2022/09/15 15:12:45 - 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: 1928540405 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 ------------------------------------------------------------ 2022/09/15 15:12:47 - mmengine - INFO - Config: default_scope = 'mmpose' default_hooks = dict( timer=dict(type='IterTimerHook'), logger=dict(type='LoggerHook', interval=50), param_scheduler=dict(type='ParamSchedulerHook'), checkpoint=dict( type='CheckpointHook', interval=1, save_best='coco/AP', rule='greater', max_keep_ckpts=1), sampler_seed=dict(type='DistSamplerSeedHook'), visualization=dict(type='PoseVisualizationHook', enable=False)) custom_hooks = [dict(type='SyncBuffersHook')] env_cfg = dict( cudnn_benchmark=False, mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0), dist_cfg=dict(backend='nccl')) vis_backends = [dict(type='LocalVisBackend')] visualizer = dict( type='PoseLocalVisualizer', vis_backends=[dict(type='LocalVisBackend')], name='visualizer') log_processor = dict( type='LogProcessor', window_size=50, by_epoch=True, num_digits=6) log_level = 'INFO' load_from = None resume = False file_client_args = dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' })) train_cfg = dict(by_epoch=True, max_epochs=210, val_interval=10) val_cfg = dict() test_cfg = dict() optim_wrapper = dict(optimizer=dict(type='Adam', lr=0.0005)) param_scheduler = [ dict( type='LinearLR', begin=0, end=500, start_factor=0.001, by_epoch=False), dict( type='MultiStepLR', begin=0, end=210, milestones=[170, 200], gamma=0.1, by_epoch=True) ] auto_scale_lr = dict(base_batch_size=512) codec = dict( type='MSRAHeatmap', input_size=(288, 384), heatmap_size=(72, 96), sigma=3, unbiased=True) 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=(48, 96)), stage3=dict( num_modules=4, num_branches=3, block='BASIC', num_blocks=(4, 4, 4), num_channels=(48, 96, 192)), stage4=dict( num_modules=3, num_branches=4, block='BASIC', num_blocks=(4, 4, 4, 4), num_channels=(48, 96, 192, 384))), init_cfg=dict( type='Pretrained', checkpoint= 'https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth' )), head=dict( type='HeatmapHead', in_channels=48, out_channels=17, deconv_out_channels=None, loss=dict(type='KeypointMSELoss', use_target_weight=True), decoder=dict( type='MSRAHeatmap', input_size=(288, 384), heatmap_size=(72, 96), sigma=3, unbiased=True)), test_cfg=dict(flip_test=True, flip_mode='heatmap', shift_heatmap=True)) dataset_type = 'CocoDataset' data_mode = 'topdown' data_root = 'data/coco/' train_pipeline = [ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='RandomFlip', direction='horizontal'), dict(type='RandomHalfBody'), dict(type='RandomBBoxTransform'), dict(type='TopdownAffine', input_size=(288, 384)), dict( type='GenerateTarget', target_type='heatmap', encoder=dict( type='MSRAHeatmap', input_size=(288, 384), heatmap_size=(72, 96), sigma=3, unbiased=True)), dict(type='PackPoseInputs') ] test_pipeline = [ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='TopdownAffine', input_size=(288, 384)), dict(type='PackPoseInputs') ] train_dataloader = dict( batch_size=32, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=True), dataset=dict( type='CocoDataset', data_root='data/coco/', data_mode='topdown', ann_file='annotations/person_keypoints_train2017.json', data_prefix=dict(img='train2017/'), pipeline=[ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='RandomFlip', direction='horizontal'), dict(type='RandomHalfBody'), dict(type='RandomBBoxTransform'), dict(type='TopdownAffine', input_size=(288, 384)), dict( type='GenerateTarget', target_type='heatmap', encoder=dict( type='MSRAHeatmap', input_size=(288, 384), heatmap_size=(72, 96), sigma=3, unbiased=True)), dict(type='PackPoseInputs') ])) val_dataloader = dict( batch_size=32, num_workers=2, persistent_workers=True, drop_last=False, sampler=dict(type='DefaultSampler', shuffle=False, round_up=False), dataset=dict( type='CocoDataset', data_root='data/coco/', data_mode='topdown', ann_file='annotations/person_keypoints_val2017.json', bbox_file= 'data/coco/person_detection_results/COCO_val2017_detections_AP_H_56_person.json', data_prefix=dict(img='val2017/'), test_mode=True, pipeline=[ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='TopdownAffine', input_size=(288, 384)), dict(type='PackPoseInputs') ])) test_dataloader = dict( batch_size=32, num_workers=2, persistent_workers=True, drop_last=False, sampler=dict(type='DefaultSampler', shuffle=False, round_up=False), dataset=dict( type='CocoDataset', data_root='data/coco/', data_mode='topdown', ann_file='annotations/person_keypoints_val2017.json', bbox_file= 'data/coco/person_detection_results/COCO_val2017_detections_AP_H_56_person.json', data_prefix=dict(img='val2017/'), test_mode=True, pipeline=[ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='TopdownAffine', input_size=(288, 384)), dict(type='PackPoseInputs') ])) val_evaluator = dict( type='CocoMetric', ann_file='data/coco/annotations/person_keypoints_val2017.json') test_evaluator = dict( type='CocoMetric', ann_file='data/coco/annotations/person_keypoints_val2017.json') launcher = 'slurm' work_dir = '/mnt/lustre/liqikai/work_dirs/20220915/dark_w48_384/' 2022/09/15 15:13:30 - 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. 2022/09/15 15:13:30 - 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. 2022/09/15 15:13:30 - 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. 2022/09/15 15:13:30 - 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. 2022/09/15 15:13:30 - 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. 2022/09/15 15:13:30 - 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. 2022/09/15 15:13:30 - 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. 2022/09/15 15:13:30 - 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. 2022/09/15 15:13:34 - 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. 2022/09/15 15:13:37 - 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. 2022/09/15 15:13:39 - 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. 2022/09/15 15:13:39 - 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_w48-8ef0771d.pth backbone.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.0.conv1.weight - torch.Size([64, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.0.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.0.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.0.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.0.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.0.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.0.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.0.bn3.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.0.bn3.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.0.downsample.0.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.0.downsample.1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.0.downsample.1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.1.conv1.weight - torch.Size([64, 256, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.1.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.1.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.1.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.1.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.1.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.1.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.1.bn3.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.1.bn3.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.2.conv1.weight - torch.Size([64, 256, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.2.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.2.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.2.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.2.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.2.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.2.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.2.bn3.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.2.bn3.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.3.conv1.weight - torch.Size([64, 256, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.3.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.3.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.3.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.3.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.3.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.3.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.3.bn3.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.3.bn3.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.transition1.0.0.weight - torch.Size([48, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.transition1.0.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.transition1.0.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.transition1.1.0.0.weight - torch.Size([96, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.transition1.1.0.1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.transition1.1.0.1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.0.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.0.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.0.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.0.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.0.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.0.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.1.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.1.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.1.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.1.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.1.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.1.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.2.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.2.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.2.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.2.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.2.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.2.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.3.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.3.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.3.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.3.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.3.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.3.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.0.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.0.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.0.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.0.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.0.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.0.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.1.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.1.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.1.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.1.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.1.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.1.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.2.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.2.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.2.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.2.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.2.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.2.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.3.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.3.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.3.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.3.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.3.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.3.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.fuse_layers.0.1.0.weight - torch.Size([48, 96, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.fuse_layers.0.1.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.fuse_layers.0.1.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.fuse_layers.1.0.0.0.weight - torch.Size([96, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.fuse_layers.1.0.0.1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.fuse_layers.1.0.0.1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.transition2.2.0.0.weight - torch.Size([192, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.transition2.2.0.1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.transition2.2.0.1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.0.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.0.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.0.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.0.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.0.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.0.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.1.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.1.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.1.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.1.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.1.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.1.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.2.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.2.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.2.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.2.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.2.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.2.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.3.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.3.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.3.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.3.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.3.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.3.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.0.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.0.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.0.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.0.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.0.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.0.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.1.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.1.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.1.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.1.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.1.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.1.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.2.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.2.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.2.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.2.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.2.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.2.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.3.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.3.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.3.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.3.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.3.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.3.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.0.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.0.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.0.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.0.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.0.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.0.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.1.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.1.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.1.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.1.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.1.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.1.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.2.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.2.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.2.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.2.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.2.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.2.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.3.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.3.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.3.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.3.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.3.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.3.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.0.1.0.weight - torch.Size([48, 96, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.0.1.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.0.1.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.0.2.0.weight - torch.Size([48, 192, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.0.2.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.0.2.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.1.0.0.0.weight - torch.Size([96, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.1.0.0.1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.1.0.0.1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.1.2.0.weight - torch.Size([96, 192, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.1.2.1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.1.2.1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.2.0.0.0.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.2.0.0.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.2.0.0.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.2.0.1.0.weight - torch.Size([192, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.2.0.1.1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.2.0.1.1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.2.1.0.0.weight - torch.Size([192, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.2.1.0.1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.2.1.0.1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.0.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.0.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.0.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.0.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.0.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.0.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.1.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.1.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.1.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.1.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.1.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.1.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.2.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.2.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.2.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.2.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.2.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.2.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.3.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.3.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.3.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.3.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.3.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.3.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.0.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.0.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.0.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.0.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.0.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.0.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.1.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.1.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.1.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.1.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.1.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.1.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.2.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.2.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.2.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.2.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.2.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.2.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.3.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.3.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.3.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.3.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.3.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.3.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.0.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.0.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.0.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.0.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.0.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.0.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.1.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.1.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.1.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.1.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.1.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.1.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.2.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.2.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.2.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.2.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.2.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.2.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.3.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.3.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.3.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.3.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.3.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.3.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.0.1.0.weight - torch.Size([48, 96, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.0.1.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.0.1.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.0.2.0.weight - torch.Size([48, 192, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.0.2.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.0.2.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.1.0.0.0.weight - torch.Size([96, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.1.0.0.1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.1.0.0.1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.1.2.0.weight - torch.Size([96, 192, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.1.2.1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.1.2.1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.2.0.0.0.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.2.0.0.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.2.0.0.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.2.0.1.0.weight - torch.Size([192, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.2.0.1.1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.2.0.1.1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.2.1.0.0.weight - torch.Size([192, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.2.1.0.1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.2.1.0.1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.0.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.0.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.0.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.0.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.0.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.0.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.1.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.1.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.1.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.1.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.1.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.1.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.2.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.2.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.2.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.2.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.2.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.2.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.3.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.3.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.3.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.3.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.3.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.3.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.0.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.0.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.0.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.0.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.0.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.0.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.1.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.1.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.1.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.1.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.1.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.1.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.2.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.2.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.2.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.2.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.2.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.2.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.3.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.3.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.3.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.3.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.3.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.3.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.0.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.0.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.0.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.0.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.0.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.0.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.1.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.1.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.1.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.1.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.1.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.1.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.2.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.2.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.2.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.2.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.2.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.2.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.3.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.3.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.3.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.3.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.3.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.3.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.0.1.0.weight - torch.Size([48, 96, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.0.1.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.0.1.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.0.2.0.weight - torch.Size([48, 192, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.0.2.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.0.2.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.1.0.0.0.weight - torch.Size([96, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.1.0.0.1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.1.0.0.1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.1.2.0.weight - torch.Size([96, 192, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.1.2.1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.1.2.1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.2.0.0.0.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.2.0.0.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.2.0.0.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.2.0.1.0.weight - torch.Size([192, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.2.0.1.1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.2.0.1.1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.2.1.0.0.weight - torch.Size([192, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.2.1.0.1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.2.1.0.1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.0.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.0.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.0.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.0.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.0.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.0.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.1.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.1.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.1.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.1.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.1.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.1.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.2.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.2.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.2.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.2.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.2.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.2.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.3.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.3.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.3.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.3.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.3.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.3.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.0.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.0.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.0.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.0.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.0.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.0.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.1.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.1.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.1.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.1.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.1.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.1.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.2.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.2.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.2.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.2.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.2.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.2.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.3.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.3.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.3.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.3.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.3.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.3.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.0.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.0.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.0.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.0.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.0.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.0.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.1.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.1.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.1.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.1.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.1.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.1.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.2.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.2.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.2.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.2.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.2.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.2.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.3.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.3.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.3.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.3.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.3.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.3.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.0.1.0.weight - torch.Size([48, 96, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.0.1.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.0.1.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.0.2.0.weight - torch.Size([48, 192, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.0.2.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.0.2.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.1.0.0.0.weight - torch.Size([96, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.1.0.0.1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.1.0.0.1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.1.2.0.weight - torch.Size([96, 192, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.1.2.1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.1.2.1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.2.0.0.0.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.2.0.0.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.2.0.0.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.2.0.1.0.weight - torch.Size([192, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.2.0.1.1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.2.0.1.1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.2.1.0.0.weight - torch.Size([192, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.2.1.0.1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.2.1.0.1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.transition3.3.0.0.weight - torch.Size([384, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.transition3.3.0.1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.transition3.3.0.1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.0.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.0.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.0.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.0.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.0.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.0.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.1.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.1.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.1.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.1.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.1.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.1.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.2.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.2.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.2.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.2.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.2.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.2.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.3.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.3.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.3.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.3.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.3.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.3.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.0.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.0.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.0.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.0.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.0.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.0.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.1.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.1.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.1.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.1.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.1.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.1.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.2.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.2.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.2.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.2.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.2.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.2.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.3.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.3.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.3.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.3.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.3.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.3.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.0.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.0.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.0.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.0.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.0.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.0.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.1.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.1.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.1.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.1.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.1.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.1.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.2.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.2.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.2.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.2.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.2.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.2.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.3.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.3.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.3.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.3.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.3.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.3.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.0.conv1.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.0.bn1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.0.bn1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.0.conv2.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.0.bn2.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.0.bn2.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.1.conv1.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.1.bn1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.1.bn1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.1.conv2.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.1.bn2.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.1.bn2.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.2.conv1.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.2.bn1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.2.bn1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.2.conv2.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.2.bn2.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.2.bn2.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.3.conv1.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.3.bn1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.3.bn1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.3.conv2.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.3.bn2.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.3.bn2.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.0.1.0.weight - torch.Size([48, 96, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.0.1.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.0.1.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.0.2.0.weight - torch.Size([48, 192, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.0.2.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.0.2.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.0.3.0.weight - torch.Size([48, 384, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.0.3.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.0.3.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.1.0.0.0.weight - torch.Size([96, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.1.0.0.1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.1.0.0.1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.1.2.0.weight - torch.Size([96, 192, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.1.2.1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.1.2.1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.1.3.0.weight - torch.Size([96, 384, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.1.3.1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.1.3.1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.2.0.0.0.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.2.0.0.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.2.0.0.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.2.0.1.0.weight - torch.Size([192, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.2.0.1.1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.2.0.1.1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.2.1.0.0.weight - torch.Size([192, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.2.1.0.1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.2.1.0.1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.2.3.0.weight - torch.Size([192, 384, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.2.3.1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.2.3.1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.3.0.0.0.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.3.0.0.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.3.0.0.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.3.0.1.0.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.3.0.1.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.3.0.1.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.3.0.2.0.weight - torch.Size([384, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.3.0.2.1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.3.0.2.1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.3.1.0.0.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.3.1.0.1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.3.1.0.1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.3.1.1.0.weight - torch.Size([384, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.3.1.1.1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.3.1.1.1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.3.2.0.0.weight - torch.Size([384, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.3.2.0.1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.3.2.0.1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.0.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.0.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.0.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.0.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.0.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.0.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.1.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.1.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.1.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.1.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.1.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.1.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.2.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.2.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.2.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.2.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.2.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.2.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.3.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.3.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.3.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.3.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.3.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.3.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.0.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.0.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.0.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.0.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.0.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.0.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.1.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.1.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.1.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.1.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.1.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.1.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.2.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.2.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.2.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.2.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.2.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.2.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.3.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.3.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.3.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.3.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.3.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.3.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.0.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.0.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.0.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.0.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.0.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.0.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.1.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.1.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.1.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.1.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.1.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.1.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.2.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.2.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.2.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.2.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.2.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.2.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.3.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.3.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.3.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.3.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.3.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.3.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.0.conv1.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.0.bn1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.0.bn1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.0.conv2.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.0.bn2.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.0.bn2.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.1.conv1.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.1.bn1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.1.bn1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.1.conv2.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.1.bn2.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.1.bn2.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.2.conv1.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.2.bn1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.2.bn1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.2.conv2.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.2.bn2.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.2.bn2.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.3.conv1.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.3.bn1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.3.bn1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.3.conv2.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.3.bn2.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.3.bn2.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.0.1.0.weight - torch.Size([48, 96, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.0.1.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.0.1.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.0.2.0.weight - torch.Size([48, 192, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.0.2.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.0.2.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.0.3.0.weight - torch.Size([48, 384, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.0.3.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.0.3.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.1.0.0.0.weight - torch.Size([96, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.1.0.0.1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.1.0.0.1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.1.2.0.weight - torch.Size([96, 192, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.1.2.1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.1.2.1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.1.3.0.weight - torch.Size([96, 384, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.1.3.1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.1.3.1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.2.0.0.0.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.2.0.0.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.2.0.0.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.2.0.1.0.weight - torch.Size([192, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.2.0.1.1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.2.0.1.1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.2.1.0.0.weight - torch.Size([192, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.2.1.0.1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.2.1.0.1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.2.3.0.weight - torch.Size([192, 384, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.2.3.1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.2.3.1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.3.0.0.0.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.3.0.0.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.3.0.0.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.3.0.1.0.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.3.0.1.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.3.0.1.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.3.0.2.0.weight - torch.Size([384, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.3.0.2.1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.3.0.2.1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.3.1.0.0.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.3.1.0.1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.3.1.0.1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.3.1.1.0.weight - torch.Size([384, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.3.1.1.1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.3.1.1.1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.3.2.0.0.weight - torch.Size([384, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.3.2.0.1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.3.2.0.1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.0.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.0.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.0.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.0.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.0.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.0.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.1.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.1.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.1.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.1.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.1.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.1.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.2.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.2.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.2.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.2.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.2.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.2.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.3.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.3.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.3.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.3.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.3.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.3.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.0.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.0.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.0.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.0.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.0.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.0.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.1.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.1.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.1.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.1.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.1.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.1.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.2.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.2.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.2.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.2.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.2.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.2.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.3.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.3.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.3.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.3.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.3.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.3.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.0.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.0.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.0.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.0.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.0.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.0.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.1.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.1.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.1.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.1.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.1.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.1.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.2.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.2.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.2.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.2.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.2.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.2.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.3.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.3.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.3.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.3.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.3.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.3.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.0.conv1.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.0.bn1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.0.bn1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.0.conv2.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.0.bn2.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.0.bn2.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.1.conv1.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.1.bn1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.1.bn1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.1.conv2.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.1.bn2.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.1.bn2.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.2.conv1.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.2.bn1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.2.bn1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.2.conv2.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.2.bn2.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.2.bn2.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.3.conv1.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.3.bn1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.3.bn1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.3.conv2.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.3.bn2.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.3.bn2.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.fuse_layers.0.1.0.weight - torch.Size([48, 96, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.fuse_layers.0.1.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.fuse_layers.0.1.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.fuse_layers.0.2.0.weight - torch.Size([48, 192, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.fuse_layers.0.2.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.fuse_layers.0.2.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.fuse_layers.0.3.0.weight - torch.Size([48, 384, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.fuse_layers.0.3.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.fuse_layers.0.3.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth head.final_layer.weight - torch.Size([17, 48, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 head.final_layer.bias - torch.Size([17]): NormalInit: mean=0, std=0.001, bias=0 2022/09/15 15:13:52 - mmengine - INFO - Checkpoints will be saved to /mnt/lustre/liqikai/work_dirs/20220915/dark_w48_384 by HardDiskBackend. 2022/09/15 15:16:13 - mmengine - INFO - Epoch(train) [1][50/586] lr: 4.954910e-05 eta: 4 days, 0:01:10 time: 2.810102 data_time: 1.153194 memory: 15239 loss_kpt: 0.002222 acc_pose: 0.144748 loss: 0.002222 2022/09/15 15:17:36 - mmengine - INFO - Epoch(train) [1][100/586] lr: 9.959920e-05 eta: 3 days, 4:33:23 time: 1.672707 data_time: 0.038029 memory: 15239 loss_kpt: 0.001846 acc_pose: 0.416945 loss: 0.001846 2022/09/15 15:18:42 - mmengine - INFO - Epoch(train) [1][150/586] lr: 1.496493e-04 eta: 2 days, 17:55:12 time: 1.309543 data_time: 0.055122 memory: 15239 loss_kpt: 0.001498 acc_pose: 0.542722 loss: 0.001498 2022/09/15 15:19:42 - mmengine - INFO - Epoch(train) [1][200/586] lr: 1.996994e-04 eta: 2 days, 11:40:39 time: 1.202274 data_time: 0.301852 memory: 15239 loss_kpt: 0.001288 acc_pose: 0.550311 loss: 0.001288 2022/09/15 15:20:40 - mmengine - INFO - Epoch(train) [1][250/586] lr: 2.497495e-04 eta: 2 days, 7:41:00 time: 1.166792 data_time: 0.037412 memory: 15239 loss_kpt: 0.001257 acc_pose: 0.543223 loss: 0.001257 2022/09/15 15:21:29 - mmengine - INFO - Epoch(train) [1][300/586] lr: 2.997996e-04 eta: 2 days, 3:54:03 time: 0.970730 data_time: 0.232784 memory: 15239 loss_kpt: 0.001173 acc_pose: 0.641127 loss: 0.001173 2022/09/15 15:21:59 - mmengine - INFO - Epoch(train) [1][350/586] lr: 3.498497e-04 eta: 1 day, 23:25:05 time: 0.605734 data_time: 0.042121 memory: 15239 loss_kpt: 0.001166 acc_pose: 0.581504 loss: 0.001166 2022/09/15 15:22:48 - mmengine - INFO - Epoch(train) [1][400/586] lr: 3.998998e-04 eta: 1 day, 21:40:26 time: 0.986148 data_time: 0.083730 memory: 15239 loss_kpt: 0.001154 acc_pose: 0.588155 loss: 0.001154 2022/09/15 15:23:33 - mmengine - INFO - Epoch(train) [1][450/586] lr: 4.499499e-04 eta: 1 day, 19:59:31 time: 0.900989 data_time: 0.030079 memory: 15239 loss_kpt: 0.001139 acc_pose: 0.630699 loss: 0.001139 2022/09/15 15:24:11 - mmengine - INFO - Epoch(train) [1][500/586] lr: 5.000000e-04 eta: 1 day, 18:07:37 time: 0.749163 data_time: 0.028646 memory: 15239 loss_kpt: 0.001102 acc_pose: 0.617892 loss: 0.001102 2022/09/15 15:24:48 - mmengine - INFO - Epoch(train) [1][550/586] lr: 5.000000e-04 eta: 1 day, 16:36:11 time: 0.750333 data_time: 0.109663 memory: 15239 loss_kpt: 0.001112 acc_pose: 0.580580 loss: 0.001112 2022/09/15 15:25:20 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 15:25:20 - mmengine - INFO - Saving checkpoint at 1 epochs 2022/09/15 15:25:50 - mmengine - INFO - Epoch(train) [2][50/586] lr: 5.000000e-04 eta: 1 day, 12:19:43 time: 0.464092 data_time: 0.032536 memory: 15239 loss_kpt: 0.001043 acc_pose: 0.656445 loss: 0.001043 2022/09/15 15:26:13 - mmengine - INFO - Epoch(train) [2][100/586] lr: 5.000000e-04 eta: 1 day, 10:48:29 time: 0.460520 data_time: 0.030874 memory: 15239 loss_kpt: 0.001077 acc_pose: 0.625224 loss: 0.001077 2022/09/15 15:26:36 - mmengine - INFO - Epoch(train) [2][150/586] lr: 5.000000e-04 eta: 1 day, 9:30:58 time: 0.470499 data_time: 0.026738 memory: 15239 loss_kpt: 0.001034 acc_pose: 0.640036 loss: 0.001034 2022/09/15 15:26:59 - mmengine - INFO - Epoch(train) [2][200/586] lr: 5.000000e-04 eta: 1 day, 8:21:20 time: 0.455498 data_time: 0.025533 memory: 15239 loss_kpt: 0.001008 acc_pose: 0.675677 loss: 0.001008 2022/09/15 15:27:22 - mmengine - INFO - Epoch(train) [2][250/586] lr: 5.000000e-04 eta: 1 day, 7:21:10 time: 0.465339 data_time: 0.027530 memory: 15239 loss_kpt: 0.000986 acc_pose: 0.697326 loss: 0.000986 2022/09/15 15:27:46 - mmengine - INFO - Epoch(train) [2][300/586] lr: 5.000000e-04 eta: 1 day, 6:28:47 time: 0.474260 data_time: 0.026745 memory: 15239 loss_kpt: 0.001018 acc_pose: 0.742043 loss: 0.001018 2022/09/15 15:28:09 - mmengine - INFO - Epoch(train) [2][350/586] lr: 5.000000e-04 eta: 1 day, 5:40:36 time: 0.461855 data_time: 0.026164 memory: 15239 loss_kpt: 0.000981 acc_pose: 0.704564 loss: 0.000981 2022/09/15 15:28:32 - mmengine - INFO - Epoch(train) [2][400/586] lr: 5.000000e-04 eta: 1 day, 4:57:00 time: 0.459382 data_time: 0.031947 memory: 15239 loss_kpt: 0.000952 acc_pose: 0.671153 loss: 0.000952 2022/09/15 15:28:39 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 15:28:56 - mmengine - INFO - Epoch(train) [2][450/586] lr: 5.000000e-04 eta: 1 day, 4:18:32 time: 0.469084 data_time: 0.026357 memory: 15239 loss_kpt: 0.000960 acc_pose: 0.678402 loss: 0.000960 2022/09/15 15:29:19 - mmengine - INFO - Epoch(train) [2][500/586] lr: 5.000000e-04 eta: 1 day, 3:42:40 time: 0.459367 data_time: 0.025661 memory: 15239 loss_kpt: 0.000918 acc_pose: 0.742379 loss: 0.000918 2022/09/15 15:29:42 - mmengine - INFO - Epoch(train) [2][550/586] lr: 5.000000e-04 eta: 1 day, 3:10:30 time: 0.465910 data_time: 0.031074 memory: 15239 loss_kpt: 0.000959 acc_pose: 0.755517 loss: 0.000959 2022/09/15 15:29:59 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 15:29:59 - mmengine - INFO - Saving checkpoint at 2 epochs 2022/09/15 15:30:30 - mmengine - INFO - Epoch(train) [3][50/586] lr: 5.000000e-04 eta: 1 day, 1:54:44 time: 0.481995 data_time: 0.043572 memory: 15239 loss_kpt: 0.000936 acc_pose: 0.734436 loss: 0.000936 2022/09/15 15:30:53 - mmengine - INFO - Epoch(train) [3][100/586] lr: 5.000000e-04 eta: 1 day, 1:29:30 time: 0.457502 data_time: 0.027733 memory: 15239 loss_kpt: 0.000916 acc_pose: 0.720800 loss: 0.000916 2022/09/15 15:31:17 - mmengine - INFO - Epoch(train) [3][150/586] lr: 5.000000e-04 eta: 1 day, 1:07:47 time: 0.478706 data_time: 0.025896 memory: 15239 loss_kpt: 0.000933 acc_pose: 0.756586 loss: 0.000933 2022/09/15 15:31:40 - mmengine - INFO - Epoch(train) [3][200/586] lr: 5.000000e-04 eta: 1 day, 0:46:40 time: 0.465826 data_time: 0.025407 memory: 15239 loss_kpt: 0.000930 acc_pose: 0.645370 loss: 0.000930 2022/09/15 15:32:03 - mmengine - INFO - Epoch(train) [3][250/586] lr: 5.000000e-04 eta: 1 day, 0:26:07 time: 0.453164 data_time: 0.025732 memory: 15239 loss_kpt: 0.000896 acc_pose: 0.696848 loss: 0.000896 2022/09/15 15:32:26 - mmengine - INFO - Epoch(train) [3][300/586] lr: 5.000000e-04 eta: 1 day, 0:08:07 time: 0.470383 data_time: 0.026663 memory: 15239 loss_kpt: 0.000911 acc_pose: 0.694116 loss: 0.000911 2022/09/15 15:32:50 - mmengine - INFO - Epoch(train) [3][350/586] lr: 5.000000e-04 eta: 23:51:09 time: 0.468588 data_time: 0.026101 memory: 15239 loss_kpt: 0.000895 acc_pose: 0.727656 loss: 0.000895 2022/09/15 15:33:12 - mmengine - INFO - Epoch(train) [3][400/586] lr: 5.000000e-04 eta: 23:34:25 time: 0.455988 data_time: 0.026321 memory: 15239 loss_kpt: 0.000915 acc_pose: 0.809851 loss: 0.000915 2022/09/15 15:33:36 - mmengine - INFO - Epoch(train) [3][450/586] lr: 5.000000e-04 eta: 23:19:22 time: 0.466690 data_time: 0.025744 memory: 15239 loss_kpt: 0.000895 acc_pose: 0.648367 loss: 0.000895 2022/09/15 15:33:59 - mmengine - INFO - Epoch(train) [3][500/586] lr: 5.000000e-04 eta: 23:05:18 time: 0.468346 data_time: 0.026843 memory: 15239 loss_kpt: 0.000883 acc_pose: 0.798966 loss: 0.000883 2022/09/15 15:34:22 - mmengine - INFO - Epoch(train) [3][550/586] lr: 5.000000e-04 eta: 22:51:28 time: 0.458793 data_time: 0.026475 memory: 15239 loss_kpt: 0.000874 acc_pose: 0.734088 loss: 0.000874 2022/09/15 15:34:39 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 15:34:39 - mmengine - INFO - Saving checkpoint at 3 epochs 2022/09/15 15:35:10 - mmengine - INFO - Epoch(train) [4][50/586] lr: 5.000000e-04 eta: 22:11:57 time: 0.476854 data_time: 0.036536 memory: 15239 loss_kpt: 0.000861 acc_pose: 0.740891 loss: 0.000861 2022/09/15 15:35:33 - mmengine - INFO - Epoch(train) [4][100/586] lr: 5.000000e-04 eta: 22:00:30 time: 0.458624 data_time: 0.031197 memory: 15239 loss_kpt: 0.000861 acc_pose: 0.713801 loss: 0.000861 2022/09/15 15:35:56 - mmengine - INFO - Epoch(train) [4][150/586] lr: 5.000000e-04 eta: 21:50:12 time: 0.469249 data_time: 0.025871 memory: 15239 loss_kpt: 0.000872 acc_pose: 0.743899 loss: 0.000872 2022/09/15 15:36:20 - mmengine - INFO - Epoch(train) [4][200/586] lr: 5.000000e-04 eta: 21:40:29 time: 0.470958 data_time: 0.030980 memory: 15239 loss_kpt: 0.000878 acc_pose: 0.647950 loss: 0.000878 2022/09/15 15:36:39 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 15:36:43 - mmengine - INFO - Epoch(train) [4][250/586] lr: 5.000000e-04 eta: 21:30:41 time: 0.459893 data_time: 0.025419 memory: 15239 loss_kpt: 0.000854 acc_pose: 0.697525 loss: 0.000854 2022/09/15 15:37:06 - mmengine - INFO - Epoch(train) [4][300/586] lr: 5.000000e-04 eta: 21:21:25 time: 0.461361 data_time: 0.025989 memory: 15239 loss_kpt: 0.000853 acc_pose: 0.717434 loss: 0.000853 2022/09/15 15:37:29 - mmengine - INFO - Epoch(train) [4][350/586] lr: 5.000000e-04 eta: 21:12:57 time: 0.469533 data_time: 0.029494 memory: 15239 loss_kpt: 0.000861 acc_pose: 0.730552 loss: 0.000861 2022/09/15 15:37:52 - mmengine - INFO - Epoch(train) [4][400/586] lr: 5.000000e-04 eta: 21:04:29 time: 0.461397 data_time: 0.026213 memory: 15239 loss_kpt: 0.000862 acc_pose: 0.722421 loss: 0.000862 2022/09/15 15:38:15 - mmengine - INFO - Epoch(train) [4][450/586] lr: 5.000000e-04 eta: 20:56:13 time: 0.457602 data_time: 0.026411 memory: 15239 loss_kpt: 0.000861 acc_pose: 0.744240 loss: 0.000861 2022/09/15 15:38:39 - mmengine - INFO - Epoch(train) [4][500/586] lr: 5.000000e-04 eta: 20:48:40 time: 0.466205 data_time: 0.030140 memory: 15239 loss_kpt: 0.000836 acc_pose: 0.703839 loss: 0.000836 2022/09/15 15:39:02 - mmengine - INFO - Epoch(train) [4][550/586] lr: 5.000000e-04 eta: 20:41:25 time: 0.465809 data_time: 0.025612 memory: 15239 loss_kpt: 0.000862 acc_pose: 0.706001 loss: 0.000862 2022/09/15 15:39:19 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 15:39:19 - mmengine - INFO - Saving checkpoint at 4 epochs 2022/09/15 15:39:50 - mmengine - INFO - Epoch(train) [5][50/586] lr: 5.000000e-04 eta: 20:15:35 time: 0.466804 data_time: 0.029721 memory: 15239 loss_kpt: 0.000855 acc_pose: 0.745214 loss: 0.000855 2022/09/15 15:40:13 - mmengine - INFO - Epoch(train) [5][100/586] lr: 5.000000e-04 eta: 20:09:13 time: 0.461955 data_time: 0.026370 memory: 15239 loss_kpt: 0.000814 acc_pose: 0.738724 loss: 0.000814 2022/09/15 15:40:36 - mmengine - INFO - Epoch(train) [5][150/586] lr: 5.000000e-04 eta: 20:03:14 time: 0.465296 data_time: 0.027695 memory: 15239 loss_kpt: 0.000825 acc_pose: 0.769956 loss: 0.000825 2022/09/15 15:40:59 - mmengine - INFO - Epoch(train) [5][200/586] lr: 5.000000e-04 eta: 19:57:35 time: 0.468318 data_time: 0.024424 memory: 15239 loss_kpt: 0.000802 acc_pose: 0.652010 loss: 0.000802 2022/09/15 15:41:22 - mmengine - INFO - Epoch(train) [5][250/586] lr: 5.000000e-04 eta: 19:51:49 time: 0.460233 data_time: 0.025976 memory: 15239 loss_kpt: 0.000835 acc_pose: 0.790254 loss: 0.000835 2022/09/15 15:41:46 - mmengine - INFO - Epoch(train) [5][300/586] lr: 5.000000e-04 eta: 19:46:34 time: 0.468246 data_time: 0.025000 memory: 15239 loss_kpt: 0.000813 acc_pose: 0.752032 loss: 0.000813 2022/09/15 15:42:09 - mmengine - INFO - Epoch(train) [5][350/586] lr: 5.000000e-04 eta: 19:41:09 time: 0.459047 data_time: 0.025116 memory: 15239 loss_kpt: 0.000829 acc_pose: 0.714388 loss: 0.000829 2022/09/15 15:42:32 - mmengine - INFO - Epoch(train) [5][400/586] lr: 5.000000e-04 eta: 19:35:54 time: 0.458408 data_time: 0.025827 memory: 15239 loss_kpt: 0.000848 acc_pose: 0.814387 loss: 0.000848 2022/09/15 15:42:55 - mmengine - INFO - Epoch(train) [5][450/586] lr: 5.000000e-04 eta: 19:31:06 time: 0.466311 data_time: 0.030715 memory: 15239 loss_kpt: 0.000820 acc_pose: 0.726283 loss: 0.000820 2022/09/15 15:43:18 - mmengine - INFO - Epoch(train) [5][500/586] lr: 5.000000e-04 eta: 19:26:36 time: 0.470178 data_time: 0.027069 memory: 15239 loss_kpt: 0.000838 acc_pose: 0.743857 loss: 0.000838 2022/09/15 15:43:42 - mmengine - INFO - Epoch(train) [5][550/586] lr: 5.000000e-04 eta: 19:22:23 time: 0.474686 data_time: 0.025597 memory: 15239 loss_kpt: 0.000786 acc_pose: 0.667385 loss: 0.000786 2022/09/15 15:43:59 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 15:43:59 - mmengine - INFO - Saving checkpoint at 5 epochs 2022/09/15 15:44:29 - mmengine - INFO - Epoch(train) [6][50/586] lr: 5.000000e-04 eta: 19:03:56 time: 0.473605 data_time: 0.031584 memory: 15239 loss_kpt: 0.000800 acc_pose: 0.727904 loss: 0.000800 2022/09/15 15:44:39 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 15:44:53 - mmengine - INFO - Epoch(train) [6][100/586] lr: 5.000000e-04 eta: 19:00:07 time: 0.470439 data_time: 0.026568 memory: 15239 loss_kpt: 0.000792 acc_pose: 0.752531 loss: 0.000792 2022/09/15 15:45:17 - mmengine - INFO - Epoch(train) [6][150/586] lr: 5.000000e-04 eta: 18:56:36 time: 0.475964 data_time: 0.025844 memory: 15239 loss_kpt: 0.000824 acc_pose: 0.764264 loss: 0.000824 2022/09/15 15:45:40 - mmengine - INFO - Epoch(train) [6][200/586] lr: 5.000000e-04 eta: 18:52:39 time: 0.459884 data_time: 0.026584 memory: 15239 loss_kpt: 0.000802 acc_pose: 0.743514 loss: 0.000802 2022/09/15 15:46:03 - mmengine - INFO - Epoch(train) [6][250/586] lr: 5.000000e-04 eta: 18:49:17 time: 0.474104 data_time: 0.026060 memory: 15239 loss_kpt: 0.000782 acc_pose: 0.767573 loss: 0.000782 2022/09/15 15:46:27 - mmengine - INFO - Epoch(train) [6][300/586] lr: 5.000000e-04 eta: 18:45:45 time: 0.466110 data_time: 0.026653 memory: 15239 loss_kpt: 0.000778 acc_pose: 0.693873 loss: 0.000778 2022/09/15 15:46:50 - mmengine - INFO - Epoch(train) [6][350/586] lr: 5.000000e-04 eta: 18:42:09 time: 0.460936 data_time: 0.025654 memory: 15239 loss_kpt: 0.000783 acc_pose: 0.694797 loss: 0.000783 2022/09/15 15:47:13 - mmengine - INFO - Epoch(train) [6][400/586] lr: 5.000000e-04 eta: 18:38:47 time: 0.465255 data_time: 0.030057 memory: 15239 loss_kpt: 0.000775 acc_pose: 0.795290 loss: 0.000775 2022/09/15 15:47:36 - mmengine - INFO - Epoch(train) [6][450/586] lr: 5.000000e-04 eta: 18:35:17 time: 0.457932 data_time: 0.025600 memory: 15239 loss_kpt: 0.000779 acc_pose: 0.698013 loss: 0.000779 2022/09/15 15:47:59 - mmengine - INFO - Epoch(train) [6][500/586] lr: 5.000000e-04 eta: 18:32:01 time: 0.462831 data_time: 0.024944 memory: 15239 loss_kpt: 0.000789 acc_pose: 0.770539 loss: 0.000789 2022/09/15 15:48:22 - mmengine - INFO - Epoch(train) [6][550/586] lr: 5.000000e-04 eta: 18:29:01 time: 0.469402 data_time: 0.027101 memory: 15239 loss_kpt: 0.000790 acc_pose: 0.795638 loss: 0.000790 2022/09/15 15:48:39 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 15:48:39 - mmengine - INFO - Saving checkpoint at 6 epochs 2022/09/15 15:49:11 - mmengine - INFO - Epoch(train) [7][50/586] lr: 5.000000e-04 eta: 18:14:38 time: 0.470618 data_time: 0.033151 memory: 15239 loss_kpt: 0.000783 acc_pose: 0.801695 loss: 0.000783 2022/09/15 15:49:35 - mmengine - INFO - Epoch(train) [7][100/586] lr: 5.000000e-04 eta: 18:11:49 time: 0.463625 data_time: 0.026596 memory: 15239 loss_kpt: 0.000793 acc_pose: 0.805643 loss: 0.000793 2022/09/15 15:49:58 - mmengine - INFO - Epoch(train) [7][150/586] lr: 5.000000e-04 eta: 18:09:15 time: 0.470620 data_time: 0.025718 memory: 15239 loss_kpt: 0.000765 acc_pose: 0.887884 loss: 0.000765 2022/09/15 15:50:21 - mmengine - INFO - Epoch(train) [7][200/586] lr: 5.000000e-04 eta: 18:06:27 time: 0.459986 data_time: 0.031113 memory: 15239 loss_kpt: 0.000776 acc_pose: 0.812487 loss: 0.000776 2022/09/15 15:50:44 - mmengine - INFO - Epoch(train) [7][250/586] lr: 5.000000e-04 eta: 18:03:55 time: 0.467431 data_time: 0.026813 memory: 15239 loss_kpt: 0.000781 acc_pose: 0.810997 loss: 0.000781 2022/09/15 15:51:08 - mmengine - INFO - Epoch(train) [7][300/586] lr: 5.000000e-04 eta: 18:01:19 time: 0.462857 data_time: 0.026695 memory: 15239 loss_kpt: 0.000771 acc_pose: 0.797271 loss: 0.000771 2022/09/15 15:51:31 - mmengine - INFO - Epoch(train) [7][350/586] lr: 5.000000e-04 eta: 17:58:40 time: 0.458721 data_time: 0.026114 memory: 15239 loss_kpt: 0.000776 acc_pose: 0.762497 loss: 0.000776 2022/09/15 15:51:54 - mmengine - INFO - Epoch(train) [7][400/586] lr: 5.000000e-04 eta: 17:56:11 time: 0.462742 data_time: 0.026189 memory: 15239 loss_kpt: 0.000785 acc_pose: 0.782090 loss: 0.000785 2022/09/15 15:52:17 - mmengine - INFO - Epoch(train) [7][450/586] lr: 5.000000e-04 eta: 17:53:48 time: 0.464770 data_time: 0.026088 memory: 15239 loss_kpt: 0.000789 acc_pose: 0.788508 loss: 0.000789 2022/09/15 15:52:33 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 15:52:40 - mmengine - INFO - Epoch(train) [7][500/586] lr: 5.000000e-04 eta: 17:51:23 time: 0.461776 data_time: 0.031782 memory: 15239 loss_kpt: 0.000774 acc_pose: 0.762577 loss: 0.000774 2022/09/15 15:53:04 - mmengine - INFO - Epoch(train) [7][550/586] lr: 5.000000e-04 eta: 17:49:15 time: 0.470779 data_time: 0.025642 memory: 15239 loss_kpt: 0.000769 acc_pose: 0.692582 loss: 0.000769 2022/09/15 15:53:20 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 15:53:20 - mmengine - INFO - Saving checkpoint at 7 epochs 2022/09/15 15:53:50 - mmengine - INFO - Epoch(train) [8][50/586] lr: 5.000000e-04 eta: 17:37:22 time: 0.461416 data_time: 0.029827 memory: 15239 loss_kpt: 0.000774 acc_pose: 0.801169 loss: 0.000774 2022/09/15 15:54:14 - mmengine - INFO - Epoch(train) [8][100/586] lr: 5.000000e-04 eta: 17:35:21 time: 0.467441 data_time: 0.025241 memory: 15239 loss_kpt: 0.000748 acc_pose: 0.754689 loss: 0.000748 2022/09/15 15:54:37 - mmengine - INFO - Epoch(train) [8][150/586] lr: 5.000000e-04 eta: 17:33:20 time: 0.465081 data_time: 0.025761 memory: 15239 loss_kpt: 0.000775 acc_pose: 0.828592 loss: 0.000775 2022/09/15 15:55:00 - mmengine - INFO - Epoch(train) [8][200/586] lr: 5.000000e-04 eta: 17:31:18 time: 0.462519 data_time: 0.025439 memory: 15239 loss_kpt: 0.000753 acc_pose: 0.749455 loss: 0.000753 2022/09/15 15:55:24 - mmengine - INFO - Epoch(train) [8][250/586] lr: 5.000000e-04 eta: 17:29:45 time: 0.482403 data_time: 0.026234 memory: 15239 loss_kpt: 0.000745 acc_pose: 0.780741 loss: 0.000745 2022/09/15 15:55:47 - mmengine - INFO - Epoch(train) [8][300/586] lr: 5.000000e-04 eta: 17:27:47 time: 0.463136 data_time: 0.026315 memory: 15239 loss_kpt: 0.000752 acc_pose: 0.814984 loss: 0.000752 2022/09/15 15:56:11 - mmengine - INFO - Epoch(train) [8][350/586] lr: 5.000000e-04 eta: 17:25:55 time: 0.465712 data_time: 0.026419 memory: 15239 loss_kpt: 0.000737 acc_pose: 0.751620 loss: 0.000737 2022/09/15 15:56:34 - mmengine - INFO - Epoch(train) [8][400/586] lr: 5.000000e-04 eta: 17:24:14 time: 0.471829 data_time: 0.026533 memory: 15239 loss_kpt: 0.000762 acc_pose: 0.760749 loss: 0.000762 2022/09/15 15:56:57 - mmengine - INFO - Epoch(train) [8][450/586] lr: 5.000000e-04 eta: 17:22:20 time: 0.461404 data_time: 0.025297 memory: 15239 loss_kpt: 0.000755 acc_pose: 0.776067 loss: 0.000755 2022/09/15 15:57:21 - mmengine - INFO - Epoch(train) [8][500/586] lr: 5.000000e-04 eta: 17:20:37 time: 0.468278 data_time: 0.029563 memory: 15239 loss_kpt: 0.000758 acc_pose: 0.754154 loss: 0.000758 2022/09/15 15:57:44 - mmengine - INFO - Epoch(train) [8][550/586] lr: 5.000000e-04 eta: 17:18:57 time: 0.468958 data_time: 0.026277 memory: 15239 loss_kpt: 0.000767 acc_pose: 0.780993 loss: 0.000767 2022/09/15 15:58:01 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 15:58:01 - mmengine - INFO - Saving checkpoint at 8 epochs 2022/09/15 15:58:32 - mmengine - INFO - Epoch(train) [9][50/586] lr: 5.000000e-04 eta: 17:09:19 time: 0.479341 data_time: 0.031369 memory: 15239 loss_kpt: 0.000750 acc_pose: 0.744568 loss: 0.000750 2022/09/15 15:58:55 - mmengine - INFO - Epoch(train) [9][100/586] lr: 5.000000e-04 eta: 17:07:47 time: 0.468123 data_time: 0.025280 memory: 15239 loss_kpt: 0.000787 acc_pose: 0.706135 loss: 0.000787 2022/09/15 15:59:19 - mmengine - INFO - Epoch(train) [9][150/586] lr: 5.000000e-04 eta: 17:06:08 time: 0.461745 data_time: 0.026296 memory: 15239 loss_kpt: 0.000756 acc_pose: 0.756712 loss: 0.000756 2022/09/15 15:59:42 - mmengine - INFO - Epoch(train) [9][200/586] lr: 5.000000e-04 eta: 17:04:30 time: 0.461235 data_time: 0.025981 memory: 15239 loss_kpt: 0.000745 acc_pose: 0.725109 loss: 0.000745 2022/09/15 16:00:08 - mmengine - INFO - Epoch(train) [9][250/586] lr: 5.000000e-04 eta: 17:04:04 time: 0.520405 data_time: 0.041070 memory: 15239 loss_kpt: 0.000746 acc_pose: 0.768721 loss: 0.000746 2022/09/15 16:00:30 - mmengine - INFO - Epoch(train) [9][300/586] lr: 5.000000e-04 eta: 17:02:19 time: 0.453912 data_time: 0.026510 memory: 15239 loss_kpt: 0.000758 acc_pose: 0.735859 loss: 0.000758 2022/09/15 16:00:36 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 16:00:53 - mmengine - INFO - Epoch(train) [9][350/586] lr: 5.000000e-04 eta: 17:00:42 time: 0.458568 data_time: 0.026471 memory: 15239 loss_kpt: 0.000727 acc_pose: 0.817088 loss: 0.000727 2022/09/15 16:01:17 - mmengine - INFO - Epoch(train) [9][400/586] lr: 5.000000e-04 eta: 16:59:23 time: 0.472919 data_time: 0.025433 memory: 15239 loss_kpt: 0.000762 acc_pose: 0.749023 loss: 0.000762 2022/09/15 16:01:40 - mmengine - INFO - Epoch(train) [9][450/586] lr: 5.000000e-04 eta: 16:57:46 time: 0.456309 data_time: 0.026309 memory: 15239 loss_kpt: 0.000779 acc_pose: 0.787874 loss: 0.000779 2022/09/15 16:02:03 - mmengine - INFO - Epoch(train) [9][500/586] lr: 5.000000e-04 eta: 16:56:19 time: 0.464508 data_time: 0.025934 memory: 15239 loss_kpt: 0.000723 acc_pose: 0.684671 loss: 0.000723 2022/09/15 16:02:27 - mmengine - INFO - Epoch(train) [9][550/586] lr: 5.000000e-04 eta: 16:55:08 time: 0.477545 data_time: 0.025807 memory: 15239 loss_kpt: 0.000781 acc_pose: 0.752116 loss: 0.000781 2022/09/15 16:02:43 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 16:02:43 - mmengine - INFO - Saving checkpoint at 9 epochs 2022/09/15 16:03:14 - mmengine - INFO - Epoch(train) [10][50/586] lr: 5.000000e-04 eta: 16:46:43 time: 0.471923 data_time: 0.031472 memory: 15239 loss_kpt: 0.000736 acc_pose: 0.776915 loss: 0.000736 2022/09/15 16:03:37 - mmengine - INFO - Epoch(train) [10][100/586] lr: 5.000000e-04 eta: 16:45:29 time: 0.469057 data_time: 0.026365 memory: 15239 loss_kpt: 0.000744 acc_pose: 0.825199 loss: 0.000744 2022/09/15 16:04:00 - mmengine - INFO - Epoch(train) [10][150/586] lr: 5.000000e-04 eta: 16:44:07 time: 0.460749 data_time: 0.025872 memory: 15239 loss_kpt: 0.000765 acc_pose: 0.782473 loss: 0.000765 2022/09/15 16:04:24 - mmengine - INFO - Epoch(train) [10][200/586] lr: 5.000000e-04 eta: 16:42:50 time: 0.464372 data_time: 0.030691 memory: 15239 loss_kpt: 0.000753 acc_pose: 0.760287 loss: 0.000753 2022/09/15 16:04:47 - mmengine - INFO - Epoch(train) [10][250/586] lr: 5.000000e-04 eta: 16:41:29 time: 0.459301 data_time: 0.026197 memory: 15239 loss_kpt: 0.000723 acc_pose: 0.686260 loss: 0.000723 2022/09/15 16:05:10 - mmengine - INFO - Epoch(train) [10][300/586] lr: 5.000000e-04 eta: 16:40:09 time: 0.460267 data_time: 0.027827 memory: 15239 loss_kpt: 0.000748 acc_pose: 0.687330 loss: 0.000748 2022/09/15 16:05:33 - mmengine - INFO - Epoch(train) [10][350/586] lr: 5.000000e-04 eta: 16:39:00 time: 0.469245 data_time: 0.026990 memory: 15239 loss_kpt: 0.000735 acc_pose: 0.807041 loss: 0.000735 2022/09/15 16:05:56 - mmengine - INFO - Epoch(train) [10][400/586] lr: 5.000000e-04 eta: 16:37:48 time: 0.465168 data_time: 0.026172 memory: 15239 loss_kpt: 0.000738 acc_pose: 0.833481 loss: 0.000738 2022/09/15 16:06:19 - mmengine - INFO - Epoch(train) [10][450/586] lr: 5.000000e-04 eta: 16:36:24 time: 0.452506 data_time: 0.025820 memory: 15239 loss_kpt: 0.000736 acc_pose: 0.785617 loss: 0.000736 2022/09/15 16:06:42 - mmengine - INFO - Epoch(train) [10][500/586] lr: 5.000000e-04 eta: 16:35:10 time: 0.462170 data_time: 0.031173 memory: 15239 loss_kpt: 0.000733 acc_pose: 0.807329 loss: 0.000733 2022/09/15 16:07:05 - mmengine - INFO - Epoch(train) [10][550/586] lr: 5.000000e-04 eta: 16:34:00 time: 0.464486 data_time: 0.026185 memory: 15239 loss_kpt: 0.000740 acc_pose: 0.770225 loss: 0.000740 2022/09/15 16:07:22 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 16:07:22 - mmengine - INFO - Saving checkpoint at 10 epochs 2022/09/15 16:07:46 - mmengine - INFO - Epoch(val) [10][50/407] eta: 0:01:47 time: 0.302363 data_time: 0.056587 memory: 15239 2022/09/15 16:07:58 - mmengine - INFO - Epoch(val) [10][100/407] eta: 0:01:17 time: 0.254035 data_time: 0.009241 memory: 2064 2022/09/15 16:08:11 - mmengine - INFO - Epoch(val) [10][150/407] eta: 0:01:04 time: 0.249560 data_time: 0.008321 memory: 2064 2022/09/15 16:08:23 - mmengine - INFO - Epoch(val) [10][200/407] eta: 0:00:51 time: 0.248581 data_time: 0.008098 memory: 2064 2022/09/15 16:08:36 - mmengine - INFO - Epoch(val) [10][250/407] eta: 0:00:39 time: 0.250673 data_time: 0.008018 memory: 2064 2022/09/15 16:08:49 - mmengine - INFO - Epoch(val) [10][300/407] eta: 0:00:27 time: 0.253818 data_time: 0.013000 memory: 2064 2022/09/15 16:09:01 - mmengine - INFO - Epoch(val) [10][350/407] eta: 0:00:14 time: 0.252341 data_time: 0.008870 memory: 2064 2022/09/15 16:09:14 - mmengine - INFO - Epoch(val) [10][400/407] eta: 0:00:01 time: 0.247029 data_time: 0.008085 memory: 2064 2022/09/15 16:09:49 - mmengine - INFO - Evaluating CocoMetric... 2022/09/15 16:10:02 - mmengine - INFO - Epoch(val) [10][407/407] coco/AP: 0.694263 coco/AP .5: 0.877986 coco/AP .75: 0.758474 coco/AP (M): 0.654525 coco/AP (L): 0.766751 coco/AR: 0.751008 coco/AR .5: 0.919868 coco/AR .75: 0.810139 coco/AR (M): 0.705190 coco/AR (L): 0.816797 2022/09/15 16:10:06 - mmengine - INFO - The best checkpoint with 0.6943 coco/AP at 10 epoch is saved to best_coco/AP_epoch_10.pth. 2022/09/15 16:10:29 - mmengine - INFO - Epoch(train) [11][50/586] lr: 5.000000e-04 eta: 16:26:33 time: 0.468702 data_time: 0.031046 memory: 15239 loss_kpt: 0.000738 acc_pose: 0.797401 loss: 0.000738 2022/09/15 16:10:53 - mmengine - INFO - Epoch(train) [11][100/586] lr: 5.000000e-04 eta: 16:25:29 time: 0.465131 data_time: 0.024405 memory: 15239 loss_kpt: 0.000733 acc_pose: 0.743852 loss: 0.000733 2022/09/15 16:11:11 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 16:11:16 - mmengine - INFO - Epoch(train) [11][150/586] lr: 5.000000e-04 eta: 16:24:16 time: 0.456691 data_time: 0.024526 memory: 15239 loss_kpt: 0.000747 acc_pose: 0.754314 loss: 0.000747 2022/09/15 16:11:39 - mmengine - INFO - Epoch(train) [11][200/586] lr: 5.000000e-04 eta: 16:23:14 time: 0.465848 data_time: 0.029148 memory: 15239 loss_kpt: 0.000741 acc_pose: 0.741563 loss: 0.000741 2022/09/15 16:12:02 - mmengine - INFO - Epoch(train) [11][250/586] lr: 5.000000e-04 eta: 16:22:13 time: 0.466867 data_time: 0.026139 memory: 15239 loss_kpt: 0.000731 acc_pose: 0.685574 loss: 0.000731 2022/09/15 16:12:25 - mmengine - INFO - Epoch(train) [11][300/586] lr: 5.000000e-04 eta: 16:21:06 time: 0.460339 data_time: 0.024881 memory: 15239 loss_kpt: 0.000729 acc_pose: 0.796405 loss: 0.000729 2022/09/15 16:12:48 - mmengine - INFO - Epoch(train) [11][350/586] lr: 5.000000e-04 eta: 16:20:02 time: 0.461858 data_time: 0.024799 memory: 15239 loss_kpt: 0.000719 acc_pose: 0.827683 loss: 0.000719 2022/09/15 16:13:12 - mmengine - INFO - Epoch(train) [11][400/586] lr: 5.000000e-04 eta: 16:19:01 time: 0.464902 data_time: 0.024442 memory: 15239 loss_kpt: 0.000728 acc_pose: 0.724034 loss: 0.000728 2022/09/15 16:13:35 - mmengine - INFO - Epoch(train) [11][450/586] lr: 5.000000e-04 eta: 16:17:55 time: 0.458319 data_time: 0.024747 memory: 15239 loss_kpt: 0.000736 acc_pose: 0.809446 loss: 0.000736 2022/09/15 16:13:58 - mmengine - INFO - Epoch(train) [11][500/586] lr: 5.000000e-04 eta: 16:16:54 time: 0.463433 data_time: 0.025638 memory: 15239 loss_kpt: 0.000730 acc_pose: 0.762763 loss: 0.000730 2022/09/15 16:14:21 - mmengine - INFO - Epoch(train) [11][550/586] lr: 5.000000e-04 eta: 16:15:56 time: 0.466731 data_time: 0.024314 memory: 15239 loss_kpt: 0.000743 acc_pose: 0.760627 loss: 0.000743 2022/09/15 16:14:37 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 16:14:37 - mmengine - INFO - Saving checkpoint at 11 epochs 2022/09/15 16:15:08 - mmengine - INFO - Epoch(train) [12][50/586] lr: 5.000000e-04 eta: 16:09:18 time: 0.467464 data_time: 0.030647 memory: 15239 loss_kpt: 0.000726 acc_pose: 0.847397 loss: 0.000726 2022/09/15 16:15:31 - mmengine - INFO - Epoch(train) [12][100/586] lr: 5.000000e-04 eta: 16:08:32 time: 0.475301 data_time: 0.025537 memory: 15239 loss_kpt: 0.000743 acc_pose: 0.773022 loss: 0.000743 2022/09/15 16:15:55 - mmengine - INFO - Epoch(train) [12][150/586] lr: 5.000000e-04 eta: 16:07:33 time: 0.461097 data_time: 0.024141 memory: 15239 loss_kpt: 0.000719 acc_pose: 0.756797 loss: 0.000719 2022/09/15 16:16:17 - mmengine - INFO - Epoch(train) [12][200/586] lr: 5.000000e-04 eta: 16:06:32 time: 0.456706 data_time: 0.025321 memory: 15239 loss_kpt: 0.000714 acc_pose: 0.805644 loss: 0.000714 2022/09/15 16:16:41 - mmengine - INFO - Epoch(train) [12][250/586] lr: 5.000000e-04 eta: 16:05:41 time: 0.468340 data_time: 0.027329 memory: 15239 loss_kpt: 0.000699 acc_pose: 0.835124 loss: 0.000699 2022/09/15 16:17:04 - mmengine - INFO - Epoch(train) [12][300/586] lr: 5.000000e-04 eta: 16:04:42 time: 0.458382 data_time: 0.024014 memory: 15239 loss_kpt: 0.000715 acc_pose: 0.747502 loss: 0.000715 2022/09/15 16:17:27 - mmengine - INFO - Epoch(train) [12][350/586] lr: 5.000000e-04 eta: 16:03:45 time: 0.459977 data_time: 0.024237 memory: 15239 loss_kpt: 0.000726 acc_pose: 0.813048 loss: 0.000726 2022/09/15 16:17:51 - mmengine - INFO - Epoch(train) [12][400/586] lr: 5.000000e-04 eta: 16:03:05 time: 0.479865 data_time: 0.025622 memory: 15239 loss_kpt: 0.000714 acc_pose: 0.802039 loss: 0.000714 2022/09/15 16:18:14 - mmengine - INFO - Epoch(train) [12][450/586] lr: 5.000000e-04 eta: 16:02:11 time: 0.462295 data_time: 0.025176 memory: 15239 loss_kpt: 0.000733 acc_pose: 0.714540 loss: 0.000733 2022/09/15 16:18:37 - mmengine - INFO - Epoch(train) [12][500/586] lr: 5.000000e-04 eta: 16:01:14 time: 0.458316 data_time: 0.025169 memory: 15239 loss_kpt: 0.000740 acc_pose: 0.733439 loss: 0.000740 2022/09/15 16:19:00 - mmengine - INFO - Epoch(train) [12][550/586] lr: 5.000000e-04 eta: 16:00:28 time: 0.471791 data_time: 0.024106 memory: 15239 loss_kpt: 0.000711 acc_pose: 0.778510 loss: 0.000711 2022/09/15 16:19:02 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 16:19:17 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 16:19:17 - mmengine - INFO - Saving checkpoint at 12 epochs 2022/09/15 16:19:48 - mmengine - INFO - Epoch(train) [13][50/586] lr: 5.000000e-04 eta: 15:54:34 time: 0.473537 data_time: 0.037772 memory: 15239 loss_kpt: 0.000710 acc_pose: 0.827052 loss: 0.000710 2022/09/15 16:20:12 - mmengine - INFO - Epoch(train) [13][100/586] lr: 5.000000e-04 eta: 15:54:00 time: 0.482482 data_time: 0.027684 memory: 15239 loss_kpt: 0.000700 acc_pose: 0.710796 loss: 0.000700 2022/09/15 16:20:35 - mmengine - INFO - Epoch(train) [13][150/586] lr: 5.000000e-04 eta: 15:53:13 time: 0.465627 data_time: 0.033299 memory: 15239 loss_kpt: 0.000693 acc_pose: 0.716747 loss: 0.000693 2022/09/15 16:20:58 - mmengine - INFO - Epoch(train) [13][200/586] lr: 5.000000e-04 eta: 15:52:21 time: 0.459047 data_time: 0.027900 memory: 15239 loss_kpt: 0.000721 acc_pose: 0.716785 loss: 0.000721 2022/09/15 16:21:22 - mmengine - INFO - Epoch(train) [13][250/586] lr: 5.000000e-04 eta: 15:51:38 time: 0.471159 data_time: 0.027736 memory: 15239 loss_kpt: 0.000706 acc_pose: 0.699660 loss: 0.000706 2022/09/15 16:21:45 - mmengine - INFO - Epoch(train) [13][300/586] lr: 5.000000e-04 eta: 15:50:50 time: 0.462705 data_time: 0.024722 memory: 15239 loss_kpt: 0.000716 acc_pose: 0.723367 loss: 0.000716 2022/09/15 16:22:08 - mmengine - INFO - Epoch(train) [13][350/586] lr: 5.000000e-04 eta: 15:50:03 time: 0.464689 data_time: 0.023803 memory: 15239 loss_kpt: 0.000706 acc_pose: 0.719339 loss: 0.000706 2022/09/15 16:22:32 - mmengine - INFO - Epoch(train) [13][400/586] lr: 5.000000e-04 eta: 15:49:18 time: 0.466948 data_time: 0.023889 memory: 15239 loss_kpt: 0.000706 acc_pose: 0.835164 loss: 0.000706 2022/09/15 16:22:54 - mmengine - INFO - Epoch(train) [13][450/586] lr: 5.000000e-04 eta: 15:48:25 time: 0.456516 data_time: 0.027669 memory: 15239 loss_kpt: 0.000704 acc_pose: 0.764224 loss: 0.000704 2022/09/15 16:23:18 - mmengine - INFO - Epoch(train) [13][500/586] lr: 5.000000e-04 eta: 15:47:40 time: 0.465656 data_time: 0.024434 memory: 15239 loss_kpt: 0.000726 acc_pose: 0.754845 loss: 0.000726 2022/09/15 16:23:41 - mmengine - INFO - Epoch(train) [13][550/586] lr: 5.000000e-04 eta: 15:46:58 time: 0.469266 data_time: 0.026870 memory: 15239 loss_kpt: 0.000718 acc_pose: 0.833412 loss: 0.000718 2022/09/15 16:23:57 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 16:23:57 - mmengine - INFO - Saving checkpoint at 13 epochs 2022/09/15 16:24:28 - mmengine - INFO - Epoch(train) [14][50/586] lr: 5.000000e-04 eta: 15:41:34 time: 0.471977 data_time: 0.031564 memory: 15239 loss_kpt: 0.000691 acc_pose: 0.773743 loss: 0.000691 2022/09/15 16:24:52 - mmengine - INFO - Epoch(train) [14][100/586] lr: 5.000000e-04 eta: 15:41:02 time: 0.478790 data_time: 0.025066 memory: 15239 loss_kpt: 0.000698 acc_pose: 0.810871 loss: 0.000698 2022/09/15 16:25:15 - mmengine - INFO - Epoch(train) [14][150/586] lr: 5.000000e-04 eta: 15:40:14 time: 0.458707 data_time: 0.024688 memory: 15239 loss_kpt: 0.000680 acc_pose: 0.805994 loss: 0.000680 2022/09/15 16:25:38 - mmengine - INFO - Epoch(train) [14][200/586] lr: 5.000000e-04 eta: 15:39:30 time: 0.461998 data_time: 0.024823 memory: 15239 loss_kpt: 0.000687 acc_pose: 0.816153 loss: 0.000687 2022/09/15 16:26:02 - mmengine - INFO - Epoch(train) [14][250/586] lr: 5.000000e-04 eta: 15:38:56 time: 0.476075 data_time: 0.024769 memory: 15239 loss_kpt: 0.000716 acc_pose: 0.803209 loss: 0.000716 2022/09/15 16:26:24 - mmengine - INFO - Epoch(train) [14][300/586] lr: 5.000000e-04 eta: 15:38:06 time: 0.453501 data_time: 0.025019 memory: 15239 loss_kpt: 0.000714 acc_pose: 0.719863 loss: 0.000714 2022/09/15 16:26:48 - mmengine - INFO - Epoch(train) [14][350/586] lr: 5.000000e-04 eta: 15:37:27 time: 0.469268 data_time: 0.028057 memory: 15239 loss_kpt: 0.000708 acc_pose: 0.835111 loss: 0.000708 2022/09/15 16:27:03 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 16:27:11 - mmengine - INFO - Epoch(train) [14][400/586] lr: 5.000000e-04 eta: 15:36:42 time: 0.460754 data_time: 0.024456 memory: 15239 loss_kpt: 0.000671 acc_pose: 0.797538 loss: 0.000671 2022/09/15 16:27:34 - mmengine - INFO - Epoch(train) [14][450/586] lr: 5.000000e-04 eta: 15:35:55 time: 0.456051 data_time: 0.026269 memory: 15239 loss_kpt: 0.000691 acc_pose: 0.775362 loss: 0.000691 2022/09/15 16:27:58 - mmengine - INFO - Epoch(train) [14][500/586] lr: 5.000000e-04 eta: 15:35:21 time: 0.474314 data_time: 0.024786 memory: 15239 loss_kpt: 0.000687 acc_pose: 0.781511 loss: 0.000687 2022/09/15 16:28:21 - mmengine - INFO - Epoch(train) [14][550/586] lr: 5.000000e-04 eta: 15:34:46 time: 0.473515 data_time: 0.024311 memory: 15239 loss_kpt: 0.000678 acc_pose: 0.838557 loss: 0.000678 2022/09/15 16:28:38 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 16:28:38 - mmengine - INFO - Saving checkpoint at 14 epochs 2022/09/15 16:29:09 - mmengine - INFO - Epoch(train) [15][50/586] lr: 5.000000e-04 eta: 15:29:51 time: 0.475539 data_time: 0.028053 memory: 15239 loss_kpt: 0.000692 acc_pose: 0.813695 loss: 0.000692 2022/09/15 16:29:33 - mmengine - INFO - Epoch(train) [15][100/586] lr: 5.000000e-04 eta: 15:29:19 time: 0.476052 data_time: 0.024939 memory: 15239 loss_kpt: 0.000706 acc_pose: 0.835615 loss: 0.000706 2022/09/15 16:29:56 - mmengine - INFO - Epoch(train) [15][150/586] lr: 5.000000e-04 eta: 15:28:37 time: 0.459029 data_time: 0.024860 memory: 15239 loss_kpt: 0.000687 acc_pose: 0.701623 loss: 0.000687 2022/09/15 16:30:19 - mmengine - INFO - Epoch(train) [15][200/586] lr: 5.000000e-04 eta: 15:27:58 time: 0.464609 data_time: 0.024443 memory: 15239 loss_kpt: 0.000725 acc_pose: 0.769896 loss: 0.000725 2022/09/15 16:30:42 - mmengine - INFO - Epoch(train) [15][250/586] lr: 5.000000e-04 eta: 15:27:19 time: 0.464685 data_time: 0.024322 memory: 15239 loss_kpt: 0.000696 acc_pose: 0.812562 loss: 0.000696 2022/09/15 16:31:06 - mmengine - INFO - Epoch(train) [15][300/586] lr: 5.000000e-04 eta: 15:26:49 time: 0.476472 data_time: 0.027640 memory: 15239 loss_kpt: 0.000687 acc_pose: 0.815325 loss: 0.000687 2022/09/15 16:31:29 - mmengine - INFO - Epoch(train) [15][350/586] lr: 5.000000e-04 eta: 15:26:08 time: 0.459768 data_time: 0.025319 memory: 15239 loss_kpt: 0.000693 acc_pose: 0.822186 loss: 0.000693 2022/09/15 16:31:52 - mmengine - INFO - Epoch(train) [15][400/586] lr: 5.000000e-04 eta: 15:25:33 time: 0.469870 data_time: 0.025360 memory: 15239 loss_kpt: 0.000708 acc_pose: 0.754643 loss: 0.000708 2022/09/15 16:32:16 - mmengine - INFO - Epoch(train) [15][450/586] lr: 5.000000e-04 eta: 15:24:59 time: 0.469739 data_time: 0.024914 memory: 15239 loss_kpt: 0.000699 acc_pose: 0.693121 loss: 0.000699 2022/09/15 16:32:39 - mmengine - INFO - Epoch(train) [15][500/586] lr: 5.000000e-04 eta: 15:24:22 time: 0.466852 data_time: 0.025638 memory: 15239 loss_kpt: 0.000712 acc_pose: 0.785827 loss: 0.000712 2022/09/15 16:33:03 - mmengine - INFO - Epoch(train) [15][550/586] lr: 5.000000e-04 eta: 15:23:50 time: 0.471887 data_time: 0.024567 memory: 15239 loss_kpt: 0.000694 acc_pose: 0.828861 loss: 0.000694 2022/09/15 16:33:19 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 16:33:19 - mmengine - INFO - Saving checkpoint at 15 epochs 2022/09/15 16:33:50 - mmengine - INFO - Epoch(train) [16][50/586] lr: 5.000000e-04 eta: 15:19:21 time: 0.482355 data_time: 0.032886 memory: 15239 loss_kpt: 0.000692 acc_pose: 0.728310 loss: 0.000692 2022/09/15 16:34:14 - mmengine - INFO - Epoch(train) [16][100/586] lr: 5.000000e-04 eta: 15:18:45 time: 0.464495 data_time: 0.024414 memory: 15239 loss_kpt: 0.000689 acc_pose: 0.827702 loss: 0.000689 2022/09/15 16:34:37 - mmengine - INFO - Epoch(train) [16][150/586] lr: 5.000000e-04 eta: 15:18:10 time: 0.466310 data_time: 0.024568 memory: 15239 loss_kpt: 0.000711 acc_pose: 0.797278 loss: 0.000711 2022/09/15 16:35:00 - mmengine - INFO - Epoch(train) [16][200/586] lr: 5.000000e-04 eta: 15:17:31 time: 0.459826 data_time: 0.024412 memory: 15239 loss_kpt: 0.000707 acc_pose: 0.816135 loss: 0.000707 2022/09/15 16:35:05 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 16:35:23 - mmengine - INFO - Epoch(train) [16][250/586] lr: 5.000000e-04 eta: 15:16:56 time: 0.465545 data_time: 0.024275 memory: 15239 loss_kpt: 0.000676 acc_pose: 0.833958 loss: 0.000676 2022/09/15 16:35:46 - mmengine - INFO - Epoch(train) [16][300/586] lr: 5.000000e-04 eta: 15:16:18 time: 0.460031 data_time: 0.024754 memory: 15239 loss_kpt: 0.000698 acc_pose: 0.768995 loss: 0.000698 2022/09/15 16:36:09 - mmengine - INFO - Epoch(train) [16][350/586] lr: 5.000000e-04 eta: 15:15:41 time: 0.460697 data_time: 0.024222 memory: 15239 loss_kpt: 0.000683 acc_pose: 0.728327 loss: 0.000683 2022/09/15 16:36:33 - mmengine - INFO - Epoch(train) [16][400/586] lr: 5.000000e-04 eta: 15:15:07 time: 0.467358 data_time: 0.024059 memory: 15239 loss_kpt: 0.000709 acc_pose: 0.824920 loss: 0.000709 2022/09/15 16:36:55 - mmengine - INFO - Epoch(train) [16][450/586] lr: 5.000000e-04 eta: 15:14:25 time: 0.452781 data_time: 0.024494 memory: 15239 loss_kpt: 0.000687 acc_pose: 0.779528 loss: 0.000687 2022/09/15 16:37:19 - mmengine - INFO - Epoch(train) [16][500/586] lr: 5.000000e-04 eta: 15:13:52 time: 0.466804 data_time: 0.024166 memory: 15239 loss_kpt: 0.000677 acc_pose: 0.679602 loss: 0.000677 2022/09/15 16:37:42 - mmengine - INFO - Epoch(train) [16][550/586] lr: 5.000000e-04 eta: 15:13:19 time: 0.467577 data_time: 0.024365 memory: 15239 loss_kpt: 0.000702 acc_pose: 0.699984 loss: 0.000702 2022/09/15 16:37:58 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 16:37:58 - mmengine - INFO - Saving checkpoint at 16 epochs 2022/09/15 16:38:29 - mmengine - INFO - Epoch(train) [17][50/586] lr: 5.000000e-04 eta: 15:09:02 time: 0.472282 data_time: 0.028446 memory: 15239 loss_kpt: 0.000709 acc_pose: 0.798286 loss: 0.000709 2022/09/15 16:38:52 - mmengine - INFO - Epoch(train) [17][100/586] lr: 5.000000e-04 eta: 15:08:31 time: 0.467852 data_time: 0.026165 memory: 15239 loss_kpt: 0.000692 acc_pose: 0.756546 loss: 0.000692 2022/09/15 16:39:15 - mmengine - INFO - Epoch(train) [17][150/586] lr: 5.000000e-04 eta: 15:07:59 time: 0.466289 data_time: 0.023974 memory: 15239 loss_kpt: 0.000679 acc_pose: 0.864098 loss: 0.000679 2022/09/15 16:39:39 - mmengine - INFO - Epoch(train) [17][200/586] lr: 5.000000e-04 eta: 15:07:24 time: 0.461645 data_time: 0.025080 memory: 15239 loss_kpt: 0.000672 acc_pose: 0.824490 loss: 0.000672 2022/09/15 16:40:02 - mmengine - INFO - Epoch(train) [17][250/586] lr: 5.000000e-04 eta: 15:06:52 time: 0.466051 data_time: 0.024952 memory: 15239 loss_kpt: 0.000693 acc_pose: 0.803799 loss: 0.000693 2022/09/15 16:40:25 - mmengine - INFO - Epoch(train) [17][300/586] lr: 5.000000e-04 eta: 15:06:20 time: 0.465856 data_time: 0.024001 memory: 15239 loss_kpt: 0.000670 acc_pose: 0.834756 loss: 0.000670 2022/09/15 16:40:48 - mmengine - INFO - Epoch(train) [17][350/586] lr: 5.000000e-04 eta: 15:05:46 time: 0.462638 data_time: 0.024573 memory: 15239 loss_kpt: 0.000680 acc_pose: 0.795707 loss: 0.000680 2022/09/15 16:41:12 - mmengine - INFO - Epoch(train) [17][400/586] lr: 5.000000e-04 eta: 15:05:14 time: 0.465598 data_time: 0.023836 memory: 15239 loss_kpt: 0.000673 acc_pose: 0.850358 loss: 0.000673 2022/09/15 16:41:34 - mmengine - INFO - Epoch(train) [17][450/586] lr: 5.000000e-04 eta: 15:04:37 time: 0.455761 data_time: 0.027830 memory: 15239 loss_kpt: 0.000688 acc_pose: 0.790544 loss: 0.000688 2022/09/15 16:41:58 - mmengine - INFO - Epoch(train) [17][500/586] lr: 5.000000e-04 eta: 15:04:06 time: 0.468403 data_time: 0.026279 memory: 15239 loss_kpt: 0.000697 acc_pose: 0.759883 loss: 0.000697 2022/09/15 16:42:21 - mmengine - INFO - Epoch(train) [17][550/586] lr: 5.000000e-04 eta: 15:03:36 time: 0.467387 data_time: 0.024589 memory: 15239 loss_kpt: 0.000716 acc_pose: 0.737959 loss: 0.000716 2022/09/15 16:42:37 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 16:42:37 - mmengine - INFO - Saving checkpoint at 17 epochs 2022/09/15 16:43:03 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 16:43:08 - mmengine - INFO - Epoch(train) [18][50/586] lr: 5.000000e-04 eta: 14:59:34 time: 0.469769 data_time: 0.031963 memory: 15239 loss_kpt: 0.000685 acc_pose: 0.768969 loss: 0.000685 2022/09/15 16:43:32 - mmengine - INFO - Epoch(train) [18][100/586] lr: 5.000000e-04 eta: 14:59:08 time: 0.472624 data_time: 0.024322 memory: 15239 loss_kpt: 0.000677 acc_pose: 0.738709 loss: 0.000677 2022/09/15 16:43:55 - mmengine - INFO - Epoch(train) [18][150/586] lr: 5.000000e-04 eta: 14:58:35 time: 0.462096 data_time: 0.024931 memory: 15239 loss_kpt: 0.000692 acc_pose: 0.795080 loss: 0.000692 2022/09/15 16:44:18 - mmengine - INFO - Epoch(train) [18][200/586] lr: 5.000000e-04 eta: 14:58:06 time: 0.467251 data_time: 0.025899 memory: 15239 loss_kpt: 0.000691 acc_pose: 0.805517 loss: 0.000691 2022/09/15 16:44:42 - mmengine - INFO - Epoch(train) [18][250/586] lr: 5.000000e-04 eta: 14:57:37 time: 0.468230 data_time: 0.028997 memory: 15239 loss_kpt: 0.000679 acc_pose: 0.785823 loss: 0.000679 2022/09/15 16:45:05 - mmengine - INFO - Epoch(train) [18][300/586] lr: 5.000000e-04 eta: 14:57:07 time: 0.466368 data_time: 0.024892 memory: 15239 loss_kpt: 0.000684 acc_pose: 0.765770 loss: 0.000684 2022/09/15 16:45:28 - mmengine - INFO - Epoch(train) [18][350/586] lr: 5.000000e-04 eta: 14:56:34 time: 0.460237 data_time: 0.025366 memory: 15239 loss_kpt: 0.000687 acc_pose: 0.711358 loss: 0.000687 2022/09/15 16:45:51 - mmengine - INFO - Epoch(train) [18][400/586] lr: 5.000000e-04 eta: 14:56:01 time: 0.461017 data_time: 0.025539 memory: 15239 loss_kpt: 0.000661 acc_pose: 0.811210 loss: 0.000661 2022/09/15 16:46:14 - mmengine - INFO - Epoch(train) [18][450/586] lr: 5.000000e-04 eta: 14:55:31 time: 0.466110 data_time: 0.025641 memory: 15239 loss_kpt: 0.000684 acc_pose: 0.688113 loss: 0.000684 2022/09/15 16:46:38 - mmengine - INFO - Epoch(train) [18][500/586] lr: 5.000000e-04 eta: 14:55:01 time: 0.465144 data_time: 0.024323 memory: 15239 loss_kpt: 0.000699 acc_pose: 0.772685 loss: 0.000699 2022/09/15 16:47:00 - mmengine - INFO - Epoch(train) [18][550/586] lr: 5.000000e-04 eta: 14:54:28 time: 0.459550 data_time: 0.025157 memory: 15239 loss_kpt: 0.000702 acc_pose: 0.759111 loss: 0.000702 2022/09/15 16:47:17 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 16:47:17 - mmengine - INFO - Saving checkpoint at 18 epochs 2022/09/15 16:47:48 - mmengine - INFO - Epoch(train) [19][50/586] lr: 5.000000e-04 eta: 14:50:42 time: 0.471847 data_time: 0.032949 memory: 15239 loss_kpt: 0.000695 acc_pose: 0.814833 loss: 0.000695 2022/09/15 16:48:11 - mmengine - INFO - Epoch(train) [19][100/586] lr: 5.000000e-04 eta: 14:50:15 time: 0.468136 data_time: 0.024448 memory: 15239 loss_kpt: 0.000668 acc_pose: 0.877725 loss: 0.000668 2022/09/15 16:48:35 - mmengine - INFO - Epoch(train) [19][150/586] lr: 5.000000e-04 eta: 14:49:46 time: 0.465831 data_time: 0.025601 memory: 15239 loss_kpt: 0.000657 acc_pose: 0.834619 loss: 0.000657 2022/09/15 16:48:58 - mmengine - INFO - Epoch(train) [19][200/586] lr: 5.000000e-04 eta: 14:49:13 time: 0.457479 data_time: 0.025261 memory: 15239 loss_kpt: 0.000663 acc_pose: 0.801768 loss: 0.000663 2022/09/15 16:49:21 - mmengine - INFO - Epoch(train) [19][250/586] lr: 5.000000e-04 eta: 14:48:45 time: 0.466489 data_time: 0.023928 memory: 15239 loss_kpt: 0.000674 acc_pose: 0.769842 loss: 0.000674 2022/09/15 16:49:44 - mmengine - INFO - Epoch(train) [19][300/586] lr: 5.000000e-04 eta: 14:48:17 time: 0.466788 data_time: 0.025194 memory: 15239 loss_kpt: 0.000680 acc_pose: 0.872399 loss: 0.000680 2022/09/15 16:50:07 - mmengine - INFO - Epoch(train) [19][350/586] lr: 5.000000e-04 eta: 14:47:44 time: 0.458025 data_time: 0.023963 memory: 15239 loss_kpt: 0.000658 acc_pose: 0.911429 loss: 0.000658 2022/09/15 16:50:30 - mmengine - INFO - Epoch(train) [19][400/586] lr: 5.000000e-04 eta: 14:47:15 time: 0.463236 data_time: 0.024139 memory: 15239 loss_kpt: 0.000656 acc_pose: 0.762161 loss: 0.000656 2022/09/15 16:50:54 - mmengine - INFO - Epoch(train) [19][450/586] lr: 5.000000e-04 eta: 14:46:49 time: 0.471571 data_time: 0.025307 memory: 15239 loss_kpt: 0.000659 acc_pose: 0.859079 loss: 0.000659 2022/09/15 16:50:55 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 16:51:17 - mmengine - INFO - Epoch(train) [19][500/586] lr: 5.000000e-04 eta: 14:46:18 time: 0.460257 data_time: 0.025461 memory: 15239 loss_kpt: 0.000676 acc_pose: 0.766763 loss: 0.000676 2022/09/15 16:51:40 - mmengine - INFO - Epoch(train) [19][550/586] lr: 5.000000e-04 eta: 14:45:49 time: 0.463046 data_time: 0.025399 memory: 15239 loss_kpt: 0.000668 acc_pose: 0.763785 loss: 0.000668 2022/09/15 16:51:57 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 16:51:57 - mmengine - INFO - Saving checkpoint at 19 epochs 2022/09/15 16:52:27 - mmengine - INFO - Epoch(train) [20][50/586] lr: 5.000000e-04 eta: 14:42:12 time: 0.465961 data_time: 0.029097 memory: 15239 loss_kpt: 0.000678 acc_pose: 0.795510 loss: 0.000678 2022/09/15 16:52:51 - mmengine - INFO - Epoch(train) [20][100/586] lr: 5.000000e-04 eta: 14:41:45 time: 0.464684 data_time: 0.025060 memory: 15239 loss_kpt: 0.000680 acc_pose: 0.742332 loss: 0.000680 2022/09/15 16:53:14 - mmengine - INFO - Epoch(train) [20][150/586] lr: 5.000000e-04 eta: 14:41:22 time: 0.475730 data_time: 0.029122 memory: 15239 loss_kpt: 0.000690 acc_pose: 0.847370 loss: 0.000690 2022/09/15 16:53:38 - mmengine - INFO - Epoch(train) [20][200/586] lr: 5.000000e-04 eta: 14:40:53 time: 0.462654 data_time: 0.025189 memory: 15239 loss_kpt: 0.000663 acc_pose: 0.725344 loss: 0.000663 2022/09/15 16:54:01 - mmengine - INFO - Epoch(train) [20][250/586] lr: 5.000000e-04 eta: 14:40:27 time: 0.468027 data_time: 0.024545 memory: 15239 loss_kpt: 0.000636 acc_pose: 0.829053 loss: 0.000636 2022/09/15 16:54:24 - mmengine - INFO - Epoch(train) [20][300/586] lr: 5.000000e-04 eta: 14:39:59 time: 0.463384 data_time: 0.024634 memory: 15239 loss_kpt: 0.000679 acc_pose: 0.841920 loss: 0.000679 2022/09/15 16:54:47 - mmengine - INFO - Epoch(train) [20][350/586] lr: 5.000000e-04 eta: 14:39:26 time: 0.453087 data_time: 0.024925 memory: 15239 loss_kpt: 0.000674 acc_pose: 0.766436 loss: 0.000674 2022/09/15 16:55:10 - mmengine - INFO - Epoch(train) [20][400/586] lr: 5.000000e-04 eta: 14:38:56 time: 0.460987 data_time: 0.024511 memory: 15239 loss_kpt: 0.000664 acc_pose: 0.842071 loss: 0.000664 2022/09/15 16:55:33 - mmengine - INFO - Epoch(train) [20][450/586] lr: 5.000000e-04 eta: 14:38:31 time: 0.470413 data_time: 0.025345 memory: 15239 loss_kpt: 0.000675 acc_pose: 0.787437 loss: 0.000675 2022/09/15 16:55:56 - mmengine - INFO - Epoch(train) [20][500/586] lr: 5.000000e-04 eta: 14:37:58 time: 0.453674 data_time: 0.024719 memory: 15239 loss_kpt: 0.000666 acc_pose: 0.838563 loss: 0.000666 2022/09/15 16:56:19 - mmengine - INFO - Epoch(train) [20][550/586] lr: 5.000000e-04 eta: 14:37:31 time: 0.464556 data_time: 0.025271 memory: 15239 loss_kpt: 0.000667 acc_pose: 0.851437 loss: 0.000667 2022/09/15 16:56:36 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 16:56:36 - mmengine - INFO - Saving checkpoint at 20 epochs 2022/09/15 16:56:56 - mmengine - INFO - Epoch(val) [20][50/407] eta: 0:01:31 time: 0.256826 data_time: 0.012798 memory: 15239 2022/09/15 16:57:08 - mmengine - INFO - Epoch(val) [20][100/407] eta: 0:01:17 time: 0.251679 data_time: 0.008738 memory: 2064 2022/09/15 16:57:21 - mmengine - INFO - Epoch(val) [20][150/407] eta: 0:01:04 time: 0.251194 data_time: 0.008179 memory: 2064 2022/09/15 16:57:33 - mmengine - INFO - Epoch(val) [20][200/407] eta: 0:00:51 time: 0.248809 data_time: 0.008040 memory: 2064 2022/09/15 16:57:46 - mmengine - INFO - Epoch(val) [20][250/407] eta: 0:00:39 time: 0.249630 data_time: 0.008392 memory: 2064 2022/09/15 16:57:59 - mmengine - INFO - Epoch(val) [20][300/407] eta: 0:00:27 time: 0.254617 data_time: 0.013258 memory: 2064 2022/09/15 16:58:11 - mmengine - INFO - Epoch(val) [20][350/407] eta: 0:00:14 time: 0.250830 data_time: 0.008212 memory: 2064 2022/09/15 16:58:24 - mmengine - INFO - Epoch(val) [20][400/407] eta: 0:00:01 time: 0.248696 data_time: 0.008096 memory: 2064 2022/09/15 16:58:58 - mmengine - INFO - Evaluating CocoMetric... 2022/09/15 16:59:11 - mmengine - INFO - Epoch(val) [20][407/407] coco/AP: 0.714174 coco/AP .5: 0.884137 coco/AP .75: 0.781376 coco/AP (M): 0.673620 coco/AP (L): 0.786260 coco/AR: 0.767459 coco/AR .5: 0.923016 coco/AR .75: 0.825882 coco/AR (M): 0.722671 coco/AR (L): 0.831921 2022/09/15 16:59:11 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220915/dark_w48_384/best_coco/AP_epoch_10.pth is removed 2022/09/15 16:59:15 - mmengine - INFO - The best checkpoint with 0.7142 coco/AP at 20 epoch is saved to best_coco/AP_epoch_20.pth. 2022/09/15 16:59:38 - mmengine - INFO - Epoch(train) [21][50/586] lr: 5.000000e-04 eta: 14:34:05 time: 0.463499 data_time: 0.028780 memory: 15239 loss_kpt: 0.000670 acc_pose: 0.886571 loss: 0.000670 2022/09/15 17:00:02 - mmengine - INFO - Epoch(train) [21][100/586] lr: 5.000000e-04 eta: 14:33:40 time: 0.469092 data_time: 0.023597 memory: 15239 loss_kpt: 0.000678 acc_pose: 0.772932 loss: 0.000678 2022/09/15 17:00:25 - mmengine - INFO - Epoch(train) [21][150/586] lr: 5.000000e-04 eta: 14:33:15 time: 0.467708 data_time: 0.026230 memory: 15239 loss_kpt: 0.000670 acc_pose: 0.786071 loss: 0.000670 2022/09/15 17:00:48 - mmengine - INFO - Epoch(train) [21][200/586] lr: 5.000000e-04 eta: 14:32:46 time: 0.458563 data_time: 0.024576 memory: 15239 loss_kpt: 0.000660 acc_pose: 0.805575 loss: 0.000660 2022/09/15 17:01:12 - mmengine - INFO - Epoch(train) [21][250/586] lr: 5.000000e-04 eta: 14:32:20 time: 0.466832 data_time: 0.024120 memory: 15239 loss_kpt: 0.000683 acc_pose: 0.843999 loss: 0.000683 2022/09/15 17:01:25 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 17:01:35 - mmengine - INFO - Epoch(train) [21][300/586] lr: 5.000000e-04 eta: 14:31:54 time: 0.465233 data_time: 0.030611 memory: 15239 loss_kpt: 0.000658 acc_pose: 0.810303 loss: 0.000658 2022/09/15 17:01:58 - mmengine - INFO - Epoch(train) [21][350/586] lr: 5.000000e-04 eta: 14:31:25 time: 0.459963 data_time: 0.025150 memory: 15239 loss_kpt: 0.000672 acc_pose: 0.822076 loss: 0.000672 2022/09/15 17:02:22 - mmengine - INFO - Epoch(train) [21][400/586] lr: 5.000000e-04 eta: 14:31:03 time: 0.474806 data_time: 0.024514 memory: 15239 loss_kpt: 0.000651 acc_pose: 0.814232 loss: 0.000651 2022/09/15 17:02:45 - mmengine - INFO - Epoch(train) [21][450/586] lr: 5.000000e-04 eta: 14:30:39 time: 0.469735 data_time: 0.029684 memory: 15239 loss_kpt: 0.000652 acc_pose: 0.779066 loss: 0.000652 2022/09/15 17:03:08 - mmengine - INFO - Epoch(train) [21][500/586] lr: 5.000000e-04 eta: 14:30:15 time: 0.469320 data_time: 0.025510 memory: 15239 loss_kpt: 0.000655 acc_pose: 0.730298 loss: 0.000655 2022/09/15 17:03:32 - mmengine - INFO - Epoch(train) [21][550/586] lr: 5.000000e-04 eta: 14:29:51 time: 0.471003 data_time: 0.024927 memory: 15239 loss_kpt: 0.000664 acc_pose: 0.821035 loss: 0.000664 2022/09/15 17:03:48 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 17:03:49 - mmengine - INFO - Saving checkpoint at 21 epochs 2022/09/15 17:04:19 - mmengine - INFO - Epoch(train) [22][50/586] lr: 5.000000e-04 eta: 14:26:37 time: 0.466725 data_time: 0.032408 memory: 15239 loss_kpt: 0.000678 acc_pose: 0.855651 loss: 0.000678 2022/09/15 17:04:42 - mmengine - INFO - Epoch(train) [22][100/586] lr: 5.000000e-04 eta: 14:26:12 time: 0.467625 data_time: 0.024611 memory: 15239 loss_kpt: 0.000670 acc_pose: 0.758697 loss: 0.000670 2022/09/15 17:05:06 - mmengine - INFO - Epoch(train) [22][150/586] lr: 5.000000e-04 eta: 14:25:46 time: 0.464208 data_time: 0.025642 memory: 15239 loss_kpt: 0.000663 acc_pose: 0.806113 loss: 0.000663 2022/09/15 17:05:29 - mmengine - INFO - Epoch(train) [22][200/586] lr: 5.000000e-04 eta: 14:25:19 time: 0.459651 data_time: 0.024932 memory: 15239 loss_kpt: 0.000669 acc_pose: 0.791122 loss: 0.000669 2022/09/15 17:05:52 - mmengine - INFO - Epoch(train) [22][250/586] lr: 5.000000e-04 eta: 14:24:56 time: 0.472774 data_time: 0.027837 memory: 15239 loss_kpt: 0.000670 acc_pose: 0.757619 loss: 0.000670 2022/09/15 17:06:16 - mmengine - INFO - Epoch(train) [22][300/586] lr: 5.000000e-04 eta: 14:24:33 time: 0.469976 data_time: 0.024874 memory: 15239 loss_kpt: 0.000670 acc_pose: 0.816020 loss: 0.000670 2022/09/15 17:06:39 - mmengine - INFO - Epoch(train) [22][350/586] lr: 5.000000e-04 eta: 14:24:05 time: 0.458599 data_time: 0.024396 memory: 15239 loss_kpt: 0.000659 acc_pose: 0.830495 loss: 0.000659 2022/09/15 17:07:02 - mmengine - INFO - Epoch(train) [22][400/586] lr: 5.000000e-04 eta: 14:23:43 time: 0.472734 data_time: 0.025907 memory: 15239 loss_kpt: 0.000657 acc_pose: 0.787280 loss: 0.000657 2022/09/15 17:07:26 - mmengine - INFO - Epoch(train) [22][450/586] lr: 5.000000e-04 eta: 14:23:18 time: 0.467016 data_time: 0.024967 memory: 15239 loss_kpt: 0.000663 acc_pose: 0.801660 loss: 0.000663 2022/09/15 17:07:49 - mmengine - INFO - Epoch(train) [22][500/586] lr: 5.000000e-04 eta: 14:22:50 time: 0.459695 data_time: 0.023837 memory: 15239 loss_kpt: 0.000671 acc_pose: 0.813912 loss: 0.000671 2022/09/15 17:08:12 - mmengine - INFO - Epoch(train) [22][550/586] lr: 5.000000e-04 eta: 14:22:27 time: 0.469500 data_time: 0.024937 memory: 15239 loss_kpt: 0.000671 acc_pose: 0.871161 loss: 0.000671 2022/09/15 17:08:29 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 17:08:29 - mmengine - INFO - Saving checkpoint at 22 epochs 2022/09/15 17:08:59 - mmengine - INFO - Epoch(train) [23][50/586] lr: 5.000000e-04 eta: 14:19:25 time: 0.475493 data_time: 0.029337 memory: 15239 loss_kpt: 0.000656 acc_pose: 0.856960 loss: 0.000656 2022/09/15 17:09:23 - mmengine - INFO - Epoch(train) [23][100/586] lr: 5.000000e-04 eta: 14:19:00 time: 0.465152 data_time: 0.024373 memory: 15239 loss_kpt: 0.000669 acc_pose: 0.806218 loss: 0.000669 2022/09/15 17:09:26 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 17:09:46 - mmengine - INFO - Epoch(train) [23][150/586] lr: 5.000000e-04 eta: 14:18:36 time: 0.466259 data_time: 0.024043 memory: 15239 loss_kpt: 0.000664 acc_pose: 0.803820 loss: 0.000664 2022/09/15 17:10:09 - mmengine - INFO - Epoch(train) [23][200/586] lr: 5.000000e-04 eta: 14:18:11 time: 0.464667 data_time: 0.024292 memory: 15239 loss_kpt: 0.000642 acc_pose: 0.823536 loss: 0.000642 2022/09/15 17:10:33 - mmengine - INFO - Epoch(train) [23][250/586] lr: 5.000000e-04 eta: 14:17:49 time: 0.471643 data_time: 0.024698 memory: 15239 loss_kpt: 0.000639 acc_pose: 0.838921 loss: 0.000639 2022/09/15 17:10:56 - mmengine - INFO - Epoch(train) [23][300/586] lr: 5.000000e-04 eta: 14:17:25 time: 0.465316 data_time: 0.025367 memory: 15239 loss_kpt: 0.000662 acc_pose: 0.829274 loss: 0.000662 2022/09/15 17:11:19 - mmengine - INFO - Epoch(train) [23][350/586] lr: 5.000000e-04 eta: 14:16:59 time: 0.463543 data_time: 0.024176 memory: 15239 loss_kpt: 0.000649 acc_pose: 0.821522 loss: 0.000649 2022/09/15 17:11:42 - mmengine - INFO - Epoch(train) [23][400/586] lr: 5.000000e-04 eta: 14:16:34 time: 0.463436 data_time: 0.024484 memory: 15239 loss_kpt: 0.000674 acc_pose: 0.813369 loss: 0.000674 2022/09/15 17:12:06 - mmengine - INFO - Epoch(train) [23][450/586] lr: 5.000000e-04 eta: 14:16:10 time: 0.465877 data_time: 0.024517 memory: 15239 loss_kpt: 0.000644 acc_pose: 0.776461 loss: 0.000644 2022/09/15 17:12:29 - mmengine - INFO - Epoch(train) [23][500/586] lr: 5.000000e-04 eta: 14:15:44 time: 0.463936 data_time: 0.024351 memory: 15239 loss_kpt: 0.000652 acc_pose: 0.738998 loss: 0.000652 2022/09/15 17:12:52 - mmengine - INFO - Epoch(train) [23][550/586] lr: 5.000000e-04 eta: 14:15:21 time: 0.467451 data_time: 0.025191 memory: 15239 loss_kpt: 0.000658 acc_pose: 0.742297 loss: 0.000658 2022/09/15 17:13:09 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 17:13:09 - mmengine - INFO - Saving checkpoint at 23 epochs 2022/09/15 17:13:40 - mmengine - INFO - Epoch(train) [24][50/586] lr: 5.000000e-04 eta: 14:12:25 time: 0.470761 data_time: 0.032514 memory: 15239 loss_kpt: 0.000642 acc_pose: 0.821060 loss: 0.000642 2022/09/15 17:14:04 - mmengine - INFO - Epoch(train) [24][100/586] lr: 5.000000e-04 eta: 14:12:07 time: 0.479631 data_time: 0.026427 memory: 15239 loss_kpt: 0.000657 acc_pose: 0.782516 loss: 0.000657 2022/09/15 17:14:27 - mmengine - INFO - Epoch(train) [24][150/586] lr: 5.000000e-04 eta: 14:11:42 time: 0.462342 data_time: 0.023981 memory: 15239 loss_kpt: 0.000649 acc_pose: 0.787713 loss: 0.000649 2022/09/15 17:14:50 - mmengine - INFO - Epoch(train) [24][200/586] lr: 5.000000e-04 eta: 14:11:14 time: 0.457140 data_time: 0.025340 memory: 15239 loss_kpt: 0.000673 acc_pose: 0.915793 loss: 0.000673 2022/09/15 17:15:13 - mmengine - INFO - Epoch(train) [24][250/586] lr: 5.000000e-04 eta: 14:10:50 time: 0.463771 data_time: 0.024904 memory: 15239 loss_kpt: 0.000668 acc_pose: 0.818506 loss: 0.000668 2022/09/15 17:15:36 - mmengine - INFO - Epoch(train) [24][300/586] lr: 5.000000e-04 eta: 14:10:28 time: 0.470371 data_time: 0.024533 memory: 15239 loss_kpt: 0.000668 acc_pose: 0.831348 loss: 0.000668 2022/09/15 17:15:59 - mmengine - INFO - Epoch(train) [24][350/586] lr: 5.000000e-04 eta: 14:10:01 time: 0.458916 data_time: 0.024037 memory: 15239 loss_kpt: 0.000648 acc_pose: 0.805449 loss: 0.000648 2022/09/15 17:16:23 - mmengine - INFO - Epoch(train) [24][400/586] lr: 5.000000e-04 eta: 14:09:38 time: 0.468493 data_time: 0.024789 memory: 15239 loss_kpt: 0.000648 acc_pose: 0.793346 loss: 0.000648 2022/09/15 17:16:46 - mmengine - INFO - Epoch(train) [24][450/586] lr: 5.000000e-04 eta: 14:09:13 time: 0.461063 data_time: 0.023980 memory: 15239 loss_kpt: 0.000650 acc_pose: 0.783680 loss: 0.000650 2022/09/15 17:17:09 - mmengine - INFO - Epoch(train) [24][500/586] lr: 5.000000e-04 eta: 14:08:48 time: 0.463620 data_time: 0.024730 memory: 15239 loss_kpt: 0.000632 acc_pose: 0.793621 loss: 0.000632 2022/09/15 17:17:20 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 17:17:32 - mmengine - INFO - Epoch(train) [24][550/586] lr: 5.000000e-04 eta: 14:08:25 time: 0.467710 data_time: 0.025343 memory: 15239 loss_kpt: 0.000646 acc_pose: 0.869496 loss: 0.000646 2022/09/15 17:17:49 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 17:17:49 - mmengine - INFO - Saving checkpoint at 24 epochs 2022/09/15 17:18:20 - mmengine - INFO - Epoch(train) [25][50/586] lr: 5.000000e-04 eta: 14:05:35 time: 0.467230 data_time: 0.034442 memory: 15239 loss_kpt: 0.000631 acc_pose: 0.769924 loss: 0.000631 2022/09/15 17:18:43 - mmengine - INFO - Epoch(train) [25][100/586] lr: 5.000000e-04 eta: 14:05:11 time: 0.463744 data_time: 0.024064 memory: 15239 loss_kpt: 0.000654 acc_pose: 0.811543 loss: 0.000654 2022/09/15 17:19:06 - mmengine - INFO - Epoch(train) [25][150/586] lr: 5.000000e-04 eta: 14:04:47 time: 0.463007 data_time: 0.024727 memory: 15239 loss_kpt: 0.000649 acc_pose: 0.772780 loss: 0.000649 2022/09/15 17:19:29 - mmengine - INFO - Epoch(train) [25][200/586] lr: 5.000000e-04 eta: 14:04:22 time: 0.461041 data_time: 0.024613 memory: 15239 loss_kpt: 0.000653 acc_pose: 0.842475 loss: 0.000653 2022/09/15 17:19:53 - mmengine - INFO - Epoch(train) [25][250/586] lr: 5.000000e-04 eta: 14:04:00 time: 0.470322 data_time: 0.024674 memory: 15239 loss_kpt: 0.000665 acc_pose: 0.837610 loss: 0.000665 2022/09/15 17:20:16 - mmengine - INFO - Epoch(train) [25][300/586] lr: 5.000000e-04 eta: 14:03:37 time: 0.465416 data_time: 0.025329 memory: 15239 loss_kpt: 0.000638 acc_pose: 0.852175 loss: 0.000638 2022/09/15 17:20:39 - mmengine - INFO - Epoch(train) [25][350/586] lr: 5.000000e-04 eta: 14:03:14 time: 0.466905 data_time: 0.028184 memory: 15239 loss_kpt: 0.000651 acc_pose: 0.796533 loss: 0.000651 2022/09/15 17:21:03 - mmengine - INFO - Epoch(train) [25][400/586] lr: 5.000000e-04 eta: 14:02:51 time: 0.466498 data_time: 0.025187 memory: 15239 loss_kpt: 0.000635 acc_pose: 0.760367 loss: 0.000635 2022/09/15 17:21:26 - mmengine - INFO - Epoch(train) [25][450/586] lr: 5.000000e-04 eta: 14:02:27 time: 0.462980 data_time: 0.025636 memory: 15239 loss_kpt: 0.000655 acc_pose: 0.815513 loss: 0.000655 2022/09/15 17:21:49 - mmengine - INFO - Epoch(train) [25][500/586] lr: 5.000000e-04 eta: 14:02:03 time: 0.462821 data_time: 0.023866 memory: 15239 loss_kpt: 0.000648 acc_pose: 0.822006 loss: 0.000648 2022/09/15 17:22:12 - mmengine - INFO - Epoch(train) [25][550/586] lr: 5.000000e-04 eta: 14:01:38 time: 0.461285 data_time: 0.024411 memory: 15239 loss_kpt: 0.000657 acc_pose: 0.729155 loss: 0.000657 2022/09/15 17:22:28 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 17:22:28 - mmengine - INFO - Saving checkpoint at 25 epochs 2022/09/15 17:22:59 - mmengine - INFO - Epoch(train) [26][50/586] lr: 5.000000e-04 eta: 13:58:56 time: 0.470647 data_time: 0.028185 memory: 15239 loss_kpt: 0.000630 acc_pose: 0.789622 loss: 0.000630 2022/09/15 17:23:23 - mmengine - INFO - Epoch(train) [26][100/586] lr: 5.000000e-04 eta: 13:58:36 time: 0.472288 data_time: 0.025266 memory: 15239 loss_kpt: 0.000631 acc_pose: 0.843943 loss: 0.000631 2022/09/15 17:23:46 - mmengine - INFO - Epoch(train) [26][150/586] lr: 5.000000e-04 eta: 13:58:09 time: 0.455944 data_time: 0.024407 memory: 15239 loss_kpt: 0.000646 acc_pose: 0.760463 loss: 0.000646 2022/09/15 17:24:09 - mmengine - INFO - Epoch(train) [26][200/586] lr: 5.000000e-04 eta: 13:57:45 time: 0.462216 data_time: 0.026008 memory: 15239 loss_kpt: 0.000652 acc_pose: 0.791697 loss: 0.000652 2022/09/15 17:24:32 - mmengine - INFO - Epoch(train) [26][250/586] lr: 5.000000e-04 eta: 13:57:23 time: 0.467494 data_time: 0.025228 memory: 15239 loss_kpt: 0.000649 acc_pose: 0.791882 loss: 0.000649 2022/09/15 17:24:55 - mmengine - INFO - Epoch(train) [26][300/586] lr: 5.000000e-04 eta: 13:56:58 time: 0.459641 data_time: 0.025030 memory: 15239 loss_kpt: 0.000639 acc_pose: 0.855073 loss: 0.000639 2022/09/15 17:25:18 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 17:25:18 - mmengine - INFO - Epoch(train) [26][350/586] lr: 5.000000e-04 eta: 13:56:34 time: 0.462124 data_time: 0.024744 memory: 15239 loss_kpt: 0.000637 acc_pose: 0.818646 loss: 0.000637 2022/09/15 17:25:41 - mmengine - INFO - Epoch(train) [26][400/586] lr: 5.000000e-04 eta: 13:56:11 time: 0.466535 data_time: 0.025040 memory: 15239 loss_kpt: 0.000672 acc_pose: 0.852008 loss: 0.000672 2022/09/15 17:26:04 - mmengine - INFO - Epoch(train) [26][450/586] lr: 5.000000e-04 eta: 13:55:46 time: 0.458628 data_time: 0.027894 memory: 15239 loss_kpt: 0.000667 acc_pose: 0.839626 loss: 0.000667 2022/09/15 17:26:27 - mmengine - INFO - Epoch(train) [26][500/586] lr: 5.000000e-04 eta: 13:55:21 time: 0.459541 data_time: 0.025086 memory: 15239 loss_kpt: 0.000641 acc_pose: 0.887556 loss: 0.000641 2022/09/15 17:26:51 - mmengine - INFO - Epoch(train) [26][550/586] lr: 5.000000e-04 eta: 13:54:59 time: 0.468143 data_time: 0.025332 memory: 15239 loss_kpt: 0.000643 acc_pose: 0.819911 loss: 0.000643 2022/09/15 17:27:08 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 17:27:08 - mmengine - INFO - Saving checkpoint at 26 epochs 2022/09/15 17:27:38 - mmengine - INFO - Epoch(train) [27][50/586] lr: 5.000000e-04 eta: 13:52:22 time: 0.467622 data_time: 0.032604 memory: 15239 loss_kpt: 0.000650 acc_pose: 0.788509 loss: 0.000650 2022/09/15 17:28:02 - mmengine - INFO - Epoch(train) [27][100/586] lr: 5.000000e-04 eta: 13:52:03 time: 0.474894 data_time: 0.030077 memory: 15239 loss_kpt: 0.000664 acc_pose: 0.757312 loss: 0.000664 2022/09/15 17:28:25 - mmengine - INFO - Epoch(train) [27][150/586] lr: 5.000000e-04 eta: 13:51:41 time: 0.464778 data_time: 0.025708 memory: 15239 loss_kpt: 0.000638 acc_pose: 0.862135 loss: 0.000638 2022/09/15 17:28:48 - mmengine - INFO - Epoch(train) [27][200/586] lr: 5.000000e-04 eta: 13:51:17 time: 0.463060 data_time: 0.024102 memory: 15239 loss_kpt: 0.000635 acc_pose: 0.832509 loss: 0.000635 2022/09/15 17:29:12 - mmengine - INFO - Epoch(train) [27][250/586] lr: 5.000000e-04 eta: 13:50:56 time: 0.469593 data_time: 0.029451 memory: 15239 loss_kpt: 0.000654 acc_pose: 0.829254 loss: 0.000654 2022/09/15 17:29:35 - mmengine - INFO - Epoch(train) [27][300/586] lr: 5.000000e-04 eta: 13:50:32 time: 0.461273 data_time: 0.024728 memory: 15239 loss_kpt: 0.000648 acc_pose: 0.829461 loss: 0.000648 2022/09/15 17:29:58 - mmengine - INFO - Epoch(train) [27][350/586] lr: 5.000000e-04 eta: 13:50:08 time: 0.461165 data_time: 0.024946 memory: 15239 loss_kpt: 0.000652 acc_pose: 0.767917 loss: 0.000652 2022/09/15 17:30:21 - mmengine - INFO - Epoch(train) [27][400/586] lr: 5.000000e-04 eta: 13:49:47 time: 0.468330 data_time: 0.024841 memory: 15239 loss_kpt: 0.000661 acc_pose: 0.741396 loss: 0.000661 2022/09/15 17:30:44 - mmengine - INFO - Epoch(train) [27][450/586] lr: 5.000000e-04 eta: 13:49:22 time: 0.457436 data_time: 0.025224 memory: 15239 loss_kpt: 0.000652 acc_pose: 0.818222 loss: 0.000652 2022/09/15 17:31:07 - mmengine - INFO - Epoch(train) [27][500/586] lr: 5.000000e-04 eta: 13:48:59 time: 0.463759 data_time: 0.024909 memory: 15239 loss_kpt: 0.000644 acc_pose: 0.819023 loss: 0.000644 2022/09/15 17:31:30 - mmengine - INFO - Epoch(train) [27][550/586] lr: 5.000000e-04 eta: 13:48:36 time: 0.466071 data_time: 0.024347 memory: 15239 loss_kpt: 0.000654 acc_pose: 0.884282 loss: 0.000654 2022/09/15 17:31:47 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 17:31:47 - mmengine - INFO - Saving checkpoint at 27 epochs 2022/09/15 17:32:18 - mmengine - INFO - Epoch(train) [28][50/586] lr: 5.000000e-04 eta: 13:46:07 time: 0.474392 data_time: 0.032375 memory: 15239 loss_kpt: 0.000637 acc_pose: 0.752818 loss: 0.000637 2022/09/15 17:32:41 - mmengine - INFO - Epoch(train) [28][100/586] lr: 5.000000e-04 eta: 13:45:46 time: 0.466768 data_time: 0.023848 memory: 15239 loss_kpt: 0.000627 acc_pose: 0.797998 loss: 0.000627 2022/09/15 17:33:04 - mmengine - INFO - Epoch(train) [28][150/586] lr: 5.000000e-04 eta: 13:45:23 time: 0.464534 data_time: 0.024358 memory: 15239 loss_kpt: 0.000625 acc_pose: 0.779618 loss: 0.000625 2022/09/15 17:33:17 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 17:33:28 - mmengine - INFO - Epoch(train) [28][200/586] lr: 5.000000e-04 eta: 13:45:02 time: 0.466865 data_time: 0.024949 memory: 15239 loss_kpt: 0.000622 acc_pose: 0.862834 loss: 0.000622 2022/09/15 17:33:51 - mmengine - INFO - Epoch(train) [28][250/586] lr: 5.000000e-04 eta: 13:44:41 time: 0.469485 data_time: 0.024149 memory: 15239 loss_kpt: 0.000641 acc_pose: 0.882084 loss: 0.000641 2022/09/15 17:34:15 - mmengine - INFO - Epoch(train) [28][300/586] lr: 5.000000e-04 eta: 13:44:20 time: 0.468193 data_time: 0.024639 memory: 15239 loss_kpt: 0.000645 acc_pose: 0.811564 loss: 0.000645 2022/09/15 17:34:38 - mmengine - INFO - Epoch(train) [28][350/586] lr: 5.000000e-04 eta: 13:43:58 time: 0.465822 data_time: 0.025078 memory: 15239 loss_kpt: 0.000614 acc_pose: 0.852768 loss: 0.000614 2022/09/15 17:35:01 - mmengine - INFO - Epoch(train) [28][400/586] lr: 5.000000e-04 eta: 13:43:37 time: 0.468943 data_time: 0.025026 memory: 15239 loss_kpt: 0.000634 acc_pose: 0.860666 loss: 0.000634 2022/09/15 17:35:25 - mmengine - INFO - Epoch(train) [28][450/586] lr: 5.000000e-04 eta: 13:43:15 time: 0.466597 data_time: 0.025121 memory: 15239 loss_kpt: 0.000636 acc_pose: 0.722581 loss: 0.000636 2022/09/15 17:35:48 - mmengine - INFO - Epoch(train) [28][500/586] lr: 5.000000e-04 eta: 13:42:53 time: 0.465436 data_time: 0.027789 memory: 15239 loss_kpt: 0.000646 acc_pose: 0.789441 loss: 0.000646 2022/09/15 17:36:11 - mmengine - INFO - Epoch(train) [28][550/586] lr: 5.000000e-04 eta: 13:42:32 time: 0.471069 data_time: 0.025576 memory: 15239 loss_kpt: 0.000630 acc_pose: 0.867001 loss: 0.000630 2022/09/15 17:36:28 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 17:36:28 - mmengine - INFO - Saving checkpoint at 28 epochs 2022/09/15 17:36:59 - mmengine - INFO - Epoch(train) [29][50/586] lr: 5.000000e-04 eta: 13:40:10 time: 0.480462 data_time: 0.029049 memory: 15239 loss_kpt: 0.000638 acc_pose: 0.766713 loss: 0.000638 2022/09/15 17:37:22 - mmengine - INFO - Epoch(train) [29][100/586] lr: 5.000000e-04 eta: 13:39:49 time: 0.467691 data_time: 0.023502 memory: 15239 loss_kpt: 0.000626 acc_pose: 0.855804 loss: 0.000626 2022/09/15 17:37:45 - mmengine - INFO - Epoch(train) [29][150/586] lr: 5.000000e-04 eta: 13:39:24 time: 0.455496 data_time: 0.025080 memory: 15239 loss_kpt: 0.000636 acc_pose: 0.883107 loss: 0.000636 2022/09/15 17:38:08 - mmengine - INFO - Epoch(train) [29][200/586] lr: 5.000000e-04 eta: 13:39:02 time: 0.464892 data_time: 0.025742 memory: 15239 loss_kpt: 0.000627 acc_pose: 0.848754 loss: 0.000627 2022/09/15 17:38:32 - mmengine - INFO - Epoch(train) [29][250/586] lr: 5.000000e-04 eta: 13:38:43 time: 0.474429 data_time: 0.028051 memory: 15239 loss_kpt: 0.000632 acc_pose: 0.804520 loss: 0.000632 2022/09/15 17:38:56 - mmengine - INFO - Epoch(train) [29][300/586] lr: 5.000000e-04 eta: 13:38:25 time: 0.477108 data_time: 0.025666 memory: 15239 loss_kpt: 0.000614 acc_pose: 0.822999 loss: 0.000614 2022/09/15 17:39:19 - mmengine - INFO - Epoch(train) [29][350/586] lr: 5.000000e-04 eta: 13:38:03 time: 0.466541 data_time: 0.025006 memory: 15239 loss_kpt: 0.000654 acc_pose: 0.778759 loss: 0.000654 2022/09/15 17:39:42 - mmengine - INFO - Epoch(train) [29][400/586] lr: 5.000000e-04 eta: 13:37:40 time: 0.461216 data_time: 0.024388 memory: 15239 loss_kpt: 0.000626 acc_pose: 0.833643 loss: 0.000626 2022/09/15 17:40:05 - mmengine - INFO - Epoch(train) [29][450/586] lr: 5.000000e-04 eta: 13:37:18 time: 0.463590 data_time: 0.024230 memory: 15239 loss_kpt: 0.000637 acc_pose: 0.786303 loss: 0.000637 2022/09/15 17:40:29 - mmengine - INFO - Epoch(train) [29][500/586] lr: 5.000000e-04 eta: 13:36:56 time: 0.466665 data_time: 0.024907 memory: 15239 loss_kpt: 0.000632 acc_pose: 0.824184 loss: 0.000632 2022/09/15 17:40:52 - mmengine - INFO - Epoch(train) [29][550/586] lr: 5.000000e-04 eta: 13:36:34 time: 0.463804 data_time: 0.024247 memory: 15239 loss_kpt: 0.000655 acc_pose: 0.800912 loss: 0.000655 2022/09/15 17:41:09 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 17:41:09 - mmengine - INFO - Saving checkpoint at 29 epochs 2022/09/15 17:41:19 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 17:41:39 - mmengine - INFO - Epoch(train) [30][50/586] lr: 5.000000e-04 eta: 13:34:15 time: 0.476109 data_time: 0.030039 memory: 15239 loss_kpt: 0.000659 acc_pose: 0.817238 loss: 0.000659 2022/09/15 17:42:03 - mmengine - INFO - Epoch(train) [30][100/586] lr: 5.000000e-04 eta: 13:33:54 time: 0.467732 data_time: 0.025038 memory: 15239 loss_kpt: 0.000631 acc_pose: 0.847176 loss: 0.000631 2022/09/15 17:42:26 - mmengine - INFO - Epoch(train) [30][150/586] lr: 5.000000e-04 eta: 13:33:30 time: 0.458163 data_time: 0.023608 memory: 15239 loss_kpt: 0.000639 acc_pose: 0.826284 loss: 0.000639 2022/09/15 17:42:50 - mmengine - INFO - Epoch(train) [30][200/586] lr: 5.000000e-04 eta: 13:33:13 time: 0.479166 data_time: 0.025987 memory: 15239 loss_kpt: 0.000636 acc_pose: 0.863014 loss: 0.000636 2022/09/15 17:43:13 - mmengine - INFO - Epoch(train) [30][250/586] lr: 5.000000e-04 eta: 13:32:50 time: 0.461405 data_time: 0.024543 memory: 15239 loss_kpt: 0.000647 acc_pose: 0.784082 loss: 0.000647 2022/09/15 17:43:36 - mmengine - INFO - Epoch(train) [30][300/586] lr: 5.000000e-04 eta: 13:32:28 time: 0.463154 data_time: 0.025212 memory: 15239 loss_kpt: 0.000648 acc_pose: 0.736853 loss: 0.000648 2022/09/15 17:43:59 - mmengine - INFO - Epoch(train) [30][350/586] lr: 5.000000e-04 eta: 13:32:07 time: 0.468400 data_time: 0.028312 memory: 15239 loss_kpt: 0.000643 acc_pose: 0.878628 loss: 0.000643 2022/09/15 17:44:23 - mmengine - INFO - Epoch(train) [30][400/586] lr: 5.000000e-04 eta: 13:31:45 time: 0.463921 data_time: 0.024889 memory: 15239 loss_kpt: 0.000620 acc_pose: 0.797607 loss: 0.000620 2022/09/15 17:44:45 - mmengine - INFO - Epoch(train) [30][450/586] lr: 5.000000e-04 eta: 13:31:21 time: 0.457490 data_time: 0.024724 memory: 15239 loss_kpt: 0.000620 acc_pose: 0.828350 loss: 0.000620 2022/09/15 17:45:09 - mmengine - INFO - Epoch(train) [30][500/586] lr: 5.000000e-04 eta: 13:31:02 time: 0.475088 data_time: 0.025435 memory: 15239 loss_kpt: 0.000652 acc_pose: 0.812684 loss: 0.000652 2022/09/15 17:45:32 - mmengine - INFO - Epoch(train) [30][550/586] lr: 5.000000e-04 eta: 13:30:39 time: 0.461633 data_time: 0.024270 memory: 15239 loss_kpt: 0.000628 acc_pose: 0.793228 loss: 0.000628 2022/09/15 17:45:49 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 17:45:49 - mmengine - INFO - Saving checkpoint at 30 epochs 2022/09/15 17:46:09 - mmengine - INFO - Epoch(val) [30][50/407] eta: 0:01:31 time: 0.256361 data_time: 0.013532 memory: 15239 2022/09/15 17:46:22 - mmengine - INFO - Epoch(val) [30][100/407] eta: 0:01:17 time: 0.251973 data_time: 0.008289 memory: 2064 2022/09/15 17:46:34 - mmengine - INFO - Epoch(val) [30][150/407] eta: 0:01:04 time: 0.251146 data_time: 0.008428 memory: 2064 2022/09/15 17:46:47 - mmengine - INFO - Epoch(val) [30][200/407] eta: 0:00:51 time: 0.250189 data_time: 0.008356 memory: 2064 2022/09/15 17:47:00 - mmengine - INFO - Epoch(val) [30][250/407] eta: 0:00:39 time: 0.249416 data_time: 0.008118 memory: 2064 2022/09/15 17:47:12 - mmengine - INFO - Epoch(val) [30][300/407] eta: 0:00:26 time: 0.250997 data_time: 0.009586 memory: 2064 2022/09/15 17:47:24 - mmengine - INFO - Epoch(val) [30][350/407] eta: 0:00:14 time: 0.248989 data_time: 0.008290 memory: 2064 2022/09/15 17:47:37 - mmengine - INFO - Epoch(val) [30][400/407] eta: 0:00:01 time: 0.247742 data_time: 0.008659 memory: 2064 2022/09/15 17:48:11 - mmengine - INFO - Evaluating CocoMetric... 2022/09/15 17:48:24 - mmengine - INFO - Epoch(val) [30][407/407] coco/AP: 0.735175 coco/AP .5: 0.896248 coco/AP .75: 0.802848 coco/AP (M): 0.698115 coco/AP (L): 0.801908 coco/AR: 0.785249 coco/AR .5: 0.932777 coco/AR .75: 0.845403 coco/AR (M): 0.743321 coco/AR (L): 0.846042 2022/09/15 17:48:24 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220915/dark_w48_384/best_coco/AP_epoch_20.pth is removed 2022/09/15 17:48:28 - mmengine - INFO - The best checkpoint with 0.7352 coco/AP at 30 epoch is saved to best_coco/AP_epoch_30.pth. 2022/09/15 17:48:52 - mmengine - INFO - Epoch(train) [31][50/586] lr: 5.000000e-04 eta: 13:28:22 time: 0.468065 data_time: 0.028308 memory: 15239 loss_kpt: 0.000630 acc_pose: 0.785740 loss: 0.000630 2022/09/15 17:49:15 - mmengine - INFO - Epoch(train) [31][100/586] lr: 5.000000e-04 eta: 13:28:03 time: 0.473400 data_time: 0.025662 memory: 15239 loss_kpt: 0.000617 acc_pose: 0.770674 loss: 0.000617 2022/09/15 17:49:39 - mmengine - INFO - Epoch(train) [31][150/586] lr: 5.000000e-04 eta: 13:27:45 time: 0.475420 data_time: 0.024644 memory: 15239 loss_kpt: 0.000626 acc_pose: 0.812386 loss: 0.000626 2022/09/15 17:50:02 - mmengine - INFO - Epoch(train) [31][200/586] lr: 5.000000e-04 eta: 13:27:23 time: 0.464170 data_time: 0.024533 memory: 15239 loss_kpt: 0.000628 acc_pose: 0.902505 loss: 0.000628 2022/09/15 17:50:26 - mmengine - INFO - Epoch(train) [31][250/586] lr: 5.000000e-04 eta: 13:27:02 time: 0.466806 data_time: 0.026447 memory: 15239 loss_kpt: 0.000626 acc_pose: 0.775723 loss: 0.000626 2022/09/15 17:50:49 - mmengine - INFO - Epoch(train) [31][300/586] lr: 5.000000e-04 eta: 13:26:42 time: 0.471890 data_time: 0.030744 memory: 15239 loss_kpt: 0.000637 acc_pose: 0.862322 loss: 0.000637 2022/09/15 17:51:13 - mmengine - INFO - Epoch(train) [31][350/586] lr: 5.000000e-04 eta: 13:26:23 time: 0.473477 data_time: 0.025807 memory: 15239 loss_kpt: 0.000618 acc_pose: 0.778980 loss: 0.000618 2022/09/15 17:51:36 - mmengine - INFO - Epoch(train) [31][400/586] lr: 5.000000e-04 eta: 13:26:00 time: 0.459459 data_time: 0.025093 memory: 15239 loss_kpt: 0.000601 acc_pose: 0.807922 loss: 0.000601 2022/09/15 17:51:45 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 17:51:59 - mmengine - INFO - Epoch(train) [31][450/586] lr: 5.000000e-04 eta: 13:25:37 time: 0.460114 data_time: 0.028301 memory: 15239 loss_kpt: 0.000640 acc_pose: 0.822881 loss: 0.000640 2022/09/15 17:52:22 - mmengine - INFO - Epoch(train) [31][500/586] lr: 5.000000e-04 eta: 13:25:16 time: 0.466194 data_time: 0.024677 memory: 15239 loss_kpt: 0.000637 acc_pose: 0.806198 loss: 0.000637 2022/09/15 17:52:45 - mmengine - INFO - Epoch(train) [31][550/586] lr: 5.000000e-04 eta: 13:24:52 time: 0.456777 data_time: 0.024419 memory: 15239 loss_kpt: 0.000643 acc_pose: 0.789036 loss: 0.000643 2022/09/15 17:53:02 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 17:53:02 - mmengine - INFO - Saving checkpoint at 31 epochs 2022/09/15 17:53:33 - mmengine - INFO - Epoch(train) [32][50/586] lr: 5.000000e-04 eta: 13:22:42 time: 0.477794 data_time: 0.033086 memory: 15239 loss_kpt: 0.000649 acc_pose: 0.774652 loss: 0.000649 2022/09/15 17:53:56 - mmengine - INFO - Epoch(train) [32][100/586] lr: 5.000000e-04 eta: 13:22:20 time: 0.464095 data_time: 0.025132 memory: 15239 loss_kpt: 0.000649 acc_pose: 0.853796 loss: 0.000649 2022/09/15 17:54:19 - mmengine - INFO - Epoch(train) [32][150/586] lr: 5.000000e-04 eta: 13:21:59 time: 0.464534 data_time: 0.024296 memory: 15239 loss_kpt: 0.000635 acc_pose: 0.841104 loss: 0.000635 2022/09/15 17:54:43 - mmengine - INFO - Epoch(train) [32][200/586] lr: 5.000000e-04 eta: 13:21:39 time: 0.471102 data_time: 0.029361 memory: 15239 loss_kpt: 0.000624 acc_pose: 0.837258 loss: 0.000624 2022/09/15 17:55:06 - mmengine - INFO - Epoch(train) [32][250/586] lr: 5.000000e-04 eta: 13:21:19 time: 0.470005 data_time: 0.024998 memory: 15239 loss_kpt: 0.000621 acc_pose: 0.742873 loss: 0.000621 2022/09/15 17:55:29 - mmengine - INFO - Epoch(train) [32][300/586] lr: 5.000000e-04 eta: 13:20:57 time: 0.462074 data_time: 0.024314 memory: 15239 loss_kpt: 0.000633 acc_pose: 0.754372 loss: 0.000633 2022/09/15 17:55:54 - mmengine - INFO - Epoch(train) [32][350/586] lr: 5.000000e-04 eta: 13:20:40 time: 0.481615 data_time: 0.030171 memory: 15239 loss_kpt: 0.000633 acc_pose: 0.744914 loss: 0.000633 2022/09/15 17:56:17 - mmengine - INFO - Epoch(train) [32][400/586] lr: 5.000000e-04 eta: 13:20:19 time: 0.467811 data_time: 0.024731 memory: 15239 loss_kpt: 0.000619 acc_pose: 0.866078 loss: 0.000619 2022/09/15 17:56:40 - mmengine - INFO - Epoch(train) [32][450/586] lr: 5.000000e-04 eta: 13:19:58 time: 0.463930 data_time: 0.024676 memory: 15239 loss_kpt: 0.000632 acc_pose: 0.789339 loss: 0.000632 2022/09/15 17:57:04 - mmengine - INFO - Epoch(train) [32][500/586] lr: 5.000000e-04 eta: 13:19:37 time: 0.467354 data_time: 0.025400 memory: 15239 loss_kpt: 0.000614 acc_pose: 0.753766 loss: 0.000614 2022/09/15 17:57:26 - mmengine - INFO - Epoch(train) [32][550/586] lr: 5.000000e-04 eta: 13:19:14 time: 0.458154 data_time: 0.024631 memory: 15239 loss_kpt: 0.000621 acc_pose: 0.828273 loss: 0.000621 2022/09/15 17:57:43 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 17:57:43 - mmengine - INFO - Saving checkpoint at 32 epochs 2022/09/15 17:58:13 - mmengine - INFO - Epoch(train) [33][50/586] lr: 5.000000e-04 eta: 13:17:05 time: 0.468303 data_time: 0.028701 memory: 15239 loss_kpt: 0.000635 acc_pose: 0.874148 loss: 0.000635 2022/09/15 17:58:36 - mmengine - INFO - Epoch(train) [33][100/586] lr: 5.000000e-04 eta: 13:16:43 time: 0.462251 data_time: 0.025491 memory: 15239 loss_kpt: 0.000626 acc_pose: 0.815705 loss: 0.000626 2022/09/15 17:59:00 - mmengine - INFO - Epoch(train) [33][150/586] lr: 5.000000e-04 eta: 13:16:23 time: 0.470277 data_time: 0.028469 memory: 15239 loss_kpt: 0.000618 acc_pose: 0.896693 loss: 0.000618 2022/09/15 17:59:23 - mmengine - INFO - Epoch(train) [33][200/586] lr: 5.000000e-04 eta: 13:16:03 time: 0.467835 data_time: 0.024567 memory: 15239 loss_kpt: 0.000622 acc_pose: 0.819889 loss: 0.000622 2022/09/15 17:59:45 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 17:59:46 - mmengine - INFO - Epoch(train) [33][250/586] lr: 5.000000e-04 eta: 13:15:38 time: 0.453980 data_time: 0.025271 memory: 15239 loss_kpt: 0.000623 acc_pose: 0.852863 loss: 0.000623 2022/09/15 18:00:12 - mmengine - INFO - Epoch(train) [33][300/586] lr: 5.000000e-04 eta: 13:15:33 time: 0.522763 data_time: 0.034939 memory: 15239 loss_kpt: 0.000634 acc_pose: 0.810786 loss: 0.000634 2022/09/15 18:00:36 - mmengine - INFO - Epoch(train) [33][350/586] lr: 5.000000e-04 eta: 13:15:13 time: 0.470444 data_time: 0.026304 memory: 15239 loss_kpt: 0.000629 acc_pose: 0.831982 loss: 0.000629 2022/09/15 18:00:59 - mmengine - INFO - Epoch(train) [33][400/586] lr: 5.000000e-04 eta: 13:14:50 time: 0.459777 data_time: 0.024736 memory: 15239 loss_kpt: 0.000624 acc_pose: 0.817088 loss: 0.000624 2022/09/15 18:01:22 - mmengine - INFO - Epoch(train) [33][450/586] lr: 5.000000e-04 eta: 13:14:29 time: 0.466088 data_time: 0.024322 memory: 15239 loss_kpt: 0.000622 acc_pose: 0.849879 loss: 0.000622 2022/09/15 18:01:45 - mmengine - INFO - Epoch(train) [33][500/586] lr: 5.000000e-04 eta: 13:14:08 time: 0.465370 data_time: 0.025500 memory: 15239 loss_kpt: 0.000630 acc_pose: 0.838403 loss: 0.000630 2022/09/15 18:02:08 - mmengine - INFO - Epoch(train) [33][550/586] lr: 5.000000e-04 eta: 13:13:45 time: 0.460393 data_time: 0.024016 memory: 15239 loss_kpt: 0.000635 acc_pose: 0.799372 loss: 0.000635 2022/09/15 18:02:25 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 18:02:25 - mmengine - INFO - Saving checkpoint at 33 epochs 2022/09/15 18:02:56 - mmengine - INFO - Epoch(train) [34][50/586] lr: 5.000000e-04 eta: 13:11:42 time: 0.474839 data_time: 0.029539 memory: 15239 loss_kpt: 0.000638 acc_pose: 0.792896 loss: 0.000638 2022/09/15 18:03:18 - mmengine - INFO - Epoch(train) [34][100/586] lr: 5.000000e-04 eta: 13:11:19 time: 0.456622 data_time: 0.025389 memory: 15239 loss_kpt: 0.000609 acc_pose: 0.854383 loss: 0.000609 2022/09/15 18:03:42 - mmengine - INFO - Epoch(train) [34][150/586] lr: 5.000000e-04 eta: 13:10:57 time: 0.463455 data_time: 0.024081 memory: 15239 loss_kpt: 0.000612 acc_pose: 0.827801 loss: 0.000612 2022/09/15 18:04:05 - mmengine - INFO - Epoch(train) [34][200/586] lr: 5.000000e-04 eta: 13:10:36 time: 0.466522 data_time: 0.025597 memory: 15239 loss_kpt: 0.000635 acc_pose: 0.851657 loss: 0.000635 2022/09/15 18:04:28 - mmengine - INFO - Epoch(train) [34][250/586] lr: 5.000000e-04 eta: 13:10:14 time: 0.458887 data_time: 0.024143 memory: 15239 loss_kpt: 0.000623 acc_pose: 0.815720 loss: 0.000623 2022/09/15 18:04:51 - mmengine - INFO - Epoch(train) [34][300/586] lr: 5.000000e-04 eta: 13:09:53 time: 0.466911 data_time: 0.023846 memory: 15239 loss_kpt: 0.000621 acc_pose: 0.858623 loss: 0.000621 2022/09/15 18:05:15 - mmengine - INFO - Epoch(train) [34][350/586] lr: 5.000000e-04 eta: 13:09:35 time: 0.476316 data_time: 0.030281 memory: 15239 loss_kpt: 0.000631 acc_pose: 0.807489 loss: 0.000631 2022/09/15 18:05:38 - mmengine - INFO - Epoch(train) [34][400/586] lr: 5.000000e-04 eta: 13:09:11 time: 0.456475 data_time: 0.025756 memory: 15239 loss_kpt: 0.000608 acc_pose: 0.780627 loss: 0.000608 2022/09/15 18:06:01 - mmengine - INFO - Epoch(train) [34][450/586] lr: 5.000000e-04 eta: 13:08:51 time: 0.466844 data_time: 0.024016 memory: 15239 loss_kpt: 0.000613 acc_pose: 0.862042 loss: 0.000613 2022/09/15 18:06:24 - mmengine - INFO - Epoch(train) [34][500/586] lr: 5.000000e-04 eta: 13:08:29 time: 0.462813 data_time: 0.024458 memory: 15239 loss_kpt: 0.000621 acc_pose: 0.831735 loss: 0.000621 2022/09/15 18:06:48 - mmengine - INFO - Epoch(train) [34][550/586] lr: 5.000000e-04 eta: 13:08:08 time: 0.464163 data_time: 0.025668 memory: 15239 loss_kpt: 0.000589 acc_pose: 0.841574 loss: 0.000589 2022/09/15 18:07:04 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 18:07:04 - mmengine - INFO - Saving checkpoint at 34 epochs 2022/09/15 18:07:35 - mmengine - INFO - Epoch(train) [35][50/586] lr: 5.000000e-04 eta: 13:06:08 time: 0.478455 data_time: 0.030342 memory: 15239 loss_kpt: 0.000632 acc_pose: 0.847306 loss: 0.000632 2022/09/15 18:07:47 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 18:07:58 - mmengine - INFO - Epoch(train) [35][100/586] lr: 5.000000e-04 eta: 13:05:46 time: 0.461574 data_time: 0.024679 memory: 15239 loss_kpt: 0.000603 acc_pose: 0.829286 loss: 0.000603 2022/09/15 18:08:21 - mmengine - INFO - Epoch(train) [35][150/586] lr: 5.000000e-04 eta: 13:05:25 time: 0.464981 data_time: 0.025491 memory: 15239 loss_kpt: 0.000629 acc_pose: 0.854542 loss: 0.000629 2022/09/15 18:08:45 - mmengine - INFO - Epoch(train) [35][200/586] lr: 5.000000e-04 eta: 13:05:04 time: 0.463479 data_time: 0.024991 memory: 15239 loss_kpt: 0.000622 acc_pose: 0.767678 loss: 0.000622 2022/09/15 18:09:08 - mmengine - INFO - Epoch(train) [35][250/586] lr: 5.000000e-04 eta: 13:04:42 time: 0.462084 data_time: 0.024689 memory: 15239 loss_kpt: 0.000629 acc_pose: 0.770967 loss: 0.000629 2022/09/15 18:09:31 - mmengine - INFO - Epoch(train) [35][300/586] lr: 5.000000e-04 eta: 13:04:22 time: 0.466183 data_time: 0.028702 memory: 15239 loss_kpt: 0.000613 acc_pose: 0.789728 loss: 0.000613 2022/09/15 18:09:54 - mmengine - INFO - Epoch(train) [35][350/586] lr: 5.000000e-04 eta: 13:04:01 time: 0.468740 data_time: 0.024506 memory: 15239 loss_kpt: 0.000626 acc_pose: 0.763071 loss: 0.000626 2022/09/15 18:10:17 - mmengine - INFO - Epoch(train) [35][400/586] lr: 5.000000e-04 eta: 13:03:38 time: 0.456747 data_time: 0.026075 memory: 15239 loss_kpt: 0.000591 acc_pose: 0.820349 loss: 0.000591 2022/09/15 18:10:41 - mmengine - INFO - Epoch(train) [35][450/586] lr: 5.000000e-04 eta: 13:03:18 time: 0.469339 data_time: 0.025636 memory: 15239 loss_kpt: 0.000619 acc_pose: 0.814609 loss: 0.000619 2022/09/15 18:11:04 - mmengine - INFO - Epoch(train) [35][500/586] lr: 5.000000e-04 eta: 13:02:57 time: 0.465193 data_time: 0.024649 memory: 15239 loss_kpt: 0.000646 acc_pose: 0.835311 loss: 0.000646 2022/09/15 18:11:27 - mmengine - INFO - Epoch(train) [35][550/586] lr: 5.000000e-04 eta: 13:02:35 time: 0.460397 data_time: 0.024205 memory: 15239 loss_kpt: 0.000609 acc_pose: 0.792242 loss: 0.000609 2022/09/15 18:11:43 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 18:11:43 - mmengine - INFO - Saving checkpoint at 35 epochs 2022/09/15 18:12:15 - mmengine - INFO - Epoch(train) [36][50/586] lr: 5.000000e-04 eta: 13:00:41 time: 0.487696 data_time: 0.030492 memory: 15239 loss_kpt: 0.000617 acc_pose: 0.768709 loss: 0.000617 2022/09/15 18:12:38 - mmengine - INFO - Epoch(train) [36][100/586] lr: 5.000000e-04 eta: 13:00:20 time: 0.463834 data_time: 0.024553 memory: 15239 loss_kpt: 0.000617 acc_pose: 0.720708 loss: 0.000617 2022/09/15 18:13:02 - mmengine - INFO - Epoch(train) [36][150/586] lr: 5.000000e-04 eta: 13:00:01 time: 0.472407 data_time: 0.025469 memory: 15239 loss_kpt: 0.000611 acc_pose: 0.851289 loss: 0.000611 2022/09/15 18:13:25 - mmengine - INFO - Epoch(train) [36][200/586] lr: 5.000000e-04 eta: 12:59:42 time: 0.473801 data_time: 0.023651 memory: 15239 loss_kpt: 0.000618 acc_pose: 0.815529 loss: 0.000618 2022/09/15 18:13:48 - mmengine - INFO - Epoch(train) [36][250/586] lr: 5.000000e-04 eta: 12:59:20 time: 0.460035 data_time: 0.024480 memory: 15239 loss_kpt: 0.000622 acc_pose: 0.848130 loss: 0.000622 2022/09/15 18:14:12 - mmengine - INFO - Epoch(train) [36][300/586] lr: 5.000000e-04 eta: 12:59:01 time: 0.470340 data_time: 0.024469 memory: 15239 loss_kpt: 0.000603 acc_pose: 0.832114 loss: 0.000603 2022/09/15 18:14:35 - mmengine - INFO - Epoch(train) [36][350/586] lr: 5.000000e-04 eta: 12:58:38 time: 0.460322 data_time: 0.024411 memory: 15239 loss_kpt: 0.000602 acc_pose: 0.791857 loss: 0.000602 2022/09/15 18:14:58 - mmengine - INFO - Epoch(train) [36][400/586] lr: 5.000000e-04 eta: 12:58:17 time: 0.464438 data_time: 0.024345 memory: 15239 loss_kpt: 0.000625 acc_pose: 0.861957 loss: 0.000625 2022/09/15 18:15:21 - mmengine - INFO - Epoch(train) [36][450/586] lr: 5.000000e-04 eta: 12:57:56 time: 0.463072 data_time: 0.025357 memory: 15239 loss_kpt: 0.000604 acc_pose: 0.811813 loss: 0.000604 2022/09/15 18:15:40 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 18:15:44 - mmengine - INFO - Epoch(train) [36][500/586] lr: 5.000000e-04 eta: 12:57:34 time: 0.462976 data_time: 0.025324 memory: 15239 loss_kpt: 0.000630 acc_pose: 0.826972 loss: 0.000630 2022/09/15 18:16:07 - mmengine - INFO - Epoch(train) [36][550/586] lr: 5.000000e-04 eta: 12:57:12 time: 0.460454 data_time: 0.024014 memory: 15239 loss_kpt: 0.000617 acc_pose: 0.842952 loss: 0.000617 2022/09/15 18:16:24 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 18:16:24 - mmengine - INFO - Saving checkpoint at 36 epochs 2022/09/15 18:16:55 - mmengine - INFO - Epoch(train) [37][50/586] lr: 5.000000e-04 eta: 12:55:18 time: 0.473027 data_time: 0.032051 memory: 15239 loss_kpt: 0.000629 acc_pose: 0.843068 loss: 0.000629 2022/09/15 18:17:18 - mmengine - INFO - Epoch(train) [37][100/586] lr: 5.000000e-04 eta: 12:54:56 time: 0.462465 data_time: 0.026887 memory: 15239 loss_kpt: 0.000595 acc_pose: 0.807262 loss: 0.000595 2022/09/15 18:17:41 - mmengine - INFO - Epoch(train) [37][150/586] lr: 5.000000e-04 eta: 12:54:35 time: 0.462962 data_time: 0.026357 memory: 15239 loss_kpt: 0.000616 acc_pose: 0.838682 loss: 0.000616 2022/09/15 18:18:04 - mmengine - INFO - Epoch(train) [37][200/586] lr: 5.000000e-04 eta: 12:54:13 time: 0.461773 data_time: 0.024184 memory: 15239 loss_kpt: 0.000606 acc_pose: 0.832083 loss: 0.000606 2022/09/15 18:18:27 - mmengine - INFO - Epoch(train) [37][250/586] lr: 5.000000e-04 eta: 12:53:53 time: 0.467018 data_time: 0.029584 memory: 15239 loss_kpt: 0.000617 acc_pose: 0.811134 loss: 0.000617 2022/09/15 18:18:51 - mmengine - INFO - Epoch(train) [37][300/586] lr: 5.000000e-04 eta: 12:53:34 time: 0.471192 data_time: 0.023961 memory: 15239 loss_kpt: 0.000599 acc_pose: 0.801789 loss: 0.000599 2022/09/15 18:19:14 - mmengine - INFO - Epoch(train) [37][350/586] lr: 5.000000e-04 eta: 12:53:12 time: 0.462056 data_time: 0.025463 memory: 15239 loss_kpt: 0.000624 acc_pose: 0.838709 loss: 0.000624 2022/09/15 18:19:37 - mmengine - INFO - Epoch(train) [37][400/586] lr: 5.000000e-04 eta: 12:52:52 time: 0.468209 data_time: 0.027556 memory: 15239 loss_kpt: 0.000620 acc_pose: 0.742534 loss: 0.000620 2022/09/15 18:20:01 - mmengine - INFO - Epoch(train) [37][450/586] lr: 5.000000e-04 eta: 12:52:30 time: 0.460523 data_time: 0.023995 memory: 15239 loss_kpt: 0.000613 acc_pose: 0.750695 loss: 0.000613 2022/09/15 18:20:24 - mmengine - INFO - Epoch(train) [37][500/586] lr: 5.000000e-04 eta: 12:52:09 time: 0.462710 data_time: 0.024645 memory: 15239 loss_kpt: 0.000607 acc_pose: 0.777742 loss: 0.000607 2022/09/15 18:20:47 - mmengine - INFO - Epoch(train) [37][550/586] lr: 5.000000e-04 eta: 12:51:48 time: 0.466947 data_time: 0.024631 memory: 15239 loss_kpt: 0.000625 acc_pose: 0.837872 loss: 0.000625 2022/09/15 18:21:04 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 18:21:04 - mmengine - INFO - Saving checkpoint at 37 epochs 2022/09/15 18:21:34 - mmengine - INFO - Epoch(train) [38][50/586] lr: 5.000000e-04 eta: 12:49:56 time: 0.472381 data_time: 0.028672 memory: 15239 loss_kpt: 0.000626 acc_pose: 0.799892 loss: 0.000626 2022/09/15 18:21:58 - mmengine - INFO - Epoch(train) [38][100/586] lr: 5.000000e-04 eta: 12:49:37 time: 0.469435 data_time: 0.025448 memory: 15239 loss_kpt: 0.000606 acc_pose: 0.836410 loss: 0.000606 2022/09/15 18:22:21 - mmengine - INFO - Epoch(train) [38][150/586] lr: 5.000000e-04 eta: 12:49:15 time: 0.460338 data_time: 0.023634 memory: 15239 loss_kpt: 0.000610 acc_pose: 0.808790 loss: 0.000610 2022/09/15 18:22:44 - mmengine - INFO - Epoch(train) [38][200/586] lr: 5.000000e-04 eta: 12:48:54 time: 0.466767 data_time: 0.023523 memory: 15239 loss_kpt: 0.000641 acc_pose: 0.811315 loss: 0.000641 2022/09/15 18:23:07 - mmengine - INFO - Epoch(train) [38][250/586] lr: 5.000000e-04 eta: 12:48:34 time: 0.465555 data_time: 0.023891 memory: 15239 loss_kpt: 0.000595 acc_pose: 0.817035 loss: 0.000595 2022/09/15 18:23:30 - mmengine - INFO - Epoch(train) [38][300/586] lr: 5.000000e-04 eta: 12:48:11 time: 0.456944 data_time: 0.024312 memory: 15239 loss_kpt: 0.000600 acc_pose: 0.798241 loss: 0.000600 2022/09/15 18:23:39 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 18:23:54 - mmengine - INFO - Epoch(train) [38][350/586] lr: 5.000000e-04 eta: 12:47:51 time: 0.467231 data_time: 0.028464 memory: 15239 loss_kpt: 0.000605 acc_pose: 0.730087 loss: 0.000605 2022/09/15 18:24:17 - mmengine - INFO - Epoch(train) [38][400/586] lr: 5.000000e-04 eta: 12:47:29 time: 0.458901 data_time: 0.025119 memory: 15239 loss_kpt: 0.000613 acc_pose: 0.823337 loss: 0.000613 2022/09/15 18:24:40 - mmengine - INFO - Epoch(train) [38][450/586] lr: 5.000000e-04 eta: 12:47:08 time: 0.463820 data_time: 0.023441 memory: 15239 loss_kpt: 0.000625 acc_pose: 0.780168 loss: 0.000625 2022/09/15 18:25:03 - mmengine - INFO - Epoch(train) [38][500/586] lr: 5.000000e-04 eta: 12:46:48 time: 0.469562 data_time: 0.024745 memory: 15239 loss_kpt: 0.000603 acc_pose: 0.791290 loss: 0.000603 2022/09/15 18:25:26 - mmengine - INFO - Epoch(train) [38][550/586] lr: 5.000000e-04 eta: 12:46:26 time: 0.460632 data_time: 0.024156 memory: 15239 loss_kpt: 0.000599 acc_pose: 0.820436 loss: 0.000599 2022/09/15 18:25:43 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 18:25:43 - mmengine - INFO - Saving checkpoint at 38 epochs 2022/09/15 18:26:14 - mmengine - INFO - Epoch(train) [39][50/586] lr: 5.000000e-04 eta: 12:44:36 time: 0.471050 data_time: 0.031384 memory: 15239 loss_kpt: 0.000618 acc_pose: 0.854467 loss: 0.000618 2022/09/15 18:26:37 - mmengine - INFO - Epoch(train) [39][100/586] lr: 5.000000e-04 eta: 12:44:17 time: 0.468082 data_time: 0.031361 memory: 15239 loss_kpt: 0.000593 acc_pose: 0.867788 loss: 0.000593 2022/09/15 18:27:01 - mmengine - INFO - Epoch(train) [39][150/586] lr: 5.000000e-04 eta: 12:43:59 time: 0.478736 data_time: 0.024761 memory: 15239 loss_kpt: 0.000596 acc_pose: 0.808656 loss: 0.000596 2022/09/15 18:27:24 - mmengine - INFO - Epoch(train) [39][200/586] lr: 5.000000e-04 eta: 12:43:37 time: 0.460671 data_time: 0.024997 memory: 15239 loss_kpt: 0.000619 acc_pose: 0.737864 loss: 0.000619 2022/09/15 18:27:48 - mmengine - INFO - Epoch(train) [39][250/586] lr: 5.000000e-04 eta: 12:43:17 time: 0.467949 data_time: 0.024727 memory: 15239 loss_kpt: 0.000630 acc_pose: 0.828103 loss: 0.000630 2022/09/15 18:28:11 - mmengine - INFO - Epoch(train) [39][300/586] lr: 5.000000e-04 eta: 12:42:57 time: 0.465663 data_time: 0.024976 memory: 15239 loss_kpt: 0.000608 acc_pose: 0.845384 loss: 0.000608 2022/09/15 18:28:34 - mmengine - INFO - Epoch(train) [39][350/586] lr: 5.000000e-04 eta: 12:42:37 time: 0.466862 data_time: 0.023987 memory: 15239 loss_kpt: 0.000606 acc_pose: 0.822507 loss: 0.000606 2022/09/15 18:28:57 - mmengine - INFO - Epoch(train) [39][400/586] lr: 5.000000e-04 eta: 12:42:15 time: 0.462098 data_time: 0.024865 memory: 15239 loss_kpt: 0.000613 acc_pose: 0.840235 loss: 0.000613 2022/09/15 18:29:21 - mmengine - INFO - Epoch(train) [39][450/586] lr: 5.000000e-04 eta: 12:41:57 time: 0.477231 data_time: 0.028683 memory: 15239 loss_kpt: 0.000621 acc_pose: 0.807881 loss: 0.000621 2022/09/15 18:29:44 - mmengine - INFO - Epoch(train) [39][500/586] lr: 5.000000e-04 eta: 12:41:35 time: 0.456336 data_time: 0.024327 memory: 15239 loss_kpt: 0.000623 acc_pose: 0.790985 loss: 0.000623 2022/09/15 18:30:07 - mmengine - INFO - Epoch(train) [39][550/586] lr: 5.000000e-04 eta: 12:41:13 time: 0.461593 data_time: 0.025529 memory: 15239 loss_kpt: 0.000610 acc_pose: 0.805884 loss: 0.000610 2022/09/15 18:30:24 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 18:30:24 - mmengine - INFO - Saving checkpoint at 39 epochs 2022/09/15 18:30:54 - mmengine - INFO - Epoch(train) [40][50/586] lr: 5.000000e-04 eta: 12:39:25 time: 0.469837 data_time: 0.032418 memory: 15239 loss_kpt: 0.000610 acc_pose: 0.880716 loss: 0.000610 2022/09/15 18:31:18 - mmengine - INFO - Epoch(train) [40][100/586] lr: 5.000000e-04 eta: 12:39:07 time: 0.473270 data_time: 0.025481 memory: 15239 loss_kpt: 0.000610 acc_pose: 0.816288 loss: 0.000610 2022/09/15 18:31:40 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 18:31:41 - mmengine - INFO - Epoch(train) [40][150/586] lr: 5.000000e-04 eta: 12:38:46 time: 0.464196 data_time: 0.024941 memory: 15239 loss_kpt: 0.000593 acc_pose: 0.793947 loss: 0.000593 2022/09/15 18:32:05 - mmengine - INFO - Epoch(train) [40][200/586] lr: 5.000000e-04 eta: 12:38:25 time: 0.464232 data_time: 0.028586 memory: 15239 loss_kpt: 0.000619 acc_pose: 0.842976 loss: 0.000619 2022/09/15 18:32:28 - mmengine - INFO - Epoch(train) [40][250/586] lr: 5.000000e-04 eta: 12:38:05 time: 0.467585 data_time: 0.024685 memory: 15239 loss_kpt: 0.000626 acc_pose: 0.844057 loss: 0.000626 2022/09/15 18:32:51 - mmengine - INFO - Epoch(train) [40][300/586] lr: 5.000000e-04 eta: 12:37:42 time: 0.454969 data_time: 0.024429 memory: 15239 loss_kpt: 0.000611 acc_pose: 0.831628 loss: 0.000611 2022/09/15 18:33:14 - mmengine - INFO - Epoch(train) [40][350/586] lr: 5.000000e-04 eta: 12:37:21 time: 0.463879 data_time: 0.024267 memory: 15239 loss_kpt: 0.000585 acc_pose: 0.850031 loss: 0.000585 2022/09/15 18:33:37 - mmengine - INFO - Epoch(train) [40][400/586] lr: 5.000000e-04 eta: 12:37:02 time: 0.468766 data_time: 0.025423 memory: 15239 loss_kpt: 0.000626 acc_pose: 0.824585 loss: 0.000626 2022/09/15 18:34:01 - mmengine - INFO - Epoch(train) [40][450/586] lr: 5.000000e-04 eta: 12:36:42 time: 0.470906 data_time: 0.025352 memory: 15239 loss_kpt: 0.000626 acc_pose: 0.737012 loss: 0.000626 2022/09/15 18:34:24 - mmengine - INFO - Epoch(train) [40][500/586] lr: 5.000000e-04 eta: 12:36:23 time: 0.469150 data_time: 0.024923 memory: 15239 loss_kpt: 0.000619 acc_pose: 0.784290 loss: 0.000619 2022/09/15 18:34:48 - mmengine - INFO - Epoch(train) [40][550/586] lr: 5.000000e-04 eta: 12:36:03 time: 0.468151 data_time: 0.024067 memory: 15239 loss_kpt: 0.000613 acc_pose: 0.845391 loss: 0.000613 2022/09/15 18:35:04 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 18:35:04 - mmengine - INFO - Saving checkpoint at 40 epochs 2022/09/15 18:35:25 - mmengine - INFO - Epoch(val) [40][50/407] eta: 0:01:34 time: 0.263549 data_time: 0.018680 memory: 15239 2022/09/15 18:35:38 - mmengine - INFO - Epoch(val) [40][100/407] eta: 0:01:16 time: 0.249761 data_time: 0.008562 memory: 2064 2022/09/15 18:35:50 - mmengine - INFO - Epoch(val) [40][150/407] eta: 0:01:04 time: 0.251279 data_time: 0.008318 memory: 2064 2022/09/15 18:36:03 - mmengine - INFO - Epoch(val) [40][200/407] eta: 0:00:51 time: 0.250660 data_time: 0.008647 memory: 2064 2022/09/15 18:36:15 - mmengine - INFO - Epoch(val) [40][250/407] eta: 0:00:39 time: 0.249765 data_time: 0.008234 memory: 2064 2022/09/15 18:36:28 - mmengine - INFO - Epoch(val) [40][300/407] eta: 0:00:26 time: 0.250491 data_time: 0.008632 memory: 2064 2022/09/15 18:36:40 - mmengine - INFO - Epoch(val) [40][350/407] eta: 0:00:14 time: 0.251379 data_time: 0.008525 memory: 2064 2022/09/15 18:36:53 - mmengine - INFO - Epoch(val) [40][400/407] eta: 0:00:01 time: 0.249498 data_time: 0.008376 memory: 2064 2022/09/15 18:37:27 - mmengine - INFO - Evaluating CocoMetric... 2022/09/15 18:37:40 - mmengine - INFO - Epoch(val) [40][407/407] coco/AP: 0.742295 coco/AP .5: 0.897717 coco/AP .75: 0.809581 coco/AP (M): 0.702583 coco/AP (L): 0.811762 coco/AR: 0.792695 coco/AR .5: 0.934666 coco/AR .75: 0.853432 coco/AR (M): 0.749904 coco/AR (L): 0.854366 2022/09/15 18:37:41 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220915/dark_w48_384/best_coco/AP_epoch_30.pth is removed 2022/09/15 18:37:44 - mmengine - INFO - The best checkpoint with 0.7423 coco/AP at 40 epoch is saved to best_coco/AP_epoch_40.pth. 2022/09/15 18:38:07 - mmengine - INFO - Epoch(train) [41][50/586] lr: 5.000000e-04 eta: 12:34:15 time: 0.461943 data_time: 0.028311 memory: 15239 loss_kpt: 0.000612 acc_pose: 0.878952 loss: 0.000612 2022/09/15 18:38:31 - mmengine - INFO - Epoch(train) [41][100/586] lr: 5.000000e-04 eta: 12:33:56 time: 0.470199 data_time: 0.029179 memory: 15239 loss_kpt: 0.000610 acc_pose: 0.830270 loss: 0.000610 2022/09/15 18:38:54 - mmengine - INFO - Epoch(train) [41][150/586] lr: 5.000000e-04 eta: 12:33:35 time: 0.464027 data_time: 0.025060 memory: 15239 loss_kpt: 0.000611 acc_pose: 0.761860 loss: 0.000611 2022/09/15 18:39:17 - mmengine - INFO - Epoch(train) [41][200/586] lr: 5.000000e-04 eta: 12:33:13 time: 0.456845 data_time: 0.024564 memory: 15239 loss_kpt: 0.000612 acc_pose: 0.842574 loss: 0.000612 2022/09/15 18:39:41 - mmengine - INFO - Epoch(train) [41][250/586] lr: 5.000000e-04 eta: 12:32:55 time: 0.475287 data_time: 0.024831 memory: 15239 loss_kpt: 0.000603 acc_pose: 0.876602 loss: 0.000603 2022/09/15 18:40:04 - mmengine - INFO - Epoch(train) [41][300/586] lr: 5.000000e-04 eta: 12:32:33 time: 0.461193 data_time: 0.026119 memory: 15239 loss_kpt: 0.000621 acc_pose: 0.833227 loss: 0.000621 2022/09/15 18:40:27 - mmengine - INFO - Epoch(train) [41][350/586] lr: 5.000000e-04 eta: 12:32:11 time: 0.456585 data_time: 0.024766 memory: 15239 loss_kpt: 0.000618 acc_pose: 0.823825 loss: 0.000618 2022/09/15 18:40:50 - mmengine - INFO - Epoch(train) [41][400/586] lr: 5.000000e-04 eta: 12:31:53 time: 0.478036 data_time: 0.030557 memory: 15239 loss_kpt: 0.000609 acc_pose: 0.884984 loss: 0.000609 2022/09/15 18:41:13 - mmengine - INFO - Epoch(train) [41][450/586] lr: 5.000000e-04 eta: 12:31:31 time: 0.459794 data_time: 0.024220 memory: 15239 loss_kpt: 0.000593 acc_pose: 0.846239 loss: 0.000593 2022/09/15 18:41:36 - mmengine - INFO - Epoch(train) [41][500/586] lr: 5.000000e-04 eta: 12:31:09 time: 0.454484 data_time: 0.024452 memory: 15239 loss_kpt: 0.000605 acc_pose: 0.826064 loss: 0.000605 2022/09/15 18:42:00 - mmengine - INFO - Epoch(train) [41][550/586] lr: 5.000000e-04 eta: 12:30:50 time: 0.472749 data_time: 0.027997 memory: 15239 loss_kpt: 0.000608 acc_pose: 0.853528 loss: 0.000608 2022/09/15 18:42:04 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 18:42:16 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 18:42:16 - mmengine - INFO - Saving checkpoint at 41 epochs 2022/09/15 18:42:46 - mmengine - INFO - Epoch(train) [42][50/586] lr: 5.000000e-04 eta: 12:29:06 time: 0.466714 data_time: 0.031603 memory: 15239 loss_kpt: 0.000623 acc_pose: 0.818091 loss: 0.000623 2022/09/15 18:43:10 - mmengine - INFO - Epoch(train) [42][100/586] lr: 5.000000e-04 eta: 12:28:47 time: 0.475718 data_time: 0.031142 memory: 15239 loss_kpt: 0.000604 acc_pose: 0.855338 loss: 0.000604 2022/09/15 18:43:33 - mmengine - INFO - Epoch(train) [42][150/586] lr: 5.000000e-04 eta: 12:28:26 time: 0.462968 data_time: 0.027804 memory: 15239 loss_kpt: 0.000633 acc_pose: 0.865035 loss: 0.000633 2022/09/15 18:43:57 - mmengine - INFO - Epoch(train) [42][200/586] lr: 5.000000e-04 eta: 12:28:08 time: 0.474423 data_time: 0.029184 memory: 15239 loss_kpt: 0.000604 acc_pose: 0.891620 loss: 0.000604 2022/09/15 18:44:20 - mmengine - INFO - Epoch(train) [42][250/586] lr: 5.000000e-04 eta: 12:27:46 time: 0.459192 data_time: 0.028557 memory: 15239 loss_kpt: 0.000602 acc_pose: 0.874660 loss: 0.000602 2022/09/15 18:44:43 - mmengine - INFO - Epoch(train) [42][300/586] lr: 5.000000e-04 eta: 12:27:25 time: 0.459353 data_time: 0.024689 memory: 15239 loss_kpt: 0.000586 acc_pose: 0.874472 loss: 0.000586 2022/09/15 18:45:06 - mmengine - INFO - Epoch(train) [42][350/586] lr: 5.000000e-04 eta: 12:27:04 time: 0.466878 data_time: 0.024313 memory: 15239 loss_kpt: 0.000612 acc_pose: 0.792851 loss: 0.000612 2022/09/15 18:45:30 - mmengine - INFO - Epoch(train) [42][400/586] lr: 5.000000e-04 eta: 12:26:44 time: 0.465505 data_time: 0.028797 memory: 15239 loss_kpt: 0.000607 acc_pose: 0.822887 loss: 0.000607 2022/09/15 18:45:52 - mmengine - INFO - Epoch(train) [42][450/586] lr: 5.000000e-04 eta: 12:26:21 time: 0.455243 data_time: 0.025661 memory: 15239 loss_kpt: 0.000594 acc_pose: 0.853402 loss: 0.000594 2022/09/15 18:46:16 - mmengine - INFO - Epoch(train) [42][500/586] lr: 5.000000e-04 eta: 12:26:03 time: 0.475969 data_time: 0.024997 memory: 15239 loss_kpt: 0.000602 acc_pose: 0.860818 loss: 0.000602 2022/09/15 18:46:39 - mmengine - INFO - Epoch(train) [42][550/586] lr: 5.000000e-04 eta: 12:25:42 time: 0.460127 data_time: 0.025288 memory: 15239 loss_kpt: 0.000604 acc_pose: 0.820298 loss: 0.000604 2022/09/15 18:46:56 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 18:46:56 - mmengine - INFO - Saving checkpoint at 42 epochs 2022/09/15 18:47:27 - mmengine - INFO - Epoch(train) [43][50/586] lr: 5.000000e-04 eta: 12:24:04 time: 0.485897 data_time: 0.031863 memory: 15239 loss_kpt: 0.000620 acc_pose: 0.804142 loss: 0.000620 2022/09/15 18:47:50 - mmengine - INFO - Epoch(train) [43][100/586] lr: 5.000000e-04 eta: 12:23:42 time: 0.461767 data_time: 0.025125 memory: 15239 loss_kpt: 0.000601 acc_pose: 0.848384 loss: 0.000601 2022/09/15 18:48:14 - mmengine - INFO - Epoch(train) [43][150/586] lr: 5.000000e-04 eta: 12:23:22 time: 0.466750 data_time: 0.024461 memory: 15239 loss_kpt: 0.000615 acc_pose: 0.842971 loss: 0.000615 2022/09/15 18:48:37 - mmengine - INFO - Epoch(train) [43][200/586] lr: 5.000000e-04 eta: 12:23:02 time: 0.465855 data_time: 0.024697 memory: 15239 loss_kpt: 0.000602 acc_pose: 0.861322 loss: 0.000602 2022/09/15 18:49:00 - mmengine - INFO - Epoch(train) [43][250/586] lr: 5.000000e-04 eta: 12:22:43 time: 0.472153 data_time: 0.024546 memory: 15239 loss_kpt: 0.000613 acc_pose: 0.842981 loss: 0.000613 2022/09/15 18:49:23 - mmengine - INFO - Epoch(train) [43][300/586] lr: 5.000000e-04 eta: 12:22:21 time: 0.456623 data_time: 0.024001 memory: 15239 loss_kpt: 0.000605 acc_pose: 0.824019 loss: 0.000605 2022/09/15 18:49:47 - mmengine - INFO - Epoch(train) [43][350/586] lr: 5.000000e-04 eta: 12:22:02 time: 0.470851 data_time: 0.028013 memory: 15239 loss_kpt: 0.000607 acc_pose: 0.756277 loss: 0.000607 2022/09/15 18:50:04 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 18:50:10 - mmengine - INFO - Epoch(train) [43][400/586] lr: 5.000000e-04 eta: 12:21:40 time: 0.461347 data_time: 0.024353 memory: 15239 loss_kpt: 0.000614 acc_pose: 0.812386 loss: 0.000614 2022/09/15 18:50:33 - mmengine - INFO - Epoch(train) [43][450/586] lr: 5.000000e-04 eta: 12:21:19 time: 0.462663 data_time: 0.025523 memory: 15239 loss_kpt: 0.000621 acc_pose: 0.819221 loss: 0.000621 2022/09/15 18:50:57 - mmengine - INFO - Epoch(train) [43][500/586] lr: 5.000000e-04 eta: 12:21:00 time: 0.468836 data_time: 0.025721 memory: 15239 loss_kpt: 0.000596 acc_pose: 0.819350 loss: 0.000596 2022/09/15 18:51:20 - mmengine - INFO - Epoch(train) [43][550/586] lr: 5.000000e-04 eta: 12:20:39 time: 0.464643 data_time: 0.025291 memory: 15239 loss_kpt: 0.000595 acc_pose: 0.821124 loss: 0.000595 2022/09/15 18:51:36 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 18:51:36 - mmengine - INFO - Saving checkpoint at 43 epochs 2022/09/15 18:52:07 - mmengine - INFO - Epoch(train) [44][50/586] lr: 5.000000e-04 eta: 12:19:00 time: 0.472474 data_time: 0.029836 memory: 15239 loss_kpt: 0.000602 acc_pose: 0.812192 loss: 0.000602 2022/09/15 18:52:30 - mmengine - INFO - Epoch(train) [44][100/586] lr: 5.000000e-04 eta: 12:18:41 time: 0.470119 data_time: 0.027853 memory: 15239 loss_kpt: 0.000618 acc_pose: 0.790291 loss: 0.000618 2022/09/15 18:52:53 - mmengine - INFO - Epoch(train) [44][150/586] lr: 5.000000e-04 eta: 12:18:19 time: 0.459594 data_time: 0.024486 memory: 15239 loss_kpt: 0.000619 acc_pose: 0.848932 loss: 0.000619 2022/09/15 18:53:16 - mmengine - INFO - Epoch(train) [44][200/586] lr: 5.000000e-04 eta: 12:17:59 time: 0.464209 data_time: 0.024104 memory: 15239 loss_kpt: 0.000595 acc_pose: 0.762808 loss: 0.000595 2022/09/15 18:53:40 - mmengine - INFO - Epoch(train) [44][250/586] lr: 5.000000e-04 eta: 12:17:38 time: 0.464175 data_time: 0.024724 memory: 15239 loss_kpt: 0.000610 acc_pose: 0.753071 loss: 0.000610 2022/09/15 18:54:03 - mmengine - INFO - Epoch(train) [44][300/586] lr: 5.000000e-04 eta: 12:17:18 time: 0.467011 data_time: 0.026797 memory: 15239 loss_kpt: 0.000587 acc_pose: 0.791288 loss: 0.000587 2022/09/15 18:54:26 - mmengine - INFO - Epoch(train) [44][350/586] lr: 5.000000e-04 eta: 12:16:57 time: 0.460679 data_time: 0.024733 memory: 15239 loss_kpt: 0.000616 acc_pose: 0.812610 loss: 0.000616 2022/09/15 18:54:49 - mmengine - INFO - Epoch(train) [44][400/586] lr: 5.000000e-04 eta: 12:16:36 time: 0.465253 data_time: 0.024287 memory: 15239 loss_kpt: 0.000579 acc_pose: 0.795369 loss: 0.000579 2022/09/15 18:55:13 - mmengine - INFO - Epoch(train) [44][450/586] lr: 5.000000e-04 eta: 12:16:16 time: 0.464787 data_time: 0.024832 memory: 15239 loss_kpt: 0.000612 acc_pose: 0.821654 loss: 0.000612 2022/09/15 18:55:36 - mmengine - INFO - Epoch(train) [44][500/586] lr: 5.000000e-04 eta: 12:15:55 time: 0.460806 data_time: 0.024103 memory: 15239 loss_kpt: 0.000600 acc_pose: 0.836714 loss: 0.000600 2022/09/15 18:55:59 - mmengine - INFO - Epoch(train) [44][550/586] lr: 5.000000e-04 eta: 12:15:34 time: 0.462786 data_time: 0.024084 memory: 15239 loss_kpt: 0.000611 acc_pose: 0.803163 loss: 0.000611 2022/09/15 18:56:15 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 18:56:15 - mmengine - INFO - Saving checkpoint at 44 epochs 2022/09/15 18:56:46 - mmengine - INFO - Epoch(train) [45][50/586] lr: 5.000000e-04 eta: 12:13:56 time: 0.468308 data_time: 0.032119 memory: 15239 loss_kpt: 0.000591 acc_pose: 0.815973 loss: 0.000591 2022/09/15 18:57:09 - mmengine - INFO - Epoch(train) [45][100/586] lr: 5.000000e-04 eta: 12:13:36 time: 0.469625 data_time: 0.024411 memory: 15239 loss_kpt: 0.000607 acc_pose: 0.866694 loss: 0.000607 2022/09/15 18:57:32 - mmengine - INFO - Epoch(train) [45][150/586] lr: 5.000000e-04 eta: 12:13:15 time: 0.461318 data_time: 0.024541 memory: 15239 loss_kpt: 0.000606 acc_pose: 0.856151 loss: 0.000606 2022/09/15 18:57:55 - mmengine - INFO - Epoch(train) [45][200/586] lr: 5.000000e-04 eta: 12:12:54 time: 0.462153 data_time: 0.027899 memory: 15239 loss_kpt: 0.000592 acc_pose: 0.896531 loss: 0.000592 2022/09/15 18:58:03 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 18:58:18 - mmengine - INFO - Epoch(train) [45][250/586] lr: 5.000000e-04 eta: 12:12:34 time: 0.464721 data_time: 0.024874 memory: 15239 loss_kpt: 0.000617 acc_pose: 0.841910 loss: 0.000617 2022/09/15 18:58:42 - mmengine - INFO - Epoch(train) [45][300/586] lr: 5.000000e-04 eta: 12:12:14 time: 0.468338 data_time: 0.024455 memory: 15239 loss_kpt: 0.000599 acc_pose: 0.850340 loss: 0.000599 2022/09/15 18:59:05 - mmengine - INFO - Epoch(train) [45][350/586] lr: 5.000000e-04 eta: 12:11:55 time: 0.469416 data_time: 0.025867 memory: 15239 loss_kpt: 0.000617 acc_pose: 0.856214 loss: 0.000617 2022/09/15 18:59:29 - mmengine - INFO - Epoch(train) [45][400/586] lr: 5.000000e-04 eta: 12:11:34 time: 0.463624 data_time: 0.024628 memory: 15239 loss_kpt: 0.000619 acc_pose: 0.866231 loss: 0.000619 2022/09/15 18:59:51 - mmengine - INFO - Epoch(train) [45][450/586] lr: 5.000000e-04 eta: 12:11:12 time: 0.458063 data_time: 0.024762 memory: 15239 loss_kpt: 0.000608 acc_pose: 0.817237 loss: 0.000608 2022/09/15 19:00:15 - mmengine - INFO - Epoch(train) [45][500/586] lr: 5.000000e-04 eta: 12:10:51 time: 0.463698 data_time: 0.024920 memory: 15239 loss_kpt: 0.000622 acc_pose: 0.791192 loss: 0.000622 2022/09/15 19:00:38 - mmengine - INFO - Epoch(train) [45][550/586] lr: 5.000000e-04 eta: 12:10:32 time: 0.469984 data_time: 0.026553 memory: 15239 loss_kpt: 0.000603 acc_pose: 0.810088 loss: 0.000603 2022/09/15 19:00:55 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 19:00:55 - mmengine - INFO - Saving checkpoint at 45 epochs 2022/09/15 19:01:25 - mmengine - INFO - Epoch(train) [46][50/586] lr: 5.000000e-04 eta: 12:08:56 time: 0.469823 data_time: 0.028855 memory: 15239 loss_kpt: 0.000602 acc_pose: 0.783000 loss: 0.000602 2022/09/15 19:01:48 - mmengine - INFO - Epoch(train) [46][100/586] lr: 5.000000e-04 eta: 12:08:37 time: 0.470230 data_time: 0.024168 memory: 15239 loss_kpt: 0.000602 acc_pose: 0.826558 loss: 0.000602 2022/09/15 19:02:12 - mmengine - INFO - Epoch(train) [46][150/586] lr: 5.000000e-04 eta: 12:08:17 time: 0.465552 data_time: 0.028755 memory: 15239 loss_kpt: 0.000600 acc_pose: 0.802687 loss: 0.000600 2022/09/15 19:02:35 - mmengine - INFO - Epoch(train) [46][200/586] lr: 5.000000e-04 eta: 12:07:56 time: 0.463731 data_time: 0.023929 memory: 15239 loss_kpt: 0.000598 acc_pose: 0.821755 loss: 0.000598 2022/09/15 19:02:58 - mmengine - INFO - Epoch(train) [46][250/586] lr: 5.000000e-04 eta: 12:07:34 time: 0.457739 data_time: 0.024622 memory: 15239 loss_kpt: 0.000599 acc_pose: 0.875695 loss: 0.000599 2022/09/15 19:03:21 - mmengine - INFO - Epoch(train) [46][300/586] lr: 5.000000e-04 eta: 12:07:13 time: 0.461408 data_time: 0.024623 memory: 15239 loss_kpt: 0.000584 acc_pose: 0.883312 loss: 0.000584 2022/09/15 19:03:44 - mmengine - INFO - Epoch(train) [46][350/586] lr: 5.000000e-04 eta: 12:06:53 time: 0.467381 data_time: 0.024563 memory: 15239 loss_kpt: 0.000586 acc_pose: 0.792887 loss: 0.000586 2022/09/15 19:04:08 - mmengine - INFO - Epoch(train) [46][400/586] lr: 5.000000e-04 eta: 12:06:33 time: 0.466651 data_time: 0.024729 memory: 15239 loss_kpt: 0.000616 acc_pose: 0.838357 loss: 0.000616 2022/09/15 19:04:31 - mmengine - INFO - Epoch(train) [46][450/586] lr: 5.000000e-04 eta: 12:06:13 time: 0.467082 data_time: 0.029809 memory: 15239 loss_kpt: 0.000610 acc_pose: 0.856018 loss: 0.000610 2022/09/15 19:04:54 - mmengine - INFO - Epoch(train) [46][500/586] lr: 5.000000e-04 eta: 12:05:52 time: 0.464233 data_time: 0.024174 memory: 15239 loss_kpt: 0.000604 acc_pose: 0.731532 loss: 0.000604 2022/09/15 19:05:17 - mmengine - INFO - Epoch(train) [46][550/586] lr: 5.000000e-04 eta: 12:05:32 time: 0.462662 data_time: 0.024449 memory: 15239 loss_kpt: 0.000593 acc_pose: 0.870703 loss: 0.000593 2022/09/15 19:05:34 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 19:05:34 - mmengine - INFO - Saving checkpoint at 46 epochs 2022/09/15 19:06:02 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 19:06:05 - mmengine - INFO - Epoch(train) [47][50/586] lr: 5.000000e-04 eta: 12:03:59 time: 0.475985 data_time: 0.032269 memory: 15239 loss_kpt: 0.000587 acc_pose: 0.808797 loss: 0.000587 2022/09/15 19:06:28 - mmengine - INFO - Epoch(train) [47][100/586] lr: 5.000000e-04 eta: 12:03:38 time: 0.465080 data_time: 0.027236 memory: 15239 loss_kpt: 0.000602 acc_pose: 0.889437 loss: 0.000602 2022/09/15 19:06:51 - mmengine - INFO - Epoch(train) [47][150/586] lr: 5.000000e-04 eta: 12:03:18 time: 0.465733 data_time: 0.024756 memory: 15239 loss_kpt: 0.000607 acc_pose: 0.799615 loss: 0.000607 2022/09/15 19:07:15 - mmengine - INFO - Epoch(train) [47][200/586] lr: 5.000000e-04 eta: 12:02:58 time: 0.467509 data_time: 0.028128 memory: 15239 loss_kpt: 0.000575 acc_pose: 0.864265 loss: 0.000575 2022/09/15 19:07:38 - mmengine - INFO - Epoch(train) [47][250/586] lr: 5.000000e-04 eta: 12:02:38 time: 0.463171 data_time: 0.024690 memory: 15239 loss_kpt: 0.000587 acc_pose: 0.865898 loss: 0.000587 2022/09/15 19:08:01 - mmengine - INFO - Epoch(train) [47][300/586] lr: 5.000000e-04 eta: 12:02:17 time: 0.461496 data_time: 0.024070 memory: 15239 loss_kpt: 0.000591 acc_pose: 0.870326 loss: 0.000591 2022/09/15 19:08:24 - mmengine - INFO - Epoch(train) [47][350/586] lr: 5.000000e-04 eta: 12:01:56 time: 0.467073 data_time: 0.024487 memory: 15239 loss_kpt: 0.000592 acc_pose: 0.821846 loss: 0.000592 2022/09/15 19:08:47 - mmengine - INFO - Epoch(train) [47][400/586] lr: 5.000000e-04 eta: 12:01:36 time: 0.463001 data_time: 0.025345 memory: 15239 loss_kpt: 0.000604 acc_pose: 0.834746 loss: 0.000604 2022/09/15 19:09:11 - mmengine - INFO - Epoch(train) [47][450/586] lr: 5.000000e-04 eta: 12:01:15 time: 0.464701 data_time: 0.024602 memory: 15239 loss_kpt: 0.000587 acc_pose: 0.862850 loss: 0.000587 2022/09/15 19:09:34 - mmengine - INFO - Epoch(train) [47][500/586] lr: 5.000000e-04 eta: 12:00:56 time: 0.469639 data_time: 0.025111 memory: 15239 loss_kpt: 0.000618 acc_pose: 0.819725 loss: 0.000618 2022/09/15 19:09:57 - mmengine - INFO - Epoch(train) [47][550/586] lr: 5.000000e-04 eta: 12:00:35 time: 0.461236 data_time: 0.024711 memory: 15239 loss_kpt: 0.000606 acc_pose: 0.843235 loss: 0.000606 2022/09/15 19:10:14 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 19:10:14 - mmengine - INFO - Saving checkpoint at 47 epochs 2022/09/15 19:10:45 - mmengine - INFO - Epoch(train) [48][50/586] lr: 5.000000e-04 eta: 11:59:03 time: 0.472270 data_time: 0.036185 memory: 15239 loss_kpt: 0.000600 acc_pose: 0.852550 loss: 0.000600 2022/09/15 19:11:09 - mmengine - INFO - Epoch(train) [48][100/586] lr: 5.000000e-04 eta: 11:58:44 time: 0.472699 data_time: 0.027322 memory: 15239 loss_kpt: 0.000600 acc_pose: 0.853673 loss: 0.000600 2022/09/15 19:11:32 - mmengine - INFO - Epoch(train) [48][150/586] lr: 5.000000e-04 eta: 11:58:23 time: 0.462488 data_time: 0.031938 memory: 15239 loss_kpt: 0.000605 acc_pose: 0.824241 loss: 0.000605 2022/09/15 19:11:56 - mmengine - INFO - Epoch(train) [48][200/586] lr: 5.000000e-04 eta: 11:58:05 time: 0.480479 data_time: 0.031421 memory: 15239 loss_kpt: 0.000597 acc_pose: 0.820281 loss: 0.000597 2022/09/15 19:12:19 - mmengine - INFO - Epoch(train) [48][250/586] lr: 5.000000e-04 eta: 11:57:44 time: 0.459596 data_time: 0.027318 memory: 15239 loss_kpt: 0.000601 acc_pose: 0.825005 loss: 0.000601 2022/09/15 19:12:43 - mmengine - INFO - Epoch(train) [48][300/586] lr: 5.000000e-04 eta: 11:57:24 time: 0.470462 data_time: 0.027532 memory: 15239 loss_kpt: 0.000599 acc_pose: 0.869751 loss: 0.000599 2022/09/15 19:13:06 - mmengine - INFO - Epoch(train) [48][350/586] lr: 5.000000e-04 eta: 11:57:05 time: 0.467721 data_time: 0.028228 memory: 15239 loss_kpt: 0.000602 acc_pose: 0.848228 loss: 0.000602 2022/09/15 19:13:29 - mmengine - INFO - Epoch(train) [48][400/586] lr: 5.000000e-04 eta: 11:56:43 time: 0.457589 data_time: 0.024237 memory: 15239 loss_kpt: 0.000598 acc_pose: 0.808078 loss: 0.000598 2022/09/15 19:13:53 - mmengine - INFO - Epoch(train) [48][450/586] lr: 5.000000e-04 eta: 11:56:24 time: 0.475193 data_time: 0.030566 memory: 15239 loss_kpt: 0.000575 acc_pose: 0.815918 loss: 0.000575 2022/09/15 19:13:57 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 19:14:16 - mmengine - INFO - Epoch(train) [48][500/586] lr: 5.000000e-04 eta: 11:56:04 time: 0.468971 data_time: 0.025197 memory: 15239 loss_kpt: 0.000598 acc_pose: 0.822680 loss: 0.000598 2022/09/15 19:14:39 - mmengine - INFO - Epoch(train) [48][550/586] lr: 5.000000e-04 eta: 11:55:43 time: 0.459155 data_time: 0.024441 memory: 15239 loss_kpt: 0.000613 acc_pose: 0.804616 loss: 0.000613 2022/09/15 19:14:56 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 19:14:56 - mmengine - INFO - Saving checkpoint at 48 epochs 2022/09/15 19:15:26 - mmengine - INFO - Epoch(train) [49][50/586] lr: 5.000000e-04 eta: 11:54:12 time: 0.470975 data_time: 0.029217 memory: 15239 loss_kpt: 0.000585 acc_pose: 0.782946 loss: 0.000585 2022/09/15 19:15:50 - mmengine - INFO - Epoch(train) [49][100/586] lr: 5.000000e-04 eta: 11:53:52 time: 0.466051 data_time: 0.024302 memory: 15239 loss_kpt: 0.000597 acc_pose: 0.823459 loss: 0.000597 2022/09/15 19:16:13 - mmengine - INFO - Epoch(train) [49][150/586] lr: 5.000000e-04 eta: 11:53:33 time: 0.469634 data_time: 0.024675 memory: 15239 loss_kpt: 0.000602 acc_pose: 0.822989 loss: 0.000602 2022/09/15 19:16:37 - mmengine - INFO - Epoch(train) [49][200/586] lr: 5.000000e-04 eta: 11:53:13 time: 0.467559 data_time: 0.024727 memory: 15239 loss_kpt: 0.000575 acc_pose: 0.846403 loss: 0.000575 2022/09/15 19:17:00 - mmengine - INFO - Epoch(train) [49][250/586] lr: 5.000000e-04 eta: 11:52:52 time: 0.464314 data_time: 0.028229 memory: 15239 loss_kpt: 0.000599 acc_pose: 0.836456 loss: 0.000599 2022/09/15 19:17:23 - mmengine - INFO - Epoch(train) [49][300/586] lr: 5.000000e-04 eta: 11:52:31 time: 0.459707 data_time: 0.024137 memory: 15239 loss_kpt: 0.000579 acc_pose: 0.772518 loss: 0.000579 2022/09/15 19:17:46 - mmengine - INFO - Epoch(train) [49][350/586] lr: 5.000000e-04 eta: 11:52:10 time: 0.463631 data_time: 0.024407 memory: 15239 loss_kpt: 0.000575 acc_pose: 0.783177 loss: 0.000575 2022/09/15 19:18:09 - mmengine - INFO - Epoch(train) [49][400/586] lr: 5.000000e-04 eta: 11:51:50 time: 0.464642 data_time: 0.024141 memory: 15239 loss_kpt: 0.000601 acc_pose: 0.825717 loss: 0.000601 2022/09/15 19:18:32 - mmengine - INFO - Epoch(train) [49][450/586] lr: 5.000000e-04 eta: 11:51:29 time: 0.461963 data_time: 0.024712 memory: 15239 loss_kpt: 0.000609 acc_pose: 0.827833 loss: 0.000609 2022/09/15 19:18:55 - mmengine - INFO - Epoch(train) [49][500/586] lr: 5.000000e-04 eta: 11:51:08 time: 0.460774 data_time: 0.023515 memory: 15239 loss_kpt: 0.000582 acc_pose: 0.864921 loss: 0.000582 2022/09/15 19:19:19 - mmengine - INFO - Epoch(train) [49][550/586] lr: 5.000000e-04 eta: 11:50:49 time: 0.471400 data_time: 0.024863 memory: 15239 loss_kpt: 0.000576 acc_pose: 0.844495 loss: 0.000576 2022/09/15 19:19:35 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 19:19:35 - mmengine - INFO - Saving checkpoint at 49 epochs 2022/09/15 19:20:06 - mmengine - INFO - Epoch(train) [50][50/586] lr: 5.000000e-04 eta: 11:49:20 time: 0.475883 data_time: 0.034190 memory: 15239 loss_kpt: 0.000597 acc_pose: 0.791951 loss: 0.000597 2022/09/15 19:20:29 - mmengine - INFO - Epoch(train) [50][100/586] lr: 5.000000e-04 eta: 11:49:00 time: 0.462804 data_time: 0.024601 memory: 15239 loss_kpt: 0.000587 acc_pose: 0.851813 loss: 0.000587 2022/09/15 19:20:52 - mmengine - INFO - Epoch(train) [50][150/586] lr: 5.000000e-04 eta: 11:48:39 time: 0.461365 data_time: 0.024344 memory: 15239 loss_kpt: 0.000582 acc_pose: 0.845829 loss: 0.000582 2022/09/15 19:21:15 - mmengine - INFO - Epoch(train) [50][200/586] lr: 5.000000e-04 eta: 11:48:19 time: 0.467845 data_time: 0.028963 memory: 15239 loss_kpt: 0.000588 acc_pose: 0.848481 loss: 0.000588 2022/09/15 19:21:39 - mmengine - INFO - Epoch(train) [50][250/586] lr: 5.000000e-04 eta: 11:47:58 time: 0.462641 data_time: 0.024535 memory: 15239 loss_kpt: 0.000585 acc_pose: 0.840477 loss: 0.000585 2022/09/15 19:21:55 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 19:22:02 - mmengine - INFO - Epoch(train) [50][300/586] lr: 5.000000e-04 eta: 11:47:37 time: 0.460834 data_time: 0.024561 memory: 15239 loss_kpt: 0.000579 acc_pose: 0.773289 loss: 0.000579 2022/09/15 19:22:25 - mmengine - INFO - Epoch(train) [50][350/586] lr: 5.000000e-04 eta: 11:47:16 time: 0.464280 data_time: 0.027431 memory: 15239 loss_kpt: 0.000583 acc_pose: 0.857860 loss: 0.000583 2022/09/15 19:22:48 - mmengine - INFO - Epoch(train) [50][400/586] lr: 5.000000e-04 eta: 11:46:56 time: 0.463718 data_time: 0.024181 memory: 15239 loss_kpt: 0.000606 acc_pose: 0.808344 loss: 0.000606 2022/09/15 19:23:11 - mmengine - INFO - Epoch(train) [50][450/586] lr: 5.000000e-04 eta: 11:46:35 time: 0.459849 data_time: 0.024714 memory: 15239 loss_kpt: 0.000574 acc_pose: 0.888841 loss: 0.000574 2022/09/15 19:23:34 - mmengine - INFO - Epoch(train) [50][500/586] lr: 5.000000e-04 eta: 11:46:14 time: 0.466786 data_time: 0.029161 memory: 15239 loss_kpt: 0.000596 acc_pose: 0.774306 loss: 0.000596 2022/09/15 19:23:58 - mmengine - INFO - Epoch(train) [50][550/586] lr: 5.000000e-04 eta: 11:45:54 time: 0.464263 data_time: 0.023969 memory: 15239 loss_kpt: 0.000596 acc_pose: 0.749000 loss: 0.000596 2022/09/15 19:24:14 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 19:24:14 - mmengine - INFO - Saving checkpoint at 50 epochs 2022/09/15 19:24:34 - mmengine - INFO - Epoch(val) [50][50/407] eta: 0:01:32 time: 0.259723 data_time: 0.014519 memory: 15239 2022/09/15 19:24:47 - mmengine - INFO - Epoch(val) [50][100/407] eta: 0:01:17 time: 0.251963 data_time: 0.008431 memory: 2064 2022/09/15 19:24:59 - mmengine - INFO - Epoch(val) [50][150/407] eta: 0:01:04 time: 0.249983 data_time: 0.008516 memory: 2064 2022/09/15 19:25:12 - mmengine - INFO - Epoch(val) [50][200/407] eta: 0:00:51 time: 0.250884 data_time: 0.008626 memory: 2064 2022/09/15 19:25:24 - mmengine - INFO - Epoch(val) [50][250/407] eta: 0:00:39 time: 0.254512 data_time: 0.008399 memory: 2064 2022/09/15 19:25:37 - mmengine - INFO - Epoch(val) [50][300/407] eta: 0:00:27 time: 0.253323 data_time: 0.008631 memory: 2064 2022/09/15 19:25:50 - mmengine - INFO - Epoch(val) [50][350/407] eta: 0:00:14 time: 0.251403 data_time: 0.008523 memory: 2064 2022/09/15 19:26:02 - mmengine - INFO - Epoch(val) [50][400/407] eta: 0:00:01 time: 0.249058 data_time: 0.008006 memory: 2064 2022/09/15 19:26:37 - mmengine - INFO - Evaluating CocoMetric... 2022/09/15 19:26:50 - mmengine - INFO - Epoch(val) [50][407/407] coco/AP: 0.747854 coco/AP .5: 0.898843 coco/AP .75: 0.812535 coco/AP (M): 0.707639 coco/AP (L): 0.819161 coco/AR: 0.796521 coco/AR .5: 0.935611 coco/AR .75: 0.854534 coco/AR (M): 0.752090 coco/AR (L): 0.860535 2022/09/15 19:26:50 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220915/dark_w48_384/best_coco/AP_epoch_40.pth is removed 2022/09/15 19:26:54 - mmengine - INFO - The best checkpoint with 0.7479 coco/AP at 50 epoch is saved to best_coco/AP_epoch_50.pth. 2022/09/15 19:27:17 - mmengine - INFO - Epoch(train) [51][50/586] lr: 5.000000e-04 eta: 11:44:26 time: 0.469895 data_time: 0.028418 memory: 15239 loss_kpt: 0.000601 acc_pose: 0.795391 loss: 0.000601 2022/09/15 19:27:41 - mmengine - INFO - Epoch(train) [51][100/586] lr: 5.000000e-04 eta: 11:44:07 time: 0.471217 data_time: 0.024007 memory: 15239 loss_kpt: 0.000603 acc_pose: 0.862591 loss: 0.000603 2022/09/15 19:28:04 - mmengine - INFO - Epoch(train) [51][150/586] lr: 5.000000e-04 eta: 11:43:46 time: 0.463252 data_time: 0.025062 memory: 15239 loss_kpt: 0.000594 acc_pose: 0.872705 loss: 0.000594 2022/09/15 19:28:27 - mmengine - INFO - Epoch(train) [51][200/586] lr: 5.000000e-04 eta: 11:43:26 time: 0.465976 data_time: 0.024688 memory: 15239 loss_kpt: 0.000594 acc_pose: 0.883260 loss: 0.000594 2022/09/15 19:28:51 - mmengine - INFO - Epoch(train) [51][250/586] lr: 5.000000e-04 eta: 11:43:07 time: 0.472829 data_time: 0.025079 memory: 15239 loss_kpt: 0.000587 acc_pose: 0.837661 loss: 0.000587 2022/09/15 19:29:14 - mmengine - INFO - Epoch(train) [51][300/586] lr: 5.000000e-04 eta: 11:42:46 time: 0.463585 data_time: 0.024228 memory: 15239 loss_kpt: 0.000594 acc_pose: 0.822870 loss: 0.000594 2022/09/15 19:29:37 - mmengine - INFO - Epoch(train) [51][350/586] lr: 5.000000e-04 eta: 11:42:25 time: 0.460945 data_time: 0.025195 memory: 15239 loss_kpt: 0.000598 acc_pose: 0.846101 loss: 0.000598 2022/09/15 19:30:01 - mmengine - INFO - Epoch(train) [51][400/586] lr: 5.000000e-04 eta: 11:42:05 time: 0.464752 data_time: 0.024605 memory: 15239 loss_kpt: 0.000597 acc_pose: 0.812211 loss: 0.000597 2022/09/15 19:30:24 - mmengine - INFO - Epoch(train) [51][450/586] lr: 5.000000e-04 eta: 11:41:44 time: 0.460927 data_time: 0.023958 memory: 15239 loss_kpt: 0.000582 acc_pose: 0.845988 loss: 0.000582 2022/09/15 19:30:47 - mmengine - INFO - Epoch(train) [51][500/586] lr: 5.000000e-04 eta: 11:41:23 time: 0.461970 data_time: 0.024789 memory: 15239 loss_kpt: 0.000581 acc_pose: 0.852137 loss: 0.000581 2022/09/15 19:31:10 - mmengine - INFO - Epoch(train) [51][550/586] lr: 5.000000e-04 eta: 11:41:04 time: 0.471533 data_time: 0.028822 memory: 15239 loss_kpt: 0.000571 acc_pose: 0.823185 loss: 0.000571 2022/09/15 19:31:27 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 19:31:27 - mmengine - INFO - Saving checkpoint at 51 epochs 2022/09/15 19:31:58 - mmengine - INFO - Epoch(train) [52][50/586] lr: 5.000000e-04 eta: 11:39:38 time: 0.473404 data_time: 0.034171 memory: 15239 loss_kpt: 0.000575 acc_pose: 0.883525 loss: 0.000575 2022/09/15 19:32:21 - mmengine - INFO - Epoch(train) [52][100/586] lr: 5.000000e-04 eta: 11:39:17 time: 0.462735 data_time: 0.024690 memory: 15239 loss_kpt: 0.000578 acc_pose: 0.837674 loss: 0.000578 2022/09/15 19:32:28 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 19:32:45 - mmengine - INFO - Epoch(train) [52][150/586] lr: 5.000000e-04 eta: 11:38:57 time: 0.468388 data_time: 0.026392 memory: 15239 loss_kpt: 0.000575 acc_pose: 0.890277 loss: 0.000575 2022/09/15 19:33:08 - mmengine - INFO - Epoch(train) [52][200/586] lr: 5.000000e-04 eta: 11:38:37 time: 0.464542 data_time: 0.024797 memory: 15239 loss_kpt: 0.000601 acc_pose: 0.785025 loss: 0.000601 2022/09/15 19:33:31 - mmengine - INFO - Epoch(train) [52][250/586] lr: 5.000000e-04 eta: 11:38:17 time: 0.467501 data_time: 0.023605 memory: 15239 loss_kpt: 0.000604 acc_pose: 0.902698 loss: 0.000604 2022/09/15 19:33:54 - mmengine - INFO - Epoch(train) [52][300/586] lr: 5.000000e-04 eta: 11:37:55 time: 0.458414 data_time: 0.024619 memory: 15239 loss_kpt: 0.000602 acc_pose: 0.824945 loss: 0.000602 2022/09/15 19:34:18 - mmengine - INFO - Epoch(train) [52][350/586] lr: 5.000000e-04 eta: 11:37:35 time: 0.466766 data_time: 0.029657 memory: 15239 loss_kpt: 0.000595 acc_pose: 0.867144 loss: 0.000595 2022/09/15 19:34:41 - mmengine - INFO - Epoch(train) [52][400/586] lr: 5.000000e-04 eta: 11:37:14 time: 0.461176 data_time: 0.024245 memory: 15239 loss_kpt: 0.000579 acc_pose: 0.792207 loss: 0.000579 2022/09/15 19:35:04 - mmengine - INFO - Epoch(train) [52][450/586] lr: 5.000000e-04 eta: 11:36:53 time: 0.460057 data_time: 0.024929 memory: 15239 loss_kpt: 0.000600 acc_pose: 0.892213 loss: 0.000600 2022/09/15 19:35:27 - mmengine - INFO - Epoch(train) [52][500/586] lr: 5.000000e-04 eta: 11:36:33 time: 0.468888 data_time: 0.025061 memory: 15239 loss_kpt: 0.000608 acc_pose: 0.758954 loss: 0.000608 2022/09/15 19:35:50 - mmengine - INFO - Epoch(train) [52][550/586] lr: 5.000000e-04 eta: 11:36:13 time: 0.464041 data_time: 0.024341 memory: 15239 loss_kpt: 0.000584 acc_pose: 0.846890 loss: 0.000584 2022/09/15 19:36:07 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 19:36:07 - mmengine - INFO - Saving checkpoint at 52 epochs 2022/09/15 19:36:38 - mmengine - INFO - Epoch(train) [53][50/586] lr: 5.000000e-04 eta: 11:34:48 time: 0.469790 data_time: 0.035245 memory: 15239 loss_kpt: 0.000571 acc_pose: 0.895371 loss: 0.000571 2022/09/15 19:37:01 - mmengine - INFO - Epoch(train) [53][100/586] lr: 5.000000e-04 eta: 11:34:28 time: 0.469212 data_time: 0.024308 memory: 15239 loss_kpt: 0.000590 acc_pose: 0.833693 loss: 0.000590 2022/09/15 19:37:24 - mmengine - INFO - Epoch(train) [53][150/586] lr: 5.000000e-04 eta: 11:34:07 time: 0.460649 data_time: 0.024808 memory: 15239 loss_kpt: 0.000585 acc_pose: 0.836441 loss: 0.000585 2022/09/15 19:37:47 - mmengine - INFO - Epoch(train) [53][200/586] lr: 5.000000e-04 eta: 11:33:45 time: 0.456247 data_time: 0.024128 memory: 15239 loss_kpt: 0.000599 acc_pose: 0.863843 loss: 0.000599 2022/09/15 19:38:10 - mmengine - INFO - Epoch(train) [53][250/586] lr: 5.000000e-04 eta: 11:33:26 time: 0.470948 data_time: 0.028114 memory: 15239 loss_kpt: 0.000586 acc_pose: 0.798411 loss: 0.000586 2022/09/15 19:38:33 - mmengine - INFO - Epoch(train) [53][300/586] lr: 5.000000e-04 eta: 11:33:04 time: 0.454018 data_time: 0.024427 memory: 15239 loss_kpt: 0.000604 acc_pose: 0.839016 loss: 0.000604 2022/09/15 19:38:56 - mmengine - INFO - Epoch(train) [53][350/586] lr: 5.000000e-04 eta: 11:32:43 time: 0.464034 data_time: 0.023805 memory: 15239 loss_kpt: 0.000581 acc_pose: 0.768472 loss: 0.000581 2022/09/15 19:39:20 - mmengine - INFO - Epoch(train) [53][400/586] lr: 5.000000e-04 eta: 11:32:23 time: 0.466848 data_time: 0.024229 memory: 15239 loss_kpt: 0.000566 acc_pose: 0.766426 loss: 0.000566 2022/09/15 19:39:43 - mmengine - INFO - Epoch(train) [53][450/586] lr: 5.000000e-04 eta: 11:32:02 time: 0.461953 data_time: 0.024744 memory: 15239 loss_kpt: 0.000572 acc_pose: 0.806001 loss: 0.000572 2022/09/15 19:40:06 - mmengine - INFO - Epoch(train) [53][500/586] lr: 5.000000e-04 eta: 11:31:42 time: 0.465850 data_time: 0.024821 memory: 15239 loss_kpt: 0.000594 acc_pose: 0.855962 loss: 0.000594 2022/09/15 19:40:19 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 19:40:29 - mmengine - INFO - Epoch(train) [53][550/586] lr: 5.000000e-04 eta: 11:31:22 time: 0.464710 data_time: 0.029510 memory: 15239 loss_kpt: 0.000591 acc_pose: 0.814747 loss: 0.000591 2022/09/15 19:40:46 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 19:40:46 - mmengine - INFO - Saving checkpoint at 53 epochs 2022/09/15 19:41:16 - mmengine - INFO - Epoch(train) [54][50/586] lr: 5.000000e-04 eta: 11:29:57 time: 0.464482 data_time: 0.032376 memory: 15239 loss_kpt: 0.000576 acc_pose: 0.883878 loss: 0.000576 2022/09/15 19:41:40 - mmengine - INFO - Epoch(train) [54][100/586] lr: 5.000000e-04 eta: 11:29:37 time: 0.467791 data_time: 0.024865 memory: 15239 loss_kpt: 0.000603 acc_pose: 0.850720 loss: 0.000603 2022/09/15 19:42:03 - mmengine - INFO - Epoch(train) [54][150/586] lr: 5.000000e-04 eta: 11:29:16 time: 0.457919 data_time: 0.023769 memory: 15239 loss_kpt: 0.000592 acc_pose: 0.842272 loss: 0.000592 2022/09/15 19:42:26 - mmengine - INFO - Epoch(train) [54][200/586] lr: 5.000000e-04 eta: 11:28:55 time: 0.464999 data_time: 0.024706 memory: 15239 loss_kpt: 0.000576 acc_pose: 0.856051 loss: 0.000576 2022/09/15 19:42:49 - mmengine - INFO - Epoch(train) [54][250/586] lr: 5.000000e-04 eta: 11:28:34 time: 0.461699 data_time: 0.023783 memory: 15239 loss_kpt: 0.000584 acc_pose: 0.847308 loss: 0.000584 2022/09/15 19:43:12 - mmengine - INFO - Epoch(train) [54][300/586] lr: 5.000000e-04 eta: 11:28:13 time: 0.458222 data_time: 0.024606 memory: 15239 loss_kpt: 0.000569 acc_pose: 0.862311 loss: 0.000569 2022/09/15 19:43:36 - mmengine - INFO - Epoch(train) [54][350/586] lr: 5.000000e-04 eta: 11:27:54 time: 0.471549 data_time: 0.029461 memory: 15239 loss_kpt: 0.000595 acc_pose: 0.791214 loss: 0.000595 2022/09/15 19:43:59 - mmengine - INFO - Epoch(train) [54][400/586] lr: 5.000000e-04 eta: 11:27:32 time: 0.458531 data_time: 0.024789 memory: 15239 loss_kpt: 0.000578 acc_pose: 0.834927 loss: 0.000578 2022/09/15 19:44:22 - mmengine - INFO - Epoch(train) [54][450/586] lr: 5.000000e-04 eta: 11:27:12 time: 0.463620 data_time: 0.024308 memory: 15239 loss_kpt: 0.000581 acc_pose: 0.822948 loss: 0.000581 2022/09/15 19:44:45 - mmengine - INFO - Epoch(train) [54][500/586] lr: 5.000000e-04 eta: 11:26:52 time: 0.470590 data_time: 0.025289 memory: 15239 loss_kpt: 0.000592 acc_pose: 0.732518 loss: 0.000592 2022/09/15 19:45:08 - mmengine - INFO - Epoch(train) [54][550/586] lr: 5.000000e-04 eta: 11:26:31 time: 0.462704 data_time: 0.024093 memory: 15239 loss_kpt: 0.000594 acc_pose: 0.835075 loss: 0.000594 2022/09/15 19:45:25 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 19:45:25 - mmengine - INFO - Saving checkpoint at 54 epochs 2022/09/15 19:45:55 - mmengine - INFO - Epoch(train) [55][50/586] lr: 5.000000e-04 eta: 11:25:08 time: 0.465937 data_time: 0.027932 memory: 15239 loss_kpt: 0.000582 acc_pose: 0.855380 loss: 0.000582 2022/09/15 19:46:19 - mmengine - INFO - Epoch(train) [55][100/586] lr: 5.000000e-04 eta: 11:24:48 time: 0.466056 data_time: 0.028622 memory: 15239 loss_kpt: 0.000571 acc_pose: 0.889048 loss: 0.000571 2022/09/15 19:46:42 - mmengine - INFO - Epoch(train) [55][150/586] lr: 5.000000e-04 eta: 11:24:27 time: 0.459624 data_time: 0.024938 memory: 15239 loss_kpt: 0.000595 acc_pose: 0.882499 loss: 0.000595 2022/09/15 19:47:05 - mmengine - INFO - Epoch(train) [55][200/586] lr: 5.000000e-04 eta: 11:24:06 time: 0.462369 data_time: 0.024106 memory: 15239 loss_kpt: 0.000581 acc_pose: 0.881818 loss: 0.000581 2022/09/15 19:47:28 - mmengine - INFO - Epoch(train) [55][250/586] lr: 5.000000e-04 eta: 11:23:46 time: 0.467792 data_time: 0.024783 memory: 15239 loss_kpt: 0.000577 acc_pose: 0.883419 loss: 0.000577 2022/09/15 19:47:52 - mmengine - INFO - Epoch(train) [55][300/586] lr: 5.000000e-04 eta: 11:23:26 time: 0.468110 data_time: 0.029936 memory: 15239 loss_kpt: 0.000565 acc_pose: 0.821689 loss: 0.000565 2022/09/15 19:48:15 - mmengine - INFO - Epoch(train) [55][350/586] lr: 5.000000e-04 eta: 11:23:06 time: 0.462915 data_time: 0.026329 memory: 15239 loss_kpt: 0.000584 acc_pose: 0.861990 loss: 0.000584 2022/09/15 19:48:18 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 19:48:39 - mmengine - INFO - Epoch(train) [55][400/586] lr: 5.000000e-04 eta: 11:22:47 time: 0.475279 data_time: 0.028557 memory: 15239 loss_kpt: 0.000570 acc_pose: 0.827810 loss: 0.000570 2022/09/15 19:49:01 - mmengine - INFO - Epoch(train) [55][450/586] lr: 5.000000e-04 eta: 11:22:25 time: 0.455998 data_time: 0.024577 memory: 15239 loss_kpt: 0.000586 acc_pose: 0.838534 loss: 0.000586 2022/09/15 19:49:24 - mmengine - INFO - Epoch(train) [55][500/586] lr: 5.000000e-04 eta: 11:22:04 time: 0.459745 data_time: 0.024507 memory: 15239 loss_kpt: 0.000568 acc_pose: 0.824864 loss: 0.000568 2022/09/15 19:49:48 - mmengine - INFO - Epoch(train) [55][550/586] lr: 5.000000e-04 eta: 11:21:45 time: 0.473460 data_time: 0.024240 memory: 15239 loss_kpt: 0.000560 acc_pose: 0.830182 loss: 0.000560 2022/09/15 19:50:04 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 19:50:04 - mmengine - INFO - Saving checkpoint at 55 epochs 2022/09/15 19:50:35 - mmengine - INFO - Epoch(train) [56][50/586] lr: 5.000000e-04 eta: 11:20:23 time: 0.472826 data_time: 0.029927 memory: 15239 loss_kpt: 0.000595 acc_pose: 0.785610 loss: 0.000595 2022/09/15 19:50:59 - mmengine - INFO - Epoch(train) [56][100/586] lr: 5.000000e-04 eta: 11:20:04 time: 0.468365 data_time: 0.024310 memory: 15239 loss_kpt: 0.000578 acc_pose: 0.828577 loss: 0.000578 2022/09/15 19:51:22 - mmengine - INFO - Epoch(train) [56][150/586] lr: 5.000000e-04 eta: 11:19:43 time: 0.463805 data_time: 0.024573 memory: 15239 loss_kpt: 0.000573 acc_pose: 0.785639 loss: 0.000573 2022/09/15 19:51:45 - mmengine - INFO - Epoch(train) [56][200/586] lr: 5.000000e-04 eta: 11:19:23 time: 0.468312 data_time: 0.024462 memory: 15239 loss_kpt: 0.000584 acc_pose: 0.823178 loss: 0.000584 2022/09/15 19:52:09 - mmengine - INFO - Epoch(train) [56][250/586] lr: 5.000000e-04 eta: 11:19:03 time: 0.465295 data_time: 0.024769 memory: 15239 loss_kpt: 0.000572 acc_pose: 0.828834 loss: 0.000572 2022/09/15 19:52:32 - mmengine - INFO - Epoch(train) [56][300/586] lr: 5.000000e-04 eta: 11:18:41 time: 0.457387 data_time: 0.024634 memory: 15239 loss_kpt: 0.000593 acc_pose: 0.827637 loss: 0.000593 2022/09/15 19:52:55 - mmengine - INFO - Epoch(train) [56][350/586] lr: 5.000000e-04 eta: 11:18:22 time: 0.469776 data_time: 0.028689 memory: 15239 loss_kpt: 0.000576 acc_pose: 0.843313 loss: 0.000576 2022/09/15 19:53:18 - mmengine - INFO - Epoch(train) [56][400/586] lr: 5.000000e-04 eta: 11:18:01 time: 0.462479 data_time: 0.024091 memory: 15239 loss_kpt: 0.000567 acc_pose: 0.868371 loss: 0.000567 2022/09/15 19:53:41 - mmengine - INFO - Epoch(train) [56][450/586] lr: 5.000000e-04 eta: 11:17:40 time: 0.457249 data_time: 0.024729 memory: 15239 loss_kpt: 0.000575 acc_pose: 0.842193 loss: 0.000575 2022/09/15 19:54:05 - mmengine - INFO - Epoch(train) [56][500/586] lr: 5.000000e-04 eta: 11:17:21 time: 0.477020 data_time: 0.023899 memory: 15239 loss_kpt: 0.000580 acc_pose: 0.706387 loss: 0.000580 2022/09/15 19:54:28 - mmengine - INFO - Epoch(train) [56][550/586] lr: 5.000000e-04 eta: 11:17:00 time: 0.459440 data_time: 0.024686 memory: 15239 loss_kpt: 0.000578 acc_pose: 0.844797 loss: 0.000578 2022/09/15 19:54:44 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 19:54:44 - mmengine - INFO - Saving checkpoint at 56 epochs 2022/09/15 19:55:15 - mmengine - INFO - Epoch(train) [57][50/586] lr: 5.000000e-04 eta: 11:15:40 time: 0.479240 data_time: 0.038122 memory: 15239 loss_kpt: 0.000579 acc_pose: 0.852745 loss: 0.000579 2022/09/15 19:55:39 - mmengine - INFO - Epoch(train) [57][100/586] lr: 5.000000e-04 eta: 11:15:21 time: 0.471536 data_time: 0.027118 memory: 15239 loss_kpt: 0.000560 acc_pose: 0.852943 loss: 0.000560 2022/09/15 19:56:02 - mmengine - INFO - Epoch(train) [57][150/586] lr: 5.000000e-04 eta: 11:15:00 time: 0.460783 data_time: 0.024667 memory: 15239 loss_kpt: 0.000587 acc_pose: 0.808327 loss: 0.000587 2022/09/15 19:56:18 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 19:56:26 - mmengine - INFO - Epoch(train) [57][200/586] lr: 5.000000e-04 eta: 11:14:41 time: 0.471146 data_time: 0.024426 memory: 15239 loss_kpt: 0.000589 acc_pose: 0.864536 loss: 0.000589 2022/09/15 19:56:49 - mmengine - INFO - Epoch(train) [57][250/586] lr: 5.000000e-04 eta: 11:14:21 time: 0.469632 data_time: 0.024912 memory: 15239 loss_kpt: 0.000566 acc_pose: 0.736859 loss: 0.000566 2022/09/15 19:57:12 - mmengine - INFO - Epoch(train) [57][300/586] lr: 5.000000e-04 eta: 11:14:00 time: 0.458664 data_time: 0.024284 memory: 15239 loss_kpt: 0.000586 acc_pose: 0.861788 loss: 0.000586 2022/09/15 19:57:36 - mmengine - INFO - Epoch(train) [57][350/586] lr: 5.000000e-04 eta: 11:13:40 time: 0.473193 data_time: 0.025014 memory: 15239 loss_kpt: 0.000575 acc_pose: 0.869903 loss: 0.000575 2022/09/15 19:57:59 - mmengine - INFO - Epoch(train) [57][400/586] lr: 5.000000e-04 eta: 11:13:19 time: 0.461740 data_time: 0.024534 memory: 15239 loss_kpt: 0.000552 acc_pose: 0.844979 loss: 0.000552 2022/09/15 19:58:22 - mmengine - INFO - Epoch(train) [57][450/586] lr: 5.000000e-04 eta: 11:13:00 time: 0.473381 data_time: 0.025817 memory: 15239 loss_kpt: 0.000587 acc_pose: 0.871962 loss: 0.000587 2022/09/15 19:58:46 - mmengine - INFO - Epoch(train) [57][500/586] lr: 5.000000e-04 eta: 11:12:41 time: 0.477515 data_time: 0.024434 memory: 15239 loss_kpt: 0.000566 acc_pose: 0.775208 loss: 0.000566 2022/09/15 19:59:10 - mmengine - INFO - Epoch(train) [57][550/586] lr: 5.000000e-04 eta: 11:12:22 time: 0.471750 data_time: 0.027971 memory: 15239 loss_kpt: 0.000588 acc_pose: 0.827425 loss: 0.000588 2022/09/15 19:59:26 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 19:59:26 - mmengine - INFO - Saving checkpoint at 57 epochs 2022/09/15 19:59:58 - mmengine - INFO - Epoch(train) [58][50/586] lr: 5.000000e-04 eta: 11:11:04 time: 0.479079 data_time: 0.028061 memory: 15239 loss_kpt: 0.000574 acc_pose: 0.852585 loss: 0.000574 2022/09/15 20:00:21 - mmengine - INFO - Epoch(train) [58][100/586] lr: 5.000000e-04 eta: 11:10:44 time: 0.472430 data_time: 0.025343 memory: 15239 loss_kpt: 0.000564 acc_pose: 0.871123 loss: 0.000564 2022/09/15 20:00:44 - mmengine - INFO - Epoch(train) [58][150/586] lr: 5.000000e-04 eta: 11:10:23 time: 0.456388 data_time: 0.024953 memory: 15239 loss_kpt: 0.000601 acc_pose: 0.848627 loss: 0.000601 2022/09/15 20:01:08 - mmengine - INFO - Epoch(train) [58][200/586] lr: 5.000000e-04 eta: 11:10:04 time: 0.476947 data_time: 0.029893 memory: 15239 loss_kpt: 0.000580 acc_pose: 0.882196 loss: 0.000580 2022/09/15 20:01:31 - mmengine - INFO - Epoch(train) [58][250/586] lr: 5.000000e-04 eta: 11:09:44 time: 0.471502 data_time: 0.024809 memory: 15239 loss_kpt: 0.000574 acc_pose: 0.869787 loss: 0.000574 2022/09/15 20:01:55 - mmengine - INFO - Epoch(train) [58][300/586] lr: 5.000000e-04 eta: 11:09:24 time: 0.462907 data_time: 0.024252 memory: 15239 loss_kpt: 0.000575 acc_pose: 0.895930 loss: 0.000575 2022/09/15 20:02:18 - mmengine - INFO - Epoch(train) [58][350/586] lr: 5.000000e-04 eta: 11:09:04 time: 0.467326 data_time: 0.027627 memory: 15239 loss_kpt: 0.000573 acc_pose: 0.837058 loss: 0.000573 2022/09/15 20:02:41 - mmengine - INFO - Epoch(train) [58][400/586] lr: 5.000000e-04 eta: 11:08:43 time: 0.459422 data_time: 0.023479 memory: 15239 loss_kpt: 0.000587 acc_pose: 0.828225 loss: 0.000587 2022/09/15 20:03:04 - mmengine - INFO - Epoch(train) [58][450/586] lr: 5.000000e-04 eta: 11:08:22 time: 0.461387 data_time: 0.025029 memory: 15239 loss_kpt: 0.000583 acc_pose: 0.863369 loss: 0.000583 2022/09/15 20:03:27 - mmengine - INFO - Epoch(train) [58][500/586] lr: 5.000000e-04 eta: 11:08:02 time: 0.469712 data_time: 0.024420 memory: 15239 loss_kpt: 0.000586 acc_pose: 0.868833 loss: 0.000586 2022/09/15 20:03:51 - mmengine - INFO - Epoch(train) [58][550/586] lr: 5.000000e-04 eta: 11:07:41 time: 0.463411 data_time: 0.024753 memory: 15239 loss_kpt: 0.000580 acc_pose: 0.832851 loss: 0.000580 2022/09/15 20:04:07 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 20:04:07 - mmengine - INFO - Saving checkpoint at 58 epochs 2022/09/15 20:04:20 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 20:04:38 - mmengine - INFO - Epoch(train) [59][50/586] lr: 5.000000e-04 eta: 11:06:23 time: 0.469923 data_time: 0.029190 memory: 15239 loss_kpt: 0.000590 acc_pose: 0.829399 loss: 0.000590 2022/09/15 20:05:01 - mmengine - INFO - Epoch(train) [59][100/586] lr: 5.000000e-04 eta: 11:06:03 time: 0.471084 data_time: 0.025245 memory: 15239 loss_kpt: 0.000557 acc_pose: 0.811014 loss: 0.000557 2022/09/15 20:05:25 - mmengine - INFO - Epoch(train) [59][150/586] lr: 5.000000e-04 eta: 11:05:43 time: 0.465421 data_time: 0.024971 memory: 15239 loss_kpt: 0.000578 acc_pose: 0.878902 loss: 0.000578 2022/09/15 20:05:48 - mmengine - INFO - Epoch(train) [59][200/586] lr: 5.000000e-04 eta: 11:05:22 time: 0.462842 data_time: 0.024029 memory: 15239 loss_kpt: 0.000592 acc_pose: 0.751538 loss: 0.000592 2022/09/15 20:06:11 - mmengine - INFO - Epoch(train) [59][250/586] lr: 5.000000e-04 eta: 11:05:01 time: 0.457042 data_time: 0.024207 memory: 15239 loss_kpt: 0.000593 acc_pose: 0.815464 loss: 0.000593 2022/09/15 20:06:34 - mmengine - INFO - Epoch(train) [59][300/586] lr: 5.000000e-04 eta: 11:04:41 time: 0.472467 data_time: 0.023552 memory: 15239 loss_kpt: 0.000591 acc_pose: 0.857892 loss: 0.000591 2022/09/15 20:06:58 - mmengine - INFO - Epoch(train) [59][350/586] lr: 5.000000e-04 eta: 11:04:21 time: 0.468621 data_time: 0.024116 memory: 15239 loss_kpt: 0.000574 acc_pose: 0.835616 loss: 0.000574 2022/09/15 20:07:21 - mmengine - INFO - Epoch(train) [59][400/586] lr: 5.000000e-04 eta: 11:04:01 time: 0.468244 data_time: 0.024158 memory: 15239 loss_kpt: 0.000569 acc_pose: 0.851032 loss: 0.000569 2022/09/15 20:07:44 - mmengine - INFO - Epoch(train) [59][450/586] lr: 5.000000e-04 eta: 11:03:41 time: 0.469225 data_time: 0.028501 memory: 15239 loss_kpt: 0.000567 acc_pose: 0.843768 loss: 0.000567 2022/09/15 20:08:08 - mmengine - INFO - Epoch(train) [59][500/586] lr: 5.000000e-04 eta: 11:03:22 time: 0.470705 data_time: 0.023960 memory: 15239 loss_kpt: 0.000590 acc_pose: 0.855944 loss: 0.000590 2022/09/15 20:08:31 - mmengine - INFO - Epoch(train) [59][550/586] lr: 5.000000e-04 eta: 11:03:00 time: 0.453593 data_time: 0.025829 memory: 15239 loss_kpt: 0.000593 acc_pose: 0.836730 loss: 0.000593 2022/09/15 20:08:47 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 20:08:47 - mmengine - INFO - Saving checkpoint at 59 epochs 2022/09/15 20:09:19 - mmengine - INFO - Epoch(train) [60][50/586] lr: 5.000000e-04 eta: 11:01:45 time: 0.493196 data_time: 0.034142 memory: 15239 loss_kpt: 0.000585 acc_pose: 0.892017 loss: 0.000585 2022/09/15 20:09:42 - mmengine - INFO - Epoch(train) [60][100/586] lr: 5.000000e-04 eta: 11:01:24 time: 0.459857 data_time: 0.024781 memory: 15239 loss_kpt: 0.000593 acc_pose: 0.891346 loss: 0.000593 2022/09/15 20:10:05 - mmengine - INFO - Epoch(train) [60][150/586] lr: 5.000000e-04 eta: 11:01:04 time: 0.465062 data_time: 0.026672 memory: 15239 loss_kpt: 0.000570 acc_pose: 0.772164 loss: 0.000570 2022/09/15 20:10:29 - mmengine - INFO - Epoch(train) [60][200/586] lr: 5.000000e-04 eta: 11:00:44 time: 0.470437 data_time: 0.024888 memory: 15239 loss_kpt: 0.000587 acc_pose: 0.875183 loss: 0.000587 2022/09/15 20:10:51 - mmengine - INFO - Epoch(train) [60][250/586] lr: 5.000000e-04 eta: 11:00:22 time: 0.455307 data_time: 0.028154 memory: 15239 loss_kpt: 0.000552 acc_pose: 0.845395 loss: 0.000552 2022/09/15 20:11:14 - mmengine - INFO - Epoch(train) [60][300/586] lr: 5.000000e-04 eta: 11:00:01 time: 0.460374 data_time: 0.024402 memory: 15239 loss_kpt: 0.000572 acc_pose: 0.852935 loss: 0.000572 2022/09/15 20:11:38 - mmengine - INFO - Epoch(train) [60][350/586] lr: 5.000000e-04 eta: 10:59:41 time: 0.464851 data_time: 0.024093 memory: 15239 loss_kpt: 0.000575 acc_pose: 0.780062 loss: 0.000575 2022/09/15 20:12:01 - mmengine - INFO - Epoch(train) [60][400/586] lr: 5.000000e-04 eta: 10:59:21 time: 0.465818 data_time: 0.030178 memory: 15239 loss_kpt: 0.000578 acc_pose: 0.765455 loss: 0.000578 2022/09/15 20:12:13 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 20:12:24 - mmengine - INFO - Epoch(train) [60][450/586] lr: 5.000000e-04 eta: 10:58:59 time: 0.457155 data_time: 0.024301 memory: 15239 loss_kpt: 0.000580 acc_pose: 0.770620 loss: 0.000580 2022/09/15 20:12:47 - mmengine - INFO - Epoch(train) [60][500/586] lr: 5.000000e-04 eta: 10:58:40 time: 0.471089 data_time: 0.024267 memory: 15239 loss_kpt: 0.000588 acc_pose: 0.906348 loss: 0.000588 2022/09/15 20:13:10 - mmengine - INFO - Epoch(train) [60][550/586] lr: 5.000000e-04 eta: 10:58:18 time: 0.459810 data_time: 0.028131 memory: 15239 loss_kpt: 0.000574 acc_pose: 0.813512 loss: 0.000574 2022/09/15 20:13:27 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 20:13:27 - mmengine - INFO - Saving checkpoint at 60 epochs 2022/09/15 20:13:47 - mmengine - INFO - Epoch(val) [60][50/407] eta: 0:01:32 time: 0.259810 data_time: 0.015825 memory: 15239 2022/09/15 20:14:00 - mmengine - INFO - Epoch(val) [60][100/407] eta: 0:01:17 time: 0.253325 data_time: 0.010957 memory: 2064 2022/09/15 20:14:13 - mmengine - INFO - Epoch(val) [60][150/407] eta: 0:01:04 time: 0.251513 data_time: 0.008901 memory: 2064 2022/09/15 20:14:25 - mmengine - INFO - Epoch(val) [60][200/407] eta: 0:00:52 time: 0.251675 data_time: 0.008679 memory: 2064 2022/09/15 20:14:38 - mmengine - INFO - Epoch(val) [60][250/407] eta: 0:00:39 time: 0.250649 data_time: 0.008441 memory: 2064 2022/09/15 20:14:50 - mmengine - INFO - Epoch(val) [60][300/407] eta: 0:00:26 time: 0.250381 data_time: 0.008647 memory: 2064 2022/09/15 20:15:03 - mmengine - INFO - Epoch(val) [60][350/407] eta: 0:00:14 time: 0.254078 data_time: 0.008313 memory: 2064 2022/09/15 20:15:15 - mmengine - INFO - Epoch(val) [60][400/407] eta: 0:00:01 time: 0.246456 data_time: 0.008137 memory: 2064 2022/09/15 20:15:50 - mmengine - INFO - Evaluating CocoMetric... 2022/09/15 20:16:03 - mmengine - INFO - Epoch(val) [60][407/407] coco/AP: 0.750994 coco/AP .5: 0.899914 coco/AP .75: 0.815514 coco/AP (M): 0.710198 coco/AP (L): 0.822166 coco/AR: 0.799307 coco/AR .5: 0.936083 coco/AR .75: 0.857053 coco/AR (M): 0.755722 coco/AR (L): 0.862728 2022/09/15 20:16:03 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220915/dark_w48_384/best_coco/AP_epoch_50.pth is removed 2022/09/15 20:16:06 - mmengine - INFO - The best checkpoint with 0.7510 coco/AP at 60 epoch is saved to best_coco/AP_epoch_60.pth. 2022/09/15 20:16:30 - mmengine - INFO - Epoch(train) [61][50/586] lr: 5.000000e-04 eta: 10:57:03 time: 0.474769 data_time: 0.028142 memory: 15239 loss_kpt: 0.000586 acc_pose: 0.865321 loss: 0.000586 2022/09/15 20:16:53 - mmengine - INFO - Epoch(train) [61][100/586] lr: 5.000000e-04 eta: 10:56:42 time: 0.461236 data_time: 0.024593 memory: 15239 loss_kpt: 0.000560 acc_pose: 0.810342 loss: 0.000560 2022/09/15 20:17:16 - mmengine - INFO - Epoch(train) [61][150/586] lr: 5.000000e-04 eta: 10:56:21 time: 0.464064 data_time: 0.024688 memory: 15239 loss_kpt: 0.000565 acc_pose: 0.846028 loss: 0.000565 2022/09/15 20:17:40 - mmengine - INFO - Epoch(train) [61][200/586] lr: 5.000000e-04 eta: 10:56:01 time: 0.463917 data_time: 0.027232 memory: 15239 loss_kpt: 0.000563 acc_pose: 0.869212 loss: 0.000563 2022/09/15 20:18:03 - mmengine - INFO - Epoch(train) [61][250/586] lr: 5.000000e-04 eta: 10:55:40 time: 0.464216 data_time: 0.025784 memory: 15239 loss_kpt: 0.000568 acc_pose: 0.872860 loss: 0.000568 2022/09/15 20:18:26 - mmengine - INFO - Epoch(train) [61][300/586] lr: 5.000000e-04 eta: 10:55:20 time: 0.467837 data_time: 0.025202 memory: 15239 loss_kpt: 0.000577 acc_pose: 0.841227 loss: 0.000577 2022/09/15 20:18:49 - mmengine - INFO - Epoch(train) [61][350/586] lr: 5.000000e-04 eta: 10:54:59 time: 0.459904 data_time: 0.028255 memory: 15239 loss_kpt: 0.000590 acc_pose: 0.851234 loss: 0.000590 2022/09/15 20:19:13 - mmengine - INFO - Epoch(train) [61][400/586] lr: 5.000000e-04 eta: 10:54:39 time: 0.470076 data_time: 0.025013 memory: 15239 loss_kpt: 0.000568 acc_pose: 0.827515 loss: 0.000568 2022/09/15 20:19:36 - mmengine - INFO - Epoch(train) [61][450/586] lr: 5.000000e-04 eta: 10:54:19 time: 0.466756 data_time: 0.024203 memory: 15239 loss_kpt: 0.000575 acc_pose: 0.813845 loss: 0.000575 2022/09/15 20:19:59 - mmengine - INFO - Epoch(train) [61][500/586] lr: 5.000000e-04 eta: 10:53:58 time: 0.460345 data_time: 0.029859 memory: 15239 loss_kpt: 0.000584 acc_pose: 0.833331 loss: 0.000584 2022/09/15 20:20:23 - mmengine - INFO - Epoch(train) [61][550/586] lr: 5.000000e-04 eta: 10:53:38 time: 0.467599 data_time: 0.025659 memory: 15239 loss_kpt: 0.000573 acc_pose: 0.847961 loss: 0.000573 2022/09/15 20:20:39 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 20:20:39 - mmengine - INFO - Saving checkpoint at 61 epochs 2022/09/15 20:21:10 - mmengine - INFO - Epoch(train) [62][50/586] lr: 5.000000e-04 eta: 10:52:22 time: 0.472916 data_time: 0.031312 memory: 15239 loss_kpt: 0.000571 acc_pose: 0.733014 loss: 0.000571 2022/09/15 20:21:33 - mmengine - INFO - Epoch(train) [62][100/586] lr: 5.000000e-04 eta: 10:52:02 time: 0.460346 data_time: 0.025845 memory: 15239 loss_kpt: 0.000572 acc_pose: 0.833245 loss: 0.000572 2022/09/15 20:21:56 - mmengine - INFO - Epoch(train) [62][150/586] lr: 5.000000e-04 eta: 10:51:42 time: 0.468739 data_time: 0.027593 memory: 15239 loss_kpt: 0.000559 acc_pose: 0.870201 loss: 0.000559 2022/09/15 20:22:19 - mmengine - INFO - Epoch(train) [62][200/586] lr: 5.000000e-04 eta: 10:51:20 time: 0.458141 data_time: 0.024307 memory: 15239 loss_kpt: 0.000592 acc_pose: 0.878007 loss: 0.000592 2022/09/15 20:22:42 - mmengine - INFO - Epoch(train) [62][250/586] lr: 5.000000e-04 eta: 10:51:00 time: 0.463866 data_time: 0.027222 memory: 15239 loss_kpt: 0.000568 acc_pose: 0.901397 loss: 0.000568 2022/09/15 20:22:44 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 20:23:06 - mmengine - INFO - Epoch(train) [62][300/586] lr: 5.000000e-04 eta: 10:50:39 time: 0.464373 data_time: 0.025568 memory: 15239 loss_kpt: 0.000586 acc_pose: 0.803050 loss: 0.000586 2022/09/15 20:23:28 - mmengine - INFO - Epoch(train) [62][350/586] lr: 5.000000e-04 eta: 10:50:18 time: 0.457549 data_time: 0.024919 memory: 15239 loss_kpt: 0.000584 acc_pose: 0.863619 loss: 0.000584 2022/09/15 20:23:52 - mmengine - INFO - Epoch(train) [62][400/586] lr: 5.000000e-04 eta: 10:49:57 time: 0.462961 data_time: 0.024670 memory: 15239 loss_kpt: 0.000568 acc_pose: 0.870481 loss: 0.000568 2022/09/15 20:24:15 - mmengine - INFO - Epoch(train) [62][450/586] lr: 5.000000e-04 eta: 10:49:37 time: 0.470551 data_time: 0.023400 memory: 15239 loss_kpt: 0.000570 acc_pose: 0.844000 loss: 0.000570 2022/09/15 20:24:38 - mmengine - INFO - Epoch(train) [62][500/586] lr: 5.000000e-04 eta: 10:49:16 time: 0.458000 data_time: 0.024302 memory: 15239 loss_kpt: 0.000582 acc_pose: 0.810292 loss: 0.000582 2022/09/15 20:25:01 - mmengine - INFO - Epoch(train) [62][550/586] lr: 5.000000e-04 eta: 10:48:56 time: 0.466023 data_time: 0.024133 memory: 15239 loss_kpt: 0.000587 acc_pose: 0.816378 loss: 0.000587 2022/09/15 20:25:18 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 20:25:18 - mmengine - INFO - Saving checkpoint at 62 epochs 2022/09/15 20:25:49 - mmengine - INFO - Epoch(train) [63][50/586] lr: 5.000000e-04 eta: 10:47:42 time: 0.474668 data_time: 0.033268 memory: 15239 loss_kpt: 0.000581 acc_pose: 0.814368 loss: 0.000581 2022/09/15 20:26:12 - mmengine - INFO - Epoch(train) [63][100/586] lr: 5.000000e-04 eta: 10:47:22 time: 0.468937 data_time: 0.024344 memory: 15239 loss_kpt: 0.000566 acc_pose: 0.798502 loss: 0.000566 2022/09/15 20:26:36 - mmengine - INFO - Epoch(train) [63][150/586] lr: 5.000000e-04 eta: 10:47:02 time: 0.468640 data_time: 0.024701 memory: 15239 loss_kpt: 0.000588 acc_pose: 0.864875 loss: 0.000588 2022/09/15 20:26:59 - mmengine - INFO - Epoch(train) [63][200/586] lr: 5.000000e-04 eta: 10:46:42 time: 0.473551 data_time: 0.024835 memory: 15239 loss_kpt: 0.000557 acc_pose: 0.797852 loss: 0.000557 2022/09/15 20:27:23 - mmengine - INFO - Epoch(train) [63][250/586] lr: 5.000000e-04 eta: 10:46:22 time: 0.466359 data_time: 0.024458 memory: 15239 loss_kpt: 0.000564 acc_pose: 0.861867 loss: 0.000564 2022/09/15 20:27:46 - mmengine - INFO - Epoch(train) [63][300/586] lr: 5.000000e-04 eta: 10:46:01 time: 0.465556 data_time: 0.024614 memory: 15239 loss_kpt: 0.000581 acc_pose: 0.856539 loss: 0.000581 2022/09/15 20:28:09 - mmengine - INFO - Epoch(train) [63][350/586] lr: 5.000000e-04 eta: 10:45:41 time: 0.469626 data_time: 0.024382 memory: 15239 loss_kpt: 0.000568 acc_pose: 0.875459 loss: 0.000568 2022/09/15 20:28:32 - mmengine - INFO - Epoch(train) [63][400/586] lr: 5.000000e-04 eta: 10:45:20 time: 0.457582 data_time: 0.024143 memory: 15239 loss_kpt: 0.000579 acc_pose: 0.806598 loss: 0.000579 2022/09/15 20:28:56 - mmengine - INFO - Epoch(train) [63][450/586] lr: 5.000000e-04 eta: 10:45:00 time: 0.464836 data_time: 0.024960 memory: 15239 loss_kpt: 0.000564 acc_pose: 0.794653 loss: 0.000564 2022/09/15 20:29:19 - mmengine - INFO - Epoch(train) [63][500/586] lr: 5.000000e-04 eta: 10:44:39 time: 0.464761 data_time: 0.024543 memory: 15239 loss_kpt: 0.000571 acc_pose: 0.856126 loss: 0.000571 2022/09/15 20:29:42 - mmengine - INFO - Epoch(train) [63][550/586] lr: 5.000000e-04 eta: 10:44:18 time: 0.460923 data_time: 0.024121 memory: 15239 loss_kpt: 0.000566 acc_pose: 0.877812 loss: 0.000566 2022/09/15 20:29:58 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 20:29:58 - mmengine - INFO - Saving checkpoint at 63 epochs 2022/09/15 20:30:29 - mmengine - INFO - Epoch(train) [64][50/586] lr: 5.000000e-04 eta: 10:43:05 time: 0.473461 data_time: 0.028920 memory: 15239 loss_kpt: 0.000572 acc_pose: 0.843252 loss: 0.000572 2022/09/15 20:30:44 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 20:30:52 - mmengine - INFO - Epoch(train) [64][100/586] lr: 5.000000e-04 eta: 10:42:44 time: 0.463336 data_time: 0.025880 memory: 15239 loss_kpt: 0.000560 acc_pose: 0.853388 loss: 0.000560 2022/09/15 20:31:15 - mmengine - INFO - Epoch(train) [64][150/586] lr: 5.000000e-04 eta: 10:42:23 time: 0.461485 data_time: 0.025029 memory: 15239 loss_kpt: 0.000564 acc_pose: 0.890263 loss: 0.000564 2022/09/15 20:31:39 - mmengine - INFO - Epoch(train) [64][200/586] lr: 5.000000e-04 eta: 10:42:03 time: 0.467481 data_time: 0.024738 memory: 15239 loss_kpt: 0.000575 acc_pose: 0.827519 loss: 0.000575 2022/09/15 20:32:02 - mmengine - INFO - Epoch(train) [64][250/586] lr: 5.000000e-04 eta: 10:41:41 time: 0.454977 data_time: 0.023904 memory: 15239 loss_kpt: 0.000574 acc_pose: 0.841389 loss: 0.000574 2022/09/15 20:32:25 - mmengine - INFO - Epoch(train) [64][300/586] lr: 5.000000e-04 eta: 10:41:21 time: 0.460969 data_time: 0.027874 memory: 15239 loss_kpt: 0.000555 acc_pose: 0.866263 loss: 0.000555 2022/09/15 20:32:48 - mmengine - INFO - Epoch(train) [64][350/586] lr: 5.000000e-04 eta: 10:41:01 time: 0.473463 data_time: 0.025388 memory: 15239 loss_kpt: 0.000570 acc_pose: 0.852341 loss: 0.000570 2022/09/15 20:33:11 - mmengine - INFO - Epoch(train) [64][400/586] lr: 5.000000e-04 eta: 10:40:40 time: 0.458264 data_time: 0.024325 memory: 15239 loss_kpt: 0.000585 acc_pose: 0.776464 loss: 0.000585 2022/09/15 20:33:35 - mmengine - INFO - Epoch(train) [64][450/586] lr: 5.000000e-04 eta: 10:40:20 time: 0.472890 data_time: 0.028336 memory: 15239 loss_kpt: 0.000570 acc_pose: 0.877011 loss: 0.000570 2022/09/15 20:33:58 - mmengine - INFO - Epoch(train) [64][500/586] lr: 5.000000e-04 eta: 10:40:00 time: 0.466683 data_time: 0.023667 memory: 15239 loss_kpt: 0.000585 acc_pose: 0.847462 loss: 0.000585 2022/09/15 20:34:21 - mmengine - INFO - Epoch(train) [64][550/586] lr: 5.000000e-04 eta: 10:39:39 time: 0.461081 data_time: 0.025022 memory: 15239 loss_kpt: 0.000569 acc_pose: 0.828586 loss: 0.000569 2022/09/15 20:34:38 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 20:34:38 - mmengine - INFO - Saving checkpoint at 64 epochs 2022/09/15 20:35:09 - mmengine - INFO - Epoch(train) [65][50/586] lr: 5.000000e-04 eta: 10:38:28 time: 0.483791 data_time: 0.032592 memory: 15239 loss_kpt: 0.000556 acc_pose: 0.819671 loss: 0.000556 2022/09/15 20:35:33 - mmengine - INFO - Epoch(train) [65][100/586] lr: 5.000000e-04 eta: 10:38:07 time: 0.468000 data_time: 0.029047 memory: 15239 loss_kpt: 0.000565 acc_pose: 0.887177 loss: 0.000565 2022/09/15 20:35:56 - mmengine - INFO - Epoch(train) [65][150/586] lr: 5.000000e-04 eta: 10:37:47 time: 0.467066 data_time: 0.025265 memory: 15239 loss_kpt: 0.000581 acc_pose: 0.809965 loss: 0.000581 2022/09/15 20:36:20 - mmengine - INFO - Epoch(train) [65][200/586] lr: 5.000000e-04 eta: 10:37:27 time: 0.467944 data_time: 0.025796 memory: 15239 loss_kpt: 0.000568 acc_pose: 0.865201 loss: 0.000568 2022/09/15 20:36:43 - mmengine - INFO - Epoch(train) [65][250/586] lr: 5.000000e-04 eta: 10:37:07 time: 0.466269 data_time: 0.025042 memory: 15239 loss_kpt: 0.000580 acc_pose: 0.892086 loss: 0.000580 2022/09/15 20:37:06 - mmengine - INFO - Epoch(train) [65][300/586] lr: 5.000000e-04 eta: 10:36:47 time: 0.472276 data_time: 0.026382 memory: 15239 loss_kpt: 0.000558 acc_pose: 0.896860 loss: 0.000558 2022/09/15 20:37:30 - mmengine - INFO - Epoch(train) [65][350/586] lr: 5.000000e-04 eta: 10:36:27 time: 0.466693 data_time: 0.026065 memory: 15239 loss_kpt: 0.000548 acc_pose: 0.816497 loss: 0.000548 2022/09/15 20:37:53 - mmengine - INFO - Epoch(train) [65][400/586] lr: 5.000000e-04 eta: 10:36:06 time: 0.460032 data_time: 0.024311 memory: 15239 loss_kpt: 0.000566 acc_pose: 0.857232 loss: 0.000566 2022/09/15 20:38:16 - mmengine - INFO - Epoch(train) [65][450/586] lr: 5.000000e-04 eta: 10:35:45 time: 0.464583 data_time: 0.029130 memory: 15239 loss_kpt: 0.000585 acc_pose: 0.863376 loss: 0.000585 2022/09/15 20:38:38 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 20:38:40 - mmengine - INFO - Epoch(train) [65][500/586] lr: 5.000000e-04 eta: 10:35:25 time: 0.469953 data_time: 0.024537 memory: 15239 loss_kpt: 0.000560 acc_pose: 0.877588 loss: 0.000560 2022/09/15 20:39:02 - mmengine - INFO - Epoch(train) [65][550/586] lr: 5.000000e-04 eta: 10:35:03 time: 0.455732 data_time: 0.024551 memory: 15239 loss_kpt: 0.000564 acc_pose: 0.864671 loss: 0.000564 2022/09/15 20:39:20 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 20:39:20 - mmengine - INFO - Saving checkpoint at 65 epochs 2022/09/15 20:39:51 - mmengine - INFO - Epoch(train) [66][50/586] lr: 5.000000e-04 eta: 10:33:51 time: 0.470170 data_time: 0.035483 memory: 15239 loss_kpt: 0.000575 acc_pose: 0.851646 loss: 0.000575 2022/09/15 20:40:14 - mmengine - INFO - Epoch(train) [66][100/586] lr: 5.000000e-04 eta: 10:33:32 time: 0.471168 data_time: 0.032223 memory: 15239 loss_kpt: 0.000564 acc_pose: 0.853047 loss: 0.000564 2022/09/15 20:40:38 - mmengine - INFO - Epoch(train) [66][150/586] lr: 5.000000e-04 eta: 10:33:13 time: 0.478170 data_time: 0.025003 memory: 15239 loss_kpt: 0.000567 acc_pose: 0.727010 loss: 0.000567 2022/09/15 20:41:02 - mmengine - INFO - Epoch(train) [66][200/586] lr: 5.000000e-04 eta: 10:32:53 time: 0.471140 data_time: 0.028356 memory: 15239 loss_kpt: 0.000580 acc_pose: 0.806819 loss: 0.000580 2022/09/15 20:41:25 - mmengine - INFO - Epoch(train) [66][250/586] lr: 5.000000e-04 eta: 10:32:32 time: 0.464274 data_time: 0.024766 memory: 15239 loss_kpt: 0.000573 acc_pose: 0.866808 loss: 0.000573 2022/09/15 20:41:48 - mmengine - INFO - Epoch(train) [66][300/586] lr: 5.000000e-04 eta: 10:32:12 time: 0.467202 data_time: 0.024655 memory: 15239 loss_kpt: 0.000572 acc_pose: 0.852546 loss: 0.000572 2022/09/15 20:42:12 - mmengine - INFO - Epoch(train) [66][350/586] lr: 5.000000e-04 eta: 10:31:52 time: 0.467322 data_time: 0.025394 memory: 15239 loss_kpt: 0.000571 acc_pose: 0.867302 loss: 0.000571 2022/09/15 20:42:35 - mmengine - INFO - Epoch(train) [66][400/586] lr: 5.000000e-04 eta: 10:31:32 time: 0.473060 data_time: 0.024934 memory: 15239 loss_kpt: 0.000571 acc_pose: 0.859112 loss: 0.000571 2022/09/15 20:42:59 - mmengine - INFO - Epoch(train) [66][450/586] lr: 5.000000e-04 eta: 10:31:12 time: 0.466803 data_time: 0.024901 memory: 15239 loss_kpt: 0.000563 acc_pose: 0.832288 loss: 0.000563 2022/09/15 20:43:22 - mmengine - INFO - Epoch(train) [66][500/586] lr: 5.000000e-04 eta: 10:30:51 time: 0.461126 data_time: 0.024436 memory: 15239 loss_kpt: 0.000563 acc_pose: 0.791049 loss: 0.000563 2022/09/15 20:43:45 - mmengine - INFO - Epoch(train) [66][550/586] lr: 5.000000e-04 eta: 10:30:30 time: 0.463091 data_time: 0.027684 memory: 15239 loss_kpt: 0.000587 acc_pose: 0.821865 loss: 0.000587 2022/09/15 20:44:01 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 20:44:01 - mmengine - INFO - Saving checkpoint at 66 epochs 2022/09/15 20:44:32 - mmengine - INFO - Epoch(train) [67][50/586] lr: 5.000000e-04 eta: 10:29:19 time: 0.476727 data_time: 0.030577 memory: 15239 loss_kpt: 0.000548 acc_pose: 0.817120 loss: 0.000548 2022/09/15 20:44:55 - mmengine - INFO - Epoch(train) [67][100/586] lr: 5.000000e-04 eta: 10:28:59 time: 0.466266 data_time: 0.024975 memory: 15239 loss_kpt: 0.000554 acc_pose: 0.855073 loss: 0.000554 2022/09/15 20:45:19 - mmengine - INFO - Epoch(train) [67][150/586] lr: 5.000000e-04 eta: 10:28:39 time: 0.470785 data_time: 0.025345 memory: 15239 loss_kpt: 0.000583 acc_pose: 0.893616 loss: 0.000583 2022/09/15 20:45:42 - mmengine - INFO - Epoch(train) [67][200/586] lr: 5.000000e-04 eta: 10:28:20 time: 0.474880 data_time: 0.025136 memory: 15239 loss_kpt: 0.000591 acc_pose: 0.848135 loss: 0.000591 2022/09/15 20:46:06 - mmengine - INFO - Epoch(train) [67][250/586] lr: 5.000000e-04 eta: 10:27:59 time: 0.463441 data_time: 0.025075 memory: 15239 loss_kpt: 0.000574 acc_pose: 0.843221 loss: 0.000574 2022/09/15 20:46:28 - mmengine - INFO - Epoch(train) [67][300/586] lr: 5.000000e-04 eta: 10:27:37 time: 0.456649 data_time: 0.024230 memory: 15239 loss_kpt: 0.000547 acc_pose: 0.809049 loss: 0.000547 2022/09/15 20:46:40 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 20:46:52 - mmengine - INFO - Epoch(train) [67][350/586] lr: 5.000000e-04 eta: 10:27:18 time: 0.474853 data_time: 0.025200 memory: 15239 loss_kpt: 0.000566 acc_pose: 0.803624 loss: 0.000566 2022/09/15 20:47:15 - mmengine - INFO - Epoch(train) [67][400/586] lr: 5.000000e-04 eta: 10:26:57 time: 0.456988 data_time: 0.024700 memory: 15239 loss_kpt: 0.000553 acc_pose: 0.853632 loss: 0.000553 2022/09/15 20:47:38 - mmengine - INFO - Epoch(train) [67][450/586] lr: 5.000000e-04 eta: 10:26:35 time: 0.455884 data_time: 0.024804 memory: 15239 loss_kpt: 0.000563 acc_pose: 0.877630 loss: 0.000563 2022/09/15 20:48:02 - mmengine - INFO - Epoch(train) [67][500/586] lr: 5.000000e-04 eta: 10:26:15 time: 0.473343 data_time: 0.028720 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.841974 loss: 0.000543 2022/09/15 20:48:25 - mmengine - INFO - Epoch(train) [67][550/586] lr: 5.000000e-04 eta: 10:25:54 time: 0.461134 data_time: 0.025585 memory: 15239 loss_kpt: 0.000568 acc_pose: 0.883563 loss: 0.000568 2022/09/15 20:48:41 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 20:48:41 - mmengine - INFO - Saving checkpoint at 67 epochs 2022/09/15 20:49:12 - mmengine - INFO - Epoch(train) [68][50/586] lr: 5.000000e-04 eta: 10:24:45 time: 0.484463 data_time: 0.033071 memory: 15239 loss_kpt: 0.000550 acc_pose: 0.881444 loss: 0.000550 2022/09/15 20:49:35 - mmengine - INFO - Epoch(train) [68][100/586] lr: 5.000000e-04 eta: 10:24:24 time: 0.460158 data_time: 0.024449 memory: 15239 loss_kpt: 0.000555 acc_pose: 0.839858 loss: 0.000555 2022/09/15 20:49:58 - mmengine - INFO - Epoch(train) [68][150/586] lr: 5.000000e-04 eta: 10:24:03 time: 0.459892 data_time: 0.024888 memory: 15239 loss_kpt: 0.000582 acc_pose: 0.872109 loss: 0.000582 2022/09/15 20:50:22 - mmengine - INFO - Epoch(train) [68][200/586] lr: 5.000000e-04 eta: 10:23:43 time: 0.468473 data_time: 0.024154 memory: 15239 loss_kpt: 0.000577 acc_pose: 0.814730 loss: 0.000577 2022/09/15 20:50:45 - mmengine - INFO - Epoch(train) [68][250/586] lr: 5.000000e-04 eta: 10:23:22 time: 0.464989 data_time: 0.024780 memory: 15239 loss_kpt: 0.000563 acc_pose: 0.810885 loss: 0.000563 2022/09/15 20:51:08 - mmengine - INFO - Epoch(train) [68][300/586] lr: 5.000000e-04 eta: 10:23:02 time: 0.461768 data_time: 0.025800 memory: 15239 loss_kpt: 0.000559 acc_pose: 0.866817 loss: 0.000559 2022/09/15 20:51:31 - mmengine - INFO - Epoch(train) [68][350/586] lr: 5.000000e-04 eta: 10:22:41 time: 0.460438 data_time: 0.024899 memory: 15239 loss_kpt: 0.000563 acc_pose: 0.857582 loss: 0.000563 2022/09/15 20:51:55 - mmengine - INFO - Epoch(train) [68][400/586] lr: 5.000000e-04 eta: 10:22:21 time: 0.474610 data_time: 0.027220 memory: 15239 loss_kpt: 0.000570 acc_pose: 0.844317 loss: 0.000570 2022/09/15 20:52:18 - mmengine - INFO - Epoch(train) [68][450/586] lr: 5.000000e-04 eta: 10:22:00 time: 0.457968 data_time: 0.024769 memory: 15239 loss_kpt: 0.000579 acc_pose: 0.831931 loss: 0.000579 2022/09/15 20:52:41 - mmengine - INFO - Epoch(train) [68][500/586] lr: 5.000000e-04 eta: 10:21:39 time: 0.466871 data_time: 0.025680 memory: 15239 loss_kpt: 0.000579 acc_pose: 0.779794 loss: 0.000579 2022/09/15 20:53:04 - mmengine - INFO - Epoch(train) [68][550/586] lr: 5.000000e-04 eta: 10:21:18 time: 0.460728 data_time: 0.024277 memory: 15239 loss_kpt: 0.000555 acc_pose: 0.864789 loss: 0.000555 2022/09/15 20:53:21 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 20:53:21 - mmengine - INFO - Saving checkpoint at 68 epochs 2022/09/15 20:53:52 - mmengine - INFO - Epoch(train) [69][50/586] lr: 5.000000e-04 eta: 10:20:09 time: 0.478653 data_time: 0.038998 memory: 15239 loss_kpt: 0.000567 acc_pose: 0.899393 loss: 0.000567 2022/09/15 20:54:16 - mmengine - INFO - Epoch(train) [69][100/586] lr: 5.000000e-04 eta: 10:19:49 time: 0.469214 data_time: 0.024890 memory: 15239 loss_kpt: 0.000569 acc_pose: 0.890865 loss: 0.000569 2022/09/15 20:54:39 - mmengine - INFO - Epoch(train) [69][150/586] lr: 5.000000e-04 eta: 10:19:29 time: 0.467985 data_time: 0.025794 memory: 15239 loss_kpt: 0.000573 acc_pose: 0.815806 loss: 0.000573 2022/09/15 20:54:40 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 20:55:02 - mmengine - INFO - Epoch(train) [69][200/586] lr: 5.000000e-04 eta: 10:19:09 time: 0.468080 data_time: 0.029190 memory: 15239 loss_kpt: 0.000558 acc_pose: 0.866534 loss: 0.000558 2022/09/15 20:55:26 - mmengine - INFO - Epoch(train) [69][250/586] lr: 5.000000e-04 eta: 10:18:48 time: 0.467022 data_time: 0.023887 memory: 15239 loss_kpt: 0.000573 acc_pose: 0.849900 loss: 0.000573 2022/09/15 20:55:49 - mmengine - INFO - Epoch(train) [69][300/586] lr: 5.000000e-04 eta: 10:18:28 time: 0.468029 data_time: 0.025494 memory: 15239 loss_kpt: 0.000585 acc_pose: 0.849981 loss: 0.000585 2022/09/15 20:56:13 - mmengine - INFO - Epoch(train) [69][350/586] lr: 5.000000e-04 eta: 10:18:08 time: 0.467928 data_time: 0.029233 memory: 15239 loss_kpt: 0.000555 acc_pose: 0.798262 loss: 0.000555 2022/09/15 20:56:36 - mmengine - INFO - Epoch(train) [69][400/586] lr: 5.000000e-04 eta: 10:17:48 time: 0.470615 data_time: 0.024070 memory: 15239 loss_kpt: 0.000559 acc_pose: 0.864788 loss: 0.000559 2022/09/15 20:56:59 - mmengine - INFO - Epoch(train) [69][450/586] lr: 5.000000e-04 eta: 10:17:27 time: 0.464851 data_time: 0.024760 memory: 15239 loss_kpt: 0.000556 acc_pose: 0.808014 loss: 0.000556 2022/09/15 20:57:23 - mmengine - INFO - Epoch(train) [69][500/586] lr: 5.000000e-04 eta: 10:17:08 time: 0.473580 data_time: 0.028381 memory: 15239 loss_kpt: 0.000580 acc_pose: 0.799012 loss: 0.000580 2022/09/15 20:57:47 - mmengine - INFO - Epoch(train) [69][550/586] lr: 5.000000e-04 eta: 10:16:48 time: 0.472650 data_time: 0.024818 memory: 15239 loss_kpt: 0.000564 acc_pose: 0.810630 loss: 0.000564 2022/09/15 20:58:03 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 20:58:03 - mmengine - INFO - Saving checkpoint at 69 epochs 2022/09/15 20:58:34 - mmengine - INFO - Epoch(train) [70][50/586] lr: 5.000000e-04 eta: 10:15:39 time: 0.471254 data_time: 0.028638 memory: 15239 loss_kpt: 0.000546 acc_pose: 0.845269 loss: 0.000546 2022/09/15 20:58:57 - mmengine - INFO - Epoch(train) [70][100/586] lr: 5.000000e-04 eta: 10:15:18 time: 0.464839 data_time: 0.025994 memory: 15239 loss_kpt: 0.000573 acc_pose: 0.861218 loss: 0.000573 2022/09/15 20:59:20 - mmengine - INFO - Epoch(train) [70][150/586] lr: 5.000000e-04 eta: 10:14:57 time: 0.458674 data_time: 0.025432 memory: 15239 loss_kpt: 0.000564 acc_pose: 0.858420 loss: 0.000564 2022/09/15 20:59:44 - mmengine - INFO - Epoch(train) [70][200/586] lr: 5.000000e-04 eta: 10:14:37 time: 0.471572 data_time: 0.027770 memory: 15239 loss_kpt: 0.000561 acc_pose: 0.849088 loss: 0.000561 2022/09/15 21:00:07 - mmengine - INFO - Epoch(train) [70][250/586] lr: 5.000000e-04 eta: 10:14:16 time: 0.464833 data_time: 0.027924 memory: 15239 loss_kpt: 0.000572 acc_pose: 0.856821 loss: 0.000572 2022/09/15 21:00:30 - mmengine - INFO - Epoch(train) [70][300/586] lr: 5.000000e-04 eta: 10:13:55 time: 0.460524 data_time: 0.024775 memory: 15239 loss_kpt: 0.000565 acc_pose: 0.809063 loss: 0.000565 2022/09/15 21:00:54 - mmengine - INFO - Epoch(train) [70][350/586] lr: 5.000000e-04 eta: 10:13:36 time: 0.476180 data_time: 0.024477 memory: 15239 loss_kpt: 0.000557 acc_pose: 0.826663 loss: 0.000557 2022/09/15 21:01:17 - mmengine - INFO - Epoch(train) [70][400/586] lr: 5.000000e-04 eta: 10:13:16 time: 0.468199 data_time: 0.024829 memory: 15239 loss_kpt: 0.000556 acc_pose: 0.796489 loss: 0.000556 2022/09/15 21:01:40 - mmengine - INFO - Epoch(train) [70][450/586] lr: 5.000000e-04 eta: 10:12:55 time: 0.461824 data_time: 0.023733 memory: 15239 loss_kpt: 0.000580 acc_pose: 0.848690 loss: 0.000580 2022/09/15 21:02:04 - mmengine - INFO - Epoch(train) [70][500/586] lr: 5.000000e-04 eta: 10:12:34 time: 0.468084 data_time: 0.024578 memory: 15239 loss_kpt: 0.000571 acc_pose: 0.776747 loss: 0.000571 2022/09/15 21:02:27 - mmengine - INFO - Epoch(train) [70][550/586] lr: 5.000000e-04 eta: 10:12:14 time: 0.466815 data_time: 0.025496 memory: 15239 loss_kpt: 0.000558 acc_pose: 0.837115 loss: 0.000558 2022/09/15 21:02:34 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 21:02:43 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 21:02:44 - mmengine - INFO - Saving checkpoint at 70 epochs 2022/09/15 21:03:05 - mmengine - INFO - Epoch(val) [70][50/407] eta: 0:01:32 time: 0.259966 data_time: 0.014400 memory: 15239 2022/09/15 21:03:18 - mmengine - INFO - Epoch(val) [70][100/407] eta: 0:01:18 time: 0.254436 data_time: 0.008467 memory: 2064 2022/09/15 21:03:31 - mmengine - INFO - Epoch(val) [70][150/407] eta: 0:01:04 time: 0.251445 data_time: 0.008716 memory: 2064 2022/09/15 21:03:43 - mmengine - INFO - Epoch(val) [70][200/407] eta: 0:00:51 time: 0.249627 data_time: 0.008175 memory: 2064 2022/09/15 21:03:56 - mmengine - INFO - Epoch(val) [70][250/407] eta: 0:00:39 time: 0.250487 data_time: 0.008379 memory: 2064 2022/09/15 21:04:08 - mmengine - INFO - Epoch(val) [70][300/407] eta: 0:00:26 time: 0.250242 data_time: 0.008839 memory: 2064 2022/09/15 21:04:21 - mmengine - INFO - Epoch(val) [70][350/407] eta: 0:00:14 time: 0.248513 data_time: 0.007980 memory: 2064 2022/09/15 21:04:33 - mmengine - INFO - Epoch(val) [70][400/407] eta: 0:00:01 time: 0.247706 data_time: 0.008148 memory: 2064 2022/09/15 21:05:08 - mmengine - INFO - Evaluating CocoMetric... 2022/09/15 21:05:21 - mmengine - INFO - Epoch(val) [70][407/407] coco/AP: 0.753235 coco/AP .5: 0.900494 coco/AP .75: 0.815904 coco/AP (M): 0.714583 coco/AP (L): 0.823529 coco/AR: 0.802361 coco/AR .5: 0.937500 coco/AR .75: 0.859572 coco/AR (M): 0.760202 coco/AR (L): 0.863805 2022/09/15 21:05:21 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220915/dark_w48_384/best_coco/AP_epoch_60.pth is removed 2022/09/15 21:05:25 - mmengine - INFO - The best checkpoint with 0.7532 coco/AP at 70 epoch is saved to best_coco/AP_epoch_70.pth. 2022/09/15 21:05:49 - mmengine - INFO - Epoch(train) [71][50/586] lr: 5.000000e-04 eta: 10:11:07 time: 0.488056 data_time: 0.029468 memory: 15239 loss_kpt: 0.000572 acc_pose: 0.825147 loss: 0.000572 2022/09/15 21:06:12 - mmengine - INFO - Epoch(train) [71][100/586] lr: 5.000000e-04 eta: 10:10:47 time: 0.463469 data_time: 0.025067 memory: 15239 loss_kpt: 0.000560 acc_pose: 0.866122 loss: 0.000560 2022/09/15 21:06:35 - mmengine - INFO - Epoch(train) [71][150/586] lr: 5.000000e-04 eta: 10:10:25 time: 0.458524 data_time: 0.024195 memory: 15239 loss_kpt: 0.000562 acc_pose: 0.796210 loss: 0.000562 2022/09/15 21:06:59 - mmengine - INFO - Epoch(train) [71][200/586] lr: 5.000000e-04 eta: 10:10:05 time: 0.471465 data_time: 0.030162 memory: 15239 loss_kpt: 0.000559 acc_pose: 0.756357 loss: 0.000559 2022/09/15 21:07:22 - mmengine - INFO - Epoch(train) [71][250/586] lr: 5.000000e-04 eta: 10:09:45 time: 0.465658 data_time: 0.024718 memory: 15239 loss_kpt: 0.000549 acc_pose: 0.880695 loss: 0.000549 2022/09/15 21:07:45 - mmengine - INFO - Epoch(train) [71][300/586] lr: 5.000000e-04 eta: 10:09:23 time: 0.457375 data_time: 0.024583 memory: 15239 loss_kpt: 0.000575 acc_pose: 0.851687 loss: 0.000575 2022/09/15 21:08:09 - mmengine - INFO - Epoch(train) [71][350/586] lr: 5.000000e-04 eta: 10:09:03 time: 0.471312 data_time: 0.024655 memory: 15239 loss_kpt: 0.000569 acc_pose: 0.746248 loss: 0.000569 2022/09/15 21:08:32 - mmengine - INFO - Epoch(train) [71][400/586] lr: 5.000000e-04 eta: 10:08:43 time: 0.471630 data_time: 0.026714 memory: 15239 loss_kpt: 0.000572 acc_pose: 0.825573 loss: 0.000572 2022/09/15 21:08:55 - mmengine - INFO - Epoch(train) [71][450/586] lr: 5.000000e-04 eta: 10:08:23 time: 0.463649 data_time: 0.024320 memory: 15239 loss_kpt: 0.000567 acc_pose: 0.887368 loss: 0.000567 2022/09/15 21:09:19 - mmengine - INFO - Epoch(train) [71][500/586] lr: 5.000000e-04 eta: 10:08:03 time: 0.473595 data_time: 0.031173 memory: 15239 loss_kpt: 0.000552 acc_pose: 0.851539 loss: 0.000552 2022/09/15 21:09:42 - mmengine - INFO - Epoch(train) [71][550/586] lr: 5.000000e-04 eta: 10:07:43 time: 0.467696 data_time: 0.023907 memory: 15239 loss_kpt: 0.000555 acc_pose: 0.784124 loss: 0.000555 2022/09/15 21:09:59 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 21:09:59 - mmengine - INFO - Saving checkpoint at 71 epochs 2022/09/15 21:10:30 - mmengine - INFO - Epoch(train) [72][50/586] lr: 5.000000e-04 eta: 10:06:35 time: 0.472222 data_time: 0.028452 memory: 15239 loss_kpt: 0.000592 acc_pose: 0.916563 loss: 0.000592 2022/09/15 21:10:53 - mmengine - INFO - Epoch(train) [72][100/586] lr: 5.000000e-04 eta: 10:06:15 time: 0.474384 data_time: 0.024154 memory: 15239 loss_kpt: 0.000554 acc_pose: 0.856498 loss: 0.000554 2022/09/15 21:11:16 - mmengine - INFO - Epoch(train) [72][150/586] lr: 5.000000e-04 eta: 10:05:54 time: 0.456274 data_time: 0.024167 memory: 15239 loss_kpt: 0.000558 acc_pose: 0.851971 loss: 0.000558 2022/09/15 21:11:40 - mmengine - INFO - Epoch(train) [72][200/586] lr: 5.000000e-04 eta: 10:05:34 time: 0.469446 data_time: 0.024227 memory: 15239 loss_kpt: 0.000570 acc_pose: 0.744686 loss: 0.000570 2022/09/15 21:12:03 - mmengine - INFO - Epoch(train) [72][250/586] lr: 5.000000e-04 eta: 10:05:12 time: 0.459968 data_time: 0.023724 memory: 15239 loss_kpt: 0.000569 acc_pose: 0.855655 loss: 0.000569 2022/09/15 21:12:26 - mmengine - INFO - Epoch(train) [72][300/586] lr: 5.000000e-04 eta: 10:04:52 time: 0.463591 data_time: 0.026255 memory: 15239 loss_kpt: 0.000561 acc_pose: 0.867137 loss: 0.000561 2022/09/15 21:12:49 - mmengine - INFO - Epoch(train) [72][350/586] lr: 5.000000e-04 eta: 10:04:31 time: 0.469129 data_time: 0.024118 memory: 15239 loss_kpt: 0.000572 acc_pose: 0.853364 loss: 0.000572 2022/09/15 21:13:10 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 21:13:13 - mmengine - INFO - Epoch(train) [72][400/586] lr: 5.000000e-04 eta: 10:04:11 time: 0.464354 data_time: 0.029097 memory: 15239 loss_kpt: 0.000573 acc_pose: 0.890358 loss: 0.000573 2022/09/15 21:13:35 - mmengine - INFO - Epoch(train) [72][450/586] lr: 5.000000e-04 eta: 10:03:49 time: 0.456150 data_time: 0.024710 memory: 15239 loss_kpt: 0.000561 acc_pose: 0.848780 loss: 0.000561 2022/09/15 21:13:59 - mmengine - INFO - Epoch(train) [72][500/586] lr: 5.000000e-04 eta: 10:03:29 time: 0.472921 data_time: 0.023989 memory: 15239 loss_kpt: 0.000555 acc_pose: 0.832505 loss: 0.000555 2022/09/15 21:14:22 - mmengine - INFO - Epoch(train) [72][550/586] lr: 5.000000e-04 eta: 10:03:09 time: 0.466941 data_time: 0.024133 memory: 15239 loss_kpt: 0.000549 acc_pose: 0.889414 loss: 0.000549 2022/09/15 21:14:39 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 21:14:39 - mmengine - INFO - Saving checkpoint at 72 epochs 2022/09/15 21:15:09 - mmengine - INFO - Epoch(train) [73][50/586] lr: 5.000000e-04 eta: 10:02:02 time: 0.476391 data_time: 0.034095 memory: 15239 loss_kpt: 0.000555 acc_pose: 0.851910 loss: 0.000555 2022/09/15 21:15:33 - mmengine - INFO - Epoch(train) [73][100/586] lr: 5.000000e-04 eta: 10:01:42 time: 0.470756 data_time: 0.027797 memory: 15239 loss_kpt: 0.000566 acc_pose: 0.796516 loss: 0.000566 2022/09/15 21:15:56 - mmengine - INFO - Epoch(train) [73][150/586] lr: 5.000000e-04 eta: 10:01:22 time: 0.472005 data_time: 0.025219 memory: 15239 loss_kpt: 0.000563 acc_pose: 0.822290 loss: 0.000563 2022/09/15 21:16:20 - mmengine - INFO - Epoch(train) [73][200/586] lr: 5.000000e-04 eta: 10:01:02 time: 0.463410 data_time: 0.024571 memory: 15239 loss_kpt: 0.000554 acc_pose: 0.831281 loss: 0.000554 2022/09/15 21:16:43 - mmengine - INFO - Epoch(train) [73][250/586] lr: 5.000000e-04 eta: 10:00:41 time: 0.470836 data_time: 0.025062 memory: 15239 loss_kpt: 0.000550 acc_pose: 0.901755 loss: 0.000550 2022/09/15 21:17:06 - mmengine - INFO - Epoch(train) [73][300/586] lr: 5.000000e-04 eta: 10:00:20 time: 0.461498 data_time: 0.029659 memory: 15239 loss_kpt: 0.000578 acc_pose: 0.887916 loss: 0.000578 2022/09/15 21:17:30 - mmengine - INFO - Epoch(train) [73][350/586] lr: 5.000000e-04 eta: 10:00:00 time: 0.467790 data_time: 0.024997 memory: 15239 loss_kpt: 0.000561 acc_pose: 0.746156 loss: 0.000561 2022/09/15 21:17:54 - mmengine - INFO - Epoch(train) [73][400/586] lr: 5.000000e-04 eta: 9:59:41 time: 0.483932 data_time: 0.025367 memory: 15239 loss_kpt: 0.000545 acc_pose: 0.855754 loss: 0.000545 2022/09/15 21:18:17 - mmengine - INFO - Epoch(train) [73][450/586] lr: 5.000000e-04 eta: 9:59:20 time: 0.463221 data_time: 0.024067 memory: 15239 loss_kpt: 0.000550 acc_pose: 0.855053 loss: 0.000550 2022/09/15 21:18:41 - mmengine - INFO - Epoch(train) [73][500/586] lr: 5.000000e-04 eta: 9:59:01 time: 0.475332 data_time: 0.025730 memory: 15239 loss_kpt: 0.000572 acc_pose: 0.874338 loss: 0.000572 2022/09/15 21:19:04 - mmengine - INFO - Epoch(train) [73][550/586] lr: 5.000000e-04 eta: 9:58:40 time: 0.464220 data_time: 0.025609 memory: 15239 loss_kpt: 0.000569 acc_pose: 0.844611 loss: 0.000569 2022/09/15 21:19:21 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 21:19:21 - mmengine - INFO - Saving checkpoint at 73 epochs 2022/09/15 21:19:54 - mmengine - INFO - Epoch(train) [74][50/586] lr: 5.000000e-04 eta: 9:57:35 time: 0.485222 data_time: 0.031388 memory: 15239 loss_kpt: 0.000552 acc_pose: 0.848254 loss: 0.000552 2022/09/15 21:20:18 - mmengine - INFO - Epoch(train) [74][100/586] lr: 5.000000e-04 eta: 9:57:16 time: 0.481530 data_time: 0.024519 memory: 15239 loss_kpt: 0.000561 acc_pose: 0.822125 loss: 0.000561 2022/09/15 21:20:41 - mmengine - INFO - Epoch(train) [74][150/586] lr: 5.000000e-04 eta: 9:56:55 time: 0.468076 data_time: 0.026109 memory: 15239 loss_kpt: 0.000566 acc_pose: 0.840155 loss: 0.000566 2022/09/15 21:21:05 - mmengine - INFO - Epoch(train) [74][200/586] lr: 5.000000e-04 eta: 9:56:35 time: 0.471300 data_time: 0.024876 memory: 15239 loss_kpt: 0.000578 acc_pose: 0.873722 loss: 0.000578 2022/09/15 21:21:15 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 21:21:28 - mmengine - INFO - Epoch(train) [74][250/586] lr: 5.000000e-04 eta: 9:56:15 time: 0.471026 data_time: 0.024819 memory: 15239 loss_kpt: 0.000542 acc_pose: 0.892278 loss: 0.000542 2022/09/15 21:21:52 - mmengine - INFO - Epoch(train) [74][300/586] lr: 5.000000e-04 eta: 9:55:55 time: 0.473575 data_time: 0.025458 memory: 15239 loss_kpt: 0.000559 acc_pose: 0.818020 loss: 0.000559 2022/09/15 21:22:15 - mmengine - INFO - Epoch(train) [74][350/586] lr: 5.000000e-04 eta: 9:55:35 time: 0.469731 data_time: 0.024765 memory: 15239 loss_kpt: 0.000548 acc_pose: 0.778816 loss: 0.000548 2022/09/15 21:22:39 - mmengine - INFO - Epoch(train) [74][400/586] lr: 5.000000e-04 eta: 9:55:15 time: 0.475133 data_time: 0.026012 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.915387 loss: 0.000543 2022/09/15 21:23:03 - mmengine - INFO - Epoch(train) [74][450/586] lr: 5.000000e-04 eta: 9:54:55 time: 0.475107 data_time: 0.027158 memory: 15239 loss_kpt: 0.000562 acc_pose: 0.864856 loss: 0.000562 2022/09/15 21:23:26 - mmengine - INFO - Epoch(train) [74][500/586] lr: 5.000000e-04 eta: 9:54:35 time: 0.465845 data_time: 0.026769 memory: 15239 loss_kpt: 0.000577 acc_pose: 0.790937 loss: 0.000577 2022/09/15 21:23:50 - mmengine - INFO - Epoch(train) [74][550/586] lr: 5.000000e-04 eta: 9:54:15 time: 0.475419 data_time: 0.024350 memory: 15239 loss_kpt: 0.000553 acc_pose: 0.869995 loss: 0.000553 2022/09/15 21:24:06 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 21:24:07 - mmengine - INFO - Saving checkpoint at 74 epochs 2022/09/15 21:24:38 - mmengine - INFO - Epoch(train) [75][50/586] lr: 5.000000e-04 eta: 9:53:10 time: 0.476689 data_time: 0.031911 memory: 15239 loss_kpt: 0.000561 acc_pose: 0.917211 loss: 0.000561 2022/09/15 21:25:01 - mmengine - INFO - Epoch(train) [75][100/586] lr: 5.000000e-04 eta: 9:52:50 time: 0.470107 data_time: 0.025767 memory: 15239 loss_kpt: 0.000561 acc_pose: 0.873752 loss: 0.000561 2022/09/15 21:25:25 - mmengine - INFO - Epoch(train) [75][150/586] lr: 5.000000e-04 eta: 9:52:30 time: 0.475221 data_time: 0.025425 memory: 15239 loss_kpt: 0.000549 acc_pose: 0.837127 loss: 0.000549 2022/09/15 21:25:48 - mmengine - INFO - Epoch(train) [75][200/586] lr: 5.000000e-04 eta: 9:52:09 time: 0.464726 data_time: 0.026055 memory: 15239 loss_kpt: 0.000555 acc_pose: 0.844418 loss: 0.000555 2022/09/15 21:26:11 - mmengine - INFO - Epoch(train) [75][250/586] lr: 5.000000e-04 eta: 9:51:48 time: 0.465157 data_time: 0.024569 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.863782 loss: 0.000543 2022/09/15 21:26:35 - mmengine - INFO - Epoch(train) [75][300/586] lr: 5.000000e-04 eta: 9:51:29 time: 0.476232 data_time: 0.025791 memory: 15239 loss_kpt: 0.000548 acc_pose: 0.839358 loss: 0.000548 2022/09/15 21:26:59 - mmengine - INFO - Epoch(train) [75][350/586] lr: 5.000000e-04 eta: 9:51:08 time: 0.465998 data_time: 0.026182 memory: 15239 loss_kpt: 0.000551 acc_pose: 0.862536 loss: 0.000551 2022/09/15 21:27:22 - mmengine - INFO - Epoch(train) [75][400/586] lr: 5.000000e-04 eta: 9:50:48 time: 0.474618 data_time: 0.025048 memory: 15239 loss_kpt: 0.000563 acc_pose: 0.833163 loss: 0.000563 2022/09/15 21:27:46 - mmengine - INFO - Epoch(train) [75][450/586] lr: 5.000000e-04 eta: 9:50:28 time: 0.473279 data_time: 0.029079 memory: 15239 loss_kpt: 0.000552 acc_pose: 0.805045 loss: 0.000552 2022/09/15 21:28:09 - mmengine - INFO - Epoch(train) [75][500/586] lr: 5.000000e-04 eta: 9:50:08 time: 0.470184 data_time: 0.026374 memory: 15239 loss_kpt: 0.000551 acc_pose: 0.818491 loss: 0.000551 2022/09/15 21:28:33 - mmengine - INFO - Epoch(train) [75][550/586] lr: 5.000000e-04 eta: 9:49:48 time: 0.471034 data_time: 0.024238 memory: 15239 loss_kpt: 0.000567 acc_pose: 0.836847 loss: 0.000567 2022/09/15 21:28:50 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 21:28:50 - mmengine - INFO - Saving checkpoint at 75 epochs 2022/09/15 21:29:20 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 21:29:20 - mmengine - INFO - Epoch(train) [76][50/586] lr: 5.000000e-04 eta: 9:48:43 time: 0.471097 data_time: 0.030961 memory: 15239 loss_kpt: 0.000562 acc_pose: 0.849311 loss: 0.000562 2022/09/15 21:29:44 - mmengine - INFO - Epoch(train) [76][100/586] lr: 5.000000e-04 eta: 9:48:23 time: 0.475664 data_time: 0.025072 memory: 15239 loss_kpt: 0.000538 acc_pose: 0.887052 loss: 0.000538 2022/09/15 21:30:08 - mmengine - INFO - Epoch(train) [76][150/586] lr: 5.000000e-04 eta: 9:48:04 time: 0.481730 data_time: 0.025336 memory: 15239 loss_kpt: 0.000565 acc_pose: 0.819682 loss: 0.000565 2022/09/15 21:30:31 - mmengine - INFO - Epoch(train) [76][200/586] lr: 5.000000e-04 eta: 9:47:43 time: 0.464739 data_time: 0.025083 memory: 15239 loss_kpt: 0.000553 acc_pose: 0.777707 loss: 0.000553 2022/09/15 21:30:56 - mmengine - INFO - Epoch(train) [76][250/586] lr: 5.000000e-04 eta: 9:47:24 time: 0.485857 data_time: 0.030215 memory: 15239 loss_kpt: 0.000539 acc_pose: 0.876712 loss: 0.000539 2022/09/15 21:31:20 - mmengine - INFO - Epoch(train) [76][300/586] lr: 5.000000e-04 eta: 9:47:05 time: 0.479197 data_time: 0.030146 memory: 15239 loss_kpt: 0.000551 acc_pose: 0.809807 loss: 0.000551 2022/09/15 21:31:44 - mmengine - INFO - Epoch(train) [76][350/586] lr: 5.000000e-04 eta: 9:46:46 time: 0.485929 data_time: 0.034445 memory: 15239 loss_kpt: 0.000562 acc_pose: 0.840920 loss: 0.000562 2022/09/15 21:32:08 - mmengine - INFO - Epoch(train) [76][400/586] lr: 5.000000e-04 eta: 9:46:26 time: 0.477622 data_time: 0.025607 memory: 15239 loss_kpt: 0.000568 acc_pose: 0.792416 loss: 0.000568 2022/09/15 21:32:31 - mmengine - INFO - Epoch(train) [76][450/586] lr: 5.000000e-04 eta: 9:46:06 time: 0.469627 data_time: 0.026032 memory: 15239 loss_kpt: 0.000542 acc_pose: 0.897936 loss: 0.000542 2022/09/15 21:32:54 - mmengine - INFO - Epoch(train) [76][500/586] lr: 5.000000e-04 eta: 9:45:44 time: 0.460073 data_time: 0.028009 memory: 15239 loss_kpt: 0.000567 acc_pose: 0.889005 loss: 0.000567 2022/09/15 21:33:18 - mmengine - INFO - Epoch(train) [76][550/586] lr: 5.000000e-04 eta: 9:45:25 time: 0.474968 data_time: 0.031730 memory: 15239 loss_kpt: 0.000540 acc_pose: 0.847824 loss: 0.000540 2022/09/15 21:33:35 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 21:33:35 - mmengine - INFO - Saving checkpoint at 76 epochs 2022/09/15 21:34:06 - mmengine - INFO - Epoch(train) [77][50/586] lr: 5.000000e-04 eta: 9:44:20 time: 0.472130 data_time: 0.033579 memory: 15239 loss_kpt: 0.000561 acc_pose: 0.785152 loss: 0.000561 2022/09/15 21:34:30 - mmengine - INFO - Epoch(train) [77][100/586] lr: 5.000000e-04 eta: 9:44:01 time: 0.479648 data_time: 0.027923 memory: 15239 loss_kpt: 0.000553 acc_pose: 0.866198 loss: 0.000553 2022/09/15 21:34:53 - mmengine - INFO - Epoch(train) [77][150/586] lr: 5.000000e-04 eta: 9:43:40 time: 0.466489 data_time: 0.027739 memory: 15239 loss_kpt: 0.000564 acc_pose: 0.835462 loss: 0.000564 2022/09/15 21:35:17 - mmengine - INFO - Epoch(train) [77][200/586] lr: 5.000000e-04 eta: 9:43:19 time: 0.468064 data_time: 0.027880 memory: 15239 loss_kpt: 0.000550 acc_pose: 0.834199 loss: 0.000550 2022/09/15 21:35:40 - mmengine - INFO - Epoch(train) [77][250/586] lr: 5.000000e-04 eta: 9:42:59 time: 0.471419 data_time: 0.025657 memory: 15239 loss_kpt: 0.000558 acc_pose: 0.909004 loss: 0.000558 2022/09/15 21:36:04 - mmengine - INFO - Epoch(train) [77][300/586] lr: 5.000000e-04 eta: 9:42:40 time: 0.481419 data_time: 0.026531 memory: 15239 loss_kpt: 0.000562 acc_pose: 0.801742 loss: 0.000562 2022/09/15 21:36:28 - mmengine - INFO - Epoch(train) [77][350/586] lr: 5.000000e-04 eta: 9:42:19 time: 0.463302 data_time: 0.025152 memory: 15239 loss_kpt: 0.000560 acc_pose: 0.792255 loss: 0.000560 2022/09/15 21:36:52 - mmengine - INFO - Epoch(train) [77][400/586] lr: 5.000000e-04 eta: 9:41:59 time: 0.478038 data_time: 0.029771 memory: 15239 loss_kpt: 0.000563 acc_pose: 0.872486 loss: 0.000563 2022/09/15 21:37:15 - mmengine - INFO - Epoch(train) [77][450/586] lr: 5.000000e-04 eta: 9:41:39 time: 0.469523 data_time: 0.025378 memory: 15239 loss_kpt: 0.000546 acc_pose: 0.864504 loss: 0.000546 2022/09/15 21:37:22 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 21:37:39 - mmengine - INFO - Epoch(train) [77][500/586] lr: 5.000000e-04 eta: 9:41:19 time: 0.473289 data_time: 0.026821 memory: 15239 loss_kpt: 0.000557 acc_pose: 0.807070 loss: 0.000557 2022/09/15 21:38:02 - mmengine - INFO - Epoch(train) [77][550/586] lr: 5.000000e-04 eta: 9:40:58 time: 0.466815 data_time: 0.031251 memory: 15239 loss_kpt: 0.000531 acc_pose: 0.834196 loss: 0.000531 2022/09/15 21:38:19 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 21:38:19 - mmengine - INFO - Saving checkpoint at 77 epochs 2022/09/15 21:38:50 - mmengine - INFO - Epoch(train) [78][50/586] lr: 5.000000e-04 eta: 9:39:54 time: 0.469381 data_time: 0.031039 memory: 15239 loss_kpt: 0.000548 acc_pose: 0.835037 loss: 0.000548 2022/09/15 21:39:14 - mmengine - INFO - Epoch(train) [78][100/586] lr: 5.000000e-04 eta: 9:39:34 time: 0.469567 data_time: 0.025350 memory: 15239 loss_kpt: 0.000562 acc_pose: 0.851583 loss: 0.000562 2022/09/15 21:39:37 - mmengine - INFO - Epoch(train) [78][150/586] lr: 5.000000e-04 eta: 9:39:13 time: 0.467236 data_time: 0.026346 memory: 15239 loss_kpt: 0.000547 acc_pose: 0.793151 loss: 0.000547 2022/09/15 21:40:01 - mmengine - INFO - Epoch(train) [78][200/586] lr: 5.000000e-04 eta: 9:38:53 time: 0.475723 data_time: 0.025048 memory: 15239 loss_kpt: 0.000544 acc_pose: 0.850679 loss: 0.000544 2022/09/15 21:40:25 - mmengine - INFO - Epoch(train) [78][250/586] lr: 5.000000e-04 eta: 9:38:33 time: 0.471661 data_time: 0.027919 memory: 15239 loss_kpt: 0.000569 acc_pose: 0.855904 loss: 0.000569 2022/09/15 21:40:48 - mmengine - INFO - Epoch(train) [78][300/586] lr: 5.000000e-04 eta: 9:38:12 time: 0.462440 data_time: 0.025047 memory: 15239 loss_kpt: 0.000569 acc_pose: 0.843474 loss: 0.000569 2022/09/15 21:41:12 - mmengine - INFO - Epoch(train) [78][350/586] lr: 5.000000e-04 eta: 9:37:52 time: 0.478548 data_time: 0.029872 memory: 15239 loss_kpt: 0.000546 acc_pose: 0.823424 loss: 0.000546 2022/09/15 21:41:35 - mmengine - INFO - Epoch(train) [78][400/586] lr: 5.000000e-04 eta: 9:37:32 time: 0.466216 data_time: 0.024905 memory: 15239 loss_kpt: 0.000571 acc_pose: 0.832067 loss: 0.000571 2022/09/15 21:41:59 - mmengine - INFO - Epoch(train) [78][450/586] lr: 5.000000e-04 eta: 9:37:11 time: 0.468831 data_time: 0.026548 memory: 15239 loss_kpt: 0.000551 acc_pose: 0.800293 loss: 0.000551 2022/09/15 21:42:22 - mmengine - INFO - Epoch(train) [78][500/586] lr: 5.000000e-04 eta: 9:36:51 time: 0.475285 data_time: 0.024791 memory: 15239 loss_kpt: 0.000551 acc_pose: 0.838092 loss: 0.000551 2022/09/15 21:42:46 - mmengine - INFO - Epoch(train) [78][550/586] lr: 5.000000e-04 eta: 9:36:31 time: 0.468918 data_time: 0.025187 memory: 15239 loss_kpt: 0.000551 acc_pose: 0.770936 loss: 0.000551 2022/09/15 21:43:03 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 21:43:03 - mmengine - INFO - Saving checkpoint at 78 epochs 2022/09/15 21:43:34 - mmengine - INFO - Epoch(train) [79][50/586] lr: 5.000000e-04 eta: 9:35:28 time: 0.483060 data_time: 0.036248 memory: 15239 loss_kpt: 0.000552 acc_pose: 0.798874 loss: 0.000552 2022/09/15 21:43:58 - mmengine - INFO - Epoch(train) [79][100/586] lr: 5.000000e-04 eta: 9:35:08 time: 0.475164 data_time: 0.027885 memory: 15239 loss_kpt: 0.000538 acc_pose: 0.796667 loss: 0.000538 2022/09/15 21:44:21 - mmengine - INFO - Epoch(train) [79][150/586] lr: 5.000000e-04 eta: 9:34:48 time: 0.472276 data_time: 0.028329 memory: 15239 loss_kpt: 0.000547 acc_pose: 0.775843 loss: 0.000547 2022/09/15 21:44:45 - mmengine - INFO - Epoch(train) [79][200/586] lr: 5.000000e-04 eta: 9:34:27 time: 0.461730 data_time: 0.027306 memory: 15239 loss_kpt: 0.000575 acc_pose: 0.857933 loss: 0.000575 2022/09/15 21:45:08 - mmengine - INFO - Epoch(train) [79][250/586] lr: 5.000000e-04 eta: 9:34:07 time: 0.478297 data_time: 0.027867 memory: 15239 loss_kpt: 0.000558 acc_pose: 0.790439 loss: 0.000558 2022/09/15 21:45:29 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 21:45:33 - mmengine - INFO - Epoch(train) [79][300/586] lr: 5.000000e-04 eta: 9:33:48 time: 0.488575 data_time: 0.033568 memory: 15239 loss_kpt: 0.000561 acc_pose: 0.868602 loss: 0.000561 2022/09/15 21:45:57 - mmengine - INFO - Epoch(train) [79][350/586] lr: 5.000000e-04 eta: 9:33:29 time: 0.480991 data_time: 0.029809 memory: 15239 loss_kpt: 0.000557 acc_pose: 0.875515 loss: 0.000557 2022/09/15 21:46:21 - mmengine - INFO - Epoch(train) [79][400/586] lr: 5.000000e-04 eta: 9:33:09 time: 0.475062 data_time: 0.025047 memory: 15239 loss_kpt: 0.000552 acc_pose: 0.811459 loss: 0.000552 2022/09/15 21:46:45 - mmengine - INFO - Epoch(train) [79][450/586] lr: 5.000000e-04 eta: 9:32:49 time: 0.476634 data_time: 0.025302 memory: 15239 loss_kpt: 0.000546 acc_pose: 0.878103 loss: 0.000546 2022/09/15 21:47:08 - mmengine - INFO - Epoch(train) [79][500/586] lr: 5.000000e-04 eta: 9:32:28 time: 0.461314 data_time: 0.025410 memory: 15239 loss_kpt: 0.000557 acc_pose: 0.830980 loss: 0.000557 2022/09/15 21:47:31 - mmengine - INFO - Epoch(train) [79][550/586] lr: 5.000000e-04 eta: 9:32:08 time: 0.474221 data_time: 0.024943 memory: 15239 loss_kpt: 0.000575 acc_pose: 0.878056 loss: 0.000575 2022/09/15 21:47:48 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 21:47:48 - mmengine - INFO - Saving checkpoint at 79 epochs 2022/09/15 21:48:19 - mmengine - INFO - Epoch(train) [80][50/586] lr: 5.000000e-04 eta: 9:31:05 time: 0.471565 data_time: 0.034284 memory: 15239 loss_kpt: 0.000582 acc_pose: 0.797196 loss: 0.000582 2022/09/15 21:48:43 - mmengine - INFO - Epoch(train) [80][100/586] lr: 5.000000e-04 eta: 9:30:45 time: 0.476710 data_time: 0.025687 memory: 15239 loss_kpt: 0.000545 acc_pose: 0.864720 loss: 0.000545 2022/09/15 21:49:06 - mmengine - INFO - Epoch(train) [80][150/586] lr: 5.000000e-04 eta: 9:30:24 time: 0.466593 data_time: 0.025829 memory: 15239 loss_kpt: 0.000551 acc_pose: 0.906304 loss: 0.000551 2022/09/15 21:49:30 - mmengine - INFO - Epoch(train) [80][200/586] lr: 5.000000e-04 eta: 9:30:04 time: 0.469444 data_time: 0.030977 memory: 15239 loss_kpt: 0.000548 acc_pose: 0.880622 loss: 0.000548 2022/09/15 21:49:53 - mmengine - INFO - Epoch(train) [80][250/586] lr: 5.000000e-04 eta: 9:29:44 time: 0.472753 data_time: 0.026589 memory: 15239 loss_kpt: 0.000572 acc_pose: 0.849554 loss: 0.000572 2022/09/15 21:50:16 - mmengine - INFO - Epoch(train) [80][300/586] lr: 5.000000e-04 eta: 9:29:23 time: 0.464516 data_time: 0.024864 memory: 15239 loss_kpt: 0.000564 acc_pose: 0.799577 loss: 0.000564 2022/09/15 21:50:41 - mmengine - INFO - Epoch(train) [80][350/586] lr: 5.000000e-04 eta: 9:29:04 time: 0.494152 data_time: 0.033749 memory: 15239 loss_kpt: 0.000557 acc_pose: 0.882034 loss: 0.000557 2022/09/15 21:51:06 - mmengine - INFO - Epoch(train) [80][400/586] lr: 5.000000e-04 eta: 9:28:46 time: 0.498884 data_time: 0.031585 memory: 15239 loss_kpt: 0.000552 acc_pose: 0.845389 loss: 0.000552 2022/09/15 21:51:29 - mmengine - INFO - Epoch(train) [80][450/586] lr: 5.000000e-04 eta: 9:28:25 time: 0.459091 data_time: 0.025728 memory: 15239 loss_kpt: 0.000549 acc_pose: 0.863529 loss: 0.000549 2022/09/15 21:51:52 - mmengine - INFO - Epoch(train) [80][500/586] lr: 5.000000e-04 eta: 9:28:04 time: 0.465623 data_time: 0.026717 memory: 15239 loss_kpt: 0.000555 acc_pose: 0.873780 loss: 0.000555 2022/09/15 21:52:16 - mmengine - INFO - Epoch(train) [80][550/586] lr: 5.000000e-04 eta: 9:27:44 time: 0.470057 data_time: 0.024969 memory: 15239 loss_kpt: 0.000544 acc_pose: 0.839791 loss: 0.000544 2022/09/15 21:52:32 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 21:52:32 - mmengine - INFO - Saving checkpoint at 80 epochs 2022/09/15 21:52:53 - mmengine - INFO - Epoch(val) [80][50/407] eta: 0:01:32 time: 0.259664 data_time: 0.013613 memory: 15239 2022/09/15 21:53:05 - mmengine - INFO - Epoch(val) [80][100/407] eta: 0:01:17 time: 0.252924 data_time: 0.008661 memory: 2064 2022/09/15 21:53:18 - mmengine - INFO - Epoch(val) [80][150/407] eta: 0:01:04 time: 0.251614 data_time: 0.008164 memory: 2064 2022/09/15 21:53:31 - mmengine - INFO - Epoch(val) [80][200/407] eta: 0:00:52 time: 0.253301 data_time: 0.008601 memory: 2064 2022/09/15 21:53:43 - mmengine - INFO - Epoch(val) [80][250/407] eta: 0:00:40 time: 0.255206 data_time: 0.010027 memory: 2064 2022/09/15 21:53:56 - mmengine - INFO - Epoch(val) [80][300/407] eta: 0:00:27 time: 0.256114 data_time: 0.008835 memory: 2064 2022/09/15 21:54:09 - mmengine - INFO - Epoch(val) [80][350/407] eta: 0:00:14 time: 0.250765 data_time: 0.008435 memory: 2064 2022/09/15 21:54:21 - mmengine - INFO - Epoch(val) [80][400/407] eta: 0:00:01 time: 0.249100 data_time: 0.007983 memory: 2064 2022/09/15 21:54:56 - mmengine - INFO - Evaluating CocoMetric... 2022/09/15 21:55:10 - mmengine - INFO - Epoch(val) [80][407/407] coco/AP: 0.758926 coco/AP .5: 0.902673 coco/AP .75: 0.822370 coco/AP (M): 0.720094 coco/AP (L): 0.829559 coco/AR: 0.806077 coco/AR .5: 0.939861 coco/AR .75: 0.861461 coco/AR (M): 0.763289 coco/AR (L): 0.868265 2022/09/15 21:55:10 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220915/dark_w48_384/best_coco/AP_epoch_70.pth is removed 2022/09/15 21:55:14 - mmengine - INFO - The best checkpoint with 0.7589 coco/AP at 80 epoch is saved to best_coco/AP_epoch_80.pth. 2022/09/15 21:55:38 - mmengine - INFO - Epoch(train) [81][50/586] lr: 5.000000e-04 eta: 9:26:41 time: 0.466242 data_time: 0.031510 memory: 15239 loss_kpt: 0.000553 acc_pose: 0.779948 loss: 0.000553 2022/09/15 21:56:03 - mmengine - INFO - Epoch(train) [81][100/586] lr: 5.000000e-04 eta: 9:26:23 time: 0.500417 data_time: 0.034634 memory: 15239 loss_kpt: 0.000542 acc_pose: 0.778765 loss: 0.000542 2022/09/15 21:56:14 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 21:56:28 - mmengine - INFO - Epoch(train) [81][150/586] lr: 5.000000e-04 eta: 9:26:05 time: 0.506937 data_time: 0.040196 memory: 15239 loss_kpt: 0.000574 acc_pose: 0.869271 loss: 0.000574 2022/09/15 21:56:51 - mmengine - INFO - Epoch(train) [81][200/586] lr: 5.000000e-04 eta: 9:25:44 time: 0.458660 data_time: 0.029806 memory: 15239 loss_kpt: 0.000549 acc_pose: 0.905435 loss: 0.000549 2022/09/15 21:57:17 - mmengine - INFO - Epoch(train) [81][250/586] lr: 5.000000e-04 eta: 9:25:27 time: 0.511257 data_time: 0.032886 memory: 15239 loss_kpt: 0.000555 acc_pose: 0.868630 loss: 0.000555 2022/09/15 21:57:40 - mmengine - INFO - Epoch(train) [81][300/586] lr: 5.000000e-04 eta: 9:25:06 time: 0.470770 data_time: 0.029806 memory: 15239 loss_kpt: 0.000546 acc_pose: 0.868435 loss: 0.000546 2022/09/15 21:58:04 - mmengine - INFO - Epoch(train) [81][350/586] lr: 5.000000e-04 eta: 9:24:45 time: 0.466213 data_time: 0.027720 memory: 15239 loss_kpt: 0.000573 acc_pose: 0.898013 loss: 0.000573 2022/09/15 21:58:28 - mmengine - INFO - Epoch(train) [81][400/586] lr: 5.000000e-04 eta: 9:24:26 time: 0.481819 data_time: 0.027865 memory: 15239 loss_kpt: 0.000544 acc_pose: 0.872226 loss: 0.000544 2022/09/15 21:58:51 - mmengine - INFO - Epoch(train) [81][450/586] lr: 5.000000e-04 eta: 9:24:05 time: 0.468579 data_time: 0.031182 memory: 15239 loss_kpt: 0.000539 acc_pose: 0.878233 loss: 0.000539 2022/09/15 21:59:14 - mmengine - INFO - Epoch(train) [81][500/586] lr: 5.000000e-04 eta: 9:23:44 time: 0.466438 data_time: 0.027502 memory: 15239 loss_kpt: 0.000556 acc_pose: 0.823410 loss: 0.000556 2022/09/15 21:59:38 - mmengine - INFO - Epoch(train) [81][550/586] lr: 5.000000e-04 eta: 9:23:24 time: 0.472785 data_time: 0.028099 memory: 15239 loss_kpt: 0.000573 acc_pose: 0.843114 loss: 0.000573 2022/09/15 21:59:55 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 21:59:55 - mmengine - INFO - Saving checkpoint at 81 epochs 2022/09/15 22:00:27 - mmengine - INFO - Epoch(train) [82][50/586] lr: 5.000000e-04 eta: 9:22:23 time: 0.479522 data_time: 0.042365 memory: 15239 loss_kpt: 0.000546 acc_pose: 0.805964 loss: 0.000546 2022/09/15 22:00:51 - mmengine - INFO - Epoch(train) [82][100/586] lr: 5.000000e-04 eta: 9:22:04 time: 0.487956 data_time: 0.032865 memory: 15239 loss_kpt: 0.000566 acc_pose: 0.839056 loss: 0.000566 2022/09/15 22:01:15 - mmengine - INFO - Epoch(train) [82][150/586] lr: 5.000000e-04 eta: 9:21:43 time: 0.472012 data_time: 0.037433 memory: 15239 loss_kpt: 0.000536 acc_pose: 0.874859 loss: 0.000536 2022/09/15 22:01:38 - mmengine - INFO - Epoch(train) [82][200/586] lr: 5.000000e-04 eta: 9:21:22 time: 0.462951 data_time: 0.026931 memory: 15239 loss_kpt: 0.000561 acc_pose: 0.778965 loss: 0.000561 2022/09/15 22:02:02 - mmengine - INFO - Epoch(train) [82][250/586] lr: 5.000000e-04 eta: 9:21:03 time: 0.484681 data_time: 0.028374 memory: 15239 loss_kpt: 0.000552 acc_pose: 0.821298 loss: 0.000552 2022/09/15 22:02:26 - mmengine - INFO - Epoch(train) [82][300/586] lr: 5.000000e-04 eta: 9:20:42 time: 0.465537 data_time: 0.027765 memory: 15239 loss_kpt: 0.000559 acc_pose: 0.869494 loss: 0.000559 2022/09/15 22:02:49 - mmengine - INFO - Epoch(train) [82][350/586] lr: 5.000000e-04 eta: 9:20:21 time: 0.467407 data_time: 0.027771 memory: 15239 loss_kpt: 0.000547 acc_pose: 0.755783 loss: 0.000547 2022/09/15 22:03:13 - mmengine - INFO - Epoch(train) [82][400/586] lr: 5.000000e-04 eta: 9:20:01 time: 0.476429 data_time: 0.028333 memory: 15239 loss_kpt: 0.000542 acc_pose: 0.791767 loss: 0.000542 2022/09/15 22:03:36 - mmengine - INFO - Epoch(train) [82][450/586] lr: 5.000000e-04 eta: 9:19:41 time: 0.468517 data_time: 0.029218 memory: 15239 loss_kpt: 0.000580 acc_pose: 0.864204 loss: 0.000580 2022/09/15 22:03:59 - mmengine - INFO - Epoch(train) [82][500/586] lr: 5.000000e-04 eta: 9:19:20 time: 0.462628 data_time: 0.028083 memory: 15239 loss_kpt: 0.000539 acc_pose: 0.854457 loss: 0.000539 2022/09/15 22:04:16 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 22:04:23 - mmengine - INFO - Epoch(train) [82][550/586] lr: 5.000000e-04 eta: 9:19:00 time: 0.477848 data_time: 0.029461 memory: 15239 loss_kpt: 0.000551 acc_pose: 0.865772 loss: 0.000551 2022/09/15 22:04:40 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 22:04:40 - mmengine - INFO - Saving checkpoint at 82 epochs 2022/09/15 22:05:11 - mmengine - INFO - Epoch(train) [83][50/586] lr: 5.000000e-04 eta: 9:17:59 time: 0.479192 data_time: 0.039594 memory: 15239 loss_kpt: 0.000551 acc_pose: 0.850845 loss: 0.000551 2022/09/15 22:05:35 - mmengine - INFO - Epoch(train) [83][100/586] lr: 5.000000e-04 eta: 9:17:40 time: 0.488847 data_time: 0.031542 memory: 15239 loss_kpt: 0.000560 acc_pose: 0.849394 loss: 0.000560 2022/09/15 22:05:59 - mmengine - INFO - Epoch(train) [83][150/586] lr: 5.000000e-04 eta: 9:17:19 time: 0.470625 data_time: 0.026837 memory: 15239 loss_kpt: 0.000547 acc_pose: 0.823773 loss: 0.000547 2022/09/15 22:06:24 - mmengine - INFO - Epoch(train) [83][200/586] lr: 5.000000e-04 eta: 9:17:00 time: 0.491904 data_time: 0.032855 memory: 15239 loss_kpt: 0.000550 acc_pose: 0.852742 loss: 0.000550 2022/09/15 22:06:47 - mmengine - INFO - Epoch(train) [83][250/586] lr: 5.000000e-04 eta: 9:16:40 time: 0.475725 data_time: 0.026517 memory: 15239 loss_kpt: 0.000579 acc_pose: 0.804878 loss: 0.000579 2022/09/15 22:07:11 - mmengine - INFO - Epoch(train) [83][300/586] lr: 5.000000e-04 eta: 9:16:20 time: 0.476562 data_time: 0.028195 memory: 15239 loss_kpt: 0.000535 acc_pose: 0.862549 loss: 0.000535 2022/09/15 22:07:35 - mmengine - INFO - Epoch(train) [83][350/586] lr: 5.000000e-04 eta: 9:16:01 time: 0.482369 data_time: 0.028512 memory: 15239 loss_kpt: 0.000557 acc_pose: 0.845432 loss: 0.000557 2022/09/15 22:07:59 - mmengine - INFO - Epoch(train) [83][400/586] lr: 5.000000e-04 eta: 9:15:41 time: 0.480681 data_time: 0.027314 memory: 15239 loss_kpt: 0.000555 acc_pose: 0.832610 loss: 0.000555 2022/09/15 22:08:23 - mmengine - INFO - Epoch(train) [83][450/586] lr: 5.000000e-04 eta: 9:15:20 time: 0.469785 data_time: 0.028933 memory: 15239 loss_kpt: 0.000548 acc_pose: 0.794685 loss: 0.000548 2022/09/15 22:08:47 - mmengine - INFO - Epoch(train) [83][500/586] lr: 5.000000e-04 eta: 9:15:00 time: 0.475095 data_time: 0.030976 memory: 15239 loss_kpt: 0.000554 acc_pose: 0.785343 loss: 0.000554 2022/09/15 22:09:10 - mmengine - INFO - Epoch(train) [83][550/586] lr: 5.000000e-04 eta: 9:14:40 time: 0.473855 data_time: 0.028272 memory: 15239 loss_kpt: 0.000555 acc_pose: 0.909698 loss: 0.000555 2022/09/15 22:09:28 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 22:09:28 - mmengine - INFO - Saving checkpoint at 83 epochs 2022/09/15 22:09:59 - mmengine - INFO - Epoch(train) [84][50/586] lr: 5.000000e-04 eta: 9:13:39 time: 0.479438 data_time: 0.035276 memory: 15239 loss_kpt: 0.000556 acc_pose: 0.867681 loss: 0.000556 2022/09/15 22:10:22 - mmengine - INFO - Epoch(train) [84][100/586] lr: 5.000000e-04 eta: 9:13:19 time: 0.468425 data_time: 0.026412 memory: 15239 loss_kpt: 0.000554 acc_pose: 0.810542 loss: 0.000554 2022/09/15 22:10:46 - mmengine - INFO - Epoch(train) [84][150/586] lr: 5.000000e-04 eta: 9:12:58 time: 0.474267 data_time: 0.027103 memory: 15239 loss_kpt: 0.000554 acc_pose: 0.880035 loss: 0.000554 2022/09/15 22:11:10 - mmengine - INFO - Epoch(train) [84][200/586] lr: 5.000000e-04 eta: 9:12:38 time: 0.476008 data_time: 0.027037 memory: 15239 loss_kpt: 0.000563 acc_pose: 0.871411 loss: 0.000563 2022/09/15 22:11:34 - mmengine - INFO - Epoch(train) [84][250/586] lr: 5.000000e-04 eta: 9:12:18 time: 0.469670 data_time: 0.027663 memory: 15239 loss_kpt: 0.000545 acc_pose: 0.842450 loss: 0.000545 2022/09/15 22:11:57 - mmengine - INFO - Epoch(train) [84][300/586] lr: 5.000000e-04 eta: 9:11:57 time: 0.473520 data_time: 0.032530 memory: 15239 loss_kpt: 0.000557 acc_pose: 0.852436 loss: 0.000557 2022/09/15 22:12:21 - mmengine - INFO - Epoch(train) [84][350/586] lr: 5.000000e-04 eta: 9:11:37 time: 0.471750 data_time: 0.028212 memory: 15239 loss_kpt: 0.000541 acc_pose: 0.870124 loss: 0.000541 2022/09/15 22:12:26 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 22:12:44 - mmengine - INFO - Epoch(train) [84][400/586] lr: 5.000000e-04 eta: 9:11:16 time: 0.468913 data_time: 0.027087 memory: 15239 loss_kpt: 0.000550 acc_pose: 0.852637 loss: 0.000550 2022/09/15 22:13:08 - mmengine - INFO - Epoch(train) [84][450/586] lr: 5.000000e-04 eta: 9:10:56 time: 0.470860 data_time: 0.027538 memory: 15239 loss_kpt: 0.000531 acc_pose: 0.851553 loss: 0.000531 2022/09/15 22:13:32 - mmengine - INFO - Epoch(train) [84][500/586] lr: 5.000000e-04 eta: 9:10:36 time: 0.479324 data_time: 0.029399 memory: 15239 loss_kpt: 0.000556 acc_pose: 0.829553 loss: 0.000556 2022/09/15 22:13:56 - mmengine - INFO - Epoch(train) [84][550/586] lr: 5.000000e-04 eta: 9:10:16 time: 0.487421 data_time: 0.029334 memory: 15239 loss_kpt: 0.000540 acc_pose: 0.851185 loss: 0.000540 2022/09/15 22:14:13 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 22:14:13 - mmengine - INFO - Saving checkpoint at 84 epochs 2022/09/15 22:14:45 - mmengine - INFO - Epoch(train) [85][50/586] lr: 5.000000e-04 eta: 9:09:17 time: 0.489959 data_time: 0.036889 memory: 15239 loss_kpt: 0.000567 acc_pose: 0.760715 loss: 0.000567 2022/09/15 22:15:08 - mmengine - INFO - Epoch(train) [85][100/586] lr: 5.000000e-04 eta: 9:08:56 time: 0.467619 data_time: 0.031190 memory: 15239 loss_kpt: 0.000557 acc_pose: 0.813569 loss: 0.000557 2022/09/15 22:15:31 - mmengine - INFO - Epoch(train) [85][150/586] lr: 5.000000e-04 eta: 9:08:36 time: 0.468928 data_time: 0.029229 memory: 15239 loss_kpt: 0.000557 acc_pose: 0.819637 loss: 0.000557 2022/09/15 22:15:55 - mmengine - INFO - Epoch(train) [85][200/586] lr: 5.000000e-04 eta: 9:08:15 time: 0.473903 data_time: 0.026792 memory: 15239 loss_kpt: 0.000560 acc_pose: 0.751881 loss: 0.000560 2022/09/15 22:16:19 - mmengine - INFO - Epoch(train) [85][250/586] lr: 5.000000e-04 eta: 9:07:55 time: 0.476124 data_time: 0.031584 memory: 15239 loss_kpt: 0.000553 acc_pose: 0.843650 loss: 0.000553 2022/09/15 22:16:42 - mmengine - INFO - Epoch(train) [85][300/586] lr: 5.000000e-04 eta: 9:07:35 time: 0.470852 data_time: 0.028781 memory: 15239 loss_kpt: 0.000557 acc_pose: 0.908699 loss: 0.000557 2022/09/15 22:17:06 - mmengine - INFO - Epoch(train) [85][350/586] lr: 5.000000e-04 eta: 9:07:14 time: 0.469998 data_time: 0.027460 memory: 15239 loss_kpt: 0.000545 acc_pose: 0.878460 loss: 0.000545 2022/09/15 22:17:30 - mmengine - INFO - Epoch(train) [85][400/586] lr: 5.000000e-04 eta: 9:06:54 time: 0.480107 data_time: 0.029515 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.823908 loss: 0.000543 2022/09/15 22:17:54 - mmengine - INFO - Epoch(train) [85][450/586] lr: 5.000000e-04 eta: 9:06:34 time: 0.476178 data_time: 0.027772 memory: 15239 loss_kpt: 0.000537 acc_pose: 0.843311 loss: 0.000537 2022/09/15 22:18:17 - mmengine - INFO - Epoch(train) [85][500/586] lr: 5.000000e-04 eta: 9:06:13 time: 0.469846 data_time: 0.028430 memory: 15239 loss_kpt: 0.000531 acc_pose: 0.836673 loss: 0.000531 2022/09/15 22:18:41 - mmengine - INFO - Epoch(train) [85][550/586] lr: 5.000000e-04 eta: 9:05:53 time: 0.473679 data_time: 0.031833 memory: 15239 loss_kpt: 0.000542 acc_pose: 0.888524 loss: 0.000542 2022/09/15 22:18:57 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 22:18:57 - mmengine - INFO - Saving checkpoint at 85 epochs 2022/09/15 22:19:29 - mmengine - INFO - Epoch(train) [86][50/586] lr: 5.000000e-04 eta: 9:04:54 time: 0.486097 data_time: 0.042808 memory: 15239 loss_kpt: 0.000559 acc_pose: 0.886116 loss: 0.000559 2022/09/15 22:19:52 - mmengine - INFO - Epoch(train) [86][100/586] lr: 5.000000e-04 eta: 9:04:33 time: 0.465546 data_time: 0.028340 memory: 15239 loss_kpt: 0.000562 acc_pose: 0.860088 loss: 0.000562 2022/09/15 22:20:16 - mmengine - INFO - Epoch(train) [86][150/586] lr: 5.000000e-04 eta: 9:04:13 time: 0.477658 data_time: 0.028072 memory: 15239 loss_kpt: 0.000545 acc_pose: 0.847411 loss: 0.000545 2022/09/15 22:20:35 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 22:20:40 - mmengine - INFO - Epoch(train) [86][200/586] lr: 5.000000e-04 eta: 9:03:52 time: 0.472411 data_time: 0.026799 memory: 15239 loss_kpt: 0.000552 acc_pose: 0.832159 loss: 0.000552 2022/09/15 22:21:03 - mmengine - INFO - Epoch(train) [86][250/586] lr: 5.000000e-04 eta: 9:03:32 time: 0.470917 data_time: 0.027324 memory: 15239 loss_kpt: 0.000561 acc_pose: 0.704917 loss: 0.000561 2022/09/15 22:21:27 - mmengine - INFO - Epoch(train) [86][300/586] lr: 5.000000e-04 eta: 9:03:11 time: 0.469348 data_time: 0.030766 memory: 15239 loss_kpt: 0.000532 acc_pose: 0.895920 loss: 0.000532 2022/09/15 22:21:50 - mmengine - INFO - Epoch(train) [86][350/586] lr: 5.000000e-04 eta: 9:02:51 time: 0.470796 data_time: 0.026914 memory: 15239 loss_kpt: 0.000565 acc_pose: 0.879317 loss: 0.000565 2022/09/15 22:22:14 - mmengine - INFO - Epoch(train) [86][400/586] lr: 5.000000e-04 eta: 9:02:29 time: 0.463704 data_time: 0.027874 memory: 15239 loss_kpt: 0.000545 acc_pose: 0.872449 loss: 0.000545 2022/09/15 22:22:37 - mmengine - INFO - Epoch(train) [86][450/586] lr: 5.000000e-04 eta: 9:02:08 time: 0.465060 data_time: 0.027464 memory: 15239 loss_kpt: 0.000562 acc_pose: 0.855480 loss: 0.000562 2022/09/15 22:23:01 - mmengine - INFO - Epoch(train) [86][500/586] lr: 5.000000e-04 eta: 9:01:48 time: 0.478836 data_time: 0.028372 memory: 15239 loss_kpt: 0.000568 acc_pose: 0.886898 loss: 0.000568 2022/09/15 22:23:24 - mmengine - INFO - Epoch(train) [86][550/586] lr: 5.000000e-04 eta: 9:01:27 time: 0.467326 data_time: 0.028766 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.831210 loss: 0.000543 2022/09/15 22:23:41 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 22:23:41 - mmengine - INFO - Saving checkpoint at 86 epochs 2022/09/15 22:24:12 - mmengine - INFO - Epoch(train) [87][50/586] lr: 5.000000e-04 eta: 9:00:29 time: 0.487672 data_time: 0.040948 memory: 15239 loss_kpt: 0.000542 acc_pose: 0.885709 loss: 0.000542 2022/09/15 22:24:36 - mmengine - INFO - Epoch(train) [87][100/586] lr: 5.000000e-04 eta: 9:00:09 time: 0.478981 data_time: 0.038160 memory: 15239 loss_kpt: 0.000566 acc_pose: 0.816008 loss: 0.000566 2022/09/15 22:24:59 - mmengine - INFO - Epoch(train) [87][150/586] lr: 5.000000e-04 eta: 8:59:47 time: 0.457684 data_time: 0.027396 memory: 15239 loss_kpt: 0.000562 acc_pose: 0.793869 loss: 0.000562 2022/09/15 22:25:23 - mmengine - INFO - Epoch(train) [87][200/586] lr: 5.000000e-04 eta: 8:59:27 time: 0.480421 data_time: 0.027881 memory: 15239 loss_kpt: 0.000549 acc_pose: 0.849274 loss: 0.000549 2022/09/15 22:25:46 - mmengine - INFO - Epoch(train) [87][250/586] lr: 5.000000e-04 eta: 8:59:07 time: 0.469053 data_time: 0.026877 memory: 15239 loss_kpt: 0.000553 acc_pose: 0.891526 loss: 0.000553 2022/09/15 22:26:10 - mmengine - INFO - Epoch(train) [87][300/586] lr: 5.000000e-04 eta: 8:58:46 time: 0.471064 data_time: 0.027437 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.827748 loss: 0.000543 2022/09/15 22:26:34 - mmengine - INFO - Epoch(train) [87][350/586] lr: 5.000000e-04 eta: 8:58:26 time: 0.473784 data_time: 0.026868 memory: 15239 loss_kpt: 0.000541 acc_pose: 0.858201 loss: 0.000541 2022/09/15 22:26:58 - mmengine - INFO - Epoch(train) [87][400/586] lr: 5.000000e-04 eta: 8:58:06 time: 0.478158 data_time: 0.028297 memory: 15239 loss_kpt: 0.000529 acc_pose: 0.849299 loss: 0.000529 2022/09/15 22:27:21 - mmengine - INFO - Epoch(train) [87][450/586] lr: 5.000000e-04 eta: 8:57:45 time: 0.467458 data_time: 0.027818 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.855765 loss: 0.000543 2022/09/15 22:27:45 - mmengine - INFO - Epoch(train) [87][500/586] lr: 5.000000e-04 eta: 8:57:24 time: 0.468834 data_time: 0.026947 memory: 15239 loss_kpt: 0.000524 acc_pose: 0.836696 loss: 0.000524 2022/09/15 22:28:08 - mmengine - INFO - Epoch(train) [87][550/586] lr: 5.000000e-04 eta: 8:57:03 time: 0.470433 data_time: 0.028858 memory: 15239 loss_kpt: 0.000582 acc_pose: 0.865941 loss: 0.000582 2022/09/15 22:28:25 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 22:28:25 - mmengine - INFO - Saving checkpoint at 87 epochs 2022/09/15 22:28:41 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 22:28:57 - mmengine - INFO - Epoch(train) [88][50/586] lr: 5.000000e-04 eta: 8:56:05 time: 0.483381 data_time: 0.039500 memory: 15239 loss_kpt: 0.000546 acc_pose: 0.818866 loss: 0.000546 2022/09/15 22:29:20 - mmengine - INFO - Epoch(train) [88][100/586] lr: 5.000000e-04 eta: 8:55:44 time: 0.472164 data_time: 0.026538 memory: 15239 loss_kpt: 0.000545 acc_pose: 0.851791 loss: 0.000545 2022/09/15 22:29:44 - mmengine - INFO - Epoch(train) [88][150/586] lr: 5.000000e-04 eta: 8:55:24 time: 0.473754 data_time: 0.026860 memory: 15239 loss_kpt: 0.000548 acc_pose: 0.877073 loss: 0.000548 2022/09/15 22:30:08 - mmengine - INFO - Epoch(train) [88][200/586] lr: 5.000000e-04 eta: 8:55:03 time: 0.476611 data_time: 0.028106 memory: 15239 loss_kpt: 0.000555 acc_pose: 0.905027 loss: 0.000555 2022/09/15 22:30:31 - mmengine - INFO - Epoch(train) [88][250/586] lr: 5.000000e-04 eta: 8:54:43 time: 0.469334 data_time: 0.028418 memory: 15239 loss_kpt: 0.000532 acc_pose: 0.815825 loss: 0.000532 2022/09/15 22:30:56 - mmengine - INFO - Epoch(train) [88][300/586] lr: 5.000000e-04 eta: 8:54:23 time: 0.490624 data_time: 0.028731 memory: 15239 loss_kpt: 0.000551 acc_pose: 0.881296 loss: 0.000551 2022/09/15 22:31:20 - mmengine - INFO - Epoch(train) [88][350/586] lr: 5.000000e-04 eta: 8:54:03 time: 0.479437 data_time: 0.033232 memory: 15239 loss_kpt: 0.000541 acc_pose: 0.837169 loss: 0.000541 2022/09/15 22:31:43 - mmengine - INFO - Epoch(train) [88][400/586] lr: 5.000000e-04 eta: 8:53:42 time: 0.463287 data_time: 0.027469 memory: 15239 loss_kpt: 0.000557 acc_pose: 0.857229 loss: 0.000557 2022/09/15 22:32:07 - mmengine - INFO - Epoch(train) [88][450/586] lr: 5.000000e-04 eta: 8:53:22 time: 0.474221 data_time: 0.030103 memory: 15239 loss_kpt: 0.000555 acc_pose: 0.835103 loss: 0.000555 2022/09/15 22:32:30 - mmengine - INFO - Epoch(train) [88][500/586] lr: 5.000000e-04 eta: 8:53:01 time: 0.475345 data_time: 0.032564 memory: 15239 loss_kpt: 0.000544 acc_pose: 0.837515 loss: 0.000544 2022/09/15 22:32:54 - mmengine - INFO - Epoch(train) [88][550/586] lr: 5.000000e-04 eta: 8:52:41 time: 0.471274 data_time: 0.027444 memory: 15239 loss_kpt: 0.000551 acc_pose: 0.870454 loss: 0.000551 2022/09/15 22:33:11 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 22:33:11 - mmengine - INFO - Saving checkpoint at 88 epochs 2022/09/15 22:33:42 - mmengine - INFO - Epoch(train) [89][50/586] lr: 5.000000e-04 eta: 8:51:42 time: 0.478674 data_time: 0.033512 memory: 15239 loss_kpt: 0.000535 acc_pose: 0.777311 loss: 0.000535 2022/09/15 22:34:06 - mmengine - INFO - Epoch(train) [89][100/586] lr: 5.000000e-04 eta: 8:51:22 time: 0.477183 data_time: 0.026204 memory: 15239 loss_kpt: 0.000545 acc_pose: 0.859152 loss: 0.000545 2022/09/15 22:34:32 - mmengine - INFO - Epoch(train) [89][150/586] lr: 5.000000e-04 eta: 8:51:04 time: 0.507527 data_time: 0.034995 memory: 15239 loss_kpt: 0.000537 acc_pose: 0.863028 loss: 0.000537 2022/09/15 22:34:57 - mmengine - INFO - Epoch(train) [89][200/586] lr: 5.000000e-04 eta: 8:50:46 time: 0.503135 data_time: 0.030765 memory: 15239 loss_kpt: 0.000548 acc_pose: 0.882090 loss: 0.000548 2022/09/15 22:35:21 - mmengine - INFO - Epoch(train) [89][250/586] lr: 5.000000e-04 eta: 8:50:25 time: 0.478280 data_time: 0.028332 memory: 15239 loss_kpt: 0.000536 acc_pose: 0.827135 loss: 0.000536 2022/09/15 22:35:44 - mmengine - INFO - Epoch(train) [89][300/586] lr: 5.000000e-04 eta: 8:50:04 time: 0.462923 data_time: 0.026526 memory: 15239 loss_kpt: 0.000562 acc_pose: 0.806611 loss: 0.000562 2022/09/15 22:36:07 - mmengine - INFO - Epoch(train) [89][350/586] lr: 5.000000e-04 eta: 8:49:43 time: 0.465348 data_time: 0.027839 memory: 15239 loss_kpt: 0.000542 acc_pose: 0.905494 loss: 0.000542 2022/09/15 22:36:32 - mmengine - INFO - Epoch(train) [89][400/586] lr: 5.000000e-04 eta: 8:49:24 time: 0.494147 data_time: 0.026599 memory: 15239 loss_kpt: 0.000550 acc_pose: 0.796528 loss: 0.000550 2022/09/15 22:36:48 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 22:36:57 - mmengine - INFO - Epoch(train) [89][450/586] lr: 5.000000e-04 eta: 8:49:05 time: 0.495605 data_time: 0.027717 memory: 15239 loss_kpt: 0.000545 acc_pose: 0.933570 loss: 0.000545 2022/09/15 22:37:21 - mmengine - INFO - Epoch(train) [89][500/586] lr: 5.000000e-04 eta: 8:48:45 time: 0.481898 data_time: 0.027480 memory: 15239 loss_kpt: 0.000549 acc_pose: 0.858966 loss: 0.000549 2022/09/15 22:37:44 - mmengine - INFO - Epoch(train) [89][550/586] lr: 5.000000e-04 eta: 8:48:24 time: 0.469001 data_time: 0.027736 memory: 15239 loss_kpt: 0.000545 acc_pose: 0.864453 loss: 0.000545 2022/09/15 22:38:01 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 22:38:01 - mmengine - INFO - Saving checkpoint at 89 epochs 2022/09/15 22:38:32 - mmengine - INFO - Epoch(train) [90][50/586] lr: 5.000000e-04 eta: 8:47:27 time: 0.485371 data_time: 0.041377 memory: 15239 loss_kpt: 0.000540 acc_pose: 0.873079 loss: 0.000540 2022/09/15 22:38:55 - mmengine - INFO - Epoch(train) [90][100/586] lr: 5.000000e-04 eta: 8:47:06 time: 0.470249 data_time: 0.026752 memory: 15239 loss_kpt: 0.000552 acc_pose: 0.808036 loss: 0.000552 2022/09/15 22:39:19 - mmengine - INFO - Epoch(train) [90][150/586] lr: 5.000000e-04 eta: 8:46:46 time: 0.477407 data_time: 0.026777 memory: 15239 loss_kpt: 0.000530 acc_pose: 0.797649 loss: 0.000530 2022/09/15 22:39:43 - mmengine - INFO - Epoch(train) [90][200/586] lr: 5.000000e-04 eta: 8:46:26 time: 0.481823 data_time: 0.031145 memory: 15239 loss_kpt: 0.000533 acc_pose: 0.867264 loss: 0.000533 2022/09/15 22:40:07 - mmengine - INFO - Epoch(train) [90][250/586] lr: 5.000000e-04 eta: 8:46:05 time: 0.477024 data_time: 0.028098 memory: 15239 loss_kpt: 0.000537 acc_pose: 0.881835 loss: 0.000537 2022/09/15 22:40:31 - mmengine - INFO - Epoch(train) [90][300/586] lr: 5.000000e-04 eta: 8:45:44 time: 0.465130 data_time: 0.030467 memory: 15239 loss_kpt: 0.000538 acc_pose: 0.867825 loss: 0.000538 2022/09/15 22:40:55 - mmengine - INFO - Epoch(train) [90][350/586] lr: 5.000000e-04 eta: 8:45:24 time: 0.483390 data_time: 0.027734 memory: 15239 loss_kpt: 0.000540 acc_pose: 0.823350 loss: 0.000540 2022/09/15 22:41:18 - mmengine - INFO - Epoch(train) [90][400/586] lr: 5.000000e-04 eta: 8:45:03 time: 0.467635 data_time: 0.031916 memory: 15239 loss_kpt: 0.000545 acc_pose: 0.877430 loss: 0.000545 2022/09/15 22:41:41 - mmengine - INFO - Epoch(train) [90][450/586] lr: 5.000000e-04 eta: 8:44:42 time: 0.466679 data_time: 0.028514 memory: 15239 loss_kpt: 0.000544 acc_pose: 0.745530 loss: 0.000544 2022/09/15 22:42:05 - mmengine - INFO - Epoch(train) [90][500/586] lr: 5.000000e-04 eta: 8:44:22 time: 0.473734 data_time: 0.027397 memory: 15239 loss_kpt: 0.000546 acc_pose: 0.843837 loss: 0.000546 2022/09/15 22:42:29 - mmengine - INFO - Epoch(train) [90][550/586] lr: 5.000000e-04 eta: 8:44:01 time: 0.467737 data_time: 0.027132 memory: 15239 loss_kpt: 0.000538 acc_pose: 0.846415 loss: 0.000538 2022/09/15 22:42:45 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 22:42:45 - mmengine - INFO - Saving checkpoint at 90 epochs 2022/09/15 22:43:05 - mmengine - INFO - Epoch(val) [90][50/407] eta: 0:01:32 time: 0.260094 data_time: 0.016903 memory: 15239 2022/09/15 22:43:18 - mmengine - INFO - Epoch(val) [90][100/407] eta: 0:01:16 time: 0.248809 data_time: 0.008430 memory: 2064 2022/09/15 22:43:30 - mmengine - INFO - Epoch(val) [90][150/407] eta: 0:01:04 time: 0.250238 data_time: 0.008547 memory: 2064 2022/09/15 22:43:43 - mmengine - INFO - Epoch(val) [90][200/407] eta: 0:00:51 time: 0.250515 data_time: 0.008652 memory: 2064 2022/09/15 22:43:55 - mmengine - INFO - Epoch(val) [90][250/407] eta: 0:00:39 time: 0.253010 data_time: 0.008993 memory: 2064 2022/09/15 22:44:08 - mmengine - INFO - Epoch(val) [90][300/407] eta: 0:00:26 time: 0.250583 data_time: 0.008937 memory: 2064 2022/09/15 22:44:20 - mmengine - INFO - Epoch(val) [90][350/407] eta: 0:00:14 time: 0.249210 data_time: 0.008192 memory: 2064 2022/09/15 22:44:33 - mmengine - INFO - Epoch(val) [90][400/407] eta: 0:00:01 time: 0.250863 data_time: 0.011506 memory: 2064 2022/09/15 22:45:09 - mmengine - INFO - Evaluating CocoMetric... 2022/09/15 22:45:23 - mmengine - INFO - Epoch(val) [90][407/407] coco/AP: 0.757714 coco/AP .5: 0.902510 coco/AP .75: 0.820832 coco/AP (M): 0.718632 coco/AP (L): 0.827835 coco/AR: 0.806219 coco/AR .5: 0.939861 coco/AR .75: 0.862406 coco/AR (M): 0.763070 coco/AR (L): 0.869119 2022/09/15 22:45:48 - mmengine - INFO - Epoch(train) [91][50/586] lr: 5.000000e-04 eta: 8:43:04 time: 0.494598 data_time: 0.031174 memory: 15239 loss_kpt: 0.000564 acc_pose: 0.880397 loss: 0.000564 2022/09/15 22:46:11 - mmengine - INFO - Epoch(train) [91][100/586] lr: 5.000000e-04 eta: 8:42:43 time: 0.461690 data_time: 0.025649 memory: 15239 loss_kpt: 0.000547 acc_pose: 0.824424 loss: 0.000547 2022/09/15 22:46:35 - mmengine - INFO - Epoch(train) [91][150/586] lr: 5.000000e-04 eta: 8:42:22 time: 0.475217 data_time: 0.025819 memory: 15239 loss_kpt: 0.000541 acc_pose: 0.761429 loss: 0.000541 2022/09/15 22:46:58 - mmengine - INFO - Epoch(train) [91][200/586] lr: 5.000000e-04 eta: 8:42:02 time: 0.468063 data_time: 0.027312 memory: 15239 loss_kpt: 0.000531 acc_pose: 0.882139 loss: 0.000531 2022/09/15 22:47:22 - mmengine - INFO - Epoch(train) [91][250/586] lr: 5.000000e-04 eta: 8:41:42 time: 0.482951 data_time: 0.027226 memory: 15239 loss_kpt: 0.000545 acc_pose: 0.850078 loss: 0.000545 2022/09/15 22:47:27 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 22:47:46 - mmengine - INFO - Epoch(train) [91][300/586] lr: 5.000000e-04 eta: 8:41:21 time: 0.469126 data_time: 0.025085 memory: 15239 loss_kpt: 0.000554 acc_pose: 0.886681 loss: 0.000554 2022/09/15 22:48:10 - mmengine - INFO - Epoch(train) [91][350/586] lr: 5.000000e-04 eta: 8:41:01 time: 0.481568 data_time: 0.025442 memory: 15239 loss_kpt: 0.000556 acc_pose: 0.795128 loss: 0.000556 2022/09/15 22:48:33 - mmengine - INFO - Epoch(train) [91][400/586] lr: 5.000000e-04 eta: 8:40:40 time: 0.468133 data_time: 0.024813 memory: 15239 loss_kpt: 0.000544 acc_pose: 0.833317 loss: 0.000544 2022/09/15 22:48:57 - mmengine - INFO - Epoch(train) [91][450/586] lr: 5.000000e-04 eta: 8:40:20 time: 0.480033 data_time: 0.032394 memory: 15239 loss_kpt: 0.000541 acc_pose: 0.865970 loss: 0.000541 2022/09/15 22:49:21 - mmengine - INFO - Epoch(train) [91][500/586] lr: 5.000000e-04 eta: 8:39:59 time: 0.468017 data_time: 0.023633 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.800833 loss: 0.000543 2022/09/15 22:49:44 - mmengine - INFO - Epoch(train) [91][550/586] lr: 5.000000e-04 eta: 8:39:38 time: 0.473470 data_time: 0.024959 memory: 15239 loss_kpt: 0.000552 acc_pose: 0.813929 loss: 0.000552 2022/09/15 22:50:01 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 22:50:01 - mmengine - INFO - Saving checkpoint at 91 epochs 2022/09/15 22:50:33 - mmengine - INFO - Epoch(train) [92][50/586] lr: 5.000000e-04 eta: 8:38:41 time: 0.483374 data_time: 0.030933 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.888297 loss: 0.000543 2022/09/15 22:50:57 - mmengine - INFO - Epoch(train) [92][100/586] lr: 5.000000e-04 eta: 8:38:21 time: 0.479175 data_time: 0.024650 memory: 15239 loss_kpt: 0.000532 acc_pose: 0.823702 loss: 0.000532 2022/09/15 22:51:21 - mmengine - INFO - Epoch(train) [92][150/586] lr: 5.000000e-04 eta: 8:38:01 time: 0.478486 data_time: 0.025659 memory: 15239 loss_kpt: 0.000532 acc_pose: 0.864990 loss: 0.000532 2022/09/15 22:51:45 - mmengine - INFO - Epoch(train) [92][200/586] lr: 5.000000e-04 eta: 8:37:40 time: 0.479376 data_time: 0.024920 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.847320 loss: 0.000543 2022/09/15 22:52:09 - mmengine - INFO - Epoch(train) [92][250/586] lr: 5.000000e-04 eta: 8:37:21 time: 0.492597 data_time: 0.035463 memory: 15239 loss_kpt: 0.000551 acc_pose: 0.881823 loss: 0.000551 2022/09/15 22:52:33 - mmengine - INFO - Epoch(train) [92][300/586] lr: 5.000000e-04 eta: 8:37:01 time: 0.479253 data_time: 0.028111 memory: 15239 loss_kpt: 0.000554 acc_pose: 0.785885 loss: 0.000554 2022/09/15 22:52:57 - mmengine - INFO - Epoch(train) [92][350/586] lr: 5.000000e-04 eta: 8:36:40 time: 0.471602 data_time: 0.025276 memory: 15239 loss_kpt: 0.000538 acc_pose: 0.877898 loss: 0.000538 2022/09/15 22:53:21 - mmengine - INFO - Epoch(train) [92][400/586] lr: 5.000000e-04 eta: 8:36:19 time: 0.474115 data_time: 0.025545 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.840969 loss: 0.000543 2022/09/15 22:53:44 - mmengine - INFO - Epoch(train) [92][450/586] lr: 5.000000e-04 eta: 8:35:58 time: 0.468307 data_time: 0.025296 memory: 15239 loss_kpt: 0.000529 acc_pose: 0.867857 loss: 0.000529 2022/09/15 22:54:07 - mmengine - INFO - Epoch(train) [92][500/586] lr: 5.000000e-04 eta: 8:35:38 time: 0.469315 data_time: 0.024544 memory: 15239 loss_kpt: 0.000552 acc_pose: 0.869609 loss: 0.000552 2022/09/15 22:54:31 - mmengine - INFO - Epoch(train) [92][550/586] lr: 5.000000e-04 eta: 8:35:17 time: 0.470587 data_time: 0.023637 memory: 15239 loss_kpt: 0.000526 acc_pose: 0.836133 loss: 0.000526 2022/09/15 22:54:48 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 22:54:48 - mmengine - INFO - Saving checkpoint at 92 epochs 2022/09/15 22:55:18 - mmengine - INFO - Epoch(train) [93][50/586] lr: 5.000000e-04 eta: 8:34:19 time: 0.474714 data_time: 0.028618 memory: 15239 loss_kpt: 0.000535 acc_pose: 0.841990 loss: 0.000535 2022/09/15 22:55:36 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 22:55:42 - mmengine - INFO - Epoch(train) [93][100/586] lr: 5.000000e-04 eta: 8:33:59 time: 0.469966 data_time: 0.025017 memory: 15239 loss_kpt: 0.000527 acc_pose: 0.819540 loss: 0.000527 2022/09/15 22:56:05 - mmengine - INFO - Epoch(train) [93][150/586] lr: 5.000000e-04 eta: 8:33:37 time: 0.464842 data_time: 0.024694 memory: 15239 loss_kpt: 0.000538 acc_pose: 0.833386 loss: 0.000538 2022/09/15 22:56:29 - mmengine - INFO - Epoch(train) [93][200/586] lr: 5.000000e-04 eta: 8:33:16 time: 0.466566 data_time: 0.024850 memory: 15239 loss_kpt: 0.000541 acc_pose: 0.802824 loss: 0.000541 2022/09/15 22:56:52 - mmengine - INFO - Epoch(train) [93][250/586] lr: 5.000000e-04 eta: 8:32:56 time: 0.469681 data_time: 0.023743 memory: 15239 loss_kpt: 0.000529 acc_pose: 0.888681 loss: 0.000529 2022/09/15 22:57:15 - mmengine - INFO - Epoch(train) [93][300/586] lr: 5.000000e-04 eta: 8:32:34 time: 0.461532 data_time: 0.024634 memory: 15239 loss_kpt: 0.000533 acc_pose: 0.815520 loss: 0.000533 2022/09/15 22:57:38 - mmengine - INFO - Epoch(train) [93][350/586] lr: 5.000000e-04 eta: 8:32:13 time: 0.467355 data_time: 0.025195 memory: 15239 loss_kpt: 0.000553 acc_pose: 0.788734 loss: 0.000553 2022/09/15 22:58:02 - mmengine - INFO - Epoch(train) [93][400/586] lr: 5.000000e-04 eta: 8:31:52 time: 0.472187 data_time: 0.024282 memory: 15239 loss_kpt: 0.000533 acc_pose: 0.872381 loss: 0.000533 2022/09/15 22:58:25 - mmengine - INFO - Epoch(train) [93][450/586] lr: 5.000000e-04 eta: 8:31:31 time: 0.463282 data_time: 0.024122 memory: 15239 loss_kpt: 0.000533 acc_pose: 0.887018 loss: 0.000533 2022/09/15 22:58:49 - mmengine - INFO - Epoch(train) [93][500/586] lr: 5.000000e-04 eta: 8:31:11 time: 0.475646 data_time: 0.025054 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.891650 loss: 0.000543 2022/09/15 22:59:12 - mmengine - INFO - Epoch(train) [93][550/586] lr: 5.000000e-04 eta: 8:30:50 time: 0.467329 data_time: 0.024983 memory: 15239 loss_kpt: 0.000538 acc_pose: 0.821093 loss: 0.000538 2022/09/15 22:59:29 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 22:59:29 - mmengine - INFO - Saving checkpoint at 93 epochs 2022/09/15 23:00:01 - mmengine - INFO - Epoch(train) [94][50/586] lr: 5.000000e-04 eta: 8:29:53 time: 0.484731 data_time: 0.028986 memory: 15239 loss_kpt: 0.000544 acc_pose: 0.866237 loss: 0.000544 2022/09/15 23:00:24 - mmengine - INFO - Epoch(train) [94][100/586] lr: 5.000000e-04 eta: 8:29:32 time: 0.467940 data_time: 0.024298 memory: 15239 loss_kpt: 0.000539 acc_pose: 0.845245 loss: 0.000539 2022/09/15 23:00:48 - mmengine - INFO - Epoch(train) [94][150/586] lr: 5.000000e-04 eta: 8:29:12 time: 0.471403 data_time: 0.028048 memory: 15239 loss_kpt: 0.000532 acc_pose: 0.820960 loss: 0.000532 2022/09/15 23:01:11 - mmengine - INFO - Epoch(train) [94][200/586] lr: 5.000000e-04 eta: 8:28:50 time: 0.464279 data_time: 0.024084 memory: 15239 loss_kpt: 0.000540 acc_pose: 0.792042 loss: 0.000540 2022/09/15 23:01:34 - mmengine - INFO - Epoch(train) [94][250/586] lr: 5.000000e-04 eta: 8:28:29 time: 0.470512 data_time: 0.025371 memory: 15239 loss_kpt: 0.000520 acc_pose: 0.815785 loss: 0.000520 2022/09/15 23:01:58 - mmengine - INFO - Epoch(train) [94][300/586] lr: 5.000000e-04 eta: 8:28:08 time: 0.466271 data_time: 0.025150 memory: 15239 loss_kpt: 0.000555 acc_pose: 0.897651 loss: 0.000555 2022/09/15 23:02:21 - mmengine - INFO - Epoch(train) [94][350/586] lr: 5.000000e-04 eta: 8:27:47 time: 0.468381 data_time: 0.024407 memory: 15239 loss_kpt: 0.000526 acc_pose: 0.849951 loss: 0.000526 2022/09/15 23:02:45 - mmengine - INFO - Epoch(train) [94][400/586] lr: 5.000000e-04 eta: 8:27:26 time: 0.469766 data_time: 0.025337 memory: 15239 loss_kpt: 0.000538 acc_pose: 0.817722 loss: 0.000538 2022/09/15 23:03:08 - mmengine - INFO - Epoch(train) [94][450/586] lr: 5.000000e-04 eta: 8:27:05 time: 0.463820 data_time: 0.024033 memory: 15239 loss_kpt: 0.000556 acc_pose: 0.883524 loss: 0.000556 2022/09/15 23:03:32 - mmengine - INFO - Epoch(train) [94][500/586] lr: 5.000000e-04 eta: 8:26:45 time: 0.477120 data_time: 0.026755 memory: 15239 loss_kpt: 0.000538 acc_pose: 0.819967 loss: 0.000538 2022/09/15 23:03:33 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 23:03:56 - mmengine - INFO - Epoch(train) [94][550/586] lr: 5.000000e-04 eta: 8:26:25 time: 0.484052 data_time: 0.026233 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.814319 loss: 0.000543 2022/09/15 23:04:12 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 23:04:12 - mmengine - INFO - Saving checkpoint at 94 epochs 2022/09/15 23:04:43 - mmengine - INFO - Epoch(train) [95][50/586] lr: 5.000000e-04 eta: 8:25:28 time: 0.471296 data_time: 0.030809 memory: 15239 loss_kpt: 0.000524 acc_pose: 0.822676 loss: 0.000524 2022/09/15 23:05:07 - mmengine - INFO - Epoch(train) [95][100/586] lr: 5.000000e-04 eta: 8:25:08 time: 0.477411 data_time: 0.029752 memory: 15239 loss_kpt: 0.000535 acc_pose: 0.884034 loss: 0.000535 2022/09/15 23:05:30 - mmengine - INFO - Epoch(train) [95][150/586] lr: 5.000000e-04 eta: 8:24:47 time: 0.468363 data_time: 0.024170 memory: 15239 loss_kpt: 0.000524 acc_pose: 0.838318 loss: 0.000524 2022/09/15 23:05:54 - mmengine - INFO - Epoch(train) [95][200/586] lr: 5.000000e-04 eta: 8:24:26 time: 0.471083 data_time: 0.025093 memory: 15239 loss_kpt: 0.000527 acc_pose: 0.894136 loss: 0.000527 2022/09/15 23:06:17 - mmengine - INFO - Epoch(train) [95][250/586] lr: 5.000000e-04 eta: 8:24:05 time: 0.465698 data_time: 0.027841 memory: 15239 loss_kpt: 0.000541 acc_pose: 0.897337 loss: 0.000541 2022/09/15 23:06:40 - mmengine - INFO - Epoch(train) [95][300/586] lr: 5.000000e-04 eta: 8:23:43 time: 0.465741 data_time: 0.025579 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.905101 loss: 0.000543 2022/09/15 23:07:04 - mmengine - INFO - Epoch(train) [95][350/586] lr: 5.000000e-04 eta: 8:23:22 time: 0.467605 data_time: 0.025941 memory: 15239 loss_kpt: 0.000550 acc_pose: 0.842432 loss: 0.000550 2022/09/15 23:07:27 - mmengine - INFO - Epoch(train) [95][400/586] lr: 5.000000e-04 eta: 8:23:01 time: 0.464070 data_time: 0.024277 memory: 15239 loss_kpt: 0.000528 acc_pose: 0.795395 loss: 0.000528 2022/09/15 23:07:51 - mmengine - INFO - Epoch(train) [95][450/586] lr: 5.000000e-04 eta: 8:22:41 time: 0.483816 data_time: 0.028349 memory: 15239 loss_kpt: 0.000538 acc_pose: 0.831652 loss: 0.000538 2022/09/15 23:08:15 - mmengine - INFO - Epoch(train) [95][500/586] lr: 5.000000e-04 eta: 8:22:20 time: 0.465945 data_time: 0.024094 memory: 15239 loss_kpt: 0.000520 acc_pose: 0.826063 loss: 0.000520 2022/09/15 23:08:39 - mmengine - INFO - Epoch(train) [95][550/586] lr: 5.000000e-04 eta: 8:22:00 time: 0.493006 data_time: 0.024480 memory: 15239 loss_kpt: 0.000537 acc_pose: 0.858967 loss: 0.000537 2022/09/15 23:08:56 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 23:08:56 - mmengine - INFO - Saving checkpoint at 95 epochs 2022/09/15 23:09:27 - mmengine - INFO - Epoch(train) [96][50/586] lr: 5.000000e-04 eta: 8:21:05 time: 0.487874 data_time: 0.032532 memory: 15239 loss_kpt: 0.000536 acc_pose: 0.759308 loss: 0.000536 2022/09/15 23:09:51 - mmengine - INFO - Epoch(train) [96][100/586] lr: 5.000000e-04 eta: 8:20:44 time: 0.474072 data_time: 0.024900 memory: 15239 loss_kpt: 0.000550 acc_pose: 0.819115 loss: 0.000550 2022/09/15 23:10:16 - mmengine - INFO - Epoch(train) [96][150/586] lr: 5.000000e-04 eta: 8:20:25 time: 0.490508 data_time: 0.034964 memory: 15239 loss_kpt: 0.000536 acc_pose: 0.846744 loss: 0.000536 2022/09/15 23:10:40 - mmengine - INFO - Epoch(train) [96][200/586] lr: 5.000000e-04 eta: 8:20:04 time: 0.480986 data_time: 0.032894 memory: 15239 loss_kpt: 0.000541 acc_pose: 0.938419 loss: 0.000541 2022/09/15 23:11:04 - mmengine - INFO - Epoch(train) [96][250/586] lr: 5.000000e-04 eta: 8:19:45 time: 0.486750 data_time: 0.035813 memory: 15239 loss_kpt: 0.000536 acc_pose: 0.858340 loss: 0.000536 2022/09/15 23:11:28 - mmengine - INFO - Epoch(train) [96][300/586] lr: 5.000000e-04 eta: 8:19:24 time: 0.471477 data_time: 0.024443 memory: 15239 loss_kpt: 0.000539 acc_pose: 0.889955 loss: 0.000539 2022/09/15 23:11:42 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 23:11:51 - mmengine - INFO - Epoch(train) [96][350/586] lr: 5.000000e-04 eta: 8:19:03 time: 0.470591 data_time: 0.027741 memory: 15239 loss_kpt: 0.000547 acc_pose: 0.793616 loss: 0.000547 2022/09/15 23:12:15 - mmengine - INFO - Epoch(train) [96][400/586] lr: 5.000000e-04 eta: 8:18:42 time: 0.475741 data_time: 0.024981 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.818964 loss: 0.000543 2022/09/15 23:12:38 - mmengine - INFO - Epoch(train) [96][450/586] lr: 5.000000e-04 eta: 8:18:21 time: 0.467629 data_time: 0.024436 memory: 15239 loss_kpt: 0.000522 acc_pose: 0.798321 loss: 0.000522 2022/09/15 23:13:02 - mmengine - INFO - Epoch(train) [96][500/586] lr: 5.000000e-04 eta: 8:18:00 time: 0.469328 data_time: 0.024083 memory: 15239 loss_kpt: 0.000550 acc_pose: 0.816936 loss: 0.000550 2022/09/15 23:13:25 - mmengine - INFO - Epoch(train) [96][550/586] lr: 5.000000e-04 eta: 8:17:39 time: 0.467592 data_time: 0.025948 memory: 15239 loss_kpt: 0.000541 acc_pose: 0.854624 loss: 0.000541 2022/09/15 23:13:42 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 23:13:42 - mmengine - INFO - Saving checkpoint at 96 epochs 2022/09/15 23:14:13 - mmengine - INFO - Epoch(train) [97][50/586] lr: 5.000000e-04 eta: 8:16:44 time: 0.480227 data_time: 0.035580 memory: 15239 loss_kpt: 0.000533 acc_pose: 0.902633 loss: 0.000533 2022/09/15 23:14:37 - mmengine - INFO - Epoch(train) [97][100/586] lr: 5.000000e-04 eta: 8:16:23 time: 0.476506 data_time: 0.026882 memory: 15239 loss_kpt: 0.000544 acc_pose: 0.863505 loss: 0.000544 2022/09/15 23:15:00 - mmengine - INFO - Epoch(train) [97][150/586] lr: 5.000000e-04 eta: 8:16:02 time: 0.467025 data_time: 0.027985 memory: 15239 loss_kpt: 0.000525 acc_pose: 0.851607 loss: 0.000525 2022/09/15 23:15:24 - mmengine - INFO - Epoch(train) [97][200/586] lr: 5.000000e-04 eta: 8:15:41 time: 0.475712 data_time: 0.028308 memory: 15239 loss_kpt: 0.000528 acc_pose: 0.890794 loss: 0.000528 2022/09/15 23:15:47 - mmengine - INFO - Epoch(train) [97][250/586] lr: 5.000000e-04 eta: 8:15:20 time: 0.470504 data_time: 0.033174 memory: 15239 loss_kpt: 0.000546 acc_pose: 0.886681 loss: 0.000546 2022/09/15 23:16:11 - mmengine - INFO - Epoch(train) [97][300/586] lr: 5.000000e-04 eta: 8:14:59 time: 0.464275 data_time: 0.028273 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.852466 loss: 0.000543 2022/09/15 23:16:34 - mmengine - INFO - Epoch(train) [97][350/586] lr: 5.000000e-04 eta: 8:14:38 time: 0.475610 data_time: 0.035486 memory: 15239 loss_kpt: 0.000548 acc_pose: 0.888611 loss: 0.000548 2022/09/15 23:16:58 - mmengine - INFO - Epoch(train) [97][400/586] lr: 5.000000e-04 eta: 8:14:17 time: 0.470300 data_time: 0.027463 memory: 15239 loss_kpt: 0.000546 acc_pose: 0.849737 loss: 0.000546 2022/09/15 23:17:21 - mmengine - INFO - Epoch(train) [97][450/586] lr: 5.000000e-04 eta: 8:13:56 time: 0.468343 data_time: 0.031615 memory: 15239 loss_kpt: 0.000524 acc_pose: 0.890055 loss: 0.000524 2022/09/15 23:17:45 - mmengine - INFO - Epoch(train) [97][500/586] lr: 5.000000e-04 eta: 8:13:35 time: 0.469917 data_time: 0.028854 memory: 15239 loss_kpt: 0.000521 acc_pose: 0.871628 loss: 0.000521 2022/09/15 23:18:10 - mmengine - INFO - Epoch(train) [97][550/586] lr: 5.000000e-04 eta: 8:13:16 time: 0.500098 data_time: 0.037524 memory: 15239 loss_kpt: 0.000525 acc_pose: 0.898270 loss: 0.000525 2022/09/15 23:18:27 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 23:18:27 - mmengine - INFO - Saving checkpoint at 97 epochs 2022/09/15 23:18:59 - mmengine - INFO - Epoch(train) [98][50/586] lr: 5.000000e-04 eta: 8:12:21 time: 0.476322 data_time: 0.033719 memory: 15239 loss_kpt: 0.000554 acc_pose: 0.919546 loss: 0.000554 2022/09/15 23:19:23 - mmengine - INFO - Epoch(train) [98][100/586] lr: 5.000000e-04 eta: 8:12:01 time: 0.489725 data_time: 0.030499 memory: 15239 loss_kpt: 0.000534 acc_pose: 0.869167 loss: 0.000534 2022/09/15 23:19:47 - mmengine - INFO - Epoch(train) [98][150/586] lr: 5.000000e-04 eta: 8:11:40 time: 0.467153 data_time: 0.024883 memory: 15239 loss_kpt: 0.000528 acc_pose: 0.810225 loss: 0.000528 2022/09/15 23:19:50 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 23:20:10 - mmengine - INFO - Epoch(train) [98][200/586] lr: 5.000000e-04 eta: 8:11:19 time: 0.467711 data_time: 0.024187 memory: 15239 loss_kpt: 0.000537 acc_pose: 0.799726 loss: 0.000537 2022/09/15 23:20:34 - mmengine - INFO - Epoch(train) [98][250/586] lr: 5.000000e-04 eta: 8:10:58 time: 0.477346 data_time: 0.024652 memory: 15239 loss_kpt: 0.000546 acc_pose: 0.860051 loss: 0.000546 2022/09/15 23:20:57 - mmengine - INFO - Epoch(train) [98][300/586] lr: 5.000000e-04 eta: 8:10:37 time: 0.465745 data_time: 0.025165 memory: 15239 loss_kpt: 0.000532 acc_pose: 0.843623 loss: 0.000532 2022/09/15 23:21:21 - mmengine - INFO - Epoch(train) [98][350/586] lr: 5.000000e-04 eta: 8:10:16 time: 0.475367 data_time: 0.024723 memory: 15239 loss_kpt: 0.000546 acc_pose: 0.896957 loss: 0.000546 2022/09/15 23:21:45 - mmengine - INFO - Epoch(train) [98][400/586] lr: 5.000000e-04 eta: 8:09:56 time: 0.475368 data_time: 0.023886 memory: 15239 loss_kpt: 0.000544 acc_pose: 0.805040 loss: 0.000544 2022/09/15 23:22:08 - mmengine - INFO - Epoch(train) [98][450/586] lr: 5.000000e-04 eta: 8:09:34 time: 0.463653 data_time: 0.025166 memory: 15239 loss_kpt: 0.000539 acc_pose: 0.864160 loss: 0.000539 2022/09/15 23:22:31 - mmengine - INFO - Epoch(train) [98][500/586] lr: 5.000000e-04 eta: 8:09:13 time: 0.461776 data_time: 0.024045 memory: 15239 loss_kpt: 0.000556 acc_pose: 0.865351 loss: 0.000556 2022/09/15 23:22:55 - mmengine - INFO - Epoch(train) [98][550/586] lr: 5.000000e-04 eta: 8:08:53 time: 0.482423 data_time: 0.029565 memory: 15239 loss_kpt: 0.000533 acc_pose: 0.860308 loss: 0.000533 2022/09/15 23:23:11 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 23:23:11 - mmengine - INFO - Saving checkpoint at 98 epochs 2022/09/15 23:23:42 - mmengine - INFO - Epoch(train) [99][50/586] lr: 5.000000e-04 eta: 8:07:58 time: 0.476641 data_time: 0.029038 memory: 15239 loss_kpt: 0.000534 acc_pose: 0.894920 loss: 0.000534 2022/09/15 23:24:06 - mmengine - INFO - Epoch(train) [99][100/586] lr: 5.000000e-04 eta: 8:07:37 time: 0.477406 data_time: 0.024768 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.801843 loss: 0.000519 2022/09/15 23:24:29 - mmengine - INFO - Epoch(train) [99][150/586] lr: 5.000000e-04 eta: 8:07:16 time: 0.466506 data_time: 0.024158 memory: 15239 loss_kpt: 0.000544 acc_pose: 0.834458 loss: 0.000544 2022/09/15 23:24:53 - mmengine - INFO - Epoch(train) [99][200/586] lr: 5.000000e-04 eta: 8:06:55 time: 0.479588 data_time: 0.028181 memory: 15239 loss_kpt: 0.000552 acc_pose: 0.795573 loss: 0.000552 2022/09/15 23:25:17 - mmengine - INFO - Epoch(train) [99][250/586] lr: 5.000000e-04 eta: 8:06:34 time: 0.468812 data_time: 0.023715 memory: 15239 loss_kpt: 0.000526 acc_pose: 0.822375 loss: 0.000526 2022/09/15 23:25:40 - mmengine - INFO - Epoch(train) [99][300/586] lr: 5.000000e-04 eta: 8:06:13 time: 0.467538 data_time: 0.024586 memory: 15239 loss_kpt: 0.000522 acc_pose: 0.834996 loss: 0.000522 2022/09/15 23:26:04 - mmengine - INFO - Epoch(train) [99][350/586] lr: 5.000000e-04 eta: 8:05:52 time: 0.469354 data_time: 0.024858 memory: 15239 loss_kpt: 0.000520 acc_pose: 0.866694 loss: 0.000520 2022/09/15 23:26:28 - mmengine - INFO - Epoch(train) [99][400/586] lr: 5.000000e-04 eta: 8:05:31 time: 0.475401 data_time: 0.024649 memory: 15239 loss_kpt: 0.000542 acc_pose: 0.914394 loss: 0.000542 2022/09/15 23:26:51 - mmengine - INFO - Epoch(train) [99][450/586] lr: 5.000000e-04 eta: 8:05:10 time: 0.460280 data_time: 0.025546 memory: 15239 loss_kpt: 0.000528 acc_pose: 0.879746 loss: 0.000528 2022/09/15 23:27:14 - mmengine - INFO - Epoch(train) [99][500/586] lr: 5.000000e-04 eta: 8:04:49 time: 0.467991 data_time: 0.023618 memory: 15239 loss_kpt: 0.000522 acc_pose: 0.845662 loss: 0.000522 2022/09/15 23:27:38 - mmengine - INFO - Epoch(train) [99][550/586] lr: 5.000000e-04 eta: 8:04:28 time: 0.479790 data_time: 0.025044 memory: 15239 loss_kpt: 0.000562 acc_pose: 0.872440 loss: 0.000562 2022/09/15 23:27:48 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 23:27:55 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 23:27:55 - mmengine - INFO - Saving checkpoint at 99 epochs 2022/09/15 23:28:25 - mmengine - INFO - Epoch(train) [100][50/586] lr: 5.000000e-04 eta: 8:03:33 time: 0.470565 data_time: 0.032048 memory: 15239 loss_kpt: 0.000536 acc_pose: 0.914995 loss: 0.000536 2022/09/15 23:28:49 - mmengine - INFO - Epoch(train) [100][100/586] lr: 5.000000e-04 eta: 8:03:12 time: 0.469019 data_time: 0.027969 memory: 15239 loss_kpt: 0.000547 acc_pose: 0.897655 loss: 0.000547 2022/09/15 23:29:12 - mmengine - INFO - Epoch(train) [100][150/586] lr: 5.000000e-04 eta: 8:02:51 time: 0.463876 data_time: 0.028474 memory: 15239 loss_kpt: 0.000549 acc_pose: 0.886173 loss: 0.000549 2022/09/15 23:29:36 - mmengine - INFO - Epoch(train) [100][200/586] lr: 5.000000e-04 eta: 8:02:30 time: 0.472264 data_time: 0.027969 memory: 15239 loss_kpt: 0.000515 acc_pose: 0.833535 loss: 0.000515 2022/09/15 23:30:00 - mmengine - INFO - Epoch(train) [100][250/586] lr: 5.000000e-04 eta: 8:02:09 time: 0.478912 data_time: 0.033640 memory: 15239 loss_kpt: 0.000524 acc_pose: 0.851117 loss: 0.000524 2022/09/15 23:30:23 - mmengine - INFO - Epoch(train) [100][300/586] lr: 5.000000e-04 eta: 8:01:48 time: 0.464656 data_time: 0.029232 memory: 15239 loss_kpt: 0.000512 acc_pose: 0.848298 loss: 0.000512 2022/09/15 23:30:46 - mmengine - INFO - Epoch(train) [100][350/586] lr: 5.000000e-04 eta: 8:01:27 time: 0.465954 data_time: 0.027861 memory: 15239 loss_kpt: 0.000531 acc_pose: 0.856663 loss: 0.000531 2022/09/15 23:31:10 - mmengine - INFO - Epoch(train) [100][400/586] lr: 5.000000e-04 eta: 8:01:06 time: 0.472000 data_time: 0.028666 memory: 15239 loss_kpt: 0.000531 acc_pose: 0.842252 loss: 0.000531 2022/09/15 23:31:33 - mmengine - INFO - Epoch(train) [100][450/586] lr: 5.000000e-04 eta: 8:00:45 time: 0.466940 data_time: 0.030829 memory: 15239 loss_kpt: 0.000524 acc_pose: 0.876609 loss: 0.000524 2022/09/15 23:31:56 - mmengine - INFO - Epoch(train) [100][500/586] lr: 5.000000e-04 eta: 8:00:23 time: 0.462072 data_time: 0.024982 memory: 15239 loss_kpt: 0.000534 acc_pose: 0.859061 loss: 0.000534 2022/09/15 23:32:20 - mmengine - INFO - Epoch(train) [100][550/586] lr: 5.000000e-04 eta: 8:00:02 time: 0.469865 data_time: 0.025534 memory: 15239 loss_kpt: 0.000536 acc_pose: 0.865927 loss: 0.000536 2022/09/15 23:32:36 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 23:32:36 - mmengine - INFO - Saving checkpoint at 100 epochs 2022/09/15 23:32:57 - mmengine - INFO - Epoch(val) [100][50/407] eta: 0:01:33 time: 0.260540 data_time: 0.014680 memory: 15239 2022/09/15 23:33:09 - mmengine - INFO - Epoch(val) [100][100/407] eta: 0:01:17 time: 0.252479 data_time: 0.008530 memory: 2064 2022/09/15 23:33:22 - mmengine - INFO - Epoch(val) [100][150/407] eta: 0:01:05 time: 0.255366 data_time: 0.009096 memory: 2064 2022/09/15 23:33:35 - mmengine - INFO - Epoch(val) [100][200/407] eta: 0:00:52 time: 0.253644 data_time: 0.008814 memory: 2064 2022/09/15 23:33:48 - mmengine - INFO - Epoch(val) [100][250/407] eta: 0:00:40 time: 0.258095 data_time: 0.012501 memory: 2064 2022/09/15 23:34:01 - mmengine - INFO - Epoch(val) [100][300/407] eta: 0:00:27 time: 0.255004 data_time: 0.009014 memory: 2064 2022/09/15 23:34:13 - mmengine - INFO - Epoch(val) [100][350/407] eta: 0:00:14 time: 0.253732 data_time: 0.008651 memory: 2064 2022/09/15 23:34:26 - mmengine - INFO - Epoch(val) [100][400/407] eta: 0:00:01 time: 0.247418 data_time: 0.008115 memory: 2064 2022/09/15 23:35:02 - mmengine - INFO - Evaluating CocoMetric... 2022/09/15 23:35:15 - mmengine - INFO - Epoch(val) [100][407/407] coco/AP: 0.759766 coco/AP .5: 0.904734 coco/AP .75: 0.823524 coco/AP (M): 0.721432 coco/AP (L): 0.828393 coco/AR: 0.807730 coco/AR .5: 0.940019 coco/AR .75: 0.864610 coco/AR (M): 0.765392 coco/AR (L): 0.869379 2022/09/15 23:35:15 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220915/dark_w48_384/best_coco/AP_epoch_80.pth is removed 2022/09/15 23:35:19 - mmengine - INFO - The best checkpoint with 0.7598 coco/AP at 100 epoch is saved to best_coco/AP_epoch_100.pth. 2022/09/15 23:35:43 - mmengine - INFO - Epoch(train) [101][50/586] lr: 5.000000e-04 eta: 7:59:08 time: 0.474846 data_time: 0.031552 memory: 15239 loss_kpt: 0.000531 acc_pose: 0.905079 loss: 0.000531 2022/09/15 23:36:08 - mmengine - INFO - Epoch(train) [101][100/586] lr: 5.000000e-04 eta: 7:58:48 time: 0.492701 data_time: 0.037217 memory: 15239 loss_kpt: 0.000539 acc_pose: 0.835650 loss: 0.000539 2022/09/15 23:36:32 - mmengine - INFO - Epoch(train) [101][150/586] lr: 5.000000e-04 eta: 7:58:27 time: 0.481301 data_time: 0.032335 memory: 15239 loss_kpt: 0.000542 acc_pose: 0.892082 loss: 0.000542 2022/09/15 23:36:56 - mmengine - INFO - Epoch(train) [101][200/586] lr: 5.000000e-04 eta: 7:58:07 time: 0.487668 data_time: 0.034183 memory: 15239 loss_kpt: 0.000524 acc_pose: 0.853649 loss: 0.000524 2022/09/15 23:37:20 - mmengine - INFO - Epoch(train) [101][250/586] lr: 5.000000e-04 eta: 7:57:47 time: 0.480809 data_time: 0.033290 memory: 15239 loss_kpt: 0.000532 acc_pose: 0.842458 loss: 0.000532 2022/09/15 23:37:44 - mmengine - INFO - Epoch(train) [101][300/586] lr: 5.000000e-04 eta: 7:57:26 time: 0.471039 data_time: 0.025215 memory: 15239 loss_kpt: 0.000531 acc_pose: 0.863241 loss: 0.000531 2022/09/15 23:38:07 - mmengine - INFO - Epoch(train) [101][350/586] lr: 5.000000e-04 eta: 7:57:05 time: 0.464611 data_time: 0.025189 memory: 15239 loss_kpt: 0.000526 acc_pose: 0.876699 loss: 0.000526 2022/09/15 23:38:31 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 23:38:31 - mmengine - INFO - Epoch(train) [101][400/586] lr: 5.000000e-04 eta: 7:56:44 time: 0.478742 data_time: 0.032550 memory: 15239 loss_kpt: 0.000539 acc_pose: 0.825958 loss: 0.000539 2022/09/15 23:38:55 - mmengine - INFO - Epoch(train) [101][450/586] lr: 5.000000e-04 eta: 7:56:23 time: 0.470952 data_time: 0.025631 memory: 15239 loss_kpt: 0.000525 acc_pose: 0.836636 loss: 0.000525 2022/09/15 23:39:18 - mmengine - INFO - Epoch(train) [101][500/586] lr: 5.000000e-04 eta: 7:56:02 time: 0.478606 data_time: 0.024237 memory: 15239 loss_kpt: 0.000530 acc_pose: 0.909587 loss: 0.000530 2022/09/15 23:39:43 - mmengine - INFO - Epoch(train) [101][550/586] lr: 5.000000e-04 eta: 7:55:42 time: 0.482367 data_time: 0.030198 memory: 15239 loss_kpt: 0.000518 acc_pose: 0.860656 loss: 0.000518 2022/09/15 23:40:00 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 23:40:00 - mmengine - INFO - Saving checkpoint at 101 epochs 2022/09/15 23:40:32 - mmengine - INFO - Epoch(train) [102][50/586] lr: 5.000000e-04 eta: 7:54:49 time: 0.492139 data_time: 0.033695 memory: 15239 loss_kpt: 0.000535 acc_pose: 0.835927 loss: 0.000535 2022/09/15 23:40:55 - mmengine - INFO - Epoch(train) [102][100/586] lr: 5.000000e-04 eta: 7:54:28 time: 0.468062 data_time: 0.025469 memory: 15239 loss_kpt: 0.000525 acc_pose: 0.825554 loss: 0.000525 2022/09/15 23:41:18 - mmengine - INFO - Epoch(train) [102][150/586] lr: 5.000000e-04 eta: 7:54:06 time: 0.464114 data_time: 0.023831 memory: 15239 loss_kpt: 0.000529 acc_pose: 0.868231 loss: 0.000529 2022/09/15 23:41:42 - mmengine - INFO - Epoch(train) [102][200/586] lr: 5.000000e-04 eta: 7:53:45 time: 0.474229 data_time: 0.025995 memory: 15239 loss_kpt: 0.000531 acc_pose: 0.831219 loss: 0.000531 2022/09/15 23:42:06 - mmengine - INFO - Epoch(train) [102][250/586] lr: 5.000000e-04 eta: 7:53:25 time: 0.472762 data_time: 0.024717 memory: 15239 loss_kpt: 0.000529 acc_pose: 0.871060 loss: 0.000529 2022/09/15 23:42:29 - mmengine - INFO - Epoch(train) [102][300/586] lr: 5.000000e-04 eta: 7:53:03 time: 0.469606 data_time: 0.025348 memory: 15239 loss_kpt: 0.000527 acc_pose: 0.857994 loss: 0.000527 2022/09/15 23:42:53 - mmengine - INFO - Epoch(train) [102][350/586] lr: 5.000000e-04 eta: 7:52:43 time: 0.473716 data_time: 0.029403 memory: 15239 loss_kpt: 0.000557 acc_pose: 0.868710 loss: 0.000557 2022/09/15 23:43:17 - mmengine - INFO - Epoch(train) [102][400/586] lr: 5.000000e-04 eta: 7:52:22 time: 0.479604 data_time: 0.025192 memory: 15239 loss_kpt: 0.000542 acc_pose: 0.759888 loss: 0.000542 2022/09/15 23:43:40 - mmengine - INFO - Epoch(train) [102][450/586] lr: 5.000000e-04 eta: 7:52:01 time: 0.470171 data_time: 0.025535 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.866261 loss: 0.000543 2022/09/15 23:44:04 - mmengine - INFO - Epoch(train) [102][500/586] lr: 5.000000e-04 eta: 7:51:40 time: 0.472511 data_time: 0.025629 memory: 15239 loss_kpt: 0.000528 acc_pose: 0.860121 loss: 0.000528 2022/09/15 23:44:28 - mmengine - INFO - Epoch(train) [102][550/586] lr: 5.000000e-04 eta: 7:51:19 time: 0.478883 data_time: 0.025486 memory: 15239 loss_kpt: 0.000536 acc_pose: 0.849547 loss: 0.000536 2022/09/15 23:44:45 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 23:44:45 - mmengine - INFO - Saving checkpoint at 102 epochs 2022/09/15 23:45:16 - mmengine - INFO - Epoch(train) [103][50/586] lr: 5.000000e-04 eta: 7:50:26 time: 0.478267 data_time: 0.031907 memory: 15239 loss_kpt: 0.000533 acc_pose: 0.874446 loss: 0.000533 2022/09/15 23:45:40 - mmengine - INFO - Epoch(train) [103][100/586] lr: 5.000000e-04 eta: 7:50:05 time: 0.477671 data_time: 0.029727 memory: 15239 loss_kpt: 0.000527 acc_pose: 0.818861 loss: 0.000527 2022/09/15 23:46:03 - mmengine - INFO - Epoch(train) [103][150/586] lr: 5.000000e-04 eta: 7:49:43 time: 0.460136 data_time: 0.023983 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.816355 loss: 0.000508 2022/09/15 23:46:26 - mmengine - INFO - Epoch(train) [103][200/586] lr: 5.000000e-04 eta: 7:49:22 time: 0.473041 data_time: 0.024016 memory: 15239 loss_kpt: 0.000546 acc_pose: 0.895963 loss: 0.000546 2022/09/15 23:46:40 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 23:46:50 - mmengine - INFO - Epoch(train) [103][250/586] lr: 5.000000e-04 eta: 7:49:01 time: 0.468856 data_time: 0.024591 memory: 15239 loss_kpt: 0.000552 acc_pose: 0.850583 loss: 0.000552 2022/09/15 23:47:13 - mmengine - INFO - Epoch(train) [103][300/586] lr: 5.000000e-04 eta: 7:48:40 time: 0.464730 data_time: 0.024990 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.867467 loss: 0.000543 2022/09/15 23:47:37 - mmengine - INFO - Epoch(train) [103][350/586] lr: 5.000000e-04 eta: 7:48:19 time: 0.470600 data_time: 0.025366 memory: 15239 loss_kpt: 0.000528 acc_pose: 0.871732 loss: 0.000528 2022/09/15 23:48:00 - mmengine - INFO - Epoch(train) [103][400/586] lr: 5.000000e-04 eta: 7:47:58 time: 0.466947 data_time: 0.023907 memory: 15239 loss_kpt: 0.000548 acc_pose: 0.835260 loss: 0.000548 2022/09/15 23:48:24 - mmengine - INFO - Epoch(train) [103][450/586] lr: 5.000000e-04 eta: 7:47:37 time: 0.473107 data_time: 0.024373 memory: 15239 loss_kpt: 0.000534 acc_pose: 0.871068 loss: 0.000534 2022/09/15 23:48:47 - mmengine - INFO - Epoch(train) [103][500/586] lr: 5.000000e-04 eta: 7:47:15 time: 0.463600 data_time: 0.023566 memory: 15239 loss_kpt: 0.000530 acc_pose: 0.817846 loss: 0.000530 2022/09/15 23:49:10 - mmengine - INFO - Epoch(train) [103][550/586] lr: 5.000000e-04 eta: 7:46:54 time: 0.469072 data_time: 0.025129 memory: 15239 loss_kpt: 0.000539 acc_pose: 0.897959 loss: 0.000539 2022/09/15 23:49:27 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 23:49:27 - mmengine - INFO - Saving checkpoint at 103 epochs 2022/09/15 23:49:58 - mmengine - INFO - Epoch(train) [104][50/586] lr: 5.000000e-04 eta: 7:46:01 time: 0.476457 data_time: 0.032155 memory: 15239 loss_kpt: 0.000546 acc_pose: 0.850830 loss: 0.000546 2022/09/15 23:50:22 - mmengine - INFO - Epoch(train) [104][100/586] lr: 5.000000e-04 eta: 7:45:39 time: 0.466731 data_time: 0.027488 memory: 15239 loss_kpt: 0.000556 acc_pose: 0.855590 loss: 0.000556 2022/09/15 23:50:46 - mmengine - INFO - Epoch(train) [104][150/586] lr: 5.000000e-04 eta: 7:45:19 time: 0.486385 data_time: 0.036806 memory: 15239 loss_kpt: 0.000529 acc_pose: 0.915567 loss: 0.000529 2022/09/15 23:51:10 - mmengine - INFO - Epoch(train) [104][200/586] lr: 5.000000e-04 eta: 7:44:58 time: 0.475019 data_time: 0.030302 memory: 15239 loss_kpt: 0.000531 acc_pose: 0.850686 loss: 0.000531 2022/09/15 23:51:33 - mmengine - INFO - Epoch(train) [104][250/586] lr: 5.000000e-04 eta: 7:44:37 time: 0.474103 data_time: 0.024972 memory: 15239 loss_kpt: 0.000528 acc_pose: 0.847040 loss: 0.000528 2022/09/15 23:51:57 - mmengine - INFO - Epoch(train) [104][300/586] lr: 5.000000e-04 eta: 7:44:17 time: 0.474593 data_time: 0.024686 memory: 15239 loss_kpt: 0.000546 acc_pose: 0.880720 loss: 0.000546 2022/09/15 23:52:21 - mmengine - INFO - Epoch(train) [104][350/586] lr: 5.000000e-04 eta: 7:43:56 time: 0.474993 data_time: 0.026513 memory: 15239 loss_kpt: 0.000553 acc_pose: 0.838012 loss: 0.000553 2022/09/15 23:52:45 - mmengine - INFO - Epoch(train) [104][400/586] lr: 5.000000e-04 eta: 7:43:35 time: 0.471606 data_time: 0.024556 memory: 15239 loss_kpt: 0.000541 acc_pose: 0.807372 loss: 0.000541 2022/09/15 23:53:08 - mmengine - INFO - Epoch(train) [104][450/586] lr: 5.000000e-04 eta: 7:43:14 time: 0.478414 data_time: 0.024978 memory: 15239 loss_kpt: 0.000533 acc_pose: 0.781881 loss: 0.000533 2022/09/15 23:53:33 - mmengine - INFO - Epoch(train) [104][500/586] lr: 5.000000e-04 eta: 7:42:53 time: 0.481016 data_time: 0.034160 memory: 15239 loss_kpt: 0.000528 acc_pose: 0.859788 loss: 0.000528 2022/09/15 23:53:57 - mmengine - INFO - Epoch(train) [104][550/586] lr: 5.000000e-04 eta: 7:42:33 time: 0.488220 data_time: 0.033075 memory: 15239 loss_kpt: 0.000536 acc_pose: 0.888273 loss: 0.000536 2022/09/15 23:54:14 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 23:54:14 - mmengine - INFO - Saving checkpoint at 104 epochs 2022/09/15 23:54:45 - mmengine - INFO - Epoch(train) [105][50/586] lr: 5.000000e-04 eta: 7:41:40 time: 0.478952 data_time: 0.037371 memory: 15239 loss_kpt: 0.000542 acc_pose: 0.892644 loss: 0.000542 2022/09/15 23:54:47 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 23:55:08 - mmengine - INFO - Epoch(train) [105][100/586] lr: 5.000000e-04 eta: 7:41:19 time: 0.470160 data_time: 0.023749 memory: 15239 loss_kpt: 0.000530 acc_pose: 0.835375 loss: 0.000530 2022/09/15 23:55:32 - mmengine - INFO - Epoch(train) [105][150/586] lr: 5.000000e-04 eta: 7:40:58 time: 0.468283 data_time: 0.025778 memory: 15239 loss_kpt: 0.000538 acc_pose: 0.868294 loss: 0.000538 2022/09/15 23:55:55 - mmengine - INFO - Epoch(train) [105][200/586] lr: 5.000000e-04 eta: 7:40:37 time: 0.466649 data_time: 0.025353 memory: 15239 loss_kpt: 0.000538 acc_pose: 0.860289 loss: 0.000538 2022/09/15 23:56:19 - mmengine - INFO - Epoch(train) [105][250/586] lr: 5.000000e-04 eta: 7:40:16 time: 0.474842 data_time: 0.026428 memory: 15239 loss_kpt: 0.000534 acc_pose: 0.864665 loss: 0.000534 2022/09/15 23:56:42 - mmengine - INFO - Epoch(train) [105][300/586] lr: 5.000000e-04 eta: 7:39:54 time: 0.467448 data_time: 0.024574 memory: 15239 loss_kpt: 0.000546 acc_pose: 0.858607 loss: 0.000546 2022/09/15 23:57:06 - mmengine - INFO - Epoch(train) [105][350/586] lr: 5.000000e-04 eta: 7:39:33 time: 0.470832 data_time: 0.024785 memory: 15239 loss_kpt: 0.000527 acc_pose: 0.816062 loss: 0.000527 2022/09/15 23:57:29 - mmengine - INFO - Epoch(train) [105][400/586] lr: 5.000000e-04 eta: 7:39:12 time: 0.476036 data_time: 0.024133 memory: 15239 loss_kpt: 0.000542 acc_pose: 0.853616 loss: 0.000542 2022/09/15 23:57:53 - mmengine - INFO - Epoch(train) [105][450/586] lr: 5.000000e-04 eta: 7:38:51 time: 0.463023 data_time: 0.024807 memory: 15239 loss_kpt: 0.000533 acc_pose: 0.855635 loss: 0.000533 2022/09/15 23:58:16 - mmengine - INFO - Epoch(train) [105][500/586] lr: 5.000000e-04 eta: 7:38:30 time: 0.465834 data_time: 0.025607 memory: 15239 loss_kpt: 0.000554 acc_pose: 0.839661 loss: 0.000554 2022/09/15 23:58:39 - mmengine - INFO - Epoch(train) [105][550/586] lr: 5.000000e-04 eta: 7:38:08 time: 0.466319 data_time: 0.030008 memory: 15239 loss_kpt: 0.000536 acc_pose: 0.861251 loss: 0.000536 2022/09/15 23:58:56 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/15 23:58:56 - mmengine - INFO - Saving checkpoint at 105 epochs 2022/09/15 23:59:27 - mmengine - INFO - Epoch(train) [106][50/586] lr: 5.000000e-04 eta: 7:37:16 time: 0.486286 data_time: 0.032728 memory: 15239 loss_kpt: 0.000524 acc_pose: 0.879609 loss: 0.000524 2022/09/15 23:59:51 - mmengine - INFO - Epoch(train) [106][100/586] lr: 5.000000e-04 eta: 7:36:55 time: 0.476376 data_time: 0.025304 memory: 15239 loss_kpt: 0.000554 acc_pose: 0.875316 loss: 0.000554 2022/09/16 00:00:17 - mmengine - INFO - Epoch(train) [106][150/586] lr: 5.000000e-04 eta: 7:36:37 time: 0.524419 data_time: 0.030054 memory: 15239 loss_kpt: 0.000539 acc_pose: 0.856805 loss: 0.000539 2022/09/16 00:00:41 - mmengine - INFO - Epoch(train) [106][200/586] lr: 5.000000e-04 eta: 7:36:16 time: 0.473749 data_time: 0.024258 memory: 15239 loss_kpt: 0.000541 acc_pose: 0.785837 loss: 0.000541 2022/09/16 00:01:04 - mmengine - INFO - Epoch(train) [106][250/586] lr: 5.000000e-04 eta: 7:35:54 time: 0.464960 data_time: 0.024790 memory: 15239 loss_kpt: 0.000544 acc_pose: 0.861378 loss: 0.000544 2022/09/16 00:01:28 - mmengine - INFO - Epoch(train) [106][300/586] lr: 5.000000e-04 eta: 7:35:33 time: 0.470101 data_time: 0.024539 memory: 15239 loss_kpt: 0.000513 acc_pose: 0.831852 loss: 0.000513 2022/09/16 00:01:52 - mmengine - INFO - Epoch(train) [106][350/586] lr: 5.000000e-04 eta: 7:35:12 time: 0.479497 data_time: 0.023921 memory: 15239 loss_kpt: 0.000526 acc_pose: 0.828789 loss: 0.000526 2022/09/16 00:02:15 - mmengine - INFO - Epoch(train) [106][400/586] lr: 5.000000e-04 eta: 7:34:51 time: 0.472809 data_time: 0.024332 memory: 15239 loss_kpt: 0.000517 acc_pose: 0.829070 loss: 0.000517 2022/09/16 00:02:39 - mmengine - INFO - Epoch(train) [106][450/586] lr: 5.000000e-04 eta: 7:34:30 time: 0.467201 data_time: 0.024861 memory: 15239 loss_kpt: 0.000546 acc_pose: 0.838536 loss: 0.000546 2022/09/16 00:02:48 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 00:03:02 - mmengine - INFO - Epoch(train) [106][500/586] lr: 5.000000e-04 eta: 7:34:09 time: 0.467908 data_time: 0.024383 memory: 15239 loss_kpt: 0.000540 acc_pose: 0.852537 loss: 0.000540 2022/09/16 00:03:26 - mmengine - INFO - Epoch(train) [106][550/586] lr: 5.000000e-04 eta: 7:33:48 time: 0.470618 data_time: 0.026742 memory: 15239 loss_kpt: 0.000540 acc_pose: 0.847893 loss: 0.000540 2022/09/16 00:03:42 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 00:03:42 - mmengine - INFO - Saving checkpoint at 106 epochs 2022/09/16 00:04:14 - mmengine - INFO - Epoch(train) [107][50/586] lr: 5.000000e-04 eta: 7:32:56 time: 0.489680 data_time: 0.037410 memory: 15239 loss_kpt: 0.000526 acc_pose: 0.824447 loss: 0.000526 2022/09/16 00:04:38 - mmengine - INFO - Epoch(train) [107][100/586] lr: 5.000000e-04 eta: 7:32:35 time: 0.474711 data_time: 0.027841 memory: 15239 loss_kpt: 0.000517 acc_pose: 0.887463 loss: 0.000517 2022/09/16 00:05:01 - mmengine - INFO - Epoch(train) [107][150/586] lr: 5.000000e-04 eta: 7:32:13 time: 0.465908 data_time: 0.024797 memory: 15239 loss_kpt: 0.000532 acc_pose: 0.857219 loss: 0.000532 2022/09/16 00:05:25 - mmengine - INFO - Epoch(train) [107][200/586] lr: 5.000000e-04 eta: 7:31:52 time: 0.470220 data_time: 0.024707 memory: 15239 loss_kpt: 0.000540 acc_pose: 0.824861 loss: 0.000540 2022/09/16 00:05:49 - mmengine - INFO - Epoch(train) [107][250/586] lr: 5.000000e-04 eta: 7:31:31 time: 0.476993 data_time: 0.023799 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.866986 loss: 0.000519 2022/09/16 00:06:12 - mmengine - INFO - Epoch(train) [107][300/586] lr: 5.000000e-04 eta: 7:31:10 time: 0.465257 data_time: 0.025404 memory: 15239 loss_kpt: 0.000541 acc_pose: 0.781387 loss: 0.000541 2022/09/16 00:06:36 - mmengine - INFO - Epoch(train) [107][350/586] lr: 5.000000e-04 eta: 7:30:49 time: 0.473365 data_time: 0.025194 memory: 15239 loss_kpt: 0.000538 acc_pose: 0.881626 loss: 0.000538 2022/09/16 00:06:59 - mmengine - INFO - Epoch(train) [107][400/586] lr: 5.000000e-04 eta: 7:30:28 time: 0.465339 data_time: 0.027030 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.893660 loss: 0.000519 2022/09/16 00:07:22 - mmengine - INFO - Epoch(train) [107][450/586] lr: 5.000000e-04 eta: 7:30:06 time: 0.466858 data_time: 0.025197 memory: 15239 loss_kpt: 0.000541 acc_pose: 0.795392 loss: 0.000541 2022/09/16 00:07:46 - mmengine - INFO - Epoch(train) [107][500/586] lr: 5.000000e-04 eta: 7:29:45 time: 0.477375 data_time: 0.029747 memory: 15239 loss_kpt: 0.000539 acc_pose: 0.871966 loss: 0.000539 2022/09/16 00:08:10 - mmengine - INFO - Epoch(train) [107][550/586] lr: 5.000000e-04 eta: 7:29:24 time: 0.472998 data_time: 0.029010 memory: 15239 loss_kpt: 0.000535 acc_pose: 0.838533 loss: 0.000535 2022/09/16 00:08:27 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 00:08:27 - mmengine - INFO - Saving checkpoint at 107 epochs 2022/09/16 00:08:58 - mmengine - INFO - Epoch(train) [108][50/586] lr: 5.000000e-04 eta: 7:28:32 time: 0.480458 data_time: 0.032568 memory: 15239 loss_kpt: 0.000533 acc_pose: 0.865991 loss: 0.000533 2022/09/16 00:09:21 - mmengine - INFO - Epoch(train) [108][100/586] lr: 5.000000e-04 eta: 7:28:11 time: 0.467636 data_time: 0.028196 memory: 15239 loss_kpt: 0.000522 acc_pose: 0.848280 loss: 0.000522 2022/09/16 00:09:44 - mmengine - INFO - Epoch(train) [108][150/586] lr: 5.000000e-04 eta: 7:27:49 time: 0.465446 data_time: 0.031231 memory: 15239 loss_kpt: 0.000513 acc_pose: 0.893087 loss: 0.000513 2022/09/16 00:10:08 - mmengine - INFO - Epoch(train) [108][200/586] lr: 5.000000e-04 eta: 7:27:28 time: 0.466207 data_time: 0.027729 memory: 15239 loss_kpt: 0.000537 acc_pose: 0.914534 loss: 0.000537 2022/09/16 00:10:31 - mmengine - INFO - Epoch(train) [108][250/586] lr: 5.000000e-04 eta: 7:27:07 time: 0.461893 data_time: 0.027119 memory: 15239 loss_kpt: 0.000518 acc_pose: 0.873440 loss: 0.000518 2022/09/16 00:10:53 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 00:10:54 - mmengine - INFO - Epoch(train) [108][300/586] lr: 5.000000e-04 eta: 7:26:45 time: 0.469309 data_time: 0.030302 memory: 15239 loss_kpt: 0.000525 acc_pose: 0.824221 loss: 0.000525 2022/09/16 00:11:18 - mmengine - INFO - Epoch(train) [108][350/586] lr: 5.000000e-04 eta: 7:26:24 time: 0.466976 data_time: 0.024413 memory: 15239 loss_kpt: 0.000531 acc_pose: 0.842079 loss: 0.000531 2022/09/16 00:11:41 - mmengine - INFO - Epoch(train) [108][400/586] lr: 5.000000e-04 eta: 7:26:02 time: 0.460007 data_time: 0.024797 memory: 15239 loss_kpt: 0.000549 acc_pose: 0.839401 loss: 0.000549 2022/09/16 00:12:04 - mmengine - INFO - Epoch(train) [108][450/586] lr: 5.000000e-04 eta: 7:25:41 time: 0.472741 data_time: 0.028557 memory: 15239 loss_kpt: 0.000527 acc_pose: 0.867404 loss: 0.000527 2022/09/16 00:12:28 - mmengine - INFO - Epoch(train) [108][500/586] lr: 5.000000e-04 eta: 7:25:20 time: 0.471515 data_time: 0.025127 memory: 15239 loss_kpt: 0.000545 acc_pose: 0.845545 loss: 0.000545 2022/09/16 00:12:51 - mmengine - INFO - Epoch(train) [108][550/586] lr: 5.000000e-04 eta: 7:24:59 time: 0.463401 data_time: 0.028655 memory: 15239 loss_kpt: 0.000533 acc_pose: 0.880900 loss: 0.000533 2022/09/16 00:13:08 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 00:13:08 - mmengine - INFO - Saving checkpoint at 108 epochs 2022/09/16 00:13:39 - mmengine - INFO - Epoch(train) [109][50/586] lr: 5.000000e-04 eta: 7:24:07 time: 0.479799 data_time: 0.034859 memory: 15239 loss_kpt: 0.000522 acc_pose: 0.869751 loss: 0.000522 2022/09/16 00:14:02 - mmengine - INFO - Epoch(train) [109][100/586] lr: 5.000000e-04 eta: 7:23:45 time: 0.464051 data_time: 0.025266 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.857896 loss: 0.000509 2022/09/16 00:14:25 - mmengine - INFO - Epoch(train) [109][150/586] lr: 5.000000e-04 eta: 7:23:24 time: 0.465596 data_time: 0.024826 memory: 15239 loss_kpt: 0.000522 acc_pose: 0.756169 loss: 0.000522 2022/09/16 00:14:49 - mmengine - INFO - Epoch(train) [109][200/586] lr: 5.000000e-04 eta: 7:23:03 time: 0.470582 data_time: 0.028204 memory: 15239 loss_kpt: 0.000531 acc_pose: 0.874769 loss: 0.000531 2022/09/16 00:15:12 - mmengine - INFO - Epoch(train) [109][250/586] lr: 5.000000e-04 eta: 7:22:41 time: 0.465160 data_time: 0.025292 memory: 15239 loss_kpt: 0.000534 acc_pose: 0.878967 loss: 0.000534 2022/09/16 00:15:36 - mmengine - INFO - Epoch(train) [109][300/586] lr: 5.000000e-04 eta: 7:22:20 time: 0.472174 data_time: 0.025263 memory: 15239 loss_kpt: 0.000532 acc_pose: 0.851164 loss: 0.000532 2022/09/16 00:15:59 - mmengine - INFO - Epoch(train) [109][350/586] lr: 5.000000e-04 eta: 7:21:59 time: 0.473527 data_time: 0.029891 memory: 15239 loss_kpt: 0.000528 acc_pose: 0.827799 loss: 0.000528 2022/09/16 00:16:23 - mmengine - INFO - Epoch(train) [109][400/586] lr: 5.000000e-04 eta: 7:21:38 time: 0.467526 data_time: 0.025164 memory: 15239 loss_kpt: 0.000550 acc_pose: 0.871195 loss: 0.000550 2022/09/16 00:16:46 - mmengine - INFO - Epoch(train) [109][450/586] lr: 5.000000e-04 eta: 7:21:16 time: 0.465222 data_time: 0.024142 memory: 15239 loss_kpt: 0.000562 acc_pose: 0.807800 loss: 0.000562 2022/09/16 00:17:09 - mmengine - INFO - Epoch(train) [109][500/586] lr: 5.000000e-04 eta: 7:20:55 time: 0.470807 data_time: 0.027446 memory: 15239 loss_kpt: 0.000528 acc_pose: 0.808082 loss: 0.000528 2022/09/16 00:17:33 - mmengine - INFO - Epoch(train) [109][550/586] lr: 5.000000e-04 eta: 7:20:34 time: 0.466282 data_time: 0.024662 memory: 15239 loss_kpt: 0.000531 acc_pose: 0.835185 loss: 0.000531 2022/09/16 00:17:49 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 00:17:49 - mmengine - INFO - Saving checkpoint at 109 epochs 2022/09/16 00:18:21 - mmengine - INFO - Epoch(train) [110][50/586] lr: 5.000000e-04 eta: 7:19:42 time: 0.489272 data_time: 0.031308 memory: 15239 loss_kpt: 0.000536 acc_pose: 0.765583 loss: 0.000536 2022/09/16 00:18:45 - mmengine - INFO - Epoch(train) [110][100/586] lr: 5.000000e-04 eta: 7:19:21 time: 0.470427 data_time: 0.024990 memory: 15239 loss_kpt: 0.000517 acc_pose: 0.893823 loss: 0.000517 2022/09/16 00:18:57 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 00:19:08 - mmengine - INFO - Epoch(train) [110][150/586] lr: 5.000000e-04 eta: 7:19:00 time: 0.473068 data_time: 0.023816 memory: 15239 loss_kpt: 0.000562 acc_pose: 0.880510 loss: 0.000562 2022/09/16 00:19:32 - mmengine - INFO - Epoch(train) [110][200/586] lr: 5.000000e-04 eta: 7:18:39 time: 0.466669 data_time: 0.024576 memory: 15239 loss_kpt: 0.000524 acc_pose: 0.826561 loss: 0.000524 2022/09/16 00:19:55 - mmengine - INFO - Epoch(train) [110][250/586] lr: 5.000000e-04 eta: 7:18:17 time: 0.463969 data_time: 0.024170 memory: 15239 loss_kpt: 0.000529 acc_pose: 0.823210 loss: 0.000529 2022/09/16 00:20:18 - mmengine - INFO - Epoch(train) [110][300/586] lr: 5.000000e-04 eta: 7:17:56 time: 0.464610 data_time: 0.027868 memory: 15239 loss_kpt: 0.000513 acc_pose: 0.891663 loss: 0.000513 2022/09/16 00:20:41 - mmengine - INFO - Epoch(train) [110][350/586] lr: 5.000000e-04 eta: 7:17:34 time: 0.460341 data_time: 0.024382 memory: 15239 loss_kpt: 0.000534 acc_pose: 0.870707 loss: 0.000534 2022/09/16 00:21:04 - mmengine - INFO - Epoch(train) [110][400/586] lr: 5.000000e-04 eta: 7:17:13 time: 0.461317 data_time: 0.024157 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.844958 loss: 0.000543 2022/09/16 00:21:28 - mmengine - INFO - Epoch(train) [110][450/586] lr: 5.000000e-04 eta: 7:16:51 time: 0.471334 data_time: 0.028551 memory: 15239 loss_kpt: 0.000526 acc_pose: 0.857737 loss: 0.000526 2022/09/16 00:21:51 - mmengine - INFO - Epoch(train) [110][500/586] lr: 5.000000e-04 eta: 7:16:30 time: 0.471420 data_time: 0.024999 memory: 15239 loss_kpt: 0.000513 acc_pose: 0.879961 loss: 0.000513 2022/09/16 00:22:14 - mmengine - INFO - Epoch(train) [110][550/586] lr: 5.000000e-04 eta: 7:16:09 time: 0.460860 data_time: 0.023905 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.837345 loss: 0.000509 2022/09/16 00:22:31 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 00:22:31 - mmengine - INFO - Saving checkpoint at 110 epochs 2022/09/16 00:22:52 - mmengine - INFO - Epoch(val) [110][50/407] eta: 0:01:33 time: 0.261526 data_time: 0.016021 memory: 15239 2022/09/16 00:23:05 - mmengine - INFO - Epoch(val) [110][100/407] eta: 0:01:17 time: 0.254005 data_time: 0.011101 memory: 2064 2022/09/16 00:23:17 - mmengine - INFO - Epoch(val) [110][150/407] eta: 0:01:04 time: 0.251548 data_time: 0.009065 memory: 2064 2022/09/16 00:23:30 - mmengine - INFO - Epoch(val) [110][200/407] eta: 0:00:52 time: 0.251986 data_time: 0.008786 memory: 2064 2022/09/16 00:23:43 - mmengine - INFO - Epoch(val) [110][250/407] eta: 0:00:40 time: 0.255798 data_time: 0.012230 memory: 2064 2022/09/16 00:23:55 - mmengine - INFO - Epoch(val) [110][300/407] eta: 0:00:26 time: 0.251969 data_time: 0.009329 memory: 2064 2022/09/16 00:24:08 - mmengine - INFO - Epoch(val) [110][350/407] eta: 0:00:14 time: 0.251533 data_time: 0.008712 memory: 2064 2022/09/16 00:24:20 - mmengine - INFO - Epoch(val) [110][400/407] eta: 0:00:01 time: 0.247470 data_time: 0.008353 memory: 2064 2022/09/16 00:24:55 - mmengine - INFO - Evaluating CocoMetric... 2022/09/16 00:25:08 - mmengine - INFO - Epoch(val) [110][407/407] coco/AP: 0.761185 coco/AP .5: 0.905922 coco/AP .75: 0.823935 coco/AP (M): 0.722340 coco/AP (L): 0.831673 coco/AR: 0.809745 coco/AR .5: 0.941908 coco/AR .75: 0.866499 coco/AR (M): 0.766621 coco/AR (L): 0.872873 2022/09/16 00:25:08 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220915/dark_w48_384/best_coco/AP_epoch_100.pth is removed 2022/09/16 00:25:12 - mmengine - INFO - The best checkpoint with 0.7612 coco/AP at 110 epoch is saved to best_coco/AP_epoch_110.pth. 2022/09/16 00:25:36 - mmengine - INFO - Epoch(train) [111][50/586] lr: 5.000000e-04 eta: 7:15:17 time: 0.479951 data_time: 0.033395 memory: 15239 loss_kpt: 0.000520 acc_pose: 0.837982 loss: 0.000520 2022/09/16 00:26:00 - mmengine - INFO - Epoch(train) [111][100/586] lr: 5.000000e-04 eta: 7:14:56 time: 0.470222 data_time: 0.025422 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.865902 loss: 0.000543 2022/09/16 00:26:24 - mmengine - INFO - Epoch(train) [111][150/586] lr: 5.000000e-04 eta: 7:14:35 time: 0.481728 data_time: 0.024988 memory: 15239 loss_kpt: 0.000531 acc_pose: 0.870594 loss: 0.000531 2022/09/16 00:26:47 - mmengine - INFO - Epoch(train) [111][200/586] lr: 5.000000e-04 eta: 7:14:13 time: 0.454871 data_time: 0.024279 memory: 15239 loss_kpt: 0.000526 acc_pose: 0.842174 loss: 0.000526 2022/09/16 00:27:10 - mmengine - INFO - Epoch(train) [111][250/586] lr: 5.000000e-04 eta: 7:13:52 time: 0.467750 data_time: 0.028507 memory: 15239 loss_kpt: 0.000525 acc_pose: 0.779631 loss: 0.000525 2022/09/16 00:27:34 - mmengine - INFO - Epoch(train) [111][300/586] lr: 5.000000e-04 eta: 7:13:31 time: 0.476771 data_time: 0.025017 memory: 15239 loss_kpt: 0.000539 acc_pose: 0.896706 loss: 0.000539 2022/09/16 00:27:57 - mmengine - INFO - Epoch(train) [111][350/586] lr: 5.000000e-04 eta: 7:13:10 time: 0.464932 data_time: 0.024539 memory: 15239 loss_kpt: 0.000513 acc_pose: 0.849904 loss: 0.000513 2022/09/16 00:28:20 - mmengine - INFO - Epoch(train) [111][400/586] lr: 5.000000e-04 eta: 7:12:48 time: 0.463527 data_time: 0.030066 memory: 15239 loss_kpt: 0.000525 acc_pose: 0.834922 loss: 0.000525 2022/09/16 00:28:44 - mmengine - INFO - Epoch(train) [111][450/586] lr: 5.000000e-04 eta: 7:12:27 time: 0.473317 data_time: 0.024620 memory: 15239 loss_kpt: 0.000533 acc_pose: 0.832376 loss: 0.000533 2022/09/16 00:29:07 - mmengine - INFO - Epoch(train) [111][500/586] lr: 5.000000e-04 eta: 7:12:05 time: 0.460093 data_time: 0.024481 memory: 15239 loss_kpt: 0.000531 acc_pose: 0.848942 loss: 0.000531 2022/09/16 00:29:25 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 00:29:30 - mmengine - INFO - Epoch(train) [111][550/586] lr: 5.000000e-04 eta: 7:11:44 time: 0.466423 data_time: 0.028022 memory: 15239 loss_kpt: 0.000532 acc_pose: 0.862419 loss: 0.000532 2022/09/16 00:29:47 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 00:29:47 - mmengine - INFO - Saving checkpoint at 111 epochs 2022/09/16 00:30:18 - mmengine - INFO - Epoch(train) [112][50/586] lr: 5.000000e-04 eta: 7:10:52 time: 0.471327 data_time: 0.033538 memory: 15239 loss_kpt: 0.000523 acc_pose: 0.858394 loss: 0.000523 2022/09/16 00:30:41 - mmengine - INFO - Epoch(train) [112][100/586] lr: 5.000000e-04 eta: 7:10:30 time: 0.455251 data_time: 0.028312 memory: 15239 loss_kpt: 0.000530 acc_pose: 0.901519 loss: 0.000530 2022/09/16 00:31:04 - mmengine - INFO - Epoch(train) [112][150/586] lr: 5.000000e-04 eta: 7:10:09 time: 0.475034 data_time: 0.028230 memory: 15239 loss_kpt: 0.000533 acc_pose: 0.875309 loss: 0.000533 2022/09/16 00:31:28 - mmengine - INFO - Epoch(train) [112][200/586] lr: 5.000000e-04 eta: 7:09:48 time: 0.465444 data_time: 0.028816 memory: 15239 loss_kpt: 0.000553 acc_pose: 0.793931 loss: 0.000553 2022/09/16 00:31:51 - mmengine - INFO - Epoch(train) [112][250/586] lr: 5.000000e-04 eta: 7:09:26 time: 0.457861 data_time: 0.024523 memory: 15239 loss_kpt: 0.000518 acc_pose: 0.871830 loss: 0.000518 2022/09/16 00:32:14 - mmengine - INFO - Epoch(train) [112][300/586] lr: 5.000000e-04 eta: 7:09:05 time: 0.477385 data_time: 0.026287 memory: 15239 loss_kpt: 0.000528 acc_pose: 0.878359 loss: 0.000528 2022/09/16 00:32:38 - mmengine - INFO - Epoch(train) [112][350/586] lr: 5.000000e-04 eta: 7:08:44 time: 0.467023 data_time: 0.025094 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.877260 loss: 0.000508 2022/09/16 00:33:01 - mmengine - INFO - Epoch(train) [112][400/586] lr: 5.000000e-04 eta: 7:08:22 time: 0.464886 data_time: 0.024202 memory: 15239 loss_kpt: 0.000530 acc_pose: 0.834022 loss: 0.000530 2022/09/16 00:33:24 - mmengine - INFO - Epoch(train) [112][450/586] lr: 5.000000e-04 eta: 7:08:01 time: 0.465133 data_time: 0.024266 memory: 15239 loss_kpt: 0.000517 acc_pose: 0.871467 loss: 0.000517 2022/09/16 00:33:47 - mmengine - INFO - Epoch(train) [112][500/586] lr: 5.000000e-04 eta: 7:07:39 time: 0.464599 data_time: 0.024652 memory: 15239 loss_kpt: 0.000512 acc_pose: 0.850397 loss: 0.000512 2022/09/16 00:34:11 - mmengine - INFO - Epoch(train) [112][550/586] lr: 5.000000e-04 eta: 7:07:18 time: 0.466818 data_time: 0.031044 memory: 15239 loss_kpt: 0.000526 acc_pose: 0.903539 loss: 0.000526 2022/09/16 00:34:27 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 00:34:27 - mmengine - INFO - Saving checkpoint at 112 epochs 2022/09/16 00:34:59 - mmengine - INFO - Epoch(train) [113][50/586] lr: 5.000000e-04 eta: 7:06:27 time: 0.482357 data_time: 0.038777 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.903189 loss: 0.000519 2022/09/16 00:35:22 - mmengine - INFO - Epoch(train) [113][100/586] lr: 5.000000e-04 eta: 7:06:06 time: 0.462928 data_time: 0.027078 memory: 15239 loss_kpt: 0.000518 acc_pose: 0.838632 loss: 0.000518 2022/09/16 00:35:46 - mmengine - INFO - Epoch(train) [113][150/586] lr: 5.000000e-04 eta: 7:05:45 time: 0.476187 data_time: 0.031946 memory: 15239 loss_kpt: 0.000518 acc_pose: 0.831371 loss: 0.000518 2022/09/16 00:36:09 - mmengine - INFO - Epoch(train) [113][200/586] lr: 5.000000e-04 eta: 7:05:23 time: 0.458092 data_time: 0.027974 memory: 15239 loss_kpt: 0.000528 acc_pose: 0.870940 loss: 0.000528 2022/09/16 00:36:32 - mmengine - INFO - Epoch(train) [113][250/586] lr: 5.000000e-04 eta: 7:05:02 time: 0.470069 data_time: 0.031964 memory: 15239 loss_kpt: 0.000524 acc_pose: 0.824741 loss: 0.000524 2022/09/16 00:36:56 - mmengine - INFO - Epoch(train) [113][300/586] lr: 5.000000e-04 eta: 7:04:40 time: 0.468696 data_time: 0.028161 memory: 15239 loss_kpt: 0.000530 acc_pose: 0.839997 loss: 0.000530 2022/09/16 00:37:19 - mmengine - INFO - Epoch(train) [113][350/586] lr: 5.000000e-04 eta: 7:04:19 time: 0.459815 data_time: 0.028698 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.859001 loss: 0.000519 2022/09/16 00:37:27 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 00:37:42 - mmengine - INFO - Epoch(train) [113][400/586] lr: 5.000000e-04 eta: 7:03:57 time: 0.470812 data_time: 0.034859 memory: 15239 loss_kpt: 0.000535 acc_pose: 0.902175 loss: 0.000535 2022/09/16 00:38:05 - mmengine - INFO - Epoch(train) [113][450/586] lr: 5.000000e-04 eta: 7:03:36 time: 0.462044 data_time: 0.027069 memory: 15239 loss_kpt: 0.000514 acc_pose: 0.896589 loss: 0.000514 2022/09/16 00:38:29 - mmengine - INFO - Epoch(train) [113][500/586] lr: 5.000000e-04 eta: 7:03:14 time: 0.466570 data_time: 0.031408 memory: 15239 loss_kpt: 0.000497 acc_pose: 0.877073 loss: 0.000497 2022/09/16 00:38:52 - mmengine - INFO - Epoch(train) [113][550/586] lr: 5.000000e-04 eta: 7:02:53 time: 0.471835 data_time: 0.028350 memory: 15239 loss_kpt: 0.000538 acc_pose: 0.893342 loss: 0.000538 2022/09/16 00:39:09 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 00:39:09 - mmengine - INFO - Saving checkpoint at 113 epochs 2022/09/16 00:39:39 - mmengine - INFO - Epoch(train) [114][50/586] lr: 5.000000e-04 eta: 7:02:02 time: 0.466906 data_time: 0.029165 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.840772 loss: 0.000509 2022/09/16 00:40:03 - mmengine - INFO - Epoch(train) [114][100/586] lr: 5.000000e-04 eta: 7:01:41 time: 0.469466 data_time: 0.025279 memory: 15239 loss_kpt: 0.000527 acc_pose: 0.805159 loss: 0.000527 2022/09/16 00:40:26 - mmengine - INFO - Epoch(train) [114][150/586] lr: 5.000000e-04 eta: 7:01:19 time: 0.472515 data_time: 0.024681 memory: 15239 loss_kpt: 0.000527 acc_pose: 0.882437 loss: 0.000527 2022/09/16 00:40:50 - mmengine - INFO - Epoch(train) [114][200/586] lr: 5.000000e-04 eta: 7:00:58 time: 0.466444 data_time: 0.024535 memory: 15239 loss_kpt: 0.000521 acc_pose: 0.868927 loss: 0.000521 2022/09/16 00:41:13 - mmengine - INFO - Epoch(train) [114][250/586] lr: 5.000000e-04 eta: 7:00:37 time: 0.470050 data_time: 0.028992 memory: 15239 loss_kpt: 0.000525 acc_pose: 0.871850 loss: 0.000525 2022/09/16 00:41:37 - mmengine - INFO - Epoch(train) [114][300/586] lr: 5.000000e-04 eta: 7:00:15 time: 0.468220 data_time: 0.023590 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.827441 loss: 0.000519 2022/09/16 00:42:00 - mmengine - INFO - Epoch(train) [114][350/586] lr: 5.000000e-04 eta: 6:59:54 time: 0.461731 data_time: 0.024766 memory: 15239 loss_kpt: 0.000502 acc_pose: 0.847400 loss: 0.000502 2022/09/16 00:42:23 - mmengine - INFO - Epoch(train) [114][400/586] lr: 5.000000e-04 eta: 6:59:33 time: 0.471052 data_time: 0.024458 memory: 15239 loss_kpt: 0.000525 acc_pose: 0.818096 loss: 0.000525 2022/09/16 00:42:47 - mmengine - INFO - Epoch(train) [114][450/586] lr: 5.000000e-04 eta: 6:59:11 time: 0.472088 data_time: 0.024305 memory: 15239 loss_kpt: 0.000525 acc_pose: 0.875459 loss: 0.000525 2022/09/16 00:43:10 - mmengine - INFO - Epoch(train) [114][500/586] lr: 5.000000e-04 eta: 6:58:50 time: 0.472446 data_time: 0.024989 memory: 15239 loss_kpt: 0.000537 acc_pose: 0.837980 loss: 0.000537 2022/09/16 00:43:34 - mmengine - INFO - Epoch(train) [114][550/586] lr: 5.000000e-04 eta: 6:58:29 time: 0.470281 data_time: 0.024457 memory: 15239 loss_kpt: 0.000538 acc_pose: 0.847386 loss: 0.000538 2022/09/16 00:43:51 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 00:43:51 - mmengine - INFO - Saving checkpoint at 114 epochs 2022/09/16 00:44:21 - mmengine - INFO - Epoch(train) [115][50/586] lr: 5.000000e-04 eta: 6:57:38 time: 0.472434 data_time: 0.028765 memory: 15239 loss_kpt: 0.000537 acc_pose: 0.848135 loss: 0.000537 2022/09/16 00:44:44 - mmengine - INFO - Epoch(train) [115][100/586] lr: 5.000000e-04 eta: 6:57:16 time: 0.459369 data_time: 0.024104 memory: 15239 loss_kpt: 0.000511 acc_pose: 0.883585 loss: 0.000511 2022/09/16 00:45:07 - mmengine - INFO - Epoch(train) [115][150/586] lr: 5.000000e-04 eta: 6:56:55 time: 0.469011 data_time: 0.024611 memory: 15239 loss_kpt: 0.000547 acc_pose: 0.799168 loss: 0.000547 2022/09/16 00:45:29 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 00:45:31 - mmengine - INFO - Epoch(train) [115][200/586] lr: 5.000000e-04 eta: 6:56:33 time: 0.461789 data_time: 0.024352 memory: 15239 loss_kpt: 0.000513 acc_pose: 0.858824 loss: 0.000513 2022/09/16 00:45:54 - mmengine - INFO - Epoch(train) [115][250/586] lr: 5.000000e-04 eta: 6:56:12 time: 0.466796 data_time: 0.025356 memory: 15239 loss_kpt: 0.000517 acc_pose: 0.887935 loss: 0.000517 2022/09/16 00:46:17 - mmengine - INFO - Epoch(train) [115][300/586] lr: 5.000000e-04 eta: 6:55:51 time: 0.464767 data_time: 0.024694 memory: 15239 loss_kpt: 0.000528 acc_pose: 0.856808 loss: 0.000528 2022/09/16 00:46:41 - mmengine - INFO - Epoch(train) [115][350/586] lr: 5.000000e-04 eta: 6:55:29 time: 0.467412 data_time: 0.025032 memory: 15239 loss_kpt: 0.000518 acc_pose: 0.892282 loss: 0.000518 2022/09/16 00:47:04 - mmengine - INFO - Epoch(train) [115][400/586] lr: 5.000000e-04 eta: 6:55:08 time: 0.465534 data_time: 0.024416 memory: 15239 loss_kpt: 0.000520 acc_pose: 0.881512 loss: 0.000520 2022/09/16 00:47:27 - mmengine - INFO - Epoch(train) [115][450/586] lr: 5.000000e-04 eta: 6:54:46 time: 0.461331 data_time: 0.024956 memory: 15239 loss_kpt: 0.000524 acc_pose: 0.829139 loss: 0.000524 2022/09/16 00:47:50 - mmengine - INFO - Epoch(train) [115][500/586] lr: 5.000000e-04 eta: 6:54:25 time: 0.470252 data_time: 0.028718 memory: 15239 loss_kpt: 0.000527 acc_pose: 0.824723 loss: 0.000527 2022/09/16 00:48:14 - mmengine - INFO - Epoch(train) [115][550/586] lr: 5.000000e-04 eta: 6:54:03 time: 0.471424 data_time: 0.025926 memory: 15239 loss_kpt: 0.000541 acc_pose: 0.855748 loss: 0.000541 2022/09/16 00:48:31 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 00:48:31 - mmengine - INFO - Saving checkpoint at 115 epochs 2022/09/16 00:49:01 - mmengine - INFO - Epoch(train) [116][50/586] lr: 5.000000e-04 eta: 6:53:13 time: 0.473730 data_time: 0.031158 memory: 15239 loss_kpt: 0.000520 acc_pose: 0.876486 loss: 0.000520 2022/09/16 00:49:24 - mmengine - INFO - Epoch(train) [116][100/586] lr: 5.000000e-04 eta: 6:52:51 time: 0.458413 data_time: 0.028415 memory: 15239 loss_kpt: 0.000525 acc_pose: 0.836567 loss: 0.000525 2022/09/16 00:49:48 - mmengine - INFO - Epoch(train) [116][150/586] lr: 5.000000e-04 eta: 6:52:30 time: 0.469492 data_time: 0.027273 memory: 15239 loss_kpt: 0.000524 acc_pose: 0.884778 loss: 0.000524 2022/09/16 00:50:11 - mmengine - INFO - Epoch(train) [116][200/586] lr: 5.000000e-04 eta: 6:52:09 time: 0.473155 data_time: 0.028607 memory: 15239 loss_kpt: 0.000512 acc_pose: 0.885960 loss: 0.000512 2022/09/16 00:50:35 - mmengine - INFO - Epoch(train) [116][250/586] lr: 5.000000e-04 eta: 6:51:47 time: 0.463021 data_time: 0.027591 memory: 15239 loss_kpt: 0.000530 acc_pose: 0.829261 loss: 0.000530 2022/09/16 00:50:58 - mmengine - INFO - Epoch(train) [116][300/586] lr: 5.000000e-04 eta: 6:51:26 time: 0.473044 data_time: 0.028474 memory: 15239 loss_kpt: 0.000528 acc_pose: 0.879686 loss: 0.000528 2022/09/16 00:51:22 - mmengine - INFO - Epoch(train) [116][350/586] lr: 5.000000e-04 eta: 6:51:05 time: 0.483884 data_time: 0.034382 memory: 15239 loss_kpt: 0.000521 acc_pose: 0.805748 loss: 0.000521 2022/09/16 00:51:45 - mmengine - INFO - Epoch(train) [116][400/586] lr: 5.000000e-04 eta: 6:50:44 time: 0.460098 data_time: 0.027467 memory: 15239 loss_kpt: 0.000515 acc_pose: 0.846999 loss: 0.000515 2022/09/16 00:52:09 - mmengine - INFO - Epoch(train) [116][450/586] lr: 5.000000e-04 eta: 6:50:23 time: 0.476686 data_time: 0.026351 memory: 15239 loss_kpt: 0.000539 acc_pose: 0.888795 loss: 0.000539 2022/09/16 00:52:32 - mmengine - INFO - Epoch(train) [116][500/586] lr: 5.000000e-04 eta: 6:50:01 time: 0.462479 data_time: 0.024059 memory: 15239 loss_kpt: 0.000518 acc_pose: 0.886992 loss: 0.000518 2022/09/16 00:52:55 - mmengine - INFO - Epoch(train) [116][550/586] lr: 5.000000e-04 eta: 6:49:39 time: 0.460021 data_time: 0.024138 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.901106 loss: 0.000519 2022/09/16 00:53:12 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 00:53:12 - mmengine - INFO - Saving checkpoint at 116 epochs 2022/09/16 00:53:31 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 00:53:43 - mmengine - INFO - Epoch(train) [117][50/586] lr: 5.000000e-04 eta: 6:48:49 time: 0.471882 data_time: 0.029293 memory: 15239 loss_kpt: 0.000517 acc_pose: 0.857629 loss: 0.000517 2022/09/16 00:54:06 - mmengine - INFO - Epoch(train) [117][100/586] lr: 5.000000e-04 eta: 6:48:28 time: 0.470769 data_time: 0.025213 memory: 15239 loss_kpt: 0.000529 acc_pose: 0.829879 loss: 0.000529 2022/09/16 00:54:30 - mmengine - INFO - Epoch(train) [117][150/586] lr: 5.000000e-04 eta: 6:48:07 time: 0.475763 data_time: 0.024892 memory: 15239 loss_kpt: 0.000542 acc_pose: 0.748105 loss: 0.000542 2022/09/16 00:54:53 - mmengine - INFO - Epoch(train) [117][200/586] lr: 5.000000e-04 eta: 6:47:45 time: 0.464243 data_time: 0.024221 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.867702 loss: 0.000509 2022/09/16 00:55:17 - mmengine - INFO - Epoch(train) [117][250/586] lr: 5.000000e-04 eta: 6:47:23 time: 0.464897 data_time: 0.024436 memory: 15239 loss_kpt: 0.000524 acc_pose: 0.828270 loss: 0.000524 2022/09/16 00:55:40 - mmengine - INFO - Epoch(train) [117][300/586] lr: 5.000000e-04 eta: 6:47:02 time: 0.470475 data_time: 0.024664 memory: 15239 loss_kpt: 0.000527 acc_pose: 0.863751 loss: 0.000527 2022/09/16 00:56:04 - mmengine - INFO - Epoch(train) [117][350/586] lr: 5.000000e-04 eta: 6:46:41 time: 0.468772 data_time: 0.024376 memory: 15239 loss_kpt: 0.000523 acc_pose: 0.863914 loss: 0.000523 2022/09/16 00:56:27 - mmengine - INFO - Epoch(train) [117][400/586] lr: 5.000000e-04 eta: 6:46:19 time: 0.468167 data_time: 0.029057 memory: 15239 loss_kpt: 0.000518 acc_pose: 0.906866 loss: 0.000518 2022/09/16 00:56:51 - mmengine - INFO - Epoch(train) [117][450/586] lr: 5.000000e-04 eta: 6:45:58 time: 0.471090 data_time: 0.026474 memory: 15239 loss_kpt: 0.000525 acc_pose: 0.829774 loss: 0.000525 2022/09/16 00:57:14 - mmengine - INFO - Epoch(train) [117][500/586] lr: 5.000000e-04 eta: 6:45:37 time: 0.469259 data_time: 0.024524 memory: 15239 loss_kpt: 0.000524 acc_pose: 0.865282 loss: 0.000524 2022/09/16 00:57:37 - mmengine - INFO - Epoch(train) [117][550/586] lr: 5.000000e-04 eta: 6:45:15 time: 0.458473 data_time: 0.024943 memory: 15239 loss_kpt: 0.000520 acc_pose: 0.835500 loss: 0.000520 2022/09/16 00:57:54 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 00:57:54 - mmengine - INFO - Saving checkpoint at 117 epochs 2022/09/16 00:58:24 - mmengine - INFO - Epoch(train) [118][50/586] lr: 5.000000e-04 eta: 6:44:25 time: 0.471500 data_time: 0.037988 memory: 15239 loss_kpt: 0.000522 acc_pose: 0.859031 loss: 0.000522 2022/09/16 00:58:48 - mmengine - INFO - Epoch(train) [118][100/586] lr: 5.000000e-04 eta: 6:44:04 time: 0.477034 data_time: 0.029424 memory: 15239 loss_kpt: 0.000516 acc_pose: 0.872080 loss: 0.000516 2022/09/16 00:59:12 - mmengine - INFO - Epoch(train) [118][150/586] lr: 5.000000e-04 eta: 6:43:43 time: 0.485265 data_time: 0.032752 memory: 15239 loss_kpt: 0.000520 acc_pose: 0.916747 loss: 0.000520 2022/09/16 00:59:35 - mmengine - INFO - Epoch(train) [118][200/586] lr: 5.000000e-04 eta: 6:43:22 time: 0.462630 data_time: 0.028192 memory: 15239 loss_kpt: 0.000506 acc_pose: 0.847590 loss: 0.000506 2022/09/16 00:59:59 - mmengine - INFO - Epoch(train) [118][250/586] lr: 5.000000e-04 eta: 6:43:00 time: 0.468378 data_time: 0.029085 memory: 15239 loss_kpt: 0.000517 acc_pose: 0.865013 loss: 0.000517 2022/09/16 01:00:22 - mmengine - INFO - Epoch(train) [118][300/586] lr: 5.000000e-04 eta: 6:42:38 time: 0.460765 data_time: 0.028140 memory: 15239 loss_kpt: 0.000535 acc_pose: 0.843608 loss: 0.000535 2022/09/16 01:00:46 - mmengine - INFO - Epoch(train) [118][350/586] lr: 5.000000e-04 eta: 6:42:17 time: 0.475099 data_time: 0.032782 memory: 15239 loss_kpt: 0.000516 acc_pose: 0.882083 loss: 0.000516 2022/09/16 01:01:09 - mmengine - INFO - Epoch(train) [118][400/586] lr: 5.000000e-04 eta: 6:41:56 time: 0.458651 data_time: 0.028550 memory: 15239 loss_kpt: 0.000532 acc_pose: 0.790449 loss: 0.000532 2022/09/16 01:01:26 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 01:01:32 - mmengine - INFO - Epoch(train) [118][450/586] lr: 5.000000e-04 eta: 6:41:34 time: 0.473271 data_time: 0.027648 memory: 15239 loss_kpt: 0.000541 acc_pose: 0.896567 loss: 0.000541 2022/09/16 01:01:56 - mmengine - INFO - Epoch(train) [118][500/586] lr: 5.000000e-04 eta: 6:41:13 time: 0.465423 data_time: 0.026664 memory: 15239 loss_kpt: 0.000510 acc_pose: 0.841781 loss: 0.000510 2022/09/16 01:02:18 - mmengine - INFO - Epoch(train) [118][550/586] lr: 5.000000e-04 eta: 6:40:51 time: 0.457178 data_time: 0.027757 memory: 15239 loss_kpt: 0.000502 acc_pose: 0.826332 loss: 0.000502 2022/09/16 01:02:35 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 01:02:35 - mmengine - INFO - Saving checkpoint at 118 epochs 2022/09/16 01:03:07 - mmengine - INFO - Epoch(train) [119][50/586] lr: 5.000000e-04 eta: 6:40:02 time: 0.493443 data_time: 0.032981 memory: 15239 loss_kpt: 0.000524 acc_pose: 0.883201 loss: 0.000524 2022/09/16 01:03:30 - mmengine - INFO - Epoch(train) [119][100/586] lr: 5.000000e-04 eta: 6:39:40 time: 0.460169 data_time: 0.024642 memory: 15239 loss_kpt: 0.000520 acc_pose: 0.860243 loss: 0.000520 2022/09/16 01:03:54 - mmengine - INFO - Epoch(train) [119][150/586] lr: 5.000000e-04 eta: 6:39:19 time: 0.479464 data_time: 0.026028 memory: 15239 loss_kpt: 0.000507 acc_pose: 0.867186 loss: 0.000507 2022/09/16 01:04:17 - mmengine - INFO - Epoch(train) [119][200/586] lr: 5.000000e-04 eta: 6:38:58 time: 0.471837 data_time: 0.030686 memory: 15239 loss_kpt: 0.000527 acc_pose: 0.892341 loss: 0.000527 2022/09/16 01:04:41 - mmengine - INFO - Epoch(train) [119][250/586] lr: 5.000000e-04 eta: 6:38:37 time: 0.469695 data_time: 0.024574 memory: 15239 loss_kpt: 0.000510 acc_pose: 0.812582 loss: 0.000510 2022/09/16 01:05:04 - mmengine - INFO - Epoch(train) [119][300/586] lr: 5.000000e-04 eta: 6:38:15 time: 0.467707 data_time: 0.024106 memory: 15239 loss_kpt: 0.000540 acc_pose: 0.869645 loss: 0.000540 2022/09/16 01:05:28 - mmengine - INFO - Epoch(train) [119][350/586] lr: 5.000000e-04 eta: 6:37:54 time: 0.483320 data_time: 0.025330 memory: 15239 loss_kpt: 0.000512 acc_pose: 0.864279 loss: 0.000512 2022/09/16 01:05:51 - mmengine - INFO - Epoch(train) [119][400/586] lr: 5.000000e-04 eta: 6:37:33 time: 0.462223 data_time: 0.024778 memory: 15239 loss_kpt: 0.000523 acc_pose: 0.834902 loss: 0.000523 2022/09/16 01:06:15 - mmengine - INFO - Epoch(train) [119][450/586] lr: 5.000000e-04 eta: 6:37:11 time: 0.473114 data_time: 0.026820 memory: 15239 loss_kpt: 0.000518 acc_pose: 0.876590 loss: 0.000518 2022/09/16 01:06:39 - mmengine - INFO - Epoch(train) [119][500/586] lr: 5.000000e-04 eta: 6:36:50 time: 0.473811 data_time: 0.023997 memory: 15239 loss_kpt: 0.000533 acc_pose: 0.831323 loss: 0.000533 2022/09/16 01:07:02 - mmengine - INFO - Epoch(train) [119][550/586] lr: 5.000000e-04 eta: 6:36:29 time: 0.473503 data_time: 0.024399 memory: 15239 loss_kpt: 0.000527 acc_pose: 0.896744 loss: 0.000527 2022/09/16 01:07:19 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 01:07:19 - mmengine - INFO - Saving checkpoint at 119 epochs 2022/09/16 01:07:50 - mmengine - INFO - Epoch(train) [120][50/586] lr: 5.000000e-04 eta: 6:35:40 time: 0.474906 data_time: 0.031961 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.831052 loss: 0.000519 2022/09/16 01:08:14 - mmengine - INFO - Epoch(train) [120][100/586] lr: 5.000000e-04 eta: 6:35:18 time: 0.465493 data_time: 0.024329 memory: 15239 loss_kpt: 0.000512 acc_pose: 0.874355 loss: 0.000512 2022/09/16 01:08:37 - mmengine - INFO - Epoch(train) [120][150/586] lr: 5.000000e-04 eta: 6:34:57 time: 0.467685 data_time: 0.029229 memory: 15239 loss_kpt: 0.000525 acc_pose: 0.877712 loss: 0.000525 2022/09/16 01:09:01 - mmengine - INFO - Epoch(train) [120][200/586] lr: 5.000000e-04 eta: 6:34:35 time: 0.472845 data_time: 0.024942 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.770194 loss: 0.000519 2022/09/16 01:09:24 - mmengine - INFO - Epoch(train) [120][250/586] lr: 5.000000e-04 eta: 6:34:14 time: 0.470199 data_time: 0.024463 memory: 15239 loss_kpt: 0.000520 acc_pose: 0.874559 loss: 0.000520 2022/09/16 01:09:32 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 01:09:48 - mmengine - INFO - Epoch(train) [120][300/586] lr: 5.000000e-04 eta: 6:33:53 time: 0.472452 data_time: 0.028986 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.896319 loss: 0.000519 2022/09/16 01:10:11 - mmengine - INFO - Epoch(train) [120][350/586] lr: 5.000000e-04 eta: 6:33:31 time: 0.470006 data_time: 0.024108 memory: 15239 loss_kpt: 0.000515 acc_pose: 0.876605 loss: 0.000515 2022/09/16 01:10:35 - mmengine - INFO - Epoch(train) [120][400/586] lr: 5.000000e-04 eta: 6:33:10 time: 0.467163 data_time: 0.025043 memory: 15239 loss_kpt: 0.000510 acc_pose: 0.859676 loss: 0.000510 2022/09/16 01:10:58 - mmengine - INFO - Epoch(train) [120][450/586] lr: 5.000000e-04 eta: 6:32:48 time: 0.463714 data_time: 0.025285 memory: 15239 loss_kpt: 0.000505 acc_pose: 0.812879 loss: 0.000505 2022/09/16 01:11:22 - mmengine - INFO - Epoch(train) [120][500/586] lr: 5.000000e-04 eta: 6:32:27 time: 0.476928 data_time: 0.024756 memory: 15239 loss_kpt: 0.000504 acc_pose: 0.816875 loss: 0.000504 2022/09/16 01:11:45 - mmengine - INFO - Epoch(train) [120][550/586] lr: 5.000000e-04 eta: 6:32:06 time: 0.470292 data_time: 0.026540 memory: 15239 loss_kpt: 0.000522 acc_pose: 0.864061 loss: 0.000522 2022/09/16 01:12:02 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 01:12:02 - mmengine - INFO - Saving checkpoint at 120 epochs 2022/09/16 01:12:22 - mmengine - INFO - Epoch(val) [120][50/407] eta: 0:01:32 time: 0.260080 data_time: 0.014557 memory: 15239 2022/09/16 01:12:35 - mmengine - INFO - Epoch(val) [120][100/407] eta: 0:01:17 time: 0.250983 data_time: 0.008854 memory: 2064 2022/09/16 01:12:47 - mmengine - INFO - Epoch(val) [120][150/407] eta: 0:01:04 time: 0.250553 data_time: 0.008780 memory: 2064 2022/09/16 01:13:00 - mmengine - INFO - Epoch(val) [120][200/407] eta: 0:00:51 time: 0.249035 data_time: 0.008690 memory: 2064 2022/09/16 01:13:13 - mmengine - INFO - Epoch(val) [120][250/407] eta: 0:00:40 time: 0.256223 data_time: 0.011906 memory: 2064 2022/09/16 01:13:25 - mmengine - INFO - Epoch(val) [120][300/407] eta: 0:00:26 time: 0.249868 data_time: 0.008670 memory: 2064 2022/09/16 01:13:37 - mmengine - INFO - Epoch(val) [120][350/407] eta: 0:00:14 time: 0.247426 data_time: 0.008748 memory: 2064 2022/09/16 01:13:50 - mmengine - INFO - Epoch(val) [120][400/407] eta: 0:00:01 time: 0.249357 data_time: 0.009237 memory: 2064 2022/09/16 01:14:25 - mmengine - INFO - Evaluating CocoMetric... 2022/09/16 01:14:37 - mmengine - INFO - Epoch(val) [120][407/407] coco/AP: 0.762370 coco/AP .5: 0.908114 coco/AP .75: 0.825340 coco/AP (M): 0.720650 coco/AP (L): 0.835333 coco/AR: 0.810390 coco/AR .5: 0.942223 coco/AR .75: 0.868860 coco/AR (M): 0.764709 coco/AR (L): 0.876589 2022/09/16 01:14:38 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220915/dark_w48_384/best_coco/AP_epoch_110.pth is removed 2022/09/16 01:14:41 - mmengine - INFO - The best checkpoint with 0.7624 coco/AP at 120 epoch is saved to best_coco/AP_epoch_120.pth. 2022/09/16 01:15:05 - mmengine - INFO - Epoch(train) [121][50/586] lr: 5.000000e-04 eta: 6:31:16 time: 0.468045 data_time: 0.031034 memory: 15239 loss_kpt: 0.000520 acc_pose: 0.878943 loss: 0.000520 2022/09/16 01:15:28 - mmengine - INFO - Epoch(train) [121][100/586] lr: 5.000000e-04 eta: 6:30:55 time: 0.469535 data_time: 0.031017 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.888758 loss: 0.000508 2022/09/16 01:15:51 - mmengine - INFO - Epoch(train) [121][150/586] lr: 5.000000e-04 eta: 6:30:33 time: 0.454629 data_time: 0.025472 memory: 15239 loss_kpt: 0.000526 acc_pose: 0.843926 loss: 0.000526 2022/09/16 01:16:14 - mmengine - INFO - Epoch(train) [121][200/586] lr: 5.000000e-04 eta: 6:30:11 time: 0.466428 data_time: 0.024790 memory: 15239 loss_kpt: 0.000545 acc_pose: 0.858531 loss: 0.000545 2022/09/16 01:16:38 - mmengine - INFO - Epoch(train) [121][250/586] lr: 5.000000e-04 eta: 6:29:50 time: 0.467917 data_time: 0.024461 memory: 15239 loss_kpt: 0.000528 acc_pose: 0.906781 loss: 0.000528 2022/09/16 01:17:01 - mmengine - INFO - Epoch(train) [121][300/586] lr: 5.000000e-04 eta: 6:29:28 time: 0.460805 data_time: 0.024117 memory: 15239 loss_kpt: 0.000510 acc_pose: 0.838160 loss: 0.000510 2022/09/16 01:17:24 - mmengine - INFO - Epoch(train) [121][350/586] lr: 5.000000e-04 eta: 6:29:07 time: 0.466994 data_time: 0.025104 memory: 15239 loss_kpt: 0.000522 acc_pose: 0.825048 loss: 0.000522 2022/09/16 01:17:48 - mmengine - INFO - Epoch(train) [121][400/586] lr: 5.000000e-04 eta: 6:28:46 time: 0.474383 data_time: 0.025706 memory: 15239 loss_kpt: 0.000507 acc_pose: 0.867644 loss: 0.000507 2022/09/16 01:18:11 - mmengine - INFO - Epoch(train) [121][450/586] lr: 5.000000e-04 eta: 6:28:24 time: 0.461528 data_time: 0.024952 memory: 15239 loss_kpt: 0.000528 acc_pose: 0.888429 loss: 0.000528 2022/09/16 01:18:34 - mmengine - INFO - Epoch(train) [121][500/586] lr: 5.000000e-04 eta: 6:28:02 time: 0.467157 data_time: 0.025730 memory: 15239 loss_kpt: 0.000527 acc_pose: 0.872678 loss: 0.000527 2022/09/16 01:18:58 - mmengine - INFO - Epoch(train) [121][550/586] lr: 5.000000e-04 eta: 6:27:41 time: 0.473572 data_time: 0.024466 memory: 15239 loss_kpt: 0.000526 acc_pose: 0.849448 loss: 0.000526 2022/09/16 01:19:15 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 01:19:15 - mmengine - INFO - Saving checkpoint at 121 epochs 2022/09/16 01:19:45 - mmengine - INFO - Epoch(train) [122][50/586] lr: 5.000000e-04 eta: 6:26:52 time: 0.467890 data_time: 0.031058 memory: 15239 loss_kpt: 0.000510 acc_pose: 0.859371 loss: 0.000510 2022/09/16 01:20:06 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 01:20:09 - mmengine - INFO - Epoch(train) [122][100/586] lr: 5.000000e-04 eta: 6:26:30 time: 0.467961 data_time: 0.027350 memory: 15239 loss_kpt: 0.000513 acc_pose: 0.899763 loss: 0.000513 2022/09/16 01:20:32 - mmengine - INFO - Epoch(train) [122][150/586] lr: 5.000000e-04 eta: 6:26:09 time: 0.459906 data_time: 0.029003 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.922042 loss: 0.000508 2022/09/16 01:20:55 - mmengine - INFO - Epoch(train) [122][200/586] lr: 5.000000e-04 eta: 6:25:47 time: 0.460283 data_time: 0.024998 memory: 15239 loss_kpt: 0.000523 acc_pose: 0.802763 loss: 0.000523 2022/09/16 01:21:18 - mmengine - INFO - Epoch(train) [122][250/586] lr: 5.000000e-04 eta: 6:25:26 time: 0.475044 data_time: 0.025813 memory: 15239 loss_kpt: 0.000513 acc_pose: 0.896164 loss: 0.000513 2022/09/16 01:21:42 - mmengine - INFO - Epoch(train) [122][300/586] lr: 5.000000e-04 eta: 6:25:04 time: 0.465648 data_time: 0.024905 memory: 15239 loss_kpt: 0.000526 acc_pose: 0.846138 loss: 0.000526 2022/09/16 01:22:05 - mmengine - INFO - Epoch(train) [122][350/586] lr: 5.000000e-04 eta: 6:24:43 time: 0.468685 data_time: 0.025199 memory: 15239 loss_kpt: 0.000510 acc_pose: 0.843295 loss: 0.000510 2022/09/16 01:22:28 - mmengine - INFO - Epoch(train) [122][400/586] lr: 5.000000e-04 eta: 6:24:21 time: 0.461700 data_time: 0.025400 memory: 15239 loss_kpt: 0.000513 acc_pose: 0.939265 loss: 0.000513 2022/09/16 01:22:52 - mmengine - INFO - Epoch(train) [122][450/586] lr: 5.000000e-04 eta: 6:24:00 time: 0.466992 data_time: 0.024797 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.828362 loss: 0.000519 2022/09/16 01:23:15 - mmengine - INFO - Epoch(train) [122][500/586] lr: 5.000000e-04 eta: 6:23:38 time: 0.468465 data_time: 0.026810 memory: 15239 loss_kpt: 0.000525 acc_pose: 0.899219 loss: 0.000525 2022/09/16 01:23:38 - mmengine - INFO - Epoch(train) [122][550/586] lr: 5.000000e-04 eta: 6:23:16 time: 0.461314 data_time: 0.024500 memory: 15239 loss_kpt: 0.000525 acc_pose: 0.885161 loss: 0.000525 2022/09/16 01:23:55 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 01:23:55 - mmengine - INFO - Saving checkpoint at 122 epochs 2022/09/16 01:24:27 - mmengine - INFO - Epoch(train) [123][50/586] lr: 5.000000e-04 eta: 6:22:28 time: 0.497521 data_time: 0.039864 memory: 15239 loss_kpt: 0.000534 acc_pose: 0.869383 loss: 0.000534 2022/09/16 01:24:51 - mmengine - INFO - Epoch(train) [123][100/586] lr: 5.000000e-04 eta: 6:22:07 time: 0.481859 data_time: 0.028075 memory: 15239 loss_kpt: 0.000512 acc_pose: 0.863617 loss: 0.000512 2022/09/16 01:25:15 - mmengine - INFO - Epoch(train) [123][150/586] lr: 5.000000e-04 eta: 6:21:46 time: 0.473518 data_time: 0.028819 memory: 15239 loss_kpt: 0.000502 acc_pose: 0.871351 loss: 0.000502 2022/09/16 01:25:39 - mmengine - INFO - Epoch(train) [123][200/586] lr: 5.000000e-04 eta: 6:21:26 time: 0.492803 data_time: 0.027663 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.894042 loss: 0.000519 2022/09/16 01:26:03 - mmengine - INFO - Epoch(train) [123][250/586] lr: 5.000000e-04 eta: 6:21:04 time: 0.473341 data_time: 0.028823 memory: 15239 loss_kpt: 0.000526 acc_pose: 0.858143 loss: 0.000526 2022/09/16 01:26:27 - mmengine - INFO - Epoch(train) [123][300/586] lr: 5.000000e-04 eta: 6:20:43 time: 0.479311 data_time: 0.031302 memory: 15239 loss_kpt: 0.000521 acc_pose: 0.864273 loss: 0.000521 2022/09/16 01:26:51 - mmengine - INFO - Epoch(train) [123][350/586] lr: 5.000000e-04 eta: 6:20:22 time: 0.476280 data_time: 0.029044 memory: 15239 loss_kpt: 0.000523 acc_pose: 0.839740 loss: 0.000523 2022/09/16 01:27:15 - mmengine - INFO - Epoch(train) [123][400/586] lr: 5.000000e-04 eta: 6:20:01 time: 0.475323 data_time: 0.028012 memory: 15239 loss_kpt: 0.000536 acc_pose: 0.855506 loss: 0.000536 2022/09/16 01:27:38 - mmengine - INFO - Epoch(train) [123][450/586] lr: 5.000000e-04 eta: 6:19:39 time: 0.471905 data_time: 0.031594 memory: 15239 loss_kpt: 0.000530 acc_pose: 0.928447 loss: 0.000530 2022/09/16 01:28:02 - mmengine - INFO - Epoch(train) [123][500/586] lr: 5.000000e-04 eta: 6:19:18 time: 0.469279 data_time: 0.028034 memory: 15239 loss_kpt: 0.000503 acc_pose: 0.832614 loss: 0.000503 2022/09/16 01:28:06 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 01:28:25 - mmengine - INFO - Epoch(train) [123][550/586] lr: 5.000000e-04 eta: 6:18:56 time: 0.467972 data_time: 0.032955 memory: 15239 loss_kpt: 0.000520 acc_pose: 0.871741 loss: 0.000520 2022/09/16 01:28:42 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 01:28:42 - mmengine - INFO - Saving checkpoint at 123 epochs 2022/09/16 01:29:12 - mmengine - INFO - Epoch(train) [124][50/586] lr: 5.000000e-04 eta: 6:18:07 time: 0.464914 data_time: 0.033014 memory: 15239 loss_kpt: 0.000532 acc_pose: 0.782582 loss: 0.000532 2022/09/16 01:29:35 - mmengine - INFO - Epoch(train) [124][100/586] lr: 5.000000e-04 eta: 6:17:46 time: 0.468326 data_time: 0.028065 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.836022 loss: 0.000509 2022/09/16 01:29:59 - mmengine - INFO - Epoch(train) [124][150/586] lr: 5.000000e-04 eta: 6:17:24 time: 0.464480 data_time: 0.027541 memory: 15239 loss_kpt: 0.000530 acc_pose: 0.865411 loss: 0.000530 2022/09/16 01:30:22 - mmengine - INFO - Epoch(train) [124][200/586] lr: 5.000000e-04 eta: 6:17:03 time: 0.468074 data_time: 0.026850 memory: 15239 loss_kpt: 0.000522 acc_pose: 0.794648 loss: 0.000522 2022/09/16 01:30:45 - mmengine - INFO - Epoch(train) [124][250/586] lr: 5.000000e-04 eta: 6:16:41 time: 0.464043 data_time: 0.030745 memory: 15239 loss_kpt: 0.000535 acc_pose: 0.853441 loss: 0.000535 2022/09/16 01:31:09 - mmengine - INFO - Epoch(train) [124][300/586] lr: 5.000000e-04 eta: 6:16:20 time: 0.465575 data_time: 0.024393 memory: 15239 loss_kpt: 0.000521 acc_pose: 0.908793 loss: 0.000521 2022/09/16 01:31:32 - mmengine - INFO - Epoch(train) [124][350/586] lr: 5.000000e-04 eta: 6:15:58 time: 0.469040 data_time: 0.025691 memory: 15239 loss_kpt: 0.000521 acc_pose: 0.879783 loss: 0.000521 2022/09/16 01:31:56 - mmengine - INFO - Epoch(train) [124][400/586] lr: 5.000000e-04 eta: 6:15:37 time: 0.471216 data_time: 0.026432 memory: 15239 loss_kpt: 0.000517 acc_pose: 0.858362 loss: 0.000517 2022/09/16 01:32:19 - mmengine - INFO - Epoch(train) [124][450/586] lr: 5.000000e-04 eta: 6:15:15 time: 0.465113 data_time: 0.028067 memory: 15239 loss_kpt: 0.000515 acc_pose: 0.882376 loss: 0.000515 2022/09/16 01:32:43 - mmengine - INFO - Epoch(train) [124][500/586] lr: 5.000000e-04 eta: 6:14:54 time: 0.475750 data_time: 0.025441 memory: 15239 loss_kpt: 0.000516 acc_pose: 0.907509 loss: 0.000516 2022/09/16 01:33:06 - mmengine - INFO - Epoch(train) [124][550/586] lr: 5.000000e-04 eta: 6:14:33 time: 0.467030 data_time: 0.024652 memory: 15239 loss_kpt: 0.000515 acc_pose: 0.882035 loss: 0.000515 2022/09/16 01:33:23 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 01:33:23 - mmengine - INFO - Saving checkpoint at 124 epochs 2022/09/16 01:33:53 - mmengine - INFO - Epoch(train) [125][50/586] lr: 5.000000e-04 eta: 6:13:44 time: 0.476774 data_time: 0.029128 memory: 15239 loss_kpt: 0.000504 acc_pose: 0.853987 loss: 0.000504 2022/09/16 01:34:17 - mmengine - INFO - Epoch(train) [125][100/586] lr: 5.000000e-04 eta: 6:13:23 time: 0.466353 data_time: 0.025034 memory: 15239 loss_kpt: 0.000516 acc_pose: 0.893992 loss: 0.000516 2022/09/16 01:34:40 - mmengine - INFO - Epoch(train) [125][150/586] lr: 5.000000e-04 eta: 6:13:01 time: 0.467777 data_time: 0.024317 memory: 15239 loss_kpt: 0.000526 acc_pose: 0.844143 loss: 0.000526 2022/09/16 01:35:04 - mmengine - INFO - Epoch(train) [125][200/586] lr: 5.000000e-04 eta: 6:12:40 time: 0.470833 data_time: 0.027775 memory: 15239 loss_kpt: 0.000517 acc_pose: 0.844865 loss: 0.000517 2022/09/16 01:35:27 - mmengine - INFO - Epoch(train) [125][250/586] lr: 5.000000e-04 eta: 6:12:18 time: 0.471411 data_time: 0.024999 memory: 15239 loss_kpt: 0.000535 acc_pose: 0.860499 loss: 0.000535 2022/09/16 01:35:51 - mmengine - INFO - Epoch(train) [125][300/586] lr: 5.000000e-04 eta: 6:11:57 time: 0.470833 data_time: 0.026245 memory: 15239 loss_kpt: 0.000520 acc_pose: 0.885493 loss: 0.000520 2022/09/16 01:36:08 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 01:36:14 - mmengine - INFO - Epoch(train) [125][350/586] lr: 5.000000e-04 eta: 6:11:35 time: 0.467976 data_time: 0.029028 memory: 15239 loss_kpt: 0.000530 acc_pose: 0.848637 loss: 0.000530 2022/09/16 01:36:38 - mmengine - INFO - Epoch(train) [125][400/586] lr: 5.000000e-04 eta: 6:11:14 time: 0.469671 data_time: 0.024892 memory: 15239 loss_kpt: 0.000507 acc_pose: 0.911155 loss: 0.000507 2022/09/16 01:37:01 - mmengine - INFO - Epoch(train) [125][450/586] lr: 5.000000e-04 eta: 6:10:52 time: 0.462177 data_time: 0.024427 memory: 15239 loss_kpt: 0.000526 acc_pose: 0.825464 loss: 0.000526 2022/09/16 01:37:25 - mmengine - INFO - Epoch(train) [125][500/586] lr: 5.000000e-04 eta: 6:10:31 time: 0.478440 data_time: 0.025976 memory: 15239 loss_kpt: 0.000526 acc_pose: 0.889388 loss: 0.000526 2022/09/16 01:37:48 - mmengine - INFO - Epoch(train) [125][550/586] lr: 5.000000e-04 eta: 6:10:10 time: 0.464069 data_time: 0.025270 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.852540 loss: 0.000508 2022/09/16 01:38:04 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 01:38:04 - mmengine - INFO - Saving checkpoint at 125 epochs 2022/09/16 01:38:36 - mmengine - INFO - Epoch(train) [126][50/586] lr: 5.000000e-04 eta: 6:09:22 time: 0.481416 data_time: 0.028315 memory: 15239 loss_kpt: 0.000516 acc_pose: 0.866162 loss: 0.000516 2022/09/16 01:38:59 - mmengine - INFO - Epoch(train) [126][100/586] lr: 5.000000e-04 eta: 6:09:00 time: 0.468580 data_time: 0.024640 memory: 15239 loss_kpt: 0.000514 acc_pose: 0.845637 loss: 0.000514 2022/09/16 01:39:22 - mmengine - INFO - Epoch(train) [126][150/586] lr: 5.000000e-04 eta: 6:08:39 time: 0.468467 data_time: 0.024771 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.901850 loss: 0.000519 2022/09/16 01:39:46 - mmengine - INFO - Epoch(train) [126][200/586] lr: 5.000000e-04 eta: 6:08:17 time: 0.472745 data_time: 0.025394 memory: 15239 loss_kpt: 0.000518 acc_pose: 0.843856 loss: 0.000518 2022/09/16 01:40:10 - mmengine - INFO - Epoch(train) [126][250/586] lr: 5.000000e-04 eta: 6:07:56 time: 0.473622 data_time: 0.025583 memory: 15239 loss_kpt: 0.000518 acc_pose: 0.812652 loss: 0.000518 2022/09/16 01:40:33 - mmengine - INFO - Epoch(train) [126][300/586] lr: 5.000000e-04 eta: 6:07:34 time: 0.466539 data_time: 0.024378 memory: 15239 loss_kpt: 0.000520 acc_pose: 0.919025 loss: 0.000520 2022/09/16 01:40:56 - mmengine - INFO - Epoch(train) [126][350/586] lr: 5.000000e-04 eta: 6:07:13 time: 0.464274 data_time: 0.025380 memory: 15239 loss_kpt: 0.000510 acc_pose: 0.889245 loss: 0.000510 2022/09/16 01:41:20 - mmengine - INFO - Epoch(train) [126][400/586] lr: 5.000000e-04 eta: 6:06:51 time: 0.472377 data_time: 0.027266 memory: 15239 loss_kpt: 0.000512 acc_pose: 0.881094 loss: 0.000512 2022/09/16 01:41:43 - mmengine - INFO - Epoch(train) [126][450/586] lr: 5.000000e-04 eta: 6:06:29 time: 0.456323 data_time: 0.025076 memory: 15239 loss_kpt: 0.000503 acc_pose: 0.797410 loss: 0.000503 2022/09/16 01:42:06 - mmengine - INFO - Epoch(train) [126][500/586] lr: 5.000000e-04 eta: 6:06:08 time: 0.467709 data_time: 0.023846 memory: 15239 loss_kpt: 0.000516 acc_pose: 0.882457 loss: 0.000516 2022/09/16 01:42:30 - mmengine - INFO - Epoch(train) [126][550/586] lr: 5.000000e-04 eta: 6:05:46 time: 0.472823 data_time: 0.025918 memory: 15239 loss_kpt: 0.000516 acc_pose: 0.923606 loss: 0.000516 2022/09/16 01:42:46 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 01:42:46 - mmengine - INFO - Saving checkpoint at 126 epochs 2022/09/16 01:43:17 - mmengine - INFO - Epoch(train) [127][50/586] lr: 5.000000e-04 eta: 6:04:58 time: 0.468384 data_time: 0.028201 memory: 15239 loss_kpt: 0.000537 acc_pose: 0.844250 loss: 0.000537 2022/09/16 01:43:40 - mmengine - INFO - Epoch(train) [127][100/586] lr: 5.000000e-04 eta: 6:04:37 time: 0.471224 data_time: 0.024488 memory: 15239 loss_kpt: 0.000527 acc_pose: 0.873548 loss: 0.000527 2022/09/16 01:44:03 - mmengine - INFO - Epoch(train) [127][150/586] lr: 5.000000e-04 eta: 6:04:15 time: 0.457073 data_time: 0.023690 memory: 15239 loss_kpt: 0.000523 acc_pose: 0.883868 loss: 0.000523 2022/09/16 01:44:10 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 01:44:27 - mmengine - INFO - Epoch(train) [127][200/586] lr: 5.000000e-04 eta: 6:03:54 time: 0.482100 data_time: 0.024105 memory: 15239 loss_kpt: 0.000515 acc_pose: 0.899263 loss: 0.000515 2022/09/16 01:44:50 - mmengine - INFO - Epoch(train) [127][250/586] lr: 5.000000e-04 eta: 6:03:32 time: 0.463327 data_time: 0.023875 memory: 15239 loss_kpt: 0.000503 acc_pose: 0.854343 loss: 0.000503 2022/09/16 01:45:14 - mmengine - INFO - Epoch(train) [127][300/586] lr: 5.000000e-04 eta: 6:03:11 time: 0.469165 data_time: 0.024592 memory: 15239 loss_kpt: 0.000514 acc_pose: 0.866870 loss: 0.000514 2022/09/16 01:45:37 - mmengine - INFO - Epoch(train) [127][350/586] lr: 5.000000e-04 eta: 6:02:49 time: 0.471125 data_time: 0.029220 memory: 15239 loss_kpt: 0.000513 acc_pose: 0.835211 loss: 0.000513 2022/09/16 01:46:00 - mmengine - INFO - Epoch(train) [127][400/586] lr: 5.000000e-04 eta: 6:02:28 time: 0.460405 data_time: 0.025551 memory: 15239 loss_kpt: 0.000527 acc_pose: 0.877337 loss: 0.000527 2022/09/16 01:46:24 - mmengine - INFO - Epoch(train) [127][450/586] lr: 5.000000e-04 eta: 6:02:06 time: 0.468568 data_time: 0.024421 memory: 15239 loss_kpt: 0.000522 acc_pose: 0.817554 loss: 0.000522 2022/09/16 01:46:47 - mmengine - INFO - Epoch(train) [127][500/586] lr: 5.000000e-04 eta: 6:01:44 time: 0.464445 data_time: 0.024854 memory: 15239 loss_kpt: 0.000538 acc_pose: 0.810762 loss: 0.000538 2022/09/16 01:47:10 - mmengine - INFO - Epoch(train) [127][550/586] lr: 5.000000e-04 eta: 6:01:23 time: 0.460372 data_time: 0.024596 memory: 15239 loss_kpt: 0.000526 acc_pose: 0.930716 loss: 0.000526 2022/09/16 01:47:27 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 01:47:27 - mmengine - INFO - Saving checkpoint at 127 epochs 2022/09/16 01:47:57 - mmengine - INFO - Epoch(train) [128][50/586] lr: 5.000000e-04 eta: 6:00:35 time: 0.471375 data_time: 0.030216 memory: 15239 loss_kpt: 0.000503 acc_pose: 0.875854 loss: 0.000503 2022/09/16 01:48:21 - mmengine - INFO - Epoch(train) [128][100/586] lr: 5.000000e-04 eta: 6:00:13 time: 0.472384 data_time: 0.025165 memory: 15239 loss_kpt: 0.000513 acc_pose: 0.895908 loss: 0.000513 2022/09/16 01:48:44 - mmengine - INFO - Epoch(train) [128][150/586] lr: 5.000000e-04 eta: 5:59:52 time: 0.467763 data_time: 0.024339 memory: 15239 loss_kpt: 0.000512 acc_pose: 0.855630 loss: 0.000512 2022/09/16 01:49:08 - mmengine - INFO - Epoch(train) [128][200/586] lr: 5.000000e-04 eta: 5:59:30 time: 0.467627 data_time: 0.024078 memory: 15239 loss_kpt: 0.000516 acc_pose: 0.922072 loss: 0.000516 2022/09/16 01:49:32 - mmengine - INFO - Epoch(train) [128][250/586] lr: 5.000000e-04 eta: 5:59:09 time: 0.476264 data_time: 0.026646 memory: 15239 loss_kpt: 0.000524 acc_pose: 0.741640 loss: 0.000524 2022/09/16 01:49:55 - mmengine - INFO - Epoch(train) [128][300/586] lr: 5.000000e-04 eta: 5:58:47 time: 0.463015 data_time: 0.024477 memory: 15239 loss_kpt: 0.000496 acc_pose: 0.854069 loss: 0.000496 2022/09/16 01:50:18 - mmengine - INFO - Epoch(train) [128][350/586] lr: 5.000000e-04 eta: 5:58:26 time: 0.466929 data_time: 0.024787 memory: 15239 loss_kpt: 0.000495 acc_pose: 0.852718 loss: 0.000495 2022/09/16 01:50:41 - mmengine - INFO - Epoch(train) [128][400/586] lr: 5.000000e-04 eta: 5:58:04 time: 0.462793 data_time: 0.029623 memory: 15239 loss_kpt: 0.000517 acc_pose: 0.893899 loss: 0.000517 2022/09/16 01:51:04 - mmengine - INFO - Epoch(train) [128][450/586] lr: 5.000000e-04 eta: 5:57:42 time: 0.462599 data_time: 0.024580 memory: 15239 loss_kpt: 0.000507 acc_pose: 0.896939 loss: 0.000507 2022/09/16 01:51:28 - mmengine - INFO - Epoch(train) [128][500/586] lr: 5.000000e-04 eta: 5:57:21 time: 0.467264 data_time: 0.023855 memory: 15239 loss_kpt: 0.000535 acc_pose: 0.831570 loss: 0.000535 2022/09/16 01:51:51 - mmengine - INFO - Epoch(train) [128][550/586] lr: 5.000000e-04 eta: 5:56:59 time: 0.467655 data_time: 0.025273 memory: 15239 loss_kpt: 0.000512 acc_pose: 0.862196 loss: 0.000512 2022/09/16 01:52:04 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 01:52:08 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 01:52:08 - mmengine - INFO - Saving checkpoint at 128 epochs 2022/09/16 01:52:39 - mmengine - INFO - Epoch(train) [129][50/586] lr: 5.000000e-04 eta: 5:56:11 time: 0.473950 data_time: 0.030098 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.889173 loss: 0.000519 2022/09/16 01:53:02 - mmengine - INFO - Epoch(train) [129][100/586] lr: 5.000000e-04 eta: 5:55:50 time: 0.467424 data_time: 0.025185 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.902647 loss: 0.000508 2022/09/16 01:53:25 - mmengine - INFO - Epoch(train) [129][150/586] lr: 5.000000e-04 eta: 5:55:28 time: 0.463985 data_time: 0.025226 memory: 15239 loss_kpt: 0.000532 acc_pose: 0.873630 loss: 0.000532 2022/09/16 01:53:49 - mmengine - INFO - Epoch(train) [129][200/586] lr: 5.000000e-04 eta: 5:55:07 time: 0.466182 data_time: 0.023951 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.905791 loss: 0.000519 2022/09/16 01:54:13 - mmengine - INFO - Epoch(train) [129][250/586] lr: 5.000000e-04 eta: 5:54:46 time: 0.481556 data_time: 0.024322 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.848867 loss: 0.000508 2022/09/16 01:54:36 - mmengine - INFO - Epoch(train) [129][300/586] lr: 5.000000e-04 eta: 5:54:24 time: 0.466724 data_time: 0.024547 memory: 15239 loss_kpt: 0.000515 acc_pose: 0.851920 loss: 0.000515 2022/09/16 01:55:00 - mmengine - INFO - Epoch(train) [129][350/586] lr: 5.000000e-04 eta: 5:54:03 time: 0.470957 data_time: 0.029784 memory: 15239 loss_kpt: 0.000504 acc_pose: 0.905545 loss: 0.000504 2022/09/16 01:55:23 - mmengine - INFO - Epoch(train) [129][400/586] lr: 5.000000e-04 eta: 5:53:41 time: 0.467206 data_time: 0.025358 memory: 15239 loss_kpt: 0.000511 acc_pose: 0.894233 loss: 0.000511 2022/09/16 01:55:46 - mmengine - INFO - Epoch(train) [129][450/586] lr: 5.000000e-04 eta: 5:53:19 time: 0.463846 data_time: 0.025563 memory: 15239 loss_kpt: 0.000521 acc_pose: 0.816150 loss: 0.000521 2022/09/16 01:56:10 - mmengine - INFO - Epoch(train) [129][500/586] lr: 5.000000e-04 eta: 5:52:58 time: 0.472985 data_time: 0.024636 memory: 15239 loss_kpt: 0.000535 acc_pose: 0.888667 loss: 0.000535 2022/09/16 01:56:33 - mmengine - INFO - Epoch(train) [129][550/586] lr: 5.000000e-04 eta: 5:52:36 time: 0.463604 data_time: 0.025420 memory: 15239 loss_kpt: 0.000510 acc_pose: 0.862800 loss: 0.000510 2022/09/16 01:56:50 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 01:56:50 - mmengine - INFO - Saving checkpoint at 129 epochs 2022/09/16 01:57:21 - mmengine - INFO - Epoch(train) [130][50/586] lr: 5.000000e-04 eta: 5:51:49 time: 0.484650 data_time: 0.035369 memory: 15239 loss_kpt: 0.000504 acc_pose: 0.821334 loss: 0.000504 2022/09/16 01:57:44 - mmengine - INFO - Epoch(train) [130][100/586] lr: 5.000000e-04 eta: 5:51:28 time: 0.473343 data_time: 0.029020 memory: 15239 loss_kpt: 0.000505 acc_pose: 0.808880 loss: 0.000505 2022/09/16 01:58:08 - mmengine - INFO - Epoch(train) [130][150/586] lr: 5.000000e-04 eta: 5:51:06 time: 0.463823 data_time: 0.024965 memory: 15239 loss_kpt: 0.000513 acc_pose: 0.874593 loss: 0.000513 2022/09/16 01:58:31 - mmengine - INFO - Epoch(train) [130][200/586] lr: 5.000000e-04 eta: 5:50:44 time: 0.467985 data_time: 0.024555 memory: 15239 loss_kpt: 0.000504 acc_pose: 0.835416 loss: 0.000504 2022/09/16 01:58:54 - mmengine - INFO - Epoch(train) [130][250/586] lr: 5.000000e-04 eta: 5:50:23 time: 0.466677 data_time: 0.024104 memory: 15239 loss_kpt: 0.000515 acc_pose: 0.874279 loss: 0.000515 2022/09/16 01:59:18 - mmengine - INFO - Epoch(train) [130][300/586] lr: 5.000000e-04 eta: 5:50:01 time: 0.464639 data_time: 0.024444 memory: 15239 loss_kpt: 0.000507 acc_pose: 0.907601 loss: 0.000507 2022/09/16 01:59:41 - mmengine - INFO - Epoch(train) [130][350/586] lr: 5.000000e-04 eta: 5:49:40 time: 0.464488 data_time: 0.024068 memory: 15239 loss_kpt: 0.000522 acc_pose: 0.828126 loss: 0.000522 2022/09/16 02:00:04 - mmengine - INFO - Epoch(train) [130][400/586] lr: 5.000000e-04 eta: 5:49:18 time: 0.463429 data_time: 0.027930 memory: 15239 loss_kpt: 0.000515 acc_pose: 0.870070 loss: 0.000515 2022/09/16 02:00:07 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 02:00:28 - mmengine - INFO - Epoch(train) [130][450/586] lr: 5.000000e-04 eta: 5:48:56 time: 0.475410 data_time: 0.025355 memory: 15239 loss_kpt: 0.000501 acc_pose: 0.904679 loss: 0.000501 2022/09/16 02:00:52 - mmengine - INFO - Epoch(train) [130][500/586] lr: 5.000000e-04 eta: 5:48:36 time: 0.491306 data_time: 0.025503 memory: 15239 loss_kpt: 0.000503 acc_pose: 0.836132 loss: 0.000503 2022/09/16 02:01:16 - mmengine - INFO - Epoch(train) [130][550/586] lr: 5.000000e-04 eta: 5:48:14 time: 0.463976 data_time: 0.024839 memory: 15239 loss_kpt: 0.000522 acc_pose: 0.888581 loss: 0.000522 2022/09/16 02:01:33 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 02:01:33 - mmengine - INFO - Saving checkpoint at 130 epochs 2022/09/16 02:01:53 - mmengine - INFO - Epoch(val) [130][50/407] eta: 0:01:32 time: 0.259637 data_time: 0.012944 memory: 15239 2022/09/16 02:02:05 - mmengine - INFO - Epoch(val) [130][100/407] eta: 0:01:17 time: 0.251756 data_time: 0.008640 memory: 2064 2022/09/16 02:02:18 - mmengine - INFO - Epoch(val) [130][150/407] eta: 0:01:04 time: 0.250134 data_time: 0.008473 memory: 2064 2022/09/16 02:02:30 - mmengine - INFO - Epoch(val) [130][200/407] eta: 0:00:51 time: 0.250934 data_time: 0.008803 memory: 2064 2022/09/16 02:02:43 - mmengine - INFO - Epoch(val) [130][250/407] eta: 0:00:39 time: 0.253617 data_time: 0.009016 memory: 2064 2022/09/16 02:02:56 - mmengine - INFO - Epoch(val) [130][300/407] eta: 0:00:26 time: 0.251479 data_time: 0.008329 memory: 2064 2022/09/16 02:03:08 - mmengine - INFO - Epoch(val) [130][350/407] eta: 0:00:14 time: 0.251051 data_time: 0.008782 memory: 2064 2022/09/16 02:03:21 - mmengine - INFO - Epoch(val) [130][400/407] eta: 0:00:01 time: 0.248350 data_time: 0.008024 memory: 2064 2022/09/16 02:03:56 - mmengine - INFO - Evaluating CocoMetric... 2022/09/16 02:04:09 - mmengine - INFO - Epoch(val) [130][407/407] coco/AP: 0.763121 coco/AP .5: 0.907542 coco/AP .75: 0.823420 coco/AP (M): 0.725326 coco/AP (L): 0.832439 coco/AR: 0.812626 coco/AR .5: 0.943325 coco/AR .75: 0.868545 coco/AR (M): 0.770172 coco/AR (L): 0.874805 2022/09/16 02:04:09 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220915/dark_w48_384/best_coco/AP_epoch_120.pth is removed 2022/09/16 02:04:13 - mmengine - INFO - The best checkpoint with 0.7631 coco/AP at 130 epoch is saved to best_coco/AP_epoch_130.pth. 2022/09/16 02:04:37 - mmengine - INFO - Epoch(train) [131][50/586] lr: 5.000000e-04 eta: 5:47:27 time: 0.475661 data_time: 0.027982 memory: 15239 loss_kpt: 0.000501 acc_pose: 0.850773 loss: 0.000501 2022/09/16 02:05:00 - mmengine - INFO - Epoch(train) [131][100/586] lr: 5.000000e-04 eta: 5:47:05 time: 0.468537 data_time: 0.024365 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.855328 loss: 0.000519 2022/09/16 02:05:24 - mmengine - INFO - Epoch(train) [131][150/586] lr: 5.000000e-04 eta: 5:46:44 time: 0.469987 data_time: 0.024487 memory: 15239 loss_kpt: 0.000498 acc_pose: 0.842572 loss: 0.000498 2022/09/16 02:05:47 - mmengine - INFO - Epoch(train) [131][200/586] lr: 5.000000e-04 eta: 5:46:22 time: 0.469851 data_time: 0.024688 memory: 15239 loss_kpt: 0.000515 acc_pose: 0.840918 loss: 0.000515 2022/09/16 02:06:12 - mmengine - INFO - Epoch(train) [131][250/586] lr: 5.000000e-04 eta: 5:46:01 time: 0.483224 data_time: 0.028618 memory: 15239 loss_kpt: 0.000502 acc_pose: 0.900667 loss: 0.000502 2022/09/16 02:06:35 - mmengine - INFO - Epoch(train) [131][300/586] lr: 5.000000e-04 eta: 5:45:40 time: 0.472464 data_time: 0.025291 memory: 15239 loss_kpt: 0.000512 acc_pose: 0.881076 loss: 0.000512 2022/09/16 02:06:58 - mmengine - INFO - Epoch(train) [131][350/586] lr: 5.000000e-04 eta: 5:45:18 time: 0.463231 data_time: 0.025029 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.858023 loss: 0.000519 2022/09/16 02:07:22 - mmengine - INFO - Epoch(train) [131][400/586] lr: 5.000000e-04 eta: 5:44:57 time: 0.479233 data_time: 0.025346 memory: 15239 loss_kpt: 0.000524 acc_pose: 0.885986 loss: 0.000524 2022/09/16 02:07:46 - mmengine - INFO - Epoch(train) [131][450/586] lr: 5.000000e-04 eta: 5:44:35 time: 0.465544 data_time: 0.024800 memory: 15239 loss_kpt: 0.000502 acc_pose: 0.863719 loss: 0.000502 2022/09/16 02:08:09 - mmengine - INFO - Epoch(train) [131][500/586] lr: 5.000000e-04 eta: 5:44:13 time: 0.466163 data_time: 0.025002 memory: 15239 loss_kpt: 0.000515 acc_pose: 0.894523 loss: 0.000515 2022/09/16 02:08:34 - mmengine - INFO - Epoch(train) [131][550/586] lr: 5.000000e-04 eta: 5:43:53 time: 0.493622 data_time: 0.036772 memory: 15239 loss_kpt: 0.000511 acc_pose: 0.923379 loss: 0.000511 2022/09/16 02:08:50 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 02:08:51 - mmengine - INFO - Saving checkpoint at 131 epochs 2022/09/16 02:09:22 - mmengine - INFO - Epoch(train) [132][50/586] lr: 5.000000e-04 eta: 5:43:06 time: 0.479725 data_time: 0.033667 memory: 15239 loss_kpt: 0.000520 acc_pose: 0.891173 loss: 0.000520 2022/09/16 02:09:45 - mmengine - INFO - Epoch(train) [132][100/586] lr: 5.000000e-04 eta: 5:42:44 time: 0.472114 data_time: 0.024579 memory: 15239 loss_kpt: 0.000520 acc_pose: 0.889288 loss: 0.000520 2022/09/16 02:10:08 - mmengine - INFO - Epoch(train) [132][150/586] lr: 5.000000e-04 eta: 5:42:22 time: 0.460966 data_time: 0.023996 memory: 15239 loss_kpt: 0.000506 acc_pose: 0.854561 loss: 0.000506 2022/09/16 02:10:32 - mmengine - INFO - Epoch(train) [132][200/586] lr: 5.000000e-04 eta: 5:42:01 time: 0.470267 data_time: 0.028643 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.815330 loss: 0.000519 2022/09/16 02:10:48 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 02:10:55 - mmengine - INFO - Epoch(train) [132][250/586] lr: 5.000000e-04 eta: 5:41:39 time: 0.468016 data_time: 0.024240 memory: 15239 loss_kpt: 0.000527 acc_pose: 0.851081 loss: 0.000527 2022/09/16 02:11:19 - mmengine - INFO - Epoch(train) [132][300/586] lr: 5.000000e-04 eta: 5:41:18 time: 0.473053 data_time: 0.023680 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.882150 loss: 0.000509 2022/09/16 02:11:42 - mmengine - INFO - Epoch(train) [132][350/586] lr: 5.000000e-04 eta: 5:40:56 time: 0.465666 data_time: 0.024119 memory: 15239 loss_kpt: 0.000503 acc_pose: 0.849760 loss: 0.000503 2022/09/16 02:12:06 - mmengine - INFO - Epoch(train) [132][400/586] lr: 5.000000e-04 eta: 5:40:35 time: 0.474527 data_time: 0.024696 memory: 15239 loss_kpt: 0.000506 acc_pose: 0.849359 loss: 0.000506 2022/09/16 02:12:30 - mmengine - INFO - Epoch(train) [132][450/586] lr: 5.000000e-04 eta: 5:40:13 time: 0.474197 data_time: 0.026106 memory: 15239 loss_kpt: 0.000522 acc_pose: 0.778051 loss: 0.000522 2022/09/16 02:12:53 - mmengine - INFO - Epoch(train) [132][500/586] lr: 5.000000e-04 eta: 5:39:52 time: 0.470735 data_time: 0.030662 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.847883 loss: 0.000509 2022/09/16 02:13:17 - mmengine - INFO - Epoch(train) [132][550/586] lr: 5.000000e-04 eta: 5:39:30 time: 0.469834 data_time: 0.024893 memory: 15239 loss_kpt: 0.000525 acc_pose: 0.859118 loss: 0.000525 2022/09/16 02:13:33 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 02:13:33 - mmengine - INFO - Saving checkpoint at 132 epochs 2022/09/16 02:14:04 - mmengine - INFO - Epoch(train) [133][50/586] lr: 5.000000e-04 eta: 5:38:44 time: 0.482564 data_time: 0.040066 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.895360 loss: 0.000509 2022/09/16 02:14:28 - mmengine - INFO - Epoch(train) [133][100/586] lr: 5.000000e-04 eta: 5:38:22 time: 0.472736 data_time: 0.031758 memory: 15239 loss_kpt: 0.000497 acc_pose: 0.832515 loss: 0.000497 2022/09/16 02:14:51 - mmengine - INFO - Epoch(train) [133][150/586] lr: 5.000000e-04 eta: 5:38:01 time: 0.463205 data_time: 0.028590 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.888409 loss: 0.000543 2022/09/16 02:15:14 - mmengine - INFO - Epoch(train) [133][200/586] lr: 5.000000e-04 eta: 5:37:39 time: 0.463545 data_time: 0.031176 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.794679 loss: 0.000519 2022/09/16 02:15:38 - mmengine - INFO - Epoch(train) [133][250/586] lr: 5.000000e-04 eta: 5:37:17 time: 0.469568 data_time: 0.025118 memory: 15239 loss_kpt: 0.000498 acc_pose: 0.895927 loss: 0.000498 2022/09/16 02:16:01 - mmengine - INFO - Epoch(train) [133][300/586] lr: 5.000000e-04 eta: 5:36:56 time: 0.460826 data_time: 0.025142 memory: 15239 loss_kpt: 0.000523 acc_pose: 0.818134 loss: 0.000523 2022/09/16 02:16:24 - mmengine - INFO - Epoch(train) [133][350/586] lr: 5.000000e-04 eta: 5:36:34 time: 0.463402 data_time: 0.028110 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.873585 loss: 0.000508 2022/09/16 02:16:48 - mmengine - INFO - Epoch(train) [133][400/586] lr: 5.000000e-04 eta: 5:36:12 time: 0.467733 data_time: 0.024933 memory: 15239 loss_kpt: 0.000516 acc_pose: 0.867120 loss: 0.000516 2022/09/16 02:17:11 - mmengine - INFO - Epoch(train) [133][450/586] lr: 5.000000e-04 eta: 5:35:50 time: 0.462381 data_time: 0.024526 memory: 15239 loss_kpt: 0.000492 acc_pose: 0.918298 loss: 0.000492 2022/09/16 02:17:34 - mmengine - INFO - Epoch(train) [133][500/586] lr: 5.000000e-04 eta: 5:35:29 time: 0.467077 data_time: 0.028886 memory: 15239 loss_kpt: 0.000522 acc_pose: 0.883502 loss: 0.000522 2022/09/16 02:17:58 - mmengine - INFO - Epoch(train) [133][550/586] lr: 5.000000e-04 eta: 5:35:07 time: 0.469078 data_time: 0.024342 memory: 15239 loss_kpt: 0.000516 acc_pose: 0.912744 loss: 0.000516 2022/09/16 02:18:15 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 02:18:15 - mmengine - INFO - Saving checkpoint at 133 epochs 2022/09/16 02:18:45 - mmengine - INFO - Epoch(train) [134][50/586] lr: 5.000000e-04 eta: 5:34:20 time: 0.471638 data_time: 0.033627 memory: 15239 loss_kpt: 0.000505 acc_pose: 0.846073 loss: 0.000505 2022/09/16 02:18:51 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 02:19:09 - mmengine - INFO - Epoch(train) [134][100/586] lr: 5.000000e-04 eta: 5:33:59 time: 0.470013 data_time: 0.029485 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.877050 loss: 0.000508 2022/09/16 02:19:32 - mmengine - INFO - Epoch(train) [134][150/586] lr: 5.000000e-04 eta: 5:33:37 time: 0.471524 data_time: 0.028521 memory: 15239 loss_kpt: 0.000511 acc_pose: 0.839749 loss: 0.000511 2022/09/16 02:19:56 - mmengine - INFO - Epoch(train) [134][200/586] lr: 5.000000e-04 eta: 5:33:16 time: 0.473021 data_time: 0.035615 memory: 15239 loss_kpt: 0.000503 acc_pose: 0.889009 loss: 0.000503 2022/09/16 02:20:20 - mmengine - INFO - Epoch(train) [134][250/586] lr: 5.000000e-04 eta: 5:32:54 time: 0.469983 data_time: 0.031570 memory: 15239 loss_kpt: 0.000510 acc_pose: 0.824455 loss: 0.000510 2022/09/16 02:20:43 - mmengine - INFO - Epoch(train) [134][300/586] lr: 5.000000e-04 eta: 5:32:33 time: 0.462828 data_time: 0.028118 memory: 15239 loss_kpt: 0.000518 acc_pose: 0.839272 loss: 0.000518 2022/09/16 02:21:06 - mmengine - INFO - Epoch(train) [134][350/586] lr: 5.000000e-04 eta: 5:32:11 time: 0.467787 data_time: 0.030505 memory: 15239 loss_kpt: 0.000522 acc_pose: 0.806825 loss: 0.000522 2022/09/16 02:21:30 - mmengine - INFO - Epoch(train) [134][400/586] lr: 5.000000e-04 eta: 5:31:50 time: 0.470591 data_time: 0.024662 memory: 15239 loss_kpt: 0.000514 acc_pose: 0.876304 loss: 0.000514 2022/09/16 02:21:53 - mmengine - INFO - Epoch(train) [134][450/586] lr: 5.000000e-04 eta: 5:31:28 time: 0.461436 data_time: 0.024315 memory: 15239 loss_kpt: 0.000492 acc_pose: 0.822089 loss: 0.000492 2022/09/16 02:22:16 - mmengine - INFO - Epoch(train) [134][500/586] lr: 5.000000e-04 eta: 5:31:06 time: 0.465671 data_time: 0.028766 memory: 15239 loss_kpt: 0.000504 acc_pose: 0.797406 loss: 0.000504 2022/09/16 02:22:40 - mmengine - INFO - Epoch(train) [134][550/586] lr: 5.000000e-04 eta: 5:30:44 time: 0.468290 data_time: 0.025593 memory: 15239 loss_kpt: 0.000511 acc_pose: 0.858347 loss: 0.000511 2022/09/16 02:22:56 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 02:22:56 - mmengine - INFO - Saving checkpoint at 134 epochs 2022/09/16 02:23:27 - mmengine - INFO - Epoch(train) [135][50/586] lr: 5.000000e-04 eta: 5:29:58 time: 0.473725 data_time: 0.029395 memory: 15239 loss_kpt: 0.000536 acc_pose: 0.779968 loss: 0.000536 2022/09/16 02:23:51 - mmengine - INFO - Epoch(train) [135][100/586] lr: 5.000000e-04 eta: 5:29:36 time: 0.474170 data_time: 0.024287 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.811368 loss: 0.000508 2022/09/16 02:24:15 - mmengine - INFO - Epoch(train) [135][150/586] lr: 5.000000e-04 eta: 5:29:15 time: 0.466152 data_time: 0.024025 memory: 15239 loss_kpt: 0.000500 acc_pose: 0.839831 loss: 0.000500 2022/09/16 02:24:38 - mmengine - INFO - Epoch(train) [135][200/586] lr: 5.000000e-04 eta: 5:28:53 time: 0.476153 data_time: 0.025906 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.883844 loss: 0.000508 2022/09/16 02:25:02 - mmengine - INFO - Epoch(train) [135][250/586] lr: 5.000000e-04 eta: 5:28:32 time: 0.472580 data_time: 0.024412 memory: 15239 loss_kpt: 0.000515 acc_pose: 0.877520 loss: 0.000515 2022/09/16 02:25:26 - mmengine - INFO - Epoch(train) [135][300/586] lr: 5.000000e-04 eta: 5:28:10 time: 0.470838 data_time: 0.025197 memory: 15239 loss_kpt: 0.000478 acc_pose: 0.904575 loss: 0.000478 2022/09/16 02:25:50 - mmengine - INFO - Epoch(train) [135][350/586] lr: 5.000000e-04 eta: 5:27:49 time: 0.484744 data_time: 0.024581 memory: 15239 loss_kpt: 0.000527 acc_pose: 0.826435 loss: 0.000527 2022/09/16 02:26:14 - mmengine - INFO - Epoch(train) [135][400/586] lr: 5.000000e-04 eta: 5:27:28 time: 0.475030 data_time: 0.024709 memory: 15239 loss_kpt: 0.000512 acc_pose: 0.794752 loss: 0.000512 2022/09/16 02:26:37 - mmengine - INFO - Epoch(train) [135][450/586] lr: 5.000000e-04 eta: 5:27:06 time: 0.464616 data_time: 0.029293 memory: 15239 loss_kpt: 0.000499 acc_pose: 0.887116 loss: 0.000499 2022/09/16 02:26:49 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 02:27:00 - mmengine - INFO - Epoch(train) [135][500/586] lr: 5.000000e-04 eta: 5:26:45 time: 0.472647 data_time: 0.025537 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.843345 loss: 0.000509 2022/09/16 02:27:23 - mmengine - INFO - Epoch(train) [135][550/586] lr: 5.000000e-04 eta: 5:26:23 time: 0.457010 data_time: 0.024405 memory: 15239 loss_kpt: 0.000523 acc_pose: 0.908837 loss: 0.000523 2022/09/16 02:27:40 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 02:27:40 - mmengine - INFO - Saving checkpoint at 135 epochs 2022/09/16 02:28:12 - mmengine - INFO - Epoch(train) [136][50/586] lr: 5.000000e-04 eta: 5:25:37 time: 0.482844 data_time: 0.028788 memory: 15239 loss_kpt: 0.000503 acc_pose: 0.899519 loss: 0.000503 2022/09/16 02:28:35 - mmengine - INFO - Epoch(train) [136][100/586] lr: 5.000000e-04 eta: 5:25:15 time: 0.473574 data_time: 0.028147 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.832698 loss: 0.000519 2022/09/16 02:28:59 - mmengine - INFO - Epoch(train) [136][150/586] lr: 5.000000e-04 eta: 5:24:54 time: 0.472225 data_time: 0.025473 memory: 15239 loss_kpt: 0.000507 acc_pose: 0.880360 loss: 0.000507 2022/09/16 02:29:22 - mmengine - INFO - Epoch(train) [136][200/586] lr: 5.000000e-04 eta: 5:24:32 time: 0.470821 data_time: 0.024769 memory: 15239 loss_kpt: 0.000528 acc_pose: 0.788335 loss: 0.000528 2022/09/16 02:29:46 - mmengine - INFO - Epoch(train) [136][250/586] lr: 5.000000e-04 eta: 5:24:10 time: 0.466957 data_time: 0.027451 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.835682 loss: 0.000508 2022/09/16 02:30:10 - mmengine - INFO - Epoch(train) [136][300/586] lr: 5.000000e-04 eta: 5:23:49 time: 0.473804 data_time: 0.025353 memory: 15239 loss_kpt: 0.000502 acc_pose: 0.888482 loss: 0.000502 2022/09/16 02:30:33 - mmengine - INFO - Epoch(train) [136][350/586] lr: 5.000000e-04 eta: 5:23:27 time: 0.466311 data_time: 0.025112 memory: 15239 loss_kpt: 0.000504 acc_pose: 0.810674 loss: 0.000504 2022/09/16 02:30:56 - mmengine - INFO - Epoch(train) [136][400/586] lr: 5.000000e-04 eta: 5:23:06 time: 0.470524 data_time: 0.030436 memory: 15239 loss_kpt: 0.000505 acc_pose: 0.874484 loss: 0.000505 2022/09/16 02:31:19 - mmengine - INFO - Epoch(train) [136][450/586] lr: 5.000000e-04 eta: 5:22:44 time: 0.461970 data_time: 0.024496 memory: 15239 loss_kpt: 0.000514 acc_pose: 0.852468 loss: 0.000514 2022/09/16 02:31:43 - mmengine - INFO - Epoch(train) [136][500/586] lr: 5.000000e-04 eta: 5:22:22 time: 0.471920 data_time: 0.024607 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.905681 loss: 0.000509 2022/09/16 02:32:06 - mmengine - INFO - Epoch(train) [136][550/586] lr: 5.000000e-04 eta: 5:22:01 time: 0.467015 data_time: 0.024198 memory: 15239 loss_kpt: 0.000514 acc_pose: 0.864604 loss: 0.000514 2022/09/16 02:32:23 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 02:32:23 - mmengine - INFO - Saving checkpoint at 136 epochs 2022/09/16 02:32:55 - mmengine - INFO - Epoch(train) [137][50/586] lr: 5.000000e-04 eta: 5:21:15 time: 0.487082 data_time: 0.033352 memory: 15239 loss_kpt: 0.000516 acc_pose: 0.892724 loss: 0.000516 2022/09/16 02:33:18 - mmengine - INFO - Epoch(train) [137][100/586] lr: 5.000000e-04 eta: 5:20:53 time: 0.466699 data_time: 0.023730 memory: 15239 loss_kpt: 0.000517 acc_pose: 0.891242 loss: 0.000517 2022/09/16 02:33:41 - mmengine - INFO - Epoch(train) [137][150/586] lr: 5.000000e-04 eta: 5:20:31 time: 0.464470 data_time: 0.023943 memory: 15239 loss_kpt: 0.000535 acc_pose: 0.867828 loss: 0.000535 2022/09/16 02:34:05 - mmengine - INFO - Epoch(train) [137][200/586] lr: 5.000000e-04 eta: 5:20:10 time: 0.472390 data_time: 0.028941 memory: 15239 loss_kpt: 0.000503 acc_pose: 0.885110 loss: 0.000503 2022/09/16 02:34:28 - mmengine - INFO - Epoch(train) [137][250/586] lr: 5.000000e-04 eta: 5:19:48 time: 0.463703 data_time: 0.025666 memory: 15239 loss_kpt: 0.000516 acc_pose: 0.842743 loss: 0.000516 2022/09/16 02:34:51 - mmengine - INFO - Epoch(train) [137][300/586] lr: 5.000000e-04 eta: 5:19:26 time: 0.458650 data_time: 0.024485 memory: 15239 loss_kpt: 0.000501 acc_pose: 0.904839 loss: 0.000501 2022/09/16 02:34:53 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 02:35:15 - mmengine - INFO - Epoch(train) [137][350/586] lr: 5.000000e-04 eta: 5:19:05 time: 0.473322 data_time: 0.025061 memory: 15239 loss_kpt: 0.000499 acc_pose: 0.876740 loss: 0.000499 2022/09/16 02:35:38 - mmengine - INFO - Epoch(train) [137][400/586] lr: 5.000000e-04 eta: 5:18:43 time: 0.465443 data_time: 0.024908 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.866723 loss: 0.000509 2022/09/16 02:36:01 - mmengine - INFO - Epoch(train) [137][450/586] lr: 5.000000e-04 eta: 5:18:21 time: 0.459250 data_time: 0.024544 memory: 15239 loss_kpt: 0.000520 acc_pose: 0.824453 loss: 0.000520 2022/09/16 02:36:25 - mmengine - INFO - Epoch(train) [137][500/586] lr: 5.000000e-04 eta: 5:18:00 time: 0.473415 data_time: 0.028462 memory: 15239 loss_kpt: 0.000497 acc_pose: 0.851383 loss: 0.000497 2022/09/16 02:36:48 - mmengine - INFO - Epoch(train) [137][550/586] lr: 5.000000e-04 eta: 5:17:38 time: 0.458566 data_time: 0.024441 memory: 15239 loss_kpt: 0.000507 acc_pose: 0.838377 loss: 0.000507 2022/09/16 02:37:04 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 02:37:04 - mmengine - INFO - Saving checkpoint at 137 epochs 2022/09/16 02:37:35 - mmengine - INFO - Epoch(train) [138][50/586] lr: 5.000000e-04 eta: 5:16:52 time: 0.473738 data_time: 0.030253 memory: 15239 loss_kpt: 0.000518 acc_pose: 0.865167 loss: 0.000518 2022/09/16 02:37:59 - mmengine - INFO - Epoch(train) [138][100/586] lr: 5.000000e-04 eta: 5:16:30 time: 0.465926 data_time: 0.029053 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.827178 loss: 0.000508 2022/09/16 02:38:22 - mmengine - INFO - Epoch(train) [138][150/586] lr: 5.000000e-04 eta: 5:16:09 time: 0.476753 data_time: 0.025449 memory: 15239 loss_kpt: 0.000506 acc_pose: 0.868974 loss: 0.000506 2022/09/16 02:38:46 - mmengine - INFO - Epoch(train) [138][200/586] lr: 5.000000e-04 eta: 5:15:47 time: 0.470890 data_time: 0.024102 memory: 15239 loss_kpt: 0.000521 acc_pose: 0.828512 loss: 0.000521 2022/09/16 02:39:10 - mmengine - INFO - Epoch(train) [138][250/586] lr: 5.000000e-04 eta: 5:15:26 time: 0.473117 data_time: 0.024371 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.841098 loss: 0.000519 2022/09/16 02:39:33 - mmengine - INFO - Epoch(train) [138][300/586] lr: 5.000000e-04 eta: 5:15:04 time: 0.462089 data_time: 0.024360 memory: 15239 loss_kpt: 0.000503 acc_pose: 0.853439 loss: 0.000503 2022/09/16 02:39:57 - mmengine - INFO - Epoch(train) [138][350/586] lr: 5.000000e-04 eta: 5:14:42 time: 0.476433 data_time: 0.024590 memory: 15239 loss_kpt: 0.000521 acc_pose: 0.863944 loss: 0.000521 2022/09/16 02:40:20 - mmengine - INFO - Epoch(train) [138][400/586] lr: 5.000000e-04 eta: 5:14:21 time: 0.463348 data_time: 0.024363 memory: 15239 loss_kpt: 0.000524 acc_pose: 0.872556 loss: 0.000524 2022/09/16 02:40:43 - mmengine - INFO - Epoch(train) [138][450/586] lr: 5.000000e-04 eta: 5:13:59 time: 0.464382 data_time: 0.025928 memory: 15239 loss_kpt: 0.000492 acc_pose: 0.896495 loss: 0.000492 2022/09/16 02:41:07 - mmengine - INFO - Epoch(train) [138][500/586] lr: 5.000000e-04 eta: 5:13:37 time: 0.469471 data_time: 0.024370 memory: 15239 loss_kpt: 0.000502 acc_pose: 0.890778 loss: 0.000502 2022/09/16 02:41:30 - mmengine - INFO - Epoch(train) [138][550/586] lr: 5.000000e-04 eta: 5:13:16 time: 0.464677 data_time: 0.028495 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.901523 loss: 0.000519 2022/09/16 02:41:46 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 02:41:46 - mmengine - INFO - Saving checkpoint at 138 epochs 2022/09/16 02:42:17 - mmengine - INFO - Epoch(train) [139][50/586] lr: 5.000000e-04 eta: 5:12:30 time: 0.485502 data_time: 0.029163 memory: 15239 loss_kpt: 0.000514 acc_pose: 0.944142 loss: 0.000514 2022/09/16 02:42:41 - mmengine - INFO - Epoch(train) [139][100/586] lr: 5.000000e-04 eta: 5:12:08 time: 0.464895 data_time: 0.026117 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.867923 loss: 0.000508 2022/09/16 02:42:56 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 02:43:04 - mmengine - INFO - Epoch(train) [139][150/586] lr: 5.000000e-04 eta: 5:11:47 time: 0.471988 data_time: 0.028802 memory: 15239 loss_kpt: 0.000512 acc_pose: 0.831795 loss: 0.000512 2022/09/16 02:43:28 - mmengine - INFO - Epoch(train) [139][200/586] lr: 5.000000e-04 eta: 5:11:25 time: 0.464939 data_time: 0.024967 memory: 15239 loss_kpt: 0.000501 acc_pose: 0.863928 loss: 0.000501 2022/09/16 02:43:51 - mmengine - INFO - Epoch(train) [139][250/586] lr: 5.000000e-04 eta: 5:11:03 time: 0.463583 data_time: 0.025017 memory: 15239 loss_kpt: 0.000512 acc_pose: 0.819010 loss: 0.000512 2022/09/16 02:44:14 - mmengine - INFO - Epoch(train) [139][300/586] lr: 5.000000e-04 eta: 5:10:41 time: 0.464069 data_time: 0.024998 memory: 15239 loss_kpt: 0.000505 acc_pose: 0.837090 loss: 0.000505 2022/09/16 02:44:37 - mmengine - INFO - Epoch(train) [139][350/586] lr: 5.000000e-04 eta: 5:10:20 time: 0.470596 data_time: 0.024206 memory: 15239 loss_kpt: 0.000503 acc_pose: 0.862759 loss: 0.000503 2022/09/16 02:45:01 - mmengine - INFO - Epoch(train) [139][400/586] lr: 5.000000e-04 eta: 5:09:58 time: 0.462780 data_time: 0.024661 memory: 15239 loss_kpt: 0.000501 acc_pose: 0.831595 loss: 0.000501 2022/09/16 02:45:24 - mmengine - INFO - Epoch(train) [139][450/586] lr: 5.000000e-04 eta: 5:09:36 time: 0.466117 data_time: 0.029457 memory: 15239 loss_kpt: 0.000512 acc_pose: 0.876083 loss: 0.000512 2022/09/16 02:45:47 - mmengine - INFO - Epoch(train) [139][500/586] lr: 5.000000e-04 eta: 5:09:15 time: 0.466387 data_time: 0.024472 memory: 15239 loss_kpt: 0.000518 acc_pose: 0.814561 loss: 0.000518 2022/09/16 02:46:10 - mmengine - INFO - Epoch(train) [139][550/586] lr: 5.000000e-04 eta: 5:08:53 time: 0.463297 data_time: 0.024245 memory: 15239 loss_kpt: 0.000517 acc_pose: 0.799785 loss: 0.000517 2022/09/16 02:46:27 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 02:46:27 - mmengine - INFO - Saving checkpoint at 139 epochs 2022/09/16 02:46:59 - mmengine - INFO - Epoch(train) [140][50/586] lr: 5.000000e-04 eta: 5:08:07 time: 0.480716 data_time: 0.031724 memory: 15239 loss_kpt: 0.000502 acc_pose: 0.891178 loss: 0.000502 2022/09/16 02:47:23 - mmengine - INFO - Epoch(train) [140][100/586] lr: 5.000000e-04 eta: 5:07:46 time: 0.477879 data_time: 0.028763 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.855053 loss: 0.000519 2022/09/16 02:47:46 - mmengine - INFO - Epoch(train) [140][150/586] lr: 5.000000e-04 eta: 5:07:24 time: 0.464907 data_time: 0.024806 memory: 15239 loss_kpt: 0.000497 acc_pose: 0.879528 loss: 0.000497 2022/09/16 02:48:09 - mmengine - INFO - Epoch(train) [140][200/586] lr: 5.000000e-04 eta: 5:07:02 time: 0.458509 data_time: 0.024804 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.860883 loss: 0.000508 2022/09/16 02:48:33 - mmengine - INFO - Epoch(train) [140][250/586] lr: 5.000000e-04 eta: 5:06:41 time: 0.472171 data_time: 0.025443 memory: 15239 loss_kpt: 0.000514 acc_pose: 0.830914 loss: 0.000514 2022/09/16 02:48:56 - mmengine - INFO - Epoch(train) [140][300/586] lr: 5.000000e-04 eta: 5:06:19 time: 0.465902 data_time: 0.024562 memory: 15239 loss_kpt: 0.000511 acc_pose: 0.825025 loss: 0.000511 2022/09/16 02:49:19 - mmengine - INFO - Epoch(train) [140][350/586] lr: 5.000000e-04 eta: 5:05:57 time: 0.459873 data_time: 0.024302 memory: 15239 loss_kpt: 0.000521 acc_pose: 0.872834 loss: 0.000521 2022/09/16 02:49:42 - mmengine - INFO - Epoch(train) [140][400/586] lr: 5.000000e-04 eta: 5:05:35 time: 0.465648 data_time: 0.024925 memory: 15239 loss_kpt: 0.000496 acc_pose: 0.836592 loss: 0.000496 2022/09/16 02:50:06 - mmengine - INFO - Epoch(train) [140][450/586] lr: 5.000000e-04 eta: 5:05:14 time: 0.467116 data_time: 0.025420 memory: 15239 loss_kpt: 0.000516 acc_pose: 0.892443 loss: 0.000516 2022/09/16 02:50:29 - mmengine - INFO - Epoch(train) [140][500/586] lr: 5.000000e-04 eta: 5:04:52 time: 0.456171 data_time: 0.025078 memory: 15239 loss_kpt: 0.000499 acc_pose: 0.860229 loss: 0.000499 2022/09/16 02:50:50 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 02:50:52 - mmengine - INFO - Epoch(train) [140][550/586] lr: 5.000000e-04 eta: 5:04:30 time: 0.469781 data_time: 0.027374 memory: 15239 loss_kpt: 0.000491 acc_pose: 0.845336 loss: 0.000491 2022/09/16 02:51:09 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 02:51:09 - mmengine - INFO - Saving checkpoint at 140 epochs 2022/09/16 02:51:29 - mmengine - INFO - Epoch(val) [140][50/407] eta: 0:01:31 time: 0.255261 data_time: 0.013109 memory: 15239 2022/09/16 02:51:41 - mmengine - INFO - Epoch(val) [140][100/407] eta: 0:01:18 time: 0.256718 data_time: 0.012882 memory: 2064 2022/09/16 02:51:54 - mmengine - INFO - Epoch(val) [140][150/407] eta: 0:01:04 time: 0.250336 data_time: 0.008468 memory: 2064 2022/09/16 02:52:07 - mmengine - INFO - Epoch(val) [140][200/407] eta: 0:00:51 time: 0.249801 data_time: 0.008414 memory: 2064 2022/09/16 02:52:19 - mmengine - INFO - Epoch(val) [140][250/407] eta: 0:00:39 time: 0.250834 data_time: 0.009125 memory: 2064 2022/09/16 02:52:32 - mmengine - INFO - Epoch(val) [140][300/407] eta: 0:00:26 time: 0.251022 data_time: 0.008485 memory: 2064 2022/09/16 02:52:44 - mmengine - INFO - Epoch(val) [140][350/407] eta: 0:00:14 time: 0.251592 data_time: 0.008624 memory: 2064 2022/09/16 02:52:57 - mmengine - INFO - Epoch(val) [140][400/407] eta: 0:00:01 time: 0.247892 data_time: 0.008248 memory: 2064 2022/09/16 02:53:32 - mmengine - INFO - Evaluating CocoMetric... 2022/09/16 02:53:45 - mmengine - INFO - Epoch(val) [140][407/407] coco/AP: 0.763237 coco/AP .5: 0.905896 coco/AP .75: 0.828861 coco/AP (M): 0.723612 coco/AP (L): 0.833328 coco/AR: 0.812043 coco/AR .5: 0.941121 coco/AR .75: 0.871222 coco/AR (M): 0.768287 coco/AR (L): 0.875399 2022/09/16 02:53:45 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220915/dark_w48_384/best_coco/AP_epoch_130.pth is removed 2022/09/16 02:53:49 - mmengine - INFO - The best checkpoint with 0.7632 coco/AP at 140 epoch is saved to best_coco/AP_epoch_140.pth. 2022/09/16 02:54:13 - mmengine - INFO - Epoch(train) [141][50/586] lr: 5.000000e-04 eta: 5:03:44 time: 0.470584 data_time: 0.027634 memory: 15239 loss_kpt: 0.000510 acc_pose: 0.838036 loss: 0.000510 2022/09/16 02:54:36 - mmengine - INFO - Epoch(train) [141][100/586] lr: 5.000000e-04 eta: 5:03:23 time: 0.471325 data_time: 0.024828 memory: 15239 loss_kpt: 0.000506 acc_pose: 0.901639 loss: 0.000506 2022/09/16 02:55:00 - mmengine - INFO - Epoch(train) [141][150/586] lr: 5.000000e-04 eta: 5:03:01 time: 0.466265 data_time: 0.025087 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.805671 loss: 0.000519 2022/09/16 02:55:23 - mmengine - INFO - Epoch(train) [141][200/586] lr: 5.000000e-04 eta: 5:02:39 time: 0.464518 data_time: 0.024189 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.824938 loss: 0.000509 2022/09/16 02:55:46 - mmengine - INFO - Epoch(train) [141][250/586] lr: 5.000000e-04 eta: 5:02:18 time: 0.469560 data_time: 0.024688 memory: 15239 loss_kpt: 0.000510 acc_pose: 0.826360 loss: 0.000510 2022/09/16 02:56:10 - mmengine - INFO - Epoch(train) [141][300/586] lr: 5.000000e-04 eta: 5:01:56 time: 0.464510 data_time: 0.024568 memory: 15239 loss_kpt: 0.000498 acc_pose: 0.877088 loss: 0.000498 2022/09/16 02:56:33 - mmengine - INFO - Epoch(train) [141][350/586] lr: 5.000000e-04 eta: 5:01:34 time: 0.466925 data_time: 0.023998 memory: 15239 loss_kpt: 0.000510 acc_pose: 0.914050 loss: 0.000510 2022/09/16 02:56:56 - mmengine - INFO - Epoch(train) [141][400/586] lr: 5.000000e-04 eta: 5:01:13 time: 0.465157 data_time: 0.024320 memory: 15239 loss_kpt: 0.000502 acc_pose: 0.879772 loss: 0.000502 2022/09/16 02:57:19 - mmengine - INFO - Epoch(train) [141][450/586] lr: 5.000000e-04 eta: 5:00:51 time: 0.458983 data_time: 0.025261 memory: 15239 loss_kpt: 0.000521 acc_pose: 0.814860 loss: 0.000521 2022/09/16 02:57:43 - mmengine - INFO - Epoch(train) [141][500/586] lr: 5.000000e-04 eta: 5:00:29 time: 0.469365 data_time: 0.030095 memory: 15239 loss_kpt: 0.000495 acc_pose: 0.867855 loss: 0.000495 2022/09/16 02:58:06 - mmengine - INFO - Epoch(train) [141][550/586] lr: 5.000000e-04 eta: 5:00:07 time: 0.466957 data_time: 0.024105 memory: 15239 loss_kpt: 0.000503 acc_pose: 0.823884 loss: 0.000503 2022/09/16 02:58:23 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 02:58:23 - mmengine - INFO - Saving checkpoint at 141 epochs 2022/09/16 02:58:54 - mmengine - INFO - Epoch(train) [142][50/586] lr: 5.000000e-04 eta: 4:59:22 time: 0.480169 data_time: 0.028846 memory: 15239 loss_kpt: 0.000495 acc_pose: 0.924389 loss: 0.000495 2022/09/16 02:59:18 - mmengine - INFO - Epoch(train) [142][100/586] lr: 5.000000e-04 eta: 4:59:01 time: 0.477672 data_time: 0.024251 memory: 15239 loss_kpt: 0.000501 acc_pose: 0.805328 loss: 0.000501 2022/09/16 02:59:41 - mmengine - INFO - Epoch(train) [142][150/586] lr: 5.000000e-04 eta: 4:58:39 time: 0.472462 data_time: 0.024762 memory: 15239 loss_kpt: 0.000520 acc_pose: 0.815279 loss: 0.000520 2022/09/16 03:00:05 - mmengine - INFO - Epoch(train) [142][200/586] lr: 5.000000e-04 eta: 4:58:17 time: 0.467124 data_time: 0.024158 memory: 15239 loss_kpt: 0.000484 acc_pose: 0.891977 loss: 0.000484 2022/09/16 03:00:29 - mmengine - INFO - Epoch(train) [142][250/586] lr: 5.000000e-04 eta: 4:57:56 time: 0.481956 data_time: 0.023903 memory: 15239 loss_kpt: 0.000504 acc_pose: 0.869522 loss: 0.000504 2022/09/16 03:00:52 - mmengine - INFO - Epoch(train) [142][300/586] lr: 5.000000e-04 eta: 4:57:34 time: 0.470030 data_time: 0.024629 memory: 15239 loss_kpt: 0.000510 acc_pose: 0.870638 loss: 0.000510 2022/09/16 03:01:16 - mmengine - INFO - Epoch(train) [142][350/586] lr: 5.000000e-04 eta: 4:57:13 time: 0.471131 data_time: 0.024537 memory: 15239 loss_kpt: 0.000499 acc_pose: 0.862579 loss: 0.000499 2022/09/16 03:01:28 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 03:01:40 - mmengine - INFO - Epoch(train) [142][400/586] lr: 5.000000e-04 eta: 4:56:51 time: 0.481567 data_time: 0.026034 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.903079 loss: 0.000508 2022/09/16 03:02:03 - mmengine - INFO - Epoch(train) [142][450/586] lr: 5.000000e-04 eta: 4:56:30 time: 0.466383 data_time: 0.024318 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.872337 loss: 0.000509 2022/09/16 03:02:27 - mmengine - INFO - Epoch(train) [142][500/586] lr: 5.000000e-04 eta: 4:56:08 time: 0.471867 data_time: 0.024656 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.878844 loss: 0.000508 2022/09/16 03:02:50 - mmengine - INFO - Epoch(train) [142][550/586] lr: 5.000000e-04 eta: 4:55:46 time: 0.468285 data_time: 0.024745 memory: 15239 loss_kpt: 0.000510 acc_pose: 0.900444 loss: 0.000510 2022/09/16 03:03:07 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 03:03:07 - mmengine - INFO - Saving checkpoint at 142 epochs 2022/09/16 03:03:38 - mmengine - INFO - Epoch(train) [143][50/586] lr: 5.000000e-04 eta: 4:55:01 time: 0.480220 data_time: 0.028188 memory: 15239 loss_kpt: 0.000500 acc_pose: 0.854968 loss: 0.000500 2022/09/16 03:04:01 - mmengine - INFO - Epoch(train) [143][100/586] lr: 5.000000e-04 eta: 4:54:40 time: 0.464717 data_time: 0.024120 memory: 15239 loss_kpt: 0.000504 acc_pose: 0.868570 loss: 0.000504 2022/09/16 03:04:24 - mmengine - INFO - Epoch(train) [143][150/586] lr: 5.000000e-04 eta: 4:54:18 time: 0.462955 data_time: 0.025403 memory: 15239 loss_kpt: 0.000490 acc_pose: 0.827741 loss: 0.000490 2022/09/16 03:04:48 - mmengine - INFO - Epoch(train) [143][200/586] lr: 5.000000e-04 eta: 4:53:56 time: 0.468967 data_time: 0.024883 memory: 15239 loss_kpt: 0.000516 acc_pose: 0.835482 loss: 0.000516 2022/09/16 03:05:11 - mmengine - INFO - Epoch(train) [143][250/586] lr: 5.000000e-04 eta: 4:53:34 time: 0.469251 data_time: 0.025361 memory: 15239 loss_kpt: 0.000507 acc_pose: 0.841426 loss: 0.000507 2022/09/16 03:05:35 - mmengine - INFO - Epoch(train) [143][300/586] lr: 5.000000e-04 eta: 4:53:13 time: 0.463584 data_time: 0.025168 memory: 15239 loss_kpt: 0.000504 acc_pose: 0.879129 loss: 0.000504 2022/09/16 03:05:58 - mmengine - INFO - Epoch(train) [143][350/586] lr: 5.000000e-04 eta: 4:52:51 time: 0.467135 data_time: 0.028957 memory: 15239 loss_kpt: 0.000502 acc_pose: 0.858257 loss: 0.000502 2022/09/16 03:06:21 - mmengine - INFO - Epoch(train) [143][400/586] lr: 5.000000e-04 eta: 4:52:29 time: 0.465419 data_time: 0.024614 memory: 15239 loss_kpt: 0.000511 acc_pose: 0.862503 loss: 0.000511 2022/09/16 03:06:44 - mmengine - INFO - Epoch(train) [143][450/586] lr: 5.000000e-04 eta: 4:52:07 time: 0.460112 data_time: 0.024625 memory: 15239 loss_kpt: 0.000514 acc_pose: 0.857472 loss: 0.000514 2022/09/16 03:07:07 - mmengine - INFO - Epoch(train) [143][500/586] lr: 5.000000e-04 eta: 4:51:45 time: 0.465140 data_time: 0.024435 memory: 15239 loss_kpt: 0.000514 acc_pose: 0.862894 loss: 0.000514 2022/09/16 03:07:31 - mmengine - INFO - Epoch(train) [143][550/586] lr: 5.000000e-04 eta: 4:51:24 time: 0.467654 data_time: 0.024594 memory: 15239 loss_kpt: 0.000513 acc_pose: 0.906652 loss: 0.000513 2022/09/16 03:07:47 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 03:07:47 - mmengine - INFO - Saving checkpoint at 143 epochs 2022/09/16 03:08:18 - mmengine - INFO - Epoch(train) [144][50/586] lr: 5.000000e-04 eta: 4:50:39 time: 0.469871 data_time: 0.032445 memory: 15239 loss_kpt: 0.000504 acc_pose: 0.755243 loss: 0.000504 2022/09/16 03:08:42 - mmengine - INFO - Epoch(train) [144][100/586] lr: 5.000000e-04 eta: 4:50:17 time: 0.480052 data_time: 0.032030 memory: 15239 loss_kpt: 0.000503 acc_pose: 0.927936 loss: 0.000503 2022/09/16 03:09:05 - mmengine - INFO - Epoch(train) [144][150/586] lr: 5.000000e-04 eta: 4:49:55 time: 0.461738 data_time: 0.027834 memory: 15239 loss_kpt: 0.000516 acc_pose: 0.869090 loss: 0.000516 2022/09/16 03:09:28 - mmengine - INFO - Epoch(train) [144][200/586] lr: 5.000000e-04 eta: 4:49:34 time: 0.467359 data_time: 0.036132 memory: 15239 loss_kpt: 0.000518 acc_pose: 0.771665 loss: 0.000518 2022/09/16 03:09:29 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 03:09:52 - mmengine - INFO - Epoch(train) [144][250/586] lr: 5.000000e-04 eta: 4:49:12 time: 0.469955 data_time: 0.027848 memory: 15239 loss_kpt: 0.000511 acc_pose: 0.835849 loss: 0.000511 2022/09/16 03:10:15 - mmengine - INFO - Epoch(train) [144][300/586] lr: 5.000000e-04 eta: 4:48:50 time: 0.471772 data_time: 0.030705 memory: 15239 loss_kpt: 0.000497 acc_pose: 0.887677 loss: 0.000497 2022/09/16 03:10:39 - mmengine - INFO - Epoch(train) [144][350/586] lr: 5.000000e-04 eta: 4:48:29 time: 0.471486 data_time: 0.028345 memory: 15239 loss_kpt: 0.000505 acc_pose: 0.890365 loss: 0.000505 2022/09/16 03:11:03 - mmengine - INFO - Epoch(train) [144][400/586] lr: 5.000000e-04 eta: 4:48:07 time: 0.474735 data_time: 0.027902 memory: 15239 loss_kpt: 0.000533 acc_pose: 0.850635 loss: 0.000533 2022/09/16 03:11:26 - mmengine - INFO - Epoch(train) [144][450/586] lr: 5.000000e-04 eta: 4:47:45 time: 0.464678 data_time: 0.027789 memory: 15239 loss_kpt: 0.000515 acc_pose: 0.869831 loss: 0.000515 2022/09/16 03:11:49 - mmengine - INFO - Epoch(train) [144][500/586] lr: 5.000000e-04 eta: 4:47:23 time: 0.456921 data_time: 0.024473 memory: 15239 loss_kpt: 0.000502 acc_pose: 0.863090 loss: 0.000502 2022/09/16 03:12:13 - mmengine - INFO - Epoch(train) [144][550/586] lr: 5.000000e-04 eta: 4:47:02 time: 0.472121 data_time: 0.024099 memory: 15239 loss_kpt: 0.000507 acc_pose: 0.914774 loss: 0.000507 2022/09/16 03:12:29 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 03:12:29 - mmengine - INFO - Saving checkpoint at 144 epochs 2022/09/16 03:13:00 - mmengine - INFO - Epoch(train) [145][50/586] lr: 5.000000e-04 eta: 4:46:17 time: 0.475576 data_time: 0.040495 memory: 15239 loss_kpt: 0.000499 acc_pose: 0.891006 loss: 0.000499 2022/09/16 03:13:24 - mmengine - INFO - Epoch(train) [145][100/586] lr: 5.000000e-04 eta: 4:45:55 time: 0.478185 data_time: 0.024688 memory: 15239 loss_kpt: 0.000505 acc_pose: 0.843320 loss: 0.000505 2022/09/16 03:13:47 - mmengine - INFO - Epoch(train) [145][150/586] lr: 5.000000e-04 eta: 4:45:34 time: 0.461515 data_time: 0.026074 memory: 15239 loss_kpt: 0.000502 acc_pose: 0.832715 loss: 0.000502 2022/09/16 03:14:10 - mmengine - INFO - Epoch(train) [145][200/586] lr: 5.000000e-04 eta: 4:45:12 time: 0.470386 data_time: 0.027207 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.767992 loss: 0.000508 2022/09/16 03:14:34 - mmengine - INFO - Epoch(train) [145][250/586] lr: 5.000000e-04 eta: 4:44:50 time: 0.471984 data_time: 0.024613 memory: 15239 loss_kpt: 0.000498 acc_pose: 0.825148 loss: 0.000498 2022/09/16 03:14:57 - mmengine - INFO - Epoch(train) [145][300/586] lr: 5.000000e-04 eta: 4:44:28 time: 0.458739 data_time: 0.024322 memory: 15239 loss_kpt: 0.000493 acc_pose: 0.926555 loss: 0.000493 2022/09/16 03:15:20 - mmengine - INFO - Epoch(train) [145][350/586] lr: 5.000000e-04 eta: 4:44:07 time: 0.464648 data_time: 0.024035 memory: 15239 loss_kpt: 0.000503 acc_pose: 0.915826 loss: 0.000503 2022/09/16 03:15:44 - mmengine - INFO - Epoch(train) [145][400/586] lr: 5.000000e-04 eta: 4:43:45 time: 0.471404 data_time: 0.029091 memory: 15239 loss_kpt: 0.000523 acc_pose: 0.886897 loss: 0.000523 2022/09/16 03:16:07 - mmengine - INFO - Epoch(train) [145][450/586] lr: 5.000000e-04 eta: 4:43:23 time: 0.459321 data_time: 0.025272 memory: 15239 loss_kpt: 0.000514 acc_pose: 0.868108 loss: 0.000514 2022/09/16 03:16:30 - mmengine - INFO - Epoch(train) [145][500/586] lr: 5.000000e-04 eta: 4:43:01 time: 0.463836 data_time: 0.025482 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.911416 loss: 0.000508 2022/09/16 03:16:54 - mmengine - INFO - Epoch(train) [145][550/586] lr: 5.000000e-04 eta: 4:42:40 time: 0.472724 data_time: 0.030055 memory: 15239 loss_kpt: 0.000506 acc_pose: 0.862532 loss: 0.000506 2022/09/16 03:17:11 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 03:17:11 - mmengine - INFO - Saving checkpoint at 145 epochs 2022/09/16 03:17:32 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 03:17:41 - mmengine - INFO - Epoch(train) [146][50/586] lr: 5.000000e-04 eta: 4:41:55 time: 0.469066 data_time: 0.036209 memory: 15239 loss_kpt: 0.000495 acc_pose: 0.880431 loss: 0.000495 2022/09/16 03:18:05 - mmengine - INFO - Epoch(train) [146][100/586] lr: 5.000000e-04 eta: 4:41:33 time: 0.472845 data_time: 0.027976 memory: 15239 loss_kpt: 0.000489 acc_pose: 0.847514 loss: 0.000489 2022/09/16 03:18:28 - mmengine - INFO - Epoch(train) [146][150/586] lr: 5.000000e-04 eta: 4:41:11 time: 0.464595 data_time: 0.029559 memory: 15239 loss_kpt: 0.000500 acc_pose: 0.902297 loss: 0.000500 2022/09/16 03:18:52 - mmengine - INFO - Epoch(train) [146][200/586] lr: 5.000000e-04 eta: 4:40:50 time: 0.473809 data_time: 0.024426 memory: 15239 loss_kpt: 0.000501 acc_pose: 0.876127 loss: 0.000501 2022/09/16 03:19:15 - mmengine - INFO - Epoch(train) [146][250/586] lr: 5.000000e-04 eta: 4:40:28 time: 0.462291 data_time: 0.023954 memory: 15239 loss_kpt: 0.000514 acc_pose: 0.880244 loss: 0.000514 2022/09/16 03:19:39 - mmengine - INFO - Epoch(train) [146][300/586] lr: 5.000000e-04 eta: 4:40:06 time: 0.472125 data_time: 0.028930 memory: 15239 loss_kpt: 0.000488 acc_pose: 0.867224 loss: 0.000488 2022/09/16 03:20:02 - mmengine - INFO - Epoch(train) [146][350/586] lr: 5.000000e-04 eta: 4:39:44 time: 0.463838 data_time: 0.024598 memory: 15239 loss_kpt: 0.000503 acc_pose: 0.863543 loss: 0.000503 2022/09/16 03:20:25 - mmengine - INFO - Epoch(train) [146][400/586] lr: 5.000000e-04 eta: 4:39:23 time: 0.463205 data_time: 0.024035 memory: 15239 loss_kpt: 0.000507 acc_pose: 0.890015 loss: 0.000507 2022/09/16 03:20:49 - mmengine - INFO - Epoch(train) [146][450/586] lr: 5.000000e-04 eta: 4:39:01 time: 0.471402 data_time: 0.026585 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.901544 loss: 0.000519 2022/09/16 03:21:12 - mmengine - INFO - Epoch(train) [146][500/586] lr: 5.000000e-04 eta: 4:38:39 time: 0.467552 data_time: 0.024456 memory: 15239 loss_kpt: 0.000511 acc_pose: 0.722836 loss: 0.000511 2022/09/16 03:21:35 - mmengine - INFO - Epoch(train) [146][550/586] lr: 5.000000e-04 eta: 4:38:17 time: 0.463987 data_time: 0.024628 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.824085 loss: 0.000509 2022/09/16 03:21:52 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 03:21:52 - mmengine - INFO - Saving checkpoint at 146 epochs 2022/09/16 03:22:23 - mmengine - INFO - Epoch(train) [147][50/586] lr: 5.000000e-04 eta: 4:37:33 time: 0.475571 data_time: 0.028609 memory: 15239 loss_kpt: 0.000491 acc_pose: 0.860735 loss: 0.000491 2022/09/16 03:22:46 - mmengine - INFO - Epoch(train) [147][100/586] lr: 5.000000e-04 eta: 4:37:11 time: 0.461061 data_time: 0.024734 memory: 15239 loss_kpt: 0.000491 acc_pose: 0.826736 loss: 0.000491 2022/09/16 03:23:10 - mmengine - INFO - Epoch(train) [147][150/586] lr: 5.000000e-04 eta: 4:36:50 time: 0.482983 data_time: 0.025880 memory: 15239 loss_kpt: 0.000507 acc_pose: 0.838626 loss: 0.000507 2022/09/16 03:23:34 - mmengine - INFO - Epoch(train) [147][200/586] lr: 5.000000e-04 eta: 4:36:28 time: 0.469440 data_time: 0.025587 memory: 15239 loss_kpt: 0.000527 acc_pose: 0.899668 loss: 0.000527 2022/09/16 03:23:57 - mmengine - INFO - Epoch(train) [147][250/586] lr: 5.000000e-04 eta: 4:36:06 time: 0.473828 data_time: 0.025091 memory: 15239 loss_kpt: 0.000495 acc_pose: 0.866581 loss: 0.000495 2022/09/16 03:24:21 - mmengine - INFO - Epoch(train) [147][300/586] lr: 5.000000e-04 eta: 4:35:45 time: 0.471180 data_time: 0.024949 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.888330 loss: 0.000509 2022/09/16 03:24:44 - mmengine - INFO - Epoch(train) [147][350/586] lr: 5.000000e-04 eta: 4:35:23 time: 0.468437 data_time: 0.029370 memory: 15239 loss_kpt: 0.000496 acc_pose: 0.826746 loss: 0.000496 2022/09/16 03:25:08 - mmengine - INFO - Epoch(train) [147][400/586] lr: 5.000000e-04 eta: 4:35:01 time: 0.473438 data_time: 0.024593 memory: 15239 loss_kpt: 0.000523 acc_pose: 0.884621 loss: 0.000523 2022/09/16 03:25:28 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 03:25:31 - mmengine - INFO - Epoch(train) [147][450/586] lr: 5.000000e-04 eta: 4:34:39 time: 0.462983 data_time: 0.024306 memory: 15239 loss_kpt: 0.000515 acc_pose: 0.896157 loss: 0.000515 2022/09/16 03:25:55 - mmengine - INFO - Epoch(train) [147][500/586] lr: 5.000000e-04 eta: 4:34:18 time: 0.465925 data_time: 0.024616 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.872601 loss: 0.000509 2022/09/16 03:26:18 - mmengine - INFO - Epoch(train) [147][550/586] lr: 5.000000e-04 eta: 4:33:56 time: 0.469975 data_time: 0.024410 memory: 15239 loss_kpt: 0.000495 acc_pose: 0.788687 loss: 0.000495 2022/09/16 03:26:35 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 03:26:35 - mmengine - INFO - Saving checkpoint at 147 epochs 2022/09/16 03:27:06 - mmengine - INFO - Epoch(train) [148][50/586] lr: 5.000000e-04 eta: 4:33:12 time: 0.479524 data_time: 0.035811 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.880441 loss: 0.000519 2022/09/16 03:27:30 - mmengine - INFO - Epoch(train) [148][100/586] lr: 5.000000e-04 eta: 4:32:50 time: 0.471570 data_time: 0.031400 memory: 15239 loss_kpt: 0.000490 acc_pose: 0.838476 loss: 0.000490 2022/09/16 03:27:53 - mmengine - INFO - Epoch(train) [148][150/586] lr: 5.000000e-04 eta: 4:32:28 time: 0.466857 data_time: 0.028364 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.879818 loss: 0.000509 2022/09/16 03:28:16 - mmengine - INFO - Epoch(train) [148][200/586] lr: 5.000000e-04 eta: 4:32:06 time: 0.461599 data_time: 0.028099 memory: 15239 loss_kpt: 0.000505 acc_pose: 0.830331 loss: 0.000505 2022/09/16 03:28:40 - mmengine - INFO - Epoch(train) [148][250/586] lr: 5.000000e-04 eta: 4:31:45 time: 0.481259 data_time: 0.032084 memory: 15239 loss_kpt: 0.000498 acc_pose: 0.835705 loss: 0.000498 2022/09/16 03:29:03 - mmengine - INFO - Epoch(train) [148][300/586] lr: 5.000000e-04 eta: 4:31:23 time: 0.458296 data_time: 0.029564 memory: 15239 loss_kpt: 0.000535 acc_pose: 0.886278 loss: 0.000535 2022/09/16 03:29:27 - mmengine - INFO - Epoch(train) [148][350/586] lr: 5.000000e-04 eta: 4:31:01 time: 0.474832 data_time: 0.031882 memory: 15239 loss_kpt: 0.000513 acc_pose: 0.830220 loss: 0.000513 2022/09/16 03:29:50 - mmengine - INFO - Epoch(train) [148][400/586] lr: 5.000000e-04 eta: 4:30:40 time: 0.470634 data_time: 0.028456 memory: 15239 loss_kpt: 0.000492 acc_pose: 0.895764 loss: 0.000492 2022/09/16 03:30:13 - mmengine - INFO - Epoch(train) [148][450/586] lr: 5.000000e-04 eta: 4:30:18 time: 0.460469 data_time: 0.026394 memory: 15239 loss_kpt: 0.000506 acc_pose: 0.883663 loss: 0.000506 2022/09/16 03:30:36 - mmengine - INFO - Epoch(train) [148][500/586] lr: 5.000000e-04 eta: 4:29:56 time: 0.462870 data_time: 0.028529 memory: 15239 loss_kpt: 0.000498 acc_pose: 0.883649 loss: 0.000498 2022/09/16 03:31:00 - mmengine - INFO - Epoch(train) [148][550/586] lr: 5.000000e-04 eta: 4:29:34 time: 0.468972 data_time: 0.024174 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.887519 loss: 0.000509 2022/09/16 03:31:16 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 03:31:16 - mmengine - INFO - Saving checkpoint at 148 epochs 2022/09/16 03:31:47 - mmengine - INFO - Epoch(train) [149][50/586] lr: 5.000000e-04 eta: 4:28:50 time: 0.474534 data_time: 0.028892 memory: 15239 loss_kpt: 0.000507 acc_pose: 0.941398 loss: 0.000507 2022/09/16 03:32:11 - mmengine - INFO - Epoch(train) [149][100/586] lr: 5.000000e-04 eta: 4:28:28 time: 0.468495 data_time: 0.025356 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.855786 loss: 0.000508 2022/09/16 03:32:34 - mmengine - INFO - Epoch(train) [149][150/586] lr: 5.000000e-04 eta: 4:28:06 time: 0.464112 data_time: 0.025037 memory: 15239 loss_kpt: 0.000512 acc_pose: 0.904665 loss: 0.000512 2022/09/16 03:32:57 - mmengine - INFO - Epoch(train) [149][200/586] lr: 5.000000e-04 eta: 4:27:44 time: 0.464794 data_time: 0.024400 memory: 15239 loss_kpt: 0.000494 acc_pose: 0.828856 loss: 0.000494 2022/09/16 03:33:21 - mmengine - INFO - Epoch(train) [149][250/586] lr: 5.000000e-04 eta: 4:27:23 time: 0.472856 data_time: 0.024907 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.864364 loss: 0.000508 2022/09/16 03:33:31 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 03:33:44 - mmengine - INFO - Epoch(train) [149][300/586] lr: 5.000000e-04 eta: 4:27:01 time: 0.467558 data_time: 0.024024 memory: 15239 loss_kpt: 0.000487 acc_pose: 0.933717 loss: 0.000487 2022/09/16 03:34:07 - mmengine - INFO - Epoch(train) [149][350/586] lr: 5.000000e-04 eta: 4:26:39 time: 0.460663 data_time: 0.024351 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.889276 loss: 0.000508 2022/09/16 03:34:31 - mmengine - INFO - Epoch(train) [149][400/586] lr: 5.000000e-04 eta: 4:26:17 time: 0.471137 data_time: 0.024419 memory: 15239 loss_kpt: 0.000506 acc_pose: 0.831339 loss: 0.000506 2022/09/16 03:34:54 - mmengine - INFO - Epoch(train) [149][450/586] lr: 5.000000e-04 eta: 4:25:56 time: 0.466263 data_time: 0.024738 memory: 15239 loss_kpt: 0.000515 acc_pose: 0.904106 loss: 0.000515 2022/09/16 03:35:18 - mmengine - INFO - Epoch(train) [149][500/586] lr: 5.000000e-04 eta: 4:25:34 time: 0.469004 data_time: 0.024472 memory: 15239 loss_kpt: 0.000505 acc_pose: 0.841540 loss: 0.000505 2022/09/16 03:35:41 - mmengine - INFO - Epoch(train) [149][550/586] lr: 5.000000e-04 eta: 4:25:12 time: 0.465742 data_time: 0.024494 memory: 15239 loss_kpt: 0.000512 acc_pose: 0.886347 loss: 0.000512 2022/09/16 03:35:58 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 03:35:58 - mmengine - INFO - Saving checkpoint at 149 epochs 2022/09/16 03:36:29 - mmengine - INFO - Epoch(train) [150][50/586] lr: 5.000000e-04 eta: 4:24:28 time: 0.482278 data_time: 0.028797 memory: 15239 loss_kpt: 0.000505 acc_pose: 0.833109 loss: 0.000505 2022/09/16 03:36:53 - mmengine - INFO - Epoch(train) [150][100/586] lr: 5.000000e-04 eta: 4:24:06 time: 0.468687 data_time: 0.024514 memory: 15239 loss_kpt: 0.000502 acc_pose: 0.877777 loss: 0.000502 2022/09/16 03:37:16 - mmengine - INFO - Epoch(train) [150][150/586] lr: 5.000000e-04 eta: 4:23:45 time: 0.471183 data_time: 0.024895 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.854712 loss: 0.000509 2022/09/16 03:37:40 - mmengine - INFO - Epoch(train) [150][200/586] lr: 5.000000e-04 eta: 4:23:23 time: 0.476682 data_time: 0.025029 memory: 15239 loss_kpt: 0.000505 acc_pose: 0.912384 loss: 0.000505 2022/09/16 03:38:03 - mmengine - INFO - Epoch(train) [150][250/586] lr: 5.000000e-04 eta: 4:23:01 time: 0.464678 data_time: 0.024407 memory: 15239 loss_kpt: 0.000488 acc_pose: 0.773497 loss: 0.000488 2022/09/16 03:38:27 - mmengine - INFO - Epoch(train) [150][300/586] lr: 5.000000e-04 eta: 4:22:40 time: 0.470505 data_time: 0.025421 memory: 15239 loss_kpt: 0.000496 acc_pose: 0.841804 loss: 0.000496 2022/09/16 03:38:50 - mmengine - INFO - Epoch(train) [150][350/586] lr: 5.000000e-04 eta: 4:22:18 time: 0.463710 data_time: 0.028610 memory: 15239 loss_kpt: 0.000490 acc_pose: 0.853065 loss: 0.000490 2022/09/16 03:39:13 - mmengine - INFO - Epoch(train) [150][400/586] lr: 5.000000e-04 eta: 4:21:56 time: 0.462650 data_time: 0.024196 memory: 15239 loss_kpt: 0.000510 acc_pose: 0.825985 loss: 0.000510 2022/09/16 03:39:37 - mmengine - INFO - Epoch(train) [150][450/586] lr: 5.000000e-04 eta: 4:21:34 time: 0.466858 data_time: 0.026296 memory: 15239 loss_kpt: 0.000523 acc_pose: 0.822339 loss: 0.000523 2022/09/16 03:40:00 - mmengine - INFO - Epoch(train) [150][500/586] lr: 5.000000e-04 eta: 4:21:12 time: 0.467987 data_time: 0.024531 memory: 15239 loss_kpt: 0.000501 acc_pose: 0.816352 loss: 0.000501 2022/09/16 03:40:23 - mmengine - INFO - Epoch(train) [150][550/586] lr: 5.000000e-04 eta: 4:20:50 time: 0.456955 data_time: 0.024563 memory: 15239 loss_kpt: 0.000490 acc_pose: 0.928579 loss: 0.000490 2022/09/16 03:40:40 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 03:40:40 - mmengine - INFO - Saving checkpoint at 150 epochs 2022/09/16 03:41:00 - mmengine - INFO - Epoch(val) [150][50/407] eta: 0:01:32 time: 0.258128 data_time: 0.012895 memory: 15239 2022/09/16 03:41:13 - mmengine - INFO - Epoch(val) [150][100/407] eta: 0:01:16 time: 0.250376 data_time: 0.008643 memory: 2064 2022/09/16 03:41:25 - mmengine - INFO - Epoch(val) [150][150/407] eta: 0:01:04 time: 0.252038 data_time: 0.008309 memory: 2064 2022/09/16 03:41:38 - mmengine - INFO - Epoch(val) [150][200/407] eta: 0:00:53 time: 0.258169 data_time: 0.008389 memory: 2064 2022/09/16 03:41:51 - mmengine - INFO - Epoch(val) [150][250/407] eta: 0:00:39 time: 0.251641 data_time: 0.008531 memory: 2064 2022/09/16 03:42:04 - mmengine - INFO - Epoch(val) [150][300/407] eta: 0:00:27 time: 0.255906 data_time: 0.008671 memory: 2064 2022/09/16 03:42:16 - mmengine - INFO - Epoch(val) [150][350/407] eta: 0:00:14 time: 0.251972 data_time: 0.008180 memory: 2064 2022/09/16 03:42:29 - mmengine - INFO - Epoch(val) [150][400/407] eta: 0:00:01 time: 0.247436 data_time: 0.008013 memory: 2064 2022/09/16 03:43:04 - mmengine - INFO - Evaluating CocoMetric... 2022/09/16 03:43:17 - mmengine - INFO - Epoch(val) [150][407/407] coco/AP: 0.762778 coco/AP .5: 0.906560 coco/AP .75: 0.824767 coco/AP (M): 0.723001 coco/AP (L): 0.834429 coco/AR: 0.810753 coco/AR .5: 0.941593 coco/AR .75: 0.868230 coco/AR (M): 0.765856 coco/AR (L): 0.875957 2022/09/16 03:43:42 - mmengine - INFO - Epoch(train) [151][50/586] lr: 5.000000e-04 eta: 4:20:06 time: 0.482303 data_time: 0.030523 memory: 15239 loss_kpt: 0.000504 acc_pose: 0.847939 loss: 0.000504 2022/09/16 03:44:05 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 03:44:05 - mmengine - INFO - Epoch(train) [151][100/586] lr: 5.000000e-04 eta: 4:19:45 time: 0.473357 data_time: 0.024501 memory: 15239 loss_kpt: 0.000510 acc_pose: 0.832558 loss: 0.000510 2022/09/16 03:44:29 - mmengine - INFO - Epoch(train) [151][150/586] lr: 5.000000e-04 eta: 4:19:23 time: 0.469911 data_time: 0.024753 memory: 15239 loss_kpt: 0.000500 acc_pose: 0.901178 loss: 0.000500 2022/09/16 03:44:52 - mmengine - INFO - Epoch(train) [151][200/586] lr: 5.000000e-04 eta: 4:19:01 time: 0.470337 data_time: 0.024166 memory: 15239 loss_kpt: 0.000500 acc_pose: 0.849366 loss: 0.000500 2022/09/16 03:45:16 - mmengine - INFO - Epoch(train) [151][250/586] lr: 5.000000e-04 eta: 4:18:40 time: 0.471344 data_time: 0.029128 memory: 15239 loss_kpt: 0.000504 acc_pose: 0.849519 loss: 0.000504 2022/09/16 03:45:39 - mmengine - INFO - Epoch(train) [151][300/586] lr: 5.000000e-04 eta: 4:18:18 time: 0.462513 data_time: 0.023940 memory: 15239 loss_kpt: 0.000518 acc_pose: 0.841427 loss: 0.000518 2022/09/16 03:46:03 - mmengine - INFO - Epoch(train) [151][350/586] lr: 5.000000e-04 eta: 4:17:56 time: 0.471020 data_time: 0.024851 memory: 15239 loss_kpt: 0.000505 acc_pose: 0.909947 loss: 0.000505 2022/09/16 03:46:26 - mmengine - INFO - Epoch(train) [151][400/586] lr: 5.000000e-04 eta: 4:17:34 time: 0.470733 data_time: 0.024928 memory: 15239 loss_kpt: 0.000504 acc_pose: 0.912903 loss: 0.000504 2022/09/16 03:46:50 - mmengine - INFO - Epoch(train) [151][450/586] lr: 5.000000e-04 eta: 4:17:13 time: 0.468920 data_time: 0.025073 memory: 15239 loss_kpt: 0.000513 acc_pose: 0.886965 loss: 0.000513 2022/09/16 03:47:13 - mmengine - INFO - Epoch(train) [151][500/586] lr: 5.000000e-04 eta: 4:16:51 time: 0.469394 data_time: 0.025371 memory: 15239 loss_kpt: 0.000520 acc_pose: 0.840945 loss: 0.000520 2022/09/16 03:47:37 - mmengine - INFO - Epoch(train) [151][550/586] lr: 5.000000e-04 eta: 4:16:29 time: 0.472144 data_time: 0.030041 memory: 15239 loss_kpt: 0.000502 acc_pose: 0.856064 loss: 0.000502 2022/09/16 03:47:53 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 03:47:53 - mmengine - INFO - Saving checkpoint at 151 epochs 2022/09/16 03:48:24 - mmengine - INFO - Epoch(train) [152][50/586] lr: 5.000000e-04 eta: 4:15:45 time: 0.480240 data_time: 0.031611 memory: 15239 loss_kpt: 0.000502 acc_pose: 0.909360 loss: 0.000502 2022/09/16 03:48:48 - mmengine - INFO - Epoch(train) [152][100/586] lr: 5.000000e-04 eta: 4:15:24 time: 0.472705 data_time: 0.025253 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.841800 loss: 0.000509 2022/09/16 03:49:11 - mmengine - INFO - Epoch(train) [152][150/586] lr: 5.000000e-04 eta: 4:15:02 time: 0.466795 data_time: 0.024225 memory: 15239 loss_kpt: 0.000502 acc_pose: 0.909967 loss: 0.000502 2022/09/16 03:49:35 - mmengine - INFO - Epoch(train) [152][200/586] lr: 5.000000e-04 eta: 4:14:40 time: 0.477466 data_time: 0.024942 memory: 15239 loss_kpt: 0.000493 acc_pose: 0.856390 loss: 0.000493 2022/09/16 03:49:59 - mmengine - INFO - Epoch(train) [152][250/586] lr: 5.000000e-04 eta: 4:14:18 time: 0.462720 data_time: 0.024210 memory: 15239 loss_kpt: 0.000500 acc_pose: 0.886488 loss: 0.000500 2022/09/16 03:50:22 - mmengine - INFO - Epoch(train) [152][300/586] lr: 5.000000e-04 eta: 4:13:57 time: 0.469459 data_time: 0.024519 memory: 15239 loss_kpt: 0.000504 acc_pose: 0.837666 loss: 0.000504 2022/09/16 03:50:46 - mmengine - INFO - Epoch(train) [152][350/586] lr: 5.000000e-04 eta: 4:13:35 time: 0.473410 data_time: 0.030871 memory: 15239 loss_kpt: 0.000493 acc_pose: 0.856787 loss: 0.000493 2022/09/16 03:51:09 - mmengine - INFO - Epoch(train) [152][400/586] lr: 5.000000e-04 eta: 4:13:13 time: 0.468880 data_time: 0.025079 memory: 15239 loss_kpt: 0.000493 acc_pose: 0.834743 loss: 0.000493 2022/09/16 03:51:32 - mmengine - INFO - Epoch(train) [152][450/586] lr: 5.000000e-04 eta: 4:12:51 time: 0.463635 data_time: 0.024207 memory: 15239 loss_kpt: 0.000507 acc_pose: 0.874656 loss: 0.000507 2022/09/16 03:51:56 - mmengine - INFO - Epoch(train) [152][500/586] lr: 5.000000e-04 eta: 4:12:30 time: 0.468895 data_time: 0.024423 memory: 15239 loss_kpt: 0.000496 acc_pose: 0.837441 loss: 0.000496 2022/09/16 03:52:02 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 03:52:19 - mmengine - INFO - Epoch(train) [152][550/586] lr: 5.000000e-04 eta: 4:12:08 time: 0.464694 data_time: 0.024782 memory: 15239 loss_kpt: 0.000507 acc_pose: 0.840699 loss: 0.000507 2022/09/16 03:52:35 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 03:52:35 - mmengine - INFO - Saving checkpoint at 152 epochs 2022/09/16 03:53:07 - mmengine - INFO - Epoch(train) [153][50/586] lr: 5.000000e-04 eta: 4:11:24 time: 0.486102 data_time: 0.034792 memory: 15239 loss_kpt: 0.000486 acc_pose: 0.894973 loss: 0.000486 2022/09/16 03:53:30 - mmengine - INFO - Epoch(train) [153][100/586] lr: 5.000000e-04 eta: 4:11:02 time: 0.465076 data_time: 0.024790 memory: 15239 loss_kpt: 0.000503 acc_pose: 0.893668 loss: 0.000503 2022/09/16 03:53:54 - mmengine - INFO - Epoch(train) [153][150/586] lr: 5.000000e-04 eta: 4:10:41 time: 0.469449 data_time: 0.023576 memory: 15239 loss_kpt: 0.000505 acc_pose: 0.801153 loss: 0.000505 2022/09/16 03:54:17 - mmengine - INFO - Epoch(train) [153][200/586] lr: 5.000000e-04 eta: 4:10:19 time: 0.472900 data_time: 0.024707 memory: 15239 loss_kpt: 0.000502 acc_pose: 0.891587 loss: 0.000502 2022/09/16 03:54:41 - mmengine - INFO - Epoch(train) [153][250/586] lr: 5.000000e-04 eta: 4:09:57 time: 0.466023 data_time: 0.024687 memory: 15239 loss_kpt: 0.000495 acc_pose: 0.874626 loss: 0.000495 2022/09/16 03:55:05 - mmengine - INFO - Epoch(train) [153][300/586] lr: 5.000000e-04 eta: 4:09:36 time: 0.474865 data_time: 0.025637 memory: 15239 loss_kpt: 0.000492 acc_pose: 0.856783 loss: 0.000492 2022/09/16 03:55:28 - mmengine - INFO - Epoch(train) [153][350/586] lr: 5.000000e-04 eta: 4:09:14 time: 0.468866 data_time: 0.024123 memory: 15239 loss_kpt: 0.000503 acc_pose: 0.918059 loss: 0.000503 2022/09/16 03:55:51 - mmengine - INFO - Epoch(train) [153][400/586] lr: 5.000000e-04 eta: 4:08:52 time: 0.463175 data_time: 0.024836 memory: 15239 loss_kpt: 0.000497 acc_pose: 0.885950 loss: 0.000497 2022/09/16 03:56:15 - mmengine - INFO - Epoch(train) [153][450/586] lr: 5.000000e-04 eta: 4:08:30 time: 0.472171 data_time: 0.029152 memory: 15239 loss_kpt: 0.000497 acc_pose: 0.901570 loss: 0.000497 2022/09/16 03:56:38 - mmengine - INFO - Epoch(train) [153][500/586] lr: 5.000000e-04 eta: 4:08:08 time: 0.463542 data_time: 0.023813 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.845378 loss: 0.000509 2022/09/16 03:57:01 - mmengine - INFO - Epoch(train) [153][550/586] lr: 5.000000e-04 eta: 4:07:46 time: 0.465873 data_time: 0.028510 memory: 15239 loss_kpt: 0.000479 acc_pose: 0.891052 loss: 0.000479 2022/09/16 03:57:18 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 03:57:18 - mmengine - INFO - Saving checkpoint at 153 epochs 2022/09/16 03:57:49 - mmengine - INFO - Epoch(train) [154][50/586] lr: 5.000000e-04 eta: 4:07:03 time: 0.479431 data_time: 0.031618 memory: 15239 loss_kpt: 0.000510 acc_pose: 0.858064 loss: 0.000510 2022/09/16 03:58:13 - mmengine - INFO - Epoch(train) [154][100/586] lr: 5.000000e-04 eta: 4:06:41 time: 0.476195 data_time: 0.031749 memory: 15239 loss_kpt: 0.000492 acc_pose: 0.889416 loss: 0.000492 2022/09/16 03:58:37 - mmengine - INFO - Epoch(train) [154][150/586] lr: 5.000000e-04 eta: 4:06:20 time: 0.471803 data_time: 0.026961 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.879821 loss: 0.000508 2022/09/16 03:59:00 - mmengine - INFO - Epoch(train) [154][200/586] lr: 5.000000e-04 eta: 4:05:58 time: 0.471347 data_time: 0.027592 memory: 15239 loss_kpt: 0.000512 acc_pose: 0.871884 loss: 0.000512 2022/09/16 03:59:24 - mmengine - INFO - Epoch(train) [154][250/586] lr: 5.000000e-04 eta: 4:05:36 time: 0.470666 data_time: 0.027847 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.821273 loss: 0.000519 2022/09/16 03:59:47 - mmengine - INFO - Epoch(train) [154][300/586] lr: 5.000000e-04 eta: 4:05:14 time: 0.467600 data_time: 0.032057 memory: 15239 loss_kpt: 0.000503 acc_pose: 0.809720 loss: 0.000503 2022/09/16 04:00:06 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 04:00:10 - mmengine - INFO - Epoch(train) [154][350/586] lr: 5.000000e-04 eta: 4:04:52 time: 0.463126 data_time: 0.027703 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.842390 loss: 0.000508 2022/09/16 04:00:34 - mmengine - INFO - Epoch(train) [154][400/586] lr: 5.000000e-04 eta: 4:04:31 time: 0.472893 data_time: 0.027254 memory: 15239 loss_kpt: 0.000506 acc_pose: 0.901451 loss: 0.000506 2022/09/16 04:00:57 - mmengine - INFO - Epoch(train) [154][450/586] lr: 5.000000e-04 eta: 4:04:09 time: 0.458183 data_time: 0.027813 memory: 15239 loss_kpt: 0.000490 acc_pose: 0.885606 loss: 0.000490 2022/09/16 04:01:20 - mmengine - INFO - Epoch(train) [154][500/586] lr: 5.000000e-04 eta: 4:03:47 time: 0.466699 data_time: 0.033991 memory: 15239 loss_kpt: 0.000494 acc_pose: 0.920347 loss: 0.000494 2022/09/16 04:01:44 - mmengine - INFO - Epoch(train) [154][550/586] lr: 5.000000e-04 eta: 4:03:25 time: 0.468597 data_time: 0.029312 memory: 15239 loss_kpt: 0.000488 acc_pose: 0.892602 loss: 0.000488 2022/09/16 04:02:00 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 04:02:00 - mmengine - INFO - Saving checkpoint at 154 epochs 2022/09/16 04:02:31 - mmengine - INFO - Epoch(train) [155][50/586] lr: 5.000000e-04 eta: 4:02:42 time: 0.470943 data_time: 0.029071 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.810234 loss: 0.000508 2022/09/16 04:02:54 - mmengine - INFO - Epoch(train) [155][100/586] lr: 5.000000e-04 eta: 4:02:20 time: 0.474811 data_time: 0.024742 memory: 15239 loss_kpt: 0.000490 acc_pose: 0.851783 loss: 0.000490 2022/09/16 04:03:18 - mmengine - INFO - Epoch(train) [155][150/586] lr: 5.000000e-04 eta: 4:01:58 time: 0.464620 data_time: 0.024363 memory: 15239 loss_kpt: 0.000505 acc_pose: 0.918309 loss: 0.000505 2022/09/16 04:03:41 - mmengine - INFO - Epoch(train) [155][200/586] lr: 5.000000e-04 eta: 4:01:36 time: 0.476526 data_time: 0.024864 memory: 15239 loss_kpt: 0.000502 acc_pose: 0.859357 loss: 0.000502 2022/09/16 04:04:05 - mmengine - INFO - Epoch(train) [155][250/586] lr: 5.000000e-04 eta: 4:01:14 time: 0.463417 data_time: 0.028440 memory: 15239 loss_kpt: 0.000491 acc_pose: 0.809116 loss: 0.000491 2022/09/16 04:04:28 - mmengine - INFO - Epoch(train) [155][300/586] lr: 5.000000e-04 eta: 4:00:53 time: 0.468778 data_time: 0.023518 memory: 15239 loss_kpt: 0.000512 acc_pose: 0.887429 loss: 0.000512 2022/09/16 04:04:52 - mmengine - INFO - Epoch(train) [155][350/586] lr: 5.000000e-04 eta: 4:00:31 time: 0.468946 data_time: 0.025955 memory: 15239 loss_kpt: 0.000502 acc_pose: 0.864985 loss: 0.000502 2022/09/16 04:05:15 - mmengine - INFO - Epoch(train) [155][400/586] lr: 5.000000e-04 eta: 4:00:09 time: 0.467185 data_time: 0.024914 memory: 15239 loss_kpt: 0.000525 acc_pose: 0.852387 loss: 0.000525 2022/09/16 04:05:38 - mmengine - INFO - Epoch(train) [155][450/586] lr: 5.000000e-04 eta: 3:59:47 time: 0.462304 data_time: 0.024719 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.857951 loss: 0.000508 2022/09/16 04:06:01 - mmengine - INFO - Epoch(train) [155][500/586] lr: 5.000000e-04 eta: 3:59:25 time: 0.462872 data_time: 0.024849 memory: 15239 loss_kpt: 0.000480 acc_pose: 0.895497 loss: 0.000480 2022/09/16 04:06:25 - mmengine - INFO - Epoch(train) [155][550/586] lr: 5.000000e-04 eta: 3:59:04 time: 0.470785 data_time: 0.028369 memory: 15239 loss_kpt: 0.000495 acc_pose: 0.887556 loss: 0.000495 2022/09/16 04:06:41 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 04:06:41 - mmengine - INFO - Saving checkpoint at 155 epochs 2022/09/16 04:07:12 - mmengine - INFO - Epoch(train) [156][50/586] lr: 5.000000e-04 eta: 3:58:20 time: 0.473963 data_time: 0.031062 memory: 15239 loss_kpt: 0.000512 acc_pose: 0.865131 loss: 0.000512 2022/09/16 04:07:35 - mmengine - INFO - Epoch(train) [156][100/586] lr: 5.000000e-04 eta: 3:57:58 time: 0.462925 data_time: 0.024527 memory: 15239 loss_kpt: 0.000511 acc_pose: 0.843812 loss: 0.000511 2022/09/16 04:07:58 - mmengine - INFO - Epoch(train) [156][150/586] lr: 5.000000e-04 eta: 3:57:36 time: 0.465099 data_time: 0.025229 memory: 15239 loss_kpt: 0.000494 acc_pose: 0.906468 loss: 0.000494 2022/09/16 04:08:08 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 04:08:21 - mmengine - INFO - Epoch(train) [156][200/586] lr: 5.000000e-04 eta: 3:57:14 time: 0.460428 data_time: 0.027344 memory: 15239 loss_kpt: 0.000505 acc_pose: 0.921332 loss: 0.000505 2022/09/16 04:08:45 - mmengine - INFO - Epoch(train) [156][250/586] lr: 5.000000e-04 eta: 3:56:53 time: 0.472561 data_time: 0.024465 memory: 15239 loss_kpt: 0.000491 acc_pose: 0.927690 loss: 0.000491 2022/09/16 04:09:09 - mmengine - INFO - Epoch(train) [156][300/586] lr: 5.000000e-04 eta: 3:56:31 time: 0.471917 data_time: 0.025092 memory: 15239 loss_kpt: 0.000501 acc_pose: 0.876064 loss: 0.000501 2022/09/16 04:09:32 - mmengine - INFO - Epoch(train) [156][350/586] lr: 5.000000e-04 eta: 3:56:09 time: 0.461702 data_time: 0.025802 memory: 15239 loss_kpt: 0.000498 acc_pose: 0.854477 loss: 0.000498 2022/09/16 04:09:55 - mmengine - INFO - Epoch(train) [156][400/586] lr: 5.000000e-04 eta: 3:55:47 time: 0.470963 data_time: 0.029573 memory: 15239 loss_kpt: 0.000507 acc_pose: 0.878118 loss: 0.000507 2022/09/16 04:10:19 - mmengine - INFO - Epoch(train) [156][450/586] lr: 5.000000e-04 eta: 3:55:25 time: 0.468431 data_time: 0.034637 memory: 15239 loss_kpt: 0.000497 acc_pose: 0.895123 loss: 0.000497 2022/09/16 04:10:42 - mmengine - INFO - Epoch(train) [156][500/586] lr: 5.000000e-04 eta: 3:55:04 time: 0.459408 data_time: 0.029070 memory: 15239 loss_kpt: 0.000500 acc_pose: 0.870416 loss: 0.000500 2022/09/16 04:11:05 - mmengine - INFO - Epoch(train) [156][550/586] lr: 5.000000e-04 eta: 3:54:42 time: 0.459215 data_time: 0.027933 memory: 15239 loss_kpt: 0.000491 acc_pose: 0.824912 loss: 0.000491 2022/09/16 04:11:22 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 04:11:22 - mmengine - INFO - Saving checkpoint at 156 epochs 2022/09/16 04:11:52 - mmengine - INFO - Epoch(train) [157][50/586] lr: 5.000000e-04 eta: 3:53:58 time: 0.469830 data_time: 0.038867 memory: 15239 loss_kpt: 0.000490 acc_pose: 0.877504 loss: 0.000490 2022/09/16 04:12:16 - mmengine - INFO - Epoch(train) [157][100/586] lr: 5.000000e-04 eta: 3:53:36 time: 0.468231 data_time: 0.027963 memory: 15239 loss_kpt: 0.000500 acc_pose: 0.818926 loss: 0.000500 2022/09/16 04:12:39 - mmengine - INFO - Epoch(train) [157][150/586] lr: 5.000000e-04 eta: 3:53:15 time: 0.469163 data_time: 0.028289 memory: 15239 loss_kpt: 0.000493 acc_pose: 0.847384 loss: 0.000493 2022/09/16 04:13:02 - mmengine - INFO - Epoch(train) [157][200/586] lr: 5.000000e-04 eta: 3:52:53 time: 0.462081 data_time: 0.025261 memory: 15239 loss_kpt: 0.000497 acc_pose: 0.868794 loss: 0.000497 2022/09/16 04:13:26 - mmengine - INFO - Epoch(train) [157][250/586] lr: 5.000000e-04 eta: 3:52:31 time: 0.466364 data_time: 0.024387 memory: 15239 loss_kpt: 0.000496 acc_pose: 0.868428 loss: 0.000496 2022/09/16 04:13:49 - mmengine - INFO - Epoch(train) [157][300/586] lr: 5.000000e-04 eta: 3:52:09 time: 0.463499 data_time: 0.024399 memory: 15239 loss_kpt: 0.000487 acc_pose: 0.913548 loss: 0.000487 2022/09/16 04:14:12 - mmengine - INFO - Epoch(train) [157][350/586] lr: 5.000000e-04 eta: 3:51:47 time: 0.463107 data_time: 0.025113 memory: 15239 loss_kpt: 0.000496 acc_pose: 0.859932 loss: 0.000496 2022/09/16 04:14:35 - mmengine - INFO - Epoch(train) [157][400/586] lr: 5.000000e-04 eta: 3:51:25 time: 0.463459 data_time: 0.024411 memory: 15239 loss_kpt: 0.000510 acc_pose: 0.851909 loss: 0.000510 2022/09/16 04:14:58 - mmengine - INFO - Epoch(train) [157][450/586] lr: 5.000000e-04 eta: 3:51:03 time: 0.467389 data_time: 0.029075 memory: 15239 loss_kpt: 0.000499 acc_pose: 0.892326 loss: 0.000499 2022/09/16 04:15:22 - mmengine - INFO - Epoch(train) [157][500/586] lr: 5.000000e-04 eta: 3:50:42 time: 0.465854 data_time: 0.024992 memory: 15239 loss_kpt: 0.000492 acc_pose: 0.908298 loss: 0.000492 2022/09/16 04:15:45 - mmengine - INFO - Epoch(train) [157][550/586] lr: 5.000000e-04 eta: 3:50:20 time: 0.467312 data_time: 0.025781 memory: 15239 loss_kpt: 0.000516 acc_pose: 0.870148 loss: 0.000516 2022/09/16 04:16:01 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 04:16:02 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 04:16:02 - mmengine - INFO - Saving checkpoint at 157 epochs 2022/09/16 04:16:32 - mmengine - INFO - Epoch(train) [158][50/586] lr: 5.000000e-04 eta: 3:49:37 time: 0.472241 data_time: 0.033132 memory: 15239 loss_kpt: 0.000517 acc_pose: 0.892812 loss: 0.000517 2022/09/16 04:16:56 - mmengine - INFO - Epoch(train) [158][100/586] lr: 5.000000e-04 eta: 3:49:15 time: 0.474615 data_time: 0.024512 memory: 15239 loss_kpt: 0.000484 acc_pose: 0.876569 loss: 0.000484 2022/09/16 04:17:19 - mmengine - INFO - Epoch(train) [158][150/586] lr: 5.000000e-04 eta: 3:48:53 time: 0.464350 data_time: 0.024645 memory: 15239 loss_kpt: 0.000501 acc_pose: 0.846898 loss: 0.000501 2022/09/16 04:17:43 - mmengine - INFO - Epoch(train) [158][200/586] lr: 5.000000e-04 eta: 3:48:31 time: 0.467567 data_time: 0.025827 memory: 15239 loss_kpt: 0.000497 acc_pose: 0.886120 loss: 0.000497 2022/09/16 04:18:06 - mmengine - INFO - Epoch(train) [158][250/586] lr: 5.000000e-04 eta: 3:48:09 time: 0.467527 data_time: 0.027583 memory: 15239 loss_kpt: 0.000506 acc_pose: 0.843688 loss: 0.000506 2022/09/16 04:18:29 - mmengine - INFO - Epoch(train) [158][300/586] lr: 5.000000e-04 eta: 3:47:47 time: 0.463782 data_time: 0.024446 memory: 15239 loss_kpt: 0.000497 acc_pose: 0.909243 loss: 0.000497 2022/09/16 04:18:53 - mmengine - INFO - Epoch(train) [158][350/586] lr: 5.000000e-04 eta: 3:47:25 time: 0.462793 data_time: 0.024631 memory: 15239 loss_kpt: 0.000515 acc_pose: 0.891041 loss: 0.000515 2022/09/16 04:19:16 - mmengine - INFO - Epoch(train) [158][400/586] lr: 5.000000e-04 eta: 3:47:04 time: 0.468485 data_time: 0.024440 memory: 15239 loss_kpt: 0.000515 acc_pose: 0.816087 loss: 0.000515 2022/09/16 04:19:39 - mmengine - INFO - Epoch(train) [158][450/586] lr: 5.000000e-04 eta: 3:46:42 time: 0.462878 data_time: 0.027736 memory: 15239 loss_kpt: 0.000523 acc_pose: 0.752259 loss: 0.000523 2022/09/16 04:20:02 - mmengine - INFO - Epoch(train) [158][500/586] lr: 5.000000e-04 eta: 3:46:20 time: 0.466786 data_time: 0.024813 memory: 15239 loss_kpt: 0.000499 acc_pose: 0.872935 loss: 0.000499 2022/09/16 04:20:26 - mmengine - INFO - Epoch(train) [158][550/586] lr: 5.000000e-04 eta: 3:45:58 time: 0.471015 data_time: 0.024879 memory: 15239 loss_kpt: 0.000505 acc_pose: 0.862708 loss: 0.000505 2022/09/16 04:20:43 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 04:20:43 - mmengine - INFO - Saving checkpoint at 158 epochs 2022/09/16 04:21:14 - mmengine - INFO - Epoch(train) [159][50/586] lr: 5.000000e-04 eta: 3:45:15 time: 0.477140 data_time: 0.035367 memory: 15239 loss_kpt: 0.000494 acc_pose: 0.840337 loss: 0.000494 2022/09/16 04:21:37 - mmengine - INFO - Epoch(train) [159][100/586] lr: 5.000000e-04 eta: 3:44:53 time: 0.462736 data_time: 0.026813 memory: 15239 loss_kpt: 0.000501 acc_pose: 0.873322 loss: 0.000501 2022/09/16 04:22:00 - mmengine - INFO - Epoch(train) [159][150/586] lr: 5.000000e-04 eta: 3:44:31 time: 0.460586 data_time: 0.024585 memory: 15239 loss_kpt: 0.000502 acc_pose: 0.860442 loss: 0.000502 2022/09/16 04:22:23 - mmengine - INFO - Epoch(train) [159][200/586] lr: 5.000000e-04 eta: 3:44:09 time: 0.468221 data_time: 0.030071 memory: 15239 loss_kpt: 0.000504 acc_pose: 0.846699 loss: 0.000504 2022/09/16 04:22:47 - mmengine - INFO - Epoch(train) [159][250/586] lr: 5.000000e-04 eta: 3:43:48 time: 0.470250 data_time: 0.024382 memory: 15239 loss_kpt: 0.000505 acc_pose: 0.887301 loss: 0.000505 2022/09/16 04:23:10 - mmengine - INFO - Epoch(train) [159][300/586] lr: 5.000000e-04 eta: 3:43:26 time: 0.457751 data_time: 0.024791 memory: 15239 loss_kpt: 0.000506 acc_pose: 0.911935 loss: 0.000506 2022/09/16 04:23:33 - mmengine - INFO - Epoch(train) [159][350/586] lr: 5.000000e-04 eta: 3:43:04 time: 0.469240 data_time: 0.023990 memory: 15239 loss_kpt: 0.000505 acc_pose: 0.888371 loss: 0.000505 2022/09/16 04:23:57 - mmengine - INFO - Epoch(train) [159][400/586] lr: 5.000000e-04 eta: 3:42:42 time: 0.465598 data_time: 0.024123 memory: 15239 loss_kpt: 0.000506 acc_pose: 0.864016 loss: 0.000506 2022/09/16 04:24:02 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 04:24:20 - mmengine - INFO - Epoch(train) [159][450/586] lr: 5.000000e-04 eta: 3:42:20 time: 0.460106 data_time: 0.024866 memory: 15239 loss_kpt: 0.000491 acc_pose: 0.876946 loss: 0.000491 2022/09/16 04:24:43 - mmengine - INFO - Epoch(train) [159][500/586] lr: 5.000000e-04 eta: 3:41:58 time: 0.471452 data_time: 0.028667 memory: 15239 loss_kpt: 0.000511 acc_pose: 0.920721 loss: 0.000511 2022/09/16 04:25:06 - mmengine - INFO - Epoch(train) [159][550/586] lr: 5.000000e-04 eta: 3:41:36 time: 0.464942 data_time: 0.024796 memory: 15239 loss_kpt: 0.000493 acc_pose: 0.829033 loss: 0.000493 2022/09/16 04:25:23 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 04:25:23 - mmengine - INFO - Saving checkpoint at 159 epochs 2022/09/16 04:25:54 - mmengine - INFO - Epoch(train) [160][50/586] lr: 5.000000e-04 eta: 3:40:54 time: 0.481534 data_time: 0.031244 memory: 15239 loss_kpt: 0.000484 acc_pose: 0.913443 loss: 0.000484 2022/09/16 04:26:18 - mmengine - INFO - Epoch(train) [160][100/586] lr: 5.000000e-04 eta: 3:40:32 time: 0.471276 data_time: 0.027713 memory: 15239 loss_kpt: 0.000492 acc_pose: 0.884888 loss: 0.000492 2022/09/16 04:26:41 - mmengine - INFO - Epoch(train) [160][150/586] lr: 5.000000e-04 eta: 3:40:10 time: 0.463376 data_time: 0.027586 memory: 15239 loss_kpt: 0.000484 acc_pose: 0.888678 loss: 0.000484 2022/09/16 04:27:04 - mmengine - INFO - Epoch(train) [160][200/586] lr: 5.000000e-04 eta: 3:39:48 time: 0.468978 data_time: 0.032800 memory: 15239 loss_kpt: 0.000498 acc_pose: 0.863728 loss: 0.000498 2022/09/16 04:27:28 - mmengine - INFO - Epoch(train) [160][250/586] lr: 5.000000e-04 eta: 3:39:26 time: 0.469625 data_time: 0.028265 memory: 15239 loss_kpt: 0.000501 acc_pose: 0.843470 loss: 0.000501 2022/09/16 04:27:51 - mmengine - INFO - Epoch(train) [160][300/586] lr: 5.000000e-04 eta: 3:39:04 time: 0.466510 data_time: 0.028579 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.917519 loss: 0.000509 2022/09/16 04:28:14 - mmengine - INFO - Epoch(train) [160][350/586] lr: 5.000000e-04 eta: 3:38:43 time: 0.465929 data_time: 0.028623 memory: 15239 loss_kpt: 0.000496 acc_pose: 0.816650 loss: 0.000496 2022/09/16 04:28:38 - mmengine - INFO - Epoch(train) [160][400/586] lr: 5.000000e-04 eta: 3:38:21 time: 0.472578 data_time: 0.033075 memory: 15239 loss_kpt: 0.000503 acc_pose: 0.911540 loss: 0.000503 2022/09/16 04:29:02 - mmengine - INFO - Epoch(train) [160][450/586] lr: 5.000000e-04 eta: 3:37:59 time: 0.471277 data_time: 0.028026 memory: 15239 loss_kpt: 0.000507 acc_pose: 0.906633 loss: 0.000507 2022/09/16 04:29:25 - mmengine - INFO - Epoch(train) [160][500/586] lr: 5.000000e-04 eta: 3:37:37 time: 0.464963 data_time: 0.029962 memory: 15239 loss_kpt: 0.000497 acc_pose: 0.843543 loss: 0.000497 2022/09/16 04:29:48 - mmengine - INFO - Epoch(train) [160][550/586] lr: 5.000000e-04 eta: 3:37:15 time: 0.469874 data_time: 0.025765 memory: 15239 loss_kpt: 0.000523 acc_pose: 0.862309 loss: 0.000523 2022/09/16 04:30:05 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 04:30:05 - mmengine - INFO - Saving checkpoint at 160 epochs 2022/09/16 04:30:25 - mmengine - INFO - Epoch(val) [160][50/407] eta: 0:01:32 time: 0.259582 data_time: 0.014295 memory: 15239 2022/09/16 04:30:38 - mmengine - INFO - Epoch(val) [160][100/407] eta: 0:01:17 time: 0.252709 data_time: 0.008868 memory: 2064 2022/09/16 04:30:51 - mmengine - INFO - Epoch(val) [160][150/407] eta: 0:01:04 time: 0.252375 data_time: 0.008394 memory: 2064 2022/09/16 04:31:03 - mmengine - INFO - Epoch(val) [160][200/407] eta: 0:00:52 time: 0.251717 data_time: 0.008421 memory: 2064 2022/09/16 04:31:16 - mmengine - INFO - Epoch(val) [160][250/407] eta: 0:00:39 time: 0.250092 data_time: 0.008199 memory: 2064 2022/09/16 04:31:28 - mmengine - INFO - Epoch(val) [160][300/407] eta: 0:00:27 time: 0.252519 data_time: 0.008993 memory: 2064 2022/09/16 04:31:41 - mmengine - INFO - Epoch(val) [160][350/407] eta: 0:00:14 time: 0.254348 data_time: 0.008359 memory: 2064 2022/09/16 04:31:54 - mmengine - INFO - Epoch(val) [160][400/407] eta: 0:00:01 time: 0.247611 data_time: 0.008226 memory: 2064 2022/09/16 04:32:28 - mmengine - INFO - Evaluating CocoMetric... 2022/09/16 04:32:41 - mmengine - INFO - Epoch(val) [160][407/407] coco/AP: 0.763721 coco/AP .5: 0.907332 coco/AP .75: 0.824049 coco/AP (M): 0.723094 coco/AP (L): 0.836579 coco/AR: 0.812012 coco/AR .5: 0.941751 coco/AR .75: 0.865869 coco/AR (M): 0.767823 coco/AR (L): 0.876886 2022/09/16 04:32:41 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220915/dark_w48_384/best_coco/AP_epoch_140.pth is removed 2022/09/16 04:32:45 - mmengine - INFO - The best checkpoint with 0.7637 coco/AP at 160 epoch is saved to best_coco/AP_epoch_160.pth. 2022/09/16 04:33:09 - mmengine - INFO - Epoch(train) [161][50/586] lr: 5.000000e-04 eta: 3:36:33 time: 0.476859 data_time: 0.031623 memory: 15239 loss_kpt: 0.000498 acc_pose: 0.838156 loss: 0.000498 2022/09/16 04:33:33 - mmengine - INFO - Epoch(train) [161][100/586] lr: 5.000000e-04 eta: 3:36:11 time: 0.466340 data_time: 0.028435 memory: 15239 loss_kpt: 0.000494 acc_pose: 0.824801 loss: 0.000494 2022/09/16 04:33:56 - mmengine - INFO - Epoch(train) [161][150/586] lr: 5.000000e-04 eta: 3:35:49 time: 0.463999 data_time: 0.032820 memory: 15239 loss_kpt: 0.000497 acc_pose: 0.895486 loss: 0.000497 2022/09/16 04:34:19 - mmengine - INFO - Epoch(train) [161][200/586] lr: 5.000000e-04 eta: 3:35:27 time: 0.467712 data_time: 0.028195 memory: 15239 loss_kpt: 0.000506 acc_pose: 0.909745 loss: 0.000506 2022/09/16 04:34:38 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 04:34:43 - mmengine - INFO - Epoch(train) [161][250/586] lr: 5.000000e-04 eta: 3:35:05 time: 0.477061 data_time: 0.028786 memory: 15239 loss_kpt: 0.000498 acc_pose: 0.866914 loss: 0.000498 2022/09/16 04:35:06 - mmengine - INFO - Epoch(train) [161][300/586] lr: 5.000000e-04 eta: 3:34:43 time: 0.459055 data_time: 0.028130 memory: 15239 loss_kpt: 0.000518 acc_pose: 0.903961 loss: 0.000518 2022/09/16 04:35:30 - mmengine - INFO - Epoch(train) [161][350/586] lr: 5.000000e-04 eta: 3:34:22 time: 0.472082 data_time: 0.033233 memory: 15239 loss_kpt: 0.000501 acc_pose: 0.880543 loss: 0.000501 2022/09/16 04:35:53 - mmengine - INFO - Epoch(train) [161][400/586] lr: 5.000000e-04 eta: 3:34:00 time: 0.467751 data_time: 0.029949 memory: 15239 loss_kpt: 0.000505 acc_pose: 0.868755 loss: 0.000505 2022/09/16 04:36:16 - mmengine - INFO - Epoch(train) [161][450/586] lr: 5.000000e-04 eta: 3:33:38 time: 0.459080 data_time: 0.026148 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.857214 loss: 0.000509 2022/09/16 04:36:40 - mmengine - INFO - Epoch(train) [161][500/586] lr: 5.000000e-04 eta: 3:33:16 time: 0.474366 data_time: 0.024510 memory: 15239 loss_kpt: 0.000486 acc_pose: 0.919484 loss: 0.000486 2022/09/16 04:37:03 - mmengine - INFO - Epoch(train) [161][550/586] lr: 5.000000e-04 eta: 3:32:54 time: 0.464123 data_time: 0.024691 memory: 15239 loss_kpt: 0.000502 acc_pose: 0.901938 loss: 0.000502 2022/09/16 04:37:19 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 04:37:19 - mmengine - INFO - Saving checkpoint at 161 epochs 2022/09/16 04:37:51 - mmengine - INFO - Epoch(train) [162][50/586] lr: 5.000000e-04 eta: 3:32:11 time: 0.479286 data_time: 0.031994 memory: 15239 loss_kpt: 0.000492 acc_pose: 0.873731 loss: 0.000492 2022/09/16 04:38:14 - mmengine - INFO - Epoch(train) [162][100/586] lr: 5.000000e-04 eta: 3:31:50 time: 0.463290 data_time: 0.024122 memory: 15239 loss_kpt: 0.000496 acc_pose: 0.852127 loss: 0.000496 2022/09/16 04:38:37 - mmengine - INFO - Epoch(train) [162][150/586] lr: 5.000000e-04 eta: 3:31:28 time: 0.465702 data_time: 0.029022 memory: 15239 loss_kpt: 0.000504 acc_pose: 0.920697 loss: 0.000504 2022/09/16 04:39:00 - mmengine - INFO - Epoch(train) [162][200/586] lr: 5.000000e-04 eta: 3:31:06 time: 0.462167 data_time: 0.024653 memory: 15239 loss_kpt: 0.000516 acc_pose: 0.850464 loss: 0.000516 2022/09/16 04:39:24 - mmengine - INFO - Epoch(train) [162][250/586] lr: 5.000000e-04 eta: 3:30:44 time: 0.465658 data_time: 0.024618 memory: 15239 loss_kpt: 0.000488 acc_pose: 0.912009 loss: 0.000488 2022/09/16 04:39:47 - mmengine - INFO - Epoch(train) [162][300/586] lr: 5.000000e-04 eta: 3:30:22 time: 0.467820 data_time: 0.024572 memory: 15239 loss_kpt: 0.000503 acc_pose: 0.853371 loss: 0.000503 2022/09/16 04:40:10 - mmengine - INFO - Epoch(train) [162][350/586] lr: 5.000000e-04 eta: 3:30:00 time: 0.465104 data_time: 0.024095 memory: 15239 loss_kpt: 0.000496 acc_pose: 0.851019 loss: 0.000496 2022/09/16 04:40:33 - mmengine - INFO - Epoch(train) [162][400/586] lr: 5.000000e-04 eta: 3:29:38 time: 0.457459 data_time: 0.024728 memory: 15239 loss_kpt: 0.000493 acc_pose: 0.858625 loss: 0.000493 2022/09/16 04:40:57 - mmengine - INFO - Epoch(train) [162][450/586] lr: 5.000000e-04 eta: 3:29:16 time: 0.468414 data_time: 0.028717 memory: 15239 loss_kpt: 0.000470 acc_pose: 0.891349 loss: 0.000470 2022/09/16 04:41:20 - mmengine - INFO - Epoch(train) [162][500/586] lr: 5.000000e-04 eta: 3:28:54 time: 0.465653 data_time: 0.024572 memory: 15239 loss_kpt: 0.000496 acc_pose: 0.908717 loss: 0.000496 2022/09/16 04:41:43 - mmengine - INFO - Epoch(train) [162][550/586] lr: 5.000000e-04 eta: 3:28:32 time: 0.467590 data_time: 0.024180 memory: 15239 loss_kpt: 0.000502 acc_pose: 0.888836 loss: 0.000502 2022/09/16 04:42:00 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 04:42:00 - mmengine - INFO - Saving checkpoint at 162 epochs 2022/09/16 04:42:31 - mmengine - INFO - Epoch(train) [163][50/586] lr: 5.000000e-04 eta: 3:27:50 time: 0.480339 data_time: 0.036781 memory: 15239 loss_kpt: 0.000503 acc_pose: 0.865848 loss: 0.000503 2022/09/16 04:42:40 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 04:42:54 - mmengine - INFO - Epoch(train) [163][100/586] lr: 5.000000e-04 eta: 3:27:28 time: 0.465178 data_time: 0.028367 memory: 15239 loss_kpt: 0.000506 acc_pose: 0.905164 loss: 0.000506 2022/09/16 04:43:18 - mmengine - INFO - Epoch(train) [163][150/586] lr: 5.000000e-04 eta: 3:27:06 time: 0.468466 data_time: 0.030165 memory: 15239 loss_kpt: 0.000493 acc_pose: 0.828891 loss: 0.000493 2022/09/16 04:43:41 - mmengine - INFO - Epoch(train) [163][200/586] lr: 5.000000e-04 eta: 3:26:44 time: 0.462522 data_time: 0.025918 memory: 15239 loss_kpt: 0.000511 acc_pose: 0.844411 loss: 0.000511 2022/09/16 04:44:04 - mmengine - INFO - Epoch(train) [163][250/586] lr: 5.000000e-04 eta: 3:26:22 time: 0.464183 data_time: 0.024408 memory: 15239 loss_kpt: 0.000483 acc_pose: 0.857102 loss: 0.000483 2022/09/16 04:44:27 - mmengine - INFO - Epoch(train) [163][300/586] lr: 5.000000e-04 eta: 3:26:01 time: 0.466753 data_time: 0.025555 memory: 15239 loss_kpt: 0.000491 acc_pose: 0.924461 loss: 0.000491 2022/09/16 04:44:51 - mmengine - INFO - Epoch(train) [163][350/586] lr: 5.000000e-04 eta: 3:25:39 time: 0.464711 data_time: 0.024445 memory: 15239 loss_kpt: 0.000497 acc_pose: 0.885891 loss: 0.000497 2022/09/16 04:45:14 - mmengine - INFO - Epoch(train) [163][400/586] lr: 5.000000e-04 eta: 3:25:17 time: 0.464515 data_time: 0.024842 memory: 15239 loss_kpt: 0.000500 acc_pose: 0.819230 loss: 0.000500 2022/09/16 04:45:37 - mmengine - INFO - Epoch(train) [163][450/586] lr: 5.000000e-04 eta: 3:24:55 time: 0.467517 data_time: 0.025078 memory: 15239 loss_kpt: 0.000512 acc_pose: 0.929327 loss: 0.000512 2022/09/16 04:46:01 - mmengine - INFO - Epoch(train) [163][500/586] lr: 5.000000e-04 eta: 3:24:33 time: 0.468892 data_time: 0.024581 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.855279 loss: 0.000509 2022/09/16 04:46:24 - mmengine - INFO - Epoch(train) [163][550/586] lr: 5.000000e-04 eta: 3:24:11 time: 0.470927 data_time: 0.023789 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.918286 loss: 0.000509 2022/09/16 04:46:41 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 04:46:41 - mmengine - INFO - Saving checkpoint at 163 epochs 2022/09/16 04:47:11 - mmengine - INFO - Epoch(train) [164][50/586] lr: 5.000000e-04 eta: 3:23:29 time: 0.470430 data_time: 0.031878 memory: 15239 loss_kpt: 0.000504 acc_pose: 0.879454 loss: 0.000504 2022/09/16 04:47:35 - mmengine - INFO - Epoch(train) [164][100/586] lr: 5.000000e-04 eta: 3:23:07 time: 0.476122 data_time: 0.030946 memory: 15239 loss_kpt: 0.000494 acc_pose: 0.911542 loss: 0.000494 2022/09/16 04:47:58 - mmengine - INFO - Epoch(train) [164][150/586] lr: 5.000000e-04 eta: 3:22:45 time: 0.461512 data_time: 0.029298 memory: 15239 loss_kpt: 0.000489 acc_pose: 0.875534 loss: 0.000489 2022/09/16 04:48:22 - mmengine - INFO - Epoch(train) [164][200/586] lr: 5.000000e-04 eta: 3:22:23 time: 0.469702 data_time: 0.032018 memory: 15239 loss_kpt: 0.000499 acc_pose: 0.917420 loss: 0.000499 2022/09/16 04:48:45 - mmengine - INFO - Epoch(train) [164][250/586] lr: 5.000000e-04 eta: 3:22:01 time: 0.462253 data_time: 0.026587 memory: 15239 loss_kpt: 0.000503 acc_pose: 0.893434 loss: 0.000503 2022/09/16 04:49:08 - mmengine - INFO - Epoch(train) [164][300/586] lr: 5.000000e-04 eta: 3:21:39 time: 0.460279 data_time: 0.024479 memory: 15239 loss_kpt: 0.000487 acc_pose: 0.882314 loss: 0.000487 2022/09/16 04:49:32 - mmengine - INFO - Epoch(train) [164][350/586] lr: 5.000000e-04 eta: 3:21:18 time: 0.475325 data_time: 0.030362 memory: 15239 loss_kpt: 0.000472 acc_pose: 0.894192 loss: 0.000472 2022/09/16 04:49:55 - mmengine - INFO - Epoch(train) [164][400/586] lr: 5.000000e-04 eta: 3:20:56 time: 0.463339 data_time: 0.025097 memory: 15239 loss_kpt: 0.000490 acc_pose: 0.860238 loss: 0.000490 2022/09/16 04:50:18 - mmengine - INFO - Epoch(train) [164][450/586] lr: 5.000000e-04 eta: 3:20:34 time: 0.462963 data_time: 0.024367 memory: 15239 loss_kpt: 0.000499 acc_pose: 0.860314 loss: 0.000499 2022/09/16 04:50:33 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 04:50:41 - mmengine - INFO - Epoch(train) [164][500/586] lr: 5.000000e-04 eta: 3:20:12 time: 0.466868 data_time: 0.025518 memory: 15239 loss_kpt: 0.000498 acc_pose: 0.854726 loss: 0.000498 2022/09/16 04:51:05 - mmengine - INFO - Epoch(train) [164][550/586] lr: 5.000000e-04 eta: 3:19:50 time: 0.465083 data_time: 0.025344 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.918257 loss: 0.000509 2022/09/16 04:51:21 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 04:51:21 - mmengine - INFO - Saving checkpoint at 164 epochs 2022/09/16 04:51:52 - mmengine - INFO - Epoch(train) [165][50/586] lr: 5.000000e-04 eta: 3:19:08 time: 0.480335 data_time: 0.029378 memory: 15239 loss_kpt: 0.000490 acc_pose: 0.857317 loss: 0.000490 2022/09/16 04:52:16 - mmengine - INFO - Epoch(train) [165][100/586] lr: 5.000000e-04 eta: 3:18:46 time: 0.468979 data_time: 0.024271 memory: 15239 loss_kpt: 0.000520 acc_pose: 0.842536 loss: 0.000520 2022/09/16 04:52:39 - mmengine - INFO - Epoch(train) [165][150/586] lr: 5.000000e-04 eta: 3:18:24 time: 0.469447 data_time: 0.024415 memory: 15239 loss_kpt: 0.000491 acc_pose: 0.922575 loss: 0.000491 2022/09/16 04:53:03 - mmengine - INFO - Epoch(train) [165][200/586] lr: 5.000000e-04 eta: 3:18:02 time: 0.477194 data_time: 0.024584 memory: 15239 loss_kpt: 0.000503 acc_pose: 0.836535 loss: 0.000503 2022/09/16 04:53:27 - mmengine - INFO - Epoch(train) [165][250/586] lr: 5.000000e-04 eta: 3:17:40 time: 0.469686 data_time: 0.024137 memory: 15239 loss_kpt: 0.000505 acc_pose: 0.873873 loss: 0.000505 2022/09/16 04:53:50 - mmengine - INFO - Epoch(train) [165][300/586] lr: 5.000000e-04 eta: 3:17:18 time: 0.469251 data_time: 0.029777 memory: 15239 loss_kpt: 0.000495 acc_pose: 0.849199 loss: 0.000495 2022/09/16 04:54:14 - mmengine - INFO - Epoch(train) [165][350/586] lr: 5.000000e-04 eta: 3:16:57 time: 0.473865 data_time: 0.024024 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.847286 loss: 0.000509 2022/09/16 04:54:37 - mmengine - INFO - Epoch(train) [165][400/586] lr: 5.000000e-04 eta: 3:16:35 time: 0.471752 data_time: 0.024390 memory: 15239 loss_kpt: 0.000498 acc_pose: 0.871903 loss: 0.000498 2022/09/16 04:55:00 - mmengine - INFO - Epoch(train) [165][450/586] lr: 5.000000e-04 eta: 3:16:13 time: 0.460562 data_time: 0.024872 memory: 15239 loss_kpt: 0.000496 acc_pose: 0.887078 loss: 0.000496 2022/09/16 04:55:24 - mmengine - INFO - Epoch(train) [165][500/586] lr: 5.000000e-04 eta: 3:15:51 time: 0.467389 data_time: 0.023804 memory: 15239 loss_kpt: 0.000498 acc_pose: 0.916131 loss: 0.000498 2022/09/16 04:55:47 - mmengine - INFO - Epoch(train) [165][550/586] lr: 5.000000e-04 eta: 3:15:29 time: 0.469149 data_time: 0.025833 memory: 15239 loss_kpt: 0.000483 acc_pose: 0.851761 loss: 0.000483 2022/09/16 04:56:04 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 04:56:04 - mmengine - INFO - Saving checkpoint at 165 epochs 2022/09/16 04:56:35 - mmengine - INFO - Epoch(train) [166][50/586] lr: 5.000000e-04 eta: 3:14:47 time: 0.483920 data_time: 0.033390 memory: 15239 loss_kpt: 0.000512 acc_pose: 0.869789 loss: 0.000512 2022/09/16 04:56:59 - mmengine - INFO - Epoch(train) [166][100/586] lr: 5.000000e-04 eta: 3:14:25 time: 0.472601 data_time: 0.031738 memory: 15239 loss_kpt: 0.000514 acc_pose: 0.863937 loss: 0.000514 2022/09/16 04:57:22 - mmengine - INFO - Epoch(train) [166][150/586] lr: 5.000000e-04 eta: 3:14:04 time: 0.476684 data_time: 0.025129 memory: 15239 loss_kpt: 0.000497 acc_pose: 0.931027 loss: 0.000497 2022/09/16 04:57:46 - mmengine - INFO - Epoch(train) [166][200/586] lr: 5.000000e-04 eta: 3:13:42 time: 0.468704 data_time: 0.024417 memory: 15239 loss_kpt: 0.000483 acc_pose: 0.883629 loss: 0.000483 2022/09/16 04:58:10 - mmengine - INFO - Epoch(train) [166][250/586] lr: 5.000000e-04 eta: 3:13:20 time: 0.479182 data_time: 0.029828 memory: 15239 loss_kpt: 0.000477 acc_pose: 0.861270 loss: 0.000477 2022/09/16 04:58:33 - mmengine - INFO - Epoch(train) [166][300/586] lr: 5.000000e-04 eta: 3:12:58 time: 0.465449 data_time: 0.025034 memory: 15239 loss_kpt: 0.000511 acc_pose: 0.851748 loss: 0.000511 2022/09/16 04:58:38 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 04:58:56 - mmengine - INFO - Epoch(train) [166][350/586] lr: 5.000000e-04 eta: 3:12:36 time: 0.467144 data_time: 0.025925 memory: 15239 loss_kpt: 0.000500 acc_pose: 0.896771 loss: 0.000500 2022/09/16 04:59:20 - mmengine - INFO - Epoch(train) [166][400/586] lr: 5.000000e-04 eta: 3:12:14 time: 0.466337 data_time: 0.024516 memory: 15239 loss_kpt: 0.000499 acc_pose: 0.844608 loss: 0.000499 2022/09/16 04:59:43 - mmengine - INFO - Epoch(train) [166][450/586] lr: 5.000000e-04 eta: 3:11:52 time: 0.466864 data_time: 0.024624 memory: 15239 loss_kpt: 0.000489 acc_pose: 0.831476 loss: 0.000489 2022/09/16 05:00:06 - mmengine - INFO - Epoch(train) [166][500/586] lr: 5.000000e-04 eta: 3:11:30 time: 0.464816 data_time: 0.024330 memory: 15239 loss_kpt: 0.000486 acc_pose: 0.847743 loss: 0.000486 2022/09/16 05:00:30 - mmengine - INFO - Epoch(train) [166][550/586] lr: 5.000000e-04 eta: 3:11:08 time: 0.468545 data_time: 0.029040 memory: 15239 loss_kpt: 0.000498 acc_pose: 0.893054 loss: 0.000498 2022/09/16 05:00:47 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 05:00:47 - mmengine - INFO - Saving checkpoint at 166 epochs 2022/09/16 05:01:18 - mmengine - INFO - Epoch(train) [167][50/586] lr: 5.000000e-04 eta: 3:10:27 time: 0.485894 data_time: 0.031823 memory: 15239 loss_kpt: 0.000494 acc_pose: 0.884796 loss: 0.000494 2022/09/16 05:01:42 - mmengine - INFO - Epoch(train) [167][100/586] lr: 5.000000e-04 eta: 3:10:05 time: 0.470520 data_time: 0.024609 memory: 15239 loss_kpt: 0.000491 acc_pose: 0.930302 loss: 0.000491 2022/09/16 05:02:05 - mmengine - INFO - Epoch(train) [167][150/586] lr: 5.000000e-04 eta: 3:09:43 time: 0.467713 data_time: 0.024977 memory: 15239 loss_kpt: 0.000485 acc_pose: 0.911445 loss: 0.000485 2022/09/16 05:02:29 - mmengine - INFO - Epoch(train) [167][200/586] lr: 5.000000e-04 eta: 3:09:21 time: 0.475387 data_time: 0.028750 memory: 15239 loss_kpt: 0.000498 acc_pose: 0.943897 loss: 0.000498 2022/09/16 05:02:52 - mmengine - INFO - Epoch(train) [167][250/586] lr: 5.000000e-04 eta: 3:08:59 time: 0.471061 data_time: 0.025178 memory: 15239 loss_kpt: 0.000490 acc_pose: 0.837904 loss: 0.000490 2022/09/16 05:03:16 - mmengine - INFO - Epoch(train) [167][300/586] lr: 5.000000e-04 eta: 3:08:37 time: 0.466632 data_time: 0.023977 memory: 15239 loss_kpt: 0.000507 acc_pose: 0.838225 loss: 0.000507 2022/09/16 05:03:39 - mmengine - INFO - Epoch(train) [167][350/586] lr: 5.000000e-04 eta: 3:08:15 time: 0.471464 data_time: 0.024952 memory: 15239 loss_kpt: 0.000492 acc_pose: 0.892836 loss: 0.000492 2022/09/16 05:04:03 - mmengine - INFO - Epoch(train) [167][400/586] lr: 5.000000e-04 eta: 3:07:54 time: 0.473402 data_time: 0.024428 memory: 15239 loss_kpt: 0.000494 acc_pose: 0.914087 loss: 0.000494 2022/09/16 05:04:26 - mmengine - INFO - Epoch(train) [167][450/586] lr: 5.000000e-04 eta: 3:07:32 time: 0.464103 data_time: 0.025288 memory: 15239 loss_kpt: 0.000489 acc_pose: 0.859931 loss: 0.000489 2022/09/16 05:04:50 - mmengine - INFO - Epoch(train) [167][500/586] lr: 5.000000e-04 eta: 3:07:10 time: 0.473237 data_time: 0.028069 memory: 15239 loss_kpt: 0.000491 acc_pose: 0.864536 loss: 0.000491 2022/09/16 05:05:13 - mmengine - INFO - Epoch(train) [167][550/586] lr: 5.000000e-04 eta: 3:06:48 time: 0.469457 data_time: 0.024382 memory: 15239 loss_kpt: 0.000477 acc_pose: 0.906512 loss: 0.000477 2022/09/16 05:05:30 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 05:05:30 - mmengine - INFO - Saving checkpoint at 167 epochs 2022/09/16 05:06:01 - mmengine - INFO - Epoch(train) [168][50/586] lr: 5.000000e-04 eta: 3:06:06 time: 0.472219 data_time: 0.029145 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.845130 loss: 0.000508 2022/09/16 05:06:25 - mmengine - INFO - Epoch(train) [168][100/586] lr: 5.000000e-04 eta: 3:05:44 time: 0.473310 data_time: 0.029595 memory: 15239 loss_kpt: 0.000502 acc_pose: 0.872250 loss: 0.000502 2022/09/16 05:06:43 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 05:06:49 - mmengine - INFO - Epoch(train) [168][150/586] lr: 5.000000e-04 eta: 3:05:22 time: 0.475763 data_time: 0.024656 memory: 15239 loss_kpt: 0.000479 acc_pose: 0.906526 loss: 0.000479 2022/09/16 05:07:12 - mmengine - INFO - Epoch(train) [168][200/586] lr: 5.000000e-04 eta: 3:05:01 time: 0.469179 data_time: 0.024629 memory: 15239 loss_kpt: 0.000479 acc_pose: 0.899960 loss: 0.000479 2022/09/16 05:07:36 - mmengine - INFO - Epoch(train) [168][250/586] lr: 5.000000e-04 eta: 3:04:39 time: 0.468619 data_time: 0.027899 memory: 15239 loss_kpt: 0.000506 acc_pose: 0.904236 loss: 0.000506 2022/09/16 05:07:59 - mmengine - INFO - Epoch(train) [168][300/586] lr: 5.000000e-04 eta: 3:04:17 time: 0.468064 data_time: 0.024921 memory: 15239 loss_kpt: 0.000504 acc_pose: 0.881776 loss: 0.000504 2022/09/16 05:08:22 - mmengine - INFO - Epoch(train) [168][350/586] lr: 5.000000e-04 eta: 3:03:55 time: 0.468038 data_time: 0.024728 memory: 15239 loss_kpt: 0.000517 acc_pose: 0.867401 loss: 0.000517 2022/09/16 05:08:46 - mmengine - INFO - Epoch(train) [168][400/586] lr: 5.000000e-04 eta: 3:03:33 time: 0.467698 data_time: 0.025527 memory: 15239 loss_kpt: 0.000504 acc_pose: 0.914781 loss: 0.000504 2022/09/16 05:09:10 - mmengine - INFO - Epoch(train) [168][450/586] lr: 5.000000e-04 eta: 3:03:11 time: 0.476578 data_time: 0.024512 memory: 15239 loss_kpt: 0.000491 acc_pose: 0.877887 loss: 0.000491 2022/09/16 05:09:33 - mmengine - INFO - Epoch(train) [168][500/586] lr: 5.000000e-04 eta: 3:02:49 time: 0.459401 data_time: 0.025585 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.871968 loss: 0.000508 2022/09/16 05:09:56 - mmengine - INFO - Epoch(train) [168][550/586] lr: 5.000000e-04 eta: 3:02:27 time: 0.466393 data_time: 0.028313 memory: 15239 loss_kpt: 0.000506 acc_pose: 0.848542 loss: 0.000506 2022/09/16 05:10:13 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 05:10:13 - mmengine - INFO - Saving checkpoint at 168 epochs 2022/09/16 05:10:44 - mmengine - INFO - Epoch(train) [169][50/586] lr: 5.000000e-04 eta: 3:01:45 time: 0.472193 data_time: 0.034625 memory: 15239 loss_kpt: 0.000495 acc_pose: 0.898856 loss: 0.000495 2022/09/16 05:11:07 - mmengine - INFO - Epoch(train) [169][100/586] lr: 5.000000e-04 eta: 3:01:23 time: 0.471351 data_time: 0.028238 memory: 15239 loss_kpt: 0.000479 acc_pose: 0.873348 loss: 0.000479 2022/09/16 05:11:31 - mmengine - INFO - Epoch(train) [169][150/586] lr: 5.000000e-04 eta: 3:01:02 time: 0.476705 data_time: 0.030715 memory: 15239 loss_kpt: 0.000507 acc_pose: 0.898391 loss: 0.000507 2022/09/16 05:11:54 - mmengine - INFO - Epoch(train) [169][200/586] lr: 5.000000e-04 eta: 3:00:40 time: 0.460858 data_time: 0.030618 memory: 15239 loss_kpt: 0.000490 acc_pose: 0.828715 loss: 0.000490 2022/09/16 05:12:18 - mmengine - INFO - Epoch(train) [169][250/586] lr: 5.000000e-04 eta: 3:00:18 time: 0.468553 data_time: 0.024967 memory: 15239 loss_kpt: 0.000500 acc_pose: 0.901094 loss: 0.000500 2022/09/16 05:12:41 - mmengine - INFO - Epoch(train) [169][300/586] lr: 5.000000e-04 eta: 2:59:56 time: 0.468115 data_time: 0.024527 memory: 15239 loss_kpt: 0.000507 acc_pose: 0.890360 loss: 0.000507 2022/09/16 05:13:05 - mmengine - INFO - Epoch(train) [169][350/586] lr: 5.000000e-04 eta: 2:59:34 time: 0.468377 data_time: 0.026187 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.877548 loss: 0.000508 2022/09/16 05:13:28 - mmengine - INFO - Epoch(train) [169][400/586] lr: 5.000000e-04 eta: 2:59:12 time: 0.464746 data_time: 0.024110 memory: 15239 loss_kpt: 0.000489 acc_pose: 0.869316 loss: 0.000489 2022/09/16 05:13:51 - mmengine - INFO - Epoch(train) [169][450/586] lr: 5.000000e-04 eta: 2:58:50 time: 0.468226 data_time: 0.024492 memory: 15239 loss_kpt: 0.000498 acc_pose: 0.853180 loss: 0.000498 2022/09/16 05:14:15 - mmengine - INFO - Epoch(train) [169][500/586] lr: 5.000000e-04 eta: 2:58:28 time: 0.476657 data_time: 0.025783 memory: 15239 loss_kpt: 0.000487 acc_pose: 0.883409 loss: 0.000487 2022/09/16 05:14:38 - mmengine - INFO - Epoch(train) [169][550/586] lr: 5.000000e-04 eta: 2:58:06 time: 0.464575 data_time: 0.025662 memory: 15239 loss_kpt: 0.000497 acc_pose: 0.885069 loss: 0.000497 2022/09/16 05:14:39 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 05:14:55 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 05:14:55 - mmengine - INFO - Saving checkpoint at 169 epochs 2022/09/16 05:15:27 - mmengine - INFO - Epoch(train) [170][50/586] lr: 5.000000e-04 eta: 2:57:25 time: 0.482482 data_time: 0.029040 memory: 15239 loss_kpt: 0.000488 acc_pose: 0.921539 loss: 0.000488 2022/09/16 05:15:50 - mmengine - INFO - Epoch(train) [170][100/586] lr: 5.000000e-04 eta: 2:57:03 time: 0.463643 data_time: 0.025037 memory: 15239 loss_kpt: 0.000501 acc_pose: 0.823712 loss: 0.000501 2022/09/16 05:16:14 - mmengine - INFO - Epoch(train) [170][150/586] lr: 5.000000e-04 eta: 2:56:41 time: 0.469972 data_time: 0.024078 memory: 15239 loss_kpt: 0.000499 acc_pose: 0.843738 loss: 0.000499 2022/09/16 05:16:37 - mmengine - INFO - Epoch(train) [170][200/586] lr: 5.000000e-04 eta: 2:56:19 time: 0.465146 data_time: 0.024879 memory: 15239 loss_kpt: 0.000496 acc_pose: 0.851945 loss: 0.000496 2022/09/16 05:17:00 - mmengine - INFO - Epoch(train) [170][250/586] lr: 5.000000e-04 eta: 2:55:57 time: 0.472435 data_time: 0.027417 memory: 15239 loss_kpt: 0.000488 acc_pose: 0.893847 loss: 0.000488 2022/09/16 05:17:24 - mmengine - INFO - Epoch(train) [170][300/586] lr: 5.000000e-04 eta: 2:55:35 time: 0.470629 data_time: 0.024221 memory: 15239 loss_kpt: 0.000497 acc_pose: 0.878882 loss: 0.000497 2022/09/16 05:17:48 - mmengine - INFO - Epoch(train) [170][350/586] lr: 5.000000e-04 eta: 2:55:13 time: 0.471722 data_time: 0.025893 memory: 15239 loss_kpt: 0.000497 acc_pose: 0.866720 loss: 0.000497 2022/09/16 05:18:11 - mmengine - INFO - Epoch(train) [170][400/586] lr: 5.000000e-04 eta: 2:54:51 time: 0.474449 data_time: 0.024005 memory: 15239 loss_kpt: 0.000507 acc_pose: 0.886999 loss: 0.000507 2022/09/16 05:18:35 - mmengine - INFO - Epoch(train) [170][450/586] lr: 5.000000e-04 eta: 2:54:30 time: 0.475059 data_time: 0.024209 memory: 15239 loss_kpt: 0.000478 acc_pose: 0.865795 loss: 0.000478 2022/09/16 05:18:58 - mmengine - INFO - Epoch(train) [170][500/586] lr: 5.000000e-04 eta: 2:54:08 time: 0.456899 data_time: 0.024226 memory: 15239 loss_kpt: 0.000495 acc_pose: 0.882619 loss: 0.000495 2022/09/16 05:19:22 - mmengine - INFO - Epoch(train) [170][550/586] lr: 5.000000e-04 eta: 2:53:46 time: 0.472153 data_time: 0.028546 memory: 15239 loss_kpt: 0.000504 acc_pose: 0.865641 loss: 0.000504 2022/09/16 05:19:38 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 05:19:38 - mmengine - INFO - Saving checkpoint at 170 epochs 2022/09/16 05:19:59 - mmengine - INFO - Epoch(val) [170][50/407] eta: 0:01:31 time: 0.257401 data_time: 0.013633 memory: 15239 2022/09/16 05:20:11 - mmengine - INFO - Epoch(val) [170][100/407] eta: 0:01:17 time: 0.253074 data_time: 0.009029 memory: 2064 2022/09/16 05:20:24 - mmengine - INFO - Epoch(val) [170][150/407] eta: 0:01:04 time: 0.250015 data_time: 0.008568 memory: 2064 2022/09/16 05:20:36 - mmengine - INFO - Epoch(val) [170][200/407] eta: 0:00:51 time: 0.251200 data_time: 0.008618 memory: 2064 2022/09/16 05:20:49 - mmengine - INFO - Epoch(val) [170][250/407] eta: 0:00:39 time: 0.254078 data_time: 0.008764 memory: 2064 2022/09/16 05:21:02 - mmengine - INFO - Epoch(val) [170][300/407] eta: 0:00:26 time: 0.251000 data_time: 0.008738 memory: 2064 2022/09/16 05:21:14 - mmengine - INFO - Epoch(val) [170][350/407] eta: 0:00:14 time: 0.251014 data_time: 0.008590 memory: 2064 2022/09/16 05:21:27 - mmengine - INFO - Epoch(val) [170][400/407] eta: 0:00:01 time: 0.252631 data_time: 0.008526 memory: 2064 2022/09/16 05:22:02 - mmengine - INFO - Evaluating CocoMetric... 2022/09/16 05:22:15 - mmengine - INFO - Epoch(val) [170][407/407] coco/AP: 0.765916 coco/AP .5: 0.908017 coco/AP .75: 0.828447 coco/AP (M): 0.726687 coco/AP (L): 0.837170 coco/AR: 0.814090 coco/AR .5: 0.943010 coco/AR .75: 0.870907 coco/AR (M): 0.771128 coco/AR (L): 0.876960 2022/09/16 05:22:15 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220915/dark_w48_384/best_coco/AP_epoch_160.pth is removed 2022/09/16 05:22:19 - mmengine - INFO - The best checkpoint with 0.7659 coco/AP at 170 epoch is saved to best_coco/AP_epoch_170.pth. 2022/09/16 05:22:43 - mmengine - INFO - Epoch(train) [171][50/586] lr: 5.000000e-05 eta: 2:53:04 time: 0.485929 data_time: 0.035696 memory: 15239 loss_kpt: 0.000478 acc_pose: 0.902673 loss: 0.000478 2022/09/16 05:23:07 - mmengine - INFO - Epoch(train) [171][100/586] lr: 5.000000e-05 eta: 2:52:42 time: 0.465790 data_time: 0.027948 memory: 15239 loss_kpt: 0.000469 acc_pose: 0.867926 loss: 0.000469 2022/09/16 05:23:30 - mmengine - INFO - Epoch(train) [171][150/586] lr: 5.000000e-05 eta: 2:52:20 time: 0.465219 data_time: 0.028538 memory: 15239 loss_kpt: 0.000482 acc_pose: 0.827716 loss: 0.000482 2022/09/16 05:23:53 - mmengine - INFO - Epoch(train) [171][200/586] lr: 5.000000e-05 eta: 2:51:58 time: 0.462946 data_time: 0.028226 memory: 15239 loss_kpt: 0.000482 acc_pose: 0.883699 loss: 0.000482 2022/09/16 05:24:17 - mmengine - INFO - Epoch(train) [171][250/586] lr: 5.000000e-05 eta: 2:51:36 time: 0.468418 data_time: 0.026908 memory: 15239 loss_kpt: 0.000473 acc_pose: 0.858140 loss: 0.000473 2022/09/16 05:24:40 - mmengine - INFO - Epoch(train) [171][300/586] lr: 5.000000e-05 eta: 2:51:15 time: 0.473153 data_time: 0.024746 memory: 15239 loss_kpt: 0.000469 acc_pose: 0.891136 loss: 0.000469 2022/09/16 05:25:03 - mmengine - INFO - Epoch(train) [171][350/586] lr: 5.000000e-05 eta: 2:50:53 time: 0.455661 data_time: 0.024216 memory: 15239 loss_kpt: 0.000460 acc_pose: 0.881981 loss: 0.000460 2022/09/16 05:25:17 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 05:25:27 - mmengine - INFO - Epoch(train) [171][400/586] lr: 5.000000e-05 eta: 2:50:31 time: 0.475245 data_time: 0.024392 memory: 15239 loss_kpt: 0.000474 acc_pose: 0.870368 loss: 0.000474 2022/09/16 05:25:50 - mmengine - INFO - Epoch(train) [171][450/586] lr: 5.000000e-05 eta: 2:50:09 time: 0.465418 data_time: 0.027283 memory: 15239 loss_kpt: 0.000481 acc_pose: 0.866905 loss: 0.000481 2022/09/16 05:26:13 - mmengine - INFO - Epoch(train) [171][500/586] lr: 5.000000e-05 eta: 2:49:47 time: 0.458155 data_time: 0.023779 memory: 15239 loss_kpt: 0.000474 acc_pose: 0.821664 loss: 0.000474 2022/09/16 05:26:36 - mmengine - INFO - Epoch(train) [171][550/586] lr: 5.000000e-05 eta: 2:49:25 time: 0.466363 data_time: 0.023973 memory: 15239 loss_kpt: 0.000470 acc_pose: 0.871877 loss: 0.000470 2022/09/16 05:26:53 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 05:26:53 - mmengine - INFO - Saving checkpoint at 171 epochs 2022/09/16 05:27:24 - mmengine - INFO - Epoch(train) [172][50/586] lr: 5.000000e-05 eta: 2:48:43 time: 0.479614 data_time: 0.034835 memory: 15239 loss_kpt: 0.000480 acc_pose: 0.879714 loss: 0.000480 2022/09/16 05:27:49 - mmengine - INFO - Epoch(train) [172][100/586] lr: 5.000000e-05 eta: 2:48:22 time: 0.483227 data_time: 0.024549 memory: 15239 loss_kpt: 0.000472 acc_pose: 0.834182 loss: 0.000472 2022/09/16 05:28:12 - mmengine - INFO - Epoch(train) [172][150/586] lr: 5.000000e-05 eta: 2:48:00 time: 0.462312 data_time: 0.024320 memory: 15239 loss_kpt: 0.000469 acc_pose: 0.887305 loss: 0.000469 2022/09/16 05:28:35 - mmengine - INFO - Epoch(train) [172][200/586] lr: 5.000000e-05 eta: 2:47:38 time: 0.465512 data_time: 0.023423 memory: 15239 loss_kpt: 0.000486 acc_pose: 0.905800 loss: 0.000486 2022/09/16 05:28:59 - mmengine - INFO - Epoch(train) [172][250/586] lr: 5.000000e-05 eta: 2:47:16 time: 0.474359 data_time: 0.027568 memory: 15239 loss_kpt: 0.000477 acc_pose: 0.920521 loss: 0.000477 2022/09/16 05:29:22 - mmengine - INFO - Epoch(train) [172][300/586] lr: 5.000000e-05 eta: 2:46:54 time: 0.464386 data_time: 0.025374 memory: 15239 loss_kpt: 0.000488 acc_pose: 0.917021 loss: 0.000488 2022/09/16 05:29:46 - mmengine - INFO - Epoch(train) [172][350/586] lr: 5.000000e-05 eta: 2:46:32 time: 0.473763 data_time: 0.024116 memory: 15239 loss_kpt: 0.000476 acc_pose: 0.874175 loss: 0.000476 2022/09/16 05:30:09 - mmengine - INFO - Epoch(train) [172][400/586] lr: 5.000000e-05 eta: 2:46:10 time: 0.472669 data_time: 0.024202 memory: 15239 loss_kpt: 0.000474 acc_pose: 0.879367 loss: 0.000474 2022/09/16 05:30:33 - mmengine - INFO - Epoch(train) [172][450/586] lr: 5.000000e-05 eta: 2:45:48 time: 0.476017 data_time: 0.027065 memory: 15239 loss_kpt: 0.000470 acc_pose: 0.866983 loss: 0.000470 2022/09/16 05:30:56 - mmengine - INFO - Epoch(train) [172][500/586] lr: 5.000000e-05 eta: 2:45:26 time: 0.466090 data_time: 0.025061 memory: 15239 loss_kpt: 0.000456 acc_pose: 0.929690 loss: 0.000456 2022/09/16 05:31:20 - mmengine - INFO - Epoch(train) [172][550/586] lr: 5.000000e-05 eta: 2:45:04 time: 0.465952 data_time: 0.023881 memory: 15239 loss_kpt: 0.000480 acc_pose: 0.860987 loss: 0.000480 2022/09/16 05:31:37 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 05:31:37 - mmengine - INFO - Saving checkpoint at 172 epochs 2022/09/16 05:32:07 - mmengine - INFO - Epoch(train) [173][50/586] lr: 5.000000e-05 eta: 2:44:23 time: 0.471006 data_time: 0.035747 memory: 15239 loss_kpt: 0.000479 acc_pose: 0.890453 loss: 0.000479 2022/09/16 05:32:31 - mmengine - INFO - Epoch(train) [173][100/586] lr: 5.000000e-05 eta: 2:44:01 time: 0.471460 data_time: 0.024384 memory: 15239 loss_kpt: 0.000478 acc_pose: 0.878893 loss: 0.000478 2022/09/16 05:32:54 - mmengine - INFO - Epoch(train) [173][150/586] lr: 5.000000e-05 eta: 2:43:39 time: 0.475784 data_time: 0.024990 memory: 15239 loss_kpt: 0.000482 acc_pose: 0.894597 loss: 0.000482 2022/09/16 05:33:18 - mmengine - INFO - Epoch(train) [173][200/586] lr: 5.000000e-05 eta: 2:43:17 time: 0.473121 data_time: 0.024602 memory: 15239 loss_kpt: 0.000470 acc_pose: 0.845542 loss: 0.000470 2022/09/16 05:33:22 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 05:33:42 - mmengine - INFO - Epoch(train) [173][250/586] lr: 5.000000e-05 eta: 2:42:55 time: 0.470052 data_time: 0.025582 memory: 15239 loss_kpt: 0.000469 acc_pose: 0.821081 loss: 0.000469 2022/09/16 05:34:05 - mmengine - INFO - Epoch(train) [173][300/586] lr: 5.000000e-05 eta: 2:42:33 time: 0.468634 data_time: 0.024404 memory: 15239 loss_kpt: 0.000467 acc_pose: 0.873071 loss: 0.000467 2022/09/16 05:34:29 - mmengine - INFO - Epoch(train) [173][350/586] lr: 5.000000e-05 eta: 2:42:12 time: 0.476934 data_time: 0.024087 memory: 15239 loss_kpt: 0.000465 acc_pose: 0.851475 loss: 0.000465 2022/09/16 05:34:52 - mmengine - INFO - Epoch(train) [173][400/586] lr: 5.000000e-05 eta: 2:41:50 time: 0.466528 data_time: 0.024885 memory: 15239 loss_kpt: 0.000473 acc_pose: 0.884092 loss: 0.000473 2022/09/16 05:35:16 - mmengine - INFO - Epoch(train) [173][450/586] lr: 5.000000e-05 eta: 2:41:28 time: 0.464925 data_time: 0.023650 memory: 15239 loss_kpt: 0.000466 acc_pose: 0.864269 loss: 0.000466 2022/09/16 05:35:39 - mmengine - INFO - Epoch(train) [173][500/586] lr: 5.000000e-05 eta: 2:41:06 time: 0.478124 data_time: 0.029882 memory: 15239 loss_kpt: 0.000489 acc_pose: 0.847528 loss: 0.000489 2022/09/16 05:36:02 - mmengine - INFO - Epoch(train) [173][550/586] lr: 5.000000e-05 eta: 2:40:44 time: 0.457404 data_time: 0.023649 memory: 15239 loss_kpt: 0.000469 acc_pose: 0.859640 loss: 0.000469 2022/09/16 05:36:19 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 05:36:19 - mmengine - INFO - Saving checkpoint at 173 epochs 2022/09/16 05:36:50 - mmengine - INFO - Epoch(train) [174][50/586] lr: 5.000000e-05 eta: 2:40:02 time: 0.473061 data_time: 0.033368 memory: 15239 loss_kpt: 0.000468 acc_pose: 0.866713 loss: 0.000468 2022/09/16 05:37:14 - mmengine - INFO - Epoch(train) [174][100/586] lr: 5.000000e-05 eta: 2:39:40 time: 0.465656 data_time: 0.028922 memory: 15239 loss_kpt: 0.000457 acc_pose: 0.873936 loss: 0.000457 2022/09/16 05:37:38 - mmengine - INFO - Epoch(train) [174][150/586] lr: 5.000000e-05 eta: 2:39:19 time: 0.476105 data_time: 0.032189 memory: 15239 loss_kpt: 0.000477 acc_pose: 0.908575 loss: 0.000477 2022/09/16 05:38:01 - mmengine - INFO - Epoch(train) [174][200/586] lr: 5.000000e-05 eta: 2:38:57 time: 0.463606 data_time: 0.029468 memory: 15239 loss_kpt: 0.000466 acc_pose: 0.825991 loss: 0.000466 2022/09/16 05:38:24 - mmengine - INFO - Epoch(train) [174][250/586] lr: 5.000000e-05 eta: 2:38:35 time: 0.465240 data_time: 0.027802 memory: 15239 loss_kpt: 0.000464 acc_pose: 0.875843 loss: 0.000464 2022/09/16 05:38:47 - mmengine - INFO - Epoch(train) [174][300/586] lr: 5.000000e-05 eta: 2:38:13 time: 0.462740 data_time: 0.027692 memory: 15239 loss_kpt: 0.000454 acc_pose: 0.895810 loss: 0.000454 2022/09/16 05:39:11 - mmengine - INFO - Epoch(train) [174][350/586] lr: 5.000000e-05 eta: 2:37:51 time: 0.471553 data_time: 0.028785 memory: 15239 loss_kpt: 0.000465 acc_pose: 0.922601 loss: 0.000465 2022/09/16 05:39:34 - mmengine - INFO - Epoch(train) [174][400/586] lr: 5.000000e-05 eta: 2:37:29 time: 0.456983 data_time: 0.025208 memory: 15239 loss_kpt: 0.000484 acc_pose: 0.911115 loss: 0.000484 2022/09/16 05:39:57 - mmengine - INFO - Epoch(train) [174][450/586] lr: 5.000000e-05 eta: 2:37:07 time: 0.470791 data_time: 0.024028 memory: 15239 loss_kpt: 0.000476 acc_pose: 0.921594 loss: 0.000476 2022/09/16 05:40:20 - mmengine - INFO - Epoch(train) [174][500/586] lr: 5.000000e-05 eta: 2:36:45 time: 0.464895 data_time: 0.024639 memory: 15239 loss_kpt: 0.000457 acc_pose: 0.868596 loss: 0.000457 2022/09/16 05:40:43 - mmengine - INFO - Epoch(train) [174][550/586] lr: 5.000000e-05 eta: 2:36:23 time: 0.459902 data_time: 0.023581 memory: 15239 loss_kpt: 0.000465 acc_pose: 0.903554 loss: 0.000465 2022/09/16 05:41:00 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 05:41:00 - mmengine - INFO - Saving checkpoint at 174 epochs 2022/09/16 05:41:25 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 05:41:32 - mmengine - INFO - Epoch(train) [175][50/586] lr: 5.000000e-05 eta: 2:35:42 time: 0.484135 data_time: 0.034594 memory: 15239 loss_kpt: 0.000464 acc_pose: 0.904565 loss: 0.000464 2022/09/16 05:41:55 - mmengine - INFO - Epoch(train) [175][100/586] lr: 5.000000e-05 eta: 2:35:20 time: 0.468345 data_time: 0.024454 memory: 15239 loss_kpt: 0.000467 acc_pose: 0.845610 loss: 0.000467 2022/09/16 05:42:19 - mmengine - INFO - Epoch(train) [175][150/586] lr: 5.000000e-05 eta: 2:34:58 time: 0.471162 data_time: 0.028350 memory: 15239 loss_kpt: 0.000479 acc_pose: 0.830578 loss: 0.000479 2022/09/16 05:42:42 - mmengine - INFO - Epoch(train) [175][200/586] lr: 5.000000e-05 eta: 2:34:36 time: 0.469732 data_time: 0.024192 memory: 15239 loss_kpt: 0.000453 acc_pose: 0.882896 loss: 0.000453 2022/09/16 05:43:06 - mmengine - INFO - Epoch(train) [175][250/586] lr: 5.000000e-05 eta: 2:34:14 time: 0.470748 data_time: 0.024909 memory: 15239 loss_kpt: 0.000469 acc_pose: 0.840730 loss: 0.000469 2022/09/16 05:43:29 - mmengine - INFO - Epoch(train) [175][300/586] lr: 5.000000e-05 eta: 2:33:52 time: 0.470441 data_time: 0.024771 memory: 15239 loss_kpt: 0.000470 acc_pose: 0.905819 loss: 0.000470 2022/09/16 05:43:53 - mmengine - INFO - Epoch(train) [175][350/586] lr: 5.000000e-05 eta: 2:33:30 time: 0.480391 data_time: 0.024720 memory: 15239 loss_kpt: 0.000472 acc_pose: 0.906637 loss: 0.000472 2022/09/16 05:44:16 - mmengine - INFO - Epoch(train) [175][400/586] lr: 5.000000e-05 eta: 2:33:08 time: 0.465403 data_time: 0.024283 memory: 15239 loss_kpt: 0.000478 acc_pose: 0.885829 loss: 0.000478 2022/09/16 05:44:41 - mmengine - INFO - Epoch(train) [175][450/586] lr: 5.000000e-05 eta: 2:32:46 time: 0.485846 data_time: 0.028117 memory: 15239 loss_kpt: 0.000453 acc_pose: 0.880889 loss: 0.000453 2022/09/16 05:45:04 - mmengine - INFO - Epoch(train) [175][500/586] lr: 5.000000e-05 eta: 2:32:24 time: 0.467802 data_time: 0.024622 memory: 15239 loss_kpt: 0.000460 acc_pose: 0.865854 loss: 0.000460 2022/09/16 05:45:27 - mmengine - INFO - Epoch(train) [175][550/586] lr: 5.000000e-05 eta: 2:32:02 time: 0.459671 data_time: 0.023504 memory: 15239 loss_kpt: 0.000444 acc_pose: 0.871552 loss: 0.000444 2022/09/16 05:45:44 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 05:45:44 - mmengine - INFO - Saving checkpoint at 175 epochs 2022/09/16 05:46:15 - mmengine - INFO - Epoch(train) [176][50/586] lr: 5.000000e-05 eta: 2:31:21 time: 0.476755 data_time: 0.029386 memory: 15239 loss_kpt: 0.000451 acc_pose: 0.834717 loss: 0.000451 2022/09/16 05:46:38 - mmengine - INFO - Epoch(train) [176][100/586] lr: 5.000000e-05 eta: 2:30:59 time: 0.463868 data_time: 0.025161 memory: 15239 loss_kpt: 0.000467 acc_pose: 0.848625 loss: 0.000467 2022/09/16 05:47:02 - mmengine - INFO - Epoch(train) [176][150/586] lr: 5.000000e-05 eta: 2:30:37 time: 0.473618 data_time: 0.024107 memory: 15239 loss_kpt: 0.000459 acc_pose: 0.868899 loss: 0.000459 2022/09/16 05:47:25 - mmengine - INFO - Epoch(train) [176][200/586] lr: 5.000000e-05 eta: 2:30:15 time: 0.461074 data_time: 0.024857 memory: 15239 loss_kpt: 0.000460 acc_pose: 0.897690 loss: 0.000460 2022/09/16 05:47:48 - mmengine - INFO - Epoch(train) [176][250/586] lr: 5.000000e-05 eta: 2:29:53 time: 0.467081 data_time: 0.023641 memory: 15239 loss_kpt: 0.000454 acc_pose: 0.921393 loss: 0.000454 2022/09/16 05:48:11 - mmengine - INFO - Epoch(train) [176][300/586] lr: 5.000000e-05 eta: 2:29:32 time: 0.467107 data_time: 0.024093 memory: 15239 loss_kpt: 0.000464 acc_pose: 0.801109 loss: 0.000464 2022/09/16 05:48:34 - mmengine - INFO - Epoch(train) [176][350/586] lr: 5.000000e-05 eta: 2:29:09 time: 0.459860 data_time: 0.024991 memory: 15239 loss_kpt: 0.000470 acc_pose: 0.851722 loss: 0.000470 2022/09/16 05:48:58 - mmengine - INFO - Epoch(train) [176][400/586] lr: 5.000000e-05 eta: 2:28:48 time: 0.468507 data_time: 0.028058 memory: 15239 loss_kpt: 0.000478 acc_pose: 0.870978 loss: 0.000478 2022/09/16 05:49:21 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 05:49:21 - mmengine - INFO - Epoch(train) [176][450/586] lr: 5.000000e-05 eta: 2:28:26 time: 0.466900 data_time: 0.024338 memory: 15239 loss_kpt: 0.000467 acc_pose: 0.900780 loss: 0.000467 2022/09/16 05:49:44 - mmengine - INFO - Epoch(train) [176][500/586] lr: 5.000000e-05 eta: 2:28:04 time: 0.464243 data_time: 0.024505 memory: 15239 loss_kpt: 0.000466 acc_pose: 0.933511 loss: 0.000466 2022/09/16 05:50:07 - mmengine - INFO - Epoch(train) [176][550/586] lr: 5.000000e-05 eta: 2:27:41 time: 0.458367 data_time: 0.023819 memory: 15239 loss_kpt: 0.000477 acc_pose: 0.857445 loss: 0.000477 2022/09/16 05:50:24 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 05:50:24 - mmengine - INFO - Saving checkpoint at 176 epochs 2022/09/16 05:50:55 - mmengine - INFO - Epoch(train) [177][50/586] lr: 5.000000e-05 eta: 2:27:01 time: 0.484798 data_time: 0.039808 memory: 15239 loss_kpt: 0.000447 acc_pose: 0.883653 loss: 0.000447 2022/09/16 05:51:19 - mmengine - INFO - Epoch(train) [177][100/586] lr: 5.000000e-05 eta: 2:26:39 time: 0.467131 data_time: 0.027572 memory: 15239 loss_kpt: 0.000458 acc_pose: 0.826781 loss: 0.000458 2022/09/16 05:51:43 - mmengine - INFO - Epoch(train) [177][150/586] lr: 5.000000e-05 eta: 2:26:17 time: 0.476023 data_time: 0.027117 memory: 15239 loss_kpt: 0.000471 acc_pose: 0.851928 loss: 0.000471 2022/09/16 05:52:06 - mmengine - INFO - Epoch(train) [177][200/586] lr: 5.000000e-05 eta: 2:25:55 time: 0.462868 data_time: 0.026980 memory: 15239 loss_kpt: 0.000462 acc_pose: 0.896537 loss: 0.000462 2022/09/16 05:52:30 - mmengine - INFO - Epoch(train) [177][250/586] lr: 5.000000e-05 eta: 2:25:33 time: 0.476665 data_time: 0.026835 memory: 15239 loss_kpt: 0.000444 acc_pose: 0.867827 loss: 0.000444 2022/09/16 05:52:53 - mmengine - INFO - Epoch(train) [177][300/586] lr: 5.000000e-05 eta: 2:25:11 time: 0.463974 data_time: 0.026796 memory: 15239 loss_kpt: 0.000460 acc_pose: 0.793036 loss: 0.000460 2022/09/16 05:53:16 - mmengine - INFO - Epoch(train) [177][350/586] lr: 5.000000e-05 eta: 2:24:49 time: 0.468544 data_time: 0.024654 memory: 15239 loss_kpt: 0.000485 acc_pose: 0.840323 loss: 0.000485 2022/09/16 05:53:40 - mmengine - INFO - Epoch(train) [177][400/586] lr: 5.000000e-05 eta: 2:24:27 time: 0.473234 data_time: 0.027549 memory: 15239 loss_kpt: 0.000469 acc_pose: 0.842633 loss: 0.000469 2022/09/16 05:54:03 - mmengine - INFO - Epoch(train) [177][450/586] lr: 5.000000e-05 eta: 2:24:05 time: 0.462076 data_time: 0.024280 memory: 15239 loss_kpt: 0.000469 acc_pose: 0.895970 loss: 0.000469 2022/09/16 05:54:26 - mmengine - INFO - Epoch(train) [177][500/586] lr: 5.000000e-05 eta: 2:23:43 time: 0.463483 data_time: 0.024480 memory: 15239 loss_kpt: 0.000458 acc_pose: 0.908663 loss: 0.000458 2022/09/16 05:54:50 - mmengine - INFO - Epoch(train) [177][550/586] lr: 5.000000e-05 eta: 2:23:21 time: 0.469682 data_time: 0.028900 memory: 15239 loss_kpt: 0.000457 acc_pose: 0.887561 loss: 0.000457 2022/09/16 05:55:06 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 05:55:06 - mmengine - INFO - Saving checkpoint at 177 epochs 2022/09/16 05:55:38 - mmengine - INFO - Epoch(train) [178][50/586] lr: 5.000000e-05 eta: 2:22:40 time: 0.478592 data_time: 0.031936 memory: 15239 loss_kpt: 0.000461 acc_pose: 0.936637 loss: 0.000461 2022/09/16 05:56:02 - mmengine - INFO - Epoch(train) [178][100/586] lr: 5.000000e-05 eta: 2:22:18 time: 0.488843 data_time: 0.028050 memory: 15239 loss_kpt: 0.000470 acc_pose: 0.911800 loss: 0.000470 2022/09/16 05:56:25 - mmengine - INFO - Epoch(train) [178][150/586] lr: 5.000000e-05 eta: 2:21:56 time: 0.464554 data_time: 0.023779 memory: 15239 loss_kpt: 0.000459 acc_pose: 0.858906 loss: 0.000459 2022/09/16 05:56:49 - mmengine - INFO - Epoch(train) [178][200/586] lr: 5.000000e-05 eta: 2:21:34 time: 0.469623 data_time: 0.027724 memory: 15239 loss_kpt: 0.000466 acc_pose: 0.866122 loss: 0.000466 2022/09/16 05:57:13 - mmengine - INFO - Epoch(train) [178][250/586] lr: 5.000000e-05 eta: 2:21:13 time: 0.483113 data_time: 0.023792 memory: 15239 loss_kpt: 0.000452 acc_pose: 0.936991 loss: 0.000452 2022/09/16 05:57:26 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 05:57:36 - mmengine - INFO - Epoch(train) [178][300/586] lr: 5.000000e-05 eta: 2:20:51 time: 0.469967 data_time: 0.025738 memory: 15239 loss_kpt: 0.000460 acc_pose: 0.926895 loss: 0.000460 2022/09/16 05:58:00 - mmengine - INFO - Epoch(train) [178][350/586] lr: 5.000000e-05 eta: 2:20:29 time: 0.476926 data_time: 0.024996 memory: 15239 loss_kpt: 0.000484 acc_pose: 0.885572 loss: 0.000484 2022/09/16 05:58:24 - mmengine - INFO - Epoch(train) [178][400/586] lr: 5.000000e-05 eta: 2:20:07 time: 0.474674 data_time: 0.023816 memory: 15239 loss_kpt: 0.000457 acc_pose: 0.893266 loss: 0.000457 2022/09/16 05:58:47 - mmengine - INFO - Epoch(train) [178][450/586] lr: 5.000000e-05 eta: 2:19:45 time: 0.465401 data_time: 0.023970 memory: 15239 loss_kpt: 0.000461 acc_pose: 0.890285 loss: 0.000461 2022/09/16 05:59:10 - mmengine - INFO - Epoch(train) [178][500/586] lr: 5.000000e-05 eta: 2:19:23 time: 0.462560 data_time: 0.029294 memory: 15239 loss_kpt: 0.000455 acc_pose: 0.818306 loss: 0.000455 2022/09/16 05:59:34 - mmengine - INFO - Epoch(train) [178][550/586] lr: 5.000000e-05 eta: 2:19:01 time: 0.477913 data_time: 0.023502 memory: 15239 loss_kpt: 0.000449 acc_pose: 0.878164 loss: 0.000449 2022/09/16 05:59:52 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 05:59:52 - mmengine - INFO - Saving checkpoint at 178 epochs 2022/09/16 06:00:24 - mmengine - INFO - Epoch(train) [179][50/586] lr: 5.000000e-05 eta: 2:18:20 time: 0.507762 data_time: 0.031455 memory: 15239 loss_kpt: 0.000450 acc_pose: 0.876965 loss: 0.000450 2022/09/16 06:00:48 - mmengine - INFO - Epoch(train) [179][100/586] lr: 5.000000e-05 eta: 2:17:59 time: 0.480473 data_time: 0.023968 memory: 15239 loss_kpt: 0.000454 acc_pose: 0.850028 loss: 0.000454 2022/09/16 06:01:11 - mmengine - INFO - Epoch(train) [179][150/586] lr: 5.000000e-05 eta: 2:17:37 time: 0.461865 data_time: 0.024206 memory: 15239 loss_kpt: 0.000455 acc_pose: 0.841375 loss: 0.000455 2022/09/16 06:01:35 - mmengine - INFO - Epoch(train) [179][200/586] lr: 5.000000e-05 eta: 2:17:15 time: 0.465478 data_time: 0.024996 memory: 15239 loss_kpt: 0.000479 acc_pose: 0.878624 loss: 0.000479 2022/09/16 06:01:58 - mmengine - INFO - Epoch(train) [179][250/586] lr: 5.000000e-05 eta: 2:16:53 time: 0.467691 data_time: 0.027314 memory: 15239 loss_kpt: 0.000467 acc_pose: 0.889988 loss: 0.000467 2022/09/16 06:02:21 - mmengine - INFO - Epoch(train) [179][300/586] lr: 5.000000e-05 eta: 2:16:31 time: 0.464451 data_time: 0.024246 memory: 15239 loss_kpt: 0.000453 acc_pose: 0.911592 loss: 0.000453 2022/09/16 06:02:45 - mmengine - INFO - Epoch(train) [179][350/586] lr: 5.000000e-05 eta: 2:16:09 time: 0.467903 data_time: 0.024763 memory: 15239 loss_kpt: 0.000459 acc_pose: 0.885733 loss: 0.000459 2022/09/16 06:03:08 - mmengine - INFO - Epoch(train) [179][400/586] lr: 5.000000e-05 eta: 2:15:47 time: 0.471720 data_time: 0.024977 memory: 15239 loss_kpt: 0.000460 acc_pose: 0.908309 loss: 0.000460 2022/09/16 06:03:31 - mmengine - INFO - Epoch(train) [179][450/586] lr: 5.000000e-05 eta: 2:15:25 time: 0.461079 data_time: 0.024142 memory: 15239 loss_kpt: 0.000468 acc_pose: 0.839846 loss: 0.000468 2022/09/16 06:03:54 - mmengine - INFO - Epoch(train) [179][500/586] lr: 5.000000e-05 eta: 2:15:02 time: 0.461367 data_time: 0.023824 memory: 15239 loss_kpt: 0.000466 acc_pose: 0.906159 loss: 0.000466 2022/09/16 06:04:18 - mmengine - INFO - Epoch(train) [179][550/586] lr: 5.000000e-05 eta: 2:14:41 time: 0.476737 data_time: 0.024639 memory: 15239 loss_kpt: 0.000473 acc_pose: 0.900717 loss: 0.000473 2022/09/16 06:04:35 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 06:04:35 - mmengine - INFO - Saving checkpoint at 179 epochs 2022/09/16 06:05:07 - mmengine - INFO - Epoch(train) [180][50/586] lr: 5.000000e-05 eta: 2:14:00 time: 0.481975 data_time: 0.034144 memory: 15239 loss_kpt: 0.000462 acc_pose: 0.867839 loss: 0.000462 2022/09/16 06:05:31 - mmengine - INFO - Epoch(train) [180][100/586] lr: 5.000000e-05 eta: 2:13:38 time: 0.479515 data_time: 0.025642 memory: 15239 loss_kpt: 0.000475 acc_pose: 0.899565 loss: 0.000475 2022/09/16 06:05:34 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 06:05:54 - mmengine - INFO - Epoch(train) [180][150/586] lr: 5.000000e-05 eta: 2:13:16 time: 0.465710 data_time: 0.023589 memory: 15239 loss_kpt: 0.000473 acc_pose: 0.911519 loss: 0.000473 2022/09/16 06:06:17 - mmengine - INFO - Epoch(train) [180][200/586] lr: 5.000000e-05 eta: 2:12:54 time: 0.463333 data_time: 0.023753 memory: 15239 loss_kpt: 0.000453 acc_pose: 0.848249 loss: 0.000453 2022/09/16 06:06:41 - mmengine - INFO - Epoch(train) [180][250/586] lr: 5.000000e-05 eta: 2:12:32 time: 0.471926 data_time: 0.024820 memory: 15239 loss_kpt: 0.000442 acc_pose: 0.907684 loss: 0.000442 2022/09/16 06:07:04 - mmengine - INFO - Epoch(train) [180][300/586] lr: 5.000000e-05 eta: 2:12:10 time: 0.460444 data_time: 0.025109 memory: 15239 loss_kpt: 0.000462 acc_pose: 0.845699 loss: 0.000462 2022/09/16 06:07:27 - mmengine - INFO - Epoch(train) [180][350/586] lr: 5.000000e-05 eta: 2:11:48 time: 0.465430 data_time: 0.023988 memory: 15239 loss_kpt: 0.000465 acc_pose: 0.918595 loss: 0.000465 2022/09/16 06:07:51 - mmengine - INFO - Epoch(train) [180][400/586] lr: 5.000000e-05 eta: 2:11:26 time: 0.469456 data_time: 0.024456 memory: 15239 loss_kpt: 0.000459 acc_pose: 0.893962 loss: 0.000459 2022/09/16 06:08:14 - mmengine - INFO - Epoch(train) [180][450/586] lr: 5.000000e-05 eta: 2:11:04 time: 0.463595 data_time: 0.024685 memory: 15239 loss_kpt: 0.000456 acc_pose: 0.880806 loss: 0.000456 2022/09/16 06:08:37 - mmengine - INFO - Epoch(train) [180][500/586] lr: 5.000000e-05 eta: 2:10:42 time: 0.465322 data_time: 0.026924 memory: 15239 loss_kpt: 0.000468 acc_pose: 0.931049 loss: 0.000468 2022/09/16 06:09:00 - mmengine - INFO - Epoch(train) [180][550/586] lr: 5.000000e-05 eta: 2:10:20 time: 0.464318 data_time: 0.023683 memory: 15239 loss_kpt: 0.000467 acc_pose: 0.884360 loss: 0.000467 2022/09/16 06:09:17 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 06:09:17 - mmengine - INFO - Saving checkpoint at 180 epochs 2022/09/16 06:09:38 - mmengine - INFO - Epoch(val) [180][50/407] eta: 0:01:32 time: 0.260382 data_time: 0.016094 memory: 15239 2022/09/16 06:09:50 - mmengine - INFO - Epoch(val) [180][100/407] eta: 0:01:16 time: 0.250790 data_time: 0.008540 memory: 2064 2022/09/16 06:10:03 - mmengine - INFO - Epoch(val) [180][150/407] eta: 0:01:04 time: 0.250854 data_time: 0.008761 memory: 2064 2022/09/16 06:10:16 - mmengine - INFO - Epoch(val) [180][200/407] eta: 0:00:52 time: 0.253381 data_time: 0.008766 memory: 2064 2022/09/16 06:10:28 - mmengine - INFO - Epoch(val) [180][250/407] eta: 0:00:39 time: 0.251711 data_time: 0.008372 memory: 2064 2022/09/16 06:10:41 - mmengine - INFO - Epoch(val) [180][300/407] eta: 0:00:26 time: 0.250152 data_time: 0.008281 memory: 2064 2022/09/16 06:10:53 - mmengine - INFO - Epoch(val) [180][350/407] eta: 0:00:14 time: 0.256763 data_time: 0.013695 memory: 2064 2022/09/16 06:11:06 - mmengine - INFO - Epoch(val) [180][400/407] eta: 0:00:01 time: 0.248051 data_time: 0.008054 memory: 2064 2022/09/16 06:11:41 - mmengine - INFO - Evaluating CocoMetric... 2022/09/16 06:11:54 - mmengine - INFO - Epoch(val) [180][407/407] coco/AP: 0.771824 coco/AP .5: 0.910483 coco/AP .75: 0.833130 coco/AP (M): 0.731630 coco/AP (L): 0.842445 coco/AR: 0.819553 coco/AR .5: 0.945686 coco/AR .75: 0.875315 coco/AR (M): 0.776427 coco/AR (L): 0.882720 2022/09/16 06:11:54 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220915/dark_w48_384/best_coco/AP_epoch_170.pth is removed 2022/09/16 06:11:58 - mmengine - INFO - The best checkpoint with 0.7718 coco/AP at 180 epoch is saved to best_coco/AP_epoch_180.pth. 2022/09/16 06:12:22 - mmengine - INFO - Epoch(train) [181][50/586] lr: 5.000000e-05 eta: 2:09:39 time: 0.473267 data_time: 0.035632 memory: 15239 loss_kpt: 0.000477 acc_pose: 0.863838 loss: 0.000477 2022/09/16 06:12:45 - mmengine - INFO - Epoch(train) [181][100/586] lr: 5.000000e-05 eta: 2:09:17 time: 0.473792 data_time: 0.027436 memory: 15239 loss_kpt: 0.000451 acc_pose: 0.916816 loss: 0.000451 2022/09/16 06:13:09 - mmengine - INFO - Epoch(train) [181][150/586] lr: 5.000000e-05 eta: 2:08:55 time: 0.467575 data_time: 0.028350 memory: 15239 loss_kpt: 0.000462 acc_pose: 0.883314 loss: 0.000462 2022/09/16 06:13:32 - mmengine - INFO - Epoch(train) [181][200/586] lr: 5.000000e-05 eta: 2:08:33 time: 0.467539 data_time: 0.024547 memory: 15239 loss_kpt: 0.000462 acc_pose: 0.925066 loss: 0.000462 2022/09/16 06:13:55 - mmengine - INFO - Epoch(train) [181][250/586] lr: 5.000000e-05 eta: 2:08:11 time: 0.467657 data_time: 0.025707 memory: 15239 loss_kpt: 0.000458 acc_pose: 0.840377 loss: 0.000458 2022/09/16 06:14:19 - mmengine - INFO - Epoch(train) [181][300/586] lr: 5.000000e-05 eta: 2:07:49 time: 0.460678 data_time: 0.023606 memory: 15239 loss_kpt: 0.000445 acc_pose: 0.895398 loss: 0.000445 2022/09/16 06:14:42 - mmengine - INFO - Epoch(train) [181][350/586] lr: 5.000000e-05 eta: 2:07:27 time: 0.472224 data_time: 0.024019 memory: 15239 loss_kpt: 0.000459 acc_pose: 0.917580 loss: 0.000459 2022/09/16 06:15:06 - mmengine - INFO - Epoch(train) [181][400/586] lr: 5.000000e-05 eta: 2:07:05 time: 0.474486 data_time: 0.025118 memory: 15239 loss_kpt: 0.000456 acc_pose: 0.903060 loss: 0.000456 2022/09/16 06:15:29 - mmengine - INFO - Epoch(train) [181][450/586] lr: 5.000000e-05 eta: 2:06:44 time: 0.470466 data_time: 0.027958 memory: 15239 loss_kpt: 0.000461 acc_pose: 0.836685 loss: 0.000461 2022/09/16 06:15:53 - mmengine - INFO - Epoch(train) [181][500/586] lr: 5.000000e-05 eta: 2:06:22 time: 0.474358 data_time: 0.025700 memory: 15239 loss_kpt: 0.000459 acc_pose: 0.890329 loss: 0.000459 2022/09/16 06:16:03 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 06:16:17 - mmengine - INFO - Epoch(train) [181][550/586] lr: 5.000000e-05 eta: 2:06:00 time: 0.466863 data_time: 0.024286 memory: 15239 loss_kpt: 0.000450 acc_pose: 0.923636 loss: 0.000450 2022/09/16 06:16:33 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 06:16:33 - mmengine - INFO - Saving checkpoint at 181 epochs 2022/09/16 06:17:04 - mmengine - INFO - Epoch(train) [182][50/586] lr: 5.000000e-05 eta: 2:05:19 time: 0.478264 data_time: 0.031491 memory: 15239 loss_kpt: 0.000449 acc_pose: 0.904776 loss: 0.000449 2022/09/16 06:17:28 - mmengine - INFO - Epoch(train) [182][100/586] lr: 5.000000e-05 eta: 2:04:57 time: 0.478204 data_time: 0.024239 memory: 15239 loss_kpt: 0.000447 acc_pose: 0.873506 loss: 0.000447 2022/09/16 06:17:51 - mmengine - INFO - Epoch(train) [182][150/586] lr: 5.000000e-05 eta: 2:04:35 time: 0.465088 data_time: 0.024047 memory: 15239 loss_kpt: 0.000468 acc_pose: 0.883188 loss: 0.000468 2022/09/16 06:18:15 - mmengine - INFO - Epoch(train) [182][200/586] lr: 5.000000e-05 eta: 2:04:13 time: 0.472370 data_time: 0.024902 memory: 15239 loss_kpt: 0.000456 acc_pose: 0.870858 loss: 0.000456 2022/09/16 06:18:38 - mmengine - INFO - Epoch(train) [182][250/586] lr: 5.000000e-05 eta: 2:03:51 time: 0.466368 data_time: 0.025572 memory: 15239 loss_kpt: 0.000469 acc_pose: 0.909850 loss: 0.000469 2022/09/16 06:19:02 - mmengine - INFO - Epoch(train) [182][300/586] lr: 5.000000e-05 eta: 2:03:29 time: 0.467956 data_time: 0.024860 memory: 15239 loss_kpt: 0.000457 acc_pose: 0.910841 loss: 0.000457 2022/09/16 06:19:25 - mmengine - INFO - Epoch(train) [182][350/586] lr: 5.000000e-05 eta: 2:03:07 time: 0.463644 data_time: 0.027335 memory: 15239 loss_kpt: 0.000466 acc_pose: 0.894322 loss: 0.000466 2022/09/16 06:19:49 - mmengine - INFO - Epoch(train) [182][400/586] lr: 5.000000e-05 eta: 2:02:45 time: 0.470546 data_time: 0.023976 memory: 15239 loss_kpt: 0.000449 acc_pose: 0.915813 loss: 0.000449 2022/09/16 06:20:12 - mmengine - INFO - Epoch(train) [182][450/586] lr: 5.000000e-05 eta: 2:02:23 time: 0.461047 data_time: 0.024663 memory: 15239 loss_kpt: 0.000459 acc_pose: 0.877441 loss: 0.000459 2022/09/16 06:20:35 - mmengine - INFO - Epoch(train) [182][500/586] lr: 5.000000e-05 eta: 2:02:01 time: 0.466535 data_time: 0.028018 memory: 15239 loss_kpt: 0.000463 acc_pose: 0.880210 loss: 0.000463 2022/09/16 06:20:59 - mmengine - INFO - Epoch(train) [182][550/586] lr: 5.000000e-05 eta: 2:01:39 time: 0.476650 data_time: 0.024013 memory: 15239 loss_kpt: 0.000461 acc_pose: 0.881113 loss: 0.000461 2022/09/16 06:21:15 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 06:21:15 - mmengine - INFO - Saving checkpoint at 182 epochs 2022/09/16 06:21:46 - mmengine - INFO - Epoch(train) [183][50/586] lr: 5.000000e-05 eta: 2:00:59 time: 0.472267 data_time: 0.033575 memory: 15239 loss_kpt: 0.000448 acc_pose: 0.904252 loss: 0.000448 2022/09/16 06:22:09 - mmengine - INFO - Epoch(train) [183][100/586] lr: 5.000000e-05 eta: 2:00:37 time: 0.464469 data_time: 0.027915 memory: 15239 loss_kpt: 0.000461 acc_pose: 0.885785 loss: 0.000461 2022/09/16 06:22:33 - mmengine - INFO - Epoch(train) [183][150/586] lr: 5.000000e-05 eta: 2:00:15 time: 0.463725 data_time: 0.028046 memory: 15239 loss_kpt: 0.000467 acc_pose: 0.895426 loss: 0.000467 2022/09/16 06:22:56 - mmengine - INFO - Epoch(train) [183][200/586] lr: 5.000000e-05 eta: 1:59:53 time: 0.466777 data_time: 0.031876 memory: 15239 loss_kpt: 0.000449 acc_pose: 0.879949 loss: 0.000449 2022/09/16 06:23:19 - mmengine - INFO - Epoch(train) [183][250/586] lr: 5.000000e-05 eta: 1:59:31 time: 0.464986 data_time: 0.027187 memory: 15239 loss_kpt: 0.000454 acc_pose: 0.885916 loss: 0.000454 2022/09/16 06:23:42 - mmengine - INFO - Epoch(train) [183][300/586] lr: 5.000000e-05 eta: 1:59:09 time: 0.465148 data_time: 0.027806 memory: 15239 loss_kpt: 0.000452 acc_pose: 0.898671 loss: 0.000452 2022/09/16 06:24:05 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 06:24:06 - mmengine - INFO - Epoch(train) [183][350/586] lr: 5.000000e-05 eta: 1:58:47 time: 0.465871 data_time: 0.027662 memory: 15239 loss_kpt: 0.000447 acc_pose: 0.845967 loss: 0.000447 2022/09/16 06:24:29 - mmengine - INFO - Epoch(train) [183][400/586] lr: 5.000000e-05 eta: 1:58:25 time: 0.466282 data_time: 0.027626 memory: 15239 loss_kpt: 0.000456 acc_pose: 0.872649 loss: 0.000456 2022/09/16 06:24:53 - mmengine - INFO - Epoch(train) [183][450/586] lr: 5.000000e-05 eta: 1:58:03 time: 0.470267 data_time: 0.027112 memory: 15239 loss_kpt: 0.000457 acc_pose: 0.865521 loss: 0.000457 2022/09/16 06:25:16 - mmengine - INFO - Epoch(train) [183][500/586] lr: 5.000000e-05 eta: 1:57:41 time: 0.473693 data_time: 0.024854 memory: 15239 loss_kpt: 0.000477 acc_pose: 0.894708 loss: 0.000477 2022/09/16 06:25:39 - mmengine - INFO - Epoch(train) [183][550/586] lr: 5.000000e-05 eta: 1:57:19 time: 0.462434 data_time: 0.024135 memory: 15239 loss_kpt: 0.000453 acc_pose: 0.873016 loss: 0.000453 2022/09/16 06:25:57 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 06:25:57 - mmengine - INFO - Saving checkpoint at 183 epochs 2022/09/16 06:26:28 - mmengine - INFO - Epoch(train) [184][50/586] lr: 5.000000e-05 eta: 1:56:38 time: 0.474429 data_time: 0.036642 memory: 15239 loss_kpt: 0.000462 acc_pose: 0.837383 loss: 0.000462 2022/09/16 06:26:51 - mmengine - INFO - Epoch(train) [184][100/586] lr: 5.000000e-05 eta: 1:56:16 time: 0.470434 data_time: 0.027078 memory: 15239 loss_kpt: 0.000443 acc_pose: 0.862125 loss: 0.000443 2022/09/16 06:27:15 - mmengine - INFO - Epoch(train) [184][150/586] lr: 5.000000e-05 eta: 1:55:54 time: 0.473598 data_time: 0.027129 memory: 15239 loss_kpt: 0.000474 acc_pose: 0.891516 loss: 0.000474 2022/09/16 06:27:38 - mmengine - INFO - Epoch(train) [184][200/586] lr: 5.000000e-05 eta: 1:55:32 time: 0.463691 data_time: 0.027243 memory: 15239 loss_kpt: 0.000472 acc_pose: 0.900032 loss: 0.000472 2022/09/16 06:28:02 - mmengine - INFO - Epoch(train) [184][250/586] lr: 5.000000e-05 eta: 1:55:10 time: 0.474683 data_time: 0.028093 memory: 15239 loss_kpt: 0.000449 acc_pose: 0.890818 loss: 0.000449 2022/09/16 06:28:26 - mmengine - INFO - Epoch(train) [184][300/586] lr: 5.000000e-05 eta: 1:54:48 time: 0.475430 data_time: 0.024054 memory: 15239 loss_kpt: 0.000456 acc_pose: 0.873750 loss: 0.000456 2022/09/16 06:28:49 - mmengine - INFO - Epoch(train) [184][350/586] lr: 5.000000e-05 eta: 1:54:26 time: 0.478814 data_time: 0.024275 memory: 15239 loss_kpt: 0.000454 acc_pose: 0.908369 loss: 0.000454 2022/09/16 06:29:13 - mmengine - INFO - Epoch(train) [184][400/586] lr: 5.000000e-05 eta: 1:54:04 time: 0.467447 data_time: 0.024216 memory: 15239 loss_kpt: 0.000450 acc_pose: 0.787279 loss: 0.000450 2022/09/16 06:29:36 - mmengine - INFO - Epoch(train) [184][450/586] lr: 5.000000e-05 eta: 1:53:42 time: 0.471976 data_time: 0.023899 memory: 15239 loss_kpt: 0.000433 acc_pose: 0.905189 loss: 0.000433 2022/09/16 06:30:00 - mmengine - INFO - Epoch(train) [184][500/586] lr: 5.000000e-05 eta: 1:53:20 time: 0.465780 data_time: 0.024837 memory: 15239 loss_kpt: 0.000456 acc_pose: 0.875474 loss: 0.000456 2022/09/16 06:30:23 - mmengine - INFO - Epoch(train) [184][550/586] lr: 5.000000e-05 eta: 1:52:58 time: 0.464892 data_time: 0.024667 memory: 15239 loss_kpt: 0.000463 acc_pose: 0.925324 loss: 0.000463 2022/09/16 06:30:40 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 06:30:40 - mmengine - INFO - Saving checkpoint at 184 epochs 2022/09/16 06:31:11 - mmengine - INFO - Epoch(train) [185][50/586] lr: 5.000000e-05 eta: 1:52:18 time: 0.477910 data_time: 0.033989 memory: 15239 loss_kpt: 0.000471 acc_pose: 0.893581 loss: 0.000471 2022/09/16 06:31:34 - mmengine - INFO - Epoch(train) [185][100/586] lr: 5.000000e-05 eta: 1:51:56 time: 0.467658 data_time: 0.024298 memory: 15239 loss_kpt: 0.000441 acc_pose: 0.947111 loss: 0.000441 2022/09/16 06:31:57 - mmengine - INFO - Epoch(train) [185][150/586] lr: 5.000000e-05 eta: 1:51:34 time: 0.463828 data_time: 0.024141 memory: 15239 loss_kpt: 0.000448 acc_pose: 0.923203 loss: 0.000448 2022/09/16 06:32:09 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 06:32:21 - mmengine - INFO - Epoch(train) [185][200/586] lr: 5.000000e-05 eta: 1:51:12 time: 0.466959 data_time: 0.023762 memory: 15239 loss_kpt: 0.000465 acc_pose: 0.888232 loss: 0.000465 2022/09/16 06:32:44 - mmengine - INFO - Epoch(train) [185][250/586] lr: 5.000000e-05 eta: 1:50:50 time: 0.465122 data_time: 0.024120 memory: 15239 loss_kpt: 0.000470 acc_pose: 0.905525 loss: 0.000470 2022/09/16 06:33:08 - mmengine - INFO - Epoch(train) [185][300/586] lr: 5.000000e-05 eta: 1:50:28 time: 0.472164 data_time: 0.023837 memory: 15239 loss_kpt: 0.000461 acc_pose: 0.890843 loss: 0.000461 2022/09/16 06:33:31 - mmengine - INFO - Epoch(train) [185][350/586] lr: 5.000000e-05 eta: 1:50:06 time: 0.464777 data_time: 0.024052 memory: 15239 loss_kpt: 0.000459 acc_pose: 0.938927 loss: 0.000459 2022/09/16 06:33:54 - mmengine - INFO - Epoch(train) [185][400/586] lr: 5.000000e-05 eta: 1:49:44 time: 0.459304 data_time: 0.023009 memory: 15239 loss_kpt: 0.000459 acc_pose: 0.915060 loss: 0.000459 2022/09/16 06:34:17 - mmengine - INFO - Epoch(train) [185][450/586] lr: 5.000000e-05 eta: 1:49:22 time: 0.466509 data_time: 0.024575 memory: 15239 loss_kpt: 0.000450 acc_pose: 0.908338 loss: 0.000450 2022/09/16 06:34:41 - mmengine - INFO - Epoch(train) [185][500/586] lr: 5.000000e-05 eta: 1:49:00 time: 0.468993 data_time: 0.028001 memory: 15239 loss_kpt: 0.000448 acc_pose: 0.872141 loss: 0.000448 2022/09/16 06:35:04 - mmengine - INFO - Epoch(train) [185][550/586] lr: 5.000000e-05 eta: 1:48:38 time: 0.458679 data_time: 0.024060 memory: 15239 loss_kpt: 0.000449 acc_pose: 0.869238 loss: 0.000449 2022/09/16 06:35:20 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 06:35:20 - mmengine - INFO - Saving checkpoint at 185 epochs 2022/09/16 06:35:51 - mmengine - INFO - Epoch(train) [186][50/586] lr: 5.000000e-05 eta: 1:47:58 time: 0.476785 data_time: 0.029484 memory: 15239 loss_kpt: 0.000448 acc_pose: 0.901439 loss: 0.000448 2022/09/16 06:36:15 - mmengine - INFO - Epoch(train) [186][100/586] lr: 5.000000e-05 eta: 1:47:36 time: 0.470698 data_time: 0.025134 memory: 15239 loss_kpt: 0.000470 acc_pose: 0.881921 loss: 0.000470 2022/09/16 06:36:39 - mmengine - INFO - Epoch(train) [186][150/586] lr: 5.000000e-05 eta: 1:47:14 time: 0.477063 data_time: 0.024384 memory: 15239 loss_kpt: 0.000450 acc_pose: 0.881624 loss: 0.000450 2022/09/16 06:37:02 - mmengine - INFO - Epoch(train) [186][200/586] lr: 5.000000e-05 eta: 1:46:52 time: 0.464665 data_time: 0.024121 memory: 15239 loss_kpt: 0.000467 acc_pose: 0.905168 loss: 0.000467 2022/09/16 06:37:25 - mmengine - INFO - Epoch(train) [186][250/586] lr: 5.000000e-05 eta: 1:46:29 time: 0.462964 data_time: 0.023709 memory: 15239 loss_kpt: 0.000446 acc_pose: 0.893651 loss: 0.000446 2022/09/16 06:37:48 - mmengine - INFO - Epoch(train) [186][300/586] lr: 5.000000e-05 eta: 1:46:07 time: 0.466246 data_time: 0.023727 memory: 15239 loss_kpt: 0.000454 acc_pose: 0.907780 loss: 0.000454 2022/09/16 06:38:12 - mmengine - INFO - Epoch(train) [186][350/586] lr: 5.000000e-05 eta: 1:45:45 time: 0.469129 data_time: 0.023475 memory: 15239 loss_kpt: 0.000447 acc_pose: 0.855625 loss: 0.000447 2022/09/16 06:38:35 - mmengine - INFO - Epoch(train) [186][400/586] lr: 5.000000e-05 eta: 1:45:23 time: 0.456700 data_time: 0.024537 memory: 15239 loss_kpt: 0.000457 acc_pose: 0.916534 loss: 0.000457 2022/09/16 06:38:58 - mmengine - INFO - Epoch(train) [186][450/586] lr: 5.000000e-05 eta: 1:45:01 time: 0.469617 data_time: 0.024620 memory: 15239 loss_kpt: 0.000452 acc_pose: 0.919885 loss: 0.000452 2022/09/16 06:39:21 - mmengine - INFO - Epoch(train) [186][500/586] lr: 5.000000e-05 eta: 1:44:39 time: 0.464749 data_time: 0.023367 memory: 15239 loss_kpt: 0.000458 acc_pose: 0.937673 loss: 0.000458 2022/09/16 06:39:45 - mmengine - INFO - Epoch(train) [186][550/586] lr: 5.000000e-05 eta: 1:44:17 time: 0.464283 data_time: 0.023846 memory: 15239 loss_kpt: 0.000445 acc_pose: 0.887297 loss: 0.000445 2022/09/16 06:40:01 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 06:40:01 - mmengine - INFO - Saving checkpoint at 186 epochs 2022/09/16 06:40:11 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 06:40:32 - mmengine - INFO - Epoch(train) [187][50/586] lr: 5.000000e-05 eta: 1:43:37 time: 0.469939 data_time: 0.029154 memory: 15239 loss_kpt: 0.000455 acc_pose: 0.831562 loss: 0.000455 2022/09/16 06:40:55 - mmengine - INFO - Epoch(train) [187][100/586] lr: 5.000000e-05 eta: 1:43:15 time: 0.466054 data_time: 0.024528 memory: 15239 loss_kpt: 0.000443 acc_pose: 0.896219 loss: 0.000443 2022/09/16 06:41:19 - mmengine - INFO - Epoch(train) [187][150/586] lr: 5.000000e-05 eta: 1:42:53 time: 0.472958 data_time: 0.024158 memory: 15239 loss_kpt: 0.000463 acc_pose: 0.891258 loss: 0.000463 2022/09/16 06:41:42 - mmengine - INFO - Epoch(train) [187][200/586] lr: 5.000000e-05 eta: 1:42:31 time: 0.461076 data_time: 0.024180 memory: 15239 loss_kpt: 0.000455 acc_pose: 0.843412 loss: 0.000455 2022/09/16 06:42:06 - mmengine - INFO - Epoch(train) [187][250/586] lr: 5.000000e-05 eta: 1:42:09 time: 0.467448 data_time: 0.027933 memory: 15239 loss_kpt: 0.000454 acc_pose: 0.915631 loss: 0.000454 2022/09/16 06:42:29 - mmengine - INFO - Epoch(train) [187][300/586] lr: 5.000000e-05 eta: 1:41:47 time: 0.466257 data_time: 0.023848 memory: 15239 loss_kpt: 0.000466 acc_pose: 0.884975 loss: 0.000466 2022/09/16 06:42:52 - mmengine - INFO - Epoch(train) [187][350/586] lr: 5.000000e-05 eta: 1:41:25 time: 0.466367 data_time: 0.023586 memory: 15239 loss_kpt: 0.000446 acc_pose: 0.861870 loss: 0.000446 2022/09/16 06:43:16 - mmengine - INFO - Epoch(train) [187][400/586] lr: 5.000000e-05 eta: 1:41:03 time: 0.465890 data_time: 0.027417 memory: 15239 loss_kpt: 0.000446 acc_pose: 0.920935 loss: 0.000446 2022/09/16 06:43:39 - mmengine - INFO - Epoch(train) [187][450/586] lr: 5.000000e-05 eta: 1:40:41 time: 0.460436 data_time: 0.023687 memory: 15239 loss_kpt: 0.000442 acc_pose: 0.895790 loss: 0.000442 2022/09/16 06:44:02 - mmengine - INFO - Epoch(train) [187][500/586] lr: 5.000000e-05 eta: 1:40:19 time: 0.477114 data_time: 0.024305 memory: 15239 loss_kpt: 0.000447 acc_pose: 0.846032 loss: 0.000447 2022/09/16 06:44:26 - mmengine - INFO - Epoch(train) [187][550/586] lr: 5.000000e-05 eta: 1:39:57 time: 0.467940 data_time: 0.029586 memory: 15239 loss_kpt: 0.000475 acc_pose: 0.902462 loss: 0.000475 2022/09/16 06:44:43 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 06:44:43 - mmengine - INFO - Saving checkpoint at 187 epochs 2022/09/16 06:45:14 - mmengine - INFO - Epoch(train) [188][50/586] lr: 5.000000e-05 eta: 1:39:17 time: 0.476918 data_time: 0.030946 memory: 15239 loss_kpt: 0.000468 acc_pose: 0.945160 loss: 0.000468 2022/09/16 06:45:37 - mmengine - INFO - Epoch(train) [188][100/586] lr: 5.000000e-05 eta: 1:38:55 time: 0.461244 data_time: 0.030384 memory: 15239 loss_kpt: 0.000469 acc_pose: 0.867044 loss: 0.000469 2022/09/16 06:46:01 - mmengine - INFO - Epoch(train) [188][150/586] lr: 5.000000e-05 eta: 1:38:33 time: 0.481771 data_time: 0.027982 memory: 15239 loss_kpt: 0.000452 acc_pose: 0.857213 loss: 0.000452 2022/09/16 06:46:25 - mmengine - INFO - Epoch(train) [188][200/586] lr: 5.000000e-05 eta: 1:38:11 time: 0.478977 data_time: 0.028307 memory: 15239 loss_kpt: 0.000430 acc_pose: 0.887721 loss: 0.000430 2022/09/16 06:46:49 - mmengine - INFO - Epoch(train) [188][250/586] lr: 5.000000e-05 eta: 1:37:49 time: 0.477999 data_time: 0.026636 memory: 15239 loss_kpt: 0.000459 acc_pose: 0.886880 loss: 0.000459 2022/09/16 06:47:12 - mmengine - INFO - Epoch(train) [188][300/586] lr: 5.000000e-05 eta: 1:37:27 time: 0.466637 data_time: 0.023803 memory: 15239 loss_kpt: 0.000455 acc_pose: 0.880970 loss: 0.000455 2022/09/16 06:47:36 - mmengine - INFO - Epoch(train) [188][350/586] lr: 5.000000e-05 eta: 1:37:05 time: 0.474248 data_time: 0.023893 memory: 15239 loss_kpt: 0.000466 acc_pose: 0.931190 loss: 0.000466 2022/09/16 06:48:00 - mmengine - INFO - Epoch(train) [188][400/586] lr: 5.000000e-05 eta: 1:36:43 time: 0.481797 data_time: 0.024803 memory: 15239 loss_kpt: 0.000447 acc_pose: 0.844319 loss: 0.000447 2022/09/16 06:48:09 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 06:48:24 - mmengine - INFO - Epoch(train) [188][450/586] lr: 5.000000e-05 eta: 1:36:21 time: 0.473594 data_time: 0.024830 memory: 15239 loss_kpt: 0.000459 acc_pose: 0.791542 loss: 0.000459 2022/09/16 06:48:48 - mmengine - INFO - Epoch(train) [188][500/586] lr: 5.000000e-05 eta: 1:35:59 time: 0.481298 data_time: 0.024443 memory: 15239 loss_kpt: 0.000454 acc_pose: 0.862609 loss: 0.000454 2022/09/16 06:49:11 - mmengine - INFO - Epoch(train) [188][550/586] lr: 5.000000e-05 eta: 1:35:37 time: 0.469711 data_time: 0.028456 memory: 15239 loss_kpt: 0.000456 acc_pose: 0.828439 loss: 0.000456 2022/09/16 06:49:28 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 06:49:28 - mmengine - INFO - Saving checkpoint at 188 epochs 2022/09/16 06:50:00 - mmengine - INFO - Epoch(train) [189][50/586] lr: 5.000000e-05 eta: 1:34:57 time: 0.486205 data_time: 0.037416 memory: 15239 loss_kpt: 0.000462 acc_pose: 0.926304 loss: 0.000462 2022/09/16 06:50:24 - mmengine - INFO - Epoch(train) [189][100/586] lr: 5.000000e-05 eta: 1:34:35 time: 0.471123 data_time: 0.024669 memory: 15239 loss_kpt: 0.000448 acc_pose: 0.905295 loss: 0.000448 2022/09/16 06:50:48 - mmengine - INFO - Epoch(train) [189][150/586] lr: 5.000000e-05 eta: 1:34:13 time: 0.478908 data_time: 0.024174 memory: 15239 loss_kpt: 0.000447 acc_pose: 0.920473 loss: 0.000447 2022/09/16 06:51:11 - mmengine - INFO - Epoch(train) [189][200/586] lr: 5.000000e-05 eta: 1:33:51 time: 0.461486 data_time: 0.024126 memory: 15239 loss_kpt: 0.000437 acc_pose: 0.819356 loss: 0.000437 2022/09/16 06:51:34 - mmengine - INFO - Epoch(train) [189][250/586] lr: 5.000000e-05 eta: 1:33:29 time: 0.468647 data_time: 0.024274 memory: 15239 loss_kpt: 0.000457 acc_pose: 0.892165 loss: 0.000457 2022/09/16 06:51:58 - mmengine - INFO - Epoch(train) [189][300/586] lr: 5.000000e-05 eta: 1:33:07 time: 0.472551 data_time: 0.024014 memory: 15239 loss_kpt: 0.000446 acc_pose: 0.871896 loss: 0.000446 2022/09/16 06:52:22 - mmengine - INFO - Epoch(train) [189][350/586] lr: 5.000000e-05 eta: 1:32:45 time: 0.479382 data_time: 0.025451 memory: 15239 loss_kpt: 0.000456 acc_pose: 0.885502 loss: 0.000456 2022/09/16 06:52:45 - mmengine - INFO - Epoch(train) [189][400/586] lr: 5.000000e-05 eta: 1:32:23 time: 0.467396 data_time: 0.023897 memory: 15239 loss_kpt: 0.000452 acc_pose: 0.950025 loss: 0.000452 2022/09/16 06:53:09 - mmengine - INFO - Epoch(train) [189][450/586] lr: 5.000000e-05 eta: 1:32:01 time: 0.464731 data_time: 0.023844 memory: 15239 loss_kpt: 0.000456 acc_pose: 0.836148 loss: 0.000456 2022/09/16 06:53:32 - mmengine - INFO - Epoch(train) [189][500/586] lr: 5.000000e-05 eta: 1:31:39 time: 0.470733 data_time: 0.024058 memory: 15239 loss_kpt: 0.000452 acc_pose: 0.870414 loss: 0.000452 2022/09/16 06:53:55 - mmengine - INFO - Epoch(train) [189][550/586] lr: 5.000000e-05 eta: 1:31:17 time: 0.462527 data_time: 0.025082 memory: 15239 loss_kpt: 0.000454 acc_pose: 0.897494 loss: 0.000454 2022/09/16 06:54:11 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 06:54:12 - mmengine - INFO - Saving checkpoint at 189 epochs 2022/09/16 06:54:44 - mmengine - INFO - Epoch(train) [190][50/586] lr: 5.000000e-05 eta: 1:30:37 time: 0.486283 data_time: 0.034774 memory: 15239 loss_kpt: 0.000457 acc_pose: 0.882042 loss: 0.000457 2022/09/16 06:55:08 - mmengine - INFO - Epoch(train) [190][100/586] lr: 5.000000e-05 eta: 1:30:15 time: 0.478860 data_time: 0.031069 memory: 15239 loss_kpt: 0.000438 acc_pose: 0.885162 loss: 0.000438 2022/09/16 06:55:31 - mmengine - INFO - Epoch(train) [190][150/586] lr: 5.000000e-05 eta: 1:29:53 time: 0.468240 data_time: 0.027216 memory: 15239 loss_kpt: 0.000443 acc_pose: 0.879872 loss: 0.000443 2022/09/16 06:55:55 - mmengine - INFO - Epoch(train) [190][200/586] lr: 5.000000e-05 eta: 1:29:31 time: 0.474678 data_time: 0.030930 memory: 15239 loss_kpt: 0.000462 acc_pose: 0.899939 loss: 0.000462 2022/09/16 06:56:16 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 06:56:18 - mmengine - INFO - Epoch(train) [190][250/586] lr: 5.000000e-05 eta: 1:29:09 time: 0.465105 data_time: 0.027606 memory: 15239 loss_kpt: 0.000449 acc_pose: 0.860853 loss: 0.000449 2022/09/16 06:56:42 - mmengine - INFO - Epoch(train) [190][300/586] lr: 5.000000e-05 eta: 1:28:47 time: 0.470381 data_time: 0.025314 memory: 15239 loss_kpt: 0.000469 acc_pose: 0.887984 loss: 0.000469 2022/09/16 06:57:05 - mmengine - INFO - Epoch(train) [190][350/586] lr: 5.000000e-05 eta: 1:28:25 time: 0.465680 data_time: 0.028703 memory: 15239 loss_kpt: 0.000442 acc_pose: 0.839185 loss: 0.000442 2022/09/16 06:57:28 - mmengine - INFO - Epoch(train) [190][400/586] lr: 5.000000e-05 eta: 1:28:03 time: 0.470203 data_time: 0.024176 memory: 15239 loss_kpt: 0.000458 acc_pose: 0.897303 loss: 0.000458 2022/09/16 06:57:52 - mmengine - INFO - Epoch(train) [190][450/586] lr: 5.000000e-05 eta: 1:27:41 time: 0.466765 data_time: 0.023966 memory: 15239 loss_kpt: 0.000460 acc_pose: 0.839767 loss: 0.000460 2022/09/16 06:58:16 - mmengine - INFO - Epoch(train) [190][500/586] lr: 5.000000e-05 eta: 1:27:19 time: 0.476246 data_time: 0.023951 memory: 15239 loss_kpt: 0.000445 acc_pose: 0.910621 loss: 0.000445 2022/09/16 06:58:39 - mmengine - INFO - Epoch(train) [190][550/586] lr: 5.000000e-05 eta: 1:26:57 time: 0.468169 data_time: 0.024849 memory: 15239 loss_kpt: 0.000449 acc_pose: 0.918946 loss: 0.000449 2022/09/16 06:58:56 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 06:58:56 - mmengine - INFO - Saving checkpoint at 190 epochs 2022/09/16 06:59:16 - mmengine - INFO - Epoch(val) [190][50/407] eta: 0:01:33 time: 0.261947 data_time: 0.015861 memory: 15239 2022/09/16 06:59:29 - mmengine - INFO - Epoch(val) [190][100/407] eta: 0:01:17 time: 0.253817 data_time: 0.011523 memory: 2064 2022/09/16 06:59:41 - mmengine - INFO - Epoch(val) [190][150/407] eta: 0:01:04 time: 0.252131 data_time: 0.010564 memory: 2064 2022/09/16 06:59:54 - mmengine - INFO - Epoch(val) [190][200/407] eta: 0:00:52 time: 0.253366 data_time: 0.008258 memory: 2064 2022/09/16 07:00:07 - mmengine - INFO - Epoch(val) [190][250/407] eta: 0:00:40 time: 0.256581 data_time: 0.013616 memory: 2064 2022/09/16 07:00:19 - mmengine - INFO - Epoch(val) [190][300/407] eta: 0:00:26 time: 0.249896 data_time: 0.008116 memory: 2064 2022/09/16 07:00:32 - mmengine - INFO - Epoch(val) [190][350/407] eta: 0:00:14 time: 0.250958 data_time: 0.008535 memory: 2064 2022/09/16 07:00:44 - mmengine - INFO - Epoch(val) [190][400/407] eta: 0:00:01 time: 0.248535 data_time: 0.007781 memory: 2064 2022/09/16 07:01:19 - mmengine - INFO - Evaluating CocoMetric... 2022/09/16 07:01:33 - mmengine - INFO - Epoch(val) [190][407/407] coco/AP: 0.772040 coco/AP .5: 0.910565 coco/AP .75: 0.833233 coco/AP (M): 0.731958 coco/AP (L): 0.843212 coco/AR: 0.820135 coco/AR .5: 0.947103 coco/AR .75: 0.875315 coco/AR (M): 0.777192 coco/AR (L): 0.882646 2022/09/16 07:01:33 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220915/dark_w48_384/best_coco/AP_epoch_180.pth is removed 2022/09/16 07:01:36 - mmengine - INFO - The best checkpoint with 0.7720 coco/AP at 190 epoch is saved to best_coco/AP_epoch_190.pth. 2022/09/16 07:02:00 - mmengine - INFO - Epoch(train) [191][50/586] lr: 5.000000e-05 eta: 1:26:17 time: 0.470887 data_time: 0.031289 memory: 15239 loss_kpt: 0.000457 acc_pose: 0.897970 loss: 0.000457 2022/09/16 07:02:24 - mmengine - INFO - Epoch(train) [191][100/586] lr: 5.000000e-05 eta: 1:25:55 time: 0.473191 data_time: 0.027707 memory: 15239 loss_kpt: 0.000456 acc_pose: 0.851125 loss: 0.000456 2022/09/16 07:02:47 - mmengine - INFO - Epoch(train) [191][150/586] lr: 5.000000e-05 eta: 1:25:33 time: 0.466355 data_time: 0.027124 memory: 15239 loss_kpt: 0.000462 acc_pose: 0.865716 loss: 0.000462 2022/09/16 07:03:10 - mmengine - INFO - Epoch(train) [191][200/586] lr: 5.000000e-05 eta: 1:25:11 time: 0.464615 data_time: 0.028261 memory: 15239 loss_kpt: 0.000468 acc_pose: 0.906522 loss: 0.000468 2022/09/16 07:03:34 - mmengine - INFO - Epoch(train) [191][250/586] lr: 5.000000e-05 eta: 1:24:49 time: 0.474148 data_time: 0.024112 memory: 15239 loss_kpt: 0.000463 acc_pose: 0.860059 loss: 0.000463 2022/09/16 07:03:57 - mmengine - INFO - Epoch(train) [191][300/586] lr: 5.000000e-05 eta: 1:24:27 time: 0.472251 data_time: 0.023651 memory: 15239 loss_kpt: 0.000434 acc_pose: 0.899615 loss: 0.000434 2022/09/16 07:04:21 - mmengine - INFO - Epoch(train) [191][350/586] lr: 5.000000e-05 eta: 1:24:05 time: 0.469393 data_time: 0.024762 memory: 15239 loss_kpt: 0.000449 acc_pose: 0.918328 loss: 0.000449 2022/09/16 07:04:45 - mmengine - INFO - Epoch(train) [191][400/586] lr: 5.000000e-05 eta: 1:23:43 time: 0.471795 data_time: 0.024440 memory: 15239 loss_kpt: 0.000447 acc_pose: 0.887775 loss: 0.000447 2022/09/16 07:05:08 - mmengine - INFO - Epoch(train) [191][450/586] lr: 5.000000e-05 eta: 1:23:20 time: 0.473135 data_time: 0.023866 memory: 15239 loss_kpt: 0.000462 acc_pose: 0.878055 loss: 0.000462 2022/09/16 07:05:32 - mmengine - INFO - Epoch(train) [191][500/586] lr: 5.000000e-05 eta: 1:22:58 time: 0.465638 data_time: 0.024094 memory: 15239 loss_kpt: 0.000446 acc_pose: 0.917403 loss: 0.000446 2022/09/16 07:05:55 - mmengine - INFO - Epoch(train) [191][550/586] lr: 5.000000e-05 eta: 1:22:36 time: 0.462807 data_time: 0.024471 memory: 15239 loss_kpt: 0.000448 acc_pose: 0.878393 loss: 0.000448 2022/09/16 07:06:12 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 07:06:12 - mmengine - INFO - Saving checkpoint at 191 epochs 2022/09/16 07:06:43 - mmengine - INFO - Epoch(train) [192][50/586] lr: 5.000000e-05 eta: 1:21:57 time: 0.481228 data_time: 0.036201 memory: 15239 loss_kpt: 0.000463 acc_pose: 0.930838 loss: 0.000463 2022/09/16 07:06:54 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 07:07:07 - mmengine - INFO - Epoch(train) [192][100/586] lr: 5.000000e-05 eta: 1:21:35 time: 0.474862 data_time: 0.032146 memory: 15239 loss_kpt: 0.000469 acc_pose: 0.892341 loss: 0.000469 2022/09/16 07:07:30 - mmengine - INFO - Epoch(train) [192][150/586] lr: 5.000000e-05 eta: 1:21:13 time: 0.471107 data_time: 0.024161 memory: 15239 loss_kpt: 0.000453 acc_pose: 0.869475 loss: 0.000453 2022/09/16 07:07:53 - mmengine - INFO - Epoch(train) [192][200/586] lr: 5.000000e-05 eta: 1:20:51 time: 0.462012 data_time: 0.023722 memory: 15239 loss_kpt: 0.000457 acc_pose: 0.932493 loss: 0.000457 2022/09/16 07:08:17 - mmengine - INFO - Epoch(train) [192][250/586] lr: 5.000000e-05 eta: 1:20:29 time: 0.467197 data_time: 0.023629 memory: 15239 loss_kpt: 0.000461 acc_pose: 0.883577 loss: 0.000461 2022/09/16 07:08:40 - mmengine - INFO - Epoch(train) [192][300/586] lr: 5.000000e-05 eta: 1:20:06 time: 0.466157 data_time: 0.024093 memory: 15239 loss_kpt: 0.000473 acc_pose: 0.815008 loss: 0.000473 2022/09/16 07:09:04 - mmengine - INFO - Epoch(train) [192][350/586] lr: 5.000000e-05 eta: 1:19:44 time: 0.473086 data_time: 0.027643 memory: 15239 loss_kpt: 0.000444 acc_pose: 0.932922 loss: 0.000444 2022/09/16 07:09:27 - mmengine - INFO - Epoch(train) [192][400/586] lr: 5.000000e-05 eta: 1:19:22 time: 0.462815 data_time: 0.023932 memory: 15239 loss_kpt: 0.000443 acc_pose: 0.913216 loss: 0.000443 2022/09/16 07:09:50 - mmengine - INFO - Epoch(train) [192][450/586] lr: 5.000000e-05 eta: 1:19:00 time: 0.469192 data_time: 0.023773 memory: 15239 loss_kpt: 0.000470 acc_pose: 0.899585 loss: 0.000470 2022/09/16 07:10:14 - mmengine - INFO - Epoch(train) [192][500/586] lr: 5.000000e-05 eta: 1:18:38 time: 0.471011 data_time: 0.027425 memory: 15239 loss_kpt: 0.000456 acc_pose: 0.882289 loss: 0.000456 2022/09/16 07:10:38 - mmengine - INFO - Epoch(train) [192][550/586] lr: 5.000000e-05 eta: 1:18:16 time: 0.475389 data_time: 0.024150 memory: 15239 loss_kpt: 0.000468 acc_pose: 0.916585 loss: 0.000468 2022/09/16 07:10:55 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 07:10:55 - mmengine - INFO - Saving checkpoint at 192 epochs 2022/09/16 07:11:26 - mmengine - INFO - Epoch(train) [193][50/586] lr: 5.000000e-05 eta: 1:17:37 time: 0.475961 data_time: 0.031636 memory: 15239 loss_kpt: 0.000442 acc_pose: 0.904371 loss: 0.000442 2022/09/16 07:11:49 - mmengine - INFO - Epoch(train) [193][100/586] lr: 5.000000e-05 eta: 1:17:15 time: 0.473133 data_time: 0.026258 memory: 15239 loss_kpt: 0.000468 acc_pose: 0.880563 loss: 0.000468 2022/09/16 07:12:13 - mmengine - INFO - Epoch(train) [193][150/586] lr: 5.000000e-05 eta: 1:16:53 time: 0.482552 data_time: 0.024076 memory: 15239 loss_kpt: 0.000454 acc_pose: 0.872434 loss: 0.000454 2022/09/16 07:12:37 - mmengine - INFO - Epoch(train) [193][200/586] lr: 5.000000e-05 eta: 1:16:31 time: 0.464117 data_time: 0.024490 memory: 15239 loss_kpt: 0.000460 acc_pose: 0.897678 loss: 0.000460 2022/09/16 07:13:00 - mmengine - INFO - Epoch(train) [193][250/586] lr: 5.000000e-05 eta: 1:16:08 time: 0.470368 data_time: 0.024619 memory: 15239 loss_kpt: 0.000454 acc_pose: 0.835070 loss: 0.000454 2022/09/16 07:13:24 - mmengine - INFO - Epoch(train) [193][300/586] lr: 5.000000e-05 eta: 1:15:46 time: 0.466455 data_time: 0.023410 memory: 15239 loss_kpt: 0.000449 acc_pose: 0.890729 loss: 0.000449 2022/09/16 07:13:47 - mmengine - INFO - Epoch(train) [193][350/586] lr: 5.000000e-05 eta: 1:15:24 time: 0.459374 data_time: 0.023910 memory: 15239 loss_kpt: 0.000452 acc_pose: 0.841941 loss: 0.000452 2022/09/16 07:14:10 - mmengine - INFO - Epoch(train) [193][400/586] lr: 5.000000e-05 eta: 1:15:02 time: 0.460903 data_time: 0.029257 memory: 15239 loss_kpt: 0.000451 acc_pose: 0.892711 loss: 0.000451 2022/09/16 07:14:33 - mmengine - INFO - Epoch(train) [193][450/586] lr: 5.000000e-05 eta: 1:14:40 time: 0.472468 data_time: 0.023845 memory: 15239 loss_kpt: 0.000452 acc_pose: 0.892317 loss: 0.000452 2022/09/16 07:14:51 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 07:14:56 - mmengine - INFO - Epoch(train) [193][500/586] lr: 5.000000e-05 eta: 1:14:18 time: 0.462624 data_time: 0.023614 memory: 15239 loss_kpt: 0.000436 acc_pose: 0.893669 loss: 0.000436 2022/09/16 07:15:19 - mmengine - INFO - Epoch(train) [193][550/586] lr: 5.000000e-05 eta: 1:13:56 time: 0.462219 data_time: 0.024711 memory: 15239 loss_kpt: 0.000450 acc_pose: 0.908015 loss: 0.000450 2022/09/16 07:15:36 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 07:15:36 - mmengine - INFO - Saving checkpoint at 193 epochs 2022/09/16 07:16:08 - mmengine - INFO - Epoch(train) [194][50/586] lr: 5.000000e-05 eta: 1:13:16 time: 0.474150 data_time: 0.032057 memory: 15239 loss_kpt: 0.000444 acc_pose: 0.905010 loss: 0.000444 2022/09/16 07:16:31 - mmengine - INFO - Epoch(train) [194][100/586] lr: 5.000000e-05 eta: 1:12:54 time: 0.462861 data_time: 0.027773 memory: 15239 loss_kpt: 0.000454 acc_pose: 0.868015 loss: 0.000454 2022/09/16 07:16:54 - mmengine - INFO - Epoch(train) [194][150/586] lr: 5.000000e-05 eta: 1:12:32 time: 0.473984 data_time: 0.027163 memory: 15239 loss_kpt: 0.000454 acc_pose: 0.867306 loss: 0.000454 2022/09/16 07:17:18 - mmengine - INFO - Epoch(train) [194][200/586] lr: 5.000000e-05 eta: 1:12:10 time: 0.467612 data_time: 0.025195 memory: 15239 loss_kpt: 0.000452 acc_pose: 0.890359 loss: 0.000452 2022/09/16 07:17:41 - mmengine - INFO - Epoch(train) [194][250/586] lr: 5.000000e-05 eta: 1:11:48 time: 0.460614 data_time: 0.027973 memory: 15239 loss_kpt: 0.000461 acc_pose: 0.838914 loss: 0.000461 2022/09/16 07:18:04 - mmengine - INFO - Epoch(train) [194][300/586] lr: 5.000000e-05 eta: 1:11:26 time: 0.465705 data_time: 0.023969 memory: 15239 loss_kpt: 0.000439 acc_pose: 0.885022 loss: 0.000439 2022/09/16 07:18:28 - mmengine - INFO - Epoch(train) [194][350/586] lr: 5.000000e-05 eta: 1:11:04 time: 0.467798 data_time: 0.026555 memory: 15239 loss_kpt: 0.000438 acc_pose: 0.900723 loss: 0.000438 2022/09/16 07:18:51 - mmengine - INFO - Epoch(train) [194][400/586] lr: 5.000000e-05 eta: 1:10:42 time: 0.464306 data_time: 0.024482 memory: 15239 loss_kpt: 0.000448 acc_pose: 0.929531 loss: 0.000448 2022/09/16 07:19:14 - mmengine - INFO - Epoch(train) [194][450/586] lr: 5.000000e-05 eta: 1:10:20 time: 0.466264 data_time: 0.023937 memory: 15239 loss_kpt: 0.000452 acc_pose: 0.850542 loss: 0.000452 2022/09/16 07:19:38 - mmengine - INFO - Epoch(train) [194][500/586] lr: 5.000000e-05 eta: 1:09:58 time: 0.468556 data_time: 0.024204 memory: 15239 loss_kpt: 0.000465 acc_pose: 0.885928 loss: 0.000465 2022/09/16 07:20:01 - mmengine - INFO - Epoch(train) [194][550/586] lr: 5.000000e-05 eta: 1:09:36 time: 0.460551 data_time: 0.024416 memory: 15239 loss_kpt: 0.000456 acc_pose: 0.908730 loss: 0.000456 2022/09/16 07:20:17 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 07:20:17 - mmengine - INFO - Saving checkpoint at 194 epochs 2022/09/16 07:20:49 - mmengine - INFO - Epoch(train) [195][50/586] lr: 5.000000e-05 eta: 1:08:56 time: 0.479996 data_time: 0.028561 memory: 15239 loss_kpt: 0.000442 acc_pose: 0.877773 loss: 0.000442 2022/09/16 07:21:12 - mmengine - INFO - Epoch(train) [195][100/586] lr: 5.000000e-05 eta: 1:08:34 time: 0.459378 data_time: 0.024046 memory: 15239 loss_kpt: 0.000435 acc_pose: 0.919084 loss: 0.000435 2022/09/16 07:21:35 - mmengine - INFO - Epoch(train) [195][150/586] lr: 5.000000e-05 eta: 1:08:12 time: 0.476544 data_time: 0.024786 memory: 15239 loss_kpt: 0.000459 acc_pose: 0.879775 loss: 0.000459 2022/09/16 07:21:59 - mmengine - INFO - Epoch(train) [195][200/586] lr: 5.000000e-05 eta: 1:07:50 time: 0.467540 data_time: 0.028966 memory: 15239 loss_kpt: 0.000464 acc_pose: 0.910547 loss: 0.000464 2022/09/16 07:22:22 - mmengine - INFO - Epoch(train) [195][250/586] lr: 5.000000e-05 eta: 1:07:28 time: 0.461248 data_time: 0.023935 memory: 15239 loss_kpt: 0.000444 acc_pose: 0.908443 loss: 0.000444 2022/09/16 07:22:45 - mmengine - INFO - Epoch(train) [195][300/586] lr: 5.000000e-05 eta: 1:07:06 time: 0.464856 data_time: 0.024131 memory: 15239 loss_kpt: 0.000453 acc_pose: 0.860507 loss: 0.000453 2022/09/16 07:22:52 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 07:23:08 - mmengine - INFO - Epoch(train) [195][350/586] lr: 5.000000e-05 eta: 1:06:44 time: 0.466033 data_time: 0.024619 memory: 15239 loss_kpt: 0.000456 acc_pose: 0.901314 loss: 0.000456 2022/09/16 07:23:31 - mmengine - INFO - Epoch(train) [195][400/586] lr: 5.000000e-05 eta: 1:06:22 time: 0.461338 data_time: 0.023540 memory: 15239 loss_kpt: 0.000438 acc_pose: 0.926827 loss: 0.000438 2022/09/16 07:23:55 - mmengine - INFO - Epoch(train) [195][450/586] lr: 5.000000e-05 eta: 1:06:00 time: 0.462447 data_time: 0.023797 memory: 15239 loss_kpt: 0.000445 acc_pose: 0.855500 loss: 0.000445 2022/09/16 07:24:18 - mmengine - INFO - Epoch(train) [195][500/586] lr: 5.000000e-05 eta: 1:05:37 time: 0.471449 data_time: 0.027421 memory: 15239 loss_kpt: 0.000443 acc_pose: 0.913161 loss: 0.000443 2022/09/16 07:24:42 - mmengine - INFO - Epoch(train) [195][550/586] lr: 5.000000e-05 eta: 1:05:15 time: 0.469907 data_time: 0.025136 memory: 15239 loss_kpt: 0.000447 acc_pose: 0.804652 loss: 0.000447 2022/09/16 07:24:58 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 07:24:58 - mmengine - INFO - Saving checkpoint at 195 epochs 2022/09/16 07:25:30 - mmengine - INFO - Epoch(train) [196][50/586] lr: 5.000000e-05 eta: 1:04:36 time: 0.488320 data_time: 0.028690 memory: 15239 loss_kpt: 0.000445 acc_pose: 0.804357 loss: 0.000445 2022/09/16 07:25:53 - mmengine - INFO - Epoch(train) [196][100/586] lr: 5.000000e-05 eta: 1:04:14 time: 0.466692 data_time: 0.027905 memory: 15239 loss_kpt: 0.000447 acc_pose: 0.908071 loss: 0.000447 2022/09/16 07:26:17 - mmengine - INFO - Epoch(train) [196][150/586] lr: 5.000000e-05 eta: 1:03:52 time: 0.476061 data_time: 0.023707 memory: 15239 loss_kpt: 0.000462 acc_pose: 0.902547 loss: 0.000462 2022/09/16 07:26:41 - mmengine - INFO - Epoch(train) [196][200/586] lr: 5.000000e-05 eta: 1:03:30 time: 0.475832 data_time: 0.023763 memory: 15239 loss_kpt: 0.000454 acc_pose: 0.890005 loss: 0.000454 2022/09/16 07:27:04 - mmengine - INFO - Epoch(train) [196][250/586] lr: 5.000000e-05 eta: 1:03:08 time: 0.471921 data_time: 0.023567 memory: 15239 loss_kpt: 0.000429 acc_pose: 0.927663 loss: 0.000429 2022/09/16 07:27:28 - mmengine - INFO - Epoch(train) [196][300/586] lr: 5.000000e-05 eta: 1:02:46 time: 0.468168 data_time: 0.025866 memory: 15239 loss_kpt: 0.000456 acc_pose: 0.847349 loss: 0.000456 2022/09/16 07:27:51 - mmengine - INFO - Epoch(train) [196][350/586] lr: 5.000000e-05 eta: 1:02:24 time: 0.465872 data_time: 0.024471 memory: 15239 loss_kpt: 0.000459 acc_pose: 0.874031 loss: 0.000459 2022/09/16 07:28:15 - mmengine - INFO - Epoch(train) [196][400/586] lr: 5.000000e-05 eta: 1:02:02 time: 0.467491 data_time: 0.024075 memory: 15239 loss_kpt: 0.000436 acc_pose: 0.847410 loss: 0.000436 2022/09/16 07:28:38 - mmengine - INFO - Epoch(train) [196][450/586] lr: 5.000000e-05 eta: 1:01:39 time: 0.460129 data_time: 0.027734 memory: 15239 loss_kpt: 0.000458 acc_pose: 0.931798 loss: 0.000458 2022/09/16 07:29:01 - mmengine - INFO - Epoch(train) [196][500/586] lr: 5.000000e-05 eta: 1:01:17 time: 0.472288 data_time: 0.023991 memory: 15239 loss_kpt: 0.000437 acc_pose: 0.922518 loss: 0.000437 2022/09/16 07:29:25 - mmengine - INFO - Epoch(train) [196][550/586] lr: 5.000000e-05 eta: 1:00:55 time: 0.472425 data_time: 0.024523 memory: 15239 loss_kpt: 0.000439 acc_pose: 0.872605 loss: 0.000439 2022/09/16 07:29:42 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 07:29:42 - mmengine - INFO - Saving checkpoint at 196 epochs 2022/09/16 07:30:12 - mmengine - INFO - Epoch(train) [197][50/586] lr: 5.000000e-05 eta: 1:00:16 time: 0.475596 data_time: 0.032381 memory: 15239 loss_kpt: 0.000459 acc_pose: 0.845420 loss: 0.000459 2022/09/16 07:30:36 - mmengine - INFO - Epoch(train) [197][100/586] lr: 5.000000e-05 eta: 0:59:54 time: 0.476308 data_time: 0.031737 memory: 15239 loss_kpt: 0.000444 acc_pose: 0.900883 loss: 0.000444 2022/09/16 07:30:57 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 07:31:00 - mmengine - INFO - Epoch(train) [197][150/586] lr: 5.000000e-05 eta: 0:59:32 time: 0.467220 data_time: 0.027829 memory: 15239 loss_kpt: 0.000476 acc_pose: 0.879822 loss: 0.000476 2022/09/16 07:31:24 - mmengine - INFO - Epoch(train) [197][200/586] lr: 5.000000e-05 eta: 0:59:10 time: 0.477856 data_time: 0.029335 memory: 15239 loss_kpt: 0.000436 acc_pose: 0.894025 loss: 0.000436 2022/09/16 07:31:47 - mmengine - INFO - Epoch(train) [197][250/586] lr: 5.000000e-05 eta: 0:58:48 time: 0.469621 data_time: 0.024987 memory: 15239 loss_kpt: 0.000445 acc_pose: 0.929648 loss: 0.000445 2022/09/16 07:32:10 - mmengine - INFO - Epoch(train) [197][300/586] lr: 5.000000e-05 eta: 0:58:26 time: 0.465545 data_time: 0.024714 memory: 15239 loss_kpt: 0.000455 acc_pose: 0.887730 loss: 0.000455 2022/09/16 07:32:34 - mmengine - INFO - Epoch(train) [197][350/586] lr: 5.000000e-05 eta: 0:58:04 time: 0.468947 data_time: 0.028208 memory: 15239 loss_kpt: 0.000453 acc_pose: 0.873182 loss: 0.000453 2022/09/16 07:32:57 - mmengine - INFO - Epoch(train) [197][400/586] lr: 5.000000e-05 eta: 0:57:42 time: 0.462939 data_time: 0.024110 memory: 15239 loss_kpt: 0.000439 acc_pose: 0.895618 loss: 0.000439 2022/09/16 07:33:21 - mmengine - INFO - Epoch(train) [197][450/586] lr: 5.000000e-05 eta: 0:57:19 time: 0.470333 data_time: 0.024321 memory: 15239 loss_kpt: 0.000447 acc_pose: 0.912803 loss: 0.000447 2022/09/16 07:33:44 - mmengine - INFO - Epoch(train) [197][500/586] lr: 5.000000e-05 eta: 0:56:57 time: 0.466014 data_time: 0.024112 memory: 15239 loss_kpt: 0.000436 acc_pose: 0.907554 loss: 0.000436 2022/09/16 07:34:07 - mmengine - INFO - Epoch(train) [197][550/586] lr: 5.000000e-05 eta: 0:56:35 time: 0.462130 data_time: 0.024171 memory: 15239 loss_kpt: 0.000450 acc_pose: 0.923099 loss: 0.000450 2022/09/16 07:34:24 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 07:34:24 - mmengine - INFO - Saving checkpoint at 197 epochs 2022/09/16 07:34:55 - mmengine - INFO - Epoch(train) [198][50/586] lr: 5.000000e-05 eta: 0:55:56 time: 0.482761 data_time: 0.030567 memory: 15239 loss_kpt: 0.000450 acc_pose: 0.888099 loss: 0.000450 2022/09/16 07:35:19 - mmengine - INFO - Epoch(train) [198][100/586] lr: 5.000000e-05 eta: 0:55:34 time: 0.480883 data_time: 0.025459 memory: 15239 loss_kpt: 0.000446 acc_pose: 0.844871 loss: 0.000446 2022/09/16 07:35:43 - mmengine - INFO - Epoch(train) [198][150/586] lr: 5.000000e-05 eta: 0:55:12 time: 0.463729 data_time: 0.023530 memory: 15239 loss_kpt: 0.000466 acc_pose: 0.845070 loss: 0.000466 2022/09/16 07:36:06 - mmengine - INFO - Epoch(train) [198][200/586] lr: 5.000000e-05 eta: 0:54:50 time: 0.468796 data_time: 0.024633 memory: 15239 loss_kpt: 0.000451 acc_pose: 0.841218 loss: 0.000451 2022/09/16 07:36:29 - mmengine - INFO - Epoch(train) [198][250/586] lr: 5.000000e-05 eta: 0:54:28 time: 0.468129 data_time: 0.024078 memory: 15239 loss_kpt: 0.000443 acc_pose: 0.928439 loss: 0.000443 2022/09/16 07:36:53 - mmengine - INFO - Epoch(train) [198][300/586] lr: 5.000000e-05 eta: 0:54:06 time: 0.461774 data_time: 0.024136 memory: 15239 loss_kpt: 0.000467 acc_pose: 0.890173 loss: 0.000467 2022/09/16 07:37:16 - mmengine - INFO - Epoch(train) [198][350/586] lr: 5.000000e-05 eta: 0:53:44 time: 0.469354 data_time: 0.024968 memory: 15239 loss_kpt: 0.000442 acc_pose: 0.880961 loss: 0.000442 2022/09/16 07:37:40 - mmengine - INFO - Epoch(train) [198][400/586] lr: 5.000000e-05 eta: 0:53:21 time: 0.475820 data_time: 0.024919 memory: 15239 loss_kpt: 0.000444 acc_pose: 0.907606 loss: 0.000444 2022/09/16 07:38:03 - mmengine - INFO - Epoch(train) [198][450/586] lr: 5.000000e-05 eta: 0:52:59 time: 0.472119 data_time: 0.023733 memory: 15239 loss_kpt: 0.000453 acc_pose: 0.905449 loss: 0.000453 2022/09/16 07:38:27 - mmengine - INFO - Epoch(train) [198][500/586] lr: 5.000000e-05 eta: 0:52:37 time: 0.460765 data_time: 0.023789 memory: 15239 loss_kpt: 0.000453 acc_pose: 0.860595 loss: 0.000453 2022/09/16 07:38:50 - mmengine - INFO - Epoch(train) [198][550/586] lr: 5.000000e-05 eta: 0:52:15 time: 0.472394 data_time: 0.025560 memory: 15239 loss_kpt: 0.000442 acc_pose: 0.878608 loss: 0.000442 2022/09/16 07:38:54 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 07:39:07 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 07:39:07 - mmengine - INFO - Saving checkpoint at 198 epochs 2022/09/16 07:39:38 - mmengine - INFO - Epoch(train) [199][50/586] lr: 5.000000e-05 eta: 0:51:36 time: 0.475670 data_time: 0.035729 memory: 15239 loss_kpt: 0.000458 acc_pose: 0.909133 loss: 0.000458 2022/09/16 07:40:01 - mmengine - INFO - Epoch(train) [199][100/586] lr: 5.000000e-05 eta: 0:51:14 time: 0.468969 data_time: 0.028051 memory: 15239 loss_kpt: 0.000447 acc_pose: 0.911571 loss: 0.000447 2022/09/16 07:40:25 - mmengine - INFO - Epoch(train) [199][150/586] lr: 5.000000e-05 eta: 0:50:52 time: 0.478159 data_time: 0.030673 memory: 15239 loss_kpt: 0.000445 acc_pose: 0.868799 loss: 0.000445 2022/09/16 07:40:48 - mmengine - INFO - Epoch(train) [199][200/586] lr: 5.000000e-05 eta: 0:50:30 time: 0.461183 data_time: 0.027085 memory: 15239 loss_kpt: 0.000446 acc_pose: 0.928390 loss: 0.000446 2022/09/16 07:41:11 - mmengine - INFO - Epoch(train) [199][250/586] lr: 5.000000e-05 eta: 0:50:08 time: 0.464254 data_time: 0.024390 memory: 15239 loss_kpt: 0.000454 acc_pose: 0.895874 loss: 0.000454 2022/09/16 07:41:35 - mmengine - INFO - Epoch(train) [199][300/586] lr: 5.000000e-05 eta: 0:49:46 time: 0.466368 data_time: 0.030082 memory: 15239 loss_kpt: 0.000452 acc_pose: 0.880018 loss: 0.000452 2022/09/16 07:41:58 - mmengine - INFO - Epoch(train) [199][350/586] lr: 5.000000e-05 eta: 0:49:23 time: 0.463780 data_time: 0.024134 memory: 15239 loss_kpt: 0.000458 acc_pose: 0.919889 loss: 0.000458 2022/09/16 07:42:21 - mmengine - INFO - Epoch(train) [199][400/586] lr: 5.000000e-05 eta: 0:49:01 time: 0.470811 data_time: 0.025175 memory: 15239 loss_kpt: 0.000472 acc_pose: 0.902738 loss: 0.000472 2022/09/16 07:42:45 - mmengine - INFO - Epoch(train) [199][450/586] lr: 5.000000e-05 eta: 0:48:39 time: 0.472127 data_time: 0.031618 memory: 15239 loss_kpt: 0.000449 acc_pose: 0.929031 loss: 0.000449 2022/09/16 07:43:08 - mmengine - INFO - Epoch(train) [199][500/586] lr: 5.000000e-05 eta: 0:48:17 time: 0.467108 data_time: 0.024810 memory: 15239 loss_kpt: 0.000446 acc_pose: 0.876945 loss: 0.000446 2022/09/16 07:43:32 - mmengine - INFO - Epoch(train) [199][550/586] lr: 5.000000e-05 eta: 0:47:55 time: 0.469954 data_time: 0.024011 memory: 15239 loss_kpt: 0.000442 acc_pose: 0.916363 loss: 0.000442 2022/09/16 07:43:49 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 07:43:49 - mmengine - INFO - Saving checkpoint at 199 epochs 2022/09/16 07:44:20 - mmengine - INFO - Epoch(train) [200][50/586] lr: 5.000000e-05 eta: 0:47:16 time: 0.474730 data_time: 0.031226 memory: 15239 loss_kpt: 0.000456 acc_pose: 0.905644 loss: 0.000456 2022/09/16 07:44:43 - mmengine - INFO - Epoch(train) [200][100/586] lr: 5.000000e-05 eta: 0:46:54 time: 0.466248 data_time: 0.031018 memory: 15239 loss_kpt: 0.000445 acc_pose: 0.887427 loss: 0.000445 2022/09/16 07:45:06 - mmengine - INFO - Epoch(train) [200][150/586] lr: 5.000000e-05 eta: 0:46:32 time: 0.461697 data_time: 0.027686 memory: 15239 loss_kpt: 0.000445 acc_pose: 0.898475 loss: 0.000445 2022/09/16 07:45:30 - mmengine - INFO - Epoch(train) [200][200/586] lr: 5.000000e-05 eta: 0:46:10 time: 0.475043 data_time: 0.029043 memory: 15239 loss_kpt: 0.000435 acc_pose: 0.938823 loss: 0.000435 2022/09/16 07:45:53 - mmengine - INFO - Epoch(train) [200][250/586] lr: 5.000000e-05 eta: 0:45:48 time: 0.456582 data_time: 0.028146 memory: 15239 loss_kpt: 0.000467 acc_pose: 0.923117 loss: 0.000467 2022/09/16 07:46:17 - mmengine - INFO - Epoch(train) [200][300/586] lr: 5.000000e-05 eta: 0:45:26 time: 0.473974 data_time: 0.031465 memory: 15239 loss_kpt: 0.000442 acc_pose: 0.928911 loss: 0.000442 2022/09/16 07:46:40 - mmengine - INFO - Epoch(train) [200][350/586] lr: 5.000000e-05 eta: 0:45:03 time: 0.467707 data_time: 0.028232 memory: 15239 loss_kpt: 0.000444 acc_pose: 0.902821 loss: 0.000444 2022/09/16 07:46:57 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 07:47:03 - mmengine - INFO - Epoch(train) [200][400/586] lr: 5.000000e-05 eta: 0:44:41 time: 0.460994 data_time: 0.031149 memory: 15239 loss_kpt: 0.000459 acc_pose: 0.841954 loss: 0.000459 2022/09/16 07:47:26 - mmengine - INFO - Epoch(train) [200][450/586] lr: 5.000000e-05 eta: 0:44:19 time: 0.466910 data_time: 0.024053 memory: 15239 loss_kpt: 0.000454 acc_pose: 0.887014 loss: 0.000454 2022/09/16 07:47:50 - mmengine - INFO - Epoch(train) [200][500/586] lr: 5.000000e-05 eta: 0:43:57 time: 0.473115 data_time: 0.025903 memory: 15239 loss_kpt: 0.000465 acc_pose: 0.878892 loss: 0.000465 2022/09/16 07:48:13 - mmengine - INFO - Epoch(train) [200][550/586] lr: 5.000000e-05 eta: 0:43:35 time: 0.466521 data_time: 0.023935 memory: 15239 loss_kpt: 0.000433 acc_pose: 0.906375 loss: 0.000433 2022/09/16 07:48:30 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 07:48:30 - mmengine - INFO - Saving checkpoint at 200 epochs 2022/09/16 07:48:50 - mmengine - INFO - Epoch(val) [200][50/407] eta: 0:01:33 time: 0.262246 data_time: 0.016620 memory: 15239 2022/09/16 07:49:03 - mmengine - INFO - Epoch(val) [200][100/407] eta: 0:01:17 time: 0.252348 data_time: 0.008366 memory: 2064 2022/09/16 07:49:16 - mmengine - INFO - Epoch(val) [200][150/407] eta: 0:01:05 time: 0.253241 data_time: 0.012102 memory: 2064 2022/09/16 07:49:28 - mmengine - INFO - Epoch(val) [200][200/407] eta: 0:00:51 time: 0.250677 data_time: 0.008512 memory: 2064 2022/09/16 07:49:41 - mmengine - INFO - Epoch(val) [200][250/407] eta: 0:00:39 time: 0.250066 data_time: 0.008220 memory: 2064 2022/09/16 07:49:53 - mmengine - INFO - Epoch(val) [200][300/407] eta: 0:00:27 time: 0.252551 data_time: 0.008459 memory: 2064 2022/09/16 07:50:06 - mmengine - INFO - Epoch(val) [200][350/407] eta: 0:00:14 time: 0.249637 data_time: 0.008130 memory: 2064 2022/09/16 07:50:18 - mmengine - INFO - Epoch(val) [200][400/407] eta: 0:00:01 time: 0.247083 data_time: 0.007973 memory: 2064 2022/09/16 07:50:53 - mmengine - INFO - Evaluating CocoMetric... 2022/09/16 07:51:06 - mmengine - INFO - Epoch(val) [200][407/407] coco/AP: 0.771938 coco/AP .5: 0.911559 coco/AP .75: 0.833066 coco/AP (M): 0.732724 coco/AP (L): 0.842405 coco/AR: 0.819884 coco/AR .5: 0.946788 coco/AR .75: 0.876417 coco/AR (M): 0.777001 coco/AR (L): 0.882720 2022/09/16 07:51:31 - mmengine - INFO - Epoch(train) [201][50/586] lr: 5.000000e-06 eta: 0:42:56 time: 0.493485 data_time: 0.030649 memory: 15239 loss_kpt: 0.000467 acc_pose: 0.870121 loss: 0.000467 2022/09/16 07:51:55 - mmengine - INFO - Epoch(train) [201][100/586] lr: 5.000000e-06 eta: 0:42:34 time: 0.467438 data_time: 0.024210 memory: 15239 loss_kpt: 0.000452 acc_pose: 0.874218 loss: 0.000452 2022/09/16 07:52:18 - mmengine - INFO - Epoch(train) [201][150/586] lr: 5.000000e-06 eta: 0:42:12 time: 0.473671 data_time: 0.023745 memory: 15239 loss_kpt: 0.000449 acc_pose: 0.908508 loss: 0.000449 2022/09/16 07:52:42 - mmengine - INFO - Epoch(train) [201][200/586] lr: 5.000000e-06 eta: 0:41:50 time: 0.478577 data_time: 0.025898 memory: 15239 loss_kpt: 0.000453 acc_pose: 0.889286 loss: 0.000453 2022/09/16 07:53:06 - mmengine - INFO - Epoch(train) [201][250/586] lr: 5.000000e-06 eta: 0:41:28 time: 0.467641 data_time: 0.025347 memory: 15239 loss_kpt: 0.000466 acc_pose: 0.895318 loss: 0.000466 2022/09/16 07:53:29 - mmengine - INFO - Epoch(train) [201][300/586] lr: 5.000000e-06 eta: 0:41:06 time: 0.468167 data_time: 0.024219 memory: 15239 loss_kpt: 0.000439 acc_pose: 0.843950 loss: 0.000439 2022/09/16 07:53:52 - mmengine - INFO - Epoch(train) [201][350/586] lr: 5.000000e-06 eta: 0:40:43 time: 0.467894 data_time: 0.024017 memory: 15239 loss_kpt: 0.000444 acc_pose: 0.852304 loss: 0.000444 2022/09/16 07:54:16 - mmengine - INFO - Epoch(train) [201][400/586] lr: 5.000000e-06 eta: 0:40:21 time: 0.466857 data_time: 0.028038 memory: 15239 loss_kpt: 0.000450 acc_pose: 0.896856 loss: 0.000450 2022/09/16 07:54:39 - mmengine - INFO - Epoch(train) [201][450/586] lr: 5.000000e-06 eta: 0:39:59 time: 0.463385 data_time: 0.024059 memory: 15239 loss_kpt: 0.000459 acc_pose: 0.920025 loss: 0.000459 2022/09/16 07:55:02 - mmengine - INFO - Epoch(train) [201][500/586] lr: 5.000000e-06 eta: 0:39:37 time: 0.465505 data_time: 0.024226 memory: 15239 loss_kpt: 0.000451 acc_pose: 0.889740 loss: 0.000451 2022/09/16 07:55:26 - mmengine - INFO - Epoch(train) [201][550/586] lr: 5.000000e-06 eta: 0:39:15 time: 0.465219 data_time: 0.024375 memory: 15239 loss_kpt: 0.000454 acc_pose: 0.830984 loss: 0.000454 2022/09/16 07:55:43 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 07:55:43 - mmengine - INFO - Saving checkpoint at 201 epochs 2022/09/16 07:56:14 - mmengine - INFO - Epoch(train) [202][50/586] lr: 5.000000e-06 eta: 0:38:36 time: 0.477540 data_time: 0.034374 memory: 15239 loss_kpt: 0.000447 acc_pose: 0.891970 loss: 0.000447 2022/09/16 07:56:37 - mmengine - INFO - Epoch(train) [202][100/586] lr: 5.000000e-06 eta: 0:38:14 time: 0.470122 data_time: 0.027172 memory: 15239 loss_kpt: 0.000441 acc_pose: 0.841591 loss: 0.000441 2022/09/16 07:57:01 - mmengine - INFO - Epoch(train) [202][150/586] lr: 5.000000e-06 eta: 0:37:52 time: 0.468381 data_time: 0.030482 memory: 15239 loss_kpt: 0.000454 acc_pose: 0.915175 loss: 0.000454 2022/09/16 07:57:24 - mmengine - INFO - Epoch(train) [202][200/586] lr: 5.000000e-06 eta: 0:37:30 time: 0.474443 data_time: 0.027973 memory: 15239 loss_kpt: 0.000458 acc_pose: 0.891419 loss: 0.000458 2022/09/16 07:57:31 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 07:57:48 - mmengine - INFO - Epoch(train) [202][250/586] lr: 5.000000e-06 eta: 0:37:08 time: 0.465961 data_time: 0.027926 memory: 15239 loss_kpt: 0.000451 acc_pose: 0.864503 loss: 0.000451 2022/09/16 07:58:11 - mmengine - INFO - Epoch(train) [202][300/586] lr: 5.000000e-06 eta: 0:36:46 time: 0.471893 data_time: 0.028265 memory: 15239 loss_kpt: 0.000466 acc_pose: 0.876406 loss: 0.000466 2022/09/16 07:58:35 - mmengine - INFO - Epoch(train) [202][350/586] lr: 5.000000e-06 eta: 0:36:23 time: 0.471570 data_time: 0.024470 memory: 15239 loss_kpt: 0.000454 acc_pose: 0.859885 loss: 0.000454 2022/09/16 07:58:58 - mmengine - INFO - Epoch(train) [202][400/586] lr: 5.000000e-06 eta: 0:36:01 time: 0.467775 data_time: 0.027045 memory: 15239 loss_kpt: 0.000448 acc_pose: 0.878026 loss: 0.000448 2022/09/16 07:59:22 - mmengine - INFO - Epoch(train) [202][450/586] lr: 5.000000e-06 eta: 0:35:39 time: 0.467496 data_time: 0.024923 memory: 15239 loss_kpt: 0.000450 acc_pose: 0.799875 loss: 0.000450 2022/09/16 07:59:45 - mmengine - INFO - Epoch(train) [202][500/586] lr: 5.000000e-06 eta: 0:35:17 time: 0.466124 data_time: 0.024631 memory: 15239 loss_kpt: 0.000446 acc_pose: 0.887364 loss: 0.000446 2022/09/16 08:00:09 - mmengine - INFO - Epoch(train) [202][550/586] lr: 5.000000e-06 eta: 0:34:55 time: 0.469455 data_time: 0.028455 memory: 15239 loss_kpt: 0.000456 acc_pose: 0.895694 loss: 0.000456 2022/09/16 08:00:25 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 08:00:25 - mmengine - INFO - Saving checkpoint at 202 epochs 2022/09/16 08:00:57 - mmengine - INFO - Epoch(train) [203][50/586] lr: 5.000000e-06 eta: 0:34:16 time: 0.476721 data_time: 0.034801 memory: 15239 loss_kpt: 0.000438 acc_pose: 0.897593 loss: 0.000438 2022/09/16 08:01:20 - mmengine - INFO - Epoch(train) [203][100/586] lr: 5.000000e-06 eta: 0:33:54 time: 0.460458 data_time: 0.028489 memory: 15239 loss_kpt: 0.000449 acc_pose: 0.892603 loss: 0.000449 2022/09/16 08:01:43 - mmengine - INFO - Epoch(train) [203][150/586] lr: 5.000000e-06 eta: 0:33:32 time: 0.470127 data_time: 0.033452 memory: 15239 loss_kpt: 0.000442 acc_pose: 0.923383 loss: 0.000442 2022/09/16 08:02:06 - mmengine - INFO - Epoch(train) [203][200/586] lr: 5.000000e-06 eta: 0:33:10 time: 0.467037 data_time: 0.024264 memory: 15239 loss_kpt: 0.000434 acc_pose: 0.920149 loss: 0.000434 2022/09/16 08:02:30 - mmengine - INFO - Epoch(train) [203][250/586] lr: 5.000000e-06 eta: 0:32:48 time: 0.461924 data_time: 0.024157 memory: 15239 loss_kpt: 0.000446 acc_pose: 0.894921 loss: 0.000446 2022/09/16 08:02:53 - mmengine - INFO - Epoch(train) [203][300/586] lr: 5.000000e-06 eta: 0:32:26 time: 0.469350 data_time: 0.027188 memory: 15239 loss_kpt: 0.000448 acc_pose: 0.928001 loss: 0.000448 2022/09/16 08:03:16 - mmengine - INFO - Epoch(train) [203][350/586] lr: 5.000000e-06 eta: 0:32:03 time: 0.466414 data_time: 0.024655 memory: 15239 loss_kpt: 0.000455 acc_pose: 0.875608 loss: 0.000455 2022/09/16 08:03:39 - mmengine - INFO - Epoch(train) [203][400/586] lr: 5.000000e-06 eta: 0:31:41 time: 0.460336 data_time: 0.023666 memory: 15239 loss_kpt: 0.000459 acc_pose: 0.840672 loss: 0.000459 2022/09/16 08:04:03 - mmengine - INFO - Epoch(train) [203][450/586] lr: 5.000000e-06 eta: 0:31:19 time: 0.475579 data_time: 0.027594 memory: 15239 loss_kpt: 0.000451 acc_pose: 0.918247 loss: 0.000451 2022/09/16 08:04:27 - mmengine - INFO - Epoch(train) [203][500/586] lr: 5.000000e-06 eta: 0:30:57 time: 0.468855 data_time: 0.024056 memory: 15239 loss_kpt: 0.000443 acc_pose: 0.874499 loss: 0.000443 2022/09/16 08:04:50 - mmengine - INFO - Epoch(train) [203][550/586] lr: 5.000000e-06 eta: 0:30:35 time: 0.464999 data_time: 0.024620 memory: 15239 loss_kpt: 0.000436 acc_pose: 0.872499 loss: 0.000436 2022/09/16 08:05:07 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 08:05:07 - mmengine - INFO - Saving checkpoint at 203 epochs 2022/09/16 08:05:34 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 08:05:38 - mmengine - INFO - Epoch(train) [204][50/586] lr: 5.000000e-06 eta: 0:29:56 time: 0.471647 data_time: 0.034985 memory: 15239 loss_kpt: 0.000443 acc_pose: 0.804026 loss: 0.000443 2022/09/16 08:06:01 - mmengine - INFO - Epoch(train) [204][100/586] lr: 5.000000e-06 eta: 0:29:34 time: 0.465352 data_time: 0.029109 memory: 15239 loss_kpt: 0.000451 acc_pose: 0.896219 loss: 0.000451 2022/09/16 08:06:24 - mmengine - INFO - Epoch(train) [204][150/586] lr: 5.000000e-06 eta: 0:29:12 time: 0.467171 data_time: 0.027120 memory: 15239 loss_kpt: 0.000458 acc_pose: 0.880307 loss: 0.000458 2022/09/16 08:06:48 - mmengine - INFO - Epoch(train) [204][200/586] lr: 5.000000e-06 eta: 0:28:50 time: 0.474667 data_time: 0.028998 memory: 15239 loss_kpt: 0.000455 acc_pose: 0.949826 loss: 0.000455 2022/09/16 08:07:12 - mmengine - INFO - Epoch(train) [204][250/586] lr: 5.000000e-06 eta: 0:28:28 time: 0.469519 data_time: 0.028709 memory: 15239 loss_kpt: 0.000450 acc_pose: 0.932432 loss: 0.000450 2022/09/16 08:07:35 - mmengine - INFO - Epoch(train) [204][300/586] lr: 5.000000e-06 eta: 0:28:06 time: 0.471608 data_time: 0.035889 memory: 15239 loss_kpt: 0.000452 acc_pose: 0.907554 loss: 0.000452 2022/09/16 08:07:59 - mmengine - INFO - Epoch(train) [204][350/586] lr: 5.000000e-06 eta: 0:27:43 time: 0.466605 data_time: 0.028350 memory: 15239 loss_kpt: 0.000449 acc_pose: 0.883564 loss: 0.000449 2022/09/16 08:08:22 - mmengine - INFO - Epoch(train) [204][400/586] lr: 5.000000e-06 eta: 0:27:21 time: 0.463359 data_time: 0.028163 memory: 15239 loss_kpt: 0.000446 acc_pose: 0.877206 loss: 0.000446 2022/09/16 08:08:45 - mmengine - INFO - Epoch(train) [204][450/586] lr: 5.000000e-06 eta: 0:26:59 time: 0.465393 data_time: 0.027426 memory: 15239 loss_kpt: 0.000438 acc_pose: 0.871773 loss: 0.000438 2022/09/16 08:09:09 - mmengine - INFO - Epoch(train) [204][500/586] lr: 5.000000e-06 eta: 0:26:37 time: 0.470467 data_time: 0.031696 memory: 15239 loss_kpt: 0.000426 acc_pose: 0.880169 loss: 0.000426 2022/09/16 08:09:32 - mmengine - INFO - Epoch(train) [204][550/586] lr: 5.000000e-06 eta: 0:26:15 time: 0.461583 data_time: 0.027639 memory: 15239 loss_kpt: 0.000449 acc_pose: 0.895819 loss: 0.000449 2022/09/16 08:09:49 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 08:09:49 - mmengine - INFO - Saving checkpoint at 204 epochs 2022/09/16 08:10:20 - mmengine - INFO - Epoch(train) [205][50/586] lr: 5.000000e-06 eta: 0:25:36 time: 0.485271 data_time: 0.036030 memory: 15239 loss_kpt: 0.000442 acc_pose: 0.900178 loss: 0.000442 2022/09/16 08:10:43 - mmengine - INFO - Epoch(train) [205][100/586] lr: 5.000000e-06 eta: 0:25:14 time: 0.456696 data_time: 0.024648 memory: 15239 loss_kpt: 0.000448 acc_pose: 0.877932 loss: 0.000448 2022/09/16 08:11:07 - mmengine - INFO - Epoch(train) [205][150/586] lr: 5.000000e-06 eta: 0:24:52 time: 0.476132 data_time: 0.028230 memory: 15239 loss_kpt: 0.000450 acc_pose: 0.915459 loss: 0.000450 2022/09/16 08:11:30 - mmengine - INFO - Epoch(train) [205][200/586] lr: 5.000000e-06 eta: 0:24:30 time: 0.462922 data_time: 0.024711 memory: 15239 loss_kpt: 0.000452 acc_pose: 0.913331 loss: 0.000452 2022/09/16 08:11:53 - mmengine - INFO - Epoch(train) [205][250/586] lr: 5.000000e-06 eta: 0:24:08 time: 0.465511 data_time: 0.024778 memory: 15239 loss_kpt: 0.000437 acc_pose: 0.888255 loss: 0.000437 2022/09/16 08:12:17 - mmengine - INFO - Epoch(train) [205][300/586] lr: 5.000000e-06 eta: 0:23:46 time: 0.474188 data_time: 0.024346 memory: 15239 loss_kpt: 0.000449 acc_pose: 0.892799 loss: 0.000449 2022/09/16 08:12:40 - mmengine - INFO - Epoch(train) [205][350/586] lr: 5.000000e-06 eta: 0:23:24 time: 0.463839 data_time: 0.024052 memory: 15239 loss_kpt: 0.000438 acc_pose: 0.890197 loss: 0.000438 2022/09/16 08:13:04 - mmengine - INFO - Epoch(train) [205][400/586] lr: 5.000000e-06 eta: 0:23:01 time: 0.471991 data_time: 0.024946 memory: 15239 loss_kpt: 0.000451 acc_pose: 0.865944 loss: 0.000451 2022/09/16 08:13:27 - mmengine - INFO - Epoch(train) [205][450/586] lr: 5.000000e-06 eta: 0:22:39 time: 0.473178 data_time: 0.024968 memory: 15239 loss_kpt: 0.000459 acc_pose: 0.884152 loss: 0.000459 2022/09/16 08:13:30 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 08:13:52 - mmengine - INFO - Epoch(train) [205][500/586] lr: 5.000000e-06 eta: 0:22:17 time: 0.486073 data_time: 0.023882 memory: 15239 loss_kpt: 0.000439 acc_pose: 0.861708 loss: 0.000439 2022/09/16 08:14:15 - mmengine - INFO - Epoch(train) [205][550/586] lr: 5.000000e-06 eta: 0:21:55 time: 0.461620 data_time: 0.024757 memory: 15239 loss_kpt: 0.000442 acc_pose: 0.911259 loss: 0.000442 2022/09/16 08:14:32 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 08:14:32 - mmengine - INFO - Saving checkpoint at 205 epochs 2022/09/16 08:15:03 - mmengine - INFO - Epoch(train) [206][50/586] lr: 5.000000e-06 eta: 0:21:17 time: 0.474964 data_time: 0.031749 memory: 15239 loss_kpt: 0.000439 acc_pose: 0.914539 loss: 0.000439 2022/09/16 08:15:27 - mmengine - INFO - Epoch(train) [206][100/586] lr: 5.000000e-06 eta: 0:20:54 time: 0.464620 data_time: 0.032383 memory: 15239 loss_kpt: 0.000433 acc_pose: 0.872695 loss: 0.000433 2022/09/16 08:15:50 - mmengine - INFO - Epoch(train) [206][150/586] lr: 5.000000e-06 eta: 0:20:32 time: 0.467898 data_time: 0.028737 memory: 15239 loss_kpt: 0.000456 acc_pose: 0.852479 loss: 0.000456 2022/09/16 08:16:13 - mmengine - INFO - Epoch(train) [206][200/586] lr: 5.000000e-06 eta: 0:20:10 time: 0.468231 data_time: 0.027766 memory: 15239 loss_kpt: 0.000433 acc_pose: 0.890188 loss: 0.000433 2022/09/16 08:16:36 - mmengine - INFO - Epoch(train) [206][250/586] lr: 5.000000e-06 eta: 0:19:48 time: 0.458507 data_time: 0.029947 memory: 15239 loss_kpt: 0.000456 acc_pose: 0.894870 loss: 0.000456 2022/09/16 08:17:00 - mmengine - INFO - Epoch(train) [206][300/586] lr: 5.000000e-06 eta: 0:19:26 time: 0.469276 data_time: 0.025835 memory: 15239 loss_kpt: 0.000443 acc_pose: 0.912750 loss: 0.000443 2022/09/16 08:17:24 - mmengine - INFO - Epoch(train) [206][350/586] lr: 5.000000e-06 eta: 0:19:04 time: 0.478402 data_time: 0.024789 memory: 15239 loss_kpt: 0.000452 acc_pose: 0.882951 loss: 0.000452 2022/09/16 08:17:48 - mmengine - INFO - Epoch(train) [206][400/586] lr: 5.000000e-06 eta: 0:18:41 time: 0.474824 data_time: 0.024741 memory: 15239 loss_kpt: 0.000443 acc_pose: 0.954355 loss: 0.000443 2022/09/16 08:18:11 - mmengine - INFO - Epoch(train) [206][450/586] lr: 5.000000e-06 eta: 0:18:19 time: 0.476974 data_time: 0.024726 memory: 15239 loss_kpt: 0.000454 acc_pose: 0.838628 loss: 0.000454 2022/09/16 08:18:35 - mmengine - INFO - Epoch(train) [206][500/586] lr: 5.000000e-06 eta: 0:17:57 time: 0.468687 data_time: 0.024757 memory: 15239 loss_kpt: 0.000435 acc_pose: 0.872876 loss: 0.000435 2022/09/16 08:18:58 - mmengine - INFO - Epoch(train) [206][550/586] lr: 5.000000e-06 eta: 0:17:35 time: 0.463824 data_time: 0.023357 memory: 15239 loss_kpt: 0.000463 acc_pose: 0.935578 loss: 0.000463 2022/09/16 08:19:15 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 08:19:15 - mmengine - INFO - Saving checkpoint at 206 epochs 2022/09/16 08:19:46 - mmengine - INFO - Epoch(train) [207][50/586] lr: 5.000000e-06 eta: 0:16:57 time: 0.473675 data_time: 0.030664 memory: 15239 loss_kpt: 0.000449 acc_pose: 0.935137 loss: 0.000449 2022/09/16 08:20:09 - mmengine - INFO - Epoch(train) [207][100/586] lr: 5.000000e-06 eta: 0:16:34 time: 0.461650 data_time: 0.023974 memory: 15239 loss_kpt: 0.000460 acc_pose: 0.873307 loss: 0.000460 2022/09/16 08:20:33 - mmengine - INFO - Epoch(train) [207][150/586] lr: 5.000000e-06 eta: 0:16:12 time: 0.470418 data_time: 0.024050 memory: 15239 loss_kpt: 0.000445 acc_pose: 0.935487 loss: 0.000445 2022/09/16 08:20:56 - mmengine - INFO - Epoch(train) [207][200/586] lr: 5.000000e-06 eta: 0:15:50 time: 0.460654 data_time: 0.023727 memory: 15239 loss_kpt: 0.000447 acc_pose: 0.934753 loss: 0.000447 2022/09/16 08:21:19 - mmengine - INFO - Epoch(train) [207][250/586] lr: 5.000000e-06 eta: 0:15:28 time: 0.462155 data_time: 0.024915 memory: 15239 loss_kpt: 0.000440 acc_pose: 0.861329 loss: 0.000440 2022/09/16 08:21:35 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 08:21:42 - mmengine - INFO - Epoch(train) [207][300/586] lr: 5.000000e-06 eta: 0:15:06 time: 0.467151 data_time: 0.024750 memory: 15239 loss_kpt: 0.000460 acc_pose: 0.863669 loss: 0.000460 2022/09/16 08:22:06 - mmengine - INFO - Epoch(train) [207][350/586] lr: 5.000000e-06 eta: 0:14:44 time: 0.466444 data_time: 0.024174 memory: 15239 loss_kpt: 0.000447 acc_pose: 0.904281 loss: 0.000447 2022/09/16 08:22:29 - mmengine - INFO - Epoch(train) [207][400/586] lr: 5.000000e-06 eta: 0:14:22 time: 0.461521 data_time: 0.024034 memory: 15239 loss_kpt: 0.000444 acc_pose: 0.926199 loss: 0.000444 2022/09/16 08:22:52 - mmengine - INFO - Epoch(train) [207][450/586] lr: 5.000000e-06 eta: 0:13:59 time: 0.470786 data_time: 0.024261 memory: 15239 loss_kpt: 0.000454 acc_pose: 0.881296 loss: 0.000454 2022/09/16 08:23:15 - mmengine - INFO - Epoch(train) [207][500/586] lr: 5.000000e-06 eta: 0:13:37 time: 0.465580 data_time: 0.024278 memory: 15239 loss_kpt: 0.000442 acc_pose: 0.940070 loss: 0.000442 2022/09/16 08:23:39 - mmengine - INFO - Epoch(train) [207][550/586] lr: 5.000000e-06 eta: 0:13:15 time: 0.461314 data_time: 0.023903 memory: 15239 loss_kpt: 0.000445 acc_pose: 0.896633 loss: 0.000445 2022/09/16 08:23:55 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 08:23:56 - mmengine - INFO - Saving checkpoint at 207 epochs 2022/09/16 08:24:27 - mmengine - INFO - Epoch(train) [208][50/586] lr: 5.000000e-06 eta: 0:12:37 time: 0.478156 data_time: 0.028568 memory: 15239 loss_kpt: 0.000445 acc_pose: 0.895971 loss: 0.000445 2022/09/16 08:24:50 - mmengine - INFO - Epoch(train) [208][100/586] lr: 5.000000e-06 eta: 0:12:15 time: 0.467398 data_time: 0.024360 memory: 15239 loss_kpt: 0.000440 acc_pose: 0.899781 loss: 0.000440 2022/09/16 08:25:13 - mmengine - INFO - Epoch(train) [208][150/586] lr: 5.000000e-06 eta: 0:11:52 time: 0.468536 data_time: 0.024332 memory: 15239 loss_kpt: 0.000442 acc_pose: 0.872761 loss: 0.000442 2022/09/16 08:25:37 - mmengine - INFO - Epoch(train) [208][200/586] lr: 5.000000e-06 eta: 0:11:30 time: 0.473876 data_time: 0.024666 memory: 15239 loss_kpt: 0.000439 acc_pose: 0.847322 loss: 0.000439 2022/09/16 08:26:00 - mmengine - INFO - Epoch(train) [208][250/586] lr: 5.000000e-06 eta: 0:11:08 time: 0.457258 data_time: 0.025208 memory: 15239 loss_kpt: 0.000460 acc_pose: 0.901980 loss: 0.000460 2022/09/16 08:26:24 - mmengine - INFO - Epoch(train) [208][300/586] lr: 5.000000e-06 eta: 0:10:46 time: 0.471115 data_time: 0.024849 memory: 15239 loss_kpt: 0.000463 acc_pose: 0.899007 loss: 0.000463 2022/09/16 08:26:48 - mmengine - INFO - Epoch(train) [208][350/586] lr: 5.000000e-06 eta: 0:10:24 time: 0.480127 data_time: 0.028440 memory: 15239 loss_kpt: 0.000444 acc_pose: 0.874454 loss: 0.000444 2022/09/16 08:27:11 - mmengine - INFO - Epoch(train) [208][400/586] lr: 5.000000e-06 eta: 0:10:02 time: 0.466373 data_time: 0.023967 memory: 15239 loss_kpt: 0.000452 acc_pose: 0.890164 loss: 0.000452 2022/09/16 08:27:34 - mmengine - INFO - Epoch(train) [208][450/586] lr: 5.000000e-06 eta: 0:09:40 time: 0.469203 data_time: 0.024456 memory: 15239 loss_kpt: 0.000448 acc_pose: 0.900153 loss: 0.000448 2022/09/16 08:27:58 - mmengine - INFO - Epoch(train) [208][500/586] lr: 5.000000e-06 eta: 0:09:17 time: 0.467816 data_time: 0.024098 memory: 15239 loss_kpt: 0.000447 acc_pose: 0.899543 loss: 0.000447 2022/09/16 08:28:21 - mmengine - INFO - Epoch(train) [208][550/586] lr: 5.000000e-06 eta: 0:08:55 time: 0.461665 data_time: 0.024572 memory: 15239 loss_kpt: 0.000439 acc_pose: 0.942615 loss: 0.000439 2022/09/16 08:28:38 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 08:28:38 - mmengine - INFO - Saving checkpoint at 208 epochs 2022/09/16 08:29:09 - mmengine - INFO - Epoch(train) [209][50/586] lr: 5.000000e-06 eta: 0:08:17 time: 0.487343 data_time: 0.034855 memory: 15239 loss_kpt: 0.000448 acc_pose: 0.867731 loss: 0.000448 2022/09/16 08:29:32 - mmengine - INFO - Epoch(train) [209][100/586] lr: 5.000000e-06 eta: 0:07:55 time: 0.463973 data_time: 0.028458 memory: 15239 loss_kpt: 0.000427 acc_pose: 0.892656 loss: 0.000427 2022/09/16 08:29:39 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 08:29:56 - mmengine - INFO - Epoch(train) [209][150/586] lr: 5.000000e-06 eta: 0:07:33 time: 0.472728 data_time: 0.027866 memory: 15239 loss_kpt: 0.000449 acc_pose: 0.920653 loss: 0.000449 2022/09/16 08:30:20 - mmengine - INFO - Epoch(train) [209][200/586] lr: 5.000000e-06 eta: 0:07:10 time: 0.471310 data_time: 0.023386 memory: 15239 loss_kpt: 0.000449 acc_pose: 0.857406 loss: 0.000449 2022/09/16 08:30:43 - mmengine - INFO - Epoch(train) [209][250/586] lr: 5.000000e-06 eta: 0:06:48 time: 0.462182 data_time: 0.025954 memory: 15239 loss_kpt: 0.000445 acc_pose: 0.903993 loss: 0.000445 2022/09/16 08:31:06 - mmengine - INFO - Epoch(train) [209][300/586] lr: 5.000000e-06 eta: 0:06:26 time: 0.467021 data_time: 0.024732 memory: 15239 loss_kpt: 0.000443 acc_pose: 0.897977 loss: 0.000443 2022/09/16 08:31:30 - mmengine - INFO - Epoch(train) [209][350/586] lr: 5.000000e-06 eta: 0:06:04 time: 0.469749 data_time: 0.024468 memory: 15239 loss_kpt: 0.000443 acc_pose: 0.864190 loss: 0.000443 2022/09/16 08:31:53 - mmengine - INFO - Epoch(train) [209][400/586] lr: 5.000000e-06 eta: 0:05:42 time: 0.460036 data_time: 0.024152 memory: 15239 loss_kpt: 0.000439 acc_pose: 0.939389 loss: 0.000439 2022/09/16 08:32:16 - mmengine - INFO - Epoch(train) [209][450/586] lr: 5.000000e-06 eta: 0:05:20 time: 0.468134 data_time: 0.024146 memory: 15239 loss_kpt: 0.000441 acc_pose: 0.890374 loss: 0.000441 2022/09/16 08:32:40 - mmengine - INFO - Epoch(train) [209][500/586] lr: 5.000000e-06 eta: 0:04:57 time: 0.470924 data_time: 0.023935 memory: 15239 loss_kpt: 0.000445 acc_pose: 0.921376 loss: 0.000445 2022/09/16 08:33:03 - mmengine - INFO - Epoch(train) [209][550/586] lr: 5.000000e-06 eta: 0:04:35 time: 0.459897 data_time: 0.024013 memory: 15239 loss_kpt: 0.000443 acc_pose: 0.879674 loss: 0.000443 2022/09/16 08:33:20 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 08:33:20 - mmengine - INFO - Saving checkpoint at 209 epochs 2022/09/16 08:33:51 - mmengine - INFO - Epoch(train) [210][50/586] lr: 5.000000e-06 eta: 0:03:57 time: 0.476191 data_time: 0.036945 memory: 15239 loss_kpt: 0.000455 acc_pose: 0.882250 loss: 0.000455 2022/09/16 08:34:14 - mmengine - INFO - Epoch(train) [210][100/586] lr: 5.000000e-06 eta: 0:03:35 time: 0.459237 data_time: 0.027794 memory: 15239 loss_kpt: 0.000449 acc_pose: 0.913208 loss: 0.000449 2022/09/16 08:34:38 - mmengine - INFO - Epoch(train) [210][150/586] lr: 5.000000e-06 eta: 0:03:13 time: 0.473870 data_time: 0.026807 memory: 15239 loss_kpt: 0.000446 acc_pose: 0.891846 loss: 0.000446 2022/09/16 08:35:01 - mmengine - INFO - Epoch(train) [210][200/586] lr: 5.000000e-06 eta: 0:02:51 time: 0.464050 data_time: 0.024011 memory: 15239 loss_kpt: 0.000433 acc_pose: 0.888320 loss: 0.000433 2022/09/16 08:35:24 - mmengine - INFO - Epoch(train) [210][250/586] lr: 5.000000e-06 eta: 0:02:28 time: 0.459219 data_time: 0.024426 memory: 15239 loss_kpt: 0.000440 acc_pose: 0.836872 loss: 0.000440 2022/09/16 08:35:48 - mmengine - INFO - Epoch(train) [210][300/586] lr: 5.000000e-06 eta: 0:02:06 time: 0.479030 data_time: 0.024399 memory: 15239 loss_kpt: 0.000452 acc_pose: 0.883073 loss: 0.000452 2022/09/16 08:36:11 - mmengine - INFO - Epoch(train) [210][350/586] lr: 5.000000e-06 eta: 0:01:44 time: 0.465155 data_time: 0.023652 memory: 15239 loss_kpt: 0.000437 acc_pose: 0.863781 loss: 0.000437 2022/09/16 08:36:35 - mmengine - INFO - Epoch(train) [210][400/586] lr: 5.000000e-06 eta: 0:01:22 time: 0.467789 data_time: 0.024874 memory: 15239 loss_kpt: 0.000460 acc_pose: 0.886701 loss: 0.000460 2022/09/16 08:36:58 - mmengine - INFO - Epoch(train) [210][450/586] lr: 5.000000e-06 eta: 0:01:00 time: 0.470285 data_time: 0.024658 memory: 15239 loss_kpt: 0.000456 acc_pose: 0.883238 loss: 0.000456 2022/09/16 08:37:22 - mmengine - INFO - Epoch(train) [210][500/586] lr: 5.000000e-06 eta: 0:00:38 time: 0.467238 data_time: 0.024319 memory: 15239 loss_kpt: 0.000461 acc_pose: 0.898676 loss: 0.000461 2022/09/16 08:37:34 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 08:37:45 - mmengine - INFO - Epoch(train) [210][550/586] lr: 5.000000e-06 eta: 0:00:15 time: 0.465844 data_time: 0.023648 memory: 15239 loss_kpt: 0.000447 acc_pose: 0.888268 loss: 0.000447 2022/09/16 08:38:02 - mmengine - INFO - Exp name: td-hm_hrnet-w48_dark-8xb32-210e_coco-384x288_20220915_151236 2022/09/16 08:38:02 - mmengine - INFO - Saving checkpoint at 210 epochs 2022/09/16 08:38:22 - mmengine - INFO - Epoch(val) [210][50/407] eta: 0:01:33 time: 0.261692 data_time: 0.016362 memory: 15239 2022/09/16 08:38:35 - mmengine - INFO - Epoch(val) [210][100/407] eta: 0:01:16 time: 0.249630 data_time: 0.008461 memory: 2064 2022/09/16 08:38:47 - mmengine - INFO - Epoch(val) [210][150/407] eta: 0:01:05 time: 0.253844 data_time: 0.010672 memory: 2064 2022/09/16 08:39:00 - mmengine - INFO - Epoch(val) [210][200/407] eta: 0:00:52 time: 0.251980 data_time: 0.008637 memory: 2064 2022/09/16 08:39:13 - mmengine - INFO - Epoch(val) [210][250/407] eta: 0:00:39 time: 0.251327 data_time: 0.011346 memory: 2064 2022/09/16 08:39:25 - mmengine - INFO - Epoch(val) [210][300/407] eta: 0:00:27 time: 0.252424 data_time: 0.009122 memory: 2064 2022/09/16 08:39:38 - mmengine - INFO - Epoch(val) [210][350/407] eta: 0:00:14 time: 0.250101 data_time: 0.008277 memory: 2064 2022/09/16 08:39:50 - mmengine - INFO - Epoch(val) [210][400/407] eta: 0:00:01 time: 0.246737 data_time: 0.007788 memory: 2064 2022/09/16 08:40:25 - mmengine - INFO - Evaluating CocoMetric... 2022/09/16 08:40:38 - mmengine - INFO - Epoch(val) [210][407/407] coco/AP: 0.772500 coco/AP .5: 0.911419 coco/AP .75: 0.833437 coco/AP (M): 0.732460 coco/AP (L): 0.844048 coco/AR: 0.820702 coco/AR .5: 0.948048 coco/AR .75: 0.876417 coco/AR (M): 0.776482 coco/AR (L): 0.884987 2022/09/16 08:40:38 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220915/dark_w48_384/best_coco/AP_epoch_190.pth is removed 2022/09/16 08:40:42 - mmengine - INFO - The best checkpoint with 0.7725 coco/AP at 210 epoch is saved to best_coco/AP_epoch_210.pth.