2022/09/08 23:06:34 - 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: 388795017 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 23:06:36 - 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=(288, 384), heatmap_size=(72, 96), sigma=3) 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=(288, 384), heatmap_size=(72, 96), sigma=3)), 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=(288, 384)), dict( type='GenerateTarget', target_type='heatmap', encoder=dict( type='MSRAHeatmap', input_size=(288, 384), heatmap_size=(72, 96), sigma=3)), 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=(288, 384)), 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=(288, 384)), dict( type='GenerateTarget', target_type='heatmap', encoder=dict( type='MSRAHeatmap', input_size=(288, 384), heatmap_size=(72, 96), sigma=3)), 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=(288, 384)), 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=(288, 384)), 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_384/' 2022/09/08 23:07:10 - 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 23:07:10 - 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 23:07:10 - 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 23:07:10 - 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 23:07:10 - 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 23:07:10 - 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 23:07:10 - 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 23:07:10 - 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 23:07:14 - 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 23:07:16 - 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 23:07:18 - 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 23:07:18 - 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 23:07:33 - mmengine - INFO - Checkpoints will be saved to /mnt/lustre/liqikai/work_dirs/20220908/hrnet_w32_384 by HardDiskBackend. 2022/09/08 23:10:48 - mmengine - INFO - Epoch(train) [1][50/293] lr: 4.954910e-05 eta: 2 days, 18:29:58 time: 3.893924 data_time: 0.707206 memory: 21676 loss_kpt: 0.002219 acc_pose: 0.129941 loss: 0.002219 2022/09/08 23:12:04 - mmengine - INFO - Epoch(train) [1][100/293] lr: 9.959920e-05 eta: 1 day, 22:16:39 time: 1.530126 data_time: 0.218909 memory: 21676 loss_kpt: 0.001866 acc_pose: 0.354936 loss: 0.001866 2022/09/08 23:13:10 - mmengine - INFO - Epoch(train) [1][150/293] lr: 1.496493e-04 eta: 1 day, 14:15:07 time: 1.306523 data_time: 0.116071 memory: 21676 loss_kpt: 0.001572 acc_pose: 0.496312 loss: 0.001572 2022/09/08 23:14:25 - mmengine - INFO - Epoch(train) [1][200/293] lr: 1.996994e-04 eta: 1 day, 11:05:37 time: 1.509301 data_time: 0.448582 memory: 21676 loss_kpt: 0.001353 acc_pose: 0.582897 loss: 0.001353 2022/09/08 23:15:20 - mmengine - INFO - Epoch(train) [1][250/293] lr: 2.497495e-04 eta: 1 day, 7:49:11 time: 1.106714 data_time: 0.138056 memory: 21676 loss_kpt: 0.001231 acc_pose: 0.568585 loss: 0.001231 2022/09/08 23:16:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/08 23:16:08 - mmengine - INFO - Saving checkpoint at 1 epochs 2022/09/08 23:16:51 - mmengine - INFO - Epoch(train) [2][50/293] lr: 3.428427e-04 eta: 1 day, 1:03:55 time: 0.770189 data_time: 0.110372 memory: 21676 loss_kpt: 0.001132 acc_pose: 0.679739 loss: 0.001132 2022/09/08 23:17:29 - mmengine - INFO - Epoch(train) [2][100/293] lr: 3.928928e-04 eta: 23:28:45 time: 0.750160 data_time: 0.094242 memory: 21676 loss_kpt: 0.001088 acc_pose: 0.673478 loss: 0.001088 2022/09/08 23:18:07 - mmengine - INFO - Epoch(train) [2][150/293] lr: 4.429429e-04 eta: 22:15:40 time: 0.756522 data_time: 0.102678 memory: 21676 loss_kpt: 0.001081 acc_pose: 0.648084 loss: 0.001081 2022/09/08 23:18:44 - mmengine - INFO - Epoch(train) [2][200/293] lr: 4.929930e-04 eta: 21:16:49 time: 0.752215 data_time: 0.096995 memory: 21676 loss_kpt: 0.001058 acc_pose: 0.560401 loss: 0.001058 2022/09/08 23:19:22 - mmengine - INFO - Epoch(train) [2][250/293] lr: 5.000000e-04 eta: 20:28:26 time: 0.749249 data_time: 0.097001 memory: 21676 loss_kpt: 0.001047 acc_pose: 0.703986 loss: 0.001047 2022/09/08 23:19:54 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/08 23:19:54 - mmengine - INFO - Saving checkpoint at 2 epochs 2022/09/08 23:20:37 - mmengine - INFO - Epoch(train) [3][50/293] lr: 5.000000e-04 eta: 18:28:55 time: 0.773433 data_time: 0.110395 memory: 21676 loss_kpt: 0.000992 acc_pose: 0.667014 loss: 0.000992 2022/09/08 23:21:14 - mmengine - INFO - Epoch(train) [3][100/293] lr: 5.000000e-04 eta: 18:03:18 time: 0.758495 data_time: 0.099970 memory: 21676 loss_kpt: 0.000973 acc_pose: 0.679425 loss: 0.000973 2022/09/08 23:21:52 - mmengine - INFO - Epoch(train) [3][150/293] lr: 5.000000e-04 eta: 17:40:07 time: 0.744408 data_time: 0.098054 memory: 21676 loss_kpt: 0.000947 acc_pose: 0.711696 loss: 0.000947 2022/09/08 23:22:30 - mmengine - INFO - Epoch(train) [3][200/293] lr: 5.000000e-04 eta: 17:21:04 time: 0.763872 data_time: 0.094984 memory: 21676 loss_kpt: 0.000947 acc_pose: 0.688705 loss: 0.000947 2022/09/08 23:23:07 - mmengine - INFO - Epoch(train) [3][250/293] lr: 5.000000e-04 eta: 17:03:20 time: 0.749543 data_time: 0.092062 memory: 21676 loss_kpt: 0.000939 acc_pose: 0.672898 loss: 0.000939 2022/09/08 23:23:39 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/08 23:23:39 - mmengine - INFO - Saving checkpoint at 3 epochs 2022/09/08 23:24:22 - mmengine - INFO - Epoch(train) [4][50/293] lr: 5.000000e-04 eta: 16:01:08 time: 0.766381 data_time: 0.101920 memory: 21676 loss_kpt: 0.000931 acc_pose: 0.642421 loss: 0.000931 2022/09/08 23:25:00 - mmengine - INFO - Epoch(train) [4][100/293] lr: 5.000000e-04 eta: 15:50:24 time: 0.758713 data_time: 0.107056 memory: 21676 loss_kpt: 0.000934 acc_pose: 0.692816 loss: 0.000934 2022/09/08 23:25:16 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/08 23:25:39 - mmengine - INFO - Epoch(train) [4][150/293] lr: 5.000000e-04 eta: 15:41:10 time: 0.769185 data_time: 0.095536 memory: 21676 loss_kpt: 0.000913 acc_pose: 0.759844 loss: 0.000913 2022/09/08 23:26:17 - mmengine - INFO - Epoch(train) [4][200/293] lr: 5.000000e-04 eta: 15:32:16 time: 0.759574 data_time: 0.099692 memory: 21676 loss_kpt: 0.000894 acc_pose: 0.750292 loss: 0.000894 2022/09/08 23:26:54 - mmengine - INFO - Epoch(train) [4][250/293] lr: 5.000000e-04 eta: 15:23:51 time: 0.753527 data_time: 0.097810 memory: 21676 loss_kpt: 0.000890 acc_pose: 0.687463 loss: 0.000890 2022/09/08 23:27:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/08 23:27:26 - mmengine - INFO - Saving checkpoint at 4 epochs 2022/09/08 23:28:09 - mmengine - INFO - Epoch(train) [5][50/293] lr: 5.000000e-04 eta: 14:44:03 time: 0.773986 data_time: 0.110398 memory: 21676 loss_kpt: 0.000865 acc_pose: 0.716969 loss: 0.000865 2022/09/08 23:28:46 - mmengine - INFO - Epoch(train) [5][100/293] lr: 5.000000e-04 eta: 14:37:58 time: 0.744197 data_time: 0.096753 memory: 21676 loss_kpt: 0.000888 acc_pose: 0.779745 loss: 0.000888 2022/09/08 23:29:24 - mmengine - INFO - Epoch(train) [5][150/293] lr: 5.000000e-04 eta: 14:33:09 time: 0.766367 data_time: 0.094369 memory: 21676 loss_kpt: 0.000883 acc_pose: 0.752079 loss: 0.000883 2022/09/08 23:30:02 - mmengine - INFO - Epoch(train) [5][200/293] lr: 5.000000e-04 eta: 14:28:15 time: 0.756043 data_time: 0.097048 memory: 21676 loss_kpt: 0.000866 acc_pose: 0.708417 loss: 0.000866 2022/09/08 23:30:39 - mmengine - INFO - Epoch(train) [5][250/293] lr: 5.000000e-04 eta: 14:23:24 time: 0.748754 data_time: 0.098259 memory: 21676 loss_kpt: 0.000869 acc_pose: 0.753273 loss: 0.000869 2022/09/08 23:31:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/08 23:31:13 - mmengine - INFO - Saving checkpoint at 5 epochs 2022/09/08 23:31:56 - mmengine - INFO - Epoch(train) [6][50/293] lr: 5.000000e-04 eta: 13:54:35 time: 0.770629 data_time: 0.105154 memory: 21676 loss_kpt: 0.000835 acc_pose: 0.734421 loss: 0.000835 2022/09/08 23:32:34 - mmengine - INFO - Epoch(train) [6][100/293] lr: 5.000000e-04 eta: 13:51:24 time: 0.756152 data_time: 0.098236 memory: 21676 loss_kpt: 0.000840 acc_pose: 0.789144 loss: 0.000840 2022/09/08 23:33:12 - mmengine - INFO - Epoch(train) [6][150/293] lr: 5.000000e-04 eta: 13:48:51 time: 0.771824 data_time: 0.102182 memory: 21676 loss_kpt: 0.000847 acc_pose: 0.729788 loss: 0.000847 2022/09/08 23:33:50 - mmengine - INFO - Epoch(train) [6][200/293] lr: 5.000000e-04 eta: 13:45:36 time: 0.744826 data_time: 0.097925 memory: 21676 loss_kpt: 0.000852 acc_pose: 0.734076 loss: 0.000852 2022/09/08 23:34:27 - mmengine - INFO - Epoch(train) [6][250/293] lr: 5.000000e-04 eta: 13:42:51 time: 0.756472 data_time: 0.101943 memory: 21676 loss_kpt: 0.000835 acc_pose: 0.761351 loss: 0.000835 2022/09/08 23:35:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/08 23:35:00 - mmengine - INFO - Saving checkpoint at 6 epochs 2022/09/08 23:35:44 - mmengine - INFO - Epoch(train) [7][50/293] lr: 5.000000e-04 eta: 13:20:47 time: 0.780111 data_time: 0.112980 memory: 21676 loss_kpt: 0.000816 acc_pose: 0.735258 loss: 0.000816 2022/09/08 23:36:21 - mmengine - INFO - Epoch(train) [7][100/293] lr: 5.000000e-04 eta: 13:18:34 time: 0.746543 data_time: 0.096491 memory: 21676 loss_kpt: 0.000836 acc_pose: 0.698566 loss: 0.000836 2022/09/08 23:36:59 - mmengine - INFO - Epoch(train) [7][150/293] lr: 5.000000e-04 eta: 13:16:43 time: 0.758123 data_time: 0.110356 memory: 21676 loss_kpt: 0.000828 acc_pose: 0.756284 loss: 0.000828 2022/09/08 23:37:37 - mmengine - INFO - Epoch(train) [7][200/293] lr: 5.000000e-04 eta: 13:15:01 time: 0.760826 data_time: 0.100909 memory: 21676 loss_kpt: 0.000825 acc_pose: 0.745084 loss: 0.000825 2022/09/08 23:38:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/08 23:38:14 - mmengine - INFO - Epoch(train) [7][250/293] lr: 5.000000e-04 eta: 13:13:00 time: 0.745996 data_time: 0.100208 memory: 21676 loss_kpt: 0.000826 acc_pose: 0.752071 loss: 0.000826 2022/09/08 23:38:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/08 23:38:46 - mmengine - INFO - Saving checkpoint at 7 epochs 2022/09/08 23:39:29 - mmengine - INFO - Epoch(train) [8][50/293] lr: 5.000000e-04 eta: 12:54:54 time: 0.771853 data_time: 0.109768 memory: 21676 loss_kpt: 0.000804 acc_pose: 0.718107 loss: 0.000804 2022/09/08 23:40:07 - mmengine - INFO - Epoch(train) [8][100/293] lr: 5.000000e-04 eta: 12:53:37 time: 0.754518 data_time: 0.104299 memory: 21676 loss_kpt: 0.000801 acc_pose: 0.758265 loss: 0.000801 2022/09/08 23:40:45 - mmengine - INFO - Epoch(train) [8][150/293] lr: 5.000000e-04 eta: 12:52:27 time: 0.758790 data_time: 0.100885 memory: 21676 loss_kpt: 0.000795 acc_pose: 0.788812 loss: 0.000795 2022/09/08 23:41:23 - mmengine - INFO - Epoch(train) [8][200/293] lr: 5.000000e-04 eta: 12:51:16 time: 0.756852 data_time: 0.099782 memory: 21676 loss_kpt: 0.000793 acc_pose: 0.740767 loss: 0.000793 2022/09/08 23:42:01 - mmengine - INFO - Epoch(train) [8][250/293] lr: 5.000000e-04 eta: 12:50:17 time: 0.764981 data_time: 0.100466 memory: 21676 loss_kpt: 0.000798 acc_pose: 0.756774 loss: 0.000798 2022/09/08 23:42:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/08 23:42:33 - mmengine - INFO - Saving checkpoint at 8 epochs 2022/09/08 23:43:16 - mmengine - INFO - Epoch(train) [9][50/293] lr: 5.000000e-04 eta: 12:35:23 time: 0.786591 data_time: 0.125365 memory: 21676 loss_kpt: 0.000784 acc_pose: 0.750292 loss: 0.000784 2022/09/08 23:43:54 - mmengine - INFO - Epoch(train) [9][100/293] lr: 5.000000e-04 eta: 12:34:40 time: 0.762754 data_time: 0.104767 memory: 21676 loss_kpt: 0.000790 acc_pose: 0.718227 loss: 0.000790 2022/09/08 23:44:32 - mmengine - INFO - Epoch(train) [9][150/293] lr: 5.000000e-04 eta: 12:33:44 time: 0.751138 data_time: 0.096409 memory: 21676 loss_kpt: 0.000799 acc_pose: 0.731538 loss: 0.000799 2022/09/08 23:45:09 - mmengine - INFO - Epoch(train) [9][200/293] lr: 5.000000e-04 eta: 12:32:52 time: 0.754722 data_time: 0.099200 memory: 21676 loss_kpt: 0.000800 acc_pose: 0.695786 loss: 0.000800 2022/09/08 23:45:47 - mmengine - INFO - Epoch(train) [9][250/293] lr: 5.000000e-04 eta: 12:31:57 time: 0.751147 data_time: 0.099722 memory: 21676 loss_kpt: 0.000780 acc_pose: 0.762580 loss: 0.000780 2022/09/08 23:46:20 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/08 23:46:20 - mmengine - INFO - Saving checkpoint at 9 epochs 2022/09/08 23:47:03 - mmengine - INFO - Epoch(train) [10][50/293] lr: 5.000000e-04 eta: 12:19:03 time: 0.781743 data_time: 0.112056 memory: 21676 loss_kpt: 0.000768 acc_pose: 0.829611 loss: 0.000768 2022/09/08 23:47:40 - mmengine - INFO - Epoch(train) [10][100/293] lr: 5.000000e-04 eta: 12:18:15 time: 0.744192 data_time: 0.101757 memory: 21676 loss_kpt: 0.000764 acc_pose: 0.802028 loss: 0.000764 2022/09/08 23:48:18 - mmengine - INFO - Epoch(train) [10][150/293] lr: 5.000000e-04 eta: 12:17:37 time: 0.752734 data_time: 0.100862 memory: 21676 loss_kpt: 0.000785 acc_pose: 0.782313 loss: 0.000785 2022/09/08 23:48:55 - mmengine - INFO - Epoch(train) [10][200/293] lr: 5.000000e-04 eta: 12:16:53 time: 0.747727 data_time: 0.101760 memory: 21676 loss_kpt: 0.000783 acc_pose: 0.805743 loss: 0.000783 2022/09/08 23:49:33 - mmengine - INFO - Epoch(train) [10][250/293] lr: 5.000000e-04 eta: 12:16:20 time: 0.757205 data_time: 0.101869 memory: 21676 loss_kpt: 0.000766 acc_pose: 0.823672 loss: 0.000766 2022/09/08 23:50:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/08 23:50:05 - mmengine - INFO - Saving checkpoint at 10 epochs 2022/09/08 23:50:23 - mmengine - INFO - Epoch(val) [10][50/407] eta: 0:01:22 time: 0.232181 data_time: 0.087725 memory: 21676 2022/09/08 23:50:31 - mmengine - INFO - Epoch(val) [10][100/407] eta: 0:00:47 time: 0.155482 data_time: 0.013324 memory: 1375 2022/09/08 23:50:38 - mmengine - INFO - Epoch(val) [10][150/407] eta: 0:00:39 time: 0.153180 data_time: 0.011477 memory: 1375 2022/09/08 23:50:46 - mmengine - INFO - Epoch(val) [10][200/407] eta: 0:00:31 time: 0.151356 data_time: 0.008567 memory: 1375 2022/09/08 23:50:54 - mmengine - INFO - Epoch(val) [10][250/407] eta: 0:00:24 time: 0.152946 data_time: 0.008097 memory: 1375 2022/09/08 23:51:01 - mmengine - INFO - Epoch(val) [10][300/407] eta: 0:00:16 time: 0.150206 data_time: 0.008258 memory: 1375 2022/09/08 23:51:09 - mmengine - INFO - Epoch(val) [10][350/407] eta: 0:00:09 time: 0.160006 data_time: 0.016249 memory: 1375 2022/09/08 23:51:17 - mmengine - INFO - Epoch(val) [10][400/407] eta: 0:00:01 time: 0.150868 data_time: 0.008217 memory: 1375 2022/09/08 23:51:54 - mmengine - INFO - Evaluating CocoMetric... 2022/09/08 23:52:08 - mmengine - INFO - Epoch(val) [10][407/407] coco/AP: 0.675279 coco/AP .5: 0.876468 coco/AP .75: 0.748302 coco/AP (M): 0.634278 coco/AP (L): 0.747809 coco/AR: 0.732683 coco/AR .5: 0.918136 coco/AR .75: 0.801480 coco/AR (M): 0.686151 coco/AR (L): 0.799257 2022/09/08 23:52:10 - mmengine - INFO - The best checkpoint with 0.6753 coco/AP at 10 epoch is saved to best_coco/AP_epoch_10.pth. 2022/09/08 23:52:49 - mmengine - INFO - Epoch(train) [11][50/293] lr: 5.000000e-04 eta: 12:04:51 time: 0.772093 data_time: 0.116868 memory: 21676 loss_kpt: 0.000793 acc_pose: 0.741442 loss: 0.000793 2022/09/08 23:53:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/08 23:53:26 - mmengine - INFO - Epoch(train) [11][100/293] lr: 5.000000e-04 eta: 12:04:16 time: 0.744173 data_time: 0.098538 memory: 21676 loss_kpt: 0.000759 acc_pose: 0.785183 loss: 0.000759 2022/09/08 23:54:04 - mmengine - INFO - Epoch(train) [11][150/293] lr: 5.000000e-04 eta: 12:03:42 time: 0.746215 data_time: 0.089968 memory: 21676 loss_kpt: 0.000755 acc_pose: 0.719772 loss: 0.000755 2022/09/08 23:54:42 - mmengine - INFO - Epoch(train) [11][200/293] lr: 5.000000e-04 eta: 12:03:30 time: 0.770254 data_time: 0.099528 memory: 21676 loss_kpt: 0.000773 acc_pose: 0.748387 loss: 0.000773 2022/09/08 23:55:20 - mmengine - INFO - Epoch(train) [11][250/293] lr: 5.000000e-04 eta: 12:02:59 time: 0.749535 data_time: 0.105847 memory: 21676 loss_kpt: 0.000771 acc_pose: 0.749654 loss: 0.000771 2022/09/08 23:55:52 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/08 23:55:52 - mmengine - INFO - Saving checkpoint at 11 epochs 2022/09/08 23:56:37 - mmengine - INFO - Epoch(train) [12][50/293] lr: 5.000000e-04 eta: 11:53:01 time: 0.789082 data_time: 0.112695 memory: 21676 loss_kpt: 0.000734 acc_pose: 0.765812 loss: 0.000734 2022/09/08 23:57:16 - mmengine - INFO - Epoch(train) [12][100/293] lr: 5.000000e-04 eta: 11:53:04 time: 0.779129 data_time: 0.098830 memory: 21676 loss_kpt: 0.000762 acc_pose: 0.756760 loss: 0.000762 2022/09/08 23:57:54 - mmengine - INFO - Epoch(train) [12][150/293] lr: 5.000000e-04 eta: 11:52:55 time: 0.768219 data_time: 0.099195 memory: 21676 loss_kpt: 0.000757 acc_pose: 0.801921 loss: 0.000757 2022/09/08 23:58:32 - mmengine - INFO - Epoch(train) [12][200/293] lr: 5.000000e-04 eta: 11:52:35 time: 0.754693 data_time: 0.097229 memory: 21676 loss_kpt: 0.000757 acc_pose: 0.737283 loss: 0.000757 2022/09/08 23:59:10 - mmengine - INFO - Epoch(train) [12][250/293] lr: 5.000000e-04 eta: 11:52:18 time: 0.759167 data_time: 0.095496 memory: 21676 loss_kpt: 0.000741 acc_pose: 0.753633 loss: 0.000741 2022/09/08 23:59:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/08 23:59:43 - mmengine - INFO - Saving checkpoint at 12 epochs 2022/09/09 00:00:28 - mmengine - INFO - Epoch(train) [13][50/293] lr: 5.000000e-04 eta: 11:43:45 time: 0.822794 data_time: 0.113090 memory: 21676 loss_kpt: 0.000752 acc_pose: 0.761045 loss: 0.000752 2022/09/09 00:01:06 - mmengine - INFO - Epoch(train) [13][100/293] lr: 5.000000e-04 eta: 11:43:35 time: 0.761911 data_time: 0.100879 memory: 21676 loss_kpt: 0.000767 acc_pose: 0.734899 loss: 0.000767 2022/09/09 00:01:45 - mmengine - INFO - Epoch(train) [13][150/293] lr: 5.000000e-04 eta: 11:43:36 time: 0.775302 data_time: 0.105162 memory: 21676 loss_kpt: 0.000761 acc_pose: 0.779974 loss: 0.000761 2022/09/09 00:02:24 - mmengine - INFO - Epoch(train) [13][200/293] lr: 5.000000e-04 eta: 11:43:33 time: 0.772869 data_time: 0.101875 memory: 21676 loss_kpt: 0.000756 acc_pose: 0.792019 loss: 0.000756 2022/09/09 00:03:02 - mmengine - INFO - Epoch(train) [13][250/293] lr: 5.000000e-04 eta: 11:43:18 time: 0.758615 data_time: 0.102803 memory: 21676 loss_kpt: 0.000743 acc_pose: 0.776117 loss: 0.000743 2022/09/09 00:03:34 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 00:03:34 - mmengine - INFO - Saving checkpoint at 13 epochs 2022/09/09 00:04:17 - mmengine - INFO - Epoch(train) [14][50/293] lr: 5.000000e-04 eta: 11:34:48 time: 0.767224 data_time: 0.116331 memory: 21676 loss_kpt: 0.000723 acc_pose: 0.786767 loss: 0.000723 2022/09/09 00:04:55 - mmengine - INFO - Epoch(train) [14][100/293] lr: 5.000000e-04 eta: 11:34:50 time: 0.774224 data_time: 0.105722 memory: 21676 loss_kpt: 0.000735 acc_pose: 0.791814 loss: 0.000735 2022/09/09 00:05:33 - mmengine - INFO - Epoch(train) [14][150/293] lr: 5.000000e-04 eta: 11:34:38 time: 0.756457 data_time: 0.100328 memory: 21676 loss_kpt: 0.000744 acc_pose: 0.792176 loss: 0.000744 2022/09/09 00:06:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 00:06:11 - mmengine - INFO - Epoch(train) [14][200/293] lr: 5.000000e-04 eta: 11:34:24 time: 0.755986 data_time: 0.102208 memory: 21676 loss_kpt: 0.000740 acc_pose: 0.823623 loss: 0.000740 2022/09/09 00:06:49 - mmengine - INFO - Epoch(train) [14][250/293] lr: 5.000000e-04 eta: 11:34:09 time: 0.753492 data_time: 0.104555 memory: 21676 loss_kpt: 0.000752 acc_pose: 0.744313 loss: 0.000752 2022/09/09 00:07:21 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 00:07:21 - mmengine - INFO - Saving checkpoint at 14 epochs 2022/09/09 00:08:05 - mmengine - INFO - Epoch(train) [15][50/293] lr: 5.000000e-04 eta: 11:26:33 time: 0.785412 data_time: 0.112432 memory: 21676 loss_kpt: 0.000730 acc_pose: 0.791063 loss: 0.000730 2022/09/09 00:08:43 - mmengine - INFO - Epoch(train) [15][100/293] lr: 5.000000e-04 eta: 11:26:26 time: 0.760650 data_time: 0.103971 memory: 21676 loss_kpt: 0.000734 acc_pose: 0.734059 loss: 0.000734 2022/09/09 00:09:21 - mmengine - INFO - Epoch(train) [15][150/293] lr: 5.000000e-04 eta: 11:26:23 time: 0.766620 data_time: 0.105752 memory: 21676 loss_kpt: 0.000751 acc_pose: 0.783621 loss: 0.000751 2022/09/09 00:10:00 - mmengine - INFO - Epoch(train) [15][200/293] lr: 5.000000e-04 eta: 11:26:25 time: 0.776180 data_time: 0.095419 memory: 21676 loss_kpt: 0.000730 acc_pose: 0.755619 loss: 0.000730 2022/09/09 00:10:38 - mmengine - INFO - Epoch(train) [15][250/293] lr: 5.000000e-04 eta: 11:26:11 time: 0.753777 data_time: 0.094874 memory: 21676 loss_kpt: 0.000722 acc_pose: 0.726234 loss: 0.000722 2022/09/09 00:11:10 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 00:11:10 - mmengine - INFO - Saving checkpoint at 15 epochs 2022/09/09 00:11:52 - mmengine - INFO - Epoch(train) [16][50/293] lr: 5.000000e-04 eta: 11:18:53 time: 0.760769 data_time: 0.108777 memory: 21676 loss_kpt: 0.000745 acc_pose: 0.785761 loss: 0.000745 2022/09/09 00:12:30 - mmengine - INFO - Epoch(train) [16][100/293] lr: 5.000000e-04 eta: 11:18:46 time: 0.759333 data_time: 0.103074 memory: 21676 loss_kpt: 0.000720 acc_pose: 0.704233 loss: 0.000720 2022/09/09 00:13:08 - mmengine - INFO - Epoch(train) [16][150/293] lr: 5.000000e-04 eta: 11:18:31 time: 0.746657 data_time: 0.104363 memory: 21676 loss_kpt: 0.000731 acc_pose: 0.790115 loss: 0.000731 2022/09/09 00:13:46 - mmengine - INFO - Epoch(train) [16][200/293] lr: 5.000000e-04 eta: 11:18:26 time: 0.765311 data_time: 0.111804 memory: 21676 loss_kpt: 0.000735 acc_pose: 0.769646 loss: 0.000735 2022/09/09 00:14:23 - mmengine - INFO - Epoch(train) [16][250/293] lr: 5.000000e-04 eta: 11:18:10 time: 0.745872 data_time: 0.099935 memory: 21676 loss_kpt: 0.000733 acc_pose: 0.776718 loss: 0.000733 2022/09/09 00:14:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 00:14:56 - mmengine - INFO - Saving checkpoint at 16 epochs 2022/09/09 00:15:40 - mmengine - INFO - Epoch(train) [17][50/293] lr: 5.000000e-04 eta: 11:11:36 time: 0.784163 data_time: 0.116472 memory: 21676 loss_kpt: 0.000723 acc_pose: 0.805117 loss: 0.000723 2022/09/09 00:16:18 - mmengine - INFO - Epoch(train) [17][100/293] lr: 5.000000e-04 eta: 11:11:35 time: 0.768781 data_time: 0.105470 memory: 21676 loss_kpt: 0.000714 acc_pose: 0.801143 loss: 0.000714 2022/09/09 00:16:57 - mmengine - INFO - Epoch(train) [17][150/293] lr: 5.000000e-04 eta: 11:11:32 time: 0.765647 data_time: 0.107665 memory: 21676 loss_kpt: 0.000713 acc_pose: 0.752013 loss: 0.000713 2022/09/09 00:17:35 - mmengine - INFO - Epoch(train) [17][200/293] lr: 5.000000e-04 eta: 11:11:31 time: 0.769071 data_time: 0.103577 memory: 21676 loss_kpt: 0.000717 acc_pose: 0.784624 loss: 0.000717 2022/09/09 00:18:14 - mmengine - INFO - Epoch(train) [17][250/293] lr: 5.000000e-04 eta: 11:11:32 time: 0.776523 data_time: 0.106930 memory: 21676 loss_kpt: 0.000743 acc_pose: 0.739950 loss: 0.000743 2022/09/09 00:18:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 00:18:46 - mmengine - INFO - Saving checkpoint at 17 epochs 2022/09/09 00:19:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 00:19:29 - mmengine - INFO - Epoch(train) [18][50/293] lr: 5.000000e-04 eta: 11:05:21 time: 0.780334 data_time: 0.111426 memory: 21676 loss_kpt: 0.000713 acc_pose: 0.805116 loss: 0.000713 2022/09/09 00:20:08 - mmengine - INFO - Epoch(train) [18][100/293] lr: 5.000000e-04 eta: 11:05:22 time: 0.771879 data_time: 0.106508 memory: 21676 loss_kpt: 0.000718 acc_pose: 0.739377 loss: 0.000718 2022/09/09 00:20:46 - mmengine - INFO - Epoch(train) [18][150/293] lr: 5.000000e-04 eta: 11:05:15 time: 0.758964 data_time: 0.107579 memory: 21676 loss_kpt: 0.000716 acc_pose: 0.767887 loss: 0.000716 2022/09/09 00:21:24 - mmengine - INFO - Epoch(train) [18][200/293] lr: 5.000000e-04 eta: 11:05:04 time: 0.752957 data_time: 0.103640 memory: 21676 loss_kpt: 0.000725 acc_pose: 0.817430 loss: 0.000725 2022/09/09 00:22:01 - mmengine - INFO - Epoch(train) [18][250/293] lr: 5.000000e-04 eta: 11:04:49 time: 0.745819 data_time: 0.099993 memory: 21676 loss_kpt: 0.000721 acc_pose: 0.782892 loss: 0.000721 2022/09/09 00:22:34 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 00:22:34 - mmengine - INFO - Saving checkpoint at 18 epochs 2022/09/09 00:23:17 - mmengine - INFO - Epoch(train) [19][50/293] lr: 5.000000e-04 eta: 10:58:57 time: 0.775627 data_time: 0.112688 memory: 21676 loss_kpt: 0.000707 acc_pose: 0.796489 loss: 0.000707 2022/09/09 00:23:55 - mmengine - INFO - Epoch(train) [19][100/293] lr: 5.000000e-04 eta: 10:58:51 time: 0.759508 data_time: 0.106308 memory: 21676 loss_kpt: 0.000720 acc_pose: 0.750990 loss: 0.000720 2022/09/09 00:24:32 - mmengine - INFO - Epoch(train) [19][150/293] lr: 5.000000e-04 eta: 10:58:42 time: 0.755143 data_time: 0.105241 memory: 21676 loss_kpt: 0.000709 acc_pose: 0.729222 loss: 0.000709 2022/09/09 00:25:10 - mmengine - INFO - Epoch(train) [19][200/293] lr: 5.000000e-04 eta: 10:58:31 time: 0.751719 data_time: 0.103225 memory: 21676 loss_kpt: 0.000715 acc_pose: 0.772770 loss: 0.000715 2022/09/09 00:25:48 - mmengine - INFO - Epoch(train) [19][250/293] lr: 5.000000e-04 eta: 10:58:21 time: 0.755327 data_time: 0.098441 memory: 21676 loss_kpt: 0.000724 acc_pose: 0.760568 loss: 0.000724 2022/09/09 00:26:20 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 00:26:20 - mmengine - INFO - Saving checkpoint at 19 epochs 2022/09/09 00:27:04 - mmengine - INFO - Epoch(train) [20][50/293] lr: 5.000000e-04 eta: 10:53:00 time: 0.797692 data_time: 0.121469 memory: 21676 loss_kpt: 0.000719 acc_pose: 0.750428 loss: 0.000719 2022/09/09 00:27:43 - mmengine - INFO - Epoch(train) [20][100/293] lr: 5.000000e-04 eta: 10:52:56 time: 0.763572 data_time: 0.102128 memory: 21676 loss_kpt: 0.000719 acc_pose: 0.775073 loss: 0.000719 2022/09/09 00:28:21 - mmengine - INFO - Epoch(train) [20][150/293] lr: 5.000000e-04 eta: 10:52:53 time: 0.767170 data_time: 0.107072 memory: 21676 loss_kpt: 0.000723 acc_pose: 0.795500 loss: 0.000723 2022/09/09 00:28:59 - mmengine - INFO - Epoch(train) [20][200/293] lr: 5.000000e-04 eta: 10:52:47 time: 0.761727 data_time: 0.101395 memory: 21676 loss_kpt: 0.000719 acc_pose: 0.787803 loss: 0.000719 2022/09/09 00:29:37 - mmengine - INFO - Epoch(train) [20][250/293] lr: 5.000000e-04 eta: 10:52:39 time: 0.760029 data_time: 0.104798 memory: 21676 loss_kpt: 0.000710 acc_pose: 0.802584 loss: 0.000710 2022/09/09 00:30:10 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 00:30:10 - mmengine - INFO - Saving checkpoint at 20 epochs 2022/09/09 00:30:22 - mmengine - INFO - Epoch(val) [20][50/407] eta: 0:00:55 time: 0.155259 data_time: 0.013571 memory: 21676 2022/09/09 00:30:30 - mmengine - INFO - Epoch(val) [20][100/407] eta: 0:00:46 time: 0.150032 data_time: 0.008198 memory: 1375 2022/09/09 00:30:37 - mmengine - INFO - Epoch(val) [20][150/407] eta: 0:00:38 time: 0.151692 data_time: 0.009424 memory: 1375 2022/09/09 00:30:45 - mmengine - INFO - Epoch(val) [20][200/407] eta: 0:00:31 time: 0.150369 data_time: 0.008369 memory: 1375 2022/09/09 00:30:53 - mmengine - INFO - Epoch(val) [20][250/407] eta: 0:00:24 time: 0.154299 data_time: 0.008977 memory: 1375 2022/09/09 00:31:00 - mmengine - INFO - Epoch(val) [20][300/407] eta: 0:00:16 time: 0.151234 data_time: 0.008369 memory: 1375 2022/09/09 00:31:08 - mmengine - INFO - Epoch(val) [20][350/407] eta: 0:00:08 time: 0.153726 data_time: 0.010344 memory: 1375 2022/09/09 00:31:16 - mmengine - INFO - Epoch(val) [20][400/407] eta: 0:00:01 time: 0.156675 data_time: 0.015108 memory: 1375 2022/09/09 00:31:52 - mmengine - INFO - Evaluating CocoMetric... 2022/09/09 00:32:06 - mmengine - INFO - Epoch(val) [20][407/407] coco/AP: 0.705114 coco/AP .5: 0.885342 coco/AP .75: 0.775528 coco/AP (M): 0.666083 coco/AP (L): 0.776644 coco/AR: 0.759934 coco/AR .5: 0.924748 coco/AR .75: 0.825409 coco/AR (M): 0.713849 coco/AR (L): 0.826310 2022/09/09 00:32:06 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220908/hrnet_w32_384/best_coco/AP_epoch_10.pth is removed 2022/09/09 00:32:09 - mmengine - INFO - The best checkpoint with 0.7051 coco/AP at 20 epoch is saved to best_coco/AP_epoch_20.pth. 2022/09/09 00:32:48 - mmengine - INFO - Epoch(train) [21][50/293] lr: 5.000000e-04 eta: 10:47:29 time: 0.786445 data_time: 0.115519 memory: 21676 loss_kpt: 0.000705 acc_pose: 0.788454 loss: 0.000705 2022/09/09 00:33:26 - mmengine - INFO - Epoch(train) [21][100/293] lr: 5.000000e-04 eta: 10:47:23 time: 0.761079 data_time: 0.108920 memory: 21676 loss_kpt: 0.000702 acc_pose: 0.793308 loss: 0.000702 2022/09/09 00:33:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 00:34:04 - mmengine - INFO - Epoch(train) [21][150/293] lr: 5.000000e-04 eta: 10:47:15 time: 0.757920 data_time: 0.097714 memory: 21676 loss_kpt: 0.000712 acc_pose: 0.762524 loss: 0.000712 2022/09/09 00:34:43 - mmengine - INFO - Epoch(train) [21][200/293] lr: 5.000000e-04 eta: 10:47:15 time: 0.776041 data_time: 0.107075 memory: 21676 loss_kpt: 0.000698 acc_pose: 0.797283 loss: 0.000698 2022/09/09 00:35:20 - mmengine - INFO - Epoch(train) [21][250/293] lr: 5.000000e-04 eta: 10:47:05 time: 0.754637 data_time: 0.102103 memory: 21676 loss_kpt: 0.000691 acc_pose: 0.841207 loss: 0.000691 2022/09/09 00:35:53 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 00:35:53 - mmengine - INFO - Saving checkpoint at 21 epochs 2022/09/09 00:36:36 - mmengine - INFO - Epoch(train) [22][50/293] lr: 5.000000e-04 eta: 10:42:08 time: 0.782745 data_time: 0.115455 memory: 21676 loss_kpt: 0.000699 acc_pose: 0.766820 loss: 0.000699 2022/09/09 00:37:15 - mmengine - INFO - Epoch(train) [22][100/293] lr: 5.000000e-04 eta: 10:42:07 time: 0.773069 data_time: 0.101795 memory: 21676 loss_kpt: 0.000690 acc_pose: 0.759230 loss: 0.000690 2022/09/09 00:37:53 - mmengine - INFO - Epoch(train) [22][150/293] lr: 5.000000e-04 eta: 10:42:03 time: 0.768471 data_time: 0.103271 memory: 21676 loss_kpt: 0.000708 acc_pose: 0.816271 loss: 0.000708 2022/09/09 00:38:32 - mmengine - INFO - Epoch(train) [22][200/293] lr: 5.000000e-04 eta: 10:41:59 time: 0.768464 data_time: 0.099265 memory: 21676 loss_kpt: 0.000709 acc_pose: 0.792960 loss: 0.000709 2022/09/09 00:39:10 - mmengine - INFO - Epoch(train) [22][250/293] lr: 5.000000e-04 eta: 10:41:56 time: 0.770609 data_time: 0.107147 memory: 21676 loss_kpt: 0.000695 acc_pose: 0.789953 loss: 0.000695 2022/09/09 00:39:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 00:39:43 - mmengine - INFO - Saving checkpoint at 22 epochs 2022/09/09 00:40:28 - mmengine - INFO - Epoch(train) [23][50/293] lr: 5.000000e-04 eta: 10:37:21 time: 0.804164 data_time: 0.114543 memory: 21676 loss_kpt: 0.000703 acc_pose: 0.759873 loss: 0.000703 2022/09/09 00:41:06 - mmengine - INFO - Epoch(train) [23][100/293] lr: 5.000000e-04 eta: 10:37:17 time: 0.767583 data_time: 0.103565 memory: 21676 loss_kpt: 0.000695 acc_pose: 0.760604 loss: 0.000695 2022/09/09 00:41:44 - mmengine - INFO - Epoch(train) [23][150/293] lr: 5.000000e-04 eta: 10:37:10 time: 0.762232 data_time: 0.098566 memory: 21676 loss_kpt: 0.000694 acc_pose: 0.760371 loss: 0.000694 2022/09/09 00:42:22 - mmengine - INFO - Epoch(train) [23][200/293] lr: 5.000000e-04 eta: 10:37:00 time: 0.757165 data_time: 0.099930 memory: 21676 loss_kpt: 0.000706 acc_pose: 0.727822 loss: 0.000706 2022/09/09 00:43:00 - mmengine - INFO - Epoch(train) [23][250/293] lr: 5.000000e-04 eta: 10:36:50 time: 0.756646 data_time: 0.099029 memory: 21676 loss_kpt: 0.000706 acc_pose: 0.771994 loss: 0.000706 2022/09/09 00:43:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 00:43:33 - mmengine - INFO - Saving checkpoint at 23 epochs 2022/09/09 00:44:16 - mmengine - INFO - Epoch(train) [24][50/293] lr: 5.000000e-04 eta: 10:32:19 time: 0.785733 data_time: 0.118952 memory: 21676 loss_kpt: 0.000689 acc_pose: 0.793784 loss: 0.000689 2022/09/09 00:44:55 - mmengine - INFO - Epoch(train) [24][100/293] lr: 5.000000e-04 eta: 10:32:17 time: 0.773967 data_time: 0.112011 memory: 21676 loss_kpt: 0.000694 acc_pose: 0.778440 loss: 0.000694 2022/09/09 00:45:33 - mmengine - INFO - Epoch(train) [24][150/293] lr: 5.000000e-04 eta: 10:32:11 time: 0.764730 data_time: 0.107277 memory: 21676 loss_kpt: 0.000673 acc_pose: 0.802213 loss: 0.000673 2022/09/09 00:46:12 - mmengine - INFO - Epoch(train) [24][200/293] lr: 5.000000e-04 eta: 10:32:05 time: 0.768928 data_time: 0.103246 memory: 21676 loss_kpt: 0.000685 acc_pose: 0.813583 loss: 0.000685 2022/09/09 00:46:50 - mmengine - INFO - Epoch(train) [24][250/293] lr: 5.000000e-04 eta: 10:31:58 time: 0.764542 data_time: 0.105566 memory: 21676 loss_kpt: 0.000706 acc_pose: 0.792724 loss: 0.000706 2022/09/09 00:46:58 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 00:47:22 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 00:47:22 - mmengine - INFO - Saving checkpoint at 24 epochs 2022/09/09 00:48:06 - mmengine - INFO - Epoch(train) [25][50/293] lr: 5.000000e-04 eta: 10:27:41 time: 0.792071 data_time: 0.113168 memory: 21676 loss_kpt: 0.000679 acc_pose: 0.830596 loss: 0.000679 2022/09/09 00:48:45 - mmengine - INFO - Epoch(train) [25][100/293] lr: 5.000000e-04 eta: 10:27:41 time: 0.784702 data_time: 0.099286 memory: 21676 loss_kpt: 0.000683 acc_pose: 0.835256 loss: 0.000683 2022/09/09 00:49:23 - mmengine - INFO - Epoch(train) [25][150/293] lr: 5.000000e-04 eta: 10:27:31 time: 0.756828 data_time: 0.100329 memory: 21676 loss_kpt: 0.000687 acc_pose: 0.807705 loss: 0.000687 2022/09/09 00:50:01 - mmengine - INFO - Epoch(train) [25][200/293] lr: 5.000000e-04 eta: 10:27:23 time: 0.763407 data_time: 0.100063 memory: 21676 loss_kpt: 0.000702 acc_pose: 0.761453 loss: 0.000702 2022/09/09 00:50:39 - mmengine - INFO - Epoch(train) [25][250/293] lr: 5.000000e-04 eta: 10:27:13 time: 0.759659 data_time: 0.101054 memory: 21676 loss_kpt: 0.000704 acc_pose: 0.812487 loss: 0.000704 2022/09/09 00:51:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 00:51:11 - mmengine - INFO - Saving checkpoint at 25 epochs 2022/09/09 00:51:55 - mmengine - INFO - Epoch(train) [26][50/293] lr: 5.000000e-04 eta: 10:23:03 time: 0.783673 data_time: 0.113542 memory: 21676 loss_kpt: 0.000686 acc_pose: 0.827204 loss: 0.000686 2022/09/09 00:52:33 - mmengine - INFO - Epoch(train) [26][100/293] lr: 5.000000e-04 eta: 10:22:53 time: 0.758929 data_time: 0.104916 memory: 21676 loss_kpt: 0.000691 acc_pose: 0.807002 loss: 0.000691 2022/09/09 00:53:10 - mmengine - INFO - Epoch(train) [26][150/293] lr: 5.000000e-04 eta: 10:22:41 time: 0.752687 data_time: 0.102471 memory: 21676 loss_kpt: 0.000683 acc_pose: 0.822158 loss: 0.000683 2022/09/09 00:53:48 - mmengine - INFO - Epoch(train) [26][200/293] lr: 5.000000e-04 eta: 10:22:31 time: 0.759335 data_time: 0.100072 memory: 21676 loss_kpt: 0.000711 acc_pose: 0.759579 loss: 0.000711 2022/09/09 00:54:26 - mmengine - INFO - Epoch(train) [26][250/293] lr: 5.000000e-04 eta: 10:22:19 time: 0.755589 data_time: 0.103267 memory: 21676 loss_kpt: 0.000685 acc_pose: 0.796774 loss: 0.000685 2022/09/09 00:54:58 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 00:54:58 - mmengine - INFO - Saving checkpoint at 26 epochs 2022/09/09 00:55:42 - mmengine - INFO - Epoch(train) [27][50/293] lr: 5.000000e-04 eta: 10:18:17 time: 0.781047 data_time: 0.116843 memory: 21676 loss_kpt: 0.000680 acc_pose: 0.796324 loss: 0.000680 2022/09/09 00:56:21 - mmengine - INFO - Epoch(train) [27][100/293] lr: 5.000000e-04 eta: 10:18:11 time: 0.771011 data_time: 0.103751 memory: 21676 loss_kpt: 0.000686 acc_pose: 0.804315 loss: 0.000686 2022/09/09 00:56:59 - mmengine - INFO - Epoch(train) [27][150/293] lr: 5.000000e-04 eta: 10:18:03 time: 0.765751 data_time: 0.103922 memory: 21676 loss_kpt: 0.000693 acc_pose: 0.764527 loss: 0.000693 2022/09/09 00:57:37 - mmengine - INFO - Epoch(train) [27][200/293] lr: 5.000000e-04 eta: 10:17:52 time: 0.757759 data_time: 0.102416 memory: 21676 loss_kpt: 0.000686 acc_pose: 0.845184 loss: 0.000686 2022/09/09 00:58:15 - mmengine - INFO - Epoch(train) [27][250/293] lr: 5.000000e-04 eta: 10:17:42 time: 0.762241 data_time: 0.107309 memory: 21676 loss_kpt: 0.000681 acc_pose: 0.844839 loss: 0.000681 2022/09/09 00:58:47 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 00:58:47 - mmengine - INFO - Saving checkpoint at 27 epochs 2022/09/09 00:59:31 - mmengine - INFO - Epoch(train) [28][50/293] lr: 5.000000e-04 eta: 10:13:49 time: 0.783860 data_time: 0.118426 memory: 21676 loss_kpt: 0.000691 acc_pose: 0.822035 loss: 0.000691 2022/09/09 01:00:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 01:00:08 - mmengine - INFO - Epoch(train) [28][100/293] lr: 5.000000e-04 eta: 10:13:35 time: 0.748125 data_time: 0.099186 memory: 21676 loss_kpt: 0.000680 acc_pose: 0.774606 loss: 0.000680 2022/09/09 01:00:47 - mmengine - INFO - Epoch(train) [28][150/293] lr: 5.000000e-04 eta: 10:13:30 time: 0.774508 data_time: 0.104233 memory: 21676 loss_kpt: 0.000664 acc_pose: 0.748471 loss: 0.000664 2022/09/09 01:01:25 - mmengine - INFO - Epoch(train) [28][200/293] lr: 5.000000e-04 eta: 10:13:18 time: 0.756706 data_time: 0.102216 memory: 21676 loss_kpt: 0.000681 acc_pose: 0.805930 loss: 0.000681 2022/09/09 01:02:03 - mmengine - INFO - Epoch(train) [28][250/293] lr: 5.000000e-04 eta: 10:13:08 time: 0.763678 data_time: 0.097887 memory: 21676 loss_kpt: 0.000679 acc_pose: 0.811382 loss: 0.000679 2022/09/09 01:02:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 01:02:35 - mmengine - INFO - Saving checkpoint at 28 epochs 2022/09/09 01:03:19 - mmengine - INFO - Epoch(train) [29][50/293] lr: 5.000000e-04 eta: 10:09:23 time: 0.785700 data_time: 0.112388 memory: 21676 loss_kpt: 0.000682 acc_pose: 0.819403 loss: 0.000682 2022/09/09 01:03:58 - mmengine - INFO - Epoch(train) [29][100/293] lr: 5.000000e-04 eta: 10:09:18 time: 0.775290 data_time: 0.111748 memory: 21676 loss_kpt: 0.000673 acc_pose: 0.813495 loss: 0.000673 2022/09/09 01:04:36 - mmengine - INFO - Epoch(train) [29][150/293] lr: 5.000000e-04 eta: 10:09:12 time: 0.777205 data_time: 0.105636 memory: 21676 loss_kpt: 0.000667 acc_pose: 0.757880 loss: 0.000667 2022/09/09 01:05:14 - mmengine - INFO - Epoch(train) [29][200/293] lr: 5.000000e-04 eta: 10:09:00 time: 0.759637 data_time: 0.101874 memory: 21676 loss_kpt: 0.000661 acc_pose: 0.832206 loss: 0.000661 2022/09/09 01:05:52 - mmengine - INFO - Epoch(train) [29][250/293] lr: 5.000000e-04 eta: 10:08:46 time: 0.752168 data_time: 0.100781 memory: 21676 loss_kpt: 0.000684 acc_pose: 0.764130 loss: 0.000684 2022/09/09 01:06:24 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 01:06:24 - mmengine - INFO - Saving checkpoint at 29 epochs 2022/09/09 01:07:08 - mmengine - INFO - Epoch(train) [30][50/293] lr: 5.000000e-04 eta: 10:05:10 time: 0.788663 data_time: 0.120152 memory: 21676 loss_kpt: 0.000680 acc_pose: 0.752787 loss: 0.000680 2022/09/09 01:07:46 - mmengine - INFO - Epoch(train) [30][100/293] lr: 5.000000e-04 eta: 10:05:00 time: 0.762954 data_time: 0.100203 memory: 21676 loss_kpt: 0.000678 acc_pose: 0.832066 loss: 0.000678 2022/09/09 01:08:24 - mmengine - INFO - Epoch(train) [30][150/293] lr: 5.000000e-04 eta: 10:04:49 time: 0.763357 data_time: 0.108290 memory: 21676 loss_kpt: 0.000677 acc_pose: 0.774895 loss: 0.000677 2022/09/09 01:09:02 - mmengine - INFO - Epoch(train) [30][200/293] lr: 5.000000e-04 eta: 10:04:34 time: 0.749361 data_time: 0.101962 memory: 21676 loss_kpt: 0.000676 acc_pose: 0.814370 loss: 0.000676 2022/09/09 01:09:40 - mmengine - INFO - Epoch(train) [30][250/293] lr: 5.000000e-04 eta: 10:04:22 time: 0.762484 data_time: 0.110047 memory: 21676 loss_kpt: 0.000681 acc_pose: 0.772859 loss: 0.000681 2022/09/09 01:10:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 01:10:13 - mmengine - INFO - Saving checkpoint at 30 epochs 2022/09/09 01:10:25 - mmengine - INFO - Epoch(val) [30][50/407] eta: 0:00:56 time: 0.157926 data_time: 0.015362 memory: 21676 2022/09/09 01:10:33 - mmengine - INFO - Epoch(val) [30][100/407] eta: 0:00:46 time: 0.150489 data_time: 0.008285 memory: 1375 2022/09/09 01:10:40 - mmengine - INFO - Epoch(val) [30][150/407] eta: 0:00:38 time: 0.150828 data_time: 0.009354 memory: 1375 2022/09/09 01:10:48 - mmengine - INFO - Epoch(val) [30][200/407] eta: 0:00:31 time: 0.149897 data_time: 0.008121 memory: 1375 2022/09/09 01:10:55 - mmengine - INFO - Epoch(val) [30][250/407] eta: 0:00:23 time: 0.150718 data_time: 0.009202 memory: 1375 2022/09/09 01:11:03 - mmengine - INFO - Epoch(val) [30][300/407] eta: 0:00:16 time: 0.153566 data_time: 0.008740 memory: 1375 2022/09/09 01:11:11 - mmengine - INFO - Epoch(val) [30][350/407] eta: 0:00:08 time: 0.151521 data_time: 0.008851 memory: 1375 2022/09/09 01:11:18 - mmengine - INFO - Epoch(val) [30][400/407] eta: 0:00:01 time: 0.148884 data_time: 0.008610 memory: 1375 2022/09/09 01:11:54 - mmengine - INFO - Evaluating CocoMetric... 2022/09/09 01:12:08 - mmengine - INFO - Epoch(val) [30][407/407] coco/AP: 0.718418 coco/AP .5: 0.891641 coco/AP .75: 0.785942 coco/AP (M): 0.681653 coco/AP (L): 0.787032 coco/AR: 0.772402 coco/AR .5: 0.930573 coco/AR .75: 0.834383 coco/AR (M): 0.729227 coco/AR (L): 0.834894 2022/09/09 01:12:08 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220908/hrnet_w32_384/best_coco/AP_epoch_20.pth is removed 2022/09/09 01:12:11 - mmengine - INFO - The best checkpoint with 0.7184 coco/AP at 30 epoch is saved to best_coco/AP_epoch_30.pth. 2022/09/09 01:12:51 - mmengine - INFO - Epoch(train) [31][50/293] lr: 5.000000e-04 eta: 10:00:55 time: 0.795071 data_time: 0.111583 memory: 21676 loss_kpt: 0.000673 acc_pose: 0.809229 loss: 0.000673 2022/09/09 01:13:30 - mmengine - INFO - Epoch(train) [31][100/293] lr: 5.000000e-04 eta: 10:00:52 time: 0.790656 data_time: 0.107849 memory: 21676 loss_kpt: 0.000678 acc_pose: 0.827904 loss: 0.000678 2022/09/09 01:14:09 - mmengine - INFO - Epoch(train) [31][150/293] lr: 5.000000e-04 eta: 10:00:46 time: 0.782173 data_time: 0.104000 memory: 21676 loss_kpt: 0.000673 acc_pose: 0.803843 loss: 0.000673 2022/09/09 01:14:49 - mmengine - INFO - Epoch(train) [31][200/293] lr: 5.000000e-04 eta: 10:00:41 time: 0.785105 data_time: 0.103877 memory: 21676 loss_kpt: 0.000661 acc_pose: 0.823492 loss: 0.000661 2022/09/09 01:14:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 01:15:27 - mmengine - INFO - Epoch(train) [31][250/293] lr: 5.000000e-04 eta: 10:00:31 time: 0.769293 data_time: 0.099522 memory: 21676 loss_kpt: 0.000683 acc_pose: 0.807928 loss: 0.000683 2022/09/09 01:16:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 01:16:00 - mmengine - INFO - Saving checkpoint at 31 epochs 2022/09/09 01:16:44 - mmengine - INFO - Epoch(train) [32][50/293] lr: 5.000000e-04 eta: 9:57:09 time: 0.796000 data_time: 0.110936 memory: 21676 loss_kpt: 0.000664 acc_pose: 0.800662 loss: 0.000664 2022/09/09 01:17:24 - mmengine - INFO - Epoch(train) [32][100/293] lr: 5.000000e-04 eta: 9:57:07 time: 0.796531 data_time: 0.110173 memory: 21676 loss_kpt: 0.000683 acc_pose: 0.750748 loss: 0.000683 2022/09/09 01:18:02 - mmengine - INFO - Epoch(train) [32][150/293] lr: 5.000000e-04 eta: 9:56:54 time: 0.757402 data_time: 0.099628 memory: 21676 loss_kpt: 0.000663 acc_pose: 0.797642 loss: 0.000663 2022/09/09 01:18:40 - mmengine - INFO - Epoch(train) [32][200/293] lr: 5.000000e-04 eta: 9:56:40 time: 0.756933 data_time: 0.099362 memory: 21676 loss_kpt: 0.000666 acc_pose: 0.828669 loss: 0.000666 2022/09/09 01:19:18 - mmengine - INFO - Epoch(train) [32][250/293] lr: 5.000000e-04 eta: 9:56:27 time: 0.762821 data_time: 0.101683 memory: 21676 loss_kpt: 0.000658 acc_pose: 0.867297 loss: 0.000658 2022/09/09 01:19:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 01:19:50 - mmengine - INFO - Saving checkpoint at 32 epochs 2022/09/09 01:20:34 - mmengine - INFO - Epoch(train) [33][50/293] lr: 5.000000e-04 eta: 9:53:13 time: 0.802566 data_time: 0.111205 memory: 21676 loss_kpt: 0.000679 acc_pose: 0.717829 loss: 0.000679 2022/09/09 01:21:12 - mmengine - INFO - Epoch(train) [33][100/293] lr: 5.000000e-04 eta: 9:53:01 time: 0.763779 data_time: 0.106538 memory: 21676 loss_kpt: 0.000663 acc_pose: 0.857937 loss: 0.000663 2022/09/09 01:21:50 - mmengine - INFO - Epoch(train) [33][150/293] lr: 5.000000e-04 eta: 9:52:46 time: 0.753007 data_time: 0.102884 memory: 21676 loss_kpt: 0.000682 acc_pose: 0.809149 loss: 0.000682 2022/09/09 01:22:28 - mmengine - INFO - Epoch(train) [33][200/293] lr: 5.000000e-04 eta: 9:52:30 time: 0.754550 data_time: 0.107328 memory: 21676 loss_kpt: 0.000676 acc_pose: 0.775169 loss: 0.000676 2022/09/09 01:23:06 - mmengine - INFO - Epoch(train) [33][250/293] lr: 5.000000e-04 eta: 9:52:17 time: 0.760248 data_time: 0.106708 memory: 21676 loss_kpt: 0.000683 acc_pose: 0.832575 loss: 0.000683 2022/09/09 01:23:38 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 01:23:38 - mmengine - INFO - Saving checkpoint at 33 epochs 2022/09/09 01:24:22 - mmengine - INFO - Epoch(train) [34][50/293] lr: 5.000000e-04 eta: 9:49:02 time: 0.782877 data_time: 0.120877 memory: 21676 loss_kpt: 0.000663 acc_pose: 0.836357 loss: 0.000663 2022/09/09 01:25:00 - mmengine - INFO - Epoch(train) [34][100/293] lr: 5.000000e-04 eta: 9:48:50 time: 0.763294 data_time: 0.104967 memory: 21676 loss_kpt: 0.000671 acc_pose: 0.824086 loss: 0.000671 2022/09/09 01:25:38 - mmengine - INFO - Epoch(train) [34][150/293] lr: 5.000000e-04 eta: 9:48:38 time: 0.767727 data_time: 0.110050 memory: 21676 loss_kpt: 0.000659 acc_pose: 0.824540 loss: 0.000659 2022/09/09 01:26:16 - mmengine - INFO - Epoch(train) [34][200/293] lr: 5.000000e-04 eta: 9:48:25 time: 0.763911 data_time: 0.101865 memory: 21676 loss_kpt: 0.000667 acc_pose: 0.782155 loss: 0.000667 2022/09/09 01:26:54 - mmengine - INFO - Epoch(train) [34][250/293] lr: 5.000000e-04 eta: 9:48:09 time: 0.754619 data_time: 0.106154 memory: 21676 loss_kpt: 0.000675 acc_pose: 0.780203 loss: 0.000675 2022/09/09 01:27:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 01:27:27 - mmengine - INFO - Saving checkpoint at 34 epochs 2022/09/09 01:28:01 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 01:28:11 - mmengine - INFO - Epoch(train) [35][50/293] lr: 5.000000e-04 eta: 9:45:03 time: 0.795237 data_time: 0.115818 memory: 21676 loss_kpt: 0.000656 acc_pose: 0.828470 loss: 0.000656 2022/09/09 01:28:49 - mmengine - INFO - Epoch(train) [35][100/293] lr: 5.000000e-04 eta: 9:44:53 time: 0.773423 data_time: 0.103281 memory: 21676 loss_kpt: 0.000660 acc_pose: 0.780547 loss: 0.000660 2022/09/09 01:29:27 - mmengine - INFO - Epoch(train) [35][150/293] lr: 5.000000e-04 eta: 9:44:38 time: 0.756482 data_time: 0.103579 memory: 21676 loss_kpt: 0.000659 acc_pose: 0.803234 loss: 0.000659 2022/09/09 01:30:06 - mmengine - INFO - Epoch(train) [35][200/293] lr: 5.000000e-04 eta: 9:44:26 time: 0.771060 data_time: 0.107385 memory: 21676 loss_kpt: 0.000659 acc_pose: 0.803931 loss: 0.000659 2022/09/09 01:30:44 - mmengine - INFO - Epoch(train) [35][250/293] lr: 5.000000e-04 eta: 9:44:11 time: 0.758714 data_time: 0.108625 memory: 21676 loss_kpt: 0.000668 acc_pose: 0.797975 loss: 0.000668 2022/09/09 01:31:16 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 01:31:16 - mmengine - INFO - Saving checkpoint at 35 epochs 2022/09/09 01:32:00 - mmengine - INFO - Epoch(train) [36][50/293] lr: 5.000000e-04 eta: 9:41:11 time: 0.800931 data_time: 0.116728 memory: 21676 loss_kpt: 0.000664 acc_pose: 0.802338 loss: 0.000664 2022/09/09 01:32:38 - mmengine - INFO - Epoch(train) [36][100/293] lr: 5.000000e-04 eta: 9:40:57 time: 0.762891 data_time: 0.104211 memory: 21676 loss_kpt: 0.000669 acc_pose: 0.801641 loss: 0.000669 2022/09/09 01:33:16 - mmengine - INFO - Epoch(train) [36][150/293] lr: 5.000000e-04 eta: 9:40:42 time: 0.758579 data_time: 0.108297 memory: 21676 loss_kpt: 0.000653 acc_pose: 0.859011 loss: 0.000653 2022/09/09 01:33:54 - mmengine - INFO - Epoch(train) [36][200/293] lr: 5.000000e-04 eta: 9:40:26 time: 0.757407 data_time: 0.107652 memory: 21676 loss_kpt: 0.000672 acc_pose: 0.826940 loss: 0.000672 2022/09/09 01:34:32 - mmengine - INFO - Epoch(train) [36][250/293] lr: 5.000000e-04 eta: 9:40:10 time: 0.755235 data_time: 0.101970 memory: 21676 loss_kpt: 0.000669 acc_pose: 0.787123 loss: 0.000669 2022/09/09 01:35:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 01:35:04 - mmengine - INFO - Saving checkpoint at 36 epochs 2022/09/09 01:35:49 - mmengine - INFO - Epoch(train) [37][50/293] lr: 5.000000e-04 eta: 9:37:13 time: 0.794600 data_time: 0.112013 memory: 21676 loss_kpt: 0.000656 acc_pose: 0.831629 loss: 0.000656 2022/09/09 01:36:26 - mmengine - INFO - Epoch(train) [37][100/293] lr: 5.000000e-04 eta: 9:36:56 time: 0.752956 data_time: 0.103482 memory: 21676 loss_kpt: 0.000660 acc_pose: 0.829727 loss: 0.000660 2022/09/09 01:37:04 - mmengine - INFO - Epoch(train) [37][150/293] lr: 5.000000e-04 eta: 9:36:41 time: 0.759113 data_time: 0.102698 memory: 21676 loss_kpt: 0.000653 acc_pose: 0.829905 loss: 0.000653 2022/09/09 01:37:42 - mmengine - INFO - Epoch(train) [37][200/293] lr: 5.000000e-04 eta: 9:36:25 time: 0.756047 data_time: 0.111785 memory: 21676 loss_kpt: 0.000649 acc_pose: 0.823759 loss: 0.000649 2022/09/09 01:38:20 - mmengine - INFO - Epoch(train) [37][250/293] lr: 5.000000e-04 eta: 9:36:06 time: 0.749114 data_time: 0.099926 memory: 21676 loss_kpt: 0.000670 acc_pose: 0.789732 loss: 0.000670 2022/09/09 01:38:52 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 01:38:52 - mmengine - INFO - Saving checkpoint at 37 epochs 2022/09/09 01:39:35 - mmengine - INFO - Epoch(train) [38][50/293] lr: 5.000000e-04 eta: 9:33:09 time: 0.776045 data_time: 0.115160 memory: 21676 loss_kpt: 0.000651 acc_pose: 0.836559 loss: 0.000651 2022/09/09 01:40:13 - mmengine - INFO - Epoch(train) [38][100/293] lr: 5.000000e-04 eta: 9:32:53 time: 0.757365 data_time: 0.103125 memory: 21676 loss_kpt: 0.000652 acc_pose: 0.811262 loss: 0.000652 2022/09/09 01:40:51 - mmengine - INFO - Epoch(train) [38][150/293] lr: 5.000000e-04 eta: 9:32:36 time: 0.752054 data_time: 0.106691 memory: 21676 loss_kpt: 0.000659 acc_pose: 0.832078 loss: 0.000659 2022/09/09 01:40:58 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 01:41:29 - mmengine - INFO - Epoch(train) [38][200/293] lr: 5.000000e-04 eta: 9:32:19 time: 0.754609 data_time: 0.107451 memory: 21676 loss_kpt: 0.000657 acc_pose: 0.813240 loss: 0.000657 2022/09/09 01:42:06 - mmengine - INFO - Epoch(train) [38][250/293] lr: 5.000000e-04 eta: 9:32:01 time: 0.753182 data_time: 0.100769 memory: 21676 loss_kpt: 0.000646 acc_pose: 0.846916 loss: 0.000646 2022/09/09 01:42:38 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 01:42:38 - mmengine - INFO - Saving checkpoint at 38 epochs 2022/09/09 01:43:21 - mmengine - INFO - Epoch(train) [39][50/293] lr: 5.000000e-04 eta: 9:29:04 time: 0.758633 data_time: 0.113695 memory: 21676 loss_kpt: 0.000646 acc_pose: 0.801743 loss: 0.000646 2022/09/09 01:43:59 - mmengine - INFO - Epoch(train) [39][100/293] lr: 5.000000e-04 eta: 9:28:47 time: 0.754382 data_time: 0.099049 memory: 21676 loss_kpt: 0.000649 acc_pose: 0.838664 loss: 0.000649 2022/09/09 01:44:37 - mmengine - INFO - Epoch(train) [39][150/293] lr: 5.000000e-04 eta: 9:28:31 time: 0.759400 data_time: 0.103161 memory: 21676 loss_kpt: 0.000659 acc_pose: 0.807714 loss: 0.000659 2022/09/09 01:45:15 - mmengine - INFO - Epoch(train) [39][200/293] lr: 5.000000e-04 eta: 9:28:15 time: 0.760905 data_time: 0.103368 memory: 21676 loss_kpt: 0.000654 acc_pose: 0.810561 loss: 0.000654 2022/09/09 01:45:52 - mmengine - INFO - Epoch(train) [39][250/293] lr: 5.000000e-04 eta: 9:27:58 time: 0.754335 data_time: 0.113306 memory: 21676 loss_kpt: 0.000652 acc_pose: 0.813976 loss: 0.000652 2022/09/09 01:46:25 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 01:46:25 - mmengine - INFO - Saving checkpoint at 39 epochs 2022/09/09 01:47:09 - mmengine - INFO - Epoch(train) [40][50/293] lr: 5.000000e-04 eta: 9:25:10 time: 0.783739 data_time: 0.108410 memory: 21676 loss_kpt: 0.000650 acc_pose: 0.797902 loss: 0.000650 2022/09/09 01:47:47 - mmengine - INFO - Epoch(train) [40][100/293] lr: 5.000000e-04 eta: 9:24:54 time: 0.759123 data_time: 0.106511 memory: 21676 loss_kpt: 0.000659 acc_pose: 0.794320 loss: 0.000659 2022/09/09 01:48:24 - mmengine - INFO - Epoch(train) [40][150/293] lr: 5.000000e-04 eta: 9:24:36 time: 0.751971 data_time: 0.100893 memory: 21676 loss_kpt: 0.000645 acc_pose: 0.795911 loss: 0.000645 2022/09/09 01:49:02 - mmengine - INFO - Epoch(train) [40][200/293] lr: 5.000000e-04 eta: 9:24:19 time: 0.757436 data_time: 0.106538 memory: 21676 loss_kpt: 0.000640 acc_pose: 0.833223 loss: 0.000640 2022/09/09 01:49:40 - mmengine - INFO - Epoch(train) [40][250/293] lr: 5.000000e-04 eta: 9:24:02 time: 0.758127 data_time: 0.099657 memory: 21676 loss_kpt: 0.000649 acc_pose: 0.804037 loss: 0.000649 2022/09/09 01:50:12 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 01:50:12 - mmengine - INFO - Saving checkpoint at 40 epochs 2022/09/09 01:50:24 - mmengine - INFO - Epoch(val) [40][50/407] eta: 0:00:58 time: 0.163281 data_time: 0.021450 memory: 21676 2022/09/09 01:50:32 - mmengine - INFO - Epoch(val) [40][100/407] eta: 0:00:46 time: 0.150709 data_time: 0.008878 memory: 1375 2022/09/09 01:50:40 - mmengine - INFO - Epoch(val) [40][150/407] eta: 0:00:42 time: 0.166335 data_time: 0.023931 memory: 1375 2022/09/09 01:50:48 - mmengine - INFO - Epoch(val) [40][200/407] eta: 0:00:31 time: 0.151390 data_time: 0.009132 memory: 1375 2022/09/09 01:50:55 - mmengine - INFO - Epoch(val) [40][250/407] eta: 0:00:23 time: 0.151241 data_time: 0.008853 memory: 1375 2022/09/09 01:51:03 - mmengine - INFO - Epoch(val) [40][300/407] eta: 0:00:16 time: 0.152298 data_time: 0.010256 memory: 1375 2022/09/09 01:51:10 - mmengine - INFO - Epoch(val) [40][350/407] eta: 0:00:08 time: 0.151880 data_time: 0.008648 memory: 1375 2022/09/09 01:51:18 - mmengine - INFO - Epoch(val) [40][400/407] eta: 0:00:01 time: 0.148923 data_time: 0.008290 memory: 1375 2022/09/09 01:51:54 - mmengine - INFO - Evaluating CocoMetric... 2022/09/09 01:52:08 - mmengine - INFO - Epoch(val) [40][407/407] coco/AP: 0.729095 coco/AP .5: 0.894195 coco/AP .75: 0.799032 coco/AP (M): 0.688482 coco/AP (L): 0.800478 coco/AR: 0.780762 coco/AR .5: 0.931675 coco/AR .75: 0.843356 coco/AR (M): 0.734854 coco/AR (L): 0.846897 2022/09/09 01:52:08 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220908/hrnet_w32_384/best_coco/AP_epoch_30.pth is removed 2022/09/09 01:52:12 - mmengine - INFO - The best checkpoint with 0.7291 coco/AP at 40 epoch is saved to best_coco/AP_epoch_40.pth. 2022/09/09 01:52:50 - mmengine - INFO - Epoch(train) [41][50/293] lr: 5.000000e-04 eta: 9:21:16 time: 0.773159 data_time: 0.108887 memory: 21676 loss_kpt: 0.000648 acc_pose: 0.863368 loss: 0.000648 2022/09/09 01:53:28 - mmengine - INFO - Epoch(train) [41][100/293] lr: 5.000000e-04 eta: 9:20:59 time: 0.760505 data_time: 0.104469 memory: 21676 loss_kpt: 0.000650 acc_pose: 0.829627 loss: 0.000650 2022/09/09 01:54:06 - mmengine - INFO - Epoch(train) [41][150/293] lr: 5.000000e-04 eta: 9:20:42 time: 0.754071 data_time: 0.101382 memory: 21676 loss_kpt: 0.000657 acc_pose: 0.793355 loss: 0.000657 2022/09/09 01:54:44 - mmengine - INFO - Epoch(train) [41][200/293] lr: 5.000000e-04 eta: 9:20:25 time: 0.758526 data_time: 0.109263 memory: 21676 loss_kpt: 0.000642 acc_pose: 0.834117 loss: 0.000642 2022/09/09 01:55:22 - mmengine - INFO - Epoch(train) [41][250/293] lr: 5.000000e-04 eta: 9:20:07 time: 0.754862 data_time: 0.105637 memory: 21676 loss_kpt: 0.000651 acc_pose: 0.790946 loss: 0.000651 2022/09/09 01:55:45 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 01:55:54 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 01:55:54 - mmengine - INFO - Saving checkpoint at 41 epochs 2022/09/09 01:56:38 - mmengine - INFO - Epoch(train) [42][50/293] lr: 5.000000e-04 eta: 9:17:27 time: 0.791375 data_time: 0.121306 memory: 21676 loss_kpt: 0.000639 acc_pose: 0.795556 loss: 0.000639 2022/09/09 01:57:16 - mmengine - INFO - Epoch(train) [42][100/293] lr: 5.000000e-04 eta: 9:17:12 time: 0.766993 data_time: 0.105900 memory: 21676 loss_kpt: 0.000639 acc_pose: 0.821229 loss: 0.000639 2022/09/09 01:57:54 - mmengine - INFO - Epoch(train) [42][150/293] lr: 5.000000e-04 eta: 9:16:54 time: 0.755471 data_time: 0.105334 memory: 21676 loss_kpt: 0.000642 acc_pose: 0.827966 loss: 0.000642 2022/09/09 01:58:32 - mmengine - INFO - Epoch(train) [42][200/293] lr: 5.000000e-04 eta: 9:16:38 time: 0.765068 data_time: 0.105432 memory: 21676 loss_kpt: 0.000645 acc_pose: 0.790940 loss: 0.000645 2022/09/09 01:59:10 - mmengine - INFO - Epoch(train) [42][250/293] lr: 5.000000e-04 eta: 9:16:19 time: 0.749105 data_time: 0.101977 memory: 21676 loss_kpt: 0.000640 acc_pose: 0.797609 loss: 0.000640 2022/09/09 01:59:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 01:59:42 - mmengine - INFO - Saving checkpoint at 42 epochs 2022/09/09 02:00:27 - mmengine - INFO - Epoch(train) [43][50/293] lr: 5.000000e-04 eta: 9:13:46 time: 0.808477 data_time: 0.116951 memory: 21676 loss_kpt: 0.000641 acc_pose: 0.808670 loss: 0.000641 2022/09/09 02:01:05 - mmengine - INFO - Epoch(train) [43][100/293] lr: 5.000000e-04 eta: 9:13:28 time: 0.758009 data_time: 0.103689 memory: 21676 loss_kpt: 0.000648 acc_pose: 0.757523 loss: 0.000648 2022/09/09 02:01:44 - mmengine - INFO - Epoch(train) [43][150/293] lr: 5.000000e-04 eta: 9:13:13 time: 0.770163 data_time: 0.104875 memory: 21676 loss_kpt: 0.000635 acc_pose: 0.825140 loss: 0.000635 2022/09/09 02:02:21 - mmengine - INFO - Epoch(train) [43][200/293] lr: 5.000000e-04 eta: 9:12:54 time: 0.753374 data_time: 0.102976 memory: 21676 loss_kpt: 0.000644 acc_pose: 0.814755 loss: 0.000644 2022/09/09 02:02:59 - mmengine - INFO - Epoch(train) [43][250/293] lr: 5.000000e-04 eta: 9:12:37 time: 0.760114 data_time: 0.103951 memory: 21676 loss_kpt: 0.000631 acc_pose: 0.762281 loss: 0.000631 2022/09/09 02:03:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 02:03:32 - mmengine - INFO - Saving checkpoint at 43 epochs 2022/09/09 02:04:15 - mmengine - INFO - Epoch(train) [44][50/293] lr: 5.000000e-04 eta: 9:10:02 time: 0.783036 data_time: 0.113811 memory: 21676 loss_kpt: 0.000629 acc_pose: 0.790420 loss: 0.000629 2022/09/09 02:04:54 - mmengine - INFO - Epoch(train) [44][100/293] lr: 5.000000e-04 eta: 9:09:47 time: 0.771274 data_time: 0.108129 memory: 21676 loss_kpt: 0.000646 acc_pose: 0.845414 loss: 0.000646 2022/09/09 02:05:32 - mmengine - INFO - Epoch(train) [44][150/293] lr: 5.000000e-04 eta: 9:09:31 time: 0.769032 data_time: 0.106118 memory: 21676 loss_kpt: 0.000653 acc_pose: 0.808044 loss: 0.000653 2022/09/09 02:06:11 - mmengine - INFO - Epoch(train) [44][200/293] lr: 5.000000e-04 eta: 9:09:15 time: 0.772779 data_time: 0.109327 memory: 21676 loss_kpt: 0.000645 acc_pose: 0.823163 loss: 0.000645 2022/09/09 02:06:49 - mmengine - INFO - Epoch(train) [44][250/293] lr: 5.000000e-04 eta: 9:08:56 time: 0.752963 data_time: 0.105543 memory: 21676 loss_kpt: 0.000651 acc_pose: 0.839993 loss: 0.000651 2022/09/09 02:07:21 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 02:07:21 - mmengine - INFO - Saving checkpoint at 44 epochs 2022/09/09 02:08:05 - mmengine - INFO - Epoch(train) [45][50/293] lr: 5.000000e-04 eta: 9:06:24 time: 0.783834 data_time: 0.109645 memory: 21676 loss_kpt: 0.000645 acc_pose: 0.821489 loss: 0.000645 2022/09/09 02:08:43 - mmengine - INFO - Epoch(train) [45][100/293] lr: 5.000000e-04 eta: 9:06:08 time: 0.767340 data_time: 0.109703 memory: 21676 loss_kpt: 0.000642 acc_pose: 0.851136 loss: 0.000642 2022/09/09 02:08:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 02:09:21 - mmengine - INFO - Epoch(train) [45][150/293] lr: 5.000000e-04 eta: 9:05:50 time: 0.762704 data_time: 0.099683 memory: 21676 loss_kpt: 0.000640 acc_pose: 0.825648 loss: 0.000640 2022/09/09 02:09:59 - mmengine - INFO - Epoch(train) [45][200/293] lr: 5.000000e-04 eta: 9:05:32 time: 0.758310 data_time: 0.109257 memory: 21676 loss_kpt: 0.000654 acc_pose: 0.804233 loss: 0.000654 2022/09/09 02:10:37 - mmengine - INFO - Epoch(train) [45][250/293] lr: 5.000000e-04 eta: 9:05:12 time: 0.752591 data_time: 0.103842 memory: 21676 loss_kpt: 0.000643 acc_pose: 0.755449 loss: 0.000643 2022/09/09 02:11:09 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 02:11:09 - mmengine - INFO - Saving checkpoint at 45 epochs 2022/09/09 02:11:53 - mmengine - INFO - Epoch(train) [46][50/293] lr: 5.000000e-04 eta: 9:02:45 time: 0.797434 data_time: 0.123916 memory: 21676 loss_kpt: 0.000630 acc_pose: 0.814936 loss: 0.000630 2022/09/09 02:12:32 - mmengine - INFO - Epoch(train) [46][100/293] lr: 5.000000e-04 eta: 9:02:32 time: 0.785719 data_time: 0.104650 memory: 21676 loss_kpt: 0.000635 acc_pose: 0.765166 loss: 0.000635 2022/09/09 02:13:11 - mmengine - INFO - Epoch(train) [46][150/293] lr: 5.000000e-04 eta: 9:02:15 time: 0.768137 data_time: 0.100156 memory: 21676 loss_kpt: 0.000642 acc_pose: 0.813667 loss: 0.000642 2022/09/09 02:13:49 - mmengine - INFO - Epoch(train) [46][200/293] lr: 5.000000e-04 eta: 9:01:59 time: 0.773556 data_time: 0.109581 memory: 21676 loss_kpt: 0.000630 acc_pose: 0.761474 loss: 0.000630 2022/09/09 02:14:27 - mmengine - INFO - Epoch(train) [46][250/293] lr: 5.000000e-04 eta: 9:01:40 time: 0.756222 data_time: 0.102935 memory: 21676 loss_kpt: 0.000636 acc_pose: 0.769134 loss: 0.000636 2022/09/09 02:14:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 02:14:59 - mmengine - INFO - Saving checkpoint at 46 epochs 2022/09/09 02:15:43 - mmengine - INFO - Epoch(train) [47][50/293] lr: 5.000000e-04 eta: 8:59:14 time: 0.793228 data_time: 0.123771 memory: 21676 loss_kpt: 0.000625 acc_pose: 0.832527 loss: 0.000625 2022/09/09 02:16:22 - mmengine - INFO - Epoch(train) [47][100/293] lr: 5.000000e-04 eta: 8:59:01 time: 0.787790 data_time: 0.100504 memory: 21676 loss_kpt: 0.000641 acc_pose: 0.830328 loss: 0.000641 2022/09/09 02:17:00 - mmengine - INFO - Epoch(train) [47][150/293] lr: 5.000000e-04 eta: 8:58:43 time: 0.762355 data_time: 0.108755 memory: 21676 loss_kpt: 0.000639 acc_pose: 0.831876 loss: 0.000639 2022/09/09 02:17:38 - mmengine - INFO - Epoch(train) [47][200/293] lr: 5.000000e-04 eta: 8:58:22 time: 0.751665 data_time: 0.105780 memory: 21676 loss_kpt: 0.000635 acc_pose: 0.803127 loss: 0.000635 2022/09/09 02:18:16 - mmengine - INFO - Epoch(train) [47][250/293] lr: 5.000000e-04 eta: 8:58:03 time: 0.758337 data_time: 0.105876 memory: 21676 loss_kpt: 0.000623 acc_pose: 0.818336 loss: 0.000623 2022/09/09 02:18:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 02:18:49 - mmengine - INFO - Saving checkpoint at 47 epochs 2022/09/09 02:19:33 - mmengine - INFO - Epoch(train) [48][50/293] lr: 5.000000e-04 eta: 8:55:39 time: 0.785173 data_time: 0.118748 memory: 21676 loss_kpt: 0.000641 acc_pose: 0.824895 loss: 0.000641 2022/09/09 02:20:12 - mmengine - INFO - Epoch(train) [48][100/293] lr: 5.000000e-04 eta: 8:55:24 time: 0.785374 data_time: 0.111768 memory: 21676 loss_kpt: 0.000627 acc_pose: 0.830100 loss: 0.000627 2022/09/09 02:20:51 - mmengine - INFO - Epoch(train) [48][150/293] lr: 5.000000e-04 eta: 8:55:08 time: 0.776033 data_time: 0.116714 memory: 21676 loss_kpt: 0.000644 acc_pose: 0.834646 loss: 0.000644 2022/09/09 02:21:29 - mmengine - INFO - Epoch(train) [48][200/293] lr: 5.000000e-04 eta: 8:54:50 time: 0.764433 data_time: 0.107822 memory: 21676 loss_kpt: 0.000643 acc_pose: 0.834210 loss: 0.000643 2022/09/09 02:21:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 02:22:06 - mmengine - INFO - Epoch(train) [48][250/293] lr: 5.000000e-04 eta: 8:54:28 time: 0.744799 data_time: 0.103839 memory: 21676 loss_kpt: 0.000631 acc_pose: 0.819619 loss: 0.000631 2022/09/09 02:22:39 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 02:22:39 - mmengine - INFO - Saving checkpoint at 48 epochs 2022/09/09 02:23:22 - mmengine - INFO - Epoch(train) [49][50/293] lr: 5.000000e-04 eta: 8:52:07 time: 0.792702 data_time: 0.113710 memory: 21676 loss_kpt: 0.000628 acc_pose: 0.770590 loss: 0.000628 2022/09/09 02:24:00 - mmengine - INFO - Epoch(train) [49][100/293] lr: 5.000000e-04 eta: 8:51:46 time: 0.746998 data_time: 0.109604 memory: 21676 loss_kpt: 0.000644 acc_pose: 0.861401 loss: 0.000644 2022/09/09 02:24:38 - mmengine - INFO - Epoch(train) [49][150/293] lr: 5.000000e-04 eta: 8:51:27 time: 0.760295 data_time: 0.110921 memory: 21676 loss_kpt: 0.000658 acc_pose: 0.808553 loss: 0.000658 2022/09/09 02:25:15 - mmengine - INFO - Epoch(train) [49][200/293] lr: 5.000000e-04 eta: 8:51:06 time: 0.753888 data_time: 0.100242 memory: 21676 loss_kpt: 0.000630 acc_pose: 0.839109 loss: 0.000630 2022/09/09 02:25:53 - mmengine - INFO - Epoch(train) [49][250/293] lr: 5.000000e-04 eta: 8:50:47 time: 0.760218 data_time: 0.102239 memory: 21676 loss_kpt: 0.000635 acc_pose: 0.783136 loss: 0.000635 2022/09/09 02:26:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 02:26:26 - mmengine - INFO - Saving checkpoint at 49 epochs 2022/09/09 02:27:08 - mmengine - INFO - Epoch(train) [50][50/293] lr: 5.000000e-04 eta: 8:48:25 time: 0.768667 data_time: 0.108118 memory: 21676 loss_kpt: 0.000634 acc_pose: 0.838743 loss: 0.000634 2022/09/09 02:27:47 - mmengine - INFO - Epoch(train) [50][100/293] lr: 5.000000e-04 eta: 8:48:05 time: 0.761271 data_time: 0.110275 memory: 21676 loss_kpt: 0.000631 acc_pose: 0.848030 loss: 0.000631 2022/09/09 02:28:25 - mmengine - INFO - Epoch(train) [50][150/293] lr: 5.000000e-04 eta: 8:47:47 time: 0.768701 data_time: 0.103928 memory: 21676 loss_kpt: 0.000634 acc_pose: 0.847920 loss: 0.000634 2022/09/09 02:29:03 - mmengine - INFO - Epoch(train) [50][200/293] lr: 5.000000e-04 eta: 8:47:26 time: 0.753965 data_time: 0.107106 memory: 21676 loss_kpt: 0.000634 acc_pose: 0.851216 loss: 0.000634 2022/09/09 02:29:41 - mmengine - INFO - Epoch(train) [50][250/293] lr: 5.000000e-04 eta: 8:47:07 time: 0.762737 data_time: 0.113328 memory: 21676 loss_kpt: 0.000643 acc_pose: 0.774501 loss: 0.000643 2022/09/09 02:30:14 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 02:30:14 - mmengine - INFO - Saving checkpoint at 50 epochs 2022/09/09 02:30:26 - mmengine - INFO - Epoch(val) [50][50/407] eta: 0:00:57 time: 0.161876 data_time: 0.017316 memory: 21676 2022/09/09 02:30:33 - mmengine - INFO - Epoch(val) [50][100/407] eta: 0:00:46 time: 0.150599 data_time: 0.008402 memory: 1375 2022/09/09 02:30:41 - mmengine - INFO - Epoch(val) [50][150/407] eta: 0:00:38 time: 0.149393 data_time: 0.008415 memory: 1375 2022/09/09 02:30:48 - mmengine - INFO - Epoch(val) [50][200/407] eta: 0:00:31 time: 0.151575 data_time: 0.009553 memory: 1375 2022/09/09 02:30:56 - mmengine - INFO - Epoch(val) [50][250/407] eta: 0:00:23 time: 0.152652 data_time: 0.009532 memory: 1375 2022/09/09 02:31:03 - mmengine - INFO - Epoch(val) [50][300/407] eta: 0:00:16 time: 0.149721 data_time: 0.008520 memory: 1375 2022/09/09 02:31:11 - mmengine - INFO - Epoch(val) [50][350/407] eta: 0:00:08 time: 0.149925 data_time: 0.008343 memory: 1375 2022/09/09 02:31:18 - mmengine - INFO - Epoch(val) [50][400/407] eta: 0:00:01 time: 0.149868 data_time: 0.008341 memory: 1375 2022/09/09 02:31:56 - mmengine - INFO - Evaluating CocoMetric... 2022/09/09 02:32:10 - mmengine - INFO - Epoch(val) [50][407/407] coco/AP: 0.732052 coco/AP .5: 0.897760 coco/AP .75: 0.800484 coco/AP (M): 0.692484 coco/AP (L): 0.802984 coco/AR: 0.784399 coco/AR .5: 0.934666 coco/AR .75: 0.845560 coco/AR (M): 0.739689 coco/AR (L): 0.849015 2022/09/09 02:32:10 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220908/hrnet_w32_384/best_coco/AP_epoch_40.pth is removed 2022/09/09 02:32:13 - mmengine - INFO - The best checkpoint with 0.7321 coco/AP at 50 epoch is saved to best_coco/AP_epoch_50.pth. 2022/09/09 02:32:51 - mmengine - INFO - Epoch(train) [51][50/293] lr: 5.000000e-04 eta: 8:44:48 time: 0.774682 data_time: 0.117639 memory: 21676 loss_kpt: 0.000624 acc_pose: 0.816045 loss: 0.000624 2022/09/09 02:33:29 - mmengine - INFO - Epoch(train) [51][100/293] lr: 5.000000e-04 eta: 8:44:28 time: 0.757961 data_time: 0.102569 memory: 21676 loss_kpt: 0.000632 acc_pose: 0.794720 loss: 0.000632 2022/09/09 02:34:08 - mmengine - INFO - Epoch(train) [51][150/293] lr: 5.000000e-04 eta: 8:44:09 time: 0.763177 data_time: 0.102307 memory: 21676 loss_kpt: 0.000620 acc_pose: 0.826921 loss: 0.000620 2022/09/09 02:34:45 - mmengine - INFO - Epoch(train) [51][200/293] lr: 5.000000e-04 eta: 8:43:47 time: 0.750835 data_time: 0.099727 memory: 21676 loss_kpt: 0.000640 acc_pose: 0.805760 loss: 0.000640 2022/09/09 02:35:23 - mmengine - INFO - Epoch(train) [51][250/293] lr: 5.000000e-04 eta: 8:43:27 time: 0.759448 data_time: 0.110777 memory: 21676 loss_kpt: 0.000642 acc_pose: 0.787349 loss: 0.000642 2022/09/09 02:35:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 02:35:56 - mmengine - INFO - Saving checkpoint at 51 epochs 2022/09/09 02:36:39 - mmengine - INFO - Epoch(train) [52][50/293] lr: 5.000000e-04 eta: 8:41:11 time: 0.782475 data_time: 0.114474 memory: 21676 loss_kpt: 0.000635 acc_pose: 0.777018 loss: 0.000635 2022/09/09 02:36:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 02:37:18 - mmengine - INFO - Epoch(train) [52][100/293] lr: 5.000000e-04 eta: 8:40:54 time: 0.778302 data_time: 0.107165 memory: 21676 loss_kpt: 0.000639 acc_pose: 0.804517 loss: 0.000639 2022/09/09 02:37:57 - mmengine - INFO - Epoch(train) [52][150/293] lr: 5.000000e-04 eta: 8:40:38 time: 0.787685 data_time: 0.104769 memory: 21676 loss_kpt: 0.000624 acc_pose: 0.854344 loss: 0.000624 2022/09/09 02:38:36 - mmengine - INFO - Epoch(train) [52][200/293] lr: 5.000000e-04 eta: 8:40:22 time: 0.786072 data_time: 0.103616 memory: 21676 loss_kpt: 0.000643 acc_pose: 0.799561 loss: 0.000643 2022/09/09 02:39:15 - mmengine - INFO - Epoch(train) [52][250/293] lr: 5.000000e-04 eta: 8:40:04 time: 0.772058 data_time: 0.108640 memory: 21676 loss_kpt: 0.000622 acc_pose: 0.882233 loss: 0.000622 2022/09/09 02:39:47 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 02:39:47 - mmengine - INFO - Saving checkpoint at 52 epochs 2022/09/09 02:40:32 - mmengine - INFO - Epoch(train) [53][50/293] lr: 5.000000e-04 eta: 8:37:52 time: 0.798804 data_time: 0.118884 memory: 21676 loss_kpt: 0.000637 acc_pose: 0.839944 loss: 0.000637 2022/09/09 02:41:10 - mmengine - INFO - Epoch(train) [53][100/293] lr: 5.000000e-04 eta: 8:37:34 time: 0.770185 data_time: 0.102322 memory: 21676 loss_kpt: 0.000640 acc_pose: 0.796665 loss: 0.000640 2022/09/09 02:41:48 - mmengine - INFO - Epoch(train) [53][150/293] lr: 5.000000e-04 eta: 8:37:12 time: 0.754881 data_time: 0.098653 memory: 21676 loss_kpt: 0.000635 acc_pose: 0.801635 loss: 0.000635 2022/09/09 02:42:26 - mmengine - INFO - Epoch(train) [53][200/293] lr: 5.000000e-04 eta: 8:36:52 time: 0.761404 data_time: 0.108958 memory: 21676 loss_kpt: 0.000627 acc_pose: 0.813233 loss: 0.000627 2022/09/09 02:43:05 - mmengine - INFO - Epoch(train) [53][250/293] lr: 5.000000e-04 eta: 8:36:33 time: 0.770015 data_time: 0.103512 memory: 21676 loss_kpt: 0.000635 acc_pose: 0.828394 loss: 0.000635 2022/09/09 02:43:37 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 02:43:37 - mmengine - INFO - Saving checkpoint at 53 epochs 2022/09/09 02:44:21 - mmengine - INFO - Epoch(train) [54][50/293] lr: 5.000000e-04 eta: 8:34:21 time: 0.783048 data_time: 0.106901 memory: 21676 loss_kpt: 0.000634 acc_pose: 0.803053 loss: 0.000634 2022/09/09 02:45:00 - mmengine - INFO - Epoch(train) [54][100/293] lr: 5.000000e-04 eta: 8:34:03 time: 0.779184 data_time: 0.103968 memory: 21676 loss_kpt: 0.000622 acc_pose: 0.799277 loss: 0.000622 2022/09/09 02:45:38 - mmengine - INFO - Epoch(train) [54][150/293] lr: 5.000000e-04 eta: 8:33:44 time: 0.770755 data_time: 0.111636 memory: 21676 loss_kpt: 0.000628 acc_pose: 0.868306 loss: 0.000628 2022/09/09 02:46:17 - mmengine - INFO - Epoch(train) [54][200/293] lr: 5.000000e-04 eta: 8:33:25 time: 0.774168 data_time: 0.107084 memory: 21676 loss_kpt: 0.000641 acc_pose: 0.817178 loss: 0.000641 2022/09/09 02:46:55 - mmengine - INFO - Epoch(train) [54][250/293] lr: 5.000000e-04 eta: 8:33:05 time: 0.761968 data_time: 0.110530 memory: 21676 loss_kpt: 0.000627 acc_pose: 0.780099 loss: 0.000627 2022/09/09 02:47:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 02:47:27 - mmengine - INFO - Saving checkpoint at 54 epochs 2022/09/09 02:48:12 - mmengine - INFO - Epoch(train) [55][50/293] lr: 5.000000e-04 eta: 8:30:57 time: 0.796114 data_time: 0.112538 memory: 21676 loss_kpt: 0.000624 acc_pose: 0.833211 loss: 0.000624 2022/09/09 02:48:50 - mmengine - INFO - Epoch(train) [55][100/293] lr: 5.000000e-04 eta: 8:30:36 time: 0.759650 data_time: 0.101654 memory: 21676 loss_kpt: 0.000626 acc_pose: 0.808307 loss: 0.000626 2022/09/09 02:49:27 - mmengine - INFO - Epoch(train) [55][150/293] lr: 5.000000e-04 eta: 8:30:14 time: 0.754077 data_time: 0.107676 memory: 21676 loss_kpt: 0.000618 acc_pose: 0.779237 loss: 0.000618 2022/09/09 02:49:48 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 02:50:05 - mmengine - INFO - Epoch(train) [55][200/293] lr: 5.000000e-04 eta: 8:29:51 time: 0.750393 data_time: 0.103289 memory: 21676 loss_kpt: 0.000612 acc_pose: 0.777985 loss: 0.000612 2022/09/09 02:50:43 - mmengine - INFO - Epoch(train) [55][250/293] lr: 5.000000e-04 eta: 8:29:30 time: 0.756314 data_time: 0.108059 memory: 21676 loss_kpt: 0.000620 acc_pose: 0.822224 loss: 0.000620 2022/09/09 02:51:16 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 02:51:16 - mmengine - INFO - Saving checkpoint at 55 epochs 2022/09/09 02:51:59 - mmengine - INFO - Epoch(train) [56][50/293] lr: 5.000000e-04 eta: 8:27:21 time: 0.777572 data_time: 0.112873 memory: 21676 loss_kpt: 0.000624 acc_pose: 0.810518 loss: 0.000624 2022/09/09 02:52:37 - mmengine - INFO - Epoch(train) [56][100/293] lr: 5.000000e-04 eta: 8:26:59 time: 0.756259 data_time: 0.104939 memory: 21676 loss_kpt: 0.000636 acc_pose: 0.820186 loss: 0.000636 2022/09/09 02:53:15 - mmengine - INFO - Epoch(train) [56][150/293] lr: 5.000000e-04 eta: 8:26:38 time: 0.759800 data_time: 0.106829 memory: 21676 loss_kpt: 0.000614 acc_pose: 0.862668 loss: 0.000614 2022/09/09 02:53:53 - mmengine - INFO - Epoch(train) [56][200/293] lr: 5.000000e-04 eta: 8:26:17 time: 0.762030 data_time: 0.107628 memory: 21676 loss_kpt: 0.000624 acc_pose: 0.809341 loss: 0.000624 2022/09/09 02:54:32 - mmengine - INFO - Epoch(train) [56][250/293] lr: 5.000000e-04 eta: 8:25:58 time: 0.777194 data_time: 0.103784 memory: 21676 loss_kpt: 0.000626 acc_pose: 0.856764 loss: 0.000626 2022/09/09 02:55:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 02:55:05 - mmengine - INFO - Saving checkpoint at 56 epochs 2022/09/09 02:55:49 - mmengine - INFO - Epoch(train) [57][50/293] lr: 5.000000e-04 eta: 8:23:52 time: 0.788282 data_time: 0.112545 memory: 21676 loss_kpt: 0.000612 acc_pose: 0.802258 loss: 0.000612 2022/09/09 02:56:29 - mmengine - INFO - Epoch(train) [57][100/293] lr: 5.000000e-04 eta: 8:23:36 time: 0.797587 data_time: 0.106091 memory: 21676 loss_kpt: 0.000619 acc_pose: 0.859812 loss: 0.000619 2022/09/09 02:57:07 - mmengine - INFO - Epoch(train) [57][150/293] lr: 5.000000e-04 eta: 8:23:14 time: 0.762380 data_time: 0.105740 memory: 21676 loss_kpt: 0.000625 acc_pose: 0.801061 loss: 0.000625 2022/09/09 02:57:45 - mmengine - INFO - Epoch(train) [57][200/293] lr: 5.000000e-04 eta: 8:22:53 time: 0.761821 data_time: 0.101175 memory: 21676 loss_kpt: 0.000628 acc_pose: 0.792000 loss: 0.000628 2022/09/09 02:58:23 - mmengine - INFO - Epoch(train) [57][250/293] lr: 5.000000e-04 eta: 8:22:31 time: 0.759725 data_time: 0.109519 memory: 21676 loss_kpt: 0.000629 acc_pose: 0.859635 loss: 0.000629 2022/09/09 02:58:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 02:58:55 - mmengine - INFO - Saving checkpoint at 57 epochs 2022/09/09 02:59:38 - mmengine - INFO - Epoch(train) [58][50/293] lr: 5.000000e-04 eta: 8:20:26 time: 0.778027 data_time: 0.111363 memory: 21676 loss_kpt: 0.000632 acc_pose: 0.829109 loss: 0.000632 2022/09/09 03:00:16 - mmengine - INFO - Epoch(train) [58][100/293] lr: 5.000000e-04 eta: 8:20:04 time: 0.759274 data_time: 0.100175 memory: 21676 loss_kpt: 0.000635 acc_pose: 0.819589 loss: 0.000635 2022/09/09 03:00:54 - mmengine - INFO - Epoch(train) [58][150/293] lr: 5.000000e-04 eta: 8:19:42 time: 0.756868 data_time: 0.105717 memory: 21676 loss_kpt: 0.000621 acc_pose: 0.768257 loss: 0.000621 2022/09/09 03:01:32 - mmengine - INFO - Epoch(train) [58][200/293] lr: 5.000000e-04 eta: 8:19:20 time: 0.755298 data_time: 0.101895 memory: 21676 loss_kpt: 0.000626 acc_pose: 0.832143 loss: 0.000626 2022/09/09 03:02:10 - mmengine - INFO - Epoch(train) [58][250/293] lr: 5.000000e-04 eta: 8:18:58 time: 0.759668 data_time: 0.108391 memory: 21676 loss_kpt: 0.000624 acc_pose: 0.862474 loss: 0.000624 2022/09/09 03:02:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 03:02:41 - mmengine - INFO - Saving checkpoint at 58 epochs 2022/09/09 03:02:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 03:03:25 - mmengine - INFO - Epoch(train) [59][50/293] lr: 5.000000e-04 eta: 8:16:54 time: 0.781621 data_time: 0.114236 memory: 21676 loss_kpt: 0.000634 acc_pose: 0.804926 loss: 0.000634 2022/09/09 03:04:04 - mmengine - INFO - Epoch(train) [59][100/293] lr: 5.000000e-04 eta: 8:16:35 time: 0.780053 data_time: 0.109512 memory: 21676 loss_kpt: 0.000620 acc_pose: 0.796379 loss: 0.000620 2022/09/09 03:04:41 - mmengine - INFO - Epoch(train) [59][150/293] lr: 5.000000e-04 eta: 8:16:11 time: 0.747749 data_time: 0.104069 memory: 21676 loss_kpt: 0.000633 acc_pose: 0.824017 loss: 0.000633 2022/09/09 03:05:19 - mmengine - INFO - Epoch(train) [59][200/293] lr: 5.000000e-04 eta: 8:15:48 time: 0.749058 data_time: 0.101576 memory: 21676 loss_kpt: 0.000606 acc_pose: 0.842032 loss: 0.000606 2022/09/09 03:05:56 - mmengine - INFO - Epoch(train) [59][250/293] lr: 5.000000e-04 eta: 8:15:25 time: 0.753063 data_time: 0.104010 memory: 21676 loss_kpt: 0.000623 acc_pose: 0.857797 loss: 0.000623 2022/09/09 03:06:28 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 03:06:28 - mmengine - INFO - Saving checkpoint at 59 epochs 2022/09/09 03:07:11 - mmengine - INFO - Epoch(train) [60][50/293] lr: 5.000000e-04 eta: 8:13:24 time: 0.786264 data_time: 0.114289 memory: 21676 loss_kpt: 0.000619 acc_pose: 0.811732 loss: 0.000619 2022/09/09 03:07:49 - mmengine - INFO - Epoch(train) [60][100/293] lr: 5.000000e-04 eta: 8:13:02 time: 0.764151 data_time: 0.104315 memory: 21676 loss_kpt: 0.000617 acc_pose: 0.811059 loss: 0.000617 2022/09/09 03:08:26 - mmengine - INFO - Epoch(train) [60][150/293] lr: 5.000000e-04 eta: 8:12:39 time: 0.749581 data_time: 0.101487 memory: 21676 loss_kpt: 0.000617 acc_pose: 0.839766 loss: 0.000617 2022/09/09 03:09:04 - mmengine - INFO - Epoch(train) [60][200/293] lr: 5.000000e-04 eta: 8:12:16 time: 0.757151 data_time: 0.107415 memory: 21676 loss_kpt: 0.000622 acc_pose: 0.873197 loss: 0.000622 2022/09/09 03:09:42 - mmengine - INFO - Epoch(train) [60][250/293] lr: 5.000000e-04 eta: 8:11:54 time: 0.761850 data_time: 0.101665 memory: 21676 loss_kpt: 0.000608 acc_pose: 0.858714 loss: 0.000608 2022/09/09 03:10:15 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 03:10:15 - mmengine - INFO - Saving checkpoint at 60 epochs 2022/09/09 03:10:27 - mmengine - INFO - Epoch(val) [60][50/407] eta: 0:00:56 time: 0.158046 data_time: 0.014341 memory: 21676 2022/09/09 03:10:35 - mmengine - INFO - Epoch(val) [60][100/407] eta: 0:00:46 time: 0.150251 data_time: 0.008593 memory: 1375 2022/09/09 03:10:43 - mmengine - INFO - Epoch(val) [60][150/407] eta: 0:00:41 time: 0.160759 data_time: 0.013995 memory: 1375 2022/09/09 03:10:51 - mmengine - INFO - Epoch(val) [60][200/407] eta: 0:00:31 time: 0.150763 data_time: 0.008479 memory: 1375 2022/09/09 03:10:58 - mmengine - INFO - Epoch(val) [60][250/407] eta: 0:00:23 time: 0.151961 data_time: 0.009576 memory: 1375 2022/09/09 03:11:06 - mmengine - INFO - Epoch(val) [60][300/407] eta: 0:00:16 time: 0.152462 data_time: 0.008742 memory: 1375 2022/09/09 03:11:13 - mmengine - INFO - Epoch(val) [60][350/407] eta: 0:00:08 time: 0.150146 data_time: 0.008939 memory: 1375 2022/09/09 03:11:21 - mmengine - INFO - Epoch(val) [60][400/407] eta: 0:00:01 time: 0.148773 data_time: 0.008536 memory: 1375 2022/09/09 03:11:57 - mmengine - INFO - Evaluating CocoMetric... 2022/09/09 03:12:11 - mmengine - INFO - Epoch(val) [60][407/407] coco/AP: 0.736338 coco/AP .5: 0.897431 coco/AP .75: 0.805741 coco/AP (M): 0.697580 coco/AP (L): 0.807787 coco/AR: 0.788130 coco/AR .5: 0.935768 coco/AR .75: 0.850283 coco/AR (M): 0.744141 coco/AR (L): 0.851579 2022/09/09 03:12:11 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220908/hrnet_w32_384/best_coco/AP_epoch_50.pth is removed 2022/09/09 03:12:14 - mmengine - INFO - The best checkpoint with 0.7363 coco/AP at 60 epoch is saved to best_coco/AP_epoch_60.pth. 2022/09/09 03:12:53 - mmengine - INFO - Epoch(train) [61][50/293] lr: 5.000000e-04 eta: 8:09:53 time: 0.781436 data_time: 0.114946 memory: 21676 loss_kpt: 0.000606 acc_pose: 0.838450 loss: 0.000606 2022/09/09 03:13:31 - mmengine - INFO - Epoch(train) [61][100/293] lr: 5.000000e-04 eta: 8:09:31 time: 0.759004 data_time: 0.101036 memory: 21676 loss_kpt: 0.000621 acc_pose: 0.865853 loss: 0.000621 2022/09/09 03:14:09 - mmengine - INFO - Epoch(train) [61][150/293] lr: 5.000000e-04 eta: 8:09:09 time: 0.759914 data_time: 0.107524 memory: 21676 loss_kpt: 0.000602 acc_pose: 0.876395 loss: 0.000602 2022/09/09 03:14:47 - mmengine - INFO - Epoch(train) [61][200/293] lr: 5.000000e-04 eta: 8:08:46 time: 0.760439 data_time: 0.104576 memory: 21676 loss_kpt: 0.000618 acc_pose: 0.786214 loss: 0.000618 2022/09/09 03:15:25 - mmengine - INFO - Epoch(train) [61][250/293] lr: 5.000000e-04 eta: 8:08:24 time: 0.761583 data_time: 0.103202 memory: 21676 loss_kpt: 0.000621 acc_pose: 0.808149 loss: 0.000621 2022/09/09 03:15:57 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 03:15:57 - mmengine - INFO - Saving checkpoint at 61 epochs 2022/09/09 03:16:42 - mmengine - INFO - Epoch(train) [62][50/293] lr: 5.000000e-04 eta: 8:06:26 time: 0.792310 data_time: 0.108217 memory: 21676 loss_kpt: 0.000624 acc_pose: 0.798371 loss: 0.000624 2022/09/09 03:17:21 - mmengine - INFO - Epoch(train) [62][100/293] lr: 5.000000e-04 eta: 8:06:06 time: 0.781723 data_time: 0.104949 memory: 21676 loss_kpt: 0.000632 acc_pose: 0.816084 loss: 0.000632 2022/09/09 03:17:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 03:18:00 - mmengine - INFO - Epoch(train) [62][150/293] lr: 5.000000e-04 eta: 8:05:47 time: 0.785397 data_time: 0.098667 memory: 21676 loss_kpt: 0.000611 acc_pose: 0.836142 loss: 0.000611 2022/09/09 03:18:39 - mmengine - INFO - Epoch(train) [62][200/293] lr: 5.000000e-04 eta: 8:05:26 time: 0.771504 data_time: 0.112102 memory: 21676 loss_kpt: 0.000619 acc_pose: 0.825614 loss: 0.000619 2022/09/09 03:19:16 - mmengine - INFO - Epoch(train) [62][250/293] lr: 5.000000e-04 eta: 8:05:02 time: 0.756721 data_time: 0.102627 memory: 21676 loss_kpt: 0.000610 acc_pose: 0.865588 loss: 0.000610 2022/09/09 03:19:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 03:19:49 - mmengine - INFO - Saving checkpoint at 62 epochs 2022/09/09 03:20:31 - mmengine - INFO - Epoch(train) [63][50/293] lr: 5.000000e-04 eta: 8:03:05 time: 0.785130 data_time: 0.119160 memory: 21676 loss_kpt: 0.000602 acc_pose: 0.846543 loss: 0.000602 2022/09/09 03:21:11 - mmengine - INFO - Epoch(train) [63][100/293] lr: 5.000000e-04 eta: 8:02:46 time: 0.785855 data_time: 0.107166 memory: 21676 loss_kpt: 0.000613 acc_pose: 0.828473 loss: 0.000613 2022/09/09 03:21:50 - mmengine - INFO - Epoch(train) [63][150/293] lr: 5.000000e-04 eta: 8:02:25 time: 0.778898 data_time: 0.105675 memory: 21676 loss_kpt: 0.000610 acc_pose: 0.852436 loss: 0.000610 2022/09/09 03:22:29 - mmengine - INFO - Epoch(train) [63][200/293] lr: 5.000000e-04 eta: 8:02:04 time: 0.777731 data_time: 0.102546 memory: 21676 loss_kpt: 0.000619 acc_pose: 0.847267 loss: 0.000619 2022/09/09 03:23:07 - mmengine - INFO - Epoch(train) [63][250/293] lr: 5.000000e-04 eta: 8:01:43 time: 0.771368 data_time: 0.108305 memory: 21676 loss_kpt: 0.000619 acc_pose: 0.835128 loss: 0.000619 2022/09/09 03:23:40 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 03:23:40 - mmengine - INFO - Saving checkpoint at 63 epochs 2022/09/09 03:24:23 - mmengine - INFO - Epoch(train) [64][50/293] lr: 5.000000e-04 eta: 7:59:46 time: 0.781444 data_time: 0.110562 memory: 21676 loss_kpt: 0.000625 acc_pose: 0.836566 loss: 0.000625 2022/09/09 03:25:01 - mmengine - INFO - Epoch(train) [64][100/293] lr: 5.000000e-04 eta: 7:59:24 time: 0.767480 data_time: 0.105523 memory: 21676 loss_kpt: 0.000628 acc_pose: 0.770005 loss: 0.000628 2022/09/09 03:25:40 - mmengine - INFO - Epoch(train) [64][150/293] lr: 5.000000e-04 eta: 7:59:02 time: 0.769182 data_time: 0.106930 memory: 21676 loss_kpt: 0.000613 acc_pose: 0.817010 loss: 0.000613 2022/09/09 03:26:18 - mmengine - INFO - Epoch(train) [64][200/293] lr: 5.000000e-04 eta: 7:58:39 time: 0.764046 data_time: 0.110485 memory: 21676 loss_kpt: 0.000623 acc_pose: 0.812622 loss: 0.000623 2022/09/09 03:26:56 - mmengine - INFO - Epoch(train) [64][250/293] lr: 5.000000e-04 eta: 7:58:16 time: 0.756100 data_time: 0.104022 memory: 21676 loss_kpt: 0.000613 acc_pose: 0.877270 loss: 0.000613 2022/09/09 03:27:28 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 03:27:28 - mmengine - INFO - Saving checkpoint at 64 epochs 2022/09/09 03:28:12 - mmengine - INFO - Epoch(train) [65][50/293] lr: 5.000000e-04 eta: 7:56:20 time: 0.779566 data_time: 0.119065 memory: 21676 loss_kpt: 0.000636 acc_pose: 0.819982 loss: 0.000636 2022/09/09 03:28:50 - mmengine - INFO - Epoch(train) [65][100/293] lr: 5.000000e-04 eta: 7:55:57 time: 0.761226 data_time: 0.106093 memory: 21676 loss_kpt: 0.000635 acc_pose: 0.817071 loss: 0.000635 2022/09/09 03:29:28 - mmengine - INFO - Epoch(train) [65][150/293] lr: 5.000000e-04 eta: 7:55:35 time: 0.764082 data_time: 0.107395 memory: 21676 loss_kpt: 0.000623 acc_pose: 0.825054 loss: 0.000623 2022/09/09 03:30:06 - mmengine - INFO - Epoch(train) [65][200/293] lr: 5.000000e-04 eta: 7:55:12 time: 0.763624 data_time: 0.103397 memory: 21676 loss_kpt: 0.000604 acc_pose: 0.813539 loss: 0.000604 2022/09/09 03:30:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 03:30:45 - mmengine - INFO - Epoch(train) [65][250/293] lr: 5.000000e-04 eta: 7:54:49 time: 0.762551 data_time: 0.107052 memory: 21676 loss_kpt: 0.000609 acc_pose: 0.847020 loss: 0.000609 2022/09/09 03:31:16 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 03:31:16 - mmengine - INFO - Saving checkpoint at 65 epochs 2022/09/09 03:31:59 - mmengine - INFO - Epoch(train) [66][50/293] lr: 5.000000e-04 eta: 7:52:53 time: 0.769844 data_time: 0.110627 memory: 21676 loss_kpt: 0.000600 acc_pose: 0.822657 loss: 0.000600 2022/09/09 03:32:38 - mmengine - INFO - Epoch(train) [66][100/293] lr: 5.000000e-04 eta: 7:52:31 time: 0.767987 data_time: 0.106868 memory: 21676 loss_kpt: 0.000612 acc_pose: 0.855064 loss: 0.000612 2022/09/09 03:33:16 - mmengine - INFO - Epoch(train) [66][150/293] lr: 5.000000e-04 eta: 7:52:08 time: 0.766006 data_time: 0.099774 memory: 21676 loss_kpt: 0.000616 acc_pose: 0.889325 loss: 0.000616 2022/09/09 03:33:54 - mmengine - INFO - Epoch(train) [66][200/293] lr: 5.000000e-04 eta: 7:51:45 time: 0.759263 data_time: 0.105226 memory: 21676 loss_kpt: 0.000612 acc_pose: 0.802313 loss: 0.000612 2022/09/09 03:34:31 - mmengine - INFO - Epoch(train) [66][250/293] lr: 5.000000e-04 eta: 7:51:20 time: 0.744743 data_time: 0.100316 memory: 21676 loss_kpt: 0.000615 acc_pose: 0.812075 loss: 0.000615 2022/09/09 03:35:03 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 03:35:03 - mmengine - INFO - Saving checkpoint at 66 epochs 2022/09/09 03:35:47 - mmengine - INFO - Epoch(train) [67][50/293] lr: 5.000000e-04 eta: 7:49:29 time: 0.797211 data_time: 0.118076 memory: 21676 loss_kpt: 0.000610 acc_pose: 0.865350 loss: 0.000610 2022/09/09 03:36:26 - mmengine - INFO - Epoch(train) [67][100/293] lr: 5.000000e-04 eta: 7:49:08 time: 0.786486 data_time: 0.109663 memory: 21676 loss_kpt: 0.000623 acc_pose: 0.814476 loss: 0.000623 2022/09/09 03:37:05 - mmengine - INFO - Epoch(train) [67][150/293] lr: 5.000000e-04 eta: 7:48:46 time: 0.776926 data_time: 0.108441 memory: 21676 loss_kpt: 0.000615 acc_pose: 0.847767 loss: 0.000615 2022/09/09 03:37:43 - mmengine - INFO - Epoch(train) [67][200/293] lr: 5.000000e-04 eta: 7:48:22 time: 0.753251 data_time: 0.104649 memory: 21676 loss_kpt: 0.000613 acc_pose: 0.823167 loss: 0.000613 2022/09/09 03:38:20 - mmengine - INFO - Epoch(train) [67][250/293] lr: 5.000000e-04 eta: 7:47:57 time: 0.751799 data_time: 0.104314 memory: 21676 loss_kpt: 0.000613 acc_pose: 0.840570 loss: 0.000613 2022/09/09 03:38:53 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 03:38:53 - mmengine - INFO - Saving checkpoint at 67 epochs 2022/09/09 03:39:37 - mmengine - INFO - Epoch(train) [68][50/293] lr: 5.000000e-04 eta: 7:46:05 time: 0.780826 data_time: 0.111648 memory: 21676 loss_kpt: 0.000633 acc_pose: 0.801692 loss: 0.000633 2022/09/09 03:40:14 - mmengine - INFO - Epoch(train) [68][100/293] lr: 5.000000e-04 eta: 7:45:41 time: 0.754832 data_time: 0.101101 memory: 21676 loss_kpt: 0.000611 acc_pose: 0.856322 loss: 0.000611 2022/09/09 03:40:53 - mmengine - INFO - Epoch(train) [68][150/293] lr: 5.000000e-04 eta: 7:45:18 time: 0.765228 data_time: 0.100793 memory: 21676 loss_kpt: 0.000611 acc_pose: 0.844581 loss: 0.000611 2022/09/09 03:41:31 - mmengine - INFO - Epoch(train) [68][200/293] lr: 5.000000e-04 eta: 7:44:55 time: 0.765933 data_time: 0.109434 memory: 21676 loss_kpt: 0.000610 acc_pose: 0.798150 loss: 0.000610 2022/09/09 03:42:09 - mmengine - INFO - Epoch(train) [68][250/293] lr: 5.000000e-04 eta: 7:44:31 time: 0.756272 data_time: 0.101167 memory: 21676 loss_kpt: 0.000606 acc_pose: 0.832890 loss: 0.000606 2022/09/09 03:42:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 03:42:41 - mmengine - INFO - Saving checkpoint at 68 epochs 2022/09/09 03:43:25 - mmengine - INFO - Epoch(train) [69][50/293] lr: 5.000000e-04 eta: 7:42:40 time: 0.777420 data_time: 0.110445 memory: 21676 loss_kpt: 0.000612 acc_pose: 0.849161 loss: 0.000612 2022/09/09 03:43:45 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 03:44:03 - mmengine - INFO - Epoch(train) [69][100/293] lr: 5.000000e-04 eta: 7:42:17 time: 0.769929 data_time: 0.103383 memory: 21676 loss_kpt: 0.000598 acc_pose: 0.817394 loss: 0.000598 2022/09/09 03:44:43 - mmengine - INFO - Epoch(train) [69][150/293] lr: 5.000000e-04 eta: 7:41:55 time: 0.784213 data_time: 0.106706 memory: 21676 loss_kpt: 0.000603 acc_pose: 0.783635 loss: 0.000603 2022/09/09 03:45:21 - mmengine - INFO - Epoch(train) [69][200/293] lr: 5.000000e-04 eta: 7:41:32 time: 0.763700 data_time: 0.101255 memory: 21676 loss_kpt: 0.000600 acc_pose: 0.820143 loss: 0.000600 2022/09/09 03:45:58 - mmengine - INFO - Epoch(train) [69][250/293] lr: 5.000000e-04 eta: 7:41:07 time: 0.753167 data_time: 0.103403 memory: 21676 loss_kpt: 0.000596 acc_pose: 0.793786 loss: 0.000596 2022/09/09 03:46:31 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 03:46:31 - mmengine - INFO - Saving checkpoint at 69 epochs 2022/09/09 03:47:14 - mmengine - INFO - Epoch(train) [70][50/293] lr: 5.000000e-04 eta: 7:39:19 time: 0.794295 data_time: 0.127496 memory: 21676 loss_kpt: 0.000619 acc_pose: 0.851576 loss: 0.000619 2022/09/09 03:47:53 - mmengine - INFO - Epoch(train) [70][100/293] lr: 5.000000e-04 eta: 7:38:56 time: 0.770325 data_time: 0.105233 memory: 21676 loss_kpt: 0.000607 acc_pose: 0.840827 loss: 0.000607 2022/09/09 03:48:32 - mmengine - INFO - Epoch(train) [70][150/293] lr: 5.000000e-04 eta: 7:38:34 time: 0.780264 data_time: 0.104621 memory: 21676 loss_kpt: 0.000613 acc_pose: 0.830717 loss: 0.000613 2022/09/09 03:49:10 - mmengine - INFO - Epoch(train) [70][200/293] lr: 5.000000e-04 eta: 7:38:10 time: 0.764641 data_time: 0.106423 memory: 21676 loss_kpt: 0.000615 acc_pose: 0.829954 loss: 0.000615 2022/09/09 03:49:48 - mmengine - INFO - Epoch(train) [70][250/293] lr: 5.000000e-04 eta: 7:37:45 time: 0.752632 data_time: 0.111817 memory: 21676 loss_kpt: 0.000615 acc_pose: 0.828676 loss: 0.000615 2022/09/09 03:50:20 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 03:50:20 - mmengine - INFO - Saving checkpoint at 70 epochs 2022/09/09 03:50:33 - mmengine - INFO - Epoch(val) [70][50/407] eta: 0:00:55 time: 0.156246 data_time: 0.014261 memory: 21676 2022/09/09 03:50:40 - mmengine - INFO - Epoch(val) [70][100/407] eta: 0:00:46 time: 0.151632 data_time: 0.008789 memory: 1375 2022/09/09 03:50:48 - mmengine - INFO - Epoch(val) [70][150/407] eta: 0:00:38 time: 0.149760 data_time: 0.008300 memory: 1375 2022/09/09 03:50:55 - mmengine - INFO - Epoch(val) [70][200/407] eta: 0:00:32 time: 0.155007 data_time: 0.008630 memory: 1375 2022/09/09 03:51:03 - mmengine - INFO - Epoch(val) [70][250/407] eta: 0:00:24 time: 0.154074 data_time: 0.011622 memory: 1375 2022/09/09 03:51:11 - mmengine - INFO - Epoch(val) [70][300/407] eta: 0:00:16 time: 0.150643 data_time: 0.008904 memory: 1375 2022/09/09 03:51:18 - mmengine - INFO - Epoch(val) [70][350/407] eta: 0:00:08 time: 0.150590 data_time: 0.008657 memory: 1375 2022/09/09 03:51:25 - mmengine - INFO - Epoch(val) [70][400/407] eta: 0:00:01 time: 0.147655 data_time: 0.007915 memory: 1375 2022/09/09 03:52:02 - mmengine - INFO - Evaluating CocoMetric... 2022/09/09 03:52:16 - mmengine - INFO - Epoch(val) [70][407/407] coco/AP: 0.737950 coco/AP .5: 0.896041 coco/AP .75: 0.808446 coco/AP (M): 0.698698 coco/AP (L): 0.808930 coco/AR: 0.790003 coco/AR .5: 0.932777 coco/AR .75: 0.853904 coco/AR (M): 0.745616 coco/AR (L): 0.854255 2022/09/09 03:52:16 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220908/hrnet_w32_384/best_coco/AP_epoch_60.pth is removed 2022/09/09 03:52:19 - mmengine - INFO - The best checkpoint with 0.7379 coco/AP at 70 epoch is saved to best_coco/AP_epoch_70.pth. 2022/09/09 03:52:58 - mmengine - INFO - Epoch(train) [71][50/293] lr: 5.000000e-04 eta: 7:35:58 time: 0.792031 data_time: 0.113235 memory: 21676 loss_kpt: 0.000607 acc_pose: 0.834885 loss: 0.000607 2022/09/09 03:53:38 - mmengine - INFO - Epoch(train) [71][100/293] lr: 5.000000e-04 eta: 7:35:36 time: 0.783566 data_time: 0.108202 memory: 21676 loss_kpt: 0.000615 acc_pose: 0.838727 loss: 0.000615 2022/09/09 03:54:16 - mmengine - INFO - Epoch(train) [71][150/293] lr: 5.000000e-04 eta: 7:35:13 time: 0.772416 data_time: 0.103442 memory: 21676 loss_kpt: 0.000607 acc_pose: 0.843391 loss: 0.000607 2022/09/09 03:54:56 - mmengine - INFO - Epoch(train) [71][200/293] lr: 5.000000e-04 eta: 7:34:51 time: 0.783555 data_time: 0.106259 memory: 21676 loss_kpt: 0.000625 acc_pose: 0.809715 loss: 0.000625 2022/09/09 03:55:34 - mmengine - INFO - Epoch(train) [71][250/293] lr: 5.000000e-04 eta: 7:34:27 time: 0.767498 data_time: 0.104399 memory: 21676 loss_kpt: 0.000612 acc_pose: 0.819494 loss: 0.000612 2022/09/09 03:56:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 03:56:06 - mmengine - INFO - Saving checkpoint at 71 epochs 2022/09/09 03:56:50 - mmengine - INFO - Epoch(train) [72][50/293] lr: 5.000000e-04 eta: 7:32:39 time: 0.778064 data_time: 0.111371 memory: 21676 loss_kpt: 0.000597 acc_pose: 0.813173 loss: 0.000597 2022/09/09 03:57:28 - mmengine - INFO - Epoch(train) [72][100/293] lr: 5.000000e-04 eta: 7:32:15 time: 0.763618 data_time: 0.098536 memory: 21676 loss_kpt: 0.000602 acc_pose: 0.854018 loss: 0.000602 2022/09/09 03:58:08 - mmengine - INFO - Epoch(train) [72][150/293] lr: 5.000000e-04 eta: 7:31:54 time: 0.792223 data_time: 0.099027 memory: 21676 loss_kpt: 0.000614 acc_pose: 0.811265 loss: 0.000614 2022/09/09 03:58:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 03:58:46 - mmengine - INFO - Epoch(train) [72][200/293] lr: 5.000000e-04 eta: 7:31:31 time: 0.778563 data_time: 0.099740 memory: 21676 loss_kpt: 0.000602 acc_pose: 0.842642 loss: 0.000602 2022/09/09 03:59:25 - mmengine - INFO - Epoch(train) [72][250/293] lr: 5.000000e-04 eta: 7:31:08 time: 0.772450 data_time: 0.109780 memory: 21676 loss_kpt: 0.000617 acc_pose: 0.808225 loss: 0.000617 2022/09/09 03:59:57 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 03:59:57 - mmengine - INFO - Saving checkpoint at 72 epochs 2022/09/09 04:00:42 - mmengine - INFO - Epoch(train) [73][50/293] lr: 5.000000e-04 eta: 7:29:23 time: 0.793230 data_time: 0.118645 memory: 21676 loss_kpt: 0.000598 acc_pose: 0.827710 loss: 0.000598 2022/09/09 04:01:21 - mmengine - INFO - Epoch(train) [73][100/293] lr: 5.000000e-04 eta: 7:29:00 time: 0.778557 data_time: 0.106865 memory: 21676 loss_kpt: 0.000605 acc_pose: 0.842899 loss: 0.000605 2022/09/09 04:01:59 - mmengine - INFO - Epoch(train) [73][150/293] lr: 5.000000e-04 eta: 7:28:35 time: 0.762799 data_time: 0.100049 memory: 21676 loss_kpt: 0.000614 acc_pose: 0.812779 loss: 0.000614 2022/09/09 04:02:37 - mmengine - INFO - Epoch(train) [73][200/293] lr: 5.000000e-04 eta: 7:28:10 time: 0.754731 data_time: 0.102702 memory: 21676 loss_kpt: 0.000616 acc_pose: 0.847962 loss: 0.000616 2022/09/09 04:03:15 - mmengine - INFO - Epoch(train) [73][250/293] lr: 5.000000e-04 eta: 7:27:46 time: 0.765725 data_time: 0.107150 memory: 21676 loss_kpt: 0.000618 acc_pose: 0.834238 loss: 0.000618 2022/09/09 04:03:47 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 04:03:47 - mmengine - INFO - Saving checkpoint at 73 epochs 2022/09/09 04:04:31 - mmengine - INFO - Epoch(train) [74][50/293] lr: 5.000000e-04 eta: 7:26:00 time: 0.781119 data_time: 0.117659 memory: 21676 loss_kpt: 0.000591 acc_pose: 0.863533 loss: 0.000591 2022/09/09 04:05:10 - mmengine - INFO - Epoch(train) [74][100/293] lr: 5.000000e-04 eta: 7:25:38 time: 0.779833 data_time: 0.110437 memory: 21676 loss_kpt: 0.000613 acc_pose: 0.844898 loss: 0.000613 2022/09/09 04:05:48 - mmengine - INFO - Epoch(train) [74][150/293] lr: 5.000000e-04 eta: 7:25:12 time: 0.753629 data_time: 0.102267 memory: 21676 loss_kpt: 0.000605 acc_pose: 0.833513 loss: 0.000605 2022/09/09 04:06:25 - mmengine - INFO - Epoch(train) [74][200/293] lr: 5.000000e-04 eta: 7:24:46 time: 0.750762 data_time: 0.104329 memory: 21676 loss_kpt: 0.000598 acc_pose: 0.847130 loss: 0.000598 2022/09/09 04:07:03 - mmengine - INFO - Epoch(train) [74][250/293] lr: 5.000000e-04 eta: 7:24:22 time: 0.764736 data_time: 0.103092 memory: 21676 loss_kpt: 0.000608 acc_pose: 0.831350 loss: 0.000608 2022/09/09 04:07:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 04:07:36 - mmengine - INFO - Saving checkpoint at 74 epochs 2022/09/09 04:08:18 - mmengine - INFO - Epoch(train) [75][50/293] lr: 5.000000e-04 eta: 7:22:36 time: 0.768801 data_time: 0.119821 memory: 21676 loss_kpt: 0.000601 acc_pose: 0.871924 loss: 0.000601 2022/09/09 04:08:56 - mmengine - INFO - Epoch(train) [75][100/293] lr: 5.000000e-04 eta: 7:22:10 time: 0.750081 data_time: 0.105146 memory: 21676 loss_kpt: 0.000601 acc_pose: 0.803625 loss: 0.000601 2022/09/09 04:09:33 - mmengine - INFO - Epoch(train) [75][150/293] lr: 5.000000e-04 eta: 7:21:45 time: 0.757252 data_time: 0.101961 memory: 21676 loss_kpt: 0.000599 acc_pose: 0.820159 loss: 0.000599 2022/09/09 04:10:12 - mmengine - INFO - Epoch(train) [75][200/293] lr: 5.000000e-04 eta: 7:21:21 time: 0.766472 data_time: 0.106376 memory: 21676 loss_kpt: 0.000604 acc_pose: 0.834983 loss: 0.000604 2022/09/09 04:10:49 - mmengine - INFO - Epoch(train) [75][250/293] lr: 5.000000e-04 eta: 7:20:55 time: 0.748917 data_time: 0.099430 memory: 21676 loss_kpt: 0.000602 acc_pose: 0.865397 loss: 0.000602 2022/09/09 04:11:22 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 04:11:22 - mmengine - INFO - Saving checkpoint at 75 epochs 2022/09/09 04:11:45 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 04:12:05 - mmengine - INFO - Epoch(train) [76][50/293] lr: 5.000000e-04 eta: 7:19:12 time: 0.786877 data_time: 0.109220 memory: 21676 loss_kpt: 0.000597 acc_pose: 0.804325 loss: 0.000597 2022/09/09 04:12:44 - mmengine - INFO - Epoch(train) [76][100/293] lr: 5.000000e-04 eta: 7:18:49 time: 0.784458 data_time: 0.100765 memory: 21676 loss_kpt: 0.000610 acc_pose: 0.844718 loss: 0.000610 2022/09/09 04:13:22 - mmengine - INFO - Epoch(train) [76][150/293] lr: 5.000000e-04 eta: 7:18:24 time: 0.757217 data_time: 0.108659 memory: 21676 loss_kpt: 0.000607 acc_pose: 0.788376 loss: 0.000607 2022/09/09 04:14:00 - mmengine - INFO - Epoch(train) [76][200/293] lr: 5.000000e-04 eta: 7:17:58 time: 0.755733 data_time: 0.108715 memory: 21676 loss_kpt: 0.000591 acc_pose: 0.864195 loss: 0.000591 2022/09/09 04:14:38 - mmengine - INFO - Epoch(train) [76][250/293] lr: 5.000000e-04 eta: 7:17:33 time: 0.758755 data_time: 0.103725 memory: 21676 loss_kpt: 0.000619 acc_pose: 0.817904 loss: 0.000619 2022/09/09 04:15:10 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 04:15:10 - mmengine - INFO - Saving checkpoint at 76 epochs 2022/09/09 04:15:53 - mmengine - INFO - Epoch(train) [77][50/293] lr: 5.000000e-04 eta: 7:15:50 time: 0.779009 data_time: 0.116939 memory: 21676 loss_kpt: 0.000591 acc_pose: 0.840213 loss: 0.000591 2022/09/09 04:16:31 - mmengine - INFO - Epoch(train) [77][100/293] lr: 5.000000e-04 eta: 7:15:25 time: 0.760181 data_time: 0.100518 memory: 21676 loss_kpt: 0.000608 acc_pose: 0.855905 loss: 0.000608 2022/09/09 04:17:09 - mmengine - INFO - Epoch(train) [77][150/293] lr: 5.000000e-04 eta: 7:14:59 time: 0.759731 data_time: 0.103018 memory: 21676 loss_kpt: 0.000596 acc_pose: 0.845190 loss: 0.000596 2022/09/09 04:17:47 - mmengine - INFO - Epoch(train) [77][200/293] lr: 5.000000e-04 eta: 7:14:34 time: 0.757761 data_time: 0.106523 memory: 21676 loss_kpt: 0.000614 acc_pose: 0.816746 loss: 0.000614 2022/09/09 04:18:25 - mmengine - INFO - Epoch(train) [77][250/293] lr: 5.000000e-04 eta: 7:14:09 time: 0.764218 data_time: 0.099616 memory: 21676 loss_kpt: 0.000602 acc_pose: 0.820283 loss: 0.000602 2022/09/09 04:18:57 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 04:18:57 - mmengine - INFO - Saving checkpoint at 77 epochs 2022/09/09 04:19:41 - mmengine - INFO - Epoch(train) [78][50/293] lr: 5.000000e-04 eta: 7:12:27 time: 0.780162 data_time: 0.119123 memory: 21676 loss_kpt: 0.000600 acc_pose: 0.817312 loss: 0.000600 2022/09/09 04:20:19 - mmengine - INFO - Epoch(train) [78][100/293] lr: 5.000000e-04 eta: 7:12:01 time: 0.756151 data_time: 0.102499 memory: 21676 loss_kpt: 0.000609 acc_pose: 0.824176 loss: 0.000609 2022/09/09 04:20:57 - mmengine - INFO - Epoch(train) [78][150/293] lr: 5.000000e-04 eta: 7:11:36 time: 0.763177 data_time: 0.113936 memory: 21676 loss_kpt: 0.000595 acc_pose: 0.837847 loss: 0.000595 2022/09/09 04:21:35 - mmengine - INFO - Epoch(train) [78][200/293] lr: 5.000000e-04 eta: 7:11:11 time: 0.759062 data_time: 0.106550 memory: 21676 loss_kpt: 0.000619 acc_pose: 0.836678 loss: 0.000619 2022/09/09 04:22:13 - mmengine - INFO - Epoch(train) [78][250/293] lr: 5.000000e-04 eta: 7:10:46 time: 0.767616 data_time: 0.102035 memory: 21676 loss_kpt: 0.000619 acc_pose: 0.835878 loss: 0.000619 2022/09/09 04:22:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 04:22:46 - mmengine - INFO - Saving checkpoint at 78 epochs 2022/09/09 04:23:30 - mmengine - INFO - Epoch(train) [79][50/293] lr: 5.000000e-04 eta: 7:09:06 time: 0.793493 data_time: 0.115545 memory: 21676 loss_kpt: 0.000604 acc_pose: 0.852909 loss: 0.000604 2022/09/09 04:24:09 - mmengine - INFO - Epoch(train) [79][100/293] lr: 5.000000e-04 eta: 7:08:42 time: 0.780531 data_time: 0.105454 memory: 21676 loss_kpt: 0.000597 acc_pose: 0.828188 loss: 0.000597 2022/09/09 04:24:45 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 04:24:48 - mmengine - INFO - Epoch(train) [79][150/293] lr: 5.000000e-04 eta: 7:08:19 time: 0.785584 data_time: 0.109972 memory: 21676 loss_kpt: 0.000601 acc_pose: 0.843932 loss: 0.000601 2022/09/09 04:25:26 - mmengine - INFO - Epoch(train) [79][200/293] lr: 5.000000e-04 eta: 7:07:54 time: 0.765173 data_time: 0.108289 memory: 21676 loss_kpt: 0.000608 acc_pose: 0.798522 loss: 0.000608 2022/09/09 04:26:04 - mmengine - INFO - Epoch(train) [79][250/293] lr: 5.000000e-04 eta: 7:07:28 time: 0.753705 data_time: 0.100253 memory: 21676 loss_kpt: 0.000604 acc_pose: 0.852528 loss: 0.000604 2022/09/09 04:26:36 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 04:26:36 - mmengine - INFO - Saving checkpoint at 79 epochs 2022/09/09 04:27:20 - mmengine - INFO - Epoch(train) [80][50/293] lr: 5.000000e-04 eta: 7:05:48 time: 0.785533 data_time: 0.108658 memory: 21676 loss_kpt: 0.000596 acc_pose: 0.846023 loss: 0.000596 2022/09/09 04:27:59 - mmengine - INFO - Epoch(train) [80][100/293] lr: 5.000000e-04 eta: 7:05:23 time: 0.768764 data_time: 0.103025 memory: 21676 loss_kpt: 0.000595 acc_pose: 0.806322 loss: 0.000595 2022/09/09 04:28:37 - mmengine - INFO - Epoch(train) [80][150/293] lr: 5.000000e-04 eta: 7:04:58 time: 0.763959 data_time: 0.107520 memory: 21676 loss_kpt: 0.000582 acc_pose: 0.800613 loss: 0.000582 2022/09/09 04:29:15 - mmengine - INFO - Epoch(train) [80][200/293] lr: 5.000000e-04 eta: 7:04:32 time: 0.757959 data_time: 0.108261 memory: 21676 loss_kpt: 0.000607 acc_pose: 0.817070 loss: 0.000607 2022/09/09 04:29:53 - mmengine - INFO - Epoch(train) [80][250/293] lr: 5.000000e-04 eta: 7:04:06 time: 0.764024 data_time: 0.105783 memory: 21676 loss_kpt: 0.000603 acc_pose: 0.800212 loss: 0.000603 2022/09/09 04:30:25 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 04:30:25 - mmengine - INFO - Saving checkpoint at 80 epochs 2022/09/09 04:30:38 - mmengine - INFO - Epoch(val) [80][50/407] eta: 0:00:59 time: 0.166030 data_time: 0.023478 memory: 21676 2022/09/09 04:30:46 - mmengine - INFO - Epoch(val) [80][100/407] eta: 0:00:46 time: 0.152152 data_time: 0.009396 memory: 1375 2022/09/09 04:30:53 - mmengine - INFO - Epoch(val) [80][150/407] eta: 0:00:39 time: 0.152731 data_time: 0.011313 memory: 1375 2022/09/09 04:31:01 - mmengine - INFO - Epoch(val) [80][200/407] eta: 0:00:31 time: 0.150408 data_time: 0.009258 memory: 1375 2022/09/09 04:31:08 - mmengine - INFO - Epoch(val) [80][250/407] eta: 0:00:23 time: 0.150536 data_time: 0.008933 memory: 1375 2022/09/09 04:31:16 - mmengine - INFO - Epoch(val) [80][300/407] eta: 0:00:15 time: 0.149200 data_time: 0.008955 memory: 1375 2022/09/09 04:31:23 - mmengine - INFO - Epoch(val) [80][350/407] eta: 0:00:08 time: 0.150000 data_time: 0.008139 memory: 1375 2022/09/09 04:31:31 - mmengine - INFO - Epoch(val) [80][400/407] eta: 0:00:01 time: 0.150427 data_time: 0.009753 memory: 1375 2022/09/09 04:32:07 - mmengine - INFO - Evaluating CocoMetric... 2022/09/09 04:32:21 - mmengine - INFO - Epoch(val) [80][407/407] coco/AP: 0.740192 coco/AP .5: 0.896991 coco/AP .75: 0.809064 coco/AP (M): 0.702091 coco/AP (L): 0.809508 coco/AR: 0.791908 coco/AR .5: 0.934351 coco/AR .75: 0.852802 coco/AR (M): 0.748320 coco/AR (L): 0.855072 2022/09/09 04:32:21 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220908/hrnet_w32_384/best_coco/AP_epoch_70.pth is removed 2022/09/09 04:32:23 - mmengine - INFO - The best checkpoint with 0.7402 coco/AP at 80 epoch is saved to best_coco/AP_epoch_80.pth. 2022/09/09 04:33:03 - mmengine - INFO - Epoch(train) [81][50/293] lr: 5.000000e-04 eta: 7:02:27 time: 0.785444 data_time: 0.116128 memory: 21676 loss_kpt: 0.000595 acc_pose: 0.846957 loss: 0.000595 2022/09/09 04:33:42 - mmengine - INFO - Epoch(train) [81][100/293] lr: 5.000000e-04 eta: 7:02:03 time: 0.784024 data_time: 0.103400 memory: 21676 loss_kpt: 0.000593 acc_pose: 0.801435 loss: 0.000593 2022/09/09 04:34:20 - mmengine - INFO - Epoch(train) [81][150/293] lr: 5.000000e-04 eta: 7:01:38 time: 0.763921 data_time: 0.109688 memory: 21676 loss_kpt: 0.000607 acc_pose: 0.839790 loss: 0.000607 2022/09/09 04:34:58 - mmengine - INFO - Epoch(train) [81][200/293] lr: 5.000000e-04 eta: 7:01:12 time: 0.762450 data_time: 0.105775 memory: 21676 loss_kpt: 0.000594 acc_pose: 0.860108 loss: 0.000594 2022/09/09 04:35:37 - mmengine - INFO - Epoch(train) [81][250/293] lr: 5.000000e-04 eta: 7:00:47 time: 0.770861 data_time: 0.104596 memory: 21676 loss_kpt: 0.000595 acc_pose: 0.840323 loss: 0.000595 2022/09/09 04:36:09 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 04:36:09 - mmengine - INFO - Saving checkpoint at 81 epochs 2022/09/09 04:36:52 - mmengine - INFO - Epoch(train) [82][50/293] lr: 5.000000e-04 eta: 6:59:10 time: 0.794991 data_time: 0.128183 memory: 21676 loss_kpt: 0.000593 acc_pose: 0.854203 loss: 0.000593 2022/09/09 04:37:31 - mmengine - INFO - Epoch(train) [82][100/293] lr: 5.000000e-04 eta: 6:58:45 time: 0.778739 data_time: 0.106430 memory: 21676 loss_kpt: 0.000603 acc_pose: 0.793956 loss: 0.000603 2022/09/09 04:38:10 - mmengine - INFO - Epoch(train) [82][150/293] lr: 5.000000e-04 eta: 6:58:21 time: 0.784334 data_time: 0.103552 memory: 21676 loss_kpt: 0.000599 acc_pose: 0.795990 loss: 0.000599 2022/09/09 04:38:49 - mmengine - INFO - Epoch(train) [82][200/293] lr: 5.000000e-04 eta: 6:57:56 time: 0.765728 data_time: 0.108445 memory: 21676 loss_kpt: 0.000606 acc_pose: 0.814119 loss: 0.000606 2022/09/09 04:39:26 - mmengine - INFO - Epoch(train) [82][250/293] lr: 5.000000e-04 eta: 6:57:29 time: 0.754983 data_time: 0.107551 memory: 21676 loss_kpt: 0.000598 acc_pose: 0.870749 loss: 0.000598 2022/09/09 04:39:39 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 04:39:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 04:39:59 - mmengine - INFO - Saving checkpoint at 82 epochs 2022/09/09 04:40:42 - mmengine - INFO - Epoch(train) [83][50/293] lr: 5.000000e-04 eta: 6:55:52 time: 0.787730 data_time: 0.111117 memory: 21676 loss_kpt: 0.000598 acc_pose: 0.828360 loss: 0.000598 2022/09/09 04:41:21 - mmengine - INFO - Epoch(train) [83][100/293] lr: 5.000000e-04 eta: 6:55:28 time: 0.781946 data_time: 0.107587 memory: 21676 loss_kpt: 0.000600 acc_pose: 0.860506 loss: 0.000600 2022/09/09 04:42:00 - mmengine - INFO - Epoch(train) [83][150/293] lr: 5.000000e-04 eta: 6:55:03 time: 0.779736 data_time: 0.105332 memory: 21676 loss_kpt: 0.000595 acc_pose: 0.828072 loss: 0.000595 2022/09/09 04:42:38 - mmengine - INFO - Epoch(train) [83][200/293] lr: 5.000000e-04 eta: 6:54:37 time: 0.767201 data_time: 0.109281 memory: 21676 loss_kpt: 0.000591 acc_pose: 0.815416 loss: 0.000591 2022/09/09 04:43:16 - mmengine - INFO - Epoch(train) [83][250/293] lr: 5.000000e-04 eta: 6:54:10 time: 0.750627 data_time: 0.102706 memory: 21676 loss_kpt: 0.000596 acc_pose: 0.862842 loss: 0.000596 2022/09/09 04:43:48 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 04:43:48 - mmengine - INFO - Saving checkpoint at 83 epochs 2022/09/09 04:44:32 - mmengine - INFO - Epoch(train) [84][50/293] lr: 5.000000e-04 eta: 6:52:34 time: 0.787578 data_time: 0.112239 memory: 21676 loss_kpt: 0.000590 acc_pose: 0.841193 loss: 0.000590 2022/09/09 04:45:12 - mmengine - INFO - Epoch(train) [84][100/293] lr: 5.000000e-04 eta: 6:52:10 time: 0.795628 data_time: 0.110435 memory: 21676 loss_kpt: 0.000605 acc_pose: 0.847903 loss: 0.000605 2022/09/09 04:45:50 - mmengine - INFO - Epoch(train) [84][150/293] lr: 5.000000e-04 eta: 6:51:44 time: 0.761952 data_time: 0.104594 memory: 21676 loss_kpt: 0.000587 acc_pose: 0.790260 loss: 0.000587 2022/09/09 04:46:27 - mmengine - INFO - Epoch(train) [84][200/293] lr: 5.000000e-04 eta: 6:51:17 time: 0.752285 data_time: 0.104283 memory: 21676 loss_kpt: 0.000594 acc_pose: 0.821737 loss: 0.000594 2022/09/09 04:47:05 - mmengine - INFO - Epoch(train) [84][250/293] lr: 5.000000e-04 eta: 6:50:50 time: 0.745677 data_time: 0.102762 memory: 21676 loss_kpt: 0.000594 acc_pose: 0.843578 loss: 0.000594 2022/09/09 04:47:37 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 04:47:37 - mmengine - INFO - Saving checkpoint at 84 epochs 2022/09/09 04:48:22 - mmengine - INFO - Epoch(train) [85][50/293] lr: 5.000000e-04 eta: 6:49:16 time: 0.805646 data_time: 0.122145 memory: 21676 loss_kpt: 0.000590 acc_pose: 0.792484 loss: 0.000590 2022/09/09 04:49:01 - mmengine - INFO - Epoch(train) [85][100/293] lr: 5.000000e-04 eta: 6:48:51 time: 0.778100 data_time: 0.105351 memory: 21676 loss_kpt: 0.000590 acc_pose: 0.860442 loss: 0.000590 2022/09/09 04:49:39 - mmengine - INFO - Epoch(train) [85][150/293] lr: 5.000000e-04 eta: 6:48:24 time: 0.761613 data_time: 0.106780 memory: 21676 loss_kpt: 0.000603 acc_pose: 0.840480 loss: 0.000603 2022/09/09 04:50:17 - mmengine - INFO - Epoch(train) [85][200/293] lr: 5.000000e-04 eta: 6:47:58 time: 0.757636 data_time: 0.100336 memory: 21676 loss_kpt: 0.000601 acc_pose: 0.842562 loss: 0.000601 2022/09/09 04:50:55 - mmengine - INFO - Epoch(train) [85][250/293] lr: 5.000000e-04 eta: 6:47:31 time: 0.761072 data_time: 0.105832 memory: 21676 loss_kpt: 0.000595 acc_pose: 0.810638 loss: 0.000595 2022/09/09 04:51:28 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 04:51:28 - mmengine - INFO - Saving checkpoint at 85 epochs 2022/09/09 04:52:12 - mmengine - INFO - Epoch(train) [86][50/293] lr: 5.000000e-04 eta: 6:45:56 time: 0.788800 data_time: 0.114319 memory: 21676 loss_kpt: 0.000594 acc_pose: 0.803502 loss: 0.000594 2022/09/09 04:52:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 04:52:50 - mmengine - INFO - Epoch(train) [86][100/293] lr: 5.000000e-04 eta: 6:45:30 time: 0.760655 data_time: 0.105714 memory: 21676 loss_kpt: 0.000588 acc_pose: 0.799498 loss: 0.000588 2022/09/09 04:53:28 - mmengine - INFO - Epoch(train) [86][150/293] lr: 5.000000e-04 eta: 6:45:03 time: 0.753427 data_time: 0.102899 memory: 21676 loss_kpt: 0.000588 acc_pose: 0.890750 loss: 0.000588 2022/09/09 04:54:06 - mmengine - INFO - Epoch(train) [86][200/293] lr: 5.000000e-04 eta: 6:44:37 time: 0.771262 data_time: 0.105639 memory: 21676 loss_kpt: 0.000593 acc_pose: 0.852412 loss: 0.000593 2022/09/09 04:54:44 - mmengine - INFO - Epoch(train) [86][250/293] lr: 5.000000e-04 eta: 6:44:10 time: 0.754991 data_time: 0.101653 memory: 21676 loss_kpt: 0.000594 acc_pose: 0.811428 loss: 0.000594 2022/09/09 04:55:16 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 04:55:16 - mmengine - INFO - Saving checkpoint at 86 epochs 2022/09/09 04:56:00 - mmengine - INFO - Epoch(train) [87][50/293] lr: 5.000000e-04 eta: 6:42:36 time: 0.790734 data_time: 0.121745 memory: 21676 loss_kpt: 0.000601 acc_pose: 0.820271 loss: 0.000601 2022/09/09 04:56:38 - mmengine - INFO - Epoch(train) [87][100/293] lr: 5.000000e-04 eta: 6:42:09 time: 0.753447 data_time: 0.105123 memory: 21676 loss_kpt: 0.000589 acc_pose: 0.848196 loss: 0.000589 2022/09/09 04:57:15 - mmengine - INFO - Epoch(train) [87][150/293] lr: 5.000000e-04 eta: 6:41:42 time: 0.753728 data_time: 0.101055 memory: 21676 loss_kpt: 0.000581 acc_pose: 0.848727 loss: 0.000581 2022/09/09 04:57:54 - mmengine - INFO - Epoch(train) [87][200/293] lr: 5.000000e-04 eta: 6:41:16 time: 0.770671 data_time: 0.106494 memory: 21676 loss_kpt: 0.000596 acc_pose: 0.820631 loss: 0.000596 2022/09/09 04:58:32 - mmengine - INFO - Epoch(train) [87][250/293] lr: 5.000000e-04 eta: 6:40:49 time: 0.751957 data_time: 0.104562 memory: 21676 loss_kpt: 0.000601 acc_pose: 0.859120 loss: 0.000601 2022/09/09 04:59:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 04:59:04 - mmengine - INFO - Saving checkpoint at 87 epochs 2022/09/09 04:59:48 - mmengine - INFO - Epoch(train) [88][50/293] lr: 5.000000e-04 eta: 6:39:15 time: 0.788441 data_time: 0.107823 memory: 21676 loss_kpt: 0.000598 acc_pose: 0.793283 loss: 0.000598 2022/09/09 05:00:27 - mmengine - INFO - Epoch(train) [88][100/293] lr: 5.000000e-04 eta: 6:38:49 time: 0.773160 data_time: 0.101798 memory: 21676 loss_kpt: 0.000599 acc_pose: 0.824455 loss: 0.000599 2022/09/09 05:01:06 - mmengine - INFO - Epoch(train) [88][150/293] lr: 5.000000e-04 eta: 6:38:24 time: 0.783470 data_time: 0.110062 memory: 21676 loss_kpt: 0.000583 acc_pose: 0.849552 loss: 0.000583 2022/09/09 05:01:44 - mmengine - INFO - Epoch(train) [88][200/293] lr: 5.000000e-04 eta: 6:37:58 time: 0.764544 data_time: 0.100351 memory: 21676 loss_kpt: 0.000593 acc_pose: 0.847310 loss: 0.000593 2022/09/09 05:02:23 - mmengine - INFO - Epoch(train) [88][250/293] lr: 5.000000e-04 eta: 6:37:32 time: 0.768165 data_time: 0.103146 memory: 21676 loss_kpt: 0.000599 acc_pose: 0.827161 loss: 0.000599 2022/09/09 05:02:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 05:02:55 - mmengine - INFO - Saving checkpoint at 88 epochs 2022/09/09 05:03:39 - mmengine - INFO - Epoch(train) [89][50/293] lr: 5.000000e-04 eta: 6:35:59 time: 0.790847 data_time: 0.113888 memory: 21676 loss_kpt: 0.000591 acc_pose: 0.812474 loss: 0.000591 2022/09/09 05:04:18 - mmengine - INFO - Epoch(train) [89][100/293] lr: 5.000000e-04 eta: 6:35:32 time: 0.768407 data_time: 0.102394 memory: 21676 loss_kpt: 0.000596 acc_pose: 0.840553 loss: 0.000596 2022/09/09 05:04:56 - mmengine - INFO - Epoch(train) [89][150/293] lr: 5.000000e-04 eta: 6:35:06 time: 0.759554 data_time: 0.098085 memory: 21676 loss_kpt: 0.000606 acc_pose: 0.772137 loss: 0.000606 2022/09/09 05:05:34 - mmengine - INFO - Epoch(train) [89][200/293] lr: 5.000000e-04 eta: 6:34:39 time: 0.764859 data_time: 0.104559 memory: 21676 loss_kpt: 0.000597 acc_pose: 0.794579 loss: 0.000597 2022/09/09 05:05:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 05:06:12 - mmengine - INFO - Epoch(train) [89][250/293] lr: 5.000000e-04 eta: 6:34:13 time: 0.765520 data_time: 0.102481 memory: 21676 loss_kpt: 0.000609 acc_pose: 0.822334 loss: 0.000609 2022/09/09 05:06:45 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 05:06:45 - mmengine - INFO - Saving checkpoint at 89 epochs 2022/09/09 05:07:29 - mmengine - INFO - Epoch(train) [90][50/293] lr: 5.000000e-04 eta: 6:32:40 time: 0.792849 data_time: 0.117052 memory: 21676 loss_kpt: 0.000595 acc_pose: 0.863639 loss: 0.000595 2022/09/09 05:08:08 - mmengine - INFO - Epoch(train) [90][100/293] lr: 5.000000e-04 eta: 6:32:14 time: 0.774837 data_time: 0.104968 memory: 21676 loss_kpt: 0.000601 acc_pose: 0.812487 loss: 0.000601 2022/09/09 05:08:46 - mmengine - INFO - Epoch(train) [90][150/293] lr: 5.000000e-04 eta: 6:31:48 time: 0.770651 data_time: 0.102822 memory: 21676 loss_kpt: 0.000592 acc_pose: 0.870289 loss: 0.000592 2022/09/09 05:09:24 - mmengine - INFO - Epoch(train) [90][200/293] lr: 5.000000e-04 eta: 6:31:21 time: 0.754312 data_time: 0.106188 memory: 21676 loss_kpt: 0.000599 acc_pose: 0.841913 loss: 0.000599 2022/09/09 05:10:02 - mmengine - INFO - Epoch(train) [90][250/293] lr: 5.000000e-04 eta: 6:30:53 time: 0.748015 data_time: 0.101883 memory: 21676 loss_kpt: 0.000593 acc_pose: 0.827977 loss: 0.000593 2022/09/09 05:10:34 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 05:10:34 - mmengine - INFO - Saving checkpoint at 90 epochs 2022/09/09 05:10:46 - mmengine - INFO - Epoch(val) [90][50/407] eta: 0:00:55 time: 0.155956 data_time: 0.014235 memory: 21676 2022/09/09 05:10:53 - mmengine - INFO - Epoch(val) [90][100/407] eta: 0:00:47 time: 0.154172 data_time: 0.009058 memory: 1375 2022/09/09 05:11:01 - mmengine - INFO - Epoch(val) [90][150/407] eta: 0:00:39 time: 0.153519 data_time: 0.011518 memory: 1375 2022/09/09 05:11:09 - mmengine - INFO - Epoch(val) [90][200/407] eta: 0:00:31 time: 0.151068 data_time: 0.009372 memory: 1375 2022/09/09 05:11:16 - mmengine - INFO - Epoch(val) [90][250/407] eta: 0:00:23 time: 0.150418 data_time: 0.008585 memory: 1375 2022/09/09 05:11:24 - mmengine - INFO - Epoch(val) [90][300/407] eta: 0:00:16 time: 0.151090 data_time: 0.008526 memory: 1375 2022/09/09 05:11:31 - mmengine - INFO - Epoch(val) [90][350/407] eta: 0:00:08 time: 0.150769 data_time: 0.008783 memory: 1375 2022/09/09 05:11:39 - mmengine - INFO - Epoch(val) [90][400/407] eta: 0:00:01 time: 0.149748 data_time: 0.008524 memory: 1375 2022/09/09 05:12:16 - mmengine - INFO - Evaluating CocoMetric... 2022/09/09 05:12:31 - mmengine - INFO - Epoch(val) [90][407/407] coco/AP: 0.742174 coco/AP .5: 0.899259 coco/AP .75: 0.812262 coco/AP (M): 0.702588 coco/AP (L): 0.812611 coco/AR: 0.793939 coco/AR .5: 0.936713 coco/AR .75: 0.856581 coco/AR (M): 0.749713 coco/AR (L): 0.857451 2022/09/09 05:12:31 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220908/hrnet_w32_384/best_coco/AP_epoch_80.pth is removed 2022/09/09 05:12:33 - mmengine - INFO - The best checkpoint with 0.7422 coco/AP at 90 epoch is saved to best_coco/AP_epoch_90.pth. 2022/09/09 05:13:13 - mmengine - INFO - Epoch(train) [91][50/293] lr: 5.000000e-04 eta: 6:29:21 time: 0.791955 data_time: 0.110918 memory: 21676 loss_kpt: 0.000592 acc_pose: 0.821160 loss: 0.000592 2022/09/09 05:13:52 - mmengine - INFO - Epoch(train) [91][100/293] lr: 5.000000e-04 eta: 6:28:56 time: 0.780527 data_time: 0.106419 memory: 21676 loss_kpt: 0.000589 acc_pose: 0.808979 loss: 0.000589 2022/09/09 05:14:30 - mmengine - INFO - Epoch(train) [91][150/293] lr: 5.000000e-04 eta: 6:28:28 time: 0.758033 data_time: 0.100413 memory: 21676 loss_kpt: 0.000596 acc_pose: 0.814891 loss: 0.000596 2022/09/09 05:15:08 - mmengine - INFO - Epoch(train) [91][200/293] lr: 5.000000e-04 eta: 6:28:02 time: 0.769341 data_time: 0.103138 memory: 21676 loss_kpt: 0.000599 acc_pose: 0.825474 loss: 0.000599 2022/09/09 05:15:46 - mmengine - INFO - Epoch(train) [91][250/293] lr: 5.000000e-04 eta: 6:27:34 time: 0.749971 data_time: 0.102210 memory: 21676 loss_kpt: 0.000600 acc_pose: 0.861145 loss: 0.000600 2022/09/09 05:16:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 05:16:19 - mmengine - INFO - Saving checkpoint at 91 epochs 2022/09/09 05:17:02 - mmengine - INFO - Epoch(train) [92][50/293] lr: 5.000000e-04 eta: 6:26:04 time: 0.797799 data_time: 0.124130 memory: 21676 loss_kpt: 0.000595 acc_pose: 0.800342 loss: 0.000595 2022/09/09 05:17:41 - mmengine - INFO - Epoch(train) [92][100/293] lr: 5.000000e-04 eta: 6:25:37 time: 0.775054 data_time: 0.113692 memory: 21676 loss_kpt: 0.000602 acc_pose: 0.798372 loss: 0.000602 2022/09/09 05:18:19 - mmengine - INFO - Epoch(train) [92][150/293] lr: 5.000000e-04 eta: 6:25:11 time: 0.764787 data_time: 0.100378 memory: 21676 loss_kpt: 0.000595 acc_pose: 0.826272 loss: 0.000595 2022/09/09 05:18:57 - mmengine - INFO - Epoch(train) [92][200/293] lr: 5.000000e-04 eta: 6:24:43 time: 0.759197 data_time: 0.102324 memory: 21676 loss_kpt: 0.000585 acc_pose: 0.788701 loss: 0.000585 2022/09/09 05:19:36 - mmengine - INFO - Epoch(train) [92][250/293] lr: 5.000000e-04 eta: 6:24:16 time: 0.762952 data_time: 0.101757 memory: 21676 loss_kpt: 0.000585 acc_pose: 0.812509 loss: 0.000585 2022/09/09 05:20:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 05:20:08 - mmengine - INFO - Saving checkpoint at 92 epochs 2022/09/09 05:20:47 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 05:20:51 - mmengine - INFO - Epoch(train) [93][50/293] lr: 5.000000e-04 eta: 6:22:44 time: 0.771904 data_time: 0.115941 memory: 21676 loss_kpt: 0.000596 acc_pose: 0.826213 loss: 0.000596 2022/09/09 05:21:29 - mmengine - INFO - Epoch(train) [93][100/293] lr: 5.000000e-04 eta: 6:22:17 time: 0.750940 data_time: 0.099215 memory: 21676 loss_kpt: 0.000596 acc_pose: 0.797544 loss: 0.000596 2022/09/09 05:22:07 - mmengine - INFO - Epoch(train) [93][150/293] lr: 5.000000e-04 eta: 6:21:49 time: 0.759108 data_time: 0.104678 memory: 21676 loss_kpt: 0.000582 acc_pose: 0.831892 loss: 0.000582 2022/09/09 05:22:45 - mmengine - INFO - Epoch(train) [93][200/293] lr: 5.000000e-04 eta: 6:21:23 time: 0.767573 data_time: 0.107845 memory: 21676 loss_kpt: 0.000578 acc_pose: 0.800017 loss: 0.000578 2022/09/09 05:23:24 - mmengine - INFO - Epoch(train) [93][250/293] lr: 5.000000e-04 eta: 6:20:56 time: 0.771712 data_time: 0.104757 memory: 21676 loss_kpt: 0.000572 acc_pose: 0.851498 loss: 0.000572 2022/09/09 05:23:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 05:23:56 - mmengine - INFO - Saving checkpoint at 93 epochs 2022/09/09 05:24:40 - mmengine - INFO - Epoch(train) [94][50/293] lr: 5.000000e-04 eta: 6:19:25 time: 0.779148 data_time: 0.118683 memory: 21676 loss_kpt: 0.000583 acc_pose: 0.867397 loss: 0.000583 2022/09/09 05:25:18 - mmengine - INFO - Epoch(train) [94][100/293] lr: 5.000000e-04 eta: 6:18:58 time: 0.764145 data_time: 0.103926 memory: 21676 loss_kpt: 0.000601 acc_pose: 0.865925 loss: 0.000601 2022/09/09 05:25:56 - mmengine - INFO - Epoch(train) [94][150/293] lr: 5.000000e-04 eta: 6:18:31 time: 0.759714 data_time: 0.105666 memory: 21676 loss_kpt: 0.000593 acc_pose: 0.835574 loss: 0.000593 2022/09/09 05:26:35 - mmengine - INFO - Epoch(train) [94][200/293] lr: 5.000000e-04 eta: 6:18:04 time: 0.774127 data_time: 0.107269 memory: 21676 loss_kpt: 0.000582 acc_pose: 0.811437 loss: 0.000582 2022/09/09 05:27:13 - mmengine - INFO - Epoch(train) [94][250/293] lr: 5.000000e-04 eta: 6:17:37 time: 0.755457 data_time: 0.100330 memory: 21676 loss_kpt: 0.000585 acc_pose: 0.807157 loss: 0.000585 2022/09/09 05:27:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 05:27:44 - mmengine - INFO - Saving checkpoint at 94 epochs 2022/09/09 05:28:28 - mmengine - INFO - Epoch(train) [95][50/293] lr: 5.000000e-04 eta: 6:16:07 time: 0.789816 data_time: 0.119569 memory: 21676 loss_kpt: 0.000593 acc_pose: 0.863354 loss: 0.000593 2022/09/09 05:29:07 - mmengine - INFO - Epoch(train) [95][100/293] lr: 5.000000e-04 eta: 6:15:41 time: 0.787798 data_time: 0.109707 memory: 21676 loss_kpt: 0.000593 acc_pose: 0.815709 loss: 0.000593 2022/09/09 05:29:47 - mmengine - INFO - Epoch(train) [95][150/293] lr: 5.000000e-04 eta: 6:15:16 time: 0.794081 data_time: 0.107408 memory: 21676 loss_kpt: 0.000581 acc_pose: 0.854863 loss: 0.000581 2022/09/09 05:30:25 - mmengine - INFO - Epoch(train) [95][200/293] lr: 5.000000e-04 eta: 6:14:48 time: 0.759184 data_time: 0.104988 memory: 21676 loss_kpt: 0.000591 acc_pose: 0.834925 loss: 0.000591 2022/09/09 05:31:03 - mmengine - INFO - Epoch(train) [95][250/293] lr: 5.000000e-04 eta: 6:14:21 time: 0.761478 data_time: 0.102594 memory: 21676 loss_kpt: 0.000589 acc_pose: 0.763646 loss: 0.000589 2022/09/09 05:31:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 05:31:35 - mmengine - INFO - Saving checkpoint at 95 epochs 2022/09/09 05:32:19 - mmengine - INFO - Epoch(train) [96][50/293] lr: 5.000000e-04 eta: 6:12:53 time: 0.802906 data_time: 0.123650 memory: 21676 loss_kpt: 0.000598 acc_pose: 0.860987 loss: 0.000598 2022/09/09 05:32:58 - mmengine - INFO - Epoch(train) [96][100/293] lr: 5.000000e-04 eta: 6:12:26 time: 0.778930 data_time: 0.099924 memory: 21676 loss_kpt: 0.000581 acc_pose: 0.848636 loss: 0.000581 2022/09/09 05:33:37 - mmengine - INFO - Epoch(train) [96][150/293] lr: 5.000000e-04 eta: 6:12:00 time: 0.787450 data_time: 0.103401 memory: 21676 loss_kpt: 0.000592 acc_pose: 0.826508 loss: 0.000592 2022/09/09 05:33:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 05:34:16 - mmengine - INFO - Epoch(train) [96][200/293] lr: 5.000000e-04 eta: 6:11:33 time: 0.766633 data_time: 0.098848 memory: 21676 loss_kpt: 0.000601 acc_pose: 0.846770 loss: 0.000601 2022/09/09 05:34:53 - mmengine - INFO - Epoch(train) [96][250/293] lr: 5.000000e-04 eta: 6:11:05 time: 0.750147 data_time: 0.102721 memory: 21676 loss_kpt: 0.000592 acc_pose: 0.854906 loss: 0.000592 2022/09/09 05:35:25 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 05:35:25 - mmengine - INFO - Saving checkpoint at 96 epochs 2022/09/09 05:36:09 - mmengine - INFO - Epoch(train) [97][50/293] lr: 5.000000e-04 eta: 6:09:36 time: 0.786252 data_time: 0.111020 memory: 21676 loss_kpt: 0.000582 acc_pose: 0.773146 loss: 0.000582 2022/09/09 05:36:47 - mmengine - INFO - Epoch(train) [97][100/293] lr: 5.000000e-04 eta: 6:09:09 time: 0.760178 data_time: 0.108587 memory: 21676 loss_kpt: 0.000591 acc_pose: 0.815734 loss: 0.000591 2022/09/09 05:37:25 - mmengine - INFO - Epoch(train) [97][150/293] lr: 5.000000e-04 eta: 6:08:41 time: 0.766645 data_time: 0.100387 memory: 21676 loss_kpt: 0.000585 acc_pose: 0.869665 loss: 0.000585 2022/09/09 05:38:04 - mmengine - INFO - Epoch(train) [97][200/293] lr: 5.000000e-04 eta: 6:08:14 time: 0.767062 data_time: 0.108542 memory: 21676 loss_kpt: 0.000595 acc_pose: 0.856281 loss: 0.000595 2022/09/09 05:38:41 - mmengine - INFO - Epoch(train) [97][250/293] lr: 5.000000e-04 eta: 6:07:46 time: 0.757583 data_time: 0.101679 memory: 21676 loss_kpt: 0.000585 acc_pose: 0.834448 loss: 0.000585 2022/09/09 05:39:14 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 05:39:14 - mmengine - INFO - Saving checkpoint at 97 epochs 2022/09/09 05:39:59 - mmengine - INFO - Epoch(train) [98][50/293] lr: 5.000000e-04 eta: 6:06:18 time: 0.791624 data_time: 0.125740 memory: 21676 loss_kpt: 0.000581 acc_pose: 0.842483 loss: 0.000581 2022/09/09 05:40:38 - mmengine - INFO - Epoch(train) [98][100/293] lr: 5.000000e-04 eta: 6:05:52 time: 0.779614 data_time: 0.103960 memory: 21676 loss_kpt: 0.000581 acc_pose: 0.837249 loss: 0.000581 2022/09/09 05:41:16 - mmengine - INFO - Epoch(train) [98][150/293] lr: 5.000000e-04 eta: 6:05:24 time: 0.768624 data_time: 0.105523 memory: 21676 loss_kpt: 0.000599 acc_pose: 0.795419 loss: 0.000599 2022/09/09 05:41:54 - mmengine - INFO - Epoch(train) [98][200/293] lr: 5.000000e-04 eta: 6:04:56 time: 0.754248 data_time: 0.101980 memory: 21676 loss_kpt: 0.000595 acc_pose: 0.846745 loss: 0.000595 2022/09/09 05:42:33 - mmengine - INFO - Epoch(train) [98][250/293] lr: 5.000000e-04 eta: 6:04:29 time: 0.770961 data_time: 0.097899 memory: 21676 loss_kpt: 0.000588 acc_pose: 0.799006 loss: 0.000588 2022/09/09 05:43:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 05:43:05 - mmengine - INFO - Saving checkpoint at 98 epochs 2022/09/09 05:43:49 - mmengine - INFO - Epoch(train) [99][50/293] lr: 5.000000e-04 eta: 6:03:02 time: 0.789333 data_time: 0.117995 memory: 21676 loss_kpt: 0.000579 acc_pose: 0.829282 loss: 0.000579 2022/09/09 05:44:28 - mmengine - INFO - Epoch(train) [99][100/293] lr: 5.000000e-04 eta: 6:02:35 time: 0.781709 data_time: 0.110087 memory: 21676 loss_kpt: 0.000594 acc_pose: 0.843711 loss: 0.000594 2022/09/09 05:45:06 - mmengine - INFO - Epoch(train) [99][150/293] lr: 5.000000e-04 eta: 6:02:08 time: 0.773642 data_time: 0.106038 memory: 21676 loss_kpt: 0.000597 acc_pose: 0.858157 loss: 0.000597 2022/09/09 05:45:44 - mmengine - INFO - Epoch(train) [99][200/293] lr: 5.000000e-04 eta: 6:01:40 time: 0.753101 data_time: 0.101469 memory: 21676 loss_kpt: 0.000586 acc_pose: 0.810029 loss: 0.000586 2022/09/09 05:46:22 - mmengine - INFO - Epoch(train) [99][250/293] lr: 5.000000e-04 eta: 6:01:12 time: 0.757832 data_time: 0.103081 memory: 21676 loss_kpt: 0.000593 acc_pose: 0.804756 loss: 0.000593 2022/09/09 05:46:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 05:46:54 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 05:46:54 - mmengine - INFO - Saving checkpoint at 99 epochs 2022/09/09 05:47:38 - mmengine - INFO - Epoch(train) [100][50/293] lr: 5.000000e-04 eta: 5:59:44 time: 0.781351 data_time: 0.113055 memory: 21676 loss_kpt: 0.000590 acc_pose: 0.830318 loss: 0.000590 2022/09/09 05:48:16 - mmengine - INFO - Epoch(train) [100][100/293] lr: 5.000000e-04 eta: 5:59:16 time: 0.763600 data_time: 0.107916 memory: 21676 loss_kpt: 0.000577 acc_pose: 0.825456 loss: 0.000577 2022/09/09 05:48:54 - mmengine - INFO - Epoch(train) [100][150/293] lr: 5.000000e-04 eta: 5:58:49 time: 0.763405 data_time: 0.097318 memory: 21676 loss_kpt: 0.000598 acc_pose: 0.773975 loss: 0.000598 2022/09/09 05:49:32 - mmengine - INFO - Epoch(train) [100][200/293] lr: 5.000000e-04 eta: 5:58:20 time: 0.747358 data_time: 0.104833 memory: 21676 loss_kpt: 0.000586 acc_pose: 0.843224 loss: 0.000586 2022/09/09 05:50:10 - mmengine - INFO - Epoch(train) [100][250/293] lr: 5.000000e-04 eta: 5:57:52 time: 0.759828 data_time: 0.100779 memory: 21676 loss_kpt: 0.000589 acc_pose: 0.851825 loss: 0.000589 2022/09/09 05:50:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 05:50:42 - mmengine - INFO - Saving checkpoint at 100 epochs 2022/09/09 05:50:54 - mmengine - INFO - Epoch(val) [100][50/407] eta: 0:00:56 time: 0.158302 data_time: 0.014413 memory: 21676 2022/09/09 05:51:02 - mmengine - INFO - Epoch(val) [100][100/407] eta: 0:00:46 time: 0.151613 data_time: 0.009311 memory: 1375 2022/09/09 05:51:09 - mmengine - INFO - Epoch(val) [100][150/407] eta: 0:00:38 time: 0.150044 data_time: 0.009044 memory: 1375 2022/09/09 05:51:17 - mmengine - INFO - Epoch(val) [100][200/407] eta: 0:00:31 time: 0.151100 data_time: 0.009474 memory: 1375 2022/09/09 05:51:25 - mmengine - INFO - Epoch(val) [100][250/407] eta: 0:00:24 time: 0.155636 data_time: 0.013188 memory: 1375 2022/09/09 05:51:32 - mmengine - INFO - Epoch(val) [100][300/407] eta: 0:00:16 time: 0.150694 data_time: 0.008454 memory: 1375 2022/09/09 05:51:40 - mmengine - INFO - Epoch(val) [100][350/407] eta: 0:00:08 time: 0.149873 data_time: 0.008005 memory: 1375 2022/09/09 05:51:47 - mmengine - INFO - Epoch(val) [100][400/407] eta: 0:00:01 time: 0.151124 data_time: 0.010093 memory: 1375 2022/09/09 05:52:25 - mmengine - INFO - Evaluating CocoMetric... 2022/09/09 05:52:39 - mmengine - INFO - Epoch(val) [100][407/407] coco/AP: 0.745557 coco/AP .5: 0.899614 coco/AP .75: 0.812078 coco/AP (M): 0.706873 coco/AP (L): 0.816912 coco/AR: 0.797025 coco/AR .5: 0.937815 coco/AR .75: 0.858155 coco/AR (M): 0.752772 coco/AR (L): 0.860944 2022/09/09 05:52:39 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220908/hrnet_w32_384/best_coco/AP_epoch_90.pth is removed 2022/09/09 05:52:42 - mmengine - INFO - The best checkpoint with 0.7456 coco/AP at 100 epoch is saved to best_coco/AP_epoch_100.pth. 2022/09/09 05:53:22 - mmengine - INFO - Epoch(train) [101][50/293] lr: 5.000000e-04 eta: 5:56:26 time: 0.790582 data_time: 0.117510 memory: 21676 loss_kpt: 0.000570 acc_pose: 0.851681 loss: 0.000570 2022/09/09 05:53:59 - mmengine - INFO - Epoch(train) [101][100/293] lr: 5.000000e-04 eta: 5:55:57 time: 0.756684 data_time: 0.101298 memory: 21676 loss_kpt: 0.000585 acc_pose: 0.867198 loss: 0.000585 2022/09/09 05:54:37 - mmengine - INFO - Epoch(train) [101][150/293] lr: 5.000000e-04 eta: 5:55:29 time: 0.746683 data_time: 0.099512 memory: 21676 loss_kpt: 0.000605 acc_pose: 0.813713 loss: 0.000605 2022/09/09 05:55:15 - mmengine - INFO - Epoch(train) [101][200/293] lr: 5.000000e-04 eta: 5:55:01 time: 0.770841 data_time: 0.105444 memory: 21676 loss_kpt: 0.000584 acc_pose: 0.804433 loss: 0.000584 2022/09/09 05:55:53 - mmengine - INFO - Epoch(train) [101][250/293] lr: 5.000000e-04 eta: 5:54:33 time: 0.756445 data_time: 0.100863 memory: 21676 loss_kpt: 0.000594 acc_pose: 0.819396 loss: 0.000594 2022/09/09 05:56:25 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 05:56:26 - mmengine - INFO - Saving checkpoint at 101 epochs 2022/09/09 05:57:08 - mmengine - INFO - Epoch(train) [102][50/293] lr: 5.000000e-04 eta: 5:53:06 time: 0.770468 data_time: 0.106117 memory: 21676 loss_kpt: 0.000577 acc_pose: 0.823121 loss: 0.000577 2022/09/09 05:57:46 - mmengine - INFO - Epoch(train) [102][100/293] lr: 5.000000e-04 eta: 5:52:38 time: 0.771943 data_time: 0.099371 memory: 21676 loss_kpt: 0.000585 acc_pose: 0.845090 loss: 0.000585 2022/09/09 05:58:26 - mmengine - INFO - Epoch(train) [102][150/293] lr: 5.000000e-04 eta: 5:52:12 time: 0.783832 data_time: 0.104112 memory: 21676 loss_kpt: 0.000587 acc_pose: 0.844400 loss: 0.000587 2022/09/09 05:59:04 - mmengine - INFO - Epoch(train) [102][200/293] lr: 5.000000e-04 eta: 5:51:44 time: 0.770719 data_time: 0.095750 memory: 21676 loss_kpt: 0.000582 acc_pose: 0.824356 loss: 0.000582 2022/09/09 05:59:42 - mmengine - INFO - Epoch(train) [102][250/293] lr: 5.000000e-04 eta: 5:51:16 time: 0.757125 data_time: 0.095551 memory: 21676 loss_kpt: 0.000588 acc_pose: 0.800523 loss: 0.000588 2022/09/09 06:00:16 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 06:00:16 - mmengine - INFO - Saving checkpoint at 102 epochs 2022/09/09 06:01:00 - mmengine - INFO - Epoch(train) [103][50/293] lr: 5.000000e-04 eta: 5:49:50 time: 0.786472 data_time: 0.112935 memory: 21676 loss_kpt: 0.000573 acc_pose: 0.869140 loss: 0.000573 2022/09/09 06:01:39 - mmengine - INFO - Epoch(train) [103][100/293] lr: 5.000000e-04 eta: 5:49:22 time: 0.768219 data_time: 0.104575 memory: 21676 loss_kpt: 0.000579 acc_pose: 0.853940 loss: 0.000579 2022/09/09 06:01:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 06:02:17 - mmengine - INFO - Epoch(train) [103][150/293] lr: 5.000000e-04 eta: 5:48:54 time: 0.758421 data_time: 0.096336 memory: 21676 loss_kpt: 0.000592 acc_pose: 0.856430 loss: 0.000592 2022/09/09 06:02:54 - mmengine - INFO - Epoch(train) [103][200/293] lr: 5.000000e-04 eta: 5:48:25 time: 0.751113 data_time: 0.095298 memory: 21676 loss_kpt: 0.000577 acc_pose: 0.847681 loss: 0.000577 2022/09/09 06:03:31 - mmengine - INFO - Epoch(train) [103][250/293] lr: 5.000000e-04 eta: 5:47:56 time: 0.746225 data_time: 0.095888 memory: 21676 loss_kpt: 0.000580 acc_pose: 0.855965 loss: 0.000580 2022/09/09 06:04:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 06:04:04 - mmengine - INFO - Saving checkpoint at 103 epochs 2022/09/09 06:04:48 - mmengine - INFO - Epoch(train) [104][50/293] lr: 5.000000e-04 eta: 5:46:31 time: 0.784886 data_time: 0.108220 memory: 21676 loss_kpt: 0.000591 acc_pose: 0.847808 loss: 0.000591 2022/09/09 06:05:26 - mmengine - INFO - Epoch(train) [104][100/293] lr: 5.000000e-04 eta: 5:46:03 time: 0.762300 data_time: 0.098056 memory: 21676 loss_kpt: 0.000580 acc_pose: 0.829247 loss: 0.000580 2022/09/09 06:06:05 - mmengine - INFO - Epoch(train) [104][150/293] lr: 5.000000e-04 eta: 5:45:34 time: 0.761244 data_time: 0.094726 memory: 21676 loss_kpt: 0.000593 acc_pose: 0.883116 loss: 0.000593 2022/09/09 06:06:42 - mmengine - INFO - Epoch(train) [104][200/293] lr: 5.000000e-04 eta: 5:45:06 time: 0.751172 data_time: 0.096536 memory: 21676 loss_kpt: 0.000586 acc_pose: 0.828715 loss: 0.000586 2022/09/09 06:07:20 - mmengine - INFO - Epoch(train) [104][250/293] lr: 5.000000e-04 eta: 5:44:37 time: 0.758556 data_time: 0.094730 memory: 21676 loss_kpt: 0.000583 acc_pose: 0.855770 loss: 0.000583 2022/09/09 06:07:52 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 06:07:52 - mmengine - INFO - Saving checkpoint at 104 epochs 2022/09/09 06:08:35 - mmengine - INFO - Epoch(train) [105][50/293] lr: 5.000000e-04 eta: 5:43:12 time: 0.768439 data_time: 0.107820 memory: 21676 loss_kpt: 0.000587 acc_pose: 0.807731 loss: 0.000587 2022/09/09 06:09:14 - mmengine - INFO - Epoch(train) [105][100/293] lr: 5.000000e-04 eta: 5:42:44 time: 0.767403 data_time: 0.101294 memory: 21676 loss_kpt: 0.000582 acc_pose: 0.804094 loss: 0.000582 2022/09/09 06:09:51 - mmengine - INFO - Epoch(train) [105][150/293] lr: 5.000000e-04 eta: 5:42:15 time: 0.757952 data_time: 0.094497 memory: 21676 loss_kpt: 0.000585 acc_pose: 0.824624 loss: 0.000585 2022/09/09 06:10:30 - mmengine - INFO - Epoch(train) [105][200/293] lr: 5.000000e-04 eta: 5:41:47 time: 0.761473 data_time: 0.098985 memory: 21676 loss_kpt: 0.000582 acc_pose: 0.824297 loss: 0.000582 2022/09/09 06:11:07 - mmengine - INFO - Epoch(train) [105][250/293] lr: 5.000000e-04 eta: 5:41:18 time: 0.753180 data_time: 0.097712 memory: 21676 loss_kpt: 0.000571 acc_pose: 0.877399 loss: 0.000571 2022/09/09 06:11:39 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 06:11:39 - mmengine - INFO - Saving checkpoint at 105 epochs 2022/09/09 06:12:24 - mmengine - INFO - Epoch(train) [106][50/293] lr: 5.000000e-04 eta: 5:39:54 time: 0.797125 data_time: 0.110794 memory: 21676 loss_kpt: 0.000579 acc_pose: 0.805384 loss: 0.000579 2022/09/09 06:13:01 - mmengine - INFO - Epoch(train) [106][100/293] lr: 5.000000e-04 eta: 5:39:26 time: 0.754113 data_time: 0.098040 memory: 21676 loss_kpt: 0.000577 acc_pose: 0.821399 loss: 0.000577 2022/09/09 06:13:40 - mmengine - INFO - Epoch(train) [106][150/293] lr: 5.000000e-04 eta: 5:38:57 time: 0.763549 data_time: 0.095220 memory: 21676 loss_kpt: 0.000577 acc_pose: 0.820867 loss: 0.000577 2022/09/09 06:14:18 - mmengine - INFO - Epoch(train) [106][200/293] lr: 5.000000e-04 eta: 5:38:29 time: 0.761640 data_time: 0.101162 memory: 21676 loss_kpt: 0.000583 acc_pose: 0.831096 loss: 0.000583 2022/09/09 06:14:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 06:14:56 - mmengine - INFO - Epoch(train) [106][250/293] lr: 5.000000e-04 eta: 5:38:00 time: 0.758981 data_time: 0.096717 memory: 21676 loss_kpt: 0.000561 acc_pose: 0.821033 loss: 0.000561 2022/09/09 06:15:28 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 06:15:28 - mmengine - INFO - Saving checkpoint at 106 epochs 2022/09/09 06:16:12 - mmengine - INFO - Epoch(train) [107][50/293] lr: 5.000000e-04 eta: 5:36:37 time: 0.796991 data_time: 0.114693 memory: 21676 loss_kpt: 0.000588 acc_pose: 0.829345 loss: 0.000588 2022/09/09 06:16:51 - mmengine - INFO - Epoch(train) [107][100/293] lr: 5.000000e-04 eta: 5:36:10 time: 0.788475 data_time: 0.098402 memory: 21676 loss_kpt: 0.000582 acc_pose: 0.854780 loss: 0.000582 2022/09/09 06:17:30 - mmengine - INFO - Epoch(train) [107][150/293] lr: 5.000000e-04 eta: 5:35:43 time: 0.787482 data_time: 0.096968 memory: 21676 loss_kpt: 0.000588 acc_pose: 0.803756 loss: 0.000588 2022/09/09 06:18:08 - mmengine - INFO - Epoch(train) [107][200/293] lr: 5.000000e-04 eta: 5:35:14 time: 0.759953 data_time: 0.096663 memory: 21676 loss_kpt: 0.000585 acc_pose: 0.790909 loss: 0.000585 2022/09/09 06:18:47 - mmengine - INFO - Epoch(train) [107][250/293] lr: 5.000000e-04 eta: 5:34:46 time: 0.767217 data_time: 0.097309 memory: 21676 loss_kpt: 0.000576 acc_pose: 0.886751 loss: 0.000576 2022/09/09 06:19:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 06:19:19 - mmengine - INFO - Saving checkpoint at 107 epochs 2022/09/09 06:20:03 - mmengine - INFO - Epoch(train) [108][50/293] lr: 5.000000e-04 eta: 5:33:22 time: 0.786223 data_time: 0.115513 memory: 21676 loss_kpt: 0.000587 acc_pose: 0.830712 loss: 0.000587 2022/09/09 06:20:42 - mmengine - INFO - Epoch(train) [108][100/293] lr: 5.000000e-04 eta: 5:32:54 time: 0.766605 data_time: 0.094565 memory: 21676 loss_kpt: 0.000585 acc_pose: 0.813005 loss: 0.000585 2022/09/09 06:21:19 - mmengine - INFO - Epoch(train) [108][150/293] lr: 5.000000e-04 eta: 5:32:25 time: 0.757273 data_time: 0.102853 memory: 21676 loss_kpt: 0.000576 acc_pose: 0.856207 loss: 0.000576 2022/09/09 06:21:57 - mmengine - INFO - Epoch(train) [108][200/293] lr: 5.000000e-04 eta: 5:31:57 time: 0.755070 data_time: 0.095811 memory: 21676 loss_kpt: 0.000592 acc_pose: 0.834427 loss: 0.000592 2022/09/09 06:22:36 - mmengine - INFO - Epoch(train) [108][250/293] lr: 5.000000e-04 eta: 5:31:28 time: 0.772632 data_time: 0.107041 memory: 21676 loss_kpt: 0.000575 acc_pose: 0.807211 loss: 0.000575 2022/09/09 06:23:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 06:23:08 - mmengine - INFO - Saving checkpoint at 108 epochs 2022/09/09 06:23:51 - mmengine - INFO - Epoch(train) [109][50/293] lr: 5.000000e-04 eta: 5:30:05 time: 0.778260 data_time: 0.111043 memory: 21676 loss_kpt: 0.000578 acc_pose: 0.866658 loss: 0.000578 2022/09/09 06:24:30 - mmengine - INFO - Epoch(train) [109][100/293] lr: 5.000000e-04 eta: 5:29:37 time: 0.773147 data_time: 0.106014 memory: 21676 loss_kpt: 0.000569 acc_pose: 0.855747 loss: 0.000569 2022/09/09 06:25:08 - mmengine - INFO - Epoch(train) [109][150/293] lr: 5.000000e-04 eta: 5:29:09 time: 0.772027 data_time: 0.108321 memory: 21676 loss_kpt: 0.000574 acc_pose: 0.845051 loss: 0.000574 2022/09/09 06:25:47 - mmengine - INFO - Epoch(train) [109][200/293] lr: 5.000000e-04 eta: 5:28:40 time: 0.761060 data_time: 0.109085 memory: 21676 loss_kpt: 0.000583 acc_pose: 0.822863 loss: 0.000583 2022/09/09 06:26:24 - mmengine - INFO - Epoch(train) [109][250/293] lr: 5.000000e-04 eta: 5:28:11 time: 0.751043 data_time: 0.108741 memory: 21676 loss_kpt: 0.000587 acc_pose: 0.853023 loss: 0.000587 2022/09/09 06:26:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 06:26:56 - mmengine - INFO - Saving checkpoint at 109 epochs 2022/09/09 06:27:40 - mmengine - INFO - Epoch(train) [110][50/293] lr: 5.000000e-04 eta: 5:26:48 time: 0.782550 data_time: 0.119743 memory: 21676 loss_kpt: 0.000579 acc_pose: 0.838210 loss: 0.000579 2022/09/09 06:27:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 06:28:18 - mmengine - INFO - Epoch(train) [110][100/293] lr: 5.000000e-04 eta: 5:26:20 time: 0.760233 data_time: 0.108469 memory: 21676 loss_kpt: 0.000585 acc_pose: 0.877609 loss: 0.000585 2022/09/09 06:28:56 - mmengine - INFO - Epoch(train) [110][150/293] lr: 5.000000e-04 eta: 5:25:51 time: 0.761318 data_time: 0.103533 memory: 21676 loss_kpt: 0.000574 acc_pose: 0.830324 loss: 0.000574 2022/09/09 06:29:34 - mmengine - INFO - Epoch(train) [110][200/293] lr: 5.000000e-04 eta: 5:25:22 time: 0.757628 data_time: 0.102989 memory: 21676 loss_kpt: 0.000583 acc_pose: 0.842232 loss: 0.000583 2022/09/09 06:30:12 - mmengine - INFO - Epoch(train) [110][250/293] lr: 5.000000e-04 eta: 5:24:53 time: 0.764162 data_time: 0.104294 memory: 21676 loss_kpt: 0.000582 acc_pose: 0.817619 loss: 0.000582 2022/09/09 06:30:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 06:30:44 - mmengine - INFO - Saving checkpoint at 110 epochs 2022/09/09 06:30:56 - mmengine - INFO - Epoch(val) [110][50/407] eta: 0:00:55 time: 0.155463 data_time: 0.013304 memory: 21676 2022/09/09 06:31:04 - mmengine - INFO - Epoch(val) [110][100/407] eta: 0:00:46 time: 0.150190 data_time: 0.008656 memory: 1375 2022/09/09 06:31:11 - mmengine - INFO - Epoch(val) [110][150/407] eta: 0:00:38 time: 0.150814 data_time: 0.008383 memory: 1375 2022/09/09 06:31:19 - mmengine - INFO - Epoch(val) [110][200/407] eta: 0:00:31 time: 0.153243 data_time: 0.008774 memory: 1375 2022/09/09 06:31:27 - mmengine - INFO - Epoch(val) [110][250/407] eta: 0:00:23 time: 0.150024 data_time: 0.008802 memory: 1375 2022/09/09 06:31:34 - mmengine - INFO - Epoch(val) [110][300/407] eta: 0:00:16 time: 0.154434 data_time: 0.012224 memory: 1375 2022/09/09 06:31:42 - mmengine - INFO - Epoch(val) [110][350/407] eta: 0:00:08 time: 0.152136 data_time: 0.009806 memory: 1375 2022/09/09 06:31:49 - mmengine - INFO - Epoch(val) [110][400/407] eta: 0:00:01 time: 0.149375 data_time: 0.008227 memory: 1375 2022/09/09 06:32:26 - mmengine - INFO - Evaluating CocoMetric... 2022/09/09 06:32:40 - mmengine - INFO - Epoch(val) [110][407/407] coco/AP: 0.747627 coco/AP .5: 0.900147 coco/AP .75: 0.818607 coco/AP (M): 0.708134 coco/AP (L): 0.818260 coco/AR: 0.798693 coco/AR .5: 0.937657 coco/AR .75: 0.862248 coco/AR (M): 0.755067 coco/AR (L): 0.862170 2022/09/09 06:32:41 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220908/hrnet_w32_384/best_coco/AP_epoch_100.pth is removed 2022/09/09 06:32:43 - mmengine - INFO - The best checkpoint with 0.7476 coco/AP at 110 epoch is saved to best_coco/AP_epoch_110.pth. 2022/09/09 06:33:22 - mmengine - INFO - Epoch(train) [111][50/293] lr: 5.000000e-04 eta: 5:23:31 time: 0.782400 data_time: 0.113083 memory: 21676 loss_kpt: 0.000563 acc_pose: 0.817688 loss: 0.000563 2022/09/09 06:34:02 - mmengine - INFO - Epoch(train) [111][100/293] lr: 5.000000e-04 eta: 5:23:03 time: 0.781749 data_time: 0.093187 memory: 21676 loss_kpt: 0.000585 acc_pose: 0.857619 loss: 0.000585 2022/09/09 06:34:41 - mmengine - INFO - Epoch(train) [111][150/293] lr: 5.000000e-04 eta: 5:22:36 time: 0.799159 data_time: 0.101011 memory: 21676 loss_kpt: 0.000581 acc_pose: 0.876571 loss: 0.000581 2022/09/09 06:35:20 - mmengine - INFO - Epoch(train) [111][200/293] lr: 5.000000e-04 eta: 5:22:08 time: 0.778838 data_time: 0.096192 memory: 21676 loss_kpt: 0.000573 acc_pose: 0.818597 loss: 0.000573 2022/09/09 06:36:00 - mmengine - INFO - Epoch(train) [111][250/293] lr: 5.000000e-04 eta: 5:21:40 time: 0.782200 data_time: 0.098038 memory: 21676 loss_kpt: 0.000578 acc_pose: 0.837064 loss: 0.000578 2022/09/09 06:36:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 06:36:32 - mmengine - INFO - Saving checkpoint at 111 epochs 2022/09/09 06:37:16 - mmengine - INFO - Epoch(train) [112][50/293] lr: 5.000000e-04 eta: 5:20:19 time: 0.792967 data_time: 0.116574 memory: 21676 loss_kpt: 0.000580 acc_pose: 0.852289 loss: 0.000580 2022/09/09 06:37:55 - mmengine - INFO - Epoch(train) [112][100/293] lr: 5.000000e-04 eta: 5:19:51 time: 0.780622 data_time: 0.100679 memory: 21676 loss_kpt: 0.000580 acc_pose: 0.829585 loss: 0.000580 2022/09/09 06:38:33 - mmengine - INFO - Epoch(train) [112][150/293] lr: 5.000000e-04 eta: 5:19:22 time: 0.771879 data_time: 0.101355 memory: 21676 loss_kpt: 0.000586 acc_pose: 0.854324 loss: 0.000586 2022/09/09 06:39:12 - mmengine - INFO - Epoch(train) [112][200/293] lr: 5.000000e-04 eta: 5:18:53 time: 0.767262 data_time: 0.097522 memory: 21676 loss_kpt: 0.000573 acc_pose: 0.824294 loss: 0.000573 2022/09/09 06:39:49 - mmengine - INFO - Epoch(train) [112][250/293] lr: 5.000000e-04 eta: 5:18:24 time: 0.752903 data_time: 0.097141 memory: 21676 loss_kpt: 0.000577 acc_pose: 0.835396 loss: 0.000577 2022/09/09 06:40:21 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 06:40:21 - mmengine - INFO - Saving checkpoint at 112 epochs 2022/09/09 06:41:06 - mmengine - INFO - Epoch(train) [113][50/293] lr: 5.000000e-04 eta: 5:17:03 time: 0.795657 data_time: 0.113008 memory: 21676 loss_kpt: 0.000578 acc_pose: 0.820428 loss: 0.000578 2022/09/09 06:41:44 - mmengine - INFO - Epoch(train) [113][100/293] lr: 5.000000e-04 eta: 5:16:35 time: 0.772363 data_time: 0.099344 memory: 21676 loss_kpt: 0.000576 acc_pose: 0.788086 loss: 0.000576 2022/09/09 06:42:22 - mmengine - INFO - Epoch(train) [113][150/293] lr: 5.000000e-04 eta: 5:16:05 time: 0.752866 data_time: 0.097641 memory: 21676 loss_kpt: 0.000571 acc_pose: 0.868001 loss: 0.000571 2022/09/09 06:42:47 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 06:43:00 - mmengine - INFO - Epoch(train) [113][200/293] lr: 5.000000e-04 eta: 5:15:36 time: 0.756113 data_time: 0.097352 memory: 21676 loss_kpt: 0.000575 acc_pose: 0.859593 loss: 0.000575 2022/09/09 06:43:37 - mmengine - INFO - Epoch(train) [113][250/293] lr: 5.000000e-04 eta: 5:15:06 time: 0.747147 data_time: 0.092663 memory: 21676 loss_kpt: 0.000577 acc_pose: 0.845259 loss: 0.000577 2022/09/09 06:44:09 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 06:44:09 - mmengine - INFO - Saving checkpoint at 113 epochs 2022/09/09 06:44:54 - mmengine - INFO - Epoch(train) [114][50/293] lr: 5.000000e-04 eta: 5:13:46 time: 0.791878 data_time: 0.111243 memory: 21676 loss_kpt: 0.000574 acc_pose: 0.813920 loss: 0.000574 2022/09/09 06:45:33 - mmengine - INFO - Epoch(train) [114][100/293] lr: 5.000000e-04 eta: 5:13:18 time: 0.784551 data_time: 0.093586 memory: 21676 loss_kpt: 0.000570 acc_pose: 0.819956 loss: 0.000570 2022/09/09 06:46:12 - mmengine - INFO - Epoch(train) [114][150/293] lr: 5.000000e-04 eta: 5:12:49 time: 0.773460 data_time: 0.097182 memory: 21676 loss_kpt: 0.000573 acc_pose: 0.821803 loss: 0.000573 2022/09/09 06:46:50 - mmengine - INFO - Epoch(train) [114][200/293] lr: 5.000000e-04 eta: 5:12:20 time: 0.761605 data_time: 0.093478 memory: 21676 loss_kpt: 0.000578 acc_pose: 0.858743 loss: 0.000578 2022/09/09 06:47:27 - mmengine - INFO - Epoch(train) [114][250/293] lr: 5.000000e-04 eta: 5:11:51 time: 0.754414 data_time: 0.095375 memory: 21676 loss_kpt: 0.000586 acc_pose: 0.790114 loss: 0.000586 2022/09/09 06:48:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 06:48:00 - mmengine - INFO - Saving checkpoint at 114 epochs 2022/09/09 06:48:44 - mmengine - INFO - Epoch(train) [115][50/293] lr: 5.000000e-04 eta: 5:10:30 time: 0.793488 data_time: 0.111503 memory: 21676 loss_kpt: 0.000579 acc_pose: 0.868578 loss: 0.000579 2022/09/09 06:49:23 - mmengine - INFO - Epoch(train) [115][100/293] lr: 5.000000e-04 eta: 5:10:02 time: 0.780609 data_time: 0.097222 memory: 21676 loss_kpt: 0.000572 acc_pose: 0.843714 loss: 0.000572 2022/09/09 06:50:01 - mmengine - INFO - Epoch(train) [115][150/293] lr: 5.000000e-04 eta: 5:09:33 time: 0.757360 data_time: 0.103590 memory: 21676 loss_kpt: 0.000568 acc_pose: 0.814817 loss: 0.000568 2022/09/09 06:50:39 - mmengine - INFO - Epoch(train) [115][200/293] lr: 5.000000e-04 eta: 5:09:04 time: 0.759267 data_time: 0.098516 memory: 21676 loss_kpt: 0.000580 acc_pose: 0.856310 loss: 0.000580 2022/09/09 06:51:17 - mmengine - INFO - Epoch(train) [115][250/293] lr: 5.000000e-04 eta: 5:08:35 time: 0.767996 data_time: 0.101167 memory: 21676 loss_kpt: 0.000580 acc_pose: 0.803910 loss: 0.000580 2022/09/09 06:51:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 06:51:50 - mmengine - INFO - Saving checkpoint at 115 epochs 2022/09/09 06:52:34 - mmengine - INFO - Epoch(train) [116][50/293] lr: 5.000000e-04 eta: 5:07:15 time: 0.787730 data_time: 0.111257 memory: 21676 loss_kpt: 0.000568 acc_pose: 0.876272 loss: 0.000568 2022/09/09 06:53:12 - mmengine - INFO - Epoch(train) [116][100/293] lr: 5.000000e-04 eta: 5:06:46 time: 0.771752 data_time: 0.096718 memory: 21676 loss_kpt: 0.000567 acc_pose: 0.865203 loss: 0.000567 2022/09/09 06:53:51 - mmengine - INFO - Epoch(train) [116][150/293] lr: 5.000000e-04 eta: 5:06:17 time: 0.765486 data_time: 0.098191 memory: 21676 loss_kpt: 0.000562 acc_pose: 0.842124 loss: 0.000562 2022/09/09 06:54:29 - mmengine - INFO - Epoch(train) [116][200/293] lr: 5.000000e-04 eta: 5:05:48 time: 0.759935 data_time: 0.098813 memory: 21676 loss_kpt: 0.000580 acc_pose: 0.893142 loss: 0.000580 2022/09/09 06:55:06 - mmengine - INFO - Epoch(train) [116][250/293] lr: 5.000000e-04 eta: 5:05:18 time: 0.752086 data_time: 0.096313 memory: 21676 loss_kpt: 0.000570 acc_pose: 0.849549 loss: 0.000570 2022/09/09 06:55:39 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 06:55:39 - mmengine - INFO - Saving checkpoint at 116 epochs 2022/09/09 06:55:53 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 06:56:23 - mmengine - INFO - Epoch(train) [117][50/293] lr: 5.000000e-04 eta: 5:03:58 time: 0.786994 data_time: 0.111811 memory: 21676 loss_kpt: 0.000562 acc_pose: 0.844320 loss: 0.000562 2022/09/09 06:57:01 - mmengine - INFO - Epoch(train) [117][100/293] lr: 5.000000e-04 eta: 5:03:29 time: 0.775335 data_time: 0.093456 memory: 21676 loss_kpt: 0.000563 acc_pose: 0.860607 loss: 0.000563 2022/09/09 06:57:40 - mmengine - INFO - Epoch(train) [117][150/293] lr: 5.000000e-04 eta: 5:03:00 time: 0.768329 data_time: 0.099672 memory: 21676 loss_kpt: 0.000587 acc_pose: 0.864933 loss: 0.000587 2022/09/09 06:58:17 - mmengine - INFO - Epoch(train) [117][200/293] lr: 5.000000e-04 eta: 5:02:31 time: 0.748767 data_time: 0.093231 memory: 21676 loss_kpt: 0.000587 acc_pose: 0.809701 loss: 0.000587 2022/09/09 06:58:55 - mmengine - INFO - Epoch(train) [117][250/293] lr: 5.000000e-04 eta: 5:02:01 time: 0.759694 data_time: 0.102571 memory: 21676 loss_kpt: 0.000570 acc_pose: 0.838935 loss: 0.000570 2022/09/09 06:59:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 06:59:27 - mmengine - INFO - Saving checkpoint at 117 epochs 2022/09/09 07:00:11 - mmengine - INFO - Epoch(train) [118][50/293] lr: 5.000000e-04 eta: 5:00:42 time: 0.794822 data_time: 0.107278 memory: 21676 loss_kpt: 0.000574 acc_pose: 0.875049 loss: 0.000574 2022/09/09 07:00:49 - mmengine - INFO - Epoch(train) [118][100/293] lr: 5.000000e-04 eta: 5:00:13 time: 0.759292 data_time: 0.096931 memory: 21676 loss_kpt: 0.000564 acc_pose: 0.822806 loss: 0.000564 2022/09/09 07:01:27 - mmengine - INFO - Epoch(train) [118][150/293] lr: 5.000000e-04 eta: 4:59:43 time: 0.759926 data_time: 0.100317 memory: 21676 loss_kpt: 0.000579 acc_pose: 0.817987 loss: 0.000579 2022/09/09 07:02:04 - mmengine - INFO - Epoch(train) [118][200/293] lr: 5.000000e-04 eta: 4:59:14 time: 0.754952 data_time: 0.095776 memory: 21676 loss_kpt: 0.000570 acc_pose: 0.786579 loss: 0.000570 2022/09/09 07:02:42 - mmengine - INFO - Epoch(train) [118][250/293] lr: 5.000000e-04 eta: 4:58:44 time: 0.758584 data_time: 0.104821 memory: 21676 loss_kpt: 0.000559 acc_pose: 0.857669 loss: 0.000559 2022/09/09 07:03:14 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 07:03:15 - mmengine - INFO - Saving checkpoint at 118 epochs 2022/09/09 07:03:58 - mmengine - INFO - Epoch(train) [119][50/293] lr: 5.000000e-04 eta: 4:57:25 time: 0.777053 data_time: 0.106651 memory: 21676 loss_kpt: 0.000589 acc_pose: 0.841286 loss: 0.000589 2022/09/09 07:04:36 - mmengine - INFO - Epoch(train) [119][100/293] lr: 5.000000e-04 eta: 4:56:56 time: 0.766809 data_time: 0.106926 memory: 21676 loss_kpt: 0.000569 acc_pose: 0.877220 loss: 0.000569 2022/09/09 07:05:15 - mmengine - INFO - Epoch(train) [119][150/293] lr: 5.000000e-04 eta: 4:56:27 time: 0.773133 data_time: 0.096271 memory: 21676 loss_kpt: 0.000570 acc_pose: 0.837283 loss: 0.000570 2022/09/09 07:05:53 - mmengine - INFO - Epoch(train) [119][200/293] lr: 5.000000e-04 eta: 4:55:57 time: 0.764756 data_time: 0.098214 memory: 21676 loss_kpt: 0.000583 acc_pose: 0.835042 loss: 0.000583 2022/09/09 07:06:32 - mmengine - INFO - Epoch(train) [119][250/293] lr: 5.000000e-04 eta: 4:55:28 time: 0.765316 data_time: 0.096970 memory: 21676 loss_kpt: 0.000574 acc_pose: 0.845363 loss: 0.000574 2022/09/09 07:07:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 07:07:04 - mmengine - INFO - Saving checkpoint at 119 epochs 2022/09/09 07:07:47 - mmengine - INFO - Epoch(train) [120][50/293] lr: 5.000000e-04 eta: 4:54:10 time: 0.797797 data_time: 0.109630 memory: 21676 loss_kpt: 0.000560 acc_pose: 0.839027 loss: 0.000560 2022/09/09 07:08:26 - mmengine - INFO - Epoch(train) [120][100/293] lr: 5.000000e-04 eta: 4:53:41 time: 0.774723 data_time: 0.097892 memory: 21676 loss_kpt: 0.000574 acc_pose: 0.890778 loss: 0.000574 2022/09/09 07:08:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 07:09:03 - mmengine - INFO - Epoch(train) [120][150/293] lr: 5.000000e-04 eta: 4:53:11 time: 0.750663 data_time: 0.093143 memory: 21676 loss_kpt: 0.000564 acc_pose: 0.851281 loss: 0.000564 2022/09/09 07:09:41 - mmengine - INFO - Epoch(train) [120][200/293] lr: 5.000000e-04 eta: 4:52:41 time: 0.749231 data_time: 0.096620 memory: 21676 loss_kpt: 0.000564 acc_pose: 0.867812 loss: 0.000564 2022/09/09 07:10:19 - mmengine - INFO - Epoch(train) [120][250/293] lr: 5.000000e-04 eta: 4:52:11 time: 0.758399 data_time: 0.096242 memory: 21676 loss_kpt: 0.000567 acc_pose: 0.879147 loss: 0.000567 2022/09/09 07:10:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 07:10:51 - mmengine - INFO - Saving checkpoint at 120 epochs 2022/09/09 07:11:04 - mmengine - INFO - Epoch(val) [120][50/407] eta: 0:00:57 time: 0.161910 data_time: 0.018302 memory: 21676 2022/09/09 07:11:12 - mmengine - INFO - Epoch(val) [120][100/407] eta: 0:00:47 time: 0.153448 data_time: 0.008653 memory: 1375 2022/09/09 07:11:20 - mmengine - INFO - Epoch(val) [120][150/407] eta: 0:00:39 time: 0.153405 data_time: 0.009045 memory: 1375 2022/09/09 07:11:27 - mmengine - INFO - Epoch(val) [120][200/407] eta: 0:00:31 time: 0.152688 data_time: 0.009268 memory: 1375 2022/09/09 07:11:35 - mmengine - INFO - Epoch(val) [120][250/407] eta: 0:00:24 time: 0.157763 data_time: 0.013042 memory: 1375 2022/09/09 07:11:43 - mmengine - INFO - Epoch(val) [120][300/407] eta: 0:00:16 time: 0.151458 data_time: 0.008670 memory: 1375 2022/09/09 07:11:50 - mmengine - INFO - Epoch(val) [120][350/407] eta: 0:00:08 time: 0.154182 data_time: 0.012270 memory: 1375 2022/09/09 07:11:58 - mmengine - INFO - Epoch(val) [120][400/407] eta: 0:00:01 time: 0.149080 data_time: 0.007966 memory: 1375 2022/09/09 07:12:34 - mmengine - INFO - Evaluating CocoMetric... 2022/09/09 07:12:48 - mmengine - INFO - Epoch(val) [120][407/407] coco/AP: 0.747310 coco/AP .5: 0.899019 coco/AP .75: 0.817009 coco/AP (M): 0.708501 coco/AP (L): 0.816991 coco/AR: 0.799229 coco/AR .5: 0.938130 coco/AR .75: 0.860516 coco/AR (M): 0.755258 coco/AR (L): 0.862951 2022/09/09 07:13:26 - mmengine - INFO - Epoch(train) [121][50/293] lr: 5.000000e-04 eta: 4:50:52 time: 0.769923 data_time: 0.103336 memory: 21676 loss_kpt: 0.000564 acc_pose: 0.831957 loss: 0.000564 2022/09/09 07:14:04 - mmengine - INFO - Epoch(train) [121][100/293] lr: 5.000000e-04 eta: 4:50:23 time: 0.760172 data_time: 0.100304 memory: 21676 loss_kpt: 0.000560 acc_pose: 0.822316 loss: 0.000560 2022/09/09 07:14:42 - mmengine - INFO - Epoch(train) [121][150/293] lr: 5.000000e-04 eta: 4:49:53 time: 0.763886 data_time: 0.098267 memory: 21676 loss_kpt: 0.000576 acc_pose: 0.819717 loss: 0.000576 2022/09/09 07:15:20 - mmengine - INFO - Epoch(train) [121][200/293] lr: 5.000000e-04 eta: 4:49:23 time: 0.752434 data_time: 0.093021 memory: 21676 loss_kpt: 0.000589 acc_pose: 0.807656 loss: 0.000589 2022/09/09 07:15:58 - mmengine - INFO - Epoch(train) [121][250/293] lr: 5.000000e-04 eta: 4:48:54 time: 0.756093 data_time: 0.100723 memory: 21676 loss_kpt: 0.000572 acc_pose: 0.781711 loss: 0.000572 2022/09/09 07:16:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 07:16:30 - mmengine - INFO - Saving checkpoint at 121 epochs 2022/09/09 07:17:15 - mmengine - INFO - Epoch(train) [122][50/293] lr: 5.000000e-04 eta: 4:47:36 time: 0.794419 data_time: 0.116014 memory: 21676 loss_kpt: 0.000576 acc_pose: 0.838792 loss: 0.000576 2022/09/09 07:17:53 - mmengine - INFO - Epoch(train) [122][100/293] lr: 5.000000e-04 eta: 4:47:07 time: 0.772101 data_time: 0.099971 memory: 21676 loss_kpt: 0.000570 acc_pose: 0.874554 loss: 0.000570 2022/09/09 07:18:32 - mmengine - INFO - Epoch(train) [122][150/293] lr: 5.000000e-04 eta: 4:46:37 time: 0.770860 data_time: 0.102823 memory: 21676 loss_kpt: 0.000573 acc_pose: 0.850682 loss: 0.000573 2022/09/09 07:19:10 - mmengine - INFO - Epoch(train) [122][200/293] lr: 5.000000e-04 eta: 4:46:08 time: 0.771576 data_time: 0.099071 memory: 21676 loss_kpt: 0.000559 acc_pose: 0.837109 loss: 0.000559 2022/09/09 07:19:48 - mmengine - INFO - Epoch(train) [122][250/293] lr: 5.000000e-04 eta: 4:45:38 time: 0.751604 data_time: 0.096388 memory: 21676 loss_kpt: 0.000572 acc_pose: 0.812915 loss: 0.000572 2022/09/09 07:20:20 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 07:20:20 - mmengine - INFO - Saving checkpoint at 122 epochs 2022/09/09 07:21:03 - mmengine - INFO - Epoch(train) [123][50/293] lr: 5.000000e-04 eta: 4:44:20 time: 0.765879 data_time: 0.105011 memory: 21676 loss_kpt: 0.000559 acc_pose: 0.807506 loss: 0.000559 2022/09/09 07:21:41 - mmengine - INFO - Epoch(train) [123][100/293] lr: 5.000000e-04 eta: 4:43:50 time: 0.762726 data_time: 0.096596 memory: 21676 loss_kpt: 0.000578 acc_pose: 0.895424 loss: 0.000578 2022/09/09 07:22:19 - mmengine - INFO - Epoch(train) [123][150/293] lr: 5.000000e-04 eta: 4:43:20 time: 0.747942 data_time: 0.093992 memory: 21676 loss_kpt: 0.000567 acc_pose: 0.854935 loss: 0.000567 2022/09/09 07:22:57 - mmengine - INFO - Epoch(train) [123][200/293] lr: 5.000000e-04 eta: 4:42:50 time: 0.759898 data_time: 0.097605 memory: 21676 loss_kpt: 0.000567 acc_pose: 0.860674 loss: 0.000567 2022/09/09 07:23:35 - mmengine - INFO - Epoch(train) [123][250/293] lr: 5.000000e-04 eta: 4:42:20 time: 0.761445 data_time: 0.093360 memory: 21676 loss_kpt: 0.000582 acc_pose: 0.854750 loss: 0.000582 2022/09/09 07:23:38 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 07:24:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 07:24:07 - mmengine - INFO - Saving checkpoint at 123 epochs 2022/09/09 07:24:51 - mmengine - INFO - Epoch(train) [124][50/293] lr: 5.000000e-04 eta: 4:41:03 time: 0.791599 data_time: 0.105413 memory: 21676 loss_kpt: 0.000578 acc_pose: 0.833222 loss: 0.000578 2022/09/09 07:25:30 - mmengine - INFO - Epoch(train) [124][100/293] lr: 5.000000e-04 eta: 4:40:34 time: 0.776063 data_time: 0.098580 memory: 21676 loss_kpt: 0.000570 acc_pose: 0.867336 loss: 0.000570 2022/09/09 07:26:09 - mmengine - INFO - Epoch(train) [124][150/293] lr: 5.000000e-04 eta: 4:40:05 time: 0.769188 data_time: 0.100787 memory: 21676 loss_kpt: 0.000576 acc_pose: 0.844764 loss: 0.000576 2022/09/09 07:26:47 - mmengine - INFO - Epoch(train) [124][200/293] lr: 5.000000e-04 eta: 4:39:35 time: 0.767933 data_time: 0.096831 memory: 21676 loss_kpt: 0.000566 acc_pose: 0.847201 loss: 0.000566 2022/09/09 07:27:24 - mmengine - INFO - Epoch(train) [124][250/293] lr: 5.000000e-04 eta: 4:39:05 time: 0.747863 data_time: 0.097317 memory: 21676 loss_kpt: 0.000577 acc_pose: 0.808640 loss: 0.000577 2022/09/09 07:27:57 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 07:27:57 - mmengine - INFO - Saving checkpoint at 124 epochs 2022/09/09 07:28:41 - mmengine - INFO - Epoch(train) [125][50/293] lr: 5.000000e-04 eta: 4:37:48 time: 0.793377 data_time: 0.107300 memory: 21676 loss_kpt: 0.000560 acc_pose: 0.831847 loss: 0.000560 2022/09/09 07:29:20 - mmengine - INFO - Epoch(train) [125][100/293] lr: 5.000000e-04 eta: 4:37:19 time: 0.778578 data_time: 0.098252 memory: 21676 loss_kpt: 0.000567 acc_pose: 0.813401 loss: 0.000567 2022/09/09 07:29:59 - mmengine - INFO - Epoch(train) [125][150/293] lr: 5.000000e-04 eta: 4:36:50 time: 0.781853 data_time: 0.102099 memory: 21676 loss_kpt: 0.000583 acc_pose: 0.838373 loss: 0.000583 2022/09/09 07:30:38 - mmengine - INFO - Epoch(train) [125][200/293] lr: 5.000000e-04 eta: 4:36:20 time: 0.774616 data_time: 0.098081 memory: 21676 loss_kpt: 0.000580 acc_pose: 0.868772 loss: 0.000580 2022/09/09 07:31:16 - mmengine - INFO - Epoch(train) [125][250/293] lr: 5.000000e-04 eta: 4:35:51 time: 0.769287 data_time: 0.101377 memory: 21676 loss_kpt: 0.000568 acc_pose: 0.810882 loss: 0.000568 2022/09/09 07:31:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 07:31:49 - mmengine - INFO - Saving checkpoint at 125 epochs 2022/09/09 07:32:32 - mmengine - INFO - Epoch(train) [126][50/293] lr: 5.000000e-04 eta: 4:34:33 time: 0.772562 data_time: 0.109381 memory: 21676 loss_kpt: 0.000560 acc_pose: 0.843187 loss: 0.000560 2022/09/09 07:33:10 - mmengine - INFO - Epoch(train) [126][100/293] lr: 5.000000e-04 eta: 4:34:03 time: 0.751442 data_time: 0.100612 memory: 21676 loss_kpt: 0.000558 acc_pose: 0.856152 loss: 0.000558 2022/09/09 07:33:47 - mmengine - INFO - Epoch(train) [126][150/293] lr: 5.000000e-04 eta: 4:33:33 time: 0.751685 data_time: 0.096981 memory: 21676 loss_kpt: 0.000564 acc_pose: 0.846502 loss: 0.000564 2022/09/09 07:34:27 - mmengine - INFO - Epoch(train) [126][200/293] lr: 5.000000e-04 eta: 4:33:04 time: 0.780672 data_time: 0.096438 memory: 21676 loss_kpt: 0.000575 acc_pose: 0.815959 loss: 0.000575 2022/09/09 07:35:04 - mmengine - INFO - Epoch(train) [126][250/293] lr: 5.000000e-04 eta: 4:32:34 time: 0.750886 data_time: 0.096958 memory: 21676 loss_kpt: 0.000570 acc_pose: 0.867987 loss: 0.000570 2022/09/09 07:35:36 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 07:35:36 - mmengine - INFO - Saving checkpoint at 126 epochs 2022/09/09 07:36:21 - mmengine - INFO - Epoch(train) [127][50/293] lr: 5.000000e-04 eta: 4:31:18 time: 0.798191 data_time: 0.108364 memory: 21676 loss_kpt: 0.000566 acc_pose: 0.857483 loss: 0.000566 2022/09/09 07:36:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 07:37:00 - mmengine - INFO - Epoch(train) [127][100/293] lr: 5.000000e-04 eta: 4:30:48 time: 0.778174 data_time: 0.095779 memory: 21676 loss_kpt: 0.000565 acc_pose: 0.859270 loss: 0.000565 2022/09/09 07:37:38 - mmengine - INFO - Epoch(train) [127][150/293] lr: 5.000000e-04 eta: 4:30:18 time: 0.761188 data_time: 0.093502 memory: 21676 loss_kpt: 0.000562 acc_pose: 0.834676 loss: 0.000562 2022/09/09 07:38:16 - mmengine - INFO - Epoch(train) [127][200/293] lr: 5.000000e-04 eta: 4:29:48 time: 0.756275 data_time: 0.099081 memory: 21676 loss_kpt: 0.000570 acc_pose: 0.872450 loss: 0.000570 2022/09/09 07:38:53 - mmengine - INFO - Epoch(train) [127][250/293] lr: 5.000000e-04 eta: 4:29:18 time: 0.757394 data_time: 0.098017 memory: 21676 loss_kpt: 0.000571 acc_pose: 0.840696 loss: 0.000571 2022/09/09 07:39:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 07:39:26 - mmengine - INFO - Saving checkpoint at 127 epochs 2022/09/09 07:40:09 - mmengine - INFO - Epoch(train) [128][50/293] lr: 5.000000e-04 eta: 4:28:02 time: 0.781168 data_time: 0.111817 memory: 21676 loss_kpt: 0.000574 acc_pose: 0.824890 loss: 0.000574 2022/09/09 07:40:48 - mmengine - INFO - Epoch(train) [128][100/293] lr: 5.000000e-04 eta: 4:27:32 time: 0.766227 data_time: 0.096119 memory: 21676 loss_kpt: 0.000563 acc_pose: 0.795130 loss: 0.000563 2022/09/09 07:41:26 - mmengine - INFO - Epoch(train) [128][150/293] lr: 5.000000e-04 eta: 4:27:02 time: 0.770836 data_time: 0.097379 memory: 21676 loss_kpt: 0.000583 acc_pose: 0.852426 loss: 0.000583 2022/09/09 07:42:04 - mmengine - INFO - Epoch(train) [128][200/293] lr: 5.000000e-04 eta: 4:26:32 time: 0.758819 data_time: 0.097822 memory: 21676 loss_kpt: 0.000560 acc_pose: 0.858561 loss: 0.000560 2022/09/09 07:42:42 - mmengine - INFO - Epoch(train) [128][250/293] lr: 5.000000e-04 eta: 4:26:02 time: 0.765521 data_time: 0.098763 memory: 21676 loss_kpt: 0.000568 acc_pose: 0.825865 loss: 0.000568 2022/09/09 07:43:15 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 07:43:15 - mmengine - INFO - Saving checkpoint at 128 epochs 2022/09/09 07:43:58 - mmengine - INFO - Epoch(train) [129][50/293] lr: 5.000000e-04 eta: 4:24:46 time: 0.782166 data_time: 0.111495 memory: 21676 loss_kpt: 0.000560 acc_pose: 0.825480 loss: 0.000560 2022/09/09 07:44:36 - mmengine - INFO - Epoch(train) [129][100/293] lr: 5.000000e-04 eta: 4:24:16 time: 0.764207 data_time: 0.097006 memory: 21676 loss_kpt: 0.000569 acc_pose: 0.833607 loss: 0.000569 2022/09/09 07:45:14 - mmengine - INFO - Epoch(train) [129][150/293] lr: 5.000000e-04 eta: 4:23:47 time: 0.764430 data_time: 0.093564 memory: 21676 loss_kpt: 0.000565 acc_pose: 0.854082 loss: 0.000565 2022/09/09 07:45:52 - mmengine - INFO - Epoch(train) [129][200/293] lr: 5.000000e-04 eta: 4:23:16 time: 0.754623 data_time: 0.097340 memory: 21676 loss_kpt: 0.000560 acc_pose: 0.861212 loss: 0.000560 2022/09/09 07:46:30 - mmengine - INFO - Epoch(train) [129][250/293] lr: 5.000000e-04 eta: 4:22:46 time: 0.759871 data_time: 0.098245 memory: 21676 loss_kpt: 0.000567 acc_pose: 0.854965 loss: 0.000567 2022/09/09 07:47:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 07:47:02 - mmengine - INFO - Saving checkpoint at 129 epochs 2022/09/09 07:47:46 - mmengine - INFO - Epoch(train) [130][50/293] lr: 5.000000e-04 eta: 4:21:31 time: 0.790679 data_time: 0.109567 memory: 21676 loss_kpt: 0.000569 acc_pose: 0.817495 loss: 0.000569 2022/09/09 07:48:24 - mmengine - INFO - Epoch(train) [130][100/293] lr: 5.000000e-04 eta: 4:21:01 time: 0.761367 data_time: 0.097808 memory: 21676 loss_kpt: 0.000572 acc_pose: 0.833287 loss: 0.000572 2022/09/09 07:49:02 - mmengine - INFO - Epoch(train) [130][150/293] lr: 5.000000e-04 eta: 4:20:30 time: 0.751315 data_time: 0.099532 memory: 21676 loss_kpt: 0.000558 acc_pose: 0.888054 loss: 0.000558 2022/09/09 07:49:40 - mmengine - INFO - Epoch(train) [130][200/293] lr: 5.000000e-04 eta: 4:20:00 time: 0.765604 data_time: 0.097184 memory: 21676 loss_kpt: 0.000572 acc_pose: 0.870351 loss: 0.000572 2022/09/09 07:49:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 07:50:18 - mmengine - INFO - Epoch(train) [130][250/293] lr: 5.000000e-04 eta: 4:19:30 time: 0.762126 data_time: 0.096114 memory: 21676 loss_kpt: 0.000557 acc_pose: 0.850401 loss: 0.000557 2022/09/09 07:50:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 07:50:51 - mmengine - INFO - Saving checkpoint at 130 epochs 2022/09/09 07:51:04 - mmengine - INFO - Epoch(val) [130][50/407] eta: 0:00:57 time: 0.159767 data_time: 0.014905 memory: 21676 2022/09/09 07:51:12 - mmengine - INFO - Epoch(val) [130][100/407] eta: 0:00:47 time: 0.153166 data_time: 0.009217 memory: 1375 2022/09/09 07:51:19 - mmengine - INFO - Epoch(val) [130][150/407] eta: 0:00:39 time: 0.154510 data_time: 0.009349 memory: 1375 2022/09/09 07:51:27 - mmengine - INFO - Epoch(val) [130][200/407] eta: 0:00:32 time: 0.155763 data_time: 0.013721 memory: 1375 2022/09/09 07:51:35 - mmengine - INFO - Epoch(val) [130][250/407] eta: 0:00:23 time: 0.152798 data_time: 0.009108 memory: 1375 2022/09/09 07:51:43 - mmengine - INFO - Epoch(val) [130][300/407] eta: 0:00:16 time: 0.152879 data_time: 0.009465 memory: 1375 2022/09/09 07:51:50 - mmengine - INFO - Epoch(val) [130][350/407] eta: 0:00:08 time: 0.151158 data_time: 0.008381 memory: 1375 2022/09/09 07:51:58 - mmengine - INFO - Epoch(val) [130][400/407] eta: 0:00:01 time: 0.148544 data_time: 0.007870 memory: 1375 2022/09/09 07:52:34 - mmengine - INFO - Evaluating CocoMetric... 2022/09/09 07:52:48 - mmengine - INFO - Epoch(val) [130][407/407] coco/AP: 0.750426 coco/AP .5: 0.899739 coco/AP .75: 0.818223 coco/AP (M): 0.710535 coco/AP (L): 0.821755 coco/AR: 0.800992 coco/AR .5: 0.937343 coco/AR .75: 0.861933 coco/AR (M): 0.756433 coco/AR (L): 0.865775 2022/09/09 07:52:48 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220908/hrnet_w32_384/best_coco/AP_epoch_110.pth is removed 2022/09/09 07:52:51 - mmengine - INFO - The best checkpoint with 0.7504 coco/AP at 130 epoch is saved to best_coco/AP_epoch_130.pth. 2022/09/09 07:53:31 - mmengine - INFO - Epoch(train) [131][50/293] lr: 5.000000e-04 eta: 4:18:15 time: 0.796821 data_time: 0.110784 memory: 21676 loss_kpt: 0.000564 acc_pose: 0.882743 loss: 0.000564 2022/09/09 07:54:09 - mmengine - INFO - Epoch(train) [131][100/293] lr: 5.000000e-04 eta: 4:17:45 time: 0.762496 data_time: 0.098049 memory: 21676 loss_kpt: 0.000568 acc_pose: 0.788728 loss: 0.000568 2022/09/09 07:54:47 - mmengine - INFO - Epoch(train) [131][150/293] lr: 5.000000e-04 eta: 4:17:15 time: 0.760560 data_time: 0.098506 memory: 21676 loss_kpt: 0.000570 acc_pose: 0.908437 loss: 0.000570 2022/09/09 07:55:25 - mmengine - INFO - Epoch(train) [131][200/293] lr: 5.000000e-04 eta: 4:16:45 time: 0.751659 data_time: 0.092715 memory: 21676 loss_kpt: 0.000570 acc_pose: 0.827983 loss: 0.000570 2022/09/09 07:56:02 - mmengine - INFO - Epoch(train) [131][250/293] lr: 5.000000e-04 eta: 4:16:14 time: 0.746815 data_time: 0.095994 memory: 21676 loss_kpt: 0.000567 acc_pose: 0.834292 loss: 0.000567 2022/09/09 07:56:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 07:56:35 - mmengine - INFO - Saving checkpoint at 131 epochs 2022/09/09 07:57:18 - mmengine - INFO - Epoch(train) [132][50/293] lr: 5.000000e-04 eta: 4:14:59 time: 0.787803 data_time: 0.106229 memory: 21676 loss_kpt: 0.000562 acc_pose: 0.879717 loss: 0.000562 2022/09/09 07:57:56 - mmengine - INFO - Epoch(train) [132][100/293] lr: 5.000000e-04 eta: 4:14:29 time: 0.756894 data_time: 0.100620 memory: 21676 loss_kpt: 0.000560 acc_pose: 0.839199 loss: 0.000560 2022/09/09 07:58:34 - mmengine - INFO - Epoch(train) [132][150/293] lr: 5.000000e-04 eta: 4:13:58 time: 0.759010 data_time: 0.098063 memory: 21676 loss_kpt: 0.000573 acc_pose: 0.821557 loss: 0.000573 2022/09/09 07:59:11 - mmengine - INFO - Epoch(train) [132][200/293] lr: 5.000000e-04 eta: 4:13:28 time: 0.753506 data_time: 0.096064 memory: 21676 loss_kpt: 0.000573 acc_pose: 0.858823 loss: 0.000573 2022/09/09 07:59:49 - mmengine - INFO - Epoch(train) [132][250/293] lr: 5.000000e-04 eta: 4:12:58 time: 0.758499 data_time: 0.098705 memory: 21676 loss_kpt: 0.000557 acc_pose: 0.871990 loss: 0.000557 2022/09/09 08:00:21 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 08:00:21 - mmengine - INFO - Saving checkpoint at 132 epochs 2022/09/09 08:01:05 - mmengine - INFO - Epoch(train) [133][50/293] lr: 5.000000e-04 eta: 4:11:43 time: 0.790556 data_time: 0.110753 memory: 21676 loss_kpt: 0.000568 acc_pose: 0.880284 loss: 0.000568 2022/09/09 08:01:44 - mmengine - INFO - Epoch(train) [133][100/293] lr: 5.000000e-04 eta: 4:11:13 time: 0.784404 data_time: 0.098878 memory: 21676 loss_kpt: 0.000562 acc_pose: 0.862875 loss: 0.000562 2022/09/09 08:02:23 - mmengine - INFO - Epoch(train) [133][150/293] lr: 5.000000e-04 eta: 4:10:43 time: 0.766140 data_time: 0.097979 memory: 21676 loss_kpt: 0.000566 acc_pose: 0.835639 loss: 0.000566 2022/09/09 08:03:01 - mmengine - INFO - Epoch(train) [133][200/293] lr: 5.000000e-04 eta: 4:10:13 time: 0.773037 data_time: 0.101028 memory: 21676 loss_kpt: 0.000556 acc_pose: 0.816792 loss: 0.000556 2022/09/09 08:03:40 - mmengine - INFO - Epoch(train) [133][250/293] lr: 5.000000e-04 eta: 4:09:44 time: 0.780310 data_time: 0.098301 memory: 21676 loss_kpt: 0.000561 acc_pose: 0.776028 loss: 0.000561 2022/09/09 08:04:12 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 08:04:12 - mmengine - INFO - Saving checkpoint at 133 epochs 2022/09/09 08:04:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 08:04:57 - mmengine - INFO - Epoch(train) [134][50/293] lr: 5.000000e-04 eta: 4:08:29 time: 0.786838 data_time: 0.112913 memory: 21676 loss_kpt: 0.000561 acc_pose: 0.858061 loss: 0.000561 2022/09/09 08:05:35 - mmengine - INFO - Epoch(train) [134][100/293] lr: 5.000000e-04 eta: 4:07:59 time: 0.777362 data_time: 0.099459 memory: 21676 loss_kpt: 0.000566 acc_pose: 0.832461 loss: 0.000566 2022/09/09 08:06:14 - mmengine - INFO - Epoch(train) [134][150/293] lr: 5.000000e-04 eta: 4:07:29 time: 0.772478 data_time: 0.100639 memory: 21676 loss_kpt: 0.000573 acc_pose: 0.865444 loss: 0.000573 2022/09/09 08:06:53 - mmengine - INFO - Epoch(train) [134][200/293] lr: 5.000000e-04 eta: 4:07:00 time: 0.783145 data_time: 0.101310 memory: 21676 loss_kpt: 0.000569 acc_pose: 0.825757 loss: 0.000569 2022/09/09 08:07:32 - mmengine - INFO - Epoch(train) [134][250/293] lr: 5.000000e-04 eta: 4:06:30 time: 0.782359 data_time: 0.101730 memory: 21676 loss_kpt: 0.000561 acc_pose: 0.849651 loss: 0.000561 2022/09/09 08:08:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 08:08:06 - mmengine - INFO - Saving checkpoint at 134 epochs 2022/09/09 08:08:49 - mmengine - INFO - Epoch(train) [135][50/293] lr: 5.000000e-04 eta: 4:05:15 time: 0.778131 data_time: 0.108398 memory: 21676 loss_kpt: 0.000553 acc_pose: 0.809520 loss: 0.000553 2022/09/09 08:09:28 - mmengine - INFO - Epoch(train) [135][100/293] lr: 5.000000e-04 eta: 4:04:46 time: 0.779062 data_time: 0.094738 memory: 21676 loss_kpt: 0.000557 acc_pose: 0.805552 loss: 0.000557 2022/09/09 08:10:06 - mmengine - INFO - Epoch(train) [135][150/293] lr: 5.000000e-04 eta: 4:04:15 time: 0.763689 data_time: 0.099198 memory: 21676 loss_kpt: 0.000559 acc_pose: 0.865643 loss: 0.000559 2022/09/09 08:10:44 - mmengine - INFO - Epoch(train) [135][200/293] lr: 5.000000e-04 eta: 4:03:45 time: 0.752262 data_time: 0.096205 memory: 21676 loss_kpt: 0.000569 acc_pose: 0.839593 loss: 0.000569 2022/09/09 08:11:22 - mmengine - INFO - Epoch(train) [135][250/293] lr: 5.000000e-04 eta: 4:03:14 time: 0.763502 data_time: 0.096519 memory: 21676 loss_kpt: 0.000564 acc_pose: 0.858004 loss: 0.000564 2022/09/09 08:11:54 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 08:11:54 - mmengine - INFO - Saving checkpoint at 135 epochs 2022/09/09 08:12:38 - mmengine - INFO - Epoch(train) [136][50/293] lr: 5.000000e-04 eta: 4:02:00 time: 0.788461 data_time: 0.110332 memory: 21676 loss_kpt: 0.000562 acc_pose: 0.856309 loss: 0.000562 2022/09/09 08:13:16 - mmengine - INFO - Epoch(train) [136][100/293] lr: 5.000000e-04 eta: 4:01:30 time: 0.763271 data_time: 0.100129 memory: 21676 loss_kpt: 0.000572 acc_pose: 0.861599 loss: 0.000572 2022/09/09 08:13:54 - mmengine - INFO - Epoch(train) [136][150/293] lr: 5.000000e-04 eta: 4:00:59 time: 0.752413 data_time: 0.097111 memory: 21676 loss_kpt: 0.000569 acc_pose: 0.860638 loss: 0.000569 2022/09/09 08:14:32 - mmengine - INFO - Epoch(train) [136][200/293] lr: 5.000000e-04 eta: 4:00:29 time: 0.766896 data_time: 0.099677 memory: 21676 loss_kpt: 0.000562 acc_pose: 0.871059 loss: 0.000562 2022/09/09 08:15:10 - mmengine - INFO - Epoch(train) [136][250/293] lr: 5.000000e-04 eta: 3:59:59 time: 0.754491 data_time: 0.095939 memory: 21676 loss_kpt: 0.000550 acc_pose: 0.852863 loss: 0.000550 2022/09/09 08:15:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 08:15:42 - mmengine - INFO - Saving checkpoint at 136 epochs 2022/09/09 08:16:25 - mmengine - INFO - Epoch(train) [137][50/293] lr: 5.000000e-04 eta: 3:58:44 time: 0.774327 data_time: 0.109137 memory: 21676 loss_kpt: 0.000554 acc_pose: 0.800240 loss: 0.000554 2022/09/09 08:17:02 - mmengine - INFO - Epoch(train) [137][100/293] lr: 5.000000e-04 eta: 3:58:14 time: 0.750480 data_time: 0.093046 memory: 21676 loss_kpt: 0.000569 acc_pose: 0.811288 loss: 0.000569 2022/09/09 08:17:40 - mmengine - INFO - Epoch(train) [137][150/293] lr: 5.000000e-04 eta: 3:57:43 time: 0.756369 data_time: 0.092326 memory: 21676 loss_kpt: 0.000580 acc_pose: 0.859901 loss: 0.000580 2022/09/09 08:17:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 08:18:18 - mmengine - INFO - Epoch(train) [137][200/293] lr: 5.000000e-04 eta: 3:57:12 time: 0.750957 data_time: 0.096806 memory: 21676 loss_kpt: 0.000554 acc_pose: 0.819272 loss: 0.000554 2022/09/09 08:18:55 - mmengine - INFO - Epoch(train) [137][250/293] lr: 5.000000e-04 eta: 3:56:42 time: 0.750698 data_time: 0.092836 memory: 21676 loss_kpt: 0.000571 acc_pose: 0.823576 loss: 0.000571 2022/09/09 08:19:28 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 08:19:28 - mmengine - INFO - Saving checkpoint at 137 epochs 2022/09/09 08:20:11 - mmengine - INFO - Epoch(train) [138][50/293] lr: 5.000000e-04 eta: 3:55:28 time: 0.784796 data_time: 0.119963 memory: 21676 loss_kpt: 0.000583 acc_pose: 0.805622 loss: 0.000583 2022/09/09 08:20:50 - mmengine - INFO - Epoch(train) [138][100/293] lr: 5.000000e-04 eta: 3:54:58 time: 0.766363 data_time: 0.098246 memory: 21676 loss_kpt: 0.000553 acc_pose: 0.834662 loss: 0.000553 2022/09/09 08:21:28 - mmengine - INFO - Epoch(train) [138][150/293] lr: 5.000000e-04 eta: 3:54:28 time: 0.771707 data_time: 0.096592 memory: 21676 loss_kpt: 0.000569 acc_pose: 0.811800 loss: 0.000569 2022/09/09 08:22:07 - mmengine - INFO - Epoch(train) [138][200/293] lr: 5.000000e-04 eta: 3:53:57 time: 0.766699 data_time: 0.093892 memory: 21676 loss_kpt: 0.000564 acc_pose: 0.837667 loss: 0.000564 2022/09/09 08:22:44 - mmengine - INFO - Epoch(train) [138][250/293] lr: 5.000000e-04 eta: 3:53:26 time: 0.753961 data_time: 0.097645 memory: 21676 loss_kpt: 0.000564 acc_pose: 0.873347 loss: 0.000564 2022/09/09 08:23:16 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 08:23:16 - mmengine - INFO - Saving checkpoint at 138 epochs 2022/09/09 08:24:00 - mmengine - INFO - Epoch(train) [139][50/293] lr: 5.000000e-04 eta: 3:52:13 time: 0.785223 data_time: 0.112644 memory: 21676 loss_kpt: 0.000563 acc_pose: 0.830970 loss: 0.000563 2022/09/09 08:24:39 - mmengine - INFO - Epoch(train) [139][100/293] lr: 5.000000e-04 eta: 3:51:43 time: 0.775098 data_time: 0.102956 memory: 21676 loss_kpt: 0.000566 acc_pose: 0.833834 loss: 0.000566 2022/09/09 08:25:18 - mmengine - INFO - Epoch(train) [139][150/293] lr: 5.000000e-04 eta: 3:51:13 time: 0.785972 data_time: 0.106992 memory: 21676 loss_kpt: 0.000557 acc_pose: 0.849024 loss: 0.000557 2022/09/09 08:25:56 - mmengine - INFO - Epoch(train) [139][200/293] lr: 5.000000e-04 eta: 3:50:42 time: 0.747656 data_time: 0.096525 memory: 21676 loss_kpt: 0.000546 acc_pose: 0.864307 loss: 0.000546 2022/09/09 08:26:34 - mmengine - INFO - Epoch(train) [139][250/293] lr: 5.000000e-04 eta: 3:50:12 time: 0.758661 data_time: 0.093226 memory: 21676 loss_kpt: 0.000570 acc_pose: 0.865348 loss: 0.000570 2022/09/09 08:27:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 08:27:06 - mmengine - INFO - Saving checkpoint at 139 epochs 2022/09/09 08:27:49 - mmengine - INFO - Epoch(train) [140][50/293] lr: 5.000000e-04 eta: 3:48:58 time: 0.763465 data_time: 0.107101 memory: 21676 loss_kpt: 0.000559 acc_pose: 0.867622 loss: 0.000559 2022/09/09 08:28:27 - mmengine - INFO - Epoch(train) [140][100/293] lr: 5.000000e-04 eta: 3:48:27 time: 0.758335 data_time: 0.097809 memory: 21676 loss_kpt: 0.000560 acc_pose: 0.838925 loss: 0.000560 2022/09/09 08:29:05 - mmengine - INFO - Epoch(train) [140][150/293] lr: 5.000000e-04 eta: 3:47:57 time: 0.762907 data_time: 0.104095 memory: 21676 loss_kpt: 0.000553 acc_pose: 0.856476 loss: 0.000553 2022/09/09 08:29:42 - mmengine - INFO - Epoch(train) [140][200/293] lr: 5.000000e-04 eta: 3:47:26 time: 0.748578 data_time: 0.097146 memory: 21676 loss_kpt: 0.000566 acc_pose: 0.887305 loss: 0.000566 2022/09/09 08:30:21 - mmengine - INFO - Epoch(train) [140][250/293] lr: 5.000000e-04 eta: 3:46:55 time: 0.766802 data_time: 0.094656 memory: 21676 loss_kpt: 0.000557 acc_pose: 0.877015 loss: 0.000557 2022/09/09 08:30:39 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 08:30:53 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 08:30:53 - mmengine - INFO - Saving checkpoint at 140 epochs 2022/09/09 08:31:06 - mmengine - INFO - Epoch(val) [140][50/407] eta: 0:00:56 time: 0.158135 data_time: 0.014547 memory: 21676 2022/09/09 08:31:14 - mmengine - INFO - Epoch(val) [140][100/407] eta: 0:00:48 time: 0.156495 data_time: 0.008685 memory: 1375 2022/09/09 08:31:21 - mmengine - INFO - Epoch(val) [140][150/407] eta: 0:00:39 time: 0.152544 data_time: 0.009416 memory: 1375 2022/09/09 08:31:29 - mmengine - INFO - Epoch(val) [140][200/407] eta: 0:00:31 time: 0.154114 data_time: 0.009216 memory: 1375 2022/09/09 08:31:37 - mmengine - INFO - Epoch(val) [140][250/407] eta: 0:00:23 time: 0.151848 data_time: 0.008914 memory: 1375 2022/09/09 08:31:44 - mmengine - INFO - Epoch(val) [140][300/407] eta: 0:00:16 time: 0.151688 data_time: 0.008807 memory: 1375 2022/09/09 08:31:52 - mmengine - INFO - Epoch(val) [140][350/407] eta: 0:00:08 time: 0.153347 data_time: 0.008838 memory: 1375 2022/09/09 08:31:59 - mmengine - INFO - Epoch(val) [140][400/407] eta: 0:00:01 time: 0.148830 data_time: 0.008269 memory: 1375 2022/09/09 08:32:36 - mmengine - INFO - Evaluating CocoMetric... 2022/09/09 08:32:49 - mmengine - INFO - Epoch(val) [140][407/407] coco/AP: 0.748323 coco/AP .5: 0.901802 coco/AP .75: 0.815766 coco/AP (M): 0.709058 coco/AP (L): 0.819999 coco/AR: 0.800441 coco/AR .5: 0.940019 coco/AR .75: 0.860831 coco/AR (M): 0.755367 coco/AR (L): 0.865440 2022/09/09 08:33:29 - mmengine - INFO - Epoch(train) [141][50/293] lr: 5.000000e-04 eta: 3:45:43 time: 0.790475 data_time: 0.105286 memory: 21676 loss_kpt: 0.000565 acc_pose: 0.847148 loss: 0.000565 2022/09/09 08:34:08 - mmengine - INFO - Epoch(train) [141][100/293] lr: 5.000000e-04 eta: 3:45:13 time: 0.783053 data_time: 0.093740 memory: 21676 loss_kpt: 0.000566 acc_pose: 0.860204 loss: 0.000566 2022/09/09 08:34:47 - mmengine - INFO - Epoch(train) [141][150/293] lr: 5.000000e-04 eta: 3:44:42 time: 0.767285 data_time: 0.102593 memory: 21676 loss_kpt: 0.000555 acc_pose: 0.845252 loss: 0.000555 2022/09/09 08:35:26 - mmengine - INFO - Epoch(train) [141][200/293] lr: 5.000000e-04 eta: 3:44:12 time: 0.788667 data_time: 0.100760 memory: 21676 loss_kpt: 0.000574 acc_pose: 0.865582 loss: 0.000574 2022/09/09 08:36:05 - mmengine - INFO - Epoch(train) [141][250/293] lr: 5.000000e-04 eta: 3:43:42 time: 0.770928 data_time: 0.097562 memory: 21676 loss_kpt: 0.000566 acc_pose: 0.839057 loss: 0.000566 2022/09/09 08:36:37 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 08:36:37 - mmengine - INFO - Saving checkpoint at 141 epochs 2022/09/09 08:37:21 - mmengine - INFO - Epoch(train) [142][50/293] lr: 5.000000e-04 eta: 3:42:29 time: 0.789227 data_time: 0.106134 memory: 21676 loss_kpt: 0.000558 acc_pose: 0.882515 loss: 0.000558 2022/09/09 08:37:59 - mmengine - INFO - Epoch(train) [142][100/293] lr: 5.000000e-04 eta: 3:41:58 time: 0.755010 data_time: 0.095835 memory: 21676 loss_kpt: 0.000557 acc_pose: 0.798890 loss: 0.000557 2022/09/09 08:38:37 - mmengine - INFO - Epoch(train) [142][150/293] lr: 5.000000e-04 eta: 3:41:28 time: 0.759667 data_time: 0.099710 memory: 21676 loss_kpt: 0.000556 acc_pose: 0.837475 loss: 0.000556 2022/09/09 08:39:15 - mmengine - INFO - Epoch(train) [142][200/293] lr: 5.000000e-04 eta: 3:40:57 time: 0.766887 data_time: 0.103266 memory: 21676 loss_kpt: 0.000555 acc_pose: 0.858838 loss: 0.000555 2022/09/09 08:39:54 - mmengine - INFO - Epoch(train) [142][250/293] lr: 5.000000e-04 eta: 3:40:26 time: 0.761476 data_time: 0.097474 memory: 21676 loss_kpt: 0.000562 acc_pose: 0.865693 loss: 0.000562 2022/09/09 08:40:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 08:40:26 - mmengine - INFO - Saving checkpoint at 142 epochs 2022/09/09 08:41:10 - mmengine - INFO - Epoch(train) [143][50/293] lr: 5.000000e-04 eta: 3:39:14 time: 0.792347 data_time: 0.102160 memory: 21676 loss_kpt: 0.000561 acc_pose: 0.808422 loss: 0.000561 2022/09/09 08:41:49 - mmengine - INFO - Epoch(train) [143][100/293] lr: 5.000000e-04 eta: 3:38:44 time: 0.772352 data_time: 0.097065 memory: 21676 loss_kpt: 0.000568 acc_pose: 0.820479 loss: 0.000568 2022/09/09 08:42:26 - mmengine - INFO - Epoch(train) [143][150/293] lr: 5.000000e-04 eta: 3:38:13 time: 0.754007 data_time: 0.096547 memory: 21676 loss_kpt: 0.000567 acc_pose: 0.878590 loss: 0.000567 2022/09/09 08:43:04 - mmengine - INFO - Epoch(train) [143][200/293] lr: 5.000000e-04 eta: 3:37:42 time: 0.762509 data_time: 0.100314 memory: 21676 loss_kpt: 0.000566 acc_pose: 0.868029 loss: 0.000566 2022/09/09 08:43:42 - mmengine - INFO - Epoch(train) [143][250/293] lr: 5.000000e-04 eta: 3:37:11 time: 0.742647 data_time: 0.096945 memory: 21676 loss_kpt: 0.000564 acc_pose: 0.855106 loss: 0.000564 2022/09/09 08:44:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 08:44:13 - mmengine - INFO - Saving checkpoint at 143 epochs 2022/09/09 08:44:58 - mmengine - INFO - Epoch(train) [144][50/293] lr: 5.000000e-04 eta: 3:35:59 time: 0.796331 data_time: 0.101966 memory: 21676 loss_kpt: 0.000560 acc_pose: 0.848864 loss: 0.000560 2022/09/09 08:45:37 - mmengine - INFO - Epoch(train) [144][100/293] lr: 5.000000e-04 eta: 3:35:29 time: 0.785800 data_time: 0.104256 memory: 21676 loss_kpt: 0.000568 acc_pose: 0.824632 loss: 0.000568 2022/09/09 08:45:38 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 08:46:16 - mmengine - INFO - Epoch(train) [144][150/293] lr: 5.000000e-04 eta: 3:34:58 time: 0.775064 data_time: 0.099825 memory: 21676 loss_kpt: 0.000555 acc_pose: 0.826801 loss: 0.000555 2022/09/09 08:46:54 - mmengine - INFO - Epoch(train) [144][200/293] lr: 5.000000e-04 eta: 3:34:28 time: 0.765461 data_time: 0.094978 memory: 21676 loss_kpt: 0.000564 acc_pose: 0.863452 loss: 0.000564 2022/09/09 08:47:32 - mmengine - INFO - Epoch(train) [144][250/293] lr: 5.000000e-04 eta: 3:33:57 time: 0.748344 data_time: 0.093189 memory: 21676 loss_kpt: 0.000569 acc_pose: 0.887232 loss: 0.000569 2022/09/09 08:48:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 08:48:04 - mmengine - INFO - Saving checkpoint at 144 epochs 2022/09/09 08:48:48 - mmengine - INFO - Epoch(train) [145][50/293] lr: 5.000000e-04 eta: 3:32:45 time: 0.785257 data_time: 0.113332 memory: 21676 loss_kpt: 0.000541 acc_pose: 0.843844 loss: 0.000541 2022/09/09 08:49:26 - mmengine - INFO - Epoch(train) [145][100/293] lr: 5.000000e-04 eta: 3:32:14 time: 0.771341 data_time: 0.100924 memory: 21676 loss_kpt: 0.000561 acc_pose: 0.885518 loss: 0.000561 2022/09/09 08:50:04 - mmengine - INFO - Epoch(train) [145][150/293] lr: 5.000000e-04 eta: 3:31:43 time: 0.764265 data_time: 0.101414 memory: 21676 loss_kpt: 0.000546 acc_pose: 0.851043 loss: 0.000546 2022/09/09 08:50:43 - mmengine - INFO - Epoch(train) [145][200/293] lr: 5.000000e-04 eta: 3:31:13 time: 0.765655 data_time: 0.098866 memory: 21676 loss_kpt: 0.000562 acc_pose: 0.893636 loss: 0.000562 2022/09/09 08:51:21 - mmengine - INFO - Epoch(train) [145][250/293] lr: 5.000000e-04 eta: 3:30:42 time: 0.758348 data_time: 0.096013 memory: 21676 loss_kpt: 0.000557 acc_pose: 0.839960 loss: 0.000557 2022/09/09 08:51:53 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 08:51:53 - mmengine - INFO - Saving checkpoint at 145 epochs 2022/09/09 08:52:36 - mmengine - INFO - Epoch(train) [146][50/293] lr: 5.000000e-04 eta: 3:29:30 time: 0.777091 data_time: 0.110255 memory: 21676 loss_kpt: 0.000551 acc_pose: 0.806610 loss: 0.000551 2022/09/09 08:53:14 - mmengine - INFO - Epoch(train) [146][100/293] lr: 5.000000e-04 eta: 3:28:59 time: 0.764506 data_time: 0.102888 memory: 21676 loss_kpt: 0.000560 acc_pose: 0.859984 loss: 0.000560 2022/09/09 08:53:53 - mmengine - INFO - Epoch(train) [146][150/293] lr: 5.000000e-04 eta: 3:28:29 time: 0.774845 data_time: 0.099138 memory: 21676 loss_kpt: 0.000564 acc_pose: 0.828498 loss: 0.000564 2022/09/09 08:54:31 - mmengine - INFO - Epoch(train) [146][200/293] lr: 5.000000e-04 eta: 3:27:58 time: 0.761881 data_time: 0.100191 memory: 21676 loss_kpt: 0.000560 acc_pose: 0.835769 loss: 0.000560 2022/09/09 08:55:09 - mmengine - INFO - Epoch(train) [146][250/293] lr: 5.000000e-04 eta: 3:27:27 time: 0.754401 data_time: 0.096466 memory: 21676 loss_kpt: 0.000558 acc_pose: 0.851441 loss: 0.000558 2022/09/09 08:55:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 08:55:41 - mmengine - INFO - Saving checkpoint at 146 epochs 2022/09/09 08:56:25 - mmengine - INFO - Epoch(train) [147][50/293] lr: 5.000000e-04 eta: 3:26:15 time: 0.783258 data_time: 0.112209 memory: 21676 loss_kpt: 0.000546 acc_pose: 0.835607 loss: 0.000546 2022/09/09 08:57:03 - mmengine - INFO - Epoch(train) [147][100/293] lr: 5.000000e-04 eta: 3:25:44 time: 0.768225 data_time: 0.096413 memory: 21676 loss_kpt: 0.000555 acc_pose: 0.819838 loss: 0.000555 2022/09/09 08:57:42 - mmengine - INFO - Epoch(train) [147][150/293] lr: 5.000000e-04 eta: 3:25:14 time: 0.771942 data_time: 0.099975 memory: 21676 loss_kpt: 0.000542 acc_pose: 0.881110 loss: 0.000542 2022/09/09 08:58:20 - mmengine - INFO - Epoch(train) [147][200/293] lr: 5.000000e-04 eta: 3:24:43 time: 0.779314 data_time: 0.104251 memory: 21676 loss_kpt: 0.000541 acc_pose: 0.849198 loss: 0.000541 2022/09/09 08:58:38 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 08:59:00 - mmengine - INFO - Epoch(train) [147][250/293] lr: 5.000000e-04 eta: 3:24:13 time: 0.783204 data_time: 0.102766 memory: 21676 loss_kpt: 0.000572 acc_pose: 0.804103 loss: 0.000572 2022/09/09 08:59:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 08:59:33 - mmengine - INFO - Saving checkpoint at 147 epochs 2022/09/09 09:00:16 - mmengine - INFO - Epoch(train) [148][50/293] lr: 5.000000e-04 eta: 3:23:02 time: 0.790932 data_time: 0.113010 memory: 21676 loss_kpt: 0.000567 acc_pose: 0.834182 loss: 0.000567 2022/09/09 09:00:55 - mmengine - INFO - Epoch(train) [148][100/293] lr: 5.000000e-04 eta: 3:22:31 time: 0.767430 data_time: 0.101908 memory: 21676 loss_kpt: 0.000545 acc_pose: 0.815650 loss: 0.000545 2022/09/09 09:01:34 - mmengine - INFO - Epoch(train) [148][150/293] lr: 5.000000e-04 eta: 3:22:00 time: 0.790547 data_time: 0.112536 memory: 21676 loss_kpt: 0.000548 acc_pose: 0.852141 loss: 0.000548 2022/09/09 09:02:13 - mmengine - INFO - Epoch(train) [148][200/293] lr: 5.000000e-04 eta: 3:21:30 time: 0.774395 data_time: 0.105127 memory: 21676 loss_kpt: 0.000564 acc_pose: 0.811200 loss: 0.000564 2022/09/09 09:02:52 - mmengine - INFO - Epoch(train) [148][250/293] lr: 5.000000e-04 eta: 3:20:59 time: 0.771446 data_time: 0.105223 memory: 21676 loss_kpt: 0.000559 acc_pose: 0.848193 loss: 0.000559 2022/09/09 09:03:24 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 09:03:24 - mmengine - INFO - Saving checkpoint at 148 epochs 2022/09/09 09:04:08 - mmengine - INFO - Epoch(train) [149][50/293] lr: 5.000000e-04 eta: 3:19:48 time: 0.783177 data_time: 0.109256 memory: 21676 loss_kpt: 0.000551 acc_pose: 0.838437 loss: 0.000551 2022/09/09 09:04:47 - mmengine - INFO - Epoch(train) [149][100/293] lr: 5.000000e-04 eta: 3:19:17 time: 0.774874 data_time: 0.102569 memory: 21676 loss_kpt: 0.000556 acc_pose: 0.828186 loss: 0.000556 2022/09/09 09:05:25 - mmengine - INFO - Epoch(train) [149][150/293] lr: 5.000000e-04 eta: 3:18:46 time: 0.758796 data_time: 0.096194 memory: 21676 loss_kpt: 0.000562 acc_pose: 0.833733 loss: 0.000562 2022/09/09 09:06:04 - mmengine - INFO - Epoch(train) [149][200/293] lr: 5.000000e-04 eta: 3:18:15 time: 0.774793 data_time: 0.096719 memory: 21676 loss_kpt: 0.000562 acc_pose: 0.883788 loss: 0.000562 2022/09/09 09:06:42 - mmengine - INFO - Epoch(train) [149][250/293] lr: 5.000000e-04 eta: 3:17:45 time: 0.776310 data_time: 0.098767 memory: 21676 loss_kpt: 0.000560 acc_pose: 0.856636 loss: 0.000560 2022/09/09 09:07:14 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 09:07:14 - mmengine - INFO - Saving checkpoint at 149 epochs 2022/09/09 09:07:59 - mmengine - INFO - Epoch(train) [150][50/293] lr: 5.000000e-04 eta: 3:16:34 time: 0.793289 data_time: 0.112538 memory: 21676 loss_kpt: 0.000555 acc_pose: 0.803477 loss: 0.000555 2022/09/09 09:08:38 - mmengine - INFO - Epoch(train) [150][100/293] lr: 5.000000e-04 eta: 3:16:03 time: 0.780125 data_time: 0.106051 memory: 21676 loss_kpt: 0.000565 acc_pose: 0.829965 loss: 0.000565 2022/09/09 09:09:18 - mmengine - INFO - Epoch(train) [150][150/293] lr: 5.000000e-04 eta: 3:15:33 time: 0.797511 data_time: 0.103202 memory: 21676 loss_kpt: 0.000559 acc_pose: 0.875935 loss: 0.000559 2022/09/09 09:09:57 - mmengine - INFO - Epoch(train) [150][200/293] lr: 5.000000e-04 eta: 3:15:02 time: 0.772407 data_time: 0.106608 memory: 21676 loss_kpt: 0.000551 acc_pose: 0.814523 loss: 0.000551 2022/09/09 09:10:35 - mmengine - INFO - Epoch(train) [150][250/293] lr: 5.000000e-04 eta: 3:14:31 time: 0.774392 data_time: 0.096568 memory: 21676 loss_kpt: 0.000562 acc_pose: 0.873739 loss: 0.000562 2022/09/09 09:11:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 09:11:07 - mmengine - INFO - Saving checkpoint at 150 epochs 2022/09/09 09:11:20 - mmengine - INFO - Epoch(val) [150][50/407] eta: 0:00:56 time: 0.157860 data_time: 0.014458 memory: 21676 2022/09/09 09:11:28 - mmengine - INFO - Epoch(val) [150][100/407] eta: 0:00:48 time: 0.156472 data_time: 0.008487 memory: 1375 2022/09/09 09:11:36 - mmengine - INFO - Epoch(val) [150][150/407] eta: 0:00:39 time: 0.152210 data_time: 0.008573 memory: 1375 2022/09/09 09:11:43 - mmengine - INFO - Epoch(val) [150][200/407] eta: 0:00:31 time: 0.152448 data_time: 0.008771 memory: 1375 2022/09/09 09:11:51 - mmengine - INFO - Epoch(val) [150][250/407] eta: 0:00:23 time: 0.152429 data_time: 0.009864 memory: 1375 2022/09/09 09:11:58 - mmengine - INFO - Epoch(val) [150][300/407] eta: 0:00:16 time: 0.152501 data_time: 0.008627 memory: 1375 2022/09/09 09:12:06 - mmengine - INFO - Epoch(val) [150][350/407] eta: 0:00:08 time: 0.152559 data_time: 0.009086 memory: 1375 2022/09/09 09:12:14 - mmengine - INFO - Epoch(val) [150][400/407] eta: 0:00:01 time: 0.149464 data_time: 0.008094 memory: 1375 2022/09/09 09:12:50 - mmengine - INFO - Evaluating CocoMetric... 2022/09/09 09:13:04 - mmengine - INFO - Epoch(val) [150][407/407] coco/AP: 0.750512 coco/AP .5: 0.903436 coco/AP .75: 0.820802 coco/AP (M): 0.712521 coco/AP (L): 0.820230 coco/AR: 0.801307 coco/AR .5: 0.941121 coco/AR .75: 0.863980 coco/AR (M): 0.758017 coco/AR (L): 0.864363 2022/09/09 09:13:04 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220908/hrnet_w32_384/best_coco/AP_epoch_130.pth is removed 2022/09/09 09:13:06 - mmengine - INFO - The best checkpoint with 0.7505 coco/AP at 150 epoch is saved to best_coco/AP_epoch_150.pth. 2022/09/09 09:13:45 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 09:13:45 - mmengine - INFO - Epoch(train) [151][50/293] lr: 5.000000e-04 eta: 3:13:21 time: 0.778759 data_time: 0.105023 memory: 21676 loss_kpt: 0.000560 acc_pose: 0.833950 loss: 0.000560 2022/09/09 09:14:24 - mmengine - INFO - Epoch(train) [151][100/293] lr: 5.000000e-04 eta: 3:12:50 time: 0.766386 data_time: 0.097530 memory: 21676 loss_kpt: 0.000551 acc_pose: 0.832077 loss: 0.000551 2022/09/09 09:15:02 - mmengine - INFO - Epoch(train) [151][150/293] lr: 5.000000e-04 eta: 3:12:19 time: 0.769453 data_time: 0.093321 memory: 21676 loss_kpt: 0.000554 acc_pose: 0.843691 loss: 0.000554 2022/09/09 09:15:40 - mmengine - INFO - Epoch(train) [151][200/293] lr: 5.000000e-04 eta: 3:11:47 time: 0.752494 data_time: 0.099540 memory: 21676 loss_kpt: 0.000566 acc_pose: 0.827337 loss: 0.000566 2022/09/09 09:16:18 - mmengine - INFO - Epoch(train) [151][250/293] lr: 5.000000e-04 eta: 3:11:16 time: 0.755682 data_time: 0.095594 memory: 21676 loss_kpt: 0.000566 acc_pose: 0.827379 loss: 0.000566 2022/09/09 09:16:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 09:16:50 - mmengine - INFO - Saving checkpoint at 151 epochs 2022/09/09 09:17:33 - mmengine - INFO - Epoch(train) [152][50/293] lr: 5.000000e-04 eta: 3:10:06 time: 0.779959 data_time: 0.106153 memory: 21676 loss_kpt: 0.000550 acc_pose: 0.848035 loss: 0.000550 2022/09/09 09:18:12 - mmengine - INFO - Epoch(train) [152][100/293] lr: 5.000000e-04 eta: 3:09:35 time: 0.765789 data_time: 0.098004 memory: 21676 loss_kpt: 0.000554 acc_pose: 0.843443 loss: 0.000554 2022/09/09 09:18:50 - mmengine - INFO - Epoch(train) [152][150/293] lr: 5.000000e-04 eta: 3:09:04 time: 0.764249 data_time: 0.100381 memory: 21676 loss_kpt: 0.000550 acc_pose: 0.834902 loss: 0.000550 2022/09/09 09:19:28 - mmengine - INFO - Epoch(train) [152][200/293] lr: 5.000000e-04 eta: 3:08:32 time: 0.756218 data_time: 0.096636 memory: 21676 loss_kpt: 0.000553 acc_pose: 0.855210 loss: 0.000553 2022/09/09 09:20:06 - mmengine - INFO - Epoch(train) [152][250/293] lr: 5.000000e-04 eta: 3:08:01 time: 0.758394 data_time: 0.097094 memory: 21676 loss_kpt: 0.000563 acc_pose: 0.862140 loss: 0.000563 2022/09/09 09:20:38 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 09:20:38 - mmengine - INFO - Saving checkpoint at 152 epochs 2022/09/09 09:21:22 - mmengine - INFO - Epoch(train) [153][50/293] lr: 5.000000e-04 eta: 3:06:51 time: 0.792850 data_time: 0.108763 memory: 21676 loss_kpt: 0.000547 acc_pose: 0.850394 loss: 0.000547 2022/09/09 09:22:00 - mmengine - INFO - Epoch(train) [153][100/293] lr: 5.000000e-04 eta: 3:06:20 time: 0.769793 data_time: 0.097935 memory: 21676 loss_kpt: 0.000563 acc_pose: 0.846072 loss: 0.000563 2022/09/09 09:22:38 - mmengine - INFO - Epoch(train) [153][150/293] lr: 5.000000e-04 eta: 3:05:49 time: 0.757661 data_time: 0.092837 memory: 21676 loss_kpt: 0.000559 acc_pose: 0.860850 loss: 0.000559 2022/09/09 09:23:16 - mmengine - INFO - Epoch(train) [153][200/293] lr: 5.000000e-04 eta: 3:05:17 time: 0.744596 data_time: 0.092593 memory: 21676 loss_kpt: 0.000557 acc_pose: 0.856979 loss: 0.000557 2022/09/09 09:23:53 - mmengine - INFO - Epoch(train) [153][250/293] lr: 5.000000e-04 eta: 3:04:46 time: 0.757664 data_time: 0.097314 memory: 21676 loss_kpt: 0.000562 acc_pose: 0.880171 loss: 0.000562 2022/09/09 09:24:25 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 09:24:26 - mmengine - INFO - Saving checkpoint at 153 epochs 2022/09/09 09:25:09 - mmengine - INFO - Epoch(train) [154][50/293] lr: 5.000000e-04 eta: 3:03:36 time: 0.783783 data_time: 0.109201 memory: 21676 loss_kpt: 0.000556 acc_pose: 0.883252 loss: 0.000556 2022/09/09 09:25:46 - mmengine - INFO - Epoch(train) [154][100/293] lr: 5.000000e-04 eta: 3:03:05 time: 0.754191 data_time: 0.093196 memory: 21676 loss_kpt: 0.000561 acc_pose: 0.830523 loss: 0.000561 2022/09/09 09:26:24 - mmengine - INFO - Epoch(train) [154][150/293] lr: 5.000000e-04 eta: 3:02:33 time: 0.750665 data_time: 0.093293 memory: 21676 loss_kpt: 0.000549 acc_pose: 0.875571 loss: 0.000549 2022/09/09 09:26:40 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 09:27:02 - mmengine - INFO - Epoch(train) [154][200/293] lr: 5.000000e-04 eta: 3:02:02 time: 0.758758 data_time: 0.103703 memory: 21676 loss_kpt: 0.000569 acc_pose: 0.856056 loss: 0.000569 2022/09/09 09:27:40 - mmengine - INFO - Epoch(train) [154][250/293] lr: 5.000000e-04 eta: 3:01:30 time: 0.755403 data_time: 0.096860 memory: 21676 loss_kpt: 0.000554 acc_pose: 0.828331 loss: 0.000554 2022/09/09 09:28:12 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 09:28:12 - mmengine - INFO - Saving checkpoint at 154 epochs 2022/09/09 09:28:56 - mmengine - INFO - Epoch(train) [155][50/293] lr: 5.000000e-04 eta: 3:00:21 time: 0.782536 data_time: 0.104788 memory: 21676 loss_kpt: 0.000556 acc_pose: 0.846109 loss: 0.000556 2022/09/09 09:29:33 - mmengine - INFO - Epoch(train) [155][100/293] lr: 5.000000e-04 eta: 2:59:49 time: 0.745086 data_time: 0.098123 memory: 21676 loss_kpt: 0.000558 acc_pose: 0.827590 loss: 0.000558 2022/09/09 09:30:11 - mmengine - INFO - Epoch(train) [155][150/293] lr: 5.000000e-04 eta: 2:59:18 time: 0.761454 data_time: 0.096816 memory: 21676 loss_kpt: 0.000561 acc_pose: 0.854899 loss: 0.000561 2022/09/09 09:30:50 - mmengine - INFO - Epoch(train) [155][200/293] lr: 5.000000e-04 eta: 2:58:47 time: 0.771151 data_time: 0.098399 memory: 21676 loss_kpt: 0.000556 acc_pose: 0.842925 loss: 0.000556 2022/09/09 09:31:27 - mmengine - INFO - Epoch(train) [155][250/293] lr: 5.000000e-04 eta: 2:58:15 time: 0.750827 data_time: 0.100184 memory: 21676 loss_kpt: 0.000555 acc_pose: 0.879494 loss: 0.000555 2022/09/09 09:32:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 09:32:00 - mmengine - INFO - Saving checkpoint at 155 epochs 2022/09/09 09:32:43 - mmengine - INFO - Epoch(train) [156][50/293] lr: 5.000000e-04 eta: 2:57:06 time: 0.779099 data_time: 0.108132 memory: 21676 loss_kpt: 0.000553 acc_pose: 0.826962 loss: 0.000553 2022/09/09 09:33:21 - mmengine - INFO - Epoch(train) [156][100/293] lr: 5.000000e-04 eta: 2:56:34 time: 0.759164 data_time: 0.095393 memory: 21676 loss_kpt: 0.000555 acc_pose: 0.865610 loss: 0.000555 2022/09/09 09:34:00 - mmengine - INFO - Epoch(train) [156][150/293] lr: 5.000000e-04 eta: 2:56:03 time: 0.778092 data_time: 0.103657 memory: 21676 loss_kpt: 0.000550 acc_pose: 0.853375 loss: 0.000550 2022/09/09 09:34:38 - mmengine - INFO - Epoch(train) [156][200/293] lr: 5.000000e-04 eta: 2:55:32 time: 0.750483 data_time: 0.103143 memory: 21676 loss_kpt: 0.000542 acc_pose: 0.807731 loss: 0.000542 2022/09/09 09:35:15 - mmengine - INFO - Epoch(train) [156][250/293] lr: 5.000000e-04 eta: 2:55:00 time: 0.751416 data_time: 0.095324 memory: 21676 loss_kpt: 0.000569 acc_pose: 0.791167 loss: 0.000569 2022/09/09 09:35:47 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 09:35:47 - mmengine - INFO - Saving checkpoint at 156 epochs 2022/09/09 09:36:31 - mmengine - INFO - Epoch(train) [157][50/293] lr: 5.000000e-04 eta: 2:53:51 time: 0.784504 data_time: 0.111522 memory: 21676 loss_kpt: 0.000551 acc_pose: 0.868771 loss: 0.000551 2022/09/09 09:37:09 - mmengine - INFO - Epoch(train) [157][100/293] lr: 5.000000e-04 eta: 2:53:20 time: 0.757578 data_time: 0.094698 memory: 21676 loss_kpt: 0.000560 acc_pose: 0.833084 loss: 0.000560 2022/09/09 09:37:47 - mmengine - INFO - Epoch(train) [157][150/293] lr: 5.000000e-04 eta: 2:52:48 time: 0.762264 data_time: 0.098022 memory: 21676 loss_kpt: 0.000550 acc_pose: 0.876120 loss: 0.000550 2022/09/09 09:38:25 - mmengine - INFO - Epoch(train) [157][200/293] lr: 5.000000e-04 eta: 2:52:17 time: 0.758560 data_time: 0.096995 memory: 21676 loss_kpt: 0.000559 acc_pose: 0.880346 loss: 0.000559 2022/09/09 09:39:02 - mmengine - INFO - Epoch(train) [157][250/293] lr: 5.000000e-04 eta: 2:51:45 time: 0.749277 data_time: 0.097736 memory: 21676 loss_kpt: 0.000550 acc_pose: 0.875100 loss: 0.000550 2022/09/09 09:39:34 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 09:39:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 09:39:35 - mmengine - INFO - Saving checkpoint at 157 epochs 2022/09/09 09:40:19 - mmengine - INFO - Epoch(train) [158][50/293] lr: 5.000000e-04 eta: 2:50:36 time: 0.786107 data_time: 0.120265 memory: 21676 loss_kpt: 0.000549 acc_pose: 0.848751 loss: 0.000549 2022/09/09 09:40:57 - mmengine - INFO - Epoch(train) [158][100/293] lr: 5.000000e-04 eta: 2:50:05 time: 0.772035 data_time: 0.097674 memory: 21676 loss_kpt: 0.000557 acc_pose: 0.856741 loss: 0.000557 2022/09/09 09:41:35 - mmengine - INFO - Epoch(train) [158][150/293] lr: 5.000000e-04 eta: 2:49:34 time: 0.758760 data_time: 0.102223 memory: 21676 loss_kpt: 0.000554 acc_pose: 0.842889 loss: 0.000554 2022/09/09 09:42:14 - mmengine - INFO - Epoch(train) [158][200/293] lr: 5.000000e-04 eta: 2:49:02 time: 0.767740 data_time: 0.097865 memory: 21676 loss_kpt: 0.000562 acc_pose: 0.843828 loss: 0.000562 2022/09/09 09:42:52 - mmengine - INFO - Epoch(train) [158][250/293] lr: 5.000000e-04 eta: 2:48:31 time: 0.760962 data_time: 0.104218 memory: 21676 loss_kpt: 0.000551 acc_pose: 0.841219 loss: 0.000551 2022/09/09 09:43:24 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 09:43:24 - mmengine - INFO - Saving checkpoint at 158 epochs 2022/09/09 09:44:07 - mmengine - INFO - Epoch(train) [159][50/293] lr: 5.000000e-04 eta: 2:47:22 time: 0.792823 data_time: 0.122574 memory: 21676 loss_kpt: 0.000543 acc_pose: 0.852120 loss: 0.000543 2022/09/09 09:44:46 - mmengine - INFO - Epoch(train) [159][100/293] lr: 5.000000e-04 eta: 2:46:51 time: 0.782543 data_time: 0.103712 memory: 21676 loss_kpt: 0.000554 acc_pose: 0.847213 loss: 0.000554 2022/09/09 09:45:25 - mmengine - INFO - Epoch(train) [159][150/293] lr: 5.000000e-04 eta: 2:46:20 time: 0.771902 data_time: 0.103864 memory: 21676 loss_kpt: 0.000552 acc_pose: 0.809017 loss: 0.000552 2022/09/09 09:46:03 - mmengine - INFO - Epoch(train) [159][200/293] lr: 5.000000e-04 eta: 2:45:48 time: 0.756343 data_time: 0.105126 memory: 21676 loss_kpt: 0.000548 acc_pose: 0.851596 loss: 0.000548 2022/09/09 09:46:41 - mmengine - INFO - Epoch(train) [159][250/293] lr: 5.000000e-04 eta: 2:45:17 time: 0.763739 data_time: 0.108017 memory: 21676 loss_kpt: 0.000552 acc_pose: 0.854311 loss: 0.000552 2022/09/09 09:47:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 09:47:13 - mmengine - INFO - Saving checkpoint at 159 epochs 2022/09/09 09:47:56 - mmengine - INFO - Epoch(train) [160][50/293] lr: 5.000000e-04 eta: 2:44:08 time: 0.791916 data_time: 0.118328 memory: 21676 loss_kpt: 0.000546 acc_pose: 0.837117 loss: 0.000546 2022/09/09 09:48:35 - mmengine - INFO - Epoch(train) [160][100/293] lr: 5.000000e-04 eta: 2:43:37 time: 0.766541 data_time: 0.104563 memory: 21676 loss_kpt: 0.000557 acc_pose: 0.848188 loss: 0.000557 2022/09/09 09:49:12 - mmengine - INFO - Epoch(train) [160][150/293] lr: 5.000000e-04 eta: 2:43:05 time: 0.751740 data_time: 0.098631 memory: 21676 loss_kpt: 0.000552 acc_pose: 0.857006 loss: 0.000552 2022/09/09 09:49:50 - mmengine - INFO - Epoch(train) [160][200/293] lr: 5.000000e-04 eta: 2:42:34 time: 0.755057 data_time: 0.105297 memory: 21676 loss_kpt: 0.000540 acc_pose: 0.868361 loss: 0.000540 2022/09/09 09:50:28 - mmengine - INFO - Epoch(train) [160][250/293] lr: 5.000000e-04 eta: 2:42:02 time: 0.756329 data_time: 0.105802 memory: 21676 loss_kpt: 0.000553 acc_pose: 0.831714 loss: 0.000553 2022/09/09 09:51:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 09:51:00 - mmengine - INFO - Saving checkpoint at 160 epochs 2022/09/09 09:51:13 - mmengine - INFO - Epoch(val) [160][50/407] eta: 0:00:55 time: 0.155162 data_time: 0.013884 memory: 21676 2022/09/09 09:51:20 - mmengine - INFO - Epoch(val) [160][100/407] eta: 0:00:46 time: 0.151713 data_time: 0.008787 memory: 1375 2022/09/09 09:51:28 - mmengine - INFO - Epoch(val) [160][150/407] eta: 0:00:38 time: 0.151365 data_time: 0.008887 memory: 1375 2022/09/09 09:51:36 - mmengine - INFO - Epoch(val) [160][200/407] eta: 0:00:32 time: 0.155220 data_time: 0.009569 memory: 1375 2022/09/09 09:51:43 - mmengine - INFO - Epoch(val) [160][250/407] eta: 0:00:23 time: 0.152830 data_time: 0.010523 memory: 1375 2022/09/09 09:51:51 - mmengine - INFO - Epoch(val) [160][300/407] eta: 0:00:16 time: 0.150865 data_time: 0.008646 memory: 1375 2022/09/09 09:51:59 - mmengine - INFO - Epoch(val) [160][350/407] eta: 0:00:08 time: 0.155523 data_time: 0.012321 memory: 1375 2022/09/09 09:52:06 - mmengine - INFO - Epoch(val) [160][400/407] eta: 0:00:01 time: 0.148660 data_time: 0.008283 memory: 1375 2022/09/09 09:52:43 - mmengine - INFO - Evaluating CocoMetric... 2022/09/09 09:52:57 - mmengine - INFO - Epoch(val) [160][407/407] coco/AP: 0.753133 coco/AP .5: 0.901609 coco/AP .75: 0.820194 coco/AP (M): 0.715544 coco/AP (L): 0.821929 coco/AR: 0.803259 coco/AR .5: 0.939704 coco/AR .75: 0.862248 coco/AR (M): 0.760858 coco/AR (L): 0.865589 2022/09/09 09:52:57 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220908/hrnet_w32_384/best_coco/AP_epoch_150.pth is removed 2022/09/09 09:53:00 - mmengine - INFO - The best checkpoint with 0.7531 coco/AP at 160 epoch is saved to best_coco/AP_epoch_160.pth. 2022/09/09 09:53:40 - mmengine - INFO - Epoch(train) [161][50/293] lr: 5.000000e-04 eta: 2:40:54 time: 0.798290 data_time: 0.125695 memory: 21676 loss_kpt: 0.000547 acc_pose: 0.834073 loss: 0.000547 2022/09/09 09:54:19 - mmengine - INFO - Epoch(train) [161][100/293] lr: 5.000000e-04 eta: 2:40:22 time: 0.778825 data_time: 0.110776 memory: 21676 loss_kpt: 0.000541 acc_pose: 0.824735 loss: 0.000541 2022/09/09 09:54:34 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 09:54:57 - mmengine - INFO - Epoch(train) [161][150/293] lr: 5.000000e-04 eta: 2:39:51 time: 0.768354 data_time: 0.102195 memory: 21676 loss_kpt: 0.000559 acc_pose: 0.887985 loss: 0.000559 2022/09/09 09:55:35 - mmengine - INFO - Epoch(train) [161][200/293] lr: 5.000000e-04 eta: 2:39:19 time: 0.761412 data_time: 0.108202 memory: 21676 loss_kpt: 0.000561 acc_pose: 0.799347 loss: 0.000561 2022/09/09 09:56:13 - mmengine - INFO - Epoch(train) [161][250/293] lr: 5.000000e-04 eta: 2:38:48 time: 0.747694 data_time: 0.101708 memory: 21676 loss_kpt: 0.000543 acc_pose: 0.833771 loss: 0.000543 2022/09/09 09:56:45 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 09:56:45 - mmengine - INFO - Saving checkpoint at 161 epochs 2022/09/09 09:57:28 - mmengine - INFO - Epoch(train) [162][50/293] lr: 5.000000e-04 eta: 2:37:39 time: 0.780022 data_time: 0.115132 memory: 21676 loss_kpt: 0.000547 acc_pose: 0.840852 loss: 0.000547 2022/09/09 09:58:07 - mmengine - INFO - Epoch(train) [162][100/293] lr: 5.000000e-04 eta: 2:37:08 time: 0.782880 data_time: 0.103057 memory: 21676 loss_kpt: 0.000540 acc_pose: 0.869755 loss: 0.000540 2022/09/09 09:58:45 - mmengine - INFO - Epoch(train) [162][150/293] lr: 5.000000e-04 eta: 2:36:37 time: 0.761629 data_time: 0.099905 memory: 21676 loss_kpt: 0.000568 acc_pose: 0.817213 loss: 0.000568 2022/09/09 09:59:23 - mmengine - INFO - Epoch(train) [162][200/293] lr: 5.000000e-04 eta: 2:36:05 time: 0.750557 data_time: 0.102609 memory: 21676 loss_kpt: 0.000550 acc_pose: 0.853879 loss: 0.000550 2022/09/09 10:00:00 - mmengine - INFO - Epoch(train) [162][250/293] lr: 5.000000e-04 eta: 2:35:33 time: 0.758903 data_time: 0.103771 memory: 21676 loss_kpt: 0.000554 acc_pose: 0.829913 loss: 0.000554 2022/09/09 10:00:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 10:00:33 - mmengine - INFO - Saving checkpoint at 162 epochs 2022/09/09 10:01:17 - mmengine - INFO - Epoch(train) [163][50/293] lr: 5.000000e-04 eta: 2:34:25 time: 0.796053 data_time: 0.120664 memory: 21676 loss_kpt: 0.000556 acc_pose: 0.884810 loss: 0.000556 2022/09/09 10:01:56 - mmengine - INFO - Epoch(train) [163][100/293] lr: 5.000000e-04 eta: 2:33:54 time: 0.781971 data_time: 0.111762 memory: 21676 loss_kpt: 0.000550 acc_pose: 0.877437 loss: 0.000550 2022/09/09 10:02:34 - mmengine - INFO - Epoch(train) [163][150/293] lr: 5.000000e-04 eta: 2:33:22 time: 0.756959 data_time: 0.105359 memory: 21676 loss_kpt: 0.000552 acc_pose: 0.820161 loss: 0.000552 2022/09/09 10:03:12 - mmengine - INFO - Epoch(train) [163][200/293] lr: 5.000000e-04 eta: 2:32:51 time: 0.756147 data_time: 0.101517 memory: 21676 loss_kpt: 0.000557 acc_pose: 0.879465 loss: 0.000557 2022/09/09 10:03:50 - mmengine - INFO - Epoch(train) [163][250/293] lr: 5.000000e-04 eta: 2:32:19 time: 0.760806 data_time: 0.102343 memory: 21676 loss_kpt: 0.000542 acc_pose: 0.870610 loss: 0.000542 2022/09/09 10:04:22 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 10:04:22 - mmengine - INFO - Saving checkpoint at 163 epochs 2022/09/09 10:05:05 - mmengine - INFO - Epoch(train) [164][50/293] lr: 5.000000e-04 eta: 2:31:11 time: 0.789132 data_time: 0.119701 memory: 21676 loss_kpt: 0.000548 acc_pose: 0.839763 loss: 0.000548 2022/09/09 10:05:44 - mmengine - INFO - Epoch(train) [164][100/293] lr: 5.000000e-04 eta: 2:30:40 time: 0.787709 data_time: 0.105113 memory: 21676 loss_kpt: 0.000561 acc_pose: 0.859829 loss: 0.000561 2022/09/09 10:06:23 - mmengine - INFO - Epoch(train) [164][150/293] lr: 5.000000e-04 eta: 2:30:08 time: 0.772170 data_time: 0.104036 memory: 21676 loss_kpt: 0.000536 acc_pose: 0.861024 loss: 0.000536 2022/09/09 10:07:01 - mmengine - INFO - Epoch(train) [164][200/293] lr: 5.000000e-04 eta: 2:29:37 time: 0.756773 data_time: 0.104540 memory: 21676 loss_kpt: 0.000552 acc_pose: 0.865028 loss: 0.000552 2022/09/09 10:07:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 10:07:39 - mmengine - INFO - Epoch(train) [164][250/293] lr: 5.000000e-04 eta: 2:29:05 time: 0.768734 data_time: 0.100174 memory: 21676 loss_kpt: 0.000554 acc_pose: 0.855777 loss: 0.000554 2022/09/09 10:08:12 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 10:08:12 - mmengine - INFO - Saving checkpoint at 164 epochs 2022/09/09 10:08:55 - mmengine - INFO - Epoch(train) [165][50/293] lr: 5.000000e-04 eta: 2:27:57 time: 0.797000 data_time: 0.120516 memory: 21676 loss_kpt: 0.000557 acc_pose: 0.867955 loss: 0.000557 2022/09/09 10:09:35 - mmengine - INFO - Epoch(train) [165][100/293] lr: 5.000000e-04 eta: 2:27:26 time: 0.784576 data_time: 0.113798 memory: 21676 loss_kpt: 0.000555 acc_pose: 0.881226 loss: 0.000555 2022/09/09 10:10:14 - mmengine - INFO - Epoch(train) [165][150/293] lr: 5.000000e-04 eta: 2:26:55 time: 0.781908 data_time: 0.109995 memory: 21676 loss_kpt: 0.000555 acc_pose: 0.861327 loss: 0.000555 2022/09/09 10:10:52 - mmengine - INFO - Epoch(train) [165][200/293] lr: 5.000000e-04 eta: 2:26:23 time: 0.768282 data_time: 0.106488 memory: 21676 loss_kpt: 0.000555 acc_pose: 0.854707 loss: 0.000555 2022/09/09 10:11:30 - mmengine - INFO - Epoch(train) [165][250/293] lr: 5.000000e-04 eta: 2:25:51 time: 0.764956 data_time: 0.105172 memory: 21676 loss_kpt: 0.000537 acc_pose: 0.855315 loss: 0.000537 2022/09/09 10:12:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 10:12:02 - mmengine - INFO - Saving checkpoint at 165 epochs 2022/09/09 10:12:45 - mmengine - INFO - Epoch(train) [166][50/293] lr: 5.000000e-04 eta: 2:24:44 time: 0.775185 data_time: 0.114087 memory: 21676 loss_kpt: 0.000540 acc_pose: 0.832618 loss: 0.000540 2022/09/09 10:13:23 - mmengine - INFO - Epoch(train) [166][100/293] lr: 5.000000e-04 eta: 2:24:12 time: 0.751135 data_time: 0.100105 memory: 21676 loss_kpt: 0.000551 acc_pose: 0.850500 loss: 0.000551 2022/09/09 10:14:01 - mmengine - INFO - Epoch(train) [166][150/293] lr: 5.000000e-04 eta: 2:23:40 time: 0.763315 data_time: 0.104521 memory: 21676 loss_kpt: 0.000551 acc_pose: 0.812572 loss: 0.000551 2022/09/09 10:14:39 - mmengine - INFO - Epoch(train) [166][200/293] lr: 5.000000e-04 eta: 2:23:08 time: 0.755861 data_time: 0.100512 memory: 21676 loss_kpt: 0.000552 acc_pose: 0.851486 loss: 0.000552 2022/09/09 10:15:16 - mmengine - INFO - Epoch(train) [166][250/293] lr: 5.000000e-04 eta: 2:22:37 time: 0.751715 data_time: 0.100279 memory: 21676 loss_kpt: 0.000549 acc_pose: 0.870019 loss: 0.000549 2022/09/09 10:15:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 10:15:49 - mmengine - INFO - Saving checkpoint at 166 epochs 2022/09/09 10:16:32 - mmengine - INFO - Epoch(train) [167][50/293] lr: 5.000000e-04 eta: 2:21:29 time: 0.781399 data_time: 0.115118 memory: 21676 loss_kpt: 0.000534 acc_pose: 0.861607 loss: 0.000534 2022/09/09 10:17:11 - mmengine - INFO - Epoch(train) [167][100/293] lr: 5.000000e-04 eta: 2:20:57 time: 0.762439 data_time: 0.103916 memory: 21676 loss_kpt: 0.000539 acc_pose: 0.879025 loss: 0.000539 2022/09/09 10:17:48 - mmengine - INFO - Epoch(train) [167][150/293] lr: 5.000000e-04 eta: 2:20:26 time: 0.758531 data_time: 0.101450 memory: 21676 loss_kpt: 0.000558 acc_pose: 0.883593 loss: 0.000558 2022/09/09 10:18:27 - mmengine - INFO - Epoch(train) [167][200/293] lr: 5.000000e-04 eta: 2:19:54 time: 0.761169 data_time: 0.108566 memory: 21676 loss_kpt: 0.000541 acc_pose: 0.856151 loss: 0.000541 2022/09/09 10:19:05 - mmengine - INFO - Epoch(train) [167][250/293] lr: 5.000000e-04 eta: 2:19:22 time: 0.760950 data_time: 0.105048 memory: 21676 loss_kpt: 0.000557 acc_pose: 0.830803 loss: 0.000557 2022/09/09 10:19:37 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 10:19:37 - mmengine - INFO - Saving checkpoint at 167 epochs 2022/09/09 10:20:21 - mmengine - INFO - Epoch(train) [168][50/293] lr: 5.000000e-04 eta: 2:18:15 time: 0.790148 data_time: 0.114582 memory: 21676 loss_kpt: 0.000551 acc_pose: 0.864637 loss: 0.000551 2022/09/09 10:20:36 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 10:21:00 - mmengine - INFO - Epoch(train) [168][100/293] lr: 5.000000e-04 eta: 2:17:43 time: 0.781536 data_time: 0.106857 memory: 21676 loss_kpt: 0.000558 acc_pose: 0.864097 loss: 0.000558 2022/09/09 10:21:39 - mmengine - INFO - Epoch(train) [168][150/293] lr: 5.000000e-04 eta: 2:17:12 time: 0.781893 data_time: 0.106387 memory: 21676 loss_kpt: 0.000563 acc_pose: 0.880370 loss: 0.000563 2022/09/09 10:22:18 - mmengine - INFO - Epoch(train) [168][200/293] lr: 5.000000e-04 eta: 2:16:40 time: 0.780669 data_time: 0.103187 memory: 21676 loss_kpt: 0.000558 acc_pose: 0.889965 loss: 0.000558 2022/09/09 10:22:56 - mmengine - INFO - Epoch(train) [168][250/293] lr: 5.000000e-04 eta: 2:16:08 time: 0.758141 data_time: 0.100768 memory: 21676 loss_kpt: 0.000566 acc_pose: 0.853695 loss: 0.000566 2022/09/09 10:23:29 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 10:23:29 - mmengine - INFO - Saving checkpoint at 168 epochs 2022/09/09 10:24:11 - mmengine - INFO - Epoch(train) [169][50/293] lr: 5.000000e-04 eta: 2:15:01 time: 0.780242 data_time: 0.112347 memory: 21676 loss_kpt: 0.000546 acc_pose: 0.823844 loss: 0.000546 2022/09/09 10:24:51 - mmengine - INFO - Epoch(train) [169][100/293] lr: 5.000000e-04 eta: 2:14:30 time: 0.795386 data_time: 0.102140 memory: 21676 loss_kpt: 0.000561 acc_pose: 0.843983 loss: 0.000561 2022/09/09 10:25:29 - mmengine - INFO - Epoch(train) [169][150/293] lr: 5.000000e-04 eta: 2:13:58 time: 0.756892 data_time: 0.100260 memory: 21676 loss_kpt: 0.000545 acc_pose: 0.826714 loss: 0.000545 2022/09/09 10:26:07 - mmengine - INFO - Epoch(train) [169][200/293] lr: 5.000000e-04 eta: 2:13:26 time: 0.762010 data_time: 0.101656 memory: 21676 loss_kpt: 0.000541 acc_pose: 0.850331 loss: 0.000541 2022/09/09 10:26:45 - mmengine - INFO - Epoch(train) [169][250/293] lr: 5.000000e-04 eta: 2:12:54 time: 0.762755 data_time: 0.099858 memory: 21676 loss_kpt: 0.000554 acc_pose: 0.852783 loss: 0.000554 2022/09/09 10:27:17 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 10:27:17 - mmengine - INFO - Saving checkpoint at 169 epochs 2022/09/09 10:28:01 - mmengine - INFO - Epoch(train) [170][50/293] lr: 5.000000e-04 eta: 2:11:48 time: 0.794392 data_time: 0.110312 memory: 21676 loss_kpt: 0.000545 acc_pose: 0.881478 loss: 0.000545 2022/09/09 10:28:40 - mmengine - INFO - Epoch(train) [170][100/293] lr: 5.000000e-04 eta: 2:11:16 time: 0.766808 data_time: 0.101155 memory: 21676 loss_kpt: 0.000544 acc_pose: 0.856801 loss: 0.000544 2022/09/09 10:29:17 - mmengine - INFO - Epoch(train) [170][150/293] lr: 5.000000e-04 eta: 2:10:44 time: 0.747491 data_time: 0.105562 memory: 21676 loss_kpt: 0.000557 acc_pose: 0.810912 loss: 0.000557 2022/09/09 10:29:55 - mmengine - INFO - Epoch(train) [170][200/293] lr: 5.000000e-04 eta: 2:10:12 time: 0.761323 data_time: 0.104305 memory: 21676 loss_kpt: 0.000540 acc_pose: 0.870401 loss: 0.000540 2022/09/09 10:30:34 - mmengine - INFO - Epoch(train) [170][250/293] lr: 5.000000e-04 eta: 2:09:40 time: 0.775348 data_time: 0.109484 memory: 21676 loss_kpt: 0.000544 acc_pose: 0.858964 loss: 0.000544 2022/09/09 10:31:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 10:31:07 - mmengine - INFO - Saving checkpoint at 170 epochs 2022/09/09 10:31:20 - mmengine - INFO - Epoch(val) [170][50/407] eta: 0:00:56 time: 0.158435 data_time: 0.015173 memory: 21676 2022/09/09 10:31:27 - mmengine - INFO - Epoch(val) [170][100/407] eta: 0:00:46 time: 0.150452 data_time: 0.008614 memory: 1375 2022/09/09 10:31:35 - mmengine - INFO - Epoch(val) [170][150/407] eta: 0:00:38 time: 0.150667 data_time: 0.008847 memory: 1375 2022/09/09 10:31:42 - mmengine - INFO - Epoch(val) [170][200/407] eta: 0:00:31 time: 0.153622 data_time: 0.012648 memory: 1375 2022/09/09 10:31:50 - mmengine - INFO - Epoch(val) [170][250/407] eta: 0:00:24 time: 0.155113 data_time: 0.012144 memory: 1375 2022/09/09 10:31:58 - mmengine - INFO - Epoch(val) [170][300/407] eta: 0:00:16 time: 0.149844 data_time: 0.009221 memory: 1375 2022/09/09 10:32:05 - mmengine - INFO - Epoch(val) [170][350/407] eta: 0:00:08 time: 0.150103 data_time: 0.008209 memory: 1375 2022/09/09 10:32:13 - mmengine - INFO - Epoch(val) [170][400/407] eta: 0:00:01 time: 0.149506 data_time: 0.007778 memory: 1375 2022/09/09 10:32:49 - mmengine - INFO - Evaluating CocoMetric... 2022/09/09 10:33:03 - mmengine - INFO - Epoch(val) [170][407/407] coco/AP: 0.751180 coco/AP .5: 0.901304 coco/AP .75: 0.820324 coco/AP (M): 0.713247 coco/AP (L): 0.819471 coco/AR: 0.801527 coco/AR .5: 0.937972 coco/AR .75: 0.862720 coco/AR (M): 0.758918 coco/AR (L): 0.863471 2022/09/09 10:33:43 - mmengine - INFO - Epoch(train) [171][50/293] lr: 5.000000e-05 eta: 2:08:34 time: 0.799957 data_time: 0.123710 memory: 21676 loss_kpt: 0.000535 acc_pose: 0.836923 loss: 0.000535 2022/09/09 10:34:22 - mmengine - INFO - Epoch(train) [171][100/293] lr: 5.000000e-05 eta: 2:08:02 time: 0.782157 data_time: 0.100502 memory: 21676 loss_kpt: 0.000550 acc_pose: 0.822769 loss: 0.000550 2022/09/09 10:35:01 - mmengine - INFO - Epoch(train) [171][150/293] lr: 5.000000e-05 eta: 2:07:30 time: 0.778800 data_time: 0.104100 memory: 21676 loss_kpt: 0.000528 acc_pose: 0.835003 loss: 0.000528 2022/09/09 10:35:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 10:35:40 - mmengine - INFO - Epoch(train) [171][200/293] lr: 5.000000e-05 eta: 2:06:59 time: 0.776620 data_time: 0.113190 memory: 21676 loss_kpt: 0.000532 acc_pose: 0.864970 loss: 0.000532 2022/09/09 10:36:18 - mmengine - INFO - Epoch(train) [171][250/293] lr: 5.000000e-05 eta: 2:06:27 time: 0.753576 data_time: 0.108085 memory: 21676 loss_kpt: 0.000529 acc_pose: 0.851004 loss: 0.000529 2022/09/09 10:36:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 10:36:50 - mmengine - INFO - Saving checkpoint at 171 epochs 2022/09/09 10:37:34 - mmengine - INFO - Epoch(train) [172][50/293] lr: 5.000000e-05 eta: 2:05:20 time: 0.795753 data_time: 0.120345 memory: 21676 loss_kpt: 0.000536 acc_pose: 0.903214 loss: 0.000536 2022/09/09 10:38:13 - mmengine - INFO - Epoch(train) [172][100/293] lr: 5.000000e-05 eta: 2:04:48 time: 0.776946 data_time: 0.106016 memory: 21676 loss_kpt: 0.000523 acc_pose: 0.889444 loss: 0.000523 2022/09/09 10:38:52 - mmengine - INFO - Epoch(train) [172][150/293] lr: 5.000000e-05 eta: 2:04:17 time: 0.779720 data_time: 0.107115 memory: 21676 loss_kpt: 0.000522 acc_pose: 0.846223 loss: 0.000522 2022/09/09 10:39:31 - mmengine - INFO - Epoch(train) [172][200/293] lr: 5.000000e-05 eta: 2:03:45 time: 0.783055 data_time: 0.106474 memory: 21676 loss_kpt: 0.000525 acc_pose: 0.880150 loss: 0.000525 2022/09/09 10:40:11 - mmengine - INFO - Epoch(train) [172][250/293] lr: 5.000000e-05 eta: 2:03:13 time: 0.786626 data_time: 0.106570 memory: 21676 loss_kpt: 0.000525 acc_pose: 0.844817 loss: 0.000525 2022/09/09 10:40:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 10:40:44 - mmengine - INFO - Saving checkpoint at 172 epochs 2022/09/09 10:41:28 - mmengine - INFO - Epoch(train) [173][50/293] lr: 5.000000e-05 eta: 2:02:07 time: 0.796413 data_time: 0.112612 memory: 21676 loss_kpt: 0.000528 acc_pose: 0.870102 loss: 0.000528 2022/09/09 10:42:06 - mmengine - INFO - Epoch(train) [173][100/293] lr: 5.000000e-05 eta: 2:01:35 time: 0.753195 data_time: 0.110221 memory: 21676 loss_kpt: 0.000515 acc_pose: 0.883777 loss: 0.000515 2022/09/09 10:42:44 - mmengine - INFO - Epoch(train) [173][150/293] lr: 5.000000e-05 eta: 2:01:03 time: 0.754898 data_time: 0.104509 memory: 21676 loss_kpt: 0.000512 acc_pose: 0.839877 loss: 0.000512 2022/09/09 10:43:22 - mmengine - INFO - Epoch(train) [173][200/293] lr: 5.000000e-05 eta: 2:00:31 time: 0.766579 data_time: 0.102304 memory: 21676 loss_kpt: 0.000527 acc_pose: 0.815370 loss: 0.000527 2022/09/09 10:44:01 - mmengine - INFO - Epoch(train) [173][250/293] lr: 5.000000e-05 eta: 1:59:59 time: 0.770398 data_time: 0.100103 memory: 21676 loss_kpt: 0.000530 acc_pose: 0.874636 loss: 0.000530 2022/09/09 10:44:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 10:44:33 - mmengine - INFO - Saving checkpoint at 173 epochs 2022/09/09 10:45:16 - mmengine - INFO - Epoch(train) [174][50/293] lr: 5.000000e-05 eta: 1:58:53 time: 0.775234 data_time: 0.113886 memory: 21676 loss_kpt: 0.000526 acc_pose: 0.858963 loss: 0.000526 2022/09/09 10:45:54 - mmengine - INFO - Epoch(train) [174][100/293] lr: 5.000000e-05 eta: 1:58:21 time: 0.758876 data_time: 0.100892 memory: 21676 loss_kpt: 0.000528 acc_pose: 0.867674 loss: 0.000528 2022/09/09 10:46:33 - mmengine - INFO - Epoch(train) [174][150/293] lr: 5.000000e-05 eta: 1:57:49 time: 0.771982 data_time: 0.100811 memory: 21676 loss_kpt: 0.000534 acc_pose: 0.837612 loss: 0.000534 2022/09/09 10:47:11 - mmengine - INFO - Epoch(train) [174][200/293] lr: 5.000000e-05 eta: 1:57:17 time: 0.765781 data_time: 0.104449 memory: 21676 loss_kpt: 0.000525 acc_pose: 0.866274 loss: 0.000525 2022/09/09 10:47:49 - mmengine - INFO - Epoch(train) [174][250/293] lr: 5.000000e-05 eta: 1:56:45 time: 0.756573 data_time: 0.098873 memory: 21676 loss_kpt: 0.000526 acc_pose: 0.871864 loss: 0.000526 2022/09/09 10:48:21 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 10:48:21 - mmengine - INFO - Saving checkpoint at 174 epochs 2022/09/09 10:48:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 10:49:05 - mmengine - INFO - Epoch(train) [175][50/293] lr: 5.000000e-05 eta: 1:55:39 time: 0.786521 data_time: 0.113737 memory: 21676 loss_kpt: 0.000529 acc_pose: 0.867741 loss: 0.000529 2022/09/09 10:49:44 - mmengine - INFO - Epoch(train) [175][100/293] lr: 5.000000e-05 eta: 1:55:07 time: 0.769324 data_time: 0.104643 memory: 21676 loss_kpt: 0.000533 acc_pose: 0.839069 loss: 0.000533 2022/09/09 10:50:23 - mmengine - INFO - Epoch(train) [175][150/293] lr: 5.000000e-05 eta: 1:54:35 time: 0.785809 data_time: 0.106033 memory: 21676 loss_kpt: 0.000534 acc_pose: 0.880524 loss: 0.000534 2022/09/09 10:51:01 - mmengine - INFO - Epoch(train) [175][200/293] lr: 5.000000e-05 eta: 1:54:03 time: 0.759491 data_time: 0.102644 memory: 21676 loss_kpt: 0.000535 acc_pose: 0.875067 loss: 0.000535 2022/09/09 10:51:39 - mmengine - INFO - Epoch(train) [175][250/293] lr: 5.000000e-05 eta: 1:53:31 time: 0.767924 data_time: 0.102854 memory: 21676 loss_kpt: 0.000515 acc_pose: 0.903933 loss: 0.000515 2022/09/09 10:52:12 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 10:52:12 - mmengine - INFO - Saving checkpoint at 175 epochs 2022/09/09 10:52:55 - mmengine - INFO - Epoch(train) [176][50/293] lr: 5.000000e-05 eta: 1:52:25 time: 0.774977 data_time: 0.116375 memory: 21676 loss_kpt: 0.000533 acc_pose: 0.873241 loss: 0.000533 2022/09/09 10:53:34 - mmengine - INFO - Epoch(train) [176][100/293] lr: 5.000000e-05 eta: 1:51:53 time: 0.762022 data_time: 0.108616 memory: 21676 loss_kpt: 0.000523 acc_pose: 0.883424 loss: 0.000523 2022/09/09 10:54:11 - mmengine - INFO - Epoch(train) [176][150/293] lr: 5.000000e-05 eta: 1:51:21 time: 0.758785 data_time: 0.105595 memory: 21676 loss_kpt: 0.000514 acc_pose: 0.865724 loss: 0.000514 2022/09/09 10:54:49 - mmengine - INFO - Epoch(train) [176][200/293] lr: 5.000000e-05 eta: 1:50:48 time: 0.748785 data_time: 0.102831 memory: 21676 loss_kpt: 0.000525 acc_pose: 0.865843 loss: 0.000525 2022/09/09 10:55:27 - mmengine - INFO - Epoch(train) [176][250/293] lr: 5.000000e-05 eta: 1:50:16 time: 0.766304 data_time: 0.104688 memory: 21676 loss_kpt: 0.000524 acc_pose: 0.895187 loss: 0.000524 2022/09/09 10:56:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 10:56:00 - mmengine - INFO - Saving checkpoint at 176 epochs 2022/09/09 10:56:44 - mmengine - INFO - Epoch(train) [177][50/293] lr: 5.000000e-05 eta: 1:49:11 time: 0.794665 data_time: 0.113660 memory: 21676 loss_kpt: 0.000508 acc_pose: 0.866864 loss: 0.000508 2022/09/09 10:57:23 - mmengine - INFO - Epoch(train) [177][100/293] lr: 5.000000e-05 eta: 1:48:39 time: 0.781618 data_time: 0.103503 memory: 21676 loss_kpt: 0.000522 acc_pose: 0.844240 loss: 0.000522 2022/09/09 10:58:02 - mmengine - INFO - Epoch(train) [177][150/293] lr: 5.000000e-05 eta: 1:48:07 time: 0.784616 data_time: 0.105843 memory: 21676 loss_kpt: 0.000518 acc_pose: 0.822928 loss: 0.000518 2022/09/09 10:58:41 - mmengine - INFO - Epoch(train) [177][200/293] lr: 5.000000e-05 eta: 1:47:35 time: 0.770857 data_time: 0.106956 memory: 21676 loss_kpt: 0.000526 acc_pose: 0.901004 loss: 0.000526 2022/09/09 10:59:18 - mmengine - INFO - Epoch(train) [177][250/293] lr: 5.000000e-05 eta: 1:47:03 time: 0.754183 data_time: 0.100478 memory: 21676 loss_kpt: 0.000518 acc_pose: 0.849136 loss: 0.000518 2022/09/09 10:59:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 10:59:50 - mmengine - INFO - Saving checkpoint at 177 epochs 2022/09/09 11:00:34 - mmengine - INFO - Epoch(train) [178][50/293] lr: 5.000000e-05 eta: 1:45:57 time: 0.789664 data_time: 0.118466 memory: 21676 loss_kpt: 0.000515 acc_pose: 0.836878 loss: 0.000515 2022/09/09 11:01:12 - mmengine - INFO - Epoch(train) [178][100/293] lr: 5.000000e-05 eta: 1:45:25 time: 0.755519 data_time: 0.102032 memory: 21676 loss_kpt: 0.000515 acc_pose: 0.881836 loss: 0.000515 2022/09/09 11:01:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 11:01:50 - mmengine - INFO - Epoch(train) [178][150/293] lr: 5.000000e-05 eta: 1:44:53 time: 0.760154 data_time: 0.103764 memory: 21676 loss_kpt: 0.000519 acc_pose: 0.900969 loss: 0.000519 2022/09/09 11:02:28 - mmengine - INFO - Epoch(train) [178][200/293] lr: 5.000000e-05 eta: 1:44:21 time: 0.762038 data_time: 0.107293 memory: 21676 loss_kpt: 0.000520 acc_pose: 0.842303 loss: 0.000520 2022/09/09 11:03:06 - mmengine - INFO - Epoch(train) [178][250/293] lr: 5.000000e-05 eta: 1:43:48 time: 0.752503 data_time: 0.105478 memory: 21676 loss_kpt: 0.000511 acc_pose: 0.850304 loss: 0.000511 2022/09/09 11:03:38 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 11:03:38 - mmengine - INFO - Saving checkpoint at 178 epochs 2022/09/09 11:04:22 - mmengine - INFO - Epoch(train) [179][50/293] lr: 5.000000e-05 eta: 1:42:43 time: 0.797374 data_time: 0.117440 memory: 21676 loss_kpt: 0.000501 acc_pose: 0.885682 loss: 0.000501 2022/09/09 11:05:01 - mmengine - INFO - Epoch(train) [179][100/293] lr: 5.000000e-05 eta: 1:42:11 time: 0.779809 data_time: 0.099681 memory: 21676 loss_kpt: 0.000524 acc_pose: 0.864330 loss: 0.000524 2022/09/09 11:05:40 - mmengine - INFO - Epoch(train) [179][150/293] lr: 5.000000e-05 eta: 1:41:39 time: 0.766616 data_time: 0.116790 memory: 21676 loss_kpt: 0.000516 acc_pose: 0.858424 loss: 0.000516 2022/09/09 11:06:18 - mmengine - INFO - Epoch(train) [179][200/293] lr: 5.000000e-05 eta: 1:41:07 time: 0.772522 data_time: 0.108689 memory: 21676 loss_kpt: 0.000519 acc_pose: 0.865761 loss: 0.000519 2022/09/09 11:06:56 - mmengine - INFO - Epoch(train) [179][250/293] lr: 5.000000e-05 eta: 1:40:35 time: 0.760412 data_time: 0.103410 memory: 21676 loss_kpt: 0.000522 acc_pose: 0.894677 loss: 0.000522 2022/09/09 11:07:29 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 11:07:29 - mmengine - INFO - Saving checkpoint at 179 epochs 2022/09/09 11:08:13 - mmengine - INFO - Epoch(train) [180][50/293] lr: 5.000000e-05 eta: 1:39:29 time: 0.788582 data_time: 0.113885 memory: 21676 loss_kpt: 0.000514 acc_pose: 0.889281 loss: 0.000514 2022/09/09 11:08:51 - mmengine - INFO - Epoch(train) [180][100/293] lr: 5.000000e-05 eta: 1:38:57 time: 0.763545 data_time: 0.114354 memory: 21676 loss_kpt: 0.000514 acc_pose: 0.868494 loss: 0.000514 2022/09/09 11:09:29 - mmengine - INFO - Epoch(train) [180][150/293] lr: 5.000000e-05 eta: 1:38:25 time: 0.762951 data_time: 0.103483 memory: 21676 loss_kpt: 0.000524 acc_pose: 0.853426 loss: 0.000524 2022/09/09 11:10:07 - mmengine - INFO - Epoch(train) [180][200/293] lr: 5.000000e-05 eta: 1:37:53 time: 0.760425 data_time: 0.104649 memory: 21676 loss_kpt: 0.000523 acc_pose: 0.861026 loss: 0.000523 2022/09/09 11:10:44 - mmengine - INFO - Epoch(train) [180][250/293] lr: 5.000000e-05 eta: 1:37:21 time: 0.749677 data_time: 0.100274 memory: 21676 loss_kpt: 0.000510 acc_pose: 0.852239 loss: 0.000510 2022/09/09 11:11:17 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 11:11:17 - mmengine - INFO - Saving checkpoint at 180 epochs 2022/09/09 11:11:30 - mmengine - INFO - Epoch(val) [180][50/407] eta: 0:00:55 time: 0.156462 data_time: 0.013666 memory: 21676 2022/09/09 11:11:37 - mmengine - INFO - Epoch(val) [180][100/407] eta: 0:00:46 time: 0.151158 data_time: 0.008351 memory: 1375 2022/09/09 11:11:45 - mmengine - INFO - Epoch(val) [180][150/407] eta: 0:00:38 time: 0.149841 data_time: 0.008216 memory: 1375 2022/09/09 11:11:52 - mmengine - INFO - Epoch(val) [180][200/407] eta: 0:00:31 time: 0.151271 data_time: 0.009285 memory: 1375 2022/09/09 11:12:00 - mmengine - INFO - Epoch(val) [180][250/407] eta: 0:00:24 time: 0.154626 data_time: 0.013842 memory: 1375 2022/09/09 11:12:07 - mmengine - INFO - Epoch(val) [180][300/407] eta: 0:00:16 time: 0.150136 data_time: 0.008863 memory: 1375 2022/09/09 11:12:15 - mmengine - INFO - Epoch(val) [180][350/407] eta: 0:00:08 time: 0.151425 data_time: 0.009008 memory: 1375 2022/09/09 11:12:22 - mmengine - INFO - Epoch(val) [180][400/407] eta: 0:00:01 time: 0.148511 data_time: 0.008386 memory: 1375 2022/09/09 11:12:58 - mmengine - INFO - Evaluating CocoMetric... 2022/09/09 11:13:12 - mmengine - INFO - Epoch(val) [180][407/407] coco/AP: 0.759640 coco/AP .5: 0.908144 coco/AP .75: 0.826044 coco/AP (M): 0.721301 coco/AP (L): 0.828361 coco/AR: 0.809131 coco/AR .5: 0.943325 coco/AR .75: 0.868545 coco/AR (M): 0.766239 coco/AR (L): 0.871200 2022/09/09 11:13:13 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220908/hrnet_w32_384/best_coco/AP_epoch_160.pth is removed 2022/09/09 11:13:15 - mmengine - INFO - The best checkpoint with 0.7596 coco/AP at 180 epoch is saved to best_coco/AP_epoch_180.pth. 2022/09/09 11:13:55 - mmengine - INFO - Epoch(train) [181][50/293] lr: 5.000000e-05 eta: 1:36:15 time: 0.788060 data_time: 0.112413 memory: 21676 loss_kpt: 0.000521 acc_pose: 0.840338 loss: 0.000521 2022/09/09 11:14:34 - mmengine - INFO - Epoch(train) [181][100/293] lr: 5.000000e-05 eta: 1:35:43 time: 0.785498 data_time: 0.113290 memory: 21676 loss_kpt: 0.000508 acc_pose: 0.882485 loss: 0.000508 2022/09/09 11:15:13 - mmengine - INFO - Epoch(train) [181][150/293] lr: 5.000000e-05 eta: 1:35:11 time: 0.782833 data_time: 0.105590 memory: 21676 loss_kpt: 0.000517 acc_pose: 0.875062 loss: 0.000517 2022/09/09 11:15:52 - mmengine - INFO - Epoch(train) [181][200/293] lr: 5.000000e-05 eta: 1:34:39 time: 0.775699 data_time: 0.105018 memory: 21676 loss_kpt: 0.000499 acc_pose: 0.843234 loss: 0.000499 2022/09/09 11:16:31 - mmengine - INFO - Epoch(train) [181][250/293] lr: 5.000000e-05 eta: 1:34:07 time: 0.787148 data_time: 0.103919 memory: 21676 loss_kpt: 0.000517 acc_pose: 0.866667 loss: 0.000517 2022/09/09 11:16:39 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 11:17:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 11:17:04 - mmengine - INFO - Saving checkpoint at 181 epochs 2022/09/09 11:17:48 - mmengine - INFO - Epoch(train) [182][50/293] lr: 5.000000e-05 eta: 1:33:02 time: 0.805392 data_time: 0.115723 memory: 21676 loss_kpt: 0.000526 acc_pose: 0.867910 loss: 0.000526 2022/09/09 11:18:27 - mmengine - INFO - Epoch(train) [182][100/293] lr: 5.000000e-05 eta: 1:32:30 time: 0.768639 data_time: 0.103104 memory: 21676 loss_kpt: 0.000524 acc_pose: 0.806156 loss: 0.000524 2022/09/09 11:19:04 - mmengine - INFO - Epoch(train) [182][150/293] lr: 5.000000e-05 eta: 1:31:58 time: 0.752435 data_time: 0.100694 memory: 21676 loss_kpt: 0.000519 acc_pose: 0.902797 loss: 0.000519 2022/09/09 11:19:41 - mmengine - INFO - Epoch(train) [182][200/293] lr: 5.000000e-05 eta: 1:31:25 time: 0.744062 data_time: 0.099228 memory: 21676 loss_kpt: 0.000516 acc_pose: 0.880517 loss: 0.000516 2022/09/09 11:20:19 - mmengine - INFO - Epoch(train) [182][250/293] lr: 5.000000e-05 eta: 1:30:53 time: 0.756538 data_time: 0.102645 memory: 21676 loss_kpt: 0.000510 acc_pose: 0.866127 loss: 0.000510 2022/09/09 11:20:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 11:20:51 - mmengine - INFO - Saving checkpoint at 182 epochs 2022/09/09 11:21:34 - mmengine - INFO - Epoch(train) [183][50/293] lr: 5.000000e-05 eta: 1:29:48 time: 0.793475 data_time: 0.119120 memory: 21676 loss_kpt: 0.000518 acc_pose: 0.843204 loss: 0.000518 2022/09/09 11:22:13 - mmengine - INFO - Epoch(train) [183][100/293] lr: 5.000000e-05 eta: 1:29:16 time: 0.762497 data_time: 0.106702 memory: 21676 loss_kpt: 0.000512 acc_pose: 0.910265 loss: 0.000512 2022/09/09 11:22:51 - mmengine - INFO - Epoch(train) [183][150/293] lr: 5.000000e-05 eta: 1:28:44 time: 0.769313 data_time: 0.104021 memory: 21676 loss_kpt: 0.000516 acc_pose: 0.846441 loss: 0.000516 2022/09/09 11:23:29 - mmengine - INFO - Epoch(train) [183][200/293] lr: 5.000000e-05 eta: 1:28:11 time: 0.767185 data_time: 0.105316 memory: 21676 loss_kpt: 0.000516 acc_pose: 0.860404 loss: 0.000516 2022/09/09 11:24:08 - mmengine - INFO - Epoch(train) [183][250/293] lr: 5.000000e-05 eta: 1:27:39 time: 0.763419 data_time: 0.108329 memory: 21676 loss_kpt: 0.000521 acc_pose: 0.916398 loss: 0.000521 2022/09/09 11:24:40 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 11:24:40 - mmengine - INFO - Saving checkpoint at 183 epochs 2022/09/09 11:25:24 - mmengine - INFO - Epoch(train) [184][50/293] lr: 5.000000e-05 eta: 1:26:34 time: 0.794054 data_time: 0.126492 memory: 21676 loss_kpt: 0.000507 acc_pose: 0.826278 loss: 0.000507 2022/09/09 11:26:03 - mmengine - INFO - Epoch(train) [184][100/293] lr: 5.000000e-05 eta: 1:26:02 time: 0.777116 data_time: 0.110525 memory: 21676 loss_kpt: 0.000519 acc_pose: 0.858042 loss: 0.000519 2022/09/09 11:26:42 - mmengine - INFO - Epoch(train) [184][150/293] lr: 5.000000e-05 eta: 1:25:30 time: 0.774951 data_time: 0.106203 memory: 21676 loss_kpt: 0.000534 acc_pose: 0.879769 loss: 0.000534 2022/09/09 11:27:21 - mmengine - INFO - Epoch(train) [184][200/293] lr: 5.000000e-05 eta: 1:24:58 time: 0.786776 data_time: 0.105999 memory: 21676 loss_kpt: 0.000511 acc_pose: 0.889117 loss: 0.000511 2022/09/09 11:28:00 - mmengine - INFO - Epoch(train) [184][250/293] lr: 5.000000e-05 eta: 1:24:26 time: 0.766808 data_time: 0.104565 memory: 21676 loss_kpt: 0.000511 acc_pose: 0.856900 loss: 0.000511 2022/09/09 11:28:31 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 11:28:31 - mmengine - INFO - Saving checkpoint at 184 epochs 2022/09/09 11:29:16 - mmengine - INFO - Epoch(train) [185][50/293] lr: 5.000000e-05 eta: 1:23:21 time: 0.800132 data_time: 0.123182 memory: 21676 loss_kpt: 0.000516 acc_pose: 0.870963 loss: 0.000516 2022/09/09 11:29:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 11:29:55 - mmengine - INFO - Epoch(train) [185][100/293] lr: 5.000000e-05 eta: 1:22:49 time: 0.784693 data_time: 0.106145 memory: 21676 loss_kpt: 0.000507 acc_pose: 0.886400 loss: 0.000507 2022/09/09 11:30:34 - mmengine - INFO - Epoch(train) [185][150/293] lr: 5.000000e-05 eta: 1:22:17 time: 0.769393 data_time: 0.105641 memory: 21676 loss_kpt: 0.000509 acc_pose: 0.815733 loss: 0.000509 2022/09/09 11:31:12 - mmengine - INFO - Epoch(train) [185][200/293] lr: 5.000000e-05 eta: 1:21:44 time: 0.772613 data_time: 0.099453 memory: 21676 loss_kpt: 0.000528 acc_pose: 0.843305 loss: 0.000528 2022/09/09 11:31:51 - mmengine - INFO - Epoch(train) [185][250/293] lr: 5.000000e-05 eta: 1:21:12 time: 0.766040 data_time: 0.106922 memory: 21676 loss_kpt: 0.000515 acc_pose: 0.897983 loss: 0.000515 2022/09/09 11:32:23 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 11:32:23 - mmengine - INFO - Saving checkpoint at 185 epochs 2022/09/09 11:33:06 - mmengine - INFO - Epoch(train) [186][50/293] lr: 5.000000e-05 eta: 1:20:07 time: 0.779863 data_time: 0.112929 memory: 21676 loss_kpt: 0.000515 acc_pose: 0.835439 loss: 0.000515 2022/09/09 11:33:45 - mmengine - INFO - Epoch(train) [186][100/293] lr: 5.000000e-05 eta: 1:19:35 time: 0.768825 data_time: 0.105317 memory: 21676 loss_kpt: 0.000520 acc_pose: 0.862899 loss: 0.000520 2022/09/09 11:34:23 - mmengine - INFO - Epoch(train) [186][150/293] lr: 5.000000e-05 eta: 1:19:03 time: 0.770804 data_time: 0.101219 memory: 21676 loss_kpt: 0.000510 acc_pose: 0.850294 loss: 0.000510 2022/09/09 11:35:03 - mmengine - INFO - Epoch(train) [186][200/293] lr: 5.000000e-05 eta: 1:18:30 time: 0.783577 data_time: 0.106041 memory: 21676 loss_kpt: 0.000516 acc_pose: 0.895875 loss: 0.000516 2022/09/09 11:35:41 - mmengine - INFO - Epoch(train) [186][250/293] lr: 5.000000e-05 eta: 1:17:58 time: 0.770712 data_time: 0.108988 memory: 21676 loss_kpt: 0.000508 acc_pose: 0.874611 loss: 0.000508 2022/09/09 11:36:14 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 11:36:14 - mmengine - INFO - Saving checkpoint at 186 epochs 2022/09/09 11:36:58 - mmengine - INFO - Epoch(train) [187][50/293] lr: 5.000000e-05 eta: 1:16:54 time: 0.791214 data_time: 0.124934 memory: 21676 loss_kpt: 0.000507 acc_pose: 0.854844 loss: 0.000507 2022/09/09 11:37:37 - mmengine - INFO - Epoch(train) [187][100/293] lr: 5.000000e-05 eta: 1:16:22 time: 0.780696 data_time: 0.104904 memory: 21676 loss_kpt: 0.000505 acc_pose: 0.865975 loss: 0.000505 2022/09/09 11:38:17 - mmengine - INFO - Epoch(train) [187][150/293] lr: 5.000000e-05 eta: 1:15:49 time: 0.790429 data_time: 0.107721 memory: 21676 loss_kpt: 0.000506 acc_pose: 0.841490 loss: 0.000506 2022/09/09 11:38:56 - mmengine - INFO - Epoch(train) [187][200/293] lr: 5.000000e-05 eta: 1:15:17 time: 0.779340 data_time: 0.113717 memory: 21676 loss_kpt: 0.000521 acc_pose: 0.870962 loss: 0.000521 2022/09/09 11:39:34 - mmengine - INFO - Epoch(train) [187][250/293] lr: 5.000000e-05 eta: 1:14:45 time: 0.770747 data_time: 0.103799 memory: 21676 loss_kpt: 0.000499 acc_pose: 0.884240 loss: 0.000499 2022/09/09 11:40:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 11:40:07 - mmengine - INFO - Saving checkpoint at 187 epochs 2022/09/09 11:40:51 - mmengine - INFO - Epoch(train) [188][50/293] lr: 5.000000e-05 eta: 1:13:40 time: 0.785734 data_time: 0.118865 memory: 21676 loss_kpt: 0.000506 acc_pose: 0.874763 loss: 0.000506 2022/09/09 11:41:30 - mmengine - INFO - Epoch(train) [188][100/293] lr: 5.000000e-05 eta: 1:13:08 time: 0.785612 data_time: 0.106148 memory: 21676 loss_kpt: 0.000522 acc_pose: 0.843170 loss: 0.000522 2022/09/09 11:42:09 - mmengine - INFO - Epoch(train) [188][150/293] lr: 5.000000e-05 eta: 1:12:36 time: 0.784140 data_time: 0.105330 memory: 21676 loss_kpt: 0.000502 acc_pose: 0.860297 loss: 0.000502 2022/09/09 11:42:49 - mmengine - INFO - Epoch(train) [188][200/293] lr: 5.000000e-05 eta: 1:12:03 time: 0.786366 data_time: 0.110769 memory: 21676 loss_kpt: 0.000511 acc_pose: 0.819662 loss: 0.000511 2022/09/09 11:42:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 11:43:28 - mmengine - INFO - Epoch(train) [188][250/293] lr: 5.000000e-05 eta: 1:11:31 time: 0.779219 data_time: 0.110738 memory: 21676 loss_kpt: 0.000515 acc_pose: 0.837763 loss: 0.000515 2022/09/09 11:44:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 11:44:00 - mmengine - INFO - Saving checkpoint at 188 epochs 2022/09/09 11:44:43 - mmengine - INFO - Epoch(train) [189][50/293] lr: 5.000000e-05 eta: 1:10:27 time: 0.786458 data_time: 0.115635 memory: 21676 loss_kpt: 0.000508 acc_pose: 0.882434 loss: 0.000508 2022/09/09 11:45:22 - mmengine - INFO - Epoch(train) [189][100/293] lr: 5.000000e-05 eta: 1:09:55 time: 0.776202 data_time: 0.105405 memory: 21676 loss_kpt: 0.000522 acc_pose: 0.869332 loss: 0.000522 2022/09/09 11:46:01 - mmengine - INFO - Epoch(train) [189][150/293] lr: 5.000000e-05 eta: 1:09:22 time: 0.768654 data_time: 0.104222 memory: 21676 loss_kpt: 0.000501 acc_pose: 0.831954 loss: 0.000501 2022/09/09 11:46:40 - mmengine - INFO - Epoch(train) [189][200/293] lr: 5.000000e-05 eta: 1:08:50 time: 0.781913 data_time: 0.110099 memory: 21676 loss_kpt: 0.000527 acc_pose: 0.828373 loss: 0.000527 2022/09/09 11:47:18 - mmengine - INFO - Epoch(train) [189][250/293] lr: 5.000000e-05 eta: 1:08:17 time: 0.772556 data_time: 0.111022 memory: 21676 loss_kpt: 0.000509 acc_pose: 0.857944 loss: 0.000509 2022/09/09 11:47:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 11:47:51 - mmengine - INFO - Saving checkpoint at 189 epochs 2022/09/09 11:48:36 - mmengine - INFO - Epoch(train) [190][50/293] lr: 5.000000e-05 eta: 1:07:14 time: 0.799384 data_time: 0.122376 memory: 21676 loss_kpt: 0.000514 acc_pose: 0.859256 loss: 0.000514 2022/09/09 11:49:15 - mmengine - INFO - Epoch(train) [190][100/293] lr: 5.000000e-05 eta: 1:06:41 time: 0.788280 data_time: 0.100914 memory: 21676 loss_kpt: 0.000510 acc_pose: 0.882240 loss: 0.000510 2022/09/09 11:49:55 - mmengine - INFO - Epoch(train) [190][150/293] lr: 5.000000e-05 eta: 1:06:09 time: 0.788747 data_time: 0.107069 memory: 21676 loss_kpt: 0.000504 acc_pose: 0.875497 loss: 0.000504 2022/09/09 11:50:34 - mmengine - INFO - Epoch(train) [190][200/293] lr: 5.000000e-05 eta: 1:05:36 time: 0.785466 data_time: 0.103516 memory: 21676 loss_kpt: 0.000506 acc_pose: 0.877632 loss: 0.000506 2022/09/09 11:51:13 - mmengine - INFO - Epoch(train) [190][250/293] lr: 5.000000e-05 eta: 1:05:04 time: 0.779994 data_time: 0.107169 memory: 21676 loss_kpt: 0.000511 acc_pose: 0.867586 loss: 0.000511 2022/09/09 11:51:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 11:51:46 - mmengine - INFO - Saving checkpoint at 190 epochs 2022/09/09 11:51:59 - mmengine - INFO - Epoch(val) [190][50/407] eta: 0:00:55 time: 0.155859 data_time: 0.013745 memory: 21676 2022/09/09 11:52:07 - mmengine - INFO - Epoch(val) [190][100/407] eta: 0:00:46 time: 0.151850 data_time: 0.008534 memory: 1375 2022/09/09 11:52:14 - mmengine - INFO - Epoch(val) [190][150/407] eta: 0:00:38 time: 0.150074 data_time: 0.008970 memory: 1375 2022/09/09 11:52:22 - mmengine - INFO - Epoch(val) [190][200/407] eta: 0:00:31 time: 0.153854 data_time: 0.008463 memory: 1375 2022/09/09 11:52:30 - mmengine - INFO - Epoch(val) [190][250/407] eta: 0:00:23 time: 0.151939 data_time: 0.008526 memory: 1375 2022/09/09 11:52:37 - mmengine - INFO - Epoch(val) [190][300/407] eta: 0:00:16 time: 0.150426 data_time: 0.008350 memory: 1375 2022/09/09 11:52:45 - mmengine - INFO - Epoch(val) [190][350/407] eta: 0:00:08 time: 0.149447 data_time: 0.008869 memory: 1375 2022/09/09 11:52:52 - mmengine - INFO - Epoch(val) [190][400/407] eta: 0:00:01 time: 0.149309 data_time: 0.008431 memory: 1375 2022/09/09 11:53:29 - mmengine - INFO - Evaluating CocoMetric... 2022/09/09 11:53:43 - mmengine - INFO - Epoch(val) [190][407/407] coco/AP: 0.760161 coco/AP .5: 0.907637 coco/AP .75: 0.828187 coco/AP (M): 0.721873 coco/AP (L): 0.829422 coco/AR: 0.810406 coco/AR .5: 0.943482 coco/AR .75: 0.870749 coco/AR (M): 0.766976 coco/AR (L): 0.873058 2022/09/09 11:53:44 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220908/hrnet_w32_384/best_coco/AP_epoch_180.pth is removed 2022/09/09 11:53:47 - mmengine - INFO - The best checkpoint with 0.7602 coco/AP at 190 epoch is saved to best_coco/AP_epoch_190.pth. 2022/09/09 11:54:26 - mmengine - INFO - Epoch(train) [191][50/293] lr: 5.000000e-05 eta: 1:04:00 time: 0.785227 data_time: 0.108354 memory: 21676 loss_kpt: 0.000513 acc_pose: 0.876492 loss: 0.000513 2022/09/09 11:55:05 - mmengine - INFO - Epoch(train) [191][100/293] lr: 5.000000e-05 eta: 1:03:28 time: 0.787139 data_time: 0.100341 memory: 21676 loss_kpt: 0.000506 acc_pose: 0.891154 loss: 0.000506 2022/09/09 11:55:44 - mmengine - INFO - Epoch(train) [191][150/293] lr: 5.000000e-05 eta: 1:02:55 time: 0.777819 data_time: 0.094498 memory: 21676 loss_kpt: 0.000521 acc_pose: 0.862199 loss: 0.000521 2022/09/09 11:56:23 - mmengine - INFO - Epoch(train) [191][200/293] lr: 5.000000e-05 eta: 1:02:23 time: 0.775958 data_time: 0.095293 memory: 21676 loss_kpt: 0.000514 acc_pose: 0.840016 loss: 0.000514 2022/09/09 11:57:02 - mmengine - INFO - Epoch(train) [191][250/293] lr: 5.000000e-05 eta: 1:01:50 time: 0.780725 data_time: 0.091388 memory: 21676 loss_kpt: 0.000503 acc_pose: 0.871947 loss: 0.000503 2022/09/09 11:57:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 11:57:36 - mmengine - INFO - Saving checkpoint at 191 epochs 2022/09/09 11:58:09 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 11:58:19 - mmengine - INFO - Epoch(train) [192][50/293] lr: 5.000000e-05 eta: 1:00:47 time: 0.773389 data_time: 0.109743 memory: 21676 loss_kpt: 0.000523 acc_pose: 0.841678 loss: 0.000523 2022/09/09 11:58:58 - mmengine - INFO - Epoch(train) [192][100/293] lr: 5.000000e-05 eta: 1:00:14 time: 0.772200 data_time: 0.102698 memory: 21676 loss_kpt: 0.000509 acc_pose: 0.849267 loss: 0.000509 2022/09/09 11:59:36 - mmengine - INFO - Epoch(train) [192][150/293] lr: 5.000000e-05 eta: 0:59:41 time: 0.768755 data_time: 0.099456 memory: 21676 loss_kpt: 0.000514 acc_pose: 0.888158 loss: 0.000514 2022/09/09 12:00:18 - mmengine - INFO - Epoch(train) [192][200/293] lr: 5.000000e-05 eta: 0:59:09 time: 0.831103 data_time: 0.104504 memory: 21676 loss_kpt: 0.000514 acc_pose: 0.888517 loss: 0.000514 2022/09/09 12:00:56 - mmengine - INFO - Epoch(train) [192][250/293] lr: 5.000000e-05 eta: 0:58:37 time: 0.771668 data_time: 0.103997 memory: 21676 loss_kpt: 0.000511 acc_pose: 0.840898 loss: 0.000511 2022/09/09 12:01:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 12:01:30 - mmengine - INFO - Saving checkpoint at 192 epochs 2022/09/09 12:02:16 - mmengine - INFO - Epoch(train) [193][50/293] lr: 5.000000e-05 eta: 0:57:33 time: 0.804160 data_time: 0.106244 memory: 21676 loss_kpt: 0.000498 acc_pose: 0.847265 loss: 0.000498 2022/09/09 12:02:55 - mmengine - INFO - Epoch(train) [193][100/293] lr: 5.000000e-05 eta: 0:57:01 time: 0.792112 data_time: 0.094407 memory: 21676 loss_kpt: 0.000498 acc_pose: 0.845366 loss: 0.000498 2022/09/09 12:03:34 - mmengine - INFO - Epoch(train) [193][150/293] lr: 5.000000e-05 eta: 0:56:28 time: 0.781104 data_time: 0.097447 memory: 21676 loss_kpt: 0.000506 acc_pose: 0.909920 loss: 0.000506 2022/09/09 12:04:13 - mmengine - INFO - Epoch(train) [193][200/293] lr: 5.000000e-05 eta: 0:55:56 time: 0.769329 data_time: 0.103556 memory: 21676 loss_kpt: 0.000511 acc_pose: 0.843826 loss: 0.000511 2022/09/09 12:04:51 - mmengine - INFO - Epoch(train) [193][250/293] lr: 5.000000e-05 eta: 0:55:23 time: 0.757873 data_time: 0.098150 memory: 21676 loss_kpt: 0.000512 acc_pose: 0.845381 loss: 0.000512 2022/09/09 12:05:23 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 12:05:23 - mmengine - INFO - Saving checkpoint at 193 epochs 2022/09/09 12:06:07 - mmengine - INFO - Epoch(train) [194][50/293] lr: 5.000000e-05 eta: 0:54:20 time: 0.785205 data_time: 0.107241 memory: 21676 loss_kpt: 0.000513 acc_pose: 0.894788 loss: 0.000513 2022/09/09 12:06:46 - mmengine - INFO - Epoch(train) [194][100/293] lr: 5.000000e-05 eta: 0:53:47 time: 0.773987 data_time: 0.100850 memory: 21676 loss_kpt: 0.000502 acc_pose: 0.873948 loss: 0.000502 2022/09/09 12:07:25 - mmengine - INFO - Epoch(train) [194][150/293] lr: 5.000000e-05 eta: 0:53:14 time: 0.794252 data_time: 0.096786 memory: 21676 loss_kpt: 0.000503 acc_pose: 0.858241 loss: 0.000503 2022/09/09 12:08:04 - mmengine - INFO - Epoch(train) [194][200/293] lr: 5.000000e-05 eta: 0:52:42 time: 0.769579 data_time: 0.102103 memory: 21676 loss_kpt: 0.000510 acc_pose: 0.862788 loss: 0.000510 2022/09/09 12:08:41 - mmengine - INFO - Epoch(train) [194][250/293] lr: 5.000000e-05 eta: 0:52:09 time: 0.752737 data_time: 0.101525 memory: 21676 loss_kpt: 0.000499 acc_pose: 0.853911 loss: 0.000499 2022/09/09 12:09:14 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 12:09:14 - mmengine - INFO - Saving checkpoint at 194 epochs 2022/09/09 12:09:58 - mmengine - INFO - Epoch(train) [195][50/293] lr: 5.000000e-05 eta: 0:51:06 time: 0.795072 data_time: 0.112622 memory: 21676 loss_kpt: 0.000507 acc_pose: 0.879971 loss: 0.000507 2022/09/09 12:10:37 - mmengine - INFO - Epoch(train) [195][100/293] lr: 5.000000e-05 eta: 0:50:33 time: 0.770335 data_time: 0.097012 memory: 21676 loss_kpt: 0.000492 acc_pose: 0.880838 loss: 0.000492 2022/09/09 12:11:16 - mmengine - INFO - Epoch(train) [195][150/293] lr: 5.000000e-05 eta: 0:50:01 time: 0.771866 data_time: 0.092107 memory: 21676 loss_kpt: 0.000516 acc_pose: 0.868618 loss: 0.000516 2022/09/09 12:11:22 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 12:11:54 - mmengine - INFO - Epoch(train) [195][200/293] lr: 5.000000e-05 eta: 0:49:28 time: 0.770649 data_time: 0.097548 memory: 21676 loss_kpt: 0.000519 acc_pose: 0.872313 loss: 0.000519 2022/09/09 12:12:33 - mmengine - INFO - Epoch(train) [195][250/293] lr: 5.000000e-05 eta: 0:48:55 time: 0.772081 data_time: 0.098898 memory: 21676 loss_kpt: 0.000505 acc_pose: 0.843880 loss: 0.000505 2022/09/09 12:13:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 12:13:05 - mmengine - INFO - Saving checkpoint at 195 epochs 2022/09/09 12:13:49 - mmengine - INFO - Epoch(train) [196][50/293] lr: 5.000000e-05 eta: 0:47:52 time: 0.782921 data_time: 0.105619 memory: 21676 loss_kpt: 0.000499 acc_pose: 0.859227 loss: 0.000499 2022/09/09 12:14:27 - mmengine - INFO - Epoch(train) [196][100/293] lr: 5.000000e-05 eta: 0:47:19 time: 0.769522 data_time: 0.096519 memory: 21676 loss_kpt: 0.000500 acc_pose: 0.832428 loss: 0.000500 2022/09/09 12:15:06 - mmengine - INFO - Epoch(train) [196][150/293] lr: 5.000000e-05 eta: 0:46:47 time: 0.777004 data_time: 0.099754 memory: 21676 loss_kpt: 0.000514 acc_pose: 0.864144 loss: 0.000514 2022/09/09 12:15:44 - mmengine - INFO - Epoch(train) [196][200/293] lr: 5.000000e-05 eta: 0:46:14 time: 0.760005 data_time: 0.096046 memory: 21676 loss_kpt: 0.000516 acc_pose: 0.838688 loss: 0.000516 2022/09/09 12:16:22 - mmengine - INFO - Epoch(train) [196][250/293] lr: 5.000000e-05 eta: 0:45:41 time: 0.753941 data_time: 0.095052 memory: 21676 loss_kpt: 0.000511 acc_pose: 0.862109 loss: 0.000511 2022/09/09 12:16:54 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 12:16:54 - mmengine - INFO - Saving checkpoint at 196 epochs 2022/09/09 12:17:39 - mmengine - INFO - Epoch(train) [197][50/293] lr: 5.000000e-05 eta: 0:44:38 time: 0.790752 data_time: 0.108715 memory: 21676 loss_kpt: 0.000513 acc_pose: 0.871234 loss: 0.000513 2022/09/09 12:18:18 - mmengine - INFO - Epoch(train) [197][100/293] lr: 5.000000e-05 eta: 0:44:06 time: 0.775308 data_time: 0.100620 memory: 21676 loss_kpt: 0.000507 acc_pose: 0.820000 loss: 0.000507 2022/09/09 12:18:56 - mmengine - INFO - Epoch(train) [197][150/293] lr: 5.000000e-05 eta: 0:43:33 time: 0.775350 data_time: 0.097437 memory: 21676 loss_kpt: 0.000508 acc_pose: 0.922234 loss: 0.000508 2022/09/09 12:19:36 - mmengine - INFO - Epoch(train) [197][200/293] lr: 5.000000e-05 eta: 0:43:00 time: 0.785032 data_time: 0.099038 memory: 21676 loss_kpt: 0.000512 acc_pose: 0.878094 loss: 0.000512 2022/09/09 12:20:14 - mmengine - INFO - Epoch(train) [197][250/293] lr: 5.000000e-05 eta: 0:42:28 time: 0.777692 data_time: 0.095330 memory: 21676 loss_kpt: 0.000496 acc_pose: 0.893870 loss: 0.000496 2022/09/09 12:20:47 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 12:20:47 - mmengine - INFO - Saving checkpoint at 197 epochs 2022/09/09 12:21:32 - mmengine - INFO - Epoch(train) [198][50/293] lr: 5.000000e-05 eta: 0:41:25 time: 0.797009 data_time: 0.104787 memory: 21676 loss_kpt: 0.000508 acc_pose: 0.877204 loss: 0.000508 2022/09/09 12:22:11 - mmengine - INFO - Epoch(train) [198][100/293] lr: 5.000000e-05 eta: 0:40:52 time: 0.787320 data_time: 0.096403 memory: 21676 loss_kpt: 0.000498 acc_pose: 0.852740 loss: 0.000498 2022/09/09 12:22:50 - mmengine - INFO - Epoch(train) [198][150/293] lr: 5.000000e-05 eta: 0:40:19 time: 0.776401 data_time: 0.098651 memory: 21676 loss_kpt: 0.000514 acc_pose: 0.826074 loss: 0.000514 2022/09/09 12:23:29 - mmengine - INFO - Epoch(train) [198][200/293] lr: 5.000000e-05 eta: 0:39:47 time: 0.778466 data_time: 0.101141 memory: 21676 loss_kpt: 0.000505 acc_pose: 0.887151 loss: 0.000505 2022/09/09 12:24:08 - mmengine - INFO - Epoch(train) [198][250/293] lr: 5.000000e-05 eta: 0:39:14 time: 0.778494 data_time: 0.098334 memory: 21676 loss_kpt: 0.000525 acc_pose: 0.890831 loss: 0.000525 2022/09/09 12:24:31 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 12:24:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 12:24:41 - mmengine - INFO - Saving checkpoint at 198 epochs 2022/09/09 12:25:25 - mmengine - INFO - Epoch(train) [199][50/293] lr: 5.000000e-05 eta: 0:38:11 time: 0.795635 data_time: 0.111277 memory: 21676 loss_kpt: 0.000505 acc_pose: 0.869993 loss: 0.000505 2022/09/09 12:26:05 - mmengine - INFO - Epoch(train) [199][100/293] lr: 5.000000e-05 eta: 0:37:38 time: 0.789241 data_time: 0.096496 memory: 21676 loss_kpt: 0.000502 acc_pose: 0.856757 loss: 0.000502 2022/09/09 12:26:43 - mmengine - INFO - Epoch(train) [199][150/293] lr: 5.000000e-05 eta: 0:37:06 time: 0.771569 data_time: 0.093733 memory: 21676 loss_kpt: 0.000511 acc_pose: 0.859815 loss: 0.000511 2022/09/09 12:27:22 - mmengine - INFO - Epoch(train) [199][200/293] lr: 5.000000e-05 eta: 0:36:33 time: 0.775442 data_time: 0.097029 memory: 21676 loss_kpt: 0.000507 acc_pose: 0.910474 loss: 0.000507 2022/09/09 12:28:00 - mmengine - INFO - Epoch(train) [199][250/293] lr: 5.000000e-05 eta: 0:36:00 time: 0.756891 data_time: 0.092868 memory: 21676 loss_kpt: 0.000505 acc_pose: 0.883779 loss: 0.000505 2022/09/09 12:28:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 12:28:32 - mmengine - INFO - Saving checkpoint at 199 epochs 2022/09/09 12:29:16 - mmengine - INFO - Epoch(train) [200][50/293] lr: 5.000000e-05 eta: 0:34:57 time: 0.787098 data_time: 0.110335 memory: 21676 loss_kpt: 0.000498 acc_pose: 0.887716 loss: 0.000498 2022/09/09 12:29:55 - mmengine - INFO - Epoch(train) [200][100/293] lr: 5.000000e-05 eta: 0:34:25 time: 0.781688 data_time: 0.094685 memory: 21676 loss_kpt: 0.000514 acc_pose: 0.875997 loss: 0.000514 2022/09/09 12:30:34 - mmengine - INFO - Epoch(train) [200][150/293] lr: 5.000000e-05 eta: 0:33:52 time: 0.776348 data_time: 0.096748 memory: 21676 loss_kpt: 0.000515 acc_pose: 0.857857 loss: 0.000515 2022/09/09 12:31:12 - mmengine - INFO - Epoch(train) [200][200/293] lr: 5.000000e-05 eta: 0:33:19 time: 0.763861 data_time: 0.096270 memory: 21676 loss_kpt: 0.000502 acc_pose: 0.880735 loss: 0.000502 2022/09/09 12:31:50 - mmengine - INFO - Epoch(train) [200][250/293] lr: 5.000000e-05 eta: 0:32:46 time: 0.759116 data_time: 0.097629 memory: 21676 loss_kpt: 0.000507 acc_pose: 0.870216 loss: 0.000507 2022/09/09 12:32:22 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 12:32:22 - mmengine - INFO - Saving checkpoint at 200 epochs 2022/09/09 12:32:35 - mmengine - INFO - Epoch(val) [200][50/407] eta: 0:00:56 time: 0.158828 data_time: 0.014349 memory: 21676 2022/09/09 12:32:42 - mmengine - INFO - Epoch(val) [200][100/407] eta: 0:00:48 time: 0.156559 data_time: 0.009162 memory: 1375 2022/09/09 12:32:50 - mmengine - INFO - Epoch(val) [200][150/407] eta: 0:00:39 time: 0.151752 data_time: 0.008958 memory: 1375 2022/09/09 12:32:58 - mmengine - INFO - Epoch(val) [200][200/407] eta: 0:00:31 time: 0.152385 data_time: 0.009041 memory: 1375 2022/09/09 12:33:05 - mmengine - INFO - Epoch(val) [200][250/407] eta: 0:00:24 time: 0.157791 data_time: 0.009145 memory: 1375 2022/09/09 12:33:13 - mmengine - INFO - Epoch(val) [200][300/407] eta: 0:00:16 time: 0.152327 data_time: 0.009075 memory: 1375 2022/09/09 12:33:21 - mmengine - INFO - Epoch(val) [200][350/407] eta: 0:00:08 time: 0.153383 data_time: 0.009701 memory: 1375 2022/09/09 12:33:28 - mmengine - INFO - Epoch(val) [200][400/407] eta: 0:00:01 time: 0.148478 data_time: 0.007916 memory: 1375 2022/09/09 12:34:04 - mmengine - INFO - Evaluating CocoMetric... 2022/09/09 12:34:18 - mmengine - INFO - Epoch(val) [200][407/407] coco/AP: 0.760319 coco/AP .5: 0.907752 coco/AP .75: 0.825496 coco/AP (M): 0.722145 coco/AP (L): 0.829203 coco/AR: 0.810170 coco/AR .5: 0.942223 coco/AR .75: 0.868073 coco/AR (M): 0.767604 coco/AR (L): 0.872166 2022/09/09 12:34:18 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220908/hrnet_w32_384/best_coco/AP_epoch_190.pth is removed 2022/09/09 12:34:21 - mmengine - INFO - The best checkpoint with 0.7603 coco/AP at 200 epoch is saved to best_coco/AP_epoch_200.pth. 2022/09/09 12:35:00 - mmengine - INFO - Epoch(train) [201][50/293] lr: 5.000000e-06 eta: 0:31:44 time: 0.785234 data_time: 0.104860 memory: 21676 loss_kpt: 0.000513 acc_pose: 0.883620 loss: 0.000513 2022/09/09 12:35:38 - mmengine - INFO - Epoch(train) [201][100/293] lr: 5.000000e-06 eta: 0:31:11 time: 0.768333 data_time: 0.096622 memory: 21676 loss_kpt: 0.000517 acc_pose: 0.887099 loss: 0.000517 2022/09/09 12:36:16 - mmengine - INFO - Epoch(train) [201][150/293] lr: 5.000000e-06 eta: 0:30:38 time: 0.760044 data_time: 0.096705 memory: 21676 loss_kpt: 0.000499 acc_pose: 0.865833 loss: 0.000499 2022/09/09 12:36:54 - mmengine - INFO - Epoch(train) [201][200/293] lr: 5.000000e-06 eta: 0:30:05 time: 0.752654 data_time: 0.099286 memory: 21676 loss_kpt: 0.000510 acc_pose: 0.877424 loss: 0.000510 2022/09/09 12:37:32 - mmengine - INFO - Epoch(train) [201][250/293] lr: 5.000000e-06 eta: 0:29:32 time: 0.763115 data_time: 0.093316 memory: 21676 loss_kpt: 0.000521 acc_pose: 0.882025 loss: 0.000521 2022/09/09 12:38:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 12:38:05 - mmengine - INFO - Saving checkpoint at 201 epochs 2022/09/09 12:38:48 - mmengine - INFO - Epoch(train) [202][50/293] lr: 5.000000e-06 eta: 0:28:30 time: 0.760186 data_time: 0.108655 memory: 21676 loss_kpt: 0.000507 acc_pose: 0.869500 loss: 0.000507 2022/09/09 12:39:26 - mmengine - INFO - Epoch(train) [202][100/293] lr: 5.000000e-06 eta: 0:27:57 time: 0.769460 data_time: 0.097409 memory: 21676 loss_kpt: 0.000502 acc_pose: 0.856680 loss: 0.000502 2022/09/09 12:39:31 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 12:40:04 - mmengine - INFO - Epoch(train) [202][150/293] lr: 5.000000e-06 eta: 0:27:24 time: 0.762294 data_time: 0.097427 memory: 21676 loss_kpt: 0.000521 acc_pose: 0.852368 loss: 0.000521 2022/09/09 12:40:42 - mmengine - INFO - Epoch(train) [202][200/293] lr: 5.000000e-06 eta: 0:26:51 time: 0.761046 data_time: 0.097470 memory: 21676 loss_kpt: 0.000503 acc_pose: 0.875466 loss: 0.000503 2022/09/09 12:41:20 - mmengine - INFO - Epoch(train) [202][250/293] lr: 5.000000e-06 eta: 0:26:18 time: 0.758399 data_time: 0.098628 memory: 21676 loss_kpt: 0.000511 acc_pose: 0.831432 loss: 0.000511 2022/09/09 12:41:52 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 12:41:53 - mmengine - INFO - Saving checkpoint at 202 epochs 2022/09/09 12:42:36 - mmengine - INFO - Epoch(train) [203][50/293] lr: 5.000000e-06 eta: 0:25:16 time: 0.788049 data_time: 0.111336 memory: 21676 loss_kpt: 0.000505 acc_pose: 0.886312 loss: 0.000505 2022/09/09 12:43:14 - mmengine - INFO - Epoch(train) [203][100/293] lr: 5.000000e-06 eta: 0:24:43 time: 0.773024 data_time: 0.103452 memory: 21676 loss_kpt: 0.000505 acc_pose: 0.878786 loss: 0.000505 2022/09/09 12:43:53 - mmengine - INFO - Epoch(train) [203][150/293] lr: 5.000000e-06 eta: 0:24:10 time: 0.772422 data_time: 0.106313 memory: 21676 loss_kpt: 0.000497 acc_pose: 0.824466 loss: 0.000497 2022/09/09 12:44:32 - mmengine - INFO - Epoch(train) [203][200/293] lr: 5.000000e-06 eta: 0:23:38 time: 0.782751 data_time: 0.106657 memory: 21676 loss_kpt: 0.000512 acc_pose: 0.881667 loss: 0.000512 2022/09/09 12:45:10 - mmengine - INFO - Epoch(train) [203][250/293] lr: 5.000000e-06 eta: 0:23:05 time: 0.754976 data_time: 0.098186 memory: 21676 loss_kpt: 0.000496 acc_pose: 0.855553 loss: 0.000496 2022/09/09 12:45:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 12:45:42 - mmengine - INFO - Saving checkpoint at 203 epochs 2022/09/09 12:46:25 - mmengine - INFO - Epoch(train) [204][50/293] lr: 5.000000e-06 eta: 0:22:02 time: 0.780963 data_time: 0.107973 memory: 21676 loss_kpt: 0.000505 acc_pose: 0.888333 loss: 0.000505 2022/09/09 12:47:04 - mmengine - INFO - Epoch(train) [204][100/293] lr: 5.000000e-06 eta: 0:21:29 time: 0.782621 data_time: 0.097032 memory: 21676 loss_kpt: 0.000505 acc_pose: 0.862742 loss: 0.000505 2022/09/09 12:47:44 - mmengine - INFO - Epoch(train) [204][150/293] lr: 5.000000e-06 eta: 0:20:57 time: 0.802055 data_time: 0.104582 memory: 21676 loss_kpt: 0.000522 acc_pose: 0.846804 loss: 0.000522 2022/09/09 12:48:24 - mmengine - INFO - Epoch(train) [204][200/293] lr: 5.000000e-06 eta: 0:20:24 time: 0.790918 data_time: 0.098530 memory: 21676 loss_kpt: 0.000504 acc_pose: 0.869779 loss: 0.000504 2022/09/09 12:49:02 - mmengine - INFO - Epoch(train) [204][250/293] lr: 5.000000e-06 eta: 0:19:51 time: 0.770719 data_time: 0.097515 memory: 21676 loss_kpt: 0.000503 acc_pose: 0.856289 loss: 0.000503 2022/09/09 12:49:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 12:49:35 - mmengine - INFO - Saving checkpoint at 204 epochs 2022/09/09 12:50:20 - mmengine - INFO - Epoch(train) [205][50/293] lr: 5.000000e-06 eta: 0:18:49 time: 0.789940 data_time: 0.108017 memory: 21676 loss_kpt: 0.000497 acc_pose: 0.870585 loss: 0.000497 2022/09/09 12:50:59 - mmengine - INFO - Epoch(train) [205][100/293] lr: 5.000000e-06 eta: 0:18:16 time: 0.775788 data_time: 0.099333 memory: 21676 loss_kpt: 0.000505 acc_pose: 0.880278 loss: 0.000505 2022/09/09 12:51:38 - mmengine - INFO - Epoch(train) [205][150/293] lr: 5.000000e-06 eta: 0:17:43 time: 0.781889 data_time: 0.099993 memory: 21676 loss_kpt: 0.000507 acc_pose: 0.875816 loss: 0.000507 2022/09/09 12:52:17 - mmengine - INFO - Epoch(train) [205][200/293] lr: 5.000000e-06 eta: 0:17:10 time: 0.783129 data_time: 0.100880 memory: 21676 loss_kpt: 0.000505 acc_pose: 0.884661 loss: 0.000505 2022/09/09 12:52:39 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 12:52:56 - mmengine - INFO - Epoch(train) [205][250/293] lr: 5.000000e-06 eta: 0:16:37 time: 0.778694 data_time: 0.102422 memory: 21676 loss_kpt: 0.000500 acc_pose: 0.874561 loss: 0.000500 2022/09/09 12:53:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 12:53:30 - mmengine - INFO - Saving checkpoint at 205 epochs 2022/09/09 12:54:14 - mmengine - INFO - Epoch(train) [206][50/293] lr: 5.000000e-06 eta: 0:15:35 time: 0.782136 data_time: 0.106991 memory: 21676 loss_kpt: 0.000500 acc_pose: 0.880592 loss: 0.000500 2022/09/09 12:54:53 - mmengine - INFO - Epoch(train) [206][100/293] lr: 5.000000e-06 eta: 0:15:02 time: 0.777487 data_time: 0.104573 memory: 21676 loss_kpt: 0.000501 acc_pose: 0.887163 loss: 0.000501 2022/09/09 12:55:32 - mmengine - INFO - Epoch(train) [206][150/293] lr: 5.000000e-06 eta: 0:14:29 time: 0.776714 data_time: 0.102452 memory: 21676 loss_kpt: 0.000493 acc_pose: 0.862516 loss: 0.000493 2022/09/09 12:56:11 - mmengine - INFO - Epoch(train) [206][200/293] lr: 5.000000e-06 eta: 0:13:56 time: 0.782715 data_time: 0.098603 memory: 21676 loss_kpt: 0.000503 acc_pose: 0.880605 loss: 0.000503 2022/09/09 12:56:50 - mmengine - INFO - Epoch(train) [206][250/293] lr: 5.000000e-06 eta: 0:13:23 time: 0.775835 data_time: 0.109384 memory: 21676 loss_kpt: 0.000505 acc_pose: 0.860852 loss: 0.000505 2022/09/09 12:57:22 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 12:57:22 - mmengine - INFO - Saving checkpoint at 206 epochs 2022/09/09 12:58:07 - mmengine - INFO - Epoch(train) [207][50/293] lr: 5.000000e-06 eta: 0:12:21 time: 0.787149 data_time: 0.106891 memory: 21676 loss_kpt: 0.000502 acc_pose: 0.867129 loss: 0.000502 2022/09/09 12:58:46 - mmengine - INFO - Epoch(train) [207][100/293] lr: 5.000000e-06 eta: 0:11:48 time: 0.783693 data_time: 0.103721 memory: 21676 loss_kpt: 0.000494 acc_pose: 0.868975 loss: 0.000494 2022/09/09 12:59:26 - mmengine - INFO - Epoch(train) [207][150/293] lr: 5.000000e-06 eta: 0:11:15 time: 0.785786 data_time: 0.105100 memory: 21676 loss_kpt: 0.000505 acc_pose: 0.849606 loss: 0.000505 2022/09/09 13:00:05 - mmengine - INFO - Epoch(train) [207][200/293] lr: 5.000000e-06 eta: 0:10:42 time: 0.781294 data_time: 0.101346 memory: 21676 loss_kpt: 0.000513 acc_pose: 0.845354 loss: 0.000513 2022/09/09 13:00:43 - mmengine - INFO - Epoch(train) [207][250/293] lr: 5.000000e-06 eta: 0:10:09 time: 0.773011 data_time: 0.100254 memory: 21676 loss_kpt: 0.000502 acc_pose: 0.851762 loss: 0.000502 2022/09/09 13:01:16 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 13:01:16 - mmengine - INFO - Saving checkpoint at 207 epochs 2022/09/09 13:02:00 - mmengine - INFO - Epoch(train) [208][50/293] lr: 5.000000e-06 eta: 0:09:08 time: 0.786339 data_time: 0.112351 memory: 21676 loss_kpt: 0.000498 acc_pose: 0.886147 loss: 0.000498 2022/09/09 13:02:39 - mmengine - INFO - Epoch(train) [208][100/293] lr: 5.000000e-06 eta: 0:08:35 time: 0.772485 data_time: 0.103429 memory: 21676 loss_kpt: 0.000494 acc_pose: 0.872293 loss: 0.000494 2022/09/09 13:03:18 - mmengine - INFO - Epoch(train) [208][150/293] lr: 5.000000e-06 eta: 0:08:02 time: 0.785986 data_time: 0.097776 memory: 21676 loss_kpt: 0.000507 acc_pose: 0.861918 loss: 0.000507 2022/09/09 13:03:57 - mmengine - INFO - Epoch(train) [208][200/293] lr: 5.000000e-06 eta: 0:07:29 time: 0.772131 data_time: 0.095751 memory: 21676 loss_kpt: 0.000509 acc_pose: 0.846393 loss: 0.000509 2022/09/09 13:04:36 - mmengine - INFO - Epoch(train) [208][250/293] lr: 5.000000e-06 eta: 0:06:56 time: 0.779486 data_time: 0.097563 memory: 21676 loss_kpt: 0.000517 acc_pose: 0.910130 loss: 0.000517 2022/09/09 13:05:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 13:05:08 - mmengine - INFO - Saving checkpoint at 208 epochs 2022/09/09 13:05:52 - mmengine - INFO - Epoch(train) [209][50/293] lr: 5.000000e-06 eta: 0:05:54 time: 0.794002 data_time: 0.108089 memory: 21676 loss_kpt: 0.000510 acc_pose: 0.859570 loss: 0.000510 2022/09/09 13:05:57 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 13:06:31 - mmengine - INFO - Epoch(train) [209][100/293] lr: 5.000000e-06 eta: 0:05:21 time: 0.787603 data_time: 0.095819 memory: 21676 loss_kpt: 0.000505 acc_pose: 0.875431 loss: 0.000505 2022/09/09 13:07:10 - mmengine - INFO - Epoch(train) [209][150/293] lr: 5.000000e-06 eta: 0:04:48 time: 0.778238 data_time: 0.100270 memory: 21676 loss_kpt: 0.000507 acc_pose: 0.890648 loss: 0.000507 2022/09/09 13:07:48 - mmengine - INFO - Epoch(train) [209][200/293] lr: 5.000000e-06 eta: 0:04:15 time: 0.748339 data_time: 0.100239 memory: 21676 loss_kpt: 0.000519 acc_pose: 0.879496 loss: 0.000519 2022/09/09 13:08:26 - mmengine - INFO - Epoch(train) [209][250/293] lr: 5.000000e-06 eta: 0:03:42 time: 0.761043 data_time: 0.094095 memory: 21676 loss_kpt: 0.000505 acc_pose: 0.839969 loss: 0.000505 2022/09/09 13:08:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 13:08:59 - mmengine - INFO - Saving checkpoint at 209 epochs 2022/09/09 13:09:43 - mmengine - INFO - Epoch(train) [210][50/293] lr: 5.000000e-06 eta: 0:02:40 time: 0.791229 data_time: 0.105909 memory: 21676 loss_kpt: 0.000509 acc_pose: 0.887535 loss: 0.000509 2022/09/09 13:10:22 - mmengine - INFO - Epoch(train) [210][100/293] lr: 5.000000e-06 eta: 0:02:07 time: 0.771801 data_time: 0.098625 memory: 21676 loss_kpt: 0.000507 acc_pose: 0.850145 loss: 0.000507 2022/09/09 13:11:01 - mmengine - INFO - Epoch(train) [210][150/293] lr: 5.000000e-06 eta: 0:01:34 time: 0.787426 data_time: 0.103368 memory: 21676 loss_kpt: 0.000507 acc_pose: 0.897446 loss: 0.000507 2022/09/09 13:11:40 - mmengine - INFO - Epoch(train) [210][200/293] lr: 5.000000e-06 eta: 0:01:01 time: 0.781444 data_time: 0.096346 memory: 21676 loss_kpt: 0.000495 acc_pose: 0.869843 loss: 0.000495 2022/09/09 13:12:19 - mmengine - INFO - Epoch(train) [210][250/293] lr: 5.000000e-06 eta: 0:00:28 time: 0.771698 data_time: 0.094255 memory: 21676 loss_kpt: 0.000501 acc_pose: 0.899915 loss: 0.000501 2022/09/09 13:12:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_8xb64-210e_coco-384x288_20220908_230625 2022/09/09 13:12:51 - mmengine - INFO - Saving checkpoint at 210 epochs 2022/09/09 13:13:03 - mmengine - INFO - Epoch(val) [210][50/407] eta: 0:00:56 time: 0.157446 data_time: 0.014160 memory: 21676 2022/09/09 13:13:11 - mmengine - INFO - Epoch(val) [210][100/407] eta: 0:00:47 time: 0.153864 data_time: 0.008959 memory: 1375 2022/09/09 13:13:19 - mmengine - INFO - Epoch(val) [210][150/407] eta: 0:00:40 time: 0.157263 data_time: 0.009476 memory: 1375 2022/09/09 13:13:27 - mmengine - INFO - Epoch(val) [210][200/407] eta: 0:00:31 time: 0.153650 data_time: 0.011046 memory: 1375 2022/09/09 13:13:34 - mmengine - INFO - Epoch(val) [210][250/407] eta: 0:00:23 time: 0.150969 data_time: 0.008365 memory: 1375 2022/09/09 13:13:42 - mmengine - INFO - Epoch(val) [210][300/407] eta: 0:00:16 time: 0.151453 data_time: 0.009132 memory: 1375 2022/09/09 13:13:49 - mmengine - INFO - Epoch(val) [210][350/407] eta: 0:00:08 time: 0.151602 data_time: 0.009238 memory: 1375 2022/09/09 13:13:57 - mmengine - INFO - Epoch(val) [210][400/407] eta: 0:00:01 time: 0.150040 data_time: 0.008974 memory: 1375 2022/09/09 13:14:33 - mmengine - INFO - Evaluating CocoMetric... 2022/09/09 13:14:47 - mmengine - INFO - Epoch(val) [210][407/407] coco/AP: 0.760870 coco/AP .5: 0.908413 coco/AP .75: 0.826271 coco/AP (M): 0.722878 coco/AP (L): 0.829364 coco/AR: 0.811004 coco/AR .5: 0.944270 coco/AR .75: 0.869805 coco/AR (M): 0.768506 coco/AR (L): 0.872650 2022/09/09 13:14:47 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220908/hrnet_w32_384/best_coco/AP_epoch_200.pth is removed 2022/09/09 13:14:50 - mmengine - INFO - The best checkpoint with 0.7609 coco/AP at 210 epoch is saved to best_coco/AP_epoch_210.pth.