/293] lr: 5.000000e-04 eta: 2:59:35 time: 0.505158 data_time: 0.075203 memory: 9871 loss_kpt: 0.000609 acc_pose: 0.818872 loss: 0.000609 2022/09/08 18:13:28 - mmengine - INFO - Epoch(train) [125][200/293] lr: 5.000000e-04 eta: 2:59:16 time: 0.492080 data_time: 0.079923 memory: 9871 loss_kpt: 0.000626 acc_pose: 0.814031 loss: 0.000626 2022/09/08 18:13:54 - mmengine - INFO - Epoch(train) [125][250/293] lr: 5.000000e-04 eta: 2:58:57 time: 0.509382 data_time: 0.075728 memory: 9871 loss_kpt: 0.000629 acc_pose: 0.819799 loss: 0.000629 2022/09/08 18:14:15 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 18:14:15 - mmengine - INFO - Saving checkpoint at 125 epochs 2022/09/08 18:14:45 - mmengine - INFO - Epoch(train) [126][50/293] lr: 5.000000e-04 eta: 2:58:07 time: 0.506430 data_time: 0.079978 memory: 9871 loss_kpt: 0.000617 acc_pose: 0.832582 loss: 0.000617 2022/09/08 18:15:10 - mmengine - INFO - Epoch(train) [126][100/293] lr: 5.000000e-04 eta: 2:57:48 time: 0.498341 data_time: 0.072338 memory: 9871 loss_kpt: 0.000609 acc_pose: 0.804171 loss: 0.000609 2022/09/08 18:15:34 - mmengine - INFO - Epoch(train) [126][150/293] lr: 5.000000e-04 eta: 2:57:28 time: 0.489820 data_time: 0.076731 memory: 9871 loss_kpt: 0.000614 acc_pose: 0.840750 loss: 0.000614 2022/09/08 18:15:59 - mmengine - INFO - Epoch(train) [126][200/293] lr: 5.000000e-04 eta: 2:57:09 time: 0.497648 data_time: 0.071689 memory: 9871 loss_kpt: 0.000621 acc_pose: 0.860203 loss: 0.000621 2022/09/08 18:16:24 - mmengine - INFO - Epoch(train) [126][250/293] lr: 5.000000e-04 eta: 2:56:50 time: 0.502003 data_time: 0.077090 memory: 9871 loss_kpt: 0.000611 acc_pose: 0.872677 loss: 0.000611 2022/09/08 18:16:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 18:16:46 - mmengine - INFO - Saving checkpoint at 126 epochs 2022/09/08 18:17:16 - mmengine - INFO - Epoch(train) [127][50/293] lr: 5.000000e-04 eta: 2:56:00 time: 0.502823 data_time: 0.082008 memory: 9871 loss_kpt: 0.000610 acc_pose: 0.865750 loss: 0.000610 2022/09/08 18:17:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 18:17:41 - mmengine - INFO - Epoch(train) [127][100/293] lr: 5.000000e-04 eta: 2:55:42 time: 0.515862 data_time: 0.078195 memory: 9871 loss_kpt: 0.000623 acc_pose: 0.826108 loss: 0.000623 2022/09/08 18:18:06 - mmengine - INFO - Epoch(train) [127][150/293] lr: 5.000000e-04 eta: 2:55:22 time: 0.496700 data_time: 0.077013 memory: 9871 loss_kpt: 0.000614 acc_pose: 0.848962 loss: 0.000614 2022/09/08 18:18:31 - mmengine - INFO - Epoch(train) [127][200/293] lr: 5.000000e-04 eta: 2:55:03 time: 0.503428 data_time: 0.075373 memory: 9871 loss_kpt: 0.000625 acc_pose: 0.829717 loss: 0.000625 2022/09/08 18:18:57 - mmengine - INFO - Epoch(train) [127][250/293] lr: 5.000000e-04 eta: 2:54:44 time: 0.507378 data_time: 0.071841 memory: 9871 loss_kpt: 0.000620 acc_pose: 0.799769 loss: 0.000620 2022/09/08 18:19:18 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 18:19:18 - mmengine - INFO - Saving checkpoint at 127 epochs 2022/09/08 18:19:48 - mmengine - INFO - Epoch(train) [128][50/293] lr: 5.000000e-04 eta: 2:53:54 time: 0.499272 data_time: 0.083787 memory: 9871 loss_kpt: 0.000620 acc_pose: 0.849504 loss: 0.000620 2022/09/08 18:20:14 - mmengine - INFO - Epoch(train) [128][100/293] lr: 5.000000e-04 eta: 2:53:35 time: 0.509866 data_time: 0.079776 memory: 9871 loss_kpt: 0.000612 acc_pose: 0.828393 loss: 0.000612 2022/09/08 18:20:38 - mmengine - INFO - Epoch(train) [128][150/293] lr: 5.000000e-04 eta: 2:53:16 time: 0.495287 data_time: 0.075624 memory: 9871 loss_kpt: 0.000610 acc_pose: 0.848896 loss: 0.000610 2022/09/08 18:21:04 - mmengine - INFO - Epoch(train) [128][200/293] lr: 5.000000e-04 eta: 2:52:57 time: 0.507750 data_time: 0.071199 memory: 9871 loss_kpt: 0.000622 acc_pose: 0.847882 loss: 0.000622 2022/09/08 18:21:29 - mmengine - INFO - Epoch(train) [128][250/293] lr: 5.000000e-04 eta: 2:52:38 time: 0.497264 data_time: 0.080161 memory: 9871 loss_kpt: 0.000623 acc_pose: 0.841213 loss: 0.000623 2022/09/08 18:21:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 18:21:50 - mmengine - INFO - Saving checkpoint at 128 epochs 2022/09/08 18:22:20 - mmengine - INFO - Epoch(train) [129][50/293] lr: 5.000000e-04 eta: 2:51:48 time: 0.511047 data_time: 0.083588 memory: 9871 loss_kpt: 0.000621 acc_pose: 0.846306 loss: 0.000621 2022/09/08 18:22:44 - mmengine - INFO - Epoch(train) [129][100/293] lr: 5.000000e-04 eta: 2:51:29 time: 0.491056 data_time: 0.071439 memory: 9871 loss_kpt: 0.000611 acc_pose: 0.840423 loss: 0.000611 2022/09/08 18:23:09 - mmengine - INFO - Epoch(train) [129][150/293] lr: 5.000000e-04 eta: 2:51:09 time: 0.493158 data_time: 0.079588 memory: 9871 loss_kpt: 0.000620 acc_pose: 0.833576 loss: 0.000620 2022/09/08 18:23:34 - mmengine - INFO - Epoch(train) [129][200/293] lr: 5.000000e-04 eta: 2:50:50 time: 0.503983 data_time: 0.071580 memory: 9871 loss_kpt: 0.000627 acc_pose: 0.823932 loss: 0.000627 2022/09/08 18:23:59 - mmengine - INFO - Epoch(train) [129][250/293] lr: 5.000000e-04 eta: 2:50:31 time: 0.502168 data_time: 0.075321 memory: 9871 loss_kpt: 0.000615 acc_pose: 0.793645 loss: 0.000615 2022/09/08 18:24:21 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 18:24:21 - mmengine - INFO - Saving checkpoint at 129 epochs 2022/09/08 18:24:51 - mmengine - INFO - Epoch(train) [130][50/293] lr: 5.000000e-04 eta: 2:49:42 time: 0.509471 data_time: 0.082585 memory: 9871 loss_kpt: 0.000603 acc_pose: 0.834389 loss: 0.000603 2022/09/08 18:25:16 - mmengine - INFO - Epoch(train) [130][100/293] lr: 5.000000e-04 eta: 2:49:22 time: 0.498920 data_time: 0.074433 memory: 9871 loss_kpt: 0.000607 acc_pose: 0.842182 loss: 0.000607 2022/09/08 18:25:41 - mmengine - INFO - Epoch(train) [130][150/293] lr: 5.000000e-04 eta: 2:49:03 time: 0.500669 data_time: 0.075664 memory: 9871 loss_kpt: 0.000615 acc_pose: 0.807464 loss: 0.000615 2022/09/08 18:26:06 - mmengine - INFO - Epoch(train) [130][200/293] lr: 5.000000e-04 eta: 2:48:44 time: 0.500385 data_time: 0.082128 memory: 9871 loss_kpt: 0.000612 acc_pose: 0.837348 loss: 0.000612 2022/09/08 18:26:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 18:26:30 - mmengine - INFO - Epoch(train) [130][250/293] lr: 5.000000e-04 eta: 2:48:24 time: 0.488232 data_time: 0.072483 memory: 9871 loss_kpt: 0.000608 acc_pose: 0.844399 loss: 0.000608 2022/09/08 18:26:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 18:26:51 - mmengine - INFO - Saving checkpoint at 130 epochs 2022/09/08 18:27:03 - mmengine - INFO - Epoch(val) [130][50/407] eta: 0:00:47 time: 0.131726 data_time: 0.022536 memory: 9871 2022/09/08 18:27:09 - mmengine - INFO - Epoch(val) [130][100/407] eta: 0:00:37 time: 0.121631 data_time: 0.011798 memory: 920 2022/09/08 18:27:15 - mmengine - INFO - Epoch(val) [130][150/407] eta: 0:00:30 time: 0.118811 data_time: 0.010337 memory: 920 2022/09/08 18:27:22 - mmengine - INFO - Epoch(val) [130][200/407] eta: 0:00:26 time: 0.126051 data_time: 0.015631 memory: 920 2022/09/08 18:27:28 - mmengine - INFO - Epoch(val) [130][250/407] eta: 0:00:19 time: 0.127242 data_time: 0.020068 memory: 920 2022/09/08 18:27:34 - mmengine - INFO - Epoch(val) [130][300/407] eta: 0:00:13 time: 0.126419 data_time: 0.018846 memory: 920 2022/09/08 18:27:40 - mmengine - INFO - Epoch(val) [130][350/407] eta: 0:00:06 time: 0.119147 data_time: 0.009434 memory: 920 2022/09/08 18:27:46 - mmengine - INFO - Epoch(val) [130][400/407] eta: 0:00:00 time: 0.113873 data_time: 0.013187 memory: 920 2022/09/08 18:28:21 - mmengine - INFO - Evaluating CocoMetric... 2022/09/08 18:28:35 - mmengine - INFO - Epoch(val) [130][407/407] coco/AP: 0.734245 coco/AP .5: 0.899049 coco/AP .75: 0.809021 coco/AP (M): 0.696510 coco/AP (L): 0.801515 coco/AR: 0.787374 coco/AR .5: 0.937028 coco/AR .75: 0.853275 coco/AR (M): 0.745343 coco/AR (L): 0.848161 2022/09/08 18:28:35 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220908/hrnet_w32_256/best_coco/AP_epoch_120.pth is removed 2022/09/08 18:28:38 - mmengine - INFO - The best checkpoint with 0.7342 coco/AP at 130 epoch is saved to best_coco/AP_epoch_130.pth. 2022/09/08 18:29:02 - mmengine - INFO - Epoch(train) [131][50/293] lr: 5.000000e-04 eta: 2:47:35 time: 0.492696 data_time: 0.080218 memory: 9871 loss_kpt: 0.000621 acc_pose: 0.830383 loss: 0.000621 2022/09/08 18:29:27 - mmengine - INFO - Epoch(train) [131][100/293] lr: 5.000000e-04 eta: 2:47:15 time: 0.499216 data_time: 0.078456 memory: 9871 loss_kpt: 0.000617 acc_pose: 0.799350 loss: 0.000617 2022/09/08 18:29:53 - mmengine - INFO - Epoch(train) [131][150/293] lr: 5.000000e-04 eta: 2:46:56 time: 0.510669 data_time: 0.072566 memory: 9871 loss_kpt: 0.000611 acc_pose: 0.789805 loss: 0.000611 2022/09/08 18:30:18 - mmengine - INFO - Epoch(train) [131][200/293] lr: 5.000000e-04 eta: 2:46:37 time: 0.494618 data_time: 0.076333 memory: 9871 loss_kpt: 0.000612 acc_pose: 0.829601 loss: 0.000612 2022/09/08 18:30:42 - mmengine - INFO - Epoch(train) [131][250/293] lr: 5.000000e-04 eta: 2:46:17 time: 0.486570 data_time: 0.070558 memory: 9871 loss_kpt: 0.000618 acc_pose: 0.854510 loss: 0.000618 2022/09/08 18:31:03 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 18:31:03 - mmengine - INFO - Saving checkpoint at 131 epochs 2022/09/08 18:31:34 - mmengine - INFO - Epoch(train) [132][50/293] lr: 5.000000e-04 eta: 2:45:29 time: 0.524333 data_time: 0.084764 memory: 9871 loss_kpt: 0.000616 acc_pose: 0.857769 loss: 0.000616 2022/09/08 18:31:59 - mmengine - INFO - Epoch(train) [132][100/293] lr: 5.000000e-04 eta: 2:45:09 time: 0.496144 data_time: 0.077684 memory: 9871 loss_kpt: 0.000604 acc_pose: 0.857658 loss: 0.000604 2022/09/08 18:32:23 - mmengine - INFO - Epoch(train) [132][150/293] lr: 5.000000e-04 eta: 2:44:49 time: 0.486918 data_time: 0.071747 memory: 9871 loss_kpt: 0.000620 acc_pose: 0.820465 loss: 0.000620 2022/09/08 18:32:48 - mmengine - INFO - Epoch(train) [132][200/293] lr: 5.000000e-04 eta: 2:44:30 time: 0.488927 data_time: 0.075652 memory: 9871 loss_kpt: 0.000609 acc_pose: 0.834171 loss: 0.000609 2022/09/08 18:33:13 - mmengine - INFO - Epoch(train) [132][250/293] lr: 5.000000e-04 eta: 2:44:10 time: 0.505349 data_time: 0.078665 memory: 9871 loss_kpt: 0.000617 acc_pose: 0.838936 loss: 0.000617 2022/09/08 18:33:34 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 18:33:34 - mmengine - INFO - Saving checkpoint at 132 epochs 2022/09/08 18:34:04 - mmengine - INFO - Epoch(train) [133][50/293] lr: 5.000000e-04 eta: 2:43:22 time: 0.508022 data_time: 0.081690 memory: 9871 loss_kpt: 0.000608 acc_pose: 0.847324 loss: 0.000608 2022/09/08 18:34:29 - mmengine - INFO - Epoch(train) [133][100/293] lr: 5.000000e-04 eta: 2:43:02 time: 0.505441 data_time: 0.076027 memory: 9871 loss_kpt: 0.000622 acc_pose: 0.830557 loss: 0.000622 2022/09/08 18:34:55 - mmengine - INFO - Epoch(train) [133][150/293] lr: 5.000000e-04 eta: 2:42:43 time: 0.504512 data_time: 0.079536 memory: 9871 loss_kpt: 0.000607 acc_pose: 0.857054 loss: 0.000607 2022/09/08 18:35:19 - mmengine - INFO - Epoch(train) [133][200/293] lr: 5.000000e-04 eta: 2:42:23 time: 0.490943 data_time: 0.075307 memory: 9871 loss_kpt: 0.000622 acc_pose: 0.799396 loss: 0.000622 2022/09/08 18:35:45 - mmengine - INFO - Epoch(train) [133][250/293] lr: 5.000000e-04 eta: 2:42:04 time: 0.509107 data_time: 0.071312 memory: 9871 loss_kpt: 0.000620 acc_pose: 0.819160 loss: 0.000620 2022/09/08 18:36:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 18:36:06 - mmengine - INFO - Saving checkpoint at 133 epochs 2022/09/08 18:36:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 18:36:36 - mmengine - INFO - Epoch(train) [134][50/293] lr: 5.000000e-04 eta: 2:41:16 time: 0.507954 data_time: 0.077564 memory: 9871 loss_kpt: 0.000608 acc_pose: 0.856903 loss: 0.000608 2022/09/08 18:37:01 - mmengine - INFO - Epoch(train) [134][100/293] lr: 5.000000e-04 eta: 2:40:56 time: 0.497302 data_time: 0.072718 memory: 9871 loss_kpt: 0.000617 acc_pose: 0.883593 loss: 0.000617 2022/09/08 18:37:27 - mmengine - INFO - Epoch(train) [134][150/293] lr: 5.000000e-04 eta: 2:40:37 time: 0.514569 data_time: 0.077001 memory: 9871 loss_kpt: 0.000606 acc_pose: 0.778287 loss: 0.000606 2022/09/08 18:37:52 - mmengine - INFO - Epoch(train) [134][200/293] lr: 5.000000e-04 eta: 2:40:18 time: 0.500502 data_time: 0.074476 memory: 9871 loss_kpt: 0.000615 acc_pose: 0.818266 loss: 0.000615 2022/09/08 18:38:17 - mmengine - INFO - Epoch(train) [134][250/293] lr: 5.000000e-04 eta: 2:39:58 time: 0.496598 data_time: 0.071821 memory: 9871 loss_kpt: 0.000615 acc_pose: 0.813727 loss: 0.000615 2022/09/08 18:38:38 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 18:38:38 - mmengine - INFO - Saving checkpoint at 134 epochs 2022/09/08 18:39:08 - mmengine - INFO - Epoch(train) [135][50/293] lr: 5.000000e-04 eta: 2:39:10 time: 0.512095 data_time: 0.079565 memory: 9871 loss_kpt: 0.000620 acc_pose: 0.840833 loss: 0.000620 2022/09/08 18:39:33 - mmengine - INFO - Epoch(train) [135][100/293] lr: 5.000000e-04 eta: 2:38:50 time: 0.501451 data_time: 0.076113 memory: 9871 loss_kpt: 0.000600 acc_pose: 0.828710 loss: 0.000600 2022/09/08 18:39:58 - mmengine - INFO - Epoch(train) [135][150/293] lr: 5.000000e-04 eta: 2:38:31 time: 0.498899 data_time: 0.074438 memory: 9871 loss_kpt: 0.000610 acc_pose: 0.852318 loss: 0.000610 2022/09/08 18:40:23 - mmengine - INFO - Epoch(train) [135][200/293] lr: 5.000000e-04 eta: 2:38:11 time: 0.497397 data_time: 0.078648 memory: 9871 loss_kpt: 0.000617 acc_pose: 0.834091 loss: 0.000617 2022/09/08 18:40:48 - mmengine - INFO - Epoch(train) [135][250/293] lr: 5.000000e-04 eta: 2:37:51 time: 0.494688 data_time: 0.069846 memory: 9871 loss_kpt: 0.000612 acc_pose: 0.843071 loss: 0.000612 2022/09/08 18:41:09 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 18:41:09 - mmengine - INFO - Saving checkpoint at 135 epochs 2022/09/08 18:41:39 - mmengine - INFO - Epoch(train) [136][50/293] lr: 5.000000e-04 eta: 2:37:03 time: 0.504541 data_time: 0.088777 memory: 9871 loss_kpt: 0.000624 acc_pose: 0.817158 loss: 0.000624 2022/09/08 18:42:04 - mmengine - INFO - Epoch(train) [136][100/293] lr: 5.000000e-04 eta: 2:36:44 time: 0.501517 data_time: 0.077411 memory: 9871 loss_kpt: 0.000610 acc_pose: 0.836647 loss: 0.000610 2022/09/08 18:42:29 - mmengine - INFO - Epoch(train) [136][150/293] lr: 5.000000e-04 eta: 2:36:24 time: 0.500786 data_time: 0.072037 memory: 9871 loss_kpt: 0.000601 acc_pose: 0.851202 loss: 0.000601 2022/09/08 18:42:54 - mmengine - INFO - Epoch(train) [136][200/293] lr: 5.000000e-04 eta: 2:36:04 time: 0.493627 data_time: 0.077810 memory: 9871 loss_kpt: 0.000614 acc_pose: 0.857065 loss: 0.000614 2022/09/08 18:43:18 - mmengine - INFO - Epoch(train) [136][250/293] lr: 5.000000e-04 eta: 2:35:45 time: 0.491805 data_time: 0.074805 memory: 9871 loss_kpt: 0.000603 acc_pose: 0.765977 loss: 0.000603 2022/09/08 18:43:39 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 18:43:39 - mmengine - INFO - Saving checkpoint at 136 epochs 2022/09/08 18:44:09 - mmengine - INFO - Epoch(train) [137][50/293] lr: 5.000000e-04 eta: 2:34:56 time: 0.501375 data_time: 0.083641 memory: 9871 loss_kpt: 0.000605 acc_pose: 0.826435 loss: 0.000605 2022/09/08 18:44:33 - mmengine - INFO - Epoch(train) [137][100/293] lr: 5.000000e-04 eta: 2:34:37 time: 0.487185 data_time: 0.070589 memory: 9871 loss_kpt: 0.000605 acc_pose: 0.852826 loss: 0.000605 2022/09/08 18:44:58 - mmengine - INFO - Epoch(train) [137][150/293] lr: 5.000000e-04 eta: 2:34:17 time: 0.498446 data_time: 0.070594 memory: 9871 loss_kpt: 0.000615 acc_pose: 0.747244 loss: 0.000615 2022/09/08 18:44:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 18:45:23 - mmengine - INFO - Epoch(train) [137][200/293] lr: 5.000000e-04 eta: 2:33:57 time: 0.501391 data_time: 0.082355 memory: 9871 loss_kpt: 0.000609 acc_pose: 0.866582 loss: 0.000609 2022/09/08 18:45:48 - mmengine - INFO - Epoch(train) [137][250/293] lr: 5.000000e-04 eta: 2:33:38 time: 0.493789 data_time: 0.071997 memory: 9871 loss_kpt: 0.000625 acc_pose: 0.844208 loss: 0.000625 2022/09/08 18:46:10 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 18:46:10 - mmengine - INFO - Saving checkpoint at 137 epochs 2022/09/08 18:46:40 - mmengine - INFO - Epoch(train) [138][50/293] lr: 5.000000e-04 eta: 2:32:50 time: 0.509189 data_time: 0.082822 memory: 9871 loss_kpt: 0.000600 acc_pose: 0.850877 loss: 0.000600 2022/09/08 18:47:04 - mmengine - INFO - Epoch(train) [138][100/293] lr: 5.000000e-04 eta: 2:32:30 time: 0.495858 data_time: 0.070223 memory: 9871 loss_kpt: 0.000619 acc_pose: 0.835874 loss: 0.000619 2022/09/08 18:47:29 - mmengine - INFO - Epoch(train) [138][150/293] lr: 5.000000e-04 eta: 2:32:10 time: 0.496748 data_time: 0.069523 memory: 9871 loss_kpt: 0.000602 acc_pose: 0.831344 loss: 0.000602 2022/09/08 18:47:55 - mmengine - INFO - Epoch(train) [138][200/293] lr: 5.000000e-04 eta: 2:31:51 time: 0.506826 data_time: 0.086106 memory: 9871 loss_kpt: 0.000605 acc_pose: 0.851421 loss: 0.000605 2022/09/08 18:48:19 - mmengine - INFO - Epoch(train) [138][250/293] lr: 5.000000e-04 eta: 2:31:31 time: 0.495150 data_time: 0.073569 memory: 9871 loss_kpt: 0.000598 acc_pose: 0.799358 loss: 0.000598 2022/09/08 18:48:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 18:48:41 - mmengine - INFO - Saving checkpoint at 138 epochs 2022/09/08 18:49:12 - mmengine - INFO - Epoch(train) [139][50/293] lr: 5.000000e-04 eta: 2:30:44 time: 0.510178 data_time: 0.077829 memory: 9871 loss_kpt: 0.000617 acc_pose: 0.850449 loss: 0.000617 2022/09/08 18:49:36 - mmengine - INFO - Epoch(train) [139][100/293] lr: 5.000000e-04 eta: 2:30:24 time: 0.498725 data_time: 0.080965 memory: 9871 loss_kpt: 0.000602 acc_pose: 0.815974 loss: 0.000602 2022/09/08 18:50:01 - mmengine - INFO - Epoch(train) [139][150/293] lr: 5.000000e-04 eta: 2:30:04 time: 0.493240 data_time: 0.073701 memory: 9871 loss_kpt: 0.000609 acc_pose: 0.846939 loss: 0.000609 2022/09/08 18:50:26 - mmengine - INFO - Epoch(train) [139][200/293] lr: 5.000000e-04 eta: 2:29:44 time: 0.495731 data_time: 0.071291 memory: 9871 loss_kpt: 0.000607 acc_pose: 0.870995 loss: 0.000607 2022/09/08 18:50:51 - mmengine - INFO - Epoch(train) [139][250/293] lr: 5.000000e-04 eta: 2:29:25 time: 0.501873 data_time: 0.071316 memory: 9871 loss_kpt: 0.000606 acc_pose: 0.822433 loss: 0.000606 2022/09/08 18:51:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 18:51:13 - mmengine - INFO - Saving checkpoint at 139 epochs 2022/09/08 18:51:43 - mmengine - INFO - Epoch(train) [140][50/293] lr: 5.000000e-04 eta: 2:28:37 time: 0.506936 data_time: 0.082644 memory: 9871 loss_kpt: 0.000606 acc_pose: 0.874393 loss: 0.000606 2022/09/08 18:52:07 - mmengine - INFO - Epoch(train) [140][100/293] lr: 5.000000e-04 eta: 2:28:17 time: 0.488667 data_time: 0.071384 memory: 9871 loss_kpt: 0.000619 acc_pose: 0.824833 loss: 0.000619 2022/09/08 18:52:32 - mmengine - INFO - Epoch(train) [140][150/293] lr: 5.000000e-04 eta: 2:27:57 time: 0.488473 data_time: 0.079073 memory: 9871 loss_kpt: 0.000612 acc_pose: 0.821176 loss: 0.000612 2022/09/08 18:52:56 - mmengine - INFO - Epoch(train) [140][200/293] lr: 5.000000e-04 eta: 2:27:37 time: 0.493850 data_time: 0.068992 memory: 9871 loss_kpt: 0.000609 acc_pose: 0.868607 loss: 0.000609 2022/09/08 18:53:21 - mmengine - INFO - Epoch(train) [140][250/293] lr: 5.000000e-04 eta: 2:27:17 time: 0.493736 data_time: 0.076023 memory: 9871 loss_kpt: 0.000611 acc_pose: 0.837568 loss: 0.000611 2022/09/08 18:53:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 18:53:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 18:53:41 - mmengine - INFO - Saving checkpoint at 140 epochs 2022/09/08 18:53:53 - mmengine - INFO - Epoch(val) [140][50/407] eta: 0:00:46 time: 0.131520 data_time: 0.018858 memory: 9871 2022/09/08 18:53:59 - mmengine - INFO - Epoch(val) [140][100/407] eta: 0:00:37 time: 0.121757 data_time: 0.013124 memory: 920 2022/09/08 18:54:05 - mmengine - INFO - Epoch(val) [140][150/407] eta: 0:00:31 time: 0.121406 data_time: 0.012684 memory: 920 2022/09/08 18:54:11 - mmengine - INFO - Epoch(val) [140][200/407] eta: 0:00:25 time: 0.121573 data_time: 0.011306 memory: 920 2022/09/08 18:54:17 - mmengine - INFO - Epoch(val) [140][250/407] eta: 0:00:19 time: 0.122058 data_time: 0.013858 memory: 920 2022/09/08 18:54:23 - mmengine - INFO - Epoch(val) [140][300/407] eta: 0:00:12 time: 0.119419 data_time: 0.010373 memory: 920 2022/09/08 18:54:29 - mmengine - INFO - Epoch(val) [140][350/407] eta: 0:00:06 time: 0.117405 data_time: 0.011044 memory: 920 2022/09/08 18:54:35 - mmengine - INFO - Epoch(val) [140][400/407] eta: 0:00:00 time: 0.118788 data_time: 0.014630 memory: 920 2022/09/08 18:55:09 - mmengine - INFO - Evaluating CocoMetric... 2022/09/08 18:55:23 - mmengine - INFO - Epoch(val) [140][407/407] coco/AP: 0.735484 coco/AP .5: 0.899577 coco/AP .75: 0.809194 coco/AP (M): 0.700446 coco/AP (L): 0.802426 coco/AR: 0.790365 coco/AR .5: 0.939232 coco/AR .75: 0.856423 coco/AR (M): 0.748484 coco/AR (L): 0.850873 2022/09/08 18:55:23 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220908/hrnet_w32_256/best_coco/AP_epoch_130.pth is removed 2022/09/08 18:55:26 - mmengine - INFO - The best checkpoint with 0.7355 coco/AP at 140 epoch is saved to best_coco/AP_epoch_140.pth. 2022/09/08 18:55:51 - mmengine - INFO - Epoch(train) [141][50/293] lr: 5.000000e-04 eta: 2:26:30 time: 0.501600 data_time: 0.087109 memory: 9871 loss_kpt: 0.000615 acc_pose: 0.850906 loss: 0.000615 2022/09/08 18:56:15 - mmengine - INFO - Epoch(train) [141][100/293] lr: 5.000000e-04 eta: 2:26:10 time: 0.487591 data_time: 0.074899 memory: 9871 loss_kpt: 0.000612 acc_pose: 0.882032 loss: 0.000612 2022/09/08 18:56:40 - mmengine - INFO - Epoch(train) [141][150/293] lr: 5.000000e-04 eta: 2:25:50 time: 0.499930 data_time: 0.074165 memory: 9871 loss_kpt: 0.000601 acc_pose: 0.831259 loss: 0.000601 2022/09/08 18:57:06 - mmengine - INFO - Epoch(train) [141][200/293] lr: 5.000000e-04 eta: 2:25:30 time: 0.505267 data_time: 0.069198 memory: 9871 loss_kpt: 0.000607 acc_pose: 0.821880 loss: 0.000607 2022/09/08 18:57:30 - mmengine - INFO - Epoch(train) [141][250/293] lr: 5.000000e-04 eta: 2:25:10 time: 0.491513 data_time: 0.072868 memory: 9871 loss_kpt: 0.000609 acc_pose: 0.859596 loss: 0.000609 2022/09/08 18:57:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 18:57:52 - mmengine - INFO - Saving checkpoint at 141 epochs 2022/09/08 18:58:21 - mmengine - INFO - Epoch(train) [142][50/293] lr: 5.000000e-04 eta: 2:24:23 time: 0.505551 data_time: 0.086288 memory: 9871 loss_kpt: 0.000605 acc_pose: 0.854134 loss: 0.000605 2022/09/08 18:58:47 - mmengine - INFO - Epoch(train) [142][100/293] lr: 5.000000e-04 eta: 2:24:04 time: 0.515911 data_time: 0.076188 memory: 9871 loss_kpt: 0.000603 acc_pose: 0.831991 loss: 0.000603 2022/09/08 18:59:12 - mmengine - INFO - Epoch(train) [142][150/293] lr: 5.000000e-04 eta: 2:23:44 time: 0.497271 data_time: 0.071475 memory: 9871 loss_kpt: 0.000602 acc_pose: 0.790767 loss: 0.000602 2022/09/08 18:59:38 - mmengine - INFO - Epoch(train) [142][200/293] lr: 5.000000e-04 eta: 2:23:25 time: 0.513061 data_time: 0.069760 memory: 9871 loss_kpt: 0.000605 acc_pose: 0.776773 loss: 0.000605 2022/09/08 19:00:02 - mmengine - INFO - Epoch(train) [142][250/293] lr: 5.000000e-04 eta: 2:23:05 time: 0.491519 data_time: 0.070637 memory: 9871 loss_kpt: 0.000610 acc_pose: 0.826947 loss: 0.000610 2022/09/08 19:00:24 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 19:00:24 - mmengine - INFO - Saving checkpoint at 142 epochs 2022/09/08 19:00:53 - mmengine - INFO - Epoch(train) [143][50/293] lr: 5.000000e-04 eta: 2:22:17 time: 0.501746 data_time: 0.078751 memory: 9871 loss_kpt: 0.000606 acc_pose: 0.837617 loss: 0.000606 2022/09/08 19:01:18 - mmengine - INFO - Epoch(train) [143][100/293] lr: 5.000000e-04 eta: 2:21:57 time: 0.490336 data_time: 0.068488 memory: 9871 loss_kpt: 0.000611 acc_pose: 0.851077 loss: 0.000611 2022/09/08 19:01:43 - mmengine - INFO - Epoch(train) [143][150/293] lr: 5.000000e-04 eta: 2:21:38 time: 0.508650 data_time: 0.077587 memory: 9871 loss_kpt: 0.000622 acc_pose: 0.863350 loss: 0.000622 2022/09/08 19:02:08 - mmengine - INFO - Epoch(train) [143][200/293] lr: 5.000000e-04 eta: 2:21:18 time: 0.493423 data_time: 0.071317 memory: 9871 loss_kpt: 0.000602 acc_pose: 0.810431 loss: 0.000602 2022/09/08 19:02:33 - mmengine - INFO - Epoch(train) [143][250/293] lr: 5.000000e-04 eta: 2:20:58 time: 0.495040 data_time: 0.072202 memory: 9871 loss_kpt: 0.000588 acc_pose: 0.849512 loss: 0.000588 2022/09/08 19:02:54 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 19:02:54 - mmengine - INFO - Saving checkpoint at 143 epochs 2022/09/08 19:03:25 - mmengine - INFO - Epoch(train) [144][50/293] lr: 5.000000e-04 eta: 2:20:11 time: 0.521765 data_time: 0.094339 memory: 9871 loss_kpt: 0.000619 acc_pose: 0.821216 loss: 0.000619 2022/09/08 19:03:49 - mmengine - INFO - Epoch(train) [144][100/293] lr: 5.000000e-04 eta: 2:19:51 time: 0.486046 data_time: 0.072507 memory: 9871 loss_kpt: 0.000605 acc_pose: 0.808562 loss: 0.000605 2022/09/08 19:03:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 19:04:14 - mmengine - INFO - Epoch(train) [144][150/293] lr: 5.000000e-04 eta: 2:19:31 time: 0.501054 data_time: 0.073741 memory: 9871 loss_kpt: 0.000616 acc_pose: 0.807977 loss: 0.000616 2022/09/08 19:04:39 - mmengine - INFO - Epoch(train) [144][200/293] lr: 5.000000e-04 eta: 2:19:11 time: 0.495133 data_time: 0.072560 memory: 9871 loss_kpt: 0.000607 acc_pose: 0.838746 loss: 0.000607 2022/09/08 19:05:04 - mmengine - INFO - Epoch(train) [144][250/293] lr: 5.000000e-04 eta: 2:18:52 time: 0.504231 data_time: 0.076959 memory: 9871 loss_kpt: 0.000613 acc_pose: 0.836188 loss: 0.000613 2022/09/08 19:05:25 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 19:05:25 - mmengine - INFO - Saving checkpoint at 144 epochs 2022/09/08 19:05:55 - mmengine - INFO - Epoch(train) [145][50/293] lr: 5.000000e-04 eta: 2:18:05 time: 0.499874 data_time: 0.081777 memory: 9871 loss_kpt: 0.000608 acc_pose: 0.844949 loss: 0.000608 2022/09/08 19:06:20 - mmengine - INFO - Epoch(train) [145][100/293] lr: 5.000000e-04 eta: 2:17:45 time: 0.496673 data_time: 0.074548 memory: 9871 loss_kpt: 0.000608 acc_pose: 0.847452 loss: 0.000608 2022/09/08 19:06:45 - mmengine - INFO - Epoch(train) [145][150/293] lr: 5.000000e-04 eta: 2:17:25 time: 0.495243 data_time: 0.074958 memory: 9871 loss_kpt: 0.000607 acc_pose: 0.858916 loss: 0.000607 2022/09/08 19:07:10 - mmengine - INFO - Epoch(train) [145][200/293] lr: 5.000000e-04 eta: 2:17:05 time: 0.496318 data_time: 0.073321 memory: 9871 loss_kpt: 0.000615 acc_pose: 0.820083 loss: 0.000615 2022/09/08 19:07:34 - mmengine - INFO - Epoch(train) [145][250/293] lr: 5.000000e-04 eta: 2:16:45 time: 0.490993 data_time: 0.066470 memory: 9871 loss_kpt: 0.000611 acc_pose: 0.790975 loss: 0.000611 2022/09/08 19:07:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 19:07:56 - mmengine - INFO - Saving checkpoint at 145 epochs 2022/09/08 19:08:26 - mmengine - INFO - Epoch(train) [146][50/293] lr: 5.000000e-04 eta: 2:15:58 time: 0.506993 data_time: 0.078568 memory: 9871 loss_kpt: 0.000617 acc_pose: 0.828424 loss: 0.000617 2022/09/08 19:08:50 - mmengine - INFO - Epoch(train) [146][100/293] lr: 5.000000e-04 eta: 2:15:38 time: 0.484256 data_time: 0.070255 memory: 9871 loss_kpt: 0.000596 acc_pose: 0.818834 loss: 0.000596 2022/09/08 19:09:15 - mmengine - INFO - Epoch(train) [146][150/293] lr: 5.000000e-04 eta: 2:15:18 time: 0.495677 data_time: 0.071006 memory: 9871 loss_kpt: 0.000606 acc_pose: 0.860242 loss: 0.000606 2022/09/08 19:09:40 - mmengine - INFO - Epoch(train) [146][200/293] lr: 5.000000e-04 eta: 2:14:58 time: 0.500528 data_time: 0.070339 memory: 9871 loss_kpt: 0.000615 acc_pose: 0.844553 loss: 0.000615 2022/09/08 19:10:05 - mmengine - INFO - Epoch(train) [146][250/293] lr: 5.000000e-04 eta: 2:14:38 time: 0.494899 data_time: 0.070118 memory: 9871 loss_kpt: 0.000606 acc_pose: 0.880123 loss: 0.000606 2022/09/08 19:10:25 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 19:10:25 - mmengine - INFO - Saving checkpoint at 146 epochs 2022/09/08 19:10:56 - mmengine - INFO - Epoch(train) [147][50/293] lr: 5.000000e-04 eta: 2:13:52 time: 0.520297 data_time: 0.084648 memory: 9871 loss_kpt: 0.000597 acc_pose: 0.816436 loss: 0.000597 2022/09/08 19:11:21 - mmengine - INFO - Epoch(train) [147][100/293] lr: 5.000000e-04 eta: 2:13:32 time: 0.509851 data_time: 0.073423 memory: 9871 loss_kpt: 0.000595 acc_pose: 0.826530 loss: 0.000595 2022/09/08 19:11:47 - mmengine - INFO - Epoch(train) [147][150/293] lr: 5.000000e-04 eta: 2:13:13 time: 0.510606 data_time: 0.072824 memory: 9871 loss_kpt: 0.000611 acc_pose: 0.838080 loss: 0.000611 2022/09/08 19:12:12 - mmengine - INFO - Epoch(train) [147][200/293] lr: 5.000000e-04 eta: 2:12:53 time: 0.503056 data_time: 0.074410 memory: 9871 loss_kpt: 0.000611 acc_pose: 0.839340 loss: 0.000611 2022/09/08 19:12:23 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 19:12:37 - mmengine - INFO - Epoch(train) [147][250/293] lr: 5.000000e-04 eta: 2:12:33 time: 0.503718 data_time: 0.068722 memory: 9871 loss_kpt: 0.000615 acc_pose: 0.830607 loss: 0.000615 2022/09/08 19:12:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 19:12:59 - mmengine - INFO - Saving checkpoint at 147 epochs 2022/09/08 19:13:29 - mmengine - INFO - Epoch(train) [148][50/293] lr: 5.000000e-04 eta: 2:11:47 time: 0.523014 data_time: 0.093722 memory: 9871 loss_kpt: 0.000599 acc_pose: 0.841843 loss: 0.000599 2022/09/08 19:13:54 - mmengine - INFO - Epoch(train) [148][100/293] lr: 5.000000e-04 eta: 2:11:27 time: 0.488745 data_time: 0.070412 memory: 9871 loss_kpt: 0.000606 acc_pose: 0.838255 loss: 0.000606 2022/09/08 19:14:19 - mmengine - INFO - Epoch(train) [148][150/293] lr: 5.000000e-04 eta: 2:11:07 time: 0.514596 data_time: 0.077074 memory: 9871 loss_kpt: 0.000610 acc_pose: 0.853112 loss: 0.000610 2022/09/08 19:14:45 - mmengine - INFO - Epoch(train) [148][200/293] lr: 5.000000e-04 eta: 2:10:47 time: 0.503236 data_time: 0.076493 memory: 9871 loss_kpt: 0.000603 acc_pose: 0.837701 loss: 0.000603 2022/09/08 19:15:09 - mmengine - INFO - Epoch(train) [148][250/293] lr: 5.000000e-04 eta: 2:10:27 time: 0.497290 data_time: 0.072948 memory: 9871 loss_kpt: 0.000605 acc_pose: 0.846083 loss: 0.000605 2022/09/08 19:15:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 19:15:30 - mmengine - INFO - Saving checkpoint at 148 epochs 2022/09/08 19:16:01 - mmengine - INFO - Epoch(train) [149][50/293] lr: 5.000000e-04 eta: 2:09:41 time: 0.522539 data_time: 0.091579 memory: 9871 loss_kpt: 0.000610 acc_pose: 0.850702 loss: 0.000610 2022/09/08 19:16:25 - mmengine - INFO - Epoch(train) [149][100/293] lr: 5.000000e-04 eta: 2:09:21 time: 0.489794 data_time: 0.073810 memory: 9871 loss_kpt: 0.000602 acc_pose: 0.804162 loss: 0.000602 2022/09/08 19:16:50 - mmengine - INFO - Epoch(train) [149][150/293] lr: 5.000000e-04 eta: 2:09:01 time: 0.501530 data_time: 0.077974 memory: 9871 loss_kpt: 0.000608 acc_pose: 0.827146 loss: 0.000608 2022/09/08 19:17:15 - mmengine - INFO - Epoch(train) [149][200/293] lr: 5.000000e-04 eta: 2:08:41 time: 0.494280 data_time: 0.070884 memory: 9871 loss_kpt: 0.000616 acc_pose: 0.833688 loss: 0.000616 2022/09/08 19:17:40 - mmengine - INFO - Epoch(train) [149][250/293] lr: 5.000000e-04 eta: 2:08:21 time: 0.499645 data_time: 0.078624 memory: 9871 loss_kpt: 0.000616 acc_pose: 0.811959 loss: 0.000616 2022/09/08 19:18:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 19:18:05 - mmengine - INFO - Saving checkpoint at 149 epochs 2022/09/08 19:18:41 - mmengine - INFO - Epoch(train) [150][50/293] lr: 5.000000e-04 eta: 2:07:37 time: 0.629779 data_time: 0.111251 memory: 9871 loss_kpt: 0.000613 acc_pose: 0.786323 loss: 0.000613 2022/09/08 19:19:08 - mmengine - INFO - Epoch(train) [150][100/293] lr: 5.000000e-04 eta: 2:07:18 time: 0.524510 data_time: 0.075640 memory: 9871 loss_kpt: 0.000601 acc_pose: 0.833438 loss: 0.000601 2022/09/08 19:19:32 - mmengine - INFO - Epoch(train) [150][150/293] lr: 5.000000e-04 eta: 2:06:58 time: 0.492094 data_time: 0.074366 memory: 9871 loss_kpt: 0.000600 acc_pose: 0.869987 loss: 0.000600 2022/09/08 19:19:57 - mmengine - INFO - Epoch(train) [150][200/293] lr: 5.000000e-04 eta: 2:06:38 time: 0.506530 data_time: 0.074902 memory: 9871 loss_kpt: 0.000613 acc_pose: 0.849539 loss: 0.000613 2022/09/08 19:20:22 - mmengine - INFO - Epoch(train) [150][250/293] lr: 5.000000e-04 eta: 2:06:17 time: 0.495284 data_time: 0.076679 memory: 9871 loss_kpt: 0.000623 acc_pose: 0.840898 loss: 0.000623 2022/09/08 19:20:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 19:20:43 - mmengine - INFO - Saving checkpoint at 150 epochs 2022/09/08 19:20:55 - mmengine - INFO - Epoch(val) [150][50/407] eta: 0:00:46 time: 0.131325 data_time: 0.021777 memory: 9871 2022/09/08 19:21:01 - mmengine - INFO - Epoch(val) [150][100/407] eta: 0:00:39 time: 0.127619 data_time: 0.018834 memory: 920 2022/09/08 19:21:08 - mmengine - INFO - Epoch(val) [150][150/407] eta: 0:00:33 time: 0.130765 data_time: 0.021440 memory: 920 2022/09/08 19:21:14 - mmengine - INFO - Epoch(val) [150][200/407] eta: 0:00:24 time: 0.119941 data_time: 0.011528 memory: 920 2022/09/08 19:21:21 - mmengine - INFO - Epoch(val) [150][250/407] eta: 0:00:22 time: 0.140631 data_time: 0.031421 memory: 920 2022/09/08 19:21:27 - mmengine - INFO - Epoch(val) [150][300/407] eta: 0:00:13 time: 0.124443 data_time: 0.013491 memory: 920 2022/09/08 19:21:34 - mmengine - INFO - Epoch(val) [150][350/407] eta: 0:00:07 time: 0.136093 data_time: 0.025782 memory: 920 2022/09/08 19:21:39 - mmengine - INFO - Epoch(val) [150][400/407] eta: 0:00:00 time: 0.110069 data_time: 0.008104 memory: 920 2022/09/08 19:22:14 - mmengine - INFO - Evaluating CocoMetric... 2022/09/08 19:22:27 - mmengine - INFO - Epoch(val) [150][407/407] coco/AP: 0.735379 coco/AP .5: 0.899637 coco/AP .75: 0.809329 coco/AP (M): 0.700162 coco/AP (L): 0.801377 coco/AR: 0.790790 coco/AR .5: 0.939389 coco/AR .75: 0.856581 coco/AR (M): 0.748839 coco/AR (L): 0.851171 2022/09/08 19:22:53 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 19:22:53 - mmengine - INFO - Epoch(train) [151][50/293] lr: 5.000000e-04 eta: 2:05:32 time: 0.509841 data_time: 0.080225 memory: 9871 loss_kpt: 0.000614 acc_pose: 0.792359 loss: 0.000614 2022/09/08 19:23:18 - mmengine - INFO - Epoch(train) [151][100/293] lr: 5.000000e-04 eta: 2:05:11 time: 0.497071 data_time: 0.072984 memory: 9871 loss_kpt: 0.000588 acc_pose: 0.807919 loss: 0.000588 2022/09/08 19:23:43 - mmengine - INFO - Epoch(train) [151][150/293] lr: 5.000000e-04 eta: 2:04:51 time: 0.503871 data_time: 0.076819 memory: 9871 loss_kpt: 0.000605 acc_pose: 0.854515 loss: 0.000605 2022/09/08 19:24:08 - mmengine - INFO - Epoch(train) [151][200/293] lr: 5.000000e-04 eta: 2:04:31 time: 0.500868 data_time: 0.068932 memory: 9871 loss_kpt: 0.000601 acc_pose: 0.817330 loss: 0.000601 2022/09/08 19:24:33 - mmengine - INFO - Epoch(train) [151][250/293] lr: 5.000000e-04 eta: 2:04:11 time: 0.492053 data_time: 0.074143 memory: 9871 loss_kpt: 0.000603 acc_pose: 0.836339 loss: 0.000603 2022/09/08 19:24:54 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 19:24:54 - mmengine - INFO - Saving checkpoint at 151 epochs 2022/09/08 19:25:23 - mmengine - INFO - Epoch(train) [152][50/293] lr: 5.000000e-04 eta: 2:03:25 time: 0.495254 data_time: 0.080868 memory: 9871 loss_kpt: 0.000607 acc_pose: 0.850173 loss: 0.000607 2022/09/08 19:25:48 - mmengine - INFO - Epoch(train) [152][100/293] lr: 5.000000e-04 eta: 2:03:05 time: 0.487459 data_time: 0.072738 memory: 9871 loss_kpt: 0.000594 acc_pose: 0.848663 loss: 0.000594 2022/09/08 19:26:13 - mmengine - INFO - Epoch(train) [152][150/293] lr: 5.000000e-04 eta: 2:02:45 time: 0.498431 data_time: 0.078544 memory: 9871 loss_kpt: 0.000624 acc_pose: 0.814352 loss: 0.000624 2022/09/08 19:26:38 - mmengine - INFO - Epoch(train) [152][200/293] lr: 5.000000e-04 eta: 2:02:25 time: 0.507654 data_time: 0.080172 memory: 9871 loss_kpt: 0.000599 acc_pose: 0.815841 loss: 0.000599 2022/09/08 19:27:02 - mmengine - INFO - Epoch(train) [152][250/293] lr: 5.000000e-04 eta: 2:02:04 time: 0.483236 data_time: 0.070528 memory: 9871 loss_kpt: 0.000609 acc_pose: 0.848849 loss: 0.000609 2022/09/08 19:27:23 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 19:27:23 - mmengine - INFO - Saving checkpoint at 152 epochs 2022/09/08 19:27:53 - mmengine - INFO - Epoch(train) [153][50/293] lr: 5.000000e-04 eta: 2:01:19 time: 0.520630 data_time: 0.085093 memory: 9871 loss_kpt: 0.000600 acc_pose: 0.859775 loss: 0.000600 2022/09/08 19:28:20 - mmengine - INFO - Epoch(train) [153][100/293] lr: 5.000000e-04 eta: 2:00:59 time: 0.522183 data_time: 0.070881 memory: 9871 loss_kpt: 0.000608 acc_pose: 0.880230 loss: 0.000608 2022/09/08 19:28:44 - mmengine - INFO - Epoch(train) [153][150/293] lr: 5.000000e-04 eta: 2:00:39 time: 0.492530 data_time: 0.073414 memory: 9871 loss_kpt: 0.000591 acc_pose: 0.847230 loss: 0.000591 2022/09/08 19:29:09 - mmengine - INFO - Epoch(train) [153][200/293] lr: 5.000000e-04 eta: 2:00:19 time: 0.495076 data_time: 0.067718 memory: 9871 loss_kpt: 0.000596 acc_pose: 0.819768 loss: 0.000596 2022/09/08 19:29:34 - mmengine - INFO - Epoch(train) [153][250/293] lr: 5.000000e-04 eta: 1:59:58 time: 0.494828 data_time: 0.068180 memory: 9871 loss_kpt: 0.000594 acc_pose: 0.893502 loss: 0.000594 2022/09/08 19:29:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 19:29:55 - mmengine - INFO - Saving checkpoint at 153 epochs 2022/09/08 19:30:25 - mmengine - INFO - Epoch(train) [154][50/293] lr: 5.000000e-04 eta: 1:59:13 time: 0.513307 data_time: 0.079186 memory: 9871 loss_kpt: 0.000600 acc_pose: 0.865583 loss: 0.000600 2022/09/08 19:30:51 - mmengine - INFO - Epoch(train) [154][100/293] lr: 5.000000e-04 eta: 1:58:53 time: 0.508042 data_time: 0.072542 memory: 9871 loss_kpt: 0.000603 acc_pose: 0.869795 loss: 0.000603 2022/09/08 19:31:16 - mmengine - INFO - Epoch(train) [154][150/293] lr: 5.000000e-04 eta: 1:58:33 time: 0.505019 data_time: 0.072423 memory: 9871 loss_kpt: 0.000592 acc_pose: 0.827383 loss: 0.000592 2022/09/08 19:31:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 19:31:41 - mmengine - INFO - Epoch(train) [154][200/293] lr: 5.000000e-04 eta: 1:58:13 time: 0.501608 data_time: 0.073078 memory: 9871 loss_kpt: 0.000607 acc_pose: 0.871969 loss: 0.000607 2022/09/08 19:32:06 - mmengine - INFO - Epoch(train) [154][250/293] lr: 5.000000e-04 eta: 1:57:52 time: 0.498836 data_time: 0.070167 memory: 9871 loss_kpt: 0.000604 acc_pose: 0.838008 loss: 0.000604 2022/09/08 19:32:28 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 19:32:28 - mmengine - INFO - Saving checkpoint at 154 epochs 2022/09/08 19:32:57 - mmengine - INFO - Epoch(train) [155][50/293] lr: 5.000000e-04 eta: 1:57:07 time: 0.513555 data_time: 0.085348 memory: 9871 loss_kpt: 0.000614 acc_pose: 0.842217 loss: 0.000614 2022/09/08 19:33:22 - mmengine - INFO - Epoch(train) [155][100/293] lr: 5.000000e-04 eta: 1:56:47 time: 0.490268 data_time: 0.076791 memory: 9871 loss_kpt: 0.000600 acc_pose: 0.859101 loss: 0.000600 2022/09/08 19:33:47 - mmengine - INFO - Epoch(train) [155][150/293] lr: 5.000000e-04 eta: 1:56:27 time: 0.493577 data_time: 0.075252 memory: 9871 loss_kpt: 0.000591 acc_pose: 0.845219 loss: 0.000591 2022/09/08 19:34:12 - mmengine - INFO - Epoch(train) [155][200/293] lr: 5.000000e-04 eta: 1:56:06 time: 0.506926 data_time: 0.083067 memory: 9871 loss_kpt: 0.000594 acc_pose: 0.852898 loss: 0.000594 2022/09/08 19:34:37 - mmengine - INFO - Epoch(train) [155][250/293] lr: 5.000000e-04 eta: 1:55:46 time: 0.493301 data_time: 0.076281 memory: 9871 loss_kpt: 0.000605 acc_pose: 0.808959 loss: 0.000605 2022/09/08 19:34:58 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 19:34:58 - mmengine - INFO - Saving checkpoint at 155 epochs 2022/09/08 19:35:28 - mmengine - INFO - Epoch(train) [156][50/293] lr: 5.000000e-04 eta: 1:55:01 time: 0.513458 data_time: 0.086140 memory: 9871 loss_kpt: 0.000598 acc_pose: 0.874092 loss: 0.000598 2022/09/08 19:35:54 - mmengine - INFO - Epoch(train) [156][100/293] lr: 5.000000e-04 eta: 1:54:41 time: 0.505146 data_time: 0.075847 memory: 9871 loss_kpt: 0.000604 acc_pose: 0.840122 loss: 0.000604 2022/09/08 19:36:18 - mmengine - INFO - Epoch(train) [156][150/293] lr: 5.000000e-04 eta: 1:54:21 time: 0.489118 data_time: 0.073829 memory: 9871 loss_kpt: 0.000606 acc_pose: 0.825298 loss: 0.000606 2022/09/08 19:36:43 - mmengine - INFO - Epoch(train) [156][200/293] lr: 5.000000e-04 eta: 1:54:00 time: 0.502664 data_time: 0.080485 memory: 9871 loss_kpt: 0.000597 acc_pose: 0.880444 loss: 0.000597 2022/09/08 19:37:08 - mmengine - INFO - Epoch(train) [156][250/293] lr: 5.000000e-04 eta: 1:53:40 time: 0.498406 data_time: 0.078329 memory: 9871 loss_kpt: 0.000599 acc_pose: 0.917765 loss: 0.000599 2022/09/08 19:37:29 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 19:37:29 - mmengine - INFO - Saving checkpoint at 156 epochs 2022/09/08 19:37:59 - mmengine - INFO - Epoch(train) [157][50/293] lr: 5.000000e-04 eta: 1:52:55 time: 0.510627 data_time: 0.088663 memory: 9871 loss_kpt: 0.000592 acc_pose: 0.860593 loss: 0.000592 2022/09/08 19:38:24 - mmengine - INFO - Epoch(train) [157][100/293] lr: 5.000000e-04 eta: 1:52:35 time: 0.497039 data_time: 0.073622 memory: 9871 loss_kpt: 0.000624 acc_pose: 0.797662 loss: 0.000624 2022/09/08 19:38:49 - mmengine - INFO - Epoch(train) [157][150/293] lr: 5.000000e-04 eta: 1:52:14 time: 0.499938 data_time: 0.087865 memory: 9871 loss_kpt: 0.000601 acc_pose: 0.853523 loss: 0.000601 2022/09/08 19:39:14 - mmengine - INFO - Epoch(train) [157][200/293] lr: 5.000000e-04 eta: 1:51:54 time: 0.502631 data_time: 0.073560 memory: 9871 loss_kpt: 0.000603 acc_pose: 0.839016 loss: 0.000603 2022/09/08 19:39:39 - mmengine - INFO - Epoch(train) [157][250/293] lr: 5.000000e-04 eta: 1:51:34 time: 0.494487 data_time: 0.074249 memory: 9871 loss_kpt: 0.000613 acc_pose: 0.842561 loss: 0.000613 2022/09/08 19:39:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 19:40:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 19:40:00 - mmengine - INFO - Saving checkpoint at 157 epochs 2022/09/08 19:40:31 - mmengine - INFO - Epoch(train) [158][50/293] lr: 5.000000e-04 eta: 1:50:49 time: 0.524757 data_time: 0.083689 memory: 9871 loss_kpt: 0.000602 acc_pose: 0.831628 loss: 0.000602 2022/09/08 19:40:55 - mmengine - INFO - Epoch(train) [158][100/293] lr: 5.000000e-04 eta: 1:50:29 time: 0.496976 data_time: 0.085981 memory: 9871 loss_kpt: 0.000604 acc_pose: 0.820819 loss: 0.000604 2022/09/08 19:41:20 - mmengine - INFO - Epoch(train) [158][150/293] lr: 5.000000e-04 eta: 1:50:08 time: 0.493030 data_time: 0.076181 memory: 9871 loss_kpt: 0.000592 acc_pose: 0.818569 loss: 0.000592 2022/09/08 19:41:45 - mmengine - INFO - Epoch(train) [158][200/293] lr: 5.000000e-04 eta: 1:49:48 time: 0.494382 data_time: 0.076253 memory: 9871 loss_kpt: 0.000588 acc_pose: 0.803682 loss: 0.000588 2022/09/08 19:42:10 - mmengine - INFO - Epoch(train) [158][250/293] lr: 5.000000e-04 eta: 1:49:28 time: 0.507548 data_time: 0.076054 memory: 9871 loss_kpt: 0.000599 acc_pose: 0.809372 loss: 0.000599 2022/09/08 19:42:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 19:42:32 - mmengine - INFO - Saving checkpoint at 158 epochs 2022/09/08 19:43:01 - mmengine - INFO - Epoch(train) [159][50/293] lr: 5.000000e-04 eta: 1:48:43 time: 0.502627 data_time: 0.083572 memory: 9871 loss_kpt: 0.000599 acc_pose: 0.826011 loss: 0.000599 2022/09/08 19:43:26 - mmengine - INFO - Epoch(train) [159][100/293] lr: 5.000000e-04 eta: 1:48:23 time: 0.504433 data_time: 0.078138 memory: 9871 loss_kpt: 0.000605 acc_pose: 0.845224 loss: 0.000605 2022/09/08 19:43:52 - mmengine - INFO - Epoch(train) [159][150/293] lr: 5.000000e-04 eta: 1:48:02 time: 0.506231 data_time: 0.079073 memory: 9871 loss_kpt: 0.000592 acc_pose: 0.873416 loss: 0.000592 2022/09/08 19:44:16 - mmengine - INFO - Epoch(train) [159][200/293] lr: 5.000000e-04 eta: 1:47:42 time: 0.489173 data_time: 0.074056 memory: 9871 loss_kpt: 0.000599 acc_pose: 0.828821 loss: 0.000599 2022/09/08 19:44:41 - mmengine - INFO - Epoch(train) [159][250/293] lr: 5.000000e-04 eta: 1:47:21 time: 0.490897 data_time: 0.075099 memory: 9871 loss_kpt: 0.000610 acc_pose: 0.849570 loss: 0.000610 2022/09/08 19:45:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 19:45:02 - mmengine - INFO - Saving checkpoint at 159 epochs 2022/09/08 19:45:31 - mmengine - INFO - Epoch(train) [160][50/293] lr: 5.000000e-04 eta: 1:46:37 time: 0.496880 data_time: 0.077871 memory: 9871 loss_kpt: 0.000590 acc_pose: 0.817660 loss: 0.000590 2022/09/08 19:45:56 - mmengine - INFO - Epoch(train) [160][100/293] lr: 5.000000e-04 eta: 1:46:16 time: 0.497458 data_time: 0.070190 memory: 9871 loss_kpt: 0.000601 acc_pose: 0.821237 loss: 0.000601 2022/09/08 19:46:21 - mmengine - INFO - Epoch(train) [160][150/293] lr: 5.000000e-04 eta: 1:45:56 time: 0.490596 data_time: 0.071283 memory: 9871 loss_kpt: 0.000593 acc_pose: 0.838740 loss: 0.000593 2022/09/08 19:46:46 - mmengine - INFO - Epoch(train) [160][200/293] lr: 5.000000e-04 eta: 1:45:35 time: 0.501253 data_time: 0.073801 memory: 9871 loss_kpt: 0.000602 acc_pose: 0.844965 loss: 0.000602 2022/09/08 19:47:11 - mmengine - INFO - Epoch(train) [160][250/293] lr: 5.000000e-04 eta: 1:45:15 time: 0.502280 data_time: 0.076729 memory: 9871 loss_kpt: 0.000608 acc_pose: 0.806526 loss: 0.000608 2022/09/08 19:47:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 19:47:32 - mmengine - INFO - Saving checkpoint at 160 epochs 2022/09/08 19:47:43 - mmengine - INFO - Epoch(val) [160][50/407] eta: 0:00:45 time: 0.126586 data_time: 0.019279 memory: 9871 2022/09/08 19:47:49 - mmengine - INFO - Epoch(val) [160][100/407] eta: 0:00:36 time: 0.119434 data_time: 0.012199 memory: 920 2022/09/08 19:47:55 - mmengine - INFO - Epoch(val) [160][150/407] eta: 0:00:31 time: 0.122825 data_time: 0.016963 memory: 920 2022/09/08 19:48:01 - mmengine - INFO - Epoch(val) [160][200/407] eta: 0:00:24 time: 0.116493 data_time: 0.011959 memory: 920 2022/09/08 19:48:07 - mmengine - INFO - Epoch(val) [160][250/407] eta: 0:00:18 time: 0.115214 data_time: 0.009526 memory: 920 2022/09/08 19:48:13 - mmengine - INFO - Epoch(val) [160][300/407] eta: 0:00:12 time: 0.121148 data_time: 0.013653 memory: 920 2022/09/08 19:48:19 - mmengine - INFO - Epoch(val) [160][350/407] eta: 0:00:07 time: 0.127445 data_time: 0.022552 memory: 920 2022/09/08 19:48:25 - mmengine - INFO - Epoch(val) [160][400/407] eta: 0:00:00 time: 0.110034 data_time: 0.008713 memory: 920 2022/09/08 19:48:59 - mmengine - INFO - Evaluating CocoMetric... 2022/09/08 19:49:13 - mmengine - INFO - Epoch(val) [160][407/407] coco/AP: 0.734695 coco/AP .5: 0.897575 coco/AP .75: 0.810710 coco/AP (M): 0.699059 coco/AP (L): 0.802773 coco/AR: 0.789657 coco/AR .5: 0.937028 coco/AR .75: 0.857210 coco/AR (M): 0.748238 coco/AR (L): 0.850130 2022/09/08 19:49:39 - mmengine - INFO - Epoch(train) [161][50/293] lr: 5.000000e-04 eta: 1:44:31 time: 0.513635 data_time: 0.080755 memory: 9871 loss_kpt: 0.000592 acc_pose: 0.851593 loss: 0.000592 2022/09/08 19:50:04 - mmengine - INFO - Epoch(train) [161][100/293] lr: 5.000000e-04 eta: 1:44:10 time: 0.499522 data_time: 0.076805 memory: 9871 loss_kpt: 0.000605 acc_pose: 0.831100 loss: 0.000605 2022/09/08 19:50:14 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 19:50:29 - mmengine - INFO - Epoch(train) [161][150/293] lr: 5.000000e-04 eta: 1:43:50 time: 0.500484 data_time: 0.072432 memory: 9871 loss_kpt: 0.000615 acc_pose: 0.844219 loss: 0.000615 2022/09/08 19:50:54 - mmengine - INFO - Epoch(train) [161][200/293] lr: 5.000000e-04 eta: 1:43:29 time: 0.506322 data_time: 0.081879 memory: 9871 loss_kpt: 0.000600 acc_pose: 0.841026 loss: 0.000600 2022/09/08 19:51:19 - mmengine - INFO - Epoch(train) [161][250/293] lr: 5.000000e-04 eta: 1:43:09 time: 0.495544 data_time: 0.077368 memory: 9871 loss_kpt: 0.000605 acc_pose: 0.837822 loss: 0.000605 2022/09/08 19:51:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 19:51:41 - mmengine - INFO - Saving checkpoint at 161 epochs 2022/09/08 19:52:11 - mmengine - INFO - Epoch(train) [162][50/293] lr: 5.000000e-04 eta: 1:42:25 time: 0.509004 data_time: 0.085484 memory: 9871 loss_kpt: 0.000597 acc_pose: 0.825180 loss: 0.000597 2022/09/08 19:52:36 - mmengine - INFO - Epoch(train) [162][100/293] lr: 5.000000e-04 eta: 1:42:04 time: 0.495377 data_time: 0.074280 memory: 9871 loss_kpt: 0.000604 acc_pose: 0.845180 loss: 0.000604 2022/09/08 19:53:01 - mmengine - INFO - Epoch(train) [162][150/293] lr: 5.000000e-04 eta: 1:41:44 time: 0.494778 data_time: 0.081129 memory: 9871 loss_kpt: 0.000590 acc_pose: 0.816180 loss: 0.000590 2022/09/08 19:53:26 - mmengine - INFO - Epoch(train) [162][200/293] lr: 5.000000e-04 eta: 1:41:23 time: 0.508075 data_time: 0.069295 memory: 9871 loss_kpt: 0.000606 acc_pose: 0.829665 loss: 0.000606 2022/09/08 19:53:51 - mmengine - INFO - Epoch(train) [162][250/293] lr: 5.000000e-04 eta: 1:41:03 time: 0.498122 data_time: 0.078475 memory: 9871 loss_kpt: 0.000610 acc_pose: 0.795427 loss: 0.000610 2022/09/08 19:54:12 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 19:54:12 - mmengine - INFO - Saving checkpoint at 162 epochs 2022/09/08 19:54:42 - mmengine - INFO - Epoch(train) [163][50/293] lr: 5.000000e-04 eta: 1:40:18 time: 0.500070 data_time: 0.080992 memory: 9871 loss_kpt: 0.000596 acc_pose: 0.829344 loss: 0.000596 2022/09/08 19:55:06 - mmengine - INFO - Epoch(train) [163][100/293] lr: 5.000000e-04 eta: 1:39:58 time: 0.481088 data_time: 0.073306 memory: 9871 loss_kpt: 0.000613 acc_pose: 0.834822 loss: 0.000613 2022/09/08 19:55:31 - mmengine - INFO - Epoch(train) [163][150/293] lr: 5.000000e-04 eta: 1:39:37 time: 0.494657 data_time: 0.078117 memory: 9871 loss_kpt: 0.000620 acc_pose: 0.801556 loss: 0.000620 2022/09/08 19:55:55 - mmengine - INFO - Epoch(train) [163][200/293] lr: 5.000000e-04 eta: 1:39:17 time: 0.491164 data_time: 0.071911 memory: 9871 loss_kpt: 0.000592 acc_pose: 0.868036 loss: 0.000592 2022/09/08 19:56:20 - mmengine - INFO - Epoch(train) [163][250/293] lr: 5.000000e-04 eta: 1:38:56 time: 0.497441 data_time: 0.074297 memory: 9871 loss_kpt: 0.000590 acc_pose: 0.860845 loss: 0.000590 2022/09/08 19:56:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 19:56:42 - mmengine - INFO - Saving checkpoint at 163 epochs 2022/09/08 19:57:11 - mmengine - INFO - Epoch(train) [164][50/293] lr: 5.000000e-04 eta: 1:38:12 time: 0.510741 data_time: 0.088385 memory: 9871 loss_kpt: 0.000595 acc_pose: 0.831887 loss: 0.000595 2022/09/08 19:57:36 - mmengine - INFO - Epoch(train) [164][100/293] lr: 5.000000e-04 eta: 1:37:52 time: 0.497786 data_time: 0.071921 memory: 9871 loss_kpt: 0.000601 acc_pose: 0.869935 loss: 0.000601 2022/09/08 19:58:02 - mmengine - INFO - Epoch(train) [164][150/293] lr: 5.000000e-04 eta: 1:37:31 time: 0.507182 data_time: 0.076802 memory: 9871 loss_kpt: 0.000614 acc_pose: 0.804193 loss: 0.000614 2022/09/08 19:58:27 - mmengine - INFO - Epoch(train) [164][200/293] lr: 5.000000e-04 eta: 1:37:11 time: 0.502425 data_time: 0.080794 memory: 9871 loss_kpt: 0.000610 acc_pose: 0.830228 loss: 0.000610 2022/09/08 19:58:47 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 19:58:52 - mmengine - INFO - Epoch(train) [164][250/293] lr: 5.000000e-04 eta: 1:36:50 time: 0.493792 data_time: 0.075483 memory: 9871 loss_kpt: 0.000594 acc_pose: 0.803851 loss: 0.000594 2022/09/08 19:59:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 19:59:13 - mmengine - INFO - Saving checkpoint at 164 epochs 2022/09/08 19:59:43 - mmengine - INFO - Epoch(train) [165][50/293] lr: 5.000000e-04 eta: 1:36:06 time: 0.502065 data_time: 0.085360 memory: 9871 loss_kpt: 0.000604 acc_pose: 0.784676 loss: 0.000604 2022/09/08 20:00:08 - mmengine - INFO - Epoch(train) [165][100/293] lr: 5.000000e-04 eta: 1:35:46 time: 0.502607 data_time: 0.077210 memory: 9871 loss_kpt: 0.000590 acc_pose: 0.875642 loss: 0.000590 2022/09/08 20:00:33 - mmengine - INFO - Epoch(train) [165][150/293] lr: 5.000000e-04 eta: 1:35:25 time: 0.496384 data_time: 0.077933 memory: 9871 loss_kpt: 0.000603 acc_pose: 0.842891 loss: 0.000603 2022/09/08 20:00:57 - mmengine - INFO - Epoch(train) [165][200/293] lr: 5.000000e-04 eta: 1:35:04 time: 0.493260 data_time: 0.077088 memory: 9871 loss_kpt: 0.000605 acc_pose: 0.823931 loss: 0.000605 2022/09/08 20:01:22 - mmengine - INFO - Epoch(train) [165][250/293] lr: 5.000000e-04 eta: 1:34:44 time: 0.497139 data_time: 0.079412 memory: 9871 loss_kpt: 0.000602 acc_pose: 0.880882 loss: 0.000602 2022/09/08 20:01:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 20:01:44 - mmengine - INFO - Saving checkpoint at 165 epochs 2022/09/08 20:02:13 - mmengine - INFO - Epoch(train) [166][50/293] lr: 5.000000e-04 eta: 1:34:00 time: 0.504007 data_time: 0.084173 memory: 9871 loss_kpt: 0.000585 acc_pose: 0.831282 loss: 0.000585 2022/09/08 20:02:38 - mmengine - INFO - Epoch(train) [166][100/293] lr: 5.000000e-04 eta: 1:33:39 time: 0.492067 data_time: 0.079057 memory: 9871 loss_kpt: 0.000605 acc_pose: 0.805907 loss: 0.000605 2022/09/08 20:03:04 - mmengine - INFO - Epoch(train) [166][150/293] lr: 5.000000e-04 eta: 1:33:19 time: 0.508951 data_time: 0.080549 memory: 9871 loss_kpt: 0.000605 acc_pose: 0.782179 loss: 0.000605 2022/09/08 20:03:29 - mmengine - INFO - Epoch(train) [166][200/293] lr: 5.000000e-04 eta: 1:32:58 time: 0.502034 data_time: 0.075431 memory: 9871 loss_kpt: 0.000599 acc_pose: 0.827128 loss: 0.000599 2022/09/08 20:03:54 - mmengine - INFO - Epoch(train) [166][250/293] lr: 5.000000e-04 eta: 1:32:38 time: 0.503552 data_time: 0.080145 memory: 9871 loss_kpt: 0.000591 acc_pose: 0.837893 loss: 0.000591 2022/09/08 20:04:15 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 20:04:15 - mmengine - INFO - Saving checkpoint at 166 epochs 2022/09/08 20:04:46 - mmengine - INFO - Epoch(train) [167][50/293] lr: 5.000000e-04 eta: 1:31:54 time: 0.516660 data_time: 0.094917 memory: 9871 loss_kpt: 0.000596 acc_pose: 0.826728 loss: 0.000596 2022/09/08 20:05:11 - mmengine - INFO - Epoch(train) [167][100/293] lr: 5.000000e-04 eta: 1:31:34 time: 0.497922 data_time: 0.072670 memory: 9871 loss_kpt: 0.000588 acc_pose: 0.806938 loss: 0.000588 2022/09/08 20:05:36 - mmengine - INFO - Epoch(train) [167][150/293] lr: 5.000000e-04 eta: 1:31:13 time: 0.501492 data_time: 0.078355 memory: 9871 loss_kpt: 0.000596 acc_pose: 0.833800 loss: 0.000596 2022/09/08 20:06:01 - mmengine - INFO - Epoch(train) [167][200/293] lr: 5.000000e-04 eta: 1:30:52 time: 0.497667 data_time: 0.076736 memory: 9871 loss_kpt: 0.000604 acc_pose: 0.865361 loss: 0.000604 2022/09/08 20:06:26 - mmengine - INFO - Epoch(train) [167][250/293] lr: 5.000000e-04 eta: 1:30:32 time: 0.503175 data_time: 0.081706 memory: 9871 loss_kpt: 0.000600 acc_pose: 0.839854 loss: 0.000600 2022/09/08 20:06:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 20:06:46 - mmengine - INFO - Saving checkpoint at 167 epochs 2022/09/08 20:07:17 - mmengine - INFO - Epoch(train) [168][50/293] lr: 5.000000e-04 eta: 1:29:48 time: 0.510418 data_time: 0.087349 memory: 9871 loss_kpt: 0.000597 acc_pose: 0.869356 loss: 0.000597 2022/09/08 20:07:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 20:07:41 - mmengine - INFO - Epoch(train) [168][100/293] lr: 5.000000e-04 eta: 1:29:28 time: 0.495783 data_time: 0.079655 memory: 9871 loss_kpt: 0.000596 acc_pose: 0.898751 loss: 0.000596 2022/09/08 20:08:07 - mmengine - INFO - Epoch(train) [168][150/293] lr: 5.000000e-04 eta: 1:29:07 time: 0.519200 data_time: 0.083069 memory: 9871 loss_kpt: 0.000595 acc_pose: 0.879098 loss: 0.000595 2022/09/08 20:08:32 - mmengine - INFO - Epoch(train) [168][200/293] lr: 5.000000e-04 eta: 1:28:47 time: 0.487827 data_time: 0.071912 memory: 9871 loss_kpt: 0.000598 acc_pose: 0.861143 loss: 0.000598 2022/09/08 20:08:57 - mmengine - INFO - Epoch(train) [168][250/293] lr: 5.000000e-04 eta: 1:28:26 time: 0.498636 data_time: 0.078242 memory: 9871 loss_kpt: 0.000600 acc_pose: 0.891462 loss: 0.000600 2022/09/08 20:09:17 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 20:09:17 - mmengine - INFO - Saving checkpoint at 168 epochs 2022/09/08 20:09:47 - mmengine - INFO - Epoch(train) [169][50/293] lr: 5.000000e-04 eta: 1:27:42 time: 0.503681 data_time: 0.086295 memory: 9871 loss_kpt: 0.000606 acc_pose: 0.821109 loss: 0.000606 2022/09/08 20:10:12 - mmengine - INFO - Epoch(train) [169][100/293] lr: 5.000000e-04 eta: 1:27:22 time: 0.505545 data_time: 0.080178 memory: 9871 loss_kpt: 0.000582 acc_pose: 0.800452 loss: 0.000582 2022/09/08 20:10:37 - mmengine - INFO - Epoch(train) [169][150/293] lr: 5.000000e-04 eta: 1:27:01 time: 0.495272 data_time: 0.073137 memory: 9871 loss_kpt: 0.000590 acc_pose: 0.861046 loss: 0.000590 2022/09/08 20:11:03 - mmengine - INFO - Epoch(train) [169][200/293] lr: 5.000000e-04 eta: 1:26:41 time: 0.512619 data_time: 0.080527 memory: 9871 loss_kpt: 0.000595 acc_pose: 0.843573 loss: 0.000595 2022/09/08 20:11:28 - mmengine - INFO - Epoch(train) [169][250/293] lr: 5.000000e-04 eta: 1:26:20 time: 0.499546 data_time: 0.074398 memory: 9871 loss_kpt: 0.000594 acc_pose: 0.867863 loss: 0.000594 2022/09/08 20:11:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 20:11:49 - mmengine - INFO - Saving checkpoint at 169 epochs 2022/09/08 20:12:19 - mmengine - INFO - Epoch(train) [170][50/293] lr: 5.000000e-04 eta: 1:25:37 time: 0.507129 data_time: 0.084926 memory: 9871 loss_kpt: 0.000598 acc_pose: 0.852357 loss: 0.000598 2022/09/08 20:12:44 - mmengine - INFO - Epoch(train) [170][100/293] lr: 5.000000e-04 eta: 1:25:16 time: 0.500062 data_time: 0.072384 memory: 9871 loss_kpt: 0.000602 acc_pose: 0.879698 loss: 0.000602 2022/09/08 20:13:10 - mmengine - INFO - Epoch(train) [170][150/293] lr: 5.000000e-04 eta: 1:24:55 time: 0.511391 data_time: 0.089168 memory: 9871 loss_kpt: 0.000605 acc_pose: 0.814829 loss: 0.000605 2022/09/08 20:13:35 - mmengine - INFO - Epoch(train) [170][200/293] lr: 5.000000e-04 eta: 1:24:35 time: 0.496629 data_time: 0.079840 memory: 9871 loss_kpt: 0.000596 acc_pose: 0.829703 loss: 0.000596 2022/09/08 20:14:00 - mmengine - INFO - Epoch(train) [170][250/293] lr: 5.000000e-04 eta: 1:24:14 time: 0.500194 data_time: 0.078315 memory: 9871 loss_kpt: 0.000596 acc_pose: 0.862983 loss: 0.000596 2022/09/08 20:14:22 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 20:14:22 - mmengine - INFO - Saving checkpoint at 170 epochs 2022/09/08 20:14:33 - mmengine - INFO - Epoch(val) [170][50/407] eta: 0:00:43 time: 0.122635 data_time: 0.015965 memory: 9871 2022/09/08 20:14:38 - mmengine - INFO - Epoch(val) [170][100/407] eta: 0:00:35 time: 0.114399 data_time: 0.010328 memory: 920 2022/09/08 20:14:44 - mmengine - INFO - Epoch(val) [170][150/407] eta: 0:00:29 time: 0.115204 data_time: 0.010157 memory: 920 2022/09/08 20:14:50 - mmengine - INFO - Epoch(val) [170][200/407] eta: 0:00:23 time: 0.113151 data_time: 0.008747 memory: 920 2022/09/08 20:14:56 - mmengine - INFO - Epoch(val) [170][250/407] eta: 0:00:18 time: 0.119051 data_time: 0.014930 memory: 920 2022/09/08 20:15:02 - mmengine - INFO - Epoch(val) [170][300/407] eta: 0:00:12 time: 0.120343 data_time: 0.016157 memory: 920 2022/09/08 20:15:07 - mmengine - INFO - Epoch(val) [170][350/407] eta: 0:00:06 time: 0.113604 data_time: 0.008868 memory: 920 2022/09/08 20:15:13 - mmengine - INFO - Epoch(val) [170][400/407] eta: 0:00:00 time: 0.110470 data_time: 0.008875 memory: 920 2022/09/08 20:15:48 - mmengine - INFO - Evaluating CocoMetric... 2022/09/08 20:16:01 - mmengine - INFO - Epoch(val) [170][407/407] coco/AP: 0.738343 coco/AP .5: 0.900436 coco/AP .75: 0.811604 coco/AP (M): 0.701973 coco/AP (L): 0.805866 coco/AR: 0.792916 coco/AR .5: 0.938445 coco/AR .75: 0.858312 coco/AR (M): 0.750041 coco/AR (L): 0.854589 2022/09/08 20:16:01 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220908/hrnet_w32_256/best_coco/AP_epoch_140.pth is removed 2022/09/08 20:16:04 - mmengine - INFO - The best checkpoint with 0.7383 coco/AP at 170 epoch is saved to best_coco/AP_epoch_170.pth. 2022/09/08 20:16:30 - mmengine - INFO - Epoch(train) [171][50/293] lr: 5.000000e-05 eta: 1:23:31 time: 0.513412 data_time: 0.082667 memory: 9871 loss_kpt: 0.000583 acc_pose: 0.833126 loss: 0.000583 2022/09/08 20:16:54 - mmengine - INFO - Epoch(train) [171][100/293] lr: 5.000000e-05 eta: 1:23:10 time: 0.490267 data_time: 0.077840 memory: 9871 loss_kpt: 0.000570 acc_pose: 0.851525 loss: 0.000570 2022/09/08 20:17:20 - mmengine - INFO - Epoch(train) [171][150/293] lr: 5.000000e-05 eta: 1:22:50 time: 0.514928 data_time: 0.079733 memory: 9871 loss_kpt: 0.000583 acc_pose: 0.802903 loss: 0.000583 2022/09/08 20:17:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 20:17:46 - mmengine - INFO - Epoch(train) [171][200/293] lr: 5.000000e-05 eta: 1:22:29 time: 0.512150 data_time: 0.077628 memory: 9871 loss_kpt: 0.000575 acc_pose: 0.842898 loss: 0.000575 2022/09/08 20:18:11 - mmengine - INFO - Epoch(train) [171][250/293] lr: 5.000000e-05 eta: 1:22:08 time: 0.500758 data_time: 0.077883 memory: 9871 loss_kpt: 0.000588 acc_pose: 0.859126 loss: 0.000588 2022/09/08 20:18:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 20:18:32 - mmengine - INFO - Saving checkpoint at 171 epochs 2022/09/08 20:19:02 - mmengine - INFO - Epoch(train) [172][50/293] lr: 5.000000e-05 eta: 1:21:25 time: 0.510017 data_time: 0.090829 memory: 9871 loss_kpt: 0.000579 acc_pose: 0.877075 loss: 0.000579 2022/09/08 20:19:26 - mmengine - INFO - Epoch(train) [172][100/293] lr: 5.000000e-05 eta: 1:21:04 time: 0.490506 data_time: 0.078569 memory: 9871 loss_kpt: 0.000581 acc_pose: 0.853996 loss: 0.000581 2022/09/08 20:19:51 - mmengine - INFO - Epoch(train) [172][150/293] lr: 5.000000e-05 eta: 1:20:44 time: 0.502574 data_time: 0.078874 memory: 9871 loss_kpt: 0.000562 acc_pose: 0.855687 loss: 0.000562 2022/09/08 20:20:16 - mmengine - INFO - Epoch(train) [172][200/293] lr: 5.000000e-05 eta: 1:20:23 time: 0.500570 data_time: 0.077355 memory: 9871 loss_kpt: 0.000576 acc_pose: 0.851567 loss: 0.000576 2022/09/08 20:20:41 - mmengine - INFO - Epoch(train) [172][250/293] lr: 5.000000e-05 eta: 1:20:02 time: 0.489021 data_time: 0.076008 memory: 9871 loss_kpt: 0.000582 acc_pose: 0.875336 loss: 0.000582 2022/09/08 20:21:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 20:21:02 - mmengine - INFO - Saving checkpoint at 172 epochs 2022/09/08 20:21:32 - mmengine - INFO - Epoch(train) [173][50/293] lr: 5.000000e-05 eta: 1:19:19 time: 0.500036 data_time: 0.083504 memory: 9871 loss_kpt: 0.000567 acc_pose: 0.837021 loss: 0.000567 2022/09/08 20:21:58 - mmengine - INFO - Epoch(train) [173][100/293] lr: 5.000000e-05 eta: 1:18:58 time: 0.510752 data_time: 0.076412 memory: 9871 loss_kpt: 0.000583 acc_pose: 0.843512 loss: 0.000583 2022/09/08 20:22:23 - mmengine - INFO - Epoch(train) [173][150/293] lr: 5.000000e-05 eta: 1:18:38 time: 0.501397 data_time: 0.075332 memory: 9871 loss_kpt: 0.000585 acc_pose: 0.882473 loss: 0.000585 2022/09/08 20:22:48 - mmengine - INFO - Epoch(train) [173][200/293] lr: 5.000000e-05 eta: 1:18:17 time: 0.502793 data_time: 0.076755 memory: 9871 loss_kpt: 0.000571 acc_pose: 0.892258 loss: 0.000571 2022/09/08 20:23:12 - mmengine - INFO - Epoch(train) [173][250/293] lr: 5.000000e-05 eta: 1:17:56 time: 0.492204 data_time: 0.078760 memory: 9871 loss_kpt: 0.000573 acc_pose: 0.830842 loss: 0.000573 2022/09/08 20:23:34 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 20:23:34 - mmengine - INFO - Saving checkpoint at 173 epochs 2022/09/08 20:24:04 - mmengine - INFO - Epoch(train) [174][50/293] lr: 5.000000e-05 eta: 1:17:13 time: 0.508717 data_time: 0.079821 memory: 9871 loss_kpt: 0.000568 acc_pose: 0.850966 loss: 0.000568 2022/09/08 20:24:28 - mmengine - INFO - Epoch(train) [174][100/293] lr: 5.000000e-05 eta: 1:16:52 time: 0.495629 data_time: 0.074742 memory: 9871 loss_kpt: 0.000562 acc_pose: 0.879647 loss: 0.000562 2022/09/08 20:24:54 - mmengine - INFO - Epoch(train) [174][150/293] lr: 5.000000e-05 eta: 1:16:32 time: 0.509066 data_time: 0.080467 memory: 9871 loss_kpt: 0.000575 acc_pose: 0.851926 loss: 0.000575 2022/09/08 20:25:19 - mmengine - INFO - Epoch(train) [174][200/293] lr: 5.000000e-05 eta: 1:16:11 time: 0.498806 data_time: 0.075164 memory: 9871 loss_kpt: 0.000574 acc_pose: 0.823007 loss: 0.000574 2022/09/08 20:25:44 - mmengine - INFO - Epoch(train) [174][250/293] lr: 5.000000e-05 eta: 1:15:50 time: 0.497573 data_time: 0.072620 memory: 9871 loss_kpt: 0.000566 acc_pose: 0.841145 loss: 0.000566 2022/09/08 20:26:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 20:26:05 - mmengine - INFO - Saving checkpoint at 174 epochs 2022/09/08 20:26:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 20:26:35 - mmengine - INFO - Epoch(train) [175][50/293] lr: 5.000000e-05 eta: 1:15:07 time: 0.508237 data_time: 0.086588 memory: 9871 loss_kpt: 0.000575 acc_pose: 0.833467 loss: 0.000575 2022/09/08 20:27:00 - mmengine - INFO - Epoch(train) [175][100/293] lr: 5.000000e-05 eta: 1:14:46 time: 0.502420 data_time: 0.075449 memory: 9871 loss_kpt: 0.000577 acc_pose: 0.854014 loss: 0.000577 2022/09/08 20:27:25 - mmengine - INFO - Epoch(train) [175][150/293] lr: 5.000000e-05 eta: 1:14:26 time: 0.487416 data_time: 0.077156 memory: 9871 loss_kpt: 0.000568 acc_pose: 0.850663 loss: 0.000568 2022/09/08 20:27:50 - mmengine - INFO - Epoch(train) [175][200/293] lr: 5.000000e-05 eta: 1:14:05 time: 0.512545 data_time: 0.081532 memory: 9871 loss_kpt: 0.000573 acc_pose: 0.799356 loss: 0.000573 2022/09/08 20:28:15 - mmengine - INFO - Epoch(train) [175][250/293] lr: 5.000000e-05 eta: 1:13:44 time: 0.494678 data_time: 0.071021 memory: 9871 loss_kpt: 0.000576 acc_pose: 0.812347 loss: 0.000576 2022/09/08 20:28:37 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 20:28:37 - mmengine - INFO - Saving checkpoint at 175 epochs 2022/09/08 20:29:06 - mmengine - INFO - Epoch(train) [176][50/293] lr: 5.000000e-05 eta: 1:13:01 time: 0.506101 data_time: 0.085756 memory: 9871 loss_kpt: 0.000575 acc_pose: 0.864746 loss: 0.000575 2022/09/08 20:29:32 - mmengine - INFO - Epoch(train) [176][100/293] lr: 5.000000e-05 eta: 1:12:40 time: 0.500169 data_time: 0.082394 memory: 9871 loss_kpt: 0.000566 acc_pose: 0.825979 loss: 0.000566 2022/09/08 20:29:57 - mmengine - INFO - Epoch(train) [176][150/293] lr: 5.000000e-05 eta: 1:12:20 time: 0.500986 data_time: 0.077510 memory: 9871 loss_kpt: 0.000553 acc_pose: 0.824214 loss: 0.000553 2022/09/08 20:30:21 - mmengine - INFO - Epoch(train) [176][200/293] lr: 5.000000e-05 eta: 1:11:59 time: 0.491631 data_time: 0.076598 memory: 9871 loss_kpt: 0.000563 acc_pose: 0.781336 loss: 0.000563 2022/09/08 20:30:47 - mmengine - INFO - Epoch(train) [176][250/293] lr: 5.000000e-05 eta: 1:11:38 time: 0.510644 data_time: 0.071535 memory: 9871 loss_kpt: 0.000575 acc_pose: 0.843855 loss: 0.000575 2022/09/08 20:31:09 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 20:31:09 - mmengine - INFO - Saving checkpoint at 176 epochs 2022/09/08 20:31:38 - mmengine - INFO - Epoch(train) [177][50/293] lr: 5.000000e-05 eta: 1:10:55 time: 0.505451 data_time: 0.085452 memory: 9871 loss_kpt: 0.000562 acc_pose: 0.843709 loss: 0.000562 2022/09/08 20:32:04 - mmengine - INFO - Epoch(train) [177][100/293] lr: 5.000000e-05 eta: 1:10:35 time: 0.508814 data_time: 0.072696 memory: 9871 loss_kpt: 0.000563 acc_pose: 0.860045 loss: 0.000563 2022/09/08 20:32:29 - mmengine - INFO - Epoch(train) [177][150/293] lr: 5.000000e-05 eta: 1:10:14 time: 0.512789 data_time: 0.074489 memory: 9871 loss_kpt: 0.000576 acc_pose: 0.855626 loss: 0.000576 2022/09/08 20:32:54 - mmengine - INFO - Epoch(train) [177][200/293] lr: 5.000000e-05 eta: 1:09:53 time: 0.499205 data_time: 0.078736 memory: 9871 loss_kpt: 0.000560 acc_pose: 0.885669 loss: 0.000560 2022/09/08 20:33:19 - mmengine - INFO - Epoch(train) [177][250/293] lr: 5.000000e-05 eta: 1:09:32 time: 0.496939 data_time: 0.078946 memory: 9871 loss_kpt: 0.000562 acc_pose: 0.890421 loss: 0.000562 2022/09/08 20:33:40 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 20:33:40 - mmengine - INFO - Saving checkpoint at 177 epochs 2022/09/08 20:34:11 - mmengine - INFO - Epoch(train) [178][50/293] lr: 5.000000e-05 eta: 1:08:50 time: 0.514451 data_time: 0.087403 memory: 9871 loss_kpt: 0.000577 acc_pose: 0.828989 loss: 0.000577 2022/09/08 20:34:36 - mmengine - INFO - Epoch(train) [178][100/293] lr: 5.000000e-05 eta: 1:08:29 time: 0.506276 data_time: 0.076865 memory: 9871 loss_kpt: 0.000566 acc_pose: 0.833680 loss: 0.000566 2022/09/08 20:34:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 20:35:01 - mmengine - INFO - Epoch(train) [178][150/293] lr: 5.000000e-05 eta: 1:08:08 time: 0.504652 data_time: 0.077440 memory: 9871 loss_kpt: 0.000556 acc_pose: 0.812492 loss: 0.000556 2022/09/08 20:35:27 - mmengine - INFO - Epoch(train) [178][200/293] lr: 5.000000e-05 eta: 1:07:47 time: 0.505892 data_time: 0.081094 memory: 9871 loss_kpt: 0.000556 acc_pose: 0.849480 loss: 0.000556 2022/09/08 20:35:51 - mmengine - INFO - Epoch(train) [178][250/293] lr: 5.000000e-05 eta: 1:07:26 time: 0.490153 data_time: 0.074749 memory: 9871 loss_kpt: 0.000568 acc_pose: 0.853894 loss: 0.000568 2022/09/08 20:36:12 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 20:36:12 - mmengine - INFO - Saving checkpoint at 178 epochs 2022/09/08 20:36:42 - mmengine - INFO - Epoch(train) [179][50/293] lr: 5.000000e-05 eta: 1:06:44 time: 0.510970 data_time: 0.084305 memory: 9871 loss_kpt: 0.000569 acc_pose: 0.850920 loss: 0.000569 2022/09/08 20:37:07 - mmengine - INFO - Epoch(train) [179][100/293] lr: 5.000000e-05 eta: 1:06:23 time: 0.496527 data_time: 0.082389 memory: 9871 loss_kpt: 0.000570 acc_pose: 0.850086 loss: 0.000570 2022/09/08 20:37:32 - mmengine - INFO - Epoch(train) [179][150/293] lr: 5.000000e-05 eta: 1:06:02 time: 0.500714 data_time: 0.072505 memory: 9871 loss_kpt: 0.000564 acc_pose: 0.863688 loss: 0.000564 2022/09/08 20:37:57 - mmengine - INFO - Epoch(train) [179][200/293] lr: 5.000000e-05 eta: 1:05:41 time: 0.502924 data_time: 0.078188 memory: 9871 loss_kpt: 0.000558 acc_pose: 0.890585 loss: 0.000558 2022/09/08 20:38:22 - mmengine - INFO - Epoch(train) [179][250/293] lr: 5.000000e-05 eta: 1:05:20 time: 0.498270 data_time: 0.082963 memory: 9871 loss_kpt: 0.000561 acc_pose: 0.827629 loss: 0.000561 2022/09/08 20:38:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 20:38:43 - mmengine - INFO - Saving checkpoint at 179 epochs 2022/09/08 20:39:13 - mmengine - INFO - Epoch(train) [180][50/293] lr: 5.000000e-05 eta: 1:04:38 time: 0.510225 data_time: 0.081477 memory: 9871 loss_kpt: 0.000576 acc_pose: 0.871977 loss: 0.000576 2022/09/08 20:39:38 - mmengine - INFO - Epoch(train) [180][100/293] lr: 5.000000e-05 eta: 1:04:17 time: 0.501652 data_time: 0.082224 memory: 9871 loss_kpt: 0.000564 acc_pose: 0.837178 loss: 0.000564 2022/09/08 20:40:03 - mmengine - INFO - Epoch(train) [180][150/293] lr: 5.000000e-05 eta: 1:03:56 time: 0.501547 data_time: 0.077177 memory: 9871 loss_kpt: 0.000554 acc_pose: 0.818159 loss: 0.000554 2022/09/08 20:40:28 - mmengine - INFO - Epoch(train) [180][200/293] lr: 5.000000e-05 eta: 1:03:35 time: 0.496902 data_time: 0.080824 memory: 9871 loss_kpt: 0.000560 acc_pose: 0.854624 loss: 0.000560 2022/09/08 20:40:52 - mmengine - INFO - Epoch(train) [180][250/293] lr: 5.000000e-05 eta: 1:03:14 time: 0.486102 data_time: 0.077506 memory: 9871 loss_kpt: 0.000575 acc_pose: 0.824021 loss: 0.000575 2022/09/08 20:41:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 20:41:13 - mmengine - INFO - Saving checkpoint at 180 epochs 2022/09/08 20:41:24 - mmengine - INFO - Epoch(val) [180][50/407] eta: 0:00:45 time: 0.127497 data_time: 0.020695 memory: 9871 2022/09/08 20:41:30 - mmengine - INFO - Epoch(val) [180][100/407] eta: 0:00:38 time: 0.123854 data_time: 0.017532 memory: 920 2022/09/08 20:41:37 - mmengine - INFO - Epoch(val) [180][150/407] eta: 0:00:32 time: 0.126277 data_time: 0.018190 memory: 920 2022/09/08 20:41:42 - mmengine - INFO - Epoch(val) [180][200/407] eta: 0:00:23 time: 0.114343 data_time: 0.009702 memory: 920 2022/09/08 20:41:48 - mmengine - INFO - Epoch(val) [180][250/407] eta: 0:00:18 time: 0.115690 data_time: 0.009837 memory: 920 2022/09/08 20:41:54 - mmengine - INFO - Epoch(val) [180][300/407] eta: 0:00:12 time: 0.121091 data_time: 0.014329 memory: 920 2022/09/08 20:42:00 - mmengine - INFO - Epoch(val) [180][350/407] eta: 0:00:06 time: 0.118462 data_time: 0.010168 memory: 920 2022/09/08 20:42:06 - mmengine - INFO - Epoch(val) [180][400/407] eta: 0:00:00 time: 0.108923 data_time: 0.008119 memory: 920 2022/09/08 20:42:40 - mmengine - INFO - Evaluating CocoMetric... 2022/09/08 20:42:53 - mmengine - INFO - Epoch(val) [180][407/407] coco/AP: 0.745773 coco/AP .5: 0.905091 coco/AP .75: 0.819381 coco/AP (M): 0.709651 coco/AP (L): 0.813098 coco/AR: 0.799166 coco/AR .5: 0.941278 coco/AR .75: 0.864452 coco/AR (M): 0.756760 coco/AR (L): 0.860870 2022/09/08 20:42:53 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220908/hrnet_w32_256/best_coco/AP_epoch_170.pth is removed 2022/09/08 20:42:57 - mmengine - INFO - The best checkpoint with 0.7458 coco/AP at 180 epoch is saved to best_coco/AP_epoch_180.pth. 2022/09/08 20:43:23 - mmengine - INFO - Epoch(train) [181][50/293] lr: 5.000000e-05 eta: 1:02:32 time: 0.522927 data_time: 0.088765 memory: 9871 loss_kpt: 0.000564 acc_pose: 0.868699 loss: 0.000564 2022/09/08 20:43:47 - mmengine - INFO - Epoch(train) [181][100/293] lr: 5.000000e-05 eta: 1:02:11 time: 0.492626 data_time: 0.070676 memory: 9871 loss_kpt: 0.000558 acc_pose: 0.878595 loss: 0.000558 2022/09/08 20:44:13 - mmengine - INFO - Epoch(train) [181][150/293] lr: 5.000000e-05 eta: 1:01:50 time: 0.506931 data_time: 0.073509 memory: 9871 loss_kpt: 0.000558 acc_pose: 0.901118 loss: 0.000558 2022/09/08 20:44:38 - mmengine - INFO - Epoch(train) [181][200/293] lr: 5.000000e-05 eta: 1:01:29 time: 0.498519 data_time: 0.075646 memory: 9871 loss_kpt: 0.000561 acc_pose: 0.892076 loss: 0.000561 2022/09/08 20:45:02 - mmengine - INFO - Epoch(train) [181][250/293] lr: 5.000000e-05 eta: 1:01:08 time: 0.491115 data_time: 0.077663 memory: 9871 loss_kpt: 0.000564 acc_pose: 0.836193 loss: 0.000564 2022/09/08 20:45:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 20:45:24 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 20:45:24 - mmengine - INFO - Saving checkpoint at 181 epochs 2022/09/08 20:45:53 - mmengine - INFO - Epoch(train) [182][50/293] lr: 5.000000e-05 eta: 1:00:26 time: 0.497560 data_time: 0.080977 memory: 9871 loss_kpt: 0.000547 acc_pose: 0.858821 loss: 0.000547 2022/09/08 20:46:18 - mmengine - INFO - Epoch(train) [182][100/293] lr: 5.000000e-05 eta: 1:00:05 time: 0.497362 data_time: 0.073640 memory: 9871 loss_kpt: 0.000553 acc_pose: 0.850536 loss: 0.000553 2022/09/08 20:46:43 - mmengine - INFO - Epoch(train) [182][150/293] lr: 5.000000e-05 eta: 0:59:44 time: 0.497492 data_time: 0.081194 memory: 9871 loss_kpt: 0.000568 acc_pose: 0.834718 loss: 0.000568 2022/09/08 20:47:07 - mmengine - INFO - Epoch(train) [182][200/293] lr: 5.000000e-05 eta: 0:59:23 time: 0.496177 data_time: 0.072876 memory: 9871 loss_kpt: 0.000570 acc_pose: 0.852483 loss: 0.000570 2022/09/08 20:47:33 - mmengine - INFO - Epoch(train) [182][250/293] lr: 5.000000e-05 eta: 0:59:02 time: 0.504414 data_time: 0.072490 memory: 9871 loss_kpt: 0.000558 acc_pose: 0.859527 loss: 0.000558 2022/09/08 20:47:54 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 20:47:54 - mmengine - INFO - Saving checkpoint at 182 epochs 2022/09/08 20:48:23 - mmengine - INFO - Epoch(train) [183][50/293] lr: 5.000000e-05 eta: 0:58:20 time: 0.498815 data_time: 0.086748 memory: 9871 loss_kpt: 0.000576 acc_pose: 0.911916 loss: 0.000576 2022/09/08 20:48:48 - mmengine - INFO - Epoch(train) [183][100/293] lr: 5.000000e-05 eta: 0:57:59 time: 0.494898 data_time: 0.072666 memory: 9871 loss_kpt: 0.000563 acc_pose: 0.840078 loss: 0.000563 2022/09/08 20:49:13 - mmengine - INFO - Epoch(train) [183][150/293] lr: 5.000000e-05 eta: 0:57:38 time: 0.504215 data_time: 0.085251 memory: 9871 loss_kpt: 0.000573 acc_pose: 0.838112 loss: 0.000573 2022/09/08 20:49:38 - mmengine - INFO - Epoch(train) [183][200/293] lr: 5.000000e-05 eta: 0:57:17 time: 0.510869 data_time: 0.077435 memory: 9871 loss_kpt: 0.000564 acc_pose: 0.884457 loss: 0.000564 2022/09/08 20:50:03 - mmengine - INFO - Epoch(train) [183][250/293] lr: 5.000000e-05 eta: 0:56:56 time: 0.496337 data_time: 0.076572 memory: 9871 loss_kpt: 0.000569 acc_pose: 0.844298 loss: 0.000569 2022/09/08 20:50:24 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 20:50:24 - mmengine - INFO - Saving checkpoint at 183 epochs 2022/09/08 20:50:54 - mmengine - INFO - Epoch(train) [184][50/293] lr: 5.000000e-05 eta: 0:56:14 time: 0.513253 data_time: 0.088131 memory: 9871 loss_kpt: 0.000564 acc_pose: 0.869756 loss: 0.000564 2022/09/08 20:51:19 - mmengine - INFO - Epoch(train) [184][100/293] lr: 5.000000e-05 eta: 0:55:53 time: 0.492485 data_time: 0.075956 memory: 9871 loss_kpt: 0.000577 acc_pose: 0.855028 loss: 0.000577 2022/09/08 20:51:45 - mmengine - INFO - Epoch(train) [184][150/293] lr: 5.000000e-05 eta: 0:55:33 time: 0.515457 data_time: 0.087697 memory: 9871 loss_kpt: 0.000560 acc_pose: 0.843155 loss: 0.000560 2022/09/08 20:52:09 - mmengine - INFO - Epoch(train) [184][200/293] lr: 5.000000e-05 eta: 0:55:12 time: 0.490682 data_time: 0.072902 memory: 9871 loss_kpt: 0.000570 acc_pose: 0.850108 loss: 0.000570 2022/09/08 20:52:35 - mmengine - INFO - Epoch(train) [184][250/293] lr: 5.000000e-05 eta: 0:54:51 time: 0.506360 data_time: 0.074708 memory: 9871 loss_kpt: 0.000563 acc_pose: 0.869485 loss: 0.000563 2022/09/08 20:52:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 20:52:56 - mmengine - INFO - Saving checkpoint at 184 epochs 2022/09/08 20:53:26 - mmengine - INFO - Epoch(train) [185][50/293] lr: 5.000000e-05 eta: 0:54:09 time: 0.509954 data_time: 0.087557 memory: 9871 loss_kpt: 0.000567 acc_pose: 0.838203 loss: 0.000567 2022/09/08 20:53:45 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 20:53:51 - mmengine - INFO - Epoch(train) [185][100/293] lr: 5.000000e-05 eta: 0:53:48 time: 0.500806 data_time: 0.070190 memory: 9871 loss_kpt: 0.000552 acc_pose: 0.849615 loss: 0.000552 2022/09/08 20:54:17 - mmengine - INFO - Epoch(train) [185][150/293] lr: 5.000000e-05 eta: 0:53:27 time: 0.508585 data_time: 0.073955 memory: 9871 loss_kpt: 0.000568 acc_pose: 0.859761 loss: 0.000568 2022/09/08 20:54:42 - mmengine - INFO - Epoch(train) [185][200/293] lr: 5.000000e-05 eta: 0:53:06 time: 0.500328 data_time: 0.071777 memory: 9871 loss_kpt: 0.000572 acc_pose: 0.874211 loss: 0.000572 2022/09/08 20:55:07 - mmengine - INFO - Epoch(train) [185][250/293] lr: 5.000000e-05 eta: 0:52:45 time: 0.494157 data_time: 0.070482 memory: 9871 loss_kpt: 0.000562 acc_pose: 0.862477 loss: 0.000562 2022/09/08 20:55:28 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 20:55:28 - mmengine - INFO - Saving checkpoint at 185 epochs 2022/09/08 20:55:58 - mmengine - INFO - Epoch(train) [186][50/293] lr: 5.000000e-05 eta: 0:52:03 time: 0.508047 data_time: 0.078895 memory: 9871 loss_kpt: 0.000554 acc_pose: 0.847271 loss: 0.000554 2022/09/08 20:56:22 - mmengine - INFO - Epoch(train) [186][100/293] lr: 5.000000e-05 eta: 0:51:42 time: 0.488591 data_time: 0.077200 memory: 9871 loss_kpt: 0.000559 acc_pose: 0.829500 loss: 0.000559 2022/09/08 20:56:48 - mmengine - INFO - Epoch(train) [186][150/293] lr: 5.000000e-05 eta: 0:51:21 time: 0.516812 data_time: 0.078757 memory: 9871 loss_kpt: 0.000569 acc_pose: 0.839523 loss: 0.000569 2022/09/08 20:57:13 - mmengine - INFO - Epoch(train) [186][200/293] lr: 5.000000e-05 eta: 0:51:00 time: 0.496470 data_time: 0.077892 memory: 9871 loss_kpt: 0.000550 acc_pose: 0.847361 loss: 0.000550 2022/09/08 20:57:37 - mmengine - INFO - Epoch(train) [186][250/293] lr: 5.000000e-05 eta: 0:50:39 time: 0.491091 data_time: 0.080992 memory: 9871 loss_kpt: 0.000564 acc_pose: 0.861944 loss: 0.000564 2022/09/08 20:57:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 20:57:59 - mmengine - INFO - Saving checkpoint at 186 epochs 2022/09/08 20:58:29 - mmengine - INFO - Epoch(train) [187][50/293] lr: 5.000000e-05 eta: 0:49:57 time: 0.510509 data_time: 0.084748 memory: 9871 loss_kpt: 0.000555 acc_pose: 0.861064 loss: 0.000555 2022/09/08 20:58:54 - mmengine - INFO - Epoch(train) [187][100/293] lr: 5.000000e-05 eta: 0:49:36 time: 0.512888 data_time: 0.082273 memory: 9871 loss_kpt: 0.000559 acc_pose: 0.824859 loss: 0.000559 2022/09/08 20:59:19 - mmengine - INFO - Epoch(train) [187][150/293] lr: 5.000000e-05 eta: 0:49:15 time: 0.493778 data_time: 0.076178 memory: 9871 loss_kpt: 0.000553 acc_pose: 0.819002 loss: 0.000553 2022/09/08 20:59:44 - mmengine - INFO - Epoch(train) [187][200/293] lr: 5.000000e-05 eta: 0:48:54 time: 0.488588 data_time: 0.073899 memory: 9871 loss_kpt: 0.000552 acc_pose: 0.886428 loss: 0.000552 2022/09/08 21:00:09 - mmengine - INFO - Epoch(train) [187][250/293] lr: 5.000000e-05 eta: 0:48:33 time: 0.504297 data_time: 0.079222 memory: 9871 loss_kpt: 0.000551 acc_pose: 0.835422 loss: 0.000551 2022/09/08 21:00:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 21:00:30 - mmengine - INFO - Saving checkpoint at 187 epochs 2022/09/08 21:01:00 - mmengine - INFO - Epoch(train) [188][50/293] lr: 5.000000e-05 eta: 0:47:51 time: 0.502204 data_time: 0.082941 memory: 9871 loss_kpt: 0.000549 acc_pose: 0.833412 loss: 0.000549 2022/09/08 21:01:25 - mmengine - INFO - Epoch(train) [188][100/293] lr: 5.000000e-05 eta: 0:47:30 time: 0.498541 data_time: 0.077439 memory: 9871 loss_kpt: 0.000560 acc_pose: 0.847725 loss: 0.000560 2022/09/08 21:01:49 - mmengine - INFO - Epoch(train) [188][150/293] lr: 5.000000e-05 eta: 0:47:09 time: 0.488338 data_time: 0.074370 memory: 9871 loss_kpt: 0.000540 acc_pose: 0.835330 loss: 0.000540 2022/09/08 21:02:13 - mmengine - INFO - Epoch(train) [188][200/293] lr: 5.000000e-05 eta: 0:46:48 time: 0.486249 data_time: 0.076549 memory: 9871 loss_kpt: 0.000556 acc_pose: 0.853304 loss: 0.000556 2022/09/08 21:02:18 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 21:02:38 - mmengine - INFO - Epoch(train) [188][250/293] lr: 5.000000e-05 eta: 0:46:27 time: 0.496696 data_time: 0.080187 memory: 9871 loss_kpt: 0.000564 acc_pose: 0.857596 loss: 0.000564 2022/09/08 21:03:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 21:03:00 - mmengine - INFO - Saving checkpoint at 188 epochs 2022/09/08 21:03:29 - mmengine - INFO - Epoch(train) [189][50/293] lr: 5.000000e-05 eta: 0:45:45 time: 0.511930 data_time: 0.083031 memory: 9871 loss_kpt: 0.000551 acc_pose: 0.869278 loss: 0.000551 2022/09/08 21:03:54 - mmengine - INFO - Epoch(train) [189][100/293] lr: 5.000000e-05 eta: 0:45:24 time: 0.496758 data_time: 0.076107 memory: 9871 loss_kpt: 0.000559 acc_pose: 0.850941 loss: 0.000559 2022/09/08 21:04:19 - mmengine - INFO - Epoch(train) [189][150/293] lr: 5.000000e-05 eta: 0:45:03 time: 0.492555 data_time: 0.072996 memory: 9871 loss_kpt: 0.000565 acc_pose: 0.829024 loss: 0.000565 2022/09/08 21:04:43 - mmengine - INFO - Epoch(train) [189][200/293] lr: 5.000000e-05 eta: 0:44:42 time: 0.488384 data_time: 0.075799 memory: 9871 loss_kpt: 0.000564 acc_pose: 0.861927 loss: 0.000564 2022/09/08 21:05:09 - mmengine - INFO - Epoch(train) [189][250/293] lr: 5.000000e-05 eta: 0:44:21 time: 0.515307 data_time: 0.080450 memory: 9871 loss_kpt: 0.000554 acc_pose: 0.867411 loss: 0.000554 2022/09/08 21:05:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 21:05:30 - mmengine - INFO - Saving checkpoint at 189 epochs 2022/09/08 21:06:00 - mmengine - INFO - Epoch(train) [190][50/293] lr: 5.000000e-05 eta: 0:43:39 time: 0.509872 data_time: 0.084789 memory: 9871 loss_kpt: 0.000568 acc_pose: 0.845624 loss: 0.000568 2022/09/08 21:06:25 - mmengine - INFO - Epoch(train) [190][100/293] lr: 5.000000e-05 eta: 0:43:18 time: 0.493084 data_time: 0.073308 memory: 9871 loss_kpt: 0.000553 acc_pose: 0.878561 loss: 0.000553 2022/09/08 21:06:51 - mmengine - INFO - Epoch(train) [190][150/293] lr: 5.000000e-05 eta: 0:42:57 time: 0.523832 data_time: 0.076491 memory: 9871 loss_kpt: 0.000575 acc_pose: 0.861212 loss: 0.000575 2022/09/08 21:07:15 - mmengine - INFO - Epoch(train) [190][200/293] lr: 5.000000e-05 eta: 0:42:36 time: 0.491745 data_time: 0.076936 memory: 9871 loss_kpt: 0.000568 acc_pose: 0.840977 loss: 0.000568 2022/09/08 21:07:40 - mmengine - INFO - Epoch(train) [190][250/293] lr: 5.000000e-05 eta: 0:42:15 time: 0.497509 data_time: 0.082193 memory: 9871 loss_kpt: 0.000558 acc_pose: 0.852711 loss: 0.000558 2022/09/08 21:08:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 21:08:02 - mmengine - INFO - Saving checkpoint at 190 epochs 2022/09/08 21:08:13 - mmengine - INFO - Epoch(val) [190][50/407] eta: 0:00:43 time: 0.120762 data_time: 0.016600 memory: 9871 2022/09/08 21:08:19 - mmengine - INFO - Epoch(val) [190][100/407] eta: 0:00:36 time: 0.118416 data_time: 0.013589 memory: 920 2022/09/08 21:08:24 - mmengine - INFO - Epoch(val) [190][150/407] eta: 0:00:30 time: 0.117661 data_time: 0.013377 memory: 920 2022/09/08 21:08:30 - mmengine - INFO - Epoch(val) [190][200/407] eta: 0:00:24 time: 0.117234 data_time: 0.012094 memory: 920 2022/09/08 21:08:36 - mmengine - INFO - Epoch(val) [190][250/407] eta: 0:00:18 time: 0.119662 data_time: 0.013496 memory: 920 2022/09/08 21:08:42 - mmengine - INFO - Epoch(val) [190][300/407] eta: 0:00:12 time: 0.113410 data_time: 0.009947 memory: 920 2022/09/08 21:08:48 - mmengine - INFO - Epoch(val) [190][350/407] eta: 0:00:06 time: 0.120310 data_time: 0.014104 memory: 920 2022/09/08 21:08:53 - mmengine - INFO - Epoch(val) [190][400/407] eta: 0:00:00 time: 0.109500 data_time: 0.007707 memory: 920 2022/09/08 21:09:28 - mmengine - INFO - Evaluating CocoMetric... 2022/09/08 21:09:41 - mmengine - INFO - Epoch(val) [190][407/407] coco/AP: 0.746888 coco/AP .5: 0.905779 coco/AP .75: 0.820140 coco/AP (M): 0.711481 coco/AP (L): 0.813294 coco/AR: 0.800630 coco/AR .5: 0.942695 coco/AR .75: 0.864767 coco/AR (M): 0.758700 coco/AR (L): 0.861353 2022/09/08 21:09:41 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220908/hrnet_w32_256/best_coco/AP_epoch_180.pth is removed 2022/09/08 21:09:44 - mmengine - INFO - The best checkpoint with 0.7469 coco/AP at 190 epoch is saved to best_coco/AP_epoch_190.pth. 2022/09/08 21:10:10 - mmengine - INFO - Epoch(train) [191][50/293] lr: 5.000000e-05 eta: 0:41:33 time: 0.514986 data_time: 0.092511 memory: 9871 loss_kpt: 0.000556 acc_pose: 0.866883 loss: 0.000556 2022/09/08 21:10:35 - mmengine - INFO - Epoch(train) [191][100/293] lr: 5.000000e-05 eta: 0:41:12 time: 0.489965 data_time: 0.073799 memory: 9871 loss_kpt: 0.000564 acc_pose: 0.820818 loss: 0.000564 2022/09/08 21:10:59 - mmengine - INFO - Epoch(train) [191][150/293] lr: 5.000000e-05 eta: 0:40:51 time: 0.494671 data_time: 0.077630 memory: 9871 loss_kpt: 0.000551 acc_pose: 0.861471 loss: 0.000551 2022/09/08 21:11:25 - mmengine - INFO - Epoch(train) [191][200/293] lr: 5.000000e-05 eta: 0:40:30 time: 0.508447 data_time: 0.077926 memory: 9871 loss_kpt: 0.000565 acc_pose: 0.837918 loss: 0.000565 2022/09/08 21:11:50 - mmengine - INFO - Epoch(train) [191][250/293] lr: 5.000000e-05 eta: 0:40:09 time: 0.498506 data_time: 0.078009 memory: 9871 loss_kpt: 0.000553 acc_pose: 0.844899 loss: 0.000553 2022/09/08 21:12:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 21:12:11 - mmengine - INFO - Saving checkpoint at 191 epochs 2022/09/08 21:12:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 21:12:41 - mmengine - INFO - Epoch(train) [192][50/293] lr: 5.000000e-05 eta: 0:39:28 time: 0.513919 data_time: 0.091798 memory: 9871 loss_kpt: 0.000572 acc_pose: 0.868107 loss: 0.000572 2022/09/08 21:13:06 - mmengine - INFO - Epoch(train) [192][100/293] lr: 5.000000e-05 eta: 0:39:07 time: 0.494769 data_time: 0.077318 memory: 9871 loss_kpt: 0.000573 acc_pose: 0.817940 loss: 0.000573 2022/09/08 21:13:31 - mmengine - INFO - Epoch(train) [192][150/293] lr: 5.000000e-05 eta: 0:38:45 time: 0.495987 data_time: 0.081759 memory: 9871 loss_kpt: 0.000555 acc_pose: 0.854135 loss: 0.000555 2022/09/08 21:13:55 - mmengine - INFO - Epoch(train) [192][200/293] lr: 5.000000e-05 eta: 0:38:24 time: 0.491187 data_time: 0.077566 memory: 9871 loss_kpt: 0.000565 acc_pose: 0.856183 loss: 0.000565 2022/09/08 21:14:20 - mmengine - INFO - Epoch(train) [192][250/293] lr: 5.000000e-05 eta: 0:38:03 time: 0.501563 data_time: 0.074430 memory: 9871 loss_kpt: 0.000562 acc_pose: 0.836380 loss: 0.000562 2022/09/08 21:14:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 21:14:42 - mmengine - INFO - Saving checkpoint at 192 epochs 2022/09/08 21:15:11 - mmengine - INFO - Epoch(train) [193][50/293] lr: 5.000000e-05 eta: 0:37:22 time: 0.505002 data_time: 0.078028 memory: 9871 loss_kpt: 0.000559 acc_pose: 0.853334 loss: 0.000559 2022/09/08 21:15:36 - mmengine - INFO - Epoch(train) [193][100/293] lr: 5.000000e-05 eta: 0:37:01 time: 0.499396 data_time: 0.076469 memory: 9871 loss_kpt: 0.000564 acc_pose: 0.851668 loss: 0.000564 2022/09/08 21:16:02 - mmengine - INFO - Epoch(train) [193][150/293] lr: 5.000000e-05 eta: 0:36:40 time: 0.504459 data_time: 0.076195 memory: 9871 loss_kpt: 0.000567 acc_pose: 0.857894 loss: 0.000567 2022/09/08 21:16:27 - mmengine - INFO - Epoch(train) [193][200/293] lr: 5.000000e-05 eta: 0:36:18 time: 0.504391 data_time: 0.077122 memory: 9871 loss_kpt: 0.000569 acc_pose: 0.851295 loss: 0.000569 2022/09/08 21:16:51 - mmengine - INFO - Epoch(train) [193][250/293] lr: 5.000000e-05 eta: 0:35:57 time: 0.486442 data_time: 0.075400 memory: 9871 loss_kpt: 0.000562 acc_pose: 0.844810 loss: 0.000562 2022/09/08 21:17:12 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 21:17:12 - mmengine - INFO - Saving checkpoint at 193 epochs 2022/09/08 21:17:42 - mmengine - INFO - Epoch(train) [194][50/293] lr: 5.000000e-05 eta: 0:35:16 time: 0.514894 data_time: 0.085849 memory: 9871 loss_kpt: 0.000557 acc_pose: 0.804418 loss: 0.000557 2022/09/08 21:18:07 - mmengine - INFO - Epoch(train) [194][100/293] lr: 5.000000e-05 eta: 0:34:55 time: 0.501007 data_time: 0.085014 memory: 9871 loss_kpt: 0.000555 acc_pose: 0.846926 loss: 0.000555 2022/09/08 21:18:32 - mmengine - INFO - Epoch(train) [194][150/293] lr: 5.000000e-05 eta: 0:34:34 time: 0.499666 data_time: 0.079600 memory: 9871 loss_kpt: 0.000569 acc_pose: 0.842784 loss: 0.000569 2022/09/08 21:18:57 - mmengine - INFO - Epoch(train) [194][200/293] lr: 5.000000e-05 eta: 0:34:12 time: 0.492373 data_time: 0.073248 memory: 9871 loss_kpt: 0.000563 acc_pose: 0.841955 loss: 0.000563 2022/09/08 21:19:23 - mmengine - INFO - Epoch(train) [194][250/293] lr: 5.000000e-05 eta: 0:33:51 time: 0.509516 data_time: 0.083147 memory: 9871 loss_kpt: 0.000568 acc_pose: 0.859134 loss: 0.000568 2022/09/08 21:19:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 21:19:44 - mmengine - INFO - Saving checkpoint at 194 epochs 2022/09/08 21:20:14 - mmengine - INFO - Epoch(train) [195][50/293] lr: 5.000000e-05 eta: 0:33:10 time: 0.503234 data_time: 0.083769 memory: 9871 loss_kpt: 0.000558 acc_pose: 0.828018 loss: 0.000558 2022/09/08 21:20:39 - mmengine - INFO - Epoch(train) [195][100/293] lr: 5.000000e-05 eta: 0:32:49 time: 0.497642 data_time: 0.081948 memory: 9871 loss_kpt: 0.000558 acc_pose: 0.856830 loss: 0.000558 2022/09/08 21:21:04 - mmengine - INFO - Epoch(train) [195][150/293] lr: 5.000000e-05 eta: 0:32:28 time: 0.507785 data_time: 0.079219 memory: 9871 loss_kpt: 0.000554 acc_pose: 0.875921 loss: 0.000554 2022/09/08 21:21:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 21:21:30 - mmengine - INFO - Epoch(train) [195][200/293] lr: 5.000000e-05 eta: 0:32:07 time: 0.514024 data_time: 0.078148 memory: 9871 loss_kpt: 0.000551 acc_pose: 0.852212 loss: 0.000551 2022/09/08 21:21:55 - mmengine - INFO - Epoch(train) [195][250/293] lr: 5.000000e-05 eta: 0:31:46 time: 0.498401 data_time: 0.076993 memory: 9871 loss_kpt: 0.000550 acc_pose: 0.871034 loss: 0.000550 2022/09/08 21:22:16 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 21:22:16 - mmengine - INFO - Saving checkpoint at 195 epochs 2022/09/08 21:22:46 - mmengine - INFO - Epoch(train) [196][50/293] lr: 5.000000e-05 eta: 0:31:04 time: 0.510691 data_time: 0.086389 memory: 9871 loss_kpt: 0.000558 acc_pose: 0.843285 loss: 0.000558 2022/09/08 21:23:11 - mmengine - INFO - Epoch(train) [196][100/293] lr: 5.000000e-05 eta: 0:30:43 time: 0.498098 data_time: 0.078509 memory: 9871 loss_kpt: 0.000553 acc_pose: 0.854892 loss: 0.000553 2022/09/08 21:23:36 - mmengine - INFO - Epoch(train) [196][150/293] lr: 5.000000e-05 eta: 0:30:22 time: 0.503110 data_time: 0.075427 memory: 9871 loss_kpt: 0.000560 acc_pose: 0.861816 loss: 0.000560 2022/09/08 21:24:01 - mmengine - INFO - Epoch(train) [196][200/293] lr: 5.000000e-05 eta: 0:30:01 time: 0.500987 data_time: 0.073510 memory: 9871 loss_kpt: 0.000560 acc_pose: 0.802173 loss: 0.000560 2022/09/08 21:24:26 - mmengine - INFO - Epoch(train) [196][250/293] lr: 5.000000e-05 eta: 0:29:40 time: 0.506906 data_time: 0.088157 memory: 9871 loss_kpt: 0.000550 acc_pose: 0.887393 loss: 0.000550 2022/09/08 21:24:48 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 21:24:48 - mmengine - INFO - Saving checkpoint at 196 epochs 2022/09/08 21:25:18 - mmengine - INFO - Epoch(train) [197][50/293] lr: 5.000000e-05 eta: 0:28:59 time: 0.510484 data_time: 0.088793 memory: 9871 loss_kpt: 0.000554 acc_pose: 0.864087 loss: 0.000554 2022/09/08 21:25:43 - mmengine - INFO - Epoch(train) [197][100/293] lr: 5.000000e-05 eta: 0:28:38 time: 0.511169 data_time: 0.079655 memory: 9871 loss_kpt: 0.000568 acc_pose: 0.868322 loss: 0.000568 2022/09/08 21:26:08 - mmengine - INFO - Epoch(train) [197][150/293] lr: 5.000000e-05 eta: 0:28:16 time: 0.485533 data_time: 0.072779 memory: 9871 loss_kpt: 0.000571 acc_pose: 0.851195 loss: 0.000571 2022/09/08 21:26:33 - mmengine - INFO - Epoch(train) [197][200/293] lr: 5.000000e-05 eta: 0:27:55 time: 0.506493 data_time: 0.080950 memory: 9871 loss_kpt: 0.000559 acc_pose: 0.822943 loss: 0.000559 2022/09/08 21:26:58 - mmengine - INFO - Epoch(train) [197][250/293] lr: 5.000000e-05 eta: 0:27:34 time: 0.493073 data_time: 0.073958 memory: 9871 loss_kpt: 0.000562 acc_pose: 0.830306 loss: 0.000562 2022/09/08 21:27:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 21:27:19 - mmengine - INFO - Saving checkpoint at 197 epochs 2022/09/08 21:27:49 - mmengine - INFO - Epoch(train) [198][50/293] lr: 5.000000e-05 eta: 0:26:53 time: 0.518506 data_time: 0.088827 memory: 9871 loss_kpt: 0.000568 acc_pose: 0.830618 loss: 0.000568 2022/09/08 21:28:14 - mmengine - INFO - Epoch(train) [198][100/293] lr: 5.000000e-05 eta: 0:26:32 time: 0.497789 data_time: 0.074081 memory: 9871 loss_kpt: 0.000554 acc_pose: 0.876950 loss: 0.000554 2022/09/08 21:28:39 - mmengine - INFO - Epoch(train) [198][150/293] lr: 5.000000e-05 eta: 0:26:10 time: 0.489900 data_time: 0.076075 memory: 9871 loss_kpt: 0.000548 acc_pose: 0.833676 loss: 0.000548 2022/09/08 21:29:04 - mmengine - INFO - Epoch(train) [198][200/293] lr: 5.000000e-05 eta: 0:25:49 time: 0.511357 data_time: 0.075538 memory: 9871 loss_kpt: 0.000555 acc_pose: 0.867937 loss: 0.000555 2022/09/08 21:29:29 - mmengine - INFO - Epoch(train) [198][250/293] lr: 5.000000e-05 eta: 0:25:28 time: 0.506936 data_time: 0.077041 memory: 9871 loss_kpt: 0.000547 acc_pose: 0.842621 loss: 0.000547 2022/09/08 21:29:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 21:29:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 21:29:50 - mmengine - INFO - Saving checkpoint at 198 epochs 2022/09/08 21:30:21 - mmengine - INFO - Epoch(train) [199][50/293] lr: 5.000000e-05 eta: 0:24:47 time: 0.516762 data_time: 0.084006 memory: 9871 loss_kpt: 0.000568 acc_pose: 0.867663 loss: 0.000568 2022/09/08 21:30:45 - mmengine - INFO - Epoch(train) [199][100/293] lr: 5.000000e-05 eta: 0:24:26 time: 0.486659 data_time: 0.071503 memory: 9871 loss_kpt: 0.000546 acc_pose: 0.858983 loss: 0.000546 2022/09/08 21:31:10 - mmengine - INFO - Epoch(train) [199][150/293] lr: 5.000000e-05 eta: 0:24:05 time: 0.502987 data_time: 0.076487 memory: 9871 loss_kpt: 0.000556 acc_pose: 0.862669 loss: 0.000556 2022/09/08 21:31:35 - mmengine - INFO - Epoch(train) [199][200/293] lr: 5.000000e-05 eta: 0:23:43 time: 0.500734 data_time: 0.073683 memory: 9871 loss_kpt: 0.000562 acc_pose: 0.876333 loss: 0.000562 2022/09/08 21:32:01 - mmengine - INFO - Epoch(train) [199][250/293] lr: 5.000000e-05 eta: 0:23:22 time: 0.508846 data_time: 0.073369 memory: 9871 loss_kpt: 0.000566 acc_pose: 0.870458 loss: 0.000566 2022/09/08 21:32:22 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 21:32:22 - mmengine - INFO - Saving checkpoint at 199 epochs 2022/09/08 21:32:53 - mmengine - INFO - Epoch(train) [200][50/293] lr: 5.000000e-05 eta: 0:22:41 time: 0.524607 data_time: 0.092333 memory: 9871 loss_kpt: 0.000561 acc_pose: 0.837370 loss: 0.000561 2022/09/08 21:33:18 - mmengine - INFO - Epoch(train) [200][100/293] lr: 5.000000e-05 eta: 0:22:20 time: 0.503407 data_time: 0.076788 memory: 9871 loss_kpt: 0.000555 acc_pose: 0.900998 loss: 0.000555 2022/09/08 21:33:43 - mmengine - INFO - Epoch(train) [200][150/293] lr: 5.000000e-05 eta: 0:21:59 time: 0.499799 data_time: 0.077063 memory: 9871 loss_kpt: 0.000554 acc_pose: 0.861229 loss: 0.000554 2022/09/08 21:34:08 - mmengine - INFO - Epoch(train) [200][200/293] lr: 5.000000e-05 eta: 0:21:38 time: 0.493913 data_time: 0.077117 memory: 9871 loss_kpt: 0.000559 acc_pose: 0.862675 loss: 0.000559 2022/09/08 21:34:32 - mmengine - INFO - Epoch(train) [200][250/293] lr: 5.000000e-05 eta: 0:21:16 time: 0.497288 data_time: 0.080714 memory: 9871 loss_kpt: 0.000552 acc_pose: 0.877592 loss: 0.000552 2022/09/08 21:34:54 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 21:34:54 - mmengine - INFO - Saving checkpoint at 200 epochs 2022/09/08 21:35:05 - mmengine - INFO - Epoch(val) [200][50/407] eta: 0:00:44 time: 0.123698 data_time: 0.015898 memory: 9871 2022/09/08 21:35:11 - mmengine - INFO - Epoch(val) [200][100/407] eta: 0:00:35 time: 0.115718 data_time: 0.010180 memory: 920 2022/09/08 21:35:17 - mmengine - INFO - Epoch(val) [200][150/407] eta: 0:00:28 time: 0.111555 data_time: 0.008408 memory: 920 2022/09/08 21:35:22 - mmengine - INFO - Epoch(val) [200][200/407] eta: 0:00:23 time: 0.115709 data_time: 0.011026 memory: 920 2022/09/08 21:35:28 - mmengine - INFO - Epoch(val) [200][250/407] eta: 0:00:17 time: 0.112563 data_time: 0.008529 memory: 920 2022/09/08 21:35:34 - mmengine - INFO - Epoch(val) [200][300/407] eta: 0:00:12 time: 0.120249 data_time: 0.015916 memory: 920 2022/09/08 21:35:40 - mmengine - INFO - Epoch(val) [200][350/407] eta: 0:00:06 time: 0.117816 data_time: 0.011866 memory: 920 2022/09/08 21:35:46 - mmengine - INFO - Epoch(val) [200][400/407] eta: 0:00:00 time: 0.115306 data_time: 0.012835 memory: 920 2022/09/08 21:36:20 - mmengine - INFO - Evaluating CocoMetric... 2022/09/08 21:36:33 - mmengine - INFO - Epoch(val) [200][407/407] coco/AP: 0.748990 coco/AP .5: 0.906337 coco/AP .75: 0.821018 coco/AP (M): 0.714182 coco/AP (L): 0.815710 coco/AR: 0.803763 coco/AR .5: 0.945057 coco/AR .75: 0.867128 coco/AR (M): 0.762333 coco/AR (L): 0.863768 2022/09/08 21:36:34 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220908/hrnet_w32_256/best_coco/AP_epoch_190.pth is removed 2022/09/08 21:36:36 - mmengine - INFO - The best checkpoint with 0.7490 coco/AP at 200 epoch is saved to best_coco/AP_epoch_200.pth. 2022/09/08 21:37:02 - mmengine - INFO - Epoch(train) [201][50/293] lr: 5.000000e-06 eta: 0:20:36 time: 0.516102 data_time: 0.090357 memory: 9871 loss_kpt: 0.000565 acc_pose: 0.878022 loss: 0.000565 2022/09/08 21:37:27 - mmengine - INFO - Epoch(train) [201][100/293] lr: 5.000000e-06 eta: 0:20:14 time: 0.497669 data_time: 0.071229 memory: 9871 loss_kpt: 0.000569 acc_pose: 0.879776 loss: 0.000569 2022/09/08 21:37:52 - mmengine - INFO - Epoch(train) [201][150/293] lr: 5.000000e-06 eta: 0:19:53 time: 0.500683 data_time: 0.080417 memory: 9871 loss_kpt: 0.000569 acc_pose: 0.854475 loss: 0.000569 2022/09/08 21:38:18 - mmengine - INFO - Epoch(train) [201][200/293] lr: 5.000000e-06 eta: 0:19:32 time: 0.506453 data_time: 0.082481 memory: 9871 loss_kpt: 0.000553 acc_pose: 0.878055 loss: 0.000553 2022/09/08 21:38:42 - mmengine - INFO - Epoch(train) [201][250/293] lr: 5.000000e-06 eta: 0:19:11 time: 0.498143 data_time: 0.076481 memory: 9871 loss_kpt: 0.000546 acc_pose: 0.848602 loss: 0.000546 2022/09/08 21:39:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 21:39:04 - mmengine - INFO - Saving checkpoint at 201 epochs 2022/09/08 21:39:34 - mmengine - INFO - Epoch(train) [202][50/293] lr: 5.000000e-06 eta: 0:18:30 time: 0.514403 data_time: 0.085358 memory: 9871 loss_kpt: 0.000559 acc_pose: 0.892773 loss: 0.000559 2022/09/08 21:39:59 - mmengine - INFO - Epoch(train) [202][100/293] lr: 5.000000e-06 eta: 0:18:09 time: 0.497046 data_time: 0.082909 memory: 9871 loss_kpt: 0.000568 acc_pose: 0.864380 loss: 0.000568 2022/09/08 21:40:03 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 21:40:24 - mmengine - INFO - Epoch(train) [202][150/293] lr: 5.000000e-06 eta: 0:17:47 time: 0.501500 data_time: 0.079379 memory: 9871 loss_kpt: 0.000553 acc_pose: 0.877143 loss: 0.000553 2022/09/08 21:40:49 - mmengine - INFO - Epoch(train) [202][200/293] lr: 5.000000e-06 eta: 0:17:26 time: 0.500035 data_time: 0.080460 memory: 9871 loss_kpt: 0.000547 acc_pose: 0.893350 loss: 0.000547 2022/09/08 21:41:14 - mmengine - INFO - Epoch(train) [202][250/293] lr: 5.000000e-06 eta: 0:17:05 time: 0.494250 data_time: 0.073219 memory: 9871 loss_kpt: 0.000550 acc_pose: 0.817476 loss: 0.000550 2022/09/08 21:41:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 21:41:35 - mmengine - INFO - Saving checkpoint at 202 epochs 2022/09/08 21:42:05 - mmengine - INFO - Epoch(train) [203][50/293] lr: 5.000000e-06 eta: 0:16:24 time: 0.509013 data_time: 0.088047 memory: 9871 loss_kpt: 0.000553 acc_pose: 0.835441 loss: 0.000553 2022/09/08 21:42:30 - mmengine - INFO - Epoch(train) [203][100/293] lr: 5.000000e-06 eta: 0:16:03 time: 0.496254 data_time: 0.081960 memory: 9871 loss_kpt: 0.000559 acc_pose: 0.831060 loss: 0.000559 2022/09/08 21:42:55 - mmengine - INFO - Epoch(train) [203][150/293] lr: 5.000000e-06 eta: 0:15:41 time: 0.499722 data_time: 0.072938 memory: 9871 loss_kpt: 0.000540 acc_pose: 0.858629 loss: 0.000540 2022/09/08 21:43:20 - mmengine - INFO - Epoch(train) [203][200/293] lr: 5.000000e-06 eta: 0:15:20 time: 0.491890 data_time: 0.078983 memory: 9871 loss_kpt: 0.000544 acc_pose: 0.859802 loss: 0.000544 2022/09/08 21:43:44 - mmengine - INFO - Epoch(train) [203][250/293] lr: 5.000000e-06 eta: 0:14:59 time: 0.494334 data_time: 0.079384 memory: 9871 loss_kpt: 0.000566 acc_pose: 0.872808 loss: 0.000566 2022/09/08 21:44:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 21:44:05 - mmengine - INFO - Saving checkpoint at 203 epochs 2022/09/08 21:44:36 - mmengine - INFO - Epoch(train) [204][50/293] lr: 5.000000e-06 eta: 0:14:18 time: 0.514646 data_time: 0.084478 memory: 9871 loss_kpt: 0.000558 acc_pose: 0.812271 loss: 0.000558 2022/09/08 21:45:01 - mmengine - INFO - Epoch(train) [204][100/293] lr: 5.000000e-06 eta: 0:13:57 time: 0.503237 data_time: 0.077090 memory: 9871 loss_kpt: 0.000559 acc_pose: 0.883616 loss: 0.000559 2022/09/08 21:45:25 - mmengine - INFO - Epoch(train) [204][150/293] lr: 5.000000e-06 eta: 0:13:36 time: 0.490514 data_time: 0.083715 memory: 9871 loss_kpt: 0.000552 acc_pose: 0.869243 loss: 0.000552 2022/09/08 21:45:51 - mmengine - INFO - Epoch(train) [204][200/293] lr: 5.000000e-06 eta: 0:13:14 time: 0.503311 data_time: 0.075855 memory: 9871 loss_kpt: 0.000559 acc_pose: 0.828652 loss: 0.000559 2022/09/08 21:46:15 - mmengine - INFO - Epoch(train) [204][250/293] lr: 5.000000e-06 eta: 0:12:53 time: 0.496112 data_time: 0.071669 memory: 9871 loss_kpt: 0.000548 acc_pose: 0.825348 loss: 0.000548 2022/09/08 21:46:37 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 21:46:37 - mmengine - INFO - Saving checkpoint at 204 epochs 2022/09/08 21:47:07 - mmengine - INFO - Epoch(train) [205][50/293] lr: 5.000000e-06 eta: 0:12:13 time: 0.506157 data_time: 0.086511 memory: 9871 loss_kpt: 0.000553 acc_pose: 0.882227 loss: 0.000553 2022/09/08 21:47:32 - mmengine - INFO - Epoch(train) [205][100/293] lr: 5.000000e-06 eta: 0:11:51 time: 0.502953 data_time: 0.076664 memory: 9871 loss_kpt: 0.000562 acc_pose: 0.841049 loss: 0.000562 2022/09/08 21:47:57 - mmengine - INFO - Epoch(train) [205][150/293] lr: 5.000000e-06 eta: 0:11:30 time: 0.503586 data_time: 0.076348 memory: 9871 loss_kpt: 0.000558 acc_pose: 0.871659 loss: 0.000558 2022/09/08 21:48:22 - mmengine - INFO - Epoch(train) [205][200/293] lr: 5.000000e-06 eta: 0:11:08 time: 0.488976 data_time: 0.072582 memory: 9871 loss_kpt: 0.000555 acc_pose: 0.875089 loss: 0.000555 2022/09/08 21:48:36 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 21:48:47 - mmengine - INFO - Epoch(train) [205][250/293] lr: 5.000000e-06 eta: 0:10:47 time: 0.505093 data_time: 0.079572 memory: 9871 loss_kpt: 0.000556 acc_pose: 0.866662 loss: 0.000556 2022/09/08 21:49:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 21:49:08 - mmengine - INFO - Saving checkpoint at 205 epochs 2022/09/08 21:49:39 - mmengine - INFO - Epoch(train) [206][50/293] lr: 5.000000e-06 eta: 0:10:07 time: 0.525694 data_time: 0.087762 memory: 9871 loss_kpt: 0.000541 acc_pose: 0.859722 loss: 0.000541 2022/09/08 21:50:04 - mmengine - INFO - Epoch(train) [206][100/293] lr: 5.000000e-06 eta: 0:09:45 time: 0.496376 data_time: 0.075339 memory: 9871 loss_kpt: 0.000560 acc_pose: 0.855277 loss: 0.000560 2022/09/08 21:50:29 - mmengine - INFO - Epoch(train) [206][150/293] lr: 5.000000e-06 eta: 0:09:24 time: 0.494005 data_time: 0.077149 memory: 9871 loss_kpt: 0.000554 acc_pose: 0.852690 loss: 0.000554 2022/09/08 21:50:55 - mmengine - INFO - Epoch(train) [206][200/293] lr: 5.000000e-06 eta: 0:09:03 time: 0.516764 data_time: 0.076354 memory: 9871 loss_kpt: 0.000564 acc_pose: 0.866117 loss: 0.000564 2022/09/08 21:51:19 - mmengine - INFO - Epoch(train) [206][250/293] lr: 5.000000e-06 eta: 0:08:41 time: 0.494945 data_time: 0.077019 memory: 9871 loss_kpt: 0.000541 acc_pose: 0.872294 loss: 0.000541 2022/09/08 21:51:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 21:51:41 - mmengine - INFO - Saving checkpoint at 206 epochs 2022/09/08 21:52:11 - mmengine - INFO - Epoch(train) [207][50/293] lr: 5.000000e-06 eta: 0:08:01 time: 0.510810 data_time: 0.076821 memory: 9871 loss_kpt: 0.000558 acc_pose: 0.856113 loss: 0.000558 2022/09/08 21:52:36 - mmengine - INFO - Epoch(train) [207][100/293] lr: 5.000000e-06 eta: 0:07:40 time: 0.500077 data_time: 0.085610 memory: 9871 loss_kpt: 0.000560 acc_pose: 0.854699 loss: 0.000560 2022/09/08 21:53:01 - mmengine - INFO - Epoch(train) [207][150/293] lr: 5.000000e-06 eta: 0:07:18 time: 0.497364 data_time: 0.074930 memory: 9871 loss_kpt: 0.000564 acc_pose: 0.842057 loss: 0.000564 2022/09/08 21:53:26 - mmengine - INFO - Epoch(train) [207][200/293] lr: 5.000000e-06 eta: 0:06:57 time: 0.501730 data_time: 0.072004 memory: 9871 loss_kpt: 0.000564 acc_pose: 0.845234 loss: 0.000564 2022/09/08 21:53:51 - mmengine - INFO - Epoch(train) [207][250/293] lr: 5.000000e-06 eta: 0:06:35 time: 0.499026 data_time: 0.074065 memory: 9871 loss_kpt: 0.000556 acc_pose: 0.818825 loss: 0.000556 2022/09/08 21:54:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 21:54:13 - mmengine - INFO - Saving checkpoint at 207 epochs 2022/09/08 21:54:43 - mmengine - INFO - Epoch(train) [208][50/293] lr: 5.000000e-06 eta: 0:05:55 time: 0.520052 data_time: 0.084127 memory: 9871 loss_kpt: 0.000544 acc_pose: 0.829290 loss: 0.000544 2022/09/08 21:55:08 - mmengine - INFO - Epoch(train) [208][100/293] lr: 5.000000e-06 eta: 0:05:34 time: 0.502141 data_time: 0.077206 memory: 9871 loss_kpt: 0.000559 acc_pose: 0.874116 loss: 0.000559 2022/09/08 21:55:34 - mmengine - INFO - Epoch(train) [208][150/293] lr: 5.000000e-06 eta: 0:05:12 time: 0.511381 data_time: 0.071079 memory: 9871 loss_kpt: 0.000558 acc_pose: 0.843379 loss: 0.000558 2022/09/08 21:55:59 - mmengine - INFO - Epoch(train) [208][200/293] lr: 5.000000e-06 eta: 0:04:51 time: 0.501277 data_time: 0.077019 memory: 9871 loss_kpt: 0.000558 acc_pose: 0.862583 loss: 0.000558 2022/09/08 21:56:24 - mmengine - INFO - Epoch(train) [208][250/293] lr: 5.000000e-06 eta: 0:04:30 time: 0.509963 data_time: 0.070430 memory: 9871 loss_kpt: 0.000552 acc_pose: 0.855542 loss: 0.000552 2022/09/08 21:56:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 21:56:46 - mmengine - INFO - Saving checkpoint at 208 epochs 2022/09/08 21:57:16 - mmengine - INFO - Epoch(train) [209][50/293] lr: 5.000000e-06 eta: 0:03:50 time: 0.511801 data_time: 0.088079 memory: 9871 loss_kpt: 0.000561 acc_pose: 0.838951 loss: 0.000561 2022/09/08 21:57:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 21:57:41 - mmengine - INFO - Epoch(train) [209][100/293] lr: 5.000000e-06 eta: 0:03:28 time: 0.503119 data_time: 0.073421 memory: 9871 loss_kpt: 0.000556 acc_pose: 0.873501 loss: 0.000556 2022/09/08 21:58:06 - mmengine - INFO - Epoch(train) [209][150/293] lr: 5.000000e-06 eta: 0:03:07 time: 0.502372 data_time: 0.077180 memory: 9871 loss_kpt: 0.000551 acc_pose: 0.829919 loss: 0.000551 2022/09/08 21:58:31 - mmengine - INFO - Epoch(train) [209][200/293] lr: 5.000000e-06 eta: 0:02:45 time: 0.500019 data_time: 0.084575 memory: 9871 loss_kpt: 0.000559 acc_pose: 0.826371 loss: 0.000559 2022/09/08 21:58:56 - mmengine - INFO - Epoch(train) [209][250/293] lr: 5.000000e-06 eta: 0:02:24 time: 0.500792 data_time: 0.073705 memory: 9871 loss_kpt: 0.000561 acc_pose: 0.797878 loss: 0.000561 2022/09/08 21:59:18 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 21:59:18 - mmengine - INFO - Saving checkpoint at 209 epochs 2022/09/08 21:59:47 - mmengine - INFO - Epoch(train) [210][50/293] lr: 5.000000e-06 eta: 0:01:44 time: 0.509172 data_time: 0.097628 memory: 9871 loss_kpt: 0.000548 acc_pose: 0.832570 loss: 0.000548 2022/09/08 22:00:12 - mmengine - INFO - Epoch(train) [210][100/293] lr: 5.000000e-06 eta: 0:01:22 time: 0.500167 data_time: 0.077832 memory: 9871 loss_kpt: 0.000554 acc_pose: 0.865270 loss: 0.000554 2022/09/08 22:00:38 - mmengine - INFO - Epoch(train) [210][150/293] lr: 5.000000e-06 eta: 0:01:01 time: 0.503447 data_time: 0.079533 memory: 9871 loss_kpt: 0.000553 acc_pose: 0.873342 loss: 0.000553 2022/09/08 22:01:03 - mmengine - INFO - Epoch(train) [210][200/293] lr: 5.000000e-06 eta: 0:00:39 time: 0.510056 data_time: 0.078998 memory: 9871 loss_kpt: 0.000547 acc_pose: 0.885946 loss: 0.000547 2022/09/08 22:01:28 - mmengine - INFO - Epoch(train) [210][250/293] lr: 5.000000e-06 eta: 0:00:18 time: 0.499969 data_time: 0.074886 memory: 9871 loss_kpt: 0.000550 acc_pose: 0.907556 loss: 0.000550 2022/09/08 22:01:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-256x192_20220908_123645 2022/09/08 22:01:50 - mmengine - INFO - Saving checkpoint at 210 epochs 2022/09/08 22:02:00 - mmengine - INFO - Epoch(val) [210][50/407] eta: 0:00:43 time: 0.120742 data_time: 0.015730 memory: 9871 2022/09/08 22:02:06 - mmengine - INFO - Epoch(val) [210][100/407] eta: 0:00:38 time: 0.126008 data_time: 0.013998 memory: 920 2022/09/08 22:02:12 - mmengine - INFO - Epoch(val) [210][150/407] eta: 0:00:30 time: 0.120602 data_time: 0.015714 memory: 920 2022/09/08 22:02:18 - mmengine - INFO - Epoch(val) [210][200/407] eta: 0:00:23 time: 0.112788 data_time: 0.008751 memory: 920 2022/09/08 22:02:24 - mmengine - INFO - Epoch(val) [210][250/407] eta: 0:00:17 time: 0.114567 data_time: 0.008965 memory: 920 2022/09/08 22:02:30 - mmengine - INFO - Epoch(val) [210][300/407] eta: 0:00:12 time: 0.113928 data_time: 0.009331 memory: 920 2022/09/08 22:02:35 - mmengine - INFO - Epoch(val) [210][350/407] eta: 0:00:06 time: 0.115562 data_time: 0.009839 memory: 920 2022/09/08 22:02:41 - mmengine - INFO - Epoch(val) [210][400/407] eta: 0:00:00 time: 0.112608 data_time: 0.010622 memory: 920 2022/09/08 22:03:16 - mmengine - INFO - Evaluating CocoMetric... 2022/09/08 22:03:29 - mmengine - INFO - Epoch(val) [210][407/407] coco/AP: 0.748553 coco/AP .5: 0.906214 coco/AP .75: 0.820932 coco/AP (M): 0.713460 coco/AP (L): 0.815429 coco/AR: 0.803086 coco/AR .5: 0.944427 coco/AR .75: 0.867601 coco/AR (M): 0.761704 coco/AR (L): 0.862951