2022/11/28 12:06:08 - mmengine - INFO - ------------------------------------------------------------ System environment: sys.platform: linux Python: 3.9.13 (main, Aug 25 2022, 23:26:10) [GCC 11.2.0] CUDA available: True numpy_random_seed: 127827721 GPU 0,1,2,3,4,5,6,7: NVIDIA A100-SXM4-80GB CUDA_HOME: /mnt/petrelfs/share/cuda-11.3 NVCC: Cuda compilation tools, release 11.3, V11.3.109 GCC: gcc (GCC) 5.4.0 PyTorch: 1.11.0 PyTorch compiling details: PyTorch built with: - GCC 7.3 - 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 v2.5.2 (Git Hash a9302535553c73243c632ad3c4c80beec3d19a1e) - 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 8.2 - Magma 2.5.2 - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.3, CUDNN_VERSION=8.2.0, CXX_COMPILER=/opt/rh/devtoolset-7/root/usr/bin/c++, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -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-sign-compare -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 -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.11.0, 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: 0.12.0 OpenCV: 4.6.0 MMEngine: 0.3.1 Runtime environment: cudnn_benchmark: False mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0} dist_cfg: {'backend': 'nccl'} seed: None diff_rank_seed: False deterministic: False Distributed launcher: pytorch Distributed training: True GPU number: 8 ------------------------------------------------------------ 2022/11/28 12:06:08 - mmengine - INFO - Config: default_scope = 'mmaction' default_hooks = dict( runtime_info=dict(type='RuntimeInfoHook'), timer=dict(type='IterTimerHook'), logger=dict(type='LoggerHook', interval=100, ignore_last=False), param_scheduler=dict(type='ParamSchedulerHook'), checkpoint=dict(type='CheckpointHook', interval=1, save_best='auto'), sampler_seed=dict(type='DistSamplerSeedHook'), sync_buffers=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')) log_processor = dict(type='LogProcessor', window_size=20, by_epoch=True) vis_backends = [dict(type='LocalVisBackend')] visualizer = dict( type='ActionVisualizer', vis_backends=[dict(type='LocalVisBackend')]) log_level = 'INFO' load_from = None resume = False model = dict( type='RecognizerGCN', backbone=dict( type='STGCN', graph_cfg=dict(layout='nturgb+d', mode='stgcn_spatial')), cls_head=dict(type='GCNHead', num_classes=60, in_channels=256)) dataset_type = 'PoseDataset' ann_file = 'data/skeleton/ntu60_3d.pkl' train_pipeline = [ dict(type='PreNormalize3D'), dict(type='GenSkeFeat', dataset='nturgb+d', feats=['jm']), dict(type='UniformSampleFrames', clip_len=100), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ] val_pipeline = [ dict(type='PreNormalize3D'), dict(type='GenSkeFeat', dataset='nturgb+d', feats=['jm']), dict( type='UniformSampleFrames', clip_len=100, num_clips=1, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ] test_pipeline = [ dict(type='PreNormalize3D'), dict(type='GenSkeFeat', dataset='nturgb+d', feats=['jm']), dict( type='UniformSampleFrames', clip_len=100, num_clips=10, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ] train_dataloader = dict( batch_size=16, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=True), dataset=dict( type='RepeatDataset', times=5, dataset=dict( type='PoseDataset', ann_file='data/skeleton/ntu60_3d.pkl', pipeline=[ dict(type='PreNormalize3D'), dict(type='GenSkeFeat', dataset='nturgb+d', feats=['jm']), dict(type='UniformSampleFrames', clip_len=100), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ], split='xsub_train'))) val_dataloader = dict( batch_size=16, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='PoseDataset', ann_file='data/skeleton/ntu60_3d.pkl', pipeline=[ dict(type='PreNormalize3D'), dict(type='GenSkeFeat', dataset='nturgb+d', feats=['jm']), dict( type='UniformSampleFrames', clip_len=100, num_clips=1, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ], split='xsub_val', test_mode=True)) test_dataloader = dict( batch_size=1, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='PoseDataset', ann_file='data/skeleton/ntu60_3d.pkl', pipeline=[ dict(type='PreNormalize3D'), dict(type='GenSkeFeat', dataset='nturgb+d', feats=['jm']), dict( type='UniformSampleFrames', clip_len=100, num_clips=10, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ], split='xsub_val', test_mode=True)) val_evaluator = [dict(type='AccMetric')] test_evaluator = [dict(type='AccMetric')] train_cfg = dict( type='EpochBasedTrainLoop', max_epochs=16, val_begin=1, val_interval=1) val_cfg = dict(type='ValLoop') test_cfg = dict(type='TestLoop') param_scheduler = [ dict( type='CosineAnnealingLR', eta_min=0, T_max=16, by_epoch=True, convert_to_iter_based=True) ] optim_wrapper = dict( optimizer=dict( type='SGD', lr=0.1, momentum=0.9, weight_decay=0.0005, nesterov=True)) auto_scale_lr = dict(enable=False, base_batch_size=128) launcher = 'pytorch' work_dir = './work_dirs/stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d' randomness = dict(seed=None, diff_rank_seed=False, deterministic=False) 2022/11/28 12:06:08 - mmengine - INFO - Result has been saved to /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d/modules_statistic_results.json Name of parameter - Initialization information data_bn.weight - torch.Size([75]): The value is the same before and after calling `init_weights` of STGCN data_bn.bias - torch.Size([75]): The value is the same before and after calling `init_weights` of STGCN gcn.0.gcn.PA - torch.Size([3, 25, 25]): The value is the same before and after calling `init_weights` of STGCN gcn.0.gcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.0.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.0.gcn.conv.weight - torch.Size([192, 3, 1, 1]): The value is the same before and after calling `init_weights` of STGCN gcn.0.gcn.conv.bias - torch.Size([192]): The value is the same before and after calling `init_weights` of STGCN gcn.0.tcn.conv.weight - torch.Size([64, 64, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.0.tcn.conv.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.0.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.0.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.1.gcn.PA - torch.Size([3, 25, 25]): The value is the same before and after calling `init_weights` of STGCN gcn.1.gcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.1.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.1.gcn.conv.weight - torch.Size([192, 64, 1, 1]): The value is the same before and after calling `init_weights` of STGCN gcn.1.gcn.conv.bias - torch.Size([192]): The value is the same before and after calling `init_weights` of STGCN gcn.1.tcn.conv.weight - torch.Size([64, 64, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.1.tcn.conv.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.1.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.1.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.2.gcn.PA - torch.Size([3, 25, 25]): The value is the same before and after calling `init_weights` of STGCN gcn.2.gcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.2.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.2.gcn.conv.weight - torch.Size([192, 64, 1, 1]): The value is the same before and after calling `init_weights` of STGCN gcn.2.gcn.conv.bias - torch.Size([192]): The value is the same before and after calling `init_weights` of STGCN gcn.2.tcn.conv.weight - torch.Size([64, 64, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.2.tcn.conv.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.2.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.2.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.3.gcn.PA - torch.Size([3, 25, 25]): The value is the same before and after calling `init_weights` of STGCN gcn.3.gcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.3.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.3.gcn.conv.weight - torch.Size([192, 64, 1, 1]): The value is the same before and after calling `init_weights` of STGCN gcn.3.gcn.conv.bias - torch.Size([192]): The value is the same before and after calling `init_weights` of STGCN gcn.3.tcn.conv.weight - torch.Size([64, 64, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.3.tcn.conv.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.3.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.3.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.4.gcn.PA - torch.Size([3, 25, 25]): The value is the same before and after calling `init_weights` of STGCN gcn.4.gcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.4.gcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.4.gcn.conv.weight - torch.Size([384, 64, 1, 1]): The value is the same before and after calling `init_weights` of STGCN gcn.4.gcn.conv.bias - torch.Size([384]): The value is the same before and after calling `init_weights` of STGCN gcn.4.tcn.conv.weight - torch.Size([128, 128, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.4.tcn.conv.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.4.tcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.4.tcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.4.residual.conv.weight - torch.Size([128, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.4.residual.conv.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.4.residual.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.4.residual.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.5.gcn.PA - torch.Size([3, 25, 25]): The value is the same before and after calling `init_weights` of STGCN gcn.5.gcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.5.gcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.5.gcn.conv.weight - torch.Size([384, 128, 1, 1]): The value is the same before and after calling `init_weights` of STGCN gcn.5.gcn.conv.bias - torch.Size([384]): The value is the same before and after calling `init_weights` of STGCN gcn.5.tcn.conv.weight - torch.Size([128, 128, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.5.tcn.conv.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.5.tcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.5.tcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.6.gcn.PA - torch.Size([3, 25, 25]): The value is the same before and after calling `init_weights` of STGCN gcn.6.gcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.6.gcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.6.gcn.conv.weight - torch.Size([384, 128, 1, 1]): The value is the same before and after calling `init_weights` of STGCN gcn.6.gcn.conv.bias - torch.Size([384]): The value is the same before and after calling `init_weights` of STGCN gcn.6.tcn.conv.weight - torch.Size([128, 128, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.6.tcn.conv.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.6.tcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.6.tcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.7.gcn.PA - torch.Size([3, 25, 25]): The value is the same before and after calling `init_weights` of STGCN gcn.7.gcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.7.gcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.7.gcn.conv.weight - torch.Size([768, 128, 1, 1]): The value is the same before and after calling `init_weights` of STGCN gcn.7.gcn.conv.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of STGCN gcn.7.tcn.conv.weight - torch.Size([256, 256, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.7.tcn.conv.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.7.tcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.7.tcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.7.residual.conv.weight - torch.Size([256, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.7.residual.conv.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.7.residual.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.7.residual.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.8.gcn.PA - torch.Size([3, 25, 25]): The value is the same before and after calling `init_weights` of STGCN gcn.8.gcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.8.gcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.8.gcn.conv.weight - torch.Size([768, 256, 1, 1]): The value is the same before and after calling `init_weights` of STGCN gcn.8.gcn.conv.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of STGCN gcn.8.tcn.conv.weight - torch.Size([256, 256, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.8.tcn.conv.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.8.tcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.8.tcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.9.gcn.PA - torch.Size([3, 25, 25]): The value is the same before and after calling `init_weights` of STGCN gcn.9.gcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.9.gcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.9.gcn.conv.weight - torch.Size([768, 256, 1, 1]): The value is the same before and after calling `init_weights` of STGCN gcn.9.gcn.conv.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of STGCN gcn.9.tcn.conv.weight - torch.Size([256, 256, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.9.tcn.conv.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.9.tcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.9.tcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN Name of parameter - Initialization information fc.weight - torch.Size([60, 256]): NormalInit: mean=0, std=0.01, bias=0 fc.bias - torch.Size([60]): NormalInit: mean=0, std=0.01, bias=0 2022/11/28 12:06:46 - mmengine - INFO - Checkpoints will be saved to /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d. 2022/11/28 12:06:52 - mmengine - INFO - Epoch(train) [1][100/1567] lr: 9.9996e-02 eta: 0:24:14 time: 0.0429 data_time: 0.0062 memory: 1793 loss: 2.6128 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.6128 2022/11/28 12:06:56 - mmengine - INFO - Epoch(train) [1][200/1567] lr: 9.9984e-02 eta: 0:21:05 time: 0.0433 data_time: 0.0061 memory: 1793 loss: 2.0128 top1_acc: 0.2500 top5_acc: 0.8125 loss_cls: 2.0128 2022/11/28 12:07:00 - mmengine - INFO - Epoch(train) [1][300/1567] lr: 9.9965e-02 eta: 0:19:57 time: 0.0432 data_time: 0.0061 memory: 1793 loss: 1.6664 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.6664 2022/11/28 12:07:05 - mmengine - INFO - Epoch(train) [1][400/1567] lr: 9.9938e-02 eta: 0:19:22 time: 0.0432 data_time: 0.0061 memory: 1793 loss: 1.4547 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.4547 2022/11/28 12:07:09 - mmengine - INFO - Epoch(train) [1][500/1567] lr: 9.9902e-02 eta: 0:18:58 time: 0.0439 data_time: 0.0062 memory: 1793 loss: 1.1767 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1767 2022/11/28 12:07:13 - mmengine - INFO - Epoch(train) [1][600/1567] lr: 9.9859e-02 eta: 0:18:44 time: 0.0437 data_time: 0.0060 memory: 1793 loss: 1.2310 top1_acc: 0.5625 top5_acc: 1.0000 loss_cls: 1.2310 2022/11/28 12:07:18 - mmengine - INFO - Epoch(train) [1][700/1567] lr: 9.9808e-02 eta: 0:18:33 time: 0.0435 data_time: 0.0059 memory: 1793 loss: 1.2069 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.2069 2022/11/28 12:07:22 - mmengine - INFO - Epoch(train) [1][800/1567] lr: 9.9750e-02 eta: 0:18:21 time: 0.0431 data_time: 0.0060 memory: 1793 loss: 1.0265 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0265 2022/11/28 12:07:27 - mmengine - INFO - Epoch(train) [1][900/1567] lr: 9.9683e-02 eta: 0:18:12 time: 0.0436 data_time: 0.0072 memory: 1793 loss: 1.0433 top1_acc: 0.4375 top5_acc: 0.9375 loss_cls: 1.0433 2022/11/28 12:07:31 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:07:31 - mmengine - INFO - Epoch(train) [1][1000/1567] lr: 9.9609e-02 eta: 0:18:04 time: 0.0436 data_time: 0.0066 memory: 1793 loss: 1.0029 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.0029 2022/11/28 12:07:35 - mmengine - INFO - Epoch(train) [1][1100/1567] lr: 9.9527e-02 eta: 0:17:58 time: 0.0467 data_time: 0.0067 memory: 1793 loss: 0.9329 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 0.9329 2022/11/28 12:07:40 - mmengine - INFO - Epoch(train) [1][1200/1567] lr: 9.9437e-02 eta: 0:17:49 time: 0.0433 data_time: 0.0060 memory: 1793 loss: 0.8987 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 0.8987 2022/11/28 12:07:44 - mmengine - INFO - Epoch(train) [1][1300/1567] lr: 9.9339e-02 eta: 0:17:43 time: 0.0431 data_time: 0.0059 memory: 1793 loss: 0.9946 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.9946 2022/11/28 12:07:48 - mmengine - INFO - Epoch(train) [1][1400/1567] lr: 9.9234e-02 eta: 0:17:36 time: 0.0428 data_time: 0.0060 memory: 1793 loss: 0.8520 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.8520 2022/11/28 12:07:53 - mmengine - INFO - Epoch(train) [1][1500/1567] lr: 9.9121e-02 eta: 0:17:29 time: 0.0429 data_time: 0.0061 memory: 1793 loss: 0.6940 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.6940 2022/11/28 12:07:56 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:07:56 - mmengine - INFO - Epoch(train) [1][1567/1567] lr: 9.9040e-02 eta: 0:17:25 time: 0.0430 data_time: 0.0057 memory: 1793 loss: 0.9343 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.9343 2022/11/28 12:07:56 - mmengine - INFO - Saving checkpoint at 1 epochs 2022/11/28 12:08:00 - mmengine - INFO - Epoch(val) [1][100/129] eta: 0:00:01 time: 0.0328 data_time: 0.0195 memory: 364 2022/11/28 12:08:01 - mmengine - INFO - Epoch(val) [1][129/129] acc/top1: 0.5216 acc/top5: 0.8359 acc/mean1: 0.5215 2022/11/28 12:08:01 - mmengine - INFO - The best checkpoint with 0.5216 acc/top1 at 1 epoch is saved to best_acc/top1_epoch_1.pth. 2022/11/28 12:08:05 - mmengine - INFO - Epoch(train) [2][100/1567] lr: 9.8914e-02 eta: 0:17:20 time: 0.0431 data_time: 0.0061 memory: 1793 loss: 0.7818 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.7818 2022/11/28 12:08:10 - mmengine - INFO - Epoch(train) [2][200/1567] lr: 9.8781e-02 eta: 0:17:15 time: 0.0440 data_time: 0.0061 memory: 1793 loss: 0.7274 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.7274 2022/11/28 12:08:14 - mmengine - INFO - Epoch(train) [2][300/1567] lr: 9.8639e-02 eta: 0:17:09 time: 0.0430 data_time: 0.0060 memory: 1793 loss: 0.7162 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.7162 2022/11/28 12:08:18 - mmengine - INFO - Epoch(train) [2][400/1567] lr: 9.8491e-02 eta: 0:17:03 time: 0.0431 data_time: 0.0060 memory: 1793 loss: 0.6954 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.6954 2022/11/28 12:08:20 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:08:23 - mmengine - INFO - Epoch(train) [2][500/1567] lr: 9.8334e-02 eta: 0:16:58 time: 0.0432 data_time: 0.0060 memory: 1793 loss: 0.7848 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.7848 2022/11/28 12:08:27 - mmengine - INFO - Epoch(train) [2][600/1567] lr: 9.8170e-02 eta: 0:16:52 time: 0.0431 data_time: 0.0064 memory: 1793 loss: 0.7269 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 0.7269 2022/11/28 12:08:32 - mmengine - INFO - Epoch(train) [2][700/1567] lr: 9.7998e-02 eta: 0:16:47 time: 0.0431 data_time: 0.0062 memory: 1793 loss: 0.6846 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.6846 2022/11/28 12:08:36 - mmengine - INFO - Epoch(train) [2][800/1567] lr: 9.7819e-02 eta: 0:16:42 time: 0.0428 data_time: 0.0060 memory: 1793 loss: 0.7032 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.7032 2022/11/28 12:08:40 - mmengine - INFO - Epoch(train) [2][900/1567] lr: 9.7632e-02 eta: 0:16:37 time: 0.0457 data_time: 0.0061 memory: 1793 loss: 0.7450 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.7450 2022/11/28 12:08:45 - mmengine - INFO - Epoch(train) [2][1000/1567] lr: 9.7438e-02 eta: 0:16:32 time: 0.0433 data_time: 0.0060 memory: 1793 loss: 0.6253 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.6253 2022/11/28 12:08:49 - mmengine - INFO - Epoch(train) [2][1100/1567] lr: 9.7236e-02 eta: 0:16:27 time: 0.0428 data_time: 0.0060 memory: 1793 loss: 0.6687 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.6687 2022/11/28 12:08:53 - mmengine - INFO - Epoch(train) [2][1200/1567] lr: 9.7027e-02 eta: 0:16:22 time: 0.0429 data_time: 0.0061 memory: 1793 loss: 0.6273 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.6273 2022/11/28 12:08:58 - mmengine - INFO - Epoch(train) [2][1300/1567] lr: 9.6810e-02 eta: 0:16:18 time: 0.0459 data_time: 0.0060 memory: 1793 loss: 0.6390 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.6390 2022/11/28 12:09:02 - mmengine - INFO - Epoch(train) [2][1400/1567] lr: 9.6587e-02 eta: 0:16:13 time: 0.0438 data_time: 0.0060 memory: 1793 loss: 0.7205 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.7205 2022/11/28 12:09:03 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:09:06 - mmengine - INFO - Epoch(train) [2][1500/1567] lr: 9.6355e-02 eta: 0:16:08 time: 0.0429 data_time: 0.0060 memory: 1793 loss: 0.6040 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.6040 2022/11/28 12:09:09 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:09:09 - mmengine - INFO - Epoch(train) [2][1567/1567] lr: 9.6196e-02 eta: 0:16:06 time: 0.0471 data_time: 0.0068 memory: 1793 loss: 0.7536 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.7536 2022/11/28 12:09:09 - mmengine - INFO - Saving checkpoint at 2 epochs 2022/11/28 12:09:13 - mmengine - INFO - Epoch(val) [2][100/129] eta: 0:00:00 time: 0.0335 data_time: 0.0202 memory: 364 2022/11/28 12:09:14 - mmengine - INFO - Epoch(val) [2][129/129] acc/top1: 0.5508 acc/top5: 0.8513 acc/mean1: 0.5507 2022/11/28 12:09:14 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_1.pth is removed 2022/11/28 12:09:15 - mmengine - INFO - The best checkpoint with 0.5508 acc/top1 at 2 epoch is saved to best_acc/top1_epoch_2.pth. 2022/11/28 12:09:19 - mmengine - INFO - Epoch(train) [3][100/1567] lr: 9.5953e-02 eta: 0:16:02 time: 0.0435 data_time: 0.0060 memory: 1793 loss: 0.6661 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 0.6661 2022/11/28 12:09:23 - mmengine - INFO - Epoch(train) [3][200/1567] lr: 9.5703e-02 eta: 0:15:57 time: 0.0428 data_time: 0.0061 memory: 1793 loss: 0.6839 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.6839 2022/11/28 12:09:28 - mmengine - INFO - Epoch(train) [3][300/1567] lr: 9.5445e-02 eta: 0:15:52 time: 0.0432 data_time: 0.0060 memory: 1793 loss: 0.5810 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.5810 2022/11/28 12:09:32 - mmengine - INFO - Epoch(train) [3][400/1567] lr: 9.5180e-02 eta: 0:15:47 time: 0.0433 data_time: 0.0061 memory: 1793 loss: 0.6940 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.6940 2022/11/28 12:09:36 - mmengine - INFO - Epoch(train) [3][500/1567] lr: 9.4908e-02 eta: 0:15:43 time: 0.0433 data_time: 0.0060 memory: 1793 loss: 0.6090 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6090 2022/11/28 12:09:41 - mmengine - INFO - Epoch(train) [3][600/1567] lr: 9.4629e-02 eta: 0:15:38 time: 0.0434 data_time: 0.0064 memory: 1793 loss: 0.6572 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.6572 2022/11/28 12:09:45 - mmengine - INFO - Epoch(train) [3][700/1567] lr: 9.4343e-02 eta: 0:15:34 time: 0.0433 data_time: 0.0065 memory: 1793 loss: 0.6637 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 0.6637 2022/11/28 12:09:50 - mmengine - INFO - Epoch(train) [3][800/1567] lr: 9.4050e-02 eta: 0:15:29 time: 0.0427 data_time: 0.0060 memory: 1793 loss: 0.6100 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.6100 2022/11/28 12:09:52 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:09:54 - mmengine - INFO - Epoch(train) [3][900/1567] lr: 9.3750e-02 eta: 0:15:24 time: 0.0450 data_time: 0.0061 memory: 1793 loss: 0.5820 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5820 2022/11/28 12:09:58 - mmengine - INFO - Epoch(train) [3][1000/1567] lr: 9.3444e-02 eta: 0:15:20 time: 0.0427 data_time: 0.0060 memory: 1793 loss: 0.5283 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.5283 2022/11/28 12:10:03 - mmengine - INFO - Epoch(train) [3][1100/1567] lr: 9.3130e-02 eta: 0:15:15 time: 0.0429 data_time: 0.0061 memory: 1793 loss: 0.6685 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.6685 2022/11/28 12:10:07 - mmengine - INFO - Epoch(train) [3][1200/1567] lr: 9.2810e-02 eta: 0:15:11 time: 0.0429 data_time: 0.0059 memory: 1793 loss: 0.4811 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4811 2022/11/28 12:10:11 - mmengine - INFO - Epoch(train) [3][1300/1567] lr: 9.2483e-02 eta: 0:15:06 time: 0.0430 data_time: 0.0060 memory: 1793 loss: 0.6201 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6201 2022/11/28 12:10:16 - mmengine - INFO - Epoch(train) [3][1400/1567] lr: 9.2149e-02 eta: 0:15:01 time: 0.0429 data_time: 0.0060 memory: 1793 loss: 0.6351 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.6351 2022/11/28 12:10:20 - mmengine - INFO - Epoch(train) [3][1500/1567] lr: 9.1809e-02 eta: 0:14:56 time: 0.0429 data_time: 0.0060 memory: 1793 loss: 0.5415 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5415 2022/11/28 12:10:23 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:10:23 - mmengine - INFO - Epoch(train) [3][1567/1567] lr: 9.1577e-02 eta: 0:14:53 time: 0.0419 data_time: 0.0058 memory: 1793 loss: 0.7037 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.7037 2022/11/28 12:10:23 - mmengine - INFO - Saving checkpoint at 3 epochs 2022/11/28 12:10:27 - mmengine - INFO - Epoch(val) [3][100/129] eta: 0:00:00 time: 0.0330 data_time: 0.0194 memory: 364 2022/11/28 12:10:28 - mmengine - INFO - Epoch(val) [3][129/129] acc/top1: 0.6335 acc/top5: 0.8936 acc/mean1: 0.6333 2022/11/28 12:10:28 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_2.pth is removed 2022/11/28 12:10:28 - mmengine - INFO - The best checkpoint with 0.6335 acc/top1 at 3 epoch is saved to best_acc/top1_epoch_3.pth. 2022/11/28 12:10:33 - mmengine - INFO - Epoch(train) [4][100/1567] lr: 9.1226e-02 eta: 0:14:50 time: 0.0433 data_time: 0.0062 memory: 1793 loss: 0.5518 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.5518 2022/11/28 12:10:37 - mmengine - INFO - Epoch(train) [4][200/1567] lr: 9.0868e-02 eta: 0:14:45 time: 0.0434 data_time: 0.0061 memory: 1793 loss: 0.5558 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5558 2022/11/28 12:10:41 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:10:41 - mmengine - INFO - Epoch(train) [4][300/1567] lr: 9.0504e-02 eta: 0:14:41 time: 0.0438 data_time: 0.0061 memory: 1793 loss: 0.5675 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5675 2022/11/28 12:10:46 - mmengine - INFO - Epoch(train) [4][400/1567] lr: 9.0133e-02 eta: 0:14:36 time: 0.0448 data_time: 0.0067 memory: 1793 loss: 0.5456 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5456 2022/11/28 12:10:50 - mmengine - INFO - Epoch(train) [4][500/1567] lr: 8.9756e-02 eta: 0:14:32 time: 0.0427 data_time: 0.0060 memory: 1793 loss: 0.6443 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.6443 2022/11/28 12:10:54 - mmengine - INFO - Epoch(train) [4][600/1567] lr: 8.9373e-02 eta: 0:14:27 time: 0.0439 data_time: 0.0061 memory: 1793 loss: 0.5925 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5925 2022/11/28 12:10:59 - mmengine - INFO - Epoch(train) [4][700/1567] lr: 8.8984e-02 eta: 0:14:23 time: 0.0427 data_time: 0.0060 memory: 1793 loss: 0.5421 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.5421 2022/11/28 12:11:03 - mmengine - INFO - Epoch(train) [4][800/1567] lr: 8.8589e-02 eta: 0:14:18 time: 0.0431 data_time: 0.0061 memory: 1793 loss: 0.5451 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.5451 2022/11/28 12:11:07 - mmengine - INFO - Epoch(train) [4][900/1567] lr: 8.8187e-02 eta: 0:14:13 time: 0.0427 data_time: 0.0061 memory: 1793 loss: 0.4505 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4505 2022/11/28 12:11:12 - mmengine - INFO - Epoch(train) [4][1000/1567] lr: 8.7780e-02 eta: 0:14:09 time: 0.0434 data_time: 0.0068 memory: 1793 loss: 0.5739 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.5739 2022/11/28 12:11:16 - mmengine - INFO - Epoch(train) [4][1100/1567] lr: 8.7367e-02 eta: 0:14:04 time: 0.0435 data_time: 0.0067 memory: 1793 loss: 0.5255 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5255 2022/11/28 12:11:20 - mmengine - INFO - Epoch(train) [4][1200/1567] lr: 8.6947e-02 eta: 0:14:00 time: 0.0432 data_time: 0.0066 memory: 1793 loss: 0.5318 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.5318 2022/11/28 12:11:25 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:11:25 - mmengine - INFO - Epoch(train) [4][1300/1567] lr: 8.6522e-02 eta: 0:13:55 time: 0.0436 data_time: 0.0068 memory: 1793 loss: 0.5821 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5821 2022/11/28 12:11:29 - mmengine - INFO - Epoch(train) [4][1400/1567] lr: 8.6092e-02 eta: 0:13:51 time: 0.0430 data_time: 0.0062 memory: 1793 loss: 0.4059 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4059 2022/11/28 12:11:33 - mmengine - INFO - Epoch(train) [4][1500/1567] lr: 8.5655e-02 eta: 0:13:46 time: 0.0433 data_time: 0.0061 memory: 1793 loss: 0.4384 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4384 2022/11/28 12:11:36 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:11:36 - mmengine - INFO - Epoch(train) [4][1567/1567] lr: 8.5360e-02 eta: 0:13:43 time: 0.0421 data_time: 0.0058 memory: 1793 loss: 0.6341 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.6341 2022/11/28 12:11:36 - mmengine - INFO - Saving checkpoint at 4 epochs 2022/11/28 12:11:40 - mmengine - INFO - Epoch(val) [4][100/129] eta: 0:00:01 time: 0.0334 data_time: 0.0199 memory: 364 2022/11/28 12:11:41 - mmengine - INFO - Epoch(val) [4][129/129] acc/top1: 0.6539 acc/top5: 0.9237 acc/mean1: 0.6538 2022/11/28 12:11:41 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_3.pth is removed 2022/11/28 12:11:42 - mmengine - INFO - The best checkpoint with 0.6539 acc/top1 at 4 epoch is saved to best_acc/top1_epoch_4.pth. 2022/11/28 12:11:46 - mmengine - INFO - Epoch(train) [5][100/1567] lr: 8.4914e-02 eta: 0:13:39 time: 0.0428 data_time: 0.0061 memory: 1793 loss: 0.4897 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4897 2022/11/28 12:11:50 - mmengine - INFO - Epoch(train) [5][200/1567] lr: 8.4463e-02 eta: 0:13:34 time: 0.0430 data_time: 0.0061 memory: 1793 loss: 0.5168 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.5168 2022/11/28 12:11:55 - mmengine - INFO - Epoch(train) [5][300/1567] lr: 8.4006e-02 eta: 0:13:30 time: 0.0436 data_time: 0.0061 memory: 1793 loss: 0.5332 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5332 2022/11/28 12:11:59 - mmengine - INFO - Epoch(train) [5][400/1567] lr: 8.3544e-02 eta: 0:13:25 time: 0.0433 data_time: 0.0060 memory: 1793 loss: 0.4444 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.4444 2022/11/28 12:12:03 - mmengine - INFO - Epoch(train) [5][500/1567] lr: 8.3077e-02 eta: 0:13:21 time: 0.0427 data_time: 0.0061 memory: 1793 loss: 0.4703 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.4703 2022/11/28 12:12:08 - mmengine - INFO - Epoch(train) [5][600/1567] lr: 8.2605e-02 eta: 0:13:16 time: 0.0428 data_time: 0.0062 memory: 1793 loss: 0.4969 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.4969 2022/11/28 12:12:12 - mmengine - INFO - Epoch(train) [5][700/1567] lr: 8.2127e-02 eta: 0:13:12 time: 0.0427 data_time: 0.0060 memory: 1793 loss: 0.4893 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4893 2022/11/28 12:12:13 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:12:16 - mmengine - INFO - Epoch(train) [5][800/1567] lr: 8.1645e-02 eta: 0:13:07 time: 0.0429 data_time: 0.0061 memory: 1793 loss: 0.5201 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.5201 2022/11/28 12:12:21 - mmengine - INFO - Epoch(train) [5][900/1567] lr: 8.1157e-02 eta: 0:13:03 time: 0.0428 data_time: 0.0061 memory: 1793 loss: 0.4955 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4955 2022/11/28 12:12:25 - mmengine - INFO - Epoch(train) [5][1000/1567] lr: 8.0665e-02 eta: 0:12:58 time: 0.0433 data_time: 0.0065 memory: 1793 loss: 0.4992 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4992 2022/11/28 12:12:29 - mmengine - INFO - Epoch(train) [5][1100/1567] lr: 8.0167e-02 eta: 0:12:54 time: 0.0437 data_time: 0.0062 memory: 1793 loss: 0.4616 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.4616 2022/11/28 12:12:34 - mmengine - INFO - Epoch(train) [5][1200/1567] lr: 7.9665e-02 eta: 0:12:49 time: 0.0432 data_time: 0.0065 memory: 1793 loss: 0.5403 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.5403 2022/11/28 12:12:38 - mmengine - INFO - Epoch(train) [5][1300/1567] lr: 7.9159e-02 eta: 0:12:45 time: 0.0432 data_time: 0.0065 memory: 1793 loss: 0.4064 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4064 2022/11/28 12:12:42 - mmengine - INFO - Epoch(train) [5][1400/1567] lr: 7.8647e-02 eta: 0:12:41 time: 0.0470 data_time: 0.0096 memory: 1793 loss: 0.5754 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.5754 2022/11/28 12:12:47 - mmengine - INFO - Epoch(train) [5][1500/1567] lr: 7.8132e-02 eta: 0:12:36 time: 0.0436 data_time: 0.0061 memory: 1793 loss: 0.4952 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4952 2022/11/28 12:12:50 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:12:50 - mmengine - INFO - Epoch(train) [5][1567/1567] lr: 7.7784e-02 eta: 0:12:33 time: 0.0420 data_time: 0.0058 memory: 1793 loss: 0.5911 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.5911 2022/11/28 12:12:50 - mmengine - INFO - Saving checkpoint at 5 epochs 2022/11/28 12:12:53 - mmengine - INFO - Epoch(val) [5][100/129] eta: 0:00:01 time: 0.0328 data_time: 0.0191 memory: 364 2022/11/28 12:12:55 - mmengine - INFO - Epoch(val) [5][129/129] acc/top1: 0.6873 acc/top5: 0.9262 acc/mean1: 0.6873 2022/11/28 12:12:55 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_4.pth is removed 2022/11/28 12:12:55 - mmengine - INFO - The best checkpoint with 0.6873 acc/top1 at 5 epoch is saved to best_acc/top1_epoch_5.pth. 2022/11/28 12:13:00 - mmengine - INFO - Epoch(train) [6][100/1567] lr: 7.7261e-02 eta: 0:12:29 time: 0.0440 data_time: 0.0069 memory: 1793 loss: 0.4600 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4600 2022/11/28 12:13:02 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:13:04 - mmengine - INFO - Epoch(train) [6][200/1567] lr: 7.6733e-02 eta: 0:12:25 time: 0.0435 data_time: 0.0060 memory: 1793 loss: 0.5861 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5861 2022/11/28 12:13:08 - mmengine - INFO - Epoch(train) [6][300/1567] lr: 7.6202e-02 eta: 0:12:21 time: 0.0434 data_time: 0.0066 memory: 1793 loss: 0.3842 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3842 2022/11/28 12:13:13 - mmengine - INFO - Epoch(train) [6][400/1567] lr: 7.5666e-02 eta: 0:12:16 time: 0.0431 data_time: 0.0059 memory: 1793 loss: 0.4143 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.4143 2022/11/28 12:13:17 - mmengine - INFO - Epoch(train) [6][500/1567] lr: 7.5126e-02 eta: 0:12:12 time: 0.0443 data_time: 0.0064 memory: 1793 loss: 0.5370 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5370 2022/11/28 12:13:21 - mmengine - INFO - Epoch(train) [6][600/1567] lr: 7.4583e-02 eta: 0:12:07 time: 0.0435 data_time: 0.0071 memory: 1793 loss: 0.4578 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4578 2022/11/28 12:13:26 - mmengine - INFO - Epoch(train) [6][700/1567] lr: 7.4035e-02 eta: 0:12:03 time: 0.0437 data_time: 0.0061 memory: 1793 loss: 0.4663 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4663 2022/11/28 12:13:30 - mmengine - INFO - Epoch(train) [6][800/1567] lr: 7.3484e-02 eta: 0:11:59 time: 0.0433 data_time: 0.0060 memory: 1793 loss: 0.4676 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4676 2022/11/28 12:13:35 - mmengine - INFO - Epoch(train) [6][900/1567] lr: 7.2929e-02 eta: 0:11:54 time: 0.0434 data_time: 0.0060 memory: 1793 loss: 0.5048 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.5048 2022/11/28 12:13:39 - mmengine - INFO - Epoch(train) [6][1000/1567] lr: 7.2371e-02 eta: 0:11:50 time: 0.0440 data_time: 0.0067 memory: 1793 loss: 0.4425 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4425 2022/11/28 12:13:43 - mmengine - INFO - Epoch(train) [6][1100/1567] lr: 7.1809e-02 eta: 0:11:45 time: 0.0431 data_time: 0.0064 memory: 1793 loss: 0.4515 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4515 2022/11/28 12:13:46 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:13:48 - mmengine - INFO - Epoch(train) [6][1200/1567] lr: 7.1243e-02 eta: 0:11:41 time: 0.0433 data_time: 0.0062 memory: 1793 loss: 0.4439 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4439 2022/11/28 12:13:52 - mmengine - INFO - Epoch(train) [6][1300/1567] lr: 7.0674e-02 eta: 0:11:37 time: 0.0434 data_time: 0.0062 memory: 1793 loss: 0.3931 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 0.3931 2022/11/28 12:13:56 - mmengine - INFO - Epoch(train) [6][1400/1567] lr: 7.0102e-02 eta: 0:11:32 time: 0.0434 data_time: 0.0063 memory: 1793 loss: 0.4138 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.4138 2022/11/28 12:14:01 - mmengine - INFO - Epoch(train) [6][1500/1567] lr: 6.9527e-02 eta: 0:11:28 time: 0.0434 data_time: 0.0065 memory: 1793 loss: 0.4853 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4853 2022/11/28 12:14:04 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:14:04 - mmengine - INFO - Epoch(train) [6][1567/1567] lr: 6.9140e-02 eta: 0:11:25 time: 0.0419 data_time: 0.0059 memory: 1793 loss: 0.5021 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.5021 2022/11/28 12:14:04 - mmengine - INFO - Saving checkpoint at 6 epochs 2022/11/28 12:14:07 - mmengine - INFO - Epoch(val) [6][100/129] eta: 0:00:00 time: 0.0341 data_time: 0.0207 memory: 364 2022/11/28 12:14:09 - mmengine - INFO - Epoch(val) [6][129/129] acc/top1: 0.7035 acc/top5: 0.9332 acc/mean1: 0.7035 2022/11/28 12:14:09 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_5.pth is removed 2022/11/28 12:14:09 - mmengine - INFO - The best checkpoint with 0.7035 acc/top1 at 6 epoch is saved to best_acc/top1_epoch_6.pth. 2022/11/28 12:14:13 - mmengine - INFO - Epoch(train) [7][100/1567] lr: 6.8560e-02 eta: 0:11:21 time: 0.0429 data_time: 0.0061 memory: 1793 loss: 0.4087 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.4087 2022/11/28 12:14:18 - mmengine - INFO - Epoch(train) [7][200/1567] lr: 6.7976e-02 eta: 0:11:16 time: 0.0432 data_time: 0.0061 memory: 1793 loss: 0.4648 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4648 2022/11/28 12:14:22 - mmengine - INFO - Epoch(train) [7][300/1567] lr: 6.7390e-02 eta: 0:11:12 time: 0.0429 data_time: 0.0061 memory: 1793 loss: 0.4144 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4144 2022/11/28 12:14:26 - mmengine - INFO - Epoch(train) [7][400/1567] lr: 6.6802e-02 eta: 0:11:08 time: 0.0432 data_time: 0.0060 memory: 1793 loss: 0.4000 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4000 2022/11/28 12:14:31 - mmengine - INFO - Epoch(train) [7][500/1567] lr: 6.6210e-02 eta: 0:11:03 time: 0.0433 data_time: 0.0060 memory: 1793 loss: 0.4251 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4251 2022/11/28 12:14:35 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:14:35 - mmengine - INFO - Epoch(train) [7][600/1567] lr: 6.5616e-02 eta: 0:10:59 time: 0.0427 data_time: 0.0061 memory: 1793 loss: 0.3518 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3518 2022/11/28 12:14:39 - mmengine - INFO - Epoch(train) [7][700/1567] lr: 6.5020e-02 eta: 0:10:54 time: 0.0443 data_time: 0.0060 memory: 1793 loss: 0.3916 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3916 2022/11/28 12:14:44 - mmengine - INFO - Epoch(train) [7][800/1567] lr: 6.4421e-02 eta: 0:10:50 time: 0.0434 data_time: 0.0061 memory: 1793 loss: 0.4876 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4876 2022/11/28 12:14:48 - mmengine - INFO - Epoch(train) [7][900/1567] lr: 6.3820e-02 eta: 0:10:45 time: 0.0435 data_time: 0.0060 memory: 1793 loss: 0.4104 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4104 2022/11/28 12:14:53 - mmengine - INFO - Epoch(train) [7][1000/1567] lr: 6.3217e-02 eta: 0:10:41 time: 0.0427 data_time: 0.0060 memory: 1793 loss: 0.3714 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3714 2022/11/28 12:14:57 - mmengine - INFO - Epoch(train) [7][1100/1567] lr: 6.2612e-02 eta: 0:10:37 time: 0.0431 data_time: 0.0060 memory: 1793 loss: 0.3962 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3962 2022/11/28 12:15:01 - mmengine - INFO - Epoch(train) [7][1200/1567] lr: 6.2005e-02 eta: 0:10:32 time: 0.0431 data_time: 0.0061 memory: 1793 loss: 0.3686 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3686 2022/11/28 12:15:06 - mmengine - INFO - Epoch(train) [7][1300/1567] lr: 6.1396e-02 eta: 0:10:28 time: 0.0432 data_time: 0.0060 memory: 1793 loss: 0.3130 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3130 2022/11/28 12:15:10 - mmengine - INFO - Epoch(train) [7][1400/1567] lr: 6.0785e-02 eta: 0:10:23 time: 0.0438 data_time: 0.0060 memory: 1793 loss: 0.3571 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3571 2022/11/28 12:15:14 - mmengine - INFO - Epoch(train) [7][1500/1567] lr: 6.0172e-02 eta: 0:10:19 time: 0.0435 data_time: 0.0060 memory: 1793 loss: 0.2710 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2710 2022/11/28 12:15:17 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:15:17 - mmengine - INFO - Epoch(train) [7][1567/1567] lr: 5.9761e-02 eta: 0:10:16 time: 0.0425 data_time: 0.0058 memory: 1793 loss: 0.4948 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.4948 2022/11/28 12:15:17 - mmengine - INFO - Saving checkpoint at 7 epochs 2022/11/28 12:15:21 - mmengine - INFO - Epoch(val) [7][100/129] eta: 0:00:00 time: 0.0327 data_time: 0.0193 memory: 364 2022/11/28 12:15:22 - mmengine - INFO - Epoch(val) [7][129/129] acc/top1: 0.5994 acc/top5: 0.8750 acc/mean1: 0.5992 2022/11/28 12:15:24 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:15:27 - mmengine - INFO - Epoch(train) [8][100/1567] lr: 5.9145e-02 eta: 0:10:12 time: 0.0443 data_time: 0.0062 memory: 1793 loss: 0.3939 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.3939 2022/11/28 12:15:31 - mmengine - INFO - Epoch(train) [8][200/1567] lr: 5.8529e-02 eta: 0:10:08 time: 0.0442 data_time: 0.0060 memory: 1793 loss: 0.5436 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.5436 2022/11/28 12:15:35 - mmengine - INFO - Epoch(train) [8][300/1567] lr: 5.7911e-02 eta: 0:10:03 time: 0.0437 data_time: 0.0066 memory: 1793 loss: 0.4186 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4186 2022/11/28 12:15:40 - mmengine - INFO - Epoch(train) [8][400/1567] lr: 5.7292e-02 eta: 0:09:59 time: 0.0438 data_time: 0.0063 memory: 1793 loss: 0.3211 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.3211 2022/11/28 12:15:44 - mmengine - INFO - Epoch(train) [8][500/1567] lr: 5.6671e-02 eta: 0:09:54 time: 0.0429 data_time: 0.0062 memory: 1793 loss: 0.3863 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.3863 2022/11/28 12:15:48 - mmengine - INFO - Epoch(train) [8][600/1567] lr: 5.6050e-02 eta: 0:09:50 time: 0.0432 data_time: 0.0060 memory: 1793 loss: 0.3514 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3514 2022/11/28 12:15:53 - mmengine - INFO - Epoch(train) [8][700/1567] lr: 5.5427e-02 eta: 0:09:46 time: 0.0434 data_time: 0.0060 memory: 1793 loss: 0.3131 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3131 2022/11/28 12:15:57 - mmengine - INFO - Epoch(train) [8][800/1567] lr: 5.4804e-02 eta: 0:09:41 time: 0.0437 data_time: 0.0067 memory: 1793 loss: 0.3958 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3958 2022/11/28 12:16:02 - mmengine - INFO - Epoch(train) [8][900/1567] lr: 5.4180e-02 eta: 0:09:37 time: 0.0436 data_time: 0.0060 memory: 1793 loss: 0.3324 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3324 2022/11/28 12:16:06 - mmengine - INFO - Epoch(train) [8][1000/1567] lr: 5.3556e-02 eta: 0:09:33 time: 0.0433 data_time: 0.0060 memory: 1793 loss: 0.2581 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2581 2022/11/28 12:16:07 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:16:10 - mmengine - INFO - Epoch(train) [8][1100/1567] lr: 5.2930e-02 eta: 0:09:28 time: 0.0439 data_time: 0.0060 memory: 1793 loss: 0.3296 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3296 2022/11/28 12:16:15 - mmengine - INFO - Epoch(train) [8][1200/1567] lr: 5.2305e-02 eta: 0:09:24 time: 0.0439 data_time: 0.0059 memory: 1793 loss: 0.3446 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3446 2022/11/28 12:16:19 - mmengine - INFO - Epoch(train) [8][1300/1567] lr: 5.1679e-02 eta: 0:09:19 time: 0.0430 data_time: 0.0059 memory: 1793 loss: 0.3376 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.3376 2022/11/28 12:16:24 - mmengine - INFO - Epoch(train) [8][1400/1567] lr: 5.1052e-02 eta: 0:09:15 time: 0.0431 data_time: 0.0061 memory: 1793 loss: 0.2755 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2755 2022/11/28 12:16:28 - mmengine - INFO - Epoch(train) [8][1500/1567] lr: 5.0426e-02 eta: 0:09:11 time: 0.0437 data_time: 0.0066 memory: 1793 loss: 0.2824 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2824 2022/11/28 12:16:31 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:16:31 - mmengine - INFO - Epoch(train) [8][1567/1567] lr: 5.0006e-02 eta: 0:09:08 time: 0.0421 data_time: 0.0058 memory: 1793 loss: 0.3632 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.3632 2022/11/28 12:16:31 - mmengine - INFO - Saving checkpoint at 8 epochs 2022/11/28 12:16:35 - mmengine - INFO - Epoch(val) [8][100/129] eta: 0:00:00 time: 0.0326 data_time: 0.0192 memory: 364 2022/11/28 12:16:36 - mmengine - INFO - Epoch(val) [8][129/129] acc/top1: 0.7029 acc/top5: 0.9281 acc/mean1: 0.7029 2022/11/28 12:16:40 - mmengine - INFO - Epoch(train) [9][100/1567] lr: 4.9380e-02 eta: 0:09:03 time: 0.0439 data_time: 0.0067 memory: 1793 loss: 0.3814 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.3814 2022/11/28 12:16:45 - mmengine - INFO - Epoch(train) [9][200/1567] lr: 4.8753e-02 eta: 0:08:59 time: 0.0434 data_time: 0.0060 memory: 1793 loss: 0.2716 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2716 2022/11/28 12:16:49 - mmengine - INFO - Epoch(train) [9][300/1567] lr: 4.8127e-02 eta: 0:08:55 time: 0.0449 data_time: 0.0073 memory: 1793 loss: 0.3126 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3126 2022/11/28 12:16:54 - mmengine - INFO - Epoch(train) [9][400/1567] lr: 4.7501e-02 eta: 0:08:51 time: 0.0434 data_time: 0.0062 memory: 1793 loss: 0.2691 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2691 2022/11/28 12:16:56 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:16:58 - mmengine - INFO - Epoch(train) [9][500/1567] lr: 4.6876e-02 eta: 0:08:46 time: 0.0436 data_time: 0.0065 memory: 1793 loss: 0.3229 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3229 2022/11/28 12:17:02 - mmengine - INFO - Epoch(train) [9][600/1567] lr: 4.6251e-02 eta: 0:08:42 time: 0.0438 data_time: 0.0061 memory: 1793 loss: 0.2509 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2509 2022/11/28 12:17:07 - mmengine - INFO - Epoch(train) [9][700/1567] lr: 4.5626e-02 eta: 0:08:37 time: 0.0439 data_time: 0.0062 memory: 1793 loss: 0.2787 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2787 2022/11/28 12:17:11 - mmengine - INFO - Epoch(train) [9][800/1567] lr: 4.5003e-02 eta: 0:08:33 time: 0.0438 data_time: 0.0061 memory: 1793 loss: 0.2639 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2639 2022/11/28 12:17:16 - mmengine - INFO - Epoch(train) [9][900/1567] lr: 4.4380e-02 eta: 0:08:29 time: 0.0434 data_time: 0.0060 memory: 1793 loss: 0.3074 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3074 2022/11/28 12:17:20 - mmengine - INFO - Epoch(train) [9][1000/1567] lr: 4.3757e-02 eta: 0:08:24 time: 0.0434 data_time: 0.0059 memory: 1793 loss: 0.3299 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.3299 2022/11/28 12:17:24 - mmengine - INFO - Epoch(train) [9][1100/1567] lr: 4.3136e-02 eta: 0:08:20 time: 0.0463 data_time: 0.0080 memory: 1793 loss: 0.2702 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2702 2022/11/28 12:17:29 - mmengine - INFO - Epoch(train) [9][1200/1567] lr: 4.2516e-02 eta: 0:08:16 time: 0.0429 data_time: 0.0061 memory: 1793 loss: 0.2088 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2088 2022/11/28 12:17:33 - mmengine - INFO - Epoch(train) [9][1300/1567] lr: 4.1897e-02 eta: 0:08:11 time: 0.0430 data_time: 0.0061 memory: 1793 loss: 0.3106 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3106 2022/11/28 12:17:37 - mmengine - INFO - Epoch(train) [9][1400/1567] lr: 4.1280e-02 eta: 0:08:07 time: 0.0432 data_time: 0.0060 memory: 1793 loss: 0.2725 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2725 2022/11/28 12:17:40 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:17:42 - mmengine - INFO - Epoch(train) [9][1500/1567] lr: 4.0664e-02 eta: 0:08:02 time: 0.0439 data_time: 0.0061 memory: 1793 loss: 0.2794 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2794 2022/11/28 12:17:44 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:17:44 - mmengine - INFO - Epoch(train) [9][1567/1567] lr: 4.0252e-02 eta: 0:07:59 time: 0.0419 data_time: 0.0058 memory: 1793 loss: 0.4480 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.4480 2022/11/28 12:17:44 - mmengine - INFO - Saving checkpoint at 9 epochs 2022/11/28 12:17:48 - mmengine - INFO - Epoch(val) [9][100/129] eta: 0:00:00 time: 0.0332 data_time: 0.0193 memory: 364 2022/11/28 12:17:49 - mmengine - INFO - Epoch(val) [9][129/129] acc/top1: 0.7581 acc/top5: 0.9467 acc/mean1: 0.7578 2022/11/28 12:17:49 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_6.pth is removed 2022/11/28 12:17:50 - mmengine - INFO - The best checkpoint with 0.7581 acc/top1 at 9 epoch is saved to best_acc/top1_epoch_9.pth. 2022/11/28 12:17:54 - mmengine - INFO - Epoch(train) [10][100/1567] lr: 3.9638e-02 eta: 0:07:55 time: 0.0439 data_time: 0.0068 memory: 1793 loss: 0.1702 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1702 2022/11/28 12:17:59 - mmengine - INFO - Epoch(train) [10][200/1567] lr: 3.9026e-02 eta: 0:07:51 time: 0.0436 data_time: 0.0067 memory: 1793 loss: 0.2445 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2445 2022/11/28 12:18:03 - mmengine - INFO - Epoch(train) [10][300/1567] lr: 3.8415e-02 eta: 0:07:46 time: 0.0433 data_time: 0.0063 memory: 1793 loss: 0.3176 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3176 2022/11/28 12:18:07 - mmengine - INFO - Epoch(train) [10][400/1567] lr: 3.7807e-02 eta: 0:07:42 time: 0.0431 data_time: 0.0061 memory: 1793 loss: 0.2449 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2449 2022/11/28 12:18:12 - mmengine - INFO - Epoch(train) [10][500/1567] lr: 3.7200e-02 eta: 0:07:38 time: 0.0431 data_time: 0.0062 memory: 1793 loss: 0.3030 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3030 2022/11/28 12:18:16 - mmengine - INFO - Epoch(train) [10][600/1567] lr: 3.6596e-02 eta: 0:07:33 time: 0.0432 data_time: 0.0061 memory: 1793 loss: 0.2291 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2291 2022/11/28 12:18:20 - mmengine - INFO - Epoch(train) [10][700/1567] lr: 3.5993e-02 eta: 0:07:29 time: 0.0430 data_time: 0.0061 memory: 1793 loss: 0.1939 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1939 2022/11/28 12:18:25 - mmengine - INFO - Epoch(train) [10][800/1567] lr: 3.5393e-02 eta: 0:07:24 time: 0.0435 data_time: 0.0061 memory: 1793 loss: 0.2143 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2143 2022/11/28 12:18:29 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:18:29 - mmengine - INFO - Epoch(train) [10][900/1567] lr: 3.4795e-02 eta: 0:07:20 time: 0.0437 data_time: 0.0061 memory: 1793 loss: 0.2842 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.2842 2022/11/28 12:18:33 - mmengine - INFO - Epoch(train) [10][1000/1567] lr: 3.4199e-02 eta: 0:07:16 time: 0.0435 data_time: 0.0061 memory: 1793 loss: 0.1886 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1886 2022/11/28 12:18:38 - mmengine - INFO - Epoch(train) [10][1100/1567] lr: 3.3606e-02 eta: 0:07:11 time: 0.0438 data_time: 0.0061 memory: 1793 loss: 0.2936 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2936 2022/11/28 12:18:42 - mmengine - INFO - Epoch(train) [10][1200/1567] lr: 3.3015e-02 eta: 0:07:07 time: 0.0434 data_time: 0.0061 memory: 1793 loss: 0.2431 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2431 2022/11/28 12:18:46 - mmengine - INFO - Epoch(train) [10][1300/1567] lr: 3.2428e-02 eta: 0:07:02 time: 0.0438 data_time: 0.0060 memory: 1793 loss: 0.2478 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2478 2022/11/28 12:18:51 - mmengine - INFO - Epoch(train) [10][1400/1567] lr: 3.1842e-02 eta: 0:06:58 time: 0.0432 data_time: 0.0061 memory: 1793 loss: 0.2258 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2258 2022/11/28 12:18:55 - mmengine - INFO - Epoch(train) [10][1500/1567] lr: 3.1260e-02 eta: 0:06:54 time: 0.0442 data_time: 0.0061 memory: 1793 loss: 0.2145 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2145 2022/11/28 12:18:58 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:18:58 - mmengine - INFO - Epoch(train) [10][1567/1567] lr: 3.0872e-02 eta: 0:06:51 time: 0.0424 data_time: 0.0059 memory: 1793 loss: 0.3102 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3102 2022/11/28 12:18:58 - mmengine - INFO - Saving checkpoint at 10 epochs 2022/11/28 12:19:02 - mmengine - INFO - Epoch(val) [10][100/129] eta: 0:00:00 time: 0.0329 data_time: 0.0196 memory: 364 2022/11/28 12:19:03 - mmengine - INFO - Epoch(val) [10][129/129] acc/top1: 0.7719 acc/top5: 0.9478 acc/mean1: 0.7719 2022/11/28 12:19:03 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_9.pth is removed 2022/11/28 12:19:03 - mmengine - INFO - The best checkpoint with 0.7719 acc/top1 at 10 epoch is saved to best_acc/top1_epoch_10.pth. 2022/11/28 12:19:08 - mmengine - INFO - Epoch(train) [11][100/1567] lr: 3.0294e-02 eta: 0:06:46 time: 0.0427 data_time: 0.0061 memory: 1793 loss: 0.2021 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2021 2022/11/28 12:19:12 - mmengine - INFO - Epoch(train) [11][200/1567] lr: 2.9720e-02 eta: 0:06:42 time: 0.0439 data_time: 0.0062 memory: 1793 loss: 0.1870 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1870 2022/11/28 12:19:17 - mmengine - INFO - Epoch(train) [11][300/1567] lr: 2.9149e-02 eta: 0:06:38 time: 0.0443 data_time: 0.0063 memory: 1793 loss: 0.2617 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2617 2022/11/28 12:19:18 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:19:21 - mmengine - INFO - Epoch(train) [11][400/1567] lr: 2.8581e-02 eta: 0:06:33 time: 0.0429 data_time: 0.0060 memory: 1793 loss: 0.2014 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2014 2022/11/28 12:19:26 - mmengine - INFO - Epoch(train) [11][500/1567] lr: 2.8017e-02 eta: 0:06:29 time: 0.0434 data_time: 0.0065 memory: 1793 loss: 0.1925 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1925 2022/11/28 12:19:30 - mmengine - INFO - Epoch(train) [11][600/1567] lr: 2.7456e-02 eta: 0:06:25 time: 0.0430 data_time: 0.0060 memory: 1793 loss: 0.2950 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.2950 2022/11/28 12:19:34 - mmengine - INFO - Epoch(train) [11][700/1567] lr: 2.6898e-02 eta: 0:06:20 time: 0.0430 data_time: 0.0061 memory: 1793 loss: 0.1663 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1663 2022/11/28 12:19:39 - mmengine - INFO - Epoch(train) [11][800/1567] lr: 2.6345e-02 eta: 0:06:16 time: 0.0434 data_time: 0.0062 memory: 1793 loss: 0.1895 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1895 2022/11/28 12:19:43 - mmengine - INFO - Epoch(train) [11][900/1567] lr: 2.5794e-02 eta: 0:06:11 time: 0.0434 data_time: 0.0060 memory: 1793 loss: 0.1771 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.1771 2022/11/28 12:19:47 - mmengine - INFO - Epoch(train) [11][1000/1567] lr: 2.5248e-02 eta: 0:06:07 time: 0.0444 data_time: 0.0065 memory: 1793 loss: 0.1413 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1413 2022/11/28 12:19:52 - mmengine - INFO - Epoch(train) [11][1100/1567] lr: 2.4706e-02 eta: 0:06:03 time: 0.0464 data_time: 0.0067 memory: 1793 loss: 0.1642 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1642 2022/11/28 12:19:56 - mmengine - INFO - Epoch(train) [11][1200/1567] lr: 2.4167e-02 eta: 0:05:58 time: 0.0461 data_time: 0.0060 memory: 1793 loss: 0.1263 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1263 2022/11/28 12:20:01 - mmengine - INFO - Epoch(train) [11][1300/1567] lr: 2.3633e-02 eta: 0:05:54 time: 0.0432 data_time: 0.0061 memory: 1793 loss: 0.1503 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1503 2022/11/28 12:20:02 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:20:05 - mmengine - INFO - Epoch(train) [11][1400/1567] lr: 2.3103e-02 eta: 0:05:50 time: 0.0432 data_time: 0.0061 memory: 1793 loss: 0.1532 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1532 2022/11/28 12:20:10 - mmengine - INFO - Epoch(train) [11][1500/1567] lr: 2.2577e-02 eta: 0:05:45 time: 0.0440 data_time: 0.0062 memory: 1793 loss: 0.1477 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1477 2022/11/28 12:20:12 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:20:12 - mmengine - INFO - Epoch(train) [11][1567/1567] lr: 2.2227e-02 eta: 0:05:42 time: 0.0431 data_time: 0.0064 memory: 1793 loss: 0.2904 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.2904 2022/11/28 12:20:12 - mmengine - INFO - Saving checkpoint at 11 epochs 2022/11/28 12:20:16 - mmengine - INFO - Epoch(val) [11][100/129] eta: 0:00:00 time: 0.0325 data_time: 0.0191 memory: 364 2022/11/28 12:20:17 - mmengine - INFO - Epoch(val) [11][129/129] acc/top1: 0.8136 acc/top5: 0.9617 acc/mean1: 0.8135 2022/11/28 12:20:17 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_10.pth is removed 2022/11/28 12:20:18 - mmengine - INFO - The best checkpoint with 0.8136 acc/top1 at 11 epoch is saved to best_acc/top1_epoch_11.pth. 2022/11/28 12:20:22 - mmengine - INFO - Epoch(train) [12][100/1567] lr: 2.1708e-02 eta: 0:05:38 time: 0.0466 data_time: 0.0061 memory: 1793 loss: 0.1819 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1819 2022/11/28 12:20:27 - mmengine - INFO - Epoch(train) [12][200/1567] lr: 2.1194e-02 eta: 0:05:34 time: 0.0435 data_time: 0.0061 memory: 1793 loss: 0.1523 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1523 2022/11/28 12:20:31 - mmengine - INFO - Epoch(train) [12][300/1567] lr: 2.0684e-02 eta: 0:05:29 time: 0.0437 data_time: 0.0061 memory: 1793 loss: 0.1064 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1064 2022/11/28 12:20:36 - mmengine - INFO - Epoch(train) [12][400/1567] lr: 2.0179e-02 eta: 0:05:25 time: 0.0477 data_time: 0.0061 memory: 1793 loss: 0.1289 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1289 2022/11/28 12:20:40 - mmengine - INFO - Epoch(train) [12][500/1567] lr: 1.9678e-02 eta: 0:05:21 time: 0.0449 data_time: 0.0061 memory: 1793 loss: 0.1252 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1252 2022/11/28 12:20:44 - mmengine - INFO - Epoch(train) [12][600/1567] lr: 1.9182e-02 eta: 0:05:16 time: 0.0435 data_time: 0.0065 memory: 1793 loss: 0.1229 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1229 2022/11/28 12:20:49 - mmengine - INFO - Epoch(train) [12][700/1567] lr: 1.8691e-02 eta: 0:05:12 time: 0.0437 data_time: 0.0066 memory: 1793 loss: 0.1323 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1323 2022/11/28 12:20:52 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:20:53 - mmengine - INFO - Epoch(train) [12][800/1567] lr: 1.8205e-02 eta: 0:05:08 time: 0.0434 data_time: 0.0061 memory: 1793 loss: 0.1397 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1397 2022/11/28 12:20:58 - mmengine - INFO - Epoch(train) [12][900/1567] lr: 1.7724e-02 eta: 0:05:03 time: 0.0441 data_time: 0.0061 memory: 1793 loss: 0.1582 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1582 2022/11/28 12:21:02 - mmengine - INFO - Epoch(train) [12][1000/1567] lr: 1.7248e-02 eta: 0:04:59 time: 0.0451 data_time: 0.0066 memory: 1793 loss: 0.1141 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1141 2022/11/28 12:21:06 - mmengine - INFO - Epoch(train) [12][1100/1567] lr: 1.6778e-02 eta: 0:04:55 time: 0.0433 data_time: 0.0060 memory: 1793 loss: 0.0952 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0952 2022/11/28 12:21:11 - mmengine - INFO - Epoch(train) [12][1200/1567] lr: 1.6312e-02 eta: 0:04:50 time: 0.0437 data_time: 0.0063 memory: 1793 loss: 0.1520 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1520 2022/11/28 12:21:15 - mmengine - INFO - Epoch(train) [12][1300/1567] lr: 1.5852e-02 eta: 0:04:46 time: 0.0435 data_time: 0.0063 memory: 1793 loss: 0.0975 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0975 2022/11/28 12:21:20 - mmengine - INFO - Epoch(train) [12][1400/1567] lr: 1.5397e-02 eta: 0:04:41 time: 0.0435 data_time: 0.0061 memory: 1793 loss: 0.0994 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0994 2022/11/28 12:21:24 - mmengine - INFO - Epoch(train) [12][1500/1567] lr: 1.4947e-02 eta: 0:04:37 time: 0.0437 data_time: 0.0062 memory: 1793 loss: 0.1031 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1031 2022/11/28 12:21:27 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:21:27 - mmengine - INFO - Epoch(train) [12][1567/1567] lr: 1.4649e-02 eta: 0:04:34 time: 0.0427 data_time: 0.0058 memory: 1793 loss: 0.3022 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.3022 2022/11/28 12:21:27 - mmengine - INFO - Saving checkpoint at 12 epochs 2022/11/28 12:21:31 - mmengine - INFO - Epoch(val) [12][100/129] eta: 0:00:00 time: 0.0324 data_time: 0.0191 memory: 364 2022/11/28 12:21:32 - mmengine - INFO - Epoch(val) [12][129/129] acc/top1: 0.8152 acc/top5: 0.9627 acc/mean1: 0.8152 2022/11/28 12:21:32 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_11.pth is removed 2022/11/28 12:21:32 - mmengine - INFO - The best checkpoint with 0.8152 acc/top1 at 12 epoch is saved to best_acc/top1_epoch_12.pth. 2022/11/28 12:21:37 - mmengine - INFO - Epoch(train) [13][100/1567] lr: 1.4209e-02 eta: 0:04:30 time: 0.0431 data_time: 0.0060 memory: 1793 loss: 0.0911 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0911 2022/11/28 12:21:41 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:21:41 - mmengine - INFO - Epoch(train) [13][200/1567] lr: 1.3774e-02 eta: 0:04:25 time: 0.0437 data_time: 0.0065 memory: 1793 loss: 0.0746 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0746 2022/11/28 12:21:46 - mmengine - INFO - Epoch(train) [13][300/1567] lr: 1.3345e-02 eta: 0:04:21 time: 0.0438 data_time: 0.0065 memory: 1793 loss: 0.0706 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0706 2022/11/28 12:21:50 - mmengine - INFO - Epoch(train) [13][400/1567] lr: 1.2922e-02 eta: 0:04:17 time: 0.0442 data_time: 0.0065 memory: 1793 loss: 0.0804 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0804 2022/11/28 12:21:54 - mmengine - INFO - Epoch(train) [13][500/1567] lr: 1.2505e-02 eta: 0:04:12 time: 0.0441 data_time: 0.0066 memory: 1793 loss: 0.0974 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0974 2022/11/28 12:21:59 - mmengine - INFO - Epoch(train) [13][600/1567] lr: 1.2093e-02 eta: 0:04:08 time: 0.0432 data_time: 0.0061 memory: 1793 loss: 0.0763 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0763 2022/11/28 12:22:03 - mmengine - INFO - Epoch(train) [13][700/1567] lr: 1.1687e-02 eta: 0:04:03 time: 0.0434 data_time: 0.0060 memory: 1793 loss: 0.0686 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0686 2022/11/28 12:22:07 - mmengine - INFO - Epoch(train) [13][800/1567] lr: 1.1288e-02 eta: 0:03:59 time: 0.0432 data_time: 0.0061 memory: 1793 loss: 0.0548 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0548 2022/11/28 12:22:12 - mmengine - INFO - Epoch(train) [13][900/1567] lr: 1.0894e-02 eta: 0:03:55 time: 0.0432 data_time: 0.0060 memory: 1793 loss: 0.0691 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0691 2022/11/28 12:22:16 - mmengine - INFO - Epoch(train) [13][1000/1567] lr: 1.0507e-02 eta: 0:03:50 time: 0.0438 data_time: 0.0060 memory: 1793 loss: 0.0808 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0808 2022/11/28 12:22:20 - mmengine - INFO - Epoch(train) [13][1100/1567] lr: 1.0126e-02 eta: 0:03:46 time: 0.0435 data_time: 0.0062 memory: 1793 loss: 0.0497 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0497 2022/11/28 12:22:25 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:22:25 - mmengine - INFO - Epoch(train) [13][1200/1567] lr: 9.7512e-03 eta: 0:03:41 time: 0.0436 data_time: 0.0061 memory: 1793 loss: 0.0504 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0504 2022/11/28 12:22:29 - mmengine - INFO - Epoch(train) [13][1300/1567] lr: 9.3826e-03 eta: 0:03:37 time: 0.0439 data_time: 0.0060 memory: 1793 loss: 0.0566 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0566 2022/11/28 12:22:34 - mmengine - INFO - Epoch(train) [13][1400/1567] lr: 9.0204e-03 eta: 0:03:33 time: 0.0440 data_time: 0.0061 memory: 1793 loss: 0.0866 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0866 2022/11/28 12:22:38 - mmengine - INFO - Epoch(train) [13][1500/1567] lr: 8.6647e-03 eta: 0:03:28 time: 0.0437 data_time: 0.0060 memory: 1793 loss: 0.0658 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0658 2022/11/28 12:22:41 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:22:41 - mmengine - INFO - Epoch(train) [13][1567/1567] lr: 8.4300e-03 eta: 0:03:25 time: 0.0422 data_time: 0.0058 memory: 1793 loss: 0.1742 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1742 2022/11/28 12:22:41 - mmengine - INFO - Saving checkpoint at 13 epochs 2022/11/28 12:22:45 - mmengine - INFO - Epoch(val) [13][100/129] eta: 0:00:00 time: 0.0339 data_time: 0.0206 memory: 364 2022/11/28 12:22:46 - mmengine - INFO - Epoch(val) [13][129/129] acc/top1: 0.8296 acc/top5: 0.9662 acc/mean1: 0.8295 2022/11/28 12:22:46 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_12.pth is removed 2022/11/28 12:22:46 - mmengine - INFO - The best checkpoint with 0.8296 acc/top1 at 13 epoch is saved to best_acc/top1_epoch_13.pth. 2022/11/28 12:22:51 - mmengine - INFO - Epoch(train) [14][100/1567] lr: 8.0851e-03 eta: 0:03:21 time: 0.0432 data_time: 0.0061 memory: 1793 loss: 0.0571 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0571 2022/11/28 12:22:55 - mmengine - INFO - Epoch(train) [14][200/1567] lr: 7.7469e-03 eta: 0:03:17 time: 0.0438 data_time: 0.0068 memory: 1793 loss: 0.0474 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0474 2022/11/28 12:22:59 - mmengine - INFO - Epoch(train) [14][300/1567] lr: 7.4152e-03 eta: 0:03:12 time: 0.0431 data_time: 0.0061 memory: 1793 loss: 0.0571 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0571 2022/11/28 12:23:04 - mmengine - INFO - Epoch(train) [14][400/1567] lr: 7.0902e-03 eta: 0:03:08 time: 0.0436 data_time: 0.0064 memory: 1793 loss: 0.0631 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0631 2022/11/28 12:23:08 - mmengine - INFO - Epoch(train) [14][500/1567] lr: 6.7720e-03 eta: 0:03:04 time: 0.0440 data_time: 0.0075 memory: 1793 loss: 0.0372 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0372 2022/11/28 12:23:13 - mmengine - INFO - Epoch(train) [14][600/1567] lr: 6.4606e-03 eta: 0:02:59 time: 0.0443 data_time: 0.0068 memory: 1793 loss: 0.0385 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0385 2022/11/28 12:23:14 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:23:17 - mmengine - INFO - Epoch(train) [14][700/1567] lr: 6.1560e-03 eta: 0:02:55 time: 0.0440 data_time: 0.0068 memory: 1793 loss: 0.0290 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0290 2022/11/28 12:23:22 - mmengine - INFO - Epoch(train) [14][800/1567] lr: 5.8582e-03 eta: 0:02:50 time: 0.0443 data_time: 0.0068 memory: 1793 loss: 0.0200 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0200 2022/11/28 12:23:26 - mmengine - INFO - Epoch(train) [14][900/1567] lr: 5.5675e-03 eta: 0:02:46 time: 0.0441 data_time: 0.0075 memory: 1793 loss: 0.0519 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0519 2022/11/28 12:23:30 - mmengine - INFO - Epoch(train) [14][1000/1567] lr: 5.2836e-03 eta: 0:02:42 time: 0.0441 data_time: 0.0075 memory: 1793 loss: 0.0286 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0286 2022/11/28 12:23:35 - mmengine - INFO - Epoch(train) [14][1100/1567] lr: 5.0068e-03 eta: 0:02:37 time: 0.0432 data_time: 0.0061 memory: 1793 loss: 0.0497 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0497 2022/11/28 12:23:39 - mmengine - INFO - Epoch(train) [14][1200/1567] lr: 4.7371e-03 eta: 0:02:33 time: 0.0441 data_time: 0.0062 memory: 1793 loss: 0.0293 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0293 2022/11/28 12:23:44 - mmengine - INFO - Epoch(train) [14][1300/1567] lr: 4.4745e-03 eta: 0:02:29 time: 0.0431 data_time: 0.0061 memory: 1793 loss: 0.0166 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0166 2022/11/28 12:23:48 - mmengine - INFO - Epoch(train) [14][1400/1567] lr: 4.2190e-03 eta: 0:02:24 time: 0.0431 data_time: 0.0062 memory: 1793 loss: 0.0347 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0347 2022/11/28 12:23:52 - mmengine - INFO - Epoch(train) [14][1500/1567] lr: 3.9707e-03 eta: 0:02:20 time: 0.0431 data_time: 0.0061 memory: 1793 loss: 0.0281 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0281 2022/11/28 12:23:55 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:23:55 - mmengine - INFO - Epoch(train) [14][1567/1567] lr: 3.8084e-03 eta: 0:02:17 time: 0.0422 data_time: 0.0058 memory: 1793 loss: 0.2748 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2748 2022/11/28 12:23:55 - mmengine - INFO - Saving checkpoint at 14 epochs 2022/11/28 12:23:59 - mmengine - INFO - Epoch(val) [14][100/129] eta: 0:00:00 time: 0.0330 data_time: 0.0192 memory: 364 2022/11/28 12:24:00 - mmengine - INFO - Epoch(val) [14][129/129] acc/top1: 0.8425 acc/top5: 0.9694 acc/mean1: 0.8424 2022/11/28 12:24:00 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_13.pth is removed 2022/11/28 12:24:00 - mmengine - INFO - The best checkpoint with 0.8425 acc/top1 at 14 epoch is saved to best_acc/top1_epoch_14.pth. 2022/11/28 12:24:03 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:24:05 - mmengine - INFO - Epoch(train) [15][100/1567] lr: 3.5722e-03 eta: 0:02:12 time: 0.0439 data_time: 0.0062 memory: 1793 loss: 0.0199 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0199 2022/11/28 12:24:09 - mmengine - INFO - Epoch(train) [15][200/1567] lr: 3.3433e-03 eta: 0:02:08 time: 0.0439 data_time: 0.0061 memory: 1793 loss: 0.0301 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0301 2022/11/28 12:24:14 - mmengine - INFO - Epoch(train) [15][300/1567] lr: 3.1217e-03 eta: 0:02:04 time: 0.0431 data_time: 0.0061 memory: 1793 loss: 0.0362 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0362 2022/11/28 12:24:18 - mmengine - INFO - Epoch(train) [15][400/1567] lr: 2.9075e-03 eta: 0:01:59 time: 0.0435 data_time: 0.0067 memory: 1793 loss: 0.0274 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0274 2022/11/28 12:24:22 - mmengine - INFO - Epoch(train) [15][500/1567] lr: 2.7007e-03 eta: 0:01:55 time: 0.0434 data_time: 0.0061 memory: 1793 loss: 0.0224 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0224 2022/11/28 12:24:27 - mmengine - INFO - Epoch(train) [15][600/1567] lr: 2.5013e-03 eta: 0:01:51 time: 0.0432 data_time: 0.0061 memory: 1793 loss: 0.0221 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0221 2022/11/28 12:24:31 - mmengine - INFO - Epoch(train) [15][700/1567] lr: 2.3093e-03 eta: 0:01:46 time: 0.0436 data_time: 0.0066 memory: 1793 loss: 0.0166 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0166 2022/11/28 12:24:36 - mmengine - INFO - Epoch(train) [15][800/1567] lr: 2.1249e-03 eta: 0:01:42 time: 0.0435 data_time: 0.0066 memory: 1793 loss: 0.0188 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0188 2022/11/28 12:24:40 - mmengine - INFO - Epoch(train) [15][900/1567] lr: 1.9479e-03 eta: 0:01:37 time: 0.0442 data_time: 0.0073 memory: 1793 loss: 0.0245 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0245 2022/11/28 12:24:44 - mmengine - INFO - Epoch(train) [15][1000/1567] lr: 1.7785e-03 eta: 0:01:33 time: 0.0437 data_time: 0.0060 memory: 1793 loss: 0.0157 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0157 2022/11/28 12:24:47 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:24:49 - mmengine - INFO - Epoch(train) [15][1100/1567] lr: 1.6167e-03 eta: 0:01:29 time: 0.0428 data_time: 0.0061 memory: 1793 loss: 0.0186 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0186 2022/11/28 12:24:53 - mmengine - INFO - Epoch(train) [15][1200/1567] lr: 1.4625e-03 eta: 0:01:24 time: 0.0433 data_time: 0.0066 memory: 1793 loss: 0.0184 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0184 2022/11/28 12:24:57 - mmengine - INFO - Epoch(train) [15][1300/1567] lr: 1.3159e-03 eta: 0:01:20 time: 0.0440 data_time: 0.0067 memory: 1793 loss: 0.0213 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0213 2022/11/28 12:25:02 - mmengine - INFO - Epoch(train) [15][1400/1567] lr: 1.1769e-03 eta: 0:01:15 time: 0.0442 data_time: 0.0061 memory: 1793 loss: 0.0173 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0173 2022/11/28 12:25:06 - mmengine - INFO - Epoch(train) [15][1500/1567] lr: 1.0456e-03 eta: 0:01:11 time: 0.0437 data_time: 0.0061 memory: 1793 loss: 0.0231 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0231 2022/11/28 12:25:09 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:25:09 - mmengine - INFO - Epoch(train) [15][1567/1567] lr: 9.6196e-04 eta: 0:01:08 time: 0.0434 data_time: 0.0061 memory: 1793 loss: 0.1767 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1767 2022/11/28 12:25:09 - mmengine - INFO - Saving checkpoint at 15 epochs 2022/11/28 12:25:13 - mmengine - INFO - Epoch(val) [15][100/129] eta: 0:00:00 time: 0.0324 data_time: 0.0191 memory: 364 2022/11/28 12:25:14 - mmengine - INFO - Epoch(val) [15][129/129] acc/top1: 0.8525 acc/top5: 0.9707 acc/mean1: 0.8524 2022/11/28 12:25:14 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_14.pth is removed 2022/11/28 12:25:14 - mmengine - INFO - The best checkpoint with 0.8525 acc/top1 at 15 epoch is saved to best_acc/top1_epoch_15.pth. 2022/11/28 12:25:19 - mmengine - INFO - Epoch(train) [16][100/1567] lr: 8.4351e-04 eta: 0:01:04 time: 0.0441 data_time: 0.0061 memory: 1793 loss: 0.0114 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0114 2022/11/28 12:25:23 - mmengine - INFO - Epoch(train) [16][200/1567] lr: 7.3277e-04 eta: 0:00:59 time: 0.0431 data_time: 0.0061 memory: 1793 loss: 0.0127 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0127 2022/11/28 12:25:28 - mmengine - INFO - Epoch(train) [16][300/1567] lr: 6.2978e-04 eta: 0:00:55 time: 0.0435 data_time: 0.0061 memory: 1793 loss: 0.0250 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0250 2022/11/28 12:25:32 - mmengine - INFO - Epoch(train) [16][400/1567] lr: 5.3453e-04 eta: 0:00:51 time: 0.0451 data_time: 0.0062 memory: 1793 loss: 0.0171 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0171 2022/11/28 12:25:36 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:25:36 - mmengine - INFO - Epoch(train) [16][500/1567] lr: 4.4705e-04 eta: 0:00:46 time: 0.0428 data_time: 0.0061 memory: 1793 loss: 0.0162 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0162 2022/11/28 12:25:41 - mmengine - INFO - Epoch(train) [16][600/1567] lr: 3.6735e-04 eta: 0:00:42 time: 0.0437 data_time: 0.0068 memory: 1793 loss: 0.0189 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0189 2022/11/28 12:25:45 - mmengine - INFO - Epoch(train) [16][700/1567] lr: 2.9544e-04 eta: 0:00:37 time: 0.0437 data_time: 0.0067 memory: 1793 loss: 0.0230 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0230 2022/11/28 12:25:49 - mmengine - INFO - Epoch(train) [16][800/1567] lr: 2.3134e-04 eta: 0:00:33 time: 0.0438 data_time: 0.0068 memory: 1793 loss: 0.0220 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0220 2022/11/28 12:25:54 - mmengine - INFO - Epoch(train) [16][900/1567] lr: 1.7505e-04 eta: 0:00:29 time: 0.0439 data_time: 0.0064 memory: 1793 loss: 0.0174 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0174 2022/11/28 12:25:58 - mmengine - INFO - Epoch(train) [16][1000/1567] lr: 1.2658e-04 eta: 0:00:24 time: 0.0437 data_time: 0.0061 memory: 1793 loss: 0.0177 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0177 2022/11/28 12:26:03 - mmengine - INFO - Epoch(train) [16][1100/1567] lr: 8.5947e-05 eta: 0:00:20 time: 0.0438 data_time: 0.0061 memory: 1793 loss: 0.0245 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0245 2022/11/28 12:26:07 - mmengine - INFO - Epoch(train) [16][1200/1567] lr: 5.3147e-05 eta: 0:00:16 time: 0.0434 data_time: 0.0061 memory: 1793 loss: 0.0155 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0155 2022/11/28 12:26:11 - mmengine - INFO - Epoch(train) [16][1300/1567] lr: 2.8190e-05 eta: 0:00:11 time: 0.0438 data_time: 0.0060 memory: 1793 loss: 0.0160 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0160 2022/11/28 12:26:16 - mmengine - INFO - Epoch(train) [16][1400/1567] lr: 1.1078e-05 eta: 0:00:07 time: 0.0438 data_time: 0.0060 memory: 1793 loss: 0.0157 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0157 2022/11/28 12:26:20 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:26:20 - mmengine - INFO - Epoch(train) [16][1500/1567] lr: 1.8150e-06 eta: 0:00:02 time: 0.0442 data_time: 0.0061 memory: 1793 loss: 0.0212 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0212 2022/11/28 12:26:23 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_120601 2022/11/28 12:26:23 - mmengine - INFO - Epoch(train) [16][1567/1567] lr: 3.9252e-10 eta: 0:00:00 time: 0.0434 data_time: 0.0059 memory: 1793 loss: 0.1798 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.1798 2022/11/28 12:26:23 - mmengine - INFO - Saving checkpoint at 16 epochs 2022/11/28 12:26:27 - mmengine - INFO - Epoch(val) [16][100/129] eta: 0:00:00 time: 0.0324 data_time: 0.0184 memory: 364 2022/11/28 12:26:28 - mmengine - INFO - Epoch(val) [16][129/129] acc/top1: 0.8547 acc/top5: 0.9717 acc/mean1: 0.8546 2022/11/28 12:26:28 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_15.pth is removed 2022/11/28 12:26:28 - mmengine - INFO - The best checkpoint with 0.8547 acc/top1 at 16 epoch is saved to best_acc/top1_epoch_16.pth.