2022/09/22 10:30:02 - mmengine - INFO - ------------------------------------------------------------ System environment: sys.platform: linux Python: 3.8.13 (default, Mar 28 2022, 11:38:47) [GCC 7.5.0] CUDA available: True numpy_random_seed: 189046839 GPU 0,1,2,3,4,5,6,7: NVIDIA A100-SXM4-80GB CUDA_HOME: /mnt/lustre/share/cuda-11.3 NVCC: Cuda compilation tools, release 11.3, V11.3.109 GCC: gcc (GCC) 5.4.0 PyTorch: 1.12.1 PyTorch compiling details: PyTorch built with: - GCC 9.3 - C++ Version: 201402 - Intel(R) oneAPI Math Kernel Library Version 2021.4-Product Build 20210904 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v2.6.0 (Git Hash 52b5f107dd9cf10910aaa19cb47f3abf9b349815) - OpenMP 201511 (a.k.a. OpenMP 4.5) - LAPACK is enabled (usually provided by MKL) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 11.3 - 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_61,code=sm_61;-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;-gencode;arch=compute_37,code=compute_37 - CuDNN 8.3.2 (built against CUDA 11.5) - Magma 2.5.2 - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.3, CUDNN_VERSION=8.3.2, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -fabi-version=11 -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-unused-parameter -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 -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.12.1, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=OFF, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, TorchVision: 0.13.1 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 ------------------------------------------------------------ 2022/09/22 10:30:03 - 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=10, max_keep_ckpts=1, save_best='coco/AP', rule='greater'), sampler_seed=dict(type='DistSamplerSeedHook'), visualization=dict(type='PoseVisualizationHook', enable=False)) custom_hooks = [dict(type='SyncBuffersHook')] env_cfg = dict( cudnn_benchmark=False, mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0), dist_cfg=dict(backend='nccl')) vis_backends = [dict(type='LocalVisBackend')] visualizer = dict( type='PoseLocalVisualizer', vis_backends=[dict(type='LocalVisBackend')], name='visualizer') log_processor = dict( type='LogProcessor', window_size=50, by_epoch=True, num_digits=6) log_level = 'INFO' load_from = None resume = False file_client_args = dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' })) train_cfg = dict(by_epoch=True, max_epochs=210, val_interval=10) val_cfg = dict() test_cfg = dict() optim_wrapper = dict(optimizer=dict(type='Adam', lr=0.0005)) param_scheduler = [ dict( type='LinearLR', begin=0, end=500, start_factor=0.001, by_epoch=False), dict( type='MultiStepLR', begin=0, end=210, milestones=[170, 200], gamma=0.1, by_epoch=True) ] auto_scale_lr = dict(base_batch_size=512) codec = dict( type='MSRAHeatmap', input_size=(192, 256), heatmap_size=(48, 64), sigma=2) model = dict( type='TopdownPoseEstimator', data_preprocessor=dict( type='PoseDataPreprocessor', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], bgr_to_rgb=True), backbone=dict( type='ResNet', depth=50, init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')), head=dict( type='HeatmapHead', in_channels=2048, out_channels=17, loss=dict(type='KeypointMSELoss', use_target_weight=True), decoder=dict( type='MSRAHeatmap', input_size=(192, 256), heatmap_size=(48, 64), sigma=2)), test_cfg=dict(flip_test=True, flip_mode='heatmap', shift_heatmap=True)) dataset_type = 'CocoDataset' data_mode = 'topdown' data_root = 'data/coco/' train_pipeline = [ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='RandomFlip', direction='horizontal'), dict(type='RandomHalfBody'), dict(type='RandomBBoxTransform'), dict(type='TopdownAffine', input_size=(192, 256)), dict( type='GenerateTarget', target_type='heatmap', encoder=dict( type='MSRAHeatmap', input_size=(192, 256), heatmap_size=(48, 64), sigma=2)), dict(type='PackPoseInputs') ] val_pipeline = [ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='TopdownAffine', input_size=(192, 256)), dict(type='PackPoseInputs') ] train_dataloader = dict( batch_size=64, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=True), dataset=dict( type='CocoDataset', data_root='data/coco/', data_mode='topdown', ann_file='annotations/person_keypoints_train2017.json', data_prefix=dict(img='train2017/'), pipeline=[ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='RandomFlip', direction='horizontal'), dict(type='RandomHalfBody'), dict(type='RandomBBoxTransform'), dict(type='TopdownAffine', input_size=(192, 256)), dict( type='GenerateTarget', target_type='heatmap', encoder=dict( type='MSRAHeatmap', input_size=(192, 256), heatmap_size=(48, 64), sigma=2)), dict(type='PackPoseInputs') ])) val_dataloader = dict( batch_size=32, num_workers=2, persistent_workers=True, drop_last=False, sampler=dict(type='DefaultSampler', shuffle=False, round_up=False), dataset=dict( type='CocoDataset', data_root='data/coco/', data_mode='topdown', ann_file='annotations/person_keypoints_val2017.json', bbox_file= 'data/coco/person_detection_results/COCO_val2017_detections_AP_H_56_person.json', data_prefix=dict(img='val2017/'), test_mode=True, pipeline=[ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='TopdownAffine', input_size=(192, 256)), dict(type='PackPoseInputs') ])) test_dataloader = dict( batch_size=32, num_workers=2, persistent_workers=True, drop_last=False, sampler=dict(type='DefaultSampler', shuffle=False, round_up=False), dataset=dict( type='CocoDataset', data_root='data/coco/', data_mode='topdown', ann_file='annotations/person_keypoints_val2017.json', bbox_file= 'data/coco/person_detection_results/COCO_val2017_detections_AP_H_56_person.json', data_prefix=dict(img='val2017/'), test_mode=True, pipeline=[ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='TopdownAffine', input_size=(192, 256)), dict(type='PackPoseInputs') ])) val_evaluator = dict( type='CocoMetric', ann_file='data/coco/annotations/person_keypoints_val2017.json') test_evaluator = dict( type='CocoMetric', ann_file='data/coco/annotations/person_keypoints_val2017.json') launcher = 'slurm' work_dir = '/mnt/lustre/liqikai/work_dirs/20220922/res50_256/' 2022/09/22 10:30:48 - 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. 2022/09/22 10:30:48 - 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. 2022/09/22 10:30:48 - 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. 2022/09/22 10:30:48 - 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. 2022/09/22 10:30:48 - 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. 2022/09/22 10:30:48 - 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. 2022/09/22 10:30:48 - 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. 2022/09/22 10:30:48 - 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. 2022/09/22 10:30:52 - 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. 2022/09/22 10:30:53 - 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. 2022/09/22 10:30:56 - 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. 2022/09/22 10:30:56 - 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, 7, 7]): PretrainedInit: load from torchvision://resnet50 backbone.bn1.weight - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.bn1.bias - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.conv1.weight - torch.Size([64, 64, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.bn1.weight - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.bn1.bias - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.bn2.weight - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.bn2.bias - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.bn3.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.bn3.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.downsample.0.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.downsample.1.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.downsample.1.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.conv1.weight - torch.Size([64, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.bn1.weight - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.bn1.bias - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.bn2.weight - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.bn2.bias - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.bn3.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.bn3.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.conv1.weight - torch.Size([64, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.bn1.weight - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.bn1.bias - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.bn2.weight - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.bn2.bias - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.bn3.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.bn3.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.conv1.weight - torch.Size([128, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.bn1.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.bn1.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.bn2.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.bn2.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.conv3.weight - torch.Size([512, 128, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.bn3.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.bn3.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.downsample.0.weight - torch.Size([512, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.downsample.1.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.downsample.1.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.conv1.weight - torch.Size([128, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.bn1.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.bn1.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.bn2.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.bn2.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.conv3.weight - torch.Size([512, 128, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.bn3.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.bn3.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.conv1.weight - torch.Size([128, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.bn1.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.bn1.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.bn2.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.bn2.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.conv3.weight - torch.Size([512, 128, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.bn3.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.bn3.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.conv1.weight - torch.Size([128, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.bn1.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.bn1.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.bn2.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.bn2.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.conv3.weight - torch.Size([512, 128, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.bn3.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.bn3.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.conv1.weight - torch.Size([256, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.bn1.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.bn1.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.bn2.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.bn2.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.bn3.weight - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.bn3.bias - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.downsample.0.weight - torch.Size([1024, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.downsample.1.weight - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.downsample.1.bias - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.bn1.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.bn1.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.bn2.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.bn2.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.bn3.weight - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.bn3.bias - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.bn1.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.bn1.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.bn2.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.bn2.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.bn3.weight - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.bn3.bias - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.bn1.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.bn1.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.bn2.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.bn2.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.bn3.weight - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.bn3.bias - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.bn1.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.bn1.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.bn2.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.bn2.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.bn3.weight - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.bn3.bias - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.bn1.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.bn1.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.bn2.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.bn2.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.bn3.weight - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.bn3.bias - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.conv1.weight - torch.Size([512, 1024, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.bn1.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.bn1.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.conv2.weight - torch.Size([512, 512, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.bn2.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.bn2.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.conv3.weight - torch.Size([2048, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.bn3.weight - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.bn3.bias - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.downsample.0.weight - torch.Size([2048, 1024, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.downsample.1.weight - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.downsample.1.bias - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.conv1.weight - torch.Size([512, 2048, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.bn1.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.bn1.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.conv2.weight - torch.Size([512, 512, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.bn2.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.bn2.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.conv3.weight - torch.Size([2048, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.bn3.weight - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.bn3.bias - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.conv1.weight - torch.Size([512, 2048, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.bn1.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.bn1.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.conv2.weight - torch.Size([512, 512, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.bn2.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.bn2.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.conv3.weight - torch.Size([2048, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.bn3.weight - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.bn3.bias - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 head.deconv_layers.0.weight - torch.Size([2048, 256, 4, 4]): NormalInit: mean=0, std=0.001, bias=0 head.deconv_layers.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.deconv_layers.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.deconv_layers.3.weight - torch.Size([256, 256, 4, 4]): NormalInit: mean=0, std=0.001, bias=0 head.deconv_layers.4.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.deconv_layers.4.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.deconv_layers.6.weight - torch.Size([256, 256, 4, 4]): NormalInit: mean=0, std=0.001, bias=0 head.deconv_layers.7.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.deconv_layers.7.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.final_layer.weight - torch.Size([17, 256, 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 2022/09/22 10:30:56 - mmengine - INFO - Checkpoints will be saved to /mnt/lustre/liqikai/work_dirs/20220922/res50_256 by HardDiskBackend. 2022/09/22 10:31:37 - mmengine - INFO - Epoch(train) [1][50/293] lr: 4.954910e-05 eta: 14:01:02 time: 0.820797 data_time: 0.288783 memory: 6691 loss_kpt: 0.002166 acc_pose: 0.171965 loss: 0.002166 2022/09/22 10:32:05 - mmengine - INFO - Epoch(train) [1][100/293] lr: 9.959920e-05 eta: 11:54:33 time: 0.575049 data_time: 0.113765 memory: 6691 loss_kpt: 0.001853 acc_pose: 0.317684 loss: 0.001853 2022/09/22 10:32:33 - mmengine - INFO - Epoch(train) [1][150/293] lr: 1.496493e-04 eta: 11:06:20 time: 0.558227 data_time: 0.187667 memory: 6691 loss_kpt: 0.001583 acc_pose: 0.426976 loss: 0.001583 2022/09/22 10:33:01 - mmengine - INFO - Epoch(train) [1][200/293] lr: 1.996994e-04 eta: 10:42:12 time: 0.559042 data_time: 0.102963 memory: 6691 loss_kpt: 0.001446 acc_pose: 0.505434 loss: 0.001446 2022/09/22 10:33:29 - mmengine - INFO - Epoch(train) [1][250/293] lr: 2.497495e-04 eta: 10:25:23 time: 0.548562 data_time: 0.083780 memory: 6691 loss_kpt: 0.001379 acc_pose: 0.545067 loss: 0.001379 2022/09/22 10:33:52 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 10:34:21 - mmengine - INFO - Epoch(train) [2][50/293] lr: 3.428427e-04 eta: 9:01:19 time: 0.579747 data_time: 0.176576 memory: 6691 loss_kpt: 0.001271 acc_pose: 0.565265 loss: 0.001271 2022/09/22 10:34:49 - mmengine - INFO - Epoch(train) [2][100/293] lr: 3.928928e-04 eta: 9:04:06 time: 0.555749 data_time: 0.092664 memory: 6691 loss_kpt: 0.001242 acc_pose: 0.472198 loss: 0.001242 2022/09/22 10:35:15 - mmengine - INFO - Epoch(train) [2][150/293] lr: 4.429429e-04 eta: 9:03:44 time: 0.534654 data_time: 0.088622 memory: 6691 loss_kpt: 0.001224 acc_pose: 0.568440 loss: 0.001224 2022/09/22 10:35:42 - mmengine - INFO - Epoch(train) [2][200/293] lr: 4.929930e-04 eta: 9:03:59 time: 0.540814 data_time: 0.101786 memory: 6691 loss_kpt: 0.001215 acc_pose: 0.590611 loss: 0.001215 2022/09/22 10:36:10 - mmengine - INFO - Epoch(train) [2][250/293] lr: 5.000000e-04 eta: 9:05:46 time: 0.558506 data_time: 0.088516 memory: 6691 loss_kpt: 0.001173 acc_pose: 0.650161 loss: 0.001173 2022/09/22 10:36:33 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 10:37:02 - mmengine - INFO - Epoch(train) [3][50/293] lr: 5.000000e-04 eta: 8:32:22 time: 0.590557 data_time: 0.194542 memory: 6691 loss_kpt: 0.001160 acc_pose: 0.594098 loss: 0.001160 2022/09/22 10:37:32 - mmengine - INFO - Epoch(train) [3][100/293] lr: 5.000000e-04 eta: 8:37:55 time: 0.585674 data_time: 0.146011 memory: 6691 loss_kpt: 0.001128 acc_pose: 0.559536 loss: 0.001128 2022/09/22 10:38:00 - mmengine - INFO - Epoch(train) [3][150/293] lr: 5.000000e-04 eta: 8:40:52 time: 0.559871 data_time: 0.097064 memory: 6691 loss_kpt: 0.001121 acc_pose: 0.613391 loss: 0.001121 2022/09/22 10:38:28 - mmengine - INFO - Epoch(train) [3][200/293] lr: 5.000000e-04 eta: 8:43:53 time: 0.567546 data_time: 0.104446 memory: 6691 loss_kpt: 0.001117 acc_pose: 0.648231 loss: 0.001117 2022/09/22 10:38:55 - mmengine - INFO - Epoch(train) [3][250/293] lr: 5.000000e-04 eta: 8:45:09 time: 0.545582 data_time: 0.087404 memory: 6691 loss_kpt: 0.001099 acc_pose: 0.640231 loss: 0.001099 2022/09/22 10:39:20 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 10:39:49 - mmengine - INFO - Epoch(train) [4][50/293] lr: 5.000000e-04 eta: 8:24:03 time: 0.592149 data_time: 0.200097 memory: 6691 loss_kpt: 0.001089 acc_pose: 0.638323 loss: 0.001089 2022/09/22 10:40:16 - mmengine - INFO - Epoch(train) [4][100/293] lr: 5.000000e-04 eta: 8:25:51 time: 0.542064 data_time: 0.157037 memory: 6691 loss_kpt: 0.001077 acc_pose: 0.672068 loss: 0.001077 2022/09/22 10:40:28 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 10:40:43 - mmengine - INFO - Epoch(train) [4][150/293] lr: 5.000000e-04 eta: 8:26:52 time: 0.530405 data_time: 0.096798 memory: 6691 loss_kpt: 0.001088 acc_pose: 0.678212 loss: 0.001088 2022/09/22 10:41:09 - mmengine - INFO - Epoch(train) [4][200/293] lr: 5.000000e-04 eta: 8:27:33 time: 0.526321 data_time: 0.077307 memory: 6691 loss_kpt: 0.001055 acc_pose: 0.668563 loss: 0.001055 2022/09/22 10:41:36 - mmengine - INFO - Epoch(train) [4][250/293] lr: 5.000000e-04 eta: 8:28:52 time: 0.542689 data_time: 0.088215 memory: 6691 loss_kpt: 0.001049 acc_pose: 0.641774 loss: 0.001049 2022/09/22 10:41:59 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 10:42:28 - mmengine - INFO - Epoch(train) [5][50/293] lr: 5.000000e-04 eta: 8:13:40 time: 0.589787 data_time: 0.235992 memory: 6691 loss_kpt: 0.001030 acc_pose: 0.653243 loss: 0.001030 2022/09/22 10:42:57 - mmengine - INFO - Epoch(train) [5][100/293] lr: 5.000000e-04 eta: 8:16:26 time: 0.571523 data_time: 0.100530 memory: 6691 loss_kpt: 0.001031 acc_pose: 0.692727 loss: 0.001031 2022/09/22 10:43:23 - mmengine - INFO - Epoch(train) [5][150/293] lr: 5.000000e-04 eta: 8:17:27 time: 0.532120 data_time: 0.086647 memory: 6691 loss_kpt: 0.001020 acc_pose: 0.700445 loss: 0.001020 2022/09/22 10:43:50 - mmengine - INFO - Epoch(train) [5][200/293] lr: 5.000000e-04 eta: 8:18:38 time: 0.539185 data_time: 0.115192 memory: 6691 loss_kpt: 0.001008 acc_pose: 0.649971 loss: 0.001008 2022/09/22 10:44:19 - mmengine - INFO - Epoch(train) [5][250/293] lr: 5.000000e-04 eta: 8:20:46 time: 0.569743 data_time: 0.206640 memory: 6691 loss_kpt: 0.001023 acc_pose: 0.665834 loss: 0.001023 2022/09/22 10:44:43 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 10:45:12 - mmengine - INFO - Epoch(train) [6][50/293] lr: 5.000000e-04 eta: 8:08:30 time: 0.581720 data_time: 0.211393 memory: 6691 loss_kpt: 0.001002 acc_pose: 0.687578 loss: 0.001002 2022/09/22 10:45:40 - mmengine - INFO - Epoch(train) [6][100/293] lr: 5.000000e-04 eta: 8:10:19 time: 0.558116 data_time: 0.166575 memory: 6691 loss_kpt: 0.000992 acc_pose: 0.683466 loss: 0.000992 2022/09/22 10:46:09 - mmengine - INFO - Epoch(train) [6][150/293] lr: 5.000000e-04 eta: 8:12:28 time: 0.573169 data_time: 0.192293 memory: 6691 loss_kpt: 0.000997 acc_pose: 0.640420 loss: 0.000997 2022/09/22 10:46:37 - mmengine - INFO - Epoch(train) [6][200/293] lr: 5.000000e-04 eta: 8:14:24 time: 0.571513 data_time: 0.189976 memory: 6691 loss_kpt: 0.000972 acc_pose: 0.646723 loss: 0.000972 2022/09/22 10:47:06 - mmengine - INFO - Epoch(train) [6][250/293] lr: 5.000000e-04 eta: 8:16:14 time: 0.572879 data_time: 0.193131 memory: 6691 loss_kpt: 0.000997 acc_pose: 0.657992 loss: 0.000997 2022/09/22 10:47:30 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 10:48:00 - mmengine - INFO - Epoch(train) [7][50/293] lr: 5.000000e-04 eta: 8:06:17 time: 0.592640 data_time: 0.258494 memory: 6691 loss_kpt: 0.000980 acc_pose: 0.655440 loss: 0.000980 2022/09/22 10:48:28 - mmengine - INFO - Epoch(train) [7][100/293] lr: 5.000000e-04 eta: 8:08:15 time: 0.577087 data_time: 0.167989 memory: 6691 loss_kpt: 0.000965 acc_pose: 0.606449 loss: 0.000965 2022/09/22 10:48:56 - mmengine - INFO - Epoch(train) [7][150/293] lr: 5.000000e-04 eta: 8:09:34 time: 0.557227 data_time: 0.100496 memory: 6691 loss_kpt: 0.000960 acc_pose: 0.711134 loss: 0.000960 2022/09/22 10:49:24 - mmengine - INFO - Epoch(train) [7][200/293] lr: 5.000000e-04 eta: 8:10:35 time: 0.548593 data_time: 0.086935 memory: 6691 loss_kpt: 0.000965 acc_pose: 0.713651 loss: 0.000965 2022/09/22 10:49:47 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 10:49:51 - mmengine - INFO - Epoch(train) [7][250/293] lr: 5.000000e-04 eta: 8:11:22 time: 0.542899 data_time: 0.083347 memory: 6691 loss_kpt: 0.000965 acc_pose: 0.611831 loss: 0.000965 2022/09/22 10:50:13 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 10:50:42 - mmengine - INFO - Epoch(train) [8][50/293] lr: 5.000000e-04 eta: 8:02:31 time: 0.578091 data_time: 0.272212 memory: 6691 loss_kpt: 0.000960 acc_pose: 0.684201 loss: 0.000960 2022/09/22 10:51:10 - mmengine - INFO - Epoch(train) [8][100/293] lr: 5.000000e-04 eta: 8:03:49 time: 0.561680 data_time: 0.256745 memory: 6691 loss_kpt: 0.000946 acc_pose: 0.649736 loss: 0.000946 2022/09/22 10:51:38 - mmengine - INFO - Epoch(train) [8][150/293] lr: 5.000000e-04 eta: 8:04:49 time: 0.551411 data_time: 0.131744 memory: 6691 loss_kpt: 0.000957 acc_pose: 0.744207 loss: 0.000957 2022/09/22 10:52:06 - mmengine - INFO - Epoch(train) [8][200/293] lr: 5.000000e-04 eta: 8:06:08 time: 0.568629 data_time: 0.101680 memory: 6691 loss_kpt: 0.000954 acc_pose: 0.689073 loss: 0.000954 2022/09/22 10:52:35 - mmengine - INFO - Epoch(train) [8][250/293] lr: 5.000000e-04 eta: 8:07:15 time: 0.563714 data_time: 0.095708 memory: 6691 loss_kpt: 0.000948 acc_pose: 0.730976 loss: 0.000948 2022/09/22 10:52:58 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 10:53:27 - mmengine - INFO - Epoch(train) [9][50/293] lr: 5.000000e-04 eta: 7:59:42 time: 0.588296 data_time: 0.224513 memory: 6691 loss_kpt: 0.000940 acc_pose: 0.709610 loss: 0.000940 2022/09/22 10:53:55 - mmengine - INFO - Epoch(train) [9][100/293] lr: 5.000000e-04 eta: 8:00:39 time: 0.554284 data_time: 0.223948 memory: 6691 loss_kpt: 0.000934 acc_pose: 0.718812 loss: 0.000934 2022/09/22 10:54:23 - mmengine - INFO - Epoch(train) [9][150/293] lr: 5.000000e-04 eta: 8:01:44 time: 0.563302 data_time: 0.240274 memory: 6691 loss_kpt: 0.000953 acc_pose: 0.709130 loss: 0.000953 2022/09/22 10:54:51 - mmengine - INFO - Epoch(train) [9][200/293] lr: 5.000000e-04 eta: 8:02:45 time: 0.563587 data_time: 0.193170 memory: 6691 loss_kpt: 0.000932 acc_pose: 0.648672 loss: 0.000932 2022/09/22 10:55:18 - mmengine - INFO - Epoch(train) [9][250/293] lr: 5.000000e-04 eta: 8:03:18 time: 0.541860 data_time: 0.097125 memory: 6691 loss_kpt: 0.000934 acc_pose: 0.643792 loss: 0.000934 2022/09/22 10:55:42 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 10:56:11 - mmengine - INFO - Epoch(train) [10][50/293] lr: 5.000000e-04 eta: 7:56:18 time: 0.573389 data_time: 0.180104 memory: 6691 loss_kpt: 0.000925 acc_pose: 0.707112 loss: 0.000925 2022/09/22 10:56:39 - mmengine - INFO - Epoch(train) [10][100/293] lr: 5.000000e-04 eta: 7:57:10 time: 0.556276 data_time: 0.092866 memory: 6691 loss_kpt: 0.000922 acc_pose: 0.683104 loss: 0.000922 2022/09/22 10:57:06 - mmengine - INFO - Epoch(train) [10][150/293] lr: 5.000000e-04 eta: 7:57:54 time: 0.552126 data_time: 0.093690 memory: 6691 loss_kpt: 0.000930 acc_pose: 0.662688 loss: 0.000930 2022/09/22 10:57:34 - mmengine - INFO - Epoch(train) [10][200/293] lr: 5.000000e-04 eta: 7:58:29 time: 0.545641 data_time: 0.085448 memory: 6691 loss_kpt: 0.000930 acc_pose: 0.687981 loss: 0.000930 2022/09/22 10:58:01 - mmengine - INFO - Epoch(train) [10][250/293] lr: 5.000000e-04 eta: 7:59:12 time: 0.555164 data_time: 0.097776 memory: 6691 loss_kpt: 0.000919 acc_pose: 0.656813 loss: 0.000919 2022/09/22 10:58:24 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 10:58:24 - mmengine - INFO - Saving checkpoint at 10 epochs 2022/09/22 10:58:49 - mmengine - INFO - Epoch(val) [10][50/407] eta: 0:02:36 time: 0.439383 data_time: 0.305613 memory: 6691 2022/09/22 10:59:04 - mmengine - INFO - Epoch(val) [10][100/407] eta: 0:01:33 time: 0.305247 data_time: 0.167336 memory: 1014 2022/09/22 10:59:20 - mmengine - INFO - Epoch(val) [10][150/407] eta: 0:01:20 time: 0.313011 data_time: 0.161454 memory: 1014 2022/09/22 10:59:35 - mmengine - INFO - Epoch(val) [10][200/407] eta: 0:01:01 time: 0.296557 data_time: 0.159623 memory: 1014 2022/09/22 10:59:50 - mmengine - INFO - Epoch(val) [10][250/407] eta: 0:00:48 time: 0.306524 data_time: 0.181402 memory: 1014 2022/09/22 11:00:05 - mmengine - INFO - Epoch(val) [10][300/407] eta: 0:00:32 time: 0.305385 data_time: 0.159778 memory: 1014 2022/09/22 11:00:21 - mmengine - INFO - Epoch(val) [10][350/407] eta: 0:00:17 time: 0.309679 data_time: 0.184505 memory: 1014 2022/09/22 11:00:36 - mmengine - INFO - Epoch(val) [10][400/407] eta: 0:00:02 time: 0.300337 data_time: 0.165495 memory: 1014 2022/09/22 11:01:12 - mmengine - INFO - Evaluating CocoMetric... 2022/09/22 11:01:25 - mmengine - INFO - Epoch(val) [10][407/407] coco/AP: 0.582785 coco/AP .5: 0.843260 coco/AP .75: 0.645957 coco/AP (M): 0.549895 coco/AP (L): 0.644732 coco/AR: 0.651779 coco/AR .5: 0.890743 coco/AR .75: 0.717097 coco/AR (M): 0.608686 coco/AR (L): 0.712635 2022/09/22 11:01:27 - mmengine - INFO - The best checkpoint with 0.5828 coco/AP at 10 epoch is saved to best_coco/AP_epoch_10.pth. 2022/09/22 11:01:54 - mmengine - INFO - Epoch(train) [11][50/293] lr: 5.000000e-04 eta: 7:52:07 time: 0.525984 data_time: 0.248731 memory: 6691 loss_kpt: 0.000913 acc_pose: 0.717375 loss: 0.000913 2022/09/22 11:02:04 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 11:02:20 - mmengine - INFO - Epoch(train) [11][100/293] lr: 5.000000e-04 eta: 7:52:33 time: 0.535523 data_time: 0.237070 memory: 6691 loss_kpt: 0.000917 acc_pose: 0.675822 loss: 0.000917 2022/09/22 11:02:47 - mmengine - INFO - Epoch(train) [11][150/293] lr: 5.000000e-04 eta: 7:52:57 time: 0.535308 data_time: 0.196455 memory: 6691 loss_kpt: 0.000908 acc_pose: 0.740482 loss: 0.000908 2022/09/22 11:03:15 - mmengine - INFO - Epoch(train) [11][200/293] lr: 5.000000e-04 eta: 7:53:49 time: 0.567122 data_time: 0.230555 memory: 6691 loss_kpt: 0.000899 acc_pose: 0.735528 loss: 0.000899 2022/09/22 11:03:44 - mmengine - INFO - Epoch(train) [11][250/293] lr: 5.000000e-04 eta: 7:54:43 time: 0.572335 data_time: 0.136646 memory: 6691 loss_kpt: 0.000900 acc_pose: 0.677110 loss: 0.000900 2022/09/22 11:04:07 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 11:04:36 - mmengine - INFO - Epoch(train) [12][50/293] lr: 5.000000e-04 eta: 7:48:58 time: 0.571602 data_time: 0.273875 memory: 6691 loss_kpt: 0.000913 acc_pose: 0.715206 loss: 0.000913 2022/09/22 11:05:03 - mmengine - INFO - Epoch(train) [12][100/293] lr: 5.000000e-04 eta: 7:49:25 time: 0.541116 data_time: 0.252049 memory: 6691 loss_kpt: 0.000896 acc_pose: 0.771345 loss: 0.000896 2022/09/22 11:05:30 - mmengine - INFO - Epoch(train) [12][150/293] lr: 5.000000e-04 eta: 7:49:42 time: 0.532052 data_time: 0.198031 memory: 6691 loss_kpt: 0.000915 acc_pose: 0.696892 loss: 0.000915 2022/09/22 11:05:58 - mmengine - INFO - Epoch(train) [12][200/293] lr: 5.000000e-04 eta: 7:50:20 time: 0.558115 data_time: 0.196617 memory: 6691 loss_kpt: 0.000903 acc_pose: 0.722020 loss: 0.000903 2022/09/22 11:06:25 - mmengine - INFO - Epoch(train) [12][250/293] lr: 5.000000e-04 eta: 7:50:50 time: 0.550037 data_time: 0.114517 memory: 6691 loss_kpt: 0.000910 acc_pose: 0.691929 loss: 0.000910 2022/09/22 11:06:48 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 11:07:17 - mmengine - INFO - Epoch(train) [13][50/293] lr: 5.000000e-04 eta: 7:45:44 time: 0.584465 data_time: 0.226783 memory: 6691 loss_kpt: 0.000891 acc_pose: 0.678821 loss: 0.000891 2022/09/22 11:07:46 - mmengine - INFO - Epoch(train) [13][100/293] lr: 5.000000e-04 eta: 7:46:33 time: 0.573552 data_time: 0.244218 memory: 6691 loss_kpt: 0.000884 acc_pose: 0.692308 loss: 0.000884 2022/09/22 11:08:14 - mmengine - INFO - Epoch(train) [13][150/293] lr: 5.000000e-04 eta: 7:47:13 time: 0.564705 data_time: 0.154438 memory: 6691 loss_kpt: 0.000893 acc_pose: 0.725753 loss: 0.000893 2022/09/22 11:08:43 - mmengine - INFO - Epoch(train) [13][200/293] lr: 5.000000e-04 eta: 7:47:49 time: 0.562011 data_time: 0.102367 memory: 6691 loss_kpt: 0.000894 acc_pose: 0.722845 loss: 0.000894 2022/09/22 11:09:11 - mmengine - INFO - Epoch(train) [13][250/293] lr: 5.000000e-04 eta: 7:48:23 time: 0.560693 data_time: 0.101101 memory: 6691 loss_kpt: 0.000893 acc_pose: 0.700441 loss: 0.000893 2022/09/22 11:09:34 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 11:10:03 - mmengine - INFO - Epoch(train) [14][50/293] lr: 5.000000e-04 eta: 7:43:27 time: 0.569402 data_time: 0.174192 memory: 6691 loss_kpt: 0.000872 acc_pose: 0.686394 loss: 0.000872 2022/09/22 11:10:31 - mmengine - INFO - Epoch(train) [14][100/293] lr: 5.000000e-04 eta: 7:44:07 time: 0.569064 data_time: 0.189772 memory: 6691 loss_kpt: 0.000865 acc_pose: 0.716346 loss: 0.000865 2022/09/22 11:10:59 - mmengine - INFO - Epoch(train) [14][150/293] lr: 5.000000e-04 eta: 7:44:31 time: 0.550316 data_time: 0.101128 memory: 6691 loss_kpt: 0.000895 acc_pose: 0.769521 loss: 0.000895 2022/09/22 11:11:21 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 11:11:26 - mmengine - INFO - Epoch(train) [14][200/293] lr: 5.000000e-04 eta: 7:44:51 time: 0.545907 data_time: 0.088510 memory: 6691 loss_kpt: 0.000883 acc_pose: 0.740019 loss: 0.000883 2022/09/22 11:11:53 - mmengine - INFO - Epoch(train) [14][250/293] lr: 5.000000e-04 eta: 7:45:15 time: 0.553065 data_time: 0.089185 memory: 6691 loss_kpt: 0.000875 acc_pose: 0.764232 loss: 0.000875 2022/09/22 11:12:18 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 11:12:47 - mmengine - INFO - Epoch(train) [15][50/293] lr: 5.000000e-04 eta: 7:40:47 time: 0.580184 data_time: 0.163487 memory: 6691 loss_kpt: 0.000869 acc_pose: 0.776751 loss: 0.000869 2022/09/22 11:13:15 - mmengine - INFO - Epoch(train) [15][100/293] lr: 5.000000e-04 eta: 7:41:23 time: 0.570119 data_time: 0.099697 memory: 6691 loss_kpt: 0.000876 acc_pose: 0.751357 loss: 0.000876 2022/09/22 11:13:43 - mmengine - INFO - Epoch(train) [15][150/293] lr: 5.000000e-04 eta: 7:41:43 time: 0.549108 data_time: 0.083830 memory: 6691 loss_kpt: 0.000871 acc_pose: 0.674495 loss: 0.000871 2022/09/22 11:14:12 - mmengine - INFO - Epoch(train) [15][200/293] lr: 5.000000e-04 eta: 7:42:18 time: 0.572315 data_time: 0.109461 memory: 6691 loss_kpt: 0.000880 acc_pose: 0.717841 loss: 0.000880 2022/09/22 11:14:39 - mmengine - INFO - Epoch(train) [15][250/293] lr: 5.000000e-04 eta: 7:42:38 time: 0.551839 data_time: 0.095476 memory: 6691 loss_kpt: 0.000880 acc_pose: 0.786587 loss: 0.000880 2022/09/22 11:15:03 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 11:15:32 - mmengine - INFO - Epoch(train) [16][50/293] lr: 5.000000e-04 eta: 7:38:21 time: 0.572877 data_time: 0.238136 memory: 6691 loss_kpt: 0.000850 acc_pose: 0.732098 loss: 0.000850 2022/09/22 11:16:00 - mmengine - INFO - Epoch(train) [16][100/293] lr: 5.000000e-04 eta: 7:38:52 time: 0.568208 data_time: 0.268643 memory: 6691 loss_kpt: 0.000869 acc_pose: 0.733996 loss: 0.000869 2022/09/22 11:16:28 - mmengine - INFO - Epoch(train) [16][150/293] lr: 5.000000e-04 eta: 7:39:09 time: 0.548624 data_time: 0.240597 memory: 6691 loss_kpt: 0.000880 acc_pose: 0.771792 loss: 0.000880 2022/09/22 11:16:54 - mmengine - INFO - Epoch(train) [16][200/293] lr: 5.000000e-04 eta: 7:39:15 time: 0.532974 data_time: 0.251962 memory: 6691 loss_kpt: 0.000864 acc_pose: 0.676575 loss: 0.000864 2022/09/22 11:17:23 - mmengine - INFO - Epoch(train) [16][250/293] lr: 5.000000e-04 eta: 7:39:47 time: 0.574927 data_time: 0.220118 memory: 6691 loss_kpt: 0.000876 acc_pose: 0.679767 loss: 0.000876 2022/09/22 11:17:48 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 11:18:17 - mmengine - INFO - Epoch(train) [17][50/293] lr: 5.000000e-04 eta: 7:35:50 time: 0.581890 data_time: 0.162200 memory: 6691 loss_kpt: 0.000872 acc_pose: 0.705920 loss: 0.000872 2022/09/22 11:18:45 - mmengine - INFO - Epoch(train) [17][100/293] lr: 5.000000e-04 eta: 7:36:20 time: 0.572947 data_time: 0.119328 memory: 6691 loss_kpt: 0.000868 acc_pose: 0.717135 loss: 0.000868 2022/09/22 11:19:13 - mmengine - INFO - Epoch(train) [17][150/293] lr: 5.000000e-04 eta: 7:36:42 time: 0.560890 data_time: 0.213675 memory: 6691 loss_kpt: 0.000858 acc_pose: 0.779413 loss: 0.000858 2022/09/22 11:19:42 - mmengine - INFO - Epoch(train) [17][200/293] lr: 5.000000e-04 eta: 7:37:07 time: 0.568602 data_time: 0.117064 memory: 6691 loss_kpt: 0.000861 acc_pose: 0.715887 loss: 0.000861 2022/09/22 11:20:10 - mmengine - INFO - Epoch(train) [17][250/293] lr: 5.000000e-04 eta: 7:37:31 time: 0.568378 data_time: 0.103616 memory: 6691 loss_kpt: 0.000852 acc_pose: 0.735901 loss: 0.000852 2022/09/22 11:20:34 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 11:20:46 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 11:21:03 - mmengine - INFO - Epoch(train) [18][50/293] lr: 5.000000e-04 eta: 7:33:37 time: 0.565452 data_time: 0.131698 memory: 6691 loss_kpt: 0.000864 acc_pose: 0.741631 loss: 0.000864 2022/09/22 11:21:30 - mmengine - INFO - Epoch(train) [18][100/293] lr: 5.000000e-04 eta: 7:33:45 time: 0.540287 data_time: 0.079547 memory: 6691 loss_kpt: 0.000861 acc_pose: 0.718434 loss: 0.000861 2022/09/22 11:21:57 - mmengine - INFO - Epoch(train) [18][150/293] lr: 5.000000e-04 eta: 7:34:02 time: 0.557932 data_time: 0.147194 memory: 6691 loss_kpt: 0.000833 acc_pose: 0.672832 loss: 0.000833 2022/09/22 11:22:26 - mmengine - INFO - Epoch(train) [18][200/293] lr: 5.000000e-04 eta: 7:34:27 time: 0.572001 data_time: 0.121217 memory: 6691 loss_kpt: 0.000846 acc_pose: 0.781964 loss: 0.000846 2022/09/22 11:22:54 - mmengine - INFO - Epoch(train) [18][250/293] lr: 5.000000e-04 eta: 7:34:38 time: 0.549547 data_time: 0.090789 memory: 6691 loss_kpt: 0.000859 acc_pose: 0.718801 loss: 0.000859 2022/09/22 11:23:17 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 11:23:46 - mmengine - INFO - Epoch(train) [19][50/293] lr: 5.000000e-04 eta: 7:31:09 time: 0.590111 data_time: 0.253419 memory: 6691 loss_kpt: 0.000859 acc_pose: 0.734303 loss: 0.000859 2022/09/22 11:24:16 - mmengine - INFO - Epoch(train) [19][100/293] lr: 5.000000e-04 eta: 7:31:37 time: 0.581759 data_time: 0.214920 memory: 6691 loss_kpt: 0.000837 acc_pose: 0.743123 loss: 0.000837 2022/09/22 11:24:45 - mmengine - INFO - Epoch(train) [19][150/293] lr: 5.000000e-04 eta: 7:32:02 time: 0.578733 data_time: 0.247739 memory: 6691 loss_kpt: 0.000849 acc_pose: 0.709061 loss: 0.000849 2022/09/22 11:25:13 - mmengine - INFO - Epoch(train) [19][200/293] lr: 5.000000e-04 eta: 7:32:25 time: 0.575066 data_time: 0.184974 memory: 6691 loss_kpt: 0.000838 acc_pose: 0.709460 loss: 0.000838 2022/09/22 11:25:41 - mmengine - INFO - Epoch(train) [19][250/293] lr: 5.000000e-04 eta: 7:32:35 time: 0.551583 data_time: 0.093763 memory: 6691 loss_kpt: 0.000852 acc_pose: 0.818494 loss: 0.000852 2022/09/22 11:26:05 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 11:26:34 - mmengine - INFO - Epoch(train) [20][50/293] lr: 5.000000e-04 eta: 7:29:15 time: 0.589738 data_time: 0.176183 memory: 6691 loss_kpt: 0.000865 acc_pose: 0.702568 loss: 0.000865 2022/09/22 11:27:02 - mmengine - INFO - Epoch(train) [20][100/293] lr: 5.000000e-04 eta: 7:29:29 time: 0.559280 data_time: 0.117727 memory: 6691 loss_kpt: 0.000852 acc_pose: 0.701329 loss: 0.000852 2022/09/22 11:27:30 - mmengine - INFO - Epoch(train) [20][150/293] lr: 5.000000e-04 eta: 7:29:35 time: 0.544915 data_time: 0.085554 memory: 6691 loss_kpt: 0.000827 acc_pose: 0.815315 loss: 0.000827 2022/09/22 11:27:57 - mmengine - INFO - Epoch(train) [20][200/293] lr: 5.000000e-04 eta: 7:29:39 time: 0.542319 data_time: 0.092617 memory: 6691 loss_kpt: 0.000835 acc_pose: 0.755977 loss: 0.000835 2022/09/22 11:28:23 - mmengine - INFO - Epoch(train) [20][250/293] lr: 5.000000e-04 eta: 7:29:33 time: 0.521963 data_time: 0.080568 memory: 6691 loss_kpt: 0.000850 acc_pose: 0.691994 loss: 0.000850 2022/09/22 11:28:46 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 11:28:46 - mmengine - INFO - Saving checkpoint at 20 epochs 2022/09/22 11:29:09 - mmengine - INFO - Epoch(val) [20][50/407] eta: 0:01:52 time: 0.315365 data_time: 0.178772 memory: 6691 2022/09/22 11:29:25 - mmengine - INFO - Epoch(val) [20][100/407] eta: 0:01:37 time: 0.316149 data_time: 0.180261 memory: 1014 2022/09/22 11:29:40 - mmengine - INFO - Epoch(val) [20][150/407] eta: 0:01:19 time: 0.307614 data_time: 0.156613 memory: 1014 2022/09/22 11:29:56 - mmengine - INFO - Epoch(val) [20][200/407] eta: 0:01:03 time: 0.305823 data_time: 0.162799 memory: 1014 2022/09/22 11:30:11 - mmengine - INFO - Epoch(val) [20][250/407] eta: 0:00:47 time: 0.299715 data_time: 0.169080 memory: 1014 2022/09/22 11:30:26 - mmengine - INFO - Epoch(val) [20][300/407] eta: 0:00:32 time: 0.301538 data_time: 0.158961 memory: 1014 2022/09/22 11:30:42 - mmengine - INFO - Epoch(val) [20][350/407] eta: 0:00:18 time: 0.321071 data_time: 0.196913 memory: 1014 2022/09/22 11:30:54 - mmengine - INFO - Epoch(val) [20][400/407] eta: 0:00:01 time: 0.239228 data_time: 0.133688 memory: 1014 2022/09/22 11:31:26 - mmengine - INFO - Evaluating CocoMetric... 2022/09/22 11:31:39 - mmengine - INFO - Epoch(val) [20][407/407] coco/AP: 0.633002 coco/AP .5: 0.863202 coco/AP .75: 0.706050 coco/AP (M): 0.595775 coco/AP (L): 0.700756 coco/AR: 0.694962 coco/AR .5: 0.906644 coco/AR .75: 0.762280 coco/AR (M): 0.648784 coco/AR (L): 0.760089 2022/09/22 11:31:40 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220922/res50_256/best_coco/AP_epoch_10.pth is removed 2022/09/22 11:31:42 - mmengine - INFO - The best checkpoint with 0.6330 coco/AP at 20 epoch is saved to best_coco/AP_epoch_20.pth. 2022/09/22 11:32:09 - mmengine - INFO - Epoch(train) [21][50/293] lr: 5.000000e-04 eta: 7:25:56 time: 0.535426 data_time: 0.235338 memory: 6691 loss_kpt: 0.000836 acc_pose: 0.698489 loss: 0.000836 2022/09/22 11:32:37 - mmengine - INFO - Epoch(train) [21][100/293] lr: 5.000000e-04 eta: 7:26:09 time: 0.559835 data_time: 0.284526 memory: 6691 loss_kpt: 0.000826 acc_pose: 0.735619 loss: 0.000826 2022/09/22 11:32:58 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 11:33:03 - mmengine - INFO - Epoch(train) [21][150/293] lr: 5.000000e-04 eta: 7:26:10 time: 0.535064 data_time: 0.079383 memory: 6691 loss_kpt: 0.000835 acc_pose: 0.759442 loss: 0.000835 2022/09/22 11:33:30 - mmengine - INFO - Epoch(train) [21][200/293] lr: 5.000000e-04 eta: 7:26:07 time: 0.528460 data_time: 0.090358 memory: 6691 loss_kpt: 0.000845 acc_pose: 0.736335 loss: 0.000845 2022/09/22 11:33:56 - mmengine - INFO - Epoch(train) [21][250/293] lr: 5.000000e-04 eta: 7:26:04 time: 0.530753 data_time: 0.077135 memory: 6691 loss_kpt: 0.000835 acc_pose: 0.763812 loss: 0.000835 2022/09/22 11:34:20 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 11:34:50 - mmengine - INFO - Epoch(train) [22][50/293] lr: 5.000000e-04 eta: 7:22:59 time: 0.582473 data_time: 0.198804 memory: 6691 loss_kpt: 0.000825 acc_pose: 0.755110 loss: 0.000825 2022/09/22 11:35:17 - mmengine - INFO - Epoch(train) [22][100/293] lr: 5.000000e-04 eta: 7:23:04 time: 0.546736 data_time: 0.094716 memory: 6691 loss_kpt: 0.000833 acc_pose: 0.731875 loss: 0.000833 2022/09/22 11:35:45 - mmengine - INFO - Epoch(train) [22][150/293] lr: 5.000000e-04 eta: 7:23:12 time: 0.553194 data_time: 0.087389 memory: 6691 loss_kpt: 0.000832 acc_pose: 0.703026 loss: 0.000832 2022/09/22 11:36:14 - mmengine - INFO - Epoch(train) [22][200/293] lr: 5.000000e-04 eta: 7:23:32 time: 0.583194 data_time: 0.096322 memory: 6691 loss_kpt: 0.000838 acc_pose: 0.752006 loss: 0.000838 2022/09/22 11:36:42 - mmengine - INFO - Epoch(train) [22][250/293] lr: 5.000000e-04 eta: 7:23:46 time: 0.571247 data_time: 0.113937 memory: 6691 loss_kpt: 0.000840 acc_pose: 0.790106 loss: 0.000840 2022/09/22 11:37:06 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 11:37:35 - mmengine - INFO - Epoch(train) [23][50/293] lr: 5.000000e-04 eta: 7:20:50 time: 0.589554 data_time: 0.121454 memory: 6691 loss_kpt: 0.000825 acc_pose: 0.792211 loss: 0.000825 2022/09/22 11:38:04 - mmengine - INFO - Epoch(train) [23][100/293] lr: 5.000000e-04 eta: 7:21:03 time: 0.567548 data_time: 0.107267 memory: 6691 loss_kpt: 0.000821 acc_pose: 0.777481 loss: 0.000821 2022/09/22 11:38:32 - mmengine - INFO - Epoch(train) [23][150/293] lr: 5.000000e-04 eta: 7:21:13 time: 0.564076 data_time: 0.095834 memory: 6691 loss_kpt: 0.000831 acc_pose: 0.781327 loss: 0.000831 2022/09/22 11:38:59 - mmengine - INFO - Epoch(train) [23][200/293] lr: 5.000000e-04 eta: 7:21:15 time: 0.545886 data_time: 0.095199 memory: 6691 loss_kpt: 0.000824 acc_pose: 0.742875 loss: 0.000824 2022/09/22 11:39:26 - mmengine - INFO - Epoch(train) [23][250/293] lr: 5.000000e-04 eta: 7:21:14 time: 0.538418 data_time: 0.087740 memory: 6691 loss_kpt: 0.000830 acc_pose: 0.721737 loss: 0.000830 2022/09/22 11:39:50 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 11:40:19 - mmengine - INFO - Epoch(train) [24][50/293] lr: 5.000000e-04 eta: 7:18:23 time: 0.584634 data_time: 0.170444 memory: 6691 loss_kpt: 0.000824 acc_pose: 0.753803 loss: 0.000824 2022/09/22 11:40:48 - mmengine - INFO - Epoch(train) [24][100/293] lr: 5.000000e-04 eta: 7:18:33 time: 0.565926 data_time: 0.131631 memory: 6691 loss_kpt: 0.000843 acc_pose: 0.728602 loss: 0.000843 2022/09/22 11:41:16 - mmengine - INFO - Epoch(train) [24][150/293] lr: 5.000000e-04 eta: 7:18:46 time: 0.574094 data_time: 0.121702 memory: 6691 loss_kpt: 0.000817 acc_pose: 0.726622 loss: 0.000817 2022/09/22 11:41:45 - mmengine - INFO - Epoch(train) [24][200/293] lr: 5.000000e-04 eta: 7:18:55 time: 0.565189 data_time: 0.094079 memory: 6691 loss_kpt: 0.000810 acc_pose: 0.740437 loss: 0.000810 2022/09/22 11:42:12 - mmengine - INFO - Epoch(train) [24][250/293] lr: 5.000000e-04 eta: 7:19:00 time: 0.558256 data_time: 0.127491 memory: 6691 loss_kpt: 0.000812 acc_pose: 0.703132 loss: 0.000812 2022/09/22 11:42:19 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 11:42:37 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 11:43:07 - mmengine - INFO - Epoch(train) [25][50/293] lr: 5.000000e-04 eta: 7:16:20 time: 0.598263 data_time: 0.203278 memory: 6691 loss_kpt: 0.000845 acc_pose: 0.770326 loss: 0.000845 2022/09/22 11:43:35 - mmengine - INFO - Epoch(train) [25][100/293] lr: 5.000000e-04 eta: 7:16:31 time: 0.572109 data_time: 0.130302 memory: 6691 loss_kpt: 0.000827 acc_pose: 0.749591 loss: 0.000827 2022/09/22 11:44:05 - mmengine - INFO - Epoch(train) [25][150/293] lr: 5.000000e-04 eta: 7:16:47 time: 0.587435 data_time: 0.127671 memory: 6691 loss_kpt: 0.000830 acc_pose: 0.761351 loss: 0.000830 2022/09/22 11:44:32 - mmengine - INFO - Epoch(train) [25][200/293] lr: 5.000000e-04 eta: 7:16:45 time: 0.542548 data_time: 0.096722 memory: 6691 loss_kpt: 0.000814 acc_pose: 0.800578 loss: 0.000814 2022/09/22 11:44:59 - mmengine - INFO - Epoch(train) [25][250/293] lr: 5.000000e-04 eta: 7:16:43 time: 0.542448 data_time: 0.094135 memory: 6691 loss_kpt: 0.000829 acc_pose: 0.787594 loss: 0.000829 2022/09/22 11:45:23 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 11:45:52 - mmengine - INFO - Epoch(train) [26][50/293] lr: 5.000000e-04 eta: 7:14:01 time: 0.577853 data_time: 0.106454 memory: 6691 loss_kpt: 0.000819 acc_pose: 0.754926 loss: 0.000819 2022/09/22 11:46:18 - mmengine - INFO - Epoch(train) [26][100/293] lr: 5.000000e-04 eta: 7:13:57 time: 0.536470 data_time: 0.088071 memory: 6691 loss_kpt: 0.000816 acc_pose: 0.783921 loss: 0.000816 2022/09/22 11:46:45 - mmengine - INFO - Epoch(train) [26][150/293] lr: 5.000000e-04 eta: 7:13:54 time: 0.539892 data_time: 0.096787 memory: 6691 loss_kpt: 0.000802 acc_pose: 0.736918 loss: 0.000802 2022/09/22 11:47:12 - mmengine - INFO - Epoch(train) [26][200/293] lr: 5.000000e-04 eta: 7:13:49 time: 0.533804 data_time: 0.084660 memory: 6691 loss_kpt: 0.000811 acc_pose: 0.785008 loss: 0.000811 2022/09/22 11:47:39 - mmengine - INFO - Epoch(train) [26][250/293] lr: 5.000000e-04 eta: 7:13:44 time: 0.536056 data_time: 0.089253 memory: 6691 loss_kpt: 0.000815 acc_pose: 0.770196 loss: 0.000815 2022/09/22 11:48:02 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 11:48:31 - mmengine - INFO - Epoch(train) [27][50/293] lr: 5.000000e-04 eta: 7:11:08 time: 0.582132 data_time: 0.267032 memory: 6691 loss_kpt: 0.000813 acc_pose: 0.703079 loss: 0.000813 2022/09/22 11:48:59 - mmengine - INFO - Epoch(train) [27][100/293] lr: 5.000000e-04 eta: 7:11:11 time: 0.556270 data_time: 0.235512 memory: 6691 loss_kpt: 0.000821 acc_pose: 0.772379 loss: 0.000821 2022/09/22 11:49:26 - mmengine - INFO - Epoch(train) [27][150/293] lr: 5.000000e-04 eta: 7:11:06 time: 0.537281 data_time: 0.259306 memory: 6691 loss_kpt: 0.000816 acc_pose: 0.727953 loss: 0.000816 2022/09/22 11:49:54 - mmengine - INFO - Epoch(train) [27][200/293] lr: 5.000000e-04 eta: 7:11:12 time: 0.569217 data_time: 0.231152 memory: 6691 loss_kpt: 0.000824 acc_pose: 0.768705 loss: 0.000824 2022/09/22 11:50:22 - mmengine - INFO - Epoch(train) [27][250/293] lr: 5.000000e-04 eta: 7:11:14 time: 0.556493 data_time: 0.145219 memory: 6691 loss_kpt: 0.000822 acc_pose: 0.793387 loss: 0.000822 2022/09/22 11:50:46 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 11:51:15 - mmengine - INFO - Epoch(train) [28][50/293] lr: 5.000000e-04 eta: 7:08:37 time: 0.564844 data_time: 0.116263 memory: 6691 loss_kpt: 0.000810 acc_pose: 0.754284 loss: 0.000810 2022/09/22 11:51:36 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 11:51:43 - mmengine - INFO - Epoch(train) [28][100/293] lr: 5.000000e-04 eta: 7:08:41 time: 0.562927 data_time: 0.095546 memory: 6691 loss_kpt: 0.000802 acc_pose: 0.751840 loss: 0.000802 2022/09/22 11:52:12 - mmengine - INFO - Epoch(train) [28][150/293] lr: 5.000000e-04 eta: 7:08:53 time: 0.589359 data_time: 0.114092 memory: 6691 loss_kpt: 0.000805 acc_pose: 0.766151 loss: 0.000805 2022/09/22 11:52:40 - mmengine - INFO - Epoch(train) [28][200/293] lr: 5.000000e-04 eta: 7:08:55 time: 0.559428 data_time: 0.103477 memory: 6691 loss_kpt: 0.000802 acc_pose: 0.759958 loss: 0.000802 2022/09/22 11:53:08 - mmengine - INFO - Epoch(train) [28][250/293] lr: 5.000000e-04 eta: 7:08:54 time: 0.554000 data_time: 0.089119 memory: 6691 loss_kpt: 0.000796 acc_pose: 0.762371 loss: 0.000796 2022/09/22 11:53:32 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 11:54:01 - mmengine - INFO - Epoch(train) [29][50/293] lr: 5.000000e-04 eta: 7:06:27 time: 0.579215 data_time: 0.217889 memory: 6691 loss_kpt: 0.000801 acc_pose: 0.821107 loss: 0.000801 2022/09/22 11:54:29 - mmengine - INFO - Epoch(train) [29][100/293] lr: 5.000000e-04 eta: 7:06:32 time: 0.571092 data_time: 0.122580 memory: 6691 loss_kpt: 0.000797 acc_pose: 0.826922 loss: 0.000797 2022/09/22 11:54:56 - mmengine - INFO - Epoch(train) [29][150/293] lr: 5.000000e-04 eta: 7:06:27 time: 0.542046 data_time: 0.085657 memory: 6691 loss_kpt: 0.000805 acc_pose: 0.742798 loss: 0.000805 2022/09/22 11:55:24 - mmengine - INFO - Epoch(train) [29][200/293] lr: 5.000000e-04 eta: 7:06:24 time: 0.546919 data_time: 0.074375 memory: 6691 loss_kpt: 0.000799 acc_pose: 0.727303 loss: 0.000799 2022/09/22 11:55:53 - mmengine - INFO - Epoch(train) [29][250/293] lr: 5.000000e-04 eta: 7:06:33 time: 0.585737 data_time: 0.097111 memory: 6691 loss_kpt: 0.000795 acc_pose: 0.771684 loss: 0.000795 2022/09/22 11:56:17 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 11:56:46 - mmengine - INFO - Epoch(train) [30][50/293] lr: 5.000000e-04 eta: 7:04:13 time: 0.592125 data_time: 0.305971 memory: 6691 loss_kpt: 0.000788 acc_pose: 0.774079 loss: 0.000788 2022/09/22 11:57:15 - mmengine - INFO - Epoch(train) [30][100/293] lr: 5.000000e-04 eta: 7:04:18 time: 0.572424 data_time: 0.225840 memory: 6691 loss_kpt: 0.000795 acc_pose: 0.754617 loss: 0.000795 2022/09/22 11:57:42 - mmengine - INFO - Epoch(train) [30][150/293] lr: 5.000000e-04 eta: 7:04:11 time: 0.536018 data_time: 0.075092 memory: 6691 loss_kpt: 0.000810 acc_pose: 0.760765 loss: 0.000810 2022/09/22 11:58:09 - mmengine - INFO - Epoch(train) [30][200/293] lr: 5.000000e-04 eta: 7:04:04 time: 0.539740 data_time: 0.113702 memory: 6691 loss_kpt: 0.000816 acc_pose: 0.798074 loss: 0.000816 2022/09/22 11:58:38 - mmengine - INFO - Epoch(train) [30][250/293] lr: 5.000000e-04 eta: 7:04:11 time: 0.582694 data_time: 0.313997 memory: 6691 loss_kpt: 0.000799 acc_pose: 0.727074 loss: 0.000799 2022/09/22 11:59:02 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 11:59:02 - mmengine - INFO - Saving checkpoint at 30 epochs 2022/09/22 11:59:23 - mmengine - INFO - Epoch(val) [30][50/407] eta: 0:01:49 time: 0.307975 data_time: 0.175404 memory: 6691 2022/09/22 11:59:39 - mmengine - INFO - Epoch(val) [30][100/407] eta: 0:01:38 time: 0.320440 data_time: 0.175439 memory: 1014 2022/09/22 11:59:55 - mmengine - INFO - Epoch(val) [30][150/407] eta: 0:01:22 time: 0.319172 data_time: 0.179776 memory: 1014 2022/09/22 12:00:12 - mmengine - INFO - Epoch(val) [30][200/407] eta: 0:01:09 time: 0.336628 data_time: 0.178332 memory: 1014 2022/09/22 12:00:28 - mmengine - INFO - Epoch(val) [30][250/407] eta: 0:00:48 time: 0.308414 data_time: 0.163499 memory: 1014 2022/09/22 12:00:43 - mmengine - INFO - Epoch(val) [30][300/407] eta: 0:00:33 time: 0.312899 data_time: 0.175668 memory: 1014 2022/09/22 12:00:59 - mmengine - INFO - Epoch(val) [30][350/407] eta: 0:00:17 time: 0.311835 data_time: 0.173347 memory: 1014 2022/09/22 12:01:11 - mmengine - INFO - Epoch(val) [30][400/407] eta: 0:00:01 time: 0.232101 data_time: 0.136054 memory: 1014 2022/09/22 12:01:43 - mmengine - INFO - Evaluating CocoMetric... 2022/09/22 12:01:56 - mmengine - INFO - Epoch(val) [30][407/407] coco/AP: 0.650211 coco/AP .5: 0.872983 coco/AP .75: 0.728056 coco/AP (M): 0.613230 coco/AP (L): 0.719629 coco/AR: 0.711571 coco/AR .5: 0.915145 coco/AR .75: 0.785264 coco/AR (M): 0.664736 coco/AR (L): 0.778224 2022/09/22 12:01:57 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220922/res50_256/best_coco/AP_epoch_20.pth is removed 2022/09/22 12:01:59 - mmengine - INFO - The best checkpoint with 0.6502 coco/AP at 30 epoch is saved to best_coco/AP_epoch_30.pth. 2022/09/22 12:02:25 - mmengine - INFO - Epoch(train) [31][50/293] lr: 5.000000e-04 eta: 7:01:35 time: 0.524876 data_time: 0.246140 memory: 6691 loss_kpt: 0.000788 acc_pose: 0.759622 loss: 0.000788 2022/09/22 12:02:53 - mmengine - INFO - Epoch(train) [31][100/293] lr: 5.000000e-04 eta: 7:01:32 time: 0.550261 data_time: 0.108745 memory: 6691 loss_kpt: 0.000806 acc_pose: 0.794553 loss: 0.000806 2022/09/22 12:03:22 - mmengine - INFO - Epoch(train) [31][150/293] lr: 5.000000e-04 eta: 7:01:37 time: 0.579878 data_time: 0.107075 memory: 6691 loss_kpt: 0.000804 acc_pose: 0.738763 loss: 0.000804 2022/09/22 12:03:50 - mmengine - INFO - Epoch(train) [31][200/293] lr: 5.000000e-04 eta: 7:01:38 time: 0.566230 data_time: 0.093940 memory: 6691 loss_kpt: 0.000800 acc_pose: 0.749737 loss: 0.000800 2022/09/22 12:03:55 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 12:04:18 - mmengine - INFO - Epoch(train) [31][250/293] lr: 5.000000e-04 eta: 7:01:36 time: 0.556682 data_time: 0.083272 memory: 6691 loss_kpt: 0.000800 acc_pose: 0.782733 loss: 0.000800 2022/09/22 12:04:42 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 12:05:10 - mmengine - INFO - Epoch(train) [32][50/293] lr: 5.000000e-04 eta: 6:59:16 time: 0.567810 data_time: 0.169675 memory: 6691 loss_kpt: 0.000780 acc_pose: 0.779588 loss: 0.000780 2022/09/22 12:05:38 - mmengine - INFO - Epoch(train) [32][100/293] lr: 5.000000e-04 eta: 6:59:18 time: 0.568410 data_time: 0.123083 memory: 6691 loss_kpt: 0.000800 acc_pose: 0.779234 loss: 0.000800 2022/09/22 12:06:05 - mmengine - INFO - Epoch(train) [32][150/293] lr: 5.000000e-04 eta: 6:59:08 time: 0.530106 data_time: 0.072987 memory: 6691 loss_kpt: 0.000803 acc_pose: 0.718259 loss: 0.000803 2022/09/22 12:06:32 - mmengine - INFO - Epoch(train) [32][200/293] lr: 5.000000e-04 eta: 6:58:58 time: 0.532896 data_time: 0.084591 memory: 6691 loss_kpt: 0.000779 acc_pose: 0.799054 loss: 0.000779 2022/09/22 12:06:59 - mmengine - INFO - Epoch(train) [32][250/293] lr: 5.000000e-04 eta: 6:58:55 time: 0.555592 data_time: 0.112105 memory: 6691 loss_kpt: 0.000797 acc_pose: 0.790552 loss: 0.000797 2022/09/22 12:07:22 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 12:07:51 - mmengine - INFO - Epoch(train) [33][50/293] lr: 5.000000e-04 eta: 6:56:44 time: 0.583916 data_time: 0.214749 memory: 6691 loss_kpt: 0.000790 acc_pose: 0.773219 loss: 0.000790 2022/09/22 12:08:20 - mmengine - INFO - Epoch(train) [33][100/293] lr: 5.000000e-04 eta: 6:56:47 time: 0.576315 data_time: 0.172030 memory: 6691 loss_kpt: 0.000790 acc_pose: 0.806763 loss: 0.000790 2022/09/22 12:08:48 - mmengine - INFO - Epoch(train) [33][150/293] lr: 5.000000e-04 eta: 6:56:42 time: 0.552112 data_time: 0.096127 memory: 6691 loss_kpt: 0.000808 acc_pose: 0.725968 loss: 0.000808 2022/09/22 12:09:15 - mmengine - INFO - Epoch(train) [33][200/293] lr: 5.000000e-04 eta: 6:56:39 time: 0.558144 data_time: 0.201456 memory: 6691 loss_kpt: 0.000796 acc_pose: 0.773435 loss: 0.000796 2022/09/22 12:09:44 - mmengine - INFO - Epoch(train) [33][250/293] lr: 5.000000e-04 eta: 6:56:37 time: 0.561372 data_time: 0.138564 memory: 6691 loss_kpt: 0.000790 acc_pose: 0.770471 loss: 0.000790 2022/09/22 12:10:06 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 12:10:36 - mmengine - INFO - Epoch(train) [34][50/293] lr: 5.000000e-04 eta: 6:54:30 time: 0.590406 data_time: 0.118843 memory: 6691 loss_kpt: 0.000794 acc_pose: 0.764173 loss: 0.000794 2022/09/22 12:11:02 - mmengine - INFO - Epoch(train) [34][100/293] lr: 5.000000e-04 eta: 6:54:21 time: 0.533454 data_time: 0.075810 memory: 6691 loss_kpt: 0.000792 acc_pose: 0.770004 loss: 0.000792 2022/09/22 12:11:30 - mmengine - INFO - Epoch(train) [34][150/293] lr: 5.000000e-04 eta: 6:54:17 time: 0.556796 data_time: 0.093329 memory: 6691 loss_kpt: 0.000786 acc_pose: 0.766408 loss: 0.000786 2022/09/22 12:11:59 - mmengine - INFO - Epoch(train) [34][200/293] lr: 5.000000e-04 eta: 6:54:18 time: 0.578176 data_time: 0.130495 memory: 6691 loss_kpt: 0.000798 acc_pose: 0.756040 loss: 0.000798 2022/09/22 12:12:28 - mmengine - INFO - Epoch(train) [34][250/293] lr: 5.000000e-04 eta: 6:54:21 time: 0.584374 data_time: 0.116532 memory: 6691 loss_kpt: 0.000795 acc_pose: 0.770086 loss: 0.000795 2022/09/22 12:12:52 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 12:13:15 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 12:13:22 - mmengine - INFO - Epoch(train) [35][50/293] lr: 5.000000e-04 eta: 6:52:20 time: 0.598406 data_time: 0.098398 memory: 6691 loss_kpt: 0.000777 acc_pose: 0.765004 loss: 0.000777 2022/09/22 12:13:50 - mmengine - INFO - Epoch(train) [35][100/293] lr: 5.000000e-04 eta: 6:52:17 time: 0.565467 data_time: 0.151716 memory: 6691 loss_kpt: 0.000783 acc_pose: 0.748128 loss: 0.000783 2022/09/22 12:14:18 - mmengine - INFO - Epoch(train) [35][150/293] lr: 5.000000e-04 eta: 6:52:09 time: 0.540865 data_time: 0.082647 memory: 6691 loss_kpt: 0.000780 acc_pose: 0.813605 loss: 0.000780 2022/09/22 12:14:45 - mmengine - INFO - Epoch(train) [35][200/293] lr: 5.000000e-04 eta: 6:51:59 time: 0.539518 data_time: 0.075421 memory: 6691 loss_kpt: 0.000783 acc_pose: 0.792954 loss: 0.000783 2022/09/22 12:15:12 - mmengine - INFO - Epoch(train) [35][250/293] lr: 5.000000e-04 eta: 6:51:51 time: 0.543865 data_time: 0.078760 memory: 6691 loss_kpt: 0.000767 acc_pose: 0.800872 loss: 0.000767 2022/09/22 12:15:35 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 12:16:05 - mmengine - INFO - Epoch(train) [36][50/293] lr: 5.000000e-04 eta: 6:49:51 time: 0.593618 data_time: 0.245684 memory: 6691 loss_kpt: 0.000791 acc_pose: 0.743635 loss: 0.000791 2022/09/22 12:16:34 - mmengine - INFO - Epoch(train) [36][100/293] lr: 5.000000e-04 eta: 6:49:54 time: 0.587872 data_time: 0.089807 memory: 6691 loss_kpt: 0.000778 acc_pose: 0.781415 loss: 0.000778 2022/09/22 12:17:03 - mmengine - INFO - Epoch(train) [36][150/293] lr: 5.000000e-04 eta: 6:49:53 time: 0.573614 data_time: 0.126561 memory: 6691 loss_kpt: 0.000774 acc_pose: 0.792211 loss: 0.000774 2022/09/22 12:17:31 - mmengine - INFO - Epoch(train) [36][200/293] lr: 5.000000e-04 eta: 6:49:47 time: 0.554646 data_time: 0.138734 memory: 6691 loss_kpt: 0.000782 acc_pose: 0.790619 loss: 0.000782 2022/09/22 12:17:59 - mmengine - INFO - Epoch(train) [36][250/293] lr: 5.000000e-04 eta: 6:49:41 time: 0.557545 data_time: 0.222140 memory: 6691 loss_kpt: 0.000783 acc_pose: 0.734396 loss: 0.000783 2022/09/22 12:18:22 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 12:18:51 - mmengine - INFO - Epoch(train) [37][50/293] lr: 5.000000e-04 eta: 6:47:40 time: 0.579016 data_time: 0.231329 memory: 6691 loss_kpt: 0.000792 acc_pose: 0.785262 loss: 0.000792 2022/09/22 12:19:20 - mmengine - INFO - Epoch(train) [37][100/293] lr: 5.000000e-04 eta: 6:47:39 time: 0.577156 data_time: 0.208829 memory: 6691 loss_kpt: 0.000793 acc_pose: 0.767009 loss: 0.000793 2022/09/22 12:19:49 - mmengine - INFO - Epoch(train) [37][150/293] lr: 5.000000e-04 eta: 6:47:38 time: 0.577296 data_time: 0.218564 memory: 6691 loss_kpt: 0.000790 acc_pose: 0.763108 loss: 0.000790 2022/09/22 12:20:16 - mmengine - INFO - Epoch(train) [37][200/293] lr: 5.000000e-04 eta: 6:47:28 time: 0.541862 data_time: 0.092753 memory: 6691 loss_kpt: 0.000771 acc_pose: 0.824975 loss: 0.000771 2022/09/22 12:20:43 - mmengine - INFO - Epoch(train) [37][250/293] lr: 5.000000e-04 eta: 6:47:21 time: 0.552930 data_time: 0.078149 memory: 6691 loss_kpt: 0.000789 acc_pose: 0.792939 loss: 0.000789 2022/09/22 12:21:06 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 12:21:35 - mmengine - INFO - Epoch(train) [38][50/293] lr: 5.000000e-04 eta: 6:45:21 time: 0.572833 data_time: 0.104693 memory: 6691 loss_kpt: 0.000793 acc_pose: 0.749827 loss: 0.000793 2022/09/22 12:22:02 - mmengine - INFO - Epoch(train) [38][100/293] lr: 5.000000e-04 eta: 6:45:11 time: 0.538679 data_time: 0.073124 memory: 6691 loss_kpt: 0.000757 acc_pose: 0.794968 loss: 0.000757 2022/09/22 12:22:29 - mmengine - INFO - Epoch(train) [38][150/293] lr: 5.000000e-04 eta: 6:45:04 time: 0.555676 data_time: 0.077673 memory: 6691 loss_kpt: 0.000781 acc_pose: 0.770869 loss: 0.000781 2022/09/22 12:22:34 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 12:22:56 - mmengine - INFO - Epoch(train) [38][200/293] lr: 5.000000e-04 eta: 6:44:53 time: 0.540411 data_time: 0.078200 memory: 6691 loss_kpt: 0.000771 acc_pose: 0.779743 loss: 0.000771 2022/09/22 12:23:23 - mmengine - INFO - Epoch(train) [38][250/293] lr: 5.000000e-04 eta: 6:44:42 time: 0.534761 data_time: 0.070177 memory: 6691 loss_kpt: 0.000777 acc_pose: 0.805269 loss: 0.000777 2022/09/22 12:23:47 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 12:24:16 - mmengine - INFO - Epoch(train) [39][50/293] lr: 5.000000e-04 eta: 6:42:49 time: 0.595529 data_time: 0.166400 memory: 6691 loss_kpt: 0.000789 acc_pose: 0.763769 loss: 0.000789 2022/09/22 12:24:43 - mmengine - INFO - Epoch(train) [39][100/293] lr: 5.000000e-04 eta: 6:42:39 time: 0.540669 data_time: 0.079198 memory: 6691 loss_kpt: 0.000769 acc_pose: 0.732764 loss: 0.000769 2022/09/22 12:25:12 - mmengine - INFO - Epoch(train) [39][150/293] lr: 5.000000e-04 eta: 6:42:37 time: 0.578171 data_time: 0.077383 memory: 6691 loss_kpt: 0.000767 acc_pose: 0.807519 loss: 0.000767 2022/09/22 12:25:41 - mmengine - INFO - Epoch(train) [39][200/293] lr: 5.000000e-04 eta: 6:42:34 time: 0.578642 data_time: 0.094734 memory: 6691 loss_kpt: 0.000776 acc_pose: 0.771690 loss: 0.000776 2022/09/22 12:26:10 - mmengine - INFO - Epoch(train) [39][250/293] lr: 5.000000e-04 eta: 6:42:30 time: 0.573515 data_time: 0.085972 memory: 6691 loss_kpt: 0.000770 acc_pose: 0.657320 loss: 0.000770 2022/09/22 12:26:33 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 12:27:03 - mmengine - INFO - Epoch(train) [40][50/293] lr: 5.000000e-04 eta: 6:40:39 time: 0.591880 data_time: 0.112560 memory: 6691 loss_kpt: 0.000771 acc_pose: 0.746173 loss: 0.000771 2022/09/22 12:27:31 - mmengine - INFO - Epoch(train) [40][100/293] lr: 5.000000e-04 eta: 6:40:36 time: 0.576841 data_time: 0.151967 memory: 6691 loss_kpt: 0.000779 acc_pose: 0.795687 loss: 0.000779 2022/09/22 12:28:00 - mmengine - INFO - Epoch(train) [40][150/293] lr: 5.000000e-04 eta: 6:40:31 time: 0.569431 data_time: 0.234094 memory: 6691 loss_kpt: 0.000772 acc_pose: 0.797984 loss: 0.000772 2022/09/22 12:28:29 - mmengine - INFO - Epoch(train) [40][200/293] lr: 5.000000e-04 eta: 6:40:28 time: 0.576438 data_time: 0.102508 memory: 6691 loss_kpt: 0.000774 acc_pose: 0.775633 loss: 0.000774 2022/09/22 12:28:57 - mmengine - INFO - Epoch(train) [40][250/293] lr: 5.000000e-04 eta: 6:40:23 time: 0.569227 data_time: 0.088231 memory: 6691 loss_kpt: 0.000783 acc_pose: 0.765666 loss: 0.000783 2022/09/22 12:29:21 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 12:29:21 - mmengine - INFO - Saving checkpoint at 40 epochs 2022/09/22 12:29:43 - mmengine - INFO - Epoch(val) [40][50/407] eta: 0:01:55 time: 0.322970 data_time: 0.175435 memory: 6691 2022/09/22 12:29:59 - mmengine - INFO - Epoch(val) [40][100/407] eta: 0:01:35 time: 0.310768 data_time: 0.169297 memory: 1014 2022/09/22 12:30:15 - mmengine - INFO - Epoch(val) [40][150/407] eta: 0:01:21 time: 0.317293 data_time: 0.177357 memory: 1014 2022/09/22 12:30:30 - mmengine - INFO - Epoch(val) [40][200/407] eta: 0:01:01 time: 0.297731 data_time: 0.168364 memory: 1014 2022/09/22 12:30:46 - mmengine - INFO - Epoch(val) [40][250/407] eta: 0:00:50 time: 0.318597 data_time: 0.175958 memory: 1014 2022/09/22 12:31:01 - mmengine - INFO - Epoch(val) [40][300/407] eta: 0:00:33 time: 0.315624 data_time: 0.184286 memory: 1014 2022/09/22 12:31:18 - mmengine - INFO - Epoch(val) [40][350/407] eta: 0:00:19 time: 0.336013 data_time: 0.191068 memory: 1014 2022/09/22 12:31:29 - mmengine - INFO - Epoch(val) [40][400/407] eta: 0:00:01 time: 0.205818 data_time: 0.113854 memory: 1014 2022/09/22 12:32:02 - mmengine - INFO - Evaluating CocoMetric... 2022/09/22 12:32:15 - mmengine - INFO - Epoch(val) [40][407/407] coco/AP: 0.660802 coco/AP .5: 0.875982 coco/AP .75: 0.739182 coco/AP (M): 0.626705 coco/AP (L): 0.724597 coco/AR: 0.722922 coco/AR .5: 0.917821 coco/AR .75: 0.796757 coco/AR (M): 0.678667 coco/AR (L): 0.786250 2022/09/22 12:32:15 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220922/res50_256/best_coco/AP_epoch_30.pth is removed 2022/09/22 12:32:17 - mmengine - INFO - The best checkpoint with 0.6608 coco/AP at 40 epoch is saved to best_coco/AP_epoch_40.pth. 2022/09/22 12:32:44 - mmengine - INFO - Epoch(train) [41][50/293] lr: 5.000000e-04 eta: 6:38:24 time: 0.547224 data_time: 0.329854 memory: 6691 loss_kpt: 0.000767 acc_pose: 0.774176 loss: 0.000767 2022/09/22 12:33:13 - mmengine - INFO - Epoch(train) [41][100/293] lr: 5.000000e-04 eta: 6:38:18 time: 0.565331 data_time: 0.154546 memory: 6691 loss_kpt: 0.000774 acc_pose: 0.712040 loss: 0.000774 2022/09/22 12:33:41 - mmengine - INFO - Epoch(train) [41][150/293] lr: 5.000000e-04 eta: 6:38:11 time: 0.562498 data_time: 0.087962 memory: 6691 loss_kpt: 0.000773 acc_pose: 0.758860 loss: 0.000773 2022/09/22 12:34:09 - mmengine - INFO - Epoch(train) [41][200/293] lr: 5.000000e-04 eta: 6:38:02 time: 0.556019 data_time: 0.079561 memory: 6691 loss_kpt: 0.000774 acc_pose: 0.771673 loss: 0.000774 2022/09/22 12:34:35 - mmengine - INFO - Epoch(train) [41][250/293] lr: 5.000000e-04 eta: 6:37:50 time: 0.536074 data_time: 0.071269 memory: 6691 loss_kpt: 0.000770 acc_pose: 0.755770 loss: 0.000770 2022/09/22 12:34:52 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 12:34:59 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 12:35:28 - mmengine - INFO - Epoch(train) [42][50/293] lr: 5.000000e-04 eta: 6:36:00 time: 0.581035 data_time: 0.256182 memory: 6691 loss_kpt: 0.000766 acc_pose: 0.799341 loss: 0.000766 2022/09/22 12:35:55 - mmengine - INFO - Epoch(train) [42][100/293] lr: 5.000000e-04 eta: 6:35:50 time: 0.548870 data_time: 0.248628 memory: 6691 loss_kpt: 0.000761 acc_pose: 0.793220 loss: 0.000761 2022/09/22 12:36:22 - mmengine - INFO - Epoch(train) [42][150/293] lr: 5.000000e-04 eta: 6:35:35 time: 0.525496 data_time: 0.241014 memory: 6691 loss_kpt: 0.000766 acc_pose: 0.743270 loss: 0.000766 2022/09/22 12:36:50 - mmengine - INFO - Epoch(train) [42][200/293] lr: 5.000000e-04 eta: 6:35:27 time: 0.560455 data_time: 0.182451 memory: 6691 loss_kpt: 0.000765 acc_pose: 0.761203 loss: 0.000765 2022/09/22 12:37:17 - mmengine - INFO - Epoch(train) [42][250/293] lr: 5.000000e-04 eta: 6:35:17 time: 0.548281 data_time: 0.099239 memory: 6691 loss_kpt: 0.000765 acc_pose: 0.748852 loss: 0.000765 2022/09/22 12:37:40 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 12:38:09 - mmengine - INFO - Epoch(train) [43][50/293] lr: 5.000000e-04 eta: 6:33:30 time: 0.585766 data_time: 0.200878 memory: 6691 loss_kpt: 0.000767 acc_pose: 0.784447 loss: 0.000767 2022/09/22 12:38:37 - mmengine - INFO - Epoch(train) [43][100/293] lr: 5.000000e-04 eta: 6:33:22 time: 0.557409 data_time: 0.192864 memory: 6691 loss_kpt: 0.000764 acc_pose: 0.760736 loss: 0.000764 2022/09/22 12:39:05 - mmengine - INFO - Epoch(train) [43][150/293] lr: 5.000000e-04 eta: 6:33:14 time: 0.561347 data_time: 0.261233 memory: 6691 loss_kpt: 0.000766 acc_pose: 0.786925 loss: 0.000766 2022/09/22 12:39:33 - mmengine - INFO - Epoch(train) [43][200/293] lr: 5.000000e-04 eta: 6:33:06 time: 0.565053 data_time: 0.163276 memory: 6691 loss_kpt: 0.000744 acc_pose: 0.717837 loss: 0.000744 2022/09/22 12:40:02 - mmengine - INFO - Epoch(train) [43][250/293] lr: 5.000000e-04 eta: 6:33:01 time: 0.580459 data_time: 0.145724 memory: 6691 loss_kpt: 0.000772 acc_pose: 0.768405 loss: 0.000772 2022/09/22 12:40:27 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 12:40:56 - mmengine - INFO - Epoch(train) [44][50/293] lr: 5.000000e-04 eta: 6:31:17 time: 0.587859 data_time: 0.221567 memory: 6691 loss_kpt: 0.000755 acc_pose: 0.814194 loss: 0.000755 2022/09/22 12:41:23 - mmengine - INFO - Epoch(train) [44][100/293] lr: 5.000000e-04 eta: 6:31:05 time: 0.544097 data_time: 0.083346 memory: 6691 loss_kpt: 0.000761 acc_pose: 0.807695 loss: 0.000761 2022/09/22 12:41:52 - mmengine - INFO - Epoch(train) [44][150/293] lr: 5.000000e-04 eta: 6:30:58 time: 0.567854 data_time: 0.085139 memory: 6691 loss_kpt: 0.000748 acc_pose: 0.764759 loss: 0.000748 2022/09/22 12:42:18 - mmengine - INFO - Epoch(train) [44][200/293] lr: 5.000000e-04 eta: 6:30:43 time: 0.530642 data_time: 0.086542 memory: 6691 loss_kpt: 0.000777 acc_pose: 0.798865 loss: 0.000777 2022/09/22 12:42:46 - mmengine - INFO - Epoch(train) [44][250/293] lr: 5.000000e-04 eta: 6:30:33 time: 0.555280 data_time: 0.145945 memory: 6691 loss_kpt: 0.000769 acc_pose: 0.773810 loss: 0.000769 2022/09/22 12:43:11 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 12:43:40 - mmengine - INFO - Epoch(train) [45][50/293] lr: 5.000000e-04 eta: 6:28:49 time: 0.576878 data_time: 0.173158 memory: 6691 loss_kpt: 0.000764 acc_pose: 0.797463 loss: 0.000764 2022/09/22 12:44:07 - mmengine - INFO - Epoch(train) [45][100/293] lr: 5.000000e-04 eta: 6:28:37 time: 0.542941 data_time: 0.093931 memory: 6691 loss_kpt: 0.000763 acc_pose: 0.791479 loss: 0.000763 2022/09/22 12:44:11 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 12:44:36 - mmengine - INFO - Epoch(train) [45][150/293] lr: 5.000000e-04 eta: 6:28:31 time: 0.576497 data_time: 0.140264 memory: 6691 loss_kpt: 0.000760 acc_pose: 0.759505 loss: 0.000760 2022/09/22 12:45:04 - mmengine - INFO - Epoch(train) [45][200/293] lr: 5.000000e-04 eta: 6:28:24 time: 0.575733 data_time: 0.118668 memory: 6691 loss_kpt: 0.000759 acc_pose: 0.733764 loss: 0.000759 2022/09/22 12:45:31 - mmengine - INFO - Epoch(train) [45][250/293] lr: 5.000000e-04 eta: 6:28:11 time: 0.541981 data_time: 0.073765 memory: 6691 loss_kpt: 0.000780 acc_pose: 0.776687 loss: 0.000780 2022/09/22 12:45:55 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 12:46:24 - mmengine - INFO - Epoch(train) [46][50/293] lr: 5.000000e-04 eta: 6:26:31 time: 0.594096 data_time: 0.268510 memory: 6691 loss_kpt: 0.000764 acc_pose: 0.795509 loss: 0.000764 2022/09/22 12:46:54 - mmengine - INFO - Epoch(train) [46][100/293] lr: 5.000000e-04 eta: 6:26:27 time: 0.589505 data_time: 0.165305 memory: 6691 loss_kpt: 0.000766 acc_pose: 0.771463 loss: 0.000766 2022/09/22 12:47:23 - mmengine - INFO - Epoch(train) [46][150/293] lr: 5.000000e-04 eta: 6:26:21 time: 0.577866 data_time: 0.106758 memory: 6691 loss_kpt: 0.000763 acc_pose: 0.803836 loss: 0.000763 2022/09/22 12:47:50 - mmengine - INFO - Epoch(train) [46][200/293] lr: 5.000000e-04 eta: 6:26:09 time: 0.547253 data_time: 0.113484 memory: 6691 loss_kpt: 0.000747 acc_pose: 0.819873 loss: 0.000747 2022/09/22 12:48:19 - mmengine - INFO - Epoch(train) [46][250/293] lr: 5.000000e-04 eta: 6:26:01 time: 0.574675 data_time: 0.214529 memory: 6691 loss_kpt: 0.000761 acc_pose: 0.833446 loss: 0.000761 2022/09/22 12:48:42 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 12:49:12 - mmengine - INFO - Epoch(train) [47][50/293] lr: 5.000000e-04 eta: 6:24:24 time: 0.600091 data_time: 0.233007 memory: 6691 loss_kpt: 0.000759 acc_pose: 0.744554 loss: 0.000759 2022/09/22 12:49:41 - mmengine - INFO - Epoch(train) [47][100/293] lr: 5.000000e-04 eta: 6:24:16 time: 0.570547 data_time: 0.282598 memory: 6691 loss_kpt: 0.000763 acc_pose: 0.816668 loss: 0.000763 2022/09/22 12:50:10 - mmengine - INFO - Epoch(train) [47][150/293] lr: 5.000000e-04 eta: 6:24:11 time: 0.589360 data_time: 0.181603 memory: 6691 loss_kpt: 0.000758 acc_pose: 0.772700 loss: 0.000758 2022/09/22 12:50:39 - mmengine - INFO - Epoch(train) [47][200/293] lr: 5.000000e-04 eta: 6:24:01 time: 0.562135 data_time: 0.114169 memory: 6691 loss_kpt: 0.000758 acc_pose: 0.732429 loss: 0.000758 2022/09/22 12:51:06 - mmengine - INFO - Epoch(train) [47][250/293] lr: 5.000000e-04 eta: 6:23:48 time: 0.547034 data_time: 0.088267 memory: 6691 loss_kpt: 0.000764 acc_pose: 0.772145 loss: 0.000764 2022/09/22 12:51:30 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 12:51:59 - mmengine - INFO - Epoch(train) [48][50/293] lr: 5.000000e-04 eta: 6:22:11 time: 0.591466 data_time: 0.292943 memory: 6691 loss_kpt: 0.000749 acc_pose: 0.782157 loss: 0.000749 2022/09/22 12:52:28 - mmengine - INFO - Epoch(train) [48][100/293] lr: 5.000000e-04 eta: 6:22:02 time: 0.566504 data_time: 0.270948 memory: 6691 loss_kpt: 0.000777 acc_pose: 0.751874 loss: 0.000777 2022/09/22 12:52:57 - mmengine - INFO - Epoch(train) [48][150/293] lr: 5.000000e-04 eta: 6:21:56 time: 0.587336 data_time: 0.235899 memory: 6691 loss_kpt: 0.000766 acc_pose: 0.772835 loss: 0.000766 2022/09/22 12:53:26 - mmengine - INFO - Epoch(train) [48][200/293] lr: 5.000000e-04 eta: 6:21:48 time: 0.575331 data_time: 0.123489 memory: 6691 loss_kpt: 0.000768 acc_pose: 0.794159 loss: 0.000768 2022/09/22 12:53:42 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 12:53:54 - mmengine - INFO - Epoch(train) [48][250/293] lr: 5.000000e-04 eta: 6:21:39 time: 0.569759 data_time: 0.096002 memory: 6691 loss_kpt: 0.000744 acc_pose: 0.796392 loss: 0.000744 2022/09/22 12:54:19 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 12:54:48 - mmengine - INFO - Epoch(train) [49][50/293] lr: 5.000000e-04 eta: 6:20:00 time: 0.577539 data_time: 0.116584 memory: 6691 loss_kpt: 0.000766 acc_pose: 0.788189 loss: 0.000766 2022/09/22 12:55:17 - mmengine - INFO - Epoch(train) [49][100/293] lr: 5.000000e-04 eta: 6:19:54 time: 0.589934 data_time: 0.110251 memory: 6691 loss_kpt: 0.000751 acc_pose: 0.749040 loss: 0.000751 2022/09/22 12:55:45 - mmengine - INFO - Epoch(train) [49][150/293] lr: 5.000000e-04 eta: 6:19:45 time: 0.567273 data_time: 0.097557 memory: 6691 loss_kpt: 0.000750 acc_pose: 0.790908 loss: 0.000750 2022/09/22 12:56:12 - mmengine - INFO - Epoch(train) [49][200/293] lr: 5.000000e-04 eta: 6:19:30 time: 0.535211 data_time: 0.085396 memory: 6691 loss_kpt: 0.000748 acc_pose: 0.761713 loss: 0.000748 2022/09/22 12:56:41 - mmengine - INFO - Epoch(train) [49][250/293] lr: 5.000000e-04 eta: 6:19:20 time: 0.567451 data_time: 0.205847 memory: 6691 loss_kpt: 0.000760 acc_pose: 0.777087 loss: 0.000760 2022/09/22 12:57:04 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 12:57:32 - mmengine - INFO - Epoch(train) [50][50/293] lr: 5.000000e-04 eta: 6:17:42 time: 0.572880 data_time: 0.149105 memory: 6691 loss_kpt: 0.000759 acc_pose: 0.781242 loss: 0.000759 2022/09/22 12:57:59 - mmengine - INFO - Epoch(train) [50][100/293] lr: 5.000000e-04 eta: 6:17:27 time: 0.535676 data_time: 0.113458 memory: 6691 loss_kpt: 0.000755 acc_pose: 0.799935 loss: 0.000755 2022/09/22 12:58:28 - mmengine - INFO - Epoch(train) [50][150/293] lr: 5.000000e-04 eta: 6:17:20 time: 0.585632 data_time: 0.109958 memory: 6691 loss_kpt: 0.000759 acc_pose: 0.776714 loss: 0.000759 2022/09/22 12:58:58 - mmengine - INFO - Epoch(train) [50][200/293] lr: 5.000000e-04 eta: 6:17:12 time: 0.583636 data_time: 0.197559 memory: 6691 loss_kpt: 0.000754 acc_pose: 0.812815 loss: 0.000754 2022/09/22 12:59:25 - mmengine - INFO - Epoch(train) [50][250/293] lr: 5.000000e-04 eta: 6:16:59 time: 0.550309 data_time: 0.230185 memory: 6691 loss_kpt: 0.000758 acc_pose: 0.745664 loss: 0.000758 2022/09/22 12:59:49 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 12:59:49 - mmengine - INFO - Saving checkpoint at 50 epochs 2022/09/22 13:00:12 - mmengine - INFO - Epoch(val) [50][50/407] eta: 0:01:54 time: 0.321756 data_time: 0.173229 memory: 6691 2022/09/22 13:00:27 - mmengine - INFO - Epoch(val) [50][100/407] eta: 0:01:34 time: 0.308813 data_time: 0.170708 memory: 1014 2022/09/22 13:00:43 - mmengine - INFO - Epoch(val) [50][150/407] eta: 0:01:21 time: 0.318992 data_time: 0.193370 memory: 1014 2022/09/22 13:00:59 - mmengine - INFO - Epoch(val) [50][200/407] eta: 0:01:06 time: 0.323331 data_time: 0.174323 memory: 1014 2022/09/22 13:01:15 - mmengine - INFO - Epoch(val) [50][250/407] eta: 0:00:49 time: 0.318195 data_time: 0.173712 memory: 1014 2022/09/22 13:01:31 - mmengine - INFO - Epoch(val) [50][300/407] eta: 0:00:33 time: 0.312058 data_time: 0.176099 memory: 1014 2022/09/22 13:01:47 - mmengine - INFO - Epoch(val) [50][350/407] eta: 0:00:18 time: 0.318882 data_time: 0.180975 memory: 1014 2022/09/22 13:01:57 - mmengine - INFO - Epoch(val) [50][400/407] eta: 0:00:01 time: 0.205986 data_time: 0.120529 memory: 1014 2022/09/22 13:02:31 - mmengine - INFO - Evaluating CocoMetric... 2022/09/22 13:02:44 - mmengine - INFO - Epoch(val) [50][407/407] coco/AP: 0.671667 coco/AP .5: 0.882605 coco/AP .75: 0.749874 coco/AP (M): 0.636898 coco/AP (L): 0.734956 coco/AR: 0.732006 coco/AR .5: 0.923804 coco/AR .75: 0.800378 coco/AR (M): 0.688937 coco/AR (L): 0.793200 2022/09/22 13:02:45 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220922/res50_256/best_coco/AP_epoch_40.pth is removed 2022/09/22 13:02:47 - mmengine - INFO - The best checkpoint with 0.6717 coco/AP at 50 epoch is saved to best_coco/AP_epoch_50.pth. 2022/09/22 13:03:14 - mmengine - INFO - Epoch(train) [51][50/293] lr: 5.000000e-04 eta: 6:15:17 time: 0.537864 data_time: 0.312618 memory: 6691 loss_kpt: 0.000756 acc_pose: 0.802962 loss: 0.000756 2022/09/22 13:03:42 - mmengine - INFO - Epoch(train) [51][100/293] lr: 5.000000e-04 eta: 6:15:05 time: 0.556852 data_time: 0.300611 memory: 6691 loss_kpt: 0.000745 acc_pose: 0.775256 loss: 0.000745 2022/09/22 13:04:08 - mmengine - INFO - Epoch(train) [51][150/293] lr: 5.000000e-04 eta: 6:14:48 time: 0.527331 data_time: 0.260831 memory: 6691 loss_kpt: 0.000750 acc_pose: 0.756991 loss: 0.000750 2022/09/22 13:04:35 - mmengine - INFO - Epoch(train) [51][200/293] lr: 5.000000e-04 eta: 6:14:33 time: 0.537540 data_time: 0.258585 memory: 6691 loss_kpt: 0.000740 acc_pose: 0.709906 loss: 0.000740 2022/09/22 13:05:03 - mmengine - INFO - Epoch(train) [51][250/293] lr: 5.000000e-04 eta: 6:14:21 time: 0.560220 data_time: 0.235040 memory: 6691 loss_kpt: 0.000738 acc_pose: 0.822752 loss: 0.000738 2022/09/22 13:05:26 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 13:05:56 - mmengine - INFO - Epoch(train) [52][50/293] lr: 5.000000e-04 eta: 6:12:48 time: 0.585770 data_time: 0.236421 memory: 6691 loss_kpt: 0.000762 acc_pose: 0.773890 loss: 0.000762 2022/09/22 13:06:00 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 13:06:25 - mmengine - INFO - Epoch(train) [52][100/293] lr: 5.000000e-04 eta: 6:12:39 time: 0.579164 data_time: 0.095176 memory: 6691 loss_kpt: 0.000738 acc_pose: 0.784698 loss: 0.000738 2022/09/22 13:06:52 - mmengine - INFO - Epoch(train) [52][150/293] lr: 5.000000e-04 eta: 6:12:25 time: 0.543783 data_time: 0.141131 memory: 6691 loss_kpt: 0.000737 acc_pose: 0.787991 loss: 0.000737 2022/09/22 13:07:19 - mmengine - INFO - Epoch(train) [52][200/293] lr: 5.000000e-04 eta: 6:12:12 time: 0.549708 data_time: 0.272141 memory: 6691 loss_kpt: 0.000755 acc_pose: 0.797217 loss: 0.000755 2022/09/22 13:07:47 - mmengine - INFO - Epoch(train) [52][250/293] lr: 5.000000e-04 eta: 6:11:59 time: 0.554541 data_time: 0.245014 memory: 6691 loss_kpt: 0.000756 acc_pose: 0.849004 loss: 0.000756 2022/09/22 13:08:10 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 13:08:39 - mmengine - INFO - Epoch(train) [53][50/293] lr: 5.000000e-04 eta: 6:10:25 time: 0.576088 data_time: 0.116253 memory: 6691 loss_kpt: 0.000745 acc_pose: 0.799799 loss: 0.000745 2022/09/22 13:09:06 - mmengine - INFO - Epoch(train) [53][100/293] lr: 5.000000e-04 eta: 6:10:10 time: 0.539054 data_time: 0.075153 memory: 6691 loss_kpt: 0.000740 acc_pose: 0.764888 loss: 0.000740 2022/09/22 13:09:34 - mmengine - INFO - Epoch(train) [53][150/293] lr: 5.000000e-04 eta: 6:09:59 time: 0.564432 data_time: 0.089177 memory: 6691 loss_kpt: 0.000738 acc_pose: 0.797488 loss: 0.000738 2022/09/22 13:10:02 - mmengine - INFO - Epoch(train) [53][200/293] lr: 5.000000e-04 eta: 6:09:46 time: 0.555619 data_time: 0.253960 memory: 6691 loss_kpt: 0.000752 acc_pose: 0.798213 loss: 0.000752 2022/09/22 13:10:31 - mmengine - INFO - Epoch(train) [53][250/293] lr: 5.000000e-04 eta: 6:09:35 time: 0.573758 data_time: 0.270567 memory: 6691 loss_kpt: 0.000745 acc_pose: 0.732666 loss: 0.000745 2022/09/22 13:10:55 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 13:11:24 - mmengine - INFO - Epoch(train) [54][50/293] lr: 5.000000e-04 eta: 6:08:05 time: 0.584049 data_time: 0.118610 memory: 6691 loss_kpt: 0.000750 acc_pose: 0.790455 loss: 0.000750 2022/09/22 13:11:52 - mmengine - INFO - Epoch(train) [54][100/293] lr: 5.000000e-04 eta: 6:07:53 time: 0.563335 data_time: 0.088819 memory: 6691 loss_kpt: 0.000741 acc_pose: 0.770154 loss: 0.000741 2022/09/22 13:12:20 - mmengine - INFO - Epoch(train) [54][150/293] lr: 5.000000e-04 eta: 6:07:40 time: 0.560550 data_time: 0.083968 memory: 6691 loss_kpt: 0.000733 acc_pose: 0.792684 loss: 0.000733 2022/09/22 13:12:49 - mmengine - INFO - Epoch(train) [54][200/293] lr: 5.000000e-04 eta: 6:07:30 time: 0.576477 data_time: 0.096115 memory: 6691 loss_kpt: 0.000750 acc_pose: 0.747734 loss: 0.000750 2022/09/22 13:13:17 - mmengine - INFO - Epoch(train) [54][250/293] lr: 5.000000e-04 eta: 6:07:17 time: 0.557545 data_time: 0.171077 memory: 6691 loss_kpt: 0.000757 acc_pose: 0.795615 loss: 0.000757 2022/09/22 13:13:40 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 13:14:09 - mmengine - INFO - Epoch(train) [55][50/293] lr: 5.000000e-04 eta: 6:05:47 time: 0.578851 data_time: 0.096537 memory: 6691 loss_kpt: 0.000747 acc_pose: 0.760830 loss: 0.000747 2022/09/22 13:14:38 - mmengine - INFO - Epoch(train) [55][100/293] lr: 5.000000e-04 eta: 6:05:36 time: 0.570061 data_time: 0.077822 memory: 6691 loss_kpt: 0.000732 acc_pose: 0.821252 loss: 0.000732 2022/09/22 13:15:06 - mmengine - INFO - Epoch(train) [55][150/293] lr: 5.000000e-04 eta: 6:05:23 time: 0.561501 data_time: 0.085887 memory: 6691 loss_kpt: 0.000757 acc_pose: 0.760634 loss: 0.000757 2022/09/22 13:15:22 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 13:15:34 - mmengine - INFO - Epoch(train) [55][200/293] lr: 5.000000e-04 eta: 6:05:11 time: 0.566907 data_time: 0.089935 memory: 6691 loss_kpt: 0.000745 acc_pose: 0.774361 loss: 0.000745 2022/09/22 13:16:03 - mmengine - INFO - Epoch(train) [55][250/293] lr: 5.000000e-04 eta: 6:04:59 time: 0.566244 data_time: 0.089043 memory: 6691 loss_kpt: 0.000743 acc_pose: 0.756205 loss: 0.000743 2022/09/22 13:16:26 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 13:16:55 - mmengine - INFO - Epoch(train) [56][50/293] lr: 5.000000e-04 eta: 6:03:30 time: 0.579409 data_time: 0.217088 memory: 6691 loss_kpt: 0.000751 acc_pose: 0.769919 loss: 0.000751 2022/09/22 13:17:23 - mmengine - INFO - Epoch(train) [56][100/293] lr: 5.000000e-04 eta: 6:03:17 time: 0.560783 data_time: 0.230507 memory: 6691 loss_kpt: 0.000755 acc_pose: 0.804313 loss: 0.000755 2022/09/22 13:17:50 - mmengine - INFO - Epoch(train) [56][150/293] lr: 5.000000e-04 eta: 6:03:00 time: 0.535318 data_time: 0.226669 memory: 6691 loss_kpt: 0.000741 acc_pose: 0.759472 loss: 0.000741 2022/09/22 13:18:18 - mmengine - INFO - Epoch(train) [56][200/293] lr: 5.000000e-04 eta: 6:02:48 time: 0.567983 data_time: 0.249702 memory: 6691 loss_kpt: 0.000745 acc_pose: 0.817816 loss: 0.000745 2022/09/22 13:18:46 - mmengine - INFO - Epoch(train) [56][250/293] lr: 5.000000e-04 eta: 6:02:35 time: 0.562192 data_time: 0.209731 memory: 6691 loss_kpt: 0.000755 acc_pose: 0.776597 loss: 0.000755 2022/09/22 13:19:11 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 13:19:41 - mmengine - INFO - Epoch(train) [57][50/293] lr: 5.000000e-04 eta: 6:01:09 time: 0.592942 data_time: 0.273608 memory: 6691 loss_kpt: 0.000745 acc_pose: 0.780019 loss: 0.000745 2022/09/22 13:20:10 - mmengine - INFO - Epoch(train) [57][100/293] lr: 5.000000e-04 eta: 6:00:59 time: 0.582667 data_time: 0.120265 memory: 6691 loss_kpt: 0.000737 acc_pose: 0.800853 loss: 0.000737 2022/09/22 13:20:38 - mmengine - INFO - Epoch(train) [57][150/293] lr: 5.000000e-04 eta: 6:00:47 time: 0.568860 data_time: 0.105792 memory: 6691 loss_kpt: 0.000750 acc_pose: 0.758029 loss: 0.000750 2022/09/22 13:21:06 - mmengine - INFO - Epoch(train) [57][200/293] lr: 5.000000e-04 eta: 6:00:32 time: 0.551722 data_time: 0.079912 memory: 6691 loss_kpt: 0.000743 acc_pose: 0.776140 loss: 0.000743 2022/09/22 13:21:34 - mmengine - INFO - Epoch(train) [57][250/293] lr: 5.000000e-04 eta: 6:00:18 time: 0.553840 data_time: 0.082831 memory: 6691 loss_kpt: 0.000751 acc_pose: 0.779210 loss: 0.000751 2022/09/22 13:21:57 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 13:22:27 - mmengine - INFO - Epoch(train) [58][50/293] lr: 5.000000e-04 eta: 5:58:53 time: 0.596536 data_time: 0.162175 memory: 6691 loss_kpt: 0.000746 acc_pose: 0.760403 loss: 0.000746 2022/09/22 13:22:55 - mmengine - INFO - Epoch(train) [58][100/293] lr: 5.000000e-04 eta: 5:58:39 time: 0.555448 data_time: 0.085672 memory: 6691 loss_kpt: 0.000730 acc_pose: 0.803392 loss: 0.000730 2022/09/22 13:23:21 - mmengine - INFO - Epoch(train) [58][150/293] lr: 5.000000e-04 eta: 5:58:22 time: 0.535093 data_time: 0.085230 memory: 6691 loss_kpt: 0.000734 acc_pose: 0.763718 loss: 0.000734 2022/09/22 13:23:49 - mmengine - INFO - Epoch(train) [58][200/293] lr: 5.000000e-04 eta: 5:58:07 time: 0.545732 data_time: 0.090149 memory: 6691 loss_kpt: 0.000759 acc_pose: 0.712177 loss: 0.000759 2022/09/22 13:24:18 - mmengine - INFO - Epoch(train) [58][250/293] lr: 5.000000e-04 eta: 5:57:56 time: 0.587928 data_time: 0.116512 memory: 6691 loss_kpt: 0.000721 acc_pose: 0.774245 loss: 0.000721 2022/09/22 13:24:41 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 13:24:45 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 13:25:10 - mmengine - INFO - Epoch(train) [59][50/293] lr: 5.000000e-04 eta: 5:56:30 time: 0.579935 data_time: 0.174901 memory: 6691 loss_kpt: 0.000736 acc_pose: 0.753655 loss: 0.000736 2022/09/22 13:25:39 - mmengine - INFO - Epoch(train) [59][100/293] lr: 5.000000e-04 eta: 5:56:19 time: 0.576932 data_time: 0.102880 memory: 6691 loss_kpt: 0.000731 acc_pose: 0.829170 loss: 0.000731 2022/09/22 13:26:07 - mmengine - INFO - Epoch(train) [59][150/293] lr: 5.000000e-04 eta: 5:56:05 time: 0.557574 data_time: 0.104900 memory: 6691 loss_kpt: 0.000732 acc_pose: 0.797487 loss: 0.000732 2022/09/22 13:26:35 - mmengine - INFO - Epoch(train) [59][200/293] lr: 5.000000e-04 eta: 5:55:51 time: 0.563136 data_time: 0.094526 memory: 6691 loss_kpt: 0.000734 acc_pose: 0.761096 loss: 0.000734 2022/09/22 13:27:04 - mmengine - INFO - Epoch(train) [59][250/293] lr: 5.000000e-04 eta: 5:55:38 time: 0.568428 data_time: 0.100197 memory: 6691 loss_kpt: 0.000746 acc_pose: 0.774987 loss: 0.000746 2022/09/22 13:27:28 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 13:27:58 - mmengine - INFO - Epoch(train) [60][50/293] lr: 5.000000e-04 eta: 5:54:14 time: 0.589063 data_time: 0.263865 memory: 6691 loss_kpt: 0.000732 acc_pose: 0.808875 loss: 0.000732 2022/09/22 13:28:26 - mmengine - INFO - Epoch(train) [60][100/293] lr: 5.000000e-04 eta: 5:54:00 time: 0.557214 data_time: 0.260106 memory: 6691 loss_kpt: 0.000727 acc_pose: 0.774533 loss: 0.000727 2022/09/22 13:28:54 - mmengine - INFO - Epoch(train) [60][150/293] lr: 5.000000e-04 eta: 5:53:46 time: 0.560276 data_time: 0.246445 memory: 6691 loss_kpt: 0.000737 acc_pose: 0.747103 loss: 0.000737 2022/09/22 13:29:21 - mmengine - INFO - Epoch(train) [60][200/293] lr: 5.000000e-04 eta: 5:53:30 time: 0.549475 data_time: 0.226398 memory: 6691 loss_kpt: 0.000734 acc_pose: 0.752191 loss: 0.000734 2022/09/22 13:29:50 - mmengine - INFO - Epoch(train) [60][250/293] lr: 5.000000e-04 eta: 5:53:18 time: 0.578307 data_time: 0.160832 memory: 6691 loss_kpt: 0.000749 acc_pose: 0.783526 loss: 0.000749 2022/09/22 13:30:14 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 13:30:14 - mmengine - INFO - Saving checkpoint at 60 epochs 2022/09/22 13:30:37 - mmengine - INFO - Epoch(val) [60][50/407] eta: 0:01:56 time: 0.327342 data_time: 0.174258 memory: 6691 2022/09/22 13:30:52 - mmengine - INFO - Epoch(val) [60][100/407] eta: 0:01:36 time: 0.313780 data_time: 0.184039 memory: 1014 2022/09/22 13:31:08 - mmengine - INFO - Epoch(val) [60][150/407] eta: 0:01:19 time: 0.310033 data_time: 0.165994 memory: 1014 2022/09/22 13:31:23 - mmengine - INFO - Epoch(val) [60][200/407] eta: 0:01:03 time: 0.306458 data_time: 0.143587 memory: 1014 2022/09/22 13:31:38 - mmengine - INFO - Epoch(val) [60][250/407] eta: 0:00:47 time: 0.301760 data_time: 0.164193 memory: 1014 2022/09/22 13:31:54 - mmengine - INFO - Epoch(val) [60][300/407] eta: 0:00:33 time: 0.311351 data_time: 0.172220 memory: 1014 2022/09/22 13:32:10 - mmengine - INFO - Epoch(val) [60][350/407] eta: 0:00:18 time: 0.321312 data_time: 0.182055 memory: 1014 2022/09/22 13:32:21 - mmengine - INFO - Epoch(val) [60][400/407] eta: 0:00:01 time: 0.223893 data_time: 0.127714 memory: 1014 2022/09/22 13:32:54 - mmengine - INFO - Evaluating CocoMetric... 2022/09/22 13:33:07 - mmengine - INFO - Epoch(val) [60][407/407] coco/AP: 0.677646 coco/AP .5: 0.884010 coco/AP .75: 0.754644 coco/AP (M): 0.640266 coco/AP (L): 0.743584 coco/AR: 0.736445 coco/AR .5: 0.923174 coco/AR .75: 0.806045 coco/AR (M): 0.691887 coco/AR (L): 0.799889 2022/09/22 13:33:07 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220922/res50_256/best_coco/AP_epoch_50.pth is removed 2022/09/22 13:33:10 - mmengine - INFO - The best checkpoint with 0.6776 coco/AP at 60 epoch is saved to best_coco/AP_epoch_60.pth. 2022/09/22 13:33:37 - mmengine - INFO - Epoch(train) [61][50/293] lr: 5.000000e-04 eta: 5:51:49 time: 0.540263 data_time: 0.340999 memory: 6691 loss_kpt: 0.000732 acc_pose: 0.725888 loss: 0.000732 2022/09/22 13:34:04 - mmengine - INFO - Epoch(train) [61][100/293] lr: 5.000000e-04 eta: 5:51:32 time: 0.537309 data_time: 0.299892 memory: 6691 loss_kpt: 0.000735 acc_pose: 0.775569 loss: 0.000735 2022/09/22 13:34:31 - mmengine - INFO - Epoch(train) [61][150/293] lr: 5.000000e-04 eta: 5:51:16 time: 0.543717 data_time: 0.234058 memory: 6691 loss_kpt: 0.000741 acc_pose: 0.792778 loss: 0.000741 2022/09/22 13:34:59 - mmengine - INFO - Epoch(train) [61][200/293] lr: 5.000000e-04 eta: 5:51:01 time: 0.553788 data_time: 0.184765 memory: 6691 loss_kpt: 0.000730 acc_pose: 0.832635 loss: 0.000730 2022/09/22 13:35:27 - mmengine - INFO - Epoch(train) [61][250/293] lr: 5.000000e-04 eta: 5:50:47 time: 0.566769 data_time: 0.107490 memory: 6691 loss_kpt: 0.000724 acc_pose: 0.755646 loss: 0.000724 2022/09/22 13:35:51 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 13:36:20 - mmengine - INFO - Epoch(train) [62][50/293] lr: 5.000000e-04 eta: 5:49:24 time: 0.576443 data_time: 0.240851 memory: 6691 loss_kpt: 0.000729 acc_pose: 0.810321 loss: 0.000729 2022/09/22 13:36:47 - mmengine - INFO - Epoch(train) [62][100/293] lr: 5.000000e-04 eta: 5:49:07 time: 0.541240 data_time: 0.104465 memory: 6691 loss_kpt: 0.000736 acc_pose: 0.779090 loss: 0.000736 2022/09/22 13:37:02 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 13:37:15 - mmengine - INFO - Epoch(train) [62][150/293] lr: 5.000000e-04 eta: 5:48:52 time: 0.560293 data_time: 0.097680 memory: 6691 loss_kpt: 0.000731 acc_pose: 0.799987 loss: 0.000731 2022/09/22 13:37:43 - mmengine - INFO - Epoch(train) [62][200/293] lr: 5.000000e-04 eta: 5:48:36 time: 0.547413 data_time: 0.085240 memory: 6691 loss_kpt: 0.000737 acc_pose: 0.792033 loss: 0.000737 2022/09/22 13:38:11 - mmengine - INFO - Epoch(train) [62][250/293] lr: 5.000000e-04 eta: 5:48:23 time: 0.567309 data_time: 0.093869 memory: 6691 loss_kpt: 0.000749 acc_pose: 0.811873 loss: 0.000749 2022/09/22 13:38:34 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 13:39:04 - mmengine - INFO - Epoch(train) [63][50/293] lr: 5.000000e-04 eta: 5:47:02 time: 0.592152 data_time: 0.154395 memory: 6691 loss_kpt: 0.000724 acc_pose: 0.787958 loss: 0.000724 2022/09/22 13:39:31 - mmengine - INFO - Epoch(train) [63][100/293] lr: 5.000000e-04 eta: 5:46:46 time: 0.551879 data_time: 0.098645 memory: 6691 loss_kpt: 0.000743 acc_pose: 0.840363 loss: 0.000743 2022/09/22 13:39:59 - mmengine - INFO - Epoch(train) [63][150/293] lr: 5.000000e-04 eta: 5:46:31 time: 0.556181 data_time: 0.098852 memory: 6691 loss_kpt: 0.000712 acc_pose: 0.753405 loss: 0.000712 2022/09/22 13:40:27 - mmengine - INFO - Epoch(train) [63][200/293] lr: 5.000000e-04 eta: 5:46:17 time: 0.570111 data_time: 0.118704 memory: 6691 loss_kpt: 0.000720 acc_pose: 0.829707 loss: 0.000720 2022/09/22 13:40:55 - mmengine - INFO - Epoch(train) [63][250/293] lr: 5.000000e-04 eta: 5:46:02 time: 0.553406 data_time: 0.086512 memory: 6691 loss_kpt: 0.000737 acc_pose: 0.757379 loss: 0.000737 2022/09/22 13:41:20 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 13:41:49 - mmengine - INFO - Epoch(train) [64][50/293] lr: 5.000000e-04 eta: 5:44:40 time: 0.582213 data_time: 0.158162 memory: 6691 loss_kpt: 0.000729 acc_pose: 0.785691 loss: 0.000729 2022/09/22 13:42:16 - mmengine - INFO - Epoch(train) [64][100/293] lr: 5.000000e-04 eta: 5:44:23 time: 0.538078 data_time: 0.085756 memory: 6691 loss_kpt: 0.000724 acc_pose: 0.807352 loss: 0.000724 2022/09/22 13:42:43 - mmengine - INFO - Epoch(train) [64][150/293] lr: 5.000000e-04 eta: 5:44:06 time: 0.540704 data_time: 0.081191 memory: 6691 loss_kpt: 0.000717 acc_pose: 0.819005 loss: 0.000717 2022/09/22 13:43:11 - mmengine - INFO - Epoch(train) [64][200/293] lr: 5.000000e-04 eta: 5:43:52 time: 0.567423 data_time: 0.094300 memory: 6691 loss_kpt: 0.000735 acc_pose: 0.796829 loss: 0.000735 2022/09/22 13:43:38 - mmengine - INFO - Epoch(train) [64][250/293] lr: 5.000000e-04 eta: 5:43:34 time: 0.536520 data_time: 0.084401 memory: 6691 loss_kpt: 0.000728 acc_pose: 0.794494 loss: 0.000728 2022/09/22 13:44:01 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 13:44:30 - mmengine - INFO - Epoch(train) [65][50/293] lr: 5.000000e-04 eta: 5:42:13 time: 0.576020 data_time: 0.191919 memory: 6691 loss_kpt: 0.000740 acc_pose: 0.775244 loss: 0.000740 2022/09/22 13:44:57 - mmengine - INFO - Epoch(train) [65][100/293] lr: 5.000000e-04 eta: 5:41:56 time: 0.545164 data_time: 0.093924 memory: 6691 loss_kpt: 0.000733 acc_pose: 0.713831 loss: 0.000733 2022/09/22 13:45:25 - mmengine - INFO - Epoch(train) [65][150/293] lr: 5.000000e-04 eta: 5:41:42 time: 0.563772 data_time: 0.116516 memory: 6691 loss_kpt: 0.000734 acc_pose: 0.774024 loss: 0.000734 2022/09/22 13:45:53 - mmengine - INFO - Epoch(train) [65][200/293] lr: 5.000000e-04 eta: 5:41:26 time: 0.560359 data_time: 0.110082 memory: 6691 loss_kpt: 0.000724 acc_pose: 0.796372 loss: 0.000724 2022/09/22 13:46:19 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 13:46:20 - mmengine - INFO - Epoch(train) [65][250/293] lr: 5.000000e-04 eta: 5:41:08 time: 0.534405 data_time: 0.090231 memory: 6691 loss_kpt: 0.000742 acc_pose: 0.766261 loss: 0.000742 2022/09/22 13:46:44 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 13:47:13 - mmengine - INFO - Epoch(train) [66][50/293] lr: 5.000000e-04 eta: 5:39:48 time: 0.577821 data_time: 0.235729 memory: 6691 loss_kpt: 0.000728 acc_pose: 0.733794 loss: 0.000728 2022/09/22 13:47:41 - mmengine - INFO - Epoch(train) [66][100/293] lr: 5.000000e-04 eta: 5:39:34 time: 0.571193 data_time: 0.149143 memory: 6691 loss_kpt: 0.000717 acc_pose: 0.841155 loss: 0.000717 2022/09/22 13:48:10 - mmengine - INFO - Epoch(train) [66][150/293] lr: 5.000000e-04 eta: 5:39:20 time: 0.569369 data_time: 0.103896 memory: 6691 loss_kpt: 0.000735 acc_pose: 0.806863 loss: 0.000735 2022/09/22 13:48:37 - mmengine - INFO - Epoch(train) [66][200/293] lr: 5.000000e-04 eta: 5:39:03 time: 0.542690 data_time: 0.090682 memory: 6691 loss_kpt: 0.000718 acc_pose: 0.781580 loss: 0.000718 2022/09/22 13:49:05 - mmengine - INFO - Epoch(train) [66][250/293] lr: 5.000000e-04 eta: 5:38:48 time: 0.562600 data_time: 0.089355 memory: 6691 loss_kpt: 0.000745 acc_pose: 0.767615 loss: 0.000745 2022/09/22 13:49:29 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 13:49:57 - mmengine - INFO - Epoch(train) [67][50/293] lr: 5.000000e-04 eta: 5:37:28 time: 0.575453 data_time: 0.151661 memory: 6691 loss_kpt: 0.000722 acc_pose: 0.786807 loss: 0.000722 2022/09/22 13:50:26 - mmengine - INFO - Epoch(train) [67][100/293] lr: 5.000000e-04 eta: 5:37:15 time: 0.578572 data_time: 0.124270 memory: 6691 loss_kpt: 0.000726 acc_pose: 0.784993 loss: 0.000726 2022/09/22 13:50:55 - mmengine - INFO - Epoch(train) [67][150/293] lr: 5.000000e-04 eta: 5:37:00 time: 0.567014 data_time: 0.102376 memory: 6691 loss_kpt: 0.000729 acc_pose: 0.808535 loss: 0.000729 2022/09/22 13:51:23 - mmengine - INFO - Epoch(train) [67][200/293] lr: 5.000000e-04 eta: 5:36:44 time: 0.559927 data_time: 0.094594 memory: 6691 loss_kpt: 0.000719 acc_pose: 0.810449 loss: 0.000719 2022/09/22 13:51:50 - mmengine - INFO - Epoch(train) [67][250/293] lr: 5.000000e-04 eta: 5:36:28 time: 0.553168 data_time: 0.090864 memory: 6691 loss_kpt: 0.000727 acc_pose: 0.788495 loss: 0.000727 2022/09/22 13:52:14 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 13:52:42 - mmengine - INFO - Epoch(train) [68][50/293] lr: 5.000000e-04 eta: 5:35:09 time: 0.572916 data_time: 0.126216 memory: 6691 loss_kpt: 0.000733 acc_pose: 0.850755 loss: 0.000733 2022/09/22 13:53:10 - mmengine - INFO - Epoch(train) [68][100/293] lr: 5.000000e-04 eta: 5:34:54 time: 0.563448 data_time: 0.209705 memory: 6691 loss_kpt: 0.000717 acc_pose: 0.755553 loss: 0.000717 2022/09/22 13:53:38 - mmengine - INFO - Epoch(train) [68][150/293] lr: 5.000000e-04 eta: 5:34:38 time: 0.559489 data_time: 0.267925 memory: 6691 loss_kpt: 0.000718 acc_pose: 0.774875 loss: 0.000718 2022/09/22 13:54:06 - mmengine - INFO - Epoch(train) [68][200/293] lr: 5.000000e-04 eta: 5:34:22 time: 0.560410 data_time: 0.215754 memory: 6691 loss_kpt: 0.000712 acc_pose: 0.868563 loss: 0.000712 2022/09/22 13:54:34 - mmengine - INFO - Epoch(train) [68][250/293] lr: 5.000000e-04 eta: 5:34:07 time: 0.560974 data_time: 0.129590 memory: 6691 loss_kpt: 0.000730 acc_pose: 0.768359 loss: 0.000730 2022/09/22 13:54:58 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 13:55:28 - mmengine - INFO - Epoch(train) [69][50/293] lr: 5.000000e-04 eta: 5:32:50 time: 0.588033 data_time: 0.284829 memory: 6691 loss_kpt: 0.000722 acc_pose: 0.817375 loss: 0.000722 2022/09/22 13:55:44 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 13:55:57 - mmengine - INFO - Epoch(train) [69][100/293] lr: 5.000000e-04 eta: 5:32:38 time: 0.592863 data_time: 0.221011 memory: 6691 loss_kpt: 0.000748 acc_pose: 0.762866 loss: 0.000748 2022/09/22 13:56:27 - mmengine - INFO - Epoch(train) [69][150/293] lr: 5.000000e-04 eta: 5:32:25 time: 0.587059 data_time: 0.188950 memory: 6691 loss_kpt: 0.000716 acc_pose: 0.828944 loss: 0.000716 2022/09/22 13:56:55 - mmengine - INFO - Epoch(train) [69][200/293] lr: 5.000000e-04 eta: 5:32:09 time: 0.567632 data_time: 0.161756 memory: 6691 loss_kpt: 0.000727 acc_pose: 0.818786 loss: 0.000727 2022/09/22 13:57:23 - mmengine - INFO - Epoch(train) [69][250/293] lr: 5.000000e-04 eta: 5:31:54 time: 0.568996 data_time: 0.091974 memory: 6691 loss_kpt: 0.000718 acc_pose: 0.801402 loss: 0.000718 2022/09/22 13:57:47 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 13:58:17 - mmengine - INFO - Epoch(train) [70][50/293] lr: 5.000000e-04 eta: 5:30:39 time: 0.596383 data_time: 0.178412 memory: 6691 loss_kpt: 0.000713 acc_pose: 0.793809 loss: 0.000713 2022/09/22 13:58:45 - mmengine - INFO - Epoch(train) [70][100/293] lr: 5.000000e-04 eta: 5:30:23 time: 0.562340 data_time: 0.259024 memory: 6691 loss_kpt: 0.000725 acc_pose: 0.792539 loss: 0.000725 2022/09/22 13:59:12 - mmengine - INFO - Epoch(train) [70][150/293] lr: 5.000000e-04 eta: 5:30:04 time: 0.533009 data_time: 0.197300 memory: 6691 loss_kpt: 0.000734 acc_pose: 0.769825 loss: 0.000734 2022/09/22 13:59:40 - mmengine - INFO - Epoch(train) [70][200/293] lr: 5.000000e-04 eta: 5:29:48 time: 0.557967 data_time: 0.110853 memory: 6691 loss_kpt: 0.000734 acc_pose: 0.803457 loss: 0.000734 2022/09/22 14:00:07 - mmengine - INFO - Epoch(train) [70][250/293] lr: 5.000000e-04 eta: 5:29:31 time: 0.555288 data_time: 0.093008 memory: 6691 loss_kpt: 0.000727 acc_pose: 0.830177 loss: 0.000727 2022/09/22 14:00:30 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 14:00:30 - mmengine - INFO - Saving checkpoint at 70 epochs 2022/09/22 14:00:53 - mmengine - INFO - Epoch(val) [70][50/407] eta: 0:01:58 time: 0.332898 data_time: 0.192087 memory: 6691 2022/09/22 14:01:08 - mmengine - INFO - Epoch(val) [70][100/407] eta: 0:01:30 time: 0.295321 data_time: 0.152384 memory: 1014 2022/09/22 14:01:23 - mmengine - INFO - Epoch(val) [70][150/407] eta: 0:01:18 time: 0.303523 data_time: 0.174705 memory: 1014 2022/09/22 14:01:39 - mmengine - INFO - Epoch(val) [70][200/407] eta: 0:01:07 time: 0.325154 data_time: 0.195256 memory: 1014 2022/09/22 14:01:55 - mmengine - INFO - Epoch(val) [70][250/407] eta: 0:00:48 time: 0.308461 data_time: 0.174117 memory: 1014 2022/09/22 14:02:10 - mmengine - INFO - Epoch(val) [70][300/407] eta: 0:00:32 time: 0.302875 data_time: 0.160104 memory: 1014 2022/09/22 14:02:26 - mmengine - INFO - Epoch(val) [70][350/407] eta: 0:00:17 time: 0.312109 data_time: 0.174282 memory: 1014 2022/09/22 14:02:37 - mmengine - INFO - Epoch(val) [70][400/407] eta: 0:00:01 time: 0.232100 data_time: 0.137829 memory: 1014 2022/09/22 14:03:11 - mmengine - INFO - Evaluating CocoMetric... 2022/09/22 14:03:24 - mmengine - INFO - Epoch(val) [70][407/407] coco/AP: 0.686801 coco/AP .5: 0.887951 coco/AP .75: 0.764231 coco/AP (M): 0.650088 coco/AP (L): 0.752704 coco/AR: 0.745529 coco/AR .5: 0.928369 coco/AR .75: 0.816908 coco/AR (M): 0.700847 coco/AR (L): 0.809253 2022/09/22 14:03:24 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220922/res50_256/best_coco/AP_epoch_60.pth is removed 2022/09/22 14:03:27 - mmengine - INFO - The best checkpoint with 0.6868 coco/AP at 70 epoch is saved to best_coco/AP_epoch_70.pth. 2022/09/22 14:03:54 - mmengine - INFO - Epoch(train) [71][50/293] lr: 5.000000e-04 eta: 5:28:13 time: 0.552285 data_time: 0.192856 memory: 6691 loss_kpt: 0.000727 acc_pose: 0.787874 loss: 0.000727 2022/09/22 14:04:23 - mmengine - INFO - Epoch(train) [71][100/293] lr: 5.000000e-04 eta: 5:27:58 time: 0.573288 data_time: 0.094548 memory: 6691 loss_kpt: 0.000706 acc_pose: 0.800275 loss: 0.000706 2022/09/22 14:04:52 - mmengine - INFO - Epoch(train) [71][150/293] lr: 5.000000e-04 eta: 5:27:43 time: 0.573955 data_time: 0.103378 memory: 6691 loss_kpt: 0.000719 acc_pose: 0.783371 loss: 0.000719 2022/09/22 14:05:20 - mmengine - INFO - Epoch(train) [71][200/293] lr: 5.000000e-04 eta: 5:27:27 time: 0.561608 data_time: 0.160370 memory: 6691 loss_kpt: 0.000723 acc_pose: 0.808972 loss: 0.000723 2022/09/22 14:05:49 - mmengine - INFO - Epoch(train) [71][250/293] lr: 5.000000e-04 eta: 5:27:13 time: 0.582042 data_time: 0.232422 memory: 6691 loss_kpt: 0.000725 acc_pose: 0.815286 loss: 0.000725 2022/09/22 14:06:13 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 14:06:42 - mmengine - INFO - Epoch(train) [72][50/293] lr: 5.000000e-04 eta: 5:25:56 time: 0.573494 data_time: 0.200033 memory: 6691 loss_kpt: 0.000733 acc_pose: 0.767686 loss: 0.000733 2022/09/22 14:07:10 - mmengine - INFO - Epoch(train) [72][100/293] lr: 5.000000e-04 eta: 5:25:41 time: 0.567493 data_time: 0.096359 memory: 6691 loss_kpt: 0.000714 acc_pose: 0.763759 loss: 0.000714 2022/09/22 14:07:38 - mmengine - INFO - Epoch(train) [72][150/293] lr: 5.000000e-04 eta: 5:25:24 time: 0.557696 data_time: 0.097299 memory: 6691 loss_kpt: 0.000723 acc_pose: 0.830759 loss: 0.000723 2022/09/22 14:08:05 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 14:08:07 - mmengine - INFO - Epoch(train) [72][200/293] lr: 5.000000e-04 eta: 5:25:10 time: 0.584480 data_time: 0.112901 memory: 6691 loss_kpt: 0.000717 acc_pose: 0.767034 loss: 0.000717 2022/09/22 14:08:34 - mmengine - INFO - Epoch(train) [72][250/293] lr: 5.000000e-04 eta: 5:24:51 time: 0.539044 data_time: 0.083668 memory: 6691 loss_kpt: 0.000726 acc_pose: 0.846150 loss: 0.000726 2022/09/22 14:08:58 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 14:09:28 - mmengine - INFO - Epoch(train) [73][50/293] lr: 5.000000e-04 eta: 5:23:38 time: 0.591501 data_time: 0.137349 memory: 6691 loss_kpt: 0.000712 acc_pose: 0.831935 loss: 0.000712 2022/09/22 14:09:56 - mmengine - INFO - Epoch(train) [73][100/293] lr: 5.000000e-04 eta: 5:23:21 time: 0.556919 data_time: 0.101229 memory: 6691 loss_kpt: 0.000721 acc_pose: 0.813667 loss: 0.000721 2022/09/22 14:10:23 - mmengine - INFO - Epoch(train) [73][150/293] lr: 5.000000e-04 eta: 5:23:03 time: 0.543687 data_time: 0.107279 memory: 6691 loss_kpt: 0.000717 acc_pose: 0.797675 loss: 0.000717 2022/09/22 14:10:51 - mmengine - INFO - Epoch(train) [73][200/293] lr: 5.000000e-04 eta: 5:22:47 time: 0.567712 data_time: 0.117692 memory: 6691 loss_kpt: 0.000710 acc_pose: 0.806075 loss: 0.000710 2022/09/22 14:11:20 - mmengine - INFO - Epoch(train) [73][250/293] lr: 5.000000e-04 eta: 5:22:32 time: 0.580450 data_time: 0.121238 memory: 6691 loss_kpt: 0.000718 acc_pose: 0.790290 loss: 0.000718 2022/09/22 14:11:45 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 14:12:14 - mmengine - INFO - Epoch(train) [74][50/293] lr: 5.000000e-04 eta: 5:21:18 time: 0.581602 data_time: 0.235368 memory: 6691 loss_kpt: 0.000724 acc_pose: 0.788045 loss: 0.000724 2022/09/22 14:12:43 - mmengine - INFO - Epoch(train) [74][100/293] lr: 5.000000e-04 eta: 5:21:02 time: 0.567617 data_time: 0.258300 memory: 6691 loss_kpt: 0.000716 acc_pose: 0.785544 loss: 0.000716 2022/09/22 14:13:11 - mmengine - INFO - Epoch(train) [74][150/293] lr: 5.000000e-04 eta: 5:20:45 time: 0.558758 data_time: 0.248057 memory: 6691 loss_kpt: 0.000717 acc_pose: 0.769881 loss: 0.000717 2022/09/22 14:13:39 - mmengine - INFO - Epoch(train) [74][200/293] lr: 5.000000e-04 eta: 5:20:29 time: 0.568500 data_time: 0.248316 memory: 6691 loss_kpt: 0.000708 acc_pose: 0.768034 loss: 0.000708 2022/09/22 14:14:09 - mmengine - INFO - Epoch(train) [74][250/293] lr: 5.000000e-04 eta: 5:20:15 time: 0.592629 data_time: 0.166888 memory: 6691 loss_kpt: 0.000717 acc_pose: 0.794117 loss: 0.000717 2022/09/22 14:14:33 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 14:15:02 - mmengine - INFO - Epoch(train) [75][50/293] lr: 5.000000e-04 eta: 5:19:02 time: 0.580026 data_time: 0.320891 memory: 6691 loss_kpt: 0.000708 acc_pose: 0.801741 loss: 0.000708 2022/09/22 14:15:30 - mmengine - INFO - Epoch(train) [75][100/293] lr: 5.000000e-04 eta: 5:18:45 time: 0.564879 data_time: 0.297059 memory: 6691 loss_kpt: 0.000718 acc_pose: 0.806028 loss: 0.000718 2022/09/22 14:15:58 - mmengine - INFO - Epoch(train) [75][150/293] lr: 5.000000e-04 eta: 5:18:27 time: 0.550892 data_time: 0.158000 memory: 6691 loss_kpt: 0.000719 acc_pose: 0.737106 loss: 0.000719 2022/09/22 14:16:26 - mmengine - INFO - Epoch(train) [75][200/293] lr: 5.000000e-04 eta: 5:18:11 time: 0.568924 data_time: 0.225098 memory: 6691 loss_kpt: 0.000713 acc_pose: 0.762823 loss: 0.000713 2022/09/22 14:16:55 - mmengine - INFO - Epoch(train) [75][250/293] lr: 5.000000e-04 eta: 5:17:56 time: 0.575302 data_time: 0.202403 memory: 6691 loss_kpt: 0.000718 acc_pose: 0.776482 loss: 0.000718 2022/09/22 14:17:19 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 14:17:34 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 14:17:48 - mmengine - INFO - Epoch(train) [76][50/293] lr: 5.000000e-04 eta: 5:16:43 time: 0.585389 data_time: 0.120386 memory: 6691 loss_kpt: 0.000715 acc_pose: 0.822832 loss: 0.000715 2022/09/22 14:18:16 - mmengine - INFO - Epoch(train) [76][100/293] lr: 5.000000e-04 eta: 5:16:26 time: 0.562118 data_time: 0.128168 memory: 6691 loss_kpt: 0.000725 acc_pose: 0.766170 loss: 0.000725 2022/09/22 14:18:43 - mmengine - INFO - Epoch(train) [76][150/293] lr: 5.000000e-04 eta: 5:16:07 time: 0.539201 data_time: 0.108692 memory: 6691 loss_kpt: 0.000708 acc_pose: 0.767381 loss: 0.000708 2022/09/22 14:19:12 - mmengine - INFO - Epoch(train) [76][200/293] lr: 5.000000e-04 eta: 5:15:50 time: 0.562389 data_time: 0.192218 memory: 6691 loss_kpt: 0.000719 acc_pose: 0.840410 loss: 0.000719 2022/09/22 14:19:40 - mmengine - INFO - Epoch(train) [76][250/293] lr: 5.000000e-04 eta: 5:15:35 time: 0.573714 data_time: 0.110770 memory: 6691 loss_kpt: 0.000720 acc_pose: 0.829368 loss: 0.000720 2022/09/22 14:20:04 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 14:20:33 - mmengine - INFO - Epoch(train) [77][50/293] lr: 5.000000e-04 eta: 5:14:22 time: 0.574715 data_time: 0.284443 memory: 6691 loss_kpt: 0.000709 acc_pose: 0.790381 loss: 0.000709 2022/09/22 14:21:02 - mmengine - INFO - Epoch(train) [77][100/293] lr: 5.000000e-04 eta: 5:14:06 time: 0.577834 data_time: 0.181672 memory: 6691 loss_kpt: 0.000712 acc_pose: 0.824812 loss: 0.000712 2022/09/22 14:21:31 - mmengine - INFO - Epoch(train) [77][150/293] lr: 5.000000e-04 eta: 5:13:50 time: 0.573320 data_time: 0.122168 memory: 6691 loss_kpt: 0.000703 acc_pose: 0.774523 loss: 0.000703 2022/09/22 14:21:59 - mmengine - INFO - Epoch(train) [77][200/293] lr: 5.000000e-04 eta: 5:13:34 time: 0.573830 data_time: 0.124957 memory: 6691 loss_kpt: 0.000719 acc_pose: 0.857460 loss: 0.000719 2022/09/22 14:22:28 - mmengine - INFO - Epoch(train) [77][250/293] lr: 5.000000e-04 eta: 5:13:18 time: 0.572813 data_time: 0.115483 memory: 6691 loss_kpt: 0.000704 acc_pose: 0.833409 loss: 0.000704 2022/09/22 14:22:53 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 14:23:22 - mmengine - INFO - Epoch(train) [78][50/293] lr: 5.000000e-04 eta: 5:12:06 time: 0.582108 data_time: 0.189448 memory: 6691 loss_kpt: 0.000714 acc_pose: 0.782866 loss: 0.000714 2022/09/22 14:23:50 - mmengine - INFO - Epoch(train) [78][100/293] lr: 5.000000e-04 eta: 5:11:49 time: 0.567840 data_time: 0.167657 memory: 6691 loss_kpt: 0.000709 acc_pose: 0.815661 loss: 0.000709 2022/09/22 14:24:18 - mmengine - INFO - Epoch(train) [78][150/293] lr: 5.000000e-04 eta: 5:11:31 time: 0.554510 data_time: 0.146560 memory: 6691 loss_kpt: 0.000698 acc_pose: 0.784426 loss: 0.000698 2022/09/22 14:24:47 - mmengine - INFO - Epoch(train) [78][200/293] lr: 5.000000e-04 eta: 5:11:15 time: 0.574458 data_time: 0.092159 memory: 6691 loss_kpt: 0.000709 acc_pose: 0.814298 loss: 0.000709 2022/09/22 14:25:16 - mmengine - INFO - Epoch(train) [78][250/293] lr: 5.000000e-04 eta: 5:10:59 time: 0.577527 data_time: 0.099763 memory: 6691 loss_kpt: 0.000714 acc_pose: 0.783953 loss: 0.000714 2022/09/22 14:25:39 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 14:26:08 - mmengine - INFO - Epoch(train) [79][50/293] lr: 5.000000e-04 eta: 5:09:48 time: 0.579407 data_time: 0.177510 memory: 6691 loss_kpt: 0.000711 acc_pose: 0.817397 loss: 0.000711 2022/09/22 14:26:35 - mmengine - INFO - Epoch(train) [79][100/293] lr: 5.000000e-04 eta: 5:09:29 time: 0.550449 data_time: 0.097569 memory: 6691 loss_kpt: 0.000708 acc_pose: 0.820921 loss: 0.000708 2022/09/22 14:27:01 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 14:27:04 - mmengine - INFO - Epoch(train) [79][150/293] lr: 5.000000e-04 eta: 5:09:13 time: 0.573804 data_time: 0.104672 memory: 6691 loss_kpt: 0.000726 acc_pose: 0.766436 loss: 0.000726 2022/09/22 14:27:32 - mmengine - INFO - Epoch(train) [79][200/293] lr: 5.000000e-04 eta: 5:08:56 time: 0.565077 data_time: 0.129728 memory: 6691 loss_kpt: 0.000707 acc_pose: 0.811856 loss: 0.000707 2022/09/22 14:28:01 - mmengine - INFO - Epoch(train) [79][250/293] lr: 5.000000e-04 eta: 5:08:40 time: 0.581947 data_time: 0.163991 memory: 6691 loss_kpt: 0.000715 acc_pose: 0.785295 loss: 0.000715 2022/09/22 14:28:25 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 14:28:54 - mmengine - INFO - Epoch(train) [80][50/293] lr: 5.000000e-04 eta: 5:07:30 time: 0.593162 data_time: 0.146254 memory: 6691 loss_kpt: 0.000707 acc_pose: 0.799059 loss: 0.000707 2022/09/22 14:29:23 - mmengine - INFO - Epoch(train) [80][100/293] lr: 5.000000e-04 eta: 5:07:14 time: 0.574685 data_time: 0.151861 memory: 6691 loss_kpt: 0.000711 acc_pose: 0.843433 loss: 0.000711 2022/09/22 14:29:52 - mmengine - INFO - Epoch(train) [80][150/293] lr: 5.000000e-04 eta: 5:06:58 time: 0.581845 data_time: 0.197998 memory: 6691 loss_kpt: 0.000686 acc_pose: 0.775616 loss: 0.000686 2022/09/22 14:30:22 - mmengine - INFO - Epoch(train) [80][200/293] lr: 5.000000e-04 eta: 5:06:43 time: 0.589268 data_time: 0.210862 memory: 6691 loss_kpt: 0.000701 acc_pose: 0.769867 loss: 0.000701 2022/09/22 14:30:50 - mmengine - INFO - Epoch(train) [80][250/293] lr: 5.000000e-04 eta: 5:06:26 time: 0.571067 data_time: 0.095992 memory: 6691 loss_kpt: 0.000709 acc_pose: 0.799570 loss: 0.000709 2022/09/22 14:31:14 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 14:31:14 - mmengine - INFO - Saving checkpoint at 80 epochs 2022/09/22 14:31:37 - mmengine - INFO - Epoch(val) [80][50/407] eta: 0:01:57 time: 0.329009 data_time: 0.185841 memory: 6691 2022/09/22 14:31:53 - mmengine - INFO - Epoch(val) [80][100/407] eta: 0:01:38 time: 0.320014 data_time: 0.185138 memory: 1014 2022/09/22 14:32:09 - mmengine - INFO - Epoch(val) [80][150/407] eta: 0:01:21 time: 0.317247 data_time: 0.180618 memory: 1014 2022/09/22 14:32:24 - mmengine - INFO - Epoch(val) [80][200/407] eta: 0:01:02 time: 0.299608 data_time: 0.164967 memory: 1014 2022/09/22 14:32:40 - mmengine - INFO - Epoch(val) [80][250/407] eta: 0:00:49 time: 0.314936 data_time: 0.190622 memory: 1014 2022/09/22 14:32:56 - mmengine - INFO - Epoch(val) [80][300/407] eta: 0:00:33 time: 0.316336 data_time: 0.178763 memory: 1014 2022/09/22 14:33:12 - mmengine - INFO - Epoch(val) [80][350/407] eta: 0:00:18 time: 0.317860 data_time: 0.167300 memory: 1014 2022/09/22 14:33:22 - mmengine - INFO - Epoch(val) [80][400/407] eta: 0:00:01 time: 0.211507 data_time: 0.114392 memory: 1014 2022/09/22 14:33:55 - mmengine - INFO - Evaluating CocoMetric... 2022/09/22 14:34:08 - mmengine - INFO - Epoch(val) [80][407/407] coco/AP: 0.684648 coco/AP .5: 0.884306 coco/AP .75: 0.765126 coco/AP (M): 0.647399 coco/AP (L): 0.753986 coco/AR: 0.743482 coco/AR .5: 0.925535 coco/AR .75: 0.817538 coco/AR (M): 0.697951 coco/AR (L): 0.808250 2022/09/22 14:34:36 - mmengine - INFO - Epoch(train) [81][50/293] lr: 5.000000e-04 eta: 5:05:15 time: 0.568647 data_time: 0.137556 memory: 6691 loss_kpt: 0.000710 acc_pose: 0.795558 loss: 0.000710 2022/09/22 14:35:05 - mmengine - INFO - Epoch(train) [81][100/293] lr: 5.000000e-04 eta: 5:04:58 time: 0.576984 data_time: 0.118809 memory: 6691 loss_kpt: 0.000718 acc_pose: 0.850860 loss: 0.000718 2022/09/22 14:35:34 - mmengine - INFO - Epoch(train) [81][150/293] lr: 5.000000e-04 eta: 5:04:42 time: 0.580573 data_time: 0.108215 memory: 6691 loss_kpt: 0.000700 acc_pose: 0.803554 loss: 0.000700 2022/09/22 14:36:03 - mmengine - INFO - Epoch(train) [81][200/293] lr: 5.000000e-04 eta: 5:04:26 time: 0.578591 data_time: 0.100121 memory: 6691 loss_kpt: 0.000707 acc_pose: 0.746024 loss: 0.000707 2022/09/22 14:36:31 - mmengine - INFO - Epoch(train) [81][250/293] lr: 5.000000e-04 eta: 5:04:08 time: 0.562274 data_time: 0.088784 memory: 6691 loss_kpt: 0.000703 acc_pose: 0.805424 loss: 0.000703 2022/09/22 14:36:55 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 14:37:24 - mmengine - INFO - Epoch(train) [82][50/293] lr: 5.000000e-04 eta: 5:02:59 time: 0.588375 data_time: 0.217028 memory: 6691 loss_kpt: 0.000726 acc_pose: 0.752679 loss: 0.000726 2022/09/22 14:37:54 - mmengine - INFO - Epoch(train) [82][100/293] lr: 5.000000e-04 eta: 5:02:43 time: 0.592854 data_time: 0.098230 memory: 6691 loss_kpt: 0.000686 acc_pose: 0.815855 loss: 0.000686 2022/09/22 14:38:22 - mmengine - INFO - Epoch(train) [82][150/293] lr: 5.000000e-04 eta: 5:02:25 time: 0.557581 data_time: 0.093012 memory: 6691 loss_kpt: 0.000694 acc_pose: 0.807655 loss: 0.000694 2022/09/22 14:38:50 - mmengine - INFO - Epoch(train) [82][200/293] lr: 5.000000e-04 eta: 5:02:08 time: 0.568940 data_time: 0.105506 memory: 6691 loss_kpt: 0.000701 acc_pose: 0.838425 loss: 0.000701 2022/09/22 14:39:19 - mmengine - INFO - Epoch(train) [82][250/293] lr: 5.000000e-04 eta: 5:01:51 time: 0.577863 data_time: 0.117403 memory: 6691 loss_kpt: 0.000722 acc_pose: 0.833253 loss: 0.000722 2022/09/22 14:39:29 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 14:39:42 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 14:40:12 - mmengine - INFO - Epoch(train) [83][50/293] lr: 5.000000e-04 eta: 5:00:43 time: 0.591073 data_time: 0.267818 memory: 6691 loss_kpt: 0.000709 acc_pose: 0.783368 loss: 0.000709 2022/09/22 14:40:41 - mmengine - INFO - Epoch(train) [83][100/293] lr: 5.000000e-04 eta: 5:00:26 time: 0.576945 data_time: 0.181315 memory: 6691 loss_kpt: 0.000704 acc_pose: 0.793804 loss: 0.000704 2022/09/22 14:41:09 - mmengine - INFO - Epoch(train) [83][150/293] lr: 5.000000e-04 eta: 5:00:08 time: 0.555692 data_time: 0.252313 memory: 6691 loss_kpt: 0.000713 acc_pose: 0.816722 loss: 0.000713 2022/09/22 14:41:38 - mmengine - INFO - Epoch(train) [83][200/293] lr: 5.000000e-04 eta: 4:59:52 time: 0.593289 data_time: 0.089157 memory: 6691 loss_kpt: 0.000721 acc_pose: 0.780896 loss: 0.000721 2022/09/22 14:42:07 - mmengine - INFO - Epoch(train) [83][250/293] lr: 5.000000e-04 eta: 4:59:35 time: 0.573328 data_time: 0.097816 memory: 6691 loss_kpt: 0.000710 acc_pose: 0.827167 loss: 0.000710 2022/09/22 14:42:31 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 14:43:00 - mmengine - INFO - Epoch(train) [84][50/293] lr: 5.000000e-04 eta: 4:58:26 time: 0.581323 data_time: 0.194355 memory: 6691 loss_kpt: 0.000694 acc_pose: 0.827311 loss: 0.000694 2022/09/22 14:43:28 - mmengine - INFO - Epoch(train) [84][100/293] lr: 5.000000e-04 eta: 4:58:07 time: 0.549168 data_time: 0.190376 memory: 6691 loss_kpt: 0.000712 acc_pose: 0.829271 loss: 0.000712 2022/09/22 14:43:57 - mmengine - INFO - Epoch(train) [84][150/293] lr: 5.000000e-04 eta: 4:57:50 time: 0.579192 data_time: 0.192930 memory: 6691 loss_kpt: 0.000736 acc_pose: 0.799128 loss: 0.000736 2022/09/22 14:44:25 - mmengine - INFO - Epoch(train) [84][200/293] lr: 5.000000e-04 eta: 4:57:33 time: 0.566569 data_time: 0.096117 memory: 6691 loss_kpt: 0.000710 acc_pose: 0.796956 loss: 0.000710 2022/09/22 14:44:53 - mmengine - INFO - Epoch(train) [84][250/293] lr: 5.000000e-04 eta: 4:57:14 time: 0.550752 data_time: 0.094556 memory: 6691 loss_kpt: 0.000720 acc_pose: 0.771667 loss: 0.000720 2022/09/22 14:45:17 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 14:45:46 - mmengine - INFO - Epoch(train) [85][50/293] lr: 5.000000e-04 eta: 4:56:05 time: 0.579428 data_time: 0.156515 memory: 6691 loss_kpt: 0.000700 acc_pose: 0.764970 loss: 0.000700 2022/09/22 14:46:14 - mmengine - INFO - Epoch(train) [85][100/293] lr: 5.000000e-04 eta: 4:55:48 time: 0.571915 data_time: 0.132637 memory: 6691 loss_kpt: 0.000704 acc_pose: 0.825024 loss: 0.000704 2022/09/22 14:46:42 - mmengine - INFO - Epoch(train) [85][150/293] lr: 5.000000e-04 eta: 4:55:29 time: 0.551735 data_time: 0.182160 memory: 6691 loss_kpt: 0.000699 acc_pose: 0.818917 loss: 0.000699 2022/09/22 14:47:09 - mmengine - INFO - Epoch(train) [85][200/293] lr: 5.000000e-04 eta: 4:55:09 time: 0.547296 data_time: 0.090030 memory: 6691 loss_kpt: 0.000711 acc_pose: 0.796159 loss: 0.000711 2022/09/22 14:47:36 - mmengine - INFO - Epoch(train) [85][250/293] lr: 5.000000e-04 eta: 4:54:49 time: 0.539205 data_time: 0.087898 memory: 6691 loss_kpt: 0.000706 acc_pose: 0.783698 loss: 0.000706 2022/09/22 14:48:00 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 14:48:28 - mmengine - INFO - Epoch(train) [86][50/293] lr: 5.000000e-04 eta: 4:53:41 time: 0.570001 data_time: 0.230316 memory: 6691 loss_kpt: 0.000707 acc_pose: 0.782912 loss: 0.000707 2022/09/22 14:48:54 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 14:48:57 - mmengine - INFO - Epoch(train) [86][100/293] lr: 5.000000e-04 eta: 4:53:23 time: 0.572896 data_time: 0.258737 memory: 6691 loss_kpt: 0.000706 acc_pose: 0.767461 loss: 0.000706 2022/09/22 14:49:25 - mmengine - INFO - Epoch(train) [86][150/293] lr: 5.000000e-04 eta: 4:53:05 time: 0.559035 data_time: 0.243017 memory: 6691 loss_kpt: 0.000702 acc_pose: 0.787896 loss: 0.000702 2022/09/22 14:49:55 - mmengine - INFO - Epoch(train) [86][200/293] lr: 5.000000e-04 eta: 4:52:48 time: 0.590697 data_time: 0.198641 memory: 6691 loss_kpt: 0.000713 acc_pose: 0.789723 loss: 0.000713 2022/09/22 14:50:23 - mmengine - INFO - Epoch(train) [86][250/293] lr: 5.000000e-04 eta: 4:52:30 time: 0.565535 data_time: 0.218576 memory: 6691 loss_kpt: 0.000704 acc_pose: 0.824668 loss: 0.000704 2022/09/22 14:50:47 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 14:51:16 - mmengine - INFO - Epoch(train) [87][50/293] lr: 5.000000e-04 eta: 4:51:23 time: 0.580831 data_time: 0.260100 memory: 6691 loss_kpt: 0.000699 acc_pose: 0.796370 loss: 0.000699 2022/09/22 14:51:44 - mmengine - INFO - Epoch(train) [87][100/293] lr: 5.000000e-04 eta: 4:51:04 time: 0.562891 data_time: 0.160575 memory: 6691 loss_kpt: 0.000703 acc_pose: 0.807892 loss: 0.000703 2022/09/22 14:52:13 - mmengine - INFO - Epoch(train) [87][150/293] lr: 5.000000e-04 eta: 4:50:47 time: 0.574830 data_time: 0.096964 memory: 6691 loss_kpt: 0.000703 acc_pose: 0.801130 loss: 0.000703 2022/09/22 14:52:41 - mmengine - INFO - Epoch(train) [87][200/293] lr: 5.000000e-04 eta: 4:50:28 time: 0.558843 data_time: 0.163254 memory: 6691 loss_kpt: 0.000713 acc_pose: 0.815426 loss: 0.000713 2022/09/22 14:53:09 - mmengine - INFO - Epoch(train) [87][250/293] lr: 5.000000e-04 eta: 4:50:10 time: 0.558718 data_time: 0.140062 memory: 6691 loss_kpt: 0.000691 acc_pose: 0.800495 loss: 0.000691 2022/09/22 14:53:33 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 14:54:02 - mmengine - INFO - Epoch(train) [88][50/293] lr: 5.000000e-04 eta: 4:49:03 time: 0.585295 data_time: 0.100738 memory: 6691 loss_kpt: 0.000690 acc_pose: 0.766960 loss: 0.000690 2022/09/22 14:54:30 - mmengine - INFO - Epoch(train) [88][100/293] lr: 5.000000e-04 eta: 4:48:43 time: 0.546773 data_time: 0.083624 memory: 6691 loss_kpt: 0.000706 acc_pose: 0.805152 loss: 0.000706 2022/09/22 14:54:57 - mmengine - INFO - Epoch(train) [88][150/293] lr: 5.000000e-04 eta: 4:48:24 time: 0.556887 data_time: 0.098688 memory: 6691 loss_kpt: 0.000706 acc_pose: 0.830632 loss: 0.000706 2022/09/22 14:55:26 - mmengine - INFO - Epoch(train) [88][200/293] lr: 5.000000e-04 eta: 4:48:06 time: 0.564799 data_time: 0.103459 memory: 6691 loss_kpt: 0.000712 acc_pose: 0.804883 loss: 0.000712 2022/09/22 14:55:54 - mmengine - INFO - Epoch(train) [88][250/293] lr: 5.000000e-04 eta: 4:47:48 time: 0.571769 data_time: 0.098244 memory: 6691 loss_kpt: 0.000705 acc_pose: 0.781758 loss: 0.000705 2022/09/22 14:56:18 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 14:56:47 - mmengine - INFO - Epoch(train) [89][50/293] lr: 5.000000e-04 eta: 4:46:41 time: 0.582834 data_time: 0.141525 memory: 6691 loss_kpt: 0.000714 acc_pose: 0.817801 loss: 0.000714 2022/09/22 14:57:15 - mmengine - INFO - Epoch(train) [89][100/293] lr: 5.000000e-04 eta: 4:46:23 time: 0.566058 data_time: 0.087562 memory: 6691 loss_kpt: 0.000688 acc_pose: 0.793362 loss: 0.000688 2022/09/22 14:57:43 - mmengine - INFO - Epoch(train) [89][150/293] lr: 5.000000e-04 eta: 4:46:05 time: 0.562205 data_time: 0.088471 memory: 6691 loss_kpt: 0.000710 acc_pose: 0.773564 loss: 0.000710 2022/09/22 14:58:11 - mmengine - INFO - Epoch(train) [89][200/293] lr: 5.000000e-04 eta: 4:45:46 time: 0.560226 data_time: 0.087246 memory: 6691 loss_kpt: 0.000706 acc_pose: 0.797404 loss: 0.000706 2022/09/22 14:58:20 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 14:58:39 - mmengine - INFO - Epoch(train) [89][250/293] lr: 5.000000e-04 eta: 4:45:26 time: 0.552259 data_time: 0.096495 memory: 6691 loss_kpt: 0.000710 acc_pose: 0.842556 loss: 0.000710 2022/09/22 14:59:02 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 14:59:32 - mmengine - INFO - Epoch(train) [90][50/293] lr: 5.000000e-04 eta: 4:44:21 time: 0.588942 data_time: 0.147360 memory: 6691 loss_kpt: 0.000707 acc_pose: 0.801376 loss: 0.000707 2022/09/22 15:00:03 - mmengine - INFO - Epoch(train) [90][100/293] lr: 5.000000e-04 eta: 4:44:06 time: 0.623924 data_time: 0.105617 memory: 6691 loss_kpt: 0.000685 acc_pose: 0.815967 loss: 0.000685 2022/09/22 15:00:31 - mmengine - INFO - Epoch(train) [90][150/293] lr: 5.000000e-04 eta: 4:43:48 time: 0.568052 data_time: 0.166015 memory: 6691 loss_kpt: 0.000715 acc_pose: 0.762606 loss: 0.000715 2022/09/22 15:01:00 - mmengine - INFO - Epoch(train) [90][200/293] lr: 5.000000e-04 eta: 4:43:30 time: 0.570054 data_time: 0.119094 memory: 6691 loss_kpt: 0.000699 acc_pose: 0.833874 loss: 0.000699 2022/09/22 15:01:29 - mmengine - INFO - Epoch(train) [90][250/293] lr: 5.000000e-04 eta: 4:43:13 time: 0.590518 data_time: 0.119963 memory: 6691 loss_kpt: 0.000701 acc_pose: 0.845472 loss: 0.000701 2022/09/22 15:01:53 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 15:01:53 - mmengine - INFO - Saving checkpoint at 90 epochs 2022/09/22 15:02:17 - mmengine - INFO - Epoch(val) [90][50/407] eta: 0:01:59 time: 0.334257 data_time: 0.171605 memory: 6691 2022/09/22 15:02:33 - mmengine - INFO - Epoch(val) [90][100/407] eta: 0:01:39 time: 0.324409 data_time: 0.186843 memory: 1014 2022/09/22 15:02:49 - mmengine - INFO - Epoch(val) [90][150/407] eta: 0:01:18 time: 0.305431 data_time: 0.163560 memory: 1014 2022/09/22 15:03:04 - mmengine - INFO - Epoch(val) [90][200/407] eta: 0:01:04 time: 0.310652 data_time: 0.185570 memory: 1014 2022/09/22 15:03:20 - mmengine - INFO - Epoch(val) [90][250/407] eta: 0:00:49 time: 0.314008 data_time: 0.181744 memory: 1014 2022/09/22 15:03:35 - mmengine - INFO - Epoch(val) [90][300/407] eta: 0:00:32 time: 0.308214 data_time: 0.174498 memory: 1014 2022/09/22 15:03:51 - mmengine - INFO - Epoch(val) [90][350/407] eta: 0:00:17 time: 0.304266 data_time: 0.173899 memory: 1014 2022/09/22 15:04:01 - mmengine - INFO - Epoch(val) [90][400/407] eta: 0:00:01 time: 0.211429 data_time: 0.123245 memory: 1014 2022/09/22 15:04:34 - mmengine - INFO - Evaluating CocoMetric... 2022/09/22 15:04:48 - mmengine - INFO - Epoch(val) [90][407/407] coco/AP: 0.688757 coco/AP .5: 0.887593 coco/AP .75: 0.765113 coco/AP (M): 0.651314 coco/AP (L): 0.757598 coco/AR: 0.748520 coco/AR .5: 0.928369 coco/AR .75: 0.817380 coco/AR (M): 0.702841 coco/AR (L): 0.813378 2022/09/22 15:04:48 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220922/res50_256/best_coco/AP_epoch_70.pth is removed 2022/09/22 15:04:50 - mmengine - INFO - The best checkpoint with 0.6888 coco/AP at 90 epoch is saved to best_coco/AP_epoch_90.pth. 2022/09/22 15:05:18 - mmengine - INFO - Epoch(train) [91][50/293] lr: 5.000000e-04 eta: 4:42:04 time: 0.547387 data_time: 0.168333 memory: 6691 loss_kpt: 0.000690 acc_pose: 0.799810 loss: 0.000690 2022/09/22 15:05:47 - mmengine - INFO - Epoch(train) [91][100/293] lr: 5.000000e-04 eta: 4:41:47 time: 0.583612 data_time: 0.186923 memory: 6691 loss_kpt: 0.000700 acc_pose: 0.817756 loss: 0.000700 2022/09/22 15:06:16 - mmengine - INFO - Epoch(train) [91][150/293] lr: 5.000000e-04 eta: 4:41:30 time: 0.581628 data_time: 0.240657 memory: 6691 loss_kpt: 0.000705 acc_pose: 0.781706 loss: 0.000705 2022/09/22 15:06:45 - mmengine - INFO - Epoch(train) [91][200/293] lr: 5.000000e-04 eta: 4:41:11 time: 0.573644 data_time: 0.156147 memory: 6691 loss_kpt: 0.000692 acc_pose: 0.843154 loss: 0.000692 2022/09/22 15:07:12 - mmengine - INFO - Epoch(train) [91][250/293] lr: 5.000000e-04 eta: 4:40:52 time: 0.555506 data_time: 0.204056 memory: 6691 loss_kpt: 0.000709 acc_pose: 0.790254 loss: 0.000709 2022/09/22 15:07:37 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 15:08:07 - mmengine - INFO - Epoch(train) [92][50/293] lr: 5.000000e-04 eta: 4:39:47 time: 0.594391 data_time: 0.111512 memory: 6691 loss_kpt: 0.000698 acc_pose: 0.805314 loss: 0.000698 2022/09/22 15:08:36 - mmengine - INFO - Epoch(train) [92][100/293] lr: 5.000000e-04 eta: 4:39:30 time: 0.583040 data_time: 0.247955 memory: 6691 loss_kpt: 0.000714 acc_pose: 0.760128 loss: 0.000714 2022/09/22 15:09:03 - mmengine - INFO - Epoch(train) [92][150/293] lr: 5.000000e-04 eta: 4:39:09 time: 0.532843 data_time: 0.259718 memory: 6691 loss_kpt: 0.000699 acc_pose: 0.828513 loss: 0.000699 2022/09/22 15:09:30 - mmengine - INFO - Epoch(train) [92][200/293] lr: 5.000000e-04 eta: 4:38:49 time: 0.552876 data_time: 0.210706 memory: 6691 loss_kpt: 0.000694 acc_pose: 0.814178 loss: 0.000694 2022/09/22 15:09:59 - mmengine - INFO - Epoch(train) [92][250/293] lr: 5.000000e-04 eta: 4:38:31 time: 0.578408 data_time: 0.195142 memory: 6691 loss_kpt: 0.000699 acc_pose: 0.826541 loss: 0.000699 2022/09/22 15:10:23 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 15:10:48 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 15:10:51 - mmengine - INFO - Epoch(train) [93][50/293] lr: 5.000000e-04 eta: 4:37:25 time: 0.566290 data_time: 0.098174 memory: 6691 loss_kpt: 0.000694 acc_pose: 0.753240 loss: 0.000694 2022/09/22 15:11:20 - mmengine - INFO - Epoch(train) [93][100/293] lr: 5.000000e-04 eta: 4:37:07 time: 0.576431 data_time: 0.110543 memory: 6691 loss_kpt: 0.000699 acc_pose: 0.813699 loss: 0.000699 2022/09/22 15:11:48 - mmengine - INFO - Epoch(train) [93][150/293] lr: 5.000000e-04 eta: 4:36:48 time: 0.561994 data_time: 0.104744 memory: 6691 loss_kpt: 0.000690 acc_pose: 0.792441 loss: 0.000690 2022/09/22 15:12:15 - mmengine - INFO - Epoch(train) [93][200/293] lr: 5.000000e-04 eta: 4:36:28 time: 0.544764 data_time: 0.077452 memory: 6691 loss_kpt: 0.000682 acc_pose: 0.822006 loss: 0.000682 2022/09/22 15:12:44 - mmengine - INFO - Epoch(train) [93][250/293] lr: 5.000000e-04 eta: 4:36:10 time: 0.573186 data_time: 0.102246 memory: 6691 loss_kpt: 0.000706 acc_pose: 0.845191 loss: 0.000706 2022/09/22 15:13:07 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 15:13:36 - mmengine - INFO - Epoch(train) [94][50/293] lr: 5.000000e-04 eta: 4:35:04 time: 0.570858 data_time: 0.183455 memory: 6691 loss_kpt: 0.000706 acc_pose: 0.787918 loss: 0.000706 2022/09/22 15:14:04 - mmengine - INFO - Epoch(train) [94][100/293] lr: 5.000000e-04 eta: 4:34:45 time: 0.558064 data_time: 0.158603 memory: 6691 loss_kpt: 0.000710 acc_pose: 0.782162 loss: 0.000710 2022/09/22 15:14:31 - mmengine - INFO - Epoch(train) [94][150/293] lr: 5.000000e-04 eta: 4:34:24 time: 0.535203 data_time: 0.321053 memory: 6691 loss_kpt: 0.000700 acc_pose: 0.813043 loss: 0.000700 2022/09/22 15:14:58 - mmengine - INFO - Epoch(train) [94][200/293] lr: 5.000000e-04 eta: 4:34:03 time: 0.538457 data_time: 0.288070 memory: 6691 loss_kpt: 0.000698 acc_pose: 0.775834 loss: 0.000698 2022/09/22 15:15:26 - mmengine - INFO - Epoch(train) [94][250/293] lr: 5.000000e-04 eta: 4:33:45 time: 0.569741 data_time: 0.162741 memory: 6691 loss_kpt: 0.000698 acc_pose: 0.833882 loss: 0.000698 2022/09/22 15:15:49 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 15:16:19 - mmengine - INFO - Epoch(train) [95][50/293] lr: 5.000000e-04 eta: 4:32:40 time: 0.584478 data_time: 0.151836 memory: 6691 loss_kpt: 0.000691 acc_pose: 0.826156 loss: 0.000691 2022/09/22 15:16:47 - mmengine - INFO - Epoch(train) [95][100/293] lr: 5.000000e-04 eta: 4:32:21 time: 0.558707 data_time: 0.079787 memory: 6691 loss_kpt: 0.000698 acc_pose: 0.777612 loss: 0.000698 2022/09/22 15:17:14 - mmengine - INFO - Epoch(train) [95][150/293] lr: 5.000000e-04 eta: 4:32:01 time: 0.554605 data_time: 0.076762 memory: 6691 loss_kpt: 0.000684 acc_pose: 0.796100 loss: 0.000684 2022/09/22 15:17:43 - mmengine - INFO - Epoch(train) [95][200/293] lr: 5.000000e-04 eta: 4:31:42 time: 0.568291 data_time: 0.090734 memory: 6691 loss_kpt: 0.000681 acc_pose: 0.779162 loss: 0.000681 2022/09/22 15:18:11 - mmengine - INFO - Epoch(train) [95][250/293] lr: 5.000000e-04 eta: 4:31:23 time: 0.559740 data_time: 0.090888 memory: 6691 loss_kpt: 0.000692 acc_pose: 0.806943 loss: 0.000692 2022/09/22 15:18:35 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 15:19:04 - mmengine - INFO - Epoch(train) [96][50/293] lr: 5.000000e-04 eta: 4:30:20 time: 0.590847 data_time: 0.145450 memory: 6691 loss_kpt: 0.000693 acc_pose: 0.741534 loss: 0.000693 2022/09/22 15:19:33 - mmengine - INFO - Epoch(train) [96][100/293] lr: 5.000000e-04 eta: 4:30:01 time: 0.571758 data_time: 0.135093 memory: 6691 loss_kpt: 0.000700 acc_pose: 0.783226 loss: 0.000700 2022/09/22 15:20:02 - mmengine - INFO - Epoch(train) [96][150/293] lr: 5.000000e-04 eta: 4:29:43 time: 0.584584 data_time: 0.222630 memory: 6691 loss_kpt: 0.000687 acc_pose: 0.819388 loss: 0.000687 2022/09/22 15:20:11 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 15:20:30 - mmengine - INFO - Epoch(train) [96][200/293] lr: 5.000000e-04 eta: 4:29:23 time: 0.559838 data_time: 0.277606 memory: 6691 loss_kpt: 0.000686 acc_pose: 0.829450 loss: 0.000686 2022/09/22 15:20:57 - mmengine - INFO - Epoch(train) [96][250/293] lr: 5.000000e-04 eta: 4:29:03 time: 0.540887 data_time: 0.111983 memory: 6691 loss_kpt: 0.000690 acc_pose: 0.798137 loss: 0.000690 2022/09/22 15:21:21 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 15:21:50 - mmengine - INFO - Epoch(train) [97][50/293] lr: 5.000000e-04 eta: 4:28:00 time: 0.590827 data_time: 0.248343 memory: 6691 loss_kpt: 0.000696 acc_pose: 0.833002 loss: 0.000696 2022/09/22 15:22:19 - mmengine - INFO - Epoch(train) [97][100/293] lr: 5.000000e-04 eta: 4:27:41 time: 0.570191 data_time: 0.131818 memory: 6691 loss_kpt: 0.000694 acc_pose: 0.793373 loss: 0.000694 2022/09/22 15:22:47 - mmengine - INFO - Epoch(train) [97][150/293] lr: 5.000000e-04 eta: 4:27:21 time: 0.551965 data_time: 0.077128 memory: 6691 loss_kpt: 0.000699 acc_pose: 0.792777 loss: 0.000699 2022/09/22 15:23:15 - mmengine - INFO - Epoch(train) [97][200/293] lr: 5.000000e-04 eta: 4:27:02 time: 0.577692 data_time: 0.079914 memory: 6691 loss_kpt: 0.000711 acc_pose: 0.809116 loss: 0.000711 2022/09/22 15:23:42 - mmengine - INFO - Epoch(train) [97][250/293] lr: 5.000000e-04 eta: 4:26:41 time: 0.536578 data_time: 0.089804 memory: 6691 loss_kpt: 0.000672 acc_pose: 0.807696 loss: 0.000672 2022/09/22 15:24:06 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 15:24:36 - mmengine - INFO - Epoch(train) [98][50/293] lr: 5.000000e-04 eta: 4:25:39 time: 0.595162 data_time: 0.149053 memory: 6691 loss_kpt: 0.000686 acc_pose: 0.800503 loss: 0.000686 2022/09/22 15:25:04 - mmengine - INFO - Epoch(train) [98][100/293] lr: 5.000000e-04 eta: 4:25:19 time: 0.560653 data_time: 0.088187 memory: 6691 loss_kpt: 0.000697 acc_pose: 0.821642 loss: 0.000697 2022/09/22 15:25:32 - mmengine - INFO - Epoch(train) [98][150/293] lr: 5.000000e-04 eta: 4:25:00 time: 0.557690 data_time: 0.083594 memory: 6691 loss_kpt: 0.000688 acc_pose: 0.830744 loss: 0.000688 2022/09/22 15:25:59 - mmengine - INFO - Epoch(train) [98][200/293] lr: 5.000000e-04 eta: 4:24:39 time: 0.540600 data_time: 0.104469 memory: 6691 loss_kpt: 0.000687 acc_pose: 0.775561 loss: 0.000687 2022/09/22 15:26:27 - mmengine - INFO - Epoch(train) [98][250/293] lr: 5.000000e-04 eta: 4:24:20 time: 0.569492 data_time: 0.174787 memory: 6691 loss_kpt: 0.000698 acc_pose: 0.835739 loss: 0.000698 2022/09/22 15:26:51 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 15:27:20 - mmengine - INFO - Epoch(train) [99][50/293] lr: 5.000000e-04 eta: 4:23:17 time: 0.581410 data_time: 0.161991 memory: 6691 loss_kpt: 0.000693 acc_pose: 0.795623 loss: 0.000693 2022/09/22 15:27:48 - mmengine - INFO - Epoch(train) [99][100/293] lr: 5.000000e-04 eta: 4:22:57 time: 0.568629 data_time: 0.156321 memory: 6691 loss_kpt: 0.000695 acc_pose: 0.836232 loss: 0.000695 2022/09/22 15:28:16 - mmengine - INFO - Epoch(train) [99][150/293] lr: 5.000000e-04 eta: 4:22:38 time: 0.559333 data_time: 0.095297 memory: 6691 loss_kpt: 0.000681 acc_pose: 0.825682 loss: 0.000681 2022/09/22 15:28:43 - mmengine - INFO - Epoch(train) [99][200/293] lr: 5.000000e-04 eta: 4:22:16 time: 0.525992 data_time: 0.082157 memory: 6691 loss_kpt: 0.000679 acc_pose: 0.811604 loss: 0.000679 2022/09/22 15:29:11 - mmengine - INFO - Epoch(train) [99][250/293] lr: 5.000000e-04 eta: 4:21:57 time: 0.565574 data_time: 0.104560 memory: 6691 loss_kpt: 0.000686 acc_pose: 0.820383 loss: 0.000686 2022/09/22 15:29:31 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 15:29:35 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 15:30:03 - mmengine - INFO - Epoch(train) [100][50/293] lr: 5.000000e-04 eta: 4:20:54 time: 0.575000 data_time: 0.126128 memory: 6691 loss_kpt: 0.000689 acc_pose: 0.817920 loss: 0.000689 2022/09/22 15:30:32 - mmengine - INFO - Epoch(train) [100][100/293] lr: 5.000000e-04 eta: 4:20:35 time: 0.570281 data_time: 0.209480 memory: 6691 loss_kpt: 0.000686 acc_pose: 0.828491 loss: 0.000686 2022/09/22 15:31:00 - mmengine - INFO - Epoch(train) [100][150/293] lr: 5.000000e-04 eta: 4:20:15 time: 0.564225 data_time: 0.092482 memory: 6691 loss_kpt: 0.000691 acc_pose: 0.830108 loss: 0.000691 2022/09/22 15:31:29 - mmengine - INFO - Epoch(train) [100][200/293] lr: 5.000000e-04 eta: 4:19:56 time: 0.571225 data_time: 0.142383 memory: 6691 loss_kpt: 0.000692 acc_pose: 0.817516 loss: 0.000692 2022/09/22 15:31:57 - mmengine - INFO - Epoch(train) [100][250/293] lr: 5.000000e-04 eta: 4:19:36 time: 0.569921 data_time: 0.087004 memory: 6691 loss_kpt: 0.000694 acc_pose: 0.806185 loss: 0.000694 2022/09/22 15:32:21 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 15:32:21 - mmengine - INFO - Saving checkpoint at 100 epochs 2022/09/22 15:32:42 - mmengine - INFO - Epoch(val) [100][50/407] eta: 0:01:53 time: 0.318996 data_time: 0.170126 memory: 6691 2022/09/22 15:32:57 - mmengine - INFO - Epoch(val) [100][100/407] eta: 0:01:30 time: 0.293697 data_time: 0.154169 memory: 1014 2022/09/22 15:33:13 - mmengine - INFO - Epoch(val) [100][150/407] eta: 0:01:23 time: 0.325166 data_time: 0.197159 memory: 1014 2022/09/22 15:33:29 - mmengine - INFO - Epoch(val) [100][200/407] eta: 0:01:03 time: 0.307363 data_time: 0.168563 memory: 1014 2022/09/22 15:33:44 - mmengine - INFO - Epoch(val) [100][250/407] eta: 0:00:47 time: 0.305395 data_time: 0.172867 memory: 1014 2022/09/22 15:33:59 - mmengine - INFO - Epoch(val) [100][300/407] eta: 0:00:31 time: 0.298403 data_time: 0.156612 memory: 1014 2022/09/22 15:34:14 - mmengine - INFO - Epoch(val) [100][350/407] eta: 0:00:17 time: 0.306763 data_time: 0.180009 memory: 1014 2022/09/22 15:34:28 - mmengine - INFO - Epoch(val) [100][400/407] eta: 0:00:01 time: 0.280497 data_time: 0.170231 memory: 1014 2022/09/22 15:35:02 - mmengine - INFO - Evaluating CocoMetric... 2022/09/22 15:35:17 - mmengine - INFO - Epoch(val) [100][407/407] coco/AP: 0.692611 coco/AP .5: 0.890449 coco/AP .75: 0.773742 coco/AP (M): 0.655251 coco/AP (L): 0.760201 coco/AR: 0.752409 coco/AR .5: 0.930730 coco/AR .75: 0.824307 coco/AR (M): 0.707648 coco/AR (L): 0.816091 2022/09/22 15:35:17 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220922/res50_256/best_coco/AP_epoch_90.pth is removed 2022/09/22 15:35:20 - mmengine - INFO - The best checkpoint with 0.6926 coco/AP at 100 epoch is saved to best_coco/AP_epoch_100.pth. 2022/09/22 15:35:46 - mmengine - INFO - Epoch(train) [101][50/293] lr: 5.000000e-04 eta: 4:18:32 time: 0.533921 data_time: 0.263918 memory: 6691 loss_kpt: 0.000694 acc_pose: 0.742152 loss: 0.000694 2022/09/22 15:36:14 - mmengine - INFO - Epoch(train) [101][100/293] lr: 5.000000e-04 eta: 4:18:12 time: 0.556397 data_time: 0.204785 memory: 6691 loss_kpt: 0.000707 acc_pose: 0.816102 loss: 0.000707 2022/09/22 15:36:42 - mmengine - INFO - Epoch(train) [101][150/293] lr: 5.000000e-04 eta: 4:17:51 time: 0.552244 data_time: 0.089560 memory: 6691 loss_kpt: 0.000702 acc_pose: 0.807583 loss: 0.000702 2022/09/22 15:37:09 - mmengine - INFO - Epoch(train) [101][200/293] lr: 5.000000e-04 eta: 4:17:31 time: 0.549669 data_time: 0.084685 memory: 6691 loss_kpt: 0.000693 acc_pose: 0.755861 loss: 0.000693 2022/09/22 15:37:38 - mmengine - INFO - Epoch(train) [101][250/293] lr: 5.000000e-04 eta: 4:17:12 time: 0.570833 data_time: 0.132707 memory: 6691 loss_kpt: 0.000702 acc_pose: 0.806657 loss: 0.000702 2022/09/22 15:38:02 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 15:38:32 - mmengine - INFO - Epoch(train) [102][50/293] lr: 5.000000e-04 eta: 4:16:10 time: 0.588406 data_time: 0.222865 memory: 6691 loss_kpt: 0.000681 acc_pose: 0.810752 loss: 0.000681 2022/09/22 15:39:01 - mmengine - INFO - Epoch(train) [102][100/293] lr: 5.000000e-04 eta: 4:15:51 time: 0.573333 data_time: 0.209946 memory: 6691 loss_kpt: 0.000685 acc_pose: 0.805124 loss: 0.000685 2022/09/22 15:39:28 - mmengine - INFO - Epoch(train) [102][150/293] lr: 5.000000e-04 eta: 4:15:30 time: 0.553562 data_time: 0.089889 memory: 6691 loss_kpt: 0.000676 acc_pose: 0.812050 loss: 0.000676 2022/09/22 15:39:56 - mmengine - INFO - Epoch(train) [102][200/293] lr: 5.000000e-04 eta: 4:15:11 time: 0.560859 data_time: 0.081966 memory: 6691 loss_kpt: 0.000687 acc_pose: 0.749285 loss: 0.000687 2022/09/22 15:40:25 - mmengine - INFO - Epoch(train) [102][250/293] lr: 5.000000e-04 eta: 4:14:51 time: 0.568909 data_time: 0.129059 memory: 6691 loss_kpt: 0.000685 acc_pose: 0.825806 loss: 0.000685 2022/09/22 15:40:49 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 15:41:18 - mmengine - INFO - Epoch(train) [103][50/293] lr: 5.000000e-04 eta: 4:13:50 time: 0.582895 data_time: 0.263644 memory: 6691 loss_kpt: 0.000699 acc_pose: 0.782936 loss: 0.000699 2022/09/22 15:41:46 - mmengine - INFO - Epoch(train) [103][100/293] lr: 5.000000e-04 eta: 4:13:29 time: 0.550116 data_time: 0.140438 memory: 6691 loss_kpt: 0.000682 acc_pose: 0.807846 loss: 0.000682 2022/09/22 15:41:53 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 15:42:13 - mmengine - INFO - Epoch(train) [103][150/293] lr: 5.000000e-04 eta: 4:13:09 time: 0.551249 data_time: 0.088152 memory: 6691 loss_kpt: 0.000700 acc_pose: 0.826306 loss: 0.000700 2022/09/22 15:42:42 - mmengine - INFO - Epoch(train) [103][200/293] lr: 5.000000e-04 eta: 4:12:49 time: 0.574876 data_time: 0.075659 memory: 6691 loss_kpt: 0.000711 acc_pose: 0.767855 loss: 0.000711 2022/09/22 15:43:10 - mmengine - INFO - Epoch(train) [103][250/293] lr: 5.000000e-04 eta: 4:12:29 time: 0.564306 data_time: 0.094163 memory: 6691 loss_kpt: 0.000688 acc_pose: 0.741912 loss: 0.000688 2022/09/22 15:43:34 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 15:44:03 - mmengine - INFO - Epoch(train) [104][50/293] lr: 5.000000e-04 eta: 4:11:28 time: 0.577930 data_time: 0.216757 memory: 6691 loss_kpt: 0.000692 acc_pose: 0.825222 loss: 0.000692 2022/09/22 15:44:32 - mmengine - INFO - Epoch(train) [104][100/293] lr: 5.000000e-04 eta: 4:11:08 time: 0.562838 data_time: 0.240654 memory: 6691 loss_kpt: 0.000683 acc_pose: 0.818220 loss: 0.000683 2022/09/22 15:45:00 - mmengine - INFO - Epoch(train) [104][150/293] lr: 5.000000e-04 eta: 4:10:49 time: 0.572233 data_time: 0.103148 memory: 6691 loss_kpt: 0.000692 acc_pose: 0.851932 loss: 0.000692 2022/09/22 15:45:28 - mmengine - INFO - Epoch(train) [104][200/293] lr: 5.000000e-04 eta: 4:10:28 time: 0.554444 data_time: 0.071858 memory: 6691 loss_kpt: 0.000697 acc_pose: 0.814875 loss: 0.000697 2022/09/22 15:45:55 - mmengine - INFO - Epoch(train) [104][250/293] lr: 5.000000e-04 eta: 4:10:07 time: 0.536469 data_time: 0.084016 memory: 6691 loss_kpt: 0.000685 acc_pose: 0.834751 loss: 0.000685 2022/09/22 15:46:18 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 15:46:48 - mmengine - INFO - Epoch(train) [105][50/293] lr: 5.000000e-04 eta: 4:09:06 time: 0.589919 data_time: 0.231675 memory: 6691 loss_kpt: 0.000701 acc_pose: 0.782850 loss: 0.000701 2022/09/22 15:47:14 - mmengine - INFO - Epoch(train) [105][100/293] lr: 5.000000e-04 eta: 4:08:45 time: 0.531117 data_time: 0.276242 memory: 6691 loss_kpt: 0.000697 acc_pose: 0.848560 loss: 0.000697 2022/09/22 15:47:42 - mmengine - INFO - Epoch(train) [105][150/293] lr: 5.000000e-04 eta: 4:08:24 time: 0.556242 data_time: 0.084527 memory: 6691 loss_kpt: 0.000693 acc_pose: 0.824017 loss: 0.000693 2022/09/22 15:48:10 - mmengine - INFO - Epoch(train) [105][200/293] lr: 5.000000e-04 eta: 4:08:04 time: 0.558303 data_time: 0.078906 memory: 6691 loss_kpt: 0.000678 acc_pose: 0.800153 loss: 0.000678 2022/09/22 15:48:39 - mmengine - INFO - Epoch(train) [105][250/293] lr: 5.000000e-04 eta: 4:07:45 time: 0.585752 data_time: 0.167150 memory: 6691 loss_kpt: 0.000699 acc_pose: 0.776430 loss: 0.000699 2022/09/22 15:49:04 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 15:49:33 - mmengine - INFO - Epoch(train) [106][50/293] lr: 5.000000e-04 eta: 4:06:45 time: 0.594205 data_time: 0.296879 memory: 6691 loss_kpt: 0.000684 acc_pose: 0.795044 loss: 0.000684 2022/09/22 15:50:01 - mmengine - INFO - Epoch(train) [106][100/293] lr: 5.000000e-04 eta: 4:06:25 time: 0.557103 data_time: 0.187567 memory: 6691 loss_kpt: 0.000679 acc_pose: 0.814040 loss: 0.000679 2022/09/22 15:50:30 - mmengine - INFO - Epoch(train) [106][150/293] lr: 5.000000e-04 eta: 4:06:05 time: 0.573529 data_time: 0.099926 memory: 6691 loss_kpt: 0.000690 acc_pose: 0.817092 loss: 0.000690 2022/09/22 15:50:57 - mmengine - INFO - Epoch(train) [106][200/293] lr: 5.000000e-04 eta: 4:05:44 time: 0.543370 data_time: 0.092650 memory: 6691 loss_kpt: 0.000696 acc_pose: 0.790833 loss: 0.000696 2022/09/22 15:51:16 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 15:51:24 - mmengine - INFO - Epoch(train) [106][250/293] lr: 5.000000e-04 eta: 4:05:23 time: 0.534956 data_time: 0.073790 memory: 6691 loss_kpt: 0.000699 acc_pose: 0.834742 loss: 0.000699 2022/09/22 15:51:46 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 15:52:16 - mmengine - INFO - Epoch(train) [107][50/293] lr: 5.000000e-04 eta: 4:04:23 time: 0.588151 data_time: 0.219011 memory: 6691 loss_kpt: 0.000673 acc_pose: 0.831441 loss: 0.000673 2022/09/22 15:52:44 - mmengine - INFO - Epoch(train) [107][100/293] lr: 5.000000e-04 eta: 4:04:03 time: 0.567865 data_time: 0.134843 memory: 6691 loss_kpt: 0.000700 acc_pose: 0.781171 loss: 0.000700 2022/09/22 15:53:13 - mmengine - INFO - Epoch(train) [107][150/293] lr: 5.000000e-04 eta: 4:03:43 time: 0.572528 data_time: 0.131085 memory: 6691 loss_kpt: 0.000695 acc_pose: 0.850290 loss: 0.000695 2022/09/22 15:53:40 - mmengine - INFO - Epoch(train) [107][200/293] lr: 5.000000e-04 eta: 4:03:22 time: 0.554101 data_time: 0.269753 memory: 6691 loss_kpt: 0.000685 acc_pose: 0.788410 loss: 0.000685 2022/09/22 15:54:08 - mmengine - INFO - Epoch(train) [107][250/293] lr: 5.000000e-04 eta: 4:03:02 time: 0.558913 data_time: 0.170604 memory: 6691 loss_kpt: 0.000693 acc_pose: 0.838104 loss: 0.000693 2022/09/22 15:54:32 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 15:55:01 - mmengine - INFO - Epoch(train) [108][50/293] lr: 5.000000e-04 eta: 4:02:02 time: 0.579993 data_time: 0.166603 memory: 6691 loss_kpt: 0.000689 acc_pose: 0.809756 loss: 0.000689 2022/09/22 15:55:28 - mmengine - INFO - Epoch(train) [108][100/293] lr: 5.000000e-04 eta: 4:01:41 time: 0.548958 data_time: 0.220208 memory: 6691 loss_kpt: 0.000686 acc_pose: 0.810799 loss: 0.000686 2022/09/22 15:55:55 - mmengine - INFO - Epoch(train) [108][150/293] lr: 5.000000e-04 eta: 4:01:20 time: 0.548095 data_time: 0.252863 memory: 6691 loss_kpt: 0.000699 acc_pose: 0.752467 loss: 0.000699 2022/09/22 15:56:23 - mmengine - INFO - Epoch(train) [108][200/293] lr: 5.000000e-04 eta: 4:00:59 time: 0.546991 data_time: 0.248858 memory: 6691 loss_kpt: 0.000694 acc_pose: 0.807081 loss: 0.000694 2022/09/22 15:56:50 - mmengine - INFO - Epoch(train) [108][250/293] lr: 5.000000e-04 eta: 4:00:38 time: 0.545530 data_time: 0.242649 memory: 6691 loss_kpt: 0.000682 acc_pose: 0.810744 loss: 0.000682 2022/09/22 15:57:14 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 15:57:43 - mmengine - INFO - Epoch(train) [109][50/293] lr: 5.000000e-04 eta: 3:59:38 time: 0.584339 data_time: 0.169510 memory: 6691 loss_kpt: 0.000685 acc_pose: 0.792343 loss: 0.000685 2022/09/22 15:58:12 - mmengine - INFO - Epoch(train) [109][100/293] lr: 5.000000e-04 eta: 3:59:19 time: 0.579728 data_time: 0.090508 memory: 6691 loss_kpt: 0.000675 acc_pose: 0.872792 loss: 0.000675 2022/09/22 15:58:40 - mmengine - INFO - Epoch(train) [109][150/293] lr: 5.000000e-04 eta: 3:58:58 time: 0.561450 data_time: 0.157298 memory: 6691 loss_kpt: 0.000686 acc_pose: 0.812500 loss: 0.000686 2022/09/22 15:59:08 - mmengine - INFO - Epoch(train) [109][200/293] lr: 5.000000e-04 eta: 3:58:38 time: 0.565441 data_time: 0.234378 memory: 6691 loss_kpt: 0.000684 acc_pose: 0.755831 loss: 0.000684 2022/09/22 15:59:37 - mmengine - INFO - Epoch(train) [109][250/293] lr: 5.000000e-04 eta: 3:58:18 time: 0.573327 data_time: 0.172217 memory: 6691 loss_kpt: 0.000695 acc_pose: 0.829179 loss: 0.000695 2022/09/22 16:00:01 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 16:00:29 - mmengine - INFO - Epoch(train) [110][50/293] lr: 5.000000e-04 eta: 3:57:18 time: 0.578482 data_time: 0.135229 memory: 6691 loss_kpt: 0.000675 acc_pose: 0.784288 loss: 0.000675 2022/09/22 16:00:37 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 16:00:59 - mmengine - INFO - Epoch(train) [110][100/293] lr: 5.000000e-04 eta: 3:56:59 time: 0.583575 data_time: 0.091618 memory: 6691 loss_kpt: 0.000696 acc_pose: 0.799936 loss: 0.000696 2022/09/22 16:01:28 - mmengine - INFO - Epoch(train) [110][150/293] lr: 5.000000e-04 eta: 3:56:39 time: 0.576683 data_time: 0.181439 memory: 6691 loss_kpt: 0.000672 acc_pose: 0.792989 loss: 0.000672 2022/09/22 16:01:56 - mmengine - INFO - Epoch(train) [110][200/293] lr: 5.000000e-04 eta: 3:56:19 time: 0.567647 data_time: 0.097049 memory: 6691 loss_kpt: 0.000691 acc_pose: 0.825142 loss: 0.000691 2022/09/22 16:02:24 - mmengine - INFO - Epoch(train) [110][250/293] lr: 5.000000e-04 eta: 3:55:59 time: 0.567804 data_time: 0.174805 memory: 6691 loss_kpt: 0.000697 acc_pose: 0.794181 loss: 0.000697 2022/09/22 16:02:47 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 16:02:47 - mmengine - INFO - Saving checkpoint at 110 epochs 2022/09/22 16:03:09 - mmengine - INFO - Epoch(val) [110][50/407] eta: 0:01:54 time: 0.320596 data_time: 0.191270 memory: 6691 2022/09/22 16:03:25 - mmengine - INFO - Epoch(val) [110][100/407] eta: 0:01:34 time: 0.307732 data_time: 0.168217 memory: 1014 2022/09/22 16:03:41 - mmengine - INFO - Epoch(val) [110][150/407] eta: 0:01:21 time: 0.315848 data_time: 0.179452 memory: 1014 2022/09/22 16:03:56 - mmengine - INFO - Epoch(val) [110][200/407] eta: 0:01:02 time: 0.303360 data_time: 0.169583 memory: 1014 2022/09/22 16:04:11 - mmengine - INFO - Epoch(val) [110][250/407] eta: 0:00:48 time: 0.307208 data_time: 0.182826 memory: 1014 2022/09/22 16:04:28 - mmengine - INFO - Epoch(val) [110][300/407] eta: 0:00:34 time: 0.324977 data_time: 0.183749 memory: 1014 2022/09/22 16:04:43 - mmengine - INFO - Epoch(val) [110][350/407] eta: 0:00:17 time: 0.307568 data_time: 0.194678 memory: 1014 2022/09/22 16:04:55 - mmengine - INFO - Epoch(val) [110][400/407] eta: 0:00:01 time: 0.246648 data_time: 0.143848 memory: 1014 2022/09/22 16:05:28 - mmengine - INFO - Evaluating CocoMetric... 2022/09/22 16:05:41 - mmengine - INFO - Epoch(val) [110][407/407] coco/AP: 0.690270 coco/AP .5: 0.884970 coco/AP .75: 0.770071 coco/AP (M): 0.653769 coco/AP (L): 0.758828 coco/AR: 0.749591 coco/AR .5: 0.927110 coco/AR .75: 0.823048 coco/AR (M): 0.705244 coco/AR (L): 0.813527 2022/09/22 16:06:10 - mmengine - INFO - Epoch(train) [111][50/293] lr: 5.000000e-04 eta: 3:54:59 time: 0.571809 data_time: 0.102417 memory: 6691 loss_kpt: 0.000691 acc_pose: 0.837492 loss: 0.000691 2022/09/22 16:06:37 - mmengine - INFO - Epoch(train) [111][100/293] lr: 5.000000e-04 eta: 3:54:38 time: 0.556447 data_time: 0.085676 memory: 6691 loss_kpt: 0.000687 acc_pose: 0.828767 loss: 0.000687 2022/09/22 16:07:06 - mmengine - INFO - Epoch(train) [111][150/293] lr: 5.000000e-04 eta: 3:54:18 time: 0.565990 data_time: 0.102984 memory: 6691 loss_kpt: 0.000685 acc_pose: 0.796418 loss: 0.000685 2022/09/22 16:07:33 - mmengine - INFO - Epoch(train) [111][200/293] lr: 5.000000e-04 eta: 3:53:57 time: 0.553114 data_time: 0.076934 memory: 6691 loss_kpt: 0.000697 acc_pose: 0.750355 loss: 0.000697 2022/09/22 16:08:02 - mmengine - INFO - Epoch(train) [111][250/293] lr: 5.000000e-04 eta: 3:53:37 time: 0.563709 data_time: 0.094845 memory: 6691 loss_kpt: 0.000690 acc_pose: 0.825143 loss: 0.000690 2022/09/22 16:08:26 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 16:08:55 - mmengine - INFO - Epoch(train) [112][50/293] lr: 5.000000e-04 eta: 3:52:38 time: 0.588000 data_time: 0.127278 memory: 6691 loss_kpt: 0.000680 acc_pose: 0.840862 loss: 0.000680 2022/09/22 16:09:24 - mmengine - INFO - Epoch(train) [112][100/293] lr: 5.000000e-04 eta: 3:52:18 time: 0.581057 data_time: 0.099918 memory: 6691 loss_kpt: 0.000668 acc_pose: 0.847794 loss: 0.000668 2022/09/22 16:09:53 - mmengine - INFO - Epoch(train) [112][150/293] lr: 5.000000e-04 eta: 3:51:59 time: 0.578886 data_time: 0.106239 memory: 6691 loss_kpt: 0.000676 acc_pose: 0.808808 loss: 0.000676 2022/09/22 16:10:22 - mmengine - INFO - Epoch(train) [112][200/293] lr: 5.000000e-04 eta: 3:51:38 time: 0.570848 data_time: 0.225163 memory: 6691 loss_kpt: 0.000684 acc_pose: 0.784331 loss: 0.000684 2022/09/22 16:10:50 - mmengine - INFO - Epoch(train) [112][250/293] lr: 5.000000e-04 eta: 3:51:18 time: 0.560903 data_time: 0.118606 memory: 6691 loss_kpt: 0.000687 acc_pose: 0.805572 loss: 0.000687 2022/09/22 16:11:14 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 16:11:44 - mmengine - INFO - Epoch(train) [113][50/293] lr: 5.000000e-04 eta: 3:50:20 time: 0.600248 data_time: 0.111230 memory: 6691 loss_kpt: 0.000674 acc_pose: 0.814749 loss: 0.000674 2022/09/22 16:12:12 - mmengine - INFO - Epoch(train) [113][100/293] lr: 5.000000e-04 eta: 3:49:59 time: 0.561097 data_time: 0.074854 memory: 6691 loss_kpt: 0.000694 acc_pose: 0.791638 loss: 0.000694 2022/09/22 16:12:39 - mmengine - INFO - Epoch(train) [113][150/293] lr: 5.000000e-04 eta: 3:49:38 time: 0.545434 data_time: 0.103861 memory: 6691 loss_kpt: 0.000682 acc_pose: 0.808633 loss: 0.000682 2022/09/22 16:12:58 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 16:13:07 - mmengine - INFO - Epoch(train) [113][200/293] lr: 5.000000e-04 eta: 3:49:17 time: 0.567541 data_time: 0.085497 memory: 6691 loss_kpt: 0.000669 acc_pose: 0.836794 loss: 0.000669 2022/09/22 16:13:35 - mmengine - INFO - Epoch(train) [113][250/293] lr: 5.000000e-04 eta: 3:48:56 time: 0.553396 data_time: 0.083602 memory: 6691 loss_kpt: 0.000681 acc_pose: 0.800795 loss: 0.000681 2022/09/22 16:13:58 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 16:14:26 - mmengine - INFO - Epoch(train) [114][50/293] lr: 5.000000e-04 eta: 3:47:57 time: 0.568531 data_time: 0.155235 memory: 6691 loss_kpt: 0.000681 acc_pose: 0.830970 loss: 0.000681 2022/09/22 16:14:54 - mmengine - INFO - Epoch(train) [114][100/293] lr: 5.000000e-04 eta: 3:47:36 time: 0.549883 data_time: 0.243495 memory: 6691 loss_kpt: 0.000674 acc_pose: 0.783466 loss: 0.000674 2022/09/22 16:15:23 - mmengine - INFO - Epoch(train) [114][150/293] lr: 5.000000e-04 eta: 3:47:16 time: 0.575091 data_time: 0.177873 memory: 6691 loss_kpt: 0.000670 acc_pose: 0.809560 loss: 0.000670 2022/09/22 16:15:51 - mmengine - INFO - Epoch(train) [114][200/293] lr: 5.000000e-04 eta: 3:46:56 time: 0.573358 data_time: 0.093613 memory: 6691 loss_kpt: 0.000672 acc_pose: 0.854031 loss: 0.000672 2022/09/22 16:16:20 - mmengine - INFO - Epoch(train) [114][250/293] lr: 5.000000e-04 eta: 3:46:36 time: 0.578702 data_time: 0.132067 memory: 6691 loss_kpt: 0.000686 acc_pose: 0.788450 loss: 0.000686 2022/09/22 16:16:43 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 16:17:12 - mmengine - INFO - Epoch(train) [115][50/293] lr: 5.000000e-04 eta: 3:45:38 time: 0.589989 data_time: 0.141969 memory: 6691 loss_kpt: 0.000680 acc_pose: 0.827035 loss: 0.000680 2022/09/22 16:17:41 - mmengine - INFO - Epoch(train) [115][100/293] lr: 5.000000e-04 eta: 3:45:18 time: 0.574716 data_time: 0.085846 memory: 6691 loss_kpt: 0.000679 acc_pose: 0.806699 loss: 0.000679 2022/09/22 16:18:09 - mmengine - INFO - Epoch(train) [115][150/293] lr: 5.000000e-04 eta: 3:44:57 time: 0.560475 data_time: 0.142770 memory: 6691 loss_kpt: 0.000681 acc_pose: 0.841087 loss: 0.000681 2022/09/22 16:18:37 - mmengine - INFO - Epoch(train) [115][200/293] lr: 5.000000e-04 eta: 3:44:36 time: 0.561724 data_time: 0.157737 memory: 6691 loss_kpt: 0.000681 acc_pose: 0.794721 loss: 0.000681 2022/09/22 16:19:05 - mmengine - INFO - Epoch(train) [115][250/293] lr: 5.000000e-04 eta: 3:44:15 time: 0.554055 data_time: 0.099411 memory: 6691 loss_kpt: 0.000686 acc_pose: 0.822217 loss: 0.000686 2022/09/22 16:19:29 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 16:19:59 - mmengine - INFO - Epoch(train) [116][50/293] lr: 5.000000e-04 eta: 3:43:17 time: 0.596647 data_time: 0.274252 memory: 6691 loss_kpt: 0.000683 acc_pose: 0.813762 loss: 0.000683 2022/09/22 16:20:27 - mmengine - INFO - Epoch(train) [116][100/293] lr: 5.000000e-04 eta: 3:42:56 time: 0.557573 data_time: 0.130353 memory: 6691 loss_kpt: 0.000659 acc_pose: 0.845306 loss: 0.000659 2022/09/22 16:20:54 - mmengine - INFO - Epoch(train) [116][150/293] lr: 5.000000e-04 eta: 3:42:35 time: 0.559206 data_time: 0.151750 memory: 6691 loss_kpt: 0.000676 acc_pose: 0.801053 loss: 0.000676 2022/09/22 16:21:24 - mmengine - INFO - Epoch(train) [116][200/293] lr: 5.000000e-04 eta: 3:42:15 time: 0.583240 data_time: 0.152749 memory: 6691 loss_kpt: 0.000681 acc_pose: 0.740861 loss: 0.000681 2022/09/22 16:21:52 - mmengine - INFO - Epoch(train) [116][250/293] lr: 5.000000e-04 eta: 3:41:55 time: 0.564809 data_time: 0.140815 memory: 6691 loss_kpt: 0.000675 acc_pose: 0.801982 loss: 0.000675 2022/09/22 16:22:15 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 16:22:22 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 16:22:45 - mmengine - INFO - Epoch(train) [117][50/293] lr: 5.000000e-04 eta: 3:40:57 time: 0.591084 data_time: 0.141003 memory: 6691 loss_kpt: 0.000670 acc_pose: 0.820734 loss: 0.000670 2022/09/22 16:23:13 - mmengine - INFO - Epoch(train) [117][100/293] lr: 5.000000e-04 eta: 3:40:37 time: 0.576951 data_time: 0.085915 memory: 6691 loss_kpt: 0.000664 acc_pose: 0.783505 loss: 0.000664 2022/09/22 16:23:42 - mmengine - INFO - Epoch(train) [117][150/293] lr: 5.000000e-04 eta: 3:40:17 time: 0.577616 data_time: 0.089123 memory: 6691 loss_kpt: 0.000679 acc_pose: 0.806200 loss: 0.000679 2022/09/22 16:24:12 - mmengine - INFO - Epoch(train) [117][200/293] lr: 5.000000e-04 eta: 3:39:57 time: 0.586108 data_time: 0.100014 memory: 6691 loss_kpt: 0.000681 acc_pose: 0.804769 loss: 0.000681 2022/09/22 16:24:41 - mmengine - INFO - Epoch(train) [117][250/293] lr: 5.000000e-04 eta: 3:39:37 time: 0.581832 data_time: 0.107585 memory: 6691 loss_kpt: 0.000670 acc_pose: 0.831452 loss: 0.000670 2022/09/22 16:25:06 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 16:25:35 - mmengine - INFO - Epoch(train) [118][50/293] lr: 5.000000e-04 eta: 3:38:39 time: 0.585350 data_time: 0.113534 memory: 6691 loss_kpt: 0.000676 acc_pose: 0.821546 loss: 0.000676 2022/09/22 16:26:04 - mmengine - INFO - Epoch(train) [118][100/293] lr: 5.000000e-04 eta: 3:38:19 time: 0.582465 data_time: 0.211638 memory: 6691 loss_kpt: 0.000676 acc_pose: 0.824349 loss: 0.000676 2022/09/22 16:26:33 - mmengine - INFO - Epoch(train) [118][150/293] lr: 5.000000e-04 eta: 3:37:59 time: 0.575200 data_time: 0.240471 memory: 6691 loss_kpt: 0.000684 acc_pose: 0.815042 loss: 0.000684 2022/09/22 16:27:01 - mmengine - INFO - Epoch(train) [118][200/293] lr: 5.000000e-04 eta: 3:37:38 time: 0.562485 data_time: 0.094131 memory: 6691 loss_kpt: 0.000673 acc_pose: 0.830291 loss: 0.000673 2022/09/22 16:27:30 - mmengine - INFO - Epoch(train) [118][250/293] lr: 5.000000e-04 eta: 3:37:17 time: 0.572530 data_time: 0.077586 memory: 6691 loss_kpt: 0.000684 acc_pose: 0.818147 loss: 0.000684 2022/09/22 16:27:53 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 16:28:22 - mmengine - INFO - Epoch(train) [119][50/293] lr: 5.000000e-04 eta: 3:36:20 time: 0.593789 data_time: 0.173867 memory: 6691 loss_kpt: 0.000674 acc_pose: 0.792472 loss: 0.000674 2022/09/22 16:28:51 - mmengine - INFO - Epoch(train) [119][100/293] lr: 5.000000e-04 eta: 3:36:00 time: 0.578026 data_time: 0.095626 memory: 6691 loss_kpt: 0.000660 acc_pose: 0.870117 loss: 0.000660 2022/09/22 16:29:19 - mmengine - INFO - Epoch(train) [119][150/293] lr: 5.000000e-04 eta: 3:35:38 time: 0.549252 data_time: 0.125677 memory: 6691 loss_kpt: 0.000673 acc_pose: 0.817619 loss: 0.000673 2022/09/22 16:29:48 - mmengine - INFO - Epoch(train) [119][200/293] lr: 5.000000e-04 eta: 3:35:18 time: 0.582140 data_time: 0.220180 memory: 6691 loss_kpt: 0.000679 acc_pose: 0.821461 loss: 0.000679 2022/09/22 16:30:15 - mmengine - INFO - Epoch(train) [119][250/293] lr: 5.000000e-04 eta: 3:34:57 time: 0.553791 data_time: 0.086380 memory: 6691 loss_kpt: 0.000676 acc_pose: 0.814277 loss: 0.000676 2022/09/22 16:30:39 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 16:31:09 - mmengine - INFO - Epoch(train) [120][50/293] lr: 5.000000e-04 eta: 3:34:00 time: 0.582608 data_time: 0.167284 memory: 6691 loss_kpt: 0.000671 acc_pose: 0.864732 loss: 0.000671 2022/09/22 16:31:37 - mmengine - INFO - Epoch(train) [120][100/293] lr: 5.000000e-04 eta: 3:33:39 time: 0.576158 data_time: 0.154911 memory: 6691 loss_kpt: 0.000674 acc_pose: 0.812220 loss: 0.000674 2022/09/22 16:31:57 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 16:32:07 - mmengine - INFO - Epoch(train) [120][150/293] lr: 5.000000e-04 eta: 3:33:19 time: 0.590833 data_time: 0.163426 memory: 6691 loss_kpt: 0.000677 acc_pose: 0.797411 loss: 0.000677 2022/09/22 16:32:36 - mmengine - INFO - Epoch(train) [120][200/293] lr: 5.000000e-04 eta: 3:32:58 time: 0.577731 data_time: 0.080155 memory: 6691 loss_kpt: 0.000699 acc_pose: 0.816712 loss: 0.000699 2022/09/22 16:33:03 - mmengine - INFO - Epoch(train) [120][250/293] lr: 5.000000e-04 eta: 3:32:37 time: 0.552398 data_time: 0.076303 memory: 6691 loss_kpt: 0.000668 acc_pose: 0.822674 loss: 0.000668 2022/09/22 16:33:28 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 16:33:28 - mmengine - INFO - Saving checkpoint at 120 epochs 2022/09/22 16:33:50 - mmengine - INFO - Epoch(val) [120][50/407] eta: 0:01:56 time: 0.325741 data_time: 0.189171 memory: 6691 2022/09/22 16:34:05 - mmengine - INFO - Epoch(val) [120][100/407] eta: 0:01:33 time: 0.304164 data_time: 0.145421 memory: 1014 2022/09/22 16:34:21 - mmengine - INFO - Epoch(val) [120][150/407] eta: 0:01:21 time: 0.316702 data_time: 0.191355 memory: 1014 2022/09/22 16:34:36 - mmengine - INFO - Epoch(val) [120][200/407] eta: 0:01:03 time: 0.305431 data_time: 0.186394 memory: 1014 2022/09/22 16:34:52 - mmengine - INFO - Epoch(val) [120][250/407] eta: 0:00:49 time: 0.312196 data_time: 0.181268 memory: 1014 2022/09/22 16:35:07 - mmengine - INFO - Epoch(val) [120][300/407] eta: 0:00:32 time: 0.303397 data_time: 0.173052 memory: 1014 2022/09/22 16:35:23 - mmengine - INFO - Epoch(val) [120][350/407] eta: 0:00:18 time: 0.321159 data_time: 0.206219 memory: 1014 2022/09/22 16:35:35 - mmengine - INFO - Epoch(val) [120][400/407] eta: 0:00:01 time: 0.242588 data_time: 0.137290 memory: 1014 2022/09/22 16:36:08 - mmengine - INFO - Evaluating CocoMetric... 2022/09/22 16:36:21 - mmengine - INFO - Epoch(val) [120][407/407] coco/AP: 0.695228 coco/AP .5: 0.888088 coco/AP .75: 0.774102 coco/AP (M): 0.655446 coco/AP (L): 0.765011 coco/AR: 0.753715 coco/AR .5: 0.927897 coco/AR .75: 0.823205 coco/AR (M): 0.707976 coco/AR (L): 0.819175 2022/09/22 16:36:21 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220922/res50_256/best_coco/AP_epoch_100.pth is removed 2022/09/22 16:36:24 - mmengine - INFO - The best checkpoint with 0.6952 coco/AP at 120 epoch is saved to best_coco/AP_epoch_120.pth. 2022/09/22 16:36:51 - mmengine - INFO - Epoch(train) [121][50/293] lr: 5.000000e-04 eta: 3:31:39 time: 0.547317 data_time: 0.208937 memory: 6691 loss_kpt: 0.000668 acc_pose: 0.788029 loss: 0.000668 2022/09/22 16:37:19 - mmengine - INFO - Epoch(train) [121][100/293] lr: 5.000000e-04 eta: 3:31:18 time: 0.566289 data_time: 0.089578 memory: 6691 loss_kpt: 0.000673 acc_pose: 0.832529 loss: 0.000673 2022/09/22 16:37:48 - mmengine - INFO - Epoch(train) [121][150/293] lr: 5.000000e-04 eta: 3:30:57 time: 0.574425 data_time: 0.118103 memory: 6691 loss_kpt: 0.000678 acc_pose: 0.819237 loss: 0.000678 2022/09/22 16:38:16 - mmengine - INFO - Epoch(train) [121][200/293] lr: 5.000000e-04 eta: 3:30:36 time: 0.565703 data_time: 0.128485 memory: 6691 loss_kpt: 0.000681 acc_pose: 0.807806 loss: 0.000681 2022/09/22 16:38:44 - mmengine - INFO - Epoch(train) [121][250/293] lr: 5.000000e-04 eta: 3:30:14 time: 0.546129 data_time: 0.076132 memory: 6691 loss_kpt: 0.000687 acc_pose: 0.814585 loss: 0.000687 2022/09/22 16:39:07 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 16:39:37 - mmengine - INFO - Epoch(train) [122][50/293] lr: 5.000000e-04 eta: 3:29:18 time: 0.586203 data_time: 0.129450 memory: 6691 loss_kpt: 0.000671 acc_pose: 0.822840 loss: 0.000671 2022/09/22 16:40:05 - mmengine - INFO - Epoch(train) [122][100/293] lr: 5.000000e-04 eta: 3:28:57 time: 0.561735 data_time: 0.083665 memory: 6691 loss_kpt: 0.000665 acc_pose: 0.801580 loss: 0.000665 2022/09/22 16:40:31 - mmengine - INFO - Epoch(train) [122][150/293] lr: 5.000000e-04 eta: 3:28:34 time: 0.528905 data_time: 0.084751 memory: 6691 loss_kpt: 0.000650 acc_pose: 0.832630 loss: 0.000650 2022/09/22 16:41:00 - mmengine - INFO - Epoch(train) [122][200/293] lr: 5.000000e-04 eta: 3:28:13 time: 0.571820 data_time: 0.076654 memory: 6691 loss_kpt: 0.000676 acc_pose: 0.865423 loss: 0.000676 2022/09/22 16:41:28 - mmengine - INFO - Epoch(train) [122][250/293] lr: 5.000000e-04 eta: 3:27:53 time: 0.573322 data_time: 0.139640 memory: 6691 loss_kpt: 0.000678 acc_pose: 0.841465 loss: 0.000678 2022/09/22 16:41:53 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 16:42:23 - mmengine - INFO - Epoch(train) [123][50/293] lr: 5.000000e-04 eta: 3:26:57 time: 0.591619 data_time: 0.156924 memory: 6691 loss_kpt: 0.000661 acc_pose: 0.789313 loss: 0.000661 2022/09/22 16:42:51 - mmengine - INFO - Epoch(train) [123][100/293] lr: 5.000000e-04 eta: 3:26:36 time: 0.570111 data_time: 0.098284 memory: 6691 loss_kpt: 0.000679 acc_pose: 0.809971 loss: 0.000679 2022/09/22 16:43:19 - mmengine - INFO - Epoch(train) [123][150/293] lr: 5.000000e-04 eta: 3:26:14 time: 0.553256 data_time: 0.070731 memory: 6691 loss_kpt: 0.000686 acc_pose: 0.828364 loss: 0.000686 2022/09/22 16:43:47 - mmengine - INFO - Epoch(train) [123][200/293] lr: 5.000000e-04 eta: 3:25:52 time: 0.553881 data_time: 0.195628 memory: 6691 loss_kpt: 0.000671 acc_pose: 0.779156 loss: 0.000671 2022/09/22 16:44:14 - mmengine - INFO - Epoch(train) [123][250/293] lr: 5.000000e-04 eta: 3:25:31 time: 0.550038 data_time: 0.256757 memory: 6691 loss_kpt: 0.000667 acc_pose: 0.862412 loss: 0.000667 2022/09/22 16:44:16 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 16:44:37 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 16:45:07 - mmengine - INFO - Epoch(train) [124][50/293] lr: 5.000000e-04 eta: 3:24:35 time: 0.596777 data_time: 0.274412 memory: 6691 loss_kpt: 0.000672 acc_pose: 0.833894 loss: 0.000672 2022/09/22 16:45:36 - mmengine - INFO - Epoch(train) [124][100/293] lr: 5.000000e-04 eta: 3:24:14 time: 0.570477 data_time: 0.204848 memory: 6691 loss_kpt: 0.000681 acc_pose: 0.850991 loss: 0.000681 2022/09/22 16:46:04 - mmengine - INFO - Epoch(train) [124][150/293] lr: 5.000000e-04 eta: 3:23:53 time: 0.560129 data_time: 0.198752 memory: 6691 loss_kpt: 0.000675 acc_pose: 0.797934 loss: 0.000675 2022/09/22 16:46:32 - mmengine - INFO - Epoch(train) [124][200/293] lr: 5.000000e-04 eta: 3:23:31 time: 0.562404 data_time: 0.100296 memory: 6691 loss_kpt: 0.000686 acc_pose: 0.807041 loss: 0.000686 2022/09/22 16:47:00 - mmengine - INFO - Epoch(train) [124][250/293] lr: 5.000000e-04 eta: 3:23:10 time: 0.559537 data_time: 0.088373 memory: 6691 loss_kpt: 0.000679 acc_pose: 0.806649 loss: 0.000679 2022/09/22 16:47:24 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 16:47:53 - mmengine - INFO - Epoch(train) [125][50/293] lr: 5.000000e-04 eta: 3:22:14 time: 0.588035 data_time: 0.125727 memory: 6691 loss_kpt: 0.000669 acc_pose: 0.783355 loss: 0.000669 2022/09/22 16:48:22 - mmengine - INFO - Epoch(train) [125][100/293] lr: 5.000000e-04 eta: 3:21:53 time: 0.571346 data_time: 0.078697 memory: 6691 loss_kpt: 0.000671 acc_pose: 0.801855 loss: 0.000671 2022/09/22 16:48:50 - mmengine - INFO - Epoch(train) [125][150/293] lr: 5.000000e-04 eta: 3:21:32 time: 0.562589 data_time: 0.092541 memory: 6691 loss_kpt: 0.000660 acc_pose: 0.821367 loss: 0.000660 2022/09/22 16:49:18 - mmengine - INFO - Epoch(train) [125][200/293] lr: 5.000000e-04 eta: 3:21:10 time: 0.565450 data_time: 0.233715 memory: 6691 loss_kpt: 0.000664 acc_pose: 0.767037 loss: 0.000664 2022/09/22 16:49:45 - mmengine - INFO - Epoch(train) [125][250/293] lr: 5.000000e-04 eta: 3:20:48 time: 0.541227 data_time: 0.162269 memory: 6691 loss_kpt: 0.000665 acc_pose: 0.798264 loss: 0.000665 2022/09/22 16:50:09 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 16:50:38 - mmengine - INFO - Epoch(train) [126][50/293] lr: 5.000000e-04 eta: 3:19:52 time: 0.575846 data_time: 0.108816 memory: 6691 loss_kpt: 0.000661 acc_pose: 0.803171 loss: 0.000661 2022/09/22 16:51:06 - mmengine - INFO - Epoch(train) [126][100/293] lr: 5.000000e-04 eta: 3:19:31 time: 0.552492 data_time: 0.161628 memory: 6691 loss_kpt: 0.000671 acc_pose: 0.845533 loss: 0.000671 2022/09/22 16:51:34 - mmengine - INFO - Epoch(train) [126][150/293] lr: 5.000000e-04 eta: 3:19:09 time: 0.567346 data_time: 0.275579 memory: 6691 loss_kpt: 0.000663 acc_pose: 0.782162 loss: 0.000663 2022/09/22 16:52:01 - mmengine - INFO - Epoch(train) [126][200/293] lr: 5.000000e-04 eta: 3:18:47 time: 0.532777 data_time: 0.149993 memory: 6691 loss_kpt: 0.000670 acc_pose: 0.798836 loss: 0.000670 2022/09/22 16:52:29 - mmengine - INFO - Epoch(train) [126][250/293] lr: 5.000000e-04 eta: 3:18:26 time: 0.568569 data_time: 0.162056 memory: 6691 loss_kpt: 0.000670 acc_pose: 0.830137 loss: 0.000670 2022/09/22 16:52:52 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 16:53:20 - mmengine - INFO - Epoch(train) [127][50/293] lr: 5.000000e-04 eta: 3:17:30 time: 0.570052 data_time: 0.162385 memory: 6691 loss_kpt: 0.000675 acc_pose: 0.884746 loss: 0.000675 2022/09/22 16:53:38 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 16:53:48 - mmengine - INFO - Epoch(train) [127][100/293] lr: 5.000000e-04 eta: 3:17:08 time: 0.545072 data_time: 0.099172 memory: 6691 loss_kpt: 0.000670 acc_pose: 0.819540 loss: 0.000670 2022/09/22 16:54:16 - mmengine - INFO - Epoch(train) [127][150/293] lr: 5.000000e-04 eta: 3:16:46 time: 0.569223 data_time: 0.178058 memory: 6691 loss_kpt: 0.000681 acc_pose: 0.783216 loss: 0.000681 2022/09/22 16:54:45 - mmengine - INFO - Epoch(train) [127][200/293] lr: 5.000000e-04 eta: 3:16:26 time: 0.587511 data_time: 0.141288 memory: 6691 loss_kpt: 0.000674 acc_pose: 0.847397 loss: 0.000674 2022/09/22 16:55:14 - mmengine - INFO - Epoch(train) [127][250/293] lr: 5.000000e-04 eta: 3:16:05 time: 0.572481 data_time: 0.145879 memory: 6691 loss_kpt: 0.000664 acc_pose: 0.842883 loss: 0.000664 2022/09/22 16:55:38 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 16:56:07 - mmengine - INFO - Epoch(train) [128][50/293] lr: 5.000000e-04 eta: 3:15:09 time: 0.578212 data_time: 0.179205 memory: 6691 loss_kpt: 0.000672 acc_pose: 0.773923 loss: 0.000672 2022/09/22 16:56:33 - mmengine - INFO - Epoch(train) [128][100/293] lr: 5.000000e-04 eta: 3:14:47 time: 0.536651 data_time: 0.078889 memory: 6691 loss_kpt: 0.000661 acc_pose: 0.735638 loss: 0.000661 2022/09/22 16:57:01 - mmengine - INFO - Epoch(train) [128][150/293] lr: 5.000000e-04 eta: 3:14:25 time: 0.548806 data_time: 0.077907 memory: 6691 loss_kpt: 0.000679 acc_pose: 0.861089 loss: 0.000679 2022/09/22 16:57:29 - mmengine - INFO - Epoch(train) [128][200/293] lr: 5.000000e-04 eta: 3:14:03 time: 0.563540 data_time: 0.079424 memory: 6691 loss_kpt: 0.000677 acc_pose: 0.799428 loss: 0.000677 2022/09/22 16:57:59 - mmengine - INFO - Epoch(train) [128][250/293] lr: 5.000000e-04 eta: 3:13:43 time: 0.590929 data_time: 0.176942 memory: 6691 loss_kpt: 0.000678 acc_pose: 0.827363 loss: 0.000678 2022/09/22 16:58:23 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 16:58:53 - mmengine - INFO - Epoch(train) [129][50/293] lr: 5.000000e-04 eta: 3:12:48 time: 0.598015 data_time: 0.174227 memory: 6691 loss_kpt: 0.000667 acc_pose: 0.799338 loss: 0.000667 2022/09/22 16:59:20 - mmengine - INFO - Epoch(train) [129][100/293] lr: 5.000000e-04 eta: 3:12:26 time: 0.546941 data_time: 0.197947 memory: 6691 loss_kpt: 0.000655 acc_pose: 0.841312 loss: 0.000655 2022/09/22 16:59:49 - mmengine - INFO - Epoch(train) [129][150/293] lr: 5.000000e-04 eta: 3:12:05 time: 0.567187 data_time: 0.305694 memory: 6691 loss_kpt: 0.000679 acc_pose: 0.831256 loss: 0.000679 2022/09/22 17:00:16 - mmengine - INFO - Epoch(train) [129][200/293] lr: 5.000000e-04 eta: 3:11:43 time: 0.548393 data_time: 0.225785 memory: 6691 loss_kpt: 0.000665 acc_pose: 0.852252 loss: 0.000665 2022/09/22 17:00:44 - mmengine - INFO - Epoch(train) [129][250/293] lr: 5.000000e-04 eta: 3:11:21 time: 0.549431 data_time: 0.198860 memory: 6691 loss_kpt: 0.000653 acc_pose: 0.825174 loss: 0.000653 2022/09/22 17:01:07 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 17:01:37 - mmengine - INFO - Epoch(train) [130][50/293] lr: 5.000000e-04 eta: 3:10:26 time: 0.588682 data_time: 0.174374 memory: 6691 loss_kpt: 0.000659 acc_pose: 0.791892 loss: 0.000659 2022/09/22 17:02:06 - mmengine - INFO - Epoch(train) [130][100/293] lr: 5.000000e-04 eta: 3:10:05 time: 0.580549 data_time: 0.164302 memory: 6691 loss_kpt: 0.000670 acc_pose: 0.827380 loss: 0.000670 2022/09/22 17:02:34 - mmengine - INFO - Epoch(train) [130][150/293] lr: 5.000000e-04 eta: 3:09:43 time: 0.559892 data_time: 0.078009 memory: 6691 loss_kpt: 0.000677 acc_pose: 0.805692 loss: 0.000677 2022/09/22 17:03:03 - mmengine - INFO - Epoch(train) [130][200/293] lr: 5.000000e-04 eta: 3:09:22 time: 0.582296 data_time: 0.129471 memory: 6691 loss_kpt: 0.000662 acc_pose: 0.789457 loss: 0.000662 2022/09/22 17:03:05 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 17:03:32 - mmengine - INFO - Epoch(train) [130][250/293] lr: 5.000000e-04 eta: 3:09:01 time: 0.582229 data_time: 0.113049 memory: 6691 loss_kpt: 0.000673 acc_pose: 0.797220 loss: 0.000673 2022/09/22 17:03:56 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 17:03:56 - mmengine - INFO - Saving checkpoint at 130 epochs 2022/09/22 17:04:18 - mmengine - INFO - Epoch(val) [130][50/407] eta: 0:01:55 time: 0.323025 data_time: 0.194881 memory: 6691 2022/09/22 17:04:33 - mmengine - INFO - Epoch(val) [130][100/407] eta: 0:01:32 time: 0.300852 data_time: 0.156851 memory: 1014 2022/09/22 17:04:48 - mmengine - INFO - Epoch(val) [130][150/407] eta: 0:01:18 time: 0.305213 data_time: 0.172806 memory: 1014 2022/09/22 17:05:03 - mmengine - INFO - Epoch(val) [130][200/407] eta: 0:01:01 time: 0.296524 data_time: 0.160549 memory: 1014 2022/09/22 17:05:19 - mmengine - INFO - Epoch(val) [130][250/407] eta: 0:00:48 time: 0.312013 data_time: 0.164149 memory: 1014 2022/09/22 17:05:35 - mmengine - INFO - Epoch(val) [130][300/407] eta: 0:00:34 time: 0.326204 data_time: 0.198492 memory: 1014 2022/09/22 17:05:51 - mmengine - INFO - Epoch(val) [130][350/407] eta: 0:00:18 time: 0.317859 data_time: 0.179888 memory: 1014 2022/09/22 17:06:02 - mmengine - INFO - Epoch(val) [130][400/407] eta: 0:00:01 time: 0.218715 data_time: 0.137207 memory: 1014 2022/09/22 17:06:35 - mmengine - INFO - Evaluating CocoMetric... 2022/09/22 17:06:48 - mmengine - INFO - Epoch(val) [130][407/407] coco/AP: 0.696745 coco/AP .5: 0.890978 coco/AP .75: 0.772400 coco/AP (M): 0.656225 coco/AP (L): 0.766598 coco/AR: 0.754518 coco/AR .5: 0.930101 coco/AR .75: 0.824150 coco/AR (M): 0.709506 coco/AR (L): 0.818766 2022/09/22 17:06:48 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220922/res50_256/best_coco/AP_epoch_120.pth is removed 2022/09/22 17:06:50 - mmengine - INFO - The best checkpoint with 0.6967 coco/AP at 130 epoch is saved to best_coco/AP_epoch_130.pth. 2022/09/22 17:07:16 - mmengine - INFO - Epoch(train) [131][50/293] lr: 5.000000e-04 eta: 3:08:05 time: 0.525029 data_time: 0.262541 memory: 6691 loss_kpt: 0.000669 acc_pose: 0.840582 loss: 0.000669 2022/09/22 17:07:45 - mmengine - INFO - Epoch(train) [131][100/293] lr: 5.000000e-04 eta: 3:07:43 time: 0.573870 data_time: 0.173290 memory: 6691 loss_kpt: 0.000668 acc_pose: 0.811844 loss: 0.000668 2022/09/22 17:08:12 - mmengine - INFO - Epoch(train) [131][150/293] lr: 5.000000e-04 eta: 3:07:21 time: 0.545721 data_time: 0.121670 memory: 6691 loss_kpt: 0.000680 acc_pose: 0.828602 loss: 0.000680 2022/09/22 17:08:40 - mmengine - INFO - Epoch(train) [131][200/293] lr: 5.000000e-04 eta: 3:06:59 time: 0.547082 data_time: 0.104428 memory: 6691 loss_kpt: 0.000671 acc_pose: 0.837233 loss: 0.000671 2022/09/22 17:09:07 - mmengine - INFO - Epoch(train) [131][250/293] lr: 5.000000e-04 eta: 3:06:37 time: 0.551488 data_time: 0.088130 memory: 6691 loss_kpt: 0.000680 acc_pose: 0.836093 loss: 0.000680 2022/09/22 17:09:31 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 17:09:59 - mmengine - INFO - Epoch(train) [132][50/293] lr: 5.000000e-04 eta: 3:05:42 time: 0.567098 data_time: 0.248185 memory: 6691 loss_kpt: 0.000677 acc_pose: 0.791207 loss: 0.000677 2022/09/22 17:10:27 - mmengine - INFO - Epoch(train) [132][100/293] lr: 5.000000e-04 eta: 3:05:20 time: 0.564275 data_time: 0.214485 memory: 6691 loss_kpt: 0.000672 acc_pose: 0.824351 loss: 0.000672 2022/09/22 17:10:56 - mmengine - INFO - Epoch(train) [132][150/293] lr: 5.000000e-04 eta: 3:04:59 time: 0.564944 data_time: 0.134522 memory: 6691 loss_kpt: 0.000675 acc_pose: 0.819314 loss: 0.000675 2022/09/22 17:11:24 - mmengine - INFO - Epoch(train) [132][200/293] lr: 5.000000e-04 eta: 3:04:37 time: 0.576090 data_time: 0.096933 memory: 6691 loss_kpt: 0.000666 acc_pose: 0.806615 loss: 0.000666 2022/09/22 17:11:52 - mmengine - INFO - Epoch(train) [132][250/293] lr: 5.000000e-04 eta: 3:04:15 time: 0.555531 data_time: 0.105396 memory: 6691 loss_kpt: 0.000669 acc_pose: 0.861371 loss: 0.000669 2022/09/22 17:12:16 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 17:12:44 - mmengine - INFO - Epoch(train) [133][50/293] lr: 5.000000e-04 eta: 3:03:21 time: 0.569078 data_time: 0.114225 memory: 6691 loss_kpt: 0.000664 acc_pose: 0.832469 loss: 0.000664 2022/09/22 17:13:12 - mmengine - INFO - Epoch(train) [133][100/293] lr: 5.000000e-04 eta: 3:02:59 time: 0.552725 data_time: 0.087872 memory: 6691 loss_kpt: 0.000668 acc_pose: 0.790790 loss: 0.000668 2022/09/22 17:13:40 - mmengine - INFO - Epoch(train) [133][150/293] lr: 5.000000e-04 eta: 3:02:37 time: 0.552357 data_time: 0.098098 memory: 6691 loss_kpt: 0.000669 acc_pose: 0.841743 loss: 0.000669 2022/09/22 17:14:08 - mmengine - INFO - Epoch(train) [133][200/293] lr: 5.000000e-04 eta: 3:02:15 time: 0.569143 data_time: 0.112523 memory: 6691 loss_kpt: 0.000662 acc_pose: 0.840560 loss: 0.000662 2022/09/22 17:14:36 - mmengine - INFO - Epoch(train) [133][250/293] lr: 5.000000e-04 eta: 3:01:53 time: 0.566743 data_time: 0.211568 memory: 6691 loss_kpt: 0.000673 acc_pose: 0.779623 loss: 0.000673 2022/09/22 17:15:01 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 17:15:20 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 17:15:31 - mmengine - INFO - Epoch(train) [134][50/293] lr: 5.000000e-04 eta: 3:01:00 time: 0.592579 data_time: 0.111686 memory: 6691 loss_kpt: 0.000675 acc_pose: 0.851366 loss: 0.000675 2022/09/22 17:15:58 - mmengine - INFO - Epoch(train) [134][100/293] lr: 5.000000e-04 eta: 3:00:38 time: 0.557507 data_time: 0.089323 memory: 6691 loss_kpt: 0.000654 acc_pose: 0.827128 loss: 0.000654 2022/09/22 17:16:26 - mmengine - INFO - Epoch(train) [134][150/293] lr: 5.000000e-04 eta: 3:00:16 time: 0.549903 data_time: 0.081504 memory: 6691 loss_kpt: 0.000679 acc_pose: 0.832934 loss: 0.000679 2022/09/22 17:16:54 - mmengine - INFO - Epoch(train) [134][200/293] lr: 5.000000e-04 eta: 2:59:54 time: 0.562376 data_time: 0.090786 memory: 6691 loss_kpt: 0.000658 acc_pose: 0.821620 loss: 0.000658 2022/09/22 17:17:22 - mmengine - INFO - Epoch(train) [134][250/293] lr: 5.000000e-04 eta: 2:59:32 time: 0.554671 data_time: 0.142230 memory: 6691 loss_kpt: 0.000676 acc_pose: 0.819253 loss: 0.000676 2022/09/22 17:17:45 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 17:18:14 - mmengine - INFO - Epoch(train) [135][50/293] lr: 5.000000e-04 eta: 2:58:38 time: 0.583348 data_time: 0.176166 memory: 6691 loss_kpt: 0.000671 acc_pose: 0.806153 loss: 0.000671 2022/09/22 17:18:43 - mmengine - INFO - Epoch(train) [135][100/293] lr: 5.000000e-04 eta: 2:58:16 time: 0.576909 data_time: 0.133229 memory: 6691 loss_kpt: 0.000681 acc_pose: 0.819854 loss: 0.000681 2022/09/22 17:19:11 - mmengine - INFO - Epoch(train) [135][150/293] lr: 5.000000e-04 eta: 2:57:54 time: 0.561634 data_time: 0.088729 memory: 6691 loss_kpt: 0.000667 acc_pose: 0.843933 loss: 0.000667 2022/09/22 17:19:39 - mmengine - INFO - Epoch(train) [135][200/293] lr: 5.000000e-04 eta: 2:57:32 time: 0.556134 data_time: 0.099903 memory: 6691 loss_kpt: 0.000676 acc_pose: 0.813725 loss: 0.000676 2022/09/22 17:20:08 - mmengine - INFO - Epoch(train) [135][250/293] lr: 5.000000e-04 eta: 2:57:11 time: 0.585943 data_time: 0.115717 memory: 6691 loss_kpt: 0.000680 acc_pose: 0.778983 loss: 0.000680 2022/09/22 17:20:31 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 17:21:01 - mmengine - INFO - Epoch(train) [136][50/293] lr: 5.000000e-04 eta: 2:56:18 time: 0.596676 data_time: 0.191835 memory: 6691 loss_kpt: 0.000662 acc_pose: 0.806226 loss: 0.000662 2022/09/22 17:21:30 - mmengine - INFO - Epoch(train) [136][100/293] lr: 5.000000e-04 eta: 2:55:56 time: 0.574165 data_time: 0.133787 memory: 6691 loss_kpt: 0.000665 acc_pose: 0.811284 loss: 0.000665 2022/09/22 17:21:59 - mmengine - INFO - Epoch(train) [136][150/293] lr: 5.000000e-04 eta: 2:55:35 time: 0.574550 data_time: 0.106883 memory: 6691 loss_kpt: 0.000683 acc_pose: 0.782750 loss: 0.000683 2022/09/22 17:22:27 - mmengine - INFO - Epoch(train) [136][200/293] lr: 5.000000e-04 eta: 2:55:13 time: 0.572801 data_time: 0.107640 memory: 6691 loss_kpt: 0.000663 acc_pose: 0.857697 loss: 0.000663 2022/09/22 17:22:55 - mmengine - INFO - Epoch(train) [136][250/293] lr: 5.000000e-04 eta: 2:54:51 time: 0.551253 data_time: 0.127263 memory: 6691 loss_kpt: 0.000674 acc_pose: 0.806392 loss: 0.000674 2022/09/22 17:23:19 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 17:23:49 - mmengine - INFO - Epoch(train) [137][50/293] lr: 5.000000e-04 eta: 2:53:58 time: 0.595860 data_time: 0.133516 memory: 6691 loss_kpt: 0.000662 acc_pose: 0.793452 loss: 0.000662 2022/09/22 17:24:18 - mmengine - INFO - Epoch(train) [137][100/293] lr: 5.000000e-04 eta: 2:53:36 time: 0.595003 data_time: 0.115339 memory: 6691 loss_kpt: 0.000664 acc_pose: 0.825527 loss: 0.000664 2022/09/22 17:24:46 - mmengine - INFO - Epoch(train) [137][150/293] lr: 5.000000e-04 eta: 2:53:14 time: 0.558188 data_time: 0.152116 memory: 6691 loss_kpt: 0.000657 acc_pose: 0.825812 loss: 0.000657 2022/09/22 17:24:47 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 17:25:14 - mmengine - INFO - Epoch(train) [137][200/293] lr: 5.000000e-04 eta: 2:52:52 time: 0.558972 data_time: 0.170238 memory: 6691 loss_kpt: 0.000681 acc_pose: 0.858092 loss: 0.000681 2022/09/22 17:25:43 - mmengine - INFO - Epoch(train) [137][250/293] lr: 5.000000e-04 eta: 2:52:31 time: 0.575097 data_time: 0.119084 memory: 6691 loss_kpt: 0.000661 acc_pose: 0.815745 loss: 0.000661 2022/09/22 17:26:07 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 17:26:38 - mmengine - INFO - Epoch(train) [138][50/293] lr: 5.000000e-04 eta: 2:51:38 time: 0.603242 data_time: 0.163055 memory: 6691 loss_kpt: 0.000663 acc_pose: 0.787816 loss: 0.000663 2022/09/22 17:27:06 - mmengine - INFO - Epoch(train) [138][100/293] lr: 5.000000e-04 eta: 2:51:16 time: 0.560854 data_time: 0.131451 memory: 6691 loss_kpt: 0.000676 acc_pose: 0.825483 loss: 0.000676 2022/09/22 17:27:34 - mmengine - INFO - Epoch(train) [138][150/293] lr: 5.000000e-04 eta: 2:50:54 time: 0.562973 data_time: 0.087986 memory: 6691 loss_kpt: 0.000666 acc_pose: 0.818040 loss: 0.000666 2022/09/22 17:28:02 - mmengine - INFO - Epoch(train) [138][200/293] lr: 5.000000e-04 eta: 2:50:32 time: 0.570227 data_time: 0.102896 memory: 6691 loss_kpt: 0.000675 acc_pose: 0.825671 loss: 0.000675 2022/09/22 17:28:30 - mmengine - INFO - Epoch(train) [138][250/293] lr: 5.000000e-04 eta: 2:50:09 time: 0.547266 data_time: 0.084194 memory: 6691 loss_kpt: 0.000660 acc_pose: 0.820492 loss: 0.000660 2022/09/22 17:28:54 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 17:29:23 - mmengine - INFO - Epoch(train) [139][50/293] lr: 5.000000e-04 eta: 2:49:16 time: 0.583463 data_time: 0.181179 memory: 6691 loss_kpt: 0.000673 acc_pose: 0.842188 loss: 0.000673 2022/09/22 17:29:53 - mmengine - INFO - Epoch(train) [139][100/293] lr: 5.000000e-04 eta: 2:48:55 time: 0.586631 data_time: 0.160030 memory: 6691 loss_kpt: 0.000661 acc_pose: 0.822585 loss: 0.000661 2022/09/22 17:30:21 - mmengine - INFO - Epoch(train) [139][150/293] lr: 5.000000e-04 eta: 2:48:33 time: 0.569878 data_time: 0.092036 memory: 6691 loss_kpt: 0.000669 acc_pose: 0.819953 loss: 0.000669 2022/09/22 17:30:51 - mmengine - INFO - Epoch(train) [139][200/293] lr: 5.000000e-04 eta: 2:48:12 time: 0.595994 data_time: 0.104537 memory: 6691 loss_kpt: 0.000668 acc_pose: 0.849363 loss: 0.000668 2022/09/22 17:31:19 - mmengine - INFO - Epoch(train) [139][250/293] lr: 5.000000e-04 eta: 2:47:50 time: 0.555160 data_time: 0.087461 memory: 6691 loss_kpt: 0.000671 acc_pose: 0.810882 loss: 0.000671 2022/09/22 17:31:42 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 17:32:11 - mmengine - INFO - Epoch(train) [140][50/293] lr: 5.000000e-04 eta: 2:46:57 time: 0.593724 data_time: 0.106199 memory: 6691 loss_kpt: 0.000674 acc_pose: 0.802120 loss: 0.000674 2022/09/22 17:32:39 - mmengine - INFO - Epoch(train) [140][100/293] lr: 5.000000e-04 eta: 2:46:34 time: 0.544200 data_time: 0.107856 memory: 6691 loss_kpt: 0.000668 acc_pose: 0.763153 loss: 0.000668 2022/09/22 17:33:08 - mmengine - INFO - Epoch(train) [140][150/293] lr: 5.000000e-04 eta: 2:46:13 time: 0.579756 data_time: 0.106310 memory: 6691 loss_kpt: 0.000654 acc_pose: 0.808503 loss: 0.000654 2022/09/22 17:33:36 - mmengine - INFO - Epoch(train) [140][200/293] lr: 5.000000e-04 eta: 2:45:50 time: 0.560579 data_time: 0.109054 memory: 6691 loss_kpt: 0.000665 acc_pose: 0.821324 loss: 0.000665 2022/09/22 17:34:04 - mmengine - INFO - Epoch(train) [140][250/293] lr: 5.000000e-04 eta: 2:45:28 time: 0.563972 data_time: 0.080774 memory: 6691 loss_kpt: 0.000662 acc_pose: 0.819629 loss: 0.000662 2022/09/22 17:34:17 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 17:34:28 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 17:34:28 - mmengine - INFO - Saving checkpoint at 140 epochs 2022/09/22 17:34:51 - mmengine - INFO - Epoch(val) [140][50/407] eta: 0:01:55 time: 0.322955 data_time: 0.165666 memory: 6691 2022/09/22 17:35:07 - mmengine - INFO - Epoch(val) [140][100/407] eta: 0:01:34 time: 0.308698 data_time: 0.159795 memory: 1014 2022/09/22 17:35:22 - mmengine - INFO - Epoch(val) [140][150/407] eta: 0:01:20 time: 0.315073 data_time: 0.163176 memory: 1014 2022/09/22 17:35:38 - mmengine - INFO - Epoch(val) [140][200/407] eta: 0:01:03 time: 0.304404 data_time: 0.168804 memory: 1014 2022/09/22 17:35:53 - mmengine - INFO - Epoch(val) [140][250/407] eta: 0:00:47 time: 0.300903 data_time: 0.176905 memory: 1014 2022/09/22 17:36:08 - mmengine - INFO - Epoch(val) [140][300/407] eta: 0:00:33 time: 0.310002 data_time: 0.181930 memory: 1014 2022/09/22 17:36:25 - mmengine - INFO - Epoch(val) [140][350/407] eta: 0:00:18 time: 0.328573 data_time: 0.194479 memory: 1014 2022/09/22 17:36:36 - mmengine - INFO - Epoch(val) [140][400/407] eta: 0:00:01 time: 0.232157 data_time: 0.135782 memory: 1014 2022/09/22 17:37:09 - mmengine - INFO - Evaluating CocoMetric... 2022/09/22 17:37:23 - mmengine - INFO - Epoch(val) [140][407/407] coco/AP: 0.696995 coco/AP .5: 0.888442 coco/AP .75: 0.775163 coco/AP (M): 0.660257 coco/AP (L): 0.764911 coco/AR: 0.756030 coco/AR .5: 0.929628 coco/AR .75: 0.824780 coco/AR (M): 0.711363 coco/AR (L): 0.819844 2022/09/22 17:37:23 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220922/res50_256/best_coco/AP_epoch_130.pth is removed 2022/09/22 17:37:25 - mmengine - INFO - The best checkpoint with 0.6970 coco/AP at 140 epoch is saved to best_coco/AP_epoch_140.pth. 2022/09/22 17:37:54 - mmengine - INFO - Epoch(train) [141][50/293] lr: 5.000000e-04 eta: 2:44:35 time: 0.563794 data_time: 0.171671 memory: 6691 loss_kpt: 0.000667 acc_pose: 0.753449 loss: 0.000667 2022/09/22 17:38:21 - mmengine - INFO - Epoch(train) [141][100/293] lr: 5.000000e-04 eta: 2:44:12 time: 0.540058 data_time: 0.080059 memory: 6691 loss_kpt: 0.000681 acc_pose: 0.810231 loss: 0.000681 2022/09/22 17:38:48 - mmengine - INFO - Epoch(train) [141][150/293] lr: 5.000000e-04 eta: 2:43:50 time: 0.556054 data_time: 0.097751 memory: 6691 loss_kpt: 0.000666 acc_pose: 0.839275 loss: 0.000666 2022/09/22 17:39:17 - mmengine - INFO - Epoch(train) [141][200/293] lr: 5.000000e-04 eta: 2:43:28 time: 0.575397 data_time: 0.091941 memory: 6691 loss_kpt: 0.000667 acc_pose: 0.860098 loss: 0.000667 2022/09/22 17:39:46 - mmengine - INFO - Epoch(train) [141][250/293] lr: 5.000000e-04 eta: 2:43:06 time: 0.568728 data_time: 0.163291 memory: 6691 loss_kpt: 0.000653 acc_pose: 0.841098 loss: 0.000653 2022/09/22 17:40:09 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 17:40:38 - mmengine - INFO - Epoch(train) [142][50/293] lr: 5.000000e-04 eta: 2:42:13 time: 0.568960 data_time: 0.270621 memory: 6691 loss_kpt: 0.000663 acc_pose: 0.801066 loss: 0.000663 2022/09/22 17:41:05 - mmengine - INFO - Epoch(train) [142][100/293] lr: 5.000000e-04 eta: 2:41:50 time: 0.544364 data_time: 0.240490 memory: 6691 loss_kpt: 0.000656 acc_pose: 0.813160 loss: 0.000656 2022/09/22 17:41:33 - mmengine - INFO - Epoch(train) [142][150/293] lr: 5.000000e-04 eta: 2:41:28 time: 0.569634 data_time: 0.087757 memory: 6691 loss_kpt: 0.000662 acc_pose: 0.811095 loss: 0.000662 2022/09/22 17:42:01 - mmengine - INFO - Epoch(train) [142][200/293] lr: 5.000000e-04 eta: 2:41:06 time: 0.559106 data_time: 0.089426 memory: 6691 loss_kpt: 0.000668 acc_pose: 0.842570 loss: 0.000668 2022/09/22 17:42:29 - mmengine - INFO - Epoch(train) [142][250/293] lr: 5.000000e-04 eta: 2:40:44 time: 0.558069 data_time: 0.095077 memory: 6691 loss_kpt: 0.000663 acc_pose: 0.799569 loss: 0.000663 2022/09/22 17:42:53 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 17:43:22 - mmengine - INFO - Epoch(train) [143][50/293] lr: 5.000000e-04 eta: 2:39:51 time: 0.576484 data_time: 0.148717 memory: 6691 loss_kpt: 0.000667 acc_pose: 0.797649 loss: 0.000667 2022/09/22 17:43:49 - mmengine - INFO - Epoch(train) [143][100/293] lr: 5.000000e-04 eta: 2:39:28 time: 0.540631 data_time: 0.097956 memory: 6691 loss_kpt: 0.000673 acc_pose: 0.830992 loss: 0.000673 2022/09/22 17:44:17 - mmengine - INFO - Epoch(train) [143][150/293] lr: 5.000000e-04 eta: 2:39:06 time: 0.563727 data_time: 0.196441 memory: 6691 loss_kpt: 0.000663 acc_pose: 0.835325 loss: 0.000663 2022/09/22 17:44:45 - mmengine - INFO - Epoch(train) [143][200/293] lr: 5.000000e-04 eta: 2:38:44 time: 0.554736 data_time: 0.236096 memory: 6691 loss_kpt: 0.000666 acc_pose: 0.793484 loss: 0.000666 2022/09/22 17:45:13 - mmengine - INFO - Epoch(train) [143][250/293] lr: 5.000000e-04 eta: 2:38:22 time: 0.569186 data_time: 0.230521 memory: 6691 loss_kpt: 0.000662 acc_pose: 0.874449 loss: 0.000662 2022/09/22 17:45:38 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 17:46:07 - mmengine - INFO - Epoch(train) [144][50/293] lr: 5.000000e-04 eta: 2:37:29 time: 0.576154 data_time: 0.094465 memory: 6691 loss_kpt: 0.000664 acc_pose: 0.758630 loss: 0.000664 2022/09/22 17:46:35 - mmengine - INFO - Epoch(train) [144][100/293] lr: 5.000000e-04 eta: 2:37:07 time: 0.564789 data_time: 0.081823 memory: 6691 loss_kpt: 0.000666 acc_pose: 0.834613 loss: 0.000666 2022/09/22 17:46:35 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 17:47:03 - mmengine - INFO - Epoch(train) [144][150/293] lr: 5.000000e-04 eta: 2:36:45 time: 0.555389 data_time: 0.087326 memory: 6691 loss_kpt: 0.000662 acc_pose: 0.851529 loss: 0.000662 2022/09/22 17:47:31 - mmengine - INFO - Epoch(train) [144][200/293] lr: 5.000000e-04 eta: 2:36:22 time: 0.563793 data_time: 0.087338 memory: 6691 loss_kpt: 0.000671 acc_pose: 0.846665 loss: 0.000671 2022/09/22 17:47:59 - mmengine - INFO - Epoch(train) [144][250/293] lr: 5.000000e-04 eta: 2:36:00 time: 0.556568 data_time: 0.094697 memory: 6691 loss_kpt: 0.000660 acc_pose: 0.884455 loss: 0.000660 2022/09/22 17:48:23 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 17:48:52 - mmengine - INFO - Epoch(train) [145][50/293] lr: 5.000000e-04 eta: 2:35:08 time: 0.594068 data_time: 0.209890 memory: 6691 loss_kpt: 0.000664 acc_pose: 0.766980 loss: 0.000664 2022/09/22 17:49:19 - mmengine - INFO - Epoch(train) [145][100/293] lr: 5.000000e-04 eta: 2:34:45 time: 0.535204 data_time: 0.098343 memory: 6691 loss_kpt: 0.000650 acc_pose: 0.835275 loss: 0.000650 2022/09/22 17:49:47 - mmengine - INFO - Epoch(train) [145][150/293] lr: 5.000000e-04 eta: 2:34:23 time: 0.556638 data_time: 0.085961 memory: 6691 loss_kpt: 0.000666 acc_pose: 0.826818 loss: 0.000666 2022/09/22 17:50:15 - mmengine - INFO - Epoch(train) [145][200/293] lr: 5.000000e-04 eta: 2:34:00 time: 0.566633 data_time: 0.087464 memory: 6691 loss_kpt: 0.000652 acc_pose: 0.794807 loss: 0.000652 2022/09/22 17:50:42 - mmengine - INFO - Epoch(train) [145][250/293] lr: 5.000000e-04 eta: 2:33:37 time: 0.539283 data_time: 0.095480 memory: 6691 loss_kpt: 0.000658 acc_pose: 0.802821 loss: 0.000658 2022/09/22 17:51:06 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 17:51:35 - mmengine - INFO - Epoch(train) [146][50/293] lr: 5.000000e-04 eta: 2:32:45 time: 0.578553 data_time: 0.166422 memory: 6691 loss_kpt: 0.000659 acc_pose: 0.817615 loss: 0.000659 2022/09/22 17:52:03 - mmengine - INFO - Epoch(train) [146][100/293] lr: 5.000000e-04 eta: 2:32:23 time: 0.558937 data_time: 0.085881 memory: 6691 loss_kpt: 0.000669 acc_pose: 0.833835 loss: 0.000669 2022/09/22 17:52:31 - mmengine - INFO - Epoch(train) [146][150/293] lr: 5.000000e-04 eta: 2:32:01 time: 0.562624 data_time: 0.127183 memory: 6691 loss_kpt: 0.000666 acc_pose: 0.798477 loss: 0.000666 2022/09/22 17:52:58 - mmengine - INFO - Epoch(train) [146][200/293] lr: 5.000000e-04 eta: 2:31:38 time: 0.535992 data_time: 0.087101 memory: 6691 loss_kpt: 0.000656 acc_pose: 0.801244 loss: 0.000656 2022/09/22 17:53:26 - mmengine - INFO - Epoch(train) [146][250/293] lr: 5.000000e-04 eta: 2:31:15 time: 0.563608 data_time: 0.091850 memory: 6691 loss_kpt: 0.000662 acc_pose: 0.780399 loss: 0.000662 2022/09/22 17:53:50 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 17:54:19 - mmengine - INFO - Epoch(train) [147][50/293] lr: 5.000000e-04 eta: 2:30:23 time: 0.577302 data_time: 0.237187 memory: 6691 loss_kpt: 0.000654 acc_pose: 0.801995 loss: 0.000654 2022/09/22 17:54:48 - mmengine - INFO - Epoch(train) [147][100/293] lr: 5.000000e-04 eta: 2:30:01 time: 0.578887 data_time: 0.157588 memory: 6691 loss_kpt: 0.000664 acc_pose: 0.804921 loss: 0.000664 2022/09/22 17:55:16 - mmengine - INFO - Epoch(train) [147][150/293] lr: 5.000000e-04 eta: 2:29:39 time: 0.562766 data_time: 0.099959 memory: 6691 loss_kpt: 0.000656 acc_pose: 0.849617 loss: 0.000656 2022/09/22 17:55:45 - mmengine - INFO - Epoch(train) [147][200/293] lr: 5.000000e-04 eta: 2:29:17 time: 0.572723 data_time: 0.113481 memory: 6691 loss_kpt: 0.000655 acc_pose: 0.821506 loss: 0.000655 2022/09/22 17:55:57 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 17:56:13 - mmengine - INFO - Epoch(train) [147][250/293] lr: 5.000000e-04 eta: 2:28:54 time: 0.564786 data_time: 0.094593 memory: 6691 loss_kpt: 0.000660 acc_pose: 0.836512 loss: 0.000660 2022/09/22 17:56:36 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 17:57:05 - mmengine - INFO - Epoch(train) [148][50/293] lr: 5.000000e-04 eta: 2:28:03 time: 0.575912 data_time: 0.129191 memory: 6691 loss_kpt: 0.000654 acc_pose: 0.786201 loss: 0.000654 2022/09/22 17:57:33 - mmengine - INFO - Epoch(train) [148][100/293] lr: 5.000000e-04 eta: 2:27:40 time: 0.565702 data_time: 0.223281 memory: 6691 loss_kpt: 0.000676 acc_pose: 0.839185 loss: 0.000676 2022/09/22 17:58:00 - mmengine - INFO - Epoch(train) [148][150/293] lr: 5.000000e-04 eta: 2:27:17 time: 0.545144 data_time: 0.232779 memory: 6691 loss_kpt: 0.000663 acc_pose: 0.824793 loss: 0.000663 2022/09/22 17:58:28 - mmengine - INFO - Epoch(train) [148][200/293] lr: 5.000000e-04 eta: 2:26:55 time: 0.541244 data_time: 0.242145 memory: 6691 loss_kpt: 0.000670 acc_pose: 0.851184 loss: 0.000670 2022/09/22 17:58:56 - mmengine - INFO - Epoch(train) [148][250/293] lr: 5.000000e-04 eta: 2:26:32 time: 0.562591 data_time: 0.131995 memory: 6691 loss_kpt: 0.000652 acc_pose: 0.810840 loss: 0.000652 2022/09/22 17:59:20 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 17:59:50 - mmengine - INFO - Epoch(train) [149][50/293] lr: 5.000000e-04 eta: 2:25:41 time: 0.594206 data_time: 0.180030 memory: 6691 loss_kpt: 0.000655 acc_pose: 0.807177 loss: 0.000655 2022/09/22 18:00:19 - mmengine - INFO - Epoch(train) [149][100/293] lr: 5.000000e-04 eta: 2:25:19 time: 0.579110 data_time: 0.135116 memory: 6691 loss_kpt: 0.000666 acc_pose: 0.832464 loss: 0.000666 2022/09/22 18:00:47 - mmengine - INFO - Epoch(train) [149][150/293] lr: 5.000000e-04 eta: 2:24:56 time: 0.575352 data_time: 0.126936 memory: 6691 loss_kpt: 0.000671 acc_pose: 0.831629 loss: 0.000671 2022/09/22 18:01:15 - mmengine - INFO - Epoch(train) [149][200/293] lr: 5.000000e-04 eta: 2:24:34 time: 0.549133 data_time: 0.080925 memory: 6691 loss_kpt: 0.000661 acc_pose: 0.769857 loss: 0.000661 2022/09/22 18:01:43 - mmengine - INFO - Epoch(train) [149][250/293] lr: 5.000000e-04 eta: 2:24:11 time: 0.563507 data_time: 0.096690 memory: 6691 loss_kpt: 0.000651 acc_pose: 0.846126 loss: 0.000651 2022/09/22 18:02:06 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 18:02:34 - mmengine - INFO - Epoch(train) [150][50/293] lr: 5.000000e-04 eta: 2:23:20 time: 0.566756 data_time: 0.151601 memory: 6691 loss_kpt: 0.000673 acc_pose: 0.797797 loss: 0.000673 2022/09/22 18:03:02 - mmengine - INFO - Epoch(train) [150][100/293] lr: 5.000000e-04 eta: 2:22:57 time: 0.545624 data_time: 0.087336 memory: 6691 loss_kpt: 0.000660 acc_pose: 0.832809 loss: 0.000660 2022/09/22 18:03:29 - mmengine - INFO - Epoch(train) [150][150/293] lr: 5.000000e-04 eta: 2:22:34 time: 0.537803 data_time: 0.092181 memory: 6691 loss_kpt: 0.000652 acc_pose: 0.790582 loss: 0.000652 2022/09/22 18:03:56 - mmengine - INFO - Epoch(train) [150][200/293] lr: 5.000000e-04 eta: 2:22:11 time: 0.558920 data_time: 0.191332 memory: 6691 loss_kpt: 0.000670 acc_pose: 0.814040 loss: 0.000670 2022/09/22 18:04:25 - mmengine - INFO - Epoch(train) [150][250/293] lr: 5.000000e-04 eta: 2:21:49 time: 0.565645 data_time: 0.074412 memory: 6691 loss_kpt: 0.000659 acc_pose: 0.821309 loss: 0.000659 2022/09/22 18:04:49 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 18:04:49 - mmengine - INFO - Saving checkpoint at 150 epochs 2022/09/22 18:05:10 - mmengine - INFO - Epoch(val) [150][50/407] eta: 0:01:58 time: 0.330571 data_time: 0.188326 memory: 6691 2022/09/22 18:05:25 - mmengine - INFO - Epoch(val) [150][100/407] eta: 0:01:29 time: 0.292306 data_time: 0.165851 memory: 1014 2022/09/22 18:05:40 - mmengine - INFO - Epoch(val) [150][150/407] eta: 0:01:18 time: 0.306142 data_time: 0.164199 memory: 1014 2022/09/22 18:05:55 - mmengine - INFO - Epoch(val) [150][200/407] eta: 0:01:00 time: 0.290493 data_time: 0.159725 memory: 1014 2022/09/22 18:06:09 - mmengine - INFO - Epoch(val) [150][250/407] eta: 0:00:45 time: 0.291857 data_time: 0.163721 memory: 1014 2022/09/22 18:06:25 - mmengine - INFO - Epoch(val) [150][300/407] eta: 0:00:32 time: 0.306204 data_time: 0.182683 memory: 1014 2022/09/22 18:06:40 - mmengine - INFO - Epoch(val) [150][350/407] eta: 0:00:17 time: 0.315078 data_time: 0.184651 memory: 1014 2022/09/22 18:06:54 - mmengine - INFO - Epoch(val) [150][400/407] eta: 0:00:01 time: 0.268693 data_time: 0.155474 memory: 1014 2022/09/22 18:07:27 - mmengine - INFO - Evaluating CocoMetric... 2022/09/22 18:07:41 - mmengine - INFO - Epoch(val) [150][407/407] coco/AP: 0.700883 coco/AP .5: 0.892242 coco/AP .75: 0.776757 coco/AP (M): 0.661920 coco/AP (L): 0.769642 coco/AR: 0.758297 coco/AR .5: 0.930573 coco/AR .75: 0.827928 coco/AR (M): 0.713002 coco/AR (L): 0.822891 2022/09/22 18:07:41 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220922/res50_256/best_coco/AP_epoch_140.pth is removed 2022/09/22 18:07:43 - mmengine - INFO - The best checkpoint with 0.7009 coco/AP at 150 epoch is saved to best_coco/AP_epoch_150.pth. 2022/09/22 18:08:10 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 18:08:10 - mmengine - INFO - Epoch(train) [151][50/293] lr: 5.000000e-04 eta: 2:20:57 time: 0.542703 data_time: 0.260570 memory: 6691 loss_kpt: 0.000648 acc_pose: 0.860165 loss: 0.000648 2022/09/22 18:08:39 - mmengine - INFO - Epoch(train) [151][100/293] lr: 5.000000e-04 eta: 2:20:34 time: 0.569614 data_time: 0.241295 memory: 6691 loss_kpt: 0.000668 acc_pose: 0.827102 loss: 0.000668 2022/09/22 18:09:07 - mmengine - INFO - Epoch(train) [151][150/293] lr: 5.000000e-04 eta: 2:20:12 time: 0.567428 data_time: 0.173236 memory: 6691 loss_kpt: 0.000672 acc_pose: 0.846694 loss: 0.000672 2022/09/22 18:09:35 - mmengine - INFO - Epoch(train) [151][200/293] lr: 5.000000e-04 eta: 2:19:49 time: 0.560692 data_time: 0.078153 memory: 6691 loss_kpt: 0.000672 acc_pose: 0.806849 loss: 0.000672 2022/09/22 18:10:02 - mmengine - INFO - Epoch(train) [151][250/293] lr: 5.000000e-04 eta: 2:19:26 time: 0.549287 data_time: 0.081259 memory: 6691 loss_kpt: 0.000650 acc_pose: 0.825905 loss: 0.000650 2022/09/22 18:10:26 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 18:10:56 - mmengine - INFO - Epoch(train) [152][50/293] lr: 5.000000e-04 eta: 2:18:36 time: 0.599417 data_time: 0.156670 memory: 6691 loss_kpt: 0.000649 acc_pose: 0.869827 loss: 0.000649 2022/09/22 18:11:26 - mmengine - INFO - Epoch(train) [152][100/293] lr: 5.000000e-04 eta: 2:18:14 time: 0.606739 data_time: 0.228326 memory: 6691 loss_kpt: 0.000667 acc_pose: 0.802058 loss: 0.000667 2022/09/22 18:11:55 - mmengine - INFO - Epoch(train) [152][150/293] lr: 5.000000e-04 eta: 2:17:51 time: 0.566954 data_time: 0.099768 memory: 6691 loss_kpt: 0.000657 acc_pose: 0.793232 loss: 0.000657 2022/09/22 18:12:24 - mmengine - INFO - Epoch(train) [152][200/293] lr: 5.000000e-04 eta: 2:17:29 time: 0.582712 data_time: 0.120185 memory: 6691 loss_kpt: 0.000669 acc_pose: 0.819794 loss: 0.000669 2022/09/22 18:12:53 - mmengine - INFO - Epoch(train) [152][250/293] lr: 5.000000e-04 eta: 2:17:07 time: 0.574358 data_time: 0.080323 memory: 6691 loss_kpt: 0.000641 acc_pose: 0.829742 loss: 0.000641 2022/09/22 18:13:17 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 18:13:45 - mmengine - INFO - Epoch(train) [153][50/293] lr: 5.000000e-04 eta: 2:16:16 time: 0.573304 data_time: 0.136663 memory: 6691 loss_kpt: 0.000670 acc_pose: 0.812212 loss: 0.000670 2022/09/22 18:14:13 - mmengine - INFO - Epoch(train) [153][100/293] lr: 5.000000e-04 eta: 2:15:53 time: 0.563366 data_time: 0.197372 memory: 6691 loss_kpt: 0.000646 acc_pose: 0.825437 loss: 0.000646 2022/09/22 18:14:42 - mmengine - INFO - Epoch(train) [153][150/293] lr: 5.000000e-04 eta: 2:15:31 time: 0.569542 data_time: 0.164227 memory: 6691 loss_kpt: 0.000648 acc_pose: 0.792047 loss: 0.000648 2022/09/22 18:15:10 - mmengine - INFO - Epoch(train) [153][200/293] lr: 5.000000e-04 eta: 2:15:08 time: 0.570720 data_time: 0.110906 memory: 6691 loss_kpt: 0.000650 acc_pose: 0.818713 loss: 0.000650 2022/09/22 18:15:37 - mmengine - INFO - Epoch(train) [153][250/293] lr: 5.000000e-04 eta: 2:14:45 time: 0.537342 data_time: 0.086512 memory: 6691 loss_kpt: 0.000656 acc_pose: 0.804931 loss: 0.000656 2022/09/22 18:16:01 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 18:16:31 - mmengine - INFO - Epoch(train) [154][50/293] lr: 5.000000e-04 eta: 2:13:54 time: 0.586019 data_time: 0.216666 memory: 6691 loss_kpt: 0.000656 acc_pose: 0.843725 loss: 0.000656 2022/09/22 18:17:00 - mmengine - INFO - Epoch(train) [154][100/293] lr: 5.000000e-04 eta: 2:13:32 time: 0.578912 data_time: 0.202162 memory: 6691 loss_kpt: 0.000656 acc_pose: 0.807631 loss: 0.000656 2022/09/22 18:17:28 - mmengine - INFO - Epoch(train) [154][150/293] lr: 5.000000e-04 eta: 2:13:09 time: 0.559127 data_time: 0.094857 memory: 6691 loss_kpt: 0.000654 acc_pose: 0.840585 loss: 0.000654 2022/09/22 18:17:40 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 18:17:56 - mmengine - INFO - Epoch(train) [154][200/293] lr: 5.000000e-04 eta: 2:12:47 time: 0.570556 data_time: 0.138587 memory: 6691 loss_kpt: 0.000635 acc_pose: 0.865927 loss: 0.000635 2022/09/22 18:18:25 - mmengine - INFO - Epoch(train) [154][250/293] lr: 5.000000e-04 eta: 2:12:24 time: 0.576167 data_time: 0.110434 memory: 6691 loss_kpt: 0.000652 acc_pose: 0.818260 loss: 0.000652 2022/09/22 18:18:49 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 18:19:19 - mmengine - INFO - Epoch(train) [155][50/293] lr: 5.000000e-04 eta: 2:11:34 time: 0.585624 data_time: 0.189894 memory: 6691 loss_kpt: 0.000656 acc_pose: 0.789409 loss: 0.000656 2022/09/22 18:19:47 - mmengine - INFO - Epoch(train) [155][100/293] lr: 5.000000e-04 eta: 2:11:11 time: 0.572589 data_time: 0.218705 memory: 6691 loss_kpt: 0.000651 acc_pose: 0.813793 loss: 0.000651 2022/09/22 18:20:14 - mmengine - INFO - Epoch(train) [155][150/293] lr: 5.000000e-04 eta: 2:10:48 time: 0.540896 data_time: 0.088694 memory: 6691 loss_kpt: 0.000660 acc_pose: 0.763315 loss: 0.000660 2022/09/22 18:20:43 - mmengine - INFO - Epoch(train) [155][200/293] lr: 5.000000e-04 eta: 2:10:26 time: 0.572933 data_time: 0.096184 memory: 6691 loss_kpt: 0.000653 acc_pose: 0.851000 loss: 0.000653 2022/09/22 18:21:10 - mmengine - INFO - Epoch(train) [155][250/293] lr: 5.000000e-04 eta: 2:10:03 time: 0.547380 data_time: 0.078072 memory: 6691 loss_kpt: 0.000650 acc_pose: 0.813306 loss: 0.000650 2022/09/22 18:21:35 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 18:22:04 - mmengine - INFO - Epoch(train) [156][50/293] lr: 5.000000e-04 eta: 2:09:12 time: 0.587202 data_time: 0.170832 memory: 6691 loss_kpt: 0.000652 acc_pose: 0.838795 loss: 0.000652 2022/09/22 18:22:32 - mmengine - INFO - Epoch(train) [156][100/293] lr: 5.000000e-04 eta: 2:08:49 time: 0.559541 data_time: 0.221288 memory: 6691 loss_kpt: 0.000653 acc_pose: 0.788001 loss: 0.000653 2022/09/22 18:23:00 - mmengine - INFO - Epoch(train) [156][150/293] lr: 5.000000e-04 eta: 2:08:27 time: 0.557278 data_time: 0.122845 memory: 6691 loss_kpt: 0.000661 acc_pose: 0.831770 loss: 0.000661 2022/09/22 18:23:29 - mmengine - INFO - Epoch(train) [156][200/293] lr: 5.000000e-04 eta: 2:08:04 time: 0.571273 data_time: 0.098343 memory: 6691 loss_kpt: 0.000654 acc_pose: 0.852062 loss: 0.000654 2022/09/22 18:23:57 - mmengine - INFO - Epoch(train) [156][250/293] lr: 5.000000e-04 eta: 2:07:41 time: 0.560395 data_time: 0.099338 memory: 6691 loss_kpt: 0.000654 acc_pose: 0.835774 loss: 0.000654 2022/09/22 18:24:22 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 18:24:51 - mmengine - INFO - Epoch(train) [157][50/293] lr: 5.000000e-04 eta: 2:06:51 time: 0.577029 data_time: 0.114346 memory: 6691 loss_kpt: 0.000650 acc_pose: 0.841192 loss: 0.000650 2022/09/22 18:25:20 - mmengine - INFO - Epoch(train) [157][100/293] lr: 5.000000e-04 eta: 2:06:28 time: 0.577349 data_time: 0.179609 memory: 6691 loss_kpt: 0.000663 acc_pose: 0.827810 loss: 0.000663 2022/09/22 18:25:49 - mmengine - INFO - Epoch(train) [157][150/293] lr: 5.000000e-04 eta: 2:06:06 time: 0.568354 data_time: 0.180615 memory: 6691 loss_kpt: 0.000648 acc_pose: 0.833006 loss: 0.000648 2022/09/22 18:26:17 - mmengine - INFO - Epoch(train) [157][200/293] lr: 5.000000e-04 eta: 2:05:43 time: 0.566768 data_time: 0.142639 memory: 6691 loss_kpt: 0.000653 acc_pose: 0.805730 loss: 0.000653 2022/09/22 18:26:44 - mmengine - INFO - Epoch(train) [157][250/293] lr: 5.000000e-04 eta: 2:05:20 time: 0.547235 data_time: 0.096937 memory: 6691 loss_kpt: 0.000656 acc_pose: 0.846432 loss: 0.000656 2022/09/22 18:27:08 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 18:27:09 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 18:27:38 - mmengine - INFO - Epoch(train) [158][50/293] lr: 5.000000e-04 eta: 2:04:30 time: 0.588717 data_time: 0.124216 memory: 6691 loss_kpt: 0.000642 acc_pose: 0.799284 loss: 0.000642 2022/09/22 18:28:05 - mmengine - INFO - Epoch(train) [158][100/293] lr: 5.000000e-04 eta: 2:04:07 time: 0.542018 data_time: 0.089066 memory: 6691 loss_kpt: 0.000655 acc_pose: 0.785200 loss: 0.000655 2022/09/22 18:28:33 - mmengine - INFO - Epoch(train) [158][150/293] lr: 5.000000e-04 eta: 2:03:44 time: 0.554580 data_time: 0.089560 memory: 6691 loss_kpt: 0.000648 acc_pose: 0.815093 loss: 0.000648 2022/09/22 18:29:02 - mmengine - INFO - Epoch(train) [158][200/293] lr: 5.000000e-04 eta: 2:03:21 time: 0.572168 data_time: 0.122617 memory: 6691 loss_kpt: 0.000649 acc_pose: 0.811319 loss: 0.000649 2022/09/22 18:29:28 - mmengine - INFO - Epoch(train) [158][250/293] lr: 5.000000e-04 eta: 2:02:58 time: 0.534299 data_time: 0.082598 memory: 6691 loss_kpt: 0.000651 acc_pose: 0.846556 loss: 0.000651 2022/09/22 18:29:52 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 18:30:21 - mmengine - INFO - Epoch(train) [159][50/293] lr: 5.000000e-04 eta: 2:02:08 time: 0.581966 data_time: 0.157684 memory: 6691 loss_kpt: 0.000660 acc_pose: 0.811521 loss: 0.000660 2022/09/22 18:30:49 - mmengine - INFO - Epoch(train) [159][100/293] lr: 5.000000e-04 eta: 2:01:45 time: 0.550056 data_time: 0.094776 memory: 6691 loss_kpt: 0.000658 acc_pose: 0.858926 loss: 0.000658 2022/09/22 18:31:17 - mmengine - INFO - Epoch(train) [159][150/293] lr: 5.000000e-04 eta: 2:01:22 time: 0.571640 data_time: 0.180178 memory: 6691 loss_kpt: 0.000649 acc_pose: 0.875482 loss: 0.000649 2022/09/22 18:31:47 - mmengine - INFO - Epoch(train) [159][200/293] lr: 5.000000e-04 eta: 2:00:59 time: 0.584918 data_time: 0.298339 memory: 6691 loss_kpt: 0.000655 acc_pose: 0.832997 loss: 0.000655 2022/09/22 18:32:14 - mmengine - INFO - Epoch(train) [159][250/293] lr: 5.000000e-04 eta: 2:00:36 time: 0.546737 data_time: 0.109456 memory: 6691 loss_kpt: 0.000667 acc_pose: 0.826470 loss: 0.000667 2022/09/22 18:32:37 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 18:33:06 - mmengine - INFO - Epoch(train) [160][50/293] lr: 5.000000e-04 eta: 1:59:46 time: 0.585529 data_time: 0.194549 memory: 6691 loss_kpt: 0.000642 acc_pose: 0.819480 loss: 0.000642 2022/09/22 18:33:35 - mmengine - INFO - Epoch(train) [160][100/293] lr: 5.000000e-04 eta: 1:59:24 time: 0.585205 data_time: 0.105594 memory: 6691 loss_kpt: 0.000659 acc_pose: 0.818028 loss: 0.000659 2022/09/22 18:34:04 - mmengine - INFO - Epoch(train) [160][150/293] lr: 5.000000e-04 eta: 1:59:01 time: 0.569023 data_time: 0.092708 memory: 6691 loss_kpt: 0.000662 acc_pose: 0.841752 loss: 0.000662 2022/09/22 18:34:32 - mmengine - INFO - Epoch(train) [160][200/293] lr: 5.000000e-04 eta: 1:58:38 time: 0.556896 data_time: 0.112395 memory: 6691 loss_kpt: 0.000647 acc_pose: 0.851788 loss: 0.000647 2022/09/22 18:34:59 - mmengine - INFO - Epoch(train) [160][250/293] lr: 5.000000e-04 eta: 1:58:15 time: 0.557592 data_time: 0.110893 memory: 6691 loss_kpt: 0.000660 acc_pose: 0.788481 loss: 0.000660 2022/09/22 18:35:22 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 18:35:22 - mmengine - INFO - Saving checkpoint at 160 epochs 2022/09/22 18:35:45 - mmengine - INFO - Epoch(val) [160][50/407] eta: 0:01:53 time: 0.317991 data_time: 0.178896 memory: 6691 2022/09/22 18:36:00 - mmengine - INFO - Epoch(val) [160][100/407] eta: 0:01:33 time: 0.305377 data_time: 0.180653 memory: 1014 2022/09/22 18:36:15 - mmengine - INFO - Epoch(val) [160][150/407] eta: 0:01:16 time: 0.298310 data_time: 0.159046 memory: 1014 2022/09/22 18:36:30 - mmengine - INFO - Epoch(val) [160][200/407] eta: 0:01:01 time: 0.295732 data_time: 0.152732 memory: 1014 2022/09/22 18:36:45 - mmengine - INFO - Epoch(val) [160][250/407] eta: 0:00:48 time: 0.309522 data_time: 0.169119 memory: 1014 2022/09/22 18:37:01 - mmengine - INFO - Epoch(val) [160][300/407] eta: 0:00:32 time: 0.307863 data_time: 0.168354 memory: 1014 2022/09/22 18:37:17 - mmengine - INFO - Epoch(val) [160][350/407] eta: 0:00:18 time: 0.319427 data_time: 0.176958 memory: 1014 2022/09/22 18:37:28 - mmengine - INFO - Epoch(val) [160][400/407] eta: 0:00:01 time: 0.232140 data_time: 0.129453 memory: 1014 2022/09/22 18:38:01 - mmengine - INFO - Evaluating CocoMetric... 2022/09/22 18:38:15 - mmengine - INFO - Epoch(val) [160][407/407] coco/AP: 0.704036 coco/AP .5: 0.893857 coco/AP .75: 0.780405 coco/AP (M): 0.666431 coco/AP (L): 0.772960 coco/AR: 0.761555 coco/AR .5: 0.932147 coco/AR .75: 0.829188 coco/AR (M): 0.716116 coco/AR (L): 0.826310 2022/09/22 18:38:15 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220922/res50_256/best_coco/AP_epoch_150.pth is removed 2022/09/22 18:38:17 - mmengine - INFO - The best checkpoint with 0.7040 coco/AP at 160 epoch is saved to best_coco/AP_epoch_160.pth. 2022/09/22 18:38:45 - mmengine - INFO - Epoch(train) [161][50/293] lr: 5.000000e-04 eta: 1:57:25 time: 0.551125 data_time: 0.284898 memory: 6691 loss_kpt: 0.000650 acc_pose: 0.818266 loss: 0.000650 2022/09/22 18:39:14 - mmengine - INFO - Epoch(train) [161][100/293] lr: 5.000000e-04 eta: 1:57:02 time: 0.573085 data_time: 0.169498 memory: 6691 loss_kpt: 0.000655 acc_pose: 0.824723 loss: 0.000655 2022/09/22 18:39:24 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 18:39:42 - mmengine - INFO - Epoch(train) [161][150/293] lr: 5.000000e-04 eta: 1:56:39 time: 0.571583 data_time: 0.100002 memory: 6691 loss_kpt: 0.000653 acc_pose: 0.859851 loss: 0.000653 2022/09/22 18:40:10 - mmengine - INFO - Epoch(train) [161][200/293] lr: 5.000000e-04 eta: 1:56:16 time: 0.549218 data_time: 0.098573 memory: 6691 loss_kpt: 0.000652 acc_pose: 0.841438 loss: 0.000652 2022/09/22 18:40:37 - mmengine - INFO - Epoch(train) [161][250/293] lr: 5.000000e-04 eta: 1:55:53 time: 0.549935 data_time: 0.095034 memory: 6691 loss_kpt: 0.000661 acc_pose: 0.848197 loss: 0.000661 2022/09/22 18:41:01 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 18:41:30 - mmengine - INFO - Epoch(train) [162][50/293] lr: 5.000000e-04 eta: 1:55:04 time: 0.582926 data_time: 0.162207 memory: 6691 loss_kpt: 0.000660 acc_pose: 0.801621 loss: 0.000660 2022/09/22 18:41:58 - mmengine - INFO - Epoch(train) [162][100/293] lr: 5.000000e-04 eta: 1:54:41 time: 0.559148 data_time: 0.162027 memory: 6691 loss_kpt: 0.000650 acc_pose: 0.830451 loss: 0.000650 2022/09/22 18:42:25 - mmengine - INFO - Epoch(train) [162][150/293] lr: 5.000000e-04 eta: 1:54:17 time: 0.539634 data_time: 0.094221 memory: 6691 loss_kpt: 0.000649 acc_pose: 0.812686 loss: 0.000649 2022/09/22 18:42:54 - mmengine - INFO - Epoch(train) [162][200/293] lr: 5.000000e-04 eta: 1:53:54 time: 0.563505 data_time: 0.085454 memory: 6691 loss_kpt: 0.000649 acc_pose: 0.819826 loss: 0.000649 2022/09/22 18:43:20 - mmengine - INFO - Epoch(train) [162][250/293] lr: 5.000000e-04 eta: 1:53:31 time: 0.527289 data_time: 0.088234 memory: 6691 loss_kpt: 0.000650 acc_pose: 0.802559 loss: 0.000650 2022/09/22 18:43:44 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 18:44:14 - mmengine - INFO - Epoch(train) [163][50/293] lr: 5.000000e-04 eta: 1:52:41 time: 0.592959 data_time: 0.279006 memory: 6691 loss_kpt: 0.000650 acc_pose: 0.832239 loss: 0.000650 2022/09/22 18:44:43 - mmengine - INFO - Epoch(train) [163][100/293] lr: 5.000000e-04 eta: 1:52:19 time: 0.575652 data_time: 0.161909 memory: 6691 loss_kpt: 0.000643 acc_pose: 0.819585 loss: 0.000643 2022/09/22 18:45:11 - mmengine - INFO - Epoch(train) [163][150/293] lr: 5.000000e-04 eta: 1:51:56 time: 0.560814 data_time: 0.090952 memory: 6691 loss_kpt: 0.000645 acc_pose: 0.781560 loss: 0.000645 2022/09/22 18:45:39 - mmengine - INFO - Epoch(train) [163][200/293] lr: 5.000000e-04 eta: 1:51:33 time: 0.565336 data_time: 0.085695 memory: 6691 loss_kpt: 0.000655 acc_pose: 0.811709 loss: 0.000655 2022/09/22 18:46:07 - mmengine - INFO - Epoch(train) [163][250/293] lr: 5.000000e-04 eta: 1:51:10 time: 0.547874 data_time: 0.087343 memory: 6691 loss_kpt: 0.000649 acc_pose: 0.852920 loss: 0.000649 2022/09/22 18:46:30 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 18:46:59 - mmengine - INFO - Epoch(train) [164][50/293] lr: 5.000000e-04 eta: 1:50:20 time: 0.577735 data_time: 0.188611 memory: 6691 loss_kpt: 0.000651 acc_pose: 0.786966 loss: 0.000651 2022/09/22 18:47:28 - mmengine - INFO - Epoch(train) [164][100/293] lr: 5.000000e-04 eta: 1:49:57 time: 0.571774 data_time: 0.144963 memory: 6691 loss_kpt: 0.000644 acc_pose: 0.836878 loss: 0.000644 2022/09/22 18:47:56 - mmengine - INFO - Epoch(train) [164][150/293] lr: 5.000000e-04 eta: 1:49:34 time: 0.562301 data_time: 0.098491 memory: 6691 loss_kpt: 0.000642 acc_pose: 0.793697 loss: 0.000642 2022/09/22 18:48:25 - mmengine - INFO - Epoch(train) [164][200/293] lr: 5.000000e-04 eta: 1:49:12 time: 0.591686 data_time: 0.099463 memory: 6691 loss_kpt: 0.000649 acc_pose: 0.829411 loss: 0.000649 2022/09/22 18:48:48 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 18:48:53 - mmengine - INFO - Epoch(train) [164][250/293] lr: 5.000000e-04 eta: 1:48:49 time: 0.559531 data_time: 0.155580 memory: 6691 loss_kpt: 0.000657 acc_pose: 0.791788 loss: 0.000657 2022/09/22 18:49:17 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 18:49:46 - mmengine - INFO - Epoch(train) [165][50/293] lr: 5.000000e-04 eta: 1:47:59 time: 0.578252 data_time: 0.145134 memory: 6691 loss_kpt: 0.000646 acc_pose: 0.773919 loss: 0.000646 2022/09/22 18:50:15 - mmengine - INFO - Epoch(train) [165][100/293] lr: 5.000000e-04 eta: 1:47:36 time: 0.569591 data_time: 0.224112 memory: 6691 loss_kpt: 0.000656 acc_pose: 0.841000 loss: 0.000656 2022/09/22 18:50:43 - mmengine - INFO - Epoch(train) [165][150/293] lr: 5.000000e-04 eta: 1:47:13 time: 0.559379 data_time: 0.162317 memory: 6691 loss_kpt: 0.000650 acc_pose: 0.855491 loss: 0.000650 2022/09/22 18:51:10 - mmengine - INFO - Epoch(train) [165][200/293] lr: 5.000000e-04 eta: 1:46:50 time: 0.546808 data_time: 0.089742 memory: 6691 loss_kpt: 0.000646 acc_pose: 0.784148 loss: 0.000646 2022/09/22 18:51:38 - mmengine - INFO - Epoch(train) [165][250/293] lr: 5.000000e-04 eta: 1:46:27 time: 0.547820 data_time: 0.093546 memory: 6691 loss_kpt: 0.000671 acc_pose: 0.788034 loss: 0.000671 2022/09/22 18:52:01 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 18:52:29 - mmengine - INFO - Epoch(train) [166][50/293] lr: 5.000000e-04 eta: 1:45:37 time: 0.559869 data_time: 0.095714 memory: 6691 loss_kpt: 0.000645 acc_pose: 0.780681 loss: 0.000645 2022/09/22 18:52:57 - mmengine - INFO - Epoch(train) [166][100/293] lr: 5.000000e-04 eta: 1:45:14 time: 0.559166 data_time: 0.101864 memory: 6691 loss_kpt: 0.000650 acc_pose: 0.835383 loss: 0.000650 2022/09/22 18:53:25 - mmengine - INFO - Epoch(train) [166][150/293] lr: 5.000000e-04 eta: 1:44:51 time: 0.548096 data_time: 0.100895 memory: 6691 loss_kpt: 0.000653 acc_pose: 0.828112 loss: 0.000653 2022/09/22 18:53:52 - mmengine - INFO - Epoch(train) [166][200/293] lr: 5.000000e-04 eta: 1:44:28 time: 0.542086 data_time: 0.099277 memory: 6691 loss_kpt: 0.000649 acc_pose: 0.812783 loss: 0.000649 2022/09/22 18:54:20 - mmengine - INFO - Epoch(train) [166][250/293] lr: 5.000000e-04 eta: 1:44:04 time: 0.555784 data_time: 0.087740 memory: 6691 loss_kpt: 0.000655 acc_pose: 0.832145 loss: 0.000655 2022/09/22 18:54:45 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 18:55:14 - mmengine - INFO - Epoch(train) [167][50/293] lr: 5.000000e-04 eta: 1:43:15 time: 0.578673 data_time: 0.155680 memory: 6691 loss_kpt: 0.000656 acc_pose: 0.831656 loss: 0.000656 2022/09/22 18:55:42 - mmengine - INFO - Epoch(train) [167][100/293] lr: 5.000000e-04 eta: 1:42:52 time: 0.573575 data_time: 0.265580 memory: 6691 loss_kpt: 0.000650 acc_pose: 0.824214 loss: 0.000650 2022/09/22 18:56:10 - mmengine - INFO - Epoch(train) [167][150/293] lr: 5.000000e-04 eta: 1:42:29 time: 0.547089 data_time: 0.144394 memory: 6691 loss_kpt: 0.000651 acc_pose: 0.855499 loss: 0.000651 2022/09/22 18:56:38 - mmengine - INFO - Epoch(train) [167][200/293] lr: 5.000000e-04 eta: 1:42:06 time: 0.570122 data_time: 0.281754 memory: 6691 loss_kpt: 0.000647 acc_pose: 0.790912 loss: 0.000647 2022/09/22 18:57:07 - mmengine - INFO - Epoch(train) [167][250/293] lr: 5.000000e-04 eta: 1:41:43 time: 0.568726 data_time: 0.185440 memory: 6691 loss_kpt: 0.000643 acc_pose: 0.812940 loss: 0.000643 2022/09/22 18:57:31 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 18:58:00 - mmengine - INFO - Epoch(train) [168][50/293] lr: 5.000000e-04 eta: 1:40:54 time: 0.583838 data_time: 0.134728 memory: 6691 loss_kpt: 0.000640 acc_pose: 0.817719 loss: 0.000640 2022/09/22 18:58:11 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 18:58:28 - mmengine - INFO - Epoch(train) [168][100/293] lr: 5.000000e-04 eta: 1:40:31 time: 0.566953 data_time: 0.153106 memory: 6691 loss_kpt: 0.000652 acc_pose: 0.760609 loss: 0.000652 2022/09/22 18:58:56 - mmengine - INFO - Epoch(train) [168][150/293] lr: 5.000000e-04 eta: 1:40:08 time: 0.557326 data_time: 0.087566 memory: 6691 loss_kpt: 0.000648 acc_pose: 0.803652 loss: 0.000648 2022/09/22 18:59:25 - mmengine - INFO - Epoch(train) [168][200/293] lr: 5.000000e-04 eta: 1:39:45 time: 0.572306 data_time: 0.097938 memory: 6691 loss_kpt: 0.000650 acc_pose: 0.847350 loss: 0.000650 2022/09/22 18:59:53 - mmengine - INFO - Epoch(train) [168][250/293] lr: 5.000000e-04 eta: 1:39:22 time: 0.565635 data_time: 0.121314 memory: 6691 loss_kpt: 0.000656 acc_pose: 0.832423 loss: 0.000656 2022/09/22 19:00:17 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 19:00:47 - mmengine - INFO - Epoch(train) [169][50/293] lr: 5.000000e-04 eta: 1:38:33 time: 0.598332 data_time: 0.212259 memory: 6691 loss_kpt: 0.000654 acc_pose: 0.835244 loss: 0.000654 2022/09/22 19:01:14 - mmengine - INFO - Epoch(train) [169][100/293] lr: 5.000000e-04 eta: 1:38:10 time: 0.540652 data_time: 0.148727 memory: 6691 loss_kpt: 0.000647 acc_pose: 0.831100 loss: 0.000647 2022/09/22 19:01:42 - mmengine - INFO - Epoch(train) [169][150/293] lr: 5.000000e-04 eta: 1:37:47 time: 0.560835 data_time: 0.205107 memory: 6691 loss_kpt: 0.000638 acc_pose: 0.786088 loss: 0.000638 2022/09/22 19:02:10 - mmengine - INFO - Epoch(train) [169][200/293] lr: 5.000000e-04 eta: 1:37:23 time: 0.557495 data_time: 0.098176 memory: 6691 loss_kpt: 0.000640 acc_pose: 0.848612 loss: 0.000640 2022/09/22 19:02:39 - mmengine - INFO - Epoch(train) [169][250/293] lr: 5.000000e-04 eta: 1:37:00 time: 0.570489 data_time: 0.106282 memory: 6691 loss_kpt: 0.000650 acc_pose: 0.840206 loss: 0.000650 2022/09/22 19:03:02 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 19:03:32 - mmengine - INFO - Epoch(train) [170][50/293] lr: 5.000000e-04 eta: 1:36:12 time: 0.587733 data_time: 0.206014 memory: 6691 loss_kpt: 0.000641 acc_pose: 0.829539 loss: 0.000641 2022/09/22 19:04:01 - mmengine - INFO - Epoch(train) [170][100/293] lr: 5.000000e-04 eta: 1:35:49 time: 0.583780 data_time: 0.183523 memory: 6691 loss_kpt: 0.000648 acc_pose: 0.833152 loss: 0.000648 2022/09/22 19:04:30 - mmengine - INFO - Epoch(train) [170][150/293] lr: 5.000000e-04 eta: 1:35:26 time: 0.580206 data_time: 0.123514 memory: 6691 loss_kpt: 0.000650 acc_pose: 0.797590 loss: 0.000650 2022/09/22 19:04:58 - mmengine - INFO - Epoch(train) [170][200/293] lr: 5.000000e-04 eta: 1:35:03 time: 0.556796 data_time: 0.101288 memory: 6691 loss_kpt: 0.000641 acc_pose: 0.835057 loss: 0.000641 2022/09/22 19:05:26 - mmengine - INFO - Epoch(train) [170][250/293] lr: 5.000000e-04 eta: 1:34:39 time: 0.552831 data_time: 0.235194 memory: 6691 loss_kpt: 0.000647 acc_pose: 0.775817 loss: 0.000647 2022/09/22 19:05:50 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 19:05:50 - mmengine - INFO - Saving checkpoint at 170 epochs 2022/09/22 19:06:12 - mmengine - INFO - Epoch(val) [170][50/407] eta: 0:01:54 time: 0.321498 data_time: 0.172351 memory: 6691 2022/09/22 19:06:28 - mmengine - INFO - Epoch(val) [170][100/407] eta: 0:01:38 time: 0.321772 data_time: 0.163060 memory: 1014 2022/09/22 19:06:44 - mmengine - INFO - Epoch(val) [170][150/407] eta: 0:01:21 time: 0.317119 data_time: 0.153065 memory: 1014 2022/09/22 19:06:59 - mmengine - INFO - Epoch(val) [170][200/407] eta: 0:01:00 time: 0.294390 data_time: 0.154640 memory: 1014 2022/09/22 19:07:14 - mmengine - INFO - Epoch(val) [170][250/407] eta: 0:00:48 time: 0.310177 data_time: 0.183150 memory: 1014 2022/09/22 19:07:30 - mmengine - INFO - Epoch(val) [170][300/407] eta: 0:00:33 time: 0.310427 data_time: 0.191004 memory: 1014 2022/09/22 19:07:46 - mmengine - INFO - Epoch(val) [170][350/407] eta: 0:00:18 time: 0.328606 data_time: 0.188958 memory: 1014 2022/09/22 19:07:57 - mmengine - INFO - Epoch(val) [170][400/407] eta: 0:00:01 time: 0.208024 data_time: 0.124487 memory: 1014 2022/09/22 19:08:29 - mmengine - INFO - Evaluating CocoMetric... 2022/09/22 19:08:43 - mmengine - INFO - Epoch(val) [170][407/407] coco/AP: 0.705077 coco/AP .5: 0.890964 coco/AP .75: 0.784345 coco/AP (M): 0.665906 coco/AP (L): 0.773430 coco/AR: 0.762185 coco/AR .5: 0.929943 coco/AR .75: 0.833753 coco/AR (M): 0.717427 coco/AR (L): 0.826124 2022/09/22 19:08:43 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220922/res50_256/best_coco/AP_epoch_160.pth is removed 2022/09/22 19:08:45 - mmengine - INFO - The best checkpoint with 0.7051 coco/AP at 170 epoch is saved to best_coco/AP_epoch_170.pth. 2022/09/22 19:09:13 - mmengine - INFO - Epoch(train) [171][50/293] lr: 5.000000e-05 eta: 1:33:50 time: 0.561603 data_time: 0.250260 memory: 6691 loss_kpt: 0.000633 acc_pose: 0.796316 loss: 0.000633 2022/09/22 19:09:41 - mmengine - INFO - Epoch(train) [171][100/293] lr: 5.000000e-05 eta: 1:33:27 time: 0.563778 data_time: 0.087263 memory: 6691 loss_kpt: 0.000639 acc_pose: 0.847857 loss: 0.000639 2022/09/22 19:10:10 - mmengine - INFO - Epoch(train) [171][150/293] lr: 5.000000e-05 eta: 1:33:04 time: 0.574699 data_time: 0.096092 memory: 6691 loss_kpt: 0.000631 acc_pose: 0.793239 loss: 0.000631 2022/09/22 19:10:31 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 19:10:37 - mmengine - INFO - Epoch(train) [171][200/293] lr: 5.000000e-05 eta: 1:32:41 time: 0.537661 data_time: 0.074153 memory: 6691 loss_kpt: 0.000634 acc_pose: 0.839683 loss: 0.000634 2022/09/22 19:11:04 - mmengine - INFO - Epoch(train) [171][250/293] lr: 5.000000e-05 eta: 1:32:17 time: 0.548762 data_time: 0.078782 memory: 6691 loss_kpt: 0.000630 acc_pose: 0.875685 loss: 0.000630 2022/09/22 19:11:28 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 19:11:58 - mmengine - INFO - Epoch(train) [172][50/293] lr: 5.000000e-05 eta: 1:31:29 time: 0.588637 data_time: 0.205327 memory: 6691 loss_kpt: 0.000633 acc_pose: 0.834590 loss: 0.000633 2022/09/22 19:12:26 - mmengine - INFO - Epoch(train) [172][100/293] lr: 5.000000e-05 eta: 1:31:06 time: 0.570981 data_time: 0.267190 memory: 6691 loss_kpt: 0.000628 acc_pose: 0.816288 loss: 0.000628 2022/09/22 19:12:55 - mmengine - INFO - Epoch(train) [172][150/293] lr: 5.000000e-05 eta: 1:30:43 time: 0.564579 data_time: 0.148560 memory: 6691 loss_kpt: 0.000603 acc_pose: 0.801975 loss: 0.000603 2022/09/22 19:13:23 - mmengine - INFO - Epoch(train) [172][200/293] lr: 5.000000e-05 eta: 1:30:19 time: 0.559064 data_time: 0.146280 memory: 6691 loss_kpt: 0.000623 acc_pose: 0.863089 loss: 0.000623 2022/09/22 19:13:52 - mmengine - INFO - Epoch(train) [172][250/293] lr: 5.000000e-05 eta: 1:29:56 time: 0.578855 data_time: 0.109371 memory: 6691 loss_kpt: 0.000629 acc_pose: 0.800472 loss: 0.000629 2022/09/22 19:14:16 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 19:14:45 - mmengine - INFO - Epoch(train) [173][50/293] lr: 5.000000e-05 eta: 1:29:08 time: 0.575354 data_time: 0.142868 memory: 6691 loss_kpt: 0.000642 acc_pose: 0.821375 loss: 0.000642 2022/09/22 19:15:12 - mmengine - INFO - Epoch(train) [173][100/293] lr: 5.000000e-05 eta: 1:28:44 time: 0.557344 data_time: 0.270699 memory: 6691 loss_kpt: 0.000627 acc_pose: 0.844596 loss: 0.000627 2022/09/22 19:15:41 - mmengine - INFO - Epoch(train) [173][150/293] lr: 5.000000e-05 eta: 1:28:21 time: 0.569380 data_time: 0.139428 memory: 6691 loss_kpt: 0.000619 acc_pose: 0.856464 loss: 0.000619 2022/09/22 19:16:10 - mmengine - INFO - Epoch(train) [173][200/293] lr: 5.000000e-05 eta: 1:27:58 time: 0.582166 data_time: 0.098060 memory: 6691 loss_kpt: 0.000638 acc_pose: 0.860127 loss: 0.000638 2022/09/22 19:16:39 - mmengine - INFO - Epoch(train) [173][250/293] lr: 5.000000e-05 eta: 1:27:35 time: 0.568922 data_time: 0.104802 memory: 6691 loss_kpt: 0.000625 acc_pose: 0.854800 loss: 0.000625 2022/09/22 19:17:01 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 19:17:30 - mmengine - INFO - Epoch(train) [174][50/293] lr: 5.000000e-05 eta: 1:26:47 time: 0.576966 data_time: 0.097226 memory: 6691 loss_kpt: 0.000612 acc_pose: 0.841754 loss: 0.000612 2022/09/22 19:17:59 - mmengine - INFO - Epoch(train) [174][100/293] lr: 5.000000e-05 eta: 1:26:23 time: 0.569869 data_time: 0.126525 memory: 6691 loss_kpt: 0.000622 acc_pose: 0.854835 loss: 0.000622 2022/09/22 19:18:27 - mmengine - INFO - Epoch(train) [174][150/293] lr: 5.000000e-05 eta: 1:26:00 time: 0.561600 data_time: 0.093842 memory: 6691 loss_kpt: 0.000630 acc_pose: 0.833179 loss: 0.000630 2022/09/22 19:18:54 - mmengine - INFO - Epoch(train) [174][200/293] lr: 5.000000e-05 eta: 1:25:37 time: 0.540743 data_time: 0.099773 memory: 6691 loss_kpt: 0.000622 acc_pose: 0.801647 loss: 0.000622 2022/09/22 19:19:23 - mmengine - INFO - Epoch(train) [174][250/293] lr: 5.000000e-05 eta: 1:25:13 time: 0.575947 data_time: 0.314900 memory: 6691 loss_kpt: 0.000626 acc_pose: 0.851448 loss: 0.000626 2022/09/22 19:19:47 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 19:19:59 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 19:20:17 - mmengine - INFO - Epoch(train) [175][50/293] lr: 5.000000e-05 eta: 1:24:25 time: 0.591199 data_time: 0.127630 memory: 6691 loss_kpt: 0.000615 acc_pose: 0.829386 loss: 0.000615 2022/09/22 19:20:45 - mmengine - INFO - Epoch(train) [175][100/293] lr: 5.000000e-05 eta: 1:24:02 time: 0.568429 data_time: 0.147263 memory: 6691 loss_kpt: 0.000620 acc_pose: 0.826063 loss: 0.000620 2022/09/22 19:21:13 - mmengine - INFO - Epoch(train) [175][150/293] lr: 5.000000e-05 eta: 1:23:39 time: 0.556519 data_time: 0.097970 memory: 6691 loss_kpt: 0.000600 acc_pose: 0.821897 loss: 0.000600 2022/09/22 19:21:43 - mmengine - INFO - Epoch(train) [175][200/293] lr: 5.000000e-05 eta: 1:23:16 time: 0.590497 data_time: 0.149544 memory: 6691 loss_kpt: 0.000613 acc_pose: 0.787499 loss: 0.000613 2022/09/22 19:22:11 - mmengine - INFO - Epoch(train) [175][250/293] lr: 5.000000e-05 eta: 1:22:52 time: 0.572088 data_time: 0.153684 memory: 6691 loss_kpt: 0.000605 acc_pose: 0.845580 loss: 0.000605 2022/09/22 19:22:36 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 19:23:05 - mmengine - INFO - Epoch(train) [176][50/293] lr: 5.000000e-05 eta: 1:22:04 time: 0.577637 data_time: 0.215866 memory: 6691 loss_kpt: 0.000610 acc_pose: 0.826544 loss: 0.000610 2022/09/22 19:23:34 - mmengine - INFO - Epoch(train) [176][100/293] lr: 5.000000e-05 eta: 1:21:41 time: 0.579688 data_time: 0.154630 memory: 6691 loss_kpt: 0.000614 acc_pose: 0.820182 loss: 0.000614 2022/09/22 19:24:02 - mmengine - INFO - Epoch(train) [176][150/293] lr: 5.000000e-05 eta: 1:21:18 time: 0.559839 data_time: 0.212516 memory: 6691 loss_kpt: 0.000624 acc_pose: 0.857516 loss: 0.000624 2022/09/22 19:24:30 - mmengine - INFO - Epoch(train) [176][200/293] lr: 5.000000e-05 eta: 1:20:55 time: 0.570391 data_time: 0.138439 memory: 6691 loss_kpt: 0.000621 acc_pose: 0.849713 loss: 0.000621 2022/09/22 19:24:58 - mmengine - INFO - Epoch(train) [176][250/293] lr: 5.000000e-05 eta: 1:20:31 time: 0.557925 data_time: 0.135464 memory: 6691 loss_kpt: 0.000626 acc_pose: 0.822036 loss: 0.000626 2022/09/22 19:25:22 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 19:25:50 - mmengine - INFO - Epoch(train) [177][50/293] lr: 5.000000e-05 eta: 1:19:43 time: 0.570172 data_time: 0.164060 memory: 6691 loss_kpt: 0.000611 acc_pose: 0.848581 loss: 0.000611 2022/09/22 19:26:19 - mmengine - INFO - Epoch(train) [177][100/293] lr: 5.000000e-05 eta: 1:19:20 time: 0.573029 data_time: 0.184152 memory: 6691 loss_kpt: 0.000600 acc_pose: 0.769463 loss: 0.000600 2022/09/22 19:26:47 - mmengine - INFO - Epoch(train) [177][150/293] lr: 5.000000e-05 eta: 1:18:56 time: 0.556088 data_time: 0.193103 memory: 6691 loss_kpt: 0.000619 acc_pose: 0.787857 loss: 0.000619 2022/09/22 19:27:14 - mmengine - INFO - Epoch(train) [177][200/293] lr: 5.000000e-05 eta: 1:18:33 time: 0.551471 data_time: 0.231402 memory: 6691 loss_kpt: 0.000627 acc_pose: 0.808949 loss: 0.000627 2022/09/22 19:27:42 - mmengine - INFO - Epoch(train) [177][250/293] lr: 5.000000e-05 eta: 1:18:09 time: 0.547915 data_time: 0.257037 memory: 6691 loss_kpt: 0.000617 acc_pose: 0.840305 loss: 0.000617 2022/09/22 19:28:04 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 19:28:33 - mmengine - INFO - Epoch(train) [178][50/293] lr: 5.000000e-05 eta: 1:17:21 time: 0.564937 data_time: 0.164750 memory: 6691 loss_kpt: 0.000612 acc_pose: 0.844196 loss: 0.000612 2022/09/22 19:29:01 - mmengine - INFO - Epoch(train) [178][100/293] lr: 5.000000e-05 eta: 1:16:58 time: 0.558530 data_time: 0.074434 memory: 6691 loss_kpt: 0.000625 acc_pose: 0.819374 loss: 0.000625 2022/09/22 19:29:22 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 19:29:29 - mmengine - INFO - Epoch(train) [178][150/293] lr: 5.000000e-05 eta: 1:16:34 time: 0.560162 data_time: 0.099777 memory: 6691 loss_kpt: 0.000608 acc_pose: 0.820703 loss: 0.000608 2022/09/22 19:29:57 - mmengine - INFO - Epoch(train) [178][200/293] lr: 5.000000e-05 eta: 1:16:11 time: 0.562184 data_time: 0.092663 memory: 6691 loss_kpt: 0.000624 acc_pose: 0.811642 loss: 0.000624 2022/09/22 19:30:25 - mmengine - INFO - Epoch(train) [178][250/293] lr: 5.000000e-05 eta: 1:15:48 time: 0.555169 data_time: 0.073902 memory: 6691 loss_kpt: 0.000618 acc_pose: 0.798361 loss: 0.000618 2022/09/22 19:30:49 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 19:31:18 - mmengine - INFO - Epoch(train) [179][50/293] lr: 5.000000e-05 eta: 1:15:00 time: 0.586470 data_time: 0.122916 memory: 6691 loss_kpt: 0.000606 acc_pose: 0.794550 loss: 0.000606 2022/09/22 19:31:46 - mmengine - INFO - Epoch(train) [179][100/293] lr: 5.000000e-05 eta: 1:14:36 time: 0.562870 data_time: 0.120609 memory: 6691 loss_kpt: 0.000610 acc_pose: 0.857826 loss: 0.000610 2022/09/22 19:32:14 - mmengine - INFO - Epoch(train) [179][150/293] lr: 5.000000e-05 eta: 1:14:13 time: 0.564736 data_time: 0.160167 memory: 6691 loss_kpt: 0.000621 acc_pose: 0.818690 loss: 0.000621 2022/09/22 19:32:42 - mmengine - INFO - Epoch(train) [179][200/293] lr: 5.000000e-05 eta: 1:13:50 time: 0.552960 data_time: 0.085733 memory: 6691 loss_kpt: 0.000603 acc_pose: 0.830533 loss: 0.000603 2022/09/22 19:33:11 - mmengine - INFO - Epoch(train) [179][250/293] lr: 5.000000e-05 eta: 1:13:26 time: 0.580153 data_time: 0.200689 memory: 6691 loss_kpt: 0.000608 acc_pose: 0.821200 loss: 0.000608 2022/09/22 19:33:35 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 19:34:05 - mmengine - INFO - Epoch(train) [180][50/293] lr: 5.000000e-05 eta: 1:12:39 time: 0.596587 data_time: 0.136335 memory: 6691 loss_kpt: 0.000609 acc_pose: 0.819384 loss: 0.000609 2022/09/22 19:34:34 - mmengine - INFO - Epoch(train) [180][100/293] lr: 5.000000e-05 eta: 1:12:15 time: 0.567612 data_time: 0.122860 memory: 6691 loss_kpt: 0.000603 acc_pose: 0.869272 loss: 0.000603 2022/09/22 19:35:02 - mmengine - INFO - Epoch(train) [180][150/293] lr: 5.000000e-05 eta: 1:11:52 time: 0.571180 data_time: 0.153837 memory: 6691 loss_kpt: 0.000603 acc_pose: 0.868656 loss: 0.000603 2022/09/22 19:35:30 - mmengine - INFO - Epoch(train) [180][200/293] lr: 5.000000e-05 eta: 1:11:28 time: 0.550173 data_time: 0.094464 memory: 6691 loss_kpt: 0.000629 acc_pose: 0.821269 loss: 0.000629 2022/09/22 19:35:57 - mmengine - INFO - Epoch(train) [180][250/293] lr: 5.000000e-05 eta: 1:11:05 time: 0.555544 data_time: 0.075837 memory: 6691 loss_kpt: 0.000622 acc_pose: 0.842500 loss: 0.000622 2022/09/22 19:36:22 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 19:36:22 - mmengine - INFO - Saving checkpoint at 180 epochs 2022/09/22 19:36:44 - mmengine - INFO - Epoch(val) [180][50/407] eta: 0:01:58 time: 0.331913 data_time: 0.204953 memory: 6691 2022/09/22 19:37:00 - mmengine - INFO - Epoch(val) [180][100/407] eta: 0:01:35 time: 0.311726 data_time: 0.166707 memory: 1014 2022/09/22 19:37:15 - mmengine - INFO - Epoch(val) [180][150/407] eta: 0:01:18 time: 0.304614 data_time: 0.171091 memory: 1014 2022/09/22 19:37:30 - mmengine - INFO - Epoch(val) [180][200/407] eta: 0:01:04 time: 0.311357 data_time: 0.173223 memory: 1014 2022/09/22 19:37:46 - mmengine - INFO - Epoch(val) [180][250/407] eta: 0:00:48 time: 0.310024 data_time: 0.178618 memory: 1014 2022/09/22 19:38:02 - mmengine - INFO - Epoch(val) [180][300/407] eta: 0:00:33 time: 0.316565 data_time: 0.193660 memory: 1014 2022/09/22 19:38:17 - mmengine - INFO - Epoch(val) [180][350/407] eta: 0:00:17 time: 0.311521 data_time: 0.170673 memory: 1014 2022/09/22 19:38:29 - mmengine - INFO - Epoch(val) [180][400/407] eta: 0:00:01 time: 0.236056 data_time: 0.140737 memory: 1014 2022/09/22 19:39:02 - mmengine - INFO - Evaluating CocoMetric... 2022/09/22 19:39:15 - mmengine - INFO - Epoch(val) [180][407/407] coco/AP: 0.715307 coco/AP .5: 0.897876 coco/AP .75: 0.794518 coco/AP (M): 0.676762 coco/AP (L): 0.783660 coco/AR: 0.770513 coco/AR .5: 0.935139 coco/AR .75: 0.840995 coco/AR (M): 0.726386 coco/AR (L): 0.834077 2022/09/22 19:39:15 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220922/res50_256/best_coco/AP_epoch_170.pth is removed 2022/09/22 19:39:17 - mmengine - INFO - The best checkpoint with 0.7153 coco/AP at 180 epoch is saved to best_coco/AP_epoch_180.pth. 2022/09/22 19:39:46 - mmengine - INFO - Epoch(train) [181][50/293] lr: 5.000000e-05 eta: 1:10:17 time: 0.562219 data_time: 0.240360 memory: 6691 loss_kpt: 0.000609 acc_pose: 0.865213 loss: 0.000609 2022/09/22 19:40:14 - mmengine - INFO - Epoch(train) [181][100/293] lr: 5.000000e-05 eta: 1:09:54 time: 0.573875 data_time: 0.255944 memory: 6691 loss_kpt: 0.000615 acc_pose: 0.852712 loss: 0.000615 2022/09/22 19:40:43 - mmengine - INFO - Epoch(train) [181][150/293] lr: 5.000000e-05 eta: 1:09:30 time: 0.569361 data_time: 0.161420 memory: 6691 loss_kpt: 0.000617 acc_pose: 0.842855 loss: 0.000617 2022/09/22 19:41:11 - mmengine - INFO - Epoch(train) [181][200/293] lr: 5.000000e-05 eta: 1:09:07 time: 0.567523 data_time: 0.139393 memory: 6691 loss_kpt: 0.000605 acc_pose: 0.826089 loss: 0.000605 2022/09/22 19:41:39 - mmengine - INFO - Epoch(train) [181][250/293] lr: 5.000000e-05 eta: 1:08:43 time: 0.558523 data_time: 0.097404 memory: 6691 loss_kpt: 0.000601 acc_pose: 0.882871 loss: 0.000601 2022/09/22 19:41:45 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 19:42:03 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 19:42:33 - mmengine - INFO - Epoch(train) [182][50/293] lr: 5.000000e-05 eta: 1:07:56 time: 0.595092 data_time: 0.122972 memory: 6691 loss_kpt: 0.000610 acc_pose: 0.842028 loss: 0.000610 2022/09/22 19:43:00 - mmengine - INFO - Epoch(train) [182][100/293] lr: 5.000000e-05 eta: 1:07:32 time: 0.536559 data_time: 0.079507 memory: 6691 loss_kpt: 0.000609 acc_pose: 0.881605 loss: 0.000609 2022/09/22 19:43:28 - mmengine - INFO - Epoch(train) [182][150/293] lr: 5.000000e-05 eta: 1:07:09 time: 0.554941 data_time: 0.079976 memory: 6691 loss_kpt: 0.000600 acc_pose: 0.844061 loss: 0.000600 2022/09/22 19:43:56 - mmengine - INFO - Epoch(train) [182][200/293] lr: 5.000000e-05 eta: 1:06:45 time: 0.562091 data_time: 0.100470 memory: 6691 loss_kpt: 0.000606 acc_pose: 0.850844 loss: 0.000606 2022/09/22 19:44:24 - mmengine - INFO - Epoch(train) [182][250/293] lr: 5.000000e-05 eta: 1:06:22 time: 0.564209 data_time: 0.089931 memory: 6691 loss_kpt: 0.000609 acc_pose: 0.884994 loss: 0.000609 2022/09/22 19:44:48 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 19:45:17 - mmengine - INFO - Epoch(train) [183][50/293] lr: 5.000000e-05 eta: 1:05:34 time: 0.579235 data_time: 0.217979 memory: 6691 loss_kpt: 0.000615 acc_pose: 0.872149 loss: 0.000615 2022/09/22 19:45:44 - mmengine - INFO - Epoch(train) [183][100/293] lr: 5.000000e-05 eta: 1:05:11 time: 0.549949 data_time: 0.082819 memory: 6691 loss_kpt: 0.000612 acc_pose: 0.857898 loss: 0.000612 2022/09/22 19:46:14 - mmengine - INFO - Epoch(train) [183][150/293] lr: 5.000000e-05 eta: 1:04:47 time: 0.581206 data_time: 0.150411 memory: 6691 loss_kpt: 0.000601 acc_pose: 0.866725 loss: 0.000601 2022/09/22 19:46:42 - mmengine - INFO - Epoch(train) [183][200/293] lr: 5.000000e-05 eta: 1:04:24 time: 0.567448 data_time: 0.131768 memory: 6691 loss_kpt: 0.000619 acc_pose: 0.854727 loss: 0.000619 2022/09/22 19:47:11 - mmengine - INFO - Epoch(train) [183][250/293] lr: 5.000000e-05 eta: 1:04:00 time: 0.572758 data_time: 0.134371 memory: 6691 loss_kpt: 0.000611 acc_pose: 0.817098 loss: 0.000611 2022/09/22 19:47:34 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 19:48:04 - mmengine - INFO - Epoch(train) [184][50/293] lr: 5.000000e-05 eta: 1:03:13 time: 0.595494 data_time: 0.199721 memory: 6691 loss_kpt: 0.000627 acc_pose: 0.790701 loss: 0.000627 2022/09/22 19:48:32 - mmengine - INFO - Epoch(train) [184][100/293] lr: 5.000000e-05 eta: 1:02:50 time: 0.550575 data_time: 0.092500 memory: 6691 loss_kpt: 0.000617 acc_pose: 0.841023 loss: 0.000617 2022/09/22 19:49:01 - mmengine - INFO - Epoch(train) [184][150/293] lr: 5.000000e-05 eta: 1:02:26 time: 0.596320 data_time: 0.127099 memory: 6691 loss_kpt: 0.000608 acc_pose: 0.850020 loss: 0.000608 2022/09/22 19:49:28 - mmengine - INFO - Epoch(train) [184][200/293] lr: 5.000000e-05 eta: 1:02:03 time: 0.533274 data_time: 0.123448 memory: 6691 loss_kpt: 0.000619 acc_pose: 0.871622 loss: 0.000619 2022/09/22 19:49:57 - mmengine - INFO - Epoch(train) [184][250/293] lr: 5.000000e-05 eta: 1:01:39 time: 0.576475 data_time: 0.088081 memory: 6691 loss_kpt: 0.000607 acc_pose: 0.852547 loss: 0.000607 2022/09/22 19:50:20 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 19:50:49 - mmengine - INFO - Epoch(train) [185][50/293] lr: 5.000000e-05 eta: 1:00:52 time: 0.575757 data_time: 0.125889 memory: 6691 loss_kpt: 0.000607 acc_pose: 0.818861 loss: 0.000607 2022/09/22 19:51:11 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 19:51:18 - mmengine - INFO - Epoch(train) [185][100/293] lr: 5.000000e-05 eta: 1:00:29 time: 0.587230 data_time: 0.104912 memory: 6691 loss_kpt: 0.000618 acc_pose: 0.852381 loss: 0.000618 2022/09/22 19:51:46 - mmengine - INFO - Epoch(train) [185][150/293] lr: 5.000000e-05 eta: 1:00:05 time: 0.559126 data_time: 0.081566 memory: 6691 loss_kpt: 0.000616 acc_pose: 0.847662 loss: 0.000616 2022/09/22 19:52:15 - mmengine - INFO - Epoch(train) [185][200/293] lr: 5.000000e-05 eta: 0:59:41 time: 0.576486 data_time: 0.087352 memory: 6691 loss_kpt: 0.000608 acc_pose: 0.883786 loss: 0.000608 2022/09/22 19:52:43 - mmengine - INFO - Epoch(train) [185][250/293] lr: 5.000000e-05 eta: 0:59:18 time: 0.560618 data_time: 0.073068 memory: 6691 loss_kpt: 0.000610 acc_pose: 0.842205 loss: 0.000610 2022/09/22 19:53:07 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 19:53:36 - mmengine - INFO - Epoch(train) [186][50/293] lr: 5.000000e-05 eta: 0:58:31 time: 0.580867 data_time: 0.125564 memory: 6691 loss_kpt: 0.000622 acc_pose: 0.851821 loss: 0.000622 2022/09/22 19:54:03 - mmengine - INFO - Epoch(train) [186][100/293] lr: 5.000000e-05 eta: 0:58:07 time: 0.540829 data_time: 0.078613 memory: 6691 loss_kpt: 0.000608 acc_pose: 0.815824 loss: 0.000608 2022/09/22 19:54:31 - mmengine - INFO - Epoch(train) [186][150/293] lr: 5.000000e-05 eta: 0:57:43 time: 0.548895 data_time: 0.090593 memory: 6691 loss_kpt: 0.000614 acc_pose: 0.815170 loss: 0.000614 2022/09/22 19:54:58 - mmengine - INFO - Epoch(train) [186][200/293] lr: 5.000000e-05 eta: 0:57:20 time: 0.549694 data_time: 0.085800 memory: 6691 loss_kpt: 0.000609 acc_pose: 0.851088 loss: 0.000609 2022/09/22 19:55:26 - mmengine - INFO - Epoch(train) [186][250/293] lr: 5.000000e-05 eta: 0:56:56 time: 0.560254 data_time: 0.145358 memory: 6691 loss_kpt: 0.000620 acc_pose: 0.850664 loss: 0.000620 2022/09/22 19:55:50 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 19:56:19 - mmengine - INFO - Epoch(train) [187][50/293] lr: 5.000000e-05 eta: 0:56:09 time: 0.586350 data_time: 0.132368 memory: 6691 loss_kpt: 0.000611 acc_pose: 0.814463 loss: 0.000611 2022/09/22 19:56:47 - mmengine - INFO - Epoch(train) [187][100/293] lr: 5.000000e-05 eta: 0:55:45 time: 0.561204 data_time: 0.127405 memory: 6691 loss_kpt: 0.000610 acc_pose: 0.805999 loss: 0.000610 2022/09/22 19:57:15 - mmengine - INFO - Epoch(train) [187][150/293] lr: 5.000000e-05 eta: 0:55:22 time: 0.559939 data_time: 0.144818 memory: 6691 loss_kpt: 0.000591 acc_pose: 0.842734 loss: 0.000591 2022/09/22 19:57:44 - mmengine - INFO - Epoch(train) [187][200/293] lr: 5.000000e-05 eta: 0:54:58 time: 0.577742 data_time: 0.104313 memory: 6691 loss_kpt: 0.000617 acc_pose: 0.828716 loss: 0.000617 2022/09/22 19:58:12 - mmengine - INFO - Epoch(train) [187][250/293] lr: 5.000000e-05 eta: 0:54:35 time: 0.562091 data_time: 0.100354 memory: 6691 loss_kpt: 0.000612 acc_pose: 0.831833 loss: 0.000612 2022/09/22 19:58:36 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 19:59:05 - mmengine - INFO - Epoch(train) [188][50/293] lr: 5.000000e-05 eta: 0:53:48 time: 0.577068 data_time: 0.126889 memory: 6691 loss_kpt: 0.000608 acc_pose: 0.871990 loss: 0.000608 2022/09/22 19:59:33 - mmengine - INFO - Epoch(train) [188][100/293] lr: 5.000000e-05 eta: 0:53:24 time: 0.562887 data_time: 0.111889 memory: 6691 loss_kpt: 0.000601 acc_pose: 0.838383 loss: 0.000601 2022/09/22 20:00:01 - mmengine - INFO - Epoch(train) [188][150/293] lr: 5.000000e-05 eta: 0:53:00 time: 0.551868 data_time: 0.096643 memory: 6691 loss_kpt: 0.000613 acc_pose: 0.833980 loss: 0.000613 2022/09/22 20:00:27 - mmengine - INFO - Epoch(train) [188][200/293] lr: 5.000000e-05 eta: 0:52:36 time: 0.518989 data_time: 0.085039 memory: 6691 loss_kpt: 0.000614 acc_pose: 0.833506 loss: 0.000614 2022/09/22 20:00:31 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 20:00:54 - mmengine - INFO - Epoch(train) [188][250/293] lr: 5.000000e-05 eta: 0:52:13 time: 0.546494 data_time: 0.096685 memory: 6691 loss_kpt: 0.000610 acc_pose: 0.832117 loss: 0.000610 2022/09/22 20:01:19 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 20:01:48 - mmengine - INFO - Epoch(train) [189][50/293] lr: 5.000000e-05 eta: 0:51:26 time: 0.579655 data_time: 0.095010 memory: 6691 loss_kpt: 0.000609 acc_pose: 0.875285 loss: 0.000609 2022/09/22 20:02:15 - mmengine - INFO - Epoch(train) [189][100/293] lr: 5.000000e-05 eta: 0:51:02 time: 0.552718 data_time: 0.112003 memory: 6691 loss_kpt: 0.000608 acc_pose: 0.886383 loss: 0.000608 2022/09/22 20:02:44 - mmengine - INFO - Epoch(train) [189][150/293] lr: 5.000000e-05 eta: 0:50:39 time: 0.564842 data_time: 0.113852 memory: 6691 loss_kpt: 0.000608 acc_pose: 0.773095 loss: 0.000608 2022/09/22 20:03:13 - mmengine - INFO - Epoch(train) [189][200/293] lr: 5.000000e-05 eta: 0:50:15 time: 0.588803 data_time: 0.114902 memory: 6691 loss_kpt: 0.000613 acc_pose: 0.838465 loss: 0.000613 2022/09/22 20:03:41 - mmengine - INFO - Epoch(train) [189][250/293] lr: 5.000000e-05 eta: 0:49:51 time: 0.549973 data_time: 0.168626 memory: 6691 loss_kpt: 0.000605 acc_pose: 0.910547 loss: 0.000605 2022/09/22 20:04:05 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 20:04:35 - mmengine - INFO - Epoch(train) [190][50/293] lr: 5.000000e-05 eta: 0:49:05 time: 0.595338 data_time: 0.201136 memory: 6691 loss_kpt: 0.000598 acc_pose: 0.816887 loss: 0.000598 2022/09/22 20:05:03 - mmengine - INFO - Epoch(train) [190][100/293] lr: 5.000000e-05 eta: 0:48:41 time: 0.568027 data_time: 0.085819 memory: 6691 loss_kpt: 0.000604 acc_pose: 0.845055 loss: 0.000604 2022/09/22 20:05:31 - mmengine - INFO - Epoch(train) [190][150/293] lr: 5.000000e-05 eta: 0:48:17 time: 0.554682 data_time: 0.083505 memory: 6691 loss_kpt: 0.000608 acc_pose: 0.849055 loss: 0.000608 2022/09/22 20:05:59 - mmengine - INFO - Epoch(train) [190][200/293] lr: 5.000000e-05 eta: 0:47:54 time: 0.554461 data_time: 0.116516 memory: 6691 loss_kpt: 0.000603 acc_pose: 0.832354 loss: 0.000603 2022/09/22 20:06:26 - mmengine - INFO - Epoch(train) [190][250/293] lr: 5.000000e-05 eta: 0:47:30 time: 0.538531 data_time: 0.099007 memory: 6691 loss_kpt: 0.000622 acc_pose: 0.809179 loss: 0.000622 2022/09/22 20:06:49 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 20:06:49 - mmengine - INFO - Saving checkpoint at 190 epochs 2022/09/22 20:07:10 - mmengine - INFO - Epoch(val) [190][50/407] eta: 0:01:53 time: 0.318861 data_time: 0.206250 memory: 6691 2022/09/22 20:07:25 - mmengine - INFO - Epoch(val) [190][100/407] eta: 0:01:31 time: 0.297501 data_time: 0.172815 memory: 1014 2022/09/22 20:07:40 - mmengine - INFO - Epoch(val) [190][150/407] eta: 0:01:18 time: 0.303792 data_time: 0.171443 memory: 1014 2022/09/22 20:07:55 - mmengine - INFO - Epoch(val) [190][200/407] eta: 0:01:00 time: 0.294357 data_time: 0.177420 memory: 1014 2022/09/22 20:08:10 - mmengine - INFO - Epoch(val) [190][250/407] eta: 0:00:46 time: 0.297830 data_time: 0.166013 memory: 1014 2022/09/22 20:08:25 - mmengine - INFO - Epoch(val) [190][300/407] eta: 0:00:32 time: 0.304608 data_time: 0.176706 memory: 1014 2022/09/22 20:08:40 - mmengine - INFO - Epoch(val) [190][350/407] eta: 0:00:16 time: 0.295767 data_time: 0.171622 memory: 1014 2022/09/22 20:08:53 - mmengine - INFO - Epoch(val) [190][400/407] eta: 0:00:01 time: 0.269548 data_time: 0.155426 memory: 1014 2022/09/22 20:09:26 - mmengine - INFO - Evaluating CocoMetric... 2022/09/22 20:09:39 - mmengine - INFO - Epoch(val) [190][407/407] coco/AP: 0.716917 coco/AP .5: 0.898041 coco/AP .75: 0.795712 coco/AP (M): 0.678141 coco/AP (L): 0.785700 coco/AR: 0.771977 coco/AR .5: 0.934509 coco/AR .75: 0.842412 coco/AR (M): 0.727233 coco/AR (L): 0.836343 2022/09/22 20:09:39 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220922/res50_256/best_coco/AP_epoch_180.pth is removed 2022/09/22 20:09:41 - mmengine - INFO - The best checkpoint with 0.7169 coco/AP at 190 epoch is saved to best_coco/AP_epoch_190.pth. 2022/09/22 20:10:09 - mmengine - INFO - Epoch(train) [191][50/293] lr: 5.000000e-05 eta: 0:46:43 time: 0.543847 data_time: 0.253100 memory: 6691 loss_kpt: 0.000609 acc_pose: 0.838360 loss: 0.000609 2022/09/22 20:10:37 - mmengine - INFO - Epoch(train) [191][100/293] lr: 5.000000e-05 eta: 0:46:19 time: 0.565460 data_time: 0.084812 memory: 6691 loss_kpt: 0.000604 acc_pose: 0.848405 loss: 0.000604 2022/09/22 20:11:04 - mmengine - INFO - Epoch(train) [191][150/293] lr: 5.000000e-05 eta: 0:45:55 time: 0.546838 data_time: 0.223879 memory: 6691 loss_kpt: 0.000607 acc_pose: 0.831487 loss: 0.000607 2022/09/22 20:11:31 - mmengine - INFO - Epoch(train) [191][200/293] lr: 5.000000e-05 eta: 0:45:32 time: 0.526637 data_time: 0.242724 memory: 6691 loss_kpt: 0.000613 acc_pose: 0.841955 loss: 0.000613 2022/09/22 20:11:59 - mmengine - INFO - Epoch(train) [191][250/293] lr: 5.000000e-05 eta: 0:45:08 time: 0.575780 data_time: 0.218651 memory: 6691 loss_kpt: 0.000596 acc_pose: 0.786976 loss: 0.000596 2022/09/22 20:12:23 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 20:12:45 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 20:12:52 - mmengine - INFO - Epoch(train) [192][50/293] lr: 5.000000e-05 eta: 0:44:21 time: 0.584214 data_time: 0.087791 memory: 6691 loss_kpt: 0.000614 acc_pose: 0.829030 loss: 0.000614 2022/09/22 20:13:21 - mmengine - INFO - Epoch(train) [192][100/293] lr: 5.000000e-05 eta: 0:43:58 time: 0.571028 data_time: 0.085749 memory: 6691 loss_kpt: 0.000600 acc_pose: 0.810232 loss: 0.000600 2022/09/22 20:13:49 - mmengine - INFO - Epoch(train) [192][150/293] lr: 5.000000e-05 eta: 0:43:34 time: 0.553166 data_time: 0.127601 memory: 6691 loss_kpt: 0.000609 acc_pose: 0.874321 loss: 0.000609 2022/09/22 20:14:16 - mmengine - INFO - Epoch(train) [192][200/293] lr: 5.000000e-05 eta: 0:43:10 time: 0.557010 data_time: 0.099263 memory: 6691 loss_kpt: 0.000609 acc_pose: 0.848805 loss: 0.000609 2022/09/22 20:14:44 - mmengine - INFO - Epoch(train) [192][250/293] lr: 5.000000e-05 eta: 0:42:46 time: 0.554048 data_time: 0.222449 memory: 6691 loss_kpt: 0.000598 acc_pose: 0.885244 loss: 0.000598 2022/09/22 20:15:08 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 20:15:37 - mmengine - INFO - Epoch(train) [193][50/293] lr: 5.000000e-05 eta: 0:42:00 time: 0.581642 data_time: 0.283230 memory: 6691 loss_kpt: 0.000595 acc_pose: 0.813903 loss: 0.000595 2022/09/22 20:16:05 - mmengine - INFO - Epoch(train) [193][100/293] lr: 5.000000e-05 eta: 0:41:36 time: 0.564548 data_time: 0.184012 memory: 6691 loss_kpt: 0.000609 acc_pose: 0.856677 loss: 0.000609 2022/09/22 20:16:34 - mmengine - INFO - Epoch(train) [193][150/293] lr: 5.000000e-05 eta: 0:41:13 time: 0.575648 data_time: 0.217517 memory: 6691 loss_kpt: 0.000595 acc_pose: 0.845014 loss: 0.000595 2022/09/22 20:17:02 - mmengine - INFO - Epoch(train) [193][200/293] lr: 5.000000e-05 eta: 0:40:49 time: 0.557322 data_time: 0.249908 memory: 6691 loss_kpt: 0.000613 acc_pose: 0.835209 loss: 0.000613 2022/09/22 20:17:30 - mmengine - INFO - Epoch(train) [193][250/293] lr: 5.000000e-05 eta: 0:40:25 time: 0.551182 data_time: 0.189807 memory: 6691 loss_kpt: 0.000603 acc_pose: 0.859658 loss: 0.000603 2022/09/22 20:17:52 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 20:18:21 - mmengine - INFO - Epoch(train) [194][50/293] lr: 5.000000e-05 eta: 0:39:39 time: 0.573925 data_time: 0.112505 memory: 6691 loss_kpt: 0.000606 acc_pose: 0.839258 loss: 0.000606 2022/09/22 20:18:48 - mmengine - INFO - Epoch(train) [194][100/293] lr: 5.000000e-05 eta: 0:39:15 time: 0.541894 data_time: 0.095609 memory: 6691 loss_kpt: 0.000612 acc_pose: 0.850580 loss: 0.000612 2022/09/22 20:19:17 - mmengine - INFO - Epoch(train) [194][150/293] lr: 5.000000e-05 eta: 0:38:51 time: 0.585953 data_time: 0.180871 memory: 6691 loss_kpt: 0.000611 acc_pose: 0.865780 loss: 0.000611 2022/09/22 20:19:44 - mmengine - INFO - Epoch(train) [194][200/293] lr: 5.000000e-05 eta: 0:38:27 time: 0.539007 data_time: 0.254939 memory: 6691 loss_kpt: 0.000596 acc_pose: 0.807201 loss: 0.000596 2022/09/22 20:20:12 - mmengine - INFO - Epoch(train) [194][250/293] lr: 5.000000e-05 eta: 0:38:03 time: 0.543519 data_time: 0.194577 memory: 6691 loss_kpt: 0.000604 acc_pose: 0.873879 loss: 0.000604 2022/09/22 20:20:34 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 20:21:03 - mmengine - INFO - Epoch(train) [195][50/293] lr: 5.000000e-05 eta: 0:37:17 time: 0.566199 data_time: 0.144128 memory: 6691 loss_kpt: 0.000607 acc_pose: 0.817877 loss: 0.000607 2022/09/22 20:21:31 - mmengine - INFO - Epoch(train) [195][100/293] lr: 5.000000e-05 eta: 0:36:53 time: 0.572381 data_time: 0.108811 memory: 6691 loss_kpt: 0.000612 acc_pose: 0.855724 loss: 0.000612 2022/09/22 20:22:00 - mmengine - INFO - Epoch(train) [195][150/293] lr: 5.000000e-05 eta: 0:36:30 time: 0.572655 data_time: 0.126089 memory: 6691 loss_kpt: 0.000616 acc_pose: 0.866395 loss: 0.000616 2022/09/22 20:22:05 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 20:22:28 - mmengine - INFO - Epoch(train) [195][200/293] lr: 5.000000e-05 eta: 0:36:06 time: 0.570265 data_time: 0.114750 memory: 6691 loss_kpt: 0.000596 acc_pose: 0.852812 loss: 0.000596 2022/09/22 20:22:56 - mmengine - INFO - Epoch(train) [195][250/293] lr: 5.000000e-05 eta: 0:35:42 time: 0.558545 data_time: 0.102649 memory: 6691 loss_kpt: 0.000608 acc_pose: 0.831514 loss: 0.000608 2022/09/22 20:23:20 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 20:23:50 - mmengine - INFO - Epoch(train) [196][50/293] lr: 5.000000e-05 eta: 0:34:56 time: 0.589643 data_time: 0.099066 memory: 6691 loss_kpt: 0.000605 acc_pose: 0.804535 loss: 0.000605 2022/09/22 20:24:18 - mmengine - INFO - Epoch(train) [196][100/293] lr: 5.000000e-05 eta: 0:34:32 time: 0.562800 data_time: 0.113357 memory: 6691 loss_kpt: 0.000611 acc_pose: 0.866941 loss: 0.000611 2022/09/22 20:24:45 - mmengine - INFO - Epoch(train) [196][150/293] lr: 5.000000e-05 eta: 0:34:08 time: 0.537467 data_time: 0.073083 memory: 6691 loss_kpt: 0.000614 acc_pose: 0.782830 loss: 0.000614 2022/09/22 20:25:14 - mmengine - INFO - Epoch(train) [196][200/293] lr: 5.000000e-05 eta: 0:33:44 time: 0.582172 data_time: 0.165284 memory: 6691 loss_kpt: 0.000604 acc_pose: 0.860956 loss: 0.000604 2022/09/22 20:25:42 - mmengine - INFO - Epoch(train) [196][250/293] lr: 5.000000e-05 eta: 0:33:20 time: 0.557041 data_time: 0.243590 memory: 6691 loss_kpt: 0.000619 acc_pose: 0.814031 loss: 0.000619 2022/09/22 20:26:06 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 20:26:35 - mmengine - INFO - Epoch(train) [197][50/293] lr: 5.000000e-05 eta: 0:32:34 time: 0.569279 data_time: 0.116915 memory: 6691 loss_kpt: 0.000612 acc_pose: 0.832785 loss: 0.000612 2022/09/22 20:27:04 - mmengine - INFO - Epoch(train) [197][100/293] lr: 5.000000e-05 eta: 0:32:11 time: 0.597701 data_time: 0.121055 memory: 6691 loss_kpt: 0.000606 acc_pose: 0.832777 loss: 0.000606 2022/09/22 20:27:32 - mmengine - INFO - Epoch(train) [197][150/293] lr: 5.000000e-05 eta: 0:31:47 time: 0.551795 data_time: 0.115754 memory: 6691 loss_kpt: 0.000607 acc_pose: 0.810474 loss: 0.000607 2022/09/22 20:28:01 - mmengine - INFO - Epoch(train) [197][200/293] lr: 5.000000e-05 eta: 0:31:23 time: 0.582994 data_time: 0.320700 memory: 6691 loss_kpt: 0.000603 acc_pose: 0.799282 loss: 0.000603 2022/09/22 20:28:29 - mmengine - INFO - Epoch(train) [197][250/293] lr: 5.000000e-05 eta: 0:30:59 time: 0.558014 data_time: 0.277545 memory: 6691 loss_kpt: 0.000600 acc_pose: 0.834369 loss: 0.000600 2022/09/22 20:28:53 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 20:29:23 - mmengine - INFO - Epoch(train) [198][50/293] lr: 5.000000e-05 eta: 0:30:13 time: 0.596405 data_time: 0.249077 memory: 6691 loss_kpt: 0.000600 acc_pose: 0.883845 loss: 0.000600 2022/09/22 20:29:52 - mmengine - INFO - Epoch(train) [198][100/293] lr: 5.000000e-05 eta: 0:29:49 time: 0.571838 data_time: 0.153982 memory: 6691 loss_kpt: 0.000612 acc_pose: 0.868898 loss: 0.000612 2022/09/22 20:30:20 - mmengine - INFO - Epoch(train) [198][150/293] lr: 5.000000e-05 eta: 0:29:25 time: 0.559059 data_time: 0.147205 memory: 6691 loss_kpt: 0.000608 acc_pose: 0.867491 loss: 0.000608 2022/09/22 20:30:48 - mmengine - INFO - Epoch(train) [198][200/293] lr: 5.000000e-05 eta: 0:29:02 time: 0.566404 data_time: 0.089856 memory: 6691 loss_kpt: 0.000591 acc_pose: 0.822179 loss: 0.000591 2022/09/22 20:31:16 - mmengine - INFO - Epoch(train) [198][250/293] lr: 5.000000e-05 eta: 0:28:38 time: 0.553746 data_time: 0.070471 memory: 6691 loss_kpt: 0.000612 acc_pose: 0.865216 loss: 0.000612 2022/09/22 20:31:31 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 20:31:39 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 20:32:09 - mmengine - INFO - Epoch(train) [199][50/293] lr: 5.000000e-05 eta: 0:27:52 time: 0.600966 data_time: 0.126848 memory: 6691 loss_kpt: 0.000601 acc_pose: 0.810568 loss: 0.000601 2022/09/22 20:32:38 - mmengine - INFO - Epoch(train) [199][100/293] lr: 5.000000e-05 eta: 0:27:28 time: 0.576578 data_time: 0.097181 memory: 6691 loss_kpt: 0.000611 acc_pose: 0.807010 loss: 0.000611 2022/09/22 20:33:06 - mmengine - INFO - Epoch(train) [199][150/293] lr: 5.000000e-05 eta: 0:27:04 time: 0.567116 data_time: 0.163039 memory: 6691 loss_kpt: 0.000607 acc_pose: 0.855065 loss: 0.000607 2022/09/22 20:33:35 - mmengine - INFO - Epoch(train) [199][200/293] lr: 5.000000e-05 eta: 0:26:40 time: 0.573298 data_time: 0.126276 memory: 6691 loss_kpt: 0.000608 acc_pose: 0.833055 loss: 0.000608 2022/09/22 20:34:03 - mmengine - INFO - Epoch(train) [199][250/293] lr: 5.000000e-05 eta: 0:26:16 time: 0.561654 data_time: 0.084124 memory: 6691 loss_kpt: 0.000597 acc_pose: 0.832363 loss: 0.000597 2022/09/22 20:34:27 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 20:34:56 - mmengine - INFO - Epoch(train) [200][50/293] lr: 5.000000e-05 eta: 0:25:31 time: 0.585082 data_time: 0.187494 memory: 6691 loss_kpt: 0.000597 acc_pose: 0.854039 loss: 0.000597 2022/09/22 20:35:24 - mmengine - INFO - Epoch(train) [200][100/293] lr: 5.000000e-05 eta: 0:25:07 time: 0.557564 data_time: 0.121411 memory: 6691 loss_kpt: 0.000599 acc_pose: 0.838476 loss: 0.000599 2022/09/22 20:35:53 - mmengine - INFO - Epoch(train) [200][150/293] lr: 5.000000e-05 eta: 0:24:43 time: 0.574812 data_time: 0.112835 memory: 6691 loss_kpt: 0.000602 acc_pose: 0.838438 loss: 0.000602 2022/09/22 20:36:22 - mmengine - INFO - Epoch(train) [200][200/293] lr: 5.000000e-05 eta: 0:24:19 time: 0.580296 data_time: 0.088831 memory: 6691 loss_kpt: 0.000616 acc_pose: 0.839104 loss: 0.000616 2022/09/22 20:36:50 - mmengine - INFO - Epoch(train) [200][250/293] lr: 5.000000e-05 eta: 0:23:55 time: 0.563360 data_time: 0.098373 memory: 6691 loss_kpt: 0.000606 acc_pose: 0.843577 loss: 0.000606 2022/09/22 20:37:14 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 20:37:14 - mmengine - INFO - Saving checkpoint at 200 epochs 2022/09/22 20:37:35 - mmengine - INFO - Epoch(val) [200][50/407] eta: 0:01:52 time: 0.314712 data_time: 0.189216 memory: 6691 2022/09/22 20:37:51 - mmengine - INFO - Epoch(val) [200][100/407] eta: 0:01:35 time: 0.309588 data_time: 0.185548 memory: 1014 2022/09/22 20:38:06 - mmengine - INFO - Epoch(val) [200][150/407] eta: 0:01:16 time: 0.296742 data_time: 0.157883 memory: 1014 2022/09/22 20:38:21 - mmengine - INFO - Epoch(val) [200][200/407] eta: 0:01:04 time: 0.312528 data_time: 0.187956 memory: 1014 2022/09/22 20:38:37 - mmengine - INFO - Epoch(val) [200][250/407] eta: 0:00:48 time: 0.307279 data_time: 0.174698 memory: 1014 2022/09/22 20:38:52 - mmengine - INFO - Epoch(val) [200][300/407] eta: 0:00:33 time: 0.313651 data_time: 0.183329 memory: 1014 2022/09/22 20:39:08 - mmengine - INFO - Epoch(val) [200][350/407] eta: 0:00:17 time: 0.305576 data_time: 0.175551 memory: 1014 2022/09/22 20:39:19 - mmengine - INFO - Epoch(val) [200][400/407] eta: 0:00:01 time: 0.229061 data_time: 0.144410 memory: 1014 2022/09/22 20:39:52 - mmengine - INFO - Evaluating CocoMetric... 2022/09/22 20:40:05 - mmengine - INFO - Epoch(val) [200][407/407] coco/AP: 0.717101 coco/AP .5: 0.897265 coco/AP .75: 0.794944 coco/AP (M): 0.677917 coco/AP (L): 0.787207 coco/AR: 0.772591 coco/AR .5: 0.935296 coco/AR .75: 0.842254 coco/AR (M): 0.727151 coco/AR (L): 0.837681 2022/09/22 20:40:05 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220922/res50_256/best_coco/AP_epoch_190.pth is removed 2022/09/22 20:40:07 - mmengine - INFO - The best checkpoint with 0.7171 coco/AP at 200 epoch is saved to best_coco/AP_epoch_200.pth. 2022/09/22 20:40:35 - mmengine - INFO - Epoch(train) [201][50/293] lr: 5.000000e-06 eta: 0:23:09 time: 0.544461 data_time: 0.252744 memory: 6691 loss_kpt: 0.000609 acc_pose: 0.837172 loss: 0.000609 2022/09/22 20:41:02 - mmengine - INFO - Epoch(train) [201][100/293] lr: 5.000000e-06 eta: 0:22:45 time: 0.545264 data_time: 0.258037 memory: 6691 loss_kpt: 0.000615 acc_pose: 0.813206 loss: 0.000615 2022/09/22 20:41:30 - mmengine - INFO - Epoch(train) [201][150/293] lr: 5.000000e-06 eta: 0:22:21 time: 0.562429 data_time: 0.127937 memory: 6691 loss_kpt: 0.000600 acc_pose: 0.835796 loss: 0.000600 2022/09/22 20:41:58 - mmengine - INFO - Epoch(train) [201][200/293] lr: 5.000000e-06 eta: 0:21:57 time: 0.553693 data_time: 0.067704 memory: 6691 loss_kpt: 0.000593 acc_pose: 0.874319 loss: 0.000593 2022/09/22 20:42:27 - mmengine - INFO - Epoch(train) [201][250/293] lr: 5.000000e-06 eta: 0:21:33 time: 0.579276 data_time: 0.082863 memory: 6691 loss_kpt: 0.000607 acc_pose: 0.874063 loss: 0.000607 2022/09/22 20:42:50 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 20:43:19 - mmengine - INFO - Epoch(train) [202][50/293] lr: 5.000000e-06 eta: 0:20:48 time: 0.576406 data_time: 0.119367 memory: 6691 loss_kpt: 0.000607 acc_pose: 0.820380 loss: 0.000607 2022/09/22 20:43:48 - mmengine - INFO - Epoch(train) [202][100/293] lr: 5.000000e-06 eta: 0:20:24 time: 0.572461 data_time: 0.083603 memory: 6691 loss_kpt: 0.000610 acc_pose: 0.834363 loss: 0.000610 2022/09/22 20:43:52 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 20:44:17 - mmengine - INFO - Epoch(train) [202][150/293] lr: 5.000000e-06 eta: 0:20:00 time: 0.573616 data_time: 0.145505 memory: 6691 loss_kpt: 0.000616 acc_pose: 0.842522 loss: 0.000616 2022/09/22 20:44:45 - mmengine - INFO - Epoch(train) [202][200/293] lr: 5.000000e-06 eta: 0:19:36 time: 0.562746 data_time: 0.132630 memory: 6691 loss_kpt: 0.000607 acc_pose: 0.825008 loss: 0.000607 2022/09/22 20:45:13 - mmengine - INFO - Epoch(train) [202][250/293] lr: 5.000000e-06 eta: 0:19:12 time: 0.572693 data_time: 0.118517 memory: 6691 loss_kpt: 0.000604 acc_pose: 0.795061 loss: 0.000604 2022/09/22 20:45:37 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 20:46:05 - mmengine - INFO - Epoch(train) [203][50/293] lr: 5.000000e-06 eta: 0:18:26 time: 0.564796 data_time: 0.201024 memory: 6691 loss_kpt: 0.000612 acc_pose: 0.824314 loss: 0.000612 2022/09/22 20:46:33 - mmengine - INFO - Epoch(train) [203][100/293] lr: 5.000000e-06 eta: 0:18:03 time: 0.566737 data_time: 0.286468 memory: 6691 loss_kpt: 0.000607 acc_pose: 0.879216 loss: 0.000607 2022/09/22 20:47:02 - mmengine - INFO - Epoch(train) [203][150/293] lr: 5.000000e-06 eta: 0:17:39 time: 0.570459 data_time: 0.208693 memory: 6691 loss_kpt: 0.000612 acc_pose: 0.852426 loss: 0.000612 2022/09/22 20:47:30 - mmengine - INFO - Epoch(train) [203][200/293] lr: 5.000000e-06 eta: 0:17:15 time: 0.553356 data_time: 0.138220 memory: 6691 loss_kpt: 0.000598 acc_pose: 0.862255 loss: 0.000598 2022/09/22 20:47:58 - mmengine - INFO - Epoch(train) [203][250/293] lr: 5.000000e-06 eta: 0:16:51 time: 0.564623 data_time: 0.235963 memory: 6691 loss_kpt: 0.000619 acc_pose: 0.843361 loss: 0.000619 2022/09/22 20:48:21 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 20:48:50 - mmengine - INFO - Epoch(train) [204][50/293] lr: 5.000000e-06 eta: 0:16:05 time: 0.574900 data_time: 0.233306 memory: 6691 loss_kpt: 0.000594 acc_pose: 0.812030 loss: 0.000594 2022/09/22 20:49:18 - mmengine - INFO - Epoch(train) [204][100/293] lr: 5.000000e-06 eta: 0:15:41 time: 0.558758 data_time: 0.102297 memory: 6691 loss_kpt: 0.000614 acc_pose: 0.843850 loss: 0.000614 2022/09/22 20:49:46 - mmengine - INFO - Epoch(train) [204][150/293] lr: 5.000000e-06 eta: 0:15:17 time: 0.561068 data_time: 0.093879 memory: 6691 loss_kpt: 0.000603 acc_pose: 0.828166 loss: 0.000603 2022/09/22 20:50:13 - mmengine - INFO - Epoch(train) [204][200/293] lr: 5.000000e-06 eta: 0:14:53 time: 0.556443 data_time: 0.087550 memory: 6691 loss_kpt: 0.000601 acc_pose: 0.877224 loss: 0.000601 2022/09/22 20:50:41 - mmengine - INFO - Epoch(train) [204][250/293] lr: 5.000000e-06 eta: 0:14:29 time: 0.558528 data_time: 0.138731 memory: 6691 loss_kpt: 0.000610 acc_pose: 0.810836 loss: 0.000610 2022/09/22 20:51:05 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 20:51:35 - mmengine - INFO - Epoch(train) [205][50/293] lr: 5.000000e-06 eta: 0:13:44 time: 0.587000 data_time: 0.153952 memory: 6691 loss_kpt: 0.000588 acc_pose: 0.859858 loss: 0.000588 2022/09/22 20:52:03 - mmengine - INFO - Epoch(train) [205][100/293] lr: 5.000000e-06 eta: 0:13:20 time: 0.562123 data_time: 0.135119 memory: 6691 loss_kpt: 0.000605 acc_pose: 0.829448 loss: 0.000605 2022/09/22 20:52:31 - mmengine - INFO - Epoch(train) [205][150/293] lr: 5.000000e-06 eta: 0:12:56 time: 0.565322 data_time: 0.148598 memory: 6691 loss_kpt: 0.000606 acc_pose: 0.842677 loss: 0.000606 2022/09/22 20:52:59 - mmengine - INFO - Epoch(train) [205][200/293] lr: 5.000000e-06 eta: 0:12:32 time: 0.556527 data_time: 0.115986 memory: 6691 loss_kpt: 0.000606 acc_pose: 0.789545 loss: 0.000606 2022/09/22 20:53:16 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 20:53:28 - mmengine - INFO - Epoch(train) [205][250/293] lr: 5.000000e-06 eta: 0:12:08 time: 0.583181 data_time: 0.081853 memory: 6691 loss_kpt: 0.000604 acc_pose: 0.835969 loss: 0.000604 2022/09/22 20:53:52 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 20:54:21 - mmengine - INFO - Epoch(train) [206][50/293] lr: 5.000000e-06 eta: 0:11:22 time: 0.580961 data_time: 0.214181 memory: 6691 loss_kpt: 0.000599 acc_pose: 0.826472 loss: 0.000599 2022/09/22 20:54:50 - mmengine - INFO - Epoch(train) [206][100/293] lr: 5.000000e-06 eta: 0:10:58 time: 0.579437 data_time: 0.162015 memory: 6691 loss_kpt: 0.000613 acc_pose: 0.816549 loss: 0.000613 2022/09/22 20:55:18 - mmengine - INFO - Epoch(train) [206][150/293] lr: 5.000000e-06 eta: 0:10:34 time: 0.548109 data_time: 0.079183 memory: 6691 loss_kpt: 0.000600 acc_pose: 0.858373 loss: 0.000600 2022/09/22 20:55:54 - mmengine - INFO - Epoch(train) [206][200/293] lr: 5.000000e-06 eta: 0:10:10 time: 0.730229 data_time: 0.098113 memory: 6691 loss_kpt: 0.000585 acc_pose: 0.812435 loss: 0.000585 2022/09/22 20:57:01 - mmengine - INFO - Epoch(train) [206][250/293] lr: 5.000000e-06 eta: 0:09:47 time: 1.326142 data_time: 0.116318 memory: 6691 loss_kpt: 0.000614 acc_pose: 0.829813 loss: 0.000614 2022/09/22 20:57:51 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 20:58:20 - mmengine - INFO - Epoch(train) [207][50/293] lr: 5.000000e-06 eta: 0:09:02 time: 0.586100 data_time: 0.122998 memory: 6691 loss_kpt: 0.000602 acc_pose: 0.843929 loss: 0.000602 2022/09/22 20:58:48 - mmengine - INFO - Epoch(train) [207][100/293] lr: 5.000000e-06 eta: 0:08:38 time: 0.559058 data_time: 0.257436 memory: 6691 loss_kpt: 0.000615 acc_pose: 0.837391 loss: 0.000615 2022/09/22 20:59:16 - mmengine - INFO - Epoch(train) [207][150/293] lr: 5.000000e-06 eta: 0:08:14 time: 0.555278 data_time: 0.148234 memory: 6691 loss_kpt: 0.000600 acc_pose: 0.856458 loss: 0.000600 2022/09/22 20:59:45 - mmengine - INFO - Epoch(train) [207][200/293] lr: 5.000000e-06 eta: 0:07:50 time: 0.577000 data_time: 0.167257 memory: 6691 loss_kpt: 0.000606 acc_pose: 0.824317 loss: 0.000606 2022/09/22 21:00:13 - mmengine - INFO - Epoch(train) [207][250/293] lr: 5.000000e-06 eta: 0:07:25 time: 0.554831 data_time: 0.074123 memory: 6691 loss_kpt: 0.000601 acc_pose: 0.799095 loss: 0.000601 2022/09/22 21:00:36 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 21:01:05 - mmengine - INFO - Epoch(train) [208][50/293] lr: 5.000000e-06 eta: 0:06:40 time: 0.566629 data_time: 0.252624 memory: 6691 loss_kpt: 0.000606 acc_pose: 0.773785 loss: 0.000606 2022/09/22 21:01:33 - mmengine - INFO - Epoch(train) [208][100/293] lr: 5.000000e-06 eta: 0:06:16 time: 0.558688 data_time: 0.202650 memory: 6691 loss_kpt: 0.000605 acc_pose: 0.836650 loss: 0.000605 2022/09/22 21:02:00 - mmengine - INFO - Epoch(train) [208][150/293] lr: 5.000000e-06 eta: 0:05:52 time: 0.548148 data_time: 0.178070 memory: 6691 loss_kpt: 0.000591 acc_pose: 0.812392 loss: 0.000591 2022/09/22 21:02:28 - mmengine - INFO - Epoch(train) [208][200/293] lr: 5.000000e-06 eta: 0:05:28 time: 0.560014 data_time: 0.135324 memory: 6691 loss_kpt: 0.000609 acc_pose: 0.881088 loss: 0.000609 2022/09/22 21:02:57 - mmengine - INFO - Epoch(train) [208][250/293] lr: 5.000000e-06 eta: 0:05:04 time: 0.576079 data_time: 0.095905 memory: 6691 loss_kpt: 0.000600 acc_pose: 0.852649 loss: 0.000600 2022/09/22 21:03:20 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 21:03:50 - mmengine - INFO - Epoch(train) [209][50/293] lr: 5.000000e-06 eta: 0:04:19 time: 0.592097 data_time: 0.196011 memory: 6691 loss_kpt: 0.000611 acc_pose: 0.848244 loss: 0.000611 2022/09/22 21:03:53 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 21:04:18 - mmengine - INFO - Epoch(train) [209][100/293] lr: 5.000000e-06 eta: 0:03:54 time: 0.556156 data_time: 0.086863 memory: 6691 loss_kpt: 0.000599 acc_pose: 0.856636 loss: 0.000599 2022/09/22 21:04:45 - mmengine - INFO - Epoch(train) [209][150/293] lr: 5.000000e-06 eta: 0:03:30 time: 0.543785 data_time: 0.081667 memory: 6691 loss_kpt: 0.000588 acc_pose: 0.847981 loss: 0.000588 2022/09/22 21:05:12 - mmengine - INFO - Epoch(train) [209][200/293] lr: 5.000000e-06 eta: 0:03:06 time: 0.555422 data_time: 0.086235 memory: 6691 loss_kpt: 0.000604 acc_pose: 0.868973 loss: 0.000604 2022/09/22 21:05:40 - mmengine - INFO - Epoch(train) [209][250/293] lr: 5.000000e-06 eta: 0:02:42 time: 0.556385 data_time: 0.099596 memory: 6691 loss_kpt: 0.000603 acc_pose: 0.877636 loss: 0.000603 2022/09/22 21:06:04 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 21:06:32 - mmengine - INFO - Epoch(train) [210][50/293] lr: 5.000000e-06 eta: 0:01:57 time: 0.573068 data_time: 0.271519 memory: 6691 loss_kpt: 0.000603 acc_pose: 0.811118 loss: 0.000603 2022/09/22 21:07:01 - mmengine - INFO - Epoch(train) [210][100/293] lr: 5.000000e-06 eta: 0:01:33 time: 0.570779 data_time: 0.244979 memory: 6691 loss_kpt: 0.000610 acc_pose: 0.832847 loss: 0.000610 2022/09/22 21:07:29 - mmengine - INFO - Epoch(train) [210][150/293] lr: 5.000000e-06 eta: 0:01:09 time: 0.555175 data_time: 0.158624 memory: 6691 loss_kpt: 0.000611 acc_pose: 0.827625 loss: 0.000611 2022/09/22 21:07:56 - mmengine - INFO - Epoch(train) [210][200/293] lr: 5.000000e-06 eta: 0:00:44 time: 0.550447 data_time: 0.099667 memory: 6691 loss_kpt: 0.000597 acc_pose: 0.882320 loss: 0.000597 2022/09/22 21:08:25 - mmengine - INFO - Epoch(train) [210][250/293] lr: 5.000000e-06 eta: 0:00:20 time: 0.573510 data_time: 0.115461 memory: 6691 loss_kpt: 0.000607 acc_pose: 0.840511 loss: 0.000607 2022/09/22 21:08:49 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-256x192_20220922_102956 2022/09/22 21:08:49 - mmengine - INFO - Saving checkpoint at 210 epochs 2022/09/22 21:09:12 - mmengine - INFO - Epoch(val) [210][50/407] eta: 0:01:56 time: 0.326398 data_time: 0.167995 memory: 6691 2022/09/22 21:09:27 - mmengine - INFO - Epoch(val) [210][100/407] eta: 0:01:32 time: 0.302784 data_time: 0.164750 memory: 1014 2022/09/22 21:09:43 - mmengine - INFO - Epoch(val) [210][150/407] eta: 0:01:25 time: 0.332097 data_time: 0.190060 memory: 1014 2022/09/22 21:09:59 - mmengine - INFO - Epoch(val) [210][200/407] eta: 0:01:03 time: 0.304726 data_time: 0.179590 memory: 1014 2022/09/22 21:10:14 - mmengine - INFO - Epoch(val) [210][250/407] eta: 0:00:49 time: 0.313158 data_time: 0.166305 memory: 1014 2022/09/22 21:10:30 - mmengine - INFO - Epoch(val) [210][300/407] eta: 0:00:32 time: 0.305042 data_time: 0.166699 memory: 1014 2022/09/22 21:10:45 - mmengine - INFO - Epoch(val) [210][350/407] eta: 0:00:17 time: 0.312270 data_time: 0.170470 memory: 1014 2022/09/22 21:10:57 - mmengine - INFO - Epoch(val) [210][400/407] eta: 0:00:01 time: 0.230532 data_time: 0.131531 memory: 1014 2022/09/22 21:11:30 - mmengine - INFO - Evaluating CocoMetric... 2022/09/22 21:11:43 - mmengine - INFO - Epoch(val) [210][407/407] coco/AP: 0.718156 coco/AP .5: 0.897584 coco/AP .75: 0.796495 coco/AP (M): 0.678777 coco/AP (L): 0.787932 coco/AR: 0.773804 coco/AR .5: 0.934194 coco/AR .75: 0.844301 coco/AR (M): 0.728380 coco/AR (L): 0.838907 2022/09/22 21:11:43 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220922/res50_256/best_coco/AP_epoch_200.pth is removed 2022/09/22 21:11:45 - mmengine - INFO - The best checkpoint with 0.7182 coco/AP at 210 epoch is saved to best_coco/AP_epoch_210.pth.