2022/11/28 11:44:42 - 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: 3044516 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 11:44:42 - 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=['b']), 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=['b']), 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=['b']), 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=['b']), 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=['b']), 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=['b']), 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-bone-u100-80e_ntu60-xsub-keypoint-3d' randomness = dict(seed=None, diff_rank_seed=False, deterministic=False) 2022/11/28 11:44:42 - mmengine - INFO - Result has been saved to /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-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 11:45:18 - mmengine - INFO - Checkpoints will be saved to /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d. 2022/11/28 11:45:25 - mmengine - INFO - Epoch(train) [1][100/1567] lr: 9.9996e-02 eta: 0:26:40 time: 0.0434 data_time: 0.0061 memory: 1793 loss: 2.9328 top1_acc: 0.4375 top5_acc: 0.5625 loss_cls: 2.9328 2022/11/28 11:45:29 - mmengine - INFO - Epoch(train) [1][200/1567] lr: 9.9984e-02 eta: 0:22:20 time: 0.0435 data_time: 0.0062 memory: 1793 loss: 2.2744 top1_acc: 0.3750 top5_acc: 0.8750 loss_cls: 2.2744 2022/11/28 11:45:33 - mmengine - INFO - Epoch(train) [1][300/1567] lr: 9.9965e-02 eta: 0:20:53 time: 0.0461 data_time: 0.0060 memory: 1793 loss: 1.9302 top1_acc: 0.2500 top5_acc: 0.6875 loss_cls: 1.9302 2022/11/28 11:45:38 - mmengine - INFO - Epoch(train) [1][400/1567] lr: 9.9938e-02 eta: 0:20:01 time: 0.0429 data_time: 0.0060 memory: 1793 loss: 1.6172 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.6172 2022/11/28 11:45:42 - mmengine - INFO - Epoch(train) [1][500/1567] lr: 9.9902e-02 eta: 0:19:32 time: 0.0430 data_time: 0.0060 memory: 1793 loss: 1.4574 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.4574 2022/11/28 11:45:46 - mmengine - INFO - Epoch(train) [1][600/1567] lr: 9.9859e-02 eta: 0:19:09 time: 0.0431 data_time: 0.0059 memory: 1793 loss: 1.3452 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.3452 2022/11/28 11:45:51 - mmengine - INFO - Epoch(train) [1][700/1567] lr: 9.9808e-02 eta: 0:18:50 time: 0.0430 data_time: 0.0060 memory: 1793 loss: 1.1268 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.1268 2022/11/28 11:45:55 - mmengine - INFO - Epoch(train) [1][800/1567] lr: 9.9750e-02 eta: 0:18:38 time: 0.0434 data_time: 0.0060 memory: 1793 loss: 1.0853 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.0853 2022/11/28 11:45:59 - mmengine - INFO - Epoch(train) [1][900/1567] lr: 9.9683e-02 eta: 0:18:26 time: 0.0432 data_time: 0.0059 memory: 1793 loss: 1.0954 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0954 2022/11/28 11:46:04 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 11:46:04 - mmengine - INFO - Epoch(train) [1][1000/1567] lr: 9.9609e-02 eta: 0:18:15 time: 0.0430 data_time: 0.0060 memory: 1793 loss: 1.0582 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.0582 2022/11/28 11:46:08 - mmengine - INFO - Epoch(train) [1][1100/1567] lr: 9.9527e-02 eta: 0:18:06 time: 0.0428 data_time: 0.0059 memory: 1793 loss: 1.0090 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.0090 2022/11/28 11:46:12 - mmengine - INFO - Epoch(train) [1][1200/1567] lr: 9.9437e-02 eta: 0:17:58 time: 0.0437 data_time: 0.0059 memory: 1793 loss: 0.9126 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9126 2022/11/28 11:46:17 - mmengine - INFO - Epoch(train) [1][1300/1567] lr: 9.9339e-02 eta: 0:17:51 time: 0.0434 data_time: 0.0065 memory: 1793 loss: 0.8500 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.8500 2022/11/28 11:46:21 - mmengine - INFO - Epoch(train) [1][1400/1567] lr: 9.9234e-02 eta: 0:17:44 time: 0.0432 data_time: 0.0064 memory: 1793 loss: 0.8590 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.8590 2022/11/28 11:46:26 - mmengine - INFO - Epoch(train) [1][1500/1567] lr: 9.9121e-02 eta: 0:17:37 time: 0.0435 data_time: 0.0060 memory: 1793 loss: 0.7772 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.7772 2022/11/28 11:46:28 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 11:46:28 - mmengine - INFO - Epoch(train) [1][1567/1567] lr: 9.9040e-02 eta: 0:17:33 time: 0.0432 data_time: 0.0059 memory: 1793 loss: 0.8453 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.8453 2022/11/28 11:46:28 - mmengine - INFO - Saving checkpoint at 1 epochs 2022/11/28 11:46:33 - mmengine - INFO - Epoch(val) [1][100/129] eta: 0:00:01 time: 0.0338 data_time: 0.0204 memory: 364 2022/11/28 11:46:34 - mmengine - INFO - Epoch(val) [1][129/129] acc/top1: 0.4343 acc/top5: 0.8842 acc/mean1: 0.4340 2022/11/28 11:46:34 - mmengine - INFO - The best checkpoint with 0.4343 acc/top1 at 1 epoch is saved to best_acc/top1_epoch_1.pth. 2022/11/28 11:46:39 - mmengine - INFO - Epoch(train) [2][100/1567] lr: 9.8914e-02 eta: 0:17:29 time: 0.0435 data_time: 0.0062 memory: 1793 loss: 0.7293 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.7293 2022/11/28 11:46:43 - mmengine - INFO - Epoch(train) [2][200/1567] lr: 9.8781e-02 eta: 0:17:22 time: 0.0429 data_time: 0.0062 memory: 1793 loss: 0.7432 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.7432 2022/11/28 11:46:47 - mmengine - INFO - Epoch(train) [2][300/1567] lr: 9.8639e-02 eta: 0:17:16 time: 0.0439 data_time: 0.0061 memory: 1793 loss: 0.7201 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.7201 2022/11/28 11:46:52 - mmengine - INFO - Epoch(train) [2][400/1567] lr: 9.8491e-02 eta: 0:17:10 time: 0.0431 data_time: 0.0061 memory: 1793 loss: 0.8266 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.8266 2022/11/28 11:46:53 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 11:46:56 - mmengine - INFO - Epoch(train) [2][500/1567] lr: 9.8334e-02 eta: 0:17:04 time: 0.0430 data_time: 0.0060 memory: 1793 loss: 0.7728 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.7728 2022/11/28 11:47:00 - mmengine - INFO - Epoch(train) [2][600/1567] lr: 9.8170e-02 eta: 0:16:58 time: 0.0429 data_time: 0.0061 memory: 1793 loss: 0.6973 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.6973 2022/11/28 11:47:04 - mmengine - INFO - Epoch(train) [2][700/1567] lr: 9.7998e-02 eta: 0:16:52 time: 0.0434 data_time: 0.0068 memory: 1793 loss: 0.7014 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.7014 2022/11/28 11:47:09 - mmengine - INFO - Epoch(train) [2][800/1567] lr: 9.7819e-02 eta: 0:16:47 time: 0.0459 data_time: 0.0074 memory: 1793 loss: 0.6860 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.6860 2022/11/28 11:47:13 - mmengine - INFO - Epoch(train) [2][900/1567] lr: 9.7632e-02 eta: 0:16:42 time: 0.0429 data_time: 0.0062 memory: 1793 loss: 0.6535 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6535 2022/11/28 11:47:18 - mmengine - INFO - Epoch(train) [2][1000/1567] lr: 9.7438e-02 eta: 0:16:37 time: 0.0471 data_time: 0.0063 memory: 1793 loss: 0.7302 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.7302 2022/11/28 11:47:22 - mmengine - INFO - Epoch(train) [2][1100/1567] lr: 9.7236e-02 eta: 0:16:32 time: 0.0430 data_time: 0.0060 memory: 1793 loss: 0.8237 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8237 2022/11/28 11:47:26 - mmengine - INFO - Epoch(train) [2][1200/1567] lr: 9.7027e-02 eta: 0:16:26 time: 0.0433 data_time: 0.0061 memory: 1793 loss: 0.7062 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.7062 2022/11/28 11:47:31 - mmengine - INFO - Epoch(train) [2][1300/1567] lr: 9.6810e-02 eta: 0:16:21 time: 0.0432 data_time: 0.0069 memory: 1793 loss: 0.6077 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.6077 2022/11/28 11:47:35 - mmengine - INFO - Epoch(train) [2][1400/1567] lr: 9.6587e-02 eta: 0:16:17 time: 0.0428 data_time: 0.0062 memory: 1793 loss: 0.6797 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.6797 2022/11/28 11:47:37 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 11:47:39 - mmengine - INFO - Epoch(train) [2][1500/1567] lr: 9.6355e-02 eta: 0:16:13 time: 0.0460 data_time: 0.0074 memory: 1793 loss: 0.5906 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5906 2022/11/28 11:47:43 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 11:47:43 - mmengine - INFO - Epoch(train) [2][1567/1567] lr: 9.6196e-02 eta: 0:16:10 time: 0.0449 data_time: 0.0087 memory: 1793 loss: 0.7589 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.7589 2022/11/28 11:47:43 - mmengine - INFO - Saving checkpoint at 2 epochs 2022/11/28 11:47:47 - mmengine - INFO - Epoch(val) [2][100/129] eta: 0:00:01 time: 0.0379 data_time: 0.0242 memory: 364 2022/11/28 11:47:48 - mmengine - INFO - Epoch(val) [2][129/129] acc/top1: 0.6264 acc/top5: 0.9218 acc/mean1: 0.6263 2022/11/28 11:47:48 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_1.pth is removed 2022/11/28 11:47:48 - mmengine - INFO - The best checkpoint with 0.6264 acc/top1 at 2 epoch is saved to best_acc/top1_epoch_2.pth. 2022/11/28 11:47:53 - mmengine - INFO - Epoch(train) [3][100/1567] lr: 9.5953e-02 eta: 0:16:06 time: 0.0445 data_time: 0.0067 memory: 1793 loss: 0.6003 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.6003 2022/11/28 11:47:57 - mmengine - INFO - Epoch(train) [3][200/1567] lr: 9.5703e-02 eta: 0:16:02 time: 0.0434 data_time: 0.0061 memory: 1793 loss: 0.5603 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.5603 2022/11/28 11:48:01 - mmengine - INFO - Epoch(train) [3][300/1567] lr: 9.5445e-02 eta: 0:15:57 time: 0.0433 data_time: 0.0062 memory: 1793 loss: 0.4951 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4951 2022/11/28 11:48:06 - mmengine - INFO - Epoch(train) [3][400/1567] lr: 9.5180e-02 eta: 0:15:52 time: 0.0430 data_time: 0.0061 memory: 1793 loss: 0.6618 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.6618 2022/11/28 11:48:10 - mmengine - INFO - Epoch(train) [3][500/1567] lr: 9.4908e-02 eta: 0:15:47 time: 0.0433 data_time: 0.0061 memory: 1793 loss: 0.6423 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.6423 2022/11/28 11:48:14 - mmengine - INFO - Epoch(train) [3][600/1567] lr: 9.4629e-02 eta: 0:15:42 time: 0.0433 data_time: 0.0061 memory: 1793 loss: 0.6125 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6125 2022/11/28 11:48:19 - mmengine - INFO - Epoch(train) [3][700/1567] lr: 9.4343e-02 eta: 0:15:37 time: 0.0430 data_time: 0.0061 memory: 1793 loss: 0.5751 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.5751 2022/11/28 11:48:23 - mmengine - INFO - Epoch(train) [3][800/1567] lr: 9.4050e-02 eta: 0:15:33 time: 0.0431 data_time: 0.0063 memory: 1793 loss: 0.6088 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6088 2022/11/28 11:48:26 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 11:48:28 - mmengine - INFO - Epoch(train) [3][900/1567] lr: 9.3750e-02 eta: 0:15:28 time: 0.0430 data_time: 0.0062 memory: 1793 loss: 0.5805 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.5805 2022/11/28 11:48:32 - mmengine - INFO - Epoch(train) [3][1000/1567] lr: 9.3444e-02 eta: 0:15:24 time: 0.0465 data_time: 0.0066 memory: 1793 loss: 0.5311 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.5311 2022/11/28 11:48:36 - mmengine - INFO - Epoch(train) [3][1100/1567] lr: 9.3130e-02 eta: 0:15:19 time: 0.0434 data_time: 0.0061 memory: 1793 loss: 0.4353 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4353 2022/11/28 11:48:41 - mmengine - INFO - Epoch(train) [3][1200/1567] lr: 9.2810e-02 eta: 0:15:14 time: 0.0441 data_time: 0.0070 memory: 1793 loss: 0.5945 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.5945 2022/11/28 11:48:45 - mmengine - INFO - Epoch(train) [3][1300/1567] lr: 9.2483e-02 eta: 0:15:10 time: 0.0434 data_time: 0.0061 memory: 1793 loss: 0.5229 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5229 2022/11/28 11:48:49 - mmengine - INFO - Epoch(train) [3][1400/1567] lr: 9.2149e-02 eta: 0:15:05 time: 0.0437 data_time: 0.0063 memory: 1793 loss: 0.5205 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.5205 2022/11/28 11:48:54 - mmengine - INFO - Epoch(train) [3][1500/1567] lr: 9.1809e-02 eta: 0:15:01 time: 0.0442 data_time: 0.0064 memory: 1793 loss: 0.4981 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.4981 2022/11/28 11:48:57 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 11:48:57 - mmengine - INFO - Epoch(train) [3][1567/1567] lr: 9.1577e-02 eta: 0:14:58 time: 0.0429 data_time: 0.0059 memory: 1793 loss: 0.6884 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.6884 2022/11/28 11:48:57 - mmengine - INFO - Saving checkpoint at 3 epochs 2022/11/28 11:49:01 - mmengine - INFO - Epoch(val) [3][100/129] eta: 0:00:01 time: 0.0340 data_time: 0.0208 memory: 364 2022/11/28 11:49:02 - mmengine - INFO - Epoch(val) [3][129/129] acc/top1: 0.7398 acc/top5: 0.9426 acc/mean1: 0.7398 2022/11/28 11:49:02 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_2.pth is removed 2022/11/28 11:49:02 - mmengine - INFO - The best checkpoint with 0.7398 acc/top1 at 3 epoch is saved to best_acc/top1_epoch_3.pth. 2022/11/28 11:49:07 - mmengine - INFO - Epoch(train) [4][100/1567] lr: 9.1226e-02 eta: 0:14:54 time: 0.0433 data_time: 0.0060 memory: 1793 loss: 0.5196 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.5196 2022/11/28 11:49:11 - mmengine - INFO - Epoch(train) [4][200/1567] lr: 9.0868e-02 eta: 0:14:49 time: 0.0439 data_time: 0.0062 memory: 1793 loss: 0.5970 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.5970 2022/11/28 11:49:16 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 11:49:16 - mmengine - INFO - Epoch(train) [4][300/1567] lr: 9.0504e-02 eta: 0:14:45 time: 0.0460 data_time: 0.0061 memory: 1793 loss: 0.4964 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4964 2022/11/28 11:49:20 - mmengine - INFO - Epoch(train) [4][400/1567] lr: 9.0133e-02 eta: 0:14:40 time: 0.0433 data_time: 0.0060 memory: 1793 loss: 0.5211 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5211 2022/11/28 11:49:24 - mmengine - INFO - Epoch(train) [4][500/1567] lr: 8.9756e-02 eta: 0:14:36 time: 0.0448 data_time: 0.0075 memory: 1793 loss: 0.4586 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.4586 2022/11/28 11:49:29 - mmengine - INFO - Epoch(train) [4][600/1567] lr: 8.9373e-02 eta: 0:14:32 time: 0.0434 data_time: 0.0061 memory: 1793 loss: 0.4271 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4271 2022/11/28 11:49:33 - mmengine - INFO - Epoch(train) [4][700/1567] lr: 8.8984e-02 eta: 0:14:27 time: 0.0447 data_time: 0.0061 memory: 1793 loss: 0.5068 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5068 2022/11/28 11:49:38 - mmengine - INFO - Epoch(train) [4][800/1567] lr: 8.8589e-02 eta: 0:14:23 time: 0.0434 data_time: 0.0062 memory: 1793 loss: 0.4535 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.4535 2022/11/28 11:49:42 - mmengine - INFO - Epoch(train) [4][900/1567] lr: 8.8187e-02 eta: 0:14:19 time: 0.0445 data_time: 0.0061 memory: 1793 loss: 0.4816 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.4816 2022/11/28 11:49:47 - mmengine - INFO - Epoch(train) [4][1000/1567] lr: 8.7780e-02 eta: 0:14:14 time: 0.0438 data_time: 0.0063 memory: 1793 loss: 0.3947 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.3947 2022/11/28 11:49:51 - mmengine - INFO - Epoch(train) [4][1100/1567] lr: 8.7367e-02 eta: 0:14:10 time: 0.0431 data_time: 0.0063 memory: 1793 loss: 0.5706 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.5706 2022/11/28 11:49:55 - mmengine - INFO - Epoch(train) [4][1200/1567] lr: 8.6947e-02 eta: 0:14:05 time: 0.0441 data_time: 0.0064 memory: 1793 loss: 0.3879 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.3879 2022/11/28 11:50:00 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 11:50:00 - mmengine - INFO - Epoch(train) [4][1300/1567] lr: 8.6522e-02 eta: 0:14:00 time: 0.0432 data_time: 0.0061 memory: 1793 loss: 0.3623 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3623 2022/11/28 11:50:04 - mmengine - INFO - Epoch(train) [4][1400/1567] lr: 8.6092e-02 eta: 0:13:56 time: 0.0437 data_time: 0.0063 memory: 1793 loss: 0.3842 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.3842 2022/11/28 11:50:08 - mmengine - INFO - Epoch(train) [4][1500/1567] lr: 8.5655e-02 eta: 0:13:51 time: 0.0438 data_time: 0.0064 memory: 1793 loss: 0.4708 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4708 2022/11/28 11:50:11 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 11:50:11 - mmengine - INFO - Epoch(train) [4][1567/1567] lr: 8.5360e-02 eta: 0:13:48 time: 0.0420 data_time: 0.0059 memory: 1793 loss: 0.5754 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.5754 2022/11/28 11:50:11 - mmengine - INFO - Saving checkpoint at 4 epochs 2022/11/28 11:50:15 - mmengine - INFO - Epoch(val) [4][100/129] eta: 0:00:01 time: 0.0337 data_time: 0.0204 memory: 364 2022/11/28 11:50:16 - mmengine - INFO - Epoch(val) [4][129/129] acc/top1: 0.7610 acc/top5: 0.9489 acc/mean1: 0.7608 2022/11/28 11:50:16 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_3.pth is removed 2022/11/28 11:50:17 - mmengine - INFO - The best checkpoint with 0.7610 acc/top1 at 4 epoch is saved to best_acc/top1_epoch_4.pth. 2022/11/28 11:50:21 - mmengine - INFO - Epoch(train) [5][100/1567] lr: 8.4914e-02 eta: 0:13:44 time: 0.0429 data_time: 0.0066 memory: 1793 loss: 0.5596 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.5596 2022/11/28 11:50:26 - mmengine - INFO - Epoch(train) [5][200/1567] lr: 8.4463e-02 eta: 0:13:39 time: 0.0430 data_time: 0.0061 memory: 1793 loss: 0.4875 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4875 2022/11/28 11:50:30 - mmengine - INFO - Epoch(train) [5][300/1567] lr: 8.4006e-02 eta: 0:13:35 time: 0.0439 data_time: 0.0063 memory: 1793 loss: 0.4262 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4262 2022/11/28 11:50:34 - mmengine - INFO - Epoch(train) [5][400/1567] lr: 8.3544e-02 eta: 0:13:31 time: 0.0441 data_time: 0.0063 memory: 1793 loss: 0.5320 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.5320 2022/11/28 11:50:39 - mmengine - INFO - Epoch(train) [5][500/1567] lr: 8.3077e-02 eta: 0:13:26 time: 0.0435 data_time: 0.0063 memory: 1793 loss: 0.3669 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3669 2022/11/28 11:50:43 - mmengine - INFO - Epoch(train) [5][600/1567] lr: 8.2605e-02 eta: 0:13:22 time: 0.0435 data_time: 0.0069 memory: 1793 loss: 0.4639 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.4639 2022/11/28 11:50:48 - mmengine - INFO - Epoch(train) [5][700/1567] lr: 8.2127e-02 eta: 0:13:17 time: 0.0437 data_time: 0.0063 memory: 1793 loss: 0.4021 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4021 2022/11/28 11:50:49 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 11:50:52 - mmengine - INFO - Epoch(train) [5][800/1567] lr: 8.1645e-02 eta: 0:13:13 time: 0.0435 data_time: 0.0065 memory: 1793 loss: 0.4611 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4611 2022/11/28 11:50:56 - mmengine - INFO - Epoch(train) [5][900/1567] lr: 8.1157e-02 eta: 0:13:08 time: 0.0439 data_time: 0.0072 memory: 1793 loss: 0.3294 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3294 2022/11/28 11:51:01 - mmengine - INFO - Epoch(train) [5][1000/1567] lr: 8.0665e-02 eta: 0:13:04 time: 0.0432 data_time: 0.0062 memory: 1793 loss: 0.3739 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3739 2022/11/28 11:51:05 - mmengine - INFO - Epoch(train) [5][1100/1567] lr: 8.0167e-02 eta: 0:12:59 time: 0.0431 data_time: 0.0061 memory: 1793 loss: 0.4483 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4483 2022/11/28 11:51:09 - mmengine - INFO - Epoch(train) [5][1200/1567] lr: 7.9665e-02 eta: 0:12:55 time: 0.0443 data_time: 0.0068 memory: 1793 loss: 0.3809 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3809 2022/11/28 11:51:14 - mmengine - INFO - Epoch(train) [5][1300/1567] lr: 7.9159e-02 eta: 0:12:50 time: 0.0458 data_time: 0.0062 memory: 1793 loss: 0.4157 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4157 2022/11/28 11:51:18 - mmengine - INFO - Epoch(train) [5][1400/1567] lr: 7.8647e-02 eta: 0:12:46 time: 0.0435 data_time: 0.0061 memory: 1793 loss: 0.5383 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5383 2022/11/28 11:51:23 - mmengine - INFO - Epoch(train) [5][1500/1567] lr: 7.8132e-02 eta: 0:12:41 time: 0.0431 data_time: 0.0062 memory: 1793 loss: 0.3317 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3317 2022/11/28 11:51:26 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 11:51:26 - mmengine - INFO - Epoch(train) [5][1567/1567] lr: 7.7784e-02 eta: 0:12:39 time: 0.0451 data_time: 0.0061 memory: 1793 loss: 0.5738 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.5738 2022/11/28 11:51:26 - mmengine - INFO - Saving checkpoint at 5 epochs 2022/11/28 11:51:30 - mmengine - INFO - Epoch(val) [5][100/129] eta: 0:00:01 time: 0.0339 data_time: 0.0200 memory: 364 2022/11/28 11:51:31 - mmengine - INFO - Epoch(val) [5][129/129] acc/top1: 0.7269 acc/top5: 0.9532 acc/mean1: 0.7267 2022/11/28 11:51:35 - mmengine - INFO - Epoch(train) [6][100/1567] lr: 7.7261e-02 eta: 0:12:35 time: 0.0432 data_time: 0.0062 memory: 1793 loss: 0.3703 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3703 2022/11/28 11:51:38 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 11:51:40 - mmengine - INFO - Epoch(train) [6][200/1567] lr: 7.6733e-02 eta: 0:12:30 time: 0.0433 data_time: 0.0061 memory: 1793 loss: 0.5023 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5023 2022/11/28 11:51:44 - mmengine - INFO - Epoch(train) [6][300/1567] lr: 7.6202e-02 eta: 0:12:26 time: 0.0442 data_time: 0.0061 memory: 1793 loss: 0.2983 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2983 2022/11/28 11:51:49 - mmengine - INFO - Epoch(train) [6][400/1567] lr: 7.5666e-02 eta: 0:12:22 time: 0.0436 data_time: 0.0061 memory: 1793 loss: 0.4642 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.4642 2022/11/28 11:51:53 - mmengine - INFO - Epoch(train) [6][500/1567] lr: 7.5126e-02 eta: 0:12:17 time: 0.0434 data_time: 0.0061 memory: 1793 loss: 0.3759 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3759 2022/11/28 11:51:57 - mmengine - INFO - Epoch(train) [6][600/1567] lr: 7.4583e-02 eta: 0:12:13 time: 0.0439 data_time: 0.0066 memory: 1793 loss: 0.3500 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3500 2022/11/28 11:52:02 - mmengine - INFO - Epoch(train) [6][700/1567] lr: 7.4035e-02 eta: 0:12:08 time: 0.0437 data_time: 0.0065 memory: 1793 loss: 0.4364 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4364 2022/11/28 11:52:06 - mmengine - INFO - Epoch(train) [6][800/1567] lr: 7.3484e-02 eta: 0:12:04 time: 0.0437 data_time: 0.0062 memory: 1793 loss: 0.4432 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4432 2022/11/28 11:52:11 - mmengine - INFO - Epoch(train) [6][900/1567] lr: 7.2929e-02 eta: 0:11:59 time: 0.0437 data_time: 0.0062 memory: 1793 loss: 0.4629 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4629 2022/11/28 11:52:15 - mmengine - INFO - Epoch(train) [6][1000/1567] lr: 7.2371e-02 eta: 0:11:55 time: 0.0437 data_time: 0.0061 memory: 1793 loss: 0.4206 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4206 2022/11/28 11:52:19 - mmengine - INFO - Epoch(train) [6][1100/1567] lr: 7.1809e-02 eta: 0:11:51 time: 0.0436 data_time: 0.0064 memory: 1793 loss: 0.4909 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4909 2022/11/28 11:52:22 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 11:52:24 - mmengine - INFO - Epoch(train) [6][1200/1567] lr: 7.1243e-02 eta: 0:11:46 time: 0.0437 data_time: 0.0064 memory: 1793 loss: 0.3665 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.3665 2022/11/28 11:52:28 - mmengine - INFO - Epoch(train) [6][1300/1567] lr: 7.0674e-02 eta: 0:11:42 time: 0.0442 data_time: 0.0062 memory: 1793 loss: 0.4426 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4426 2022/11/28 11:52:33 - mmengine - INFO - Epoch(train) [6][1400/1567] lr: 7.0102e-02 eta: 0:11:37 time: 0.0436 data_time: 0.0062 memory: 1793 loss: 0.3436 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.3436 2022/11/28 11:52:37 - mmengine - INFO - Epoch(train) [6][1500/1567] lr: 6.9527e-02 eta: 0:11:33 time: 0.0435 data_time: 0.0061 memory: 1793 loss: 0.4102 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4102 2022/11/28 11:52:40 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 11:52:40 - mmengine - INFO - Epoch(train) [6][1567/1567] lr: 6.9140e-02 eta: 0:11:30 time: 0.0430 data_time: 0.0066 memory: 1793 loss: 0.4964 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.4964 2022/11/28 11:52:40 - mmengine - INFO - Saving checkpoint at 6 epochs 2022/11/28 11:52:44 - mmengine - INFO - Epoch(val) [6][100/129] eta: 0:00:01 time: 0.0338 data_time: 0.0204 memory: 364 2022/11/28 11:52:45 - mmengine - INFO - Epoch(val) [6][129/129] acc/top1: 0.7875 acc/top5: 0.9603 acc/mean1: 0.7874 2022/11/28 11:52:45 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_4.pth is removed 2022/11/28 11:52:45 - mmengine - INFO - The best checkpoint with 0.7875 acc/top1 at 6 epoch is saved to best_acc/top1_epoch_6.pth. 2022/11/28 11:52:50 - mmengine - INFO - Epoch(train) [7][100/1567] lr: 6.8560e-02 eta: 0:11:26 time: 0.0446 data_time: 0.0066 memory: 1793 loss: 0.3788 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3788 2022/11/28 11:52:54 - mmengine - INFO - Epoch(train) [7][200/1567] lr: 6.7976e-02 eta: 0:11:22 time: 0.0488 data_time: 0.0068 memory: 1793 loss: 0.4328 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4328 2022/11/28 11:52:59 - mmengine - INFO - Epoch(train) [7][300/1567] lr: 6.7390e-02 eta: 0:11:17 time: 0.0436 data_time: 0.0063 memory: 1793 loss: 0.3669 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3669 2022/11/28 11:53:03 - mmengine - INFO - Epoch(train) [7][400/1567] lr: 6.6802e-02 eta: 0:11:13 time: 0.0436 data_time: 0.0062 memory: 1793 loss: 0.3620 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.3620 2022/11/28 11:53:08 - mmengine - INFO - Epoch(train) [7][500/1567] lr: 6.6210e-02 eta: 0:11:08 time: 0.0436 data_time: 0.0064 memory: 1793 loss: 0.3760 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3760 2022/11/28 11:53:12 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 11:53:12 - mmengine - INFO - Epoch(train) [7][600/1567] lr: 6.5616e-02 eta: 0:11:04 time: 0.0438 data_time: 0.0064 memory: 1793 loss: 0.4270 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4270 2022/11/28 11:53:16 - mmengine - INFO - Epoch(train) [7][700/1567] lr: 6.5020e-02 eta: 0:10:59 time: 0.0439 data_time: 0.0062 memory: 1793 loss: 0.4012 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4012 2022/11/28 11:53:21 - mmengine - INFO - Epoch(train) [7][800/1567] lr: 6.4421e-02 eta: 0:10:55 time: 0.0462 data_time: 0.0087 memory: 1793 loss: 0.4072 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4072 2022/11/28 11:53:25 - mmengine - INFO - Epoch(train) [7][900/1567] lr: 6.3820e-02 eta: 0:10:50 time: 0.0446 data_time: 0.0064 memory: 1793 loss: 0.3755 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3755 2022/11/28 11:53:30 - mmengine - INFO - Epoch(train) [7][1000/1567] lr: 6.3217e-02 eta: 0:10:46 time: 0.0436 data_time: 0.0064 memory: 1793 loss: 0.3112 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3112 2022/11/28 11:53:34 - mmengine - INFO - Epoch(train) [7][1100/1567] lr: 6.2612e-02 eta: 0:10:42 time: 0.0443 data_time: 0.0062 memory: 1793 loss: 0.2594 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2594 2022/11/28 11:53:38 - mmengine - INFO - Epoch(train) [7][1200/1567] lr: 6.2005e-02 eta: 0:10:37 time: 0.0441 data_time: 0.0060 memory: 1793 loss: 0.3956 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.3956 2022/11/28 11:53:43 - mmengine - INFO - Epoch(train) [7][1300/1567] lr: 6.1396e-02 eta: 0:10:33 time: 0.0446 data_time: 0.0076 memory: 1793 loss: 0.3029 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.3029 2022/11/28 11:53:48 - mmengine - INFO - Epoch(train) [7][1400/1567] lr: 6.0785e-02 eta: 0:10:29 time: 0.0464 data_time: 0.0086 memory: 1793 loss: 0.2914 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.2914 2022/11/28 11:53:52 - mmengine - INFO - Epoch(train) [7][1500/1567] lr: 6.0172e-02 eta: 0:10:25 time: 0.0433 data_time: 0.0062 memory: 1793 loss: 0.2738 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2738 2022/11/28 11:53:55 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 11:53:55 - mmengine - INFO - Epoch(train) [7][1567/1567] lr: 5.9761e-02 eta: 0:10:22 time: 0.0430 data_time: 0.0067 memory: 1793 loss: 0.5287 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.5287 2022/11/28 11:53:55 - mmengine - INFO - Saving checkpoint at 7 epochs 2022/11/28 11:53:59 - mmengine - INFO - Epoch(val) [7][100/129] eta: 0:00:01 time: 0.0342 data_time: 0.0209 memory: 364 2022/11/28 11:54:00 - mmengine - INFO - Epoch(val) [7][129/129] acc/top1: 0.7676 acc/top5: 0.9541 acc/mean1: 0.7675 2022/11/28 11:54:02 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 11:54:05 - mmengine - INFO - Epoch(train) [8][100/1567] lr: 5.9145e-02 eta: 0:10:18 time: 0.0442 data_time: 0.0062 memory: 1793 loss: 0.3114 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3114 2022/11/28 11:54:09 - mmengine - INFO - Epoch(train) [8][200/1567] lr: 5.8529e-02 eta: 0:10:13 time: 0.0439 data_time: 0.0064 memory: 1793 loss: 0.2985 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2985 2022/11/28 11:54:14 - mmengine - INFO - Epoch(train) [8][300/1567] lr: 5.7911e-02 eta: 0:10:09 time: 0.0440 data_time: 0.0062 memory: 1793 loss: 0.2805 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.2805 2022/11/28 11:54:18 - mmengine - INFO - Epoch(train) [8][400/1567] lr: 5.7292e-02 eta: 0:10:05 time: 0.0434 data_time: 0.0062 memory: 1793 loss: 0.3026 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3026 2022/11/28 11:54:23 - mmengine - INFO - Epoch(train) [8][500/1567] lr: 5.6671e-02 eta: 0:10:00 time: 0.0432 data_time: 0.0064 memory: 1793 loss: 0.2760 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2760 2022/11/28 11:54:27 - mmengine - INFO - Epoch(train) [8][600/1567] lr: 5.6050e-02 eta: 0:09:56 time: 0.0449 data_time: 0.0065 memory: 1793 loss: 0.2905 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2905 2022/11/28 11:54:32 - mmengine - INFO - Epoch(train) [8][700/1567] lr: 5.5427e-02 eta: 0:09:52 time: 0.0435 data_time: 0.0064 memory: 1793 loss: 0.2937 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2937 2022/11/28 11:54:36 - mmengine - INFO - Epoch(train) [8][800/1567] lr: 5.4804e-02 eta: 0:09:47 time: 0.0436 data_time: 0.0062 memory: 1793 loss: 0.3478 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.3478 2022/11/28 11:54:41 - mmengine - INFO - Epoch(train) [8][900/1567] lr: 5.4180e-02 eta: 0:09:43 time: 0.0435 data_time: 0.0063 memory: 1793 loss: 0.3005 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3005 2022/11/28 11:54:45 - mmengine - INFO - Epoch(train) [8][1000/1567] lr: 5.3556e-02 eta: 0:09:38 time: 0.0433 data_time: 0.0061 memory: 1793 loss: 0.3179 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3179 2022/11/28 11:54:46 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 11:54:49 - mmengine - INFO - Epoch(train) [8][1100/1567] lr: 5.2930e-02 eta: 0:09:34 time: 0.0432 data_time: 0.0061 memory: 1793 loss: 0.2737 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2737 2022/11/28 11:54:54 - mmengine - INFO - Epoch(train) [8][1200/1567] lr: 5.2305e-02 eta: 0:09:29 time: 0.0437 data_time: 0.0063 memory: 1793 loss: 0.2887 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2887 2022/11/28 11:54:58 - mmengine - INFO - Epoch(train) [8][1300/1567] lr: 5.1679e-02 eta: 0:09:25 time: 0.0436 data_time: 0.0061 memory: 1793 loss: 0.2313 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2313 2022/11/28 11:55:03 - mmengine - INFO - Epoch(train) [8][1400/1567] lr: 5.1052e-02 eta: 0:09:21 time: 0.0443 data_time: 0.0068 memory: 1793 loss: 0.2568 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2568 2022/11/28 11:55:07 - mmengine - INFO - Epoch(train) [8][1500/1567] lr: 5.0426e-02 eta: 0:09:16 time: 0.0437 data_time: 0.0064 memory: 1793 loss: 0.1975 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.1975 2022/11/28 11:55:10 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 11:55:10 - mmengine - INFO - Epoch(train) [8][1567/1567] lr: 5.0006e-02 eta: 0:09:13 time: 0.0427 data_time: 0.0060 memory: 1793 loss: 0.4643 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.4643 2022/11/28 11:55:10 - mmengine - INFO - Saving checkpoint at 8 epochs 2022/11/28 11:55:14 - mmengine - INFO - Epoch(val) [8][100/129] eta: 0:00:01 time: 0.0340 data_time: 0.0207 memory: 364 2022/11/28 11:55:15 - mmengine - INFO - Epoch(val) [8][129/129] acc/top1: 0.8206 acc/top5: 0.9648 acc/mean1: 0.8205 2022/11/28 11:55:15 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_6.pth is removed 2022/11/28 11:55:16 - mmengine - INFO - The best checkpoint with 0.8206 acc/top1 at 8 epoch is saved to best_acc/top1_epoch_8.pth. 2022/11/28 11:55:20 - mmengine - INFO - Epoch(train) [9][100/1567] lr: 4.9380e-02 eta: 0:09:09 time: 0.0436 data_time: 0.0063 memory: 1793 loss: 0.2390 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2390 2022/11/28 11:55:25 - mmengine - INFO - Epoch(train) [9][200/1567] lr: 4.8753e-02 eta: 0:09:05 time: 0.0456 data_time: 0.0070 memory: 1793 loss: 0.2171 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2171 2022/11/28 11:55:29 - mmengine - INFO - Epoch(train) [9][300/1567] lr: 4.8127e-02 eta: 0:09:00 time: 0.0494 data_time: 0.0063 memory: 1793 loss: 0.2988 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2988 2022/11/28 11:55:34 - mmengine - INFO - Epoch(train) [9][400/1567] lr: 4.7501e-02 eta: 0:08:56 time: 0.0438 data_time: 0.0062 memory: 1793 loss: 0.2412 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2412 2022/11/28 11:55:36 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 11:55:38 - mmengine - INFO - Epoch(train) [9][500/1567] lr: 4.6876e-02 eta: 0:08:52 time: 0.0438 data_time: 0.0064 memory: 1793 loss: 0.2863 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2863 2022/11/28 11:55:42 - mmengine - INFO - Epoch(train) [9][600/1567] lr: 4.6251e-02 eta: 0:08:47 time: 0.0434 data_time: 0.0062 memory: 1793 loss: 0.1993 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1993 2022/11/28 11:55:47 - mmengine - INFO - Epoch(train) [9][700/1567] lr: 4.5626e-02 eta: 0:08:43 time: 0.0441 data_time: 0.0062 memory: 1793 loss: 0.2477 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2477 2022/11/28 11:55:51 - mmengine - INFO - Epoch(train) [9][800/1567] lr: 4.5003e-02 eta: 0:08:38 time: 0.0434 data_time: 0.0062 memory: 1793 loss: 0.2231 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2231 2022/11/28 11:55:56 - mmengine - INFO - Epoch(train) [9][900/1567] lr: 4.4380e-02 eta: 0:08:34 time: 0.0443 data_time: 0.0069 memory: 1793 loss: 0.2333 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2333 2022/11/28 11:56:00 - mmengine - INFO - Epoch(train) [9][1000/1567] lr: 4.3757e-02 eta: 0:08:29 time: 0.0432 data_time: 0.0062 memory: 1793 loss: 0.2636 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2636 2022/11/28 11:56:04 - mmengine - INFO - Epoch(train) [9][1100/1567] lr: 4.3136e-02 eta: 0:08:25 time: 0.0442 data_time: 0.0063 memory: 1793 loss: 0.1685 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1685 2022/11/28 11:56:09 - mmengine - INFO - Epoch(train) [9][1200/1567] lr: 4.2516e-02 eta: 0:08:21 time: 0.0478 data_time: 0.0067 memory: 1793 loss: 0.3019 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3019 2022/11/28 11:56:13 - mmengine - INFO - Epoch(train) [9][1300/1567] lr: 4.1897e-02 eta: 0:08:16 time: 0.0441 data_time: 0.0061 memory: 1793 loss: 0.2094 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2094 2022/11/28 11:56:18 - mmengine - INFO - Epoch(train) [9][1400/1567] lr: 4.1280e-02 eta: 0:08:12 time: 0.0443 data_time: 0.0065 memory: 1793 loss: 0.2889 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2889 2022/11/28 11:56:21 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 11:56:22 - mmengine - INFO - Epoch(train) [9][1500/1567] lr: 4.0664e-02 eta: 0:08:07 time: 0.0435 data_time: 0.0062 memory: 1793 loss: 0.2201 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 0.2201 2022/11/28 11:56:25 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 11:56:25 - mmengine - INFO - Epoch(train) [9][1567/1567] lr: 4.0252e-02 eta: 0:08:04 time: 0.0465 data_time: 0.0097 memory: 1793 loss: 0.3816 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.3816 2022/11/28 11:56:25 - mmengine - INFO - Saving checkpoint at 9 epochs 2022/11/28 11:56:29 - mmengine - INFO - Epoch(val) [9][100/129] eta: 0:00:01 time: 0.0335 data_time: 0.0201 memory: 364 2022/11/28 11:56:30 - mmengine - INFO - Epoch(val) [9][129/129] acc/top1: 0.8134 acc/top5: 0.9650 acc/mean1: 0.8132 2022/11/28 11:56:35 - mmengine - INFO - Epoch(train) [10][100/1567] lr: 3.9638e-02 eta: 0:08:00 time: 0.0434 data_time: 0.0061 memory: 1793 loss: 0.1682 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1682 2022/11/28 11:56:39 - mmengine - INFO - Epoch(train) [10][200/1567] lr: 3.9026e-02 eta: 0:07:56 time: 0.0444 data_time: 0.0063 memory: 1793 loss: 0.2039 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.2039 2022/11/28 11:56:44 - mmengine - INFO - Epoch(train) [10][300/1567] lr: 3.8415e-02 eta: 0:07:51 time: 0.0432 data_time: 0.0061 memory: 1793 loss: 0.1458 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1458 2022/11/28 11:56:48 - mmengine - INFO - Epoch(train) [10][400/1567] lr: 3.7807e-02 eta: 0:07:47 time: 0.0438 data_time: 0.0062 memory: 1793 loss: 0.1192 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1192 2022/11/28 11:56:52 - mmengine - INFO - Epoch(train) [10][500/1567] lr: 3.7200e-02 eta: 0:07:42 time: 0.0443 data_time: 0.0064 memory: 1793 loss: 0.2489 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.2489 2022/11/28 11:56:57 - mmengine - INFO - Epoch(train) [10][600/1567] lr: 3.6596e-02 eta: 0:07:38 time: 0.0441 data_time: 0.0063 memory: 1793 loss: 0.1928 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.1928 2022/11/28 11:57:01 - mmengine - INFO - Epoch(train) [10][700/1567] lr: 3.5993e-02 eta: 0:07:34 time: 0.0441 data_time: 0.0062 memory: 1793 loss: 0.1616 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1616 2022/11/28 11:57:06 - mmengine - INFO - Epoch(train) [10][800/1567] lr: 3.5393e-02 eta: 0:07:29 time: 0.0436 data_time: 0.0062 memory: 1793 loss: 0.2293 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2293 2022/11/28 11:57:10 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 11:57:10 - mmengine - INFO - Epoch(train) [10][900/1567] lr: 3.4795e-02 eta: 0:07:25 time: 0.0437 data_time: 0.0064 memory: 1793 loss: 0.1722 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1722 2022/11/28 11:57:15 - mmengine - INFO - Epoch(train) [10][1000/1567] lr: 3.4199e-02 eta: 0:07:20 time: 0.0452 data_time: 0.0066 memory: 1793 loss: 0.1982 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1982 2022/11/28 11:57:19 - mmengine - INFO - Epoch(train) [10][1100/1567] lr: 3.3606e-02 eta: 0:07:16 time: 0.0443 data_time: 0.0061 memory: 1793 loss: 0.1420 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1420 2022/11/28 11:57:24 - mmengine - INFO - Epoch(train) [10][1200/1567] lr: 3.3015e-02 eta: 0:07:12 time: 0.0451 data_time: 0.0064 memory: 1793 loss: 0.1490 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1490 2022/11/28 11:57:28 - mmengine - INFO - Epoch(train) [10][1300/1567] lr: 3.2428e-02 eta: 0:07:07 time: 0.0443 data_time: 0.0063 memory: 1793 loss: 0.1710 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1710 2022/11/28 11:57:33 - mmengine - INFO - Epoch(train) [10][1400/1567] lr: 3.1842e-02 eta: 0:07:03 time: 0.0452 data_time: 0.0064 memory: 1793 loss: 0.1573 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1573 2022/11/28 11:57:37 - mmengine - INFO - Epoch(train) [10][1500/1567] lr: 3.1260e-02 eta: 0:06:58 time: 0.0432 data_time: 0.0061 memory: 1793 loss: 0.1566 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1566 2022/11/28 11:57:40 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 11:57:40 - mmengine - INFO - Epoch(train) [10][1567/1567] lr: 3.0872e-02 eta: 0:06:55 time: 0.0429 data_time: 0.0061 memory: 1793 loss: 0.3700 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.3700 2022/11/28 11:57:40 - mmengine - INFO - Saving checkpoint at 10 epochs 2022/11/28 11:57:44 - mmengine - INFO - Epoch(val) [10][100/129] eta: 0:00:01 time: 0.0334 data_time: 0.0201 memory: 364 2022/11/28 11:57:45 - mmengine - INFO - Epoch(val) [10][129/129] acc/top1: 0.8342 acc/top5: 0.9669 acc/mean1: 0.8340 2022/11/28 11:57:45 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_8.pth is removed 2022/11/28 11:57:45 - mmengine - INFO - The best checkpoint with 0.8342 acc/top1 at 10 epoch is saved to best_acc/top1_epoch_10.pth. 2022/11/28 11:57:50 - mmengine - INFO - Epoch(train) [11][100/1567] lr: 3.0294e-02 eta: 0:06:51 time: 0.0434 data_time: 0.0061 memory: 1793 loss: 0.1420 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1420 2022/11/28 11:57:54 - mmengine - INFO - Epoch(train) [11][200/1567] lr: 2.9720e-02 eta: 0:06:47 time: 0.0471 data_time: 0.0083 memory: 1793 loss: 0.1100 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1100 2022/11/28 11:57:59 - mmengine - INFO - Epoch(train) [11][300/1567] lr: 2.9149e-02 eta: 0:06:42 time: 0.0443 data_time: 0.0069 memory: 1793 loss: 0.1047 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1047 2022/11/28 11:58:00 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 11:58:03 - mmengine - INFO - Epoch(train) [11][400/1567] lr: 2.8581e-02 eta: 0:06:38 time: 0.0440 data_time: 0.0061 memory: 1793 loss: 0.1492 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1492 2022/11/28 11:58:07 - mmengine - INFO - Epoch(train) [11][500/1567] lr: 2.8017e-02 eta: 0:06:33 time: 0.0437 data_time: 0.0061 memory: 1793 loss: 0.1501 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1501 2022/11/28 11:58:12 - mmengine - INFO - Epoch(train) [11][600/1567] lr: 2.7456e-02 eta: 0:06:29 time: 0.0447 data_time: 0.0061 memory: 1793 loss: 0.1273 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.1273 2022/11/28 11:58:16 - mmengine - INFO - Epoch(train) [11][700/1567] lr: 2.6898e-02 eta: 0:06:24 time: 0.0435 data_time: 0.0060 memory: 1793 loss: 0.1302 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1302 2022/11/28 11:58:21 - mmengine - INFO - Epoch(train) [11][800/1567] lr: 2.6345e-02 eta: 0:06:20 time: 0.0430 data_time: 0.0061 memory: 1793 loss: 0.1217 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.1217 2022/11/28 11:58:25 - mmengine - INFO - Epoch(train) [11][900/1567] lr: 2.5794e-02 eta: 0:06:16 time: 0.0444 data_time: 0.0061 memory: 1793 loss: 0.1314 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1314 2022/11/28 11:58:29 - mmengine - INFO - Epoch(train) [11][1000/1567] lr: 2.5248e-02 eta: 0:06:11 time: 0.0431 data_time: 0.0061 memory: 1793 loss: 0.1132 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1132 2022/11/28 11:58:34 - mmengine - INFO - Epoch(train) [11][1100/1567] lr: 2.4706e-02 eta: 0:06:07 time: 0.0433 data_time: 0.0061 memory: 1793 loss: 0.1095 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1095 2022/11/28 11:58:38 - mmengine - INFO - Epoch(train) [11][1200/1567] lr: 2.4167e-02 eta: 0:06:02 time: 0.0432 data_time: 0.0061 memory: 1793 loss: 0.1263 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.1263 2022/11/28 11:58:43 - mmengine - INFO - Epoch(train) [11][1300/1567] lr: 2.3633e-02 eta: 0:05:58 time: 0.0436 data_time: 0.0060 memory: 1793 loss: 0.1305 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1305 2022/11/28 11:58:44 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 11:58:47 - mmengine - INFO - Epoch(train) [11][1400/1567] lr: 2.3103e-02 eta: 0:05:53 time: 0.0433 data_time: 0.0061 memory: 1793 loss: 0.1653 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1653 2022/11/28 11:58:51 - mmengine - INFO - Epoch(train) [11][1500/1567] lr: 2.2577e-02 eta: 0:05:49 time: 0.0431 data_time: 0.0061 memory: 1793 loss: 0.0864 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0864 2022/11/28 11:58:54 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 11:58:54 - mmengine - INFO - Epoch(train) [11][1567/1567] lr: 2.2227e-02 eta: 0:05:46 time: 0.0434 data_time: 0.0066 memory: 1793 loss: 0.2872 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2872 2022/11/28 11:58:54 - mmengine - INFO - Saving checkpoint at 11 epochs 2022/11/28 11:58:58 - mmengine - INFO - Epoch(val) [11][100/129] eta: 0:00:01 time: 0.0342 data_time: 0.0204 memory: 364 2022/11/28 11:58:59 - mmengine - INFO - Epoch(val) [11][129/129] acc/top1: 0.8462 acc/top5: 0.9712 acc/mean1: 0.8461 2022/11/28 11:58:59 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_10.pth is removed 2022/11/28 11:58:59 - mmengine - INFO - The best checkpoint with 0.8462 acc/top1 at 11 epoch is saved to best_acc/top1_epoch_11.pth. 2022/11/28 11:59:04 - mmengine - INFO - Epoch(train) [12][100/1567] lr: 2.1708e-02 eta: 0:05:41 time: 0.0440 data_time: 0.0069 memory: 1793 loss: 0.0785 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0785 2022/11/28 11:59:08 - mmengine - INFO - Epoch(train) [12][200/1567] lr: 2.1194e-02 eta: 0:05:37 time: 0.0440 data_time: 0.0061 memory: 1793 loss: 0.0997 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.0997 2022/11/28 11:59:13 - mmengine - INFO - Epoch(train) [12][300/1567] lr: 2.0684e-02 eta: 0:05:33 time: 0.0430 data_time: 0.0061 memory: 1793 loss: 0.0379 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0379 2022/11/28 11:59:17 - mmengine - INFO - Epoch(train) [12][400/1567] lr: 2.0179e-02 eta: 0:05:28 time: 0.0438 data_time: 0.0062 memory: 1793 loss: 0.0582 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0582 2022/11/28 11:59:21 - mmengine - INFO - Epoch(train) [12][500/1567] lr: 1.9678e-02 eta: 0:05:24 time: 0.0431 data_time: 0.0061 memory: 1793 loss: 0.0679 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0679 2022/11/28 11:59:26 - mmengine - INFO - Epoch(train) [12][600/1567] lr: 1.9182e-02 eta: 0:05:19 time: 0.0440 data_time: 0.0061 memory: 1793 loss: 0.0660 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0660 2022/11/28 11:59:30 - mmengine - INFO - Epoch(train) [12][700/1567] lr: 1.8691e-02 eta: 0:05:15 time: 0.0444 data_time: 0.0062 memory: 1793 loss: 0.0336 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0336 2022/11/28 11:59:33 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 11:59:35 - mmengine - INFO - Epoch(train) [12][800/1567] lr: 1.8205e-02 eta: 0:05:10 time: 0.0433 data_time: 0.0062 memory: 1793 loss: 0.0699 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0699 2022/11/28 11:59:39 - mmengine - INFO - Epoch(train) [12][900/1567] lr: 1.7724e-02 eta: 0:05:06 time: 0.0465 data_time: 0.0062 memory: 1793 loss: 0.0417 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0417 2022/11/28 11:59:43 - mmengine - INFO - Epoch(train) [12][1000/1567] lr: 1.7248e-02 eta: 0:05:01 time: 0.0430 data_time: 0.0061 memory: 1793 loss: 0.0489 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0489 2022/11/28 11:59:48 - mmengine - INFO - Epoch(train) [12][1100/1567] lr: 1.6778e-02 eta: 0:04:57 time: 0.0431 data_time: 0.0061 memory: 1793 loss: 0.0450 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0450 2022/11/28 11:59:52 - mmengine - INFO - Epoch(train) [12][1200/1567] lr: 1.6312e-02 eta: 0:04:53 time: 0.0430 data_time: 0.0061 memory: 1793 loss: 0.0635 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0635 2022/11/28 11:59:56 - mmengine - INFO - Epoch(train) [12][1300/1567] lr: 1.5852e-02 eta: 0:04:48 time: 0.0433 data_time: 0.0063 memory: 1793 loss: 0.0756 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0756 2022/11/28 12:00:01 - mmengine - INFO - Epoch(train) [12][1400/1567] lr: 1.5397e-02 eta: 0:04:44 time: 0.0430 data_time: 0.0061 memory: 1793 loss: 0.0588 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0588 2022/11/28 12:00:05 - mmengine - INFO - Epoch(train) [12][1500/1567] lr: 1.4947e-02 eta: 0:04:39 time: 0.0435 data_time: 0.0061 memory: 1793 loss: 0.0400 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0400 2022/11/28 12:00:08 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 12:00:08 - mmengine - INFO - Epoch(train) [12][1567/1567] lr: 1.4649e-02 eta: 0:04:36 time: 0.0419 data_time: 0.0059 memory: 1793 loss: 0.1727 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1727 2022/11/28 12:00:08 - mmengine - INFO - Saving checkpoint at 12 epochs 2022/11/28 12:00:12 - mmengine - INFO - Epoch(val) [12][100/129] eta: 0:00:01 time: 0.0334 data_time: 0.0201 memory: 364 2022/11/28 12:00:13 - mmengine - INFO - Epoch(val) [12][129/129] acc/top1: 0.8640 acc/top5: 0.9718 acc/mean1: 0.8639 2022/11/28 12:00:13 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_11.pth is removed 2022/11/28 12:00:13 - mmengine - INFO - The best checkpoint with 0.8640 acc/top1 at 12 epoch is saved to best_acc/top1_epoch_12.pth. 2022/11/28 12:00:18 - mmengine - INFO - Epoch(train) [13][100/1567] lr: 1.4209e-02 eta: 0:04:32 time: 0.0434 data_time: 0.0061 memory: 1793 loss: 0.0414 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0414 2022/11/28 12:00:22 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 12:00:22 - mmengine - INFO - Epoch(train) [13][200/1567] lr: 1.3774e-02 eta: 0:04:27 time: 0.0432 data_time: 0.0061 memory: 1793 loss: 0.0175 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0175 2022/11/28 12:00:26 - mmengine - INFO - Epoch(train) [13][300/1567] lr: 1.3345e-02 eta: 0:04:23 time: 0.0432 data_time: 0.0062 memory: 1793 loss: 0.0364 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0364 2022/11/28 12:00:31 - mmengine - INFO - Epoch(train) [13][400/1567] lr: 1.2922e-02 eta: 0:04:19 time: 0.0434 data_time: 0.0066 memory: 1793 loss: 0.0218 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0218 2022/11/28 12:00:35 - mmengine - INFO - Epoch(train) [13][500/1567] lr: 1.2505e-02 eta: 0:04:14 time: 0.0433 data_time: 0.0067 memory: 1793 loss: 0.0281 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0281 2022/11/28 12:00:39 - mmengine - INFO - Epoch(train) [13][600/1567] lr: 1.2093e-02 eta: 0:04:10 time: 0.0445 data_time: 0.0069 memory: 1793 loss: 0.0376 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0376 2022/11/28 12:00:44 - mmengine - INFO - Epoch(train) [13][700/1567] lr: 1.1687e-02 eta: 0:04:05 time: 0.0438 data_time: 0.0061 memory: 1793 loss: 0.0173 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0173 2022/11/28 12:00:48 - mmengine - INFO - Epoch(train) [13][800/1567] lr: 1.1288e-02 eta: 0:04:01 time: 0.0431 data_time: 0.0061 memory: 1793 loss: 0.0160 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0160 2022/11/28 12:00:53 - mmengine - INFO - Epoch(train) [13][900/1567] lr: 1.0894e-02 eta: 0:03:56 time: 0.0431 data_time: 0.0062 memory: 1793 loss: 0.0265 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0265 2022/11/28 12:00:57 - mmengine - INFO - Epoch(train) [13][1000/1567] lr: 1.0507e-02 eta: 0:03:52 time: 0.0435 data_time: 0.0061 memory: 1793 loss: 0.0285 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0285 2022/11/28 12:01:01 - mmengine - INFO - Epoch(train) [13][1100/1567] lr: 1.0126e-02 eta: 0:03:48 time: 0.0439 data_time: 0.0061 memory: 1793 loss: 0.0198 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0198 2022/11/28 12:01:05 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 12:01:06 - mmengine - INFO - Epoch(train) [13][1200/1567] lr: 9.7512e-03 eta: 0:03:43 time: 0.0432 data_time: 0.0062 memory: 1793 loss: 0.0134 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0134 2022/11/28 12:01:10 - mmengine - INFO - Epoch(train) [13][1300/1567] lr: 9.3826e-03 eta: 0:03:39 time: 0.0437 data_time: 0.0065 memory: 1793 loss: 0.0149 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0149 2022/11/28 12:01:14 - mmengine - INFO - Epoch(train) [13][1400/1567] lr: 9.0204e-03 eta: 0:03:34 time: 0.0438 data_time: 0.0066 memory: 1793 loss: 0.0175 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0175 2022/11/28 12:01:19 - mmengine - INFO - Epoch(train) [13][1500/1567] lr: 8.6647e-03 eta: 0:03:30 time: 0.0436 data_time: 0.0066 memory: 1793 loss: 0.0195 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0195 2022/11/28 12:01:22 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 12:01:22 - mmengine - INFO - Epoch(train) [13][1567/1567] lr: 8.4300e-03 eta: 0:03:27 time: 0.0425 data_time: 0.0063 memory: 1793 loss: 0.2366 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2366 2022/11/28 12:01:22 - mmengine - INFO - Saving checkpoint at 13 epochs 2022/11/28 12:01:26 - mmengine - INFO - Epoch(val) [13][100/129] eta: 0:00:01 time: 0.0338 data_time: 0.0203 memory: 364 2022/11/28 12:01:27 - mmengine - INFO - Epoch(val) [13][129/129] acc/top1: 0.8757 acc/top5: 0.9770 acc/mean1: 0.8756 2022/11/28 12:01:27 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_12.pth is removed 2022/11/28 12:01:27 - mmengine - INFO - The best checkpoint with 0.8757 acc/top1 at 13 epoch is saved to best_acc/top1_epoch_13.pth. 2022/11/28 12:01:32 - mmengine - INFO - Epoch(train) [14][100/1567] lr: 8.0851e-03 eta: 0:03:22 time: 0.0458 data_time: 0.0061 memory: 1793 loss: 0.0124 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0124 2022/11/28 12:01:36 - mmengine - INFO - Epoch(train) [14][200/1567] lr: 7.7469e-03 eta: 0:03:18 time: 0.0435 data_time: 0.0068 memory: 1793 loss: 0.0159 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0159 2022/11/28 12:01:40 - mmengine - INFO - Epoch(train) [14][300/1567] lr: 7.4152e-03 eta: 0:03:14 time: 0.0442 data_time: 0.0067 memory: 1793 loss: 0.0110 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0110 2022/11/28 12:01:45 - mmengine - INFO - Epoch(train) [14][400/1567] lr: 7.0902e-03 eta: 0:03:09 time: 0.0438 data_time: 0.0061 memory: 1793 loss: 0.0103 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0103 2022/11/28 12:01:49 - mmengine - INFO - Epoch(train) [14][500/1567] lr: 6.7720e-03 eta: 0:03:05 time: 0.0440 data_time: 0.0065 memory: 1793 loss: 0.0150 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0150 2022/11/28 12:01:54 - mmengine - INFO - Epoch(train) [14][600/1567] lr: 6.4606e-03 eta: 0:03:00 time: 0.0446 data_time: 0.0067 memory: 1793 loss: 0.0196 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0196 2022/11/28 12:01:55 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 12:01:58 - mmengine - INFO - Epoch(train) [14][700/1567] lr: 6.1560e-03 eta: 0:02:56 time: 0.0438 data_time: 0.0067 memory: 1793 loss: 0.0093 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0093 2022/11/28 12:02:03 - mmengine - INFO - Epoch(train) [14][800/1567] lr: 5.8582e-03 eta: 0:02:52 time: 0.0436 data_time: 0.0061 memory: 1793 loss: 0.0135 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0135 2022/11/28 12:02:07 - mmengine - INFO - Epoch(train) [14][900/1567] lr: 5.5675e-03 eta: 0:02:47 time: 0.0436 data_time: 0.0069 memory: 1793 loss: 0.0094 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0094 2022/11/28 12:02:11 - mmengine - INFO - Epoch(train) [14][1000/1567] lr: 5.2836e-03 eta: 0:02:43 time: 0.0433 data_time: 0.0061 memory: 1793 loss: 0.0155 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0155 2022/11/28 12:02:16 - mmengine - INFO - Epoch(train) [14][1100/1567] lr: 5.0068e-03 eta: 0:02:38 time: 0.0435 data_time: 0.0060 memory: 1793 loss: 0.0210 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0210 2022/11/28 12:02:20 - mmengine - INFO - Epoch(train) [14][1200/1567] lr: 4.7371e-03 eta: 0:02:34 time: 0.0438 data_time: 0.0061 memory: 1793 loss: 0.0126 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0126 2022/11/28 12:02:25 - mmengine - INFO - Epoch(train) [14][1300/1567] lr: 4.4745e-03 eta: 0:02:30 time: 0.0454 data_time: 0.0062 memory: 1793 loss: 0.0119 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0119 2022/11/28 12:02:29 - mmengine - INFO - Epoch(train) [14][1400/1567] lr: 4.2190e-03 eta: 0:02:25 time: 0.0435 data_time: 0.0060 memory: 1793 loss: 0.0083 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0083 2022/11/28 12:02:33 - mmengine - INFO - Epoch(train) [14][1500/1567] lr: 3.9707e-03 eta: 0:02:21 time: 0.0436 data_time: 0.0061 memory: 1793 loss: 0.0131 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0131 2022/11/28 12:02:36 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 12:02:36 - mmengine - INFO - Epoch(train) [14][1567/1567] lr: 3.8084e-03 eta: 0:02:18 time: 0.0422 data_time: 0.0059 memory: 1793 loss: 0.1523 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1523 2022/11/28 12:02:36 - mmengine - INFO - Saving checkpoint at 14 epochs 2022/11/28 12:02:40 - mmengine - INFO - Epoch(val) [14][100/129] eta: 0:00:01 time: 0.0354 data_time: 0.0222 memory: 364 2022/11/28 12:02:41 - mmengine - INFO - Epoch(val) [14][129/129] acc/top1: 0.8826 acc/top5: 0.9767 acc/mean1: 0.8825 2022/11/28 12:02:41 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_13.pth is removed 2022/11/28 12:02:42 - mmengine - INFO - The best checkpoint with 0.8826 acc/top1 at 14 epoch is saved to best_acc/top1_epoch_14.pth. 2022/11/28 12:02:44 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 12:02:46 - mmengine - INFO - Epoch(train) [15][100/1567] lr: 3.5722e-03 eta: 0:02:13 time: 0.0434 data_time: 0.0061 memory: 1793 loss: 0.0095 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0095 2022/11/28 12:02:50 - mmengine - INFO - Epoch(train) [15][200/1567] lr: 3.3433e-03 eta: 0:02:09 time: 0.0432 data_time: 0.0060 memory: 1793 loss: 0.0108 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0108 2022/11/28 12:02:55 - mmengine - INFO - Epoch(train) [15][300/1567] lr: 3.1217e-03 eta: 0:02:05 time: 0.0431 data_time: 0.0061 memory: 1793 loss: 0.0081 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0081 2022/11/28 12:02:59 - mmengine - INFO - Epoch(train) [15][400/1567] lr: 2.9075e-03 eta: 0:02:00 time: 0.0435 data_time: 0.0061 memory: 1793 loss: 0.0105 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0105 2022/11/28 12:03:04 - mmengine - INFO - Epoch(train) [15][500/1567] lr: 2.7007e-03 eta: 0:01:56 time: 0.0438 data_time: 0.0061 memory: 1793 loss: 0.0107 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0107 2022/11/28 12:03:08 - mmengine - INFO - Epoch(train) [15][600/1567] lr: 2.5013e-03 eta: 0:01:51 time: 0.0437 data_time: 0.0061 memory: 1793 loss: 0.0083 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0083 2022/11/28 12:03:12 - mmengine - INFO - Epoch(train) [15][700/1567] lr: 2.3093e-03 eta: 0:01:47 time: 0.0434 data_time: 0.0061 memory: 1793 loss: 0.0090 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0090 2022/11/28 12:03:17 - mmengine - INFO - Epoch(train) [15][800/1567] lr: 2.1249e-03 eta: 0:01:42 time: 0.0435 data_time: 0.0061 memory: 1793 loss: 0.0135 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0135 2022/11/28 12:03:21 - mmengine - INFO - Epoch(train) [15][900/1567] lr: 1.9479e-03 eta: 0:01:38 time: 0.0432 data_time: 0.0061 memory: 1793 loss: 0.0088 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0088 2022/11/28 12:03:25 - mmengine - INFO - Epoch(train) [15][1000/1567] lr: 1.7785e-03 eta: 0:01:34 time: 0.0439 data_time: 0.0061 memory: 1793 loss: 0.0102 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0102 2022/11/28 12:03:28 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 12:03:30 - mmengine - INFO - Epoch(train) [15][1100/1567] lr: 1.6167e-03 eta: 0:01:29 time: 0.0445 data_time: 0.0061 memory: 1793 loss: 0.0120 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0120 2022/11/28 12:03:34 - mmengine - INFO - Epoch(train) [15][1200/1567] lr: 1.4625e-03 eta: 0:01:25 time: 0.0464 data_time: 0.0061 memory: 1793 loss: 0.0096 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0096 2022/11/28 12:03:39 - mmengine - INFO - Epoch(train) [15][1300/1567] lr: 1.3159e-03 eta: 0:01:20 time: 0.0466 data_time: 0.0089 memory: 1793 loss: 0.0086 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0086 2022/11/28 12:03:43 - mmengine - INFO - Epoch(train) [15][1400/1567] lr: 1.1769e-03 eta: 0:01:16 time: 0.0435 data_time: 0.0061 memory: 1793 loss: 0.0113 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0113 2022/11/28 12:03:48 - mmengine - INFO - Epoch(train) [15][1500/1567] lr: 1.0456e-03 eta: 0:01:12 time: 0.0439 data_time: 0.0062 memory: 1793 loss: 0.0068 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0068 2022/11/28 12:03:51 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 12:03:51 - mmengine - INFO - Epoch(train) [15][1567/1567] lr: 9.6196e-04 eta: 0:01:09 time: 0.0425 data_time: 0.0059 memory: 1793 loss: 0.1177 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1177 2022/11/28 12:03:51 - mmengine - INFO - Saving checkpoint at 15 epochs 2022/11/28 12:03:54 - mmengine - INFO - Epoch(val) [15][100/129] eta: 0:00:01 time: 0.0333 data_time: 0.0201 memory: 364 2022/11/28 12:03:56 - mmengine - INFO - Epoch(val) [15][129/129] acc/top1: 0.8832 acc/top5: 0.9768 acc/mean1: 0.8831 2022/11/28 12:03:56 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_14.pth is removed 2022/11/28 12:03:56 - mmengine - INFO - The best checkpoint with 0.8832 acc/top1 at 15 epoch is saved to best_acc/top1_epoch_15.pth. 2022/11/28 12:04:00 - mmengine - INFO - Epoch(train) [16][100/1567] lr: 8.4351e-04 eta: 0:01:04 time: 0.0433 data_time: 0.0061 memory: 1793 loss: 0.0076 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0076 2022/11/28 12:04:05 - mmengine - INFO - Epoch(train) [16][200/1567] lr: 7.3277e-04 eta: 0:01:00 time: 0.0435 data_time: 0.0061 memory: 1793 loss: 0.0095 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0095 2022/11/28 12:04:09 - mmengine - INFO - Epoch(train) [16][300/1567] lr: 6.2978e-04 eta: 0:00:55 time: 0.0439 data_time: 0.0062 memory: 1793 loss: 0.0105 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0105 2022/11/28 12:04:14 - mmengine - INFO - Epoch(train) [16][400/1567] lr: 5.3453e-04 eta: 0:00:51 time: 0.0431 data_time: 0.0060 memory: 1793 loss: 0.0114 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0114 2022/11/28 12:04:18 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 12:04:18 - mmengine - INFO - Epoch(train) [16][500/1567] lr: 4.4705e-04 eta: 0:00:47 time: 0.0472 data_time: 0.0061 memory: 1793 loss: 0.0134 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0134 2022/11/28 12:04:22 - mmengine - INFO - Epoch(train) [16][600/1567] lr: 3.6735e-04 eta: 0:00:42 time: 0.0461 data_time: 0.0083 memory: 1793 loss: 0.0079 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0079 2022/11/28 12:04:27 - mmengine - INFO - Epoch(train) [16][700/1567] lr: 2.9544e-04 eta: 0:00:38 time: 0.0434 data_time: 0.0061 memory: 1793 loss: 0.0081 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0081 2022/11/28 12:04:31 - mmengine - INFO - Epoch(train) [16][800/1567] lr: 2.3134e-04 eta: 0:00:33 time: 0.0437 data_time: 0.0061 memory: 1793 loss: 0.0119 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0119 2022/11/28 12:04:36 - mmengine - INFO - Epoch(train) [16][900/1567] lr: 1.7505e-04 eta: 0:00:29 time: 0.0433 data_time: 0.0061 memory: 1793 loss: 0.0100 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0100 2022/11/28 12:04:40 - mmengine - INFO - Epoch(train) [16][1000/1567] lr: 1.2658e-04 eta: 0:00:25 time: 0.0465 data_time: 0.0079 memory: 1793 loss: 0.0089 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0089 2022/11/28 12:04:44 - mmengine - INFO - Epoch(train) [16][1100/1567] lr: 8.5947e-05 eta: 0:00:20 time: 0.0435 data_time: 0.0062 memory: 1793 loss: 0.0091 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0091 2022/11/28 12:04:49 - mmengine - INFO - Epoch(train) [16][1200/1567] lr: 5.3147e-05 eta: 0:00:16 time: 0.0433 data_time: 0.0061 memory: 1793 loss: 0.0093 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0093 2022/11/28 12:04:53 - mmengine - INFO - Epoch(train) [16][1300/1567] lr: 2.8190e-05 eta: 0:00:11 time: 0.0435 data_time: 0.0061 memory: 1793 loss: 0.0079 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0079 2022/11/28 12:04:58 - mmengine - INFO - Epoch(train) [16][1400/1567] lr: 1.1078e-05 eta: 0:00:07 time: 0.0439 data_time: 0.0061 memory: 1793 loss: 0.0135 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0135 2022/11/28 12:05:02 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 12:05:02 - mmengine - INFO - Epoch(train) [16][1500/1567] lr: 1.8150e-06 eta: 0:00:02 time: 0.0436 data_time: 0.0062 memory: 1793 loss: 0.0081 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0081 2022/11/28 12:05:05 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221128_114435 2022/11/28 12:05:05 - mmengine - INFO - Epoch(train) [16][1567/1567] lr: 3.9252e-10 eta: 0:00:00 time: 0.0421 data_time: 0.0060 memory: 1793 loss: 0.1750 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.1750 2022/11/28 12:05:05 - mmengine - INFO - Saving checkpoint at 16 epochs 2022/11/28 12:05:09 - mmengine - INFO - Epoch(val) [16][100/129] eta: 0:00:01 time: 0.0346 data_time: 0.0213 memory: 364 2022/11/28 12:05:10 - mmengine - INFO - Epoch(val) [16][129/129] acc/top1: 0.8840 acc/top5: 0.9768 acc/mean1: 0.8839 2022/11/28 12:05:10 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_15.pth is removed 2022/11/28 12:05:10 - mmengine - INFO - The best checkpoint with 0.8840 acc/top1 at 16 epoch is saved to best_acc/top1_epoch_16.pth.