2022/09/14 15:18:40 - 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: 1467232507 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 ------------------------------------------------------------ 2022/09/14 15:18:42 - 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=(192, 256), heatmap_size=(48, 64), sigma=2, heatmap_type='combined') 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=51, deconv_out_channels=None, loss=dict(type='CombinedTargetMSELoss', use_target_weight=True), decoder=dict( type='UDPHeatmap', input_size=(192, 256), heatmap_size=(48, 64), sigma=2, heatmap_type='combined')), test_cfg=dict( flip_test=True, flip_mode='udp_combined', shift_heatmap=False)) dataset_type = 'CocoDataset' data_mode = 'topdown' data_root = 'data/coco/' train_pipeline = [ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='RandomFlip', direction='horizontal'), dict(type='RandomHalfBody'), dict(type='RandomBBoxTransform'), dict(type='TopdownAffine', input_size=(192, 256), use_udp=True), dict( type='GenerateTarget', target_type='heatmap', encoder=dict( type='UDPHeatmap', input_size=(192, 256), heatmap_size=(48, 64), sigma=2, heatmap_type='combined')), dict(type='PackPoseInputs') ] test_pipeline = [ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='TopdownAffine', input_size=(192, 256), 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=(192, 256), use_udp=True), dict( type='GenerateTarget', target_type='heatmap', encoder=dict( type='UDPHeatmap', input_size=(192, 256), heatmap_size=(48, 64), sigma=2, heatmap_type='combined')), dict(type='PackPoseInputs') ])) val_dataloader = dict( batch_size=32, num_workers=2, persistent_workers=True, drop_last=False, sampler=dict(type='DefaultSampler', shuffle=False, round_up=False), dataset=dict( type='CocoDataset', data_root='data/coco/', data_mode='topdown', ann_file='annotations/person_keypoints_val2017.json', bbox_file= 'data/coco/person_detection_results/COCO_val2017_detections_AP_H_56_person.json', data_prefix=dict(img='val2017/'), test_mode=True, pipeline=[ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='TopdownAffine', input_size=(192, 256), 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=(192, 256), 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/20220914/udp_regress/' 2022/09/14 15:19:31 - 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. 2022/09/14 15:19:31 - 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. 2022/09/14 15:19:31 - 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. 2022/09/14 15:19:31 - 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. 2022/09/14 15:19:31 - 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. 2022/09/14 15:19:31 - 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. 2022/09/14 15:19:31 - 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. 2022/09/14 15:19:31 - 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. 2022/09/14 15:19:35 - 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. 2022/09/14 15:19:37 - 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. 2022/09/14 15:19:39 - 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. 2022/09/14 15:19:39 - 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([51, 32, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 head.final_layer.bias - torch.Size([51]): NormalInit: mean=0, std=0.001, bias=0 2022/09/14 15:19:54 - mmengine - INFO - Checkpoints will be saved to /mnt/lustre/liqikai/work_dirs/20220914/udp_regress by HardDiskBackend. 2022/09/14 15:22:24 - mmengine - INFO - Epoch(train) [1][50/293] lr: 4.954910e-05 eta: 2 days, 3:21:37 time: 3.007445 data_time: 1.052668 memory: 9974 loss_kpt: 0.005114 loss: 0.005114 2022/09/14 15:24:30 - mmengine - INFO - Epoch(train) [1][100/293] lr: 9.959920e-05 eta: 1 day, 23:01:46 time: 2.504725 data_time: 0.079949 memory: 9974 loss_kpt: 0.004700 loss: 0.004700 2022/09/14 15:26:45 - mmengine - INFO - Epoch(train) [1][150/293] lr: 1.496493e-04 eta: 1 day, 22:42:18 time: 2.705767 data_time: 0.084354 memory: 9974 loss_kpt: 0.004078 loss: 0.004078 2022/09/14 15:28:46 - mmengine - INFO - Epoch(train) [1][200/293] lr: 1.996994e-04 eta: 1 day, 21:21:26 time: 2.431742 data_time: 0.082072 memory: 9974 loss_kpt: 0.003616 loss: 0.003616 2022/09/14 15:30:32 - mmengine - INFO - Epoch(train) [1][250/293] lr: 2.497495e-04 eta: 1 day, 19:27:01 time: 2.113138 data_time: 0.079514 memory: 9974 loss_kpt: 0.003296 loss: 0.003296 2022/09/14 15:32:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 15:32:02 - mmengine - INFO - Saving checkpoint at 1 epochs 2022/09/14 15:34:08 - mmengine - INFO - Epoch(train) [2][50/293] lr: 3.428427e-04 eta: 1 day, 13:40:22 time: 2.442538 data_time: 0.242651 memory: 9974 loss_kpt: 0.003073 loss: 0.003073 2022/09/14 15:36:22 - mmengine - INFO - Epoch(train) [2][100/293] lr: 3.928928e-04 eta: 1 day, 14:39:23 time: 2.686054 data_time: 0.103269 memory: 9974 loss_kpt: 0.002923 loss: 0.002923 2022/09/14 15:38:28 - mmengine - INFO - Epoch(train) [2][150/293] lr: 4.429429e-04 eta: 1 day, 15:05:36 time: 2.520902 data_time: 0.893740 memory: 9974 loss_kpt: 0.002871 loss: 0.002871 2022/09/14 15:40:16 - mmengine - INFO - Epoch(train) [2][200/293] lr: 4.929930e-04 eta: 1 day, 14:48:39 time: 2.158088 data_time: 0.219849 memory: 9974 loss_kpt: 0.002788 loss: 0.002788 2022/09/14 15:41:52 - mmengine - INFO - Epoch(train) [2][250/293] lr: 5.000000e-04 eta: 1 day, 14:11:29 time: 1.912538 data_time: 0.397550 memory: 9974 loss_kpt: 0.002731 loss: 0.002731 2022/09/14 15:43:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 15:43:43 - mmengine - INFO - Saving checkpoint at 2 epochs 2022/09/14 15:46:24 - mmengine - INFO - Epoch(train) [3][50/293] lr: 5.000000e-04 eta: 1 day, 12:45:56 time: 3.164691 data_time: 0.169803 memory: 9974 loss_kpt: 0.002682 loss: 0.002682 2022/09/14 15:48:51 - mmengine - INFO - Epoch(train) [3][100/293] lr: 5.000000e-04 eta: 1 day, 13:40:56 time: 2.942134 data_time: 0.675300 memory: 9974 loss_kpt: 0.002606 loss: 0.002606 2022/09/14 15:51:41 - mmengine - INFO - Epoch(train) [3][150/293] lr: 5.000000e-04 eta: 1 day, 14:59:30 time: 3.398019 data_time: 0.534039 memory: 9974 loss_kpt: 0.002580 loss: 0.002580 2022/09/14 15:54:14 - mmengine - INFO - Epoch(train) [3][200/293] lr: 5.000000e-04 eta: 1 day, 15:45:22 time: 3.051025 data_time: 0.392089 memory: 9974 loss_kpt: 0.002522 loss: 0.002522 2022/09/14 15:56:53 - mmengine - INFO - Epoch(train) [3][250/293] lr: 5.000000e-04 eta: 1 day, 16:33:17 time: 3.180743 data_time: 0.387485 memory: 9974 loss_kpt: 0.002494 loss: 0.002494 2022/09/14 15:58:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 15:58:46 - mmengine - INFO - Saving checkpoint at 3 epochs 2022/09/14 16:00:54 - mmengine - INFO - Epoch(train) [4][50/293] lr: 5.000000e-04 eta: 1 day, 14:41:43 time: 2.490371 data_time: 0.135394 memory: 9974 loss_kpt: 0.002497 loss: 0.002497 2022/09/14 16:02:33 - mmengine - INFO - Epoch(train) [4][100/293] lr: 5.000000e-04 eta: 1 day, 14:23:54 time: 1.989985 data_time: 0.071270 memory: 9974 loss_kpt: 0.002425 loss: 0.002425 2022/09/14 16:03:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 16:04:36 - mmengine - INFO - Epoch(train) [4][150/293] lr: 5.000000e-04 eta: 1 day, 14:30:00 time: 2.446391 data_time: 0.127460 memory: 9974 loss_kpt: 0.002421 loss: 0.002421 2022/09/14 16:05:43 - mmengine - INFO - Epoch(train) [4][200/293] lr: 5.000000e-04 eta: 1 day, 13:44:18 time: 1.353078 data_time: 0.186388 memory: 9974 loss_kpt: 0.002401 loss: 0.002401 2022/09/14 16:07:19 - mmengine - INFO - Epoch(train) [4][250/293] lr: 5.000000e-04 eta: 1 day, 13:27:47 time: 1.918846 data_time: 0.250340 memory: 9974 loss_kpt: 0.002395 loss: 0.002395 2022/09/14 16:08:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 16:08:51 - mmengine - INFO - Saving checkpoint at 4 epochs 2022/09/14 16:12:52 - mmengine - INFO - Epoch(train) [5][50/293] lr: 5.000000e-04 eta: 1 day, 13:49:43 time: 4.770720 data_time: 0.857468 memory: 9974 loss_kpt: 0.002344 loss: 0.002344 2022/09/14 16:18:16 - mmengine - INFO - Epoch(train) [5][100/293] lr: 5.000000e-04 eta: 1 day, 16:34:04 time: 6.468916 data_time: 0.960891 memory: 9974 loss_kpt: 0.002331 loss: 0.002331 2022/09/14 16:19:59 - mmengine - INFO - Epoch(train) [5][150/293] lr: 5.000000e-04 eta: 1 day, 16:18:21 time: 2.062659 data_time: 1.020327 memory: 9974 loss_kpt: 0.002329 loss: 0.002329 2022/09/14 16:21:33 - mmengine - INFO - Epoch(train) [5][200/293] lr: 5.000000e-04 eta: 1 day, 15:57:28 time: 1.893592 data_time: 0.097284 memory: 9974 loss_kpt: 0.002319 loss: 0.002319 2022/09/14 16:23:20 - mmengine - INFO - Epoch(train) [5][250/293] lr: 5.000000e-04 eta: 1 day, 15:46:30 time: 2.136084 data_time: 0.086534 memory: 9974 loss_kpt: 0.002336 loss: 0.002336 2022/09/14 16:25:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 16:25:04 - mmengine - INFO - Saving checkpoint at 5 epochs 2022/09/14 16:27:07 - mmengine - INFO - Epoch(train) [6][50/293] lr: 5.000000e-04 eta: 1 day, 14:35:39 time: 2.396503 data_time: 0.292214 memory: 9974 loss_kpt: 0.002328 loss: 0.002328 2022/09/14 16:29:09 - mmengine - INFO - Epoch(train) [6][100/293] lr: 5.000000e-04 eta: 1 day, 14:37:57 time: 2.447850 data_time: 0.091957 memory: 9974 loss_kpt: 0.002272 loss: 0.002272 2022/09/14 16:30:51 - mmengine - INFO - Epoch(train) [6][150/293] lr: 5.000000e-04 eta: 1 day, 14:27:05 time: 2.030361 data_time: 0.084539 memory: 9974 loss_kpt: 0.002263 loss: 0.002263 2022/09/14 16:32:39 - mmengine - INFO - Epoch(train) [6][200/293] lr: 5.000000e-04 eta: 1 day, 14:20:52 time: 2.166752 data_time: 1.136347 memory: 9974 loss_kpt: 0.002259 loss: 0.002259 2022/09/14 16:34:33 - mmengine - INFO - Epoch(train) [6][250/293] lr: 5.000000e-04 eta: 1 day, 14:18:01 time: 2.274502 data_time: 1.394829 memory: 9974 loss_kpt: 0.002277 loss: 0.002277 2022/09/14 16:35:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 16:35:59 - mmengine - INFO - Saving checkpoint at 6 epochs 2022/09/14 16:37:36 - mmengine - INFO - Epoch(train) [7][50/293] lr: 5.000000e-04 eta: 1 day, 13:07:39 time: 1.860742 data_time: 0.687356 memory: 9974 loss_kpt: 0.002238 loss: 0.002238 2022/09/14 16:39:25 - mmengine - INFO - Epoch(train) [7][100/293] lr: 5.000000e-04 eta: 1 day, 13:04:27 time: 2.188239 data_time: 0.167782 memory: 9974 loss_kpt: 0.002211 loss: 0.002211 2022/09/14 16:41:11 - mmengine - INFO - Epoch(train) [7][150/293] lr: 5.000000e-04 eta: 1 day, 12:59:30 time: 2.118089 data_time: 0.244961 memory: 9974 loss_kpt: 0.002262 loss: 0.002262 2022/09/14 16:42:55 - mmengine - INFO - Epoch(train) [7][200/293] lr: 5.000000e-04 eta: 1 day, 12:53:53 time: 2.085479 data_time: 0.233683 memory: 9974 loss_kpt: 0.002201 loss: 0.002201 2022/09/14 16:44:21 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 16:44:40 - mmengine - INFO - Epoch(train) [7][250/293] lr: 5.000000e-04 eta: 1 day, 12:48:46 time: 2.098124 data_time: 0.839461 memory: 9974 loss_kpt: 0.002188 loss: 0.002188 2022/09/14 16:46:16 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 16:46:16 - mmengine - INFO - Saving checkpoint at 7 epochs 2022/09/14 16:48:12 - mmengine - INFO - Epoch(train) [8][50/293] lr: 5.000000e-04 eta: 1 day, 12:00:56 time: 2.258060 data_time: 0.738949 memory: 9974 loss_kpt: 0.002195 loss: 0.002195 2022/09/14 16:49:50 - mmengine - INFO - Epoch(train) [8][100/293] lr: 5.000000e-04 eta: 1 day, 11:54:04 time: 1.962348 data_time: 0.300162 memory: 9974 loss_kpt: 0.002184 loss: 0.002184 2022/09/14 16:51:19 - mmengine - INFO - Epoch(train) [8][150/293] lr: 5.000000e-04 eta: 1 day, 11:43:35 time: 1.791094 data_time: 0.342209 memory: 9974 loss_kpt: 0.002184 loss: 0.002184 2022/09/14 16:53:10 - mmengine - INFO - Epoch(train) [8][200/293] lr: 5.000000e-04 eta: 1 day, 11:42:49 time: 2.214977 data_time: 0.172092 memory: 9974 loss_kpt: 0.002196 loss: 0.002196 2022/09/14 16:54:51 - mmengine - INFO - Epoch(train) [8][250/293] lr: 5.000000e-04 eta: 1 day, 11:38:00 time: 2.028359 data_time: 0.844960 memory: 9974 loss_kpt: 0.002199 loss: 0.002199 2022/09/14 16:56:09 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 16:56:09 - mmengine - INFO - Saving checkpoint at 8 epochs 2022/09/14 16:57:45 - mmengine - INFO - Epoch(train) [9][50/293] lr: 5.000000e-04 eta: 1 day, 10:49:45 time: 1.848085 data_time: 0.912616 memory: 9974 loss_kpt: 0.002115 loss: 0.002115 2022/09/14 16:59:16 - mmengine - INFO - Epoch(train) [9][100/293] lr: 5.000000e-04 eta: 1 day, 10:42:08 time: 1.829278 data_time: 0.717226 memory: 9974 loss_kpt: 0.002119 loss: 0.002119 2022/09/14 17:00:52 - mmengine - INFO - Epoch(train) [9][150/293] lr: 5.000000e-04 eta: 1 day, 10:36:13 time: 1.904204 data_time: 0.482909 memory: 9974 loss_kpt: 0.002174 loss: 0.002174 2022/09/14 17:02:49 - mmengine - INFO - Epoch(train) [9][200/293] lr: 5.000000e-04 eta: 1 day, 10:39:14 time: 2.357553 data_time: 0.787110 memory: 9974 loss_kpt: 0.002130 loss: 0.002130 2022/09/14 17:04:44 - mmengine - INFO - Epoch(train) [9][250/293] lr: 5.000000e-04 eta: 1 day, 10:40:46 time: 2.289087 data_time: 0.166057 memory: 9974 loss_kpt: 0.002124 loss: 0.002124 2022/09/14 17:06:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 17:06:08 - mmengine - INFO - Saving checkpoint at 9 epochs 2022/09/14 17:08:01 - mmengine - INFO - Epoch(train) [10][50/293] lr: 5.000000e-04 eta: 1 day, 10:03:35 time: 2.082305 data_time: 0.592534 memory: 9974 loss_kpt: 0.002118 loss: 0.002118 2022/09/14 17:09:46 - mmengine - INFO - Epoch(train) [10][100/293] lr: 5.000000e-04 eta: 1 day, 10:01:59 time: 2.091099 data_time: 0.558060 memory: 9974 loss_kpt: 0.002158 loss: 0.002158 2022/09/14 17:11:28 - mmengine - INFO - Epoch(train) [10][150/293] lr: 5.000000e-04 eta: 1 day, 9:59:39 time: 2.050410 data_time: 0.291682 memory: 9974 loss_kpt: 0.002120 loss: 0.002120 2022/09/14 17:13:28 - mmengine - INFO - Epoch(train) [10][200/293] lr: 5.000000e-04 eta: 1 day, 10:03:24 time: 2.400843 data_time: 0.191637 memory: 9974 loss_kpt: 0.002115 loss: 0.002115 2022/09/14 17:15:24 - mmengine - INFO - Epoch(train) [10][250/293] lr: 5.000000e-04 eta: 1 day, 10:05:30 time: 2.316360 data_time: 0.183527 memory: 9974 loss_kpt: 0.002108 loss: 0.002108 2022/09/14 17:17:23 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 17:17:23 - mmengine - INFO - Saving checkpoint at 10 epochs 2022/09/14 17:18:46 - mmengine - INFO - Epoch(val) [10][50/407] eta: 0:08:37 time: 1.448845 data_time: 0.784054 memory: 9974 2022/09/14 17:20:35 - mmengine - INFO - Epoch(val) [10][100/407] eta: 0:11:08 time: 2.178833 data_time: 0.439981 memory: 918 2022/09/14 17:23:44 - mmengine - INFO - Epoch(val) [10][150/407] eta: 0:16:12 time: 3.784914 data_time: 0.261793 memory: 918 2022/09/14 17:26:33 - mmengine - INFO - Epoch(val) [10][200/407] eta: 0:11:38 time: 3.372369 data_time: 0.217022 memory: 918 2022/09/14 17:31:58 - mmengine - INFO - Epoch(val) [10][250/407] eta: 0:16:59 time: 6.493941 data_time: 0.400052 memory: 918 2022/09/14 17:38:03 - mmengine - INFO - Epoch(val) [10][300/407] eta: 0:13:00 time: 7.291084 data_time: 0.424455 memory: 918 2022/09/14 17:43:57 - mmengine - INFO - Epoch(val) [10][350/407] eta: 0:06:43 time: 7.080788 data_time: 0.410229 memory: 918 2022/09/14 17:50:17 - mmengine - INFO - Epoch(val) [10][400/407] eta: 0:00:53 time: 7.602302 data_time: 0.453538 memory: 918 2022/09/14 18:11:26 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 18:18:28 - mmengine - INFO - Epoch(val) [10][407/407] coco/AP: 0.659920 coco/AP .5: 0.869591 coco/AP .75: 0.733718 coco/AP (M): 0.623774 coco/AP (L): 0.723610 coco/AR: 0.725142 coco/AR .5: 0.910107 coco/AR .75: 0.794081 coco/AR (M): 0.681508 coco/AR (L): 0.786994 2022/09/14 18:19:41 - mmengine - INFO - The best checkpoint with 0.6599 coco/AP at 10 epoch is saved to best_coco/AP_epoch_10.pth. 2022/09/14 18:35:13 - mmengine - INFO - Epoch(train) [11][50/293] lr: 5.000000e-04 eta: 1 day, 14:03:30 time: 18.626185 data_time: 2.624472 memory: 9974 loss_kpt: 0.002095 loss: 0.002095 2022/09/14 18:40:47 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 18:49:52 - mmengine - INFO - Epoch(train) [11][100/293] lr: 5.000000e-04 eta: 1 day, 18:06:42 time: 17.577793 data_time: 1.831125 memory: 9974 loss_kpt: 0.002067 loss: 0.002067 2022/09/14 19:04:59 - mmengine - INFO - Epoch(train) [11][150/293] lr: 5.000000e-04 eta: 1 day, 22:10:30 time: 18.144349 data_time: 2.173037 memory: 9974 loss_kpt: 0.002086 loss: 0.002086 2022/09/14 19:18:39 - mmengine - INFO - Epoch(train) [11][200/293] lr: 5.000000e-04 eta: 2 days, 1:38:48 time: 16.393257 data_time: 1.918007 memory: 9974 loss_kpt: 0.002100 loss: 0.002100 2022/09/14 19:27:35 - mmengine - INFO - Epoch(train) [11][250/293] lr: 5.000000e-04 eta: 2 days, 3:33:30 time: 10.727729 data_time: 1.266659 memory: 9974 loss_kpt: 0.002084 loss: 0.002084 2022/09/14 19:33:25 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 19:33:25 - mmengine - INFO - Saving checkpoint at 11 epochs 2022/09/14 19:37:38 - mmengine - INFO - Epoch(train) [12][50/293] lr: 5.000000e-04 eta: 2 days, 3:02:56 time: 4.188221 data_time: 0.779402 memory: 9974 loss_kpt: 0.002071 loss: 0.002071 2022/09/14 19:40:07 - mmengine - INFO - Epoch(train) [12][100/293] lr: 5.000000e-04 eta: 2 days, 2:57:52 time: 2.987619 data_time: 0.817084 memory: 9974 loss_kpt: 0.002061 loss: 0.002061 2022/09/14 19:41:52 - mmengine - INFO - Epoch(train) [12][150/293] lr: 5.000000e-04 eta: 2 days, 2:40:14 time: 2.108321 data_time: 0.265652 memory: 9974 loss_kpt: 0.002159 loss: 0.002159 2022/09/14 19:43:45 - mmengine - INFO - Epoch(train) [12][200/293] lr: 5.000000e-04 eta: 2 days, 2:25:13 time: 2.260068 data_time: 0.525688 memory: 9974 loss_kpt: 0.002088 loss: 0.002088 2022/09/14 19:45:16 - mmengine - INFO - Epoch(train) [12][250/293] lr: 5.000000e-04 eta: 2 days, 2:04:23 time: 1.815077 data_time: 0.585899 memory: 9974 loss_kpt: 0.002058 loss: 0.002058 2022/09/14 19:47:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 19:47:00 - mmengine - INFO - Saving checkpoint at 12 epochs 2022/09/14 19:48:42 - mmengine - INFO - Epoch(train) [13][50/293] lr: 5.000000e-04 eta: 2 days, 1:08:13 time: 1.983259 data_time: 0.304284 memory: 9974 loss_kpt: 0.002063 loss: 0.002063 2022/09/14 19:50:34 - mmengine - INFO - Epoch(train) [13][100/293] lr: 5.000000e-04 eta: 2 days, 0:54:53 time: 2.244045 data_time: 0.198910 memory: 9974 loss_kpt: 0.002095 loss: 0.002095 2022/09/14 19:52:51 - mmengine - INFO - Epoch(train) [13][150/293] lr: 5.000000e-04 eta: 2 days, 0:48:24 time: 2.740278 data_time: 0.101488 memory: 9974 loss_kpt: 0.002081 loss: 0.002081 2022/09/14 19:54:42 - mmengine - INFO - Epoch(train) [13][200/293] lr: 5.000000e-04 eta: 2 days, 0:35:05 time: 2.203992 data_time: 0.382102 memory: 9974 loss_kpt: 0.002051 loss: 0.002051 2022/09/14 19:56:24 - mmengine - INFO - Epoch(train) [13][250/293] lr: 5.000000e-04 eta: 2 days, 0:19:57 time: 2.039403 data_time: 0.819744 memory: 9974 loss_kpt: 0.002062 loss: 0.002062 2022/09/14 19:58:14 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 19:58:14 - mmengine - INFO - Saving checkpoint at 13 epochs 2022/09/14 19:59:51 - mmengine - INFO - Epoch(train) [14][50/293] lr: 5.000000e-04 eta: 1 day, 23:28:48 time: 1.870248 data_time: 0.937346 memory: 9974 loss_kpt: 0.002024 loss: 0.002024 2022/09/14 20:01:39 - mmengine - INFO - Epoch(train) [14][100/293] lr: 5.000000e-04 eta: 1 day, 23:16:26 time: 2.157173 data_time: 0.436513 memory: 9974 loss_kpt: 0.002028 loss: 0.002028 2022/09/14 20:03:23 - mmengine - INFO - Epoch(train) [14][150/293] lr: 5.000000e-04 eta: 1 day, 23:03:33 time: 2.094612 data_time: 0.123497 memory: 9974 loss_kpt: 0.002036 loss: 0.002036 2022/09/14 20:05:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 20:05:34 - mmengine - INFO - Epoch(train) [14][200/293] lr: 5.000000e-04 eta: 1 day, 22:57:10 time: 2.612961 data_time: 0.091655 memory: 9974 loss_kpt: 0.002048 loss: 0.002048 2022/09/14 20:07:15 - mmengine - INFO - Epoch(train) [14][250/293] lr: 5.000000e-04 eta: 1 day, 22:43:57 time: 2.026074 data_time: 0.088973 memory: 9974 loss_kpt: 0.002047 loss: 0.002047 2022/09/14 20:08:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 20:08:42 - mmengine - INFO - Saving checkpoint at 14 epochs 2022/09/14 20:10:38 - mmengine - INFO - Epoch(train) [15][50/293] lr: 5.000000e-04 eta: 1 day, 22:02:45 time: 2.261758 data_time: 0.651299 memory: 9974 loss_kpt: 0.002007 loss: 0.002007 2022/09/14 20:12:30 - mmengine - INFO - Epoch(train) [15][100/293] lr: 5.000000e-04 eta: 1 day, 21:52:54 time: 2.234979 data_time: 0.088036 memory: 9974 loss_kpt: 0.002022 loss: 0.002022 2022/09/14 20:14:02 - mmengine - INFO - Epoch(train) [15][150/293] lr: 5.000000e-04 eta: 1 day, 21:38:56 time: 1.849861 data_time: 0.110558 memory: 9974 loss_kpt: 0.002029 loss: 0.002029 2022/09/14 20:16:11 - mmengine - INFO - Epoch(train) [15][200/293] lr: 5.000000e-04 eta: 1 day, 21:33:22 time: 2.583754 data_time: 0.100038 memory: 9974 loss_kpt: 0.002016 loss: 0.002016 2022/09/14 20:17:47 - mmengine - INFO - Epoch(train) [15][250/293] lr: 5.000000e-04 eta: 1 day, 21:20:26 time: 1.901755 data_time: 0.094785 memory: 9974 loss_kpt: 0.002042 loss: 0.002042 2022/09/14 20:19:16 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 20:19:16 - mmengine - INFO - Saving checkpoint at 15 epochs 2022/09/14 20:21:02 - mmengine - INFO - Epoch(train) [16][50/293] lr: 5.000000e-04 eta: 1 day, 20:41:05 time: 2.045800 data_time: 0.930853 memory: 9974 loss_kpt: 0.002031 loss: 0.002031 2022/09/14 20:22:29 - mmengine - INFO - Epoch(train) [16][100/293] lr: 5.000000e-04 eta: 1 day, 20:27:22 time: 1.742895 data_time: 0.826254 memory: 9974 loss_kpt: 0.002036 loss: 0.002036 2022/09/14 20:24:05 - mmengine - INFO - Epoch(train) [16][150/293] lr: 5.000000e-04 eta: 1 day, 20:15:45 time: 1.919449 data_time: 0.561628 memory: 9974 loss_kpt: 0.002001 loss: 0.002001 2022/09/14 20:26:23 - mmengine - INFO - Epoch(train) [16][200/293] lr: 5.000000e-04 eta: 1 day, 20:13:06 time: 2.765020 data_time: 0.097128 memory: 9974 loss_kpt: 0.001979 loss: 0.001979 2022/09/14 20:27:52 - mmengine - INFO - Epoch(train) [16][250/293] lr: 5.000000e-04 eta: 1 day, 20:00:24 time: 1.779241 data_time: 0.098794 memory: 9974 loss_kpt: 0.002015 loss: 0.002015 2022/09/14 20:28:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 20:28:56 - mmengine - INFO - Saving checkpoint at 16 epochs 2022/09/14 20:30:39 - mmengine - INFO - Epoch(train) [17][50/293] lr: 5.000000e-04 eta: 1 day, 19:24:13 time: 1.989550 data_time: 0.491218 memory: 9974 loss_kpt: 0.001965 loss: 0.001965 2022/09/14 20:32:15 - mmengine - INFO - Epoch(train) [17][100/293] lr: 5.000000e-04 eta: 1 day, 19:13:45 time: 1.923395 data_time: 0.202565 memory: 9974 loss_kpt: 0.002002 loss: 0.002002 2022/09/14 20:34:00 - mmengine - INFO - Epoch(train) [17][150/293] lr: 5.000000e-04 eta: 1 day, 19:05:11 time: 2.099356 data_time: 0.110839 memory: 9974 loss_kpt: 0.001993 loss: 0.001993 2022/09/14 20:35:43 - mmengine - INFO - Epoch(train) [17][200/293] lr: 5.000000e-04 eta: 1 day, 18:56:29 time: 2.071978 data_time: 0.696294 memory: 9974 loss_kpt: 0.002017 loss: 0.002017 2022/09/14 20:37:18 - mmengine - INFO - Epoch(train) [17][250/293] lr: 5.000000e-04 eta: 1 day, 18:46:18 time: 1.901268 data_time: 0.530458 memory: 9974 loss_kpt: 0.001987 loss: 0.001987 2022/09/14 20:39:10 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 20:39:10 - mmengine - INFO - Saving checkpoint at 17 epochs 2022/09/14 20:39:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 20:40:53 - mmengine - INFO - Epoch(train) [18][50/293] lr: 5.000000e-04 eta: 1 day, 18:13:27 time: 2.001394 data_time: 0.526527 memory: 9974 loss_kpt: 0.001996 loss: 0.001996 2022/09/14 20:42:41 - mmengine - INFO - Epoch(train) [18][100/293] lr: 5.000000e-04 eta: 1 day, 18:06:18 time: 2.159753 data_time: 0.216902 memory: 9974 loss_kpt: 0.001960 loss: 0.001960 2022/09/14 20:44:28 - mmengine - INFO - Epoch(train) [18][150/293] lr: 5.000000e-04 eta: 1 day, 17:58:57 time: 2.126724 data_time: 0.210319 memory: 9974 loss_kpt: 0.001998 loss: 0.001998 2022/09/14 20:46:21 - mmengine - INFO - Epoch(train) [18][200/293] lr: 5.000000e-04 eta: 1 day, 17:52:55 time: 2.261452 data_time: 0.206630 memory: 9974 loss_kpt: 0.001968 loss: 0.001968 2022/09/14 20:47:58 - mmengine - INFO - Epoch(train) [18][250/293] lr: 5.000000e-04 eta: 1 day, 17:44:13 time: 1.954739 data_time: 0.112321 memory: 9974 loss_kpt: 0.002008 loss: 0.002008 2022/09/14 20:49:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 20:49:27 - mmengine - INFO - Saving checkpoint at 18 epochs 2022/09/14 20:51:11 - mmengine - INFO - Epoch(train) [19][50/293] lr: 5.000000e-04 eta: 1 day, 17:14:21 time: 2.038087 data_time: 0.630193 memory: 9974 loss_kpt: 0.001937 loss: 0.001937 2022/09/14 20:52:53 - mmengine - INFO - Epoch(train) [19][100/293] lr: 5.000000e-04 eta: 1 day, 17:06:48 time: 2.028131 data_time: 0.100819 memory: 9974 loss_kpt: 0.002012 loss: 0.002012 2022/09/14 20:54:28 - mmengine - INFO - Epoch(train) [19][150/293] lr: 5.000000e-04 eta: 1 day, 16:58:16 time: 1.899866 data_time: 0.086827 memory: 9974 loss_kpt: 0.001990 loss: 0.001990 2022/09/14 20:56:39 - mmengine - INFO - Epoch(train) [19][200/293] lr: 5.000000e-04 eta: 1 day, 16:56:04 time: 2.627182 data_time: 1.950775 memory: 9974 loss_kpt: 0.001991 loss: 0.001991 2022/09/14 20:58:09 - mmengine - INFO - Epoch(train) [19][250/293] lr: 5.000000e-04 eta: 1 day, 16:46:52 time: 1.800385 data_time: 0.984874 memory: 9974 loss_kpt: 0.001965 loss: 0.001965 2022/09/14 20:59:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 20:59:51 - mmengine - INFO - Saving checkpoint at 19 epochs 2022/09/14 21:01:34 - mmengine - INFO - Epoch(train) [20][50/293] lr: 5.000000e-04 eta: 1 day, 16:18:45 time: 1.976536 data_time: 0.780665 memory: 9974 loss_kpt: 0.001932 loss: 0.001932 2022/09/14 21:02:59 - mmengine - INFO - Epoch(train) [20][100/293] lr: 5.000000e-04 eta: 1 day, 16:09:21 time: 1.713320 data_time: 0.187970 memory: 9974 loss_kpt: 0.001961 loss: 0.001961 2022/09/14 21:04:29 - mmengine - INFO - Epoch(train) [20][150/293] lr: 5.000000e-04 eta: 1 day, 16:00:48 time: 1.801585 data_time: 0.118958 memory: 9974 loss_kpt: 0.001967 loss: 0.001967 2022/09/14 21:06:02 - mmengine - INFO - Epoch(train) [20][200/293] lr: 5.000000e-04 eta: 1 day, 15:52:49 time: 1.857246 data_time: 0.116634 memory: 9974 loss_kpt: 0.001944 loss: 0.001944 2022/09/14 21:07:51 - mmengine - INFO - Epoch(train) [20][250/293] lr: 5.000000e-04 eta: 1 day, 15:47:24 time: 2.164853 data_time: 0.163556 memory: 9974 loss_kpt: 0.001954 loss: 0.001954 2022/09/14 21:09:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 21:09:08 - mmengine - INFO - Saving checkpoint at 20 epochs 2022/09/14 21:09:57 - mmengine - INFO - Epoch(val) [20][50/407] eta: 0:05:31 time: 0.928343 data_time: 0.775996 memory: 9974 2022/09/14 21:10:56 - mmengine - INFO - Epoch(val) [20][100/407] eta: 0:05:57 time: 1.165178 data_time: 1.018566 memory: 918 2022/09/14 21:11:39 - mmengine - INFO - Epoch(val) [20][150/407] eta: 0:03:43 time: 0.870318 data_time: 0.724283 memory: 918 2022/09/14 21:12:34 - mmengine - INFO - Epoch(val) [20][200/407] eta: 0:03:45 time: 1.091503 data_time: 0.940650 memory: 918 2022/09/14 21:13:08 - mmengine - INFO - Epoch(val) [20][250/407] eta: 0:01:49 time: 0.694988 data_time: 0.548101 memory: 918 2022/09/14 21:13:53 - mmengine - INFO - Epoch(val) [20][300/407] eta: 0:01:35 time: 0.889062 data_time: 0.739499 memory: 918 2022/09/14 21:14:35 - mmengine - INFO - Epoch(val) [20][350/407] eta: 0:00:48 time: 0.845318 data_time: 0.700785 memory: 918 2022/09/14 21:15:27 - mmengine - INFO - Epoch(val) [20][400/407] eta: 0:00:07 time: 1.027480 data_time: 0.880863 memory: 918 2022/09/14 21:18:12 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 21:18:25 - mmengine - INFO - Epoch(val) [20][407/407] coco/AP: 0.691911 coco/AP .5: 0.882973 coco/AP .75: 0.761457 coco/AP (M): 0.655341 coco/AP (L): 0.758390 coco/AR: 0.755715 coco/AR .5: 0.922544 coco/AR .75: 0.817853 coco/AR (M): 0.711008 coco/AR (L): 0.820030 2022/09/14 21:18:25 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/udp_regress/best_coco/AP_epoch_10.pth is removed 2022/09/14 21:18:28 - mmengine - INFO - The best checkpoint with 0.6919 coco/AP at 20 epoch is saved to best_coco/AP_epoch_20.pth. 2022/09/14 21:20:54 - mmengine - INFO - Epoch(train) [21][50/293] lr: 5.000000e-04 eta: 1 day, 15:28:55 time: 2.934580 data_time: 1.796935 memory: 9974 loss_kpt: 0.001964 loss: 0.001964 2022/09/14 21:22:30 - mmengine - INFO - Epoch(train) [21][100/293] lr: 5.000000e-04 eta: 1 day, 15:21:52 time: 1.922245 data_time: 0.383914 memory: 9974 loss_kpt: 0.001959 loss: 0.001959 2022/09/14 21:24:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 21:24:26 - mmengine - INFO - Epoch(train) [21][150/293] lr: 5.000000e-04 eta: 1 day, 15:17:55 time: 2.313722 data_time: 0.135620 memory: 9974 loss_kpt: 0.001943 loss: 0.001943 2022/09/14 21:25:59 - mmengine - INFO - Epoch(train) [21][200/293] lr: 5.000000e-04 eta: 1 day, 15:10:33 time: 1.859335 data_time: 0.231352 memory: 9974 loss_kpt: 0.001983 loss: 0.001983 2022/09/14 21:27:44 - mmengine - INFO - Epoch(train) [21][250/293] lr: 5.000000e-04 eta: 1 day, 15:05:08 time: 2.105868 data_time: 0.111072 memory: 9974 loss_kpt: 0.001943 loss: 0.001943 2022/09/14 21:29:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 21:29:08 - mmengine - INFO - Saving checkpoint at 21 epochs 2022/09/14 21:30:48 - mmengine - INFO - Epoch(train) [22][50/293] lr: 5.000000e-04 eta: 1 day, 14:40:28 time: 1.933859 data_time: 0.218706 memory: 9974 loss_kpt: 0.001954 loss: 0.001954 2022/09/14 21:32:34 - mmengine - INFO - Epoch(train) [22][100/293] lr: 5.000000e-04 eta: 1 day, 14:35:35 time: 2.138862 data_time: 0.613615 memory: 9974 loss_kpt: 0.001929 loss: 0.001929 2022/09/14 21:34:46 - mmengine - INFO - Epoch(train) [22][150/293] lr: 5.000000e-04 eta: 1 day, 14:34:19 time: 2.625925 data_time: 0.449152 memory: 9974 loss_kpt: 0.001931 loss: 0.001931 2022/09/14 21:36:27 - mmengine - INFO - Epoch(train) [22][200/293] lr: 5.000000e-04 eta: 1 day, 14:28:43 time: 2.029700 data_time: 0.139282 memory: 9974 loss_kpt: 0.001964 loss: 0.001964 2022/09/14 21:37:54 - mmengine - INFO - Epoch(train) [22][250/293] lr: 5.000000e-04 eta: 1 day, 14:20:59 time: 1.725513 data_time: 0.360335 memory: 9974 loss_kpt: 0.001968 loss: 0.001968 2022/09/14 21:38:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 21:38:59 - mmengine - INFO - Saving checkpoint at 22 epochs 2022/09/14 21:40:31 - mmengine - INFO - Epoch(train) [23][50/293] lr: 5.000000e-04 eta: 1 day, 13:56:35 time: 1.751760 data_time: 0.651922 memory: 9974 loss_kpt: 0.001955 loss: 0.001955 2022/09/14 21:42:16 - mmengine - INFO - Epoch(train) [23][100/293] lr: 5.000000e-04 eta: 1 day, 13:51:50 time: 2.099306 data_time: 0.521578 memory: 9974 loss_kpt: 0.001951 loss: 0.001951 2022/09/14 21:44:07 - mmengine - INFO - Epoch(train) [23][150/293] lr: 5.000000e-04 eta: 1 day, 13:48:00 time: 2.223161 data_time: 0.176147 memory: 9974 loss_kpt: 0.001905 loss: 0.001905 2022/09/14 21:46:00 - mmengine - INFO - Epoch(train) [23][200/293] lr: 5.000000e-04 eta: 1 day, 13:44:27 time: 2.261145 data_time: 0.418042 memory: 9974 loss_kpt: 0.001928 loss: 0.001928 2022/09/14 21:47:49 - mmengine - INFO - Epoch(train) [23][250/293] lr: 5.000000e-04 eta: 1 day, 13:40:25 time: 2.188697 data_time: 0.714546 memory: 9974 loss_kpt: 0.001922 loss: 0.001922 2022/09/14 21:48:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 21:48:56 - mmengine - INFO - Saving checkpoint at 23 epochs 2022/09/14 21:50:52 - mmengine - INFO - Epoch(train) [24][50/293] lr: 5.000000e-04 eta: 1 day, 13:20:46 time: 2.246688 data_time: 0.291938 memory: 9974 loss_kpt: 0.001956 loss: 0.001956 2022/09/14 21:52:26 - mmengine - INFO - Epoch(train) [24][100/293] lr: 5.000000e-04 eta: 1 day, 13:14:56 time: 1.886554 data_time: 0.197214 memory: 9974 loss_kpt: 0.001926 loss: 0.001926 2022/09/14 21:54:39 - mmengine - INFO - Epoch(train) [24][150/293] lr: 5.000000e-04 eta: 1 day, 13:14:14 time: 2.655770 data_time: 0.119689 memory: 9974 loss_kpt: 0.001923 loss: 0.001923 2022/09/14 21:56:23 - mmengine - INFO - Epoch(train) [24][200/293] lr: 5.000000e-04 eta: 1 day, 13:09:43 time: 2.075810 data_time: 0.246143 memory: 9974 loss_kpt: 0.001904 loss: 0.001904 2022/09/14 21:58:17 - mmengine - INFO - Epoch(train) [24][250/293] lr: 5.000000e-04 eta: 1 day, 13:06:36 time: 2.285343 data_time: 0.298900 memory: 9974 loss_kpt: 0.001933 loss: 0.001933 2022/09/14 21:58:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 22:00:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 22:00:06 - mmengine - INFO - Saving checkpoint at 24 epochs 2022/09/14 22:02:27 - mmengine - INFO - Epoch(train) [25][50/293] lr: 5.000000e-04 eta: 1 day, 12:51:10 time: 2.739191 data_time: 0.335862 memory: 9974 loss_kpt: 0.001889 loss: 0.001889 2022/09/14 22:04:46 - mmengine - INFO - Epoch(train) [25][100/293] lr: 5.000000e-04 eta: 1 day, 12:51:19 time: 2.779907 data_time: 0.102684 memory: 9974 loss_kpt: 0.001941 loss: 0.001941 2022/09/14 22:06:30 - mmengine - INFO - Epoch(train) [25][150/293] lr: 5.000000e-04 eta: 1 day, 12:47:07 time: 2.095256 data_time: 0.108028 memory: 9974 loss_kpt: 0.001899 loss: 0.001899 2022/09/14 22:08:25 - mmengine - INFO - Epoch(train) [25][200/293] lr: 5.000000e-04 eta: 1 day, 12:44:06 time: 2.280868 data_time: 0.108053 memory: 9974 loss_kpt: 0.001978 loss: 0.001978 2022/09/14 22:10:42 - mmengine - INFO - Epoch(train) [25][250/293] lr: 5.000000e-04 eta: 1 day, 12:44:05 time: 2.758323 data_time: 0.105172 memory: 9974 loss_kpt: 0.001937 loss: 0.001937 2022/09/14 22:12:03 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 22:12:03 - mmengine - INFO - Saving checkpoint at 25 epochs 2022/09/14 22:13:53 - mmengine - INFO - Epoch(train) [26][50/293] lr: 5.000000e-04 eta: 1 day, 12:25:35 time: 2.129523 data_time: 1.092558 memory: 9974 loss_kpt: 0.001920 loss: 0.001920 2022/09/14 22:15:55 - mmengine - INFO - Epoch(train) [26][100/293] lr: 5.000000e-04 eta: 1 day, 12:23:42 time: 2.443144 data_time: 0.089984 memory: 9974 loss_kpt: 0.001910 loss: 0.001910 2022/09/14 22:17:22 - mmengine - INFO - Epoch(train) [26][150/293] lr: 5.000000e-04 eta: 1 day, 12:17:39 time: 1.752193 data_time: 0.086240 memory: 9974 loss_kpt: 0.001944 loss: 0.001944 2022/09/14 22:19:06 - mmengine - INFO - Epoch(train) [26][200/293] lr: 5.000000e-04 eta: 1 day, 12:13:33 time: 2.067582 data_time: 0.282945 memory: 9974 loss_kpt: 0.001922 loss: 0.001922 2022/09/14 22:20:33 - mmengine - INFO - Epoch(train) [26][250/293] lr: 5.000000e-04 eta: 1 day, 12:07:34 time: 1.747510 data_time: 0.636692 memory: 9974 loss_kpt: 0.001899 loss: 0.001899 2022/09/14 22:22:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 22:22:08 - mmengine - INFO - Saving checkpoint at 26 epochs 2022/09/14 22:24:03 - mmengine - INFO - Epoch(train) [27][50/293] lr: 5.000000e-04 eta: 1 day, 11:50:37 time: 2.224230 data_time: 0.691832 memory: 9974 loss_kpt: 0.001968 loss: 0.001968 2022/09/14 22:26:15 - mmengine - INFO - Epoch(train) [27][100/293] lr: 5.000000e-04 eta: 1 day, 11:50:01 time: 2.636045 data_time: 0.078939 memory: 9974 loss_kpt: 0.001901 loss: 0.001901 2022/09/14 22:28:01 - mmengine - INFO - Epoch(train) [27][150/293] lr: 5.000000e-04 eta: 1 day, 11:46:30 time: 2.136230 data_time: 0.100743 memory: 9974 loss_kpt: 0.001895 loss: 0.001895 2022/09/14 22:29:48 - mmengine - INFO - Epoch(train) [27][200/293] lr: 5.000000e-04 eta: 1 day, 11:42:59 time: 2.127833 data_time: 0.352723 memory: 9974 loss_kpt: 0.001916 loss: 0.001916 2022/09/14 22:31:50 - mmengine - INFO - Epoch(train) [27][250/293] lr: 5.000000e-04 eta: 1 day, 11:41:16 time: 2.443201 data_time: 0.098718 memory: 9974 loss_kpt: 0.001915 loss: 0.001915 2022/09/14 22:33:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 22:33:06 - mmengine - INFO - Saving checkpoint at 27 epochs 2022/09/14 22:34:43 - mmengine - INFO - Epoch(train) [28][50/293] lr: 5.000000e-04 eta: 1 day, 11:23:05 time: 1.874037 data_time: 0.266063 memory: 9974 loss_kpt: 0.001917 loss: 0.001917 2022/09/14 22:36:14 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 22:36:44 - mmengine - INFO - Epoch(train) [28][100/293] lr: 5.000000e-04 eta: 1 day, 11:21:23 time: 2.425823 data_time: 0.089229 memory: 9974 loss_kpt: 0.001890 loss: 0.001890 2022/09/14 22:38:55 - mmengine - INFO - Epoch(train) [28][150/293] lr: 5.000000e-04 eta: 1 day, 11:20:41 time: 2.610609 data_time: 0.231941 memory: 9974 loss_kpt: 0.001904 loss: 0.001904 2022/09/14 22:40:49 - mmengine - INFO - Epoch(train) [28][200/293] lr: 5.000000e-04 eta: 1 day, 11:18:12 time: 2.289874 data_time: 0.101306 memory: 9974 loss_kpt: 0.001916 loss: 0.001916 2022/09/14 22:42:20 - mmengine - INFO - Epoch(train) [28][250/293] lr: 5.000000e-04 eta: 1 day, 11:13:08 time: 1.813737 data_time: 0.097621 memory: 9974 loss_kpt: 0.001885 loss: 0.001885 2022/09/14 22:43:47 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 22:43:47 - mmengine - INFO - Saving checkpoint at 28 epochs 2022/09/14 22:45:51 - mmengine - INFO - Epoch(train) [29][50/293] lr: 5.000000e-04 eta: 1 day, 10:58:38 time: 2.406565 data_time: 0.148747 memory: 9974 loss_kpt: 0.001890 loss: 0.001890 2022/09/14 22:47:15 - mmengine - INFO - Epoch(train) [29][100/293] lr: 5.000000e-04 eta: 1 day, 10:53:03 time: 1.685905 data_time: 0.182064 memory: 9974 loss_kpt: 0.001884 loss: 0.001884 2022/09/14 22:48:33 - mmengine - INFO - Epoch(train) [29][150/293] lr: 5.000000e-04 eta: 1 day, 10:46:49 time: 1.557778 data_time: 0.087798 memory: 9974 loss_kpt: 0.001881 loss: 0.001881 2022/09/14 22:50:04 - mmengine - INFO - Epoch(train) [29][200/293] lr: 5.000000e-04 eta: 1 day, 10:42:03 time: 1.819766 data_time: 0.104332 memory: 9974 loss_kpt: 0.001904 loss: 0.001904 2022/09/14 22:51:16 - mmengine - INFO - Epoch(train) [29][250/293] lr: 5.000000e-04 eta: 1 day, 10:35:17 time: 1.433185 data_time: 0.306408 memory: 9974 loss_kpt: 0.001858 loss: 0.001858 2022/09/14 22:52:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 22:52:46 - mmengine - INFO - Saving checkpoint at 29 epochs 2022/09/14 22:54:29 - mmengine - INFO - Epoch(train) [30][50/293] lr: 5.000000e-04 eta: 1 day, 10:19:26 time: 2.001001 data_time: 0.210433 memory: 9974 loss_kpt: 0.001888 loss: 0.001888 2022/09/14 22:56:38 - mmengine - INFO - Epoch(train) [30][100/293] lr: 5.000000e-04 eta: 1 day, 10:18:46 time: 2.580846 data_time: 0.085685 memory: 9974 loss_kpt: 0.001884 loss: 0.001884 2022/09/14 22:58:12 - mmengine - INFO - Epoch(train) [30][150/293] lr: 5.000000e-04 eta: 1 day, 10:14:26 time: 1.862892 data_time: 0.404756 memory: 9974 loss_kpt: 0.001894 loss: 0.001894 2022/09/14 23:00:01 - mmengine - INFO - Epoch(train) [30][200/293] lr: 5.000000e-04 eta: 1 day, 10:11:47 time: 2.190896 data_time: 0.234946 memory: 9974 loss_kpt: 0.001886 loss: 0.001886 2022/09/14 23:01:37 - mmengine - INFO - Epoch(train) [30][250/293] lr: 5.000000e-04 eta: 1 day, 10:07:47 time: 1.921986 data_time: 0.128166 memory: 9974 loss_kpt: 0.001889 loss: 0.001889 2022/09/14 23:02:39 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 23:02:39 - mmengine - INFO - Saving checkpoint at 30 epochs 2022/09/14 23:03:21 - mmengine - INFO - Epoch(val) [30][50/407] eta: 0:04:32 time: 0.762496 data_time: 0.616968 memory: 9974 2022/09/14 23:04:01 - mmengine - INFO - Epoch(val) [30][100/407] eta: 0:04:05 time: 0.798652 data_time: 0.654697 memory: 918 2022/09/14 23:04:32 - mmengine - INFO - Epoch(val) [30][150/407] eta: 0:02:41 time: 0.630165 data_time: 0.482366 memory: 918 2022/09/14 23:05:33 - mmengine - INFO - Epoch(val) [30][200/407] eta: 0:04:13 time: 1.225817 data_time: 1.076573 memory: 918 2022/09/14 23:06:17 - mmengine - INFO - Epoch(val) [30][250/407] eta: 0:02:17 time: 0.876507 data_time: 0.726919 memory: 918 2022/09/14 23:06:57 - mmengine - INFO - Epoch(val) [30][300/407] eta: 0:01:24 time: 0.791079 data_time: 0.647775 memory: 918 2022/09/14 23:07:35 - mmengine - INFO - Epoch(val) [30][350/407] eta: 0:00:43 time: 0.767499 data_time: 0.623063 memory: 918 2022/09/14 23:08:15 - mmengine - INFO - Epoch(val) [30][400/407] eta: 0:00:05 time: 0.802540 data_time: 0.658932 memory: 918 2022/09/14 23:10:38 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 23:10:51 - mmengine - INFO - Epoch(val) [30][407/407] coco/AP: 0.703526 coco/AP .5: 0.887295 coco/AP .75: 0.775806 coco/AP (M): 0.666762 coco/AP (L): 0.771849 coco/AR: 0.766294 coco/AR .5: 0.928526 coco/AR .75: 0.830605 coco/AR (M): 0.721033 coco/AR (L): 0.831141 2022/09/14 23:10:51 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/udp_regress/best_coco/AP_epoch_20.pth is removed 2022/09/14 23:10:53 - mmengine - INFO - The best checkpoint with 0.7035 coco/AP at 30 epoch is saved to best_coco/AP_epoch_30.pth. 2022/09/14 23:13:48 - mmengine - INFO - Epoch(train) [31][50/293] lr: 5.000000e-04 eta: 1 day, 10:00:02 time: 3.495717 data_time: 1.741727 memory: 9974 loss_kpt: 0.001865 loss: 0.001865 2022/09/14 23:15:36 - mmengine - INFO - Epoch(train) [31][100/293] lr: 5.000000e-04 eta: 1 day, 9:57:19 time: 2.166062 data_time: 0.293119 memory: 9974 loss_kpt: 0.001886 loss: 0.001886 2022/09/14 23:17:43 - mmengine - INFO - Epoch(train) [31][150/293] lr: 5.000000e-04 eta: 1 day, 9:56:23 time: 2.526778 data_time: 0.498425 memory: 9974 loss_kpt: 0.001931 loss: 0.001931 2022/09/14 23:19:02 - mmengine - INFO - Epoch(train) [31][200/293] lr: 5.000000e-04 eta: 1 day, 9:50:51 time: 1.582971 data_time: 0.087986 memory: 9974 loss_kpt: 0.001877 loss: 0.001877 2022/09/14 23:19:14 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 23:20:02 - mmengine - INFO - Epoch(train) [31][250/293] lr: 5.000000e-04 eta: 1 day, 9:43:31 time: 1.204600 data_time: 0.126781 memory: 9974 loss_kpt: 0.001871 loss: 0.001871 2022/09/14 23:20:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 23:20:59 - mmengine - INFO - Saving checkpoint at 31 epochs 2022/09/14 23:22:06 - mmengine - INFO - Epoch(train) [32][50/293] lr: 5.000000e-04 eta: 1 day, 9:25:27 time: 1.271401 data_time: 0.394863 memory: 9974 loss_kpt: 0.001872 loss: 0.001872 2022/09/14 23:23:33 - mmengine - INFO - Epoch(train) [32][100/293] lr: 5.000000e-04 eta: 1 day, 9:20:57 time: 1.751464 data_time: 0.156522 memory: 9974 loss_kpt: 0.001851 loss: 0.001851 2022/09/14 23:25:18 - mmengine - INFO - Epoch(train) [32][150/293] lr: 5.000000e-04 eta: 1 day, 9:18:07 time: 2.101206 data_time: 0.157190 memory: 9974 loss_kpt: 0.001874 loss: 0.001874 2022/09/14 23:26:45 - mmengine - INFO - Epoch(train) [32][200/293] lr: 5.000000e-04 eta: 1 day, 9:13:35 time: 1.732199 data_time: 0.090466 memory: 9974 loss_kpt: 0.001836 loss: 0.001836 2022/09/14 23:28:30 - mmengine - INFO - Epoch(train) [32][250/293] lr: 5.000000e-04 eta: 1 day, 9:10:47 time: 2.096628 data_time: 0.099383 memory: 9974 loss_kpt: 0.001877 loss: 0.001877 2022/09/14 23:29:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 23:29:44 - mmengine - INFO - Saving checkpoint at 32 epochs 2022/09/14 23:31:41 - mmengine - INFO - Epoch(train) [33][50/293] lr: 5.000000e-04 eta: 1 day, 8:58:08 time: 2.279307 data_time: 0.155302 memory: 9974 loss_kpt: 0.001888 loss: 0.001888 2022/09/14 23:33:03 - mmengine - INFO - Epoch(train) [33][100/293] lr: 5.000000e-04 eta: 1 day, 8:53:18 time: 1.637392 data_time: 0.161056 memory: 9974 loss_kpt: 0.001843 loss: 0.001843 2022/09/14 23:34:24 - mmengine - INFO - Epoch(train) [33][150/293] lr: 5.000000e-04 eta: 1 day, 8:48:28 time: 1.628733 data_time: 0.085900 memory: 9974 loss_kpt: 0.001849 loss: 0.001849 2022/09/14 23:36:04 - mmengine - INFO - Epoch(train) [33][200/293] lr: 5.000000e-04 eta: 1 day, 8:45:19 time: 1.995489 data_time: 0.576692 memory: 9974 loss_kpt: 0.001879 loss: 0.001879 2022/09/14 23:37:24 - mmengine - INFO - Epoch(train) [33][250/293] lr: 5.000000e-04 eta: 1 day, 8:40:26 time: 1.601790 data_time: 0.211463 memory: 9974 loss_kpt: 0.001862 loss: 0.001862 2022/09/14 23:38:47 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 23:38:47 - mmengine - INFO - Saving checkpoint at 33 epochs 2022/09/14 23:40:06 - mmengine - INFO - Epoch(train) [34][50/293] lr: 5.000000e-04 eta: 1 day, 8:24:54 time: 1.511631 data_time: 0.244251 memory: 9974 loss_kpt: 0.001848 loss: 0.001848 2022/09/14 23:41:24 - mmengine - INFO - Epoch(train) [34][100/293] lr: 5.000000e-04 eta: 1 day, 8:20:00 time: 1.565019 data_time: 0.258498 memory: 9974 loss_kpt: 0.001835 loss: 0.001835 2022/09/14 23:43:20 - mmengine - INFO - Epoch(train) [34][150/293] lr: 5.000000e-04 eta: 1 day, 8:18:26 time: 2.318517 data_time: 0.092198 memory: 9974 loss_kpt: 0.001886 loss: 0.001886 2022/09/14 23:45:03 - mmengine - INFO - Epoch(train) [34][200/293] lr: 5.000000e-04 eta: 1 day, 8:15:41 time: 2.048699 data_time: 0.115034 memory: 9974 loss_kpt: 0.001866 loss: 0.001866 2022/09/14 23:46:40 - mmengine - INFO - Epoch(train) [34][250/293] lr: 5.000000e-04 eta: 1 day, 8:12:28 time: 1.939394 data_time: 0.091944 memory: 9974 loss_kpt: 0.001881 loss: 0.001881 2022/09/14 23:48:29 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 23:48:29 - mmengine - INFO - Saving checkpoint at 34 epochs 2022/09/14 23:49:40 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 23:50:18 - mmengine - INFO - Epoch(train) [35][50/293] lr: 5.000000e-04 eta: 1 day, 8:00:06 time: 2.105552 data_time: 0.245882 memory: 9974 loss_kpt: 0.001834 loss: 0.001834 2022/09/14 23:51:49 - mmengine - INFO - Epoch(train) [35][100/293] lr: 5.000000e-04 eta: 1 day, 7:56:28 time: 1.821211 data_time: 0.093514 memory: 9974 loss_kpt: 0.001870 loss: 0.001870 2022/09/14 23:53:31 - mmengine - INFO - Epoch(train) [35][150/293] lr: 5.000000e-04 eta: 1 day, 7:53:50 time: 2.052120 data_time: 0.108145 memory: 9974 loss_kpt: 0.001850 loss: 0.001850 2022/09/14 23:55:00 - mmengine - INFO - Epoch(train) [35][200/293] lr: 5.000000e-04 eta: 1 day, 7:50:01 time: 1.771051 data_time: 0.236245 memory: 9974 loss_kpt: 0.001877 loss: 0.001877 2022/09/14 23:56:43 - mmengine - INFO - Epoch(train) [35][250/293] lr: 5.000000e-04 eta: 1 day, 7:47:25 time: 2.052597 data_time: 0.164547 memory: 9974 loss_kpt: 0.001840 loss: 0.001840 2022/09/14 23:58:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/14 23:58:11 - mmengine - INFO - Saving checkpoint at 35 epochs 2022/09/14 23:59:56 - mmengine - INFO - Epoch(train) [36][50/293] lr: 5.000000e-04 eta: 1 day, 7:35:16 time: 2.049326 data_time: 0.240798 memory: 9974 loss_kpt: 0.001851 loss: 0.001851 2022/09/15 00:01:37 - mmengine - INFO - Epoch(train) [36][100/293] lr: 5.000000e-04 eta: 1 day, 7:32:33 time: 2.010753 data_time: 0.227973 memory: 9974 loss_kpt: 0.001844 loss: 0.001844 2022/09/15 00:03:21 - mmengine - INFO - Epoch(train) [36][150/293] lr: 5.000000e-04 eta: 1 day, 7:30:06 time: 2.072386 data_time: 0.269786 memory: 9974 loss_kpt: 0.001828 loss: 0.001828 2022/09/15 00:05:04 - mmengine - INFO - Epoch(train) [36][200/293] lr: 5.000000e-04 eta: 1 day, 7:27:40 time: 2.071576 data_time: 0.106525 memory: 9974 loss_kpt: 0.001875 loss: 0.001875 2022/09/15 00:06:35 - mmengine - INFO - Epoch(train) [36][250/293] lr: 5.000000e-04 eta: 1 day, 7:24:09 time: 1.808443 data_time: 0.122918 memory: 9974 loss_kpt: 0.001895 loss: 0.001895 2022/09/15 00:07:52 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 00:07:52 - mmengine - INFO - Saving checkpoint at 36 epochs 2022/09/15 00:09:19 - mmengine - INFO - Epoch(train) [37][50/293] lr: 5.000000e-04 eta: 1 day, 7:10:55 time: 1.673963 data_time: 0.729894 memory: 9974 loss_kpt: 0.001847 loss: 0.001847 2022/09/15 00:11:16 - mmengine - INFO - Epoch(train) [37][100/293] lr: 5.000000e-04 eta: 1 day, 7:09:39 time: 2.344246 data_time: 0.150142 memory: 9974 loss_kpt: 0.001857 loss: 0.001857 2022/09/15 00:12:57 - mmengine - INFO - Epoch(train) [37][150/293] lr: 5.000000e-04 eta: 1 day, 7:07:02 time: 2.010308 data_time: 0.154696 memory: 9974 loss_kpt: 0.001860 loss: 0.001860 2022/09/15 00:14:35 - mmengine - INFO - Epoch(train) [37][200/293] lr: 5.000000e-04 eta: 1 day, 7:04:17 time: 1.970470 data_time: 0.132137 memory: 9974 loss_kpt: 0.001846 loss: 0.001846 2022/09/15 00:16:14 - mmengine - INFO - Epoch(train) [37][250/293] lr: 5.000000e-04 eta: 1 day, 7:01:34 time: 1.976748 data_time: 0.178179 memory: 9974 loss_kpt: 0.001806 loss: 0.001806 2022/09/15 00:17:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 00:17:49 - mmengine - INFO - Saving checkpoint at 37 epochs 2022/09/15 00:19:36 - mmengine - INFO - Epoch(train) [38][50/293] lr: 5.000000e-04 eta: 1 day, 6:50:17 time: 2.064919 data_time: 0.135437 memory: 9974 loss_kpt: 0.001825 loss: 0.001825 2022/09/15 00:21:06 - mmengine - INFO - Epoch(train) [38][100/293] lr: 5.000000e-04 eta: 1 day, 6:46:57 time: 1.801646 data_time: 0.121906 memory: 9974 loss_kpt: 0.001858 loss: 0.001858 2022/09/15 00:23:07 - mmengine - INFO - Epoch(train) [38][150/293] lr: 5.000000e-04 eta: 1 day, 6:45:59 time: 2.415657 data_time: 0.090404 memory: 9974 loss_kpt: 0.001862 loss: 0.001862 2022/09/15 00:23:28 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 00:25:01 - mmengine - INFO - Epoch(train) [38][200/293] lr: 5.000000e-04 eta: 1 day, 6:44:32 time: 2.289516 data_time: 0.096590 memory: 9974 loss_kpt: 0.001863 loss: 0.001863 2022/09/15 00:26:34 - mmengine - INFO - Epoch(train) [38][250/293] lr: 5.000000e-04 eta: 1 day, 6:41:25 time: 1.853585 data_time: 0.107151 memory: 9974 loss_kpt: 0.001827 loss: 0.001827 2022/09/15 00:27:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 00:27:56 - mmengine - INFO - Saving checkpoint at 38 epochs 2022/09/15 00:30:00 - mmengine - INFO - Epoch(train) [39][50/293] lr: 5.000000e-04 eta: 1 day, 6:31:48 time: 2.415676 data_time: 0.167894 memory: 9974 loss_kpt: 0.001797 loss: 0.001797 2022/09/15 00:31:57 - mmengine - INFO - Epoch(train) [39][100/293] lr: 5.000000e-04 eta: 1 day, 6:30:34 time: 2.337297 data_time: 0.449971 memory: 9974 loss_kpt: 0.001864 loss: 0.001864 2022/09/15 00:33:53 - mmengine - INFO - Epoch(train) [39][150/293] lr: 5.000000e-04 eta: 1 day, 6:29:14 time: 2.314087 data_time: 0.493910 memory: 9974 loss_kpt: 0.001835 loss: 0.001835 2022/09/15 00:35:43 - mmengine - INFO - Epoch(train) [39][200/293] lr: 5.000000e-04 eta: 1 day, 6:27:29 time: 2.203486 data_time: 0.823798 memory: 9974 loss_kpt: 0.001826 loss: 0.001826 2022/09/15 00:38:03 - mmengine - INFO - Epoch(train) [39][250/293] lr: 5.000000e-04 eta: 1 day, 6:27:57 time: 2.809246 data_time: 0.563309 memory: 9974 loss_kpt: 0.001879 loss: 0.001879 2022/09/15 00:39:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 00:39:46 - mmengine - INFO - Saving checkpoint at 39 epochs 2022/09/15 00:41:55 - mmengine - INFO - Epoch(train) [40][50/293] lr: 5.000000e-04 eta: 1 day, 6:18:56 time: 2.519142 data_time: 0.505578 memory: 9974 loss_kpt: 0.001831 loss: 0.001831 2022/09/15 00:43:44 - mmengine - INFO - Epoch(train) [40][100/293] lr: 5.000000e-04 eta: 1 day, 6:17:06 time: 2.178835 data_time: 0.204061 memory: 9974 loss_kpt: 0.001825 loss: 0.001825 2022/09/15 00:45:46 - mmengine - INFO - Epoch(train) [40][150/293] lr: 5.000000e-04 eta: 1 day, 6:16:16 time: 2.453065 data_time: 0.450681 memory: 9974 loss_kpt: 0.001823 loss: 0.001823 2022/09/15 00:47:40 - mmengine - INFO - Epoch(train) [40][200/293] lr: 5.000000e-04 eta: 1 day, 6:14:46 time: 2.268503 data_time: 0.328227 memory: 9974 loss_kpt: 0.001864 loss: 0.001864 2022/09/15 00:49:16 - mmengine - INFO - Epoch(train) [40][250/293] lr: 5.000000e-04 eta: 1 day, 6:12:03 time: 1.932043 data_time: 0.093137 memory: 9974 loss_kpt: 0.001820 loss: 0.001820 2022/09/15 00:50:45 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 00:50:45 - mmengine - INFO - Saving checkpoint at 40 epochs 2022/09/15 00:51:37 - mmengine - INFO - Epoch(val) [40][50/407] eta: 0:05:49 time: 0.978570 data_time: 0.834289 memory: 9974 2022/09/15 00:52:16 - mmengine - INFO - Epoch(val) [40][100/407] eta: 0:04:00 time: 0.784892 data_time: 0.634169 memory: 918 2022/09/15 00:53:04 - mmengine - INFO - Epoch(val) [40][150/407] eta: 0:04:07 time: 0.962807 data_time: 0.812531 memory: 918 2022/09/15 00:53:44 - mmengine - INFO - Epoch(val) [40][200/407] eta: 0:02:44 time: 0.794198 data_time: 0.645604 memory: 918 2022/09/15 00:54:21 - mmengine - INFO - Epoch(val) [40][250/407] eta: 0:01:55 time: 0.738567 data_time: 0.592795 memory: 918 2022/09/15 00:54:50 - mmengine - INFO - Epoch(val) [40][300/407] eta: 0:01:02 time: 0.584923 data_time: 0.443140 memory: 918 2022/09/15 00:55:48 - mmengine - INFO - Epoch(val) [40][350/407] eta: 0:01:06 time: 1.158156 data_time: 1.012572 memory: 918 2022/09/15 00:56:39 - mmengine - INFO - Epoch(val) [40][400/407] eta: 0:00:07 time: 1.024625 data_time: 0.873546 memory: 918 2022/09/15 00:59:36 - mmengine - INFO - Evaluating CocoMetric... 2022/09/15 00:59:49 - mmengine - INFO - Epoch(val) [40][407/407] coco/AP: 0.710777 coco/AP .5: 0.888376 coco/AP .75: 0.781562 coco/AP (M): 0.671803 coco/AP (L): 0.780038 coco/AR: 0.771411 coco/AR .5: 0.928369 coco/AR .75: 0.832966 coco/AR (M): 0.726086 coco/AR (L): 0.836603 2022/09/15 00:59:49 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/udp_regress/best_coco/AP_epoch_30.pth is removed 2022/09/15 00:59:52 - mmengine - INFO - The best checkpoint with 0.7108 coco/AP at 40 epoch is saved to best_coco/AP_epoch_40.pth. 2022/09/15 01:01:38 - mmengine - INFO - Epoch(train) [41][50/293] lr: 5.000000e-04 eta: 1 day, 6:01:53 time: 2.129363 data_time: 0.227359 memory: 9974 loss_kpt: 0.001848 loss: 0.001848 2022/09/15 01:03:16 - mmengine - INFO - Epoch(train) [41][100/293] lr: 5.000000e-04 eta: 1 day, 5:59:19 time: 1.953500 data_time: 0.201494 memory: 9974 loss_kpt: 0.001800 loss: 0.001800 2022/09/15 01:04:49 - mmengine - INFO - Epoch(train) [41][150/293] lr: 5.000000e-04 eta: 1 day, 5:56:26 time: 1.868317 data_time: 0.123666 memory: 9974 loss_kpt: 0.001807 loss: 0.001807 2022/09/15 01:06:25 - mmengine - INFO - Epoch(train) [41][200/293] lr: 5.000000e-04 eta: 1 day, 5:53:46 time: 1.922283 data_time: 0.251428 memory: 9974 loss_kpt: 0.001806 loss: 0.001806 2022/09/15 01:08:06 - mmengine - INFO - Epoch(train) [41][250/293] lr: 5.000000e-04 eta: 1 day, 5:51:26 time: 2.014673 data_time: 0.094717 memory: 9974 loss_kpt: 0.001812 loss: 0.001812 2022/09/15 01:08:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 01:09:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 01:09:19 - mmengine - INFO - Saving checkpoint at 41 epochs 2022/09/15 01:11:11 - mmengine - INFO - Epoch(train) [42][50/293] lr: 5.000000e-04 eta: 1 day, 5:41:40 time: 2.161910 data_time: 0.672586 memory: 9974 loss_kpt: 0.001824 loss: 0.001824 2022/09/15 01:12:52 - mmengine - INFO - Epoch(train) [42][100/293] lr: 5.000000e-04 eta: 1 day, 5:39:22 time: 2.014472 data_time: 0.086118 memory: 9974 loss_kpt: 0.001829 loss: 0.001829 2022/09/15 01:14:17 - mmengine - INFO - Epoch(train) [42][150/293] lr: 5.000000e-04 eta: 1 day, 5:36:02 time: 1.706298 data_time: 0.107795 memory: 9974 loss_kpt: 0.001810 loss: 0.001810 2022/09/15 01:15:34 - mmengine - INFO - Epoch(train) [42][200/293] lr: 5.000000e-04 eta: 1 day, 5:32:10 time: 1.543625 data_time: 0.298781 memory: 9974 loss_kpt: 0.001826 loss: 0.001826 2022/09/15 01:17:49 - mmengine - INFO - Epoch(train) [42][250/293] lr: 5.000000e-04 eta: 1 day, 5:32:12 time: 2.700320 data_time: 2.116778 memory: 9974 loss_kpt: 0.001826 loss: 0.001826 2022/09/15 01:19:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 01:19:19 - mmengine - INFO - Saving checkpoint at 42 epochs 2022/09/15 01:20:54 - mmengine - INFO - Epoch(train) [43][50/293] lr: 5.000000e-04 eta: 1 day, 5:21:36 time: 1.827971 data_time: 0.472386 memory: 9974 loss_kpt: 0.001814 loss: 0.001814 2022/09/15 01:22:23 - mmengine - INFO - Epoch(train) [43][100/293] lr: 5.000000e-04 eta: 1 day, 5:18:37 time: 1.788985 data_time: 0.085125 memory: 9974 loss_kpt: 0.001820 loss: 0.001820 2022/09/15 01:23:54 - mmengine - INFO - Epoch(train) [43][150/293] lr: 5.000000e-04 eta: 1 day, 5:15:43 time: 1.811477 data_time: 0.248617 memory: 9974 loss_kpt: 0.001819 loss: 0.001819 2022/09/15 01:25:39 - mmengine - INFO - Epoch(train) [43][200/293] lr: 5.000000e-04 eta: 1 day, 5:13:47 time: 2.100724 data_time: 0.096247 memory: 9974 loss_kpt: 0.001792 loss: 0.001792 2022/09/15 01:27:42 - mmengine - INFO - Epoch(train) [43][250/293] lr: 5.000000e-04 eta: 1 day, 5:13:01 time: 2.463361 data_time: 0.149461 memory: 9974 loss_kpt: 0.001836 loss: 0.001836 2022/09/15 01:29:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 01:29:06 - mmengine - INFO - Saving checkpoint at 43 epochs 2022/09/15 01:30:47 - mmengine - INFO - Epoch(train) [44][50/293] lr: 5.000000e-04 eta: 1 day, 5:03:07 time: 1.955068 data_time: 0.160869 memory: 9974 loss_kpt: 0.001803 loss: 0.001803 2022/09/15 01:32:57 - mmengine - INFO - Epoch(train) [44][100/293] lr: 5.000000e-04 eta: 1 day, 5:02:47 time: 2.588593 data_time: 0.093978 memory: 9974 loss_kpt: 0.001834 loss: 0.001834 2022/09/15 01:34:33 - mmengine - INFO - Epoch(train) [44][150/293] lr: 5.000000e-04 eta: 1 day, 5:00:18 time: 1.925626 data_time: 0.268916 memory: 9974 loss_kpt: 0.001850 loss: 0.001850 2022/09/15 01:36:17 - mmengine - INFO - Epoch(train) [44][200/293] lr: 5.000000e-04 eta: 1 day, 4:58:22 time: 2.089320 data_time: 0.088204 memory: 9974 loss_kpt: 0.001816 loss: 0.001816 2022/09/15 01:37:53 - mmengine - INFO - Epoch(train) [44][250/293] lr: 5.000000e-04 eta: 1 day, 4:55:51 time: 1.908621 data_time: 0.088433 memory: 9974 loss_kpt: 0.001812 loss: 0.001812 2022/09/15 01:39:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 01:39:32 - mmengine - INFO - Saving checkpoint at 44 epochs 2022/09/15 01:41:24 - mmengine - INFO - Epoch(train) [45][50/293] lr: 5.000000e-04 eta: 1 day, 4:46:54 time: 2.181280 data_time: 0.206413 memory: 9974 loss_kpt: 0.001822 loss: 0.001822 2022/09/15 01:43:04 - mmengine - INFO - Epoch(train) [45][100/293] lr: 5.000000e-04 eta: 1 day, 4:44:45 time: 2.010792 data_time: 0.091340 memory: 9974 loss_kpt: 0.001791 loss: 0.001791 2022/09/15 01:43:25 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 01:45:00 - mmengine - INFO - Epoch(train) [45][150/293] lr: 5.000000e-04 eta: 1 day, 4:43:32 time: 2.313072 data_time: 0.156901 memory: 9974 loss_kpt: 0.001809 loss: 0.001809 2022/09/15 01:46:52 - mmengine - INFO - Epoch(train) [45][200/293] lr: 5.000000e-04 eta: 1 day, 4:42:04 time: 2.234003 data_time: 0.185810 memory: 9974 loss_kpt: 0.001799 loss: 0.001799 2022/09/15 01:48:50 - mmengine - INFO - Epoch(train) [45][250/293] lr: 5.000000e-04 eta: 1 day, 4:40:59 time: 2.358315 data_time: 0.090321 memory: 9974 loss_kpt: 0.001841 loss: 0.001841 2022/09/15 01:50:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 01:50:30 - mmengine - INFO - Saving checkpoint at 45 epochs 2022/09/15 01:52:26 - mmengine - INFO - Epoch(train) [46][50/293] lr: 5.000000e-04 eta: 1 day, 4:32:26 time: 2.245326 data_time: 0.712126 memory: 9974 loss_kpt: 0.001770 loss: 0.001770 2022/09/15 01:54:06 - mmengine - INFO - Epoch(train) [46][100/293] lr: 5.000000e-04 eta: 1 day, 4:30:18 time: 2.009412 data_time: 0.623153 memory: 9974 loss_kpt: 0.001801 loss: 0.001801 2022/09/15 01:55:44 - mmengine - INFO - Epoch(train) [46][150/293] lr: 5.000000e-04 eta: 1 day, 4:27:59 time: 1.946064 data_time: 0.817197 memory: 9974 loss_kpt: 0.001797 loss: 0.001797 2022/09/15 01:57:21 - mmengine - INFO - Epoch(train) [46][200/293] lr: 5.000000e-04 eta: 1 day, 4:25:43 time: 1.958790 data_time: 0.097333 memory: 9974 loss_kpt: 0.001824 loss: 0.001824 2022/09/15 01:59:06 - mmengine - INFO - Epoch(train) [46][250/293] lr: 5.000000e-04 eta: 1 day, 4:23:52 time: 2.100646 data_time: 0.093218 memory: 9974 loss_kpt: 0.001821 loss: 0.001821 2022/09/15 02:00:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 02:00:26 - mmengine - INFO - Saving checkpoint at 46 epochs 2022/09/15 02:02:13 - mmengine - INFO - Epoch(train) [47][50/293] lr: 5.000000e-04 eta: 1 day, 4:14:59 time: 2.064676 data_time: 1.069473 memory: 9974 loss_kpt: 0.001808 loss: 0.001808 2022/09/15 02:04:20 - mmengine - INFO - Epoch(train) [47][100/293] lr: 5.000000e-04 eta: 1 day, 4:14:27 time: 2.535825 data_time: 1.799346 memory: 9974 loss_kpt: 0.001836 loss: 0.001836 2022/09/15 02:06:17 - mmengine - INFO - Epoch(train) [47][150/293] lr: 5.000000e-04 eta: 1 day, 4:13:20 time: 2.343837 data_time: 0.892415 memory: 9974 loss_kpt: 0.001827 loss: 0.001827 2022/09/15 02:08:50 - mmengine - INFO - Epoch(train) [47][200/293] lr: 5.000000e-04 eta: 1 day, 4:14:20 time: 3.070319 data_time: 0.183332 memory: 9974 loss_kpt: 0.001784 loss: 0.001784 2022/09/15 02:11:18 - mmengine - INFO - Epoch(train) [47][250/293] lr: 5.000000e-04 eta: 1 day, 4:14:59 time: 2.957560 data_time: 0.092206 memory: 9974 loss_kpt: 0.001772 loss: 0.001772 2022/09/15 02:13:38 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 02:13:38 - mmengine - INFO - Saving checkpoint at 47 epochs 2022/09/15 02:15:59 - mmengine - INFO - Epoch(train) [48][50/293] lr: 5.000000e-04 eta: 1 day, 4:08:15 time: 2.763580 data_time: 1.082407 memory: 9974 loss_kpt: 0.001794 loss: 0.001794 2022/09/15 02:18:38 - mmengine - INFO - Epoch(train) [48][100/293] lr: 5.000000e-04 eta: 1 day, 4:09:30 time: 3.178554 data_time: 0.341649 memory: 9974 loss_kpt: 0.001807 loss: 0.001807 2022/09/15 02:21:20 - mmengine - INFO - Epoch(train) [48][150/293] lr: 5.000000e-04 eta: 1 day, 4:10:52 time: 3.229836 data_time: 0.233348 memory: 9974 loss_kpt: 0.001797 loss: 0.001797 2022/09/15 02:23:17 - mmengine - INFO - Epoch(train) [48][200/293] lr: 5.000000e-04 eta: 1 day, 4:09:42 time: 2.344681 data_time: 0.186869 memory: 9974 loss_kpt: 0.001817 loss: 0.001817 2022/09/15 02:24:34 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 02:25:29 - mmengine - INFO - Epoch(train) [48][250/293] lr: 5.000000e-04 eta: 1 day, 4:09:24 time: 2.652492 data_time: 0.086964 memory: 9974 loss_kpt: 0.001809 loss: 0.001809 2022/09/15 02:27:36 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 02:27:36 - mmengine - INFO - Saving checkpoint at 48 epochs 2022/09/15 02:29:35 - mmengine - INFO - Epoch(train) [49][50/293] lr: 5.000000e-04 eta: 1 day, 4:01:28 time: 2.317350 data_time: 0.450783 memory: 9974 loss_kpt: 0.001807 loss: 0.001807 2022/09/15 02:31:30 - mmengine - INFO - Epoch(train) [49][100/293] lr: 5.000000e-04 eta: 1 day, 4:00:08 time: 2.283599 data_time: 0.381497 memory: 9974 loss_kpt: 0.001770 loss: 0.001770 2022/09/15 02:33:24 - mmengine - INFO - Epoch(train) [49][150/293] lr: 5.000000e-04 eta: 1 day, 3:58:49 time: 2.296035 data_time: 0.396700 memory: 9974 loss_kpt: 0.001798 loss: 0.001798 2022/09/15 02:35:26 - mmengine - INFO - Epoch(train) [49][200/293] lr: 5.000000e-04 eta: 1 day, 3:57:53 time: 2.432236 data_time: 0.772255 memory: 9974 loss_kpt: 0.001798 loss: 0.001798 2022/09/15 02:37:15 - mmengine - INFO - Epoch(train) [49][250/293] lr: 5.000000e-04 eta: 1 day, 3:56:14 time: 2.177286 data_time: 0.092772 memory: 9974 loss_kpt: 0.001782 loss: 0.001782 2022/09/15 02:38:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 02:38:43 - mmengine - INFO - Saving checkpoint at 49 epochs 2022/09/15 02:40:24 - mmengine - INFO - Epoch(train) [50][50/293] lr: 5.000000e-04 eta: 1 day, 3:47:27 time: 1.948660 data_time: 0.351379 memory: 9974 loss_kpt: 0.001775 loss: 0.001775 2022/09/15 02:42:13 - mmengine - INFO - Epoch(train) [50][100/293] lr: 5.000000e-04 eta: 1 day, 3:45:53 time: 2.197027 data_time: 0.096724 memory: 9974 loss_kpt: 0.001778 loss: 0.001778 2022/09/15 02:44:31 - mmengine - INFO - Epoch(train) [50][150/293] lr: 5.000000e-04 eta: 1 day, 3:45:48 time: 2.747717 data_time: 0.084677 memory: 9974 loss_kpt: 0.001780 loss: 0.001780 2022/09/15 02:45:54 - mmengine - INFO - Epoch(train) [50][200/293] lr: 5.000000e-04 eta: 1 day, 3:42:47 time: 1.663419 data_time: 0.413237 memory: 9974 loss_kpt: 0.001812 loss: 0.001812 2022/09/15 02:48:10 - mmengine - INFO - Epoch(train) [50][250/293] lr: 5.000000e-04 eta: 1 day, 3:42:38 time: 2.728373 data_time: 0.733177 memory: 9974 loss_kpt: 0.001802 loss: 0.001802 2022/09/15 02:49:39 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 02:49:39 - mmengine - INFO - Saving checkpoint at 50 epochs 2022/09/15 02:50:47 - mmengine - INFO - Epoch(val) [50][50/407] eta: 0:07:41 time: 1.293350 data_time: 1.147738 memory: 9974 2022/09/15 02:51:46 - mmengine - INFO - Epoch(val) [50][100/407] eta: 0:06:04 time: 1.187116 data_time: 1.039501 memory: 918 2022/09/15 02:52:29 - mmengine - INFO - Epoch(val) [50][150/407] eta: 0:03:39 time: 0.854243 data_time: 0.710779 memory: 918 2022/09/15 02:52:55 - mmengine - INFO - Epoch(val) [50][200/407] eta: 0:01:50 time: 0.531542 data_time: 0.382720 memory: 918 2022/09/15 02:53:49 - mmengine - INFO - Epoch(val) [50][250/407] eta: 0:02:46 time: 1.063332 data_time: 0.911599 memory: 918 2022/09/15 02:54:22 - mmengine - INFO - Epoch(val) [50][300/407] eta: 0:01:12 time: 0.674106 data_time: 0.531425 memory: 918 2022/09/15 02:54:51 - mmengine - INFO - Epoch(val) [50][350/407] eta: 0:00:32 time: 0.573115 data_time: 0.431853 memory: 918 2022/09/15 02:55:37 - mmengine - INFO - Epoch(val) [50][400/407] eta: 0:00:06 time: 0.912989 data_time: 0.762355 memory: 918 2022/09/15 02:56:52 - mmengine - INFO - Evaluating CocoMetric... 2022/09/15 02:57:05 - mmengine - INFO - Epoch(val) [50][407/407] coco/AP: 0.717467 coco/AP .5: 0.888899 coco/AP .75: 0.792584 coco/AP (M): 0.676925 coco/AP (L): 0.788718 coco/AR: 0.777598 coco/AR .5: 0.929314 coco/AR .75: 0.845718 coco/AR (M): 0.730784 coco/AR (L): 0.844630 2022/09/15 02:57:05 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/udp_regress/best_coco/AP_epoch_40.pth is removed 2022/09/15 02:57:07 - mmengine - INFO - The best checkpoint with 0.7175 coco/AP at 50 epoch is saved to best_coco/AP_epoch_50.pth. 2022/09/15 02:59:10 - mmengine - INFO - Epoch(train) [51][50/293] lr: 5.000000e-04 eta: 1 day, 3:35:19 time: 2.442706 data_time: 0.617523 memory: 9974 loss_kpt: 0.001779 loss: 0.001779 2022/09/15 03:01:20 - mmengine - INFO - Epoch(train) [51][100/293] lr: 5.000000e-04 eta: 1 day, 3:34:51 time: 2.609594 data_time: 0.154546 memory: 9974 loss_kpt: 0.001797 loss: 0.001797 2022/09/15 03:03:01 - mmengine - INFO - Epoch(train) [51][150/293] lr: 5.000000e-04 eta: 1 day, 3:32:47 time: 2.008896 data_time: 0.820371 memory: 9974 loss_kpt: 0.001795 loss: 0.001795 2022/09/15 03:05:06 - mmengine - INFO - Epoch(train) [51][200/293] lr: 5.000000e-04 eta: 1 day, 3:32:00 time: 2.501513 data_time: 0.185477 memory: 9974 loss_kpt: 0.001806 loss: 0.001806 2022/09/15 03:06:31 - mmengine - INFO - Epoch(train) [51][250/293] lr: 5.000000e-04 eta: 1 day, 3:29:10 time: 1.712145 data_time: 0.240984 memory: 9974 loss_kpt: 0.001815 loss: 0.001815 2022/09/15 03:08:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 03:08:05 - mmengine - INFO - Saving checkpoint at 51 epochs 2022/09/15 03:09:48 - mmengine - INFO - Epoch(train) [52][50/293] lr: 5.000000e-04 eta: 1 day, 3:20:48 time: 1.984510 data_time: 0.341765 memory: 9974 loss_kpt: 0.001772 loss: 0.001772 2022/09/15 03:10:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 03:11:45 - mmengine - INFO - Epoch(train) [52][100/293] lr: 5.000000e-04 eta: 1 day, 3:19:38 time: 2.346465 data_time: 0.594499 memory: 9974 loss_kpt: 0.001795 loss: 0.001795 2022/09/15 03:13:08 - mmengine - INFO - Epoch(train) [52][150/293] lr: 5.000000e-04 eta: 1 day, 3:16:41 time: 1.651841 data_time: 0.321810 memory: 9974 loss_kpt: 0.001782 loss: 0.001782 2022/09/15 03:14:35 - mmengine - INFO - Epoch(train) [52][200/293] lr: 5.000000e-04 eta: 1 day, 3:13:59 time: 1.748489 data_time: 0.198395 memory: 9974 loss_kpt: 0.001778 loss: 0.001778 2022/09/15 03:16:34 - mmengine - INFO - Epoch(train) [52][250/293] lr: 5.000000e-04 eta: 1 day, 3:12:54 time: 2.379531 data_time: 0.092116 memory: 9974 loss_kpt: 0.001790 loss: 0.001790 2022/09/15 03:18:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 03:18:08 - mmengine - INFO - Saving checkpoint at 52 epochs 2022/09/15 03:19:56 - mmengine - INFO - Epoch(train) [53][50/293] lr: 5.000000e-04 eta: 1 day, 3:04:58 time: 2.086388 data_time: 0.255876 memory: 9974 loss_kpt: 0.001747 loss: 0.001747 2022/09/15 03:21:33 - mmengine - INFO - Epoch(train) [53][100/293] lr: 5.000000e-04 eta: 1 day, 3:02:49 time: 1.953796 data_time: 0.094895 memory: 9974 loss_kpt: 0.001801 loss: 0.001801 2022/09/15 03:23:18 - mmengine - INFO - Epoch(train) [53][150/293] lr: 5.000000e-04 eta: 1 day, 3:01:00 time: 2.084789 data_time: 0.104993 memory: 9974 loss_kpt: 0.001815 loss: 0.001815 2022/09/15 03:24:49 - mmengine - INFO - Epoch(train) [53][200/293] lr: 5.000000e-04 eta: 1 day, 2:58:32 time: 1.821846 data_time: 0.094458 memory: 9974 loss_kpt: 0.001790 loss: 0.001790 2022/09/15 03:26:33 - mmengine - INFO - Epoch(train) [53][250/293] lr: 5.000000e-04 eta: 1 day, 2:56:42 time: 2.077437 data_time: 0.147163 memory: 9974 loss_kpt: 0.001776 loss: 0.001776 2022/09/15 03:27:58 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 03:27:58 - mmengine - INFO - Saving checkpoint at 53 epochs 2022/09/15 03:29:56 - mmengine - INFO - Epoch(train) [54][50/293] lr: 5.000000e-04 eta: 1 day, 2:49:26 time: 2.289061 data_time: 0.175221 memory: 9974 loss_kpt: 0.001744 loss: 0.001744 2022/09/15 03:31:28 - mmengine - INFO - Epoch(train) [54][100/293] lr: 5.000000e-04 eta: 1 day, 2:47:02 time: 1.837854 data_time: 0.080020 memory: 9974 loss_kpt: 0.001807 loss: 0.001807 2022/09/15 03:33:07 - mmengine - INFO - Epoch(train) [54][150/293] lr: 5.000000e-04 eta: 1 day, 2:45:01 time: 1.990034 data_time: 0.604480 memory: 9974 loss_kpt: 0.001798 loss: 0.001798 2022/09/15 03:35:08 - mmengine - INFO - Epoch(train) [54][200/293] lr: 5.000000e-04 eta: 1 day, 2:44:01 time: 2.411008 data_time: 0.229816 memory: 9974 loss_kpt: 0.001778 loss: 0.001778 2022/09/15 03:36:56 - mmengine - INFO - Epoch(train) [54][250/293] lr: 5.000000e-04 eta: 1 day, 2:42:27 time: 2.175711 data_time: 0.350281 memory: 9974 loss_kpt: 0.001792 loss: 0.001792 2022/09/15 03:38:22 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 03:38:22 - mmengine - INFO - Saving checkpoint at 54 epochs 2022/09/15 03:39:46 - mmengine - INFO - Epoch(train) [55][50/293] lr: 5.000000e-04 eta: 1 day, 2:33:42 time: 1.616618 data_time: 0.291196 memory: 9974 loss_kpt: 0.001778 loss: 0.001778 2022/09/15 03:41:11 - mmengine - INFO - Epoch(train) [55][100/293] lr: 5.000000e-04 eta: 1 day, 2:30:59 time: 1.687609 data_time: 0.491256 memory: 9974 loss_kpt: 0.001770 loss: 0.001770 2022/09/15 03:42:34 - mmengine - INFO - Epoch(train) [55][150/293] lr: 5.000000e-04 eta: 1 day, 2:28:12 time: 1.655579 data_time: 0.885523 memory: 9974 loss_kpt: 0.001751 loss: 0.001751 2022/09/15 03:43:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 03:43:43 - mmengine - INFO - Epoch(train) [55][200/293] lr: 5.000000e-04 eta: 1 day, 2:24:47 time: 1.385570 data_time: 0.461674 memory: 9974 loss_kpt: 0.001788 loss: 0.001788 2022/09/15 03:45:03 - mmengine - INFO - Epoch(train) [55][250/293] lr: 5.000000e-04 eta: 1 day, 2:21:53 time: 1.598559 data_time: 0.082911 memory: 9974 loss_kpt: 0.001776 loss: 0.001776 2022/09/15 03:46:16 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 03:46:16 - mmengine - INFO - Saving checkpoint at 55 epochs 2022/09/15 03:47:29 - mmengine - INFO - Epoch(train) [56][50/293] lr: 5.000000e-04 eta: 1 day, 2:12:51 time: 1.402696 data_time: 0.212170 memory: 9974 loss_kpt: 0.001755 loss: 0.001755 2022/09/15 03:49:50 - mmengine - INFO - Epoch(train) [56][100/293] lr: 5.000000e-04 eta: 1 day, 2:12:49 time: 2.809758 data_time: 0.097695 memory: 9974 loss_kpt: 0.001773 loss: 0.001773 2022/09/15 03:51:16 - mmengine - INFO - Epoch(train) [56][150/293] lr: 5.000000e-04 eta: 1 day, 2:10:14 time: 1.716080 data_time: 0.354109 memory: 9974 loss_kpt: 0.001750 loss: 0.001750 2022/09/15 03:52:53 - mmengine - INFO - Epoch(train) [56][200/293] lr: 5.000000e-04 eta: 1 day, 2:08:11 time: 1.949818 data_time: 0.553065 memory: 9974 loss_kpt: 0.001788 loss: 0.001788 2022/09/15 03:54:25 - mmengine - INFO - Epoch(train) [56][250/293] lr: 5.000000e-04 eta: 1 day, 2:05:54 time: 1.842590 data_time: 0.100193 memory: 9974 loss_kpt: 0.001784 loss: 0.001784 2022/09/15 03:55:52 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 03:55:52 - mmengine - INFO - Saving checkpoint at 56 epochs 2022/09/15 03:57:41 - mmengine - INFO - Epoch(train) [57][50/293] lr: 5.000000e-04 eta: 1 day, 1:58:39 time: 2.100206 data_time: 1.470232 memory: 9974 loss_kpt: 0.001781 loss: 0.001781 2022/09/15 03:59:37 - mmengine - INFO - Epoch(train) [57][100/293] lr: 5.000000e-04 eta: 1 day, 1:57:29 time: 2.326757 data_time: 0.423388 memory: 9974 loss_kpt: 0.001756 loss: 0.001756 2022/09/15 04:01:26 - mmengine - INFO - Epoch(train) [57][150/293] lr: 5.000000e-04 eta: 1 day, 1:56:01 time: 2.189476 data_time: 0.528438 memory: 9974 loss_kpt: 0.001771 loss: 0.001771 2022/09/15 04:02:59 - mmengine - INFO - Epoch(train) [57][200/293] lr: 5.000000e-04 eta: 1 day, 1:53:46 time: 1.847938 data_time: 0.891278 memory: 9974 loss_kpt: 0.001796 loss: 0.001796 2022/09/15 04:04:33 - mmengine - INFO - Epoch(train) [57][250/293] lr: 5.000000e-04 eta: 1 day, 1:51:38 time: 1.892749 data_time: 0.613835 memory: 9974 loss_kpt: 0.001788 loss: 0.001788 2022/09/15 04:05:52 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 04:05:52 - mmengine - INFO - Saving checkpoint at 57 epochs 2022/09/15 04:07:07 - mmengine - INFO - Epoch(train) [58][50/293] lr: 5.000000e-04 eta: 1 day, 1:43:01 time: 1.434711 data_time: 0.603345 memory: 9974 loss_kpt: 0.001732 loss: 0.001732 2022/09/15 04:09:02 - mmengine - INFO - Epoch(train) [58][100/293] lr: 5.000000e-04 eta: 1 day, 1:41:49 time: 2.306800 data_time: 0.086559 memory: 9974 loss_kpt: 0.001773 loss: 0.001773 2022/09/15 04:10:42 - mmengine - INFO - Epoch(train) [58][150/293] lr: 5.000000e-04 eta: 1 day, 1:39:56 time: 1.992364 data_time: 0.456119 memory: 9974 loss_kpt: 0.001766 loss: 0.001766 2022/09/15 04:12:03 - mmengine - INFO - Epoch(train) [58][200/293] lr: 5.000000e-04 eta: 1 day, 1:37:13 time: 1.613950 data_time: 0.507639 memory: 9974 loss_kpt: 0.001790 loss: 0.001790 2022/09/15 04:13:36 - mmengine - INFO - Epoch(train) [58][250/293] lr: 5.000000e-04 eta: 1 day, 1:35:05 time: 1.879048 data_time: 1.193656 memory: 9974 loss_kpt: 0.001776 loss: 0.001776 2022/09/15 04:15:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 04:15:11 - mmengine - INFO - Saving checkpoint at 58 epochs 2022/09/15 04:15:25 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 04:16:58 - mmengine - INFO - Epoch(train) [59][50/293] lr: 5.000000e-04 eta: 1 day, 1:28:02 time: 2.074443 data_time: 0.602472 memory: 9974 loss_kpt: 0.001790 loss: 0.001790 2022/09/15 04:18:49 - mmengine - INFO - Epoch(train) [59][100/293] lr: 5.000000e-04 eta: 1 day, 1:26:41 time: 2.233019 data_time: 0.908283 memory: 9974 loss_kpt: 0.001737 loss: 0.001737 2022/09/15 04:20:06 - mmengine - INFO - Epoch(train) [59][150/293] lr: 5.000000e-04 eta: 1 day, 1:23:50 time: 1.537743 data_time: 0.411434 memory: 9974 loss_kpt: 0.001778 loss: 0.001778 2022/09/15 04:21:22 - mmengine - INFO - Epoch(train) [59][200/293] lr: 5.000000e-04 eta: 1 day, 1:20:57 time: 1.517223 data_time: 0.346939 memory: 9974 loss_kpt: 0.001769 loss: 0.001769 2022/09/15 04:22:54 - mmengine - INFO - Epoch(train) [59][250/293] lr: 5.000000e-04 eta: 1 day, 1:18:47 time: 1.845232 data_time: 1.044225 memory: 9974 loss_kpt: 0.001803 loss: 0.001803 2022/09/15 04:24:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 04:24:08 - mmengine - INFO - Saving checkpoint at 59 epochs 2022/09/15 04:25:32 - mmengine - INFO - Epoch(train) [60][50/293] lr: 5.000000e-04 eta: 1 day, 1:10:55 time: 1.629862 data_time: 0.439714 memory: 9974 loss_kpt: 0.001746 loss: 0.001746 2022/09/15 04:27:11 - mmengine - INFO - Epoch(train) [60][100/293] lr: 5.000000e-04 eta: 1 day, 1:09:04 time: 1.977914 data_time: 0.096876 memory: 9974 loss_kpt: 0.001754 loss: 0.001754 2022/09/15 04:28:34 - mmengine - INFO - Epoch(train) [60][150/293] lr: 5.000000e-04 eta: 1 day, 1:06:31 time: 1.657234 data_time: 0.111592 memory: 9974 loss_kpt: 0.001771 loss: 0.001771 2022/09/15 04:29:53 - mmengine - INFO - Epoch(train) [60][200/293] lr: 5.000000e-04 eta: 1 day, 1:03:48 time: 1.566562 data_time: 0.382892 memory: 9974 loss_kpt: 0.001760 loss: 0.001760 2022/09/15 04:31:11 - mmengine - INFO - Epoch(train) [60][250/293] lr: 5.000000e-04 eta: 1 day, 1:01:05 time: 1.566590 data_time: 0.187481 memory: 9974 loss_kpt: 0.001771 loss: 0.001771 2022/09/15 04:32:23 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 04:32:23 - mmengine - INFO - Saving checkpoint at 60 epochs 2022/09/15 04:33:15 - mmengine - INFO - Epoch(val) [60][50/407] eta: 0:05:46 time: 0.969903 data_time: 0.821721 memory: 9974 2022/09/15 04:33:56 - mmengine - INFO - Epoch(val) [60][100/407] eta: 0:04:13 time: 0.826906 data_time: 0.685129 memory: 918 2022/09/15 04:34:39 - mmengine - INFO - Epoch(val) [60][150/407] eta: 0:03:39 time: 0.853952 data_time: 0.702757 memory: 918 2022/09/15 04:35:35 - mmengine - INFO - Epoch(val) [60][200/407] eta: 0:03:52 time: 1.121197 data_time: 0.976299 memory: 918 2022/09/15 04:36:03 - mmengine - INFO - Epoch(val) [60][250/407] eta: 0:01:28 time: 0.564283 data_time: 0.422755 memory: 918 2022/09/15 04:36:35 - mmengine - INFO - Epoch(val) [60][300/407] eta: 0:01:09 time: 0.646185 data_time: 0.503145 memory: 918 2022/09/15 04:37:11 - mmengine - INFO - Epoch(val) [60][350/407] eta: 0:00:40 time: 0.702434 data_time: 0.556561 memory: 918 2022/09/15 04:38:01 - mmengine - INFO - Epoch(val) [60][400/407] eta: 0:00:07 time: 1.006395 data_time: 0.853872 memory: 918 2022/09/15 04:39:24 - mmengine - INFO - Evaluating CocoMetric... 2022/09/15 04:39:37 - mmengine - INFO - Epoch(val) [60][407/407] coco/AP: 0.730261 coco/AP .5: 0.897492 coco/AP .75: 0.798909 coco/AP (M): 0.692111 coco/AP (L): 0.800693 coco/AR: 0.785815 coco/AR .5: 0.934824 coco/AR .75: 0.847607 coco/AR (M): 0.740208 coco/AR (L): 0.851914 2022/09/15 04:39:37 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/udp_regress/best_coco/AP_epoch_50.pth is removed 2022/09/15 04:39:40 - mmengine - INFO - The best checkpoint with 0.7303 coco/AP at 60 epoch is saved to best_coco/AP_epoch_60.pth. 2022/09/15 04:41:23 - mmengine - INFO - Epoch(train) [61][50/293] lr: 5.000000e-04 eta: 1 day, 0:54:18 time: 2.068371 data_time: 0.261576 memory: 9974 loss_kpt: 0.001764 loss: 0.001764 2022/09/15 04:43:09 - mmengine - INFO - Epoch(train) [61][100/293] lr: 5.000000e-04 eta: 1 day, 0:52:44 time: 2.111069 data_time: 0.084585 memory: 9974 loss_kpt: 0.001754 loss: 0.001754 2022/09/15 04:44:29 - mmengine - INFO - Epoch(train) [61][150/293] lr: 5.000000e-04 eta: 1 day, 0:50:07 time: 1.596869 data_time: 0.193776 memory: 9974 loss_kpt: 0.001766 loss: 0.001766 2022/09/15 04:45:54 - mmengine - INFO - Epoch(train) [61][200/293] lr: 5.000000e-04 eta: 1 day, 0:47:44 time: 1.705365 data_time: 0.185851 memory: 9974 loss_kpt: 0.001790 loss: 0.001790 2022/09/15 04:47:15 - mmengine - INFO - Epoch(train) [61][250/293] lr: 5.000000e-04 eta: 1 day, 0:45:10 time: 1.618513 data_time: 0.226705 memory: 9974 loss_kpt: 0.001764 loss: 0.001764 2022/09/15 04:48:37 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 04:48:37 - mmengine - INFO - Saving checkpoint at 61 epochs 2022/09/15 04:50:19 - mmengine - INFO - Epoch(train) [62][50/293] lr: 5.000000e-04 eta: 1 day, 0:38:18 time: 1.966093 data_time: 0.545830 memory: 9974 loss_kpt: 0.001773 loss: 0.001773 2022/09/15 04:51:47 - mmengine - INFO - Epoch(train) [62][100/293] lr: 5.000000e-04 eta: 1 day, 0:36:04 time: 1.768904 data_time: 0.194209 memory: 9974 loss_kpt: 0.001765 loss: 0.001765 2022/09/15 04:52:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 04:53:22 - mmengine - INFO - Epoch(train) [62][150/293] lr: 5.000000e-04 eta: 1 day, 0:34:06 time: 1.897662 data_time: 0.199771 memory: 9974 loss_kpt: 0.001771 loss: 0.001771 2022/09/15 04:54:38 - mmengine - INFO - Epoch(train) [62][200/293] lr: 5.000000e-04 eta: 1 day, 0:31:23 time: 1.515709 data_time: 0.070759 memory: 9974 loss_kpt: 0.001743 loss: 0.001743 2022/09/15 04:56:00 - mmengine - INFO - Epoch(train) [62][250/293] lr: 5.000000e-04 eta: 1 day, 0:28:55 time: 1.646924 data_time: 0.530631 memory: 9974 loss_kpt: 0.001755 loss: 0.001755 2022/09/15 04:57:12 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 04:57:12 - mmengine - INFO - Saving checkpoint at 62 epochs 2022/09/15 04:58:32 - mmengine - INFO - Epoch(train) [63][50/293] lr: 5.000000e-04 eta: 1 day, 0:21:21 time: 1.544448 data_time: 0.396109 memory: 9974 loss_kpt: 0.001759 loss: 0.001759 2022/09/15 05:00:06 - mmengine - INFO - Epoch(train) [63][100/293] lr: 5.000000e-04 eta: 1 day, 0:19:20 time: 1.862399 data_time: 0.122649 memory: 9974 loss_kpt: 0.001746 loss: 0.001746 2022/09/15 05:01:39 - mmengine - INFO - Epoch(train) [63][150/293] lr: 5.000000e-04 eta: 1 day, 0:17:22 time: 1.876956 data_time: 0.099126 memory: 9974 loss_kpt: 0.001730 loss: 0.001730 2022/09/15 05:03:01 - mmengine - INFO - Epoch(train) [63][200/293] lr: 5.000000e-04 eta: 1 day, 0:14:55 time: 1.638301 data_time: 0.284448 memory: 9974 loss_kpt: 0.001756 loss: 0.001756 2022/09/15 05:04:31 - mmengine - INFO - Epoch(train) [63][250/293] lr: 5.000000e-04 eta: 1 day, 0:12:47 time: 1.787072 data_time: 0.184526 memory: 9974 loss_kpt: 0.001763 loss: 0.001763 2022/09/15 05:05:57 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 05:05:57 - mmengine - INFO - Saving checkpoint at 63 epochs 2022/09/15 05:07:24 - mmengine - INFO - Epoch(train) [64][50/293] lr: 5.000000e-04 eta: 1 day, 0:05:36 time: 1.676212 data_time: 0.258901 memory: 9974 loss_kpt: 0.001733 loss: 0.001733 2022/09/15 05:08:33 - mmengine - INFO - Epoch(train) [64][100/293] lr: 5.000000e-04 eta: 1 day, 0:02:42 time: 1.377254 data_time: 0.088067 memory: 9974 loss_kpt: 0.001770 loss: 0.001770 2022/09/15 05:09:44 - mmengine - INFO - Epoch(train) [64][150/293] lr: 5.000000e-04 eta: 23:59:51 time: 1.412398 data_time: 0.382608 memory: 9974 loss_kpt: 0.001778 loss: 0.001778 2022/09/15 05:11:10 - mmengine - INFO - Epoch(train) [64][200/293] lr: 5.000000e-04 eta: 23:57:38 time: 1.725982 data_time: 0.289202 memory: 9974 loss_kpt: 0.001744 loss: 0.001744 2022/09/15 05:12:43 - mmengine - INFO - Epoch(train) [64][250/293] lr: 5.000000e-04 eta: 23:55:40 time: 1.859124 data_time: 0.090440 memory: 9974 loss_kpt: 0.001746 loss: 0.001746 2022/09/15 05:13:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 05:13:59 - mmengine - INFO - Saving checkpoint at 64 epochs 2022/09/15 05:16:00 - mmengine - INFO - Epoch(train) [65][50/293] lr: 5.000000e-04 eta: 23:49:53 time: 2.337436 data_time: 0.210958 memory: 9974 loss_kpt: 0.001750 loss: 0.001750 2022/09/15 05:17:48 - mmengine - INFO - Epoch(train) [65][100/293] lr: 5.000000e-04 eta: 23:48:32 time: 2.177954 data_time: 0.957070 memory: 9974 loss_kpt: 0.001738 loss: 0.001738 2022/09/15 05:19:33 - mmengine - INFO - Epoch(train) [65][150/293] lr: 5.000000e-04 eta: 23:47:01 time: 2.088755 data_time: 1.223745 memory: 9974 loss_kpt: 0.001773 loss: 0.001773 2022/09/15 05:21:00 - mmengine - INFO - Epoch(train) [65][200/293] lr: 5.000000e-04 eta: 23:44:50 time: 1.735966 data_time: 0.187273 memory: 9974 loss_kpt: 0.001773 loss: 0.001773 2022/09/15 05:23:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 05:23:13 - mmengine - INFO - Epoch(train) [65][250/293] lr: 5.000000e-04 eta: 23:44:23 time: 2.667239 data_time: 2.087748 memory: 9974 loss_kpt: 0.001769 loss: 0.001769 2022/09/15 05:24:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 05:24:27 - mmengine - INFO - Saving checkpoint at 65 epochs 2022/09/15 05:26:10 - mmengine - INFO - Epoch(train) [66][50/293] lr: 5.000000e-04 eta: 23:38:02 time: 1.991375 data_time: 0.161981 memory: 9974 loss_kpt: 0.001771 loss: 0.001771 2022/09/15 05:28:08 - mmengine - INFO - Epoch(train) [66][100/293] lr: 5.000000e-04 eta: 23:37:00 time: 2.353531 data_time: 0.097033 memory: 9974 loss_kpt: 0.001774 loss: 0.001774 2022/09/15 05:29:34 - mmengine - INFO - Epoch(train) [66][150/293] lr: 5.000000e-04 eta: 23:34:49 time: 1.724868 data_time: 0.083888 memory: 9974 loss_kpt: 0.001769 loss: 0.001769 2022/09/15 05:31:10 - mmengine - INFO - Epoch(train) [66][200/293] lr: 5.000000e-04 eta: 23:32:59 time: 1.915687 data_time: 0.087432 memory: 9974 loss_kpt: 0.001741 loss: 0.001741 2022/09/15 05:32:50 - mmengine - INFO - Epoch(train) [66][250/293] lr: 5.000000e-04 eta: 23:31:19 time: 2.004435 data_time: 0.090323 memory: 9974 loss_kpt: 0.001752 loss: 0.001752 2022/09/15 05:34:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 05:34:05 - mmengine - INFO - Saving checkpoint at 66 epochs 2022/09/15 05:35:34 - mmengine - INFO - Epoch(train) [67][50/293] lr: 5.000000e-04 eta: 23:24:34 time: 1.721445 data_time: 0.176816 memory: 9974 loss_kpt: 0.001756 loss: 0.001756 2022/09/15 05:36:54 - mmengine - INFO - Epoch(train) [67][100/293] lr: 5.000000e-04 eta: 23:22:10 time: 1.593671 data_time: 0.080006 memory: 9974 loss_kpt: 0.001786 loss: 0.001786 2022/09/15 05:38:19 - mmengine - INFO - Epoch(train) [67][150/293] lr: 5.000000e-04 eta: 23:19:58 time: 1.698022 data_time: 0.108362 memory: 9974 loss_kpt: 0.001764 loss: 0.001764 2022/09/15 05:39:53 - mmengine - INFO - Epoch(train) [67][200/293] lr: 5.000000e-04 eta: 23:18:06 time: 1.884082 data_time: 0.099556 memory: 9974 loss_kpt: 0.001739 loss: 0.001739 2022/09/15 05:41:11 - mmengine - INFO - Epoch(train) [67][250/293] lr: 5.000000e-04 eta: 23:15:38 time: 1.552126 data_time: 0.087862 memory: 9974 loss_kpt: 0.001734 loss: 0.001734 2022/09/15 05:42:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 05:42:11 - mmengine - INFO - Saving checkpoint at 67 epochs 2022/09/15 05:43:37 - mmengine - INFO - Epoch(train) [68][50/293] lr: 5.000000e-04 eta: 23:08:54 time: 1.660868 data_time: 0.127638 memory: 9974 loss_kpt: 0.001750 loss: 0.001750 2022/09/15 05:45:05 - mmengine - INFO - Epoch(train) [68][100/293] lr: 5.000000e-04 eta: 23:06:50 time: 1.758372 data_time: 0.092809 memory: 9974 loss_kpt: 0.001756 loss: 0.001756 2022/09/15 05:47:02 - mmengine - INFO - Epoch(train) [68][150/293] lr: 5.000000e-04 eta: 23:05:48 time: 2.350039 data_time: 0.426008 memory: 9974 loss_kpt: 0.001772 loss: 0.001772 2022/09/15 05:48:30 - mmengine - INFO - Epoch(train) [68][200/293] lr: 5.000000e-04 eta: 23:03:43 time: 1.749156 data_time: 0.175879 memory: 9974 loss_kpt: 0.001762 loss: 0.001762 2022/09/15 05:49:58 - mmengine - INFO - Epoch(train) [68][250/293] lr: 5.000000e-04 eta: 23:01:39 time: 1.757155 data_time: 0.186674 memory: 9974 loss_kpt: 0.001725 loss: 0.001725 2022/09/15 05:51:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 05:51:11 - mmengine - INFO - Saving checkpoint at 68 epochs 2022/09/15 05:52:42 - mmengine - INFO - Epoch(train) [69][50/293] lr: 5.000000e-04 eta: 22:55:11 time: 1.752431 data_time: 0.173890 memory: 9974 loss_kpt: 0.001752 loss: 0.001752 2022/09/15 05:53:37 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 05:54:25 - mmengine - INFO - Epoch(train) [69][100/293] lr: 5.000000e-04 eta: 22:53:40 time: 2.068339 data_time: 0.092425 memory: 9974 loss_kpt: 0.001768 loss: 0.001768 2022/09/15 05:55:44 - mmengine - INFO - Epoch(train) [69][150/293] lr: 5.000000e-04 eta: 22:51:19 time: 1.578468 data_time: 0.299803 memory: 9974 loss_kpt: 0.001718 loss: 0.001718 2022/09/15 05:57:05 - mmengine - INFO - Epoch(train) [69][200/293] lr: 5.000000e-04 eta: 22:49:02 time: 1.620788 data_time: 0.424236 memory: 9974 loss_kpt: 0.001739 loss: 0.001739 2022/09/15 05:58:22 - mmengine - INFO - Epoch(train) [69][250/293] lr: 5.000000e-04 eta: 22:46:37 time: 1.531662 data_time: 0.085896 memory: 9974 loss_kpt: 0.001755 loss: 0.001755 2022/09/15 06:00:01 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 06:00:01 - mmengine - INFO - Saving checkpoint at 69 epochs 2022/09/15 06:01:40 - mmengine - INFO - Epoch(train) [70][50/293] lr: 5.000000e-04 eta: 22:40:31 time: 1.906631 data_time: 0.824806 memory: 9974 loss_kpt: 0.001750 loss: 0.001750 2022/09/15 06:03:16 - mmengine - INFO - Epoch(train) [70][100/293] lr: 5.000000e-04 eta: 22:38:46 time: 1.916580 data_time: 0.187742 memory: 9974 loss_kpt: 0.001724 loss: 0.001724 2022/09/15 06:04:51 - mmengine - INFO - Epoch(train) [70][150/293] lr: 5.000000e-04 eta: 22:36:59 time: 1.902418 data_time: 0.515625 memory: 9974 loss_kpt: 0.001708 loss: 0.001708 2022/09/15 06:06:45 - mmengine - INFO - Epoch(train) [70][200/293] lr: 5.000000e-04 eta: 22:35:51 time: 2.279072 data_time: 0.144425 memory: 9974 loss_kpt: 0.001746 loss: 0.001746 2022/09/15 06:08:22 - mmengine - INFO - Epoch(train) [70][250/293] lr: 5.000000e-04 eta: 22:34:08 time: 1.938586 data_time: 0.128441 memory: 9974 loss_kpt: 0.001729 loss: 0.001729 2022/09/15 06:09:18 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 06:09:18 - mmengine - INFO - Saving checkpoint at 70 epochs 2022/09/15 06:10:19 - mmengine - INFO - Epoch(val) [70][50/407] eta: 0:06:50 time: 1.150119 data_time: 0.993621 memory: 9974 2022/09/15 06:11:10 - mmengine - INFO - Epoch(val) [70][100/407] eta: 0:05:13 time: 1.019569 data_time: 0.872835 memory: 918 2022/09/15 06:11:44 - mmengine - INFO - Epoch(val) [70][150/407] eta: 0:02:56 time: 0.688185 data_time: 0.540163 memory: 918 2022/09/15 06:12:35 - mmengine - INFO - Epoch(val) [70][200/407] eta: 0:03:30 time: 1.015480 data_time: 0.863751 memory: 918 2022/09/15 06:13:01 - mmengine - INFO - Epoch(val) [70][250/407] eta: 0:01:22 time: 0.523781 data_time: 0.373658 memory: 918 2022/09/15 06:13:39 - mmengine - INFO - Epoch(val) [70][300/407] eta: 0:01:20 time: 0.748666 data_time: 0.602808 memory: 918 2022/09/15 06:14:08 - mmengine - INFO - Epoch(val) [70][350/407] eta: 0:00:33 time: 0.588056 data_time: 0.443070 memory: 918 2022/09/15 06:14:59 - mmengine - INFO - Epoch(val) [70][400/407] eta: 0:00:07 time: 1.009546 data_time: 0.865874 memory: 918 2022/09/15 06:16:23 - mmengine - INFO - Evaluating CocoMetric... 2022/09/15 06:16:36 - mmengine - INFO - Epoch(val) [70][407/407] coco/AP: 0.727931 coco/AP .5: 0.892731 coco/AP .75: 0.794738 coco/AP (M): 0.688480 coco/AP (L): 0.799601 coco/AR: 0.786902 coco/AR .5: 0.932620 coco/AR .75: 0.847922 coco/AR (M): 0.740863 coco/AR (L): 0.853809 2022/09/15 06:18:16 - mmengine - INFO - Epoch(train) [71][50/293] lr: 5.000000e-04 eta: 22:28:15 time: 1.989772 data_time: 0.278240 memory: 9974 loss_kpt: 0.001732 loss: 0.001732 2022/09/15 06:19:43 - mmengine - INFO - Epoch(train) [71][100/293] lr: 5.000000e-04 eta: 22:26:13 time: 1.735013 data_time: 0.194788 memory: 9974 loss_kpt: 0.001726 loss: 0.001726 2022/09/15 06:21:07 - mmengine - INFO - Epoch(train) [71][150/293] lr: 5.000000e-04 eta: 22:24:05 time: 1.680975 data_time: 0.263872 memory: 9974 loss_kpt: 0.001751 loss: 0.001751 2022/09/15 06:22:18 - mmengine - INFO - Epoch(train) [71][200/293] lr: 5.000000e-04 eta: 22:21:32 time: 1.421598 data_time: 0.205103 memory: 9974 loss_kpt: 0.001725 loss: 0.001725 2022/09/15 06:23:46 - mmengine - INFO - Epoch(train) [71][250/293] lr: 5.000000e-04 eta: 22:19:32 time: 1.752312 data_time: 0.357020 memory: 9974 loss_kpt: 0.001748 loss: 0.001748 2022/09/15 06:24:52 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 06:24:52 - mmengine - INFO - Saving checkpoint at 71 epochs 2022/09/15 06:26:24 - mmengine - INFO - Epoch(train) [72][50/293] lr: 5.000000e-04 eta: 22:13:23 time: 1.758932 data_time: 0.392069 memory: 9974 loss_kpt: 0.001724 loss: 0.001724 2022/09/15 06:27:45 - mmengine - INFO - Epoch(train) [72][100/293] lr: 5.000000e-04 eta: 22:11:11 time: 1.620012 data_time: 0.157591 memory: 9974 loss_kpt: 0.001736 loss: 0.001736 2022/09/15 06:28:58 - mmengine - INFO - Epoch(train) [72][150/293] lr: 5.000000e-04 eta: 22:08:43 time: 1.460045 data_time: 0.152697 memory: 9974 loss_kpt: 0.001748 loss: 0.001748 2022/09/15 06:30:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 06:30:32 - mmengine - INFO - Epoch(train) [72][200/293] lr: 5.000000e-04 eta: 22:06:58 time: 1.891638 data_time: 0.117386 memory: 9974 loss_kpt: 0.001728 loss: 0.001728 2022/09/15 06:32:28 - mmengine - INFO - Epoch(train) [72][250/293] lr: 5.000000e-04 eta: 22:05:53 time: 2.306731 data_time: 1.429050 memory: 9974 loss_kpt: 0.001754 loss: 0.001754 2022/09/15 06:34:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 06:34:02 - mmengine - INFO - Saving checkpoint at 72 epochs 2022/09/15 06:35:21 - mmengine - INFO - Epoch(train) [73][50/293] lr: 5.000000e-04 eta: 21:59:26 time: 1.518549 data_time: 0.319537 memory: 9974 loss_kpt: 0.001749 loss: 0.001749 2022/09/15 06:36:38 - mmengine - INFO - Epoch(train) [73][100/293] lr: 5.000000e-04 eta: 21:57:09 time: 1.548315 data_time: 0.182943 memory: 9974 loss_kpt: 0.001694 loss: 0.001694 2022/09/15 06:38:11 - mmengine - INFO - Epoch(train) [73][150/293] lr: 5.000000e-04 eta: 21:55:21 time: 1.856513 data_time: 0.098459 memory: 9974 loss_kpt: 0.001720 loss: 0.001720 2022/09/15 06:39:44 - mmengine - INFO - Epoch(train) [73][200/293] lr: 5.000000e-04 eta: 21:53:34 time: 1.860433 data_time: 0.087963 memory: 9974 loss_kpt: 0.001725 loss: 0.001725 2022/09/15 06:41:18 - mmengine - INFO - Epoch(train) [73][250/293] lr: 5.000000e-04 eta: 21:51:49 time: 1.883566 data_time: 0.130719 memory: 9974 loss_kpt: 0.001754 loss: 0.001754 2022/09/15 06:42:25 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 06:42:25 - mmengine - INFO - Saving checkpoint at 73 epochs 2022/09/15 06:43:53 - mmengine - INFO - Epoch(train) [74][50/293] lr: 5.000000e-04 eta: 21:45:43 time: 1.685324 data_time: 0.215312 memory: 9974 loss_kpt: 0.001751 loss: 0.001751 2022/09/15 06:45:40 - mmengine - INFO - Epoch(train) [74][100/293] lr: 5.000000e-04 eta: 21:44:23 time: 2.136408 data_time: 0.411972 memory: 9974 loss_kpt: 0.001747 loss: 0.001747 2022/09/15 06:47:36 - mmengine - INFO - Epoch(train) [74][150/293] lr: 5.000000e-04 eta: 21:43:19 time: 2.325121 data_time: 0.569193 memory: 9974 loss_kpt: 0.001682 loss: 0.001682 2022/09/15 06:49:03 - mmengine - INFO - Epoch(train) [74][200/293] lr: 5.000000e-04 eta: 21:41:21 time: 1.732241 data_time: 0.418735 memory: 9974 loss_kpt: 0.001738 loss: 0.001738 2022/09/15 06:50:34 - mmengine - INFO - Epoch(train) [74][250/293] lr: 5.000000e-04 eta: 21:39:32 time: 1.836467 data_time: 1.006117 memory: 9974 loss_kpt: 0.001733 loss: 0.001733 2022/09/15 06:51:40 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 06:51:40 - mmengine - INFO - Saving checkpoint at 74 epochs 2022/09/15 06:53:20 - mmengine - INFO - Epoch(train) [75][50/293] lr: 5.000000e-04 eta: 21:33:54 time: 1.921712 data_time: 0.693807 memory: 9974 loss_kpt: 0.001693 loss: 0.001693 2022/09/15 06:54:42 - mmengine - INFO - Epoch(train) [75][100/293] lr: 5.000000e-04 eta: 21:31:48 time: 1.642093 data_time: 0.134544 memory: 9974 loss_kpt: 0.001722 loss: 0.001722 2022/09/15 06:56:15 - mmengine - INFO - Epoch(train) [75][150/293] lr: 5.000000e-04 eta: 21:30:03 time: 1.871937 data_time: 0.714651 memory: 9974 loss_kpt: 0.001735 loss: 0.001735 2022/09/15 06:57:56 - mmengine - INFO - Epoch(train) [75][200/293] lr: 5.000000e-04 eta: 21:28:31 time: 2.009211 data_time: 0.162135 memory: 9974 loss_kpt: 0.001703 loss: 0.001703 2022/09/15 06:59:37 - mmengine - INFO - Epoch(train) [75][250/293] lr: 5.000000e-04 eta: 21:27:01 time: 2.035266 data_time: 0.090717 memory: 9974 loss_kpt: 0.001753 loss: 0.001753 2022/09/15 07:00:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 07:00:56 - mmengine - INFO - Saving checkpoint at 75 epochs 2022/09/15 07:01:40 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 07:02:51 - mmengine - INFO - Epoch(train) [76][50/293] lr: 5.000000e-04 eta: 21:21:55 time: 2.237218 data_time: 0.161293 memory: 9974 loss_kpt: 0.001729 loss: 0.001729 2022/09/15 07:04:35 - mmengine - INFO - Epoch(train) [76][100/293] lr: 5.000000e-04 eta: 21:20:30 time: 2.080771 data_time: 0.089366 memory: 9974 loss_kpt: 0.001724 loss: 0.001724 2022/09/15 07:06:25 - mmengine - INFO - Epoch(train) [76][150/293] lr: 5.000000e-04 eta: 21:19:15 time: 2.202013 data_time: 0.096476 memory: 9974 loss_kpt: 0.001752 loss: 0.001752 2022/09/15 07:08:06 - mmengine - INFO - Epoch(train) [76][200/293] lr: 5.000000e-04 eta: 21:17:45 time: 2.024218 data_time: 0.425513 memory: 9974 loss_kpt: 0.001747 loss: 0.001747 2022/09/15 07:09:49 - mmengine - INFO - Epoch(train) [76][250/293] lr: 5.000000e-04 eta: 21:16:17 time: 2.056968 data_time: 1.473903 memory: 9974 loss_kpt: 0.001742 loss: 0.001742 2022/09/15 07:11:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 07:11:13 - mmengine - INFO - Saving checkpoint at 76 epochs 2022/09/15 07:13:03 - mmengine - INFO - Epoch(train) [77][50/293] lr: 5.000000e-04 eta: 21:11:06 time: 2.144498 data_time: 0.325521 memory: 9974 loss_kpt: 0.001704 loss: 0.001704 2022/09/15 07:15:04 - mmengine - INFO - Epoch(train) [77][100/293] lr: 5.000000e-04 eta: 21:10:09 time: 2.407667 data_time: 0.111020 memory: 9974 loss_kpt: 0.001711 loss: 0.001711 2022/09/15 07:16:26 - mmengine - INFO - Epoch(train) [77][150/293] lr: 5.000000e-04 eta: 21:08:05 time: 1.639503 data_time: 0.618006 memory: 9974 loss_kpt: 0.001710 loss: 0.001710 2022/09/15 07:18:03 - mmengine - INFO - Epoch(train) [77][200/293] lr: 5.000000e-04 eta: 21:06:27 time: 1.933801 data_time: 0.503729 memory: 9974 loss_kpt: 0.001747 loss: 0.001747 2022/09/15 07:19:34 - mmengine - INFO - Epoch(train) [77][250/293] lr: 5.000000e-04 eta: 21:04:40 time: 1.835700 data_time: 0.783190 memory: 9974 loss_kpt: 0.001722 loss: 0.001722 2022/09/15 07:20:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 07:20:35 - mmengine - INFO - Saving checkpoint at 77 epochs 2022/09/15 07:22:02 - mmengine - INFO - Epoch(train) [78][50/293] lr: 5.000000e-04 eta: 20:58:51 time: 1.665425 data_time: 0.262319 memory: 9974 loss_kpt: 0.001685 loss: 0.001685 2022/09/15 07:23:33 - mmengine - INFO - Epoch(train) [78][100/293] lr: 5.000000e-04 eta: 20:57:04 time: 1.824698 data_time: 0.163163 memory: 9974 loss_kpt: 0.001715 loss: 0.001715 2022/09/15 07:24:58 - mmengine - INFO - Epoch(train) [78][150/293] lr: 5.000000e-04 eta: 20:55:07 time: 1.701516 data_time: 0.093245 memory: 9974 loss_kpt: 0.001708 loss: 0.001708 2022/09/15 07:26:09 - mmengine - INFO - Epoch(train) [78][200/293] lr: 5.000000e-04 eta: 20:52:46 time: 1.427354 data_time: 0.095323 memory: 9974 loss_kpt: 0.001737 loss: 0.001737 2022/09/15 07:27:58 - mmengine - INFO - Epoch(train) [78][250/293] lr: 5.000000e-04 eta: 20:51:29 time: 2.172029 data_time: 0.093953 memory: 9974 loss_kpt: 0.001702 loss: 0.001702 2022/09/15 07:29:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 07:29:08 - mmengine - INFO - Saving checkpoint at 78 epochs 2022/09/15 07:30:30 - mmengine - INFO - Epoch(train) [79][50/293] lr: 5.000000e-04 eta: 20:45:36 time: 1.565230 data_time: 0.260072 memory: 9974 loss_kpt: 0.001707 loss: 0.001707 2022/09/15 07:32:14 - mmengine - INFO - Epoch(train) [79][100/293] lr: 5.000000e-04 eta: 20:44:12 time: 2.080397 data_time: 0.092786 memory: 9974 loss_kpt: 0.001717 loss: 0.001717 2022/09/15 07:33:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 07:33:49 - mmengine - INFO - Epoch(train) [79][150/293] lr: 5.000000e-04 eta: 20:42:32 time: 1.896327 data_time: 0.099387 memory: 9974 loss_kpt: 0.001687 loss: 0.001687 2022/09/15 07:35:27 - mmengine - INFO - Epoch(train) [79][200/293] lr: 5.000000e-04 eta: 20:40:58 time: 1.972611 data_time: 0.091763 memory: 9974 loss_kpt: 0.001689 loss: 0.001689 2022/09/15 07:36:35 - mmengine - INFO - Epoch(train) [79][250/293] lr: 5.000000e-04 eta: 20:38:33 time: 1.355574 data_time: 0.194858 memory: 9974 loss_kpt: 0.001713 loss: 0.001713 2022/09/15 07:37:37 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 07:37:37 - mmengine - INFO - Saving checkpoint at 79 epochs 2022/09/15 07:39:00 - mmengine - INFO - Epoch(train) [80][50/293] lr: 5.000000e-04 eta: 20:32:48 time: 1.599658 data_time: 0.177150 memory: 9974 loss_kpt: 0.001721 loss: 0.001721 2022/09/15 07:40:25 - mmengine - INFO - Epoch(train) [80][100/293] lr: 5.000000e-04 eta: 20:30:53 time: 1.696971 data_time: 0.094069 memory: 9974 loss_kpt: 0.001755 loss: 0.001755 2022/09/15 07:41:49 - mmengine - INFO - Epoch(train) [80][150/293] lr: 5.000000e-04 eta: 20:28:56 time: 1.679165 data_time: 0.323785 memory: 9974 loss_kpt: 0.001718 loss: 0.001718 2022/09/15 07:43:42 - mmengine - INFO - Epoch(train) [80][200/293] lr: 5.000000e-04 eta: 20:27:46 time: 2.259261 data_time: 0.409284 memory: 9974 loss_kpt: 0.001722 loss: 0.001722 2022/09/15 07:45:14 - mmengine - INFO - Epoch(train) [80][250/293] lr: 5.000000e-04 eta: 20:26:03 time: 1.848240 data_time: 1.270998 memory: 9974 loss_kpt: 0.001731 loss: 0.001731 2022/09/15 07:46:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 07:46:50 - mmengine - INFO - Saving checkpoint at 80 epochs 2022/09/15 07:47:46 - mmengine - INFO - Epoch(val) [80][50/407] eta: 0:06:16 time: 1.054229 data_time: 0.901992 memory: 9974 2022/09/15 07:48:53 - mmengine - INFO - Epoch(val) [80][100/407] eta: 0:06:49 time: 1.332838 data_time: 1.183216 memory: 918 2022/09/15 07:49:31 - mmengine - INFO - Epoch(val) [80][150/407] eta: 0:03:16 time: 0.763427 data_time: 0.619529 memory: 918 2022/09/15 07:50:20 - mmengine - INFO - Epoch(val) [80][200/407] eta: 0:03:22 time: 0.976813 data_time: 0.826261 memory: 918 2022/09/15 07:50:58 - mmengine - INFO - Epoch(val) [80][250/407] eta: 0:01:59 time: 0.760538 data_time: 0.613261 memory: 918 2022/09/15 07:51:46 - mmengine - INFO - Epoch(val) [80][300/407] eta: 0:01:44 time: 0.974994 data_time: 0.828811 memory: 918 2022/09/15 07:52:20 - mmengine - INFO - Epoch(val) [80][350/407] eta: 0:00:38 time: 0.671636 data_time: 0.527093 memory: 918 2022/09/15 07:53:53 - mmengine - INFO - Epoch(val) [80][400/407] eta: 0:00:12 time: 1.855781 data_time: 1.697234 memory: 918 2022/09/15 07:54:29 - mmengine - INFO - Evaluating CocoMetric... 2022/09/15 07:54:43 - mmengine - INFO - Epoch(val) [80][407/407] coco/AP: 0.734049 coco/AP .5: 0.897757 coco/AP .75: 0.805669 coco/AP (M): 0.696299 coco/AP (L): 0.800892 coco/AR: 0.788586 coco/AR .5: 0.933879 coco/AR .75: 0.852330 coco/AR (M): 0.743294 coco/AR (L): 0.853883 2022/09/15 07:54:43 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/udp_regress/best_coco/AP_epoch_60.pth is removed 2022/09/15 07:54:45 - mmengine - INFO - The best checkpoint with 0.7340 coco/AP at 80 epoch is saved to best_coco/AP_epoch_80.pth. 2022/09/15 07:56:28 - mmengine - INFO - Epoch(train) [81][50/293] lr: 5.000000e-04 eta: 20:21:00 time: 2.065087 data_time: 0.604872 memory: 9974 loss_kpt: 0.001724 loss: 0.001724 2022/09/15 07:57:48 - mmengine - INFO - Epoch(train) [81][100/293] lr: 5.000000e-04 eta: 20:18:57 time: 1.591641 data_time: 0.394998 memory: 9974 loss_kpt: 0.001743 loss: 0.001743 2022/09/15 07:59:10 - mmengine - INFO - Epoch(train) [81][150/293] lr: 5.000000e-04 eta: 20:16:58 time: 1.639469 data_time: 0.317412 memory: 9974 loss_kpt: 0.001719 loss: 0.001719 2022/09/15 08:00:54 - mmengine - INFO - Epoch(train) [81][200/293] lr: 5.000000e-04 eta: 20:15:35 time: 2.085227 data_time: 1.148181 memory: 9974 loss_kpt: 0.001714 loss: 0.001714 2022/09/15 08:02:54 - mmengine - INFO - Epoch(train) [81][250/293] lr: 5.000000e-04 eta: 20:14:37 time: 2.408099 data_time: 1.813645 memory: 9974 loss_kpt: 0.001724 loss: 0.001724 2022/09/15 08:04:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 08:04:27 - mmengine - INFO - Saving checkpoint at 81 epochs 2022/09/15 08:06:07 - mmengine - INFO - Epoch(train) [82][50/293] lr: 5.000000e-04 eta: 20:09:26 time: 1.921885 data_time: 0.133392 memory: 9974 loss_kpt: 0.001688 loss: 0.001688 2022/09/15 08:07:39 - mmengine - INFO - Epoch(train) [82][100/293] lr: 5.000000e-04 eta: 20:07:44 time: 1.841949 data_time: 0.103508 memory: 9974 loss_kpt: 0.001711 loss: 0.001711 2022/09/15 08:09:54 - mmengine - INFO - Epoch(train) [82][150/293] lr: 5.000000e-04 eta: 20:07:09 time: 2.709979 data_time: 0.170063 memory: 9974 loss_kpt: 0.001727 loss: 0.001727 2022/09/15 08:11:29 - mmengine - INFO - Epoch(train) [82][200/293] lr: 5.000000e-04 eta: 20:05:30 time: 1.887794 data_time: 0.098636 memory: 9974 loss_kpt: 0.001705 loss: 0.001705 2022/09/15 08:13:00 - mmengine - INFO - Epoch(train) [82][250/293] lr: 5.000000e-04 eta: 20:03:46 time: 1.820015 data_time: 0.112709 memory: 9974 loss_kpt: 0.001721 loss: 0.001721 2022/09/15 08:13:38 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 08:14:25 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 08:14:25 - mmengine - INFO - Saving checkpoint at 82 epochs 2022/09/15 08:15:58 - mmengine - INFO - Epoch(train) [83][50/293] lr: 5.000000e-04 eta: 19:58:28 time: 1.783674 data_time: 0.321208 memory: 9974 loss_kpt: 0.001738 loss: 0.001738 2022/09/15 08:17:29 - mmengine - INFO - Epoch(train) [83][100/293] lr: 5.000000e-04 eta: 19:56:45 time: 1.832010 data_time: 0.477974 memory: 9974 loss_kpt: 0.001708 loss: 0.001708 2022/09/15 08:18:54 - mmengine - INFO - Epoch(train) [83][150/293] lr: 5.000000e-04 eta: 19:54:51 time: 1.688679 data_time: 0.680382 memory: 9974 loss_kpt: 0.001681 loss: 0.001681 2022/09/15 08:20:36 - mmengine - INFO - Epoch(train) [83][200/293] lr: 5.000000e-04 eta: 19:53:25 time: 2.044531 data_time: 0.087515 memory: 9974 loss_kpt: 0.001746 loss: 0.001746 2022/09/15 08:22:32 - mmengine - INFO - Epoch(train) [83][250/293] lr: 5.000000e-04 eta: 19:52:20 time: 2.326163 data_time: 0.097072 memory: 9974 loss_kpt: 0.001726 loss: 0.001726 2022/09/15 08:23:54 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 08:23:54 - mmengine - INFO - Saving checkpoint at 83 epochs 2022/09/15 08:25:24 - mmengine - INFO - Epoch(train) [84][50/293] lr: 5.000000e-04 eta: 19:47:01 time: 1.736859 data_time: 0.200330 memory: 9974 loss_kpt: 0.001683 loss: 0.001683 2022/09/15 08:27:22 - mmengine - INFO - Epoch(train) [84][100/293] lr: 5.000000e-04 eta: 19:45:59 time: 2.357129 data_time: 0.886091 memory: 9974 loss_kpt: 0.001708 loss: 0.001708 2022/09/15 08:29:02 - mmengine - INFO - Epoch(train) [84][150/293] lr: 5.000000e-04 eta: 19:44:29 time: 1.993922 data_time: 0.088427 memory: 9974 loss_kpt: 0.001686 loss: 0.001686 2022/09/15 08:30:57 - mmengine - INFO - Epoch(train) [84][200/293] lr: 5.000000e-04 eta: 19:43:23 time: 2.308609 data_time: 0.094820 memory: 9974 loss_kpt: 0.001733 loss: 0.001733 2022/09/15 08:32:34 - mmengine - INFO - Epoch(train) [84][250/293] lr: 5.000000e-04 eta: 19:41:47 time: 1.927790 data_time: 0.080580 memory: 9974 loss_kpt: 0.001694 loss: 0.001694 2022/09/15 08:33:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 08:33:59 - mmengine - INFO - Saving checkpoint at 84 epochs 2022/09/15 08:35:23 - mmengine - INFO - Epoch(train) [85][50/293] lr: 5.000000e-04 eta: 19:36:23 time: 1.619045 data_time: 0.992316 memory: 9974 loss_kpt: 0.001708 loss: 0.001708 2022/09/15 08:36:47 - mmengine - INFO - Epoch(train) [85][100/293] lr: 5.000000e-04 eta: 19:34:29 time: 1.670299 data_time: 0.987233 memory: 9974 loss_kpt: 0.001716 loss: 0.001716 2022/09/15 08:38:02 - mmengine - INFO - Epoch(train) [85][150/293] lr: 5.000000e-04 eta: 19:32:24 time: 1.512542 data_time: 0.180014 memory: 9974 loss_kpt: 0.001700 loss: 0.001700 2022/09/15 08:39:45 - mmengine - INFO - Epoch(train) [85][200/293] lr: 5.000000e-04 eta: 19:30:58 time: 2.049837 data_time: 0.104119 memory: 9974 loss_kpt: 0.001670 loss: 0.001670 2022/09/15 08:42:20 - mmengine - INFO - Epoch(train) [85][250/293] lr: 5.000000e-04 eta: 19:30:51 time: 3.106196 data_time: 0.101108 memory: 9974 loss_kpt: 0.001690 loss: 0.001690 2022/09/15 08:44:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 08:44:11 - mmengine - INFO - Saving checkpoint at 85 epochs 2022/09/15 08:45:46 - mmengine - INFO - Epoch(train) [86][50/293] lr: 5.000000e-04 eta: 19:25:45 time: 1.828289 data_time: 0.284984 memory: 9974 loss_kpt: 0.001719 loss: 0.001719 2022/09/15 08:47:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 08:47:37 - mmengine - INFO - Epoch(train) [86][100/293] lr: 5.000000e-04 eta: 19:24:33 time: 2.227963 data_time: 0.115361 memory: 9974 loss_kpt: 0.001698 loss: 0.001698 2022/09/15 08:49:08 - mmengine - INFO - Epoch(train) [86][150/293] lr: 5.000000e-04 eta: 19:22:50 time: 1.818654 data_time: 0.206915 memory: 9974 loss_kpt: 0.001706 loss: 0.001706 2022/09/15 08:50:55 - mmengine - INFO - Epoch(train) [86][200/293] lr: 5.000000e-04 eta: 19:21:31 time: 2.137533 data_time: 0.602230 memory: 9974 loss_kpt: 0.001735 loss: 0.001735 2022/09/15 08:52:22 - mmengine - INFO - Epoch(train) [86][250/293] lr: 5.000000e-04 eta: 19:19:42 time: 1.735856 data_time: 0.141234 memory: 9974 loss_kpt: 0.001706 loss: 0.001706 2022/09/15 08:53:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 08:53:35 - mmengine - INFO - Saving checkpoint at 86 epochs 2022/09/15 08:54:55 - mmengine - INFO - Epoch(train) [87][50/293] lr: 5.000000e-04 eta: 19:14:19 time: 1.536821 data_time: 0.259410 memory: 9974 loss_kpt: 0.001699 loss: 0.001699 2022/09/15 08:56:20 - mmengine - INFO - Epoch(train) [87][100/293] lr: 5.000000e-04 eta: 19:12:29 time: 1.704860 data_time: 0.173589 memory: 9974 loss_kpt: 0.001720 loss: 0.001720 2022/09/15 08:57:48 - mmengine - INFO - Epoch(train) [87][150/293] lr: 5.000000e-04 eta: 19:10:43 time: 1.761300 data_time: 0.104729 memory: 9974 loss_kpt: 0.001715 loss: 0.001715 2022/09/15 08:59:23 - mmengine - INFO - Epoch(train) [87][200/293] lr: 5.000000e-04 eta: 19:09:07 time: 1.893359 data_time: 0.132949 memory: 9974 loss_kpt: 0.001685 loss: 0.001685 2022/09/15 09:01:17 - mmengine - INFO - Epoch(train) [87][250/293] lr: 5.000000e-04 eta: 19:07:58 time: 2.283679 data_time: 0.468678 memory: 9974 loss_kpt: 0.001712 loss: 0.001712 2022/09/15 09:03:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 09:03:07 - mmengine - INFO - Saving checkpoint at 87 epochs 2022/09/15 09:05:08 - mmengine - INFO - Epoch(train) [88][50/293] lr: 5.000000e-04 eta: 19:03:36 time: 2.357471 data_time: 1.628553 memory: 9974 loss_kpt: 0.001715 loss: 0.001715 2022/09/15 09:07:14 - mmengine - INFO - Epoch(train) [88][100/293] lr: 5.000000e-04 eta: 19:02:44 time: 2.522164 data_time: 1.119296 memory: 9974 loss_kpt: 0.001688 loss: 0.001688 2022/09/15 09:09:10 - mmengine - INFO - Epoch(train) [88][150/293] lr: 5.000000e-04 eta: 19:01:37 time: 2.307081 data_time: 0.098396 memory: 9974 loss_kpt: 0.001722 loss: 0.001722 2022/09/15 09:10:46 - mmengine - INFO - Epoch(train) [88][200/293] lr: 5.000000e-04 eta: 19:00:03 time: 1.933101 data_time: 0.216655 memory: 9974 loss_kpt: 0.001715 loss: 0.001715 2022/09/15 09:12:15 - mmengine - INFO - Epoch(train) [88][250/293] lr: 5.000000e-04 eta: 18:58:18 time: 1.773035 data_time: 0.123168 memory: 9974 loss_kpt: 0.001698 loss: 0.001698 2022/09/15 09:13:45 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 09:13:45 - mmengine - INFO - Saving checkpoint at 88 epochs 2022/09/15 09:15:26 - mmengine - INFO - Epoch(train) [89][50/293] lr: 5.000000e-04 eta: 18:53:31 time: 1.964090 data_time: 0.119612 memory: 9974 loss_kpt: 0.001705 loss: 0.001705 2022/09/15 09:17:01 - mmengine - INFO - Epoch(train) [89][100/293] lr: 5.000000e-04 eta: 18:51:55 time: 1.898241 data_time: 0.093988 memory: 9974 loss_kpt: 0.001721 loss: 0.001721 2022/09/15 09:18:34 - mmengine - INFO - Epoch(train) [89][150/293] lr: 5.000000e-04 eta: 18:50:16 time: 1.842957 data_time: 0.093596 memory: 9974 loss_kpt: 0.001680 loss: 0.001680 2022/09/15 09:19:59 - mmengine - INFO - Epoch(train) [89][200/293] lr: 5.000000e-04 eta: 18:48:28 time: 1.716090 data_time: 0.199051 memory: 9974 loss_kpt: 0.001716 loss: 0.001716 2022/09/15 09:20:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 09:21:25 - mmengine - INFO - Epoch(train) [89][250/293] lr: 5.000000e-04 eta: 18:46:39 time: 1.705994 data_time: 0.090696 memory: 9974 loss_kpt: 0.001725 loss: 0.001725 2022/09/15 09:22:48 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 09:22:48 - mmengine - INFO - Saving checkpoint at 89 epochs 2022/09/15 09:24:31 - mmengine - INFO - Epoch(train) [90][50/293] lr: 5.000000e-04 eta: 18:41:58 time: 2.005690 data_time: 0.215158 memory: 9974 loss_kpt: 0.001737 loss: 0.001737 2022/09/15 09:26:37 - mmengine - INFO - Epoch(train) [90][100/293] lr: 5.000000e-04 eta: 18:41:04 time: 2.513409 data_time: 0.112897 memory: 9974 loss_kpt: 0.001686 loss: 0.001686 2022/09/15 09:28:45 - mmengine - INFO - Epoch(train) [90][150/293] lr: 5.000000e-04 eta: 18:40:14 time: 2.569771 data_time: 1.472276 memory: 9974 loss_kpt: 0.001722 loss: 0.001722 2022/09/15 09:30:34 - mmengine - INFO - Epoch(train) [90][200/293] lr: 5.000000e-04 eta: 18:38:56 time: 2.163157 data_time: 1.523642 memory: 9974 loss_kpt: 0.001691 loss: 0.001691 2022/09/15 09:32:12 - mmengine - INFO - Epoch(train) [90][250/293] lr: 5.000000e-04 eta: 18:37:25 time: 1.961359 data_time: 0.695827 memory: 9974 loss_kpt: 0.001703 loss: 0.001703 2022/09/15 09:33:24 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 09:33:24 - mmengine - INFO - Saving checkpoint at 90 epochs 2022/09/15 09:34:10 - mmengine - INFO - Epoch(val) [90][50/407] eta: 0:05:04 time: 0.852237 data_time: 0.698670 memory: 9974 2022/09/15 09:35:12 - mmengine - INFO - Epoch(val) [90][100/407] eta: 0:06:18 time: 1.232797 data_time: 1.076025 memory: 918 2022/09/15 09:35:57 - mmengine - INFO - Epoch(val) [90][150/407] eta: 0:03:52 time: 0.905349 data_time: 0.758046 memory: 918 2022/09/15 09:36:37 - mmengine - INFO - Epoch(val) [90][200/407] eta: 0:02:45 time: 0.800503 data_time: 0.653113 memory: 918 2022/09/15 09:37:02 - mmengine - INFO - Epoch(val) [90][250/407] eta: 0:01:17 time: 0.496480 data_time: 0.353103 memory: 918 2022/09/15 09:37:44 - mmengine - INFO - Epoch(val) [90][300/407] eta: 0:01:28 time: 0.830347 data_time: 0.686469 memory: 918 2022/09/15 09:38:21 - mmengine - INFO - Epoch(val) [90][350/407] eta: 0:00:43 time: 0.755590 data_time: 0.610049 memory: 918 2022/09/15 09:38:57 - mmengine - INFO - Epoch(val) [90][400/407] eta: 0:00:04 time: 0.706270 data_time: 0.555784 memory: 918 2022/09/15 09:40:23 - mmengine - INFO - Evaluating CocoMetric... 2022/09/15 09:40:36 - mmengine - INFO - Epoch(val) [90][407/407] coco/AP: 0.731628 coco/AP .5: 0.897140 coco/AP .75: 0.796357 coco/AP (M): 0.693325 coco/AP (L): 0.800978 coco/AR: 0.790113 coco/AR .5: 0.937028 coco/AR .75: 0.849654 coco/AR (M): 0.745780 coco/AR (L): 0.854255 2022/09/15 09:42:41 - mmengine - INFO - Epoch(train) [91][50/293] lr: 5.000000e-04 eta: 18:33:18 time: 2.491798 data_time: 0.303259 memory: 9974 loss_kpt: 0.001728 loss: 0.001728 2022/09/15 09:44:31 - mmengine - INFO - Epoch(train) [91][100/293] lr: 5.000000e-04 eta: 18:32:03 time: 2.209827 data_time: 0.141741 memory: 9974 loss_kpt: 0.001699 loss: 0.001699 2022/09/15 09:45:44 - mmengine - INFO - Epoch(train) [91][150/293] lr: 5.000000e-04 eta: 18:29:58 time: 1.455515 data_time: 0.276796 memory: 9974 loss_kpt: 0.001689 loss: 0.001689 2022/09/15 09:47:38 - mmengine - INFO - Epoch(train) [91][200/293] lr: 5.000000e-04 eta: 18:28:48 time: 2.282259 data_time: 0.658057 memory: 9974 loss_kpt: 0.001707 loss: 0.001707 2022/09/15 09:49:19 - mmengine - INFO - Epoch(train) [91][250/293] lr: 5.000000e-04 eta: 18:27:20 time: 2.014563 data_time: 0.606288 memory: 9974 loss_kpt: 0.001680 loss: 0.001680 2022/09/15 09:50:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 09:50:27 - mmengine - INFO - Saving checkpoint at 91 epochs 2022/09/15 09:52:16 - mmengine - INFO - Epoch(train) [92][50/293] lr: 5.000000e-04 eta: 18:22:49 time: 2.102372 data_time: 0.294447 memory: 9974 loss_kpt: 0.001699 loss: 0.001699 2022/09/15 09:53:39 - mmengine - INFO - Epoch(train) [92][100/293] lr: 5.000000e-04 eta: 18:20:59 time: 1.660064 data_time: 0.166015 memory: 9974 loss_kpt: 0.001699 loss: 0.001699 2022/09/15 09:55:58 - mmengine - INFO - Epoch(train) [92][150/293] lr: 5.000000e-04 eta: 18:20:21 time: 2.776356 data_time: 0.340320 memory: 9974 loss_kpt: 0.001695 loss: 0.001695 2022/09/15 09:57:53 - mmengine - INFO - Epoch(train) [92][200/293] lr: 5.000000e-04 eta: 18:19:12 time: 2.311128 data_time: 0.091694 memory: 9974 loss_kpt: 0.001710 loss: 0.001710 2022/09/15 09:59:16 - mmengine - INFO - Epoch(train) [92][250/293] lr: 5.000000e-04 eta: 18:17:21 time: 1.659073 data_time: 0.163891 memory: 9974 loss_kpt: 0.001723 loss: 0.001723 2022/09/15 10:00:39 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 10:00:39 - mmengine - INFO - Saving checkpoint at 92 epochs 2022/09/15 10:01:58 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 10:02:13 - mmengine - INFO - Epoch(train) [93][50/293] lr: 5.000000e-04 eta: 18:12:33 time: 1.793445 data_time: 0.196597 memory: 9974 loss_kpt: 0.001690 loss: 0.001690 2022/09/15 10:04:13 - mmengine - INFO - Epoch(train) [93][100/293] lr: 5.000000e-04 eta: 18:11:30 time: 2.405441 data_time: 0.526468 memory: 9974 loss_kpt: 0.001699 loss: 0.001699 2022/09/15 10:05:43 - mmengine - INFO - Epoch(train) [93][150/293] lr: 5.000000e-04 eta: 18:09:48 time: 1.795134 data_time: 0.222277 memory: 9974 loss_kpt: 0.001717 loss: 0.001717 2022/09/15 10:07:06 - mmengine - INFO - Epoch(train) [93][200/293] lr: 5.000000e-04 eta: 18:07:59 time: 1.671792 data_time: 0.241607 memory: 9974 loss_kpt: 0.001701 loss: 0.001701 2022/09/15 10:09:13 - mmengine - INFO - Epoch(train) [93][250/293] lr: 5.000000e-04 eta: 18:07:04 time: 2.534985 data_time: 0.102458 memory: 9974 loss_kpt: 0.001702 loss: 0.001702 2022/09/15 10:11:10 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 10:11:10 - mmengine - INFO - Saving checkpoint at 93 epochs 2022/09/15 10:12:49 - mmengine - INFO - Epoch(train) [94][50/293] lr: 5.000000e-04 eta: 18:02:26 time: 1.918670 data_time: 0.279945 memory: 9974 loss_kpt: 0.001686 loss: 0.001686 2022/09/15 10:14:15 - mmengine - INFO - Epoch(train) [94][100/293] lr: 5.000000e-04 eta: 18:00:40 time: 1.710954 data_time: 0.339143 memory: 9974 loss_kpt: 0.001713 loss: 0.001713 2022/09/15 10:15:39 - mmengine - INFO - Epoch(train) [94][150/293] lr: 5.000000e-04 eta: 17:58:52 time: 1.691630 data_time: 0.090578 memory: 9974 loss_kpt: 0.001698 loss: 0.001698 2022/09/15 10:18:02 - mmengine - INFO - Epoch(train) [94][200/293] lr: 5.000000e-04 eta: 17:58:17 time: 2.862691 data_time: 0.094370 memory: 9974 loss_kpt: 0.001672 loss: 0.001672 2022/09/15 10:19:35 - mmengine - INFO - Epoch(train) [94][250/293] lr: 5.000000e-04 eta: 17:56:39 time: 1.845156 data_time: 0.132878 memory: 9974 loss_kpt: 0.001694 loss: 0.001694 2022/09/15 10:20:37 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 10:20:37 - mmengine - INFO - Saving checkpoint at 94 epochs 2022/09/15 10:22:03 - mmengine - INFO - Epoch(train) [95][50/293] lr: 5.000000e-04 eta: 17:51:47 time: 1.650959 data_time: 0.920945 memory: 9974 loss_kpt: 0.001691 loss: 0.001691 2022/09/15 10:23:57 - mmengine - INFO - Epoch(train) [95][100/293] lr: 5.000000e-04 eta: 17:50:36 time: 2.279310 data_time: 0.101593 memory: 9974 loss_kpt: 0.001704 loss: 0.001704 2022/09/15 10:25:35 - mmengine - INFO - Epoch(train) [95][150/293] lr: 5.000000e-04 eta: 17:49:04 time: 1.951017 data_time: 0.145628 memory: 9974 loss_kpt: 0.001674 loss: 0.001674 2022/09/15 10:26:51 - mmengine - INFO - Epoch(train) [95][200/293] lr: 5.000000e-04 eta: 17:47:07 time: 1.518876 data_time: 0.102369 memory: 9974 loss_kpt: 0.001698 loss: 0.001698 2022/09/15 10:28:35 - mmengine - INFO - Epoch(train) [95][250/293] lr: 5.000000e-04 eta: 17:45:43 time: 2.086119 data_time: 0.091862 memory: 9974 loss_kpt: 0.001708 loss: 0.001708 2022/09/15 10:30:12 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 10:30:12 - mmengine - INFO - Saving checkpoint at 95 epochs 2022/09/15 10:31:58 - mmengine - INFO - Epoch(train) [96][50/293] lr: 5.000000e-04 eta: 17:41:18 time: 2.049724 data_time: 0.146517 memory: 9974 loss_kpt: 0.001717 loss: 0.001717 2022/09/15 10:33:46 - mmengine - INFO - Epoch(train) [96][100/293] lr: 5.000000e-04 eta: 17:39:59 time: 2.158466 data_time: 0.125531 memory: 9974 loss_kpt: 0.001685 loss: 0.001685 2022/09/15 10:35:23 - mmengine - INFO - Epoch(train) [96][150/293] lr: 5.000000e-04 eta: 17:38:28 time: 1.951197 data_time: 0.096932 memory: 9974 loss_kpt: 0.001702 loss: 0.001702 2022/09/15 10:36:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 10:37:16 - mmengine - INFO - Epoch(train) [96][200/293] lr: 5.000000e-04 eta: 17:37:15 time: 2.251422 data_time: 0.161568 memory: 9974 loss_kpt: 0.001676 loss: 0.001676 2022/09/15 10:39:03 - mmengine - INFO - Epoch(train) [96][250/293] lr: 5.000000e-04 eta: 17:35:55 time: 2.139158 data_time: 0.242698 memory: 9974 loss_kpt: 0.001734 loss: 0.001734 2022/09/15 10:40:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 10:40:08 - mmengine - INFO - Saving checkpoint at 96 epochs 2022/09/15 10:41:48 - mmengine - INFO - Epoch(train) [97][50/293] lr: 5.000000e-04 eta: 17:31:24 time: 1.919355 data_time: 0.482682 memory: 9974 loss_kpt: 0.001696 loss: 0.001696 2022/09/15 10:43:45 - mmengine - INFO - Epoch(train) [97][100/293] lr: 5.000000e-04 eta: 17:30:16 time: 2.350616 data_time: 0.085079 memory: 9974 loss_kpt: 0.001690 loss: 0.001690 2022/09/15 10:45:38 - mmengine - INFO - Epoch(train) [97][150/293] lr: 5.000000e-04 eta: 17:29:03 time: 2.259098 data_time: 0.088693 memory: 9974 loss_kpt: 0.001697 loss: 0.001697 2022/09/15 10:47:10 - mmengine - INFO - Epoch(train) [97][200/293] lr: 5.000000e-04 eta: 17:27:25 time: 1.836418 data_time: 0.087181 memory: 9974 loss_kpt: 0.001729 loss: 0.001729 2022/09/15 10:49:09 - mmengine - INFO - Epoch(train) [97][250/293] lr: 5.000000e-04 eta: 17:26:19 time: 2.382686 data_time: 0.097675 memory: 9974 loss_kpt: 0.001675 loss: 0.001675 2022/09/15 10:50:38 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 10:50:38 - mmengine - INFO - Saving checkpoint at 97 epochs 2022/09/15 10:52:34 - mmengine - INFO - Epoch(train) [98][50/293] lr: 5.000000e-04 eta: 17:22:10 time: 2.257130 data_time: 0.371163 memory: 9974 loss_kpt: 0.001710 loss: 0.001710 2022/09/15 10:54:02 - mmengine - INFO - Epoch(train) [98][100/293] lr: 5.000000e-04 eta: 17:20:27 time: 1.751787 data_time: 0.127104 memory: 9974 loss_kpt: 0.001703 loss: 0.001703 2022/09/15 10:55:58 - mmengine - INFO - Epoch(train) [98][150/293] lr: 5.000000e-04 eta: 17:19:17 time: 2.322270 data_time: 0.104023 memory: 9974 loss_kpt: 0.001666 loss: 0.001666 2022/09/15 10:57:24 - mmengine - INFO - Epoch(train) [98][200/293] lr: 5.000000e-04 eta: 17:17:34 time: 1.731318 data_time: 0.105082 memory: 9974 loss_kpt: 0.001690 loss: 0.001690 2022/09/15 10:58:59 - mmengine - INFO - Epoch(train) [98][250/293] lr: 5.000000e-04 eta: 17:15:59 time: 1.888470 data_time: 0.351453 memory: 9974 loss_kpt: 0.001676 loss: 0.001676 2022/09/15 11:00:25 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 11:00:25 - mmengine - INFO - Saving checkpoint at 98 epochs 2022/09/15 11:01:50 - mmengine - INFO - Epoch(train) [99][50/293] lr: 5.000000e-04 eta: 17:11:15 time: 1.630461 data_time: 0.522827 memory: 9974 loss_kpt: 0.001713 loss: 0.001713 2022/09/15 11:03:21 - mmengine - INFO - Epoch(train) [99][100/293] lr: 5.000000e-04 eta: 17:09:37 time: 1.818301 data_time: 0.167963 memory: 9974 loss_kpt: 0.001700 loss: 0.001700 2022/09/15 11:04:57 - mmengine - INFO - Epoch(train) [99][150/293] lr: 5.000000e-04 eta: 17:08:05 time: 1.928995 data_time: 0.348869 memory: 9974 loss_kpt: 0.001680 loss: 0.001680 2022/09/15 11:06:44 - mmengine - INFO - Epoch(train) [99][200/293] lr: 5.000000e-04 eta: 17:06:44 time: 2.132578 data_time: 1.080074 memory: 9974 loss_kpt: 0.001683 loss: 0.001683 2022/09/15 11:08:27 - mmengine - INFO - Epoch(train) [99][250/293] lr: 5.000000e-04 eta: 17:05:19 time: 2.060000 data_time: 0.217114 memory: 9974 loss_kpt: 0.001709 loss: 0.001709 2022/09/15 11:09:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 11:10:01 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 11:10:02 - mmengine - INFO - Saving checkpoint at 99 epochs 2022/09/15 11:12:29 - mmengine - INFO - Epoch(train) [100][50/293] lr: 5.000000e-04 eta: 17:01:49 time: 2.891916 data_time: 0.442484 memory: 9974 loss_kpt: 0.001731 loss: 0.001731 2022/09/15 11:14:20 - mmengine - INFO - Epoch(train) [100][100/293] lr: 5.000000e-04 eta: 17:00:33 time: 2.213629 data_time: 0.344276 memory: 9974 loss_kpt: 0.001678 loss: 0.001678 2022/09/15 11:16:15 - mmengine - INFO - Epoch(train) [100][150/293] lr: 5.000000e-04 eta: 16:59:21 time: 2.293639 data_time: 0.107972 memory: 9974 loss_kpt: 0.001666 loss: 0.001666 2022/09/15 11:18:31 - mmengine - INFO - Epoch(train) [100][200/293] lr: 5.000000e-04 eta: 16:58:32 time: 2.718513 data_time: 0.095762 memory: 9974 loss_kpt: 0.001665 loss: 0.001665 2022/09/15 11:20:03 - mmengine - INFO - Epoch(train) [100][250/293] lr: 5.000000e-04 eta: 16:56:56 time: 1.857361 data_time: 0.697384 memory: 9974 loss_kpt: 0.001679 loss: 0.001679 2022/09/15 11:21:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 11:21:04 - mmengine - INFO - Saving checkpoint at 100 epochs 2022/09/15 11:22:13 - mmengine - INFO - Epoch(val) [100][50/407] eta: 0:07:53 time: 1.325484 data_time: 1.171431 memory: 9974 2022/09/15 11:22:48 - mmengine - INFO - Epoch(val) [100][100/407] eta: 0:03:33 time: 0.694511 data_time: 0.545994 memory: 918 2022/09/15 11:23:32 - mmengine - INFO - Epoch(val) [100][150/407] eta: 0:03:45 time: 0.878515 data_time: 0.730553 memory: 918 2022/09/15 11:24:11 - mmengine - INFO - Epoch(val) [100][200/407] eta: 0:02:43 time: 0.789128 data_time: 0.637565 memory: 918 2022/09/15 11:24:51 - mmengine - INFO - Epoch(val) [100][250/407] eta: 0:02:02 time: 0.782991 data_time: 0.628105 memory: 918 2022/09/15 11:25:31 - mmengine - INFO - Epoch(val) [100][300/407] eta: 0:01:26 time: 0.812411 data_time: 0.669040 memory: 918 2022/09/15 11:26:05 - mmengine - INFO - Epoch(val) [100][350/407] eta: 0:00:38 time: 0.681240 data_time: 0.531233 memory: 918 2022/09/15 11:27:03 - mmengine - INFO - Epoch(val) [100][400/407] eta: 0:00:08 time: 1.148640 data_time: 0.994818 memory: 918 2022/09/15 11:28:49 - mmengine - INFO - Evaluating CocoMetric... 2022/09/15 11:29:03 - mmengine - INFO - Epoch(val) [100][407/407] coco/AP: 0.735357 coco/AP .5: 0.898320 coco/AP .75: 0.805042 coco/AP (M): 0.695812 coco/AP (L): 0.806739 coco/AR: 0.793939 coco/AR .5: 0.937343 coco/AR .75: 0.856895 coco/AR (M): 0.748757 coco/AR (L): 0.859012 2022/09/15 11:29:03 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/udp_regress/best_coco/AP_epoch_80.pth is removed 2022/09/15 11:29:06 - mmengine - INFO - The best checkpoint with 0.7354 coco/AP at 100 epoch is saved to best_coco/AP_epoch_100.pth. 2022/09/15 11:30:30 - mmengine - INFO - Epoch(train) [101][50/293] lr: 5.000000e-04 eta: 16:52:19 time: 1.683109 data_time: 0.407685 memory: 9974 loss_kpt: 0.001680 loss: 0.001680 2022/09/15 11:31:50 - mmengine - INFO - Epoch(train) [101][100/293] lr: 5.000000e-04 eta: 16:50:29 time: 1.594297 data_time: 0.130589 memory: 9974 loss_kpt: 0.001673 loss: 0.001673 2022/09/15 11:34:01 - mmengine - INFO - Epoch(train) [101][150/293] lr: 5.000000e-04 eta: 16:49:35 time: 2.627504 data_time: 1.722217 memory: 9974 loss_kpt: 0.001680 loss: 0.001680 2022/09/15 11:35:44 - mmengine - INFO - Epoch(train) [101][200/293] lr: 5.000000e-04 eta: 16:48:10 time: 2.054663 data_time: 0.215072 memory: 9974 loss_kpt: 0.001687 loss: 0.001687 2022/09/15 11:37:40 - mmengine - INFO - Epoch(train) [101][250/293] lr: 5.000000e-04 eta: 16:46:59 time: 2.327206 data_time: 0.747015 memory: 9974 loss_kpt: 0.001660 loss: 0.001660 2022/09/15 11:39:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 11:39:19 - mmengine - INFO - Saving checkpoint at 101 epochs 2022/09/15 11:41:00 - mmengine - INFO - Epoch(train) [102][50/293] lr: 5.000000e-04 eta: 16:42:39 time: 1.947271 data_time: 0.506805 memory: 9974 loss_kpt: 0.001703 loss: 0.001703 2022/09/15 11:42:51 - mmengine - INFO - Epoch(train) [102][100/293] lr: 5.000000e-04 eta: 16:41:23 time: 2.232029 data_time: 0.199531 memory: 9974 loss_kpt: 0.001692 loss: 0.001692 2022/09/15 11:45:02 - mmengine - INFO - Epoch(train) [102][150/293] lr: 5.000000e-04 eta: 16:40:28 time: 2.616667 data_time: 0.140911 memory: 9974 loss_kpt: 0.001679 loss: 0.001679 2022/09/15 11:46:34 - mmengine - INFO - Epoch(train) [102][200/293] lr: 5.000000e-04 eta: 16:38:50 time: 1.831969 data_time: 0.089936 memory: 9974 loss_kpt: 0.001679 loss: 0.001679 2022/09/15 11:48:16 - mmengine - INFO - Epoch(train) [102][250/293] lr: 5.000000e-04 eta: 16:37:24 time: 2.039825 data_time: 0.089489 memory: 9974 loss_kpt: 0.001643 loss: 0.001643 2022/09/15 11:49:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 11:49:46 - mmengine - INFO - Saving checkpoint at 102 epochs 2022/09/15 11:51:22 - mmengine - INFO - Epoch(train) [103][50/293] lr: 5.000000e-04 eta: 16:33:01 time: 1.855353 data_time: 0.464039 memory: 9974 loss_kpt: 0.001662 loss: 0.001662 2022/09/15 11:53:10 - mmengine - INFO - Epoch(train) [103][100/293] lr: 5.000000e-04 eta: 16:31:41 time: 2.162747 data_time: 0.207600 memory: 9974 loss_kpt: 0.001692 loss: 0.001692 2022/09/15 11:53:39 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 11:54:47 - mmengine - INFO - Epoch(train) [103][150/293] lr: 5.000000e-04 eta: 16:30:10 time: 1.948192 data_time: 0.121041 memory: 9974 loss_kpt: 0.001678 loss: 0.001678 2022/09/15 11:56:30 - mmengine - INFO - Epoch(train) [103][200/293] lr: 5.000000e-04 eta: 16:28:44 time: 2.046484 data_time: 0.132626 memory: 9974 loss_kpt: 0.001653 loss: 0.001653 2022/09/15 11:58:24 - mmengine - INFO - Epoch(train) [103][250/293] lr: 5.000000e-04 eta: 16:27:31 time: 2.292695 data_time: 1.063707 memory: 9974 loss_kpt: 0.001678 loss: 0.001678 2022/09/15 11:59:52 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 11:59:52 - mmengine - INFO - Saving checkpoint at 103 epochs 2022/09/15 12:02:12 - mmengine - INFO - Epoch(train) [104][50/293] lr: 5.000000e-04 eta: 16:23:56 time: 2.746213 data_time: 1.016194 memory: 9974 loss_kpt: 0.001635 loss: 0.001635 2022/09/15 12:03:56 - mmengine - INFO - Epoch(train) [104][100/293] lr: 5.000000e-04 eta: 16:22:31 time: 2.065624 data_time: 0.340698 memory: 9974 loss_kpt: 0.001678 loss: 0.001678 2022/09/15 12:05:20 - mmengine - INFO - Epoch(train) [104][150/293] lr: 5.000000e-04 eta: 16:20:46 time: 1.686306 data_time: 0.658278 memory: 9974 loss_kpt: 0.001674 loss: 0.001674 2022/09/15 12:07:29 - mmengine - INFO - Epoch(train) [104][200/293] lr: 5.000000e-04 eta: 16:19:48 time: 2.588376 data_time: 0.594431 memory: 9974 loss_kpt: 0.001668 loss: 0.001668 2022/09/15 12:08:58 - mmengine - INFO - Epoch(train) [104][250/293] lr: 5.000000e-04 eta: 16:18:08 time: 1.778015 data_time: 0.162399 memory: 9974 loss_kpt: 0.001692 loss: 0.001692 2022/09/15 12:10:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 12:10:42 - mmengine - INFO - Saving checkpoint at 104 epochs 2022/09/15 12:12:17 - mmengine - INFO - Epoch(train) [105][50/293] lr: 5.000000e-04 eta: 16:13:47 time: 1.821708 data_time: 0.213631 memory: 9974 loss_kpt: 0.001688 loss: 0.001688 2022/09/15 12:13:44 - mmengine - INFO - Epoch(train) [105][100/293] lr: 5.000000e-04 eta: 16:12:06 time: 1.751239 data_time: 0.148503 memory: 9974 loss_kpt: 0.001698 loss: 0.001698 2022/09/15 12:16:01 - mmengine - INFO - Epoch(train) [105][150/293] lr: 5.000000e-04 eta: 16:11:14 time: 2.734048 data_time: 0.193181 memory: 9974 loss_kpt: 0.001649 loss: 0.001649 2022/09/15 12:18:15 - mmengine - INFO - Epoch(train) [105][200/293] lr: 5.000000e-04 eta: 16:10:20 time: 2.674306 data_time: 0.138766 memory: 9974 loss_kpt: 0.001689 loss: 0.001689 2022/09/15 12:19:35 - mmengine - INFO - Epoch(train) [105][250/293] lr: 5.000000e-04 eta: 16:08:31 time: 1.598245 data_time: 0.095104 memory: 9974 loss_kpt: 0.001681 loss: 0.001681 2022/09/15 12:21:28 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 12:21:29 - mmengine - INFO - Saving checkpoint at 105 epochs 2022/09/15 12:24:01 - mmengine - INFO - Epoch(train) [106][50/293] lr: 5.000000e-04 eta: 16:05:10 time: 2.994659 data_time: 0.295542 memory: 9974 loss_kpt: 0.001688 loss: 0.001688 2022/09/15 12:26:05 - mmengine - INFO - Epoch(train) [106][100/293] lr: 5.000000e-04 eta: 16:04:05 time: 2.472719 data_time: 0.891322 memory: 9974 loss_kpt: 0.001697 loss: 0.001697 2022/09/15 12:28:14 - mmengine - INFO - Epoch(train) [106][150/293] lr: 5.000000e-04 eta: 16:03:05 time: 2.577148 data_time: 0.971821 memory: 9974 loss_kpt: 0.001648 loss: 0.001648 2022/09/15 12:30:01 - mmengine - INFO - Epoch(train) [106][200/293] lr: 5.000000e-04 eta: 16:01:43 time: 2.147747 data_time: 0.197644 memory: 9974 loss_kpt: 0.001698 loss: 0.001698 2022/09/15 12:31:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 12:31:43 - mmengine - INFO - Epoch(train) [106][250/293] lr: 5.000000e-04 eta: 16:00:16 time: 2.023897 data_time: 0.098886 memory: 9974 loss_kpt: 0.001671 loss: 0.001671 2022/09/15 12:33:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 12:33:19 - mmengine - INFO - Saving checkpoint at 106 epochs 2022/09/15 12:35:15 - mmengine - INFO - Epoch(train) [107][50/293] lr: 5.000000e-04 eta: 15:56:18 time: 2.240902 data_time: 0.849384 memory: 9974 loss_kpt: 0.001699 loss: 0.001699 2022/09/15 12:37:20 - mmengine - INFO - Epoch(train) [107][100/293] lr: 5.000000e-04 eta: 15:55:14 time: 2.517865 data_time: 0.304658 memory: 9974 loss_kpt: 0.001659 loss: 0.001659 2022/09/15 12:39:23 - mmengine - INFO - Epoch(train) [107][150/293] lr: 5.000000e-04 eta: 15:54:07 time: 2.444375 data_time: 0.322514 memory: 9974 loss_kpt: 0.001674 loss: 0.001674 2022/09/15 12:40:51 - mmengine - INFO - Epoch(train) [107][200/293] lr: 5.000000e-04 eta: 15:52:27 time: 1.771234 data_time: 0.558042 memory: 9974 loss_kpt: 0.001667 loss: 0.001667 2022/09/15 12:42:56 - mmengine - INFO - Epoch(train) [107][250/293] lr: 5.000000e-04 eta: 15:51:22 time: 2.488826 data_time: 0.509424 memory: 9974 loss_kpt: 0.001660 loss: 0.001660 2022/09/15 12:45:01 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 12:45:01 - mmengine - INFO - Saving checkpoint at 107 epochs 2022/09/15 12:47:00 - mmengine - INFO - Epoch(train) [108][50/293] lr: 5.000000e-04 eta: 15:47:29 time: 2.331676 data_time: 0.163912 memory: 9974 loss_kpt: 0.001670 loss: 0.001670 2022/09/15 12:49:09 - mmengine - INFO - Epoch(train) [108][100/293] lr: 5.000000e-04 eta: 15:46:27 time: 2.561334 data_time: 0.091415 memory: 9974 loss_kpt: 0.001651 loss: 0.001651 2022/09/15 12:51:08 - mmengine - INFO - Epoch(train) [108][150/293] lr: 5.000000e-04 eta: 15:45:17 time: 2.392894 data_time: 0.154136 memory: 9974 loss_kpt: 0.001665 loss: 0.001665 2022/09/15 12:53:12 - mmengine - INFO - Epoch(train) [108][200/293] lr: 5.000000e-04 eta: 15:44:10 time: 2.472643 data_time: 0.094808 memory: 9974 loss_kpt: 0.001686 loss: 0.001686 2022/09/15 12:55:19 - mmengine - INFO - Epoch(train) [108][250/293] lr: 5.000000e-04 eta: 15:43:07 time: 2.549617 data_time: 0.465827 memory: 9974 loss_kpt: 0.001662 loss: 0.001662 2022/09/15 12:56:53 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 12:56:53 - mmengine - INFO - Saving checkpoint at 108 epochs 2022/09/15 12:59:38 - mmengine - INFO - Epoch(train) [109][50/293] lr: 5.000000e-04 eta: 15:39:58 time: 3.228450 data_time: 0.864049 memory: 9974 loss_kpt: 0.001660 loss: 0.001660 2022/09/15 13:02:08 - mmengine - INFO - Epoch(train) [109][100/293] lr: 5.000000e-04 eta: 15:39:15 time: 3.003006 data_time: 0.366646 memory: 9974 loss_kpt: 0.001670 loss: 0.001670 2022/09/15 13:04:35 - mmengine - INFO - Epoch(train) [109][150/293] lr: 5.000000e-04 eta: 15:38:29 time: 2.933079 data_time: 0.417071 memory: 9974 loss_kpt: 0.001702 loss: 0.001702 2022/09/15 13:06:50 - mmengine - INFO - Epoch(train) [109][200/293] lr: 5.000000e-04 eta: 15:37:33 time: 2.714924 data_time: 0.620313 memory: 9974 loss_kpt: 0.001678 loss: 0.001678 2022/09/15 13:08:51 - mmengine - INFO - Epoch(train) [109][250/293] lr: 5.000000e-04 eta: 15:36:22 time: 2.416575 data_time: 0.162435 memory: 9974 loss_kpt: 0.001673 loss: 0.001673 2022/09/15 13:10:52 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 13:10:52 - mmengine - INFO - Saving checkpoint at 109 epochs 2022/09/15 13:13:13 - mmengine - INFO - Epoch(train) [110][50/293] lr: 5.000000e-04 eta: 15:32:50 time: 2.755325 data_time: 0.757097 memory: 9974 loss_kpt: 0.001657 loss: 0.001657 2022/09/15 13:13:36 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 13:15:29 - mmengine - INFO - Epoch(train) [110][100/293] lr: 5.000000e-04 eta: 15:31:54 time: 2.726145 data_time: 0.097236 memory: 9974 loss_kpt: 0.001687 loss: 0.001687 2022/09/15 13:18:05 - mmengine - INFO - Epoch(train) [110][150/293] lr: 5.000000e-04 eta: 15:31:15 time: 3.111781 data_time: 0.088107 memory: 9974 loss_kpt: 0.001676 loss: 0.001676 2022/09/15 13:19:36 - mmengine - INFO - Epoch(train) [110][200/293] lr: 5.000000e-04 eta: 15:29:36 time: 1.818082 data_time: 0.122651 memory: 9974 loss_kpt: 0.001699 loss: 0.001699 2022/09/15 13:21:54 - mmengine - INFO - Epoch(train) [110][250/293] lr: 5.000000e-04 eta: 15:28:42 time: 2.774271 data_time: 0.403406 memory: 9974 loss_kpt: 0.001686 loss: 0.001686 2022/09/15 13:23:48 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 13:23:48 - mmengine - INFO - Saving checkpoint at 110 epochs 2022/09/15 13:24:51 - mmengine - INFO - Epoch(val) [110][50/407] eta: 0:07:07 time: 1.198327 data_time: 1.048481 memory: 9974 2022/09/15 13:26:18 - mmengine - INFO - Epoch(val) [110][100/407] eta: 0:08:56 time: 1.748869 data_time: 1.593966 memory: 918 2022/09/15 13:27:06 - mmengine - INFO - Epoch(val) [110][150/407] eta: 0:04:02 time: 0.942475 data_time: 0.800308 memory: 918 2022/09/15 13:28:08 - mmengine - INFO - Epoch(val) [110][200/407] eta: 0:04:20 time: 1.256380 data_time: 1.101465 memory: 918 2022/09/15 13:29:00 - mmengine - INFO - Epoch(val) [110][250/407] eta: 0:02:41 time: 1.028758 data_time: 0.886805 memory: 918 2022/09/15 13:29:44 - mmengine - INFO - Epoch(val) [110][300/407] eta: 0:01:33 time: 0.877277 data_time: 0.733104 memory: 918 2022/09/15 13:30:09 - mmengine - INFO - Epoch(val) [110][350/407] eta: 0:00:29 time: 0.516141 data_time: 0.372938 memory: 918 2022/09/15 13:31:13 - mmengine - INFO - Epoch(val) [110][400/407] eta: 0:00:08 time: 1.273671 data_time: 1.121268 memory: 918 2022/09/15 13:32:13 - mmengine - INFO - Evaluating CocoMetric... 2022/09/15 13:32:27 - mmengine - INFO - Epoch(val) [110][407/407] coco/AP: 0.739942 coco/AP .5: 0.897471 coco/AP .75: 0.811979 coco/AP (M): 0.698538 coco/AP (L): 0.812250 coco/AR: 0.796851 coco/AR .5: 0.936713 coco/AR .75: 0.860044 coco/AR (M): 0.751680 coco/AR (L): 0.862096 2022/09/15 13:32:27 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/udp_regress/best_coco/AP_epoch_100.pth is removed 2022/09/15 13:32:29 - mmengine - INFO - The best checkpoint with 0.7399 coco/AP at 110 epoch is saved to best_coco/AP_epoch_110.pth. 2022/09/15 13:36:19 - mmengine - INFO - Epoch(train) [111][50/293] lr: 5.000000e-04 eta: 15:26:33 time: 4.602695 data_time: 0.576805 memory: 9974 loss_kpt: 0.001654 loss: 0.001654 2022/09/15 13:38:33 - mmengine - INFO - Epoch(train) [111][100/293] lr: 5.000000e-04 eta: 15:25:34 time: 2.680584 data_time: 0.270920 memory: 9974 loss_kpt: 0.001672 loss: 0.001672 2022/09/15 13:41:01 - mmengine - INFO - Epoch(train) [111][150/293] lr: 5.000000e-04 eta: 15:24:46 time: 2.947551 data_time: 0.894561 memory: 9974 loss_kpt: 0.001678 loss: 0.001678 2022/09/15 13:43:20 - mmengine - INFO - Epoch(train) [111][200/293] lr: 5.000000e-04 eta: 15:23:50 time: 2.780373 data_time: 0.250018 memory: 9974 loss_kpt: 0.001640 loss: 0.001640 2022/09/15 13:45:26 - mmengine - INFO - Epoch(train) [111][250/293] lr: 5.000000e-04 eta: 15:22:42 time: 2.520924 data_time: 0.257476 memory: 9974 loss_kpt: 0.001674 loss: 0.001674 2022/09/15 13:47:15 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 13:47:15 - mmengine - INFO - Saving checkpoint at 111 epochs 2022/09/15 13:49:19 - mmengine - INFO - Epoch(train) [112][50/293] lr: 5.000000e-04 eta: 15:18:55 time: 2.411915 data_time: 0.863672 memory: 9974 loss_kpt: 0.001668 loss: 0.001668 2022/09/15 13:51:52 - mmengine - INFO - Epoch(train) [112][100/293] lr: 5.000000e-04 eta: 15:18:11 time: 3.061525 data_time: 0.775079 memory: 9974 loss_kpt: 0.001665 loss: 0.001665 2022/09/15 13:53:53 - mmengine - INFO - Epoch(train) [112][150/293] lr: 5.000000e-04 eta: 15:16:58 time: 2.421492 data_time: 0.249997 memory: 9974 loss_kpt: 0.001661 loss: 0.001661 2022/09/15 13:56:23 - mmengine - INFO - Epoch(train) [112][200/293] lr: 5.000000e-04 eta: 15:16:11 time: 2.998684 data_time: 0.622675 memory: 9974 loss_kpt: 0.001661 loss: 0.001661 2022/09/15 13:58:33 - mmengine - INFO - Epoch(train) [112][250/293] lr: 5.000000e-04 eta: 15:15:05 time: 2.591768 data_time: 0.512824 memory: 9974 loss_kpt: 0.001651 loss: 0.001651 2022/09/15 14:00:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 14:00:27 - mmengine - INFO - Saving checkpoint at 112 epochs 2022/09/15 14:03:25 - mmengine - INFO - Epoch(train) [113][50/293] lr: 5.000000e-04 eta: 15:12:06 time: 3.507777 data_time: 1.008092 memory: 9974 loss_kpt: 0.001663 loss: 0.001663 2022/09/15 14:06:07 - mmengine - INFO - Epoch(train) [113][100/293] lr: 5.000000e-04 eta: 15:11:28 time: 3.228238 data_time: 1.058357 memory: 9974 loss_kpt: 0.001636 loss: 0.001636 2022/09/15 14:08:43 - mmengine - INFO - Epoch(train) [113][150/293] lr: 5.000000e-04 eta: 15:10:45 time: 3.119867 data_time: 0.330593 memory: 9974 loss_kpt: 0.001668 loss: 0.001668 2022/09/15 14:10:24 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 14:11:19 - mmengine - INFO - Epoch(train) [113][200/293] lr: 5.000000e-04 eta: 15:10:01 time: 3.116639 data_time: 0.393577 memory: 9974 loss_kpt: 0.001670 loss: 0.001670 2022/09/15 14:13:59 - mmengine - INFO - Epoch(train) [113][250/293] lr: 5.000000e-04 eta: 15:09:21 time: 3.206938 data_time: 0.180898 memory: 9974 loss_kpt: 0.001678 loss: 0.001678 2022/09/15 14:16:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 14:16:07 - mmengine - INFO - Saving checkpoint at 113 epochs 2022/09/15 14:18:33 - mmengine - INFO - Epoch(train) [114][50/293] lr: 5.000000e-04 eta: 15:05:52 time: 2.855434 data_time: 0.255415 memory: 9974 loss_kpt: 0.001639 loss: 0.001639 2022/09/15 14:20:37 - mmengine - INFO - Epoch(train) [114][100/293] lr: 5.000000e-04 eta: 15:04:41 time: 2.483871 data_time: 0.337089 memory: 9974 loss_kpt: 0.001647 loss: 0.001647 2022/09/15 14:23:40 - mmengine - INFO - Epoch(train) [114][150/293] lr: 5.000000e-04 eta: 15:04:19 time: 3.660413 data_time: 0.090274 memory: 9974 loss_kpt: 0.001671 loss: 0.001671 2022/09/15 14:26:11 - mmengine - INFO - Epoch(train) [114][200/293] lr: 5.000000e-04 eta: 15:03:29 time: 3.016658 data_time: 1.193104 memory: 9974 loss_kpt: 0.001676 loss: 0.001676 2022/09/15 14:29:15 - mmengine - INFO - Epoch(train) [114][250/293] lr: 5.000000e-04 eta: 15:03:08 time: 3.690245 data_time: 2.180196 memory: 9974 loss_kpt: 0.001658 loss: 0.001658 2022/09/15 14:31:39 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 14:31:39 - mmengine - INFO - Saving checkpoint at 114 epochs 2022/09/15 14:33:58 - mmengine - INFO - Epoch(train) [115][50/293] lr: 5.000000e-04 eta: 14:59:33 time: 2.718586 data_time: 0.351222 memory: 9974 loss_kpt: 0.001657 loss: 0.001657 2022/09/15 14:36:22 - mmengine - INFO - Epoch(train) [115][100/293] lr: 5.000000e-04 eta: 14:58:37 time: 2.880796 data_time: 0.093405 memory: 9974 loss_kpt: 0.001675 loss: 0.001675 2022/09/15 14:38:31 - mmengine - INFO - Epoch(train) [115][150/293] lr: 5.000000e-04 eta: 14:57:28 time: 2.579488 data_time: 0.087139 memory: 9974 loss_kpt: 0.001713 loss: 0.001713 2022/09/15 14:39:51 - mmengine - INFO - Epoch(train) [115][200/293] lr: 5.000000e-04 eta: 14:55:38 time: 1.584197 data_time: 0.351172 memory: 9974 loss_kpt: 0.001702 loss: 0.001702 2022/09/15 14:42:18 - mmengine - INFO - Epoch(train) [115][250/293] lr: 5.000000e-04 eta: 14:54:44 time: 2.946936 data_time: 0.342069 memory: 9974 loss_kpt: 0.001649 loss: 0.001649 2022/09/15 14:44:09 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 14:44:09 - mmengine - INFO - Saving checkpoint at 115 epochs 2022/09/15 14:45:55 - mmengine - INFO - Epoch(train) [116][50/293] lr: 5.000000e-04 eta: 14:50:42 time: 2.045231 data_time: 0.928164 memory: 9974 loss_kpt: 0.001640 loss: 0.001640 2022/09/15 14:47:55 - mmengine - INFO - Epoch(train) [116][100/293] lr: 5.000000e-04 eta: 14:49:25 time: 2.396623 data_time: 0.200418 memory: 9974 loss_kpt: 0.001645 loss: 0.001645 2022/09/15 14:50:45 - mmengine - INFO - Epoch(train) [116][150/293] lr: 5.000000e-04 eta: 14:48:50 time: 3.415099 data_time: 2.094263 memory: 9974 loss_kpt: 0.001646 loss: 0.001646 2022/09/15 14:53:34 - mmengine - INFO - Epoch(train) [116][200/293] lr: 5.000000e-04 eta: 14:48:12 time: 3.369576 data_time: 0.380990 memory: 9974 loss_kpt: 0.001669 loss: 0.001669 2022/09/15 14:55:48 - mmengine - INFO - Epoch(train) [116][250/293] lr: 5.000000e-04 eta: 14:47:06 time: 2.683759 data_time: 1.100603 memory: 9974 loss_kpt: 0.001679 loss: 0.001679 2022/09/15 14:57:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 14:57:19 - mmengine - INFO - Saving checkpoint at 116 epochs 2022/09/15 14:57:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 14:59:43 - mmengine - INFO - Epoch(train) [117][50/293] lr: 5.000000e-04 eta: 14:43:36 time: 2.810572 data_time: 0.412607 memory: 9974 loss_kpt: 0.001683 loss: 0.001683 2022/09/15 15:01:44 - mmengine - INFO - Epoch(train) [117][100/293] lr: 5.000000e-04 eta: 14:42:19 time: 2.432457 data_time: 0.350901 memory: 9974 loss_kpt: 0.001641 loss: 0.001641 2022/09/15 15:04:55 - mmengine - INFO - Epoch(train) [117][150/293] lr: 5.000000e-04 eta: 14:41:58 time: 3.810960 data_time: 1.443514 memory: 9974 loss_kpt: 0.001648 loss: 0.001648 2022/09/15 15:07:29 - mmengine - INFO - Epoch(train) [117][200/293] lr: 5.000000e-04 eta: 14:41:08 time: 3.088421 data_time: 0.347813 memory: 9974 loss_kpt: 0.001644 loss: 0.001644 2022/09/15 15:09:41 - mmengine - INFO - Epoch(train) [117][250/293] lr: 5.000000e-04 eta: 14:40:00 time: 2.641705 data_time: 0.346105 memory: 9974 loss_kpt: 0.001641 loss: 0.001641 2022/09/15 15:11:52 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 15:11:52 - mmengine - INFO - Saving checkpoint at 117 epochs 2022/09/15 15:14:17 - mmengine - INFO - Epoch(train) [118][50/293] lr: 5.000000e-04 eta: 14:36:29 time: 2.819198 data_time: 0.690693 memory: 9974 loss_kpt: 0.001641 loss: 0.001641 2022/09/15 15:16:29 - mmengine - INFO - Epoch(train) [118][100/293] lr: 5.000000e-04 eta: 14:35:21 time: 2.652820 data_time: 0.392352 memory: 9974 loss_kpt: 0.001636 loss: 0.001636 2022/09/15 15:19:01 - mmengine - INFO - Epoch(train) [118][150/293] lr: 5.000000e-04 eta: 14:34:27 time: 3.033373 data_time: 1.000208 memory: 9974 loss_kpt: 0.001667 loss: 0.001667 2022/09/15 15:21:09 - mmengine - INFO - Epoch(train) [118][200/293] lr: 5.000000e-04 eta: 14:33:15 time: 2.566969 data_time: 0.639980 memory: 9974 loss_kpt: 0.001665 loss: 0.001665 2022/09/15 15:23:07 - mmengine - INFO - Epoch(train) [118][250/293] lr: 5.000000e-04 eta: 14:31:54 time: 2.344480 data_time: 1.011237 memory: 9974 loss_kpt: 0.001655 loss: 0.001655 2022/09/15 15:25:16 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 15:25:16 - mmengine - INFO - Saving checkpoint at 118 epochs 2022/09/15 15:27:54 - mmengine - INFO - Epoch(train) [119][50/293] lr: 5.000000e-04 eta: 14:28:35 time: 3.113381 data_time: 1.548787 memory: 9974 loss_kpt: 0.001664 loss: 0.001664 2022/09/15 15:30:19 - mmengine - INFO - Epoch(train) [119][100/293] lr: 5.000000e-04 eta: 14:27:35 time: 2.903946 data_time: 0.596352 memory: 9974 loss_kpt: 0.001660 loss: 0.001660 2022/09/15 15:32:39 - mmengine - INFO - Epoch(train) [119][150/293] lr: 5.000000e-04 eta: 14:26:31 time: 2.789446 data_time: 0.318880 memory: 9974 loss_kpt: 0.001678 loss: 0.001678 2022/09/15 15:35:24 - mmengine - INFO - Epoch(train) [119][200/293] lr: 5.000000e-04 eta: 14:25:47 time: 3.309016 data_time: 0.737734 memory: 9974 loss_kpt: 0.001701 loss: 0.001701 2022/09/15 15:38:35 - mmengine - INFO - Epoch(train) [119][250/293] lr: 5.000000e-04 eta: 14:25:22 time: 3.821645 data_time: 0.105810 memory: 9974 loss_kpt: 0.001668 loss: 0.001668 2022/09/15 15:40:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 15:40:44 - mmengine - INFO - Saving checkpoint at 119 epochs 2022/09/15 15:42:55 - mmengine - INFO - Epoch(train) [120][50/293] lr: 5.000000e-04 eta: 14:21:40 time: 2.542530 data_time: 0.706023 memory: 9974 loss_kpt: 0.001668 loss: 0.001668 2022/09/15 15:46:12 - mmengine - INFO - Epoch(train) [120][100/293] lr: 5.000000e-04 eta: 14:21:19 time: 3.941275 data_time: 0.093375 memory: 9974 loss_kpt: 0.001666 loss: 0.001666 2022/09/15 15:47:45 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 15:48:09 - mmengine - INFO - Epoch(train) [120][150/293] lr: 5.000000e-04 eta: 14:19:57 time: 2.350938 data_time: 0.198519 memory: 9974 loss_kpt: 0.001673 loss: 0.001673 2022/09/15 15:50:29 - mmengine - INFO - Epoch(train) [120][200/293] lr: 5.000000e-04 eta: 14:18:52 time: 2.799354 data_time: 1.127536 memory: 9974 loss_kpt: 0.001654 loss: 0.001654 2022/09/15 15:53:33 - mmengine - INFO - Epoch(train) [120][250/293] lr: 5.000000e-04 eta: 14:18:20 time: 3.683725 data_time: 1.201885 memory: 9974 loss_kpt: 0.001670 loss: 0.001670 2022/09/15 15:55:14 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 15:55:14 - mmengine - INFO - Saving checkpoint at 120 epochs 2022/09/15 15:57:03 - mmengine - INFO - Epoch(val) [120][50/407] eta: 0:12:35 time: 2.115623 data_time: 1.959054 memory: 9974 2022/09/15 15:58:20 - mmengine - INFO - Epoch(val) [120][100/407] eta: 0:07:53 time: 1.541930 data_time: 1.389602 memory: 918 2022/09/15 15:59:34 - mmengine - INFO - Epoch(val) [120][150/407] eta: 0:06:15 time: 1.461793 data_time: 1.306363 memory: 918 2022/09/15 16:00:29 - mmengine - INFO - Epoch(val) [120][200/407] eta: 0:03:50 time: 1.114787 data_time: 0.968074 memory: 918 2022/09/15 16:01:26 - mmengine - INFO - Epoch(val) [120][250/407] eta: 0:02:57 time: 1.132272 data_time: 0.983804 memory: 918 2022/09/15 16:02:36 - mmengine - INFO - Epoch(val) [120][300/407] eta: 0:02:31 time: 1.411597 data_time: 1.259484 memory: 918 2022/09/15 16:03:59 - mmengine - INFO - Epoch(val) [120][350/407] eta: 0:01:34 time: 1.653207 data_time: 1.504756 memory: 918 2022/09/15 16:05:36 - mmengine - INFO - Epoch(val) [120][400/407] eta: 0:00:13 time: 1.943025 data_time: 1.785314 memory: 918 2022/09/15 16:06:39 - mmengine - INFO - Evaluating CocoMetric... 2022/09/15 16:06:53 - mmengine - INFO - Epoch(val) [120][407/407] coco/AP: 0.736915 coco/AP .5: 0.897756 coco/AP .75: 0.806850 coco/AP (M): 0.699201 coco/AP (L): 0.805506 coco/AR: 0.795183 coco/AR .5: 0.936241 coco/AR .75: 0.856108 coco/AR (M): 0.751079 coco/AR (L): 0.859197 2022/09/15 16:10:16 - mmengine - INFO - Epoch(train) [121][50/293] lr: 5.000000e-04 eta: 14:15:35 time: 4.069586 data_time: 0.273297 memory: 9974 loss_kpt: 0.001655 loss: 0.001655 2022/09/15 16:13:00 - mmengine - INFO - Epoch(train) [121][100/293] lr: 5.000000e-04 eta: 14:14:47 time: 3.274049 data_time: 0.102410 memory: 9974 loss_kpt: 0.001652 loss: 0.001652 2022/09/15 16:15:23 - mmengine - INFO - Epoch(train) [121][150/293] lr: 5.000000e-04 eta: 14:13:43 time: 2.858660 data_time: 0.997149 memory: 9974 loss_kpt: 0.001668 loss: 0.001668 2022/09/15 16:18:18 - mmengine - INFO - Epoch(train) [121][200/293] lr: 5.000000e-04 eta: 14:13:02 time: 3.492780 data_time: 0.350320 memory: 9974 loss_kpt: 0.001644 loss: 0.001644 2022/09/15 16:20:46 - mmengine - INFO - Epoch(train) [121][250/293] lr: 5.000000e-04 eta: 14:12:02 time: 2.961960 data_time: 1.065283 memory: 9974 loss_kpt: 0.001639 loss: 0.001639 2022/09/15 16:23:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 16:23:00 - mmengine - INFO - Saving checkpoint at 121 epochs 2022/09/15 16:25:28 - mmengine - INFO - Epoch(train) [122][50/293] lr: 5.000000e-04 eta: 14:08:32 time: 2.890275 data_time: 1.025497 memory: 9974 loss_kpt: 0.001634 loss: 0.001634 2022/09/15 16:27:33 - mmengine - INFO - Epoch(train) [122][100/293] lr: 5.000000e-04 eta: 14:07:14 time: 2.505251 data_time: 0.107180 memory: 9974 loss_kpt: 0.001676 loss: 0.001676 2022/09/15 16:29:58 - mmengine - INFO - Epoch(train) [122][150/293] lr: 5.000000e-04 eta: 14:06:11 time: 2.897177 data_time: 0.320413 memory: 9974 loss_kpt: 0.001636 loss: 0.001636 2022/09/15 16:31:44 - mmengine - INFO - Epoch(train) [122][200/293] lr: 5.000000e-04 eta: 14:04:39 time: 2.120806 data_time: 0.947939 memory: 9974 loss_kpt: 0.001681 loss: 0.001681 2022/09/15 16:33:48 - mmengine - INFO - Epoch(train) [122][250/293] lr: 5.000000e-04 eta: 14:03:20 time: 2.486668 data_time: 0.464524 memory: 9974 loss_kpt: 0.001672 loss: 0.001672 2022/09/15 16:35:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 16:35:46 - mmengine - INFO - Saving checkpoint at 122 epochs 2022/09/15 16:37:36 - mmengine - INFO - Epoch(train) [123][50/293] lr: 5.000000e-04 eta: 13:59:24 time: 2.134531 data_time: 0.394152 memory: 9974 loss_kpt: 0.001661 loss: 0.001661 2022/09/15 16:39:30 - mmengine - INFO - Epoch(train) [123][100/293] lr: 5.000000e-04 eta: 13:57:57 time: 2.280284 data_time: 0.085747 memory: 9974 loss_kpt: 0.001658 loss: 0.001658 2022/09/15 16:41:21 - mmengine - INFO - Epoch(train) [123][150/293] lr: 5.000000e-04 eta: 13:56:29 time: 2.227202 data_time: 0.120291 memory: 9974 loss_kpt: 0.001666 loss: 0.001666 2022/09/15 16:43:18 - mmengine - INFO - Epoch(train) [123][200/293] lr: 5.000000e-04 eta: 13:55:05 time: 2.339600 data_time: 0.099983 memory: 9974 loss_kpt: 0.001671 loss: 0.001671 2022/09/15 16:45:24 - mmengine - INFO - Epoch(train) [123][250/293] lr: 5.000000e-04 eta: 13:53:46 time: 2.512697 data_time: 0.761394 memory: 9974 loss_kpt: 0.001644 loss: 0.001644 2022/09/15 16:45:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 16:47:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 16:47:02 - mmengine - INFO - Saving checkpoint at 123 epochs 2022/09/15 16:49:29 - mmengine - INFO - Epoch(train) [124][50/293] lr: 5.000000e-04 eta: 13:50:17 time: 2.867599 data_time: 0.324659 memory: 9974 loss_kpt: 0.001657 loss: 0.001657 2022/09/15 16:51:39 - mmengine - INFO - Epoch(train) [124][100/293] lr: 5.000000e-04 eta: 13:49:02 time: 2.603908 data_time: 0.350719 memory: 9974 loss_kpt: 0.001638 loss: 0.001638 2022/09/15 16:54:06 - mmengine - INFO - Epoch(train) [124][150/293] lr: 5.000000e-04 eta: 13:47:58 time: 2.931844 data_time: 1.591787 memory: 9974 loss_kpt: 0.001642 loss: 0.001642 2022/09/15 16:56:16 - mmengine - INFO - Epoch(train) [124][200/293] lr: 5.000000e-04 eta: 13:46:42 time: 2.600247 data_time: 1.986011 memory: 9974 loss_kpt: 0.001666 loss: 0.001666 2022/09/15 16:58:11 - mmengine - INFO - Epoch(train) [124][250/293] lr: 5.000000e-04 eta: 13:45:16 time: 2.308376 data_time: 0.743910 memory: 9974 loss_kpt: 0.001660 loss: 0.001660 2022/09/15 16:59:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 16:59:55 - mmengine - INFO - Saving checkpoint at 124 epochs 2022/09/15 17:02:34 - mmengine - INFO - Epoch(train) [125][50/293] lr: 5.000000e-04 eta: 13:41:55 time: 3.101076 data_time: 0.903136 memory: 9974 loss_kpt: 0.001670 loss: 0.001670 2022/09/15 17:04:54 - mmengine - INFO - Epoch(train) [125][100/293] lr: 5.000000e-04 eta: 13:40:45 time: 2.798983 data_time: 0.083793 memory: 9974 loss_kpt: 0.001656 loss: 0.001656 2022/09/15 17:06:35 - mmengine - INFO - Epoch(train) [125][150/293] lr: 5.000000e-04 eta: 13:39:10 time: 2.037935 data_time: 0.445332 memory: 9974 loss_kpt: 0.001657 loss: 0.001657 2022/09/15 17:09:01 - mmengine - INFO - Epoch(train) [125][200/293] lr: 5.000000e-04 eta: 13:38:04 time: 2.907236 data_time: 0.176893 memory: 9974 loss_kpt: 0.001666 loss: 0.001666 2022/09/15 17:11:14 - mmengine - INFO - Epoch(train) [125][250/293] lr: 5.000000e-04 eta: 13:36:50 time: 2.654247 data_time: 0.084061 memory: 9974 loss_kpt: 0.001659 loss: 0.001659 2022/09/15 17:13:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 17:13:06 - mmengine - INFO - Saving checkpoint at 125 epochs 2022/09/15 17:15:33 - mmengine - INFO - Epoch(train) [126][50/293] lr: 5.000000e-04 eta: 13:33:20 time: 2.873228 data_time: 0.211963 memory: 9974 loss_kpt: 0.001643 loss: 0.001643 2022/09/15 17:17:27 - mmengine - INFO - Epoch(train) [126][100/293] lr: 5.000000e-04 eta: 13:31:53 time: 2.280496 data_time: 0.110069 memory: 9974 loss_kpt: 0.001636 loss: 0.001636 2022/09/15 17:19:33 - mmengine - INFO - Epoch(train) [126][150/293] lr: 5.000000e-04 eta: 13:30:33 time: 2.515094 data_time: 0.137774 memory: 9974 loss_kpt: 0.001656 loss: 0.001656 2022/09/15 17:21:31 - mmengine - INFO - Epoch(train) [126][200/293] lr: 5.000000e-04 eta: 13:29:09 time: 2.373352 data_time: 0.496493 memory: 9974 loss_kpt: 0.001655 loss: 0.001655 2022/09/15 17:23:14 - mmengine - INFO - Epoch(train) [126][250/293] lr: 5.000000e-04 eta: 13:27:33 time: 2.050343 data_time: 0.132768 memory: 9974 loss_kpt: 0.001652 loss: 0.001652 2022/09/15 17:25:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 17:25:06 - mmengine - INFO - Saving checkpoint at 126 epochs 2022/09/15 17:27:26 - mmengine - INFO - Epoch(train) [127][50/293] lr: 5.000000e-04 eta: 13:24:00 time: 2.725944 data_time: 0.297349 memory: 9974 loss_kpt: 0.001630 loss: 0.001630 2022/09/15 17:28:58 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 17:29:41 - mmengine - INFO - Epoch(train) [127][100/293] lr: 5.000000e-04 eta: 13:22:46 time: 2.704277 data_time: 1.273837 memory: 9974 loss_kpt: 0.001635 loss: 0.001635 2022/09/15 17:32:04 - mmengine - INFO - Epoch(train) [127][150/293] lr: 5.000000e-04 eta: 13:21:38 time: 2.873397 data_time: 1.143419 memory: 9974 loss_kpt: 0.001651 loss: 0.001651 2022/09/15 17:33:28 - mmengine - INFO - Epoch(train) [127][200/293] lr: 5.000000e-04 eta: 13:19:50 time: 1.665189 data_time: 0.289466 memory: 9974 loss_kpt: 0.001643 loss: 0.001643 2022/09/15 17:36:03 - mmengine - INFO - Epoch(train) [127][250/293] lr: 5.000000e-04 eta: 13:18:49 time: 3.103279 data_time: 0.402586 memory: 9974 loss_kpt: 0.001644 loss: 0.001644 2022/09/15 17:37:29 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 17:37:29 - mmengine - INFO - Saving checkpoint at 127 epochs 2022/09/15 17:39:39 - mmengine - INFO - Epoch(train) [128][50/293] lr: 5.000000e-04 eta: 13:15:09 time: 2.536852 data_time: 0.284724 memory: 9974 loss_kpt: 0.001617 loss: 0.001617 2022/09/15 17:42:12 - mmengine - INFO - Epoch(train) [128][100/293] lr: 5.000000e-04 eta: 13:14:06 time: 3.060737 data_time: 0.523194 memory: 9974 loss_kpt: 0.001637 loss: 0.001637 2022/09/15 17:44:05 - mmengine - INFO - Epoch(train) [128][150/293] lr: 5.000000e-04 eta: 13:12:37 time: 2.263482 data_time: 0.093545 memory: 9974 loss_kpt: 0.001629 loss: 0.001629 2022/09/15 17:46:45 - mmengine - INFO - Epoch(train) [128][200/293] lr: 5.000000e-04 eta: 13:11:39 time: 3.210416 data_time: 0.274100 memory: 9974 loss_kpt: 0.001649 loss: 0.001649 2022/09/15 17:49:06 - mmengine - INFO - Epoch(train) [128][250/293] lr: 5.000000e-04 eta: 13:10:28 time: 2.816176 data_time: 0.384660 memory: 9974 loss_kpt: 0.001647 loss: 0.001647 2022/09/15 17:50:28 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 17:50:28 - mmengine - INFO - Saving checkpoint at 128 epochs 2022/09/15 17:53:02 - mmengine - INFO - Epoch(train) [129][50/293] lr: 5.000000e-04 eta: 13:07:04 time: 3.028857 data_time: 0.465782 memory: 9974 loss_kpt: 0.001632 loss: 0.001632 2022/09/15 17:54:57 - mmengine - INFO - Epoch(train) [129][100/293] lr: 5.000000e-04 eta: 13:05:36 time: 2.291711 data_time: 0.435361 memory: 9974 loss_kpt: 0.001651 loss: 0.001651 2022/09/15 17:57:22 - mmengine - INFO - Epoch(train) [129][150/293] lr: 5.000000e-04 eta: 13:04:27 time: 2.901905 data_time: 1.469258 memory: 9974 loss_kpt: 0.001646 loss: 0.001646 2022/09/15 17:59:12 - mmengine - INFO - Epoch(train) [129][200/293] lr: 5.000000e-04 eta: 13:02:56 time: 2.195139 data_time: 0.112843 memory: 9974 loss_kpt: 0.001639 loss: 0.001639 2022/09/15 18:01:04 - mmengine - INFO - Epoch(train) [129][250/293] lr: 5.000000e-04 eta: 13:01:26 time: 2.242444 data_time: 0.322914 memory: 9974 loss_kpt: 0.001635 loss: 0.001635 2022/09/15 18:03:09 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 18:03:09 - mmengine - INFO - Saving checkpoint at 129 epochs 2022/09/15 18:05:43 - mmengine - INFO - Epoch(train) [130][50/293] lr: 5.000000e-04 eta: 12:58:01 time: 3.004187 data_time: 1.883924 memory: 9974 loss_kpt: 0.001659 loss: 0.001659 2022/09/15 18:07:58 - mmengine - INFO - Epoch(train) [130][100/293] lr: 5.000000e-04 eta: 12:56:45 time: 2.696939 data_time: 1.334063 memory: 9974 loss_kpt: 0.001645 loss: 0.001645 2022/09/15 18:10:14 - mmengine - INFO - Epoch(train) [130][150/293] lr: 5.000000e-04 eta: 12:55:30 time: 2.721341 data_time: 0.492079 memory: 9974 loss_kpt: 0.001653 loss: 0.001653 2022/09/15 18:12:11 - mmengine - INFO - Epoch(train) [130][200/293] lr: 5.000000e-04 eta: 12:54:03 time: 2.350035 data_time: 0.883067 memory: 9974 loss_kpt: 0.001639 loss: 0.001639 2022/09/15 18:12:18 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 18:14:40 - mmengine - INFO - Epoch(train) [130][250/293] lr: 5.000000e-04 eta: 12:52:55 time: 2.974517 data_time: 0.329523 memory: 9974 loss_kpt: 0.001666 loss: 0.001666 2022/09/15 18:17:03 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 18:17:03 - mmengine - INFO - Saving checkpoint at 130 epochs 2022/09/15 18:17:47 - mmengine - INFO - Epoch(val) [130][50/407] eta: 0:04:48 time: 0.809147 data_time: 0.660954 memory: 9974 2022/09/15 18:18:54 - mmengine - INFO - Epoch(val) [130][100/407] eta: 0:06:56 time: 1.355538 data_time: 1.200094 memory: 918 2022/09/15 18:19:54 - mmengine - INFO - Epoch(val) [130][150/407] eta: 0:05:05 time: 1.189396 data_time: 1.042783 memory: 918 2022/09/15 18:20:56 - mmengine - INFO - Epoch(val) [130][200/407] eta: 0:04:15 time: 1.234188 data_time: 1.087412 memory: 918 2022/09/15 18:21:57 - mmengine - INFO - Epoch(val) [130][250/407] eta: 0:03:14 time: 1.238617 data_time: 1.089447 memory: 918 2022/09/15 18:22:39 - mmengine - INFO - Epoch(val) [130][300/407] eta: 0:01:29 time: 0.839698 data_time: 0.696250 memory: 918 2022/09/15 18:23:36 - mmengine - INFO - Epoch(val) [130][350/407] eta: 0:01:04 time: 1.131153 data_time: 0.979554 memory: 918 2022/09/15 18:24:43 - mmengine - INFO - Epoch(val) [130][400/407] eta: 0:00:09 time: 1.339798 data_time: 1.191916 memory: 918 2022/09/15 18:26:23 - mmengine - INFO - Evaluating CocoMetric... 2022/09/15 18:26:36 - mmengine - INFO - Epoch(val) [130][407/407] coco/AP: 0.741998 coco/AP .5: 0.899685 coco/AP .75: 0.811034 coco/AP (M): 0.702403 coco/AP (L): 0.811392 coco/AR: 0.798756 coco/AR .5: 0.939547 coco/AR .75: 0.860831 coco/AR (M): 0.755477 coco/AR (L): 0.861613 2022/09/15 18:26:36 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/udp_regress/best_coco/AP_epoch_110.pth is removed 2022/09/15 18:26:38 - mmengine - INFO - The best checkpoint with 0.7420 coco/AP at 130 epoch is saved to best_coco/AP_epoch_130.pth. 2022/09/15 18:29:22 - mmengine - INFO - Epoch(train) [131][50/293] lr: 5.000000e-04 eta: 12:49:39 time: 3.266706 data_time: 0.867060 memory: 9974 loss_kpt: 0.001618 loss: 0.001618 2022/09/15 18:31:45 - mmengine - INFO - Epoch(train) [131][100/293] lr: 5.000000e-04 eta: 12:48:28 time: 2.872466 data_time: 0.506955 memory: 9974 loss_kpt: 0.001668 loss: 0.001668 2022/09/15 18:34:15 - mmengine - INFO - Epoch(train) [131][150/293] lr: 5.000000e-04 eta: 12:47:20 time: 2.999481 data_time: 1.067392 memory: 9974 loss_kpt: 0.001637 loss: 0.001637 2022/09/15 18:36:01 - mmengine - INFO - Epoch(train) [131][200/293] lr: 5.000000e-04 eta: 12:45:46 time: 2.120500 data_time: 0.091044 memory: 9974 loss_kpt: 0.001647 loss: 0.001647 2022/09/15 18:38:37 - mmengine - INFO - Epoch(train) [131][250/293] lr: 5.000000e-04 eta: 12:44:41 time: 3.113875 data_time: 0.908793 memory: 9974 loss_kpt: 0.001664 loss: 0.001664 2022/09/15 18:40:29 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 18:40:29 - mmengine - INFO - Saving checkpoint at 131 epochs 2022/09/15 18:42:31 - mmengine - INFO - Epoch(train) [132][50/293] lr: 5.000000e-04 eta: 12:40:58 time: 2.371541 data_time: 0.212108 memory: 9974 loss_kpt: 0.001634 loss: 0.001634 2022/09/15 18:44:27 - mmengine - INFO - Epoch(train) [132][100/293] lr: 5.000000e-04 eta: 12:39:30 time: 2.323207 data_time: 0.209130 memory: 9974 loss_kpt: 0.001644 loss: 0.001644 2022/09/15 18:46:20 - mmengine - INFO - Epoch(train) [132][150/293] lr: 5.000000e-04 eta: 12:37:59 time: 2.249931 data_time: 0.276572 memory: 9974 loss_kpt: 0.001638 loss: 0.001638 2022/09/15 18:48:40 - mmengine - INFO - Epoch(train) [132][200/293] lr: 5.000000e-04 eta: 12:36:44 time: 2.799694 data_time: 0.233815 memory: 9974 loss_kpt: 0.001623 loss: 0.001623 2022/09/15 18:51:00 - mmengine - INFO - Epoch(train) [132][250/293] lr: 5.000000e-04 eta: 12:35:30 time: 2.796977 data_time: 0.192665 memory: 9974 loss_kpt: 0.001662 loss: 0.001662 2022/09/15 18:52:23 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 18:52:23 - mmengine - INFO - Saving checkpoint at 132 epochs 2022/09/15 18:55:05 - mmengine - INFO - Epoch(train) [133][50/293] lr: 5.000000e-04 eta: 12:32:10 time: 3.163043 data_time: 0.842291 memory: 9974 loss_kpt: 0.001629 loss: 0.001629 2022/09/15 18:56:53 - mmengine - INFO - Epoch(train) [133][100/293] lr: 5.000000e-04 eta: 12:30:37 time: 2.171208 data_time: 0.167177 memory: 9974 loss_kpt: 0.001624 loss: 0.001624 2022/09/15 18:59:22 - mmengine - INFO - Epoch(train) [133][150/293] lr: 5.000000e-04 eta: 12:29:27 time: 2.974562 data_time: 0.118740 memory: 9974 loss_kpt: 0.001617 loss: 0.001617 2022/09/15 19:01:42 - mmengine - INFO - Epoch(train) [133][200/293] lr: 5.000000e-04 eta: 12:28:12 time: 2.789932 data_time: 0.368830 memory: 9974 loss_kpt: 0.001625 loss: 0.001625 2022/09/15 19:03:49 - mmengine - INFO - Epoch(train) [133][250/293] lr: 5.000000e-04 eta: 12:26:49 time: 2.557270 data_time: 0.692809 memory: 9974 loss_kpt: 0.001632 loss: 0.001632 2022/09/15 19:05:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 19:05:56 - mmengine - INFO - Saving checkpoint at 133 epochs 2022/09/15 19:07:17 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 19:07:47 - mmengine - INFO - Epoch(train) [134][50/293] lr: 5.000000e-04 eta: 12:23:01 time: 2.145806 data_time: 0.357421 memory: 9974 loss_kpt: 0.001650 loss: 0.001650 2022/09/15 19:09:47 - mmengine - INFO - Epoch(train) [134][100/293] lr: 5.000000e-04 eta: 12:21:34 time: 2.401673 data_time: 0.307653 memory: 9974 loss_kpt: 0.001650 loss: 0.001650 2022/09/15 19:11:48 - mmengine - INFO - Epoch(train) [134][150/293] lr: 5.000000e-04 eta: 12:20:08 time: 2.431064 data_time: 0.429970 memory: 9974 loss_kpt: 0.001655 loss: 0.001655 2022/09/15 19:13:52 - mmengine - INFO - Epoch(train) [134][200/293] lr: 5.000000e-04 eta: 12:18:42 time: 2.464282 data_time: 0.380421 memory: 9974 loss_kpt: 0.001630 loss: 0.001630 2022/09/15 19:15:55 - mmengine - INFO - Epoch(train) [134][250/293] lr: 5.000000e-04 eta: 12:17:17 time: 2.473816 data_time: 0.767300 memory: 9974 loss_kpt: 0.001636 loss: 0.001636 2022/09/15 19:17:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 19:17:43 - mmengine - INFO - Saving checkpoint at 134 epochs 2022/09/15 19:19:32 - mmengine - INFO - Epoch(train) [135][50/293] lr: 5.000000e-04 eta: 12:13:28 time: 2.102765 data_time: 0.459091 memory: 9974 loss_kpt: 0.001651 loss: 0.001651 2022/09/15 19:21:44 - mmengine - INFO - Epoch(train) [135][100/293] lr: 5.000000e-04 eta: 12:12:08 time: 2.657816 data_time: 0.178526 memory: 9974 loss_kpt: 0.001656 loss: 0.001656 2022/09/15 19:24:02 - mmengine - INFO - Epoch(train) [135][150/293] lr: 5.000000e-04 eta: 12:10:50 time: 2.744354 data_time: 0.089419 memory: 9974 loss_kpt: 0.001626 loss: 0.001626 2022/09/15 19:25:38 - mmengine - INFO - Epoch(train) [135][200/293] lr: 5.000000e-04 eta: 12:09:10 time: 1.930795 data_time: 0.164471 memory: 9974 loss_kpt: 0.001619 loss: 0.001619 2022/09/15 19:27:38 - mmengine - INFO - Epoch(train) [135][250/293] lr: 5.000000e-04 eta: 12:07:42 time: 2.390841 data_time: 0.118059 memory: 9974 loss_kpt: 0.001644 loss: 0.001644 2022/09/15 19:29:24 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 19:29:24 - mmengine - INFO - Saving checkpoint at 135 epochs 2022/09/15 19:31:25 - mmengine - INFO - Epoch(train) [136][50/293] lr: 5.000000e-04 eta: 12:04:00 time: 2.343469 data_time: 0.216034 memory: 9974 loss_kpt: 0.001650 loss: 0.001650 2022/09/15 19:33:29 - mmengine - INFO - Epoch(train) [136][100/293] lr: 5.000000e-04 eta: 12:02:35 time: 2.493563 data_time: 0.132283 memory: 9974 loss_kpt: 0.001658 loss: 0.001658 2022/09/15 19:35:38 - mmengine - INFO - Epoch(train) [136][150/293] lr: 5.000000e-04 eta: 12:01:13 time: 2.577861 data_time: 0.098586 memory: 9974 loss_kpt: 0.001640 loss: 0.001640 2022/09/15 19:37:44 - mmengine - INFO - Epoch(train) [136][200/293] lr: 5.000000e-04 eta: 11:59:48 time: 2.522881 data_time: 0.194588 memory: 9974 loss_kpt: 0.001644 loss: 0.001644 2022/09/15 19:39:56 - mmengine - INFO - Epoch(train) [136][250/293] lr: 5.000000e-04 eta: 11:58:27 time: 2.623444 data_time: 0.482039 memory: 9974 loss_kpt: 0.001661 loss: 0.001661 2022/09/15 19:41:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 19:41:32 - mmengine - INFO - Saving checkpoint at 136 epochs 2022/09/15 19:43:21 - mmengine - INFO - Epoch(train) [137][50/293] lr: 5.000000e-04 eta: 11:54:39 time: 2.113200 data_time: 1.085870 memory: 9974 loss_kpt: 0.001622 loss: 0.001622 2022/09/15 19:45:36 - mmengine - INFO - Epoch(train) [137][100/293] lr: 5.000000e-04 eta: 11:53:19 time: 2.697816 data_time: 0.886661 memory: 9974 loss_kpt: 0.001650 loss: 0.001650 2022/09/15 19:47:33 - mmengine - INFO - Epoch(train) [137][150/293] lr: 5.000000e-04 eta: 11:51:50 time: 2.341007 data_time: 0.350841 memory: 9974 loss_kpt: 0.001624 loss: 0.001624 2022/09/15 19:47:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 19:49:38 - mmengine - INFO - Epoch(train) [137][200/293] lr: 5.000000e-04 eta: 11:50:25 time: 2.501711 data_time: 0.285197 memory: 9974 loss_kpt: 0.001617 loss: 0.001617 2022/09/15 19:51:53 - mmengine - INFO - Epoch(train) [137][250/293] lr: 5.000000e-04 eta: 11:49:05 time: 2.702967 data_time: 0.090219 memory: 9974 loss_kpt: 0.001646 loss: 0.001646 2022/09/15 19:53:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 19:53:02 - mmengine - INFO - Saving checkpoint at 137 epochs 2022/09/15 19:55:31 - mmengine - INFO - Epoch(train) [138][50/293] lr: 5.000000e-04 eta: 11:45:39 time: 2.916153 data_time: 1.285754 memory: 9974 loss_kpt: 0.001649 loss: 0.001649 2022/09/15 19:57:31 - mmengine - INFO - Epoch(train) [138][100/293] lr: 5.000000e-04 eta: 11:44:11 time: 2.401580 data_time: 0.249782 memory: 9974 loss_kpt: 0.001660 loss: 0.001660 2022/09/15 19:59:24 - mmengine - INFO - Epoch(train) [138][150/293] lr: 5.000000e-04 eta: 11:42:40 time: 2.273642 data_time: 0.333982 memory: 9974 loss_kpt: 0.001634 loss: 0.001634 2022/09/15 20:01:43 - mmengine - INFO - Epoch(train) [138][200/293] lr: 5.000000e-04 eta: 11:41:21 time: 2.777534 data_time: 1.177820 memory: 9974 loss_kpt: 0.001627 loss: 0.001627 2022/09/15 20:03:53 - mmengine - INFO - Epoch(train) [138][250/293] lr: 5.000000e-04 eta: 11:39:58 time: 2.592079 data_time: 0.906722 memory: 9974 loss_kpt: 0.001613 loss: 0.001613 2022/09/15 20:05:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 20:05:43 - mmengine - INFO - Saving checkpoint at 138 epochs 2022/09/15 20:08:07 - mmengine - INFO - Epoch(train) [139][50/293] lr: 5.000000e-04 eta: 11:36:30 time: 2.827776 data_time: 0.954216 memory: 9974 loss_kpt: 0.001625 loss: 0.001625 2022/09/15 20:09:51 - mmengine - INFO - Epoch(train) [139][100/293] lr: 5.000000e-04 eta: 11:34:54 time: 2.075533 data_time: 0.081460 memory: 9974 loss_kpt: 0.001627 loss: 0.001627 2022/09/15 20:12:03 - mmengine - INFO - Epoch(train) [139][150/293] lr: 5.000000e-04 eta: 11:33:31 time: 2.635355 data_time: 0.275539 memory: 9974 loss_kpt: 0.001607 loss: 0.001607 2022/09/15 20:14:27 - mmengine - INFO - Epoch(train) [139][200/293] lr: 5.000000e-04 eta: 11:32:15 time: 2.887688 data_time: 0.157630 memory: 9974 loss_kpt: 0.001653 loss: 0.001653 2022/09/15 20:16:09 - mmengine - INFO - Epoch(train) [139][250/293] lr: 5.000000e-04 eta: 11:30:37 time: 2.035523 data_time: 0.135720 memory: 9974 loss_kpt: 0.001653 loss: 0.001653 2022/09/15 20:17:54 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 20:17:54 - mmengine - INFO - Saving checkpoint at 139 epochs 2022/09/15 20:20:20 - mmengine - INFO - Epoch(train) [140][50/293] lr: 5.000000e-04 eta: 11:27:10 time: 2.860173 data_time: 0.666189 memory: 9974 loss_kpt: 0.001665 loss: 0.001665 2022/09/15 20:21:57 - mmengine - INFO - Epoch(train) [140][100/293] lr: 5.000000e-04 eta: 11:25:30 time: 1.931999 data_time: 0.429609 memory: 9974 loss_kpt: 0.001657 loss: 0.001657 2022/09/15 20:24:32 - mmengine - INFO - Epoch(train) [140][150/293] lr: 5.000000e-04 eta: 11:24:19 time: 3.101616 data_time: 0.844025 memory: 9974 loss_kpt: 0.001642 loss: 0.001642 2022/09/15 20:26:44 - mmengine - INFO - Epoch(train) [140][200/293] lr: 5.000000e-04 eta: 11:22:56 time: 2.646001 data_time: 0.970081 memory: 9974 loss_kpt: 0.001630 loss: 0.001630 2022/09/15 20:28:43 - mmengine - INFO - Epoch(train) [140][250/293] lr: 5.000000e-04 eta: 11:21:26 time: 2.381829 data_time: 0.465296 memory: 9974 loss_kpt: 0.001661 loss: 0.001661 2022/09/15 20:29:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 20:30:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 20:30:30 - mmengine - INFO - Saving checkpoint at 140 epochs 2022/09/15 20:31:49 - mmengine - INFO - Epoch(val) [140][50/407] eta: 0:08:59 time: 1.511007 data_time: 1.357195 memory: 9974 2022/09/15 20:32:42 - mmengine - INFO - Epoch(val) [140][100/407] eta: 0:05:23 time: 1.054950 data_time: 0.908048 memory: 918 2022/09/15 20:33:34 - mmengine - INFO - Epoch(val) [140][150/407] eta: 0:04:25 time: 1.033954 data_time: 0.882798 memory: 918 2022/09/15 20:34:57 - mmengine - INFO - Epoch(val) [140][200/407] eta: 0:05:43 time: 1.659122 data_time: 1.509522 memory: 918 2022/09/15 20:36:06 - mmengine - INFO - Epoch(val) [140][250/407] eta: 0:03:36 time: 1.381903 data_time: 1.237959 memory: 918 2022/09/15 20:37:05 - mmengine - INFO - Epoch(val) [140][300/407] eta: 0:02:06 time: 1.185019 data_time: 1.041642 memory: 918 2022/09/15 20:37:53 - mmengine - INFO - Epoch(val) [140][350/407] eta: 0:00:55 time: 0.971329 data_time: 0.827889 memory: 918 2022/09/15 20:38:58 - mmengine - INFO - Epoch(val) [140][400/407] eta: 0:00:09 time: 1.286811 data_time: 1.127105 memory: 918 2022/09/15 20:39:37 - mmengine - INFO - Evaluating CocoMetric... 2022/09/15 20:39:50 - mmengine - INFO - Epoch(val) [140][407/407] coco/AP: 0.746961 coco/AP .5: 0.904338 coco/AP .75: 0.817563 coco/AP (M): 0.708822 coco/AP (L): 0.814607 coco/AR: 0.802047 coco/AR .5: 0.941278 coco/AR .75: 0.862878 coco/AR (M): 0.759191 coco/AR (L): 0.864177 2022/09/15 20:39:50 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/udp_regress/best_coco/AP_epoch_130.pth is removed 2022/09/15 20:39:53 - mmengine - INFO - The best checkpoint with 0.7470 coco/AP at 140 epoch is saved to best_coco/AP_epoch_140.pth. 2022/09/15 20:41:33 - mmengine - INFO - Epoch(train) [141][50/293] lr: 5.000000e-04 eta: 11:17:39 time: 2.006145 data_time: 0.362029 memory: 9974 loss_kpt: 0.001639 loss: 0.001639 2022/09/15 20:43:13 - mmengine - INFO - Epoch(train) [141][100/293] lr: 5.000000e-04 eta: 11:16:00 time: 1.990745 data_time: 0.140448 memory: 9974 loss_kpt: 0.001635 loss: 0.001635 2022/09/15 20:44:42 - mmengine - INFO - Epoch(train) [141][150/293] lr: 5.000000e-04 eta: 11:14:15 time: 1.780518 data_time: 0.173965 memory: 9974 loss_kpt: 0.001633 loss: 0.001633 2022/09/15 20:46:08 - mmengine - INFO - Epoch(train) [141][200/293] lr: 5.000000e-04 eta: 11:12:30 time: 1.738029 data_time: 0.375705 memory: 9974 loss_kpt: 0.001644 loss: 0.001644 2022/09/15 20:47:49 - mmengine - INFO - Epoch(train) [141][250/293] lr: 5.000000e-04 eta: 11:10:51 time: 2.010992 data_time: 0.683936 memory: 9974 loss_kpt: 0.001625 loss: 0.001625 2022/09/15 20:49:01 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 20:49:01 - mmengine - INFO - Saving checkpoint at 141 epochs 2022/09/15 20:50:34 - mmengine - INFO - Epoch(train) [142][50/293] lr: 5.000000e-04 eta: 11:07:00 time: 1.792574 data_time: 0.205568 memory: 9974 loss_kpt: 0.001633 loss: 0.001633 2022/09/15 20:52:19 - mmengine - INFO - Epoch(train) [142][100/293] lr: 5.000000e-04 eta: 11:05:24 time: 2.107712 data_time: 0.086381 memory: 9974 loss_kpt: 0.001625 loss: 0.001625 2022/09/15 20:54:03 - mmengine - INFO - Epoch(train) [142][150/293] lr: 5.000000e-04 eta: 11:03:47 time: 2.078972 data_time: 0.149134 memory: 9974 loss_kpt: 0.001639 loss: 0.001639 2022/09/15 20:55:26 - mmengine - INFO - Epoch(train) [142][200/293] lr: 5.000000e-04 eta: 11:01:59 time: 1.653502 data_time: 0.248892 memory: 9974 loss_kpt: 0.001631 loss: 0.001631 2022/09/15 20:57:05 - mmengine - INFO - Epoch(train) [142][250/293] lr: 5.000000e-04 eta: 11:00:20 time: 1.978051 data_time: 0.213977 memory: 9974 loss_kpt: 0.001641 loss: 0.001641 2022/09/15 20:58:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 20:58:30 - mmengine - INFO - Saving checkpoint at 142 epochs 2022/09/15 21:00:08 - mmengine - INFO - Epoch(train) [143][50/293] lr: 5.000000e-04 eta: 10:56:33 time: 1.903503 data_time: 0.531688 memory: 9974 loss_kpt: 0.001640 loss: 0.001640 2022/09/15 21:01:44 - mmengine - INFO - Epoch(train) [143][100/293] lr: 5.000000e-04 eta: 10:54:53 time: 1.930088 data_time: 0.794533 memory: 9974 loss_kpt: 0.001641 loss: 0.001641 2022/09/15 21:03:13 - mmengine - INFO - Epoch(train) [143][150/293] lr: 5.000000e-04 eta: 10:53:08 time: 1.766825 data_time: 0.859868 memory: 9974 loss_kpt: 0.001630 loss: 0.001630 2022/09/15 21:05:11 - mmengine - INFO - Epoch(train) [143][200/293] lr: 5.000000e-04 eta: 10:51:38 time: 2.358073 data_time: 1.736104 memory: 9974 loss_kpt: 0.001625 loss: 0.001625 2022/09/15 21:06:45 - mmengine - INFO - Epoch(train) [143][250/293] lr: 5.000000e-04 eta: 10:49:57 time: 1.886621 data_time: 0.552138 memory: 9974 loss_kpt: 0.001617 loss: 0.001617 2022/09/15 21:07:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 21:07:56 - mmengine - INFO - Saving checkpoint at 143 epochs 2022/09/15 21:09:25 - mmengine - INFO - Epoch(train) [144][50/293] lr: 5.000000e-04 eta: 10:46:06 time: 1.697301 data_time: 1.205963 memory: 9974 loss_kpt: 0.001650 loss: 0.001650 2022/09/15 21:11:01 - mmengine - INFO - Epoch(train) [144][100/293] lr: 5.000000e-04 eta: 10:44:26 time: 1.919148 data_time: 0.943969 memory: 9974 loss_kpt: 0.001623 loss: 0.001623 2022/09/15 21:11:03 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 21:12:40 - mmengine - INFO - Epoch(train) [144][150/293] lr: 5.000000e-04 eta: 10:42:47 time: 1.991100 data_time: 0.765129 memory: 9974 loss_kpt: 0.001615 loss: 0.001615 2022/09/15 21:14:36 - mmengine - INFO - Epoch(train) [144][200/293] lr: 5.000000e-04 eta: 10:41:16 time: 2.323866 data_time: 0.443014 memory: 9974 loss_kpt: 0.001643 loss: 0.001643 2022/09/15 21:16:09 - mmengine - INFO - Epoch(train) [144][250/293] lr: 5.000000e-04 eta: 10:39:34 time: 1.854319 data_time: 0.139060 memory: 9974 loss_kpt: 0.001619 loss: 0.001619 2022/09/15 21:18:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 21:18:13 - mmengine - INFO - Saving checkpoint at 144 epochs 2022/09/15 21:20:56 - mmengine - INFO - Epoch(train) [145][50/293] lr: 5.000000e-04 eta: 10:36:19 time: 3.205777 data_time: 0.443882 memory: 9974 loss_kpt: 0.001627 loss: 0.001627 2022/09/15 21:22:56 - mmengine - INFO - Epoch(train) [145][100/293] lr: 5.000000e-04 eta: 10:34:49 time: 2.391746 data_time: 0.165589 memory: 9974 loss_kpt: 0.001629 loss: 0.001629 2022/09/15 21:25:25 - mmengine - INFO - Epoch(train) [145][150/293] lr: 5.000000e-04 eta: 10:33:33 time: 2.982930 data_time: 0.749529 memory: 9974 loss_kpt: 0.001623 loss: 0.001623 2022/09/15 21:27:35 - mmengine - INFO - Epoch(train) [145][200/293] lr: 5.000000e-04 eta: 10:32:08 time: 2.594096 data_time: 0.697697 memory: 9974 loss_kpt: 0.001634 loss: 0.001634 2022/09/15 21:29:38 - mmengine - INFO - Epoch(train) [145][250/293] lr: 5.000000e-04 eta: 10:30:40 time: 2.466683 data_time: 0.129714 memory: 9974 loss_kpt: 0.001618 loss: 0.001618 2022/09/15 21:31:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 21:31:08 - mmengine - INFO - Saving checkpoint at 145 epochs 2022/09/15 21:32:49 - mmengine - INFO - Epoch(train) [146][50/293] lr: 5.000000e-04 eta: 10:26:57 time: 1.965433 data_time: 0.403852 memory: 9974 loss_kpt: 0.001627 loss: 0.001627 2022/09/15 21:35:21 - mmengine - INFO - Epoch(train) [146][100/293] lr: 5.000000e-04 eta: 10:25:41 time: 3.030567 data_time: 1.274089 memory: 9974 loss_kpt: 0.001637 loss: 0.001637 2022/09/15 21:37:13 - mmengine - INFO - Epoch(train) [146][150/293] lr: 5.000000e-04 eta: 10:24:08 time: 2.249174 data_time: 0.351913 memory: 9974 loss_kpt: 0.001615 loss: 0.001615 2022/09/15 21:38:49 - mmengine - INFO - Epoch(train) [146][200/293] lr: 5.000000e-04 eta: 10:22:28 time: 1.920811 data_time: 0.803563 memory: 9974 loss_kpt: 0.001631 loss: 0.001631 2022/09/15 21:41:11 - mmengine - INFO - Epoch(train) [146][250/293] lr: 5.000000e-04 eta: 10:21:07 time: 2.836539 data_time: 0.653477 memory: 9974 loss_kpt: 0.001618 loss: 0.001618 2022/09/15 21:43:20 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 21:43:20 - mmengine - INFO - Saving checkpoint at 146 epochs 2022/09/15 21:44:59 - mmengine - INFO - Epoch(train) [147][50/293] lr: 5.000000e-04 eta: 10:17:24 time: 1.928191 data_time: 0.311971 memory: 9974 loss_kpt: 0.001610 loss: 0.001610 2022/09/15 21:47:25 - mmengine - INFO - Epoch(train) [147][100/293] lr: 5.000000e-04 eta: 10:16:05 time: 2.902800 data_time: 0.739584 memory: 9974 loss_kpt: 0.001628 loss: 0.001628 2022/09/15 21:50:01 - mmengine - INFO - Epoch(train) [147][150/293] lr: 5.000000e-04 eta: 10:14:51 time: 3.132495 data_time: 0.183476 memory: 9974 loss_kpt: 0.001608 loss: 0.001608 2022/09/15 21:52:13 - mmengine - INFO - Epoch(train) [147][200/293] lr: 5.000000e-04 eta: 10:13:26 time: 2.645049 data_time: 0.978456 memory: 9974 loss_kpt: 0.001628 loss: 0.001628 2022/09/15 21:53:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 21:54:39 - mmengine - INFO - Epoch(train) [147][250/293] lr: 5.000000e-04 eta: 10:12:07 time: 2.916913 data_time: 0.511078 memory: 9974 loss_kpt: 0.001610 loss: 0.001610 2022/09/15 21:56:03 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 21:56:03 - mmengine - INFO - Saving checkpoint at 147 epochs 2022/09/15 21:58:01 - mmengine - INFO - Epoch(train) [148][50/293] lr: 5.000000e-04 eta: 10:08:33 time: 2.281160 data_time: 0.547594 memory: 9974 loss_kpt: 0.001635 loss: 0.001635 2022/09/15 22:00:23 - mmengine - INFO - Epoch(train) [148][100/293] lr: 5.000000e-04 eta: 10:07:12 time: 2.841673 data_time: 0.147157 memory: 9974 loss_kpt: 0.001637 loss: 0.001637 2022/09/15 22:02:40 - mmengine - INFO - Epoch(train) [148][150/293] lr: 5.000000e-04 eta: 10:05:48 time: 2.742286 data_time: 1.303920 memory: 9974 loss_kpt: 0.001608 loss: 0.001608 2022/09/15 22:05:30 - mmengine - INFO - Epoch(train) [148][200/293] lr: 5.000000e-04 eta: 10:04:39 time: 3.400286 data_time: 1.000066 memory: 9974 loss_kpt: 0.001600 loss: 0.001600 2022/09/15 22:08:00 - mmengine - INFO - Epoch(train) [148][250/293] lr: 5.000000e-04 eta: 10:03:21 time: 3.003294 data_time: 0.407101 memory: 9974 loss_kpt: 0.001614 loss: 0.001614 2022/09/15 22:10:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 22:10:05 - mmengine - INFO - Saving checkpoint at 148 epochs 2022/09/15 22:12:40 - mmengine - INFO - Epoch(train) [149][50/293] lr: 5.000000e-04 eta: 10:00:03 time: 3.052392 data_time: 0.564851 memory: 9974 loss_kpt: 0.001624 loss: 0.001624 2022/09/15 22:14:35 - mmengine - INFO - Epoch(train) [149][100/293] lr: 5.000000e-04 eta: 9:58:30 time: 2.291285 data_time: 0.124340 memory: 9974 loss_kpt: 0.001591 loss: 0.001591 2022/09/15 22:16:24 - mmengine - INFO - Epoch(train) [149][150/293] lr: 5.000000e-04 eta: 9:56:54 time: 2.183264 data_time: 0.090862 memory: 9974 loss_kpt: 0.001671 loss: 0.001671 2022/09/15 22:19:05 - mmengine - INFO - Epoch(train) [149][200/293] lr: 5.000000e-04 eta: 9:55:40 time: 3.215289 data_time: 0.843683 memory: 9974 loss_kpt: 0.001641 loss: 0.001641 2022/09/15 22:21:18 - mmengine - INFO - Epoch(train) [149][250/293] lr: 5.000000e-04 eta: 9:54:14 time: 2.657175 data_time: 0.403178 memory: 9974 loss_kpt: 0.001675 loss: 0.001675 2022/09/15 22:23:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 22:23:04 - mmengine - INFO - Saving checkpoint at 149 epochs 2022/09/15 22:25:04 - mmengine - INFO - Epoch(train) [150][50/293] lr: 5.000000e-04 eta: 9:50:41 time: 2.318312 data_time: 1.690971 memory: 9974 loss_kpt: 0.001635 loss: 0.001635 2022/09/15 22:27:24 - mmengine - INFO - Epoch(train) [150][100/293] lr: 5.000000e-04 eta: 9:49:18 time: 2.809878 data_time: 0.381303 memory: 9974 loss_kpt: 0.001592 loss: 0.001592 2022/09/15 22:29:22 - mmengine - INFO - Epoch(train) [150][150/293] lr: 5.000000e-04 eta: 9:47:47 time: 2.367613 data_time: 0.256235 memory: 9974 loss_kpt: 0.001614 loss: 0.001614 2022/09/15 22:31:58 - mmengine - INFO - Epoch(train) [150][200/293] lr: 5.000000e-04 eta: 9:46:30 time: 3.112216 data_time: 0.313386 memory: 9974 loss_kpt: 0.001613 loss: 0.001613 2022/09/15 22:34:19 - mmengine - INFO - Epoch(train) [150][250/293] lr: 5.000000e-04 eta: 9:45:07 time: 2.825976 data_time: 1.599758 memory: 9974 loss_kpt: 0.001601 loss: 0.001601 2022/09/15 22:35:45 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 22:35:45 - mmengine - INFO - Saving checkpoint at 150 epochs 2022/09/15 22:37:13 - mmengine - INFO - Epoch(val) [150][50/407] eta: 0:10:09 time: 1.706584 data_time: 1.555575 memory: 9974 2022/09/15 22:38:36 - mmengine - INFO - Epoch(val) [150][100/407] eta: 0:08:28 time: 1.656285 data_time: 1.498854 memory: 918 2022/09/15 22:39:37 - mmengine - INFO - Epoch(val) [150][150/407] eta: 0:05:14 time: 1.223839 data_time: 1.077840 memory: 918 2022/09/15 22:40:44 - mmengine - INFO - Epoch(val) [150][200/407] eta: 0:04:36 time: 1.335145 data_time: 1.184164 memory: 918 2022/09/15 22:41:17 - mmengine - INFO - Epoch(val) [150][250/407] eta: 0:01:45 time: 0.672836 data_time: 0.528793 memory: 918 2022/09/15 22:41:55 - mmengine - INFO - Epoch(val) [150][300/407] eta: 0:01:21 time: 0.759546 data_time: 0.608775 memory: 918 2022/09/15 22:43:02 - mmengine - INFO - Epoch(val) [150][350/407] eta: 0:01:16 time: 1.333835 data_time: 1.185622 memory: 918 2022/09/15 22:44:25 - mmengine - INFO - Epoch(val) [150][400/407] eta: 0:00:11 time: 1.664412 data_time: 1.502239 memory: 918 2022/09/15 22:45:51 - mmengine - INFO - Evaluating CocoMetric... 2022/09/15 22:46:04 - mmengine - INFO - Epoch(val) [150][407/407] coco/AP: 0.744918 coco/AP .5: 0.900879 coco/AP .75: 0.811029 coco/AP (M): 0.704049 coco/AP (L): 0.814562 coco/AR: 0.799323 coco/AR .5: 0.937028 coco/AR .75: 0.858627 coco/AR (M): 0.754766 coco/AR (L): 0.864140 2022/09/15 22:49:12 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 22:49:12 - mmengine - INFO - Epoch(train) [151][50/293] lr: 5.000000e-04 eta: 9:42:03 time: 3.754362 data_time: 0.936942 memory: 9974 loss_kpt: 0.001612 loss: 0.001612 2022/09/15 22:51:09 - mmengine - INFO - Epoch(train) [151][100/293] lr: 5.000000e-04 eta: 9:40:30 time: 2.350740 data_time: 0.693025 memory: 9974 loss_kpt: 0.001641 loss: 0.001641 2022/09/15 22:53:07 - mmengine - INFO - Epoch(train) [151][150/293] lr: 5.000000e-04 eta: 9:38:58 time: 2.349039 data_time: 0.097488 memory: 9974 loss_kpt: 0.001631 loss: 0.001631 2022/09/15 22:55:21 - mmengine - INFO - Epoch(train) [151][200/293] lr: 5.000000e-04 eta: 9:37:32 time: 2.686393 data_time: 0.307712 memory: 9974 loss_kpt: 0.001626 loss: 0.001626 2022/09/15 22:57:58 - mmengine - INFO - Epoch(train) [151][250/293] lr: 5.000000e-04 eta: 9:36:14 time: 3.137435 data_time: 0.229152 memory: 9974 loss_kpt: 0.001619 loss: 0.001619 2022/09/15 23:00:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 23:00:04 - mmengine - INFO - Saving checkpoint at 151 epochs 2022/09/15 23:02:25 - mmengine - INFO - Epoch(train) [152][50/293] lr: 5.000000e-04 eta: 9:32:50 time: 2.763552 data_time: 0.535199 memory: 9974 loss_kpt: 0.001630 loss: 0.001630 2022/09/15 23:05:16 - mmengine - INFO - Epoch(train) [152][100/293] lr: 5.000000e-04 eta: 9:31:38 time: 3.422408 data_time: 0.089925 memory: 9974 loss_kpt: 0.001623 loss: 0.001623 2022/09/15 23:07:13 - mmengine - INFO - Epoch(train) [152][150/293] lr: 5.000000e-04 eta: 9:30:05 time: 2.332197 data_time: 0.258296 memory: 9974 loss_kpt: 0.001615 loss: 0.001615 2022/09/15 23:09:36 - mmengine - INFO - Epoch(train) [152][200/293] lr: 5.000000e-04 eta: 9:28:42 time: 2.857108 data_time: 0.124226 memory: 9974 loss_kpt: 0.001611 loss: 0.001611 2022/09/15 23:11:41 - mmengine - INFO - Epoch(train) [152][250/293] lr: 5.000000e-04 eta: 9:27:12 time: 2.512190 data_time: 0.080910 memory: 9974 loss_kpt: 0.001623 loss: 0.001623 2022/09/15 23:13:24 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 23:13:24 - mmengine - INFO - Saving checkpoint at 152 epochs 2022/09/15 23:15:58 - mmengine - INFO - Epoch(train) [153][50/293] lr: 5.000000e-04 eta: 9:23:53 time: 3.013262 data_time: 0.675579 memory: 9974 loss_kpt: 0.001624 loss: 0.001624 2022/09/15 23:18:06 - mmengine - INFO - Epoch(train) [153][100/293] lr: 5.000000e-04 eta: 9:22:24 time: 2.566378 data_time: 1.176663 memory: 9974 loss_kpt: 0.001635 loss: 0.001635 2022/09/15 23:20:31 - mmengine - INFO - Epoch(train) [153][150/293] lr: 5.000000e-04 eta: 9:21:01 time: 2.905278 data_time: 1.141764 memory: 9974 loss_kpt: 0.001627 loss: 0.001627 2022/09/15 23:22:21 - mmengine - INFO - Epoch(train) [153][200/293] lr: 5.000000e-04 eta: 9:19:25 time: 2.192103 data_time: 0.164935 memory: 9974 loss_kpt: 0.001639 loss: 0.001639 2022/09/15 23:24:52 - mmengine - INFO - Epoch(train) [153][250/293] lr: 5.000000e-04 eta: 9:18:04 time: 3.027619 data_time: 1.023497 memory: 9974 loss_kpt: 0.001600 loss: 0.001600 2022/09/15 23:27:25 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 23:27:25 - mmengine - INFO - Saving checkpoint at 153 epochs 2022/09/15 23:29:45 - mmengine - INFO - Epoch(train) [154][50/293] lr: 5.000000e-04 eta: 9:14:40 time: 2.740298 data_time: 1.874980 memory: 9974 loss_kpt: 0.001616 loss: 0.001616 2022/09/15 23:31:38 - mmengine - INFO - Epoch(train) [154][100/293] lr: 5.000000e-04 eta: 9:13:05 time: 2.258563 data_time: 0.092942 memory: 9974 loss_kpt: 0.001634 loss: 0.001634 2022/09/15 23:34:07 - mmengine - INFO - Epoch(train) [154][150/293] lr: 5.000000e-04 eta: 9:11:43 time: 2.975869 data_time: 0.396275 memory: 9974 loss_kpt: 0.001611 loss: 0.001611 2022/09/15 23:35:17 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 23:36:37 - mmengine - INFO - Epoch(train) [154][200/293] lr: 5.000000e-04 eta: 9:10:21 time: 2.997198 data_time: 0.110593 memory: 9974 loss_kpt: 0.001635 loss: 0.001635 2022/09/15 23:38:39 - mmengine - INFO - Epoch(train) [154][250/293] lr: 5.000000e-04 eta: 9:08:49 time: 2.438819 data_time: 0.142548 memory: 9974 loss_kpt: 0.001624 loss: 0.001624 2022/09/15 23:41:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 23:41:05 - mmengine - INFO - Saving checkpoint at 154 epochs 2022/09/15 23:43:18 - mmengine - INFO - Epoch(train) [155][50/293] lr: 5.000000e-04 eta: 9:05:22 time: 2.602559 data_time: 0.320408 memory: 9974 loss_kpt: 0.001596 loss: 0.001596 2022/09/15 23:45:41 - mmengine - INFO - Epoch(train) [155][100/293] lr: 5.000000e-04 eta: 9:03:58 time: 2.863377 data_time: 0.682320 memory: 9974 loss_kpt: 0.001618 loss: 0.001618 2022/09/15 23:48:23 - mmengine - INFO - Epoch(train) [155][150/293] lr: 5.000000e-04 eta: 9:02:40 time: 3.236489 data_time: 0.430278 memory: 9974 loss_kpt: 0.001635 loss: 0.001635 2022/09/15 23:50:19 - mmengine - INFO - Epoch(train) [155][200/293] lr: 5.000000e-04 eta: 9:01:05 time: 2.305340 data_time: 0.090391 memory: 9974 loss_kpt: 0.001615 loss: 0.001615 2022/09/15 23:52:55 - mmengine - INFO - Epoch(train) [155][250/293] lr: 5.000000e-04 eta: 8:59:45 time: 3.130717 data_time: 0.970246 memory: 9974 loss_kpt: 0.001617 loss: 0.001617 2022/09/15 23:55:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/15 23:55:05 - mmengine - INFO - Saving checkpoint at 155 epochs 2022/09/15 23:57:09 - mmengine - INFO - Epoch(train) [156][50/293] lr: 5.000000e-04 eta: 8:56:16 time: 2.434602 data_time: 0.140711 memory: 9974 loss_kpt: 0.001631 loss: 0.001631 2022/09/15 23:59:30 - mmengine - INFO - Epoch(train) [156][100/293] lr: 5.000000e-04 eta: 8:54:50 time: 2.807223 data_time: 0.172026 memory: 9974 loss_kpt: 0.001623 loss: 0.001623 2022/09/16 00:01:40 - mmengine - INFO - Epoch(train) [156][150/293] lr: 5.000000e-04 eta: 8:53:20 time: 2.615298 data_time: 0.107165 memory: 9974 loss_kpt: 0.001603 loss: 0.001603 2022/09/16 00:04:09 - mmengine - INFO - Epoch(train) [156][200/293] lr: 5.000000e-04 eta: 8:51:57 time: 2.981603 data_time: 0.195717 memory: 9974 loss_kpt: 0.001645 loss: 0.001645 2022/09/16 00:06:36 - mmengine - INFO - Epoch(train) [156][250/293] lr: 5.000000e-04 eta: 8:50:33 time: 2.938121 data_time: 0.210615 memory: 9974 loss_kpt: 0.001645 loss: 0.001645 2022/09/16 00:08:15 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 00:08:15 - mmengine - INFO - Saving checkpoint at 156 epochs 2022/09/16 00:11:15 - mmengine - INFO - Epoch(train) [157][50/293] lr: 5.000000e-04 eta: 8:47:23 time: 3.530942 data_time: 0.464589 memory: 9974 loss_kpt: 0.001624 loss: 0.001624 2022/09/16 00:13:23 - mmengine - INFO - Epoch(train) [157][100/293] lr: 5.000000e-04 eta: 8:45:52 time: 2.561017 data_time: 0.210954 memory: 9974 loss_kpt: 0.001590 loss: 0.001590 2022/09/16 00:15:29 - mmengine - INFO - Epoch(train) [157][150/293] lr: 5.000000e-04 eta: 8:44:21 time: 2.514838 data_time: 0.312196 memory: 9974 loss_kpt: 0.001621 loss: 0.001621 2022/09/16 00:17:42 - mmengine - INFO - Epoch(train) [157][200/293] lr: 5.000000e-04 eta: 8:42:52 time: 2.673093 data_time: 0.343484 memory: 9974 loss_kpt: 0.001616 loss: 0.001616 2022/09/16 00:20:12 - mmengine - INFO - Epoch(train) [157][250/293] lr: 5.000000e-04 eta: 8:41:28 time: 2.996786 data_time: 0.177059 memory: 9974 loss_kpt: 0.001618 loss: 0.001618 2022/09/16 00:22:10 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 00:22:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 00:22:11 - mmengine - INFO - Saving checkpoint at 157 epochs 2022/09/16 00:24:41 - mmengine - INFO - Epoch(train) [158][50/293] lr: 5.000000e-04 eta: 8:38:08 time: 2.930971 data_time: 0.803869 memory: 9974 loss_kpt: 0.001615 loss: 0.001615 2022/09/16 00:26:25 - mmengine - INFO - Epoch(train) [158][100/293] lr: 5.000000e-04 eta: 8:36:28 time: 2.076047 data_time: 0.092473 memory: 9974 loss_kpt: 0.001650 loss: 0.001650 2022/09/16 00:28:27 - mmengine - INFO - Epoch(train) [158][150/293] lr: 5.000000e-04 eta: 8:34:55 time: 2.443760 data_time: 0.560360 memory: 9974 loss_kpt: 0.001612 loss: 0.001612 2022/09/16 00:31:14 - mmengine - INFO - Epoch(train) [158][200/293] lr: 5.000000e-04 eta: 8:33:37 time: 3.335110 data_time: 0.112461 memory: 9974 loss_kpt: 0.001595 loss: 0.001595 2022/09/16 00:32:46 - mmengine - INFO - Epoch(train) [158][250/293] lr: 5.000000e-04 eta: 8:31:53 time: 1.849137 data_time: 0.149944 memory: 9974 loss_kpt: 0.001592 loss: 0.001592 2022/09/16 00:34:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 00:34:05 - mmengine - INFO - Saving checkpoint at 158 epochs 2022/09/16 00:36:14 - mmengine - INFO - Epoch(train) [159][50/293] lr: 5.000000e-04 eta: 8:28:26 time: 2.490803 data_time: 0.977444 memory: 9974 loss_kpt: 0.001610 loss: 0.001610 2022/09/16 00:38:30 - mmengine - INFO - Epoch(train) [159][100/293] lr: 5.000000e-04 eta: 8:26:57 time: 2.724910 data_time: 0.603323 memory: 9974 loss_kpt: 0.001605 loss: 0.001605 2022/09/16 00:40:43 - mmengine - INFO - Epoch(train) [159][150/293] lr: 5.000000e-04 eta: 8:25:28 time: 2.673255 data_time: 0.611914 memory: 9974 loss_kpt: 0.001596 loss: 0.001596 2022/09/16 00:43:09 - mmengine - INFO - Epoch(train) [159][200/293] lr: 5.000000e-04 eta: 8:24:02 time: 2.903769 data_time: 1.384482 memory: 9974 loss_kpt: 0.001641 loss: 0.001641 2022/09/16 00:45:06 - mmengine - INFO - Epoch(train) [159][250/293] lr: 5.000000e-04 eta: 8:22:26 time: 2.352686 data_time: 0.116879 memory: 9974 loss_kpt: 0.001598 loss: 0.001598 2022/09/16 00:47:01 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 00:47:01 - mmengine - INFO - Saving checkpoint at 159 epochs 2022/09/16 00:48:54 - mmengine - INFO - Epoch(train) [160][50/293] lr: 5.000000e-04 eta: 8:18:54 time: 2.184103 data_time: 0.326948 memory: 9974 loss_kpt: 0.001604 loss: 0.001604 2022/09/16 00:50:26 - mmengine - INFO - Epoch(train) [160][100/293] lr: 5.000000e-04 eta: 8:17:11 time: 1.839313 data_time: 0.104128 memory: 9974 loss_kpt: 0.001615 loss: 0.001615 2022/09/16 00:51:40 - mmengine - INFO - Epoch(train) [160][150/293] lr: 5.000000e-04 eta: 8:15:22 time: 1.483183 data_time: 0.100955 memory: 9974 loss_kpt: 0.001630 loss: 0.001630 2022/09/16 00:53:15 - mmengine - INFO - Epoch(train) [160][200/293] lr: 5.000000e-04 eta: 8:13:40 time: 1.890721 data_time: 0.513798 memory: 9974 loss_kpt: 0.001611 loss: 0.001611 2022/09/16 00:54:31 - mmengine - INFO - Epoch(train) [160][250/293] lr: 5.000000e-04 eta: 8:11:52 time: 1.522349 data_time: 0.400681 memory: 9974 loss_kpt: 0.001617 loss: 0.001617 2022/09/16 00:55:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 00:55:41 - mmengine - INFO - Saving checkpoint at 160 epochs 2022/09/16 00:56:38 - mmengine - INFO - Epoch(val) [160][50/407] eta: 0:06:22 time: 1.072705 data_time: 0.920189 memory: 9974 2022/09/16 00:57:23 - mmengine - INFO - Epoch(val) [160][100/407] eta: 0:04:32 time: 0.887499 data_time: 0.738174 memory: 918 2022/09/16 00:58:35 - mmengine - INFO - Epoch(val) [160][150/407] eta: 0:06:11 time: 1.446630 data_time: 1.284030 memory: 918 2022/09/16 00:59:39 - mmengine - INFO - Epoch(val) [160][200/407] eta: 0:04:24 time: 1.277606 data_time: 1.126293 memory: 918 2022/09/16 01:00:27 - mmengine - INFO - Epoch(val) [160][250/407] eta: 0:02:30 time: 0.958747 data_time: 0.811462 memory: 918 2022/09/16 01:01:06 - mmengine - INFO - Epoch(val) [160][300/407] eta: 0:01:23 time: 0.782756 data_time: 0.634001 memory: 918 2022/09/16 01:01:50 - mmengine - INFO - Epoch(val) [160][350/407] eta: 0:00:50 time: 0.881467 data_time: 0.723807 memory: 918 2022/09/16 01:02:39 - mmengine - INFO - Epoch(val) [160][400/407] eta: 0:00:06 time: 0.977146 data_time: 0.829789 memory: 918 2022/09/16 01:03:18 - mmengine - INFO - Evaluating CocoMetric... 2022/09/16 01:03:31 - mmengine - INFO - Epoch(val) [160][407/407] coco/AP: 0.745138 coco/AP .5: 0.899869 coco/AP .75: 0.814065 coco/AP (M): 0.703558 coco/AP (L): 0.818354 coco/AR: 0.800331 coco/AR .5: 0.939232 coco/AR .75: 0.860516 coco/AR (M): 0.753592 coco/AR (L): 0.867596 2022/09/16 01:05:54 - mmengine - INFO - Epoch(train) [161][50/293] lr: 5.000000e-04 eta: 8:08:32 time: 2.858932 data_time: 0.820689 memory: 9974 loss_kpt: 0.001606 loss: 0.001606 2022/09/16 01:07:24 - mmengine - INFO - Epoch(train) [161][100/293] lr: 5.000000e-04 eta: 8:06:48 time: 1.795945 data_time: 0.145446 memory: 9974 loss_kpt: 0.001604 loss: 0.001604 2022/09/16 01:08:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 01:08:37 - mmengine - INFO - Epoch(train) [161][150/293] lr: 5.000000e-04 eta: 8:04:59 time: 1.448864 data_time: 0.111572 memory: 9974 loss_kpt: 0.001620 loss: 0.001620 2022/09/16 01:10:12 - mmengine - INFO - Epoch(train) [161][200/293] lr: 5.000000e-04 eta: 8:03:17 time: 1.903379 data_time: 0.090595 memory: 9974 loss_kpt: 0.001648 loss: 0.001648 2022/09/16 01:12:14 - mmengine - INFO - Epoch(train) [161][250/293] lr: 5.000000e-04 eta: 8:01:43 time: 2.440003 data_time: 0.087099 memory: 9974 loss_kpt: 0.001599 loss: 0.001599 2022/09/16 01:13:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 01:13:30 - mmengine - INFO - Saving checkpoint at 161 epochs 2022/09/16 01:15:23 - mmengine - INFO - Epoch(train) [162][50/293] lr: 5.000000e-04 eta: 7:58:13 time: 2.192177 data_time: 0.694257 memory: 9974 loss_kpt: 0.001579 loss: 0.001579 2022/09/16 01:17:02 - mmengine - INFO - Epoch(train) [162][100/293] lr: 5.000000e-04 eta: 7:56:33 time: 1.973877 data_time: 0.331713 memory: 9974 loss_kpt: 0.001595 loss: 0.001595 2022/09/16 01:19:09 - mmengine - INFO - Epoch(train) [162][150/293] lr: 5.000000e-04 eta: 7:55:00 time: 2.548178 data_time: 0.426253 memory: 9974 loss_kpt: 0.001615 loss: 0.001615 2022/09/16 01:20:51 - mmengine - INFO - Epoch(train) [162][200/293] lr: 5.000000e-04 eta: 7:53:21 time: 2.035287 data_time: 1.340753 memory: 9974 loss_kpt: 0.001616 loss: 0.001616 2022/09/16 01:22:45 - mmengine - INFO - Epoch(train) [162][250/293] lr: 5.000000e-04 eta: 7:51:44 time: 2.273221 data_time: 0.928665 memory: 9974 loss_kpt: 0.001594 loss: 0.001594 2022/09/16 01:24:03 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 01:24:03 - mmengine - INFO - Saving checkpoint at 162 epochs 2022/09/16 01:25:14 - mmengine - INFO - Epoch(train) [163][50/293] lr: 5.000000e-04 eta: 7:48:03 time: 1.357546 data_time: 0.211251 memory: 9974 loss_kpt: 0.001609 loss: 0.001609 2022/09/16 01:26:38 - mmengine - INFO - Epoch(train) [163][100/293] lr: 5.000000e-04 eta: 7:46:17 time: 1.672209 data_time: 0.085131 memory: 9974 loss_kpt: 0.001620 loss: 0.001620 2022/09/16 01:28:30 - mmengine - INFO - Epoch(train) [163][150/293] lr: 5.000000e-04 eta: 7:44:41 time: 2.237632 data_time: 0.214451 memory: 9974 loss_kpt: 0.001634 loss: 0.001634 2022/09/16 01:30:14 - mmengine - INFO - Epoch(train) [163][200/293] lr: 5.000000e-04 eta: 7:43:02 time: 2.078204 data_time: 0.497039 memory: 9974 loss_kpt: 0.001636 loss: 0.001636 2022/09/16 01:32:43 - mmengine - INFO - Epoch(train) [163][250/293] lr: 5.000000e-04 eta: 7:41:36 time: 2.987916 data_time: 0.233780 memory: 9974 loss_kpt: 0.001618 loss: 0.001618 2022/09/16 01:34:31 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 01:34:31 - mmengine - INFO - Saving checkpoint at 163 epochs 2022/09/16 01:36:20 - mmengine - INFO - Epoch(train) [164][50/293] lr: 5.000000e-04 eta: 7:38:06 time: 2.116579 data_time: 0.119909 memory: 9974 loss_kpt: 0.001604 loss: 0.001604 2022/09/16 01:37:59 - mmengine - INFO - Epoch(train) [164][100/293] lr: 5.000000e-04 eta: 7:36:26 time: 1.976882 data_time: 0.129480 memory: 9974 loss_kpt: 0.001576 loss: 0.001576 2022/09/16 01:39:35 - mmengine - INFO - Epoch(train) [164][150/293] lr: 5.000000e-04 eta: 7:34:44 time: 1.919661 data_time: 0.201113 memory: 9974 loss_kpt: 0.001630 loss: 0.001630 2022/09/16 01:41:36 - mmengine - INFO - Epoch(train) [164][200/293] lr: 5.000000e-04 eta: 7:33:10 time: 2.425100 data_time: 0.107001 memory: 9974 loss_kpt: 0.001610 loss: 0.001610 2022/09/16 01:43:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 01:43:34 - mmengine - INFO - Epoch(train) [164][250/293] lr: 5.000000e-04 eta: 7:31:35 time: 2.359004 data_time: 0.653786 memory: 9974 loss_kpt: 0.001617 loss: 0.001617 2022/09/16 01:45:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 01:45:11 - mmengine - INFO - Saving checkpoint at 164 epochs 2022/09/16 01:47:00 - mmengine - INFO - Epoch(train) [165][50/293] lr: 5.000000e-04 eta: 7:28:06 time: 2.115721 data_time: 0.208836 memory: 9974 loss_kpt: 0.001653 loss: 0.001653 2022/09/16 01:48:44 - mmengine - INFO - Epoch(train) [165][100/293] lr: 5.000000e-04 eta: 7:26:27 time: 2.065939 data_time: 0.165148 memory: 9974 loss_kpt: 0.001603 loss: 0.001603 2022/09/16 01:50:42 - mmengine - INFO - Epoch(train) [165][150/293] lr: 5.000000e-04 eta: 7:24:52 time: 2.367111 data_time: 0.082684 memory: 9974 loss_kpt: 0.001615 loss: 0.001615 2022/09/16 01:52:36 - mmengine - INFO - Epoch(train) [165][200/293] lr: 5.000000e-04 eta: 7:23:15 time: 2.275771 data_time: 0.280919 memory: 9974 loss_kpt: 0.001626 loss: 0.001626 2022/09/16 01:54:17 - mmengine - INFO - Epoch(train) [165][250/293] lr: 5.000000e-04 eta: 7:21:35 time: 2.015332 data_time: 0.285469 memory: 9974 loss_kpt: 0.001640 loss: 0.001640 2022/09/16 01:55:52 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 01:55:52 - mmengine - INFO - Saving checkpoint at 165 epochs 2022/09/16 01:57:36 - mmengine - INFO - Epoch(train) [166][50/293] lr: 5.000000e-04 eta: 7:18:06 time: 2.013096 data_time: 0.244481 memory: 9974 loss_kpt: 0.001622 loss: 0.001622 2022/09/16 01:59:17 - mmengine - INFO - Epoch(train) [166][100/293] lr: 5.000000e-04 eta: 7:16:26 time: 2.034874 data_time: 0.990273 memory: 9974 loss_kpt: 0.001598 loss: 0.001598 2022/09/16 02:00:39 - mmengine - INFO - Epoch(train) [166][150/293] lr: 5.000000e-04 eta: 7:14:41 time: 1.638303 data_time: 0.223028 memory: 9974 loss_kpt: 0.001620 loss: 0.001620 2022/09/16 02:02:15 - mmengine - INFO - Epoch(train) [166][200/293] lr: 5.000000e-04 eta: 7:13:00 time: 1.916397 data_time: 0.283185 memory: 9974 loss_kpt: 0.001643 loss: 0.001643 2022/09/16 02:03:48 - mmengine - INFO - Epoch(train) [166][250/293] lr: 5.000000e-04 eta: 7:11:18 time: 1.852246 data_time: 0.363675 memory: 9974 loss_kpt: 0.001597 loss: 0.001597 2022/09/16 02:05:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 02:05:33 - mmengine - INFO - Saving checkpoint at 166 epochs 2022/09/16 02:07:00 - mmengine - INFO - Epoch(train) [167][50/293] lr: 5.000000e-04 eta: 7:07:45 time: 1.658563 data_time: 0.649006 memory: 9974 loss_kpt: 0.001617 loss: 0.001617 2022/09/16 02:07:56 - mmengine - INFO - Epoch(train) [167][100/293] lr: 5.000000e-04 eta: 7:05:54 time: 1.135643 data_time: 0.259382 memory: 9974 loss_kpt: 0.001605 loss: 0.001605 2022/09/16 02:09:09 - mmengine - INFO - Epoch(train) [167][150/293] lr: 5.000000e-04 eta: 7:04:06 time: 1.444829 data_time: 0.142438 memory: 9974 loss_kpt: 0.001615 loss: 0.001615 2022/09/16 02:10:18 - mmengine - INFO - Epoch(train) [167][200/293] lr: 5.000000e-04 eta: 7:02:19 time: 1.385976 data_time: 0.136437 memory: 9974 loss_kpt: 0.001607 loss: 0.001607 2022/09/16 02:11:50 - mmengine - INFO - Epoch(train) [167][250/293] lr: 5.000000e-04 eta: 7:00:37 time: 1.836013 data_time: 0.312104 memory: 9974 loss_kpt: 0.001629 loss: 0.001629 2022/09/16 02:13:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 02:13:02 - mmengine - INFO - Saving checkpoint at 167 epochs 2022/09/16 02:14:27 - mmengine - INFO - Epoch(train) [168][50/293] lr: 5.000000e-04 eta: 6:57:04 time: 1.620265 data_time: 0.151927 memory: 9974 loss_kpt: 0.001607 loss: 0.001607 2022/09/16 02:14:53 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 02:15:52 - mmengine - INFO - Epoch(train) [168][100/293] lr: 5.000000e-04 eta: 6:55:21 time: 1.705502 data_time: 0.209724 memory: 9974 loss_kpt: 0.001603 loss: 0.001603 2022/09/16 02:17:27 - mmengine - INFO - Epoch(train) [168][150/293] lr: 5.000000e-04 eta: 6:53:40 time: 1.896902 data_time: 0.084940 memory: 9974 loss_kpt: 0.001620 loss: 0.001620 2022/09/16 02:18:53 - mmengine - INFO - Epoch(train) [168][200/293] lr: 5.000000e-04 eta: 6:51:57 time: 1.722852 data_time: 0.143093 memory: 9974 loss_kpt: 0.001619 loss: 0.001619 2022/09/16 02:20:15 - mmengine - INFO - Epoch(train) [168][250/293] lr: 5.000000e-04 eta: 6:50:13 time: 1.633162 data_time: 0.246696 memory: 9974 loss_kpt: 0.001602 loss: 0.001602 2022/09/16 02:21:31 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 02:21:31 - mmengine - INFO - Saving checkpoint at 168 epochs 2022/09/16 02:23:34 - mmengine - INFO - Epoch(train) [169][50/293] lr: 5.000000e-04 eta: 6:46:51 time: 2.393045 data_time: 0.323276 memory: 9974 loss_kpt: 0.001588 loss: 0.001588 2022/09/16 02:25:10 - mmengine - INFO - Epoch(train) [169][100/293] lr: 5.000000e-04 eta: 6:45:10 time: 1.914237 data_time: 0.655778 memory: 9974 loss_kpt: 0.001604 loss: 0.001604 2022/09/16 02:26:34 - mmengine - INFO - Epoch(train) [169][150/293] lr: 5.000000e-04 eta: 6:43:27 time: 1.689847 data_time: 0.746973 memory: 9974 loss_kpt: 0.001634 loss: 0.001634 2022/09/16 02:28:26 - mmengine - INFO - Epoch(train) [169][200/293] lr: 5.000000e-04 eta: 6:41:51 time: 2.237772 data_time: 0.112771 memory: 9974 loss_kpt: 0.001623 loss: 0.001623 2022/09/16 02:29:38 - mmengine - INFO - Epoch(train) [169][250/293] lr: 5.000000e-04 eta: 6:40:04 time: 1.435668 data_time: 0.095099 memory: 9974 loss_kpt: 0.001620 loss: 0.001620 2022/09/16 02:30:39 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 02:30:39 - mmengine - INFO - Saving checkpoint at 169 epochs 2022/09/16 02:32:23 - mmengine - INFO - Epoch(train) [170][50/293] lr: 5.000000e-04 eta: 6:36:39 time: 2.006469 data_time: 0.225955 memory: 9974 loss_kpt: 0.001622 loss: 0.001622 2022/09/16 02:33:33 - mmengine - INFO - Epoch(train) [170][100/293] lr: 5.000000e-04 eta: 6:34:52 time: 1.402319 data_time: 0.139751 memory: 9974 loss_kpt: 0.001612 loss: 0.001612 2022/09/16 02:34:57 - mmengine - INFO - Epoch(train) [170][150/293] lr: 5.000000e-04 eta: 6:33:09 time: 1.688283 data_time: 0.237094 memory: 9974 loss_kpt: 0.001598 loss: 0.001598 2022/09/16 02:36:21 - mmengine - INFO - Epoch(train) [170][200/293] lr: 5.000000e-04 eta: 6:31:26 time: 1.678064 data_time: 0.095858 memory: 9974 loss_kpt: 0.001615 loss: 0.001615 2022/09/16 02:37:36 - mmengine - INFO - Epoch(train) [170][250/293] lr: 5.000000e-04 eta: 6:29:41 time: 1.487903 data_time: 0.087269 memory: 9974 loss_kpt: 0.001608 loss: 0.001608 2022/09/16 02:38:48 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 02:38:48 - mmengine - INFO - Saving checkpoint at 170 epochs 2022/09/16 02:39:34 - mmengine - INFO - Epoch(val) [170][50/407] eta: 0:05:10 time: 0.870303 data_time: 0.725878 memory: 9974 2022/09/16 02:40:11 - mmengine - INFO - Epoch(val) [170][100/407] eta: 0:03:44 time: 0.731032 data_time: 0.583469 memory: 918 2022/09/16 02:40:48 - mmengine - INFO - Epoch(val) [170][150/407] eta: 0:03:09 time: 0.738355 data_time: 0.588287 memory: 918 2022/09/16 02:41:31 - mmengine - INFO - Epoch(val) [170][200/407] eta: 0:02:59 time: 0.869237 data_time: 0.724228 memory: 918 2022/09/16 02:41:57 - mmengine - INFO - Epoch(val) [170][250/407] eta: 0:01:19 time: 0.504619 data_time: 0.361804 memory: 918 2022/09/16 02:42:29 - mmengine - INFO - Epoch(val) [170][300/407] eta: 0:01:10 time: 0.656355 data_time: 0.508502 memory: 918 2022/09/16 02:43:01 - mmengine - INFO - Epoch(val) [170][350/407] eta: 0:00:36 time: 0.636069 data_time: 0.489133 memory: 918 2022/09/16 02:43:43 - mmengine - INFO - Epoch(val) [170][400/407] eta: 0:00:05 time: 0.837698 data_time: 0.692447 memory: 918 2022/09/16 02:46:29 - mmengine - INFO - Evaluating CocoMetric... 2022/09/16 02:46:43 - mmengine - INFO - Epoch(val) [170][407/407] coco/AP: 0.743617 coco/AP .5: 0.903652 coco/AP .75: 0.811030 coco/AP (M): 0.703010 coco/AP (L): 0.813188 coco/AR: 0.800834 coco/AR .5: 0.940963 coco/AR .75: 0.859729 coco/AR (M): 0.757252 coco/AR (L): 0.863434 2022/09/16 02:48:33 - mmengine - INFO - Epoch(train) [171][50/293] lr: 5.000000e-05 eta: 6:26:18 time: 2.207789 data_time: 0.341244 memory: 9974 loss_kpt: 0.001610 loss: 0.001610 2022/09/16 02:49:59 - mmengine - INFO - Epoch(train) [171][100/293] lr: 5.000000e-05 eta: 6:24:36 time: 1.722083 data_time: 0.271203 memory: 9974 loss_kpt: 0.001574 loss: 0.001574 2022/09/16 02:51:13 - mmengine - INFO - Epoch(train) [171][150/293] lr: 5.000000e-05 eta: 6:22:51 time: 1.482639 data_time: 0.103508 memory: 9974 loss_kpt: 0.001578 loss: 0.001578 2022/09/16 02:52:09 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 02:52:24 - mmengine - INFO - Epoch(train) [171][200/293] lr: 5.000000e-05 eta: 6:21:05 time: 1.419139 data_time: 0.098007 memory: 9974 loss_kpt: 0.001583 loss: 0.001583 2022/09/16 02:53:34 - mmengine - INFO - Epoch(train) [171][250/293] lr: 5.000000e-05 eta: 6:19:19 time: 1.397485 data_time: 0.088371 memory: 9974 loss_kpt: 0.001565 loss: 0.001565 2022/09/16 02:54:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 02:54:33 - mmengine - INFO - Saving checkpoint at 171 epochs 2022/09/16 02:55:57 - mmengine - INFO - Epoch(train) [172][50/293] lr: 5.000000e-05 eta: 6:15:51 time: 1.613093 data_time: 0.169657 memory: 9974 loss_kpt: 0.001566 loss: 0.001566 2022/09/16 02:57:27 - mmengine - INFO - Epoch(train) [172][100/293] lr: 5.000000e-05 eta: 6:14:10 time: 1.801150 data_time: 0.489514 memory: 9974 loss_kpt: 0.001557 loss: 0.001557 2022/09/16 02:58:49 - mmengine - INFO - Epoch(train) [172][150/293] lr: 5.000000e-05 eta: 6:12:27 time: 1.648490 data_time: 0.677571 memory: 9974 loss_kpt: 0.001567 loss: 0.001567 2022/09/16 03:00:00 - mmengine - INFO - Epoch(train) [172][200/293] lr: 5.000000e-05 eta: 6:10:41 time: 1.412777 data_time: 0.266200 memory: 9974 loss_kpt: 0.001555 loss: 0.001555 2022/09/16 03:01:25 - mmengine - INFO - Epoch(train) [172][250/293] lr: 5.000000e-05 eta: 6:08:59 time: 1.699377 data_time: 0.089684 memory: 9974 loss_kpt: 0.001549 loss: 0.001549 2022/09/16 03:02:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 03:02:30 - mmengine - INFO - Saving checkpoint at 172 epochs 2022/09/16 03:03:56 - mmengine - INFO - Epoch(train) [173][50/293] lr: 5.000000e-05 eta: 6:05:33 time: 1.653138 data_time: 0.145585 memory: 9974 loss_kpt: 0.001575 loss: 0.001575 2022/09/16 03:05:40 - mmengine - INFO - Epoch(train) [173][100/293] lr: 5.000000e-05 eta: 6:03:55 time: 2.071379 data_time: 0.099478 memory: 9974 loss_kpt: 0.001572 loss: 0.001572 2022/09/16 03:07:30 - mmengine - INFO - Epoch(train) [173][150/293] lr: 5.000000e-05 eta: 6:02:18 time: 2.203884 data_time: 0.103871 memory: 9974 loss_kpt: 0.001538 loss: 0.001538 2022/09/16 03:08:45 - mmengine - INFO - Epoch(train) [173][200/293] lr: 5.000000e-05 eta: 6:00:34 time: 1.494272 data_time: 0.094612 memory: 9974 loss_kpt: 0.001572 loss: 0.001572 2022/09/16 03:10:05 - mmengine - INFO - Epoch(train) [173][250/293] lr: 5.000000e-05 eta: 5:58:51 time: 1.600299 data_time: 0.154245 memory: 9974 loss_kpt: 0.001553 loss: 0.001553 2022/09/16 03:11:38 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 03:11:38 - mmengine - INFO - Saving checkpoint at 173 epochs 2022/09/16 03:13:05 - mmengine - INFO - Epoch(train) [174][50/293] lr: 5.000000e-05 eta: 5:55:26 time: 1.667909 data_time: 0.142951 memory: 9974 loss_kpt: 0.001538 loss: 0.001538 2022/09/16 03:14:28 - mmengine - INFO - Epoch(train) [174][100/293] lr: 5.000000e-05 eta: 5:53:44 time: 1.658295 data_time: 0.190697 memory: 9974 loss_kpt: 0.001542 loss: 0.001542 2022/09/16 03:15:51 - mmengine - INFO - Epoch(train) [174][150/293] lr: 5.000000e-05 eta: 5:52:01 time: 1.661231 data_time: 0.372515 memory: 9974 loss_kpt: 0.001541 loss: 0.001541 2022/09/16 03:17:10 - mmengine - INFO - Epoch(train) [174][200/293] lr: 5.000000e-05 eta: 5:50:19 time: 1.591667 data_time: 0.611148 memory: 9974 loss_kpt: 0.001565 loss: 0.001565 2022/09/16 03:18:26 - mmengine - INFO - Epoch(train) [174][250/293] lr: 5.000000e-05 eta: 5:48:35 time: 1.503749 data_time: 0.167713 memory: 9974 loss_kpt: 0.001540 loss: 0.001540 2022/09/16 03:19:28 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 03:19:28 - mmengine - INFO - Saving checkpoint at 174 epochs 2022/09/16 03:20:03 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 03:20:59 - mmengine - INFO - Epoch(train) [175][50/293] lr: 5.000000e-05 eta: 5:45:12 time: 1.753095 data_time: 0.984202 memory: 9974 loss_kpt: 0.001535 loss: 0.001535 2022/09/16 03:22:20 - mmengine - INFO - Epoch(train) [175][100/293] lr: 5.000000e-05 eta: 5:43:29 time: 1.611686 data_time: 1.089767 memory: 9974 loss_kpt: 0.001573 loss: 0.001573 2022/09/16 03:23:23 - mmengine - INFO - Epoch(train) [175][150/293] lr: 5.000000e-05 eta: 5:41:44 time: 1.274759 data_time: 0.211610 memory: 9974 loss_kpt: 0.001533 loss: 0.001533 2022/09/16 03:24:30 - mmengine - INFO - Epoch(train) [175][200/293] lr: 5.000000e-05 eta: 5:39:58 time: 1.327699 data_time: 0.129125 memory: 9974 loss_kpt: 0.001540 loss: 0.001540 2022/09/16 03:26:42 - mmengine - INFO - Epoch(train) [175][250/293] lr: 5.000000e-05 eta: 5:38:27 time: 2.652898 data_time: 0.146660 memory: 9974 loss_kpt: 0.001570 loss: 0.001570 2022/09/16 03:28:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 03:28:06 - mmengine - INFO - Saving checkpoint at 175 epochs 2022/09/16 03:29:42 - mmengine - INFO - Epoch(train) [176][50/293] lr: 5.000000e-05 eta: 5:35:05 time: 1.859094 data_time: 0.290249 memory: 9974 loss_kpt: 0.001553 loss: 0.001553 2022/09/16 03:31:09 - mmengine - INFO - Epoch(train) [176][100/293] lr: 5.000000e-05 eta: 5:33:25 time: 1.743473 data_time: 0.095508 memory: 9974 loss_kpt: 0.001540 loss: 0.001540 2022/09/16 03:32:26 - mmengine - INFO - Epoch(train) [176][150/293] lr: 5.000000e-05 eta: 5:31:42 time: 1.536752 data_time: 0.552107 memory: 9974 loss_kpt: 0.001546 loss: 0.001546 2022/09/16 03:33:24 - mmengine - INFO - Epoch(train) [176][200/293] lr: 5.000000e-05 eta: 5:29:55 time: 1.154690 data_time: 0.142492 memory: 9974 loss_kpt: 0.001541 loss: 0.001541 2022/09/16 03:34:27 - mmengine - INFO - Epoch(train) [176][250/293] lr: 5.000000e-05 eta: 5:28:10 time: 1.256695 data_time: 0.091378 memory: 9974 loss_kpt: 0.001521 loss: 0.001521 2022/09/16 03:35:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 03:35:08 - mmengine - INFO - Saving checkpoint at 176 epochs 2022/09/16 03:36:11 - mmengine - INFO - Epoch(train) [177][50/293] lr: 5.000000e-05 eta: 5:24:43 time: 1.186693 data_time: 0.214499 memory: 9974 loss_kpt: 0.001547 loss: 0.001547 2022/09/16 03:37:51 - mmengine - INFO - Epoch(train) [177][100/293] lr: 5.000000e-05 eta: 5:23:05 time: 2.007302 data_time: 0.143443 memory: 9974 loss_kpt: 0.001547 loss: 0.001547 2022/09/16 03:40:14 - mmengine - INFO - Epoch(train) [177][150/293] lr: 5.000000e-05 eta: 5:21:36 time: 2.864000 data_time: 1.710251 memory: 9974 loss_kpt: 0.001554 loss: 0.001554 2022/09/16 03:41:56 - mmengine - INFO - Epoch(train) [177][200/293] lr: 5.000000e-05 eta: 5:19:58 time: 2.042156 data_time: 1.182674 memory: 9974 loss_kpt: 0.001543 loss: 0.001543 2022/09/16 03:43:55 - mmengine - INFO - Epoch(train) [177][250/293] lr: 5.000000e-05 eta: 5:18:23 time: 2.368339 data_time: 1.618122 memory: 9974 loss_kpt: 0.001539 loss: 0.001539 2022/09/16 03:45:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 03:45:32 - mmengine - INFO - Saving checkpoint at 177 epochs 2022/09/16 03:47:17 - mmengine - INFO - Epoch(train) [178][50/293] lr: 5.000000e-05 eta: 5:15:05 time: 2.020555 data_time: 0.799802 memory: 9974 loss_kpt: 0.001523 loss: 0.001523 2022/09/16 03:48:55 - mmengine - INFO - Epoch(train) [178][100/293] lr: 5.000000e-05 eta: 5:13:27 time: 1.963034 data_time: 1.383495 memory: 9974 loss_kpt: 0.001566 loss: 0.001566 2022/09/16 03:50:01 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 03:50:16 - mmengine - INFO - Epoch(train) [178][150/293] lr: 5.000000e-05 eta: 5:11:46 time: 1.615324 data_time: 0.457200 memory: 9974 loss_kpt: 0.001535 loss: 0.001535 2022/09/16 03:51:43 - mmengine - INFO - Epoch(train) [178][200/293] lr: 5.000000e-05 eta: 5:10:05 time: 1.745048 data_time: 0.961174 memory: 9974 loss_kpt: 0.001522 loss: 0.001522 2022/09/16 03:53:44 - mmengine - INFO - Epoch(train) [178][250/293] lr: 5.000000e-05 eta: 5:08:31 time: 2.415830 data_time: 1.645967 memory: 9974 loss_kpt: 0.001559 loss: 0.001559 2022/09/16 03:55:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 03:55:00 - mmengine - INFO - Saving checkpoint at 178 epochs 2022/09/16 03:56:12 - mmengine - INFO - Epoch(train) [179][50/293] lr: 5.000000e-05 eta: 5:05:08 time: 1.371479 data_time: 0.174590 memory: 9974 loss_kpt: 0.001521 loss: 0.001521 2022/09/16 03:57:55 - mmengine - INFO - Epoch(train) [179][100/293] lr: 5.000000e-05 eta: 5:03:31 time: 2.065451 data_time: 0.863493 memory: 9974 loss_kpt: 0.001546 loss: 0.001546 2022/09/16 03:59:35 - mmengine - INFO - Epoch(train) [179][150/293] lr: 5.000000e-05 eta: 5:01:53 time: 2.008759 data_time: 0.119476 memory: 9974 loss_kpt: 0.001542 loss: 0.001542 2022/09/16 04:00:58 - mmengine - INFO - Epoch(train) [179][200/293] lr: 5.000000e-05 eta: 5:00:12 time: 1.655958 data_time: 0.837014 memory: 9974 loss_kpt: 0.001544 loss: 0.001544 2022/09/16 04:02:14 - mmengine - INFO - Epoch(train) [179][250/293] lr: 5.000000e-05 eta: 4:58:30 time: 1.508774 data_time: 0.164183 memory: 9974 loss_kpt: 0.001527 loss: 0.001527 2022/09/16 04:03:17 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 04:03:17 - mmengine - INFO - Saving checkpoint at 179 epochs 2022/09/16 04:04:34 - mmengine - INFO - Epoch(train) [180][50/293] lr: 5.000000e-05 eta: 4:55:09 time: 1.468219 data_time: 0.665982 memory: 9974 loss_kpt: 0.001546 loss: 0.001546 2022/09/16 04:06:05 - mmengine - INFO - Epoch(train) [180][100/293] lr: 5.000000e-05 eta: 4:53:30 time: 1.831703 data_time: 0.076606 memory: 9974 loss_kpt: 0.001536 loss: 0.001536 2022/09/16 04:07:24 - mmengine - INFO - Epoch(train) [180][150/293] lr: 5.000000e-05 eta: 4:51:48 time: 1.575259 data_time: 0.200140 memory: 9974 loss_kpt: 0.001521 loss: 0.001521 2022/09/16 04:08:33 - mmengine - INFO - Epoch(train) [180][200/293] lr: 5.000000e-05 eta: 4:50:05 time: 1.373044 data_time: 0.337990 memory: 9974 loss_kpt: 0.001515 loss: 0.001515 2022/09/16 04:09:55 - mmengine - INFO - Epoch(train) [180][250/293] lr: 5.000000e-05 eta: 4:48:25 time: 1.651462 data_time: 0.379569 memory: 9974 loss_kpt: 0.001525 loss: 0.001525 2022/09/16 04:11:22 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 04:11:22 - mmengine - INFO - Saving checkpoint at 180 epochs 2022/09/16 04:12:23 - mmengine - INFO - Epoch(val) [180][50/407] eta: 0:06:53 time: 1.158280 data_time: 1.004853 memory: 9974 2022/09/16 04:13:21 - mmengine - INFO - Epoch(val) [180][100/407] eta: 0:05:57 time: 1.164402 data_time: 1.016343 memory: 918 2022/09/16 04:14:01 - mmengine - INFO - Epoch(val) [180][150/407] eta: 0:03:23 time: 0.791745 data_time: 0.643780 memory: 918 2022/09/16 04:14:42 - mmengine - INFO - Epoch(val) [180][200/407] eta: 0:02:48 time: 0.812605 data_time: 0.665377 memory: 918 2022/09/16 04:15:09 - mmengine - INFO - Epoch(val) [180][250/407] eta: 0:01:24 time: 0.539915 data_time: 0.386521 memory: 918 2022/09/16 04:15:36 - mmengine - INFO - Epoch(val) [180][300/407] eta: 0:00:58 time: 0.543364 data_time: 0.387281 memory: 918 2022/09/16 04:16:03 - mmengine - INFO - Epoch(val) [180][350/407] eta: 0:00:31 time: 0.549165 data_time: 0.399503 memory: 918 2022/09/16 04:16:57 - mmengine - INFO - Epoch(val) [180][400/407] eta: 0:00:07 time: 1.066928 data_time: 0.923531 memory: 918 2022/09/16 04:17:35 - mmengine - INFO - Evaluating CocoMetric... 2022/09/16 04:17:49 - mmengine - INFO - Epoch(val) [180][407/407] coco/AP: 0.755121 coco/AP .5: 0.906683 coco/AP .75: 0.821310 coco/AP (M): 0.716827 coco/AP (L): 0.824286 coco/AR: 0.810721 coco/AR .5: 0.942065 coco/AR .75: 0.869647 coco/AR (M): 0.767495 coco/AR (L): 0.873504 2022/09/16 04:17:49 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/udp_regress/best_coco/AP_epoch_140.pth is removed 2022/09/16 04:17:51 - mmengine - INFO - The best checkpoint with 0.7551 coco/AP at 180 epoch is saved to best_coco/AP_epoch_180.pth. 2022/09/16 04:19:46 - mmengine - INFO - Epoch(train) [181][50/293] lr: 5.000000e-05 eta: 4:45:11 time: 2.280757 data_time: 0.435011 memory: 9974 loss_kpt: 0.001536 loss: 0.001536 2022/09/16 04:21:21 - mmengine - INFO - Epoch(train) [181][100/293] lr: 5.000000e-05 eta: 4:43:33 time: 1.913957 data_time: 0.416018 memory: 9974 loss_kpt: 0.001528 loss: 0.001528 2022/09/16 04:22:45 - mmengine - INFO - Epoch(train) [181][150/293] lr: 5.000000e-05 eta: 4:41:53 time: 1.667046 data_time: 0.088924 memory: 9974 loss_kpt: 0.001558 loss: 0.001558 2022/09/16 04:24:11 - mmengine - INFO - Epoch(train) [181][200/293] lr: 5.000000e-05 eta: 4:40:13 time: 1.731718 data_time: 0.114330 memory: 9974 loss_kpt: 0.001508 loss: 0.001508 2022/09/16 04:25:34 - mmengine - INFO - Epoch(train) [181][250/293] lr: 5.000000e-05 eta: 4:38:33 time: 1.664307 data_time: 0.572680 memory: 9974 loss_kpt: 0.001525 loss: 0.001525 2022/09/16 04:25:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 04:26:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 04:26:35 - mmengine - INFO - Saving checkpoint at 181 epochs 2022/09/16 04:28:04 - mmengine - INFO - Epoch(train) [182][50/293] lr: 5.000000e-05 eta: 4:35:15 time: 1.715761 data_time: 0.180155 memory: 9974 loss_kpt: 0.001533 loss: 0.001533 2022/09/16 04:29:30 - mmengine - INFO - Epoch(train) [182][100/293] lr: 5.000000e-05 eta: 4:33:36 time: 1.719742 data_time: 0.655245 memory: 9974 loss_kpt: 0.001545 loss: 0.001545 2022/09/16 04:30:43 - mmengine - INFO - Epoch(train) [182][150/293] lr: 5.000000e-05 eta: 4:31:54 time: 1.458471 data_time: 0.213518 memory: 9974 loss_kpt: 0.001516 loss: 0.001516 2022/09/16 04:32:22 - mmengine - INFO - Epoch(train) [182][200/293] lr: 5.000000e-05 eta: 4:30:17 time: 1.979555 data_time: 0.251352 memory: 9974 loss_kpt: 0.001538 loss: 0.001538 2022/09/16 04:34:04 - mmengine - INFO - Epoch(train) [182][250/293] lr: 5.000000e-05 eta: 4:28:40 time: 2.039956 data_time: 0.122598 memory: 9974 loss_kpt: 0.001531 loss: 0.001531 2022/09/16 04:35:14 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 04:35:14 - mmengine - INFO - Saving checkpoint at 182 epochs 2022/09/16 04:36:31 - mmengine - INFO - Epoch(train) [183][50/293] lr: 5.000000e-05 eta: 4:25:21 time: 1.489089 data_time: 0.170232 memory: 9974 loss_kpt: 0.001547 loss: 0.001547 2022/09/16 04:37:58 - mmengine - INFO - Epoch(train) [183][100/293] lr: 5.000000e-05 eta: 4:23:42 time: 1.739738 data_time: 0.179746 memory: 9974 loss_kpt: 0.001526 loss: 0.001526 2022/09/16 04:39:29 - mmengine - INFO - Epoch(train) [183][150/293] lr: 5.000000e-05 eta: 4:22:03 time: 1.809581 data_time: 0.087580 memory: 9974 loss_kpt: 0.001540 loss: 0.001540 2022/09/16 04:40:59 - mmengine - INFO - Epoch(train) [183][200/293] lr: 5.000000e-05 eta: 4:20:25 time: 1.809047 data_time: 0.211867 memory: 9974 loss_kpt: 0.001529 loss: 0.001529 2022/09/16 04:42:52 - mmengine - INFO - Epoch(train) [183][250/293] lr: 5.000000e-05 eta: 4:18:49 time: 2.257160 data_time: 0.122530 memory: 9974 loss_kpt: 0.001563 loss: 0.001563 2022/09/16 04:44:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 04:44:00 - mmengine - INFO - Saving checkpoint at 183 epochs 2022/09/16 04:45:14 - mmengine - INFO - Epoch(train) [184][50/293] lr: 5.000000e-05 eta: 4:15:32 time: 1.407837 data_time: 0.151434 memory: 9974 loss_kpt: 0.001536 loss: 0.001536 2022/09/16 04:46:57 - mmengine - INFO - Epoch(train) [184][100/293] lr: 5.000000e-05 eta: 4:13:55 time: 2.066538 data_time: 0.087945 memory: 9974 loss_kpt: 0.001521 loss: 0.001521 2022/09/16 04:48:26 - mmengine - INFO - Epoch(train) [184][150/293] lr: 5.000000e-05 eta: 4:12:16 time: 1.767505 data_time: 0.126297 memory: 9974 loss_kpt: 0.001534 loss: 0.001534 2022/09/16 04:49:40 - mmengine - INFO - Epoch(train) [184][200/293] lr: 5.000000e-05 eta: 4:10:35 time: 1.493510 data_time: 0.096043 memory: 9974 loss_kpt: 0.001557 loss: 0.001557 2022/09/16 04:50:51 - mmengine - INFO - Epoch(train) [184][250/293] lr: 5.000000e-05 eta: 4:08:54 time: 1.417454 data_time: 0.309944 memory: 9974 loss_kpt: 0.001527 loss: 0.001527 2022/09/16 04:51:52 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 04:51:52 - mmengine - INFO - Saving checkpoint at 184 epochs 2022/09/16 04:53:25 - mmengine - INFO - Epoch(train) [185][50/293] lr: 5.000000e-05 eta: 4:05:40 time: 1.791458 data_time: 0.481399 memory: 9974 loss_kpt: 0.001516 loss: 0.001516 2022/09/16 04:54:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 04:54:55 - mmengine - INFO - Epoch(train) [185][100/293] lr: 5.000000e-05 eta: 4:04:01 time: 1.796766 data_time: 0.091542 memory: 9974 loss_kpt: 0.001488 loss: 0.001488 2022/09/16 04:56:42 - mmengine - INFO - Epoch(train) [185][150/293] lr: 5.000000e-05 eta: 4:02:25 time: 2.140761 data_time: 0.096781 memory: 9974 loss_kpt: 0.001516 loss: 0.001516 2022/09/16 04:58:04 - mmengine - INFO - Epoch(train) [185][200/293] lr: 5.000000e-05 eta: 4:00:46 time: 1.625235 data_time: 0.147552 memory: 9974 loss_kpt: 0.001517 loss: 0.001517 2022/09/16 04:59:55 - mmengine - INFO - Epoch(train) [185][250/293] lr: 5.000000e-05 eta: 3:59:10 time: 2.226896 data_time: 0.090928 memory: 9974 loss_kpt: 0.001530 loss: 0.001530 2022/09/16 05:01:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 05:01:44 - mmengine - INFO - Saving checkpoint at 185 epochs 2022/09/16 05:03:14 - mmengine - INFO - Epoch(train) [186][50/293] lr: 5.000000e-05 eta: 3:55:56 time: 1.731631 data_time: 0.171207 memory: 9974 loss_kpt: 0.001520 loss: 0.001520 2022/09/16 05:04:40 - mmengine - INFO - Epoch(train) [186][100/293] lr: 5.000000e-05 eta: 3:54:18 time: 1.717227 data_time: 0.361520 memory: 9974 loss_kpt: 0.001525 loss: 0.001525 2022/09/16 05:06:00 - mmengine - INFO - Epoch(train) [186][150/293] lr: 5.000000e-05 eta: 3:52:38 time: 1.604564 data_time: 0.094440 memory: 9974 loss_kpt: 0.001538 loss: 0.001538 2022/09/16 05:07:07 - mmengine - INFO - Epoch(train) [186][200/293] lr: 5.000000e-05 eta: 3:50:57 time: 1.337536 data_time: 0.096753 memory: 9974 loss_kpt: 0.001532 loss: 0.001532 2022/09/16 05:08:31 - mmengine - INFO - Epoch(train) [186][250/293] lr: 5.000000e-05 eta: 3:49:18 time: 1.671819 data_time: 0.080887 memory: 9974 loss_kpt: 0.001532 loss: 0.001532 2022/09/16 05:09:48 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 05:09:48 - mmengine - INFO - Saving checkpoint at 186 epochs 2022/09/16 05:11:20 - mmengine - INFO - Epoch(train) [187][50/293] lr: 5.000000e-05 eta: 3:46:05 time: 1.761892 data_time: 0.346740 memory: 9974 loss_kpt: 0.001540 loss: 0.001540 2022/09/16 05:12:43 - mmengine - INFO - Epoch(train) [187][100/293] lr: 5.000000e-05 eta: 3:44:26 time: 1.659447 data_time: 0.132206 memory: 9974 loss_kpt: 0.001530 loss: 0.001530 2022/09/16 05:13:54 - mmengine - INFO - Epoch(train) [187][150/293] lr: 5.000000e-05 eta: 3:42:46 time: 1.418243 data_time: 0.483134 memory: 9974 loss_kpt: 0.001537 loss: 0.001537 2022/09/16 05:15:42 - mmengine - INFO - Epoch(train) [187][200/293] lr: 5.000000e-05 eta: 3:41:10 time: 2.171430 data_time: 0.139458 memory: 9974 loss_kpt: 0.001524 loss: 0.001524 2022/09/16 05:17:00 - mmengine - INFO - Epoch(train) [187][250/293] lr: 5.000000e-05 eta: 3:39:30 time: 1.541858 data_time: 0.090213 memory: 9974 loss_kpt: 0.001534 loss: 0.001534 2022/09/16 05:18:31 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 05:18:31 - mmengine - INFO - Saving checkpoint at 187 epochs 2022/09/16 05:20:21 - mmengine - INFO - Epoch(train) [188][50/293] lr: 5.000000e-05 eta: 3:36:21 time: 2.121452 data_time: 0.732820 memory: 9974 loss_kpt: 0.001514 loss: 0.001514 2022/09/16 05:22:37 - mmengine - INFO - Epoch(train) [188][100/293] lr: 5.000000e-05 eta: 3:34:49 time: 2.734428 data_time: 0.094755 memory: 9974 loss_kpt: 0.001535 loss: 0.001535 2022/09/16 05:24:03 - mmengine - INFO - Epoch(train) [188][150/293] lr: 5.000000e-05 eta: 3:33:10 time: 1.711977 data_time: 0.432327 memory: 9974 loss_kpt: 0.001527 loss: 0.001527 2022/09/16 05:25:36 - mmengine - INFO - Epoch(train) [188][200/293] lr: 5.000000e-05 eta: 3:31:33 time: 1.867008 data_time: 0.100900 memory: 9974 loss_kpt: 0.001542 loss: 0.001542 2022/09/16 05:25:53 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 05:27:19 - mmengine - INFO - Epoch(train) [188][250/293] lr: 5.000000e-05 eta: 3:29:56 time: 2.045936 data_time: 0.119091 memory: 9974 loss_kpt: 0.001534 loss: 0.001534 2022/09/16 05:28:31 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 05:28:31 - mmengine - INFO - Saving checkpoint at 188 epochs 2022/09/16 05:30:12 - mmengine - INFO - Epoch(train) [189][50/293] lr: 5.000000e-05 eta: 3:26:46 time: 1.946869 data_time: 0.227382 memory: 9974 loss_kpt: 0.001541 loss: 0.001541 2022/09/16 05:31:41 - mmengine - INFO - Epoch(train) [189][100/293] lr: 5.000000e-05 eta: 3:25:08 time: 1.782330 data_time: 0.140977 memory: 9974 loss_kpt: 0.001554 loss: 0.001554 2022/09/16 05:32:56 - mmengine - INFO - Epoch(train) [189][150/293] lr: 5.000000e-05 eta: 3:23:29 time: 1.505583 data_time: 0.178620 memory: 9974 loss_kpt: 0.001515 loss: 0.001515 2022/09/16 05:34:18 - mmengine - INFO - Epoch(train) [189][200/293] lr: 5.000000e-05 eta: 3:21:50 time: 1.647398 data_time: 0.507027 memory: 9974 loss_kpt: 0.001546 loss: 0.001546 2022/09/16 05:35:15 - mmengine - INFO - Epoch(train) [189][250/293] lr: 5.000000e-05 eta: 3:20:09 time: 1.135079 data_time: 0.638092 memory: 9974 loss_kpt: 0.001520 loss: 0.001520 2022/09/16 05:36:14 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 05:36:14 - mmengine - INFO - Saving checkpoint at 189 epochs 2022/09/16 05:37:24 - mmengine - INFO - Epoch(train) [190][50/293] lr: 5.000000e-05 eta: 3:16:56 time: 1.336902 data_time: 0.153375 memory: 9974 loss_kpt: 0.001532 loss: 0.001532 2022/09/16 05:38:42 - mmengine - INFO - Epoch(train) [190][100/293] lr: 5.000000e-05 eta: 3:15:17 time: 1.561645 data_time: 0.267410 memory: 9974 loss_kpt: 0.001536 loss: 0.001536 2022/09/16 05:40:03 - mmengine - INFO - Epoch(train) [190][150/293] lr: 5.000000e-05 eta: 3:13:38 time: 1.624789 data_time: 0.240269 memory: 9974 loss_kpt: 0.001532 loss: 0.001532 2022/09/16 05:41:36 - mmengine - INFO - Epoch(train) [190][200/293] lr: 5.000000e-05 eta: 3:12:01 time: 1.859128 data_time: 0.096617 memory: 9974 loss_kpt: 0.001510 loss: 0.001510 2022/09/16 05:43:33 - mmengine - INFO - Epoch(train) [190][250/293] lr: 5.000000e-05 eta: 3:10:27 time: 2.332105 data_time: 0.131944 memory: 9974 loss_kpt: 0.001537 loss: 0.001537 2022/09/16 05:44:57 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 05:44:57 - mmengine - INFO - Saving checkpoint at 190 epochs 2022/09/16 05:45:47 - mmengine - INFO - Epoch(val) [190][50/407] eta: 0:05:29 time: 0.923367 data_time: 0.776004 memory: 9974 2022/09/16 05:46:27 - mmengine - INFO - Epoch(val) [190][100/407] eta: 0:04:05 time: 0.798133 data_time: 0.642468 memory: 918 2022/09/16 05:47:14 - mmengine - INFO - Epoch(val) [190][150/407] eta: 0:04:01 time: 0.940982 data_time: 0.795530 memory: 918 2022/09/16 05:47:42 - mmengine - INFO - Epoch(val) [190][200/407] eta: 0:01:56 time: 0.560447 data_time: 0.415838 memory: 918 2022/09/16 05:48:07 - mmengine - INFO - Epoch(val) [190][250/407] eta: 0:01:20 time: 0.512221 data_time: 0.368260 memory: 918 2022/09/16 05:48:50 - mmengine - INFO - Epoch(val) [190][300/407] eta: 0:01:31 time: 0.855860 data_time: 0.708378 memory: 918 2022/09/16 05:49:20 - mmengine - INFO - Epoch(val) [190][350/407] eta: 0:00:34 time: 0.608136 data_time: 0.460195 memory: 918 2022/09/16 05:50:00 - mmengine - INFO - Epoch(val) [190][400/407] eta: 0:00:05 time: 0.782065 data_time: 0.631294 memory: 918 2022/09/16 05:52:54 - mmengine - INFO - Evaluating CocoMetric... 2022/09/16 05:53:08 - mmengine - INFO - Epoch(val) [190][407/407] coco/AP: 0.756481 coco/AP .5: 0.907578 coco/AP .75: 0.823215 coco/AP (M): 0.717835 coco/AP (L): 0.825012 coco/AR: 0.810611 coco/AR .5: 0.942853 coco/AR .75: 0.869332 coco/AR (M): 0.767331 coco/AR (L): 0.873802 2022/09/16 05:53:08 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/udp_regress/best_coco/AP_epoch_180.pth is removed 2022/09/16 05:53:11 - mmengine - INFO - The best checkpoint with 0.7565 coco/AP at 190 epoch is saved to best_coco/AP_epoch_190.pth. 2022/09/16 05:54:56 - mmengine - INFO - Epoch(train) [191][50/293] lr: 5.000000e-05 eta: 3:07:19 time: 2.106290 data_time: 0.268498 memory: 9974 loss_kpt: 0.001537 loss: 0.001537 2022/09/16 05:56:25 - mmengine - INFO - Epoch(train) [191][100/293] lr: 5.000000e-05 eta: 3:05:41 time: 1.780607 data_time: 0.245981 memory: 9974 loss_kpt: 0.001524 loss: 0.001524 2022/09/16 05:57:59 - mmengine - INFO - Epoch(train) [191][150/293] lr: 5.000000e-05 eta: 3:04:04 time: 1.882917 data_time: 0.117673 memory: 9974 loss_kpt: 0.001545 loss: 0.001545 2022/09/16 05:59:36 - mmengine - INFO - Epoch(train) [191][200/293] lr: 5.000000e-05 eta: 3:02:28 time: 1.944149 data_time: 0.191491 memory: 9974 loss_kpt: 0.001509 loss: 0.001509 2022/09/16 06:01:07 - mmengine - INFO - Epoch(train) [191][250/293] lr: 5.000000e-05 eta: 3:00:50 time: 1.812858 data_time: 0.161148 memory: 9974 loss_kpt: 0.001498 loss: 0.001498 2022/09/16 06:02:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 06:02:46 - mmengine - INFO - Saving checkpoint at 191 epochs 2022/09/16 06:04:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 06:04:25 - mmengine - INFO - Epoch(train) [192][50/293] lr: 5.000000e-05 eta: 2:57:42 time: 1.921591 data_time: 0.198143 memory: 9974 loss_kpt: 0.001530 loss: 0.001530 2022/09/16 06:05:45 - mmengine - INFO - Epoch(train) [192][100/293] lr: 5.000000e-05 eta: 2:56:04 time: 1.603708 data_time: 0.121843 memory: 9974 loss_kpt: 0.001501 loss: 0.001501 2022/09/16 06:07:09 - mmengine - INFO - Epoch(train) [192][150/293] lr: 5.000000e-05 eta: 2:54:26 time: 1.670517 data_time: 0.088296 memory: 9974 loss_kpt: 0.001525 loss: 0.001525 2022/09/16 06:08:33 - mmengine - INFO - Epoch(train) [192][200/293] lr: 5.000000e-05 eta: 2:52:48 time: 1.679579 data_time: 0.597549 memory: 9974 loss_kpt: 0.001537 loss: 0.001537 2022/09/16 06:10:21 - mmengine - INFO - Epoch(train) [192][250/293] lr: 5.000000e-05 eta: 2:51:13 time: 2.165785 data_time: 0.117291 memory: 9974 loss_kpt: 0.001507 loss: 0.001507 2022/09/16 06:11:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 06:11:27 - mmengine - INFO - Saving checkpoint at 192 epochs 2022/09/16 06:12:55 - mmengine - INFO - Epoch(train) [193][50/293] lr: 5.000000e-05 eta: 2:48:04 time: 1.692293 data_time: 0.146786 memory: 9974 loss_kpt: 0.001519 loss: 0.001519 2022/09/16 06:14:13 - mmengine - INFO - Epoch(train) [193][100/293] lr: 5.000000e-05 eta: 2:46:26 time: 1.571473 data_time: 0.126985 memory: 9974 loss_kpt: 0.001547 loss: 0.001547 2022/09/16 06:15:06 - mmengine - INFO - Epoch(train) [193][150/293] lr: 5.000000e-05 eta: 2:44:46 time: 1.042190 data_time: 0.081333 memory: 9974 loss_kpt: 0.001519 loss: 0.001519 2022/09/16 06:16:01 - mmengine - INFO - Epoch(train) [193][200/293] lr: 5.000000e-05 eta: 2:43:05 time: 1.112316 data_time: 0.174039 memory: 9974 loss_kpt: 0.001532 loss: 0.001532 2022/09/16 06:17:09 - mmengine - INFO - Epoch(train) [193][250/293] lr: 5.000000e-05 eta: 2:41:26 time: 1.348254 data_time: 0.104476 memory: 9974 loss_kpt: 0.001521 loss: 0.001521 2022/09/16 06:18:24 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 06:18:24 - mmengine - INFO - Saving checkpoint at 193 epochs 2022/09/16 06:19:50 - mmengine - INFO - Epoch(train) [194][50/293] lr: 5.000000e-05 eta: 2:38:19 time: 1.655949 data_time: 0.599740 memory: 9974 loss_kpt: 0.001536 loss: 0.001536 2022/09/16 06:21:10 - mmengine - INFO - Epoch(train) [194][100/293] lr: 5.000000e-05 eta: 2:36:41 time: 1.592186 data_time: 0.096873 memory: 9974 loss_kpt: 0.001530 loss: 0.001530 2022/09/16 06:22:32 - mmengine - INFO - Epoch(train) [194][150/293] lr: 5.000000e-05 eta: 2:35:03 time: 1.646272 data_time: 0.157809 memory: 9974 loss_kpt: 0.001492 loss: 0.001492 2022/09/16 06:23:48 - mmengine - INFO - Epoch(train) [194][200/293] lr: 5.000000e-05 eta: 2:33:25 time: 1.522965 data_time: 0.169049 memory: 9974 loss_kpt: 0.001520 loss: 0.001520 2022/09/16 06:25:13 - mmengine - INFO - Epoch(train) [194][250/293] lr: 5.000000e-05 eta: 2:31:48 time: 1.681245 data_time: 0.094248 memory: 9974 loss_kpt: 0.001528 loss: 0.001528 2022/09/16 06:26:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 06:26:19 - mmengine - INFO - Saving checkpoint at 194 epochs 2022/09/16 06:27:15 - mmengine - INFO - Epoch(train) [195][50/293] lr: 5.000000e-05 eta: 2:28:39 time: 1.057249 data_time: 0.197700 memory: 9974 loss_kpt: 0.001543 loss: 0.001543 2022/09/16 06:28:48 - mmengine - INFO - Epoch(train) [195][100/293] lr: 5.000000e-05 eta: 2:27:02 time: 1.848960 data_time: 0.106099 memory: 9974 loss_kpt: 0.001526 loss: 0.001526 2022/09/16 06:29:55 - mmengine - INFO - Epoch(train) [195][150/293] lr: 5.000000e-05 eta: 2:25:24 time: 1.355796 data_time: 0.345466 memory: 9974 loss_kpt: 0.001537 loss: 0.001537 2022/09/16 06:30:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 06:31:17 - mmengine - INFO - Epoch(train) [195][200/293] lr: 5.000000e-05 eta: 2:23:47 time: 1.626157 data_time: 0.080478 memory: 9974 loss_kpt: 0.001507 loss: 0.001507 2022/09/16 06:32:26 - mmengine - INFO - Epoch(train) [195][250/293] lr: 5.000000e-05 eta: 2:22:08 time: 1.379039 data_time: 0.246986 memory: 9974 loss_kpt: 0.001531 loss: 0.001531 2022/09/16 06:33:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 06:33:33 - mmengine - INFO - Saving checkpoint at 195 epochs 2022/09/16 06:34:59 - mmengine - INFO - Epoch(train) [196][50/293] lr: 5.000000e-05 eta: 2:19:02 time: 1.639722 data_time: 0.196759 memory: 9974 loss_kpt: 0.001538 loss: 0.001538 2022/09/16 06:36:08 - mmengine - INFO - Epoch(train) [196][100/293] lr: 5.000000e-05 eta: 2:17:24 time: 1.391972 data_time: 0.116869 memory: 9974 loss_kpt: 0.001500 loss: 0.001500 2022/09/16 06:37:42 - mmengine - INFO - Epoch(train) [196][150/293] lr: 5.000000e-05 eta: 2:15:48 time: 1.867503 data_time: 0.620695 memory: 9974 loss_kpt: 0.001549 loss: 0.001549 2022/09/16 06:39:15 - mmengine - INFO - Epoch(train) [196][200/293] lr: 5.000000e-05 eta: 2:14:12 time: 1.875485 data_time: 0.940148 memory: 9974 loss_kpt: 0.001488 loss: 0.001488 2022/09/16 06:40:38 - mmengine - INFO - Epoch(train) [196][250/293] lr: 5.000000e-05 eta: 2:12:35 time: 1.656363 data_time: 0.677918 memory: 9974 loss_kpt: 0.001518 loss: 0.001518 2022/09/16 06:41:36 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 06:41:36 - mmengine - INFO - Saving checkpoint at 196 epochs 2022/09/16 06:42:53 - mmengine - INFO - Epoch(train) [197][50/293] lr: 5.000000e-05 eta: 2:09:29 time: 1.467848 data_time: 0.310810 memory: 9974 loss_kpt: 0.001541 loss: 0.001541 2022/09/16 06:44:40 - mmengine - INFO - Epoch(train) [197][100/293] lr: 5.000000e-05 eta: 2:07:54 time: 2.135082 data_time: 0.089645 memory: 9974 loss_kpt: 0.001522 loss: 0.001522 2022/09/16 06:45:38 - mmengine - INFO - Epoch(train) [197][150/293] lr: 5.000000e-05 eta: 2:06:16 time: 1.167375 data_time: 0.244519 memory: 9974 loss_kpt: 0.001503 loss: 0.001503 2022/09/16 06:46:46 - mmengine - INFO - Epoch(train) [197][200/293] lr: 5.000000e-05 eta: 2:04:38 time: 1.356544 data_time: 0.311468 memory: 9974 loss_kpt: 0.001507 loss: 0.001507 2022/09/16 06:48:01 - mmengine - INFO - Epoch(train) [197][250/293] lr: 5.000000e-05 eta: 2:03:01 time: 1.497560 data_time: 0.423729 memory: 9974 loss_kpt: 0.001544 loss: 0.001544 2022/09/16 06:49:12 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 06:49:12 - mmengine - INFO - Saving checkpoint at 197 epochs 2022/09/16 06:50:31 - mmengine - INFO - Epoch(train) [198][50/293] lr: 5.000000e-05 eta: 1:59:56 time: 1.521184 data_time: 0.207204 memory: 9974 loss_kpt: 0.001497 loss: 0.001497 2022/09/16 06:51:44 - mmengine - INFO - Epoch(train) [198][100/293] lr: 5.000000e-05 eta: 1:58:19 time: 1.455497 data_time: 0.394777 memory: 9974 loss_kpt: 0.001516 loss: 0.001516 2022/09/16 06:53:14 - mmengine - INFO - Epoch(train) [198][150/293] lr: 5.000000e-05 eta: 1:56:43 time: 1.802713 data_time: 0.775245 memory: 9974 loss_kpt: 0.001503 loss: 0.001503 2022/09/16 06:54:29 - mmengine - INFO - Epoch(train) [198][200/293] lr: 5.000000e-05 eta: 1:55:06 time: 1.492397 data_time: 0.159847 memory: 9974 loss_kpt: 0.001524 loss: 0.001524 2022/09/16 06:55:37 - mmengine - INFO - Epoch(train) [198][250/293] lr: 5.000000e-05 eta: 1:53:28 time: 1.356408 data_time: 0.083952 memory: 9974 loss_kpt: 0.001511 loss: 0.001511 2022/09/16 06:56:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 06:56:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 06:56:27 - mmengine - INFO - Saving checkpoint at 198 epochs 2022/09/16 06:57:30 - mmengine - INFO - Epoch(train) [199][50/293] lr: 5.000000e-05 eta: 1:50:23 time: 1.187127 data_time: 0.349868 memory: 9974 loss_kpt: 0.001533 loss: 0.001533 2022/09/16 06:58:54 - mmengine - INFO - Epoch(train) [199][100/293] lr: 5.000000e-05 eta: 1:48:47 time: 1.675464 data_time: 0.459120 memory: 9974 loss_kpt: 0.001512 loss: 0.001512 2022/09/16 07:00:28 - mmengine - INFO - Epoch(train) [199][150/293] lr: 5.000000e-05 eta: 1:47:11 time: 1.890667 data_time: 0.197281 memory: 9974 loss_kpt: 0.001515 loss: 0.001515 2022/09/16 07:01:47 - mmengine - INFO - Epoch(train) [199][200/293] lr: 5.000000e-05 eta: 1:45:35 time: 1.562271 data_time: 0.091958 memory: 9974 loss_kpt: 0.001509 loss: 0.001509 2022/09/16 07:03:05 - mmengine - INFO - Epoch(train) [199][250/293] lr: 5.000000e-05 eta: 1:43:58 time: 1.563591 data_time: 0.313860 memory: 9974 loss_kpt: 0.001531 loss: 0.001531 2022/09/16 07:04:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 07:04:11 - mmengine - INFO - Saving checkpoint at 199 epochs 2022/09/16 07:05:45 - mmengine - INFO - Epoch(train) [200][50/293] lr: 5.000000e-05 eta: 1:40:56 time: 1.813619 data_time: 0.429967 memory: 9974 loss_kpt: 0.001526 loss: 0.001526 2022/09/16 07:07:11 - mmengine - INFO - Epoch(train) [200][100/293] lr: 5.000000e-05 eta: 1:39:20 time: 1.718921 data_time: 0.082543 memory: 9974 loss_kpt: 0.001485 loss: 0.001485 2022/09/16 07:08:36 - mmengine - INFO - Epoch(train) [200][150/293] lr: 5.000000e-05 eta: 1:37:44 time: 1.712419 data_time: 0.095072 memory: 9974 loss_kpt: 0.001528 loss: 0.001528 2022/09/16 07:09:59 - mmengine - INFO - Epoch(train) [200][200/293] lr: 5.000000e-05 eta: 1:36:08 time: 1.643104 data_time: 0.097179 memory: 9974 loss_kpt: 0.001496 loss: 0.001496 2022/09/16 07:11:36 - mmengine - INFO - Epoch(train) [200][250/293] lr: 5.000000e-05 eta: 1:34:33 time: 1.944321 data_time: 0.095123 memory: 9974 loss_kpt: 0.001527 loss: 0.001527 2022/09/16 07:13:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 07:13:02 - mmengine - INFO - Saving checkpoint at 200 epochs 2022/09/16 07:13:54 - mmengine - INFO - Epoch(val) [200][50/407] eta: 0:05:50 time: 0.983041 data_time: 0.835923 memory: 9974 2022/09/16 07:14:42 - mmengine - INFO - Epoch(val) [200][100/407] eta: 0:04:56 time: 0.967055 data_time: 0.821520 memory: 918 2022/09/16 07:15:20 - mmengine - INFO - Epoch(val) [200][150/407] eta: 0:03:12 time: 0.748765 data_time: 0.597607 memory: 918 2022/09/16 07:16:12 - mmengine - INFO - Epoch(val) [200][200/407] eta: 0:03:37 time: 1.049794 data_time: 0.890733 memory: 918 2022/09/16 07:16:46 - mmengine - INFO - Epoch(val) [200][250/407] eta: 0:01:47 time: 0.685830 data_time: 0.538024 memory: 918 2022/09/16 07:17:25 - mmengine - INFO - Epoch(val) [200][300/407] eta: 0:01:22 time: 0.768289 data_time: 0.625248 memory: 918 2022/09/16 07:18:11 - mmengine - INFO - Epoch(val) [200][350/407] eta: 0:00:52 time: 0.923297 data_time: 0.775452 memory: 918 2022/09/16 07:19:04 - mmengine - INFO - Epoch(val) [200][400/407] eta: 0:00:07 time: 1.051776 data_time: 0.907620 memory: 918 2022/09/16 07:20:12 - mmengine - INFO - Evaluating CocoMetric... 2022/09/16 07:20:25 - mmengine - INFO - Epoch(val) [200][407/407] coco/AP: 0.756453 coco/AP .5: 0.906009 coco/AP .75: 0.824701 coco/AP (M): 0.716432 coco/AP (L): 0.826238 coco/AR: 0.811130 coco/AR .5: 0.941751 coco/AR .75: 0.870592 coco/AR (M): 0.767331 coco/AR (L): 0.874879 2022/09/16 07:22:23 - mmengine - INFO - Epoch(train) [201][50/293] lr: 5.000000e-06 eta: 1:31:32 time: 2.345928 data_time: 0.698267 memory: 9974 loss_kpt: 0.001519 loss: 0.001519 2022/09/16 07:23:53 - mmengine - INFO - Epoch(train) [201][100/293] lr: 5.000000e-06 eta: 1:29:57 time: 1.802672 data_time: 0.525621 memory: 9974 loss_kpt: 0.001520 loss: 0.001520 2022/09/16 07:25:32 - mmengine - INFO - Epoch(train) [201][150/293] lr: 5.000000e-06 eta: 1:28:21 time: 1.975097 data_time: 0.198973 memory: 9974 loss_kpt: 0.001507 loss: 0.001507 2022/09/16 07:27:01 - mmengine - INFO - Epoch(train) [201][200/293] lr: 5.000000e-06 eta: 1:26:46 time: 1.794644 data_time: 0.091244 memory: 9974 loss_kpt: 0.001517 loss: 0.001517 2022/09/16 07:28:27 - mmengine - INFO - Epoch(train) [201][250/293] lr: 5.000000e-06 eta: 1:25:10 time: 1.703140 data_time: 0.100695 memory: 9974 loss_kpt: 0.001525 loss: 0.001525 2022/09/16 07:29:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 07:29:44 - mmengine - INFO - Saving checkpoint at 201 epochs 2022/09/16 07:31:29 - mmengine - INFO - Epoch(train) [202][50/293] lr: 5.000000e-06 eta: 1:22:09 time: 2.025159 data_time: 0.295264 memory: 9974 loss_kpt: 0.001497 loss: 0.001497 2022/09/16 07:33:04 - mmengine - INFO - Epoch(train) [202][100/293] lr: 5.000000e-06 eta: 1:20:34 time: 1.904376 data_time: 0.160712 memory: 9974 loss_kpt: 0.001529 loss: 0.001529 2022/09/16 07:33:15 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 07:34:29 - mmengine - INFO - Epoch(train) [202][150/293] lr: 5.000000e-06 eta: 1:18:58 time: 1.711224 data_time: 0.438967 memory: 9974 loss_kpt: 0.001526 loss: 0.001526 2022/09/16 07:35:44 - mmengine - INFO - Epoch(train) [202][200/293] lr: 5.000000e-06 eta: 1:17:22 time: 1.492587 data_time: 0.130778 memory: 9974 loss_kpt: 0.001539 loss: 0.001539 2022/09/16 07:36:58 - mmengine - INFO - Epoch(train) [202][250/293] lr: 5.000000e-06 eta: 1:15:46 time: 1.485999 data_time: 0.090036 memory: 9974 loss_kpt: 0.001518 loss: 0.001518 2022/09/16 07:38:15 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 07:38:15 - mmengine - INFO - Saving checkpoint at 202 epochs 2022/09/16 07:40:02 - mmengine - INFO - Epoch(train) [203][50/293] lr: 5.000000e-06 eta: 1:12:46 time: 2.066101 data_time: 0.435984 memory: 9974 loss_kpt: 0.001520 loss: 0.001520 2022/09/16 07:42:00 - mmengine - INFO - Epoch(train) [203][100/293] lr: 5.000000e-06 eta: 1:11:12 time: 2.372930 data_time: 0.119322 memory: 9974 loss_kpt: 0.001486 loss: 0.001486 2022/09/16 07:43:23 - mmengine - INFO - Epoch(train) [203][150/293] lr: 5.000000e-06 eta: 1:09:36 time: 1.660286 data_time: 0.117194 memory: 9974 loss_kpt: 0.001513 loss: 0.001513 2022/09/16 07:44:46 - mmengine - INFO - Epoch(train) [203][200/293] lr: 5.000000e-06 eta: 1:08:00 time: 1.645848 data_time: 0.097894 memory: 9974 loss_kpt: 0.001496 loss: 0.001496 2022/09/16 07:46:14 - mmengine - INFO - Epoch(train) [203][250/293] lr: 5.000000e-06 eta: 1:06:25 time: 1.767697 data_time: 0.092016 memory: 9974 loss_kpt: 0.001506 loss: 0.001506 2022/09/16 07:47:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 07:47:33 - mmengine - INFO - Saving checkpoint at 203 epochs 2022/09/16 07:48:55 - mmengine - INFO - Epoch(train) [204][50/293] lr: 5.000000e-06 eta: 1:03:25 time: 1.583205 data_time: 0.574589 memory: 9974 loss_kpt: 0.001511 loss: 0.001511 2022/09/16 07:50:22 - mmengine - INFO - Epoch(train) [204][100/293] lr: 5.000000e-06 eta: 1:01:49 time: 1.728111 data_time: 0.352040 memory: 9974 loss_kpt: 0.001520 loss: 0.001520 2022/09/16 07:52:02 - mmengine - INFO - Epoch(train) [204][150/293] lr: 5.000000e-06 eta: 1:00:14 time: 2.010997 data_time: 0.093517 memory: 9974 loss_kpt: 0.001524 loss: 0.001524 2022/09/16 07:53:49 - mmengine - INFO - Epoch(train) [204][200/293] lr: 5.000000e-06 eta: 0:58:40 time: 2.136603 data_time: 0.092116 memory: 9974 loss_kpt: 0.001508 loss: 0.001508 2022/09/16 07:55:23 - mmengine - INFO - Epoch(train) [204][250/293] lr: 5.000000e-06 eta: 0:57:05 time: 1.866396 data_time: 0.240505 memory: 9974 loss_kpt: 0.001542 loss: 0.001542 2022/09/16 07:56:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 07:56:33 - mmengine - INFO - Saving checkpoint at 204 epochs 2022/09/16 07:57:56 - mmengine - INFO - Epoch(train) [205][50/293] lr: 5.000000e-06 eta: 0:54:05 time: 1.572210 data_time: 0.204244 memory: 9974 loss_kpt: 0.001509 loss: 0.001509 2022/09/16 07:59:51 - mmengine - INFO - Epoch(train) [205][100/293] lr: 5.000000e-06 eta: 0:52:31 time: 2.311714 data_time: 0.138183 memory: 9974 loss_kpt: 0.001508 loss: 0.001508 2022/09/16 08:01:27 - mmengine - INFO - Epoch(train) [205][150/293] lr: 5.000000e-06 eta: 0:50:56 time: 1.921108 data_time: 0.106291 memory: 9974 loss_kpt: 0.001547 loss: 0.001547 2022/09/16 08:02:56 - mmengine - INFO - Epoch(train) [205][200/293] lr: 5.000000e-06 eta: 0:49:20 time: 1.784505 data_time: 0.098841 memory: 9974 loss_kpt: 0.001512 loss: 0.001512 2022/09/16 08:03:37 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 08:04:11 - mmengine - INFO - Epoch(train) [205][250/293] lr: 5.000000e-06 eta: 0:47:45 time: 1.491322 data_time: 0.090701 memory: 9974 loss_kpt: 0.001521 loss: 0.001521 2022/09/16 08:05:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 08:05:32 - mmengine - INFO - Saving checkpoint at 205 epochs 2022/09/16 08:06:41 - mmengine - INFO - Epoch(train) [206][50/293] lr: 5.000000e-06 eta: 0:44:45 time: 1.291029 data_time: 0.306031 memory: 9974 loss_kpt: 0.001527 loss: 0.001527 2022/09/16 08:08:08 - mmengine - INFO - Epoch(train) [206][100/293] lr: 5.000000e-06 eta: 0:43:10 time: 1.750853 data_time: 0.099195 memory: 9974 loss_kpt: 0.001486 loss: 0.001486 2022/09/16 08:09:39 - mmengine - INFO - Epoch(train) [206][150/293] lr: 5.000000e-06 eta: 0:41:35 time: 1.815308 data_time: 0.134650 memory: 9974 loss_kpt: 0.001510 loss: 0.001510 2022/09/16 08:11:39 - mmengine - INFO - Epoch(train) [206][200/293] lr: 5.000000e-06 eta: 0:40:01 time: 2.403641 data_time: 0.099229 memory: 9974 loss_kpt: 0.001523 loss: 0.001523 2022/09/16 08:13:29 - mmengine - INFO - Epoch(train) [206][250/293] lr: 5.000000e-06 eta: 0:38:26 time: 2.205977 data_time: 1.413700 memory: 9974 loss_kpt: 0.001542 loss: 0.001542 2022/09/16 08:14:52 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 08:14:52 - mmengine - INFO - Saving checkpoint at 206 epochs 2022/09/16 08:15:51 - mmengine - INFO - Epoch(train) [207][50/293] lr: 5.000000e-06 eta: 0:35:28 time: 1.116761 data_time: 0.201640 memory: 9974 loss_kpt: 0.001514 loss: 0.001514 2022/09/16 08:16:53 - mmengine - INFO - Epoch(train) [207][100/293] lr: 5.000000e-06 eta: 0:33:52 time: 1.231707 data_time: 0.105615 memory: 9974 loss_kpt: 0.001507 loss: 0.001507 2022/09/16 08:18:02 - mmengine - INFO - Epoch(train) [207][150/293] lr: 5.000000e-06 eta: 0:32:17 time: 1.383888 data_time: 0.099344 memory: 9974 loss_kpt: 0.001492 loss: 0.001492 2022/09/16 08:19:24 - mmengine - INFO - Epoch(train) [207][200/293] lr: 5.000000e-06 eta: 0:30:42 time: 1.643288 data_time: 0.139895 memory: 9974 loss_kpt: 0.001494 loss: 0.001494 2022/09/16 08:21:09 - mmengine - INFO - Epoch(train) [207][250/293] lr: 5.000000e-06 eta: 0:29:07 time: 2.087626 data_time: 0.095255 memory: 9974 loss_kpt: 0.001486 loss: 0.001486 2022/09/16 08:22:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 08:22:42 - mmengine - INFO - Saving checkpoint at 207 epochs 2022/09/16 08:24:27 - mmengine - INFO - Epoch(train) [208][50/293] lr: 5.000000e-06 eta: 0:26:10 time: 2.050203 data_time: 0.915321 memory: 9974 loss_kpt: 0.001496 loss: 0.001496 2022/09/16 08:25:52 - mmengine - INFO - Epoch(train) [208][100/293] lr: 5.000000e-06 eta: 0:24:35 time: 1.701969 data_time: 0.192747 memory: 9974 loss_kpt: 0.001495 loss: 0.001495 2022/09/16 08:27:31 - mmengine - INFO - Epoch(train) [208][150/293] lr: 5.000000e-06 eta: 0:23:00 time: 1.968838 data_time: 0.090925 memory: 9974 loss_kpt: 0.001483 loss: 0.001483 2022/09/16 08:28:41 - mmengine - INFO - Epoch(train) [208][200/293] lr: 5.000000e-06 eta: 0:21:25 time: 1.396520 data_time: 0.354477 memory: 9974 loss_kpt: 0.001523 loss: 0.001523 2022/09/16 08:30:21 - mmengine - INFO - Epoch(train) [208][250/293] lr: 5.000000e-06 eta: 0:19:51 time: 2.016043 data_time: 0.125331 memory: 9974 loss_kpt: 0.001523 loss: 0.001523 2022/09/16 08:31:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 08:31:46 - mmengine - INFO - Saving checkpoint at 208 epochs 2022/09/16 08:33:10 - mmengine - INFO - Epoch(train) [209][50/293] lr: 5.000000e-06 eta: 0:16:54 time: 1.599773 data_time: 0.150397 memory: 9974 loss_kpt: 0.001527 loss: 0.001527 2022/09/16 08:33:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 08:34:44 - mmengine - INFO - Epoch(train) [209][100/293] lr: 5.000000e-06 eta: 0:15:19 time: 1.883514 data_time: 0.192916 memory: 9974 loss_kpt: 0.001525 loss: 0.001525 2022/09/16 08:36:16 - mmengine - INFO - Epoch(train) [209][150/293] lr: 5.000000e-06 eta: 0:13:45 time: 1.844236 data_time: 0.103051 memory: 9974 loss_kpt: 0.001512 loss: 0.001512 2022/09/16 08:37:28 - mmengine - INFO - Epoch(train) [209][200/293] lr: 5.000000e-06 eta: 0:12:10 time: 1.431201 data_time: 0.096441 memory: 9974 loss_kpt: 0.001532 loss: 0.001532 2022/09/16 08:39:13 - mmengine - INFO - Epoch(train) [209][250/293] lr: 5.000000e-06 eta: 0:10:35 time: 2.094146 data_time: 0.136745 memory: 9974 loss_kpt: 0.001506 loss: 0.001506 2022/09/16 08:40:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 08:40:19 - mmengine - INFO - Saving checkpoint at 209 epochs 2022/09/16 08:42:03 - mmengine - INFO - Epoch(train) [210][50/293] lr: 5.000000e-06 eta: 0:07:39 time: 2.001464 data_time: 0.273638 memory: 9974 loss_kpt: 0.001527 loss: 0.001527 2022/09/16 08:43:53 - mmengine - INFO - Epoch(train) [210][100/293] lr: 5.000000e-06 eta: 0:06:05 time: 2.214639 data_time: 0.142988 memory: 9974 loss_kpt: 0.001514 loss: 0.001514 2022/09/16 08:45:24 - mmengine - INFO - Epoch(train) [210][150/293] lr: 5.000000e-06 eta: 0:04:30 time: 1.820033 data_time: 0.110334 memory: 9974 loss_kpt: 0.001529 loss: 0.001529 2022/09/16 08:46:51 - mmengine - INFO - Epoch(train) [210][200/293] lr: 5.000000e-06 eta: 0:02:55 time: 1.729780 data_time: 0.443790 memory: 9974 loss_kpt: 0.001522 loss: 0.001522 2022/09/16 08:48:18 - mmengine - INFO - Epoch(train) [210][250/293] lr: 5.000000e-06 eta: 0:01:21 time: 1.741032 data_time: 0.382428 memory: 9974 loss_kpt: 0.001496 loss: 0.001496 2022/09/16 08:49:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-regress-8xb64-210e_coco-256x192_20220914_151831 2022/09/16 08:49:43 - mmengine - INFO - Saving checkpoint at 210 epochs 2022/09/16 08:50:50 - mmengine - INFO - Epoch(val) [210][50/407] eta: 0:07:34 time: 1.273050 data_time: 1.121203 memory: 9974 2022/09/16 08:51:31 - mmengine - INFO - Epoch(val) [210][100/407] eta: 0:04:14 time: 0.827535 data_time: 0.678809 memory: 918 2022/09/16 08:52:11 - mmengine - INFO - Epoch(val) [210][150/407] eta: 0:03:23 time: 0.790202 data_time: 0.635408 memory: 918 2022/09/16 08:52:59 - mmengine - INFO - Epoch(val) [210][200/407] eta: 0:03:19 time: 0.964849 data_time: 0.811211 memory: 918 2022/09/16 08:53:26 - mmengine - INFO - Epoch(val) [210][250/407] eta: 0:01:23 time: 0.531080 data_time: 0.380701 memory: 918 2022/09/16 08:53:54 - mmengine - INFO - Epoch(val) [210][300/407] eta: 0:01:00 time: 0.565905 data_time: 0.409369 memory: 918 2022/09/16 08:54:25 - mmengine - INFO - Epoch(val) [210][350/407] eta: 0:00:35 time: 0.627164 data_time: 0.480552 memory: 918 2022/09/16 08:55:16 - mmengine - INFO - Epoch(val) [210][400/407] eta: 0:00:07 time: 1.020688 data_time: 0.868852 memory: 918 2022/09/16 08:56:22 - mmengine - INFO - Evaluating CocoMetric... 2022/09/16 08:56:36 - mmengine - INFO - Epoch(val) [210][407/407] coco/AP: 0.757429 coco/AP .5: 0.906809 coco/AP .75: 0.824513 coco/AP (M): 0.718165 coco/AP (L): 0.825717 coco/AR: 0.811713 coco/AR .5: 0.942223 coco/AR .75: 0.870120 coco/AR (M): 0.768588 coco/AR (L): 0.874470 2022/09/16 08:56:36 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/udp_regress/best_coco/AP_epoch_190.pth is removed 2022/09/16 08:56:39 - mmengine - INFO - The best checkpoint with 0.7574 coco/AP at 210 epoch is saved to best_coco/AP_epoch_210.pth.