2022/09/13 10:20:51 - 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: 628349110 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 ------------------------------------------------------------ 2022/09/13 10:20:53 - 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='UDPHeatmap', 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='UDPHeatmap', input_size=(288, 384), heatmap_size=(72, 96), sigma=3)), test_cfg=dict(flip_test=True, flip_mode='heatmap', shift_heatmap=False)) dataset_type = 'CocoDataset' data_mode = 'topdown' data_root = 'data/coco/' train_pipeline = [ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='RandomFlip', direction='horizontal'), dict(type='RandomHalfBody'), dict(type='RandomBBoxTransform'), dict(type='TopdownAffine', input_size=(288, 384), use_udp=True), dict( type='GenerateTarget', target_type='heatmap', encoder=dict( type='UDPHeatmap', 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), use_udp=True), 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), use_udp=True), dict( type='GenerateTarget', target_type='heatmap', encoder=dict( type='UDPHeatmap', 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), use_udp=True), 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), use_udp=True), 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/20220913/udp_w32_384_v1/' 2022/09/13 10:21:29 - 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. 2022/09/13 10:21:29 - 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. 2022/09/13 10:21:29 - 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. 2022/09/13 10:21:29 - 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. 2022/09/13 10:21:29 - 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. 2022/09/13 10:21:29 - 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. 2022/09/13 10:21:29 - 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. 2022/09/13 10:21:29 - 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. 2022/09/13 10:21:32 - mmengine - WARNING - Failed to search registry with scope "mmpose" in the "data sampler" registry tree. As a workaround, the current "data sampler" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmpose" is a correct scope, or whether the registry is initialized. 2022/09/13 10:21:35 - 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. 2022/09/13 10:21:36 - 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. 2022/09/13 10:21:36 - 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 2022/09/13 10:21:51 - mmengine - INFO - Checkpoints will be saved to /mnt/lustre/liqikai/work_dirs/20220913/udp_w32_384_v1 by HardDiskBackend. 2022/09/13 10:23:50 - mmengine - INFO - Epoch(train) [1][50/293] lr: 4.954910e-05 eta: 1 day, 16:54:28 time: 2.395394 data_time: 1.089534 memory: 21676 loss_kpt: 0.002232 acc_pose: 0.163800 loss: 0.002232 2022/09/13 10:25:04 - mmengine - INFO - Epoch(train) [1][100/293] lr: 9.959920e-05 eta: 1 day, 9:05:21 time: 1.482874 data_time: 0.782803 memory: 21676 loss_kpt: 0.001889 acc_pose: 0.324224 loss: 0.001889 2022/09/13 10:26:08 - mmengine - INFO - Epoch(train) [1][150/293] lr: 1.496493e-04 eta: 1 day, 5:17:55 time: 1.276943 data_time: 0.381721 memory: 21676 loss_kpt: 0.001550 acc_pose: 0.504152 loss: 0.001550 2022/09/13 10:27:03 - mmengine - INFO - Epoch(train) [1][200/293] lr: 1.996994e-04 eta: 1 day, 2:38:38 time: 1.100676 data_time: 0.089399 memory: 21676 loss_kpt: 0.001332 acc_pose: 0.584857 loss: 0.001332 2022/09/13 10:27:53 - mmengine - INFO - Epoch(train) [1][250/293] lr: 2.497495e-04 eta: 1 day, 0:41:44 time: 0.998096 data_time: 0.103146 memory: 21676 loss_kpt: 0.001254 acc_pose: 0.572192 loss: 0.001254 2022/09/13 10:28:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 10:28:27 - mmengine - INFO - Saving checkpoint at 1 epochs 2022/09/13 10:29:11 - mmengine - INFO - Epoch(train) [2][50/293] lr: 3.428427e-04 eta: 19:55:04 time: 0.785189 data_time: 0.110945 memory: 21676 loss_kpt: 0.001119 acc_pose: 0.636401 loss: 0.001119 2022/09/13 10:29:50 - mmengine - INFO - Epoch(train) [2][100/293] lr: 3.928928e-04 eta: 19:03:28 time: 0.781370 data_time: 0.099968 memory: 21676 loss_kpt: 0.001074 acc_pose: 0.655335 loss: 0.001074 2022/09/13 10:30:28 - mmengine - INFO - Epoch(train) [2][150/293] lr: 4.429429e-04 eta: 18:21:49 time: 0.767860 data_time: 0.104082 memory: 21676 loss_kpt: 0.001100 acc_pose: 0.606412 loss: 0.001100 2022/09/13 10:31:07 - mmengine - INFO - Epoch(train) [2][200/293] lr: 4.929930e-04 eta: 17:48:53 time: 0.771749 data_time: 0.102954 memory: 21676 loss_kpt: 0.001045 acc_pose: 0.695807 loss: 0.001045 2022/09/13 10:31:45 - mmengine - INFO - Epoch(train) [2][250/293] lr: 5.000000e-04 eta: 17:21:45 time: 0.770278 data_time: 0.092509 memory: 21676 loss_kpt: 0.001037 acc_pose: 0.638510 loss: 0.001037 2022/09/13 10:32:18 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 10:32:18 - mmengine - INFO - Saving checkpoint at 2 epochs 2022/09/13 10:33:02 - mmengine - INFO - Epoch(train) [3][50/293] lr: 5.000000e-04 eta: 15:50:34 time: 0.783305 data_time: 0.108080 memory: 21676 loss_kpt: 0.000986 acc_pose: 0.686984 loss: 0.000986 2022/09/13 10:33:40 - mmengine - INFO - Epoch(train) [3][100/293] lr: 5.000000e-04 eta: 15:36:49 time: 0.761321 data_time: 0.098557 memory: 21676 loss_kpt: 0.000969 acc_pose: 0.689340 loss: 0.000969 2022/09/13 10:34:18 - mmengine - INFO - Epoch(train) [3][150/293] lr: 5.000000e-04 eta: 15:25:02 time: 0.763710 data_time: 0.097011 memory: 21676 loss_kpt: 0.000964 acc_pose: 0.667464 loss: 0.000964 2022/09/13 10:34:57 - mmengine - INFO - Epoch(train) [3][200/293] lr: 5.000000e-04 eta: 15:15:27 time: 0.775941 data_time: 0.100125 memory: 21676 loss_kpt: 0.000979 acc_pose: 0.694421 loss: 0.000979 2022/09/13 10:35:36 - mmengine - INFO - Epoch(train) [3][250/293] lr: 5.000000e-04 eta: 15:06:20 time: 0.766160 data_time: 0.099238 memory: 21676 loss_kpt: 0.000941 acc_pose: 0.722881 loss: 0.000941 2022/09/13 10:36:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 10:36:08 - mmengine - INFO - Saving checkpoint at 3 epochs 2022/09/13 10:36:52 - mmengine - INFO - Epoch(train) [4][50/293] lr: 5.000000e-04 eta: 14:16:58 time: 0.783907 data_time: 0.113800 memory: 21676 loss_kpt: 0.000927 acc_pose: 0.719049 loss: 0.000927 2022/09/13 10:37:31 - mmengine - INFO - Epoch(train) [4][100/293] lr: 5.000000e-04 eta: 14:12:15 time: 0.770620 data_time: 0.110361 memory: 21676 loss_kpt: 0.000922 acc_pose: 0.710775 loss: 0.000922 2022/09/13 10:37:47 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 10:38:09 - mmengine - INFO - Epoch(train) [4][150/293] lr: 5.000000e-04 eta: 14:07:41 time: 0.765552 data_time: 0.104401 memory: 21676 loss_kpt: 0.000894 acc_pose: 0.716038 loss: 0.000894 2022/09/13 10:38:47 - mmengine - INFO - Epoch(train) [4][200/293] lr: 5.000000e-04 eta: 14:03:34 time: 0.767625 data_time: 0.101242 memory: 21676 loss_kpt: 0.000887 acc_pose: 0.707708 loss: 0.000887 2022/09/13 10:39:25 - mmengine - INFO - Epoch(train) [4][250/293] lr: 5.000000e-04 eta: 13:59:30 time: 0.761832 data_time: 0.105217 memory: 21676 loss_kpt: 0.000880 acc_pose: 0.757387 loss: 0.000880 2022/09/13 10:39:58 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 10:39:58 - mmengine - INFO - Saving checkpoint at 4 epochs 2022/09/13 10:40:43 - mmengine - INFO - Epoch(train) [5][50/293] lr: 5.000000e-04 eta: 13:27:04 time: 0.793886 data_time: 0.111985 memory: 21676 loss_kpt: 0.000846 acc_pose: 0.776029 loss: 0.000846 2022/09/13 10:41:21 - mmengine - INFO - Epoch(train) [5][100/293] lr: 5.000000e-04 eta: 13:25:11 time: 0.772124 data_time: 0.096894 memory: 21676 loss_kpt: 0.000872 acc_pose: 0.735056 loss: 0.000872 2022/09/13 10:41:59 - mmengine - INFO - Epoch(train) [5][150/293] lr: 5.000000e-04 eta: 13:23:05 time: 0.763927 data_time: 0.102433 memory: 21676 loss_kpt: 0.000856 acc_pose: 0.691892 loss: 0.000856 2022/09/13 10:42:38 - mmengine - INFO - Epoch(train) [5][200/293] lr: 5.000000e-04 eta: 13:21:07 time: 0.764988 data_time: 0.092153 memory: 21676 loss_kpt: 0.000858 acc_pose: 0.641888 loss: 0.000858 2022/09/13 10:43:15 - mmengine - INFO - Epoch(train) [5][250/293] lr: 5.000000e-04 eta: 13:18:37 time: 0.746530 data_time: 0.096546 memory: 21676 loss_kpt: 0.000857 acc_pose: 0.761265 loss: 0.000857 2022/09/13 10:43:47 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 10:43:47 - mmengine - INFO - Saving checkpoint at 5 epochs 2022/09/13 10:44:31 - mmengine - INFO - Epoch(train) [6][50/293] lr: 5.000000e-04 eta: 12:54:12 time: 0.780969 data_time: 0.114889 memory: 21676 loss_kpt: 0.000843 acc_pose: 0.693994 loss: 0.000843 2022/09/13 10:45:10 - mmengine - INFO - Epoch(train) [6][100/293] lr: 5.000000e-04 eta: 12:53:33 time: 0.773749 data_time: 0.096023 memory: 21676 loss_kpt: 0.000829 acc_pose: 0.734246 loss: 0.000829 2022/09/13 10:45:49 - mmengine - INFO - Epoch(train) [6][150/293] lr: 5.000000e-04 eta: 12:52:58 time: 0.775974 data_time: 0.097832 memory: 21676 loss_kpt: 0.000817 acc_pose: 0.740409 loss: 0.000817 2022/09/13 10:46:27 - mmengine - INFO - Epoch(train) [6][200/293] lr: 5.000000e-04 eta: 12:52:25 time: 0.776970 data_time: 0.093948 memory: 21676 loss_kpt: 0.000819 acc_pose: 0.771854 loss: 0.000819 2022/09/13 10:47:06 - mmengine - INFO - Epoch(train) [6][250/293] lr: 5.000000e-04 eta: 12:51:50 time: 0.776705 data_time: 0.098692 memory: 21676 loss_kpt: 0.000826 acc_pose: 0.718795 loss: 0.000826 2022/09/13 10:47:39 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 10:47:39 - mmengine - INFO - Saving checkpoint at 6 epochs 2022/09/13 10:48:22 - mmengine - INFO - Epoch(train) [7][50/293] lr: 5.000000e-04 eta: 12:32:15 time: 0.771762 data_time: 0.111367 memory: 21676 loss_kpt: 0.000834 acc_pose: 0.806562 loss: 0.000834 2022/09/13 10:49:01 - mmengine - INFO - Epoch(train) [7][100/293] lr: 5.000000e-04 eta: 12:32:04 time: 0.772440 data_time: 0.096991 memory: 21676 loss_kpt: 0.000812 acc_pose: 0.765891 loss: 0.000812 2022/09/13 10:49:39 - mmengine - INFO - Epoch(train) [7][150/293] lr: 5.000000e-04 eta: 12:31:46 time: 0.768994 data_time: 0.103510 memory: 21676 loss_kpt: 0.000792 acc_pose: 0.763694 loss: 0.000792 2022/09/13 10:50:18 - mmengine - INFO - Epoch(train) [7][200/293] lr: 5.000000e-04 eta: 12:31:32 time: 0.772718 data_time: 0.106739 memory: 21676 loss_kpt: 0.000812 acc_pose: 0.739376 loss: 0.000812 2022/09/13 10:50:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 10:50:57 - mmengine - INFO - Epoch(train) [7][250/293] lr: 5.000000e-04 eta: 12:31:23 time: 0.776364 data_time: 0.101019 memory: 21676 loss_kpt: 0.000807 acc_pose: 0.729492 loss: 0.000807 2022/09/13 10:51:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 10:51:30 - mmengine - INFO - Saving checkpoint at 7 epochs 2022/09/13 10:52:14 - mmengine - INFO - Epoch(train) [8][50/293] lr: 5.000000e-04 eta: 12:15:34 time: 0.787565 data_time: 0.109219 memory: 21676 loss_kpt: 0.000810 acc_pose: 0.768132 loss: 0.000810 2022/09/13 10:52:52 - mmengine - INFO - Epoch(train) [8][100/293] lr: 5.000000e-04 eta: 12:15:34 time: 0.769000 data_time: 0.099386 memory: 21676 loss_kpt: 0.000799 acc_pose: 0.756876 loss: 0.000799 2022/09/13 10:53:31 - mmengine - INFO - Epoch(train) [8][150/293] lr: 5.000000e-04 eta: 12:15:38 time: 0.774303 data_time: 0.096056 memory: 21676 loss_kpt: 0.000789 acc_pose: 0.742850 loss: 0.000789 2022/09/13 10:54:09 - mmengine - INFO - Epoch(train) [8][200/293] lr: 5.000000e-04 eta: 12:15:31 time: 0.766716 data_time: 0.102684 memory: 21676 loss_kpt: 0.000798 acc_pose: 0.719858 loss: 0.000798 2022/09/13 10:54:48 - mmengine - INFO - Epoch(train) [8][250/293] lr: 5.000000e-04 eta: 12:15:25 time: 0.768925 data_time: 0.103341 memory: 21676 loss_kpt: 0.000791 acc_pose: 0.785282 loss: 0.000791 2022/09/13 10:55:20 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 10:55:20 - mmengine - INFO - Saving checkpoint at 8 epochs 2022/09/13 10:56:04 - mmengine - INFO - Epoch(train) [9][50/293] lr: 5.000000e-04 eta: 12:01:54 time: 0.784993 data_time: 0.106094 memory: 21676 loss_kpt: 0.000766 acc_pose: 0.735518 loss: 0.000766 2022/09/13 10:56:43 - mmengine - INFO - Epoch(train) [9][100/293] lr: 5.000000e-04 eta: 12:02:12 time: 0.777582 data_time: 0.097051 memory: 21676 loss_kpt: 0.000786 acc_pose: 0.782180 loss: 0.000786 2022/09/13 10:57:22 - mmengine - INFO - Epoch(train) [9][150/293] lr: 5.000000e-04 eta: 12:02:29 time: 0.778528 data_time: 0.097941 memory: 21676 loss_kpt: 0.000785 acc_pose: 0.716237 loss: 0.000785 2022/09/13 10:58:00 - mmengine - INFO - Epoch(train) [9][200/293] lr: 5.000000e-04 eta: 12:02:35 time: 0.771367 data_time: 0.101766 memory: 21676 loss_kpt: 0.000777 acc_pose: 0.760980 loss: 0.000777 2022/09/13 10:58:39 - mmengine - INFO - Epoch(train) [9][250/293] lr: 5.000000e-04 eta: 12:02:39 time: 0.770617 data_time: 0.100923 memory: 21676 loss_kpt: 0.000770 acc_pose: 0.709586 loss: 0.000770 2022/09/13 10:59:12 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 10:59:12 - mmengine - INFO - Saving checkpoint at 9 epochs 2022/09/13 10:59:56 - mmengine - INFO - Epoch(train) [10][50/293] lr: 5.000000e-04 eta: 11:50:51 time: 0.784280 data_time: 0.106763 memory: 21676 loss_kpt: 0.000771 acc_pose: 0.727846 loss: 0.000771 2022/09/13 11:00:35 - mmengine - INFO - Epoch(train) [10][100/293] lr: 5.000000e-04 eta: 11:51:25 time: 0.790854 data_time: 0.097684 memory: 21676 loss_kpt: 0.000763 acc_pose: 0.757309 loss: 0.000763 2022/09/13 11:01:14 - mmengine - INFO - Epoch(train) [10][150/293] lr: 5.000000e-04 eta: 11:51:38 time: 0.772095 data_time: 0.097950 memory: 21676 loss_kpt: 0.000770 acc_pose: 0.725888 loss: 0.000770 2022/09/13 11:01:53 - mmengine - INFO - Epoch(train) [10][200/293] lr: 5.000000e-04 eta: 11:51:53 time: 0.776648 data_time: 0.099485 memory: 21676 loss_kpt: 0.000765 acc_pose: 0.781716 loss: 0.000765 2022/09/13 11:02:31 - mmengine - INFO - Epoch(train) [10][250/293] lr: 5.000000e-04 eta: 11:51:53 time: 0.763549 data_time: 0.100405 memory: 21676 loss_kpt: 0.000751 acc_pose: 0.715397 loss: 0.000751 2022/09/13 11:03:03 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 11:03:03 - mmengine - INFO - Saving checkpoint at 10 epochs 2022/09/13 11:03:21 - mmengine - INFO - Epoch(val) [10][50/407] eta: 0:01:33 time: 0.262249 data_time: 0.092851 memory: 21676 2022/09/13 11:03:30 - mmengine - INFO - Epoch(val) [10][100/407] eta: 0:00:54 time: 0.175938 data_time: 0.008390 memory: 1375 2022/09/13 11:03:39 - mmengine - INFO - Epoch(val) [10][150/407] eta: 0:00:45 time: 0.177044 data_time: 0.008770 memory: 1375 2022/09/13 11:03:48 - mmengine - INFO - Epoch(val) [10][200/407] eta: 0:00:36 time: 0.178271 data_time: 0.008702 memory: 1375 2022/09/13 11:03:57 - mmengine - INFO - Epoch(val) [10][250/407] eta: 0:00:28 time: 0.179303 data_time: 0.011980 memory: 1375 2022/09/13 11:04:06 - mmengine - INFO - Epoch(val) [10][300/407] eta: 0:00:19 time: 0.178010 data_time: 0.008962 memory: 1375 2022/09/13 11:04:14 - mmengine - INFO - Epoch(val) [10][350/407] eta: 0:00:10 time: 0.178170 data_time: 0.008389 memory: 1375 2022/09/13 11:04:23 - mmengine - INFO - Epoch(val) [10][400/407] eta: 0:00:01 time: 0.175753 data_time: 0.008697 memory: 1375 2022/09/13 11:05:00 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 11:05:14 - mmengine - INFO - Epoch(val) [10][407/407] coco/AP: 0.688100 coco/AP .5: 0.877098 coco/AP .75: 0.751270 coco/AP (M): 0.645967 coco/AP (L): 0.760904 coco/AR: 0.743860 coco/AR .5: 0.919553 coco/AR .75: 0.800378 coco/AR (M): 0.696121 coco/AR (L): 0.812114 2022/09/13 11:05:17 - mmengine - INFO - The best checkpoint with 0.6881 coco/AP at 10 epoch is saved to best_coco/AP_epoch_10.pth. 2022/09/13 11:05:57 - mmengine - INFO - Epoch(train) [11][50/293] lr: 5.000000e-04 eta: 11:41:24 time: 0.784172 data_time: 0.106736 memory: 21676 loss_kpt: 0.000761 acc_pose: 0.766819 loss: 0.000761 2022/09/13 11:06:12 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 11:06:36 - mmengine - INFO - Epoch(train) [11][100/293] lr: 5.000000e-04 eta: 11:41:45 time: 0.777171 data_time: 0.090868 memory: 21676 loss_kpt: 0.000756 acc_pose: 0.800720 loss: 0.000756 2022/09/13 11:07:14 - mmengine - INFO - Epoch(train) [11][150/293] lr: 5.000000e-04 eta: 11:41:51 time: 0.763663 data_time: 0.094174 memory: 21676 loss_kpt: 0.000775 acc_pose: 0.796114 loss: 0.000775 2022/09/13 11:07:51 - mmengine - INFO - Epoch(train) [11][200/293] lr: 5.000000e-04 eta: 11:41:44 time: 0.752563 data_time: 0.100541 memory: 21676 loss_kpt: 0.000749 acc_pose: 0.801548 loss: 0.000749 2022/09/13 11:08:29 - mmengine - INFO - Epoch(train) [11][250/293] lr: 5.000000e-04 eta: 11:41:41 time: 0.755922 data_time: 0.100458 memory: 21676 loss_kpt: 0.000760 acc_pose: 0.754717 loss: 0.000760 2022/09/13 11:09:01 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 11:09:01 - mmengine - INFO - Saving checkpoint at 11 epochs 2022/09/13 11:09:45 - mmengine - INFO - Epoch(train) [12][50/293] lr: 5.000000e-04 eta: 11:32:19 time: 0.787011 data_time: 0.102036 memory: 21676 loss_kpt: 0.000729 acc_pose: 0.783427 loss: 0.000729 2022/09/13 11:10:24 - mmengine - INFO - Epoch(train) [12][100/293] lr: 5.000000e-04 eta: 11:32:46 time: 0.784535 data_time: 0.098490 memory: 21676 loss_kpt: 0.000734 acc_pose: 0.752012 loss: 0.000734 2022/09/13 11:11:03 - mmengine - INFO - Epoch(train) [12][150/293] lr: 5.000000e-04 eta: 11:33:13 time: 0.786672 data_time: 0.091864 memory: 21676 loss_kpt: 0.000747 acc_pose: 0.692587 loss: 0.000747 2022/09/13 11:11:41 - mmengine - INFO - Epoch(train) [12][200/293] lr: 5.000000e-04 eta: 11:33:09 time: 0.752798 data_time: 0.098745 memory: 21676 loss_kpt: 0.000767 acc_pose: 0.777600 loss: 0.000767 2022/09/13 11:12:18 - mmengine - INFO - Epoch(train) [12][250/293] lr: 5.000000e-04 eta: 11:33:04 time: 0.751767 data_time: 0.099160 memory: 21676 loss_kpt: 0.000749 acc_pose: 0.720370 loss: 0.000749 2022/09/13 11:12:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 11:12:51 - mmengine - INFO - Saving checkpoint at 12 epochs 2022/09/13 11:13:34 - mmengine - INFO - Epoch(train) [13][50/293] lr: 5.000000e-04 eta: 11:24:33 time: 0.785619 data_time: 0.104406 memory: 21676 loss_kpt: 0.000736 acc_pose: 0.788619 loss: 0.000736 2022/09/13 11:14:14 - mmengine - INFO - Epoch(train) [13][100/293] lr: 5.000000e-04 eta: 11:25:03 time: 0.790864 data_time: 0.104601 memory: 21676 loss_kpt: 0.000730 acc_pose: 0.797214 loss: 0.000730 2022/09/13 11:14:52 - mmengine - INFO - Epoch(train) [13][150/293] lr: 5.000000e-04 eta: 11:25:17 time: 0.771922 data_time: 0.097770 memory: 21676 loss_kpt: 0.000748 acc_pose: 0.757537 loss: 0.000748 2022/09/13 11:15:31 - mmengine - INFO - Epoch(train) [13][200/293] lr: 5.000000e-04 eta: 11:25:35 time: 0.779434 data_time: 0.098477 memory: 21676 loss_kpt: 0.000730 acc_pose: 0.790960 loss: 0.000730 2022/09/13 11:16:11 - mmengine - INFO - Epoch(train) [13][250/293] lr: 5.000000e-04 eta: 11:26:03 time: 0.794133 data_time: 0.097510 memory: 21676 loss_kpt: 0.000740 acc_pose: 0.750257 loss: 0.000740 2022/09/13 11:16:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 11:16:44 - mmengine - INFO - Saving checkpoint at 13 epochs 2022/09/13 11:17:28 - mmengine - INFO - Epoch(train) [14][50/293] lr: 5.000000e-04 eta: 11:18:22 time: 0.798170 data_time: 0.107612 memory: 21676 loss_kpt: 0.000732 acc_pose: 0.774704 loss: 0.000732 2022/09/13 11:18:07 - mmengine - INFO - Epoch(train) [14][100/293] lr: 5.000000e-04 eta: 11:18:45 time: 0.784013 data_time: 0.096075 memory: 21676 loss_kpt: 0.000722 acc_pose: 0.761936 loss: 0.000722 2022/09/13 11:18:46 - mmengine - INFO - Epoch(train) [14][150/293] lr: 5.000000e-04 eta: 11:19:02 time: 0.779688 data_time: 0.099825 memory: 21676 loss_kpt: 0.000726 acc_pose: 0.780032 loss: 0.000726 2022/09/13 11:19:18 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 11:19:25 - mmengine - INFO - Epoch(train) [14][200/293] lr: 5.000000e-04 eta: 11:19:17 time: 0.777636 data_time: 0.102612 memory: 21676 loss_kpt: 0.000740 acc_pose: 0.789866 loss: 0.000740 2022/09/13 11:20:03 - mmengine - INFO - Epoch(train) [14][250/293] lr: 5.000000e-04 eta: 11:19:15 time: 0.756097 data_time: 0.096398 memory: 21676 loss_kpt: 0.000724 acc_pose: 0.811369 loss: 0.000724 2022/09/13 11:20:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 11:20:35 - mmengine - INFO - Saving checkpoint at 14 epochs 2022/09/13 11:21:19 - mmengine - INFO - Epoch(train) [15][50/293] lr: 5.000000e-04 eta: 11:12:02 time: 0.787663 data_time: 0.108089 memory: 21676 loss_kpt: 0.000730 acc_pose: 0.753907 loss: 0.000730 2022/09/13 11:21:58 - mmengine - INFO - Epoch(train) [15][100/293] lr: 5.000000e-04 eta: 11:12:23 time: 0.784375 data_time: 0.099124 memory: 21676 loss_kpt: 0.000720 acc_pose: 0.813534 loss: 0.000720 2022/09/13 11:22:38 - mmengine - INFO - Epoch(train) [15][150/293] lr: 5.000000e-04 eta: 11:12:49 time: 0.795442 data_time: 0.099644 memory: 21676 loss_kpt: 0.000721 acc_pose: 0.763929 loss: 0.000721 2022/09/13 11:23:17 - mmengine - INFO - Epoch(train) [15][200/293] lr: 5.000000e-04 eta: 11:13:06 time: 0.782761 data_time: 0.099238 memory: 21676 loss_kpt: 0.000712 acc_pose: 0.790620 loss: 0.000712 2022/09/13 11:23:56 - mmengine - INFO - Epoch(train) [15][250/293] lr: 5.000000e-04 eta: 11:13:17 time: 0.776541 data_time: 0.102536 memory: 21676 loss_kpt: 0.000732 acc_pose: 0.790560 loss: 0.000732 2022/09/13 11:24:29 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 11:24:29 - mmengine - INFO - Saving checkpoint at 15 epochs 2022/09/13 11:25:13 - mmengine - INFO - Epoch(train) [16][50/293] lr: 5.000000e-04 eta: 11:06:31 time: 0.783740 data_time: 0.107809 memory: 21676 loss_kpt: 0.000728 acc_pose: 0.792770 loss: 0.000728 2022/09/13 11:25:51 - mmengine - INFO - Epoch(train) [16][100/293] lr: 5.000000e-04 eta: 11:06:32 time: 0.756616 data_time: 0.101101 memory: 21676 loss_kpt: 0.000729 acc_pose: 0.766658 loss: 0.000729 2022/09/13 11:26:29 - mmengine - INFO - Epoch(train) [16][150/293] lr: 5.000000e-04 eta: 11:06:34 time: 0.761669 data_time: 0.096465 memory: 21676 loss_kpt: 0.000717 acc_pose: 0.768068 loss: 0.000717 2022/09/13 11:27:07 - mmengine - INFO - Epoch(train) [16][200/293] lr: 5.000000e-04 eta: 11:06:36 time: 0.761736 data_time: 0.098048 memory: 21676 loss_kpt: 0.000716 acc_pose: 0.738594 loss: 0.000716 2022/09/13 11:27:45 - mmengine - INFO - Epoch(train) [16][250/293] lr: 5.000000e-04 eta: 11:06:36 time: 0.758455 data_time: 0.091455 memory: 21676 loss_kpt: 0.000726 acc_pose: 0.763440 loss: 0.000726 2022/09/13 11:28:17 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 11:28:17 - mmengine - INFO - Saving checkpoint at 16 epochs 2022/09/13 11:29:01 - mmengine - INFO - Epoch(train) [17][50/293] lr: 5.000000e-04 eta: 11:00:22 time: 0.793997 data_time: 0.108710 memory: 21676 loss_kpt: 0.000709 acc_pose: 0.774740 loss: 0.000709 2022/09/13 11:29:40 - mmengine - INFO - Epoch(train) [17][100/293] lr: 5.000000e-04 eta: 11:00:30 time: 0.770090 data_time: 0.095294 memory: 21676 loss_kpt: 0.000714 acc_pose: 0.814044 loss: 0.000714 2022/09/13 11:30:19 - mmengine - INFO - Epoch(train) [17][150/293] lr: 5.000000e-04 eta: 11:00:44 time: 0.781803 data_time: 0.099056 memory: 21676 loss_kpt: 0.000721 acc_pose: 0.764727 loss: 0.000721 2022/09/13 11:30:58 - mmengine - INFO - Epoch(train) [17][200/293] lr: 5.000000e-04 eta: 11:00:53 time: 0.774896 data_time: 0.091231 memory: 21676 loss_kpt: 0.000722 acc_pose: 0.761974 loss: 0.000722 2022/09/13 11:31:36 - mmengine - INFO - Epoch(train) [17][250/293] lr: 5.000000e-04 eta: 11:00:59 time: 0.771219 data_time: 0.097822 memory: 21676 loss_kpt: 0.000709 acc_pose: 0.783467 loss: 0.000709 2022/09/13 11:32:09 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 11:32:09 - mmengine - INFO - Saving checkpoint at 17 epochs 2022/09/13 11:32:29 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 11:32:53 - mmengine - INFO - Epoch(train) [18][50/293] lr: 5.000000e-04 eta: 10:55:02 time: 0.784385 data_time: 0.114702 memory: 21676 loss_kpt: 0.000720 acc_pose: 0.781488 loss: 0.000720 2022/09/13 11:33:32 - mmengine - INFO - Epoch(train) [18][100/293] lr: 5.000000e-04 eta: 10:55:13 time: 0.778619 data_time: 0.097924 memory: 21676 loss_kpt: 0.000709 acc_pose: 0.744010 loss: 0.000709 2022/09/13 11:34:11 - mmengine - INFO - Epoch(train) [18][150/293] lr: 5.000000e-04 eta: 10:55:26 time: 0.781703 data_time: 0.101770 memory: 21676 loss_kpt: 0.000703 acc_pose: 0.758123 loss: 0.000703 2022/09/13 11:34:50 - mmengine - INFO - Epoch(train) [18][200/293] lr: 5.000000e-04 eta: 10:55:36 time: 0.780051 data_time: 0.097424 memory: 21676 loss_kpt: 0.000709 acc_pose: 0.791873 loss: 0.000709 2022/09/13 11:35:29 - mmengine - INFO - Epoch(train) [18][250/293] lr: 5.000000e-04 eta: 10:55:45 time: 0.780783 data_time: 0.094570 memory: 21676 loss_kpt: 0.000693 acc_pose: 0.757532 loss: 0.000693 2022/09/13 11:36:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 11:36:02 - mmengine - INFO - Saving checkpoint at 18 epochs 2022/09/13 11:36:46 - mmengine - INFO - Epoch(train) [19][50/293] lr: 5.000000e-04 eta: 10:50:11 time: 0.790219 data_time: 0.108186 memory: 21676 loss_kpt: 0.000705 acc_pose: 0.806653 loss: 0.000705 2022/09/13 11:37:25 - mmengine - INFO - Epoch(train) [19][100/293] lr: 5.000000e-04 eta: 10:50:21 time: 0.779349 data_time: 0.095483 memory: 21676 loss_kpt: 0.000693 acc_pose: 0.794652 loss: 0.000693 2022/09/13 11:38:05 - mmengine - INFO - Epoch(train) [19][150/293] lr: 5.000000e-04 eta: 10:50:37 time: 0.792333 data_time: 0.100292 memory: 21676 loss_kpt: 0.000702 acc_pose: 0.809271 loss: 0.000702 2022/09/13 11:38:44 - mmengine - INFO - Epoch(train) [19][200/293] lr: 5.000000e-04 eta: 10:50:47 time: 0.784553 data_time: 0.101475 memory: 21676 loss_kpt: 0.000702 acc_pose: 0.765918 loss: 0.000702 2022/09/13 11:39:24 - mmengine - INFO - Epoch(train) [19][250/293] lr: 5.000000e-04 eta: 10:51:01 time: 0.792786 data_time: 0.099632 memory: 21676 loss_kpt: 0.000707 acc_pose: 0.799774 loss: 0.000707 2022/09/13 11:39:57 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 11:39:57 - mmengine - INFO - Saving checkpoint at 19 epochs 2022/09/13 11:40:40 - mmengine - INFO - Epoch(train) [20][50/293] lr: 5.000000e-04 eta: 10:45:38 time: 0.777961 data_time: 0.106316 memory: 21676 loss_kpt: 0.000699 acc_pose: 0.745240 loss: 0.000699 2022/09/13 11:41:19 - mmengine - INFO - Epoch(train) [20][100/293] lr: 5.000000e-04 eta: 10:45:45 time: 0.776596 data_time: 0.096445 memory: 21676 loss_kpt: 0.000693 acc_pose: 0.792247 loss: 0.000693 2022/09/13 11:41:59 - mmengine - INFO - Epoch(train) [20][150/293] lr: 5.000000e-04 eta: 10:45:59 time: 0.793498 data_time: 0.098156 memory: 21676 loss_kpt: 0.000695 acc_pose: 0.780556 loss: 0.000695 2022/09/13 11:42:37 - mmengine - INFO - Epoch(train) [20][200/293] lr: 5.000000e-04 eta: 10:46:00 time: 0.769831 data_time: 0.101267 memory: 21676 loss_kpt: 0.000710 acc_pose: 0.819363 loss: 0.000710 2022/09/13 11:43:15 - mmengine - INFO - Epoch(train) [20][250/293] lr: 5.000000e-04 eta: 10:45:55 time: 0.756179 data_time: 0.096787 memory: 21676 loss_kpt: 0.000685 acc_pose: 0.845358 loss: 0.000685 2022/09/13 11:43:47 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 11:43:47 - mmengine - INFO - Saving checkpoint at 20 epochs 2022/09/13 11:44:01 - mmengine - INFO - Epoch(val) [20][50/407] eta: 0:01:05 time: 0.184338 data_time: 0.014179 memory: 21676 2022/09/13 11:44:10 - mmengine - INFO - Epoch(val) [20][100/407] eta: 0:00:55 time: 0.181995 data_time: 0.009017 memory: 1375 2022/09/13 11:44:18 - mmengine - INFO - Epoch(val) [20][150/407] eta: 0:00:44 time: 0.174582 data_time: 0.008331 memory: 1375 2022/09/13 11:44:27 - mmengine - INFO - Epoch(val) [20][200/407] eta: 0:00:36 time: 0.175170 data_time: 0.008524 memory: 1375 2022/09/13 11:44:36 - mmengine - INFO - Epoch(val) [20][250/407] eta: 0:00:27 time: 0.176161 data_time: 0.008739 memory: 1375 2022/09/13 11:44:45 - mmengine - INFO - Epoch(val) [20][300/407] eta: 0:00:18 time: 0.176376 data_time: 0.008540 memory: 1375 2022/09/13 11:44:54 - mmengine - INFO - Epoch(val) [20][350/407] eta: 0:00:09 time: 0.174195 data_time: 0.008369 memory: 1375 2022/09/13 11:45:02 - mmengine - INFO - Epoch(val) [20][400/407] eta: 0:00:01 time: 0.173106 data_time: 0.008222 memory: 1375 2022/09/13 11:45:39 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 11:45:52 - mmengine - INFO - Epoch(val) [20][407/407] coco/AP: 0.710132 coco/AP .5: 0.884396 coco/AP .75: 0.776470 coco/AP (M): 0.668622 coco/AP (L): 0.782581 coco/AR: 0.763303 coco/AR .5: 0.923331 coco/AR .75: 0.824465 coco/AR (M): 0.716908 coco/AR (L): 0.829840 2022/09/13 11:45:52 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220913/udp_w32_384_v1/best_coco/AP_epoch_10.pth is removed 2022/09/13 11:45:55 - mmengine - INFO - The best checkpoint with 0.7101 coco/AP at 20 epoch is saved to best_coco/AP_epoch_20.pth. 2022/09/13 11:46:35 - mmengine - INFO - Epoch(train) [21][50/293] lr: 5.000000e-04 eta: 10:40:52 time: 0.787459 data_time: 0.109275 memory: 21676 loss_kpt: 0.000702 acc_pose: 0.826196 loss: 0.000702 2022/09/13 11:47:14 - mmengine - INFO - Epoch(train) [21][100/293] lr: 5.000000e-04 eta: 10:41:01 time: 0.784949 data_time: 0.093324 memory: 21676 loss_kpt: 0.000705 acc_pose: 0.797483 loss: 0.000705 2022/09/13 11:47:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 11:47:53 - mmengine - INFO - Epoch(train) [21][150/293] lr: 5.000000e-04 eta: 10:41:07 time: 0.780722 data_time: 0.096266 memory: 21676 loss_kpt: 0.000689 acc_pose: 0.775950 loss: 0.000689 2022/09/13 11:48:32 - mmengine - INFO - Epoch(train) [21][200/293] lr: 5.000000e-04 eta: 10:41:11 time: 0.777162 data_time: 0.098649 memory: 21676 loss_kpt: 0.000708 acc_pose: 0.780488 loss: 0.000708 2022/09/13 11:49:11 - mmengine - INFO - Epoch(train) [21][250/293] lr: 5.000000e-04 eta: 10:41:16 time: 0.780094 data_time: 0.099361 memory: 21676 loss_kpt: 0.000708 acc_pose: 0.767741 loss: 0.000708 2022/09/13 11:49:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 11:49:44 - mmengine - INFO - Saving checkpoint at 21 epochs 2022/09/13 11:50:28 - mmengine - INFO - Epoch(train) [22][50/293] lr: 5.000000e-04 eta: 10:36:25 time: 0.783320 data_time: 0.108730 memory: 21676 loss_kpt: 0.000700 acc_pose: 0.810813 loss: 0.000700 2022/09/13 11:51:06 - mmengine - INFO - Epoch(train) [22][100/293] lr: 5.000000e-04 eta: 10:36:27 time: 0.774324 data_time: 0.097023 memory: 21676 loss_kpt: 0.000699 acc_pose: 0.751238 loss: 0.000699 2022/09/13 11:51:46 - mmengine - INFO - Epoch(train) [22][150/293] lr: 5.000000e-04 eta: 10:36:36 time: 0.789773 data_time: 0.101695 memory: 21676 loss_kpt: 0.000691 acc_pose: 0.769377 loss: 0.000691 2022/09/13 11:52:25 - mmengine - INFO - Epoch(train) [22][200/293] lr: 5.000000e-04 eta: 10:36:39 time: 0.776645 data_time: 0.102864 memory: 21676 loss_kpt: 0.000690 acc_pose: 0.789217 loss: 0.000690 2022/09/13 11:53:03 - mmengine - INFO - Epoch(train) [22][250/293] lr: 5.000000e-04 eta: 10:36:37 time: 0.769805 data_time: 0.107512 memory: 21676 loss_kpt: 0.000685 acc_pose: 0.781478 loss: 0.000685 2022/09/13 11:53:36 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 11:53:36 - mmengine - INFO - Saving checkpoint at 22 epochs 2022/09/13 11:54:20 - mmengine - INFO - Epoch(train) [23][50/293] lr: 5.000000e-04 eta: 10:32:02 time: 0.790960 data_time: 0.104887 memory: 21676 loss_kpt: 0.000695 acc_pose: 0.718629 loss: 0.000695 2022/09/13 11:54:59 - mmengine - INFO - Epoch(train) [23][100/293] lr: 5.000000e-04 eta: 10:32:06 time: 0.780764 data_time: 0.097370 memory: 21676 loss_kpt: 0.000680 acc_pose: 0.753322 loss: 0.000680 2022/09/13 11:55:38 - mmengine - INFO - Epoch(train) [23][150/293] lr: 5.000000e-04 eta: 10:32:08 time: 0.777637 data_time: 0.098844 memory: 21676 loss_kpt: 0.000679 acc_pose: 0.748828 loss: 0.000679 2022/09/13 11:56:18 - mmengine - INFO - Epoch(train) [23][200/293] lr: 5.000000e-04 eta: 10:32:15 time: 0.791355 data_time: 0.105833 memory: 21676 loss_kpt: 0.000686 acc_pose: 0.783152 loss: 0.000686 2022/09/13 11:56:56 - mmengine - INFO - Epoch(train) [23][250/293] lr: 5.000000e-04 eta: 10:32:14 time: 0.771693 data_time: 0.095823 memory: 21676 loss_kpt: 0.000713 acc_pose: 0.820423 loss: 0.000713 2022/09/13 11:57:29 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 11:57:29 - mmengine - INFO - Saving checkpoint at 23 epochs 2022/09/13 11:58:14 - mmengine - INFO - Epoch(train) [24][50/293] lr: 5.000000e-04 eta: 10:27:53 time: 0.798765 data_time: 0.105589 memory: 21676 loss_kpt: 0.000681 acc_pose: 0.770508 loss: 0.000681 2022/09/13 11:58:53 - mmengine - INFO - Epoch(train) [24][100/293] lr: 5.000000e-04 eta: 10:27:55 time: 0.779530 data_time: 0.096511 memory: 21676 loss_kpt: 0.000687 acc_pose: 0.762887 loss: 0.000687 2022/09/13 11:59:32 - mmengine - INFO - Epoch(train) [24][150/293] lr: 5.000000e-04 eta: 10:27:54 time: 0.773818 data_time: 0.095477 memory: 21676 loss_kpt: 0.000670 acc_pose: 0.823985 loss: 0.000670 2022/09/13 12:00:12 - mmengine - INFO - Epoch(train) [24][200/293] lr: 5.000000e-04 eta: 10:28:05 time: 0.805696 data_time: 0.098976 memory: 21676 loss_kpt: 0.000685 acc_pose: 0.784233 loss: 0.000685 2022/09/13 12:00:51 - mmengine - INFO - Epoch(train) [24][250/293] lr: 5.000000e-04 eta: 10:28:09 time: 0.789151 data_time: 0.096514 memory: 21676 loss_kpt: 0.000668 acc_pose: 0.851188 loss: 0.000668 2022/09/13 12:01:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 12:01:25 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 12:01:25 - mmengine - INFO - Saving checkpoint at 24 epochs 2022/09/13 12:02:08 - mmengine - INFO - Epoch(train) [25][50/293] lr: 5.000000e-04 eta: 10:23:48 time: 0.773712 data_time: 0.104317 memory: 21676 loss_kpt: 0.000667 acc_pose: 0.814759 loss: 0.000667 2022/09/13 12:02:45 - mmengine - INFO - Epoch(train) [25][100/293] lr: 5.000000e-04 eta: 10:23:36 time: 0.744943 data_time: 0.093510 memory: 21676 loss_kpt: 0.000668 acc_pose: 0.781889 loss: 0.000668 2022/09/13 12:03:23 - mmengine - INFO - Epoch(train) [25][150/293] lr: 5.000000e-04 eta: 10:23:25 time: 0.749657 data_time: 0.095837 memory: 21676 loss_kpt: 0.000679 acc_pose: 0.830592 loss: 0.000679 2022/09/13 12:04:01 - mmengine - INFO - Epoch(train) [25][200/293] lr: 5.000000e-04 eta: 10:23:21 time: 0.769231 data_time: 0.092346 memory: 21676 loss_kpt: 0.000675 acc_pose: 0.810067 loss: 0.000675 2022/09/13 12:04:39 - mmengine - INFO - Epoch(train) [25][250/293] lr: 5.000000e-04 eta: 10:23:14 time: 0.761737 data_time: 0.101203 memory: 21676 loss_kpt: 0.000689 acc_pose: 0.791971 loss: 0.000689 2022/09/13 12:05:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 12:05:11 - mmengine - INFO - Saving checkpoint at 25 epochs 2022/09/13 12:05:56 - mmengine - INFO - Epoch(train) [26][50/293] lr: 5.000000e-04 eta: 10:19:14 time: 0.804213 data_time: 0.108005 memory: 21676 loss_kpt: 0.000666 acc_pose: 0.822903 loss: 0.000666 2022/09/13 12:06:35 - mmengine - INFO - Epoch(train) [26][100/293] lr: 5.000000e-04 eta: 10:19:14 time: 0.779318 data_time: 0.100890 memory: 21676 loss_kpt: 0.000667 acc_pose: 0.794075 loss: 0.000667 2022/09/13 12:07:13 - mmengine - INFO - Epoch(train) [26][150/293] lr: 5.000000e-04 eta: 10:19:07 time: 0.763344 data_time: 0.094809 memory: 21676 loss_kpt: 0.000673 acc_pose: 0.825542 loss: 0.000673 2022/09/13 12:07:51 - mmengine - INFO - Epoch(train) [26][200/293] lr: 5.000000e-04 eta: 10:19:00 time: 0.762164 data_time: 0.094800 memory: 21676 loss_kpt: 0.000670 acc_pose: 0.796759 loss: 0.000670 2022/09/13 12:08:29 - mmengine - INFO - Epoch(train) [26][250/293] lr: 5.000000e-04 eta: 10:18:48 time: 0.752917 data_time: 0.095982 memory: 21676 loss_kpt: 0.000677 acc_pose: 0.818857 loss: 0.000677 2022/09/13 12:09:01 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 12:09:01 - mmengine - INFO - Saving checkpoint at 26 epochs 2022/09/13 12:09:46 - mmengine - INFO - Epoch(train) [27][50/293] lr: 5.000000e-04 eta: 10:14:54 time: 0.795098 data_time: 0.108999 memory: 21676 loss_kpt: 0.000673 acc_pose: 0.775018 loss: 0.000673 2022/09/13 12:10:25 - mmengine - INFO - Epoch(train) [27][100/293] lr: 5.000000e-04 eta: 10:14:55 time: 0.786362 data_time: 0.098575 memory: 21676 loss_kpt: 0.000681 acc_pose: 0.698226 loss: 0.000681 2022/09/13 12:11:05 - mmengine - INFO - Epoch(train) [27][150/293] lr: 5.000000e-04 eta: 10:14:58 time: 0.793610 data_time: 0.095769 memory: 21676 loss_kpt: 0.000664 acc_pose: 0.786718 loss: 0.000664 2022/09/13 12:11:44 - mmengine - INFO - Epoch(train) [27][200/293] lr: 5.000000e-04 eta: 10:14:57 time: 0.781193 data_time: 0.099401 memory: 21676 loss_kpt: 0.000678 acc_pose: 0.711228 loss: 0.000678 2022/09/13 12:12:23 - mmengine - INFO - Epoch(train) [27][250/293] lr: 5.000000e-04 eta: 10:14:57 time: 0.789171 data_time: 0.101906 memory: 21676 loss_kpt: 0.000673 acc_pose: 0.849261 loss: 0.000673 2022/09/13 12:12:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 12:12:56 - mmengine - INFO - Saving checkpoint at 27 epochs 2022/09/13 12:13:40 - mmengine - INFO - Epoch(train) [28][50/293] lr: 5.000000e-04 eta: 10:11:11 time: 0.797810 data_time: 0.102431 memory: 21676 loss_kpt: 0.000680 acc_pose: 0.848157 loss: 0.000680 2022/09/13 12:14:10 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 12:14:19 - mmengine - INFO - Epoch(train) [28][100/293] lr: 5.000000e-04 eta: 10:11:06 time: 0.771042 data_time: 0.097509 memory: 21676 loss_kpt: 0.000684 acc_pose: 0.759959 loss: 0.000684 2022/09/13 12:14:58 - mmengine - INFO - Epoch(train) [28][150/293] lr: 5.000000e-04 eta: 10:11:07 time: 0.790841 data_time: 0.101002 memory: 21676 loss_kpt: 0.000670 acc_pose: 0.877535 loss: 0.000670 2022/09/13 12:15:38 - mmengine - INFO - Epoch(train) [28][200/293] lr: 5.000000e-04 eta: 10:11:07 time: 0.790263 data_time: 0.099855 memory: 21676 loss_kpt: 0.000663 acc_pose: 0.778747 loss: 0.000663 2022/09/13 12:16:17 - mmengine - INFO - Epoch(train) [28][250/293] lr: 5.000000e-04 eta: 10:11:00 time: 0.771832 data_time: 0.099508 memory: 21676 loss_kpt: 0.000653 acc_pose: 0.823787 loss: 0.000653 2022/09/13 12:16:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 12:16:50 - mmengine - INFO - Saving checkpoint at 28 epochs 2022/09/13 12:17:34 - mmengine - INFO - Epoch(train) [29][50/293] lr: 5.000000e-04 eta: 10:07:21 time: 0.796386 data_time: 0.114229 memory: 21676 loss_kpt: 0.000670 acc_pose: 0.827507 loss: 0.000670 2022/09/13 12:18:13 - mmengine - INFO - Epoch(train) [29][100/293] lr: 5.000000e-04 eta: 10:07:17 time: 0.778327 data_time: 0.097082 memory: 21676 loss_kpt: 0.000667 acc_pose: 0.778540 loss: 0.000667 2022/09/13 12:18:52 - mmengine - INFO - Epoch(train) [29][150/293] lr: 5.000000e-04 eta: 10:07:16 time: 0.789095 data_time: 0.100267 memory: 21676 loss_kpt: 0.000660 acc_pose: 0.810473 loss: 0.000660 2022/09/13 12:19:31 - mmengine - INFO - Epoch(train) [29][200/293] lr: 5.000000e-04 eta: 10:07:13 time: 0.782757 data_time: 0.103602 memory: 21676 loss_kpt: 0.000659 acc_pose: 0.816605 loss: 0.000659 2022/09/13 12:20:10 - mmengine - INFO - Epoch(train) [29][250/293] lr: 5.000000e-04 eta: 10:07:09 time: 0.781443 data_time: 0.103671 memory: 21676 loss_kpt: 0.000659 acc_pose: 0.759747 loss: 0.000659 2022/09/13 12:20:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 12:20:43 - mmengine - INFO - Saving checkpoint at 29 epochs 2022/09/13 12:21:28 - mmengine - INFO - Epoch(train) [30][50/293] lr: 5.000000e-04 eta: 10:03:36 time: 0.795417 data_time: 0.107061 memory: 21676 loss_kpt: 0.000655 acc_pose: 0.837827 loss: 0.000655 2022/09/13 12:22:08 - mmengine - INFO - Epoch(train) [30][100/293] lr: 5.000000e-04 eta: 10:03:35 time: 0.793950 data_time: 0.105106 memory: 21676 loss_kpt: 0.000673 acc_pose: 0.771948 loss: 0.000673 2022/09/13 12:22:47 - mmengine - INFO - Epoch(train) [30][150/293] lr: 5.000000e-04 eta: 10:03:31 time: 0.781340 data_time: 0.101643 memory: 21676 loss_kpt: 0.000661 acc_pose: 0.787821 loss: 0.000661 2022/09/13 12:23:26 - mmengine - INFO - Epoch(train) [30][200/293] lr: 5.000000e-04 eta: 10:03:25 time: 0.777457 data_time: 0.099352 memory: 21676 loss_kpt: 0.000650 acc_pose: 0.821047 loss: 0.000650 2022/09/13 12:24:05 - mmengine - INFO - Epoch(train) [30][250/293] lr: 5.000000e-04 eta: 10:03:20 time: 0.782850 data_time: 0.102543 memory: 21676 loss_kpt: 0.000659 acc_pose: 0.793698 loss: 0.000659 2022/09/13 12:24:37 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 12:24:37 - mmengine - INFO - Saving checkpoint at 30 epochs 2022/09/13 12:24:51 - mmengine - INFO - Epoch(val) [30][50/407] eta: 0:01:06 time: 0.185106 data_time: 0.017176 memory: 21676 2022/09/13 12:25:00 - mmengine - INFO - Epoch(val) [30][100/407] eta: 0:00:54 time: 0.178017 data_time: 0.008976 memory: 1375 2022/09/13 12:25:09 - mmengine - INFO - Epoch(val) [30][150/407] eta: 0:00:45 time: 0.176905 data_time: 0.008772 memory: 1375 2022/09/13 12:25:18 - mmengine - INFO - Epoch(val) [30][200/407] eta: 0:00:36 time: 0.177146 data_time: 0.008867 memory: 1375 2022/09/13 12:25:27 - mmengine - INFO - Epoch(val) [30][250/407] eta: 0:00:27 time: 0.175700 data_time: 0.008658 memory: 1375 2022/09/13 12:25:35 - mmengine - INFO - Epoch(val) [30][300/407] eta: 0:00:18 time: 0.176165 data_time: 0.008626 memory: 1375 2022/09/13 12:25:44 - mmengine - INFO - Epoch(val) [30][350/407] eta: 0:00:09 time: 0.174645 data_time: 0.008835 memory: 1375 2022/09/13 12:25:53 - mmengine - INFO - Epoch(val) [30][400/407] eta: 0:00:01 time: 0.173917 data_time: 0.008096 memory: 1375 2022/09/13 12:26:29 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 12:26:43 - mmengine - INFO - Epoch(val) [30][407/407] coco/AP: 0.724105 coco/AP .5: 0.890516 coco/AP .75: 0.791464 coco/AP (M): 0.683486 coco/AP (L): 0.798402 coco/AR: 0.775882 coco/AR .5: 0.929943 coco/AR .75: 0.835642 coco/AR (M): 0.728681 coco/AR (L): 0.844333 2022/09/13 12:26:43 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220913/udp_w32_384_v1/best_coco/AP_epoch_20.pth is removed 2022/09/13 12:26:46 - mmengine - INFO - The best checkpoint with 0.7241 coco/AP at 30 epoch is saved to best_coco/AP_epoch_30.pth. 2022/09/13 12:27:26 - mmengine - INFO - Epoch(train) [31][50/293] lr: 5.000000e-04 eta: 9:59:53 time: 0.795677 data_time: 0.103908 memory: 21676 loss_kpt: 0.000650 acc_pose: 0.738449 loss: 0.000650 2022/09/13 12:28:05 - mmengine - INFO - Epoch(train) [31][100/293] lr: 5.000000e-04 eta: 9:59:48 time: 0.779290 data_time: 0.093568 memory: 21676 loss_kpt: 0.000666 acc_pose: 0.814165 loss: 0.000666 2022/09/13 12:28:44 - mmengine - INFO - Epoch(train) [31][150/293] lr: 5.000000e-04 eta: 9:59:43 time: 0.784950 data_time: 0.102534 memory: 21676 loss_kpt: 0.000647 acc_pose: 0.856317 loss: 0.000647 2022/09/13 12:29:24 - mmengine - INFO - Epoch(train) [31][200/293] lr: 5.000000e-04 eta: 9:59:42 time: 0.797924 data_time: 0.101981 memory: 21676 loss_kpt: 0.000657 acc_pose: 0.842926 loss: 0.000657 2022/09/13 12:29:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 12:30:03 - mmengine - INFO - Epoch(train) [31][250/293] lr: 5.000000e-04 eta: 9:59:38 time: 0.787511 data_time: 0.101083 memory: 21676 loss_kpt: 0.000646 acc_pose: 0.806851 loss: 0.000646 2022/09/13 12:30:36 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 12:30:36 - mmengine - INFO - Saving checkpoint at 31 epochs 2022/09/13 12:31:21 - mmengine - INFO - Epoch(train) [32][50/293] lr: 5.000000e-04 eta: 9:56:14 time: 0.787749 data_time: 0.104495 memory: 21676 loss_kpt: 0.000664 acc_pose: 0.829881 loss: 0.000664 2022/09/13 12:31:58 - mmengine - INFO - Epoch(train) [32][100/293] lr: 5.000000e-04 eta: 9:56:00 time: 0.751835 data_time: 0.098246 memory: 21676 loss_kpt: 0.000657 acc_pose: 0.843821 loss: 0.000657 2022/09/13 12:32:36 - mmengine - INFO - Epoch(train) [32][150/293] lr: 5.000000e-04 eta: 9:55:48 time: 0.760628 data_time: 0.099237 memory: 21676 loss_kpt: 0.000646 acc_pose: 0.832289 loss: 0.000646 2022/09/13 12:33:15 - mmengine - INFO - Epoch(train) [32][200/293] lr: 5.000000e-04 eta: 9:55:38 time: 0.772431 data_time: 0.099419 memory: 21676 loss_kpt: 0.000649 acc_pose: 0.825224 loss: 0.000649 2022/09/13 12:33:53 - mmengine - INFO - Epoch(train) [32][250/293] lr: 5.000000e-04 eta: 9:55:27 time: 0.764337 data_time: 0.094517 memory: 21676 loss_kpt: 0.000654 acc_pose: 0.780764 loss: 0.000654 2022/09/13 12:34:25 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 12:34:25 - mmengine - INFO - Saving checkpoint at 32 epochs 2022/09/13 12:35:10 - mmengine - INFO - Epoch(train) [33][50/293] lr: 5.000000e-04 eta: 9:52:11 time: 0.795439 data_time: 0.101667 memory: 21676 loss_kpt: 0.000640 acc_pose: 0.809162 loss: 0.000640 2022/09/13 12:35:48 - mmengine - INFO - Epoch(train) [33][100/293] lr: 5.000000e-04 eta: 9:52:04 time: 0.779097 data_time: 0.100328 memory: 21676 loss_kpt: 0.000644 acc_pose: 0.815793 loss: 0.000644 2022/09/13 12:36:27 - mmengine - INFO - Epoch(train) [33][150/293] lr: 5.000000e-04 eta: 9:51:55 time: 0.775023 data_time: 0.107002 memory: 21676 loss_kpt: 0.000663 acc_pose: 0.796635 loss: 0.000663 2022/09/13 12:37:06 - mmengine - INFO - Epoch(train) [33][200/293] lr: 5.000000e-04 eta: 9:51:46 time: 0.775306 data_time: 0.104179 memory: 21676 loss_kpt: 0.000655 acc_pose: 0.797507 loss: 0.000655 2022/09/13 12:37:44 - mmengine - INFO - Epoch(train) [33][250/293] lr: 5.000000e-04 eta: 9:51:33 time: 0.764751 data_time: 0.099329 memory: 21676 loss_kpt: 0.000649 acc_pose: 0.834659 loss: 0.000649 2022/09/13 12:38:16 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 12:38:16 - mmengine - INFO - Saving checkpoint at 33 epochs 2022/09/13 12:39:00 - mmengine - INFO - Epoch(train) [34][50/293] lr: 5.000000e-04 eta: 9:48:19 time: 0.780332 data_time: 0.117217 memory: 21676 loss_kpt: 0.000657 acc_pose: 0.802245 loss: 0.000657 2022/09/13 12:39:39 - mmengine - INFO - Epoch(train) [34][100/293] lr: 5.000000e-04 eta: 9:48:08 time: 0.770836 data_time: 0.102608 memory: 21676 loss_kpt: 0.000646 acc_pose: 0.803504 loss: 0.000646 2022/09/13 12:40:17 - mmengine - INFO - Epoch(train) [34][150/293] lr: 5.000000e-04 eta: 9:47:58 time: 0.771854 data_time: 0.100452 memory: 21676 loss_kpt: 0.000658 acc_pose: 0.812620 loss: 0.000658 2022/09/13 12:40:56 - mmengine - INFO - Epoch(train) [34][200/293] lr: 5.000000e-04 eta: 9:47:48 time: 0.772570 data_time: 0.100275 memory: 21676 loss_kpt: 0.000663 acc_pose: 0.787321 loss: 0.000663 2022/09/13 12:41:35 - mmengine - INFO - Epoch(train) [34][250/293] lr: 5.000000e-04 eta: 9:47:38 time: 0.775757 data_time: 0.105032 memory: 21676 loss_kpt: 0.000663 acc_pose: 0.836088 loss: 0.000663 2022/09/13 12:42:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 12:42:07 - mmengine - INFO - Saving checkpoint at 34 epochs 2022/09/13 12:42:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 12:42:51 - mmengine - INFO - Epoch(train) [35][50/293] lr: 5.000000e-04 eta: 9:44:30 time: 0.788743 data_time: 0.106719 memory: 21676 loss_kpt: 0.000636 acc_pose: 0.823687 loss: 0.000636 2022/09/13 12:43:30 - mmengine - INFO - Epoch(train) [35][100/293] lr: 5.000000e-04 eta: 9:44:20 time: 0.775849 data_time: 0.092129 memory: 21676 loss_kpt: 0.000658 acc_pose: 0.800000 loss: 0.000658 2022/09/13 12:44:09 - mmengine - INFO - Epoch(train) [35][150/293] lr: 5.000000e-04 eta: 9:44:11 time: 0.779246 data_time: 0.102967 memory: 21676 loss_kpt: 0.000649 acc_pose: 0.781656 loss: 0.000649 2022/09/13 12:44:47 - mmengine - INFO - Epoch(train) [35][200/293] lr: 5.000000e-04 eta: 9:44:01 time: 0.774858 data_time: 0.090635 memory: 21676 loss_kpt: 0.000646 acc_pose: 0.807379 loss: 0.000646 2022/09/13 12:45:26 - mmengine - INFO - Epoch(train) [35][250/293] lr: 5.000000e-04 eta: 9:43:50 time: 0.775824 data_time: 0.095573 memory: 21676 loss_kpt: 0.000648 acc_pose: 0.841519 loss: 0.000648 2022/09/13 12:45:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 12:45:59 - mmengine - INFO - Saving checkpoint at 35 epochs 2022/09/13 12:46:43 - mmengine - INFO - Epoch(train) [36][50/293] lr: 5.000000e-04 eta: 9:40:48 time: 0.793499 data_time: 0.107996 memory: 21676 loss_kpt: 0.000642 acc_pose: 0.821509 loss: 0.000642 2022/09/13 12:47:22 - mmengine - INFO - Epoch(train) [36][100/293] lr: 5.000000e-04 eta: 9:40:38 time: 0.777856 data_time: 0.096348 memory: 21676 loss_kpt: 0.000627 acc_pose: 0.769835 loss: 0.000627 2022/09/13 12:48:02 - mmengine - INFO - Epoch(train) [36][150/293] lr: 5.000000e-04 eta: 9:40:32 time: 0.794643 data_time: 0.094044 memory: 21676 loss_kpt: 0.000637 acc_pose: 0.799078 loss: 0.000637 2022/09/13 12:48:41 - mmengine - INFO - Epoch(train) [36][200/293] lr: 5.000000e-04 eta: 9:40:24 time: 0.785950 data_time: 0.095264 memory: 21676 loss_kpt: 0.000648 acc_pose: 0.799164 loss: 0.000648 2022/09/13 12:49:20 - mmengine - INFO - Epoch(train) [36][250/293] lr: 5.000000e-04 eta: 9:40:14 time: 0.781785 data_time: 0.093071 memory: 21676 loss_kpt: 0.000644 acc_pose: 0.778310 loss: 0.000644 2022/09/13 12:49:53 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 12:49:53 - mmengine - INFO - Saving checkpoint at 36 epochs 2022/09/13 12:50:38 - mmengine - INFO - Epoch(train) [37][50/293] lr: 5.000000e-04 eta: 9:37:17 time: 0.796268 data_time: 0.113967 memory: 21676 loss_kpt: 0.000638 acc_pose: 0.842160 loss: 0.000638 2022/09/13 12:51:17 - mmengine - INFO - Epoch(train) [37][100/293] lr: 5.000000e-04 eta: 9:37:08 time: 0.783487 data_time: 0.102854 memory: 21676 loss_kpt: 0.000661 acc_pose: 0.834288 loss: 0.000661 2022/09/13 12:51:57 - mmengine - INFO - Epoch(train) [37][150/293] lr: 5.000000e-04 eta: 9:36:58 time: 0.784553 data_time: 0.107284 memory: 21676 loss_kpt: 0.000648 acc_pose: 0.794765 loss: 0.000648 2022/09/13 12:52:35 - mmengine - INFO - Epoch(train) [37][200/293] lr: 5.000000e-04 eta: 9:36:45 time: 0.769158 data_time: 0.105552 memory: 21676 loss_kpt: 0.000633 acc_pose: 0.815634 loss: 0.000633 2022/09/13 12:53:13 - mmengine - INFO - Epoch(train) [37][250/293] lr: 5.000000e-04 eta: 9:36:30 time: 0.763894 data_time: 0.102290 memory: 21676 loss_kpt: 0.000653 acc_pose: 0.779454 loss: 0.000653 2022/09/13 12:53:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 12:53:46 - mmengine - INFO - Saving checkpoint at 37 epochs 2022/09/13 12:54:30 - mmengine - INFO - Epoch(train) [38][50/293] lr: 5.000000e-04 eta: 9:33:35 time: 0.784687 data_time: 0.118590 memory: 21676 loss_kpt: 0.000648 acc_pose: 0.853961 loss: 0.000648 2022/09/13 12:55:09 - mmengine - INFO - Epoch(train) [38][100/293] lr: 5.000000e-04 eta: 9:33:23 time: 0.775213 data_time: 0.098391 memory: 21676 loss_kpt: 0.000636 acc_pose: 0.798765 loss: 0.000636 2022/09/13 12:55:48 - mmengine - INFO - Epoch(train) [38][150/293] lr: 5.000000e-04 eta: 9:33:11 time: 0.777738 data_time: 0.102871 memory: 21676 loss_kpt: 0.000638 acc_pose: 0.774693 loss: 0.000638 2022/09/13 12:55:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 12:56:27 - mmengine - INFO - Epoch(train) [38][200/293] lr: 5.000000e-04 eta: 9:32:59 time: 0.776397 data_time: 0.108319 memory: 21676 loss_kpt: 0.000627 acc_pose: 0.807451 loss: 0.000627 2022/09/13 12:57:05 - mmengine - INFO - Epoch(train) [38][250/293] lr: 5.000000e-04 eta: 9:32:45 time: 0.770384 data_time: 0.104013 memory: 21676 loss_kpt: 0.000646 acc_pose: 0.735637 loss: 0.000646 2022/09/13 12:57:38 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 12:57:38 - mmengine - INFO - Saving checkpoint at 38 epochs 2022/09/13 12:58:22 - mmengine - INFO - Epoch(train) [39][50/293] lr: 5.000000e-04 eta: 9:29:54 time: 0.786137 data_time: 0.106376 memory: 21676 loss_kpt: 0.000644 acc_pose: 0.775595 loss: 0.000644 2022/09/13 12:59:02 - mmengine - INFO - Epoch(train) [39][100/293] lr: 5.000000e-04 eta: 9:29:46 time: 0.794755 data_time: 0.099080 memory: 21676 loss_kpt: 0.000640 acc_pose: 0.811927 loss: 0.000640 2022/09/13 12:59:41 - mmengine - INFO - Epoch(train) [39][150/293] lr: 5.000000e-04 eta: 9:29:35 time: 0.784017 data_time: 0.096775 memory: 21676 loss_kpt: 0.000631 acc_pose: 0.809199 loss: 0.000631 2022/09/13 13:00:20 - mmengine - INFO - Epoch(train) [39][200/293] lr: 5.000000e-04 eta: 9:29:22 time: 0.776860 data_time: 0.098970 memory: 21676 loss_kpt: 0.000648 acc_pose: 0.827187 loss: 0.000648 2022/09/13 13:00:58 - mmengine - INFO - Epoch(train) [39][250/293] lr: 5.000000e-04 eta: 9:29:09 time: 0.775193 data_time: 0.102636 memory: 21676 loss_kpt: 0.000645 acc_pose: 0.843787 loss: 0.000645 2022/09/13 13:01:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 13:01:32 - mmengine - INFO - Saving checkpoint at 39 epochs 2022/09/13 13:02:16 - mmengine - INFO - Epoch(train) [40][50/293] lr: 5.000000e-04 eta: 9:26:22 time: 0.791499 data_time: 0.108196 memory: 21676 loss_kpt: 0.000648 acc_pose: 0.824888 loss: 0.000648 2022/09/13 13:02:55 - mmengine - INFO - Epoch(train) [40][100/293] lr: 5.000000e-04 eta: 9:26:10 time: 0.780621 data_time: 0.101082 memory: 21676 loss_kpt: 0.000647 acc_pose: 0.811310 loss: 0.000647 2022/09/13 13:03:35 - mmengine - INFO - Epoch(train) [40][150/293] lr: 5.000000e-04 eta: 9:25:59 time: 0.786944 data_time: 0.101542 memory: 21676 loss_kpt: 0.000642 acc_pose: 0.829773 loss: 0.000642 2022/09/13 13:04:14 - mmengine - INFO - Epoch(train) [40][200/293] lr: 5.000000e-04 eta: 9:25:48 time: 0.785182 data_time: 0.104770 memory: 21676 loss_kpt: 0.000646 acc_pose: 0.764148 loss: 0.000646 2022/09/13 13:04:53 - mmengine - INFO - Epoch(train) [40][250/293] lr: 5.000000e-04 eta: 9:25:35 time: 0.780721 data_time: 0.103183 memory: 21676 loss_kpt: 0.000643 acc_pose: 0.797292 loss: 0.000643 2022/09/13 13:05:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 13:05:26 - mmengine - INFO - Saving checkpoint at 40 epochs 2022/09/13 13:05:39 - mmengine - INFO - Epoch(val) [40][50/407] eta: 0:01:05 time: 0.183382 data_time: 0.015771 memory: 21676 2022/09/13 13:05:48 - mmengine - INFO - Epoch(val) [40][100/407] eta: 0:00:53 time: 0.174628 data_time: 0.008648 memory: 1375 2022/09/13 13:05:57 - mmengine - INFO - Epoch(val) [40][150/407] eta: 0:00:45 time: 0.176466 data_time: 0.008381 memory: 1375 2022/09/13 13:06:06 - mmengine - INFO - Epoch(val) [40][200/407] eta: 0:00:36 time: 0.177617 data_time: 0.009063 memory: 1375 2022/09/13 13:06:15 - mmengine - INFO - Epoch(val) [40][250/407] eta: 0:00:27 time: 0.176250 data_time: 0.009117 memory: 1375 2022/09/13 13:06:24 - mmengine - INFO - Epoch(val) [40][300/407] eta: 0:00:19 time: 0.177762 data_time: 0.011877 memory: 1375 2022/09/13 13:06:33 - mmengine - INFO - Epoch(val) [40][350/407] eta: 0:00:10 time: 0.179515 data_time: 0.010131 memory: 1375 2022/09/13 13:06:42 - mmengine - INFO - Epoch(val) [40][400/407] eta: 0:00:01 time: 0.180935 data_time: 0.016500 memory: 1375 2022/09/13 13:07:18 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 13:07:32 - mmengine - INFO - Epoch(val) [40][407/407] coco/AP: 0.734983 coco/AP .5: 0.895262 coco/AP .75: 0.801417 coco/AP (M): 0.693341 coco/AP (L): 0.807577 coco/AR: 0.785800 coco/AR .5: 0.933092 coco/AR .75: 0.846820 coco/AR (M): 0.739279 coco/AR (L): 0.852620 2022/09/13 13:07:32 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220913/udp_w32_384_v1/best_coco/AP_epoch_30.pth is removed 2022/09/13 13:07:35 - mmengine - INFO - The best checkpoint with 0.7350 coco/AP at 40 epoch is saved to best_coco/AP_epoch_40.pth. 2022/09/13 13:08:15 - mmengine - INFO - Epoch(train) [41][50/293] lr: 5.000000e-04 eta: 9:22:53 time: 0.797796 data_time: 0.101296 memory: 21676 loss_kpt: 0.000629 acc_pose: 0.794665 loss: 0.000629 2022/09/13 13:08:53 - mmengine - INFO - Epoch(train) [41][100/293] lr: 5.000000e-04 eta: 9:22:40 time: 0.776854 data_time: 0.092667 memory: 21676 loss_kpt: 0.000634 acc_pose: 0.860404 loss: 0.000634 2022/09/13 13:09:33 - mmengine - INFO - Epoch(train) [41][150/293] lr: 5.000000e-04 eta: 9:22:28 time: 0.783258 data_time: 0.095467 memory: 21676 loss_kpt: 0.000627 acc_pose: 0.839467 loss: 0.000627 2022/09/13 13:10:10 - mmengine - INFO - Epoch(train) [41][200/293] lr: 5.000000e-04 eta: 9:22:10 time: 0.755741 data_time: 0.092353 memory: 21676 loss_kpt: 0.000638 acc_pose: 0.833966 loss: 0.000638 2022/09/13 13:10:48 - mmengine - INFO - Epoch(train) [41][250/293] lr: 5.000000e-04 eta: 9:21:52 time: 0.760408 data_time: 0.094938 memory: 21676 loss_kpt: 0.000638 acc_pose: 0.780843 loss: 0.000638 2022/09/13 13:11:12 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 13:11:21 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 13:11:21 - mmengine - INFO - Saving checkpoint at 41 epochs 2022/09/13 13:12:05 - mmengine - INFO - Epoch(train) [42][50/293] lr: 5.000000e-04 eta: 9:19:12 time: 0.790552 data_time: 0.103754 memory: 21676 loss_kpt: 0.000627 acc_pose: 0.794682 loss: 0.000627 2022/09/13 13:12:44 - mmengine - INFO - Epoch(train) [42][100/293] lr: 5.000000e-04 eta: 9:19:00 time: 0.785136 data_time: 0.098658 memory: 21676 loss_kpt: 0.000643 acc_pose: 0.815333 loss: 0.000643 2022/09/13 13:13:24 - mmengine - INFO - Epoch(train) [42][150/293] lr: 5.000000e-04 eta: 9:18:47 time: 0.786388 data_time: 0.092359 memory: 21676 loss_kpt: 0.000627 acc_pose: 0.836977 loss: 0.000627 2022/09/13 13:14:03 - mmengine - INFO - Epoch(train) [42][200/293] lr: 5.000000e-04 eta: 9:18:34 time: 0.779427 data_time: 0.091671 memory: 21676 loss_kpt: 0.000622 acc_pose: 0.832142 loss: 0.000622 2022/09/13 13:14:42 - mmengine - INFO - Epoch(train) [42][250/293] lr: 5.000000e-04 eta: 9:18:21 time: 0.786937 data_time: 0.092639 memory: 21676 loss_kpt: 0.000617 acc_pose: 0.827176 loss: 0.000617 2022/09/13 13:15:15 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 13:15:15 - mmengine - INFO - Saving checkpoint at 42 epochs 2022/09/13 13:15:59 - mmengine - INFO - Epoch(train) [43][50/293] lr: 5.000000e-04 eta: 9:15:45 time: 0.794697 data_time: 0.111988 memory: 21676 loss_kpt: 0.000621 acc_pose: 0.802955 loss: 0.000621 2022/09/13 13:16:38 - mmengine - INFO - Epoch(train) [43][100/293] lr: 5.000000e-04 eta: 9:15:31 time: 0.779126 data_time: 0.099424 memory: 21676 loss_kpt: 0.000627 acc_pose: 0.813884 loss: 0.000627 2022/09/13 13:17:17 - mmengine - INFO - Epoch(train) [43][150/293] lr: 5.000000e-04 eta: 9:15:18 time: 0.786999 data_time: 0.096719 memory: 21676 loss_kpt: 0.000648 acc_pose: 0.829007 loss: 0.000648 2022/09/13 13:17:56 - mmengine - INFO - Epoch(train) [43][200/293] lr: 5.000000e-04 eta: 9:15:03 time: 0.776954 data_time: 0.093202 memory: 21676 loss_kpt: 0.000629 acc_pose: 0.841490 loss: 0.000629 2022/09/13 13:18:35 - mmengine - INFO - Epoch(train) [43][250/293] lr: 5.000000e-04 eta: 9:14:49 time: 0.779788 data_time: 0.095969 memory: 21676 loss_kpt: 0.000636 acc_pose: 0.762968 loss: 0.000636 2022/09/13 13:19:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 13:19:08 - mmengine - INFO - Saving checkpoint at 43 epochs 2022/09/13 13:19:52 - mmengine - INFO - Epoch(train) [44][50/293] lr: 5.000000e-04 eta: 9:12:14 time: 0.790180 data_time: 0.106988 memory: 21676 loss_kpt: 0.000621 acc_pose: 0.818858 loss: 0.000621 2022/09/13 13:20:32 - mmengine - INFO - Epoch(train) [44][100/293] lr: 5.000000e-04 eta: 9:12:02 time: 0.792459 data_time: 0.096075 memory: 21676 loss_kpt: 0.000627 acc_pose: 0.801928 loss: 0.000627 2022/09/13 13:21:11 - mmengine - INFO - Epoch(train) [44][150/293] lr: 5.000000e-04 eta: 9:11:48 time: 0.779462 data_time: 0.105310 memory: 21676 loss_kpt: 0.000634 acc_pose: 0.808266 loss: 0.000634 2022/09/13 13:21:51 - mmengine - INFO - Epoch(train) [44][200/293] lr: 5.000000e-04 eta: 9:11:35 time: 0.789961 data_time: 0.098891 memory: 21676 loss_kpt: 0.000627 acc_pose: 0.809348 loss: 0.000627 2022/09/13 13:22:29 - mmengine - INFO - Epoch(train) [44][250/293] lr: 5.000000e-04 eta: 9:11:19 time: 0.772009 data_time: 0.094131 memory: 21676 loss_kpt: 0.000648 acc_pose: 0.787899 loss: 0.000648 2022/09/13 13:23:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 13:23:02 - mmengine - INFO - Saving checkpoint at 44 epochs 2022/09/13 13:23:47 - mmengine - INFO - Epoch(train) [45][50/293] lr: 5.000000e-04 eta: 9:08:49 time: 0.803013 data_time: 0.108269 memory: 21676 loss_kpt: 0.000625 acc_pose: 0.809375 loss: 0.000625 2022/09/13 13:24:26 - mmengine - INFO - Epoch(train) [45][100/293] lr: 5.000000e-04 eta: 9:08:34 time: 0.777688 data_time: 0.092642 memory: 21676 loss_kpt: 0.000643 acc_pose: 0.796158 loss: 0.000643 2022/09/13 13:24:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 13:25:04 - mmengine - INFO - Epoch(train) [45][150/293] lr: 5.000000e-04 eta: 9:08:15 time: 0.758235 data_time: 0.093131 memory: 21676 loss_kpt: 0.000624 acc_pose: 0.798869 loss: 0.000624 2022/09/13 13:25:42 - mmengine - INFO - Epoch(train) [45][200/293] lr: 5.000000e-04 eta: 9:07:57 time: 0.763978 data_time: 0.100606 memory: 21676 loss_kpt: 0.000623 acc_pose: 0.814249 loss: 0.000623 2022/09/13 13:26:20 - mmengine - INFO - Epoch(train) [45][250/293] lr: 5.000000e-04 eta: 9:07:38 time: 0.761052 data_time: 0.092195 memory: 21676 loss_kpt: 0.000630 acc_pose: 0.835408 loss: 0.000630 2022/09/13 13:26:52 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 13:26:52 - mmengine - INFO - Saving checkpoint at 45 epochs 2022/09/13 13:27:35 - mmengine - INFO - Epoch(train) [46][50/293] lr: 5.000000e-04 eta: 9:05:07 time: 0.780987 data_time: 0.105918 memory: 21676 loss_kpt: 0.000636 acc_pose: 0.818637 loss: 0.000636 2022/09/13 13:28:14 - mmengine - INFO - Epoch(train) [46][100/293] lr: 5.000000e-04 eta: 9:04:50 time: 0.770547 data_time: 0.095751 memory: 21676 loss_kpt: 0.000619 acc_pose: 0.814746 loss: 0.000619 2022/09/13 13:28:52 - mmengine - INFO - Epoch(train) [46][150/293] lr: 5.000000e-04 eta: 9:04:30 time: 0.755775 data_time: 0.095246 memory: 21676 loss_kpt: 0.000625 acc_pose: 0.836590 loss: 0.000625 2022/09/13 13:29:30 - mmengine - INFO - Epoch(train) [46][200/293] lr: 5.000000e-04 eta: 9:04:11 time: 0.761733 data_time: 0.099189 memory: 21676 loss_kpt: 0.000615 acc_pose: 0.864741 loss: 0.000615 2022/09/13 13:30:07 - mmengine - INFO - Epoch(train) [46][250/293] lr: 5.000000e-04 eta: 9:03:51 time: 0.753569 data_time: 0.094572 memory: 21676 loss_kpt: 0.000634 acc_pose: 0.823514 loss: 0.000634 2022/09/13 13:30:39 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 13:30:39 - mmengine - INFO - Saving checkpoint at 46 epochs 2022/09/13 13:31:23 - mmengine - INFO - Epoch(train) [47][50/293] lr: 5.000000e-04 eta: 9:01:24 time: 0.792475 data_time: 0.111136 memory: 21676 loss_kpt: 0.000631 acc_pose: 0.813883 loss: 0.000631 2022/09/13 13:32:02 - mmengine - INFO - Epoch(train) [47][100/293] lr: 5.000000e-04 eta: 9:01:08 time: 0.776972 data_time: 0.094641 memory: 21676 loss_kpt: 0.000624 acc_pose: 0.796448 loss: 0.000624 2022/09/13 13:32:41 - mmengine - INFO - Epoch(train) [47][150/293] lr: 5.000000e-04 eta: 9:00:53 time: 0.785891 data_time: 0.096013 memory: 21676 loss_kpt: 0.000621 acc_pose: 0.807004 loss: 0.000621 2022/09/13 13:33:19 - mmengine - INFO - Epoch(train) [47][200/293] lr: 5.000000e-04 eta: 9:00:33 time: 0.751425 data_time: 0.099424 memory: 21676 loss_kpt: 0.000624 acc_pose: 0.836073 loss: 0.000624 2022/09/13 13:33:57 - mmengine - INFO - Epoch(train) [47][250/293] lr: 5.000000e-04 eta: 9:00:13 time: 0.761830 data_time: 0.095449 memory: 21676 loss_kpt: 0.000618 acc_pose: 0.830099 loss: 0.000618 2022/09/13 13:34:29 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 13:34:29 - mmengine - INFO - Saving checkpoint at 47 epochs 2022/09/13 13:35:13 - mmengine - INFO - Epoch(train) [48][50/293] lr: 5.000000e-04 eta: 8:57:49 time: 0.791235 data_time: 0.114203 memory: 21676 loss_kpt: 0.000622 acc_pose: 0.813380 loss: 0.000622 2022/09/13 13:35:53 - mmengine - INFO - Epoch(train) [48][100/293] lr: 5.000000e-04 eta: 8:57:34 time: 0.786454 data_time: 0.096317 memory: 21676 loss_kpt: 0.000617 acc_pose: 0.840610 loss: 0.000617 2022/09/13 13:36:32 - mmengine - INFO - Epoch(train) [48][150/293] lr: 5.000000e-04 eta: 8:57:21 time: 0.795897 data_time: 0.094198 memory: 21676 loss_kpt: 0.000619 acc_pose: 0.811312 loss: 0.000619 2022/09/13 13:37:11 - mmengine - INFO - Epoch(train) [48][200/293] lr: 5.000000e-04 eta: 8:57:03 time: 0.771517 data_time: 0.096128 memory: 21676 loss_kpt: 0.000643 acc_pose: 0.830885 loss: 0.000643 2022/09/13 13:37:34 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 13:37:50 - mmengine - INFO - Epoch(train) [48][250/293] lr: 5.000000e-04 eta: 8:56:46 time: 0.777415 data_time: 0.091897 memory: 21676 loss_kpt: 0.000638 acc_pose: 0.812723 loss: 0.000638 2022/09/13 13:38:23 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 13:38:23 - mmengine - INFO - Saving checkpoint at 48 epochs 2022/09/13 13:39:07 - mmengine - INFO - Epoch(train) [49][50/293] lr: 5.000000e-04 eta: 8:54:23 time: 0.784386 data_time: 0.113167 memory: 21676 loss_kpt: 0.000623 acc_pose: 0.826350 loss: 0.000623 2022/09/13 13:39:46 - mmengine - INFO - Epoch(train) [49][100/293] lr: 5.000000e-04 eta: 8:54:07 time: 0.786276 data_time: 0.095780 memory: 21676 loss_kpt: 0.000603 acc_pose: 0.834350 loss: 0.000603 2022/09/13 13:40:26 - mmengine - INFO - Epoch(train) [49][150/293] lr: 5.000000e-04 eta: 8:53:52 time: 0.788550 data_time: 0.100659 memory: 21676 loss_kpt: 0.000617 acc_pose: 0.806279 loss: 0.000617 2022/09/13 13:41:05 - mmengine - INFO - Epoch(train) [49][200/293] lr: 5.000000e-04 eta: 8:53:36 time: 0.783916 data_time: 0.098236 memory: 21676 loss_kpt: 0.000610 acc_pose: 0.841881 loss: 0.000610 2022/09/13 13:41:44 - mmengine - INFO - Epoch(train) [49][250/293] lr: 5.000000e-04 eta: 8:53:20 time: 0.786356 data_time: 0.099892 memory: 21676 loss_kpt: 0.000640 acc_pose: 0.868710 loss: 0.000640 2022/09/13 13:42:17 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 13:42:17 - mmengine - INFO - Saving checkpoint at 49 epochs 2022/09/13 13:43:01 - mmengine - INFO - Epoch(train) [50][50/293] lr: 5.000000e-04 eta: 8:50:59 time: 0.784912 data_time: 0.115173 memory: 21676 loss_kpt: 0.000628 acc_pose: 0.771052 loss: 0.000628 2022/09/13 13:43:40 - mmengine - INFO - Epoch(train) [50][100/293] lr: 5.000000e-04 eta: 8:50:42 time: 0.775426 data_time: 0.103082 memory: 21676 loss_kpt: 0.000617 acc_pose: 0.830187 loss: 0.000617 2022/09/13 13:44:18 - mmengine - INFO - Epoch(train) [50][150/293] lr: 5.000000e-04 eta: 8:50:23 time: 0.768103 data_time: 0.103358 memory: 21676 loss_kpt: 0.000624 acc_pose: 0.824329 loss: 0.000624 2022/09/13 13:44:57 - mmengine - INFO - Epoch(train) [50][200/293] lr: 5.000000e-04 eta: 8:50:05 time: 0.776186 data_time: 0.107168 memory: 21676 loss_kpt: 0.000615 acc_pose: 0.836691 loss: 0.000615 2022/09/13 13:45:35 - mmengine - INFO - Epoch(train) [50][250/293] lr: 5.000000e-04 eta: 8:49:46 time: 0.769092 data_time: 0.098633 memory: 21676 loss_kpt: 0.000612 acc_pose: 0.802599 loss: 0.000612 2022/09/13 13:46:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 13:46:07 - mmengine - INFO - Saving checkpoint at 50 epochs 2022/09/13 13:46:22 - mmengine - INFO - Epoch(val) [50][50/407] eta: 0:01:05 time: 0.183682 data_time: 0.015288 memory: 21676 2022/09/13 13:46:30 - mmengine - INFO - Epoch(val) [50][100/407] eta: 0:00:54 time: 0.177092 data_time: 0.009400 memory: 1375 2022/09/13 13:46:39 - mmengine - INFO - Epoch(val) [50][150/407] eta: 0:00:45 time: 0.176702 data_time: 0.008903 memory: 1375 2022/09/13 13:46:48 - mmengine - INFO - Epoch(val) [50][200/407] eta: 0:00:36 time: 0.175381 data_time: 0.008662 memory: 1375 2022/09/13 13:46:57 - mmengine - INFO - Epoch(val) [50][250/407] eta: 0:00:27 time: 0.175429 data_time: 0.008260 memory: 1375 2022/09/13 13:47:06 - mmengine - INFO - Epoch(val) [50][300/407] eta: 0:00:18 time: 0.177311 data_time: 0.009047 memory: 1375 2022/09/13 13:47:14 - mmengine - INFO - Epoch(val) [50][350/407] eta: 0:00:10 time: 0.175542 data_time: 0.009258 memory: 1375 2022/09/13 13:47:23 - mmengine - INFO - Epoch(val) [50][400/407] eta: 0:00:01 time: 0.174198 data_time: 0.008183 memory: 1375 2022/09/13 13:47:59 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 13:48:13 - mmengine - INFO - Epoch(val) [50][407/407] coco/AP: 0.740947 coco/AP .5: 0.897782 coco/AP .75: 0.808523 coco/AP (M): 0.700878 coco/AP (L): 0.811481 coco/AR: 0.792003 coco/AR .5: 0.934981 coco/AR .75: 0.852015 coco/AR (M): 0.747309 coco/AR (L): 0.856373 2022/09/13 13:48:13 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220913/udp_w32_384_v1/best_coco/AP_epoch_40.pth is removed 2022/09/13 13:48:16 - mmengine - INFO - The best checkpoint with 0.7409 coco/AP at 50 epoch is saved to best_coco/AP_epoch_50.pth. 2022/09/13 13:48:56 - mmengine - INFO - Epoch(train) [51][50/293] lr: 5.000000e-04 eta: 8:47:28 time: 0.790829 data_time: 0.101728 memory: 21676 loss_kpt: 0.000611 acc_pose: 0.829505 loss: 0.000611 2022/09/13 13:49:35 - mmengine - INFO - Epoch(train) [51][100/293] lr: 5.000000e-04 eta: 8:47:12 time: 0.784805 data_time: 0.099856 memory: 21676 loss_kpt: 0.000614 acc_pose: 0.806267 loss: 0.000614 2022/09/13 13:50:14 - mmengine - INFO - Epoch(train) [51][150/293] lr: 5.000000e-04 eta: 8:46:54 time: 0.779845 data_time: 0.092456 memory: 21676 loss_kpt: 0.000609 acc_pose: 0.836300 loss: 0.000609 2022/09/13 13:50:53 - mmengine - INFO - Epoch(train) [51][200/293] lr: 5.000000e-04 eta: 8:46:37 time: 0.781690 data_time: 0.098808 memory: 21676 loss_kpt: 0.000609 acc_pose: 0.818443 loss: 0.000609 2022/09/13 13:51:31 - mmengine - INFO - Epoch(train) [51][250/293] lr: 5.000000e-04 eta: 8:46:16 time: 0.757565 data_time: 0.094262 memory: 21676 loss_kpt: 0.000621 acc_pose: 0.803322 loss: 0.000621 2022/09/13 13:52:03 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 13:52:03 - mmengine - INFO - Saving checkpoint at 51 epochs 2022/09/13 13:52:46 - mmengine - INFO - Epoch(train) [52][50/293] lr: 5.000000e-04 eta: 8:43:56 time: 0.761946 data_time: 0.100899 memory: 21676 loss_kpt: 0.000618 acc_pose: 0.839981 loss: 0.000618 2022/09/13 13:52:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 13:53:24 - mmengine - INFO - Epoch(train) [52][100/293] lr: 5.000000e-04 eta: 8:43:35 time: 0.761107 data_time: 0.091634 memory: 21676 loss_kpt: 0.000598 acc_pose: 0.878703 loss: 0.000598 2022/09/13 13:54:02 - mmengine - INFO - Epoch(train) [52][150/293] lr: 5.000000e-04 eta: 8:43:15 time: 0.766319 data_time: 0.092376 memory: 21676 loss_kpt: 0.000623 acc_pose: 0.780602 loss: 0.000623 2022/09/13 13:54:40 - mmengine - INFO - Epoch(train) [52][200/293] lr: 5.000000e-04 eta: 8:42:54 time: 0.757974 data_time: 0.097355 memory: 21676 loss_kpt: 0.000626 acc_pose: 0.800122 loss: 0.000626 2022/09/13 13:55:18 - mmengine - INFO - Epoch(train) [52][250/293] lr: 5.000000e-04 eta: 8:42:32 time: 0.755564 data_time: 0.092015 memory: 21676 loss_kpt: 0.000609 acc_pose: 0.803771 loss: 0.000609 2022/09/13 13:55:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 13:55:50 - mmengine - INFO - Saving checkpoint at 52 epochs 2022/09/13 13:56:33 - mmengine - INFO - Epoch(train) [53][50/293] lr: 5.000000e-04 eta: 8:40:18 time: 0.788460 data_time: 0.107814 memory: 21676 loss_kpt: 0.000600 acc_pose: 0.853620 loss: 0.000600 2022/09/13 13:57:12 - mmengine - INFO - Epoch(train) [53][100/293] lr: 5.000000e-04 eta: 8:39:59 time: 0.769251 data_time: 0.102336 memory: 21676 loss_kpt: 0.000614 acc_pose: 0.825973 loss: 0.000614 2022/09/13 13:57:51 - mmengine - INFO - Epoch(train) [53][150/293] lr: 5.000000e-04 eta: 8:39:41 time: 0.784710 data_time: 0.108313 memory: 21676 loss_kpt: 0.000608 acc_pose: 0.828865 loss: 0.000608 2022/09/13 13:58:30 - mmengine - INFO - Epoch(train) [53][200/293] lr: 5.000000e-04 eta: 8:39:22 time: 0.774194 data_time: 0.103896 memory: 21676 loss_kpt: 0.000636 acc_pose: 0.780861 loss: 0.000636 2022/09/13 13:59:09 - mmengine - INFO - Epoch(train) [53][250/293] lr: 5.000000e-04 eta: 8:39:04 time: 0.779394 data_time: 0.109170 memory: 21676 loss_kpt: 0.000613 acc_pose: 0.801236 loss: 0.000613 2022/09/13 13:59:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 13:59:42 - mmengine - INFO - Saving checkpoint at 53 epochs 2022/09/13 14:00:27 - mmengine - INFO - Epoch(train) [54][50/293] lr: 5.000000e-04 eta: 8:36:53 time: 0.801631 data_time: 0.108418 memory: 21676 loss_kpt: 0.000611 acc_pose: 0.819984 loss: 0.000611 2022/09/13 14:01:06 - mmengine - INFO - Epoch(train) [54][100/293] lr: 5.000000e-04 eta: 8:36:35 time: 0.780474 data_time: 0.100971 memory: 21676 loss_kpt: 0.000614 acc_pose: 0.791600 loss: 0.000614 2022/09/13 14:01:45 - mmengine - INFO - Epoch(train) [54][150/293] lr: 5.000000e-04 eta: 8:36:18 time: 0.791262 data_time: 0.100184 memory: 21676 loss_kpt: 0.000629 acc_pose: 0.803186 loss: 0.000629 2022/09/13 14:02:25 - mmengine - INFO - Epoch(train) [54][200/293] lr: 5.000000e-04 eta: 8:36:01 time: 0.789435 data_time: 0.104047 memory: 21676 loss_kpt: 0.000622 acc_pose: 0.784433 loss: 0.000622 2022/09/13 14:03:04 - mmengine - INFO - Epoch(train) [54][250/293] lr: 5.000000e-04 eta: 8:35:43 time: 0.782504 data_time: 0.101495 memory: 21676 loss_kpt: 0.000617 acc_pose: 0.816820 loss: 0.000617 2022/09/13 14:03:37 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 14:03:37 - mmengine - INFO - Saving checkpoint at 54 epochs 2022/09/13 14:04:21 - mmengine - INFO - Epoch(train) [55][50/293] lr: 5.000000e-04 eta: 8:33:34 time: 0.800099 data_time: 0.106822 memory: 21676 loss_kpt: 0.000619 acc_pose: 0.818691 loss: 0.000619 2022/09/13 14:05:00 - mmengine - INFO - Epoch(train) [55][100/293] lr: 5.000000e-04 eta: 8:33:15 time: 0.776530 data_time: 0.097415 memory: 21676 loss_kpt: 0.000601 acc_pose: 0.840015 loss: 0.000601 2022/09/13 14:05:39 - mmengine - INFO - Epoch(train) [55][150/293] lr: 5.000000e-04 eta: 8:32:56 time: 0.779258 data_time: 0.096327 memory: 21676 loss_kpt: 0.000603 acc_pose: 0.768287 loss: 0.000603 2022/09/13 14:06:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 14:06:18 - mmengine - INFO - Epoch(train) [55][200/293] lr: 5.000000e-04 eta: 8:32:36 time: 0.771121 data_time: 0.100486 memory: 21676 loss_kpt: 0.000615 acc_pose: 0.829516 loss: 0.000615 2022/09/13 14:06:55 - mmengine - INFO - Epoch(train) [55][250/293] lr: 5.000000e-04 eta: 8:32:12 time: 0.749939 data_time: 0.095591 memory: 21676 loss_kpt: 0.000598 acc_pose: 0.816778 loss: 0.000598 2022/09/13 14:07:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 14:07:27 - mmengine - INFO - Saving checkpoint at 55 epochs 2022/09/13 14:08:11 - mmengine - INFO - Epoch(train) [56][50/293] lr: 5.000000e-04 eta: 8:30:03 time: 0.786415 data_time: 0.111996 memory: 21676 loss_kpt: 0.000600 acc_pose: 0.819498 loss: 0.000600 2022/09/13 14:08:50 - mmengine - INFO - Epoch(train) [56][100/293] lr: 5.000000e-04 eta: 8:29:44 time: 0.777201 data_time: 0.100399 memory: 21676 loss_kpt: 0.000615 acc_pose: 0.821973 loss: 0.000615 2022/09/13 14:09:30 - mmengine - INFO - Epoch(train) [56][150/293] lr: 5.000000e-04 eta: 8:29:26 time: 0.785509 data_time: 0.098779 memory: 21676 loss_kpt: 0.000602 acc_pose: 0.835311 loss: 0.000602 2022/09/13 14:10:09 - mmengine - INFO - Epoch(train) [56][200/293] lr: 5.000000e-04 eta: 8:29:07 time: 0.782594 data_time: 0.096824 memory: 21676 loss_kpt: 0.000605 acc_pose: 0.838750 loss: 0.000605 2022/09/13 14:10:48 - mmengine - INFO - Epoch(train) [56][250/293] lr: 5.000000e-04 eta: 8:28:48 time: 0.784830 data_time: 0.099807 memory: 21676 loss_kpt: 0.000605 acc_pose: 0.809066 loss: 0.000605 2022/09/13 14:11:21 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 14:11:21 - mmengine - INFO - Saving checkpoint at 56 epochs 2022/09/13 14:12:04 - mmengine - INFO - Epoch(train) [57][50/293] lr: 5.000000e-04 eta: 8:26:40 time: 0.779155 data_time: 0.107117 memory: 21676 loss_kpt: 0.000620 acc_pose: 0.814785 loss: 0.000620 2022/09/13 14:12:44 - mmengine - INFO - Epoch(train) [57][100/293] lr: 5.000000e-04 eta: 8:26:21 time: 0.785041 data_time: 0.102285 memory: 21676 loss_kpt: 0.000610 acc_pose: 0.850516 loss: 0.000610 2022/09/13 14:13:22 - mmengine - INFO - Epoch(train) [57][150/293] lr: 5.000000e-04 eta: 8:26:01 time: 0.774945 data_time: 0.102406 memory: 21676 loss_kpt: 0.000628 acc_pose: 0.822226 loss: 0.000628 2022/09/13 14:14:02 - mmengine - INFO - Epoch(train) [57][200/293] lr: 5.000000e-04 eta: 8:25:42 time: 0.782204 data_time: 0.100781 memory: 21676 loss_kpt: 0.000598 acc_pose: 0.836309 loss: 0.000598 2022/09/13 14:14:41 - mmengine - INFO - Epoch(train) [57][250/293] lr: 5.000000e-04 eta: 8:25:23 time: 0.787270 data_time: 0.093900 memory: 21676 loss_kpt: 0.000628 acc_pose: 0.813418 loss: 0.000628 2022/09/13 14:15:14 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 14:15:14 - mmengine - INFO - Saving checkpoint at 57 epochs 2022/09/13 14:15:58 - mmengine - INFO - Epoch(train) [58][50/293] lr: 5.000000e-04 eta: 8:23:17 time: 0.787917 data_time: 0.103792 memory: 21676 loss_kpt: 0.000613 acc_pose: 0.761128 loss: 0.000613 2022/09/13 14:16:37 - mmengine - INFO - Epoch(train) [58][100/293] lr: 5.000000e-04 eta: 8:22:59 time: 0.788607 data_time: 0.091481 memory: 21676 loss_kpt: 0.000609 acc_pose: 0.799381 loss: 0.000609 2022/09/13 14:17:17 - mmengine - INFO - Epoch(train) [58][150/293] lr: 5.000000e-04 eta: 8:22:41 time: 0.791319 data_time: 0.092083 memory: 21676 loss_kpt: 0.000604 acc_pose: 0.828673 loss: 0.000604 2022/09/13 14:17:56 - mmengine - INFO - Epoch(train) [58][200/293] lr: 5.000000e-04 eta: 8:22:21 time: 0.782761 data_time: 0.092946 memory: 21676 loss_kpt: 0.000604 acc_pose: 0.800530 loss: 0.000604 2022/09/13 14:18:35 - mmengine - INFO - Epoch(train) [58][250/293] lr: 5.000000e-04 eta: 8:22:00 time: 0.770303 data_time: 0.098877 memory: 21676 loss_kpt: 0.000600 acc_pose: 0.817340 loss: 0.000600 2022/09/13 14:19:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 14:19:06 - mmengine - INFO - Saving checkpoint at 58 epochs 2022/09/13 14:19:16 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 14:19:51 - mmengine - INFO - Epoch(train) [59][50/293] lr: 5.000000e-04 eta: 8:19:58 time: 0.805984 data_time: 0.109574 memory: 21676 loss_kpt: 0.000613 acc_pose: 0.793013 loss: 0.000613 2022/09/13 14:20:31 - mmengine - INFO - Epoch(train) [59][100/293] lr: 5.000000e-04 eta: 8:19:39 time: 0.784977 data_time: 0.111065 memory: 21676 loss_kpt: 0.000621 acc_pose: 0.810907 loss: 0.000621 2022/09/13 14:21:09 - mmengine - INFO - Epoch(train) [59][150/293] lr: 5.000000e-04 eta: 8:19:18 time: 0.774067 data_time: 0.102290 memory: 21676 loss_kpt: 0.000604 acc_pose: 0.793435 loss: 0.000604 2022/09/13 14:21:48 - mmengine - INFO - Epoch(train) [59][200/293] lr: 5.000000e-04 eta: 8:18:57 time: 0.771267 data_time: 0.098786 memory: 21676 loss_kpt: 0.000612 acc_pose: 0.800071 loss: 0.000612 2022/09/13 14:22:26 - mmengine - INFO - Epoch(train) [59][250/293] lr: 5.000000e-04 eta: 8:18:35 time: 0.773836 data_time: 0.108609 memory: 21676 loss_kpt: 0.000592 acc_pose: 0.814771 loss: 0.000592 2022/09/13 14:22:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 14:22:59 - mmengine - INFO - Saving checkpoint at 59 epochs 2022/09/13 14:23:44 - mmengine - INFO - Epoch(train) [60][50/293] lr: 5.000000e-04 eta: 8:16:34 time: 0.797622 data_time: 0.104262 memory: 21676 loss_kpt: 0.000590 acc_pose: 0.810423 loss: 0.000590 2022/09/13 14:24:23 - mmengine - INFO - Epoch(train) [60][100/293] lr: 5.000000e-04 eta: 8:16:14 time: 0.778808 data_time: 0.095510 memory: 21676 loss_kpt: 0.000605 acc_pose: 0.854940 loss: 0.000605 2022/09/13 14:25:02 - mmengine - INFO - Epoch(train) [60][150/293] lr: 5.000000e-04 eta: 8:15:54 time: 0.781209 data_time: 0.098764 memory: 21676 loss_kpt: 0.000621 acc_pose: 0.858706 loss: 0.000621 2022/09/13 14:25:41 - mmengine - INFO - Epoch(train) [60][200/293] lr: 5.000000e-04 eta: 8:15:33 time: 0.783482 data_time: 0.093715 memory: 21676 loss_kpt: 0.000606 acc_pose: 0.835731 loss: 0.000606 2022/09/13 14:26:20 - mmengine - INFO - Epoch(train) [60][250/293] lr: 5.000000e-04 eta: 8:15:13 time: 0.784146 data_time: 0.097563 memory: 21676 loss_kpt: 0.000616 acc_pose: 0.803878 loss: 0.000616 2022/09/13 14:26:53 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 14:26:53 - mmengine - INFO - Saving checkpoint at 60 epochs 2022/09/13 14:27:07 - mmengine - INFO - Epoch(val) [60][50/407] eta: 0:01:05 time: 0.183119 data_time: 0.014510 memory: 21676 2022/09/13 14:27:16 - mmengine - INFO - Epoch(val) [60][100/407] eta: 0:00:55 time: 0.179812 data_time: 0.013816 memory: 1375 2022/09/13 14:27:24 - mmengine - INFO - Epoch(val) [60][150/407] eta: 0:00:44 time: 0.174282 data_time: 0.008473 memory: 1375 2022/09/13 14:27:33 - mmengine - INFO - Epoch(val) [60][200/407] eta: 0:00:37 time: 0.179158 data_time: 0.009279 memory: 1375 2022/09/13 14:27:42 - mmengine - INFO - Epoch(val) [60][250/407] eta: 0:00:27 time: 0.176254 data_time: 0.008498 memory: 1375 2022/09/13 14:27:51 - mmengine - INFO - Epoch(val) [60][300/407] eta: 0:00:18 time: 0.175372 data_time: 0.009009 memory: 1375 2022/09/13 14:28:00 - mmengine - INFO - Epoch(val) [60][350/407] eta: 0:00:10 time: 0.175934 data_time: 0.008826 memory: 1375 2022/09/13 14:28:08 - mmengine - INFO - Epoch(val) [60][400/407] eta: 0:00:01 time: 0.174118 data_time: 0.008276 memory: 1375 2022/09/13 14:28:45 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 14:28:59 - mmengine - INFO - Epoch(val) [60][407/407] coco/AP: 0.739375 coco/AP .5: 0.894120 coco/AP .75: 0.808561 coco/AP (M): 0.697815 coco/AP (L): 0.812849 coco/AR: 0.789232 coco/AR .5: 0.930888 coco/AR .75: 0.853117 coco/AR (M): 0.743021 coco/AR (L): 0.856076 2022/09/13 14:29:38 - mmengine - INFO - Epoch(train) [61][50/293] lr: 5.000000e-04 eta: 8:13:13 time: 0.791404 data_time: 0.104304 memory: 21676 loss_kpt: 0.000595 acc_pose: 0.847069 loss: 0.000595 2022/09/13 14:30:18 - mmengine - INFO - Epoch(train) [61][100/293] lr: 5.000000e-04 eta: 8:12:53 time: 0.790878 data_time: 0.101845 memory: 21676 loss_kpt: 0.000608 acc_pose: 0.804032 loss: 0.000608 2022/09/13 14:30:57 - mmengine - INFO - Epoch(train) [61][150/293] lr: 5.000000e-04 eta: 8:12:33 time: 0.779057 data_time: 0.095209 memory: 21676 loss_kpt: 0.000609 acc_pose: 0.794355 loss: 0.000609 2022/09/13 14:31:37 - mmengine - INFO - Epoch(train) [61][200/293] lr: 5.000000e-04 eta: 8:12:13 time: 0.791651 data_time: 0.098391 memory: 21676 loss_kpt: 0.000606 acc_pose: 0.836424 loss: 0.000606 2022/09/13 14:32:15 - mmengine - INFO - Epoch(train) [61][250/293] lr: 5.000000e-04 eta: 8:11:52 time: 0.776462 data_time: 0.098663 memory: 21676 loss_kpt: 0.000611 acc_pose: 0.802933 loss: 0.000611 2022/09/13 14:32:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 14:32:49 - mmengine - INFO - Saving checkpoint at 61 epochs 2022/09/13 14:33:33 - mmengine - INFO - Epoch(train) [62][50/293] lr: 5.000000e-04 eta: 8:09:54 time: 0.799882 data_time: 0.103273 memory: 21676 loss_kpt: 0.000596 acc_pose: 0.827811 loss: 0.000596 2022/09/13 14:34:12 - mmengine - INFO - Epoch(train) [62][100/293] lr: 5.000000e-04 eta: 8:09:33 time: 0.783973 data_time: 0.098977 memory: 21676 loss_kpt: 0.000593 acc_pose: 0.854004 loss: 0.000593 2022/09/13 14:34:34 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 14:34:51 - mmengine - INFO - Epoch(train) [62][150/293] lr: 5.000000e-04 eta: 8:09:12 time: 0.777076 data_time: 0.097912 memory: 21676 loss_kpt: 0.000607 acc_pose: 0.847682 loss: 0.000607 2022/09/13 14:35:29 - mmengine - INFO - Epoch(train) [62][200/293] lr: 5.000000e-04 eta: 8:08:48 time: 0.753675 data_time: 0.099611 memory: 21676 loss_kpt: 0.000633 acc_pose: 0.814839 loss: 0.000633 2022/09/13 14:36:07 - mmengine - INFO - Epoch(train) [62][250/293] lr: 5.000000e-04 eta: 8:08:24 time: 0.759244 data_time: 0.093134 memory: 21676 loss_kpt: 0.000602 acc_pose: 0.814848 loss: 0.000602 2022/09/13 14:36:40 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 14:36:40 - mmengine - INFO - Saving checkpoint at 62 epochs 2022/09/13 14:37:24 - mmengine - INFO - Epoch(train) [63][50/293] lr: 5.000000e-04 eta: 8:06:27 time: 0.800431 data_time: 0.109839 memory: 21676 loss_kpt: 0.000608 acc_pose: 0.803870 loss: 0.000608 2022/09/13 14:38:03 - mmengine - INFO - Epoch(train) [63][100/293] lr: 5.000000e-04 eta: 8:06:06 time: 0.783154 data_time: 0.099125 memory: 21676 loss_kpt: 0.000610 acc_pose: 0.811873 loss: 0.000610 2022/09/13 14:38:43 - mmengine - INFO - Epoch(train) [63][150/293] lr: 5.000000e-04 eta: 8:05:46 time: 0.788829 data_time: 0.098458 memory: 21676 loss_kpt: 0.000609 acc_pose: 0.799487 loss: 0.000609 2022/09/13 14:39:22 - mmengine - INFO - Epoch(train) [63][200/293] lr: 5.000000e-04 eta: 8:05:25 time: 0.784725 data_time: 0.100787 memory: 21676 loss_kpt: 0.000614 acc_pose: 0.810095 loss: 0.000614 2022/09/13 14:40:01 - mmengine - INFO - Epoch(train) [63][250/293] lr: 5.000000e-04 eta: 8:05:05 time: 0.785387 data_time: 0.095970 memory: 21676 loss_kpt: 0.000601 acc_pose: 0.809045 loss: 0.000601 2022/09/13 14:40:34 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 14:40:34 - mmengine - INFO - Saving checkpoint at 63 epochs 2022/09/13 14:41:20 - mmengine - INFO - Epoch(train) [64][50/293] lr: 5.000000e-04 eta: 8:03:10 time: 0.810137 data_time: 0.116200 memory: 21676 loss_kpt: 0.000619 acc_pose: 0.834484 loss: 0.000619 2022/09/13 14:41:59 - mmengine - INFO - Epoch(train) [64][100/293] lr: 5.000000e-04 eta: 8:02:49 time: 0.785809 data_time: 0.103150 memory: 21676 loss_kpt: 0.000596 acc_pose: 0.855051 loss: 0.000596 2022/09/13 14:42:38 - mmengine - INFO - Epoch(train) [64][150/293] lr: 5.000000e-04 eta: 8:02:29 time: 0.786806 data_time: 0.100673 memory: 21676 loss_kpt: 0.000604 acc_pose: 0.795804 loss: 0.000604 2022/09/13 14:43:17 - mmengine - INFO - Epoch(train) [64][200/293] lr: 5.000000e-04 eta: 8:02:07 time: 0.777079 data_time: 0.098632 memory: 21676 loss_kpt: 0.000611 acc_pose: 0.827337 loss: 0.000611 2022/09/13 14:43:56 - mmengine - INFO - Epoch(train) [64][250/293] lr: 5.000000e-04 eta: 8:01:46 time: 0.785856 data_time: 0.101348 memory: 21676 loss_kpt: 0.000605 acc_pose: 0.844096 loss: 0.000605 2022/09/13 14:44:29 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 14:44:29 - mmengine - INFO - Saving checkpoint at 64 epochs 2022/09/13 14:45:13 - mmengine - INFO - Epoch(train) [65][50/293] lr: 5.000000e-04 eta: 7:59:51 time: 0.796384 data_time: 0.107228 memory: 21676 loss_kpt: 0.000593 acc_pose: 0.763242 loss: 0.000593 2022/09/13 14:45:52 - mmengine - INFO - Epoch(train) [65][100/293] lr: 5.000000e-04 eta: 7:59:29 time: 0.779420 data_time: 0.094855 memory: 21676 loss_kpt: 0.000611 acc_pose: 0.795768 loss: 0.000611 2022/09/13 14:46:32 - mmengine - INFO - Epoch(train) [65][150/293] lr: 5.000000e-04 eta: 7:59:08 time: 0.783224 data_time: 0.091088 memory: 21676 loss_kpt: 0.000588 acc_pose: 0.808860 loss: 0.000588 2022/09/13 14:47:11 - mmengine - INFO - Epoch(train) [65][200/293] lr: 5.000000e-04 eta: 7:58:47 time: 0.794850 data_time: 0.094244 memory: 21676 loss_kpt: 0.000606 acc_pose: 0.854712 loss: 0.000606 2022/09/13 14:47:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 14:47:50 - mmengine - INFO - Epoch(train) [65][250/293] lr: 5.000000e-04 eta: 7:58:26 time: 0.783778 data_time: 0.091961 memory: 21676 loss_kpt: 0.000591 acc_pose: 0.777570 loss: 0.000591 2022/09/13 14:48:24 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 14:48:24 - mmengine - INFO - Saving checkpoint at 65 epochs 2022/09/13 14:49:08 - mmengine - INFO - Epoch(train) [66][50/293] lr: 5.000000e-04 eta: 7:56:32 time: 0.792094 data_time: 0.101635 memory: 21676 loss_kpt: 0.000598 acc_pose: 0.807414 loss: 0.000598 2022/09/13 14:49:47 - mmengine - INFO - Epoch(train) [66][100/293] lr: 5.000000e-04 eta: 7:56:10 time: 0.781123 data_time: 0.094300 memory: 21676 loss_kpt: 0.000592 acc_pose: 0.815511 loss: 0.000592 2022/09/13 14:50:26 - mmengine - INFO - Epoch(train) [66][150/293] lr: 5.000000e-04 eta: 7:55:47 time: 0.772871 data_time: 0.095645 memory: 21676 loss_kpt: 0.000589 acc_pose: 0.806614 loss: 0.000589 2022/09/13 14:51:04 - mmengine - INFO - Epoch(train) [66][200/293] lr: 5.000000e-04 eta: 7:55:23 time: 0.765604 data_time: 0.098160 memory: 21676 loss_kpt: 0.000584 acc_pose: 0.772365 loss: 0.000584 2022/09/13 14:51:41 - mmengine - INFO - Epoch(train) [66][250/293] lr: 5.000000e-04 eta: 7:54:58 time: 0.750338 data_time: 0.096048 memory: 21676 loss_kpt: 0.000597 acc_pose: 0.825670 loss: 0.000597 2022/09/13 14:52:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 14:52:13 - mmengine - INFO - Saving checkpoint at 66 epochs 2022/09/13 14:52:58 - mmengine - INFO - Epoch(train) [67][50/293] lr: 5.000000e-04 eta: 7:53:05 time: 0.791938 data_time: 0.107660 memory: 21676 loss_kpt: 0.000603 acc_pose: 0.820427 loss: 0.000603 2022/09/13 14:53:37 - mmengine - INFO - Epoch(train) [67][100/293] lr: 5.000000e-04 eta: 7:52:43 time: 0.785446 data_time: 0.100790 memory: 21676 loss_kpt: 0.000615 acc_pose: 0.810559 loss: 0.000615 2022/09/13 14:54:16 - mmengine - INFO - Epoch(train) [67][150/293] lr: 5.000000e-04 eta: 7:52:22 time: 0.787435 data_time: 0.098156 memory: 21676 loss_kpt: 0.000603 acc_pose: 0.824136 loss: 0.000603 2022/09/13 14:54:56 - mmengine - INFO - Epoch(train) [67][200/293] lr: 5.000000e-04 eta: 7:52:01 time: 0.790406 data_time: 0.102399 memory: 21676 loss_kpt: 0.000585 acc_pose: 0.842866 loss: 0.000585 2022/09/13 14:55:35 - mmengine - INFO - Epoch(train) [67][250/293] lr: 5.000000e-04 eta: 7:51:39 time: 0.785889 data_time: 0.103713 memory: 21676 loss_kpt: 0.000598 acc_pose: 0.857443 loss: 0.000598 2022/09/13 14:56:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 14:56:08 - mmengine - INFO - Saving checkpoint at 67 epochs 2022/09/13 14:56:52 - mmengine - INFO - Epoch(train) [68][50/293] lr: 5.000000e-04 eta: 7:49:46 time: 0.786375 data_time: 0.111093 memory: 21676 loss_kpt: 0.000601 acc_pose: 0.834150 loss: 0.000601 2022/09/13 14:57:31 - mmengine - INFO - Epoch(train) [68][100/293] lr: 5.000000e-04 eta: 7:49:24 time: 0.778429 data_time: 0.097991 memory: 21676 loss_kpt: 0.000595 acc_pose: 0.848118 loss: 0.000595 2022/09/13 14:58:10 - mmengine - INFO - Epoch(train) [68][150/293] lr: 5.000000e-04 eta: 7:49:02 time: 0.788505 data_time: 0.105792 memory: 21676 loss_kpt: 0.000596 acc_pose: 0.815827 loss: 0.000596 2022/09/13 14:58:49 - mmengine - INFO - Epoch(train) [68][200/293] lr: 5.000000e-04 eta: 7:48:39 time: 0.774365 data_time: 0.101495 memory: 21676 loss_kpt: 0.000584 acc_pose: 0.829496 loss: 0.000584 2022/09/13 14:59:28 - mmengine - INFO - Epoch(train) [68][250/293] lr: 5.000000e-04 eta: 7:48:15 time: 0.771443 data_time: 0.103773 memory: 21676 loss_kpt: 0.000600 acc_pose: 0.819710 loss: 0.000600 2022/09/13 15:00:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 15:00:00 - mmengine - INFO - Saving checkpoint at 68 epochs 2022/09/13 15:00:44 - mmengine - INFO - Epoch(train) [69][50/293] lr: 5.000000e-04 eta: 7:46:24 time: 0.786574 data_time: 0.103782 memory: 21676 loss_kpt: 0.000596 acc_pose: 0.844710 loss: 0.000596 2022/09/13 15:01:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 15:01:23 - mmengine - INFO - Epoch(train) [69][100/293] lr: 5.000000e-04 eta: 7:46:01 time: 0.781664 data_time: 0.100676 memory: 21676 loss_kpt: 0.000586 acc_pose: 0.861880 loss: 0.000586 2022/09/13 15:02:01 - mmengine - INFO - Epoch(train) [69][150/293] lr: 5.000000e-04 eta: 7:45:36 time: 0.753037 data_time: 0.097299 memory: 21676 loss_kpt: 0.000599 acc_pose: 0.769278 loss: 0.000599 2022/09/13 15:02:39 - mmengine - INFO - Epoch(train) [69][200/293] lr: 5.000000e-04 eta: 7:45:11 time: 0.758909 data_time: 0.095010 memory: 21676 loss_kpt: 0.000593 acc_pose: 0.795682 loss: 0.000593 2022/09/13 15:03:16 - mmengine - INFO - Epoch(train) [69][250/293] lr: 5.000000e-04 eta: 7:44:46 time: 0.753701 data_time: 0.090922 memory: 21676 loss_kpt: 0.000604 acc_pose: 0.838001 loss: 0.000604 2022/09/13 15:03:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 15:03:49 - mmengine - INFO - Saving checkpoint at 69 epochs 2022/09/13 15:04:33 - mmengine - INFO - Epoch(train) [70][50/293] lr: 5.000000e-04 eta: 7:42:56 time: 0.798369 data_time: 0.112807 memory: 21676 loss_kpt: 0.000578 acc_pose: 0.853664 loss: 0.000578 2022/09/13 15:05:12 - mmengine - INFO - Epoch(train) [70][100/293] lr: 5.000000e-04 eta: 7:42:33 time: 0.778645 data_time: 0.104594 memory: 21676 loss_kpt: 0.000592 acc_pose: 0.810486 loss: 0.000592 2022/09/13 15:05:51 - mmengine - INFO - Epoch(train) [70][150/293] lr: 5.000000e-04 eta: 7:42:10 time: 0.777213 data_time: 0.098632 memory: 21676 loss_kpt: 0.000591 acc_pose: 0.841619 loss: 0.000591 2022/09/13 15:06:30 - mmengine - INFO - Epoch(train) [70][200/293] lr: 5.000000e-04 eta: 7:41:47 time: 0.773218 data_time: 0.100201 memory: 21676 loss_kpt: 0.000602 acc_pose: 0.876132 loss: 0.000602 2022/09/13 15:07:08 - mmengine - INFO - Epoch(train) [70][250/293] lr: 5.000000e-04 eta: 7:41:23 time: 0.775533 data_time: 0.101725 memory: 21676 loss_kpt: 0.000596 acc_pose: 0.807153 loss: 0.000596 2022/09/13 15:07:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 15:07:42 - mmengine - INFO - Saving checkpoint at 70 epochs 2022/09/13 15:07:56 - mmengine - INFO - Epoch(val) [70][50/407] eta: 0:01:05 time: 0.183848 data_time: 0.014116 memory: 21676 2022/09/13 15:08:04 - mmengine - INFO - Epoch(val) [70][100/407] eta: 0:00:54 time: 0.175977 data_time: 0.008851 memory: 1375 2022/09/13 15:08:13 - mmengine - INFO - Epoch(val) [70][150/407] eta: 0:00:45 time: 0.175668 data_time: 0.008451 memory: 1375 2022/09/13 15:08:22 - mmengine - INFO - Epoch(val) [70][200/407] eta: 0:00:36 time: 0.176854 data_time: 0.009018 memory: 1375 2022/09/13 15:08:31 - mmengine - INFO - Epoch(val) [70][250/407] eta: 0:00:27 time: 0.175468 data_time: 0.008829 memory: 1375 2022/09/13 15:08:40 - mmengine - INFO - Epoch(val) [70][300/407] eta: 0:00:18 time: 0.175140 data_time: 0.008756 memory: 1375 2022/09/13 15:08:48 - mmengine - INFO - Epoch(val) [70][350/407] eta: 0:00:10 time: 0.176220 data_time: 0.008739 memory: 1375 2022/09/13 15:08:57 - mmengine - INFO - Epoch(val) [70][400/407] eta: 0:00:01 time: 0.178617 data_time: 0.013400 memory: 1375 2022/09/13 15:09:33 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 15:09:47 - mmengine - INFO - Epoch(val) [70][407/407] coco/AP: 0.748216 coco/AP .5: 0.900155 coco/AP .75: 0.813488 coco/AP (M): 0.708797 coco/AP (L): 0.818184 coco/AR: 0.797576 coco/AR .5: 0.936083 coco/AR .75: 0.858312 coco/AR (M): 0.754603 coco/AR (L): 0.859903 2022/09/13 15:09:47 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220913/udp_w32_384_v1/best_coco/AP_epoch_50.pth is removed 2022/09/13 15:09:50 - mmengine - INFO - The best checkpoint with 0.7482 coco/AP at 70 epoch is saved to best_coco/AP_epoch_70.pth. 2022/09/13 15:10:30 - mmengine - INFO - Epoch(train) [71][50/293] lr: 5.000000e-04 eta: 7:39:35 time: 0.799212 data_time: 0.109625 memory: 21676 loss_kpt: 0.000592 acc_pose: 0.801083 loss: 0.000592 2022/09/13 15:11:09 - mmengine - INFO - Epoch(train) [71][100/293] lr: 5.000000e-04 eta: 7:39:12 time: 0.780164 data_time: 0.097754 memory: 21676 loss_kpt: 0.000602 acc_pose: 0.830690 loss: 0.000602 2022/09/13 15:11:49 - mmengine - INFO - Epoch(train) [71][150/293] lr: 5.000000e-04 eta: 7:38:50 time: 0.790135 data_time: 0.101390 memory: 21676 loss_kpt: 0.000579 acc_pose: 0.855427 loss: 0.000579 2022/09/13 15:12:28 - mmengine - INFO - Epoch(train) [71][200/293] lr: 5.000000e-04 eta: 7:38:27 time: 0.779092 data_time: 0.101349 memory: 21676 loss_kpt: 0.000606 acc_pose: 0.817054 loss: 0.000606 2022/09/13 15:13:06 - mmengine - INFO - Epoch(train) [71][250/293] lr: 5.000000e-04 eta: 7:38:03 time: 0.771627 data_time: 0.102329 memory: 21676 loss_kpt: 0.000591 acc_pose: 0.841429 loss: 0.000591 2022/09/13 15:13:39 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 15:13:39 - mmengine - INFO - Saving checkpoint at 71 epochs 2022/09/13 15:14:24 - mmengine - INFO - Epoch(train) [72][50/293] lr: 5.000000e-04 eta: 7:36:15 time: 0.796995 data_time: 0.111850 memory: 21676 loss_kpt: 0.000577 acc_pose: 0.852506 loss: 0.000577 2022/09/13 15:15:03 - mmengine - INFO - Epoch(train) [72][100/293] lr: 5.000000e-04 eta: 7:35:52 time: 0.784058 data_time: 0.097529 memory: 21676 loss_kpt: 0.000590 acc_pose: 0.839145 loss: 0.000590 2022/09/13 15:15:43 - mmengine - INFO - Epoch(train) [72][150/293] lr: 5.000000e-04 eta: 7:35:30 time: 0.790078 data_time: 0.095727 memory: 21676 loss_kpt: 0.000587 acc_pose: 0.842063 loss: 0.000587 2022/09/13 15:16:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 15:16:21 - mmengine - INFO - Epoch(train) [72][200/293] lr: 5.000000e-04 eta: 7:35:07 time: 0.777899 data_time: 0.098463 memory: 21676 loss_kpt: 0.000586 acc_pose: 0.844279 loss: 0.000586 2022/09/13 15:17:00 - mmengine - INFO - Epoch(train) [72][250/293] lr: 5.000000e-04 eta: 7:34:42 time: 0.773312 data_time: 0.096417 memory: 21676 loss_kpt: 0.000601 acc_pose: 0.896892 loss: 0.000601 2022/09/13 15:17:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 15:17:33 - mmengine - INFO - Saving checkpoint at 72 epochs 2022/09/13 15:18:17 - mmengine - INFO - Epoch(train) [73][50/293] lr: 5.000000e-04 eta: 7:32:56 time: 0.792110 data_time: 0.110403 memory: 21676 loss_kpt: 0.000590 acc_pose: 0.818265 loss: 0.000590 2022/09/13 15:18:56 - mmengine - INFO - Epoch(train) [73][100/293] lr: 5.000000e-04 eta: 7:32:33 time: 0.783594 data_time: 0.097242 memory: 21676 loss_kpt: 0.000602 acc_pose: 0.862239 loss: 0.000602 2022/09/13 15:19:35 - mmengine - INFO - Epoch(train) [73][150/293] lr: 5.000000e-04 eta: 7:32:09 time: 0.778166 data_time: 0.096184 memory: 21676 loss_kpt: 0.000593 acc_pose: 0.822193 loss: 0.000593 2022/09/13 15:20:14 - mmengine - INFO - Epoch(train) [73][200/293] lr: 5.000000e-04 eta: 7:31:45 time: 0.778985 data_time: 0.096826 memory: 21676 loss_kpt: 0.000589 acc_pose: 0.802311 loss: 0.000589 2022/09/13 15:20:54 - mmengine - INFO - Epoch(train) [73][250/293] lr: 5.000000e-04 eta: 7:31:22 time: 0.784523 data_time: 0.097371 memory: 21676 loss_kpt: 0.000588 acc_pose: 0.828751 loss: 0.000588 2022/09/13 15:21:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 15:21:27 - mmengine - INFO - Saving checkpoint at 73 epochs 2022/09/13 15:22:12 - mmengine - INFO - Epoch(train) [74][50/293] lr: 5.000000e-04 eta: 7:29:38 time: 0.809571 data_time: 0.109139 memory: 21676 loss_kpt: 0.000584 acc_pose: 0.839988 loss: 0.000584 2022/09/13 15:22:51 - mmengine - INFO - Epoch(train) [74][100/293] lr: 5.000000e-04 eta: 7:29:14 time: 0.783426 data_time: 0.095742 memory: 21676 loss_kpt: 0.000584 acc_pose: 0.836446 loss: 0.000584 2022/09/13 15:23:30 - mmengine - INFO - Epoch(train) [74][150/293] lr: 5.000000e-04 eta: 7:28:51 time: 0.789322 data_time: 0.097184 memory: 21676 loss_kpt: 0.000589 acc_pose: 0.838748 loss: 0.000589 2022/09/13 15:24:09 - mmengine - INFO - Epoch(train) [74][200/293] lr: 5.000000e-04 eta: 7:28:27 time: 0.771026 data_time: 0.093616 memory: 21676 loss_kpt: 0.000595 acc_pose: 0.875278 loss: 0.000595 2022/09/13 15:24:48 - mmengine - INFO - Epoch(train) [74][250/293] lr: 5.000000e-04 eta: 7:28:03 time: 0.779371 data_time: 0.096395 memory: 21676 loss_kpt: 0.000598 acc_pose: 0.840487 loss: 0.000598 2022/09/13 15:25:21 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 15:25:21 - mmengine - INFO - Saving checkpoint at 74 epochs 2022/09/13 15:26:06 - mmengine - INFO - Epoch(train) [75][50/293] lr: 5.000000e-04 eta: 7:26:18 time: 0.793275 data_time: 0.106024 memory: 21676 loss_kpt: 0.000587 acc_pose: 0.850664 loss: 0.000587 2022/09/13 15:26:44 - mmengine - INFO - Epoch(train) [75][100/293] lr: 5.000000e-04 eta: 7:25:53 time: 0.772482 data_time: 0.094387 memory: 21676 loss_kpt: 0.000582 acc_pose: 0.828769 loss: 0.000582 2022/09/13 15:27:24 - mmengine - INFO - Epoch(train) [75][150/293] lr: 5.000000e-04 eta: 7:25:30 time: 0.788215 data_time: 0.093981 memory: 21676 loss_kpt: 0.000583 acc_pose: 0.786586 loss: 0.000583 2022/09/13 15:28:04 - mmengine - INFO - Epoch(train) [75][200/293] lr: 5.000000e-04 eta: 7:25:08 time: 0.803888 data_time: 0.095843 memory: 21676 loss_kpt: 0.000586 acc_pose: 0.853812 loss: 0.000586 2022/09/13 15:28:43 - mmengine - INFO - Epoch(train) [75][250/293] lr: 5.000000e-04 eta: 7:24:45 time: 0.785251 data_time: 0.093766 memory: 21676 loss_kpt: 0.000581 acc_pose: 0.878826 loss: 0.000581 2022/09/13 15:29:17 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 15:29:17 - mmengine - INFO - Saving checkpoint at 75 epochs 2022/09/13 15:29:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 15:30:01 - mmengine - INFO - Epoch(train) [76][50/293] lr: 5.000000e-04 eta: 7:23:01 time: 0.798529 data_time: 0.108795 memory: 21676 loss_kpt: 0.000580 acc_pose: 0.839511 loss: 0.000580 2022/09/13 15:30:41 - mmengine - INFO - Epoch(train) [76][100/293] lr: 5.000000e-04 eta: 7:22:38 time: 0.786955 data_time: 0.105100 memory: 21676 loss_kpt: 0.000583 acc_pose: 0.875103 loss: 0.000583 2022/09/13 15:31:20 - mmengine - INFO - Epoch(train) [76][150/293] lr: 5.000000e-04 eta: 7:22:14 time: 0.781011 data_time: 0.102027 memory: 21676 loss_kpt: 0.000590 acc_pose: 0.788284 loss: 0.000590 2022/09/13 15:31:58 - mmengine - INFO - Epoch(train) [76][200/293] lr: 5.000000e-04 eta: 7:21:49 time: 0.772887 data_time: 0.106174 memory: 21676 loss_kpt: 0.000604 acc_pose: 0.820638 loss: 0.000604 2022/09/13 15:32:37 - mmengine - INFO - Epoch(train) [76][250/293] lr: 5.000000e-04 eta: 7:21:24 time: 0.770849 data_time: 0.103177 memory: 21676 loss_kpt: 0.000595 acc_pose: 0.825917 loss: 0.000595 2022/09/13 15:33:09 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 15:33:09 - mmengine - INFO - Saving checkpoint at 76 epochs 2022/09/13 15:33:54 - mmengine - INFO - Epoch(train) [77][50/293] lr: 5.000000e-04 eta: 7:19:42 time: 0.805170 data_time: 0.115752 memory: 21676 loss_kpt: 0.000589 acc_pose: 0.796725 loss: 0.000589 2022/09/13 15:34:33 - mmengine - INFO - Epoch(train) [77][100/293] lr: 5.000000e-04 eta: 7:19:17 time: 0.773487 data_time: 0.098366 memory: 21676 loss_kpt: 0.000593 acc_pose: 0.848600 loss: 0.000593 2022/09/13 15:35:11 - mmengine - INFO - Epoch(train) [77][150/293] lr: 5.000000e-04 eta: 7:18:51 time: 0.756694 data_time: 0.097065 memory: 21676 loss_kpt: 0.000589 acc_pose: 0.859165 loss: 0.000589 2022/09/13 15:35:49 - mmengine - INFO - Epoch(train) [77][200/293] lr: 5.000000e-04 eta: 7:18:25 time: 0.760030 data_time: 0.096064 memory: 21676 loss_kpt: 0.000584 acc_pose: 0.865685 loss: 0.000584 2022/09/13 15:36:27 - mmengine - INFO - Epoch(train) [77][250/293] lr: 5.000000e-04 eta: 7:17:59 time: 0.766408 data_time: 0.093125 memory: 21676 loss_kpt: 0.000584 acc_pose: 0.833359 loss: 0.000584 2022/09/13 15:37:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 15:37:00 - mmengine - INFO - Saving checkpoint at 77 epochs 2022/09/13 15:37:43 - mmengine - INFO - Epoch(train) [78][50/293] lr: 5.000000e-04 eta: 7:16:16 time: 0.781705 data_time: 0.113569 memory: 21676 loss_kpt: 0.000585 acc_pose: 0.843133 loss: 0.000585 2022/09/13 15:38:22 - mmengine - INFO - Epoch(train) [78][100/293] lr: 5.000000e-04 eta: 7:15:51 time: 0.779920 data_time: 0.102934 memory: 21676 loss_kpt: 0.000577 acc_pose: 0.845302 loss: 0.000577 2022/09/13 15:39:01 - mmengine - INFO - Epoch(train) [78][150/293] lr: 5.000000e-04 eta: 7:15:26 time: 0.769264 data_time: 0.100020 memory: 21676 loss_kpt: 0.000589 acc_pose: 0.841085 loss: 0.000589 2022/09/13 15:39:39 - mmengine - INFO - Epoch(train) [78][200/293] lr: 5.000000e-04 eta: 7:15:00 time: 0.764743 data_time: 0.106005 memory: 21676 loss_kpt: 0.000582 acc_pose: 0.774779 loss: 0.000582 2022/09/13 15:40:17 - mmengine - INFO - Epoch(train) [78][250/293] lr: 5.000000e-04 eta: 7:14:34 time: 0.761102 data_time: 0.095118 memory: 21676 loss_kpt: 0.000593 acc_pose: 0.785177 loss: 0.000593 2022/09/13 15:40:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 15:40:49 - mmengine - INFO - Saving checkpoint at 78 epochs 2022/09/13 15:41:33 - mmengine - INFO - Epoch(train) [79][50/293] lr: 5.000000e-04 eta: 7:12:53 time: 0.792668 data_time: 0.106533 memory: 21676 loss_kpt: 0.000579 acc_pose: 0.847816 loss: 0.000579 2022/09/13 15:42:13 - mmengine - INFO - Epoch(train) [79][100/293] lr: 5.000000e-04 eta: 7:12:30 time: 0.800477 data_time: 0.095754 memory: 21676 loss_kpt: 0.000603 acc_pose: 0.803857 loss: 0.000603 2022/09/13 15:42:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 15:42:53 - mmengine - INFO - Epoch(train) [79][150/293] lr: 5.000000e-04 eta: 7:12:06 time: 0.793999 data_time: 0.098005 memory: 21676 loss_kpt: 0.000585 acc_pose: 0.844799 loss: 0.000585 2022/09/13 15:43:32 - mmengine - INFO - Epoch(train) [79][200/293] lr: 5.000000e-04 eta: 7:11:42 time: 0.782463 data_time: 0.094249 memory: 21676 loss_kpt: 0.000582 acc_pose: 0.794709 loss: 0.000582 2022/09/13 15:44:10 - mmengine - INFO - Epoch(train) [79][250/293] lr: 5.000000e-04 eta: 7:11:14 time: 0.750456 data_time: 0.091656 memory: 21676 loss_kpt: 0.000591 acc_pose: 0.846987 loss: 0.000591 2022/09/13 15:44:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 15:44:42 - mmengine - INFO - Saving checkpoint at 79 epochs 2022/09/13 15:45:27 - mmengine - INFO - Epoch(train) [80][50/293] lr: 5.000000e-04 eta: 7:09:34 time: 0.799999 data_time: 0.112454 memory: 21676 loss_kpt: 0.000581 acc_pose: 0.882501 loss: 0.000581 2022/09/13 15:46:06 - mmengine - INFO - Epoch(train) [80][100/293] lr: 5.000000e-04 eta: 7:09:10 time: 0.781083 data_time: 0.103658 memory: 21676 loss_kpt: 0.000587 acc_pose: 0.851183 loss: 0.000587 2022/09/13 15:46:44 - mmengine - INFO - Epoch(train) [80][150/293] lr: 5.000000e-04 eta: 7:08:45 time: 0.775465 data_time: 0.100640 memory: 21676 loss_kpt: 0.000575 acc_pose: 0.787118 loss: 0.000575 2022/09/13 15:47:23 - mmengine - INFO - Epoch(train) [80][200/293] lr: 5.000000e-04 eta: 7:08:19 time: 0.771039 data_time: 0.102134 memory: 21676 loss_kpt: 0.000587 acc_pose: 0.881606 loss: 0.000587 2022/09/13 15:48:01 - mmengine - INFO - Epoch(train) [80][250/293] lr: 5.000000e-04 eta: 7:07:53 time: 0.771847 data_time: 0.104045 memory: 21676 loss_kpt: 0.000596 acc_pose: 0.850537 loss: 0.000596 2022/09/13 15:48:34 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 15:48:34 - mmengine - INFO - Saving checkpoint at 80 epochs 2022/09/13 15:48:48 - mmengine - INFO - Epoch(val) [80][50/407] eta: 0:01:05 time: 0.182630 data_time: 0.014081 memory: 21676 2022/09/13 15:48:57 - mmengine - INFO - Epoch(val) [80][100/407] eta: 0:00:53 time: 0.175773 data_time: 0.008755 memory: 1375 2022/09/13 15:49:06 - mmengine - INFO - Epoch(val) [80][150/407] eta: 0:00:45 time: 0.178652 data_time: 0.008366 memory: 1375 2022/09/13 15:49:15 - mmengine - INFO - Epoch(val) [80][200/407] eta: 0:00:36 time: 0.174977 data_time: 0.008990 memory: 1375 2022/09/13 15:49:23 - mmengine - INFO - Epoch(val) [80][250/407] eta: 0:00:27 time: 0.174112 data_time: 0.008383 memory: 1375 2022/09/13 15:49:32 - mmengine - INFO - Epoch(val) [80][300/407] eta: 0:00:18 time: 0.175330 data_time: 0.008526 memory: 1375 2022/09/13 15:49:41 - mmengine - INFO - Epoch(val) [80][350/407] eta: 0:00:10 time: 0.178226 data_time: 0.008975 memory: 1375 2022/09/13 15:49:50 - mmengine - INFO - Epoch(val) [80][400/407] eta: 0:00:01 time: 0.174135 data_time: 0.008379 memory: 1375 2022/09/13 15:50:26 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 15:50:39 - mmengine - INFO - Epoch(val) [80][407/407] coco/AP: 0.749374 coco/AP .5: 0.898974 coco/AP .75: 0.817213 coco/AP (M): 0.708587 coco/AP (L): 0.821150 coco/AR: 0.798929 coco/AR .5: 0.936083 coco/AR .75: 0.861618 coco/AR (M): 0.754329 coco/AR (L): 0.863508 2022/09/13 15:50:39 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220913/udp_w32_384_v1/best_coco/AP_epoch_70.pth is removed 2022/09/13 15:50:42 - mmengine - INFO - The best checkpoint with 0.7494 coco/AP at 80 epoch is saved to best_coco/AP_epoch_80.pth. 2022/09/13 15:51:22 - mmengine - INFO - Epoch(train) [81][50/293] lr: 5.000000e-04 eta: 7:06:13 time: 0.784946 data_time: 0.105330 memory: 21676 loss_kpt: 0.000589 acc_pose: 0.813278 loss: 0.000589 2022/09/13 15:52:01 - mmengine - INFO - Epoch(train) [81][100/293] lr: 5.000000e-04 eta: 7:05:48 time: 0.782959 data_time: 0.102257 memory: 21676 loss_kpt: 0.000574 acc_pose: 0.840034 loss: 0.000574 2022/09/13 15:52:40 - mmengine - INFO - Epoch(train) [81][150/293] lr: 5.000000e-04 eta: 7:05:23 time: 0.780061 data_time: 0.100569 memory: 21676 loss_kpt: 0.000578 acc_pose: 0.806619 loss: 0.000578 2022/09/13 15:53:19 - mmengine - INFO - Epoch(train) [81][200/293] lr: 5.000000e-04 eta: 7:04:59 time: 0.785800 data_time: 0.099378 memory: 21676 loss_kpt: 0.000589 acc_pose: 0.808869 loss: 0.000589 2022/09/13 15:53:58 - mmengine - INFO - Epoch(train) [81][250/293] lr: 5.000000e-04 eta: 7:04:34 time: 0.783630 data_time: 0.103090 memory: 21676 loss_kpt: 0.000570 acc_pose: 0.858111 loss: 0.000570 2022/09/13 15:54:31 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 15:54:31 - mmengine - INFO - Saving checkpoint at 81 epochs 2022/09/13 15:55:15 - mmengine - INFO - Epoch(train) [82][50/293] lr: 5.000000e-04 eta: 7:02:54 time: 0.786351 data_time: 0.106380 memory: 21676 loss_kpt: 0.000580 acc_pose: 0.811778 loss: 0.000580 2022/09/13 15:55:54 - mmengine - INFO - Epoch(train) [82][100/293] lr: 5.000000e-04 eta: 7:02:30 time: 0.787906 data_time: 0.095479 memory: 21676 loss_kpt: 0.000571 acc_pose: 0.855201 loss: 0.000571 2022/09/13 15:56:34 - mmengine - INFO - Epoch(train) [82][150/293] lr: 5.000000e-04 eta: 7:02:06 time: 0.798030 data_time: 0.092627 memory: 21676 loss_kpt: 0.000577 acc_pose: 0.836633 loss: 0.000577 2022/09/13 15:57:13 - mmengine - INFO - Epoch(train) [82][200/293] lr: 5.000000e-04 eta: 7:01:41 time: 0.782054 data_time: 0.095968 memory: 21676 loss_kpt: 0.000594 acc_pose: 0.846428 loss: 0.000594 2022/09/13 15:57:52 - mmengine - INFO - Epoch(train) [82][250/293] lr: 5.000000e-04 eta: 7:01:16 time: 0.782260 data_time: 0.093416 memory: 21676 loss_kpt: 0.000582 acc_pose: 0.821053 loss: 0.000582 2022/09/13 15:58:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 15:58:25 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 15:58:25 - mmengine - INFO - Saving checkpoint at 82 epochs 2022/09/13 15:59:09 - mmengine - INFO - Epoch(train) [83][50/293] lr: 5.000000e-04 eta: 6:59:38 time: 0.794928 data_time: 0.102214 memory: 21676 loss_kpt: 0.000581 acc_pose: 0.826121 loss: 0.000581 2022/09/13 15:59:48 - mmengine - INFO - Epoch(train) [83][100/293] lr: 5.000000e-04 eta: 6:59:13 time: 0.781217 data_time: 0.096425 memory: 21676 loss_kpt: 0.000585 acc_pose: 0.779867 loss: 0.000585 2022/09/13 16:00:27 - mmengine - INFO - Epoch(train) [83][150/293] lr: 5.000000e-04 eta: 6:58:47 time: 0.780054 data_time: 0.099562 memory: 21676 loss_kpt: 0.000581 acc_pose: 0.783776 loss: 0.000581 2022/09/13 16:01:06 - mmengine - INFO - Epoch(train) [83][200/293] lr: 5.000000e-04 eta: 6:58:22 time: 0.785245 data_time: 0.100702 memory: 21676 loss_kpt: 0.000586 acc_pose: 0.814505 loss: 0.000586 2022/09/13 16:01:46 - mmengine - INFO - Epoch(train) [83][250/293] lr: 5.000000e-04 eta: 6:57:58 time: 0.790493 data_time: 0.105393 memory: 21676 loss_kpt: 0.000579 acc_pose: 0.828527 loss: 0.000579 2022/09/13 16:02:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 16:02:19 - mmengine - INFO - Saving checkpoint at 83 epochs 2022/09/13 16:03:03 - mmengine - INFO - Epoch(train) [84][50/293] lr: 5.000000e-04 eta: 6:56:20 time: 0.788701 data_time: 0.109074 memory: 21676 loss_kpt: 0.000575 acc_pose: 0.783017 loss: 0.000575 2022/09/13 16:03:43 - mmengine - INFO - Epoch(train) [84][100/293] lr: 5.000000e-04 eta: 6:55:55 time: 0.791592 data_time: 0.106962 memory: 21676 loss_kpt: 0.000592 acc_pose: 0.838645 loss: 0.000592 2022/09/13 16:04:22 - mmengine - INFO - Epoch(train) [84][150/293] lr: 5.000000e-04 eta: 6:55:30 time: 0.788216 data_time: 0.102604 memory: 21676 loss_kpt: 0.000576 acc_pose: 0.851856 loss: 0.000576 2022/09/13 16:05:01 - mmengine - INFO - Epoch(train) [84][200/293] lr: 5.000000e-04 eta: 6:55:05 time: 0.784986 data_time: 0.100808 memory: 21676 loss_kpt: 0.000584 acc_pose: 0.757822 loss: 0.000584 2022/09/13 16:05:41 - mmengine - INFO - Epoch(train) [84][250/293] lr: 5.000000e-04 eta: 6:54:40 time: 0.791639 data_time: 0.101658 memory: 21676 loss_kpt: 0.000581 acc_pose: 0.798272 loss: 0.000581 2022/09/13 16:06:14 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 16:06:14 - mmengine - INFO - Saving checkpoint at 84 epochs 2022/09/13 16:06:58 - mmengine - INFO - Epoch(train) [85][50/293] lr: 5.000000e-04 eta: 6:53:04 time: 0.796165 data_time: 0.104035 memory: 21676 loss_kpt: 0.000576 acc_pose: 0.809517 loss: 0.000576 2022/09/13 16:07:37 - mmengine - INFO - Epoch(train) [85][100/293] lr: 5.000000e-04 eta: 6:52:39 time: 0.788264 data_time: 0.097032 memory: 21676 loss_kpt: 0.000592 acc_pose: 0.795256 loss: 0.000592 2022/09/13 16:08:17 - mmengine - INFO - Epoch(train) [85][150/293] lr: 5.000000e-04 eta: 6:52:15 time: 0.799062 data_time: 0.104505 memory: 21676 loss_kpt: 0.000596 acc_pose: 0.841814 loss: 0.000596 2022/09/13 16:08:57 - mmengine - INFO - Epoch(train) [85][200/293] lr: 5.000000e-04 eta: 6:51:49 time: 0.781807 data_time: 0.101789 memory: 21676 loss_kpt: 0.000591 acc_pose: 0.793983 loss: 0.000591 2022/09/13 16:09:35 - mmengine - INFO - Epoch(train) [85][250/293] lr: 5.000000e-04 eta: 6:51:23 time: 0.776034 data_time: 0.099542 memory: 21676 loss_kpt: 0.000586 acc_pose: 0.824520 loss: 0.000586 2022/09/13 16:10:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 16:10:08 - mmengine - INFO - Saving checkpoint at 85 epochs 2022/09/13 16:10:52 - mmengine - INFO - Epoch(train) [86][50/293] lr: 5.000000e-04 eta: 6:49:46 time: 0.787947 data_time: 0.108342 memory: 21676 loss_kpt: 0.000566 acc_pose: 0.832640 loss: 0.000566 2022/09/13 16:11:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 16:11:31 - mmengine - INFO - Epoch(train) [86][100/293] lr: 5.000000e-04 eta: 6:49:21 time: 0.782357 data_time: 0.100111 memory: 21676 loss_kpt: 0.000594 acc_pose: 0.787583 loss: 0.000594 2022/09/13 16:12:10 - mmengine - INFO - Epoch(train) [86][150/293] lr: 5.000000e-04 eta: 6:48:55 time: 0.775891 data_time: 0.105573 memory: 21676 loss_kpt: 0.000582 acc_pose: 0.815846 loss: 0.000582 2022/09/13 16:12:49 - mmengine - INFO - Epoch(train) [86][200/293] lr: 5.000000e-04 eta: 6:48:29 time: 0.787864 data_time: 0.097658 memory: 21676 loss_kpt: 0.000581 acc_pose: 0.828657 loss: 0.000581 2022/09/13 16:13:27 - mmengine - INFO - Epoch(train) [86][250/293] lr: 5.000000e-04 eta: 6:48:03 time: 0.767700 data_time: 0.099618 memory: 21676 loss_kpt: 0.000589 acc_pose: 0.830441 loss: 0.000589 2022/09/13 16:14:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 16:14:00 - mmengine - INFO - Saving checkpoint at 86 epochs 2022/09/13 16:14:44 - mmengine - INFO - Epoch(train) [87][50/293] lr: 5.000000e-04 eta: 6:46:26 time: 0.779878 data_time: 0.106656 memory: 21676 loss_kpt: 0.000571 acc_pose: 0.835920 loss: 0.000571 2022/09/13 16:15:23 - mmengine - INFO - Epoch(train) [87][100/293] lr: 5.000000e-04 eta: 6:46:01 time: 0.788984 data_time: 0.097415 memory: 21676 loss_kpt: 0.000574 acc_pose: 0.853657 loss: 0.000574 2022/09/13 16:16:02 - mmengine - INFO - Epoch(train) [87][150/293] lr: 5.000000e-04 eta: 6:45:35 time: 0.783197 data_time: 0.095562 memory: 21676 loss_kpt: 0.000579 acc_pose: 0.847241 loss: 0.000579 2022/09/13 16:16:41 - mmengine - INFO - Epoch(train) [87][200/293] lr: 5.000000e-04 eta: 6:45:09 time: 0.778881 data_time: 0.094692 memory: 21676 loss_kpt: 0.000565 acc_pose: 0.795728 loss: 0.000565 2022/09/13 16:17:20 - mmengine - INFO - Epoch(train) [87][250/293] lr: 5.000000e-04 eta: 6:44:43 time: 0.778740 data_time: 0.096350 memory: 21676 loss_kpt: 0.000573 acc_pose: 0.846947 loss: 0.000573 2022/09/13 16:17:54 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 16:17:54 - mmengine - INFO - Saving checkpoint at 87 epochs 2022/09/13 16:18:38 - mmengine - INFO - Epoch(train) [88][50/293] lr: 5.000000e-04 eta: 6:43:08 time: 0.797192 data_time: 0.105633 memory: 21676 loss_kpt: 0.000578 acc_pose: 0.827430 loss: 0.000578 2022/09/13 16:19:17 - mmengine - INFO - Epoch(train) [88][100/293] lr: 5.000000e-04 eta: 6:42:42 time: 0.776661 data_time: 0.099899 memory: 21676 loss_kpt: 0.000573 acc_pose: 0.815098 loss: 0.000573 2022/09/13 16:19:56 - mmengine - INFO - Epoch(train) [88][150/293] lr: 5.000000e-04 eta: 6:42:16 time: 0.777699 data_time: 0.094247 memory: 21676 loss_kpt: 0.000571 acc_pose: 0.810586 loss: 0.000571 2022/09/13 16:20:34 - mmengine - INFO - Epoch(train) [88][200/293] lr: 5.000000e-04 eta: 6:41:49 time: 0.775081 data_time: 0.096739 memory: 21676 loss_kpt: 0.000584 acc_pose: 0.756362 loss: 0.000584 2022/09/13 16:21:14 - mmengine - INFO - Epoch(train) [88][250/293] lr: 5.000000e-04 eta: 6:41:23 time: 0.781635 data_time: 0.096415 memory: 21676 loss_kpt: 0.000589 acc_pose: 0.888531 loss: 0.000589 2022/09/13 16:21:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 16:21:46 - mmengine - INFO - Saving checkpoint at 88 epochs 2022/09/13 16:22:31 - mmengine - INFO - Epoch(train) [89][50/293] lr: 5.000000e-04 eta: 6:39:49 time: 0.793087 data_time: 0.110714 memory: 21676 loss_kpt: 0.000571 acc_pose: 0.792646 loss: 0.000571 2022/09/13 16:23:10 - mmengine - INFO - Epoch(train) [89][100/293] lr: 5.000000e-04 eta: 6:39:23 time: 0.783465 data_time: 0.099869 memory: 21676 loss_kpt: 0.000591 acc_pose: 0.809719 loss: 0.000591 2022/09/13 16:23:49 - mmengine - INFO - Epoch(train) [89][150/293] lr: 5.000000e-04 eta: 6:38:58 time: 0.789680 data_time: 0.098223 memory: 21676 loss_kpt: 0.000585 acc_pose: 0.876913 loss: 0.000585 2022/09/13 16:24:28 - mmengine - INFO - Epoch(train) [89][200/293] lr: 5.000000e-04 eta: 6:38:31 time: 0.772729 data_time: 0.100144 memory: 21676 loss_kpt: 0.000576 acc_pose: 0.807986 loss: 0.000576 2022/09/13 16:24:40 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 16:25:06 - mmengine - INFO - Epoch(train) [89][250/293] lr: 5.000000e-04 eta: 6:38:03 time: 0.755617 data_time: 0.101393 memory: 21676 loss_kpt: 0.000565 acc_pose: 0.827511 loss: 0.000565 2022/09/13 16:25:38 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 16:25:38 - mmengine - INFO - Saving checkpoint at 89 epochs 2022/09/13 16:26:22 - mmengine - INFO - Epoch(train) [90][50/293] lr: 5.000000e-04 eta: 6:36:29 time: 0.783769 data_time: 0.109521 memory: 21676 loss_kpt: 0.000569 acc_pose: 0.833206 loss: 0.000569 2022/09/13 16:27:01 - mmengine - INFO - Epoch(train) [90][100/293] lr: 5.000000e-04 eta: 6:36:03 time: 0.784799 data_time: 0.097913 memory: 21676 loss_kpt: 0.000596 acc_pose: 0.826062 loss: 0.000596 2022/09/13 16:27:40 - mmengine - INFO - Epoch(train) [90][150/293] lr: 5.000000e-04 eta: 6:35:36 time: 0.781278 data_time: 0.107515 memory: 21676 loss_kpt: 0.000581 acc_pose: 0.850257 loss: 0.000581 2022/09/13 16:28:19 - mmengine - INFO - Epoch(train) [90][200/293] lr: 5.000000e-04 eta: 6:35:10 time: 0.778356 data_time: 0.103648 memory: 21676 loss_kpt: 0.000565 acc_pose: 0.780796 loss: 0.000565 2022/09/13 16:28:58 - mmengine - INFO - Epoch(train) [90][250/293] lr: 5.000000e-04 eta: 6:34:43 time: 0.777611 data_time: 0.100862 memory: 21676 loss_kpt: 0.000569 acc_pose: 0.838556 loss: 0.000569 2022/09/13 16:29:31 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 16:29:31 - mmengine - INFO - Saving checkpoint at 90 epochs 2022/09/13 16:29:44 - mmengine - INFO - Epoch(val) [90][50/407] eta: 0:01:05 time: 0.183223 data_time: 0.014454 memory: 21676 2022/09/13 16:29:53 - mmengine - INFO - Epoch(val) [90][100/407] eta: 0:00:54 time: 0.177138 data_time: 0.009077 memory: 1375 2022/09/13 16:30:02 - mmengine - INFO - Epoch(val) [90][150/407] eta: 0:00:46 time: 0.180239 data_time: 0.008487 memory: 1375 2022/09/13 16:30:11 - mmengine - INFO - Epoch(val) [90][200/407] eta: 0:00:36 time: 0.175039 data_time: 0.008500 memory: 1375 2022/09/13 16:30:20 - mmengine - INFO - Epoch(val) [90][250/407] eta: 0:00:28 time: 0.180952 data_time: 0.013752 memory: 1375 2022/09/13 16:30:29 - mmengine - INFO - Epoch(val) [90][300/407] eta: 0:00:18 time: 0.176183 data_time: 0.008752 memory: 1375 2022/09/13 16:30:38 - mmengine - INFO - Epoch(val) [90][350/407] eta: 0:00:10 time: 0.176181 data_time: 0.008785 memory: 1375 2022/09/13 16:30:46 - mmengine - INFO - Epoch(val) [90][400/407] eta: 0:00:01 time: 0.174005 data_time: 0.008247 memory: 1375 2022/09/13 16:31:22 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 16:31:36 - mmengine - INFO - Epoch(val) [90][407/407] coco/AP: 0.750226 coco/AP .5: 0.899520 coco/AP .75: 0.815938 coco/AP (M): 0.709078 coco/AP (L): 0.823517 coco/AR: 0.800110 coco/AR .5: 0.936083 coco/AR .75: 0.859887 coco/AR (M): 0.754876 coco/AR (L): 0.865961 2022/09/13 16:31:36 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220913/udp_w32_384_v1/best_coco/AP_epoch_80.pth is removed 2022/09/13 16:31:39 - mmengine - INFO - The best checkpoint with 0.7502 coco/AP at 90 epoch is saved to best_coco/AP_epoch_90.pth. 2022/09/13 16:32:18 - mmengine - INFO - Epoch(train) [91][50/293] lr: 5.000000e-04 eta: 6:33:10 time: 0.794304 data_time: 0.103819 memory: 21676 loss_kpt: 0.000574 acc_pose: 0.825518 loss: 0.000574 2022/09/13 16:32:57 - mmengine - INFO - Epoch(train) [91][100/293] lr: 5.000000e-04 eta: 6:32:43 time: 0.765628 data_time: 0.095986 memory: 21676 loss_kpt: 0.000572 acc_pose: 0.834995 loss: 0.000572 2022/09/13 16:33:35 - mmengine - INFO - Epoch(train) [91][150/293] lr: 5.000000e-04 eta: 6:32:15 time: 0.762531 data_time: 0.098320 memory: 21676 loss_kpt: 0.000571 acc_pose: 0.836764 loss: 0.000571 2022/09/13 16:34:13 - mmengine - INFO - Epoch(train) [91][200/293] lr: 5.000000e-04 eta: 6:31:47 time: 0.757321 data_time: 0.094888 memory: 21676 loss_kpt: 0.000571 acc_pose: 0.842379 loss: 0.000571 2022/09/13 16:34:51 - mmengine - INFO - Epoch(train) [91][250/293] lr: 5.000000e-04 eta: 6:31:20 time: 0.767926 data_time: 0.095885 memory: 21676 loss_kpt: 0.000575 acc_pose: 0.795084 loss: 0.000575 2022/09/13 16:35:23 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 16:35:23 - mmengine - INFO - Saving checkpoint at 91 epochs 2022/09/13 16:36:07 - mmengine - INFO - Epoch(train) [92][50/293] lr: 5.000000e-04 eta: 6:29:48 time: 0.796148 data_time: 0.102381 memory: 21676 loss_kpt: 0.000569 acc_pose: 0.852478 loss: 0.000569 2022/09/13 16:36:47 - mmengine - INFO - Epoch(train) [92][100/293] lr: 5.000000e-04 eta: 6:29:21 time: 0.780195 data_time: 0.099719 memory: 21676 loss_kpt: 0.000573 acc_pose: 0.859740 loss: 0.000573 2022/09/13 16:37:25 - mmengine - INFO - Epoch(train) [92][150/293] lr: 5.000000e-04 eta: 6:28:54 time: 0.778170 data_time: 0.098275 memory: 21676 loss_kpt: 0.000562 acc_pose: 0.791973 loss: 0.000562 2022/09/13 16:38:04 - mmengine - INFO - Epoch(train) [92][200/293] lr: 5.000000e-04 eta: 6:28:27 time: 0.775189 data_time: 0.094278 memory: 21676 loss_kpt: 0.000575 acc_pose: 0.874574 loss: 0.000575 2022/09/13 16:38:44 - mmengine - INFO - Epoch(train) [92][250/293] lr: 5.000000e-04 eta: 6:28:01 time: 0.790960 data_time: 0.097945 memory: 21676 loss_kpt: 0.000584 acc_pose: 0.838566 loss: 0.000584 2022/09/13 16:39:17 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 16:39:17 - mmengine - INFO - Saving checkpoint at 92 epochs 2022/09/13 16:39:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 16:40:01 - mmengine - INFO - Epoch(train) [93][50/293] lr: 5.000000e-04 eta: 6:26:30 time: 0.791557 data_time: 0.117293 memory: 21676 loss_kpt: 0.000573 acc_pose: 0.813689 loss: 0.000573 2022/09/13 16:40:40 - mmengine - INFO - Epoch(train) [93][100/293] lr: 5.000000e-04 eta: 6:26:03 time: 0.783183 data_time: 0.095836 memory: 21676 loss_kpt: 0.000564 acc_pose: 0.792106 loss: 0.000564 2022/09/13 16:41:19 - mmengine - INFO - Epoch(train) [93][150/293] lr: 5.000000e-04 eta: 6:25:36 time: 0.777432 data_time: 0.094808 memory: 21676 loss_kpt: 0.000576 acc_pose: 0.870437 loss: 0.000576 2022/09/13 16:41:58 - mmengine - INFO - Epoch(train) [93][200/293] lr: 5.000000e-04 eta: 6:25:09 time: 0.777460 data_time: 0.092818 memory: 21676 loss_kpt: 0.000585 acc_pose: 0.881846 loss: 0.000585 2022/09/13 16:42:38 - mmengine - INFO - Epoch(train) [93][250/293] lr: 5.000000e-04 eta: 6:24:43 time: 0.789316 data_time: 0.095348 memory: 21676 loss_kpt: 0.000577 acc_pose: 0.821561 loss: 0.000577 2022/09/13 16:43:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 16:43:11 - mmengine - INFO - Saving checkpoint at 93 epochs 2022/09/13 16:43:56 - mmengine - INFO - Epoch(train) [94][50/293] lr: 5.000000e-04 eta: 6:23:12 time: 0.796261 data_time: 0.109749 memory: 21676 loss_kpt: 0.000571 acc_pose: 0.782334 loss: 0.000571 2022/09/13 16:44:35 - mmengine - INFO - Epoch(train) [94][100/293] lr: 5.000000e-04 eta: 6:22:45 time: 0.778460 data_time: 0.101765 memory: 21676 loss_kpt: 0.000576 acc_pose: 0.832592 loss: 0.000576 2022/09/13 16:45:14 - mmengine - INFO - Epoch(train) [94][150/293] lr: 5.000000e-04 eta: 6:22:18 time: 0.779131 data_time: 0.103490 memory: 21676 loss_kpt: 0.000572 acc_pose: 0.851661 loss: 0.000572 2022/09/13 16:45:53 - mmengine - INFO - Epoch(train) [94][200/293] lr: 5.000000e-04 eta: 6:21:52 time: 0.786484 data_time: 0.108309 memory: 21676 loss_kpt: 0.000586 acc_pose: 0.793149 loss: 0.000586 2022/09/13 16:46:32 - mmengine - INFO - Epoch(train) [94][250/293] lr: 5.000000e-04 eta: 6:21:25 time: 0.786216 data_time: 0.109192 memory: 21676 loss_kpt: 0.000575 acc_pose: 0.797633 loss: 0.000575 2022/09/13 16:47:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 16:47:05 - mmengine - INFO - Saving checkpoint at 94 epochs 2022/09/13 16:47:49 - mmengine - INFO - Epoch(train) [95][50/293] lr: 5.000000e-04 eta: 6:19:54 time: 0.793608 data_time: 0.113027 memory: 21676 loss_kpt: 0.000579 acc_pose: 0.827196 loss: 0.000579 2022/09/13 16:48:28 - mmengine - INFO - Epoch(train) [95][100/293] lr: 5.000000e-04 eta: 6:19:28 time: 0.784429 data_time: 0.098565 memory: 21676 loss_kpt: 0.000572 acc_pose: 0.845820 loss: 0.000572 2022/09/13 16:49:08 - mmengine - INFO - Epoch(train) [95][150/293] lr: 5.000000e-04 eta: 6:19:01 time: 0.784969 data_time: 0.098623 memory: 21676 loss_kpt: 0.000574 acc_pose: 0.866377 loss: 0.000574 2022/09/13 16:49:47 - mmengine - INFO - Epoch(train) [95][200/293] lr: 5.000000e-04 eta: 6:18:34 time: 0.780377 data_time: 0.104326 memory: 21676 loss_kpt: 0.000570 acc_pose: 0.864061 loss: 0.000570 2022/09/13 16:50:25 - mmengine - INFO - Epoch(train) [95][250/293] lr: 5.000000e-04 eta: 6:18:06 time: 0.771772 data_time: 0.093786 memory: 21676 loss_kpt: 0.000568 acc_pose: 0.856157 loss: 0.000568 2022/09/13 16:50:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 16:50:59 - mmengine - INFO - Saving checkpoint at 95 epochs 2022/09/13 16:51:43 - mmengine - INFO - Epoch(train) [96][50/293] lr: 5.000000e-04 eta: 6:16:36 time: 0.791517 data_time: 0.104003 memory: 21676 loss_kpt: 0.000584 acc_pose: 0.793341 loss: 0.000584 2022/09/13 16:52:22 - mmengine - INFO - Epoch(train) [96][100/293] lr: 5.000000e-04 eta: 6:16:09 time: 0.780497 data_time: 0.099185 memory: 21676 loss_kpt: 0.000571 acc_pose: 0.766138 loss: 0.000571 2022/09/13 16:53:00 - mmengine - INFO - Epoch(train) [96][150/293] lr: 5.000000e-04 eta: 6:15:42 time: 0.776479 data_time: 0.100878 memory: 21676 loss_kpt: 0.000567 acc_pose: 0.861329 loss: 0.000567 2022/09/13 16:53:12 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 16:53:40 - mmengine - INFO - Epoch(train) [96][200/293] lr: 5.000000e-04 eta: 6:15:15 time: 0.793277 data_time: 0.102656 memory: 21676 loss_kpt: 0.000567 acc_pose: 0.835517 loss: 0.000567 2022/09/13 16:54:19 - mmengine - INFO - Epoch(train) [96][250/293] lr: 5.000000e-04 eta: 6:14:48 time: 0.774850 data_time: 0.108729 memory: 21676 loss_kpt: 0.000573 acc_pose: 0.841356 loss: 0.000573 2022/09/13 16:54:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 16:54:51 - mmengine - INFO - Saving checkpoint at 96 epochs 2022/09/13 16:55:35 - mmengine - INFO - Epoch(train) [97][50/293] lr: 5.000000e-04 eta: 6:13:18 time: 0.783507 data_time: 0.105440 memory: 21676 loss_kpt: 0.000584 acc_pose: 0.849067 loss: 0.000584 2022/09/13 16:56:14 - mmengine - INFO - Epoch(train) [97][100/293] lr: 5.000000e-04 eta: 6:12:51 time: 0.787449 data_time: 0.108965 memory: 21676 loss_kpt: 0.000562 acc_pose: 0.832795 loss: 0.000562 2022/09/13 16:56:53 - mmengine - INFO - Epoch(train) [97][150/293] lr: 5.000000e-04 eta: 6:12:24 time: 0.775363 data_time: 0.095540 memory: 21676 loss_kpt: 0.000568 acc_pose: 0.834532 loss: 0.000568 2022/09/13 16:57:32 - mmengine - INFO - Epoch(train) [97][200/293] lr: 5.000000e-04 eta: 6:11:57 time: 0.783356 data_time: 0.097809 memory: 21676 loss_kpt: 0.000562 acc_pose: 0.860917 loss: 0.000562 2022/09/13 16:58:11 - mmengine - INFO - Epoch(train) [97][250/293] lr: 5.000000e-04 eta: 6:11:30 time: 0.786200 data_time: 0.101566 memory: 21676 loss_kpt: 0.000583 acc_pose: 0.831700 loss: 0.000583 2022/09/13 16:58:45 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 16:58:45 - mmengine - INFO - Saving checkpoint at 97 epochs 2022/09/13 16:59:29 - mmengine - INFO - Epoch(train) [98][50/293] lr: 5.000000e-04 eta: 6:10:00 time: 0.788519 data_time: 0.112406 memory: 21676 loss_kpt: 0.000586 acc_pose: 0.802510 loss: 0.000586 2022/09/13 17:00:08 - mmengine - INFO - Epoch(train) [98][100/293] lr: 5.000000e-04 eta: 6:09:33 time: 0.786626 data_time: 0.100492 memory: 21676 loss_kpt: 0.000583 acc_pose: 0.855252 loss: 0.000583 2022/09/13 17:00:47 - mmengine - INFO - Epoch(train) [98][150/293] lr: 5.000000e-04 eta: 6:09:06 time: 0.786156 data_time: 0.097485 memory: 21676 loss_kpt: 0.000560 acc_pose: 0.837769 loss: 0.000560 2022/09/13 17:01:27 - mmengine - INFO - Epoch(train) [98][200/293] lr: 5.000000e-04 eta: 6:08:39 time: 0.788884 data_time: 0.096363 memory: 21676 loss_kpt: 0.000568 acc_pose: 0.830795 loss: 0.000568 2022/09/13 17:02:06 - mmengine - INFO - Epoch(train) [98][250/293] lr: 5.000000e-04 eta: 6:08:12 time: 0.777154 data_time: 0.101469 memory: 21676 loss_kpt: 0.000572 acc_pose: 0.810404 loss: 0.000572 2022/09/13 17:02:39 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 17:02:39 - mmengine - INFO - Saving checkpoint at 98 epochs 2022/09/13 17:03:23 - mmengine - INFO - Epoch(train) [99][50/293] lr: 5.000000e-04 eta: 6:06:43 time: 0.788004 data_time: 0.110234 memory: 21676 loss_kpt: 0.000573 acc_pose: 0.882638 loss: 0.000573 2022/09/13 17:04:03 - mmengine - INFO - Epoch(train) [99][100/293] lr: 5.000000e-04 eta: 6:06:17 time: 0.799600 data_time: 0.102728 memory: 21676 loss_kpt: 0.000579 acc_pose: 0.821087 loss: 0.000579 2022/09/13 17:04:41 - mmengine - INFO - Epoch(train) [99][150/293] lr: 5.000000e-04 eta: 6:05:49 time: 0.776448 data_time: 0.097673 memory: 21676 loss_kpt: 0.000552 acc_pose: 0.852536 loss: 0.000552 2022/09/13 17:05:21 - mmengine - INFO - Epoch(train) [99][200/293] lr: 5.000000e-04 eta: 6:05:22 time: 0.783685 data_time: 0.104612 memory: 21676 loss_kpt: 0.000571 acc_pose: 0.813582 loss: 0.000571 2022/09/13 17:05:59 - mmengine - INFO - Epoch(train) [99][250/293] lr: 5.000000e-04 eta: 6:04:54 time: 0.770884 data_time: 0.102511 memory: 21676 loss_kpt: 0.000572 acc_pose: 0.813119 loss: 0.000572 2022/09/13 17:06:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 17:06:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 17:06:32 - mmengine - INFO - Saving checkpoint at 99 epochs 2022/09/13 17:07:16 - mmengine - INFO - Epoch(train) [100][50/293] lr: 5.000000e-04 eta: 6:03:25 time: 0.786861 data_time: 0.104239 memory: 21676 loss_kpt: 0.000565 acc_pose: 0.869579 loss: 0.000565 2022/09/13 17:07:55 - mmengine - INFO - Epoch(train) [100][100/293] lr: 5.000000e-04 eta: 6:02:58 time: 0.786961 data_time: 0.101446 memory: 21676 loss_kpt: 0.000575 acc_pose: 0.795242 loss: 0.000575 2022/09/13 17:08:34 - mmengine - INFO - Epoch(train) [100][150/293] lr: 5.000000e-04 eta: 6:02:30 time: 0.774356 data_time: 0.103777 memory: 21676 loss_kpt: 0.000571 acc_pose: 0.809108 loss: 0.000571 2022/09/13 17:09:14 - mmengine - INFO - Epoch(train) [100][200/293] lr: 5.000000e-04 eta: 6:02:03 time: 0.789957 data_time: 0.096652 memory: 21676 loss_kpt: 0.000575 acc_pose: 0.863290 loss: 0.000575 2022/09/13 17:09:53 - mmengine - INFO - Epoch(train) [100][250/293] lr: 5.000000e-04 eta: 6:01:35 time: 0.780368 data_time: 0.100227 memory: 21676 loss_kpt: 0.000579 acc_pose: 0.843873 loss: 0.000579 2022/09/13 17:10:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 17:10:26 - mmengine - INFO - Saving checkpoint at 100 epochs 2022/09/13 17:10:40 - mmengine - INFO - Epoch(val) [100][50/407] eta: 0:01:06 time: 0.185987 data_time: 0.014992 memory: 21676 2022/09/13 17:10:49 - mmengine - INFO - Epoch(val) [100][100/407] eta: 0:00:54 time: 0.176004 data_time: 0.008899 memory: 1375 2022/09/13 17:10:57 - mmengine - INFO - Epoch(val) [100][150/407] eta: 0:00:45 time: 0.175752 data_time: 0.008536 memory: 1375 2022/09/13 17:11:06 - mmengine - INFO - Epoch(val) [100][200/407] eta: 0:00:36 time: 0.175603 data_time: 0.008799 memory: 1375 2022/09/13 17:11:15 - mmengine - INFO - Epoch(val) [100][250/407] eta: 0:00:28 time: 0.180587 data_time: 0.008758 memory: 1375 2022/09/13 17:11:24 - mmengine - INFO - Epoch(val) [100][300/407] eta: 0:00:18 time: 0.175787 data_time: 0.009069 memory: 1375 2022/09/13 17:11:33 - mmengine - INFO - Epoch(val) [100][350/407] eta: 0:00:10 time: 0.175508 data_time: 0.008709 memory: 1375 2022/09/13 17:11:41 - mmengine - INFO - Epoch(val) [100][400/407] eta: 0:00:01 time: 0.174243 data_time: 0.008981 memory: 1375 2022/09/13 17:12:17 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 17:12:31 - mmengine - INFO - Epoch(val) [100][407/407] coco/AP: 0.751939 coco/AP .5: 0.901747 coco/AP .75: 0.816015 coco/AP (M): 0.710876 coco/AP (L): 0.825016 coco/AR: 0.801212 coco/AR .5: 0.940649 coco/AR .75: 0.859572 coco/AR (M): 0.755367 coco/AR (L): 0.867075 2022/09/13 17:12:31 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220913/udp_w32_384_v1/best_coco/AP_epoch_90.pth is removed 2022/09/13 17:12:34 - mmengine - INFO - The best checkpoint with 0.7519 coco/AP at 100 epoch is saved to best_coco/AP_epoch_100.pth. 2022/09/13 17:13:14 - mmengine - INFO - Epoch(train) [101][50/293] lr: 5.000000e-04 eta: 6:00:08 time: 0.793097 data_time: 0.109244 memory: 21676 loss_kpt: 0.000570 acc_pose: 0.834816 loss: 0.000570 2022/09/13 17:13:53 - mmengine - INFO - Epoch(train) [101][100/293] lr: 5.000000e-04 eta: 5:59:40 time: 0.779918 data_time: 0.099874 memory: 21676 loss_kpt: 0.000574 acc_pose: 0.830797 loss: 0.000574 2022/09/13 17:14:32 - mmengine - INFO - Epoch(train) [101][150/293] lr: 5.000000e-04 eta: 5:59:13 time: 0.780624 data_time: 0.102350 memory: 21676 loss_kpt: 0.000561 acc_pose: 0.836611 loss: 0.000561 2022/09/13 17:15:11 - mmengine - INFO - Epoch(train) [101][200/293] lr: 5.000000e-04 eta: 5:58:45 time: 0.782097 data_time: 0.099651 memory: 21676 loss_kpt: 0.000555 acc_pose: 0.795342 loss: 0.000555 2022/09/13 17:15:50 - mmengine - INFO - Epoch(train) [101][250/293] lr: 5.000000e-04 eta: 5:58:17 time: 0.780991 data_time: 0.101220 memory: 21676 loss_kpt: 0.000573 acc_pose: 0.885942 loss: 0.000573 2022/09/13 17:16:23 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 17:16:23 - mmengine - INFO - Saving checkpoint at 101 epochs 2022/09/13 17:17:07 - mmengine - INFO - Epoch(train) [102][50/293] lr: 5.000000e-04 eta: 5:56:51 time: 0.801427 data_time: 0.113303 memory: 21676 loss_kpt: 0.000578 acc_pose: 0.809562 loss: 0.000578 2022/09/13 17:17:46 - mmengine - INFO - Epoch(train) [102][100/293] lr: 5.000000e-04 eta: 5:56:23 time: 0.785856 data_time: 0.100236 memory: 21676 loss_kpt: 0.000565 acc_pose: 0.846896 loss: 0.000565 2022/09/13 17:18:27 - mmengine - INFO - Epoch(train) [102][150/293] lr: 5.000000e-04 eta: 5:55:57 time: 0.803451 data_time: 0.100095 memory: 21676 loss_kpt: 0.000563 acc_pose: 0.799782 loss: 0.000563 2022/09/13 17:19:05 - mmengine - INFO - Epoch(train) [102][200/293] lr: 5.000000e-04 eta: 5:55:29 time: 0.775472 data_time: 0.094621 memory: 21676 loss_kpt: 0.000580 acc_pose: 0.850652 loss: 0.000580 2022/09/13 17:19:45 - mmengine - INFO - Epoch(train) [102][250/293] lr: 5.000000e-04 eta: 5:55:01 time: 0.788048 data_time: 0.099996 memory: 21676 loss_kpt: 0.000568 acc_pose: 0.834239 loss: 0.000568 2022/09/13 17:20:18 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 17:20:18 - mmengine - INFO - Saving checkpoint at 102 epochs 2022/09/13 17:21:02 - mmengine - INFO - Epoch(train) [103][50/293] lr: 5.000000e-04 eta: 5:53:35 time: 0.797397 data_time: 0.106773 memory: 21676 loss_kpt: 0.000571 acc_pose: 0.830496 loss: 0.000571 2022/09/13 17:21:41 - mmengine - INFO - Epoch(train) [103][100/293] lr: 5.000000e-04 eta: 5:53:07 time: 0.776726 data_time: 0.098102 memory: 21676 loss_kpt: 0.000558 acc_pose: 0.832105 loss: 0.000558 2022/09/13 17:21:52 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 17:22:20 - mmengine - INFO - Epoch(train) [103][150/293] lr: 5.000000e-04 eta: 5:52:39 time: 0.782109 data_time: 0.098932 memory: 21676 loss_kpt: 0.000558 acc_pose: 0.865223 loss: 0.000558 2022/09/13 17:22:59 - mmengine - INFO - Epoch(train) [103][200/293] lr: 5.000000e-04 eta: 5:52:11 time: 0.777866 data_time: 0.102114 memory: 21676 loss_kpt: 0.000570 acc_pose: 0.851934 loss: 0.000570 2022/09/13 17:23:38 - mmengine - INFO - Epoch(train) [103][250/293] lr: 5.000000e-04 eta: 5:51:43 time: 0.776732 data_time: 0.097331 memory: 21676 loss_kpt: 0.000568 acc_pose: 0.818183 loss: 0.000568 2022/09/13 17:24:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 17:24:11 - mmengine - INFO - Saving checkpoint at 103 epochs 2022/09/13 17:24:55 - mmengine - INFO - Epoch(train) [104][50/293] lr: 5.000000e-04 eta: 5:50:16 time: 0.790006 data_time: 0.112719 memory: 21676 loss_kpt: 0.000559 acc_pose: 0.858006 loss: 0.000559 2022/09/13 17:25:34 - mmengine - INFO - Epoch(train) [104][100/293] lr: 5.000000e-04 eta: 5:49:49 time: 0.784089 data_time: 0.099299 memory: 21676 loss_kpt: 0.000551 acc_pose: 0.873790 loss: 0.000551 2022/09/13 17:26:13 - mmengine - INFO - Epoch(train) [104][150/293] lr: 5.000000e-04 eta: 5:49:21 time: 0.784609 data_time: 0.095354 memory: 21676 loss_kpt: 0.000577 acc_pose: 0.848860 loss: 0.000577 2022/09/13 17:26:53 - mmengine - INFO - Epoch(train) [104][200/293] lr: 5.000000e-04 eta: 5:48:53 time: 0.784734 data_time: 0.097310 memory: 21676 loss_kpt: 0.000566 acc_pose: 0.869857 loss: 0.000566 2022/09/13 17:27:31 - mmengine - INFO - Epoch(train) [104][250/293] lr: 5.000000e-04 eta: 5:48:25 time: 0.775300 data_time: 0.098646 memory: 21676 loss_kpt: 0.000561 acc_pose: 0.857588 loss: 0.000561 2022/09/13 17:28:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 17:28:05 - mmengine - INFO - Saving checkpoint at 104 epochs 2022/09/13 17:28:49 - mmengine - INFO - Epoch(train) [105][50/293] lr: 5.000000e-04 eta: 5:46:59 time: 0.786151 data_time: 0.107398 memory: 21676 loss_kpt: 0.000561 acc_pose: 0.821208 loss: 0.000561 2022/09/13 17:29:27 - mmengine - INFO - Epoch(train) [105][100/293] lr: 5.000000e-04 eta: 5:46:29 time: 0.751252 data_time: 0.095812 memory: 21676 loss_kpt: 0.000559 acc_pose: 0.862303 loss: 0.000559 2022/09/13 17:30:05 - mmengine - INFO - Epoch(train) [105][150/293] lr: 5.000000e-04 eta: 5:46:00 time: 0.764411 data_time: 0.093818 memory: 21676 loss_kpt: 0.000574 acc_pose: 0.859536 loss: 0.000574 2022/09/13 17:30:43 - mmengine - INFO - Epoch(train) [105][200/293] lr: 5.000000e-04 eta: 5:45:31 time: 0.760968 data_time: 0.096541 memory: 21676 loss_kpt: 0.000566 acc_pose: 0.878993 loss: 0.000566 2022/09/13 17:31:21 - mmengine - INFO - Epoch(train) [105][250/293] lr: 5.000000e-04 eta: 5:45:01 time: 0.751950 data_time: 0.092812 memory: 21676 loss_kpt: 0.000575 acc_pose: 0.843384 loss: 0.000575 2022/09/13 17:31:53 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 17:31:53 - mmengine - INFO - Saving checkpoint at 105 epochs 2022/09/13 17:32:37 - mmengine - INFO - Epoch(train) [106][50/293] lr: 5.000000e-04 eta: 5:43:36 time: 0.787896 data_time: 0.112331 memory: 21676 loss_kpt: 0.000584 acc_pose: 0.875656 loss: 0.000584 2022/09/13 17:33:16 - mmengine - INFO - Epoch(train) [106][100/293] lr: 5.000000e-04 eta: 5:43:08 time: 0.775047 data_time: 0.096768 memory: 21676 loss_kpt: 0.000569 acc_pose: 0.838383 loss: 0.000569 2022/09/13 17:33:55 - mmengine - INFO - Epoch(train) [106][150/293] lr: 5.000000e-04 eta: 5:42:39 time: 0.779671 data_time: 0.096561 memory: 21676 loss_kpt: 0.000543 acc_pose: 0.872759 loss: 0.000543 2022/09/13 17:34:34 - mmengine - INFO - Epoch(train) [106][200/293] lr: 5.000000e-04 eta: 5:42:12 time: 0.790711 data_time: 0.096671 memory: 21676 loss_kpt: 0.000563 acc_pose: 0.863678 loss: 0.000563 2022/09/13 17:35:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 17:35:14 - mmengine - INFO - Epoch(train) [106][250/293] lr: 5.000000e-04 eta: 5:41:44 time: 0.784202 data_time: 0.098298 memory: 21676 loss_kpt: 0.000559 acc_pose: 0.826270 loss: 0.000559 2022/09/13 17:35:47 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 17:35:47 - mmengine - INFO - Saving checkpoint at 106 epochs 2022/09/13 17:36:32 - mmengine - INFO - Epoch(train) [107][50/293] lr: 5.000000e-04 eta: 5:40:19 time: 0.796598 data_time: 0.109285 memory: 21676 loss_kpt: 0.000563 acc_pose: 0.802029 loss: 0.000563 2022/09/13 17:37:12 - mmengine - INFO - Epoch(train) [107][100/293] lr: 5.000000e-04 eta: 5:39:52 time: 0.804397 data_time: 0.104032 memory: 21676 loss_kpt: 0.000564 acc_pose: 0.829340 loss: 0.000564 2022/09/13 17:37:51 - mmengine - INFO - Epoch(train) [107][150/293] lr: 5.000000e-04 eta: 5:39:24 time: 0.794611 data_time: 0.104345 memory: 21676 loss_kpt: 0.000579 acc_pose: 0.826201 loss: 0.000579 2022/09/13 17:38:30 - mmengine - INFO - Epoch(train) [107][200/293] lr: 5.000000e-04 eta: 5:38:56 time: 0.779339 data_time: 0.094131 memory: 21676 loss_kpt: 0.000575 acc_pose: 0.836868 loss: 0.000575 2022/09/13 17:39:10 - mmengine - INFO - Epoch(train) [107][250/293] lr: 5.000000e-04 eta: 5:38:28 time: 0.791132 data_time: 0.093076 memory: 21676 loss_kpt: 0.000568 acc_pose: 0.875007 loss: 0.000568 2022/09/13 17:39:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 17:39:43 - mmengine - INFO - Saving checkpoint at 107 epochs 2022/09/13 17:40:27 - mmengine - INFO - Epoch(train) [108][50/293] lr: 5.000000e-04 eta: 5:37:04 time: 0.792776 data_time: 0.105136 memory: 21676 loss_kpt: 0.000565 acc_pose: 0.855360 loss: 0.000565 2022/09/13 17:41:07 - mmengine - INFO - Epoch(train) [108][100/293] lr: 5.000000e-04 eta: 5:36:36 time: 0.784012 data_time: 0.101456 memory: 21676 loss_kpt: 0.000565 acc_pose: 0.833725 loss: 0.000565 2022/09/13 17:41:44 - mmengine - INFO - Epoch(train) [108][150/293] lr: 5.000000e-04 eta: 5:36:06 time: 0.754293 data_time: 0.095284 memory: 21676 loss_kpt: 0.000554 acc_pose: 0.851531 loss: 0.000554 2022/09/13 17:42:22 - mmengine - INFO - Epoch(train) [108][200/293] lr: 5.000000e-04 eta: 5:35:36 time: 0.748594 data_time: 0.099319 memory: 21676 loss_kpt: 0.000561 acc_pose: 0.814102 loss: 0.000561 2022/09/13 17:43:00 - mmengine - INFO - Epoch(train) [108][250/293] lr: 5.000000e-04 eta: 5:35:07 time: 0.759650 data_time: 0.092809 memory: 21676 loss_kpt: 0.000552 acc_pose: 0.830351 loss: 0.000552 2022/09/13 17:43:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 17:43:32 - mmengine - INFO - Saving checkpoint at 108 epochs 2022/09/13 17:44:16 - mmengine - INFO - Epoch(train) [109][50/293] lr: 5.000000e-04 eta: 5:33:43 time: 0.794195 data_time: 0.119158 memory: 21676 loss_kpt: 0.000560 acc_pose: 0.879856 loss: 0.000560 2022/09/13 17:44:55 - mmengine - INFO - Epoch(train) [109][100/293] lr: 5.000000e-04 eta: 5:33:14 time: 0.784410 data_time: 0.099479 memory: 21676 loss_kpt: 0.000555 acc_pose: 0.847982 loss: 0.000555 2022/09/13 17:45:34 - mmengine - INFO - Epoch(train) [109][150/293] lr: 5.000000e-04 eta: 5:32:46 time: 0.777863 data_time: 0.098592 memory: 21676 loss_kpt: 0.000568 acc_pose: 0.828784 loss: 0.000568 2022/09/13 17:46:14 - mmengine - INFO - Epoch(train) [109][200/293] lr: 5.000000e-04 eta: 5:32:18 time: 0.789403 data_time: 0.097585 memory: 21676 loss_kpt: 0.000577 acc_pose: 0.877641 loss: 0.000577 2022/09/13 17:46:53 - mmengine - INFO - Epoch(train) [109][250/293] lr: 5.000000e-04 eta: 5:31:50 time: 0.788297 data_time: 0.102796 memory: 21676 loss_kpt: 0.000571 acc_pose: 0.817159 loss: 0.000571 2022/09/13 17:47:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 17:47:27 - mmengine - INFO - Saving checkpoint at 109 epochs 2022/09/13 17:48:11 - mmengine - INFO - Epoch(train) [110][50/293] lr: 5.000000e-04 eta: 5:30:26 time: 0.793923 data_time: 0.106683 memory: 21676 loss_kpt: 0.000548 acc_pose: 0.870141 loss: 0.000548 2022/09/13 17:48:22 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 17:48:51 - mmengine - INFO - Epoch(train) [110][100/293] lr: 5.000000e-04 eta: 5:29:58 time: 0.786639 data_time: 0.096585 memory: 21676 loss_kpt: 0.000563 acc_pose: 0.810110 loss: 0.000563 2022/09/13 17:49:30 - mmengine - INFO - Epoch(train) [110][150/293] lr: 5.000000e-04 eta: 5:29:29 time: 0.779442 data_time: 0.100517 memory: 21676 loss_kpt: 0.000553 acc_pose: 0.831924 loss: 0.000553 2022/09/13 17:50:08 - mmengine - INFO - Epoch(train) [110][200/293] lr: 5.000000e-04 eta: 5:29:00 time: 0.772711 data_time: 0.100632 memory: 21676 loss_kpt: 0.000556 acc_pose: 0.877429 loss: 0.000556 2022/09/13 17:50:47 - mmengine - INFO - Epoch(train) [110][250/293] lr: 5.000000e-04 eta: 5:28:31 time: 0.765734 data_time: 0.097172 memory: 21676 loss_kpt: 0.000571 acc_pose: 0.809060 loss: 0.000571 2022/09/13 17:51:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 17:51:19 - mmengine - INFO - Saving checkpoint at 110 epochs 2022/09/13 17:51:32 - mmengine - INFO - Epoch(val) [110][50/407] eta: 0:01:05 time: 0.182678 data_time: 0.014830 memory: 21676 2022/09/13 17:51:41 - mmengine - INFO - Epoch(val) [110][100/407] eta: 0:00:54 time: 0.176254 data_time: 0.008383 memory: 1375 2022/09/13 17:51:50 - mmengine - INFO - Epoch(val) [110][150/407] eta: 0:00:45 time: 0.175312 data_time: 0.008511 memory: 1375 2022/09/13 17:51:59 - mmengine - INFO - Epoch(val) [110][200/407] eta: 0:00:37 time: 0.180859 data_time: 0.013463 memory: 1375 2022/09/13 17:52:08 - mmengine - INFO - Epoch(val) [110][250/407] eta: 0:00:27 time: 0.175914 data_time: 0.008558 memory: 1375 2022/09/13 17:52:17 - mmengine - INFO - Epoch(val) [110][300/407] eta: 0:00:18 time: 0.175245 data_time: 0.008584 memory: 1375 2022/09/13 17:52:25 - mmengine - INFO - Epoch(val) [110][350/407] eta: 0:00:10 time: 0.176083 data_time: 0.008573 memory: 1375 2022/09/13 17:52:34 - mmengine - INFO - Epoch(val) [110][400/407] eta: 0:00:01 time: 0.173471 data_time: 0.008028 memory: 1375 2022/09/13 17:53:10 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 17:53:24 - mmengine - INFO - Epoch(val) [110][407/407] coco/AP: 0.752589 coco/AP .5: 0.901206 coco/AP .75: 0.819202 coco/AP (M): 0.711542 coco/AP (L): 0.823550 coco/AR: 0.802472 coco/AR .5: 0.940176 coco/AR .75: 0.861146 coco/AR (M): 0.757553 coco/AR (L): 0.867596 2022/09/13 17:53:24 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220913/udp_w32_384_v1/best_coco/AP_epoch_100.pth is removed 2022/09/13 17:53:27 - mmengine - INFO - The best checkpoint with 0.7526 coco/AP at 110 epoch is saved to best_coco/AP_epoch_110.pth. 2022/09/13 17:54:07 - mmengine - INFO - Epoch(train) [111][50/293] lr: 5.000000e-04 eta: 5:27:08 time: 0.788722 data_time: 0.107681 memory: 21676 loss_kpt: 0.000559 acc_pose: 0.881118 loss: 0.000559 2022/09/13 17:54:46 - mmengine - INFO - Epoch(train) [111][100/293] lr: 5.000000e-04 eta: 5:26:39 time: 0.789545 data_time: 0.101019 memory: 21676 loss_kpt: 0.000571 acc_pose: 0.848509 loss: 0.000571 2022/09/13 17:55:26 - mmengine - INFO - Epoch(train) [111][150/293] lr: 5.000000e-04 eta: 5:26:11 time: 0.787684 data_time: 0.092860 memory: 21676 loss_kpt: 0.000552 acc_pose: 0.838932 loss: 0.000552 2022/09/13 17:56:05 - mmengine - INFO - Epoch(train) [111][200/293] lr: 5.000000e-04 eta: 5:25:43 time: 0.783695 data_time: 0.096638 memory: 21676 loss_kpt: 0.000566 acc_pose: 0.854074 loss: 0.000566 2022/09/13 17:56:44 - mmengine - INFO - Epoch(train) [111][250/293] lr: 5.000000e-04 eta: 5:25:14 time: 0.788350 data_time: 0.099324 memory: 21676 loss_kpt: 0.000550 acc_pose: 0.853651 loss: 0.000550 2022/09/13 17:57:17 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 17:57:17 - mmengine - INFO - Saving checkpoint at 111 epochs 2022/09/13 17:58:02 - mmengine - INFO - Epoch(train) [112][50/293] lr: 5.000000e-04 eta: 5:23:52 time: 0.794431 data_time: 0.104172 memory: 21676 loss_kpt: 0.000561 acc_pose: 0.857831 loss: 0.000561 2022/09/13 17:58:41 - mmengine - INFO - Epoch(train) [112][100/293] lr: 5.000000e-04 eta: 5:23:23 time: 0.781245 data_time: 0.095496 memory: 21676 loss_kpt: 0.000552 acc_pose: 0.833001 loss: 0.000552 2022/09/13 17:59:19 - mmengine - INFO - Epoch(train) [112][150/293] lr: 5.000000e-04 eta: 5:22:54 time: 0.771836 data_time: 0.096177 memory: 21676 loss_kpt: 0.000560 acc_pose: 0.832882 loss: 0.000560 2022/09/13 17:59:57 - mmengine - INFO - Epoch(train) [112][200/293] lr: 5.000000e-04 eta: 5:22:24 time: 0.760135 data_time: 0.098641 memory: 21676 loss_kpt: 0.000553 acc_pose: 0.856087 loss: 0.000553 2022/09/13 18:00:37 - mmengine - INFO - Epoch(train) [112][250/293] lr: 5.000000e-04 eta: 5:21:56 time: 0.800735 data_time: 0.097399 memory: 21676 loss_kpt: 0.000562 acc_pose: 0.831960 loss: 0.000562 2022/09/13 18:01:10 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 18:01:10 - mmengine - INFO - Saving checkpoint at 112 epochs 2022/09/13 18:01:55 - mmengine - INFO - Epoch(train) [113][50/293] lr: 5.000000e-04 eta: 5:20:34 time: 0.799334 data_time: 0.108376 memory: 21676 loss_kpt: 0.000565 acc_pose: 0.858152 loss: 0.000565 2022/09/13 18:02:34 - mmengine - INFO - Epoch(train) [113][100/293] lr: 5.000000e-04 eta: 5:20:05 time: 0.781014 data_time: 0.100529 memory: 21676 loss_kpt: 0.000557 acc_pose: 0.907638 loss: 0.000557 2022/09/13 18:03:13 - mmengine - INFO - Epoch(train) [113][150/293] lr: 5.000000e-04 eta: 5:19:37 time: 0.790886 data_time: 0.102653 memory: 21676 loss_kpt: 0.000549 acc_pose: 0.840960 loss: 0.000549 2022/09/13 18:03:40 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 18:03:52 - mmengine - INFO - Epoch(train) [113][200/293] lr: 5.000000e-04 eta: 5:19:08 time: 0.780225 data_time: 0.104594 memory: 21676 loss_kpt: 0.000556 acc_pose: 0.839236 loss: 0.000556 2022/09/13 18:04:31 - mmengine - INFO - Epoch(train) [113][250/293] lr: 5.000000e-04 eta: 5:18:39 time: 0.773074 data_time: 0.102321 memory: 21676 loss_kpt: 0.000564 acc_pose: 0.840690 loss: 0.000564 2022/09/13 18:05:03 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 18:05:03 - mmengine - INFO - Saving checkpoint at 113 epochs 2022/09/13 18:05:48 - mmengine - INFO - Epoch(train) [114][50/293] lr: 5.000000e-04 eta: 5:17:17 time: 0.796936 data_time: 0.109102 memory: 21676 loss_kpt: 0.000546 acc_pose: 0.842169 loss: 0.000546 2022/09/13 18:06:27 - mmengine - INFO - Epoch(train) [114][100/293] lr: 5.000000e-04 eta: 5:16:48 time: 0.783212 data_time: 0.099066 memory: 21676 loss_kpt: 0.000565 acc_pose: 0.835064 loss: 0.000565 2022/09/13 18:07:05 - mmengine - INFO - Epoch(train) [114][150/293] lr: 5.000000e-04 eta: 5:16:19 time: 0.771701 data_time: 0.102653 memory: 21676 loss_kpt: 0.000560 acc_pose: 0.839375 loss: 0.000560 2022/09/13 18:07:44 - mmengine - INFO - Epoch(train) [114][200/293] lr: 5.000000e-04 eta: 5:15:50 time: 0.772373 data_time: 0.107873 memory: 21676 loss_kpt: 0.000566 acc_pose: 0.848875 loss: 0.000566 2022/09/13 18:08:23 - mmengine - INFO - Epoch(train) [114][250/293] lr: 5.000000e-04 eta: 5:15:21 time: 0.780339 data_time: 0.106042 memory: 21676 loss_kpt: 0.000546 acc_pose: 0.849689 loss: 0.000546 2022/09/13 18:08:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 18:08:56 - mmengine - INFO - Saving checkpoint at 114 epochs 2022/09/13 18:09:40 - mmengine - INFO - Epoch(train) [115][50/293] lr: 5.000000e-04 eta: 5:13:59 time: 0.792525 data_time: 0.110216 memory: 21676 loss_kpt: 0.000564 acc_pose: 0.865518 loss: 0.000564 2022/09/13 18:10:19 - mmengine - INFO - Epoch(train) [115][100/293] lr: 5.000000e-04 eta: 5:13:31 time: 0.791616 data_time: 0.098674 memory: 21676 loss_kpt: 0.000570 acc_pose: 0.846278 loss: 0.000570 2022/09/13 18:10:59 - mmengine - INFO - Epoch(train) [115][150/293] lr: 5.000000e-04 eta: 5:13:02 time: 0.787061 data_time: 0.096379 memory: 21676 loss_kpt: 0.000553 acc_pose: 0.853083 loss: 0.000553 2022/09/13 18:11:38 - mmengine - INFO - Epoch(train) [115][200/293] lr: 5.000000e-04 eta: 5:12:33 time: 0.778163 data_time: 0.092811 memory: 21676 loss_kpt: 0.000544 acc_pose: 0.802633 loss: 0.000544 2022/09/13 18:12:17 - mmengine - INFO - Epoch(train) [115][250/293] lr: 5.000000e-04 eta: 5:12:04 time: 0.784367 data_time: 0.103137 memory: 21676 loss_kpt: 0.000569 acc_pose: 0.854739 loss: 0.000569 2022/09/13 18:12:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 18:12:50 - mmengine - INFO - Saving checkpoint at 115 epochs 2022/09/13 18:13:34 - mmengine - INFO - Epoch(train) [116][50/293] lr: 5.000000e-04 eta: 5:10:43 time: 0.795663 data_time: 0.111987 memory: 21676 loss_kpt: 0.000560 acc_pose: 0.857893 loss: 0.000560 2022/09/13 18:14:13 - mmengine - INFO - Epoch(train) [116][100/293] lr: 5.000000e-04 eta: 5:10:14 time: 0.780279 data_time: 0.107319 memory: 21676 loss_kpt: 0.000563 acc_pose: 0.855538 loss: 0.000563 2022/09/13 18:14:52 - mmengine - INFO - Epoch(train) [116][150/293] lr: 5.000000e-04 eta: 5:09:45 time: 0.784872 data_time: 0.100912 memory: 21676 loss_kpt: 0.000557 acc_pose: 0.826464 loss: 0.000557 2022/09/13 18:15:32 - mmengine - INFO - Epoch(train) [116][200/293] lr: 5.000000e-04 eta: 5:09:16 time: 0.787278 data_time: 0.097995 memory: 21676 loss_kpt: 0.000549 acc_pose: 0.816428 loss: 0.000549 2022/09/13 18:16:10 - mmengine - INFO - Epoch(train) [116][250/293] lr: 5.000000e-04 eta: 5:08:46 time: 0.771578 data_time: 0.105875 memory: 21676 loss_kpt: 0.000552 acc_pose: 0.813717 loss: 0.000552 2022/09/13 18:16:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 18:16:43 - mmengine - INFO - Saving checkpoint at 116 epochs 2022/09/13 18:16:57 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 18:17:27 - mmengine - INFO - Epoch(train) [117][50/293] lr: 5.000000e-04 eta: 5:07:25 time: 0.791535 data_time: 0.105071 memory: 21676 loss_kpt: 0.000558 acc_pose: 0.821651 loss: 0.000558 2022/09/13 18:18:07 - mmengine - INFO - Epoch(train) [117][100/293] lr: 5.000000e-04 eta: 5:06:57 time: 0.794066 data_time: 0.100998 memory: 21676 loss_kpt: 0.000571 acc_pose: 0.834738 loss: 0.000571 2022/09/13 18:18:46 - mmengine - INFO - Epoch(train) [117][150/293] lr: 5.000000e-04 eta: 5:06:28 time: 0.778119 data_time: 0.093179 memory: 21676 loss_kpt: 0.000560 acc_pose: 0.880058 loss: 0.000560 2022/09/13 18:19:25 - mmengine - INFO - Epoch(train) [117][200/293] lr: 5.000000e-04 eta: 5:05:59 time: 0.788620 data_time: 0.094785 memory: 21676 loss_kpt: 0.000554 acc_pose: 0.844001 loss: 0.000554 2022/09/13 18:20:04 - mmengine - INFO - Epoch(train) [117][250/293] lr: 5.000000e-04 eta: 5:05:29 time: 0.775401 data_time: 0.093044 memory: 21676 loss_kpt: 0.000564 acc_pose: 0.794355 loss: 0.000564 2022/09/13 18:20:38 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 18:20:38 - mmengine - INFO - Saving checkpoint at 117 epochs 2022/09/13 18:21:22 - mmengine - INFO - Epoch(train) [118][50/293] lr: 5.000000e-04 eta: 5:04:09 time: 0.789103 data_time: 0.110987 memory: 21676 loss_kpt: 0.000556 acc_pose: 0.825218 loss: 0.000556 2022/09/13 18:22:01 - mmengine - INFO - Epoch(train) [118][100/293] lr: 5.000000e-04 eta: 5:03:39 time: 0.783052 data_time: 0.100790 memory: 21676 loss_kpt: 0.000551 acc_pose: 0.851907 loss: 0.000551 2022/09/13 18:22:40 - mmengine - INFO - Epoch(train) [118][150/293] lr: 5.000000e-04 eta: 5:03:11 time: 0.791601 data_time: 0.096643 memory: 21676 loss_kpt: 0.000546 acc_pose: 0.818249 loss: 0.000546 2022/09/13 18:23:20 - mmengine - INFO - Epoch(train) [118][200/293] lr: 5.000000e-04 eta: 5:02:42 time: 0.789796 data_time: 0.102995 memory: 21676 loss_kpt: 0.000577 acc_pose: 0.835085 loss: 0.000577 2022/09/13 18:23:59 - mmengine - INFO - Epoch(train) [118][250/293] lr: 5.000000e-04 eta: 5:02:12 time: 0.778911 data_time: 0.093190 memory: 21676 loss_kpt: 0.000558 acc_pose: 0.842098 loss: 0.000558 2022/09/13 18:24:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 18:24:32 - mmengine - INFO - Saving checkpoint at 118 epochs 2022/09/13 18:25:16 - mmengine - INFO - Epoch(train) [119][50/293] lr: 5.000000e-04 eta: 5:00:52 time: 0.793692 data_time: 0.108124 memory: 21676 loss_kpt: 0.000568 acc_pose: 0.835796 loss: 0.000568 2022/09/13 18:25:55 - mmengine - INFO - Epoch(train) [119][100/293] lr: 5.000000e-04 eta: 5:00:23 time: 0.783683 data_time: 0.096392 memory: 21676 loss_kpt: 0.000544 acc_pose: 0.825242 loss: 0.000544 2022/09/13 18:26:34 - mmengine - INFO - Epoch(train) [119][150/293] lr: 5.000000e-04 eta: 4:59:54 time: 0.779580 data_time: 0.097155 memory: 21676 loss_kpt: 0.000566 acc_pose: 0.864568 loss: 0.000566 2022/09/13 18:27:13 - mmengine - INFO - Epoch(train) [119][200/293] lr: 5.000000e-04 eta: 4:59:24 time: 0.784242 data_time: 0.103063 memory: 21676 loss_kpt: 0.000562 acc_pose: 0.839557 loss: 0.000562 2022/09/13 18:27:52 - mmengine - INFO - Epoch(train) [119][250/293] lr: 5.000000e-04 eta: 4:58:55 time: 0.773422 data_time: 0.092244 memory: 21676 loss_kpt: 0.000563 acc_pose: 0.858370 loss: 0.000563 2022/09/13 18:28:25 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 18:28:25 - mmengine - INFO - Saving checkpoint at 119 epochs 2022/09/13 18:29:08 - mmengine - INFO - Epoch(train) [120][50/293] lr: 5.000000e-04 eta: 4:57:34 time: 0.772476 data_time: 0.106389 memory: 21676 loss_kpt: 0.000556 acc_pose: 0.809598 loss: 0.000556 2022/09/13 18:29:46 - mmengine - INFO - Epoch(train) [120][100/293] lr: 5.000000e-04 eta: 4:57:04 time: 0.759443 data_time: 0.095672 memory: 21676 loss_kpt: 0.000555 acc_pose: 0.855449 loss: 0.000555 2022/09/13 18:30:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 18:30:24 - mmengine - INFO - Epoch(train) [120][150/293] lr: 5.000000e-04 eta: 4:56:34 time: 0.758216 data_time: 0.092735 memory: 21676 loss_kpt: 0.000575 acc_pose: 0.820585 loss: 0.000575 2022/09/13 18:31:02 - mmengine - INFO - Epoch(train) [120][200/293] lr: 5.000000e-04 eta: 4:56:04 time: 0.764242 data_time: 0.097536 memory: 21676 loss_kpt: 0.000553 acc_pose: 0.853160 loss: 0.000553 2022/09/13 18:31:40 - mmengine - INFO - Epoch(train) [120][250/293] lr: 5.000000e-04 eta: 4:55:33 time: 0.754004 data_time: 0.093209 memory: 21676 loss_kpt: 0.000542 acc_pose: 0.847942 loss: 0.000542 2022/09/13 18:32:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 18:32:13 - mmengine - INFO - Saving checkpoint at 120 epochs 2022/09/13 18:32:27 - mmengine - INFO - Epoch(val) [120][50/407] eta: 0:01:05 time: 0.184168 data_time: 0.014653 memory: 21676 2022/09/13 18:32:36 - mmengine - INFO - Epoch(val) [120][100/407] eta: 0:00:53 time: 0.175640 data_time: 0.008454 memory: 1375 2022/09/13 18:32:44 - mmengine - INFO - Epoch(val) [120][150/407] eta: 0:00:45 time: 0.177337 data_time: 0.008621 memory: 1375 2022/09/13 18:32:53 - mmengine - INFO - Epoch(val) [120][200/407] eta: 0:00:36 time: 0.178664 data_time: 0.008563 memory: 1375 2022/09/13 18:33:02 - mmengine - INFO - Epoch(val) [120][250/407] eta: 0:00:27 time: 0.175855 data_time: 0.009062 memory: 1375 2022/09/13 18:33:11 - mmengine - INFO - Epoch(val) [120][300/407] eta: 0:00:18 time: 0.175247 data_time: 0.008269 memory: 1375 2022/09/13 18:33:20 - mmengine - INFO - Epoch(val) [120][350/407] eta: 0:00:10 time: 0.175777 data_time: 0.008845 memory: 1375 2022/09/13 18:33:29 - mmengine - INFO - Epoch(val) [120][400/407] eta: 0:00:01 time: 0.174697 data_time: 0.008745 memory: 1375 2022/09/13 18:34:04 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 18:34:17 - mmengine - INFO - Epoch(val) [120][407/407] coco/AP: 0.753869 coco/AP .5: 0.898902 coco/AP .75: 0.817339 coco/AP (M): 0.715033 coco/AP (L): 0.826471 coco/AR: 0.804691 coco/AR .5: 0.939861 coco/AR .75: 0.860516 coco/AR (M): 0.759929 coco/AR (L): 0.870531 2022/09/13 18:34:17 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220913/udp_w32_384_v1/best_coco/AP_epoch_110.pth is removed 2022/09/13 18:34:21 - mmengine - INFO - The best checkpoint with 0.7539 coco/AP at 120 epoch is saved to best_coco/AP_epoch_120.pth. 2022/09/13 18:35:01 - mmengine - INFO - Epoch(train) [121][50/293] lr: 5.000000e-04 eta: 4:54:14 time: 0.794353 data_time: 0.107151 memory: 21676 loss_kpt: 0.000550 acc_pose: 0.814430 loss: 0.000550 2022/09/13 18:35:40 - mmengine - INFO - Epoch(train) [121][100/293] lr: 5.000000e-04 eta: 4:53:44 time: 0.781062 data_time: 0.100506 memory: 21676 loss_kpt: 0.000552 acc_pose: 0.869152 loss: 0.000552 2022/09/13 18:36:18 - mmengine - INFO - Epoch(train) [121][150/293] lr: 5.000000e-04 eta: 4:53:15 time: 0.775263 data_time: 0.098153 memory: 21676 loss_kpt: 0.000565 acc_pose: 0.845265 loss: 0.000565 2022/09/13 18:36:57 - mmengine - INFO - Epoch(train) [121][200/293] lr: 5.000000e-04 eta: 4:52:45 time: 0.781981 data_time: 0.092334 memory: 21676 loss_kpt: 0.000563 acc_pose: 0.886227 loss: 0.000563 2022/09/13 18:37:36 - mmengine - INFO - Epoch(train) [121][250/293] lr: 5.000000e-04 eta: 4:52:16 time: 0.778601 data_time: 0.099575 memory: 21676 loss_kpt: 0.000545 acc_pose: 0.858283 loss: 0.000545 2022/09/13 18:38:10 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 18:38:10 - mmengine - INFO - Saving checkpoint at 121 epochs 2022/09/13 18:38:54 - mmengine - INFO - Epoch(train) [122][50/293] lr: 5.000000e-04 eta: 4:50:57 time: 0.795813 data_time: 0.112217 memory: 21676 loss_kpt: 0.000562 acc_pose: 0.802565 loss: 0.000562 2022/09/13 18:39:33 - mmengine - INFO - Epoch(train) [122][100/293] lr: 5.000000e-04 eta: 4:50:27 time: 0.786622 data_time: 0.097931 memory: 21676 loss_kpt: 0.000553 acc_pose: 0.892870 loss: 0.000553 2022/09/13 18:40:13 - mmengine - INFO - Epoch(train) [122][150/293] lr: 5.000000e-04 eta: 4:49:58 time: 0.786406 data_time: 0.097955 memory: 21676 loss_kpt: 0.000554 acc_pose: 0.860381 loss: 0.000554 2022/09/13 18:40:51 - mmengine - INFO - Epoch(train) [122][200/293] lr: 5.000000e-04 eta: 4:49:28 time: 0.757606 data_time: 0.099637 memory: 21676 loss_kpt: 0.000550 acc_pose: 0.820449 loss: 0.000550 2022/09/13 18:41:29 - mmengine - INFO - Epoch(train) [122][250/293] lr: 5.000000e-04 eta: 4:48:57 time: 0.764487 data_time: 0.091993 memory: 21676 loss_kpt: 0.000558 acc_pose: 0.805132 loss: 0.000558 2022/09/13 18:42:01 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 18:42:01 - mmengine - INFO - Saving checkpoint at 122 epochs 2022/09/13 18:42:46 - mmengine - INFO - Epoch(train) [123][50/293] lr: 5.000000e-04 eta: 4:47:39 time: 0.798422 data_time: 0.111093 memory: 21676 loss_kpt: 0.000571 acc_pose: 0.757809 loss: 0.000571 2022/09/13 18:43:25 - mmengine - INFO - Epoch(train) [123][100/293] lr: 5.000000e-04 eta: 4:47:09 time: 0.786099 data_time: 0.094737 memory: 21676 loss_kpt: 0.000544 acc_pose: 0.877685 loss: 0.000544 2022/09/13 18:44:05 - mmengine - INFO - Epoch(train) [123][150/293] lr: 5.000000e-04 eta: 4:46:40 time: 0.793554 data_time: 0.106688 memory: 21676 loss_kpt: 0.000555 acc_pose: 0.838337 loss: 0.000555 2022/09/13 18:44:44 - mmengine - INFO - Epoch(train) [123][200/293] lr: 5.000000e-04 eta: 4:46:11 time: 0.785443 data_time: 0.101518 memory: 21676 loss_kpt: 0.000552 acc_pose: 0.834484 loss: 0.000552 2022/09/13 18:45:23 - mmengine - INFO - Epoch(train) [123][250/293] lr: 5.000000e-04 eta: 4:45:41 time: 0.777007 data_time: 0.099558 memory: 21676 loss_kpt: 0.000555 acc_pose: 0.861392 loss: 0.000555 2022/09/13 18:45:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 18:45:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 18:45:56 - mmengine - INFO - Saving checkpoint at 123 epochs 2022/09/13 18:46:41 - mmengine - INFO - Epoch(train) [124][50/293] lr: 5.000000e-04 eta: 4:44:22 time: 0.795464 data_time: 0.109284 memory: 21676 loss_kpt: 0.000564 acc_pose: 0.827546 loss: 0.000564 2022/09/13 18:47:20 - mmengine - INFO - Epoch(train) [124][100/293] lr: 5.000000e-04 eta: 4:43:53 time: 0.784565 data_time: 0.097567 memory: 21676 loss_kpt: 0.000552 acc_pose: 0.857003 loss: 0.000552 2022/09/13 18:48:00 - mmengine - INFO - Epoch(train) [124][150/293] lr: 5.000000e-04 eta: 4:43:24 time: 0.793629 data_time: 0.102410 memory: 21676 loss_kpt: 0.000562 acc_pose: 0.843294 loss: 0.000562 2022/09/13 18:48:39 - mmengine - INFO - Epoch(train) [124][200/293] lr: 5.000000e-04 eta: 4:42:54 time: 0.780050 data_time: 0.098662 memory: 21676 loss_kpt: 0.000562 acc_pose: 0.860210 loss: 0.000562 2022/09/13 18:49:18 - mmengine - INFO - Epoch(train) [124][250/293] lr: 5.000000e-04 eta: 4:42:24 time: 0.786825 data_time: 0.097580 memory: 21676 loss_kpt: 0.000544 acc_pose: 0.847399 loss: 0.000544 2022/09/13 18:49:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 18:49:51 - mmengine - INFO - Saving checkpoint at 124 epochs 2022/09/13 18:50:35 - mmengine - INFO - Epoch(train) [125][50/293] lr: 5.000000e-04 eta: 4:41:06 time: 0.789614 data_time: 0.104704 memory: 21676 loss_kpt: 0.000545 acc_pose: 0.838344 loss: 0.000545 2022/09/13 18:51:14 - mmengine - INFO - Epoch(train) [125][100/293] lr: 5.000000e-04 eta: 4:40:37 time: 0.786158 data_time: 0.099402 memory: 21676 loss_kpt: 0.000559 acc_pose: 0.858622 loss: 0.000559 2022/09/13 18:51:54 - mmengine - INFO - Epoch(train) [125][150/293] lr: 5.000000e-04 eta: 4:40:07 time: 0.791840 data_time: 0.100271 memory: 21676 loss_kpt: 0.000547 acc_pose: 0.845436 loss: 0.000547 2022/09/13 18:52:32 - mmengine - INFO - Epoch(train) [125][200/293] lr: 5.000000e-04 eta: 4:39:37 time: 0.762479 data_time: 0.096155 memory: 21676 loss_kpt: 0.000544 acc_pose: 0.816289 loss: 0.000544 2022/09/13 18:53:10 - mmengine - INFO - Epoch(train) [125][250/293] lr: 5.000000e-04 eta: 4:39:06 time: 0.757791 data_time: 0.093971 memory: 21676 loss_kpt: 0.000555 acc_pose: 0.824383 loss: 0.000555 2022/09/13 18:53:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 18:53:42 - mmengine - INFO - Saving checkpoint at 125 epochs 2022/09/13 18:54:26 - mmengine - INFO - Epoch(train) [126][50/293] lr: 5.000000e-04 eta: 4:37:49 time: 0.801008 data_time: 0.106894 memory: 21676 loss_kpt: 0.000563 acc_pose: 0.880532 loss: 0.000563 2022/09/13 18:55:05 - mmengine - INFO - Epoch(train) [126][100/293] lr: 5.000000e-04 eta: 4:37:19 time: 0.786376 data_time: 0.098109 memory: 21676 loss_kpt: 0.000551 acc_pose: 0.875553 loss: 0.000551 2022/09/13 18:55:45 - mmengine - INFO - Epoch(train) [126][150/293] lr: 5.000000e-04 eta: 4:36:49 time: 0.785504 data_time: 0.095217 memory: 21676 loss_kpt: 0.000556 acc_pose: 0.854107 loss: 0.000556 2022/09/13 18:56:24 - mmengine - INFO - Epoch(train) [126][200/293] lr: 5.000000e-04 eta: 4:36:20 time: 0.785178 data_time: 0.100702 memory: 21676 loss_kpt: 0.000556 acc_pose: 0.836453 loss: 0.000556 2022/09/13 18:57:03 - mmengine - INFO - Epoch(train) [126][250/293] lr: 5.000000e-04 eta: 4:35:50 time: 0.781383 data_time: 0.098887 memory: 21676 loss_kpt: 0.000560 acc_pose: 0.833054 loss: 0.000560 2022/09/13 18:57:36 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 18:57:36 - mmengine - INFO - Saving checkpoint at 126 epochs 2022/09/13 18:58:21 - mmengine - INFO - Epoch(train) [127][50/293] lr: 5.000000e-04 eta: 4:34:33 time: 0.810997 data_time: 0.109170 memory: 21676 loss_kpt: 0.000545 acc_pose: 0.821459 loss: 0.000545 2022/09/13 18:58:45 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 18:59:00 - mmengine - INFO - Epoch(train) [127][100/293] lr: 5.000000e-04 eta: 4:34:03 time: 0.778435 data_time: 0.100587 memory: 21676 loss_kpt: 0.000551 acc_pose: 0.857817 loss: 0.000551 2022/09/13 18:59:39 - mmengine - INFO - Epoch(train) [127][150/293] lr: 5.000000e-04 eta: 4:33:33 time: 0.785064 data_time: 0.103741 memory: 21676 loss_kpt: 0.000559 acc_pose: 0.847908 loss: 0.000559 2022/09/13 19:00:19 - mmengine - INFO - Epoch(train) [127][200/293] lr: 5.000000e-04 eta: 4:33:04 time: 0.799413 data_time: 0.098229 memory: 21676 loss_kpt: 0.000555 acc_pose: 0.790739 loss: 0.000555 2022/09/13 19:00:58 - mmengine - INFO - Epoch(train) [127][250/293] lr: 5.000000e-04 eta: 4:32:33 time: 0.773610 data_time: 0.098115 memory: 21676 loss_kpt: 0.000569 acc_pose: 0.797149 loss: 0.000569 2022/09/13 19:01:31 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 19:01:31 - mmengine - INFO - Saving checkpoint at 127 epochs 2022/09/13 19:02:16 - mmengine - INFO - Epoch(train) [128][50/293] lr: 5.000000e-04 eta: 4:31:17 time: 0.805404 data_time: 0.109209 memory: 21676 loss_kpt: 0.000548 acc_pose: 0.849819 loss: 0.000548 2022/09/13 19:02:55 - mmengine - INFO - Epoch(train) [128][100/293] lr: 5.000000e-04 eta: 4:30:47 time: 0.783755 data_time: 0.102588 memory: 21676 loss_kpt: 0.000559 acc_pose: 0.852454 loss: 0.000559 2022/09/13 19:03:34 - mmengine - INFO - Epoch(train) [128][150/293] lr: 5.000000e-04 eta: 4:30:17 time: 0.784294 data_time: 0.097752 memory: 21676 loss_kpt: 0.000552 acc_pose: 0.859635 loss: 0.000552 2022/09/13 19:04:14 - mmengine - INFO - Epoch(train) [128][200/293] lr: 5.000000e-04 eta: 4:29:47 time: 0.788136 data_time: 0.105820 memory: 21676 loss_kpt: 0.000559 acc_pose: 0.857549 loss: 0.000559 2022/09/13 19:04:53 - mmengine - INFO - Epoch(train) [128][250/293] lr: 5.000000e-04 eta: 4:29:17 time: 0.783984 data_time: 0.094145 memory: 21676 loss_kpt: 0.000549 acc_pose: 0.838532 loss: 0.000549 2022/09/13 19:05:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 19:05:26 - mmengine - INFO - Saving checkpoint at 128 epochs 2022/09/13 19:06:10 - mmengine - INFO - Epoch(train) [129][50/293] lr: 5.000000e-04 eta: 4:28:00 time: 0.790800 data_time: 0.110974 memory: 21676 loss_kpt: 0.000545 acc_pose: 0.862414 loss: 0.000545 2022/09/13 19:06:50 - mmengine - INFO - Epoch(train) [129][100/293] lr: 5.000000e-04 eta: 4:27:30 time: 0.790226 data_time: 0.095482 memory: 21676 loss_kpt: 0.000558 acc_pose: 0.900112 loss: 0.000558 2022/09/13 19:07:30 - mmengine - INFO - Epoch(train) [129][150/293] lr: 5.000000e-04 eta: 4:27:01 time: 0.793671 data_time: 0.101803 memory: 21676 loss_kpt: 0.000548 acc_pose: 0.868809 loss: 0.000548 2022/09/13 19:08:09 - mmengine - INFO - Epoch(train) [129][200/293] lr: 5.000000e-04 eta: 4:26:31 time: 0.783037 data_time: 0.098689 memory: 21676 loss_kpt: 0.000550 acc_pose: 0.868325 loss: 0.000550 2022/09/13 19:08:48 - mmengine - INFO - Epoch(train) [129][250/293] lr: 5.000000e-04 eta: 4:26:01 time: 0.787606 data_time: 0.101609 memory: 21676 loss_kpt: 0.000556 acc_pose: 0.859698 loss: 0.000556 2022/09/13 19:09:21 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 19:09:21 - mmengine - INFO - Saving checkpoint at 129 epochs 2022/09/13 19:10:05 - mmengine - INFO - Epoch(train) [130][50/293] lr: 5.000000e-04 eta: 4:24:44 time: 0.787872 data_time: 0.115441 memory: 21676 loss_kpt: 0.000543 acc_pose: 0.826149 loss: 0.000543 2022/09/13 19:10:44 - mmengine - INFO - Epoch(train) [130][100/293] lr: 5.000000e-04 eta: 4:24:14 time: 0.777692 data_time: 0.100650 memory: 21676 loss_kpt: 0.000536 acc_pose: 0.868647 loss: 0.000536 2022/09/13 19:11:23 - mmengine - INFO - Epoch(train) [130][150/293] lr: 5.000000e-04 eta: 4:23:44 time: 0.779070 data_time: 0.106884 memory: 21676 loss_kpt: 0.000550 acc_pose: 0.825747 loss: 0.000550 2022/09/13 19:12:02 - mmengine - INFO - Epoch(train) [130][200/293] lr: 5.000000e-04 eta: 4:23:13 time: 0.777267 data_time: 0.102640 memory: 21676 loss_kpt: 0.000555 acc_pose: 0.851145 loss: 0.000555 2022/09/13 19:12:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 19:12:41 - mmengine - INFO - Epoch(train) [130][250/293] lr: 5.000000e-04 eta: 4:22:43 time: 0.770795 data_time: 0.095477 memory: 21676 loss_kpt: 0.000554 acc_pose: 0.853551 loss: 0.000554 2022/09/13 19:13:14 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 19:13:14 - mmengine - INFO - Saving checkpoint at 130 epochs 2022/09/13 19:13:28 - mmengine - INFO - Epoch(val) [130][50/407] eta: 0:01:04 time: 0.181969 data_time: 0.013910 memory: 21676 2022/09/13 19:13:37 - mmengine - INFO - Epoch(val) [130][100/407] eta: 0:00:54 time: 0.178620 data_time: 0.009875 memory: 1375 2022/09/13 19:13:45 - mmengine - INFO - Epoch(val) [130][150/407] eta: 0:00:45 time: 0.175526 data_time: 0.008838 memory: 1375 2022/09/13 19:13:54 - mmengine - INFO - Epoch(val) [130][200/407] eta: 0:00:36 time: 0.175503 data_time: 0.008470 memory: 1375 2022/09/13 19:14:03 - mmengine - INFO - Epoch(val) [130][250/407] eta: 0:00:27 time: 0.174953 data_time: 0.008536 memory: 1375 2022/09/13 19:14:12 - mmengine - INFO - Epoch(val) [130][300/407] eta: 0:00:18 time: 0.175259 data_time: 0.008187 memory: 1375 2022/09/13 19:14:21 - mmengine - INFO - Epoch(val) [130][350/407] eta: 0:00:10 time: 0.177591 data_time: 0.008707 memory: 1375 2022/09/13 19:14:29 - mmengine - INFO - Epoch(val) [130][400/407] eta: 0:00:01 time: 0.175080 data_time: 0.008502 memory: 1375 2022/09/13 19:15:05 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 19:15:19 - mmengine - INFO - Epoch(val) [130][407/407] coco/AP: 0.755424 coco/AP .5: 0.900678 coco/AP .75: 0.820252 coco/AP (M): 0.717148 coco/AP (L): 0.825870 coco/AR: 0.804991 coco/AR .5: 0.938130 coco/AR .75: 0.861618 coco/AR (M): 0.761459 coco/AR (L): 0.868190 2022/09/13 19:15:19 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220913/udp_w32_384_v1/best_coco/AP_epoch_120.pth is removed 2022/09/13 19:15:22 - mmengine - INFO - The best checkpoint with 0.7554 coco/AP at 130 epoch is saved to best_coco/AP_epoch_130.pth. 2022/09/13 19:16:00 - mmengine - INFO - Epoch(train) [131][50/293] lr: 5.000000e-04 eta: 4:21:26 time: 0.764051 data_time: 0.102184 memory: 21676 loss_kpt: 0.000553 acc_pose: 0.819714 loss: 0.000553 2022/09/13 19:16:38 - mmengine - INFO - Epoch(train) [131][100/293] lr: 5.000000e-04 eta: 4:20:55 time: 0.764208 data_time: 0.099753 memory: 21676 loss_kpt: 0.000560 acc_pose: 0.878864 loss: 0.000560 2022/09/13 19:17:17 - mmengine - INFO - Epoch(train) [131][150/293] lr: 5.000000e-04 eta: 4:20:24 time: 0.762510 data_time: 0.096036 memory: 21676 loss_kpt: 0.000544 acc_pose: 0.840812 loss: 0.000544 2022/09/13 19:17:54 - mmengine - INFO - Epoch(train) [131][200/293] lr: 5.000000e-04 eta: 4:19:53 time: 0.756691 data_time: 0.099460 memory: 21676 loss_kpt: 0.000554 acc_pose: 0.840631 loss: 0.000554 2022/09/13 19:18:33 - mmengine - INFO - Epoch(train) [131][250/293] lr: 5.000000e-04 eta: 4:19:22 time: 0.763175 data_time: 0.099970 memory: 21676 loss_kpt: 0.000558 acc_pose: 0.801367 loss: 0.000558 2022/09/13 19:19:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 19:19:05 - mmengine - INFO - Saving checkpoint at 131 epochs 2022/09/13 19:19:49 - mmengine - INFO - Epoch(train) [132][50/293] lr: 5.000000e-04 eta: 4:18:06 time: 0.792466 data_time: 0.104517 memory: 21676 loss_kpt: 0.000559 acc_pose: 0.880104 loss: 0.000559 2022/09/13 19:20:28 - mmengine - INFO - Epoch(train) [132][100/293] lr: 5.000000e-04 eta: 4:17:36 time: 0.783320 data_time: 0.096010 memory: 21676 loss_kpt: 0.000545 acc_pose: 0.846042 loss: 0.000545 2022/09/13 19:21:07 - mmengine - INFO - Epoch(train) [132][150/293] lr: 5.000000e-04 eta: 4:17:06 time: 0.781199 data_time: 0.100530 memory: 21676 loss_kpt: 0.000548 acc_pose: 0.876826 loss: 0.000548 2022/09/13 19:21:47 - mmengine - INFO - Epoch(train) [132][200/293] lr: 5.000000e-04 eta: 4:16:36 time: 0.786752 data_time: 0.097538 memory: 21676 loss_kpt: 0.000542 acc_pose: 0.854486 loss: 0.000542 2022/09/13 19:22:26 - mmengine - INFO - Epoch(train) [132][250/293] lr: 5.000000e-04 eta: 4:16:06 time: 0.788601 data_time: 0.092786 memory: 21676 loss_kpt: 0.000561 acc_pose: 0.840744 loss: 0.000561 2022/09/13 19:22:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 19:22:59 - mmengine - INFO - Saving checkpoint at 132 epochs 2022/09/13 19:23:43 - mmengine - INFO - Epoch(train) [133][50/293] lr: 5.000000e-04 eta: 4:14:50 time: 0.790332 data_time: 0.105205 memory: 21676 loss_kpt: 0.000554 acc_pose: 0.871500 loss: 0.000554 2022/09/13 19:24:23 - mmengine - INFO - Epoch(train) [133][100/293] lr: 5.000000e-04 eta: 4:14:20 time: 0.793400 data_time: 0.096093 memory: 21676 loss_kpt: 0.000549 acc_pose: 0.840729 loss: 0.000549 2022/09/13 19:25:02 - mmengine - INFO - Epoch(train) [133][150/293] lr: 5.000000e-04 eta: 4:13:50 time: 0.788580 data_time: 0.096676 memory: 21676 loss_kpt: 0.000542 acc_pose: 0.857542 loss: 0.000542 2022/09/13 19:25:41 - mmengine - INFO - Epoch(train) [133][200/293] lr: 5.000000e-04 eta: 4:13:19 time: 0.773571 data_time: 0.095020 memory: 21676 loss_kpt: 0.000544 acc_pose: 0.859387 loss: 0.000544 2022/09/13 19:26:20 - mmengine - INFO - Epoch(train) [133][250/293] lr: 5.000000e-04 eta: 4:12:49 time: 0.774635 data_time: 0.099146 memory: 21676 loss_kpt: 0.000543 acc_pose: 0.853737 loss: 0.000543 2022/09/13 19:26:53 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 19:26:53 - mmengine - INFO - Saving checkpoint at 133 epochs 2022/09/13 19:27:22 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 19:27:36 - mmengine - INFO - Epoch(train) [134][50/293] lr: 5.000000e-04 eta: 4:11:33 time: 0.780410 data_time: 0.104651 memory: 21676 loss_kpt: 0.000539 acc_pose: 0.854314 loss: 0.000539 2022/09/13 19:28:15 - mmengine - INFO - Epoch(train) [134][100/293] lr: 5.000000e-04 eta: 4:11:02 time: 0.769809 data_time: 0.104764 memory: 21676 loss_kpt: 0.000562 acc_pose: 0.853790 loss: 0.000562 2022/09/13 19:28:53 - mmengine - INFO - Epoch(train) [134][150/293] lr: 5.000000e-04 eta: 4:10:32 time: 0.772973 data_time: 0.096439 memory: 21676 loss_kpt: 0.000543 acc_pose: 0.877842 loss: 0.000543 2022/09/13 19:29:32 - mmengine - INFO - Epoch(train) [134][200/293] lr: 5.000000e-04 eta: 4:10:01 time: 0.761605 data_time: 0.092574 memory: 21676 loss_kpt: 0.000545 acc_pose: 0.857947 loss: 0.000545 2022/09/13 19:30:09 - mmengine - INFO - Epoch(train) [134][250/293] lr: 5.000000e-04 eta: 4:09:30 time: 0.759668 data_time: 0.096951 memory: 21676 loss_kpt: 0.000557 acc_pose: 0.849331 loss: 0.000557 2022/09/13 19:30:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 19:30:42 - mmengine - INFO - Saving checkpoint at 134 epochs 2022/09/13 19:31:26 - mmengine - INFO - Epoch(train) [135][50/293] lr: 5.000000e-04 eta: 4:08:14 time: 0.792747 data_time: 0.110408 memory: 21676 loss_kpt: 0.000540 acc_pose: 0.812285 loss: 0.000540 2022/09/13 19:32:05 - mmengine - INFO - Epoch(train) [135][100/293] lr: 5.000000e-04 eta: 4:07:44 time: 0.785197 data_time: 0.102767 memory: 21676 loss_kpt: 0.000542 acc_pose: 0.757955 loss: 0.000542 2022/09/13 19:32:45 - mmengine - INFO - Epoch(train) [135][150/293] lr: 5.000000e-04 eta: 4:07:14 time: 0.783506 data_time: 0.096341 memory: 21676 loss_kpt: 0.000548 acc_pose: 0.843146 loss: 0.000548 2022/09/13 19:33:24 - mmengine - INFO - Epoch(train) [135][200/293] lr: 5.000000e-04 eta: 4:06:44 time: 0.788752 data_time: 0.101015 memory: 21676 loss_kpt: 0.000552 acc_pose: 0.819183 loss: 0.000552 2022/09/13 19:34:03 - mmengine - INFO - Epoch(train) [135][250/293] lr: 5.000000e-04 eta: 4:06:13 time: 0.784330 data_time: 0.094757 memory: 21676 loss_kpt: 0.000553 acc_pose: 0.834303 loss: 0.000553 2022/09/13 19:34:37 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 19:34:37 - mmengine - INFO - Saving checkpoint at 135 epochs 2022/09/13 19:35:20 - mmengine - INFO - Epoch(train) [136][50/293] lr: 5.000000e-04 eta: 4:04:58 time: 0.785962 data_time: 0.109548 memory: 21676 loss_kpt: 0.000551 acc_pose: 0.843599 loss: 0.000551 2022/09/13 19:36:00 - mmengine - INFO - Epoch(train) [136][100/293] lr: 5.000000e-04 eta: 4:04:28 time: 0.783357 data_time: 0.095053 memory: 21676 loss_kpt: 0.000546 acc_pose: 0.851221 loss: 0.000546 2022/09/13 19:36:39 - mmengine - INFO - Epoch(train) [136][150/293] lr: 5.000000e-04 eta: 4:03:57 time: 0.790639 data_time: 0.103456 memory: 21676 loss_kpt: 0.000547 acc_pose: 0.839892 loss: 0.000547 2022/09/13 19:37:18 - mmengine - INFO - Epoch(train) [136][200/293] lr: 5.000000e-04 eta: 4:03:27 time: 0.786092 data_time: 0.098923 memory: 21676 loss_kpt: 0.000556 acc_pose: 0.843286 loss: 0.000556 2022/09/13 19:37:57 - mmengine - INFO - Epoch(train) [136][250/293] lr: 5.000000e-04 eta: 4:02:56 time: 0.779881 data_time: 0.103663 memory: 21676 loss_kpt: 0.000545 acc_pose: 0.855919 loss: 0.000545 2022/09/13 19:38:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 19:38:30 - mmengine - INFO - Saving checkpoint at 136 epochs 2022/09/13 19:39:15 - mmengine - INFO - Epoch(train) [137][50/293] lr: 5.000000e-04 eta: 4:01:42 time: 0.794204 data_time: 0.113840 memory: 21676 loss_kpt: 0.000535 acc_pose: 0.865234 loss: 0.000535 2022/09/13 19:39:53 - mmengine - INFO - Epoch(train) [137][100/293] lr: 5.000000e-04 eta: 4:01:11 time: 0.775620 data_time: 0.101614 memory: 21676 loss_kpt: 0.000563 acc_pose: 0.837549 loss: 0.000563 2022/09/13 19:40:33 - mmengine - INFO - Epoch(train) [137][150/293] lr: 5.000000e-04 eta: 4:00:41 time: 0.783346 data_time: 0.103242 memory: 21676 loss_kpt: 0.000554 acc_pose: 0.825424 loss: 0.000554 2022/09/13 19:40:34 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 19:41:12 - mmengine - INFO - Epoch(train) [137][200/293] lr: 5.000000e-04 eta: 4:00:10 time: 0.778452 data_time: 0.108683 memory: 21676 loss_kpt: 0.000550 acc_pose: 0.867673 loss: 0.000550 2022/09/13 19:41:50 - mmengine - INFO - Epoch(train) [137][250/293] lr: 5.000000e-04 eta: 3:59:39 time: 0.777027 data_time: 0.097135 memory: 21676 loss_kpt: 0.000548 acc_pose: 0.850140 loss: 0.000548 2022/09/13 19:42:24 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 19:42:24 - mmengine - INFO - Saving checkpoint at 137 epochs 2022/09/13 19:43:09 - mmengine - INFO - Epoch(train) [138][50/293] lr: 5.000000e-04 eta: 3:58:25 time: 0.799629 data_time: 0.109455 memory: 21676 loss_kpt: 0.000552 acc_pose: 0.820867 loss: 0.000552 2022/09/13 19:43:48 - mmengine - INFO - Epoch(train) [138][100/293] lr: 5.000000e-04 eta: 3:57:54 time: 0.781619 data_time: 0.098172 memory: 21676 loss_kpt: 0.000553 acc_pose: 0.842262 loss: 0.000553 2022/09/13 19:44:27 - mmengine - INFO - Epoch(train) [138][150/293] lr: 5.000000e-04 eta: 3:57:24 time: 0.778327 data_time: 0.097365 memory: 21676 loss_kpt: 0.000558 acc_pose: 0.828507 loss: 0.000558 2022/09/13 19:45:07 - mmengine - INFO - Epoch(train) [138][200/293] lr: 5.000000e-04 eta: 3:56:53 time: 0.788516 data_time: 0.097134 memory: 21676 loss_kpt: 0.000541 acc_pose: 0.845268 loss: 0.000541 2022/09/13 19:45:46 - mmengine - INFO - Epoch(train) [138][250/293] lr: 5.000000e-04 eta: 3:56:23 time: 0.789038 data_time: 0.096495 memory: 21676 loss_kpt: 0.000534 acc_pose: 0.847034 loss: 0.000534 2022/09/13 19:46:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 19:46:19 - mmengine - INFO - Saving checkpoint at 138 epochs 2022/09/13 19:47:03 - mmengine - INFO - Epoch(train) [139][50/293] lr: 5.000000e-04 eta: 3:55:09 time: 0.793989 data_time: 0.103139 memory: 21676 loss_kpt: 0.000546 acc_pose: 0.830823 loss: 0.000546 2022/09/13 19:47:41 - mmengine - INFO - Epoch(train) [139][100/293] lr: 5.000000e-04 eta: 3:54:38 time: 0.766862 data_time: 0.094044 memory: 21676 loss_kpt: 0.000550 acc_pose: 0.878089 loss: 0.000550 2022/09/13 19:48:19 - mmengine - INFO - Epoch(train) [139][150/293] lr: 5.000000e-04 eta: 3:54:06 time: 0.748464 data_time: 0.095845 memory: 21676 loss_kpt: 0.000541 acc_pose: 0.860885 loss: 0.000541 2022/09/13 19:48:56 - mmengine - INFO - Epoch(train) [139][200/293] lr: 5.000000e-04 eta: 3:53:35 time: 0.754523 data_time: 0.093692 memory: 21676 loss_kpt: 0.000524 acc_pose: 0.868105 loss: 0.000524 2022/09/13 19:49:34 - mmengine - INFO - Epoch(train) [139][250/293] lr: 5.000000e-04 eta: 3:53:03 time: 0.760748 data_time: 0.096913 memory: 21676 loss_kpt: 0.000545 acc_pose: 0.880434 loss: 0.000545 2022/09/13 19:50:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 19:50:07 - mmengine - INFO - Saving checkpoint at 139 epochs 2022/09/13 19:50:51 - mmengine - INFO - Epoch(train) [140][50/293] lr: 5.000000e-04 eta: 3:51:49 time: 0.793227 data_time: 0.119899 memory: 21676 loss_kpt: 0.000546 acc_pose: 0.845998 loss: 0.000546 2022/09/13 19:51:31 - mmengine - INFO - Epoch(train) [140][100/293] lr: 5.000000e-04 eta: 3:51:19 time: 0.795587 data_time: 0.099317 memory: 21676 loss_kpt: 0.000544 acc_pose: 0.840132 loss: 0.000544 2022/09/13 19:52:10 - mmengine - INFO - Epoch(train) [140][150/293] lr: 5.000000e-04 eta: 3:50:49 time: 0.788482 data_time: 0.098255 memory: 21676 loss_kpt: 0.000550 acc_pose: 0.840756 loss: 0.000550 2022/09/13 19:52:50 - mmengine - INFO - Epoch(train) [140][200/293] lr: 5.000000e-04 eta: 3:50:18 time: 0.785802 data_time: 0.097108 memory: 21676 loss_kpt: 0.000548 acc_pose: 0.805812 loss: 0.000548 2022/09/13 19:53:29 - mmengine - INFO - Epoch(train) [140][250/293] lr: 5.000000e-04 eta: 3:49:47 time: 0.788747 data_time: 0.095854 memory: 21676 loss_kpt: 0.000548 acc_pose: 0.854924 loss: 0.000548 2022/09/13 19:53:47 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 19:54:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 19:54:02 - mmengine - INFO - Saving checkpoint at 140 epochs 2022/09/13 19:54:16 - mmengine - INFO - Epoch(val) [140][50/407] eta: 0:01:07 time: 0.189749 data_time: 0.015603 memory: 21676 2022/09/13 19:54:25 - mmengine - INFO - Epoch(val) [140][100/407] eta: 0:00:54 time: 0.176062 data_time: 0.010010 memory: 1375 2022/09/13 19:54:34 - mmengine - INFO - Epoch(val) [140][150/407] eta: 0:00:45 time: 0.175880 data_time: 0.008719 memory: 1375 2022/09/13 19:54:43 - mmengine - INFO - Epoch(val) [140][200/407] eta: 0:00:36 time: 0.177123 data_time: 0.009003 memory: 1375 2022/09/13 19:54:52 - mmengine - INFO - Epoch(val) [140][250/407] eta: 0:00:27 time: 0.176419 data_time: 0.008548 memory: 1375 2022/09/13 19:55:00 - mmengine - INFO - Epoch(val) [140][300/407] eta: 0:00:18 time: 0.176317 data_time: 0.009144 memory: 1375 2022/09/13 19:55:09 - mmengine - INFO - Epoch(val) [140][350/407] eta: 0:00:10 time: 0.175452 data_time: 0.008650 memory: 1375 2022/09/13 19:55:18 - mmengine - INFO - Epoch(val) [140][400/407] eta: 0:00:01 time: 0.173745 data_time: 0.008215 memory: 1375 2022/09/13 19:55:55 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 19:56:08 - mmengine - INFO - Epoch(val) [140][407/407] coco/AP: 0.755561 coco/AP .5: 0.904454 coco/AP .75: 0.818801 coco/AP (M): 0.716085 coco/AP (L): 0.827330 coco/AR: 0.805416 coco/AR .5: 0.942538 coco/AR .75: 0.861304 coco/AR (M): 0.761677 coco/AR (L): 0.869379 2022/09/13 19:56:09 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220913/udp_w32_384_v1/best_coco/AP_epoch_130.pth is removed 2022/09/13 19:56:12 - mmengine - INFO - The best checkpoint with 0.7556 coco/AP at 140 epoch is saved to best_coco/AP_epoch_140.pth. 2022/09/13 19:56:51 - mmengine - INFO - Epoch(train) [141][50/293] lr: 5.000000e-04 eta: 3:48:34 time: 0.789743 data_time: 0.108501 memory: 21676 loss_kpt: 0.000564 acc_pose: 0.843304 loss: 0.000564 2022/09/13 19:57:31 - mmengine - INFO - Epoch(train) [141][100/293] lr: 5.000000e-04 eta: 3:48:03 time: 0.787827 data_time: 0.097205 memory: 21676 loss_kpt: 0.000568 acc_pose: 0.862164 loss: 0.000568 2022/09/13 19:58:10 - mmengine - INFO - Epoch(train) [141][150/293] lr: 5.000000e-04 eta: 3:47:32 time: 0.784063 data_time: 0.096687 memory: 21676 loss_kpt: 0.000540 acc_pose: 0.877258 loss: 0.000540 2022/09/13 19:58:49 - mmengine - INFO - Epoch(train) [141][200/293] lr: 5.000000e-04 eta: 3:47:01 time: 0.773583 data_time: 0.094562 memory: 21676 loss_kpt: 0.000558 acc_pose: 0.810985 loss: 0.000558 2022/09/13 19:59:28 - mmengine - INFO - Epoch(train) [141][250/293] lr: 5.000000e-04 eta: 3:46:30 time: 0.783053 data_time: 0.100754 memory: 21676 loss_kpt: 0.000536 acc_pose: 0.866925 loss: 0.000536 2022/09/13 20:00:01 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 20:00:01 - mmengine - INFO - Saving checkpoint at 141 epochs 2022/09/13 20:00:45 - mmengine - INFO - Epoch(train) [142][50/293] lr: 5.000000e-04 eta: 3:45:17 time: 0.787129 data_time: 0.115073 memory: 21676 loss_kpt: 0.000547 acc_pose: 0.867127 loss: 0.000547 2022/09/13 20:01:23 - mmengine - INFO - Epoch(train) [142][100/293] lr: 5.000000e-04 eta: 3:44:46 time: 0.768687 data_time: 0.108063 memory: 21676 loss_kpt: 0.000543 acc_pose: 0.864758 loss: 0.000543 2022/09/13 20:02:02 - mmengine - INFO - Epoch(train) [142][150/293] lr: 5.000000e-04 eta: 3:44:15 time: 0.776093 data_time: 0.103149 memory: 21676 loss_kpt: 0.000552 acc_pose: 0.873532 loss: 0.000552 2022/09/13 20:02:41 - mmengine - INFO - Epoch(train) [142][200/293] lr: 5.000000e-04 eta: 3:43:44 time: 0.776906 data_time: 0.103735 memory: 21676 loss_kpt: 0.000540 acc_pose: 0.843732 loss: 0.000540 2022/09/13 20:03:20 - mmengine - INFO - Epoch(train) [142][250/293] lr: 5.000000e-04 eta: 3:43:13 time: 0.776276 data_time: 0.103917 memory: 21676 loss_kpt: 0.000549 acc_pose: 0.868576 loss: 0.000549 2022/09/13 20:03:52 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 20:03:52 - mmengine - INFO - Saving checkpoint at 142 epochs 2022/09/13 20:04:36 - mmengine - INFO - Epoch(train) [143][50/293] lr: 5.000000e-04 eta: 3:42:00 time: 0.797885 data_time: 0.112517 memory: 21676 loss_kpt: 0.000552 acc_pose: 0.864383 loss: 0.000552 2022/09/13 20:05:16 - mmengine - INFO - Epoch(train) [143][100/293] lr: 5.000000e-04 eta: 3:41:29 time: 0.791522 data_time: 0.098753 memory: 21676 loss_kpt: 0.000543 acc_pose: 0.872761 loss: 0.000543 2022/09/13 20:05:55 - mmengine - INFO - Epoch(train) [143][150/293] lr: 5.000000e-04 eta: 3:40:58 time: 0.783826 data_time: 0.099139 memory: 21676 loss_kpt: 0.000545 acc_pose: 0.838987 loss: 0.000545 2022/09/13 20:06:34 - mmengine - INFO - Epoch(train) [143][200/293] lr: 5.000000e-04 eta: 3:40:27 time: 0.780761 data_time: 0.093742 memory: 21676 loss_kpt: 0.000544 acc_pose: 0.817024 loss: 0.000544 2022/09/13 20:07:13 - mmengine - INFO - Epoch(train) [143][250/293] lr: 5.000000e-04 eta: 3:39:56 time: 0.778953 data_time: 0.101073 memory: 21676 loss_kpt: 0.000546 acc_pose: 0.829361 loss: 0.000546 2022/09/13 20:07:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 20:07:46 - mmengine - INFO - Saving checkpoint at 143 epochs 2022/09/13 20:08:30 - mmengine - INFO - Epoch(train) [144][50/293] lr: 5.000000e-04 eta: 3:38:43 time: 0.791106 data_time: 0.103866 memory: 21676 loss_kpt: 0.000541 acc_pose: 0.818010 loss: 0.000541 2022/09/13 20:09:09 - mmengine - INFO - Epoch(train) [144][100/293] lr: 5.000000e-04 eta: 3:38:12 time: 0.769330 data_time: 0.106280 memory: 21676 loss_kpt: 0.000522 acc_pose: 0.862298 loss: 0.000522 2022/09/13 20:09:09 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 20:09:48 - mmengine - INFO - Epoch(train) [144][150/293] lr: 5.000000e-04 eta: 3:37:41 time: 0.780607 data_time: 0.098060 memory: 21676 loss_kpt: 0.000549 acc_pose: 0.847246 loss: 0.000549 2022/09/13 20:10:27 - mmengine - INFO - Epoch(train) [144][200/293] lr: 5.000000e-04 eta: 3:37:10 time: 0.779113 data_time: 0.093817 memory: 21676 loss_kpt: 0.000552 acc_pose: 0.822506 loss: 0.000552 2022/09/13 20:11:05 - mmengine - INFO - Epoch(train) [144][250/293] lr: 5.000000e-04 eta: 3:36:39 time: 0.767280 data_time: 0.097320 memory: 21676 loss_kpt: 0.000524 acc_pose: 0.849360 loss: 0.000524 2022/09/13 20:11:38 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 20:11:38 - mmengine - INFO - Saving checkpoint at 144 epochs 2022/09/13 20:12:22 - mmengine - INFO - Epoch(train) [145][50/293] lr: 5.000000e-04 eta: 3:35:26 time: 0.790649 data_time: 0.117273 memory: 21676 loss_kpt: 0.000539 acc_pose: 0.826182 loss: 0.000539 2022/09/13 20:13:02 - mmengine - INFO - Epoch(train) [145][100/293] lr: 5.000000e-04 eta: 3:34:55 time: 0.793338 data_time: 0.108259 memory: 21676 loss_kpt: 0.000553 acc_pose: 0.805305 loss: 0.000553 2022/09/13 20:13:41 - mmengine - INFO - Epoch(train) [145][150/293] lr: 5.000000e-04 eta: 3:34:24 time: 0.789285 data_time: 0.105010 memory: 21676 loss_kpt: 0.000548 acc_pose: 0.814294 loss: 0.000548 2022/09/13 20:14:20 - mmengine - INFO - Epoch(train) [145][200/293] lr: 5.000000e-04 eta: 3:33:53 time: 0.779076 data_time: 0.103918 memory: 21676 loss_kpt: 0.000545 acc_pose: 0.893171 loss: 0.000545 2022/09/13 20:14:59 - mmengine - INFO - Epoch(train) [145][250/293] lr: 5.000000e-04 eta: 3:33:22 time: 0.777865 data_time: 0.104958 memory: 21676 loss_kpt: 0.000530 acc_pose: 0.808808 loss: 0.000530 2022/09/13 20:15:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 20:15:32 - mmengine - INFO - Saving checkpoint at 145 epochs 2022/09/13 20:16:16 - mmengine - INFO - Epoch(train) [146][50/293] lr: 5.000000e-04 eta: 3:32:10 time: 0.787530 data_time: 0.107725 memory: 21676 loss_kpt: 0.000540 acc_pose: 0.880771 loss: 0.000540 2022/09/13 20:16:55 - mmengine - INFO - Epoch(train) [146][100/293] lr: 5.000000e-04 eta: 3:31:39 time: 0.778901 data_time: 0.097285 memory: 21676 loss_kpt: 0.000540 acc_pose: 0.848632 loss: 0.000540 2022/09/13 20:17:34 - mmengine - INFO - Epoch(train) [146][150/293] lr: 5.000000e-04 eta: 3:31:08 time: 0.783616 data_time: 0.103407 memory: 21676 loss_kpt: 0.000539 acc_pose: 0.858923 loss: 0.000539 2022/09/13 20:18:14 - mmengine - INFO - Epoch(train) [146][200/293] lr: 5.000000e-04 eta: 3:30:37 time: 0.797205 data_time: 0.099150 memory: 21676 loss_kpt: 0.000545 acc_pose: 0.879245 loss: 0.000545 2022/09/13 20:18:53 - mmengine - INFO - Epoch(train) [146][250/293] lr: 5.000000e-04 eta: 3:30:06 time: 0.775504 data_time: 0.098689 memory: 21676 loss_kpt: 0.000533 acc_pose: 0.851537 loss: 0.000533 2022/09/13 20:19:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 20:19:26 - mmengine - INFO - Saving checkpoint at 146 epochs 2022/09/13 20:20:10 - mmengine - INFO - Epoch(train) [147][50/293] lr: 5.000000e-04 eta: 3:28:53 time: 0.792619 data_time: 0.108072 memory: 21676 loss_kpt: 0.000543 acc_pose: 0.859113 loss: 0.000543 2022/09/13 20:20:49 - mmengine - INFO - Epoch(train) [147][100/293] lr: 5.000000e-04 eta: 3:28:22 time: 0.778535 data_time: 0.092582 memory: 21676 loss_kpt: 0.000551 acc_pose: 0.841306 loss: 0.000551 2022/09/13 20:21:28 - mmengine - INFO - Epoch(train) [147][150/293] lr: 5.000000e-04 eta: 3:27:51 time: 0.771065 data_time: 0.099898 memory: 21676 loss_kpt: 0.000542 acc_pose: 0.836720 loss: 0.000542 2022/09/13 20:22:06 - mmengine - INFO - Epoch(train) [147][200/293] lr: 5.000000e-04 eta: 3:27:19 time: 0.771047 data_time: 0.093283 memory: 21676 loss_kpt: 0.000533 acc_pose: 0.838989 loss: 0.000533 2022/09/13 20:22:24 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 20:22:45 - mmengine - INFO - Epoch(train) [147][250/293] lr: 5.000000e-04 eta: 3:26:48 time: 0.780826 data_time: 0.098979 memory: 21676 loss_kpt: 0.000544 acc_pose: 0.801343 loss: 0.000544 2022/09/13 20:23:18 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 20:23:18 - mmengine - INFO - Saving checkpoint at 147 epochs 2022/09/13 20:24:02 - mmengine - INFO - Epoch(train) [148][50/293] lr: 5.000000e-04 eta: 3:25:36 time: 0.785248 data_time: 0.106388 memory: 21676 loss_kpt: 0.000526 acc_pose: 0.829651 loss: 0.000526 2022/09/13 20:24:41 - mmengine - INFO - Epoch(train) [148][100/293] lr: 5.000000e-04 eta: 3:25:05 time: 0.785031 data_time: 0.096845 memory: 21676 loss_kpt: 0.000552 acc_pose: 0.851179 loss: 0.000552 2022/09/13 20:25:21 - mmengine - INFO - Epoch(train) [148][150/293] lr: 5.000000e-04 eta: 3:24:34 time: 0.789124 data_time: 0.097243 memory: 21676 loss_kpt: 0.000545 acc_pose: 0.830047 loss: 0.000545 2022/09/13 20:26:00 - mmengine - INFO - Epoch(train) [148][200/293] lr: 5.000000e-04 eta: 3:24:03 time: 0.782918 data_time: 0.102450 memory: 21676 loss_kpt: 0.000531 acc_pose: 0.840902 loss: 0.000531 2022/09/13 20:26:39 - mmengine - INFO - Epoch(train) [148][250/293] lr: 5.000000e-04 eta: 3:23:32 time: 0.784819 data_time: 0.103759 memory: 21676 loss_kpt: 0.000548 acc_pose: 0.808558 loss: 0.000548 2022/09/13 20:27:12 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 20:27:12 - mmengine - INFO - Saving checkpoint at 148 epochs 2022/09/13 20:27:57 - mmengine - INFO - Epoch(train) [149][50/293] lr: 5.000000e-04 eta: 3:22:20 time: 0.800591 data_time: 0.105576 memory: 21676 loss_kpt: 0.000546 acc_pose: 0.854011 loss: 0.000546 2022/09/13 20:28:36 - mmengine - INFO - Epoch(train) [149][100/293] lr: 5.000000e-04 eta: 3:21:49 time: 0.780170 data_time: 0.100242 memory: 21676 loss_kpt: 0.000545 acc_pose: 0.837026 loss: 0.000545 2022/09/13 20:29:15 - mmengine - INFO - Epoch(train) [149][150/293] lr: 5.000000e-04 eta: 3:21:18 time: 0.787561 data_time: 0.096422 memory: 21676 loss_kpt: 0.000538 acc_pose: 0.859956 loss: 0.000538 2022/09/13 20:29:54 - mmengine - INFO - Epoch(train) [149][200/293] lr: 5.000000e-04 eta: 3:20:47 time: 0.782893 data_time: 0.099252 memory: 21676 loss_kpt: 0.000548 acc_pose: 0.886150 loss: 0.000548 2022/09/13 20:30:33 - mmengine - INFO - Epoch(train) [149][250/293] lr: 5.000000e-04 eta: 3:20:15 time: 0.774657 data_time: 0.096758 memory: 21676 loss_kpt: 0.000538 acc_pose: 0.853059 loss: 0.000538 2022/09/13 20:31:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 20:31:06 - mmengine - INFO - Saving checkpoint at 149 epochs 2022/09/13 20:31:50 - mmengine - INFO - Epoch(train) [150][50/293] lr: 5.000000e-04 eta: 3:19:04 time: 0.793889 data_time: 0.104871 memory: 21676 loss_kpt: 0.000537 acc_pose: 0.868040 loss: 0.000537 2022/09/13 20:32:29 - mmengine - INFO - Epoch(train) [150][100/293] lr: 5.000000e-04 eta: 3:18:32 time: 0.774391 data_time: 0.098332 memory: 21676 loss_kpt: 0.000528 acc_pose: 0.865097 loss: 0.000528 2022/09/13 20:33:09 - mmengine - INFO - Epoch(train) [150][150/293] lr: 5.000000e-04 eta: 3:18:01 time: 0.797650 data_time: 0.107878 memory: 21676 loss_kpt: 0.000550 acc_pose: 0.875136 loss: 0.000550 2022/09/13 20:33:48 - mmengine - INFO - Epoch(train) [150][200/293] lr: 5.000000e-04 eta: 3:17:30 time: 0.776405 data_time: 0.103013 memory: 21676 loss_kpt: 0.000558 acc_pose: 0.817221 loss: 0.000558 2022/09/13 20:34:27 - mmengine - INFO - Epoch(train) [150][250/293] lr: 5.000000e-04 eta: 3:16:58 time: 0.775323 data_time: 0.104620 memory: 21676 loss_kpt: 0.000554 acc_pose: 0.850601 loss: 0.000554 2022/09/13 20:35:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 20:35:00 - mmengine - INFO - Saving checkpoint at 150 epochs 2022/09/13 20:35:14 - mmengine - INFO - Epoch(val) [150][50/407] eta: 0:01:05 time: 0.184585 data_time: 0.014835 memory: 21676 2022/09/13 20:35:23 - mmengine - INFO - Epoch(val) [150][100/407] eta: 0:00:54 time: 0.177524 data_time: 0.008659 memory: 1375 2022/09/13 20:35:32 - mmengine - INFO - Epoch(val) [150][150/407] eta: 0:00:45 time: 0.176084 data_time: 0.008403 memory: 1375 2022/09/13 20:35:40 - mmengine - INFO - Epoch(val) [150][200/407] eta: 0:00:36 time: 0.176332 data_time: 0.008716 memory: 1375 2022/09/13 20:35:49 - mmengine - INFO - Epoch(val) [150][250/407] eta: 0:00:27 time: 0.174855 data_time: 0.009151 memory: 1375 2022/09/13 20:35:58 - mmengine - INFO - Epoch(val) [150][300/407] eta: 0:00:18 time: 0.175986 data_time: 0.009171 memory: 1375 2022/09/13 20:36:07 - mmengine - INFO - Epoch(val) [150][350/407] eta: 0:00:10 time: 0.177102 data_time: 0.008619 memory: 1375 2022/09/13 20:36:16 - mmengine - INFO - Epoch(val) [150][400/407] eta: 0:00:01 time: 0.179017 data_time: 0.013283 memory: 1375 2022/09/13 20:36:52 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 20:37:05 - mmengine - INFO - Epoch(val) [150][407/407] coco/AP: 0.759110 coco/AP .5: 0.904761 coco/AP .75: 0.822588 coco/AP (M): 0.720368 coco/AP (L): 0.828626 coco/AR: 0.807588 coco/AR .5: 0.940649 coco/AR .75: 0.865869 coco/AR (M): 0.763890 coco/AR (L): 0.871163 2022/09/13 20:37:06 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220913/udp_w32_384_v1/best_coco/AP_epoch_140.pth is removed 2022/09/13 20:37:09 - mmengine - INFO - The best checkpoint with 0.7591 coco/AP at 150 epoch is saved to best_coco/AP_epoch_150.pth. 2022/09/13 20:37:48 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 20:37:48 - mmengine - INFO - Epoch(train) [151][50/293] lr: 5.000000e-04 eta: 3:15:47 time: 0.786200 data_time: 0.105485 memory: 21676 loss_kpt: 0.000539 acc_pose: 0.847186 loss: 0.000539 2022/09/13 20:38:27 - mmengine - INFO - Epoch(train) [151][100/293] lr: 5.000000e-04 eta: 3:15:15 time: 0.778162 data_time: 0.098294 memory: 21676 loss_kpt: 0.000527 acc_pose: 0.858410 loss: 0.000527 2022/09/13 20:39:07 - mmengine - INFO - Epoch(train) [151][150/293] lr: 5.000000e-04 eta: 3:14:44 time: 0.796374 data_time: 0.101045 memory: 21676 loss_kpt: 0.000536 acc_pose: 0.832713 loss: 0.000536 2022/09/13 20:39:46 - mmengine - INFO - Epoch(train) [151][200/293] lr: 5.000000e-04 eta: 3:14:13 time: 0.788966 data_time: 0.100807 memory: 21676 loss_kpt: 0.000537 acc_pose: 0.887690 loss: 0.000537 2022/09/13 20:40:25 - mmengine - INFO - Epoch(train) [151][250/293] lr: 5.000000e-04 eta: 3:13:42 time: 0.779634 data_time: 0.093776 memory: 21676 loss_kpt: 0.000534 acc_pose: 0.860993 loss: 0.000534 2022/09/13 20:40:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 20:40:59 - mmengine - INFO - Saving checkpoint at 151 epochs 2022/09/13 20:41:42 - mmengine - INFO - Epoch(train) [152][50/293] lr: 5.000000e-04 eta: 3:12:30 time: 0.770468 data_time: 0.110458 memory: 21676 loss_kpt: 0.000553 acc_pose: 0.888643 loss: 0.000553 2022/09/13 20:42:21 - mmengine - INFO - Epoch(train) [152][100/293] lr: 5.000000e-04 eta: 3:11:59 time: 0.793454 data_time: 0.109185 memory: 21676 loss_kpt: 0.000535 acc_pose: 0.853026 loss: 0.000535 2022/09/13 20:43:01 - mmengine - INFO - Epoch(train) [152][150/293] lr: 5.000000e-04 eta: 3:11:28 time: 0.784611 data_time: 0.106534 memory: 21676 loss_kpt: 0.000549 acc_pose: 0.838261 loss: 0.000549 2022/09/13 20:43:40 - mmengine - INFO - Epoch(train) [152][200/293] lr: 5.000000e-04 eta: 3:10:56 time: 0.781040 data_time: 0.106822 memory: 21676 loss_kpt: 0.000557 acc_pose: 0.879825 loss: 0.000557 2022/09/13 20:44:18 - mmengine - INFO - Epoch(train) [152][250/293] lr: 5.000000e-04 eta: 3:10:25 time: 0.775285 data_time: 0.110399 memory: 21676 loss_kpt: 0.000540 acc_pose: 0.856059 loss: 0.000540 2022/09/13 20:44:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 20:44:51 - mmengine - INFO - Saving checkpoint at 152 epochs 2022/09/13 20:45:36 - mmengine - INFO - Epoch(train) [153][50/293] lr: 5.000000e-04 eta: 3:09:14 time: 0.792605 data_time: 0.116436 memory: 21676 loss_kpt: 0.000536 acc_pose: 0.866234 loss: 0.000536 2022/09/13 20:46:15 - mmengine - INFO - Epoch(train) [153][100/293] lr: 5.000000e-04 eta: 3:08:43 time: 0.793050 data_time: 0.095172 memory: 21676 loss_kpt: 0.000544 acc_pose: 0.851284 loss: 0.000544 2022/09/13 20:46:55 - mmengine - INFO - Epoch(train) [153][150/293] lr: 5.000000e-04 eta: 3:08:11 time: 0.783696 data_time: 0.099099 memory: 21676 loss_kpt: 0.000548 acc_pose: 0.869509 loss: 0.000548 2022/09/13 20:47:34 - mmengine - INFO - Epoch(train) [153][200/293] lr: 5.000000e-04 eta: 3:07:40 time: 0.790007 data_time: 0.098376 memory: 21676 loss_kpt: 0.000536 acc_pose: 0.863105 loss: 0.000536 2022/09/13 20:48:12 - mmengine - INFO - Epoch(train) [153][250/293] lr: 5.000000e-04 eta: 3:07:08 time: 0.762987 data_time: 0.096238 memory: 21676 loss_kpt: 0.000547 acc_pose: 0.813887 loss: 0.000547 2022/09/13 20:48:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 20:48:44 - mmengine - INFO - Saving checkpoint at 153 epochs 2022/09/13 20:49:28 - mmengine - INFO - Epoch(train) [154][50/293] lr: 5.000000e-04 eta: 3:05:57 time: 0.778017 data_time: 0.106115 memory: 21676 loss_kpt: 0.000544 acc_pose: 0.846554 loss: 0.000544 2022/09/13 20:50:08 - mmengine - INFO - Epoch(train) [154][100/293] lr: 5.000000e-04 eta: 3:05:26 time: 0.791059 data_time: 0.094462 memory: 21676 loss_kpt: 0.000538 acc_pose: 0.847353 loss: 0.000538 2022/09/13 20:50:47 - mmengine - INFO - Epoch(train) [154][150/293] lr: 5.000000e-04 eta: 3:04:54 time: 0.781375 data_time: 0.092607 memory: 21676 loss_kpt: 0.000539 acc_pose: 0.859337 loss: 0.000539 2022/09/13 20:51:03 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 20:51:25 - mmengine - INFO - Epoch(train) [154][200/293] lr: 5.000000e-04 eta: 3:04:23 time: 0.773449 data_time: 0.093836 memory: 21676 loss_kpt: 0.000548 acc_pose: 0.817016 loss: 0.000548 2022/09/13 20:52:03 - mmengine - INFO - Epoch(train) [154][250/293] lr: 5.000000e-04 eta: 3:03:51 time: 0.756666 data_time: 0.105663 memory: 21676 loss_kpt: 0.000554 acc_pose: 0.866509 loss: 0.000554 2022/09/13 20:52:36 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 20:52:36 - mmengine - INFO - Saving checkpoint at 154 epochs 2022/09/13 20:53:20 - mmengine - INFO - Epoch(train) [155][50/293] lr: 5.000000e-04 eta: 3:02:40 time: 0.796852 data_time: 0.111964 memory: 21676 loss_kpt: 0.000546 acc_pose: 0.847911 loss: 0.000546 2022/09/13 20:53:59 - mmengine - INFO - Epoch(train) [155][100/293] lr: 5.000000e-04 eta: 3:02:09 time: 0.779456 data_time: 0.104890 memory: 21676 loss_kpt: 0.000532 acc_pose: 0.816741 loss: 0.000532 2022/09/13 20:54:39 - mmengine - INFO - Epoch(train) [155][150/293] lr: 5.000000e-04 eta: 3:01:37 time: 0.784945 data_time: 0.104661 memory: 21676 loss_kpt: 0.000533 acc_pose: 0.842916 loss: 0.000533 2022/09/13 20:55:17 - mmengine - INFO - Epoch(train) [155][200/293] lr: 5.000000e-04 eta: 3:01:06 time: 0.768715 data_time: 0.100614 memory: 21676 loss_kpt: 0.000551 acc_pose: 0.886091 loss: 0.000551 2022/09/13 20:55:56 - mmengine - INFO - Epoch(train) [155][250/293] lr: 5.000000e-04 eta: 3:00:34 time: 0.785692 data_time: 0.099825 memory: 21676 loss_kpt: 0.000541 acc_pose: 0.835004 loss: 0.000541 2022/09/13 20:56:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 20:56:30 - mmengine - INFO - Saving checkpoint at 155 epochs 2022/09/13 20:57:14 - mmengine - INFO - Epoch(train) [156][50/293] lr: 5.000000e-04 eta: 2:59:24 time: 0.793467 data_time: 0.102235 memory: 21676 loss_kpt: 0.000541 acc_pose: 0.878745 loss: 0.000541 2022/09/13 20:57:53 - mmengine - INFO - Epoch(train) [156][100/293] lr: 5.000000e-04 eta: 2:58:52 time: 0.785974 data_time: 0.097605 memory: 21676 loss_kpt: 0.000535 acc_pose: 0.861987 loss: 0.000535 2022/09/13 20:58:32 - mmengine - INFO - Epoch(train) [156][150/293] lr: 5.000000e-04 eta: 2:58:21 time: 0.786658 data_time: 0.097532 memory: 21676 loss_kpt: 0.000555 acc_pose: 0.852225 loss: 0.000555 2022/09/13 20:59:12 - mmengine - INFO - Epoch(train) [156][200/293] lr: 5.000000e-04 eta: 2:57:49 time: 0.785572 data_time: 0.097952 memory: 21676 loss_kpt: 0.000535 acc_pose: 0.842944 loss: 0.000535 2022/09/13 20:59:50 - mmengine - INFO - Epoch(train) [156][250/293] lr: 5.000000e-04 eta: 2:57:18 time: 0.775275 data_time: 0.092419 memory: 21676 loss_kpt: 0.000530 acc_pose: 0.814844 loss: 0.000530 2022/09/13 21:00:23 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 21:00:23 - mmengine - INFO - Saving checkpoint at 156 epochs 2022/09/13 21:01:08 - mmengine - INFO - Epoch(train) [157][50/293] lr: 5.000000e-04 eta: 2:56:08 time: 0.800456 data_time: 0.108269 memory: 21676 loss_kpt: 0.000534 acc_pose: 0.873651 loss: 0.000534 2022/09/13 21:01:47 - mmengine - INFO - Epoch(train) [157][100/293] lr: 5.000000e-04 eta: 2:55:36 time: 0.781752 data_time: 0.096680 memory: 21676 loss_kpt: 0.000536 acc_pose: 0.844802 loss: 0.000536 2022/09/13 21:02:26 - mmengine - INFO - Epoch(train) [157][150/293] lr: 5.000000e-04 eta: 2:55:04 time: 0.783053 data_time: 0.092221 memory: 21676 loss_kpt: 0.000540 acc_pose: 0.834196 loss: 0.000540 2022/09/13 21:03:05 - mmengine - INFO - Epoch(train) [157][200/293] lr: 5.000000e-04 eta: 2:54:33 time: 0.775618 data_time: 0.095403 memory: 21676 loss_kpt: 0.000538 acc_pose: 0.865106 loss: 0.000538 2022/09/13 21:03:44 - mmengine - INFO - Epoch(train) [157][250/293] lr: 5.000000e-04 eta: 2:54:01 time: 0.777874 data_time: 0.102048 memory: 21676 loss_kpt: 0.000532 acc_pose: 0.793374 loss: 0.000532 2022/09/13 21:04:16 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 21:04:17 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 21:04:17 - mmengine - INFO - Saving checkpoint at 157 epochs 2022/09/13 21:05:01 - mmengine - INFO - Epoch(train) [158][50/293] lr: 5.000000e-04 eta: 2:52:51 time: 0.795841 data_time: 0.102605 memory: 21676 loss_kpt: 0.000550 acc_pose: 0.798881 loss: 0.000550 2022/09/13 21:05:41 - mmengine - INFO - Epoch(train) [158][100/293] lr: 5.000000e-04 eta: 2:52:20 time: 0.795881 data_time: 0.104062 memory: 21676 loss_kpt: 0.000545 acc_pose: 0.873769 loss: 0.000545 2022/09/13 21:06:20 - mmengine - INFO - Epoch(train) [158][150/293] lr: 5.000000e-04 eta: 2:51:48 time: 0.789350 data_time: 0.098281 memory: 21676 loss_kpt: 0.000533 acc_pose: 0.846323 loss: 0.000533 2022/09/13 21:06:59 - mmengine - INFO - Epoch(train) [158][200/293] lr: 5.000000e-04 eta: 2:51:16 time: 0.779832 data_time: 0.102239 memory: 21676 loss_kpt: 0.000539 acc_pose: 0.850652 loss: 0.000539 2022/09/13 21:07:38 - mmengine - INFO - Epoch(train) [158][250/293] lr: 5.000000e-04 eta: 2:50:45 time: 0.784165 data_time: 0.100941 memory: 21676 loss_kpt: 0.000539 acc_pose: 0.817708 loss: 0.000539 2022/09/13 21:08:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 21:08:11 - mmengine - INFO - Saving checkpoint at 158 epochs 2022/09/13 21:08:56 - mmengine - INFO - Epoch(train) [159][50/293] lr: 5.000000e-04 eta: 2:49:35 time: 0.800903 data_time: 0.107894 memory: 21676 loss_kpt: 0.000529 acc_pose: 0.912806 loss: 0.000529 2022/09/13 21:09:35 - mmengine - INFO - Epoch(train) [159][100/293] lr: 5.000000e-04 eta: 2:49:03 time: 0.782437 data_time: 0.097036 memory: 21676 loss_kpt: 0.000536 acc_pose: 0.849299 loss: 0.000536 2022/09/13 21:10:14 - mmengine - INFO - Epoch(train) [159][150/293] lr: 5.000000e-04 eta: 2:48:32 time: 0.781448 data_time: 0.095452 memory: 21676 loss_kpt: 0.000530 acc_pose: 0.871295 loss: 0.000530 2022/09/13 21:10:53 - mmengine - INFO - Epoch(train) [159][200/293] lr: 5.000000e-04 eta: 2:48:00 time: 0.772222 data_time: 0.098090 memory: 21676 loss_kpt: 0.000531 acc_pose: 0.866809 loss: 0.000531 2022/09/13 21:11:32 - mmengine - INFO - Epoch(train) [159][250/293] lr: 5.000000e-04 eta: 2:47:28 time: 0.790556 data_time: 0.107078 memory: 21676 loss_kpt: 0.000536 acc_pose: 0.830508 loss: 0.000536 2022/09/13 21:12:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 21:12:05 - mmengine - INFO - Saving checkpoint at 159 epochs 2022/09/13 21:12:49 - mmengine - INFO - Epoch(train) [160][50/293] lr: 5.000000e-04 eta: 2:46:19 time: 0.794084 data_time: 0.108726 memory: 21676 loss_kpt: 0.000551 acc_pose: 0.848150 loss: 0.000551 2022/09/13 21:13:28 - mmengine - INFO - Epoch(train) [160][100/293] lr: 5.000000e-04 eta: 2:45:47 time: 0.780944 data_time: 0.095298 memory: 21676 loss_kpt: 0.000537 acc_pose: 0.863458 loss: 0.000537 2022/09/13 21:14:08 - mmengine - INFO - Epoch(train) [160][150/293] lr: 5.000000e-04 eta: 2:45:15 time: 0.785329 data_time: 0.093150 memory: 21676 loss_kpt: 0.000526 acc_pose: 0.858016 loss: 0.000526 2022/09/13 21:14:47 - mmengine - INFO - Epoch(train) [160][200/293] lr: 5.000000e-04 eta: 2:44:43 time: 0.779532 data_time: 0.102921 memory: 21676 loss_kpt: 0.000530 acc_pose: 0.845538 loss: 0.000530 2022/09/13 21:15:24 - mmengine - INFO - Epoch(train) [160][250/293] lr: 5.000000e-04 eta: 2:44:11 time: 0.752331 data_time: 0.092939 memory: 21676 loss_kpt: 0.000534 acc_pose: 0.874421 loss: 0.000534 2022/09/13 21:15:57 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 21:15:57 - mmengine - INFO - Saving checkpoint at 160 epochs 2022/09/13 21:16:11 - mmengine - INFO - Epoch(val) [160][50/407] eta: 0:01:05 time: 0.183757 data_time: 0.014450 memory: 21676 2022/09/13 21:16:19 - mmengine - INFO - Epoch(val) [160][100/407] eta: 0:00:53 time: 0.175076 data_time: 0.008358 memory: 1375 2022/09/13 21:16:28 - mmengine - INFO - Epoch(val) [160][150/407] eta: 0:00:44 time: 0.174375 data_time: 0.008357 memory: 1375 2022/09/13 21:16:37 - mmengine - INFO - Epoch(val) [160][200/407] eta: 0:00:36 time: 0.177769 data_time: 0.008748 memory: 1375 2022/09/13 21:16:46 - mmengine - INFO - Epoch(val) [160][250/407] eta: 0:00:27 time: 0.175358 data_time: 0.008514 memory: 1375 2022/09/13 21:16:55 - mmengine - INFO - Epoch(val) [160][300/407] eta: 0:00:18 time: 0.174769 data_time: 0.008288 memory: 1375 2022/09/13 21:17:03 - mmengine - INFO - Epoch(val) [160][350/407] eta: 0:00:09 time: 0.175234 data_time: 0.008634 memory: 1375 2022/09/13 21:17:12 - mmengine - INFO - Epoch(val) [160][400/407] eta: 0:00:01 time: 0.172375 data_time: 0.007933 memory: 1375 2022/09/13 21:17:48 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 21:18:02 - mmengine - INFO - Epoch(val) [160][407/407] coco/AP: 0.756943 coco/AP .5: 0.903610 coco/AP .75: 0.821883 coco/AP (M): 0.717200 coco/AP (L): 0.829394 coco/AR: 0.806360 coco/AR .5: 0.940649 coco/AR .75: 0.864452 coco/AR (M): 0.761267 coco/AR (L): 0.871981 2022/09/13 21:18:42 - mmengine - INFO - Epoch(train) [161][50/293] lr: 5.000000e-04 eta: 2:43:02 time: 0.805186 data_time: 0.111003 memory: 21676 loss_kpt: 0.000531 acc_pose: 0.856649 loss: 0.000531 2022/09/13 21:19:21 - mmengine - INFO - Epoch(train) [161][100/293] lr: 5.000000e-04 eta: 2:42:30 time: 0.780145 data_time: 0.094031 memory: 21676 loss_kpt: 0.000529 acc_pose: 0.833911 loss: 0.000529 2022/09/13 21:19:37 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 21:20:00 - mmengine - INFO - Epoch(train) [161][150/293] lr: 5.000000e-04 eta: 2:41:58 time: 0.784093 data_time: 0.098447 memory: 21676 loss_kpt: 0.000540 acc_pose: 0.876453 loss: 0.000540 2022/09/13 21:20:39 - mmengine - INFO - Epoch(train) [161][200/293] lr: 5.000000e-04 eta: 2:41:27 time: 0.777777 data_time: 0.100066 memory: 21676 loss_kpt: 0.000545 acc_pose: 0.846287 loss: 0.000545 2022/09/13 21:21:18 - mmengine - INFO - Epoch(train) [161][250/293] lr: 5.000000e-04 eta: 2:40:55 time: 0.770442 data_time: 0.095018 memory: 21676 loss_kpt: 0.000539 acc_pose: 0.813992 loss: 0.000539 2022/09/13 21:21:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 21:21:51 - mmengine - INFO - Saving checkpoint at 161 epochs 2022/09/13 21:22:35 - mmengine - INFO - Epoch(train) [162][50/293] lr: 5.000000e-04 eta: 2:39:45 time: 0.784867 data_time: 0.112411 memory: 21676 loss_kpt: 0.000540 acc_pose: 0.893691 loss: 0.000540 2022/09/13 21:23:13 - mmengine - INFO - Epoch(train) [162][100/293] lr: 5.000000e-04 eta: 2:39:13 time: 0.779396 data_time: 0.096448 memory: 21676 loss_kpt: 0.000537 acc_pose: 0.844889 loss: 0.000537 2022/09/13 21:23:53 - mmengine - INFO - Epoch(train) [162][150/293] lr: 5.000000e-04 eta: 2:38:42 time: 0.784844 data_time: 0.105043 memory: 21676 loss_kpt: 0.000535 acc_pose: 0.824345 loss: 0.000535 2022/09/13 21:24:32 - mmengine - INFO - Epoch(train) [162][200/293] lr: 5.000000e-04 eta: 2:38:10 time: 0.794822 data_time: 0.104722 memory: 21676 loss_kpt: 0.000550 acc_pose: 0.823144 loss: 0.000550 2022/09/13 21:25:11 - mmengine - INFO - Epoch(train) [162][250/293] lr: 5.000000e-04 eta: 2:37:38 time: 0.773855 data_time: 0.105789 memory: 21676 loss_kpt: 0.000532 acc_pose: 0.895363 loss: 0.000532 2022/09/13 21:25:45 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 21:25:45 - mmengine - INFO - Saving checkpoint at 162 epochs 2022/09/13 21:26:29 - mmengine - INFO - Epoch(train) [163][50/293] lr: 5.000000e-04 eta: 2:36:29 time: 0.795403 data_time: 0.105437 memory: 21676 loss_kpt: 0.000542 acc_pose: 0.821092 loss: 0.000542 2022/09/13 21:27:08 - mmengine - INFO - Epoch(train) [163][100/293] lr: 5.000000e-04 eta: 2:35:57 time: 0.775441 data_time: 0.102220 memory: 21676 loss_kpt: 0.000548 acc_pose: 0.846794 loss: 0.000548 2022/09/13 21:27:47 - mmengine - INFO - Epoch(train) [163][150/293] lr: 5.000000e-04 eta: 2:35:25 time: 0.781317 data_time: 0.099875 memory: 21676 loss_kpt: 0.000531 acc_pose: 0.881696 loss: 0.000531 2022/09/13 21:28:26 - mmengine - INFO - Epoch(train) [163][200/293] lr: 5.000000e-04 eta: 2:34:53 time: 0.778507 data_time: 0.099049 memory: 21676 loss_kpt: 0.000531 acc_pose: 0.799318 loss: 0.000531 2022/09/13 21:29:05 - mmengine - INFO - Epoch(train) [163][250/293] lr: 5.000000e-04 eta: 2:34:21 time: 0.788635 data_time: 0.099734 memory: 21676 loss_kpt: 0.000536 acc_pose: 0.863472 loss: 0.000536 2022/09/13 21:29:39 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 21:29:39 - mmengine - INFO - Saving checkpoint at 163 epochs 2022/09/13 21:30:23 - mmengine - INFO - Epoch(train) [164][50/293] lr: 5.000000e-04 eta: 2:33:12 time: 0.788445 data_time: 0.106553 memory: 21676 loss_kpt: 0.000539 acc_pose: 0.840229 loss: 0.000539 2022/09/13 21:31:02 - mmengine - INFO - Epoch(train) [164][100/293] lr: 5.000000e-04 eta: 2:32:40 time: 0.775226 data_time: 0.097629 memory: 21676 loss_kpt: 0.000528 acc_pose: 0.866197 loss: 0.000528 2022/09/13 21:31:41 - mmengine - INFO - Epoch(train) [164][150/293] lr: 5.000000e-04 eta: 2:32:08 time: 0.770399 data_time: 0.099567 memory: 21676 loss_kpt: 0.000538 acc_pose: 0.853350 loss: 0.000538 2022/09/13 21:32:20 - mmengine - INFO - Epoch(train) [164][200/293] lr: 5.000000e-04 eta: 2:31:36 time: 0.781431 data_time: 0.098455 memory: 21676 loss_kpt: 0.000523 acc_pose: 0.841678 loss: 0.000523 2022/09/13 21:32:52 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 21:32:59 - mmengine - INFO - Epoch(train) [164][250/293] lr: 5.000000e-04 eta: 2:31:05 time: 0.787751 data_time: 0.098564 memory: 21676 loss_kpt: 0.000525 acc_pose: 0.866272 loss: 0.000525 2022/09/13 21:33:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 21:33:32 - mmengine - INFO - Saving checkpoint at 164 epochs 2022/09/13 21:34:16 - mmengine - INFO - Epoch(train) [165][50/293] lr: 5.000000e-04 eta: 2:29:56 time: 0.795248 data_time: 0.109194 memory: 21676 loss_kpt: 0.000539 acc_pose: 0.838039 loss: 0.000539 2022/09/13 21:34:56 - mmengine - INFO - Epoch(train) [165][100/293] lr: 5.000000e-04 eta: 2:29:24 time: 0.794295 data_time: 0.104595 memory: 21676 loss_kpt: 0.000541 acc_pose: 0.873393 loss: 0.000541 2022/09/13 21:35:35 - mmengine - INFO - Epoch(train) [165][150/293] lr: 5.000000e-04 eta: 2:28:52 time: 0.790443 data_time: 0.101127 memory: 21676 loss_kpt: 0.000531 acc_pose: 0.821124 loss: 0.000531 2022/09/13 21:36:14 - mmengine - INFO - Epoch(train) [165][200/293] lr: 5.000000e-04 eta: 2:28:20 time: 0.772558 data_time: 0.094048 memory: 21676 loss_kpt: 0.000534 acc_pose: 0.795159 loss: 0.000534 2022/09/13 21:36:54 - mmengine - INFO - Epoch(train) [165][250/293] lr: 5.000000e-04 eta: 2:27:48 time: 0.797639 data_time: 0.095760 memory: 21676 loss_kpt: 0.000542 acc_pose: 0.824917 loss: 0.000542 2022/09/13 21:37:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 21:37:27 - mmengine - INFO - Saving checkpoint at 165 epochs 2022/09/13 21:38:11 - mmengine - INFO - Epoch(train) [166][50/293] lr: 5.000000e-04 eta: 2:26:40 time: 0.793446 data_time: 0.111624 memory: 21676 loss_kpt: 0.000539 acc_pose: 0.866576 loss: 0.000539 2022/09/13 21:38:51 - mmengine - INFO - Epoch(train) [166][100/293] lr: 5.000000e-04 eta: 2:26:08 time: 0.792898 data_time: 0.105143 memory: 21676 loss_kpt: 0.000551 acc_pose: 0.889578 loss: 0.000551 2022/09/13 21:39:29 - mmengine - INFO - Epoch(train) [166][150/293] lr: 5.000000e-04 eta: 2:25:36 time: 0.774000 data_time: 0.099114 memory: 21676 loss_kpt: 0.000533 acc_pose: 0.868279 loss: 0.000533 2022/09/13 21:40:09 - mmengine - INFO - Epoch(train) [166][200/293] lr: 5.000000e-04 eta: 2:25:04 time: 0.789747 data_time: 0.102879 memory: 21676 loss_kpt: 0.000539 acc_pose: 0.895431 loss: 0.000539 2022/09/13 21:40:48 - mmengine - INFO - Epoch(train) [166][250/293] lr: 5.000000e-04 eta: 2:24:32 time: 0.781161 data_time: 0.098812 memory: 21676 loss_kpt: 0.000529 acc_pose: 0.815546 loss: 0.000529 2022/09/13 21:41:21 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 21:41:21 - mmengine - INFO - Saving checkpoint at 166 epochs 2022/09/13 21:42:06 - mmengine - INFO - Epoch(train) [167][50/293] lr: 5.000000e-04 eta: 2:23:24 time: 0.798954 data_time: 0.109477 memory: 21676 loss_kpt: 0.000529 acc_pose: 0.885630 loss: 0.000529 2022/09/13 21:42:45 - mmengine - INFO - Epoch(train) [167][100/293] lr: 5.000000e-04 eta: 2:22:52 time: 0.791314 data_time: 0.097967 memory: 21676 loss_kpt: 0.000523 acc_pose: 0.894050 loss: 0.000523 2022/09/13 21:43:25 - mmengine - INFO - Epoch(train) [167][150/293] lr: 5.000000e-04 eta: 2:22:20 time: 0.785845 data_time: 0.097289 memory: 21676 loss_kpt: 0.000524 acc_pose: 0.823496 loss: 0.000524 2022/09/13 21:44:04 - mmengine - INFO - Epoch(train) [167][200/293] lr: 5.000000e-04 eta: 2:21:48 time: 0.776542 data_time: 0.101180 memory: 21676 loss_kpt: 0.000543 acc_pose: 0.834482 loss: 0.000543 2022/09/13 21:44:42 - mmengine - INFO - Epoch(train) [167][250/293] lr: 5.000000e-04 eta: 2:21:16 time: 0.774786 data_time: 0.101483 memory: 21676 loss_kpt: 0.000539 acc_pose: 0.849470 loss: 0.000539 2022/09/13 21:45:15 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 21:45:15 - mmengine - INFO - Saving checkpoint at 167 epochs 2022/09/13 21:46:00 - mmengine - INFO - Epoch(train) [168][50/293] lr: 5.000000e-04 eta: 2:20:07 time: 0.794010 data_time: 0.106188 memory: 21676 loss_kpt: 0.000534 acc_pose: 0.855721 loss: 0.000534 2022/09/13 21:46:15 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 21:46:39 - mmengine - INFO - Epoch(train) [168][100/293] lr: 5.000000e-04 eta: 2:19:35 time: 0.786495 data_time: 0.096791 memory: 21676 loss_kpt: 0.000537 acc_pose: 0.878495 loss: 0.000537 2022/09/13 21:47:18 - mmengine - INFO - Epoch(train) [168][150/293] lr: 5.000000e-04 eta: 2:19:03 time: 0.784873 data_time: 0.098956 memory: 21676 loss_kpt: 0.000524 acc_pose: 0.850345 loss: 0.000524 2022/09/13 21:47:57 - mmengine - INFO - Epoch(train) [168][200/293] lr: 5.000000e-04 eta: 2:18:31 time: 0.782604 data_time: 0.099001 memory: 21676 loss_kpt: 0.000535 acc_pose: 0.840458 loss: 0.000535 2022/09/13 21:48:36 - mmengine - INFO - Epoch(train) [168][250/293] lr: 5.000000e-04 eta: 2:17:59 time: 0.778815 data_time: 0.097494 memory: 21676 loss_kpt: 0.000539 acc_pose: 0.876972 loss: 0.000539 2022/09/13 21:49:09 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 21:49:09 - mmengine - INFO - Saving checkpoint at 168 epochs 2022/09/13 21:49:53 - mmengine - INFO - Epoch(train) [169][50/293] lr: 5.000000e-04 eta: 2:16:51 time: 0.790756 data_time: 0.107458 memory: 21676 loss_kpt: 0.000536 acc_pose: 0.865007 loss: 0.000536 2022/09/13 21:50:32 - mmengine - INFO - Epoch(train) [169][100/293] lr: 5.000000e-04 eta: 2:16:19 time: 0.777202 data_time: 0.096612 memory: 21676 loss_kpt: 0.000524 acc_pose: 0.885757 loss: 0.000524 2022/09/13 21:51:11 - mmengine - INFO - Epoch(train) [169][150/293] lr: 5.000000e-04 eta: 2:15:47 time: 0.779970 data_time: 0.099313 memory: 21676 loss_kpt: 0.000532 acc_pose: 0.860175 loss: 0.000532 2022/09/13 21:51:50 - mmengine - INFO - Epoch(train) [169][200/293] lr: 5.000000e-04 eta: 2:15:15 time: 0.780763 data_time: 0.101433 memory: 21676 loss_kpt: 0.000530 acc_pose: 0.805716 loss: 0.000530 2022/09/13 21:52:29 - mmengine - INFO - Epoch(train) [169][250/293] lr: 5.000000e-04 eta: 2:14:42 time: 0.778210 data_time: 0.102233 memory: 21676 loss_kpt: 0.000538 acc_pose: 0.823863 loss: 0.000538 2022/09/13 21:53:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 21:53:02 - mmengine - INFO - Saving checkpoint at 169 epochs 2022/09/13 21:53:47 - mmengine - INFO - Epoch(train) [170][50/293] lr: 5.000000e-04 eta: 2:13:35 time: 0.794541 data_time: 0.114017 memory: 21676 loss_kpt: 0.000533 acc_pose: 0.836183 loss: 0.000533 2022/09/13 21:54:26 - mmengine - INFO - Epoch(train) [170][100/293] lr: 5.000000e-04 eta: 2:13:02 time: 0.777579 data_time: 0.100323 memory: 21676 loss_kpt: 0.000542 acc_pose: 0.854634 loss: 0.000542 2022/09/13 21:55:05 - mmengine - INFO - Epoch(train) [170][150/293] lr: 5.000000e-04 eta: 2:12:30 time: 0.781662 data_time: 0.101072 memory: 21676 loss_kpt: 0.000539 acc_pose: 0.854512 loss: 0.000539 2022/09/13 21:55:44 - mmengine - INFO - Epoch(train) [170][200/293] lr: 5.000000e-04 eta: 2:11:58 time: 0.775995 data_time: 0.100942 memory: 21676 loss_kpt: 0.000530 acc_pose: 0.866779 loss: 0.000530 2022/09/13 21:56:23 - mmengine - INFO - Epoch(train) [170][250/293] lr: 5.000000e-04 eta: 2:11:26 time: 0.783087 data_time: 0.100074 memory: 21676 loss_kpt: 0.000529 acc_pose: 0.841601 loss: 0.000529 2022/09/13 21:56:57 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 21:56:57 - mmengine - INFO - Saving checkpoint at 170 epochs 2022/09/13 21:57:11 - mmengine - INFO - Epoch(val) [170][50/407] eta: 0:01:05 time: 0.182991 data_time: 0.014197 memory: 21676 2022/09/13 21:57:19 - mmengine - INFO - Epoch(val) [170][100/407] eta: 0:00:54 time: 0.176934 data_time: 0.008883 memory: 1375 2022/09/13 21:57:28 - mmengine - INFO - Epoch(val) [170][150/407] eta: 0:00:45 time: 0.176511 data_time: 0.008746 memory: 1375 2022/09/13 21:57:37 - mmengine - INFO - Epoch(val) [170][200/407] eta: 0:00:37 time: 0.180619 data_time: 0.012911 memory: 1375 2022/09/13 21:57:46 - mmengine - INFO - Epoch(val) [170][250/407] eta: 0:00:27 time: 0.175039 data_time: 0.008971 memory: 1375 2022/09/13 21:57:55 - mmengine - INFO - Epoch(val) [170][300/407] eta: 0:00:18 time: 0.174440 data_time: 0.008476 memory: 1375 2022/09/13 21:58:04 - mmengine - INFO - Epoch(val) [170][350/407] eta: 0:00:10 time: 0.178146 data_time: 0.008754 memory: 1375 2022/09/13 21:58:12 - mmengine - INFO - Epoch(val) [170][400/407] eta: 0:00:01 time: 0.173583 data_time: 0.008412 memory: 1375 2022/09/13 21:58:49 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 21:59:02 - mmengine - INFO - Epoch(val) [170][407/407] coco/AP: 0.759683 coco/AP .5: 0.904862 coco/AP .75: 0.824489 coco/AP (M): 0.718378 coco/AP (L): 0.832692 coco/AR: 0.808611 coco/AR .5: 0.941436 coco/AR .75: 0.868703 coco/AR (M): 0.763453 coco/AR (L): 0.874285 2022/09/13 21:59:03 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220913/udp_w32_384_v1/best_coco/AP_epoch_150.pth is removed 2022/09/13 21:59:06 - mmengine - INFO - The best checkpoint with 0.7597 coco/AP at 170 epoch is saved to best_coco/AP_epoch_170.pth. 2022/09/13 21:59:45 - mmengine - INFO - Epoch(train) [171][50/293] lr: 5.000000e-05 eta: 2:10:18 time: 0.784581 data_time: 0.105138 memory: 21676 loss_kpt: 0.000529 acc_pose: 0.865797 loss: 0.000529 2022/09/13 22:00:24 - mmengine - INFO - Epoch(train) [171][100/293] lr: 5.000000e-05 eta: 2:09:46 time: 0.784755 data_time: 0.093404 memory: 21676 loss_kpt: 0.000534 acc_pose: 0.871698 loss: 0.000534 2022/09/13 22:01:03 - mmengine - INFO - Epoch(train) [171][150/293] lr: 5.000000e-05 eta: 2:09:14 time: 0.778374 data_time: 0.092833 memory: 21676 loss_kpt: 0.000518 acc_pose: 0.818383 loss: 0.000518 2022/09/13 22:01:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 22:01:43 - mmengine - INFO - Epoch(train) [171][200/293] lr: 5.000000e-05 eta: 2:08:41 time: 0.787288 data_time: 0.093444 memory: 21676 loss_kpt: 0.000513 acc_pose: 0.885286 loss: 0.000513 2022/09/13 22:02:22 - mmengine - INFO - Epoch(train) [171][250/293] lr: 5.000000e-05 eta: 2:08:09 time: 0.788967 data_time: 0.092886 memory: 21676 loss_kpt: 0.000519 acc_pose: 0.858525 loss: 0.000519 2022/09/13 22:02:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 22:02:55 - mmengine - INFO - Saving checkpoint at 171 epochs 2022/09/13 22:03:39 - mmengine - INFO - Epoch(train) [172][50/293] lr: 5.000000e-05 eta: 2:07:02 time: 0.783883 data_time: 0.107417 memory: 21676 loss_kpt: 0.000522 acc_pose: 0.878741 loss: 0.000522 2022/09/13 22:04:19 - mmengine - INFO - Epoch(train) [172][100/293] lr: 5.000000e-05 eta: 2:06:30 time: 0.797044 data_time: 0.097308 memory: 21676 loss_kpt: 0.000509 acc_pose: 0.861763 loss: 0.000509 2022/09/13 22:04:58 - mmengine - INFO - Epoch(train) [172][150/293] lr: 5.000000e-05 eta: 2:05:57 time: 0.786819 data_time: 0.099424 memory: 21676 loss_kpt: 0.000514 acc_pose: 0.884237 loss: 0.000514 2022/09/13 22:05:38 - mmengine - INFO - Epoch(train) [172][200/293] lr: 5.000000e-05 eta: 2:05:25 time: 0.789702 data_time: 0.098630 memory: 21676 loss_kpt: 0.000517 acc_pose: 0.831908 loss: 0.000517 2022/09/13 22:06:16 - mmengine - INFO - Epoch(train) [172][250/293] lr: 5.000000e-05 eta: 2:04:53 time: 0.753605 data_time: 0.104112 memory: 21676 loss_kpt: 0.000507 acc_pose: 0.888645 loss: 0.000507 2022/09/13 22:06:48 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 22:06:48 - mmengine - INFO - Saving checkpoint at 172 epochs 2022/09/13 22:07:32 - mmengine - INFO - Epoch(train) [173][50/293] lr: 5.000000e-05 eta: 2:03:45 time: 0.800081 data_time: 0.108758 memory: 21676 loss_kpt: 0.000514 acc_pose: 0.837656 loss: 0.000514 2022/09/13 22:08:11 - mmengine - INFO - Epoch(train) [173][100/293] lr: 5.000000e-05 eta: 2:03:13 time: 0.783969 data_time: 0.109230 memory: 21676 loss_kpt: 0.000506 acc_pose: 0.873774 loss: 0.000506 2022/09/13 22:08:51 - mmengine - INFO - Epoch(train) [173][150/293] lr: 5.000000e-05 eta: 2:02:41 time: 0.784331 data_time: 0.099996 memory: 21676 loss_kpt: 0.000515 acc_pose: 0.871382 loss: 0.000515 2022/09/13 22:09:30 - mmengine - INFO - Epoch(train) [173][200/293] lr: 5.000000e-05 eta: 2:02:09 time: 0.781292 data_time: 0.103584 memory: 21676 loss_kpt: 0.000521 acc_pose: 0.876167 loss: 0.000521 2022/09/13 22:10:09 - mmengine - INFO - Epoch(train) [173][250/293] lr: 5.000000e-05 eta: 2:01:36 time: 0.782737 data_time: 0.101561 memory: 21676 loss_kpt: 0.000503 acc_pose: 0.872092 loss: 0.000503 2022/09/13 22:10:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 22:10:43 - mmengine - INFO - Saving checkpoint at 173 epochs 2022/09/13 22:11:27 - mmengine - INFO - Epoch(train) [174][50/293] lr: 5.000000e-05 eta: 2:00:29 time: 0.790697 data_time: 0.111252 memory: 21676 loss_kpt: 0.000509 acc_pose: 0.894112 loss: 0.000509 2022/09/13 22:12:06 - mmengine - INFO - Epoch(train) [174][100/293] lr: 5.000000e-05 eta: 1:59:57 time: 0.777802 data_time: 0.100014 memory: 21676 loss_kpt: 0.000512 acc_pose: 0.870422 loss: 0.000512 2022/09/13 22:12:44 - mmengine - INFO - Epoch(train) [174][150/293] lr: 5.000000e-05 eta: 1:59:24 time: 0.773675 data_time: 0.101210 memory: 21676 loss_kpt: 0.000499 acc_pose: 0.856585 loss: 0.000499 2022/09/13 22:13:23 - mmengine - INFO - Epoch(train) [174][200/293] lr: 5.000000e-05 eta: 1:58:52 time: 0.778963 data_time: 0.099454 memory: 21676 loss_kpt: 0.000496 acc_pose: 0.857373 loss: 0.000496 2022/09/13 22:14:02 - mmengine - INFO - Epoch(train) [174][250/293] lr: 5.000000e-05 eta: 1:58:19 time: 0.774916 data_time: 0.102371 memory: 21676 loss_kpt: 0.000515 acc_pose: 0.900574 loss: 0.000515 2022/09/13 22:14:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 22:14:35 - mmengine - INFO - Saving checkpoint at 174 epochs 2022/09/13 22:14:54 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 22:15:19 - mmengine - INFO - Epoch(train) [175][50/293] lr: 5.000000e-05 eta: 1:57:12 time: 0.775438 data_time: 0.105101 memory: 21676 loss_kpt: 0.000509 acc_pose: 0.803640 loss: 0.000509 2022/09/13 22:15:58 - mmengine - INFO - Epoch(train) [175][100/293] lr: 5.000000e-05 eta: 1:56:40 time: 0.788033 data_time: 0.095958 memory: 21676 loss_kpt: 0.000513 acc_pose: 0.848081 loss: 0.000513 2022/09/13 22:16:37 - mmengine - INFO - Epoch(train) [175][150/293] lr: 5.000000e-05 eta: 1:56:08 time: 0.784754 data_time: 0.097233 memory: 21676 loss_kpt: 0.000518 acc_pose: 0.847649 loss: 0.000518 2022/09/13 22:17:16 - mmengine - INFO - Epoch(train) [175][200/293] lr: 5.000000e-05 eta: 1:55:35 time: 0.773903 data_time: 0.095548 memory: 21676 loss_kpt: 0.000510 acc_pose: 0.895360 loss: 0.000510 2022/09/13 22:17:55 - mmengine - INFO - Epoch(train) [175][250/293] lr: 5.000000e-05 eta: 1:55:03 time: 0.780918 data_time: 0.101895 memory: 21676 loss_kpt: 0.000516 acc_pose: 0.847888 loss: 0.000516 2022/09/13 22:18:28 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 22:18:28 - mmengine - INFO - Saving checkpoint at 175 epochs 2022/09/13 22:19:12 - mmengine - INFO - Epoch(train) [176][50/293] lr: 5.000000e-05 eta: 1:53:56 time: 0.790816 data_time: 0.107907 memory: 21676 loss_kpt: 0.000493 acc_pose: 0.866105 loss: 0.000493 2022/09/13 22:19:52 - mmengine - INFO - Epoch(train) [176][100/293] lr: 5.000000e-05 eta: 1:53:24 time: 0.793386 data_time: 0.097618 memory: 21676 loss_kpt: 0.000506 acc_pose: 0.882160 loss: 0.000506 2022/09/13 22:20:31 - mmengine - INFO - Epoch(train) [176][150/293] lr: 5.000000e-05 eta: 1:52:51 time: 0.787892 data_time: 0.102653 memory: 21676 loss_kpt: 0.000500 acc_pose: 0.857174 loss: 0.000500 2022/09/13 22:21:10 - mmengine - INFO - Epoch(train) [176][200/293] lr: 5.000000e-05 eta: 1:52:19 time: 0.781818 data_time: 0.099284 memory: 21676 loss_kpt: 0.000512 acc_pose: 0.888166 loss: 0.000512 2022/09/13 22:21:49 - mmengine - INFO - Epoch(train) [176][250/293] lr: 5.000000e-05 eta: 1:51:46 time: 0.779895 data_time: 0.095052 memory: 21676 loss_kpt: 0.000508 acc_pose: 0.839419 loss: 0.000508 2022/09/13 22:22:23 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 22:22:23 - mmengine - INFO - Saving checkpoint at 176 epochs 2022/09/13 22:23:06 - mmengine - INFO - Epoch(train) [177][50/293] lr: 5.000000e-05 eta: 1:50:40 time: 0.784558 data_time: 0.108991 memory: 21676 loss_kpt: 0.000507 acc_pose: 0.830996 loss: 0.000507 2022/09/13 22:23:46 - mmengine - INFO - Epoch(train) [177][100/293] lr: 5.000000e-05 eta: 1:50:07 time: 0.783336 data_time: 0.103171 memory: 21676 loss_kpt: 0.000505 acc_pose: 0.872511 loss: 0.000505 2022/09/13 22:24:24 - mmengine - INFO - Epoch(train) [177][150/293] lr: 5.000000e-05 eta: 1:49:35 time: 0.771510 data_time: 0.097629 memory: 21676 loss_kpt: 0.000514 acc_pose: 0.890469 loss: 0.000514 2022/09/13 22:25:03 - mmengine - INFO - Epoch(train) [177][200/293] lr: 5.000000e-05 eta: 1:49:02 time: 0.776979 data_time: 0.096631 memory: 21676 loss_kpt: 0.000510 acc_pose: 0.851793 loss: 0.000510 2022/09/13 22:25:42 - mmengine - INFO - Epoch(train) [177][250/293] lr: 5.000000e-05 eta: 1:48:30 time: 0.786560 data_time: 0.097687 memory: 21676 loss_kpt: 0.000498 acc_pose: 0.831414 loss: 0.000498 2022/09/13 22:26:15 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 22:26:15 - mmengine - INFO - Saving checkpoint at 177 epochs 2022/09/13 22:26:59 - mmengine - INFO - Epoch(train) [178][50/293] lr: 5.000000e-05 eta: 1:47:23 time: 0.796237 data_time: 0.118047 memory: 21676 loss_kpt: 0.000501 acc_pose: 0.896967 loss: 0.000501 2022/09/13 22:27:38 - mmengine - INFO - Epoch(train) [178][100/293] lr: 5.000000e-05 eta: 1:46:51 time: 0.781893 data_time: 0.099031 memory: 21676 loss_kpt: 0.000495 acc_pose: 0.883382 loss: 0.000495 2022/09/13 22:28:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 22:28:17 - mmengine - INFO - Epoch(train) [178][150/293] lr: 5.000000e-05 eta: 1:46:18 time: 0.778465 data_time: 0.098519 memory: 21676 loss_kpt: 0.000503 acc_pose: 0.819850 loss: 0.000503 2022/09/13 22:28:56 - mmengine - INFO - Epoch(train) [178][200/293] lr: 5.000000e-05 eta: 1:45:46 time: 0.784537 data_time: 0.098308 memory: 21676 loss_kpt: 0.000502 acc_pose: 0.835340 loss: 0.000502 2022/09/13 22:29:35 - mmengine - INFO - Epoch(train) [178][250/293] lr: 5.000000e-05 eta: 1:45:13 time: 0.765701 data_time: 0.095114 memory: 21676 loss_kpt: 0.000506 acc_pose: 0.867326 loss: 0.000506 2022/09/13 22:30:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 22:30:08 - mmengine - INFO - Saving checkpoint at 178 epochs 2022/09/13 22:30:52 - mmengine - INFO - Epoch(train) [179][50/293] lr: 5.000000e-05 eta: 1:44:07 time: 0.792847 data_time: 0.101948 memory: 21676 loss_kpt: 0.000500 acc_pose: 0.891233 loss: 0.000500 2022/09/13 22:31:31 - mmengine - INFO - Epoch(train) [179][100/293] lr: 5.000000e-05 eta: 1:43:34 time: 0.785699 data_time: 0.097464 memory: 21676 loss_kpt: 0.000515 acc_pose: 0.851517 loss: 0.000515 2022/09/13 22:32:10 - mmengine - INFO - Epoch(train) [179][150/293] lr: 5.000000e-05 eta: 1:43:02 time: 0.778657 data_time: 0.101919 memory: 21676 loss_kpt: 0.000495 acc_pose: 0.880594 loss: 0.000495 2022/09/13 22:32:49 - mmengine - INFO - Epoch(train) [179][200/293] lr: 5.000000e-05 eta: 1:42:29 time: 0.781921 data_time: 0.098409 memory: 21676 loss_kpt: 0.000492 acc_pose: 0.858602 loss: 0.000492 2022/09/13 22:33:28 - mmengine - INFO - Epoch(train) [179][250/293] lr: 5.000000e-05 eta: 1:41:57 time: 0.771291 data_time: 0.099462 memory: 21676 loss_kpt: 0.000494 acc_pose: 0.861400 loss: 0.000494 2022/09/13 22:34:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 22:34:02 - mmengine - INFO - Saving checkpoint at 179 epochs 2022/09/13 22:34:46 - mmengine - INFO - Epoch(train) [180][50/293] lr: 5.000000e-05 eta: 1:40:50 time: 0.794248 data_time: 0.114045 memory: 21676 loss_kpt: 0.000502 acc_pose: 0.822209 loss: 0.000502 2022/09/13 22:35:26 - mmengine - INFO - Epoch(train) [180][100/293] lr: 5.000000e-05 eta: 1:40:18 time: 0.790808 data_time: 0.106145 memory: 21676 loss_kpt: 0.000493 acc_pose: 0.854485 loss: 0.000493 2022/09/13 22:36:05 - mmengine - INFO - Epoch(train) [180][150/293] lr: 5.000000e-05 eta: 1:39:45 time: 0.786861 data_time: 0.099811 memory: 21676 loss_kpt: 0.000504 acc_pose: 0.879838 loss: 0.000504 2022/09/13 22:36:44 - mmengine - INFO - Epoch(train) [180][200/293] lr: 5.000000e-05 eta: 1:39:13 time: 0.782018 data_time: 0.106573 memory: 21676 loss_kpt: 0.000504 acc_pose: 0.875654 loss: 0.000504 2022/09/13 22:37:24 - mmengine - INFO - Epoch(train) [180][250/293] lr: 5.000000e-05 eta: 1:38:40 time: 0.793409 data_time: 0.101960 memory: 21676 loss_kpt: 0.000507 acc_pose: 0.854190 loss: 0.000507 2022/09/13 22:37:57 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 22:37:57 - mmengine - INFO - Saving checkpoint at 180 epochs 2022/09/13 22:38:11 - mmengine - INFO - Epoch(val) [180][50/407] eta: 0:01:06 time: 0.184919 data_time: 0.014807 memory: 21676 2022/09/13 22:38:20 - mmengine - INFO - Epoch(val) [180][100/407] eta: 0:00:54 time: 0.175959 data_time: 0.008465 memory: 1375 2022/09/13 22:38:29 - mmengine - INFO - Epoch(val) [180][150/407] eta: 0:00:45 time: 0.176808 data_time: 0.009342 memory: 1375 2022/09/13 22:38:38 - mmengine - INFO - Epoch(val) [180][200/407] eta: 0:00:36 time: 0.175441 data_time: 0.008576 memory: 1375 2022/09/13 22:38:46 - mmengine - INFO - Epoch(val) [180][250/407] eta: 0:00:27 time: 0.175696 data_time: 0.008829 memory: 1375 2022/09/13 22:38:56 - mmengine - INFO - Epoch(val) [180][300/407] eta: 0:00:19 time: 0.182109 data_time: 0.009612 memory: 1375 2022/09/13 22:39:05 - mmengine - INFO - Epoch(val) [180][350/407] eta: 0:00:10 time: 0.180510 data_time: 0.012330 memory: 1375 2022/09/13 22:39:13 - mmengine - INFO - Epoch(val) [180][400/407] eta: 0:00:01 time: 0.174407 data_time: 0.009091 memory: 1375 2022/09/13 22:39:49 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 22:40:03 - mmengine - INFO - Epoch(val) [180][407/407] coco/AP: 0.767332 coco/AP .5: 0.908386 coco/AP .75: 0.830491 coco/AP (M): 0.727667 coco/AP (L): 0.838601 coco/AR: 0.815271 coco/AR .5: 0.944584 coco/AR .75: 0.871851 coco/AR (M): 0.771702 coco/AR (L): 0.878818 2022/09/13 22:40:03 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220913/udp_w32_384_v1/best_coco/AP_epoch_170.pth is removed 2022/09/13 22:40:06 - mmengine - INFO - The best checkpoint with 0.7673 coco/AP at 180 epoch is saved to best_coco/AP_epoch_180.pth. 2022/09/13 22:40:45 - mmengine - INFO - Epoch(train) [181][50/293] lr: 5.000000e-05 eta: 1:37:34 time: 0.778887 data_time: 0.103455 memory: 21676 loss_kpt: 0.000505 acc_pose: 0.833710 loss: 0.000505 2022/09/13 22:41:24 - mmengine - INFO - Epoch(train) [181][100/293] lr: 5.000000e-05 eta: 1:37:02 time: 0.775608 data_time: 0.097684 memory: 21676 loss_kpt: 0.000506 acc_pose: 0.820367 loss: 0.000506 2022/09/13 22:42:04 - mmengine - INFO - Epoch(train) [181][150/293] lr: 5.000000e-05 eta: 1:36:29 time: 0.795106 data_time: 0.095674 memory: 21676 loss_kpt: 0.000505 acc_pose: 0.871185 loss: 0.000505 2022/09/13 22:42:42 - mmengine - INFO - Epoch(train) [181][200/293] lr: 5.000000e-05 eta: 1:35:56 time: 0.778468 data_time: 0.102415 memory: 21676 loss_kpt: 0.000505 acc_pose: 0.892150 loss: 0.000505 2022/09/13 22:43:22 - mmengine - INFO - Epoch(train) [181][250/293] lr: 5.000000e-05 eta: 1:35:24 time: 0.783559 data_time: 0.095879 memory: 21676 loss_kpt: 0.000497 acc_pose: 0.891830 loss: 0.000497 2022/09/13 22:43:29 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 22:43:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 22:43:55 - mmengine - INFO - Saving checkpoint at 181 epochs 2022/09/13 22:44:39 - mmengine - INFO - Epoch(train) [182][50/293] lr: 5.000000e-05 eta: 1:34:18 time: 0.797039 data_time: 0.111377 memory: 21676 loss_kpt: 0.000500 acc_pose: 0.854472 loss: 0.000500 2022/09/13 22:45:18 - mmengine - INFO - Epoch(train) [182][100/293] lr: 5.000000e-05 eta: 1:33:45 time: 0.779392 data_time: 0.101317 memory: 21676 loss_kpt: 0.000504 acc_pose: 0.827053 loss: 0.000504 2022/09/13 22:45:58 - mmengine - INFO - Epoch(train) [182][150/293] lr: 5.000000e-05 eta: 1:33:13 time: 0.788526 data_time: 0.098618 memory: 21676 loss_kpt: 0.000510 acc_pose: 0.858856 loss: 0.000510 2022/09/13 22:46:37 - mmengine - INFO - Epoch(train) [182][200/293] lr: 5.000000e-05 eta: 1:32:40 time: 0.778673 data_time: 0.102320 memory: 21676 loss_kpt: 0.000510 acc_pose: 0.871726 loss: 0.000510 2022/09/13 22:47:16 - mmengine - INFO - Epoch(train) [182][250/293] lr: 5.000000e-05 eta: 1:32:07 time: 0.782105 data_time: 0.100743 memory: 21676 loss_kpt: 0.000494 acc_pose: 0.842067 loss: 0.000494 2022/09/13 22:47:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 22:47:49 - mmengine - INFO - Saving checkpoint at 182 epochs 2022/09/13 22:48:34 - mmengine - INFO - Epoch(train) [183][50/293] lr: 5.000000e-05 eta: 1:31:02 time: 0.799653 data_time: 0.106213 memory: 21676 loss_kpt: 0.000488 acc_pose: 0.839185 loss: 0.000488 2022/09/13 22:49:13 - mmengine - INFO - Epoch(train) [183][100/293] lr: 5.000000e-05 eta: 1:30:29 time: 0.779557 data_time: 0.096453 memory: 21676 loss_kpt: 0.000497 acc_pose: 0.855157 loss: 0.000497 2022/09/13 22:49:52 - mmengine - INFO - Epoch(train) [183][150/293] lr: 5.000000e-05 eta: 1:29:56 time: 0.776534 data_time: 0.094378 memory: 21676 loss_kpt: 0.000521 acc_pose: 0.854959 loss: 0.000521 2022/09/13 22:50:31 - mmengine - INFO - Epoch(train) [183][200/293] lr: 5.000000e-05 eta: 1:29:24 time: 0.782448 data_time: 0.101731 memory: 21676 loss_kpt: 0.000496 acc_pose: 0.891316 loss: 0.000496 2022/09/13 22:51:09 - mmengine - INFO - Epoch(train) [183][250/293] lr: 5.000000e-05 eta: 1:28:51 time: 0.772095 data_time: 0.097228 memory: 21676 loss_kpt: 0.000506 acc_pose: 0.808878 loss: 0.000506 2022/09/13 22:51:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 22:51:42 - mmengine - INFO - Saving checkpoint at 183 epochs 2022/09/13 22:52:27 - mmengine - INFO - Epoch(train) [184][50/293] lr: 5.000000e-05 eta: 1:27:45 time: 0.792512 data_time: 0.108580 memory: 21676 loss_kpt: 0.000501 acc_pose: 0.887643 loss: 0.000501 2022/09/13 22:53:06 - mmengine - INFO - Epoch(train) [184][100/293] lr: 5.000000e-05 eta: 1:27:13 time: 0.784461 data_time: 0.104517 memory: 21676 loss_kpt: 0.000495 acc_pose: 0.865686 loss: 0.000495 2022/09/13 22:53:46 - mmengine - INFO - Epoch(train) [184][150/293] lr: 5.000000e-05 eta: 1:26:40 time: 0.788910 data_time: 0.104214 memory: 21676 loss_kpt: 0.000502 acc_pose: 0.851842 loss: 0.000502 2022/09/13 22:54:25 - mmengine - INFO - Epoch(train) [184][200/293] lr: 5.000000e-05 eta: 1:26:07 time: 0.781397 data_time: 0.098552 memory: 21676 loss_kpt: 0.000502 acc_pose: 0.876196 loss: 0.000502 2022/09/13 22:55:04 - mmengine - INFO - Epoch(train) [184][250/293] lr: 5.000000e-05 eta: 1:25:35 time: 0.779785 data_time: 0.101973 memory: 21676 loss_kpt: 0.000498 acc_pose: 0.846462 loss: 0.000498 2022/09/13 22:55:37 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 22:55:37 - mmengine - INFO - Saving checkpoint at 184 epochs 2022/09/13 22:56:20 - mmengine - INFO - Epoch(train) [185][50/293] lr: 5.000000e-05 eta: 1:24:29 time: 0.780002 data_time: 0.109631 memory: 21676 loss_kpt: 0.000483 acc_pose: 0.877775 loss: 0.000483 2022/09/13 22:56:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 22:56:59 - mmengine - INFO - Epoch(train) [185][100/293] lr: 5.000000e-05 eta: 1:23:56 time: 0.777736 data_time: 0.096303 memory: 21676 loss_kpt: 0.000500 acc_pose: 0.880763 loss: 0.000500 2022/09/13 22:57:38 - mmengine - INFO - Epoch(train) [185][150/293] lr: 5.000000e-05 eta: 1:23:23 time: 0.772839 data_time: 0.096333 memory: 21676 loss_kpt: 0.000491 acc_pose: 0.894169 loss: 0.000491 2022/09/13 22:58:17 - mmengine - INFO - Epoch(train) [185][200/293] lr: 5.000000e-05 eta: 1:22:51 time: 0.778676 data_time: 0.096532 memory: 21676 loss_kpt: 0.000505 acc_pose: 0.842262 loss: 0.000505 2022/09/13 22:58:55 - mmengine - INFO - Epoch(train) [185][250/293] lr: 5.000000e-05 eta: 1:22:18 time: 0.773093 data_time: 0.098510 memory: 21676 loss_kpt: 0.000489 acc_pose: 0.835015 loss: 0.000489 2022/09/13 22:59:28 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 22:59:28 - mmengine - INFO - Saving checkpoint at 185 epochs 2022/09/13 23:00:13 - mmengine - INFO - Epoch(train) [186][50/293] lr: 5.000000e-05 eta: 1:21:12 time: 0.794374 data_time: 0.108160 memory: 21676 loss_kpt: 0.000505 acc_pose: 0.834492 loss: 0.000505 2022/09/13 23:00:52 - mmengine - INFO - Epoch(train) [186][100/293] lr: 5.000000e-05 eta: 1:20:40 time: 0.789112 data_time: 0.094464 memory: 21676 loss_kpt: 0.000497 acc_pose: 0.873351 loss: 0.000497 2022/09/13 23:01:31 - mmengine - INFO - Epoch(train) [186][150/293] lr: 5.000000e-05 eta: 1:20:07 time: 0.774431 data_time: 0.098062 memory: 21676 loss_kpt: 0.000507 acc_pose: 0.867705 loss: 0.000507 2022/09/13 23:02:09 - mmengine - INFO - Epoch(train) [186][200/293] lr: 5.000000e-05 eta: 1:19:34 time: 0.772885 data_time: 0.093890 memory: 21676 loss_kpt: 0.000512 acc_pose: 0.850944 loss: 0.000512 2022/09/13 23:02:49 - mmengine - INFO - Epoch(train) [186][250/293] lr: 5.000000e-05 eta: 1:19:01 time: 0.784049 data_time: 0.095218 memory: 21676 loss_kpt: 0.000497 acc_pose: 0.875674 loss: 0.000497 2022/09/13 23:03:22 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 23:03:22 - mmengine - INFO - Saving checkpoint at 186 epochs 2022/09/13 23:04:07 - mmengine - INFO - Epoch(train) [187][50/293] lr: 5.000000e-05 eta: 1:17:56 time: 0.795655 data_time: 0.116182 memory: 21676 loss_kpt: 0.000508 acc_pose: 0.834242 loss: 0.000508 2022/09/13 23:04:46 - mmengine - INFO - Epoch(train) [187][100/293] lr: 5.000000e-05 eta: 1:17:23 time: 0.789063 data_time: 0.100911 memory: 21676 loss_kpt: 0.000498 acc_pose: 0.893590 loss: 0.000498 2022/09/13 23:05:25 - mmengine - INFO - Epoch(train) [187][150/293] lr: 5.000000e-05 eta: 1:16:51 time: 0.778601 data_time: 0.094781 memory: 21676 loss_kpt: 0.000489 acc_pose: 0.866936 loss: 0.000489 2022/09/13 23:06:04 - mmengine - INFO - Epoch(train) [187][200/293] lr: 5.000000e-05 eta: 1:16:18 time: 0.785868 data_time: 0.097382 memory: 21676 loss_kpt: 0.000507 acc_pose: 0.855282 loss: 0.000507 2022/09/13 23:06:42 - mmengine - INFO - Epoch(train) [187][250/293] lr: 5.000000e-05 eta: 1:15:45 time: 0.755478 data_time: 0.098163 memory: 21676 loss_kpt: 0.000481 acc_pose: 0.867801 loss: 0.000481 2022/09/13 23:07:15 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 23:07:15 - mmengine - INFO - Saving checkpoint at 187 epochs 2022/09/13 23:08:00 - mmengine - INFO - Epoch(train) [188][50/293] lr: 5.000000e-05 eta: 1:14:40 time: 0.808797 data_time: 0.114057 memory: 21676 loss_kpt: 0.000485 acc_pose: 0.867426 loss: 0.000485 2022/09/13 23:08:39 - mmengine - INFO - Epoch(train) [188][100/293] lr: 5.000000e-05 eta: 1:14:07 time: 0.780716 data_time: 0.096712 memory: 21676 loss_kpt: 0.000503 acc_pose: 0.839360 loss: 0.000503 2022/09/13 23:09:18 - mmengine - INFO - Epoch(train) [188][150/293] lr: 5.000000e-05 eta: 1:13:34 time: 0.779268 data_time: 0.096691 memory: 21676 loss_kpt: 0.000501 acc_pose: 0.820874 loss: 0.000501 2022/09/13 23:09:57 - mmengine - INFO - Epoch(train) [188][200/293] lr: 5.000000e-05 eta: 1:13:01 time: 0.772669 data_time: 0.100644 memory: 21676 loss_kpt: 0.000513 acc_pose: 0.869480 loss: 0.000513 2022/09/13 23:10:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 23:10:36 - mmengine - INFO - Epoch(train) [188][250/293] lr: 5.000000e-05 eta: 1:12:28 time: 0.778381 data_time: 0.095930 memory: 21676 loss_kpt: 0.000492 acc_pose: 0.884753 loss: 0.000492 2022/09/13 23:11:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 23:11:08 - mmengine - INFO - Saving checkpoint at 188 epochs 2022/09/13 23:11:53 - mmengine - INFO - Epoch(train) [189][50/293] lr: 5.000000e-05 eta: 1:11:24 time: 0.806519 data_time: 0.104159 memory: 21676 loss_kpt: 0.000501 acc_pose: 0.868196 loss: 0.000501 2022/09/13 23:12:32 - mmengine - INFO - Epoch(train) [189][100/293] lr: 5.000000e-05 eta: 1:10:51 time: 0.774425 data_time: 0.100147 memory: 21676 loss_kpt: 0.000504 acc_pose: 0.883233 loss: 0.000504 2022/09/13 23:13:12 - mmengine - INFO - Epoch(train) [189][150/293] lr: 5.000000e-05 eta: 1:10:18 time: 0.793206 data_time: 0.099264 memory: 21676 loss_kpt: 0.000494 acc_pose: 0.860748 loss: 0.000494 2022/09/13 23:13:50 - mmengine - INFO - Epoch(train) [189][200/293] lr: 5.000000e-05 eta: 1:09:45 time: 0.770845 data_time: 0.096517 memory: 21676 loss_kpt: 0.000490 acc_pose: 0.891880 loss: 0.000490 2022/09/13 23:14:29 - mmengine - INFO - Epoch(train) [189][250/293] lr: 5.000000e-05 eta: 1:09:12 time: 0.768929 data_time: 0.102164 memory: 21676 loss_kpt: 0.000498 acc_pose: 0.840410 loss: 0.000498 2022/09/13 23:15:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 23:15:02 - mmengine - INFO - Saving checkpoint at 189 epochs 2022/09/13 23:15:46 - mmengine - INFO - Epoch(train) [190][50/293] lr: 5.000000e-05 eta: 1:08:07 time: 0.778079 data_time: 0.110824 memory: 21676 loss_kpt: 0.000508 acc_pose: 0.855408 loss: 0.000508 2022/09/13 23:16:25 - mmengine - INFO - Epoch(train) [190][100/293] lr: 5.000000e-05 eta: 1:07:34 time: 0.771511 data_time: 0.095362 memory: 21676 loss_kpt: 0.000494 acc_pose: 0.896416 loss: 0.000494 2022/09/13 23:17:03 - mmengine - INFO - Epoch(train) [190][150/293] lr: 5.000000e-05 eta: 1:07:01 time: 0.765858 data_time: 0.096169 memory: 21676 loss_kpt: 0.000500 acc_pose: 0.877258 loss: 0.000500 2022/09/13 23:17:41 - mmengine - INFO - Epoch(train) [190][200/293] lr: 5.000000e-05 eta: 1:06:28 time: 0.767557 data_time: 0.097663 memory: 21676 loss_kpt: 0.000494 acc_pose: 0.886570 loss: 0.000494 2022/09/13 23:18:19 - mmengine - INFO - Epoch(train) [190][250/293] lr: 5.000000e-05 eta: 1:05:55 time: 0.750773 data_time: 0.101264 memory: 21676 loss_kpt: 0.000490 acc_pose: 0.870278 loss: 0.000490 2022/09/13 23:18:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 23:18:51 - mmengine - INFO - Saving checkpoint at 190 epochs 2022/09/13 23:19:05 - mmengine - INFO - Epoch(val) [190][50/407] eta: 0:01:05 time: 0.183680 data_time: 0.014295 memory: 21676 2022/09/13 23:19:14 - mmengine - INFO - Epoch(val) [190][100/407] eta: 0:00:54 time: 0.175993 data_time: 0.008724 memory: 1375 2022/09/13 23:19:23 - mmengine - INFO - Epoch(val) [190][150/407] eta: 0:00:45 time: 0.175333 data_time: 0.008477 memory: 1375 2022/09/13 23:19:32 - mmengine - INFO - Epoch(val) [190][200/407] eta: 0:00:36 time: 0.176281 data_time: 0.009082 memory: 1375 2022/09/13 23:19:40 - mmengine - INFO - Epoch(val) [190][250/407] eta: 0:00:28 time: 0.178429 data_time: 0.009827 memory: 1375 2022/09/13 23:19:49 - mmengine - INFO - Epoch(val) [190][300/407] eta: 0:00:19 time: 0.178652 data_time: 0.008499 memory: 1375 2022/09/13 23:19:58 - mmengine - INFO - Epoch(val) [190][350/407] eta: 0:00:10 time: 0.176195 data_time: 0.008839 memory: 1375 2022/09/13 23:20:07 - mmengine - INFO - Epoch(val) [190][400/407] eta: 0:00:01 time: 0.174430 data_time: 0.008790 memory: 1375 2022/09/13 23:20:43 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 23:20:57 - mmengine - INFO - Epoch(val) [190][407/407] coco/AP: 0.767787 coco/AP .5: 0.907661 coco/AP .75: 0.832158 coco/AP (M): 0.728232 coco/AP (L): 0.838477 coco/AR: 0.815349 coco/AR .5: 0.943797 coco/AR .75: 0.872166 coco/AR (M): 0.771674 coco/AR (L): 0.879227 2022/09/13 23:20:57 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220913/udp_w32_384_v1/best_coco/AP_epoch_180.pth is removed 2022/09/13 23:21:00 - mmengine - INFO - The best checkpoint with 0.7678 coco/AP at 190 epoch is saved to best_coco/AP_epoch_190.pth. 2022/09/13 23:21:39 - mmengine - INFO - Epoch(train) [191][50/293] lr: 5.000000e-05 eta: 1:04:50 time: 0.785584 data_time: 0.109713 memory: 21676 loss_kpt: 0.000501 acc_pose: 0.883134 loss: 0.000501 2022/09/13 23:22:19 - mmengine - INFO - Epoch(train) [191][100/293] lr: 5.000000e-05 eta: 1:04:18 time: 0.787131 data_time: 0.102701 memory: 21676 loss_kpt: 0.000496 acc_pose: 0.844872 loss: 0.000496 2022/09/13 23:22:58 - mmengine - INFO - Epoch(train) [191][150/293] lr: 5.000000e-05 eta: 1:03:45 time: 0.792693 data_time: 0.101213 memory: 21676 loss_kpt: 0.000488 acc_pose: 0.871614 loss: 0.000488 2022/09/13 23:23:38 - mmengine - INFO - Epoch(train) [191][200/293] lr: 5.000000e-05 eta: 1:03:12 time: 0.788868 data_time: 0.100311 memory: 21676 loss_kpt: 0.000503 acc_pose: 0.893299 loss: 0.000503 2022/09/13 23:24:18 - mmengine - INFO - Epoch(train) [191][250/293] lr: 5.000000e-05 eta: 1:02:39 time: 0.797366 data_time: 0.107362 memory: 21676 loss_kpt: 0.000496 acc_pose: 0.887227 loss: 0.000496 2022/09/13 23:24:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 23:24:51 - mmengine - INFO - Saving checkpoint at 191 epochs 2022/09/13 23:25:25 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 23:25:35 - mmengine - INFO - Epoch(train) [192][50/293] lr: 5.000000e-05 eta: 1:01:34 time: 0.787873 data_time: 0.108620 memory: 21676 loss_kpt: 0.000499 acc_pose: 0.871905 loss: 0.000499 2022/09/13 23:26:13 - mmengine - INFO - Epoch(train) [192][100/293] lr: 5.000000e-05 eta: 1:01:01 time: 0.770521 data_time: 0.108234 memory: 21676 loss_kpt: 0.000500 acc_pose: 0.859296 loss: 0.000500 2022/09/13 23:26:52 - mmengine - INFO - Epoch(train) [192][150/293] lr: 5.000000e-05 eta: 1:00:28 time: 0.768111 data_time: 0.099785 memory: 21676 loss_kpt: 0.000503 acc_pose: 0.870413 loss: 0.000503 2022/09/13 23:27:31 - mmengine - INFO - Epoch(train) [192][200/293] lr: 5.000000e-05 eta: 0:59:55 time: 0.776084 data_time: 0.109897 memory: 21676 loss_kpt: 0.000487 acc_pose: 0.863685 loss: 0.000487 2022/09/13 23:28:10 - mmengine - INFO - Epoch(train) [192][250/293] lr: 5.000000e-05 eta: 0:59:22 time: 0.784825 data_time: 0.103914 memory: 21676 loss_kpt: 0.000480 acc_pose: 0.900300 loss: 0.000480 2022/09/13 23:28:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 23:28:43 - mmengine - INFO - Saving checkpoint at 192 epochs 2022/09/13 23:29:27 - mmengine - INFO - Epoch(train) [193][50/293] lr: 5.000000e-05 eta: 0:58:18 time: 0.790938 data_time: 0.108509 memory: 21676 loss_kpt: 0.000492 acc_pose: 0.865166 loss: 0.000492 2022/09/13 23:30:07 - mmengine - INFO - Epoch(train) [193][100/293] lr: 5.000000e-05 eta: 0:57:45 time: 0.791285 data_time: 0.101170 memory: 21676 loss_kpt: 0.000496 acc_pose: 0.891477 loss: 0.000496 2022/09/13 23:30:46 - mmengine - INFO - Epoch(train) [193][150/293] lr: 5.000000e-05 eta: 0:57:12 time: 0.778868 data_time: 0.100969 memory: 21676 loss_kpt: 0.000513 acc_pose: 0.859745 loss: 0.000513 2022/09/13 23:31:25 - mmengine - INFO - Epoch(train) [193][200/293] lr: 5.000000e-05 eta: 0:56:39 time: 0.781160 data_time: 0.100269 memory: 21676 loss_kpt: 0.000494 acc_pose: 0.872017 loss: 0.000494 2022/09/13 23:32:04 - mmengine - INFO - Epoch(train) [193][250/293] lr: 5.000000e-05 eta: 0:56:06 time: 0.782079 data_time: 0.098381 memory: 21676 loss_kpt: 0.000498 acc_pose: 0.885308 loss: 0.000498 2022/09/13 23:32:37 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 23:32:37 - mmengine - INFO - Saving checkpoint at 193 epochs 2022/09/13 23:33:22 - mmengine - INFO - Epoch(train) [194][50/293] lr: 5.000000e-05 eta: 0:55:02 time: 0.794357 data_time: 0.115214 memory: 21676 loss_kpt: 0.000490 acc_pose: 0.874669 loss: 0.000490 2022/09/13 23:34:01 - mmengine - INFO - Epoch(train) [194][100/293] lr: 5.000000e-05 eta: 0:54:29 time: 0.788324 data_time: 0.101913 memory: 21676 loss_kpt: 0.000493 acc_pose: 0.918709 loss: 0.000493 2022/09/13 23:34:40 - mmengine - INFO - Epoch(train) [194][150/293] lr: 5.000000e-05 eta: 0:53:56 time: 0.778115 data_time: 0.099122 memory: 21676 loss_kpt: 0.000502 acc_pose: 0.831064 loss: 0.000502 2022/09/13 23:35:19 - mmengine - INFO - Epoch(train) [194][200/293] lr: 5.000000e-05 eta: 0:53:23 time: 0.777767 data_time: 0.096894 memory: 21676 loss_kpt: 0.000497 acc_pose: 0.841894 loss: 0.000497 2022/09/13 23:35:58 - mmengine - INFO - Epoch(train) [194][250/293] lr: 5.000000e-05 eta: 0:52:50 time: 0.784930 data_time: 0.102869 memory: 21676 loss_kpt: 0.000507 acc_pose: 0.835979 loss: 0.000507 2022/09/13 23:36:31 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 23:36:31 - mmengine - INFO - Saving checkpoint at 194 epochs 2022/09/13 23:37:15 - mmengine - INFO - Epoch(train) [195][50/293] lr: 5.000000e-05 eta: 0:51:46 time: 0.796996 data_time: 0.111578 memory: 21676 loss_kpt: 0.000483 acc_pose: 0.880669 loss: 0.000483 2022/09/13 23:37:55 - mmengine - INFO - Epoch(train) [195][100/293] lr: 5.000000e-05 eta: 0:51:13 time: 0.788782 data_time: 0.096563 memory: 21676 loss_kpt: 0.000489 acc_pose: 0.865694 loss: 0.000489 2022/09/13 23:38:33 - mmengine - INFO - Epoch(train) [195][150/293] lr: 5.000000e-05 eta: 0:50:39 time: 0.773073 data_time: 0.098258 memory: 21676 loss_kpt: 0.000498 acc_pose: 0.898874 loss: 0.000498 2022/09/13 23:38:39 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 23:39:13 - mmengine - INFO - Epoch(train) [195][200/293] lr: 5.000000e-05 eta: 0:50:06 time: 0.788845 data_time: 0.097024 memory: 21676 loss_kpt: 0.000499 acc_pose: 0.881688 loss: 0.000499 2022/09/13 23:39:52 - mmengine - INFO - Epoch(train) [195][250/293] lr: 5.000000e-05 eta: 0:49:33 time: 0.778234 data_time: 0.096967 memory: 21676 loss_kpt: 0.000512 acc_pose: 0.863459 loss: 0.000512 2022/09/13 23:40:25 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 23:40:25 - mmengine - INFO - Saving checkpoint at 195 epochs 2022/09/13 23:41:08 - mmengine - INFO - Epoch(train) [196][50/293] lr: 5.000000e-05 eta: 0:48:29 time: 0.782230 data_time: 0.101744 memory: 21676 loss_kpt: 0.000489 acc_pose: 0.843012 loss: 0.000489 2022/09/13 23:41:48 - mmengine - INFO - Epoch(train) [196][100/293] lr: 5.000000e-05 eta: 0:47:56 time: 0.785281 data_time: 0.099791 memory: 21676 loss_kpt: 0.000497 acc_pose: 0.898831 loss: 0.000497 2022/09/13 23:42:26 - mmengine - INFO - Epoch(train) [196][150/293] lr: 5.000000e-05 eta: 0:47:23 time: 0.778407 data_time: 0.100088 memory: 21676 loss_kpt: 0.000494 acc_pose: 0.892197 loss: 0.000494 2022/09/13 23:43:05 - mmengine - INFO - Epoch(train) [196][200/293] lr: 5.000000e-05 eta: 0:46:50 time: 0.761680 data_time: 0.096929 memory: 21676 loss_kpt: 0.000493 acc_pose: 0.847311 loss: 0.000493 2022/09/13 23:43:43 - mmengine - INFO - Epoch(train) [196][250/293] lr: 5.000000e-05 eta: 0:46:17 time: 0.762889 data_time: 0.101900 memory: 21676 loss_kpt: 0.000498 acc_pose: 0.842610 loss: 0.000498 2022/09/13 23:44:15 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 23:44:15 - mmengine - INFO - Saving checkpoint at 196 epochs 2022/09/13 23:44:59 - mmengine - INFO - Epoch(train) [197][50/293] lr: 5.000000e-05 eta: 0:45:13 time: 0.789020 data_time: 0.107072 memory: 21676 loss_kpt: 0.000500 acc_pose: 0.836341 loss: 0.000500 2022/09/13 23:45:38 - mmengine - INFO - Epoch(train) [197][100/293] lr: 5.000000e-05 eta: 0:44:40 time: 0.780496 data_time: 0.100308 memory: 21676 loss_kpt: 0.000501 acc_pose: 0.874426 loss: 0.000501 2022/09/13 23:46:17 - mmengine - INFO - Epoch(train) [197][150/293] lr: 5.000000e-05 eta: 0:44:07 time: 0.785699 data_time: 0.101343 memory: 21676 loss_kpt: 0.000499 acc_pose: 0.800971 loss: 0.000499 2022/09/13 23:46:56 - mmengine - INFO - Epoch(train) [197][200/293] lr: 5.000000e-05 eta: 0:43:34 time: 0.778326 data_time: 0.096745 memory: 21676 loss_kpt: 0.000496 acc_pose: 0.819966 loss: 0.000496 2022/09/13 23:47:36 - mmengine - INFO - Epoch(train) [197][250/293] lr: 5.000000e-05 eta: 0:43:00 time: 0.787357 data_time: 0.102259 memory: 21676 loss_kpt: 0.000490 acc_pose: 0.861841 loss: 0.000490 2022/09/13 23:48:09 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 23:48:09 - mmengine - INFO - Saving checkpoint at 197 epochs 2022/09/13 23:48:53 - mmengine - INFO - Epoch(train) [198][50/293] lr: 5.000000e-05 eta: 0:41:57 time: 0.786705 data_time: 0.114448 memory: 21676 loss_kpt: 0.000496 acc_pose: 0.884884 loss: 0.000496 2022/09/13 23:49:32 - mmengine - INFO - Epoch(train) [198][100/293] lr: 5.000000e-05 eta: 0:41:24 time: 0.779801 data_time: 0.098472 memory: 21676 loss_kpt: 0.000492 acc_pose: 0.872622 loss: 0.000492 2022/09/13 23:50:11 - mmengine - INFO - Epoch(train) [198][150/293] lr: 5.000000e-05 eta: 0:40:50 time: 0.780911 data_time: 0.099779 memory: 21676 loss_kpt: 0.000502 acc_pose: 0.859947 loss: 0.000502 2022/09/13 23:50:51 - mmengine - INFO - Epoch(train) [198][200/293] lr: 5.000000e-05 eta: 0:40:17 time: 0.789555 data_time: 0.106654 memory: 21676 loss_kpt: 0.000491 acc_pose: 0.888598 loss: 0.000491 2022/09/13 23:51:29 - mmengine - INFO - Epoch(train) [198][250/293] lr: 5.000000e-05 eta: 0:39:44 time: 0.771043 data_time: 0.101731 memory: 21676 loss_kpt: 0.000491 acc_pose: 0.852195 loss: 0.000491 2022/09/13 23:51:52 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 23:52:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 23:52:02 - mmengine - INFO - Saving checkpoint at 198 epochs 2022/09/13 23:52:47 - mmengine - INFO - Epoch(train) [199][50/293] lr: 5.000000e-05 eta: 0:38:40 time: 0.798314 data_time: 0.103746 memory: 21676 loss_kpt: 0.000490 acc_pose: 0.842028 loss: 0.000490 2022/09/13 23:53:26 - mmengine - INFO - Epoch(train) [199][100/293] lr: 5.000000e-05 eta: 0:38:07 time: 0.785763 data_time: 0.101677 memory: 21676 loss_kpt: 0.000497 acc_pose: 0.860311 loss: 0.000497 2022/09/13 23:54:05 - mmengine - INFO - Epoch(train) [199][150/293] lr: 5.000000e-05 eta: 0:37:34 time: 0.780142 data_time: 0.098563 memory: 21676 loss_kpt: 0.000497 acc_pose: 0.878397 loss: 0.000497 2022/09/13 23:54:45 - mmengine - INFO - Epoch(train) [199][200/293] lr: 5.000000e-05 eta: 0:37:01 time: 0.792880 data_time: 0.101749 memory: 21676 loss_kpt: 0.000490 acc_pose: 0.888817 loss: 0.000490 2022/09/13 23:55:24 - mmengine - INFO - Epoch(train) [199][250/293] lr: 5.000000e-05 eta: 0:36:28 time: 0.778329 data_time: 0.095304 memory: 21676 loss_kpt: 0.000497 acc_pose: 0.876733 loss: 0.000497 2022/09/13 23:55:57 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 23:55:57 - mmengine - INFO - Saving checkpoint at 199 epochs 2022/09/13 23:56:41 - mmengine - INFO - Epoch(train) [200][50/293] lr: 5.000000e-05 eta: 0:35:24 time: 0.793891 data_time: 0.107728 memory: 21676 loss_kpt: 0.000484 acc_pose: 0.859388 loss: 0.000484 2022/09/13 23:57:20 - mmengine - INFO - Epoch(train) [200][100/293] lr: 5.000000e-05 eta: 0:34:51 time: 0.776100 data_time: 0.094380 memory: 21676 loss_kpt: 0.000495 acc_pose: 0.867899 loss: 0.000495 2022/09/13 23:57:59 - mmengine - INFO - Epoch(train) [200][150/293] lr: 5.000000e-05 eta: 0:34:18 time: 0.783420 data_time: 0.101056 memory: 21676 loss_kpt: 0.000493 acc_pose: 0.858207 loss: 0.000493 2022/09/13 23:58:38 - mmengine - INFO - Epoch(train) [200][200/293] lr: 5.000000e-05 eta: 0:33:45 time: 0.777010 data_time: 0.105470 memory: 21676 loss_kpt: 0.000485 acc_pose: 0.898949 loss: 0.000485 2022/09/13 23:59:18 - mmengine - INFO - Epoch(train) [200][250/293] lr: 5.000000e-05 eta: 0:33:11 time: 0.794067 data_time: 0.097664 memory: 21676 loss_kpt: 0.000485 acc_pose: 0.888028 loss: 0.000485 2022/09/13 23:59:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/13 23:59:51 - mmengine - INFO - Saving checkpoint at 200 epochs 2022/09/14 00:00:06 - mmengine - INFO - Epoch(val) [200][50/407] eta: 0:01:14 time: 0.208398 data_time: 0.019213 memory: 21676 2022/09/14 00:00:15 - mmengine - INFO - Epoch(val) [200][100/407] eta: 0:00:54 time: 0.177783 data_time: 0.008926 memory: 1375 2022/09/14 00:00:24 - mmengine - INFO - Epoch(val) [200][150/407] eta: 0:00:45 time: 0.176854 data_time: 0.008437 memory: 1375 2022/09/14 00:00:33 - mmengine - INFO - Epoch(val) [200][200/407] eta: 0:00:37 time: 0.182333 data_time: 0.013697 memory: 1375 2022/09/14 00:00:42 - mmengine - INFO - Epoch(val) [200][250/407] eta: 0:00:27 time: 0.175407 data_time: 0.008389 memory: 1375 2022/09/14 00:00:51 - mmengine - INFO - Epoch(val) [200][300/407] eta: 0:00:18 time: 0.177133 data_time: 0.008775 memory: 1375 2022/09/14 00:00:59 - mmengine - INFO - Epoch(val) [200][350/407] eta: 0:00:09 time: 0.174792 data_time: 0.009172 memory: 1375 2022/09/14 00:01:08 - mmengine - INFO - Epoch(val) [200][400/407] eta: 0:00:01 time: 0.174617 data_time: 0.008424 memory: 1375 2022/09/14 00:01:44 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 00:01:58 - mmengine - INFO - Epoch(val) [200][407/407] coco/AP: 0.767155 coco/AP .5: 0.908681 coco/AP .75: 0.830984 coco/AP (M): 0.727644 coco/AP (L): 0.837232 coco/AR: 0.814610 coco/AR .5: 0.944584 coco/AR .75: 0.871537 coco/AR (M): 0.770855 coco/AR (L): 0.878372 2022/09/14 00:02:39 - mmengine - INFO - Epoch(train) [201][50/293] lr: 5.000000e-06 eta: 0:32:08 time: 0.808897 data_time: 0.109118 memory: 21676 loss_kpt: 0.000496 acc_pose: 0.866152 loss: 0.000496 2022/09/14 00:03:17 - mmengine - INFO - Epoch(train) [201][100/293] lr: 5.000000e-06 eta: 0:31:35 time: 0.778297 data_time: 0.101497 memory: 21676 loss_kpt: 0.000491 acc_pose: 0.879755 loss: 0.000491 2022/09/14 00:03:56 - mmengine - INFO - Epoch(train) [201][150/293] lr: 5.000000e-06 eta: 0:31:02 time: 0.774014 data_time: 0.093816 memory: 21676 loss_kpt: 0.000490 acc_pose: 0.897001 loss: 0.000490 2022/09/14 00:04:35 - mmengine - INFO - Epoch(train) [201][200/293] lr: 5.000000e-06 eta: 0:30:28 time: 0.779801 data_time: 0.096829 memory: 21676 loss_kpt: 0.000488 acc_pose: 0.845598 loss: 0.000488 2022/09/14 00:05:14 - mmengine - INFO - Epoch(train) [201][250/293] lr: 5.000000e-06 eta: 0:29:55 time: 0.778917 data_time: 0.099746 memory: 21676 loss_kpt: 0.000494 acc_pose: 0.835430 loss: 0.000494 2022/09/14 00:05:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/14 00:05:46 - mmengine - INFO - Saving checkpoint at 201 epochs 2022/09/14 00:06:30 - mmengine - INFO - Epoch(train) [202][50/293] lr: 5.000000e-06 eta: 0:28:52 time: 0.793188 data_time: 0.108310 memory: 21676 loss_kpt: 0.000490 acc_pose: 0.876785 loss: 0.000490 2022/09/14 00:07:09 - mmengine - INFO - Epoch(train) [202][100/293] lr: 5.000000e-06 eta: 0:28:19 time: 0.784426 data_time: 0.097016 memory: 21676 loss_kpt: 0.000485 acc_pose: 0.883084 loss: 0.000485 2022/09/14 00:07:15 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/14 00:07:48 - mmengine - INFO - Epoch(train) [202][150/293] lr: 5.000000e-06 eta: 0:27:45 time: 0.782845 data_time: 0.100509 memory: 21676 loss_kpt: 0.000499 acc_pose: 0.848307 loss: 0.000499 2022/09/14 00:08:27 - mmengine - INFO - Epoch(train) [202][200/293] lr: 5.000000e-06 eta: 0:27:12 time: 0.782466 data_time: 0.101545 memory: 21676 loss_kpt: 0.000500 acc_pose: 0.830248 loss: 0.000500 2022/09/14 00:09:07 - mmengine - INFO - Epoch(train) [202][250/293] lr: 5.000000e-06 eta: 0:26:39 time: 0.792496 data_time: 0.101961 memory: 21676 loss_kpt: 0.000490 acc_pose: 0.857843 loss: 0.000490 2022/09/14 00:09:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/14 00:09:41 - mmengine - INFO - Saving checkpoint at 202 epochs 2022/09/14 00:10:25 - mmengine - INFO - Epoch(train) [203][50/293] lr: 5.000000e-06 eta: 0:25:36 time: 0.790134 data_time: 0.107349 memory: 21676 loss_kpt: 0.000484 acc_pose: 0.856266 loss: 0.000484 2022/09/14 00:11:04 - mmengine - INFO - Epoch(train) [203][100/293] lr: 5.000000e-06 eta: 0:25:02 time: 0.786348 data_time: 0.098757 memory: 21676 loss_kpt: 0.000487 acc_pose: 0.867067 loss: 0.000487 2022/09/14 00:11:43 - mmengine - INFO - Epoch(train) [203][150/293] lr: 5.000000e-06 eta: 0:24:29 time: 0.779935 data_time: 0.100412 memory: 21676 loss_kpt: 0.000493 acc_pose: 0.876939 loss: 0.000493 2022/09/14 00:12:23 - mmengine - INFO - Epoch(train) [203][200/293] lr: 5.000000e-06 eta: 0:23:56 time: 0.792602 data_time: 0.102254 memory: 21676 loss_kpt: 0.000484 acc_pose: 0.846728 loss: 0.000484 2022/09/14 00:13:02 - mmengine - INFO - Epoch(train) [203][250/293] lr: 5.000000e-06 eta: 0:23:23 time: 0.778925 data_time: 0.098196 memory: 21676 loss_kpt: 0.000499 acc_pose: 0.861943 loss: 0.000499 2022/09/14 00:13:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/14 00:13:35 - mmengine - INFO - Saving checkpoint at 203 epochs 2022/09/14 00:14:19 - mmengine - INFO - Epoch(train) [204][50/293] lr: 5.000000e-06 eta: 0:22:19 time: 0.780459 data_time: 0.107983 memory: 21676 loss_kpt: 0.000495 acc_pose: 0.868548 loss: 0.000495 2022/09/14 00:14:58 - mmengine - INFO - Epoch(train) [204][100/293] lr: 5.000000e-06 eta: 0:21:46 time: 0.797220 data_time: 0.102778 memory: 21676 loss_kpt: 0.000492 acc_pose: 0.872405 loss: 0.000492 2022/09/14 00:15:38 - mmengine - INFO - Epoch(train) [204][150/293] lr: 5.000000e-06 eta: 0:21:13 time: 0.785110 data_time: 0.107644 memory: 21676 loss_kpt: 0.000501 acc_pose: 0.850421 loss: 0.000501 2022/09/14 00:16:16 - mmengine - INFO - Epoch(train) [204][200/293] lr: 5.000000e-06 eta: 0:20:40 time: 0.771111 data_time: 0.101895 memory: 21676 loss_kpt: 0.000497 acc_pose: 0.839722 loss: 0.000497 2022/09/14 00:16:55 - mmengine - INFO - Epoch(train) [204][250/293] lr: 5.000000e-06 eta: 0:20:06 time: 0.773129 data_time: 0.105989 memory: 21676 loss_kpt: 0.000482 acc_pose: 0.896360 loss: 0.000482 2022/09/14 00:17:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/14 00:17:27 - mmengine - INFO - Saving checkpoint at 204 epochs 2022/09/14 00:18:12 - mmengine - INFO - Epoch(train) [205][50/293] lr: 5.000000e-06 eta: 0:19:03 time: 0.795839 data_time: 0.111294 memory: 21676 loss_kpt: 0.000477 acc_pose: 0.883029 loss: 0.000477 2022/09/14 00:18:50 - mmengine - INFO - Epoch(train) [205][100/293] lr: 5.000000e-06 eta: 0:18:30 time: 0.777416 data_time: 0.098623 memory: 21676 loss_kpt: 0.000496 acc_pose: 0.856439 loss: 0.000496 2022/09/14 00:19:29 - mmengine - INFO - Epoch(train) [205][150/293] lr: 5.000000e-06 eta: 0:17:57 time: 0.780358 data_time: 0.101170 memory: 21676 loss_kpt: 0.000485 acc_pose: 0.898298 loss: 0.000485 2022/09/14 00:20:09 - mmengine - INFO - Epoch(train) [205][200/293] lr: 5.000000e-06 eta: 0:17:23 time: 0.784562 data_time: 0.108677 memory: 21676 loss_kpt: 0.000485 acc_pose: 0.844115 loss: 0.000485 2022/09/14 00:20:31 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/14 00:20:48 - mmengine - INFO - Epoch(train) [205][250/293] lr: 5.000000e-06 eta: 0:16:50 time: 0.778892 data_time: 0.104095 memory: 21676 loss_kpt: 0.000488 acc_pose: 0.843676 loss: 0.000488 2022/09/14 00:21:20 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/14 00:21:20 - mmengine - INFO - Saving checkpoint at 205 epochs 2022/09/14 00:22:05 - mmengine - INFO - Epoch(train) [206][50/293] lr: 5.000000e-06 eta: 0:15:47 time: 0.792001 data_time: 0.110999 memory: 21676 loss_kpt: 0.000489 acc_pose: 0.881514 loss: 0.000489 2022/09/14 00:22:44 - mmengine - INFO - Epoch(train) [206][100/293] lr: 5.000000e-06 eta: 0:15:14 time: 0.783274 data_time: 0.096918 memory: 21676 loss_kpt: 0.000501 acc_pose: 0.845881 loss: 0.000501 2022/09/14 00:23:23 - mmengine - INFO - Epoch(train) [206][150/293] lr: 5.000000e-06 eta: 0:14:40 time: 0.784893 data_time: 0.100157 memory: 21676 loss_kpt: 0.000491 acc_pose: 0.901064 loss: 0.000491 2022/09/14 00:24:02 - mmengine - INFO - Epoch(train) [206][200/293] lr: 5.000000e-06 eta: 0:14:07 time: 0.778451 data_time: 0.093725 memory: 21676 loss_kpt: 0.000488 acc_pose: 0.900977 loss: 0.000488 2022/09/14 00:24:40 - mmengine - INFO - Epoch(train) [206][250/293] lr: 5.000000e-06 eta: 0:13:34 time: 0.758902 data_time: 0.097953 memory: 21676 loss_kpt: 0.000468 acc_pose: 0.902626 loss: 0.000468 2022/09/14 00:25:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/14 00:25:13 - mmengine - INFO - Saving checkpoint at 206 epochs 2022/09/14 00:25:57 - mmengine - INFO - Epoch(train) [207][50/293] lr: 5.000000e-06 eta: 0:12:31 time: 0.788258 data_time: 0.106063 memory: 21676 loss_kpt: 0.000486 acc_pose: 0.891207 loss: 0.000486 2022/09/14 00:26:36 - mmengine - INFO - Epoch(train) [207][100/293] lr: 5.000000e-06 eta: 0:11:57 time: 0.779029 data_time: 0.096607 memory: 21676 loss_kpt: 0.000492 acc_pose: 0.885479 loss: 0.000492 2022/09/14 00:27:15 - mmengine - INFO - Epoch(train) [207][150/293] lr: 5.000000e-06 eta: 0:11:24 time: 0.779305 data_time: 0.096035 memory: 21676 loss_kpt: 0.000489 acc_pose: 0.914967 loss: 0.000489 2022/09/14 00:27:55 - mmengine - INFO - Epoch(train) [207][200/293] lr: 5.000000e-06 eta: 0:10:51 time: 0.785778 data_time: 0.093548 memory: 21676 loss_kpt: 0.000501 acc_pose: 0.907280 loss: 0.000501 2022/09/14 00:28:33 - mmengine - INFO - Epoch(train) [207][250/293] lr: 5.000000e-06 eta: 0:10:17 time: 0.775383 data_time: 0.102085 memory: 21676 loss_kpt: 0.000483 acc_pose: 0.829222 loss: 0.000483 2022/09/14 00:29:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/14 00:29:06 - mmengine - INFO - Saving checkpoint at 207 epochs 2022/09/14 00:29:49 - mmengine - INFO - Epoch(train) [208][50/293] lr: 5.000000e-06 eta: 0:09:15 time: 0.770716 data_time: 0.110544 memory: 21676 loss_kpt: 0.000496 acc_pose: 0.876382 loss: 0.000496 2022/09/14 00:30:27 - mmengine - INFO - Epoch(train) [208][100/293] lr: 5.000000e-06 eta: 0:08:41 time: 0.762212 data_time: 0.096835 memory: 21676 loss_kpt: 0.000487 acc_pose: 0.832358 loss: 0.000487 2022/09/14 00:31:05 - mmengine - INFO - Epoch(train) [208][150/293] lr: 5.000000e-06 eta: 0:08:08 time: 0.760542 data_time: 0.099521 memory: 21676 loss_kpt: 0.000478 acc_pose: 0.887560 loss: 0.000478 2022/09/14 00:31:43 - mmengine - INFO - Epoch(train) [208][200/293] lr: 5.000000e-06 eta: 0:07:34 time: 0.764212 data_time: 0.097522 memory: 21676 loss_kpt: 0.000489 acc_pose: 0.902286 loss: 0.000489 2022/09/14 00:32:21 - mmengine - INFO - Epoch(train) [208][250/293] lr: 5.000000e-06 eta: 0:07:01 time: 0.759684 data_time: 0.100997 memory: 21676 loss_kpt: 0.000489 acc_pose: 0.881153 loss: 0.000489 2022/09/14 00:32:54 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/14 00:32:54 - mmengine - INFO - Saving checkpoint at 208 epochs 2022/09/14 00:33:38 - mmengine - INFO - Epoch(train) [209][50/293] lr: 5.000000e-06 eta: 0:05:58 time: 0.786887 data_time: 0.112405 memory: 21676 loss_kpt: 0.000481 acc_pose: 0.863043 loss: 0.000481 2022/09/14 00:33:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/14 00:34:17 - mmengine - INFO - Epoch(train) [209][100/293] lr: 5.000000e-06 eta: 0:05:25 time: 0.786612 data_time: 0.104247 memory: 21676 loss_kpt: 0.000488 acc_pose: 0.873755 loss: 0.000488 2022/09/14 00:34:56 - mmengine - INFO - Epoch(train) [209][150/293] lr: 5.000000e-06 eta: 0:04:51 time: 0.780921 data_time: 0.100164 memory: 21676 loss_kpt: 0.000487 acc_pose: 0.909815 loss: 0.000487 2022/09/14 00:35:35 - mmengine - INFO - Epoch(train) [209][200/293] lr: 5.000000e-06 eta: 0:04:18 time: 0.781498 data_time: 0.106775 memory: 21676 loss_kpt: 0.000487 acc_pose: 0.830668 loss: 0.000487 2022/09/14 00:36:14 - mmengine - INFO - Epoch(train) [209][250/293] lr: 5.000000e-06 eta: 0:03:45 time: 0.781765 data_time: 0.109551 memory: 21676 loss_kpt: 0.000500 acc_pose: 0.866278 loss: 0.000500 2022/09/14 00:36:47 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/14 00:36:47 - mmengine - INFO - Saving checkpoint at 209 epochs 2022/09/14 00:37:31 - mmengine - INFO - Epoch(train) [210][50/293] lr: 5.000000e-06 eta: 0:02:42 time: 0.794658 data_time: 0.115124 memory: 21676 loss_kpt: 0.000495 acc_pose: 0.848074 loss: 0.000495 2022/09/14 00:38:11 - mmengine - INFO - Epoch(train) [210][100/293] lr: 5.000000e-06 eta: 0:02:09 time: 0.791988 data_time: 0.105462 memory: 21676 loss_kpt: 0.000508 acc_pose: 0.823348 loss: 0.000508 2022/09/14 00:38:51 - mmengine - INFO - Epoch(train) [210][150/293] lr: 5.000000e-06 eta: 0:01:35 time: 0.789901 data_time: 0.103120 memory: 21676 loss_kpt: 0.000486 acc_pose: 0.865706 loss: 0.000486 2022/09/14 00:39:29 - mmengine - INFO - Epoch(train) [210][200/293] lr: 5.000000e-06 eta: 0:01:02 time: 0.771639 data_time: 0.099875 memory: 21676 loss_kpt: 0.000489 acc_pose: 0.886235 loss: 0.000489 2022/09/14 00:40:09 - mmengine - INFO - Epoch(train) [210][250/293] lr: 5.000000e-06 eta: 0:00:28 time: 0.789798 data_time: 0.105224 memory: 21676 loss_kpt: 0.000473 acc_pose: 0.868612 loss: 0.000473 2022/09/14 00:40:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-384x288_20220913_102042 2022/09/14 00:40:42 - mmengine - INFO - Saving checkpoint at 210 epochs 2022/09/14 00:40:56 - mmengine - INFO - Epoch(val) [210][50/407] eta: 0:01:05 time: 0.183016 data_time: 0.014163 memory: 21676 2022/09/14 00:41:05 - mmengine - INFO - Epoch(val) [210][100/407] eta: 0:00:53 time: 0.175606 data_time: 0.008841 memory: 1375 2022/09/14 00:41:14 - mmengine - INFO - Epoch(val) [210][150/407] eta: 0:00:46 time: 0.179187 data_time: 0.008647 memory: 1375 2022/09/14 00:41:23 - mmengine - INFO - Epoch(val) [210][200/407] eta: 0:00:36 time: 0.177301 data_time: 0.009167 memory: 1375 2022/09/14 00:41:31 - mmengine - INFO - Epoch(val) [210][250/407] eta: 0:00:27 time: 0.176300 data_time: 0.009318 memory: 1375 2022/09/14 00:41:40 - mmengine - INFO - Epoch(val) [210][300/407] eta: 0:00:18 time: 0.176920 data_time: 0.008463 memory: 1375 2022/09/14 00:41:49 - mmengine - INFO - Epoch(val) [210][350/407] eta: 0:00:10 time: 0.177643 data_time: 0.008920 memory: 1375 2022/09/14 00:41:58 - mmengine - INFO - Epoch(val) [210][400/407] eta: 0:00:01 time: 0.175589 data_time: 0.008348 memory: 1375 2022/09/14 00:42:34 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 00:42:48 - mmengine - INFO - Epoch(val) [210][407/407] coco/AP: 0.767942 coco/AP .5: 0.908703 coco/AP .75: 0.831838 coco/AP (M): 0.728207 coco/AP (L): 0.839110 coco/AR: 0.815334 coco/AR .5: 0.944742 coco/AR .75: 0.872324 coco/AR (M): 0.771319 coco/AR (L): 0.879524 2022/09/14 00:42:48 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220913/udp_w32_384_v1/best_coco/AP_epoch_190.pth is removed 2022/09/14 00:42:51 - mmengine - INFO - The best checkpoint with 0.7679 coco/AP at 210 epoch is saved to best_coco/AP_epoch_210.pth.