2022/11/28 00:54:45 - 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: 150966150 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: slurm Distributed training: True GPU number: 8 ------------------------------------------------------------ 2022/11/28 00:54:45 - 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=['j']), 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=['j']), 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=['j']), 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=['j']), 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=['j']), 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=['j']), 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 = 'slurm' work_dir = './work_dirs/stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d' randomness = dict(seed=None, diff_rank_seed=False, deterministic=False) 2022/11/28 00:54:45 - mmengine - INFO - Result has been saved to /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-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 00:55:23 - mmengine - INFO - Checkpoints will be saved to /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d. 2022/11/28 00:55:30 - mmengine - INFO - Epoch(train) [1][100/1567] lr: 9.9996e-02 eta: 0:26:17 time: 0.0447 data_time: 0.0073 memory: 1793 loss: 2.8633 top1_acc: 0.1250 top5_acc: 0.5625 loss_cls: 2.8633 2022/11/28 00:55:34 - mmengine - INFO - Epoch(train) [1][200/1567] lr: 9.9984e-02 eta: 0:22:40 time: 0.0442 data_time: 0.0073 memory: 1793 loss: 2.1653 top1_acc: 0.4375 top5_acc: 0.5625 loss_cls: 2.1653 2022/11/28 00:55:39 - mmengine - INFO - Epoch(train) [1][300/1567] lr: 9.9965e-02 eta: 0:21:08 time: 0.0438 data_time: 0.0072 memory: 1793 loss: 1.7556 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.7556 2022/11/28 00:55:43 - mmengine - INFO - Epoch(train) [1][400/1567] lr: 9.9938e-02 eta: 0:20:20 time: 0.0446 data_time: 0.0072 memory: 1793 loss: 1.5650 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.5650 2022/11/28 00:55:48 - mmengine - INFO - Epoch(train) [1][500/1567] lr: 9.9902e-02 eta: 0:19:54 time: 0.0448 data_time: 0.0073 memory: 1793 loss: 1.4651 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.4651 2022/11/28 00:55:52 - mmengine - INFO - Epoch(train) [1][600/1567] lr: 9.9859e-02 eta: 0:19:35 time: 0.0436 data_time: 0.0066 memory: 1793 loss: 1.3495 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.3495 2022/11/28 00:55:57 - mmengine - INFO - Epoch(train) [1][700/1567] lr: 9.9808e-02 eta: 0:19:19 time: 0.0455 data_time: 0.0066 memory: 1793 loss: 1.2858 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.2858 2022/11/28 00:56:01 - mmengine - INFO - Epoch(train) [1][800/1567] lr: 9.9750e-02 eta: 0:19:05 time: 0.0437 data_time: 0.0066 memory: 1793 loss: 1.1241 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1241 2022/11/28 00:56:06 - mmengine - INFO - Epoch(train) [1][900/1567] lr: 9.9683e-02 eta: 0:18:52 time: 0.0440 data_time: 0.0067 memory: 1793 loss: 1.1303 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1303 2022/11/28 00:56:10 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 00:56:10 - mmengine - INFO - Epoch(train) [1][1000/1567] lr: 9.9609e-02 eta: 0:18:40 time: 0.0441 data_time: 0.0069 memory: 1793 loss: 1.0334 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0334 2022/11/28 00:56:14 - mmengine - INFO - Epoch(train) [1][1100/1567] lr: 9.9527e-02 eta: 0:18:33 time: 0.0457 data_time: 0.0063 memory: 1793 loss: 1.0364 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0364 2022/11/28 00:56:19 - mmengine - INFO - Epoch(train) [1][1200/1567] lr: 9.9437e-02 eta: 0:18:23 time: 0.0452 data_time: 0.0073 memory: 1793 loss: 0.9980 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.9980 2022/11/28 00:56:23 - mmengine - INFO - Epoch(train) [1][1300/1567] lr: 9.9339e-02 eta: 0:18:14 time: 0.0440 data_time: 0.0074 memory: 1793 loss: 0.8407 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.8407 2022/11/28 00:56:28 - mmengine - INFO - Epoch(train) [1][1400/1567] lr: 9.9234e-02 eta: 0:18:07 time: 0.0457 data_time: 0.0074 memory: 1793 loss: 0.9204 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9204 2022/11/28 00:56:32 - mmengine - INFO - Epoch(train) [1][1500/1567] lr: 9.9121e-02 eta: 0:18:01 time: 0.0434 data_time: 0.0064 memory: 1793 loss: 0.8501 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8501 2022/11/28 00:56:35 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 00:56:35 - mmengine - INFO - Epoch(train) [1][1567/1567] lr: 9.9040e-02 eta: 0:17:56 time: 0.0435 data_time: 0.0061 memory: 1793 loss: 0.8998 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.8998 2022/11/28 00:56:35 - mmengine - INFO - Saving checkpoint at 1 epochs 2022/11/28 00:56:39 - mmengine - INFO - Epoch(val) [1][100/129] eta: 0:00:01 time: 0.0344 data_time: 0.0211 memory: 364 2022/11/28 00:56:41 - mmengine - INFO - Epoch(val) [1][129/129] acc/top1: 0.5858 acc/top5: 0.8993 acc/mean1: 0.5859 2022/11/28 00:56:41 - mmengine - INFO - The best checkpoint with 0.5858 acc/top1 at 1 epoch is saved to best_acc/top1_epoch_1.pth. 2022/11/28 00:56:46 - mmengine - INFO - Epoch(train) [2][100/1567] lr: 9.8914e-02 eta: 0:17:51 time: 0.0434 data_time: 0.0064 memory: 1793 loss: 0.6833 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.6833 2022/11/28 00:56:50 - mmengine - INFO - Epoch(train) [2][200/1567] lr: 9.8781e-02 eta: 0:17:44 time: 0.0436 data_time: 0.0068 memory: 1793 loss: 0.9037 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9037 2022/11/28 00:56:54 - mmengine - INFO - Epoch(train) [2][300/1567] lr: 9.8639e-02 eta: 0:17:37 time: 0.0436 data_time: 0.0070 memory: 1793 loss: 0.8276 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.8276 2022/11/28 00:56:59 - mmengine - INFO - Epoch(train) [2][400/1567] lr: 9.8491e-02 eta: 0:17:32 time: 0.0475 data_time: 0.0064 memory: 1793 loss: 0.8508 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.8508 2022/11/28 00:57:00 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 00:57:03 - mmengine - INFO - Epoch(train) [2][500/1567] lr: 9.8334e-02 eta: 0:17:26 time: 0.0439 data_time: 0.0074 memory: 1793 loss: 0.7345 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.7345 2022/11/28 00:57:08 - mmengine - INFO - Epoch(train) [2][600/1567] lr: 9.8170e-02 eta: 0:17:20 time: 0.0445 data_time: 0.0071 memory: 1793 loss: 0.7839 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.7839 2022/11/28 00:57:12 - mmengine - INFO - Epoch(train) [2][700/1567] lr: 9.7998e-02 eta: 0:17:14 time: 0.0442 data_time: 0.0073 memory: 1793 loss: 0.8132 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8132 2022/11/28 00:57:17 - mmengine - INFO - Epoch(train) [2][800/1567] lr: 9.7819e-02 eta: 0:17:09 time: 0.0432 data_time: 0.0064 memory: 1793 loss: 0.5738 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5738 2022/11/28 00:57:21 - mmengine - INFO - Epoch(train) [2][900/1567] lr: 9.7632e-02 eta: 0:17:02 time: 0.0432 data_time: 0.0064 memory: 1793 loss: 0.6544 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.6544 2022/11/28 00:57:25 - mmengine - INFO - Epoch(train) [2][1000/1567] lr: 9.7438e-02 eta: 0:16:56 time: 0.0431 data_time: 0.0063 memory: 1793 loss: 0.6074 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.6074 2022/11/28 00:57:30 - mmengine - INFO - Epoch(train) [2][1100/1567] lr: 9.7236e-02 eta: 0:16:50 time: 0.0436 data_time: 0.0064 memory: 1793 loss: 0.6311 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.6311 2022/11/28 00:57:34 - mmengine - INFO - Epoch(train) [2][1200/1567] lr: 9.7027e-02 eta: 0:16:45 time: 0.0433 data_time: 0.0065 memory: 1793 loss: 0.6208 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.6208 2022/11/28 00:57:38 - mmengine - INFO - Epoch(train) [2][1300/1567] lr: 9.6810e-02 eta: 0:16:39 time: 0.0430 data_time: 0.0064 memory: 1793 loss: 0.6082 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6082 2022/11/28 00:57:43 - mmengine - INFO - Epoch(train) [2][1400/1567] lr: 9.6587e-02 eta: 0:16:33 time: 0.0435 data_time: 0.0064 memory: 1793 loss: 0.5755 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5755 2022/11/28 00:57:44 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 00:57:47 - mmengine - INFO - Epoch(train) [2][1500/1567] lr: 9.6355e-02 eta: 0:16:29 time: 0.0452 data_time: 0.0075 memory: 1793 loss: 0.6992 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.6992 2022/11/28 00:57:50 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 00:57:50 - mmengine - INFO - Epoch(train) [2][1567/1567] lr: 9.6196e-02 eta: 0:16:25 time: 0.0436 data_time: 0.0074 memory: 1793 loss: 0.6673 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.6673 2022/11/28 00:57:50 - mmengine - INFO - Saving checkpoint at 2 epochs 2022/11/28 00:57:54 - mmengine - INFO - Epoch(val) [2][100/129] eta: 0:00:01 time: 0.0349 data_time: 0.0212 memory: 364 2022/11/28 00:57:55 - mmengine - INFO - Epoch(val) [2][129/129] acc/top1: 0.5942 acc/top5: 0.9065 acc/mean1: 0.5944 2022/11/28 00:57:55 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_1.pth is removed 2022/11/28 00:57:56 - mmengine - INFO - The best checkpoint with 0.5942 acc/top1 at 2 epoch is saved to best_acc/top1_epoch_2.pth. 2022/11/28 00:58:00 - mmengine - INFO - Epoch(train) [3][100/1567] lr: 9.5953e-02 eta: 0:16:22 time: 0.0433 data_time: 0.0064 memory: 1793 loss: 0.6331 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.6331 2022/11/28 00:58:05 - mmengine - INFO - Epoch(train) [3][200/1567] lr: 9.5703e-02 eta: 0:16:17 time: 0.0432 data_time: 0.0064 memory: 1793 loss: 0.5743 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5743 2022/11/28 00:58:09 - mmengine - INFO - Epoch(train) [3][300/1567] lr: 9.5445e-02 eta: 0:16:11 time: 0.0433 data_time: 0.0064 memory: 1793 loss: 0.6345 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.6345 2022/11/28 00:58:14 - mmengine - INFO - Epoch(train) [3][400/1567] lr: 9.5180e-02 eta: 0:16:07 time: 0.0446 data_time: 0.0064 memory: 1793 loss: 0.4747 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4747 2022/11/28 00:58:18 - mmengine - INFO - Epoch(train) [3][500/1567] lr: 9.4908e-02 eta: 0:16:01 time: 0.0432 data_time: 0.0064 memory: 1793 loss: 0.6175 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.6175 2022/11/28 00:58:22 - mmengine - INFO - Epoch(train) [3][600/1567] lr: 9.4629e-02 eta: 0:15:56 time: 0.0438 data_time: 0.0064 memory: 1793 loss: 0.5978 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5978 2022/11/28 00:58:27 - mmengine - INFO - Epoch(train) [3][700/1567] lr: 9.4343e-02 eta: 0:15:51 time: 0.0443 data_time: 0.0069 memory: 1793 loss: 0.5818 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.5818 2022/11/28 00:58:31 - mmengine - INFO - Epoch(train) [3][800/1567] lr: 9.4050e-02 eta: 0:15:46 time: 0.0432 data_time: 0.0065 memory: 1793 loss: 0.6220 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.6220 2022/11/28 00:58:34 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 00:58:35 - mmengine - INFO - Epoch(train) [3][900/1567] lr: 9.3750e-02 eta: 0:15:41 time: 0.0430 data_time: 0.0064 memory: 1793 loss: 0.6332 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.6332 2022/11/28 00:58:40 - mmengine - INFO - Epoch(train) [3][1000/1567] lr: 9.3444e-02 eta: 0:15:36 time: 0.0433 data_time: 0.0064 memory: 1793 loss: 0.5269 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5269 2022/11/28 00:58:44 - mmengine - INFO - Epoch(train) [3][1100/1567] lr: 9.3130e-02 eta: 0:15:31 time: 0.0458 data_time: 0.0075 memory: 1793 loss: 0.5476 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5476 2022/11/28 00:58:48 - mmengine - INFO - Epoch(train) [3][1200/1567] lr: 9.2810e-02 eta: 0:15:26 time: 0.0431 data_time: 0.0064 memory: 1793 loss: 0.6084 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.6084 2022/11/28 00:58:53 - mmengine - INFO - Epoch(train) [3][1300/1567] lr: 9.2483e-02 eta: 0:15:21 time: 0.0434 data_time: 0.0064 memory: 1793 loss: 0.5752 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5752 2022/11/28 00:58:57 - mmengine - INFO - Epoch(train) [3][1400/1567] lr: 9.2149e-02 eta: 0:15:16 time: 0.0430 data_time: 0.0065 memory: 1793 loss: 0.4545 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.4545 2022/11/28 00:59:02 - mmengine - INFO - Epoch(train) [3][1500/1567] lr: 9.1809e-02 eta: 0:15:11 time: 0.0432 data_time: 0.0064 memory: 1793 loss: 0.4662 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4662 2022/11/28 00:59:05 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 00:59:05 - mmengine - INFO - Epoch(train) [3][1567/1567] lr: 9.1577e-02 eta: 0:15:08 time: 0.0419 data_time: 0.0061 memory: 1793 loss: 0.7272 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.7272 2022/11/28 00:59:05 - mmengine - INFO - Saving checkpoint at 3 epochs 2022/11/28 00:59:09 - mmengine - INFO - Epoch(val) [3][100/129] eta: 0:00:01 time: 0.0342 data_time: 0.0208 memory: 364 2022/11/28 00:59:10 - mmengine - INFO - Epoch(val) [3][129/129] acc/top1: 0.6860 acc/top5: 0.9068 acc/mean1: 0.6858 2022/11/28 00:59:10 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_2.pth is removed 2022/11/28 00:59:10 - mmengine - INFO - The best checkpoint with 0.6860 acc/top1 at 3 epoch is saved to best_acc/top1_epoch_3.pth. 2022/11/28 00:59:15 - mmengine - INFO - Epoch(train) [4][100/1567] lr: 9.1226e-02 eta: 0:15:04 time: 0.0439 data_time: 0.0070 memory: 1793 loss: 0.4338 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4338 2022/11/28 00:59:19 - mmengine - INFO - Epoch(train) [4][200/1567] lr: 9.0868e-02 eta: 0:14:59 time: 0.0435 data_time: 0.0064 memory: 1793 loss: 0.5330 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5330 2022/11/28 00:59:24 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 00:59:24 - mmengine - INFO - Epoch(train) [4][300/1567] lr: 9.0504e-02 eta: 0:14:55 time: 0.0445 data_time: 0.0070 memory: 1793 loss: 0.4515 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.4515 2022/11/28 00:59:28 - mmengine - INFO - Epoch(train) [4][400/1567] lr: 9.0133e-02 eta: 0:14:50 time: 0.0472 data_time: 0.0071 memory: 1793 loss: 0.5898 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.5898 2022/11/28 00:59:33 - mmengine - INFO - Epoch(train) [4][500/1567] lr: 8.9756e-02 eta: 0:14:46 time: 0.0437 data_time: 0.0064 memory: 1793 loss: 0.5490 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.5490 2022/11/28 00:59:37 - mmengine - INFO - Epoch(train) [4][600/1567] lr: 8.9373e-02 eta: 0:14:41 time: 0.0439 data_time: 0.0063 memory: 1793 loss: 0.3986 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.3986 2022/11/28 00:59:41 - mmengine - INFO - Epoch(train) [4][700/1567] lr: 8.8984e-02 eta: 0:14:37 time: 0.0441 data_time: 0.0064 memory: 1793 loss: 0.4009 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.4009 2022/11/28 00:59:46 - mmengine - INFO - Epoch(train) [4][800/1567] lr: 8.8589e-02 eta: 0:14:32 time: 0.0444 data_time: 0.0066 memory: 1793 loss: 0.4927 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4927 2022/11/28 00:59:50 - mmengine - INFO - Epoch(train) [4][900/1567] lr: 8.8187e-02 eta: 0:14:27 time: 0.0438 data_time: 0.0063 memory: 1793 loss: 0.5185 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5185 2022/11/28 00:59:55 - mmengine - INFO - Epoch(train) [4][1000/1567] lr: 8.7780e-02 eta: 0:14:23 time: 0.0443 data_time: 0.0070 memory: 1793 loss: 0.5976 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.5976 2022/11/28 00:59:59 - mmengine - INFO - Epoch(train) [4][1100/1567] lr: 8.7367e-02 eta: 0:14:18 time: 0.0441 data_time: 0.0067 memory: 1793 loss: 0.5117 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5117 2022/11/28 01:00:04 - mmengine - INFO - Epoch(train) [4][1200/1567] lr: 8.6947e-02 eta: 0:14:14 time: 0.0445 data_time: 0.0076 memory: 1793 loss: 0.5478 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5478 2022/11/28 01:00:08 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 01:00:08 - mmengine - INFO - Epoch(train) [4][1300/1567] lr: 8.6522e-02 eta: 0:14:10 time: 0.0435 data_time: 0.0065 memory: 1793 loss: 0.5124 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.5124 2022/11/28 01:00:13 - mmengine - INFO - Epoch(train) [4][1400/1567] lr: 8.6092e-02 eta: 0:14:05 time: 0.0434 data_time: 0.0064 memory: 1793 loss: 0.5766 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.5766 2022/11/28 01:00:17 - mmengine - INFO - Epoch(train) [4][1500/1567] lr: 8.5655e-02 eta: 0:14:01 time: 0.0438 data_time: 0.0065 memory: 1793 loss: 0.3369 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3369 2022/11/28 01:00:20 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 01:00:20 - mmengine - INFO - Epoch(train) [4][1567/1567] lr: 8.5360e-02 eta: 0:13:58 time: 0.0427 data_time: 0.0063 memory: 1793 loss: 0.6712 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.6712 2022/11/28 01:00:20 - mmengine - INFO - Saving checkpoint at 4 epochs 2022/11/28 01:00:24 - mmengine - INFO - Epoch(val) [4][100/129] eta: 0:00:01 time: 0.0340 data_time: 0.0206 memory: 364 2022/11/28 01:00:25 - mmengine - INFO - Epoch(val) [4][129/129] acc/top1: 0.7442 acc/top5: 0.9505 acc/mean1: 0.7441 2022/11/28 01:00:25 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_3.pth is removed 2022/11/28 01:00:26 - mmengine - INFO - The best checkpoint with 0.7442 acc/top1 at 4 epoch is saved to best_acc/top1_epoch_4.pth. 2022/11/28 01:00:30 - mmengine - INFO - Epoch(train) [5][100/1567] lr: 8.4914e-02 eta: 0:13:54 time: 0.0453 data_time: 0.0065 memory: 1793 loss: 0.4361 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4361 2022/11/28 01:00:35 - mmengine - INFO - Epoch(train) [5][200/1567] lr: 8.4463e-02 eta: 0:13:49 time: 0.0435 data_time: 0.0065 memory: 1793 loss: 0.5333 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.5333 2022/11/28 01:00:39 - mmengine - INFO - Epoch(train) [5][300/1567] lr: 8.4006e-02 eta: 0:13:44 time: 0.0434 data_time: 0.0064 memory: 1793 loss: 0.4402 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4402 2022/11/28 01:00:43 - mmengine - INFO - Epoch(train) [5][400/1567] lr: 8.3544e-02 eta: 0:13:40 time: 0.0468 data_time: 0.0064 memory: 1793 loss: 0.4215 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.4215 2022/11/28 01:00:48 - mmengine - INFO - Epoch(train) [5][500/1567] lr: 8.3077e-02 eta: 0:13:35 time: 0.0435 data_time: 0.0064 memory: 1793 loss: 0.4019 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.4019 2022/11/28 01:00:52 - mmengine - INFO - Epoch(train) [5][600/1567] lr: 8.2605e-02 eta: 0:13:31 time: 0.0436 data_time: 0.0065 memory: 1793 loss: 0.4008 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.4008 2022/11/28 01:00:57 - mmengine - INFO - Epoch(train) [5][700/1567] lr: 8.2127e-02 eta: 0:13:26 time: 0.0439 data_time: 0.0065 memory: 1793 loss: 0.4746 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4746 2022/11/28 01:00:58 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 01:01:01 - mmengine - INFO - Epoch(train) [5][800/1567] lr: 8.1645e-02 eta: 0:13:21 time: 0.0469 data_time: 0.0064 memory: 1793 loss: 0.5046 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5046 2022/11/28 01:01:05 - mmengine - INFO - Epoch(train) [5][900/1567] lr: 8.1157e-02 eta: 0:13:17 time: 0.0438 data_time: 0.0066 memory: 1793 loss: 0.4159 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4159 2022/11/28 01:01:10 - mmengine - INFO - Epoch(train) [5][1000/1567] lr: 8.0665e-02 eta: 0:13:12 time: 0.0439 data_time: 0.0064 memory: 1793 loss: 0.4034 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.4034 2022/11/28 01:01:14 - mmengine - INFO - Epoch(train) [5][1100/1567] lr: 8.0167e-02 eta: 0:13:08 time: 0.0436 data_time: 0.0064 memory: 1793 loss: 0.3791 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.3791 2022/11/28 01:01:19 - mmengine - INFO - Epoch(train) [5][1200/1567] lr: 7.9665e-02 eta: 0:13:03 time: 0.0435 data_time: 0.0065 memory: 1793 loss: 0.4580 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.4580 2022/11/28 01:01:23 - mmengine - INFO - Epoch(train) [5][1300/1567] lr: 7.9159e-02 eta: 0:12:58 time: 0.0446 data_time: 0.0075 memory: 1793 loss: 0.3734 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3734 2022/11/28 01:01:28 - mmengine - INFO - Epoch(train) [5][1400/1567] lr: 7.8647e-02 eta: 0:12:54 time: 0.0470 data_time: 0.0064 memory: 1793 loss: 0.4342 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4342 2022/11/28 01:01:32 - mmengine - INFO - Epoch(train) [5][1500/1567] lr: 7.8132e-02 eta: 0:12:50 time: 0.0435 data_time: 0.0065 memory: 1793 loss: 0.5087 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5087 2022/11/28 01:01:35 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 01:01:35 - mmengine - INFO - Epoch(train) [5][1567/1567] lr: 7.7784e-02 eta: 0:12:47 time: 0.0426 data_time: 0.0067 memory: 1793 loss: 0.5571 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.5571 2022/11/28 01:01:35 - mmengine - INFO - Saving checkpoint at 5 epochs 2022/11/28 01:01:39 - mmengine - INFO - Epoch(val) [5][100/129] eta: 0:00:01 time: 0.0341 data_time: 0.0208 memory: 364 2022/11/28 01:01:40 - mmengine - INFO - Epoch(val) [5][129/129] acc/top1: 0.7584 acc/top5: 0.9494 acc/mean1: 0.7582 2022/11/28 01:01:40 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_4.pth is removed 2022/11/28 01:01:41 - mmengine - INFO - The best checkpoint with 0.7584 acc/top1 at 5 epoch is saved to best_acc/top1_epoch_5.pth. 2022/11/28 01:01:45 - mmengine - INFO - Epoch(train) [6][100/1567] lr: 7.7261e-02 eta: 0:12:43 time: 0.0440 data_time: 0.0071 memory: 1793 loss: 0.3793 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3793 2022/11/28 01:01:48 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 01:01:50 - mmengine - INFO - Epoch(train) [6][200/1567] lr: 7.6733e-02 eta: 0:12:38 time: 0.0437 data_time: 0.0071 memory: 1793 loss: 0.4205 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4205 2022/11/28 01:01:54 - mmengine - INFO - Epoch(train) [6][300/1567] lr: 7.6202e-02 eta: 0:12:34 time: 0.0444 data_time: 0.0067 memory: 1793 loss: 0.4501 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4501 2022/11/28 01:01:59 - mmengine - INFO - Epoch(train) [6][400/1567] lr: 7.5666e-02 eta: 0:12:29 time: 0.0456 data_time: 0.0079 memory: 1793 loss: 0.4047 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4047 2022/11/28 01:02:03 - mmengine - INFO - Epoch(train) [6][500/1567] lr: 7.5126e-02 eta: 0:12:25 time: 0.0438 data_time: 0.0068 memory: 1793 loss: 0.3585 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3585 2022/11/28 01:02:07 - mmengine - INFO - Epoch(train) [6][600/1567] lr: 7.4583e-02 eta: 0:12:20 time: 0.0445 data_time: 0.0071 memory: 1793 loss: 0.3730 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3730 2022/11/28 01:02:12 - mmengine - INFO - Epoch(train) [6][700/1567] lr: 7.4035e-02 eta: 0:12:16 time: 0.0437 data_time: 0.0063 memory: 1793 loss: 0.4143 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4143 2022/11/28 01:02:16 - mmengine - INFO - Epoch(train) [6][800/1567] lr: 7.3484e-02 eta: 0:12:11 time: 0.0445 data_time: 0.0079 memory: 1793 loss: 0.3648 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3648 2022/11/28 01:02:21 - mmengine - INFO - Epoch(train) [6][900/1567] lr: 7.2929e-02 eta: 0:12:07 time: 0.0444 data_time: 0.0077 memory: 1793 loss: 0.4121 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4121 2022/11/28 01:02:25 - mmengine - INFO - Epoch(train) [6][1000/1567] lr: 7.2371e-02 eta: 0:12:02 time: 0.0452 data_time: 0.0076 memory: 1793 loss: 0.3639 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3639 2022/11/28 01:02:30 - mmengine - INFO - Epoch(train) [6][1100/1567] lr: 7.1809e-02 eta: 0:11:58 time: 0.0433 data_time: 0.0064 memory: 1793 loss: 0.3332 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3332 2022/11/28 01:02:32 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 01:02:34 - mmengine - INFO - Epoch(train) [6][1200/1567] lr: 7.1243e-02 eta: 0:11:53 time: 0.0437 data_time: 0.0071 memory: 1793 loss: 0.4054 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4054 2022/11/28 01:02:38 - mmengine - INFO - Epoch(train) [6][1300/1567] lr: 7.0674e-02 eta: 0:11:49 time: 0.0445 data_time: 0.0078 memory: 1793 loss: 0.3922 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.3922 2022/11/28 01:02:43 - mmengine - INFO - Epoch(train) [6][1400/1567] lr: 7.0102e-02 eta: 0:11:45 time: 0.0448 data_time: 0.0075 memory: 1793 loss: 0.3177 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.3177 2022/11/28 01:02:47 - mmengine - INFO - Epoch(train) [6][1500/1567] lr: 6.9527e-02 eta: 0:11:40 time: 0.0441 data_time: 0.0075 memory: 1793 loss: 0.4477 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4477 2022/11/28 01:02:50 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 01:02:50 - mmengine - INFO - Epoch(train) [6][1567/1567] lr: 6.9140e-02 eta: 0:11:37 time: 0.0429 data_time: 0.0071 memory: 1793 loss: 0.6297 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.6297 2022/11/28 01:02:50 - mmengine - INFO - Saving checkpoint at 6 epochs 2022/11/28 01:02:54 - mmengine - INFO - Epoch(val) [6][100/129] eta: 0:00:01 time: 0.0342 data_time: 0.0206 memory: 364 2022/11/28 01:02:56 - mmengine - INFO - Epoch(val) [6][129/129] acc/top1: 0.7846 acc/top5: 0.9564 acc/mean1: 0.7845 2022/11/28 01:02:56 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_5.pth is removed 2022/11/28 01:02:56 - mmengine - INFO - The best checkpoint with 0.7846 acc/top1 at 6 epoch is saved to best_acc/top1_epoch_6.pth. 2022/11/28 01:03:01 - mmengine - INFO - Epoch(train) [7][100/1567] lr: 6.8560e-02 eta: 0:11:33 time: 0.0437 data_time: 0.0068 memory: 1793 loss: 0.3527 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.3527 2022/11/28 01:03:05 - mmengine - INFO - Epoch(train) [7][200/1567] lr: 6.7976e-02 eta: 0:11:29 time: 0.0444 data_time: 0.0075 memory: 1793 loss: 0.3362 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3362 2022/11/28 01:03:10 - mmengine - INFO - Epoch(train) [7][300/1567] lr: 6.7390e-02 eta: 0:11:24 time: 0.0439 data_time: 0.0070 memory: 1793 loss: 0.3281 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3281 2022/11/28 01:03:14 - mmengine - INFO - Epoch(train) [7][400/1567] lr: 6.6802e-02 eta: 0:11:20 time: 0.0440 data_time: 0.0066 memory: 1793 loss: 0.3631 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3631 2022/11/28 01:03:19 - mmengine - INFO - Epoch(train) [7][500/1567] lr: 6.6210e-02 eta: 0:11:15 time: 0.0439 data_time: 0.0070 memory: 1793 loss: 0.3517 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3517 2022/11/28 01:03:23 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 01:03:23 - mmengine - INFO - Epoch(train) [7][600/1567] lr: 6.5616e-02 eta: 0:11:11 time: 0.0450 data_time: 0.0069 memory: 1793 loss: 0.3157 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3157 2022/11/28 01:03:27 - mmengine - INFO - Epoch(train) [7][700/1567] lr: 6.5020e-02 eta: 0:11:06 time: 0.0457 data_time: 0.0072 memory: 1793 loss: 0.2769 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2769 2022/11/28 01:03:32 - mmengine - INFO - Epoch(train) [7][800/1567] lr: 6.4421e-02 eta: 0:11:02 time: 0.0446 data_time: 0.0067 memory: 1793 loss: 0.3668 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3668 2022/11/28 01:03:36 - mmengine - INFO - Epoch(train) [7][900/1567] lr: 6.3820e-02 eta: 0:10:58 time: 0.0441 data_time: 0.0069 memory: 1793 loss: 0.3232 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3232 2022/11/28 01:03:41 - mmengine - INFO - Epoch(train) [7][1000/1567] lr: 6.3217e-02 eta: 0:10:53 time: 0.0445 data_time: 0.0067 memory: 1793 loss: 0.3365 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3365 2022/11/28 01:03:45 - mmengine - INFO - Epoch(train) [7][1100/1567] lr: 6.2612e-02 eta: 0:10:49 time: 0.0441 data_time: 0.0071 memory: 1793 loss: 0.3888 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.3888 2022/11/28 01:03:50 - mmengine - INFO - Epoch(train) [7][1200/1567] lr: 6.2005e-02 eta: 0:10:44 time: 0.0455 data_time: 0.0072 memory: 1793 loss: 0.3024 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3024 2022/11/28 01:03:54 - mmengine - INFO - Epoch(train) [7][1300/1567] lr: 6.1396e-02 eta: 0:10:40 time: 0.0440 data_time: 0.0070 memory: 1793 loss: 0.3907 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.3907 2022/11/28 01:03:59 - mmengine - INFO - Epoch(train) [7][1400/1567] lr: 6.0785e-02 eta: 0:10:35 time: 0.0445 data_time: 0.0069 memory: 1793 loss: 0.3462 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3462 2022/11/28 01:04:03 - mmengine - INFO - Epoch(train) [7][1500/1567] lr: 6.0172e-02 eta: 0:10:31 time: 0.0440 data_time: 0.0075 memory: 1793 loss: 0.3388 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3388 2022/11/28 01:04:06 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 01:04:06 - mmengine - INFO - Epoch(train) [7][1567/1567] lr: 5.9761e-02 eta: 0:10:28 time: 0.0436 data_time: 0.0071 memory: 1793 loss: 0.3975 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.3975 2022/11/28 01:04:06 - mmengine - INFO - Saving checkpoint at 7 epochs 2022/11/28 01:04:11 - mmengine - INFO - Epoch(val) [7][100/129] eta: 0:00:01 time: 0.0344 data_time: 0.0211 memory: 364 2022/11/28 01:04:12 - mmengine - INFO - Epoch(val) [7][129/129] acc/top1: 0.7720 acc/top5: 0.9558 acc/mean1: 0.7719 2022/11/28 01:04:13 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 01:04:16 - mmengine - INFO - Epoch(train) [8][100/1567] lr: 5.9145e-02 eta: 0:10:24 time: 0.0441 data_time: 0.0068 memory: 1793 loss: 0.2767 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.2767 2022/11/28 01:04:21 - mmengine - INFO - Epoch(train) [8][200/1567] lr: 5.8529e-02 eta: 0:10:19 time: 0.0437 data_time: 0.0069 memory: 1793 loss: 0.4225 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4225 2022/11/28 01:04:25 - mmengine - INFO - Epoch(train) [8][300/1567] lr: 5.7911e-02 eta: 0:10:15 time: 0.0445 data_time: 0.0070 memory: 1793 loss: 0.2884 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2884 2022/11/28 01:04:30 - mmengine - INFO - Epoch(train) [8][400/1567] lr: 5.7292e-02 eta: 0:10:11 time: 0.0447 data_time: 0.0065 memory: 1793 loss: 0.2711 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2711 2022/11/28 01:04:34 - mmengine - INFO - Epoch(train) [8][500/1567] lr: 5.6671e-02 eta: 0:10:06 time: 0.0436 data_time: 0.0069 memory: 1793 loss: 0.3388 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3388 2022/11/28 01:04:39 - mmengine - INFO - Epoch(train) [8][600/1567] lr: 5.6050e-02 eta: 0:10:02 time: 0.0446 data_time: 0.0074 memory: 1793 loss: 0.2717 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.2717 2022/11/28 01:04:43 - mmengine - INFO - Epoch(train) [8][700/1567] lr: 5.5427e-02 eta: 0:09:57 time: 0.0450 data_time: 0.0069 memory: 1793 loss: 0.3304 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.3304 2022/11/28 01:04:48 - mmengine - INFO - Epoch(train) [8][800/1567] lr: 5.4804e-02 eta: 0:09:53 time: 0.0447 data_time: 0.0079 memory: 1793 loss: 0.2789 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2789 2022/11/28 01:04:52 - mmengine - INFO - Epoch(train) [8][900/1567] lr: 5.4180e-02 eta: 0:09:48 time: 0.0487 data_time: 0.0070 memory: 1793 loss: 0.2488 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2488 2022/11/28 01:04:57 - mmengine - INFO - Epoch(train) [8][1000/1567] lr: 5.3556e-02 eta: 0:09:44 time: 0.0437 data_time: 0.0067 memory: 1793 loss: 0.2973 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2973 2022/11/28 01:04:58 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 01:05:01 - mmengine - INFO - Epoch(train) [8][1100/1567] lr: 5.2930e-02 eta: 0:09:40 time: 0.0437 data_time: 0.0068 memory: 1793 loss: 0.3202 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3202 2022/11/28 01:05:06 - mmengine - INFO - Epoch(train) [8][1200/1567] lr: 5.2305e-02 eta: 0:09:35 time: 0.0449 data_time: 0.0083 memory: 1793 loss: 0.2802 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.2802 2022/11/28 01:05:10 - mmengine - INFO - Epoch(train) [8][1300/1567] lr: 5.1679e-02 eta: 0:09:31 time: 0.0438 data_time: 0.0067 memory: 1793 loss: 0.2750 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2750 2022/11/28 01:05:15 - mmengine - INFO - Epoch(train) [8][1400/1567] lr: 5.1052e-02 eta: 0:09:26 time: 0.0443 data_time: 0.0070 memory: 1793 loss: 0.2999 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2999 2022/11/28 01:05:19 - mmengine - INFO - Epoch(train) [8][1500/1567] lr: 5.0426e-02 eta: 0:09:22 time: 0.0439 data_time: 0.0065 memory: 1793 loss: 0.2985 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2985 2022/11/28 01:05:22 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 01:05:22 - mmengine - INFO - Epoch(train) [8][1567/1567] lr: 5.0006e-02 eta: 0:09:19 time: 0.0429 data_time: 0.0065 memory: 1793 loss: 0.4211 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.4211 2022/11/28 01:05:22 - mmengine - INFO - Saving checkpoint at 8 epochs 2022/11/28 01:05:26 - mmengine - INFO - Epoch(val) [8][100/129] eta: 0:00:01 time: 0.0340 data_time: 0.0207 memory: 364 2022/11/28 01:05:27 - mmengine - INFO - Epoch(val) [8][129/129] acc/top1: 0.7860 acc/top5: 0.9602 acc/mean1: 0.7859 2022/11/28 01:05:27 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_6.pth is removed 2022/11/28 01:05:28 - mmengine - INFO - The best checkpoint with 0.7860 acc/top1 at 8 epoch is saved to best_acc/top1_epoch_8.pth. 2022/11/28 01:05:32 - mmengine - INFO - Epoch(train) [9][100/1567] lr: 4.9380e-02 eta: 0:09:14 time: 0.0441 data_time: 0.0071 memory: 1793 loss: 0.2379 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2379 2022/11/28 01:05:37 - mmengine - INFO - Epoch(train) [9][200/1567] lr: 4.8753e-02 eta: 0:09:10 time: 0.0444 data_time: 0.0073 memory: 1793 loss: 0.1891 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1891 2022/11/28 01:05:41 - mmengine - INFO - Epoch(train) [9][300/1567] lr: 4.8127e-02 eta: 0:09:05 time: 0.0438 data_time: 0.0070 memory: 1793 loss: 0.2262 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2262 2022/11/28 01:05:46 - mmengine - INFO - Epoch(train) [9][400/1567] lr: 4.7501e-02 eta: 0:09:01 time: 0.0481 data_time: 0.0082 memory: 1793 loss: 0.2246 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2246 2022/11/28 01:05:49 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 01:05:50 - mmengine - INFO - Epoch(train) [9][500/1567] lr: 4.6876e-02 eta: 0:08:57 time: 0.0435 data_time: 0.0065 memory: 1793 loss: 0.2250 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2250 2022/11/28 01:05:55 - mmengine - INFO - Epoch(train) [9][600/1567] lr: 4.6251e-02 eta: 0:08:52 time: 0.0446 data_time: 0.0077 memory: 1793 loss: 0.2201 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2201 2022/11/28 01:05:59 - mmengine - INFO - Epoch(train) [9][700/1567] lr: 4.5626e-02 eta: 0:08:48 time: 0.0444 data_time: 0.0074 memory: 1793 loss: 0.2766 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2766 2022/11/28 01:06:04 - mmengine - INFO - Epoch(train) [9][800/1567] lr: 4.5003e-02 eta: 0:08:43 time: 0.0454 data_time: 0.0083 memory: 1793 loss: 0.2560 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2560 2022/11/28 01:06:08 - mmengine - INFO - Epoch(train) [9][900/1567] lr: 4.4380e-02 eta: 0:08:39 time: 0.0446 data_time: 0.0069 memory: 1793 loss: 0.2307 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2307 2022/11/28 01:06:13 - mmengine - INFO - Epoch(train) [9][1000/1567] lr: 4.3757e-02 eta: 0:08:34 time: 0.0440 data_time: 0.0074 memory: 1793 loss: 0.1889 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1889 2022/11/28 01:06:17 - mmengine - INFO - Epoch(train) [9][1100/1567] lr: 4.3136e-02 eta: 0:08:30 time: 0.0440 data_time: 0.0065 memory: 1793 loss: 0.2118 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2118 2022/11/28 01:06:22 - mmengine - INFO - Epoch(train) [9][1200/1567] lr: 4.2516e-02 eta: 0:08:25 time: 0.0437 data_time: 0.0070 memory: 1793 loss: 0.1775 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1775 2022/11/28 01:06:26 - mmengine - INFO - Epoch(train) [9][1300/1567] lr: 4.1897e-02 eta: 0:08:21 time: 0.0475 data_time: 0.0069 memory: 1793 loss: 0.2393 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.2393 2022/11/28 01:06:31 - mmengine - INFO - Epoch(train) [9][1400/1567] lr: 4.1280e-02 eta: 0:08:17 time: 0.0448 data_time: 0.0065 memory: 1793 loss: 0.2355 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2355 2022/11/28 01:06:34 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 01:06:35 - mmengine - INFO - Epoch(train) [9][1500/1567] lr: 4.0664e-02 eta: 0:08:12 time: 0.0436 data_time: 0.0064 memory: 1793 loss: 0.1875 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1875 2022/11/28 01:06:38 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 01:06:38 - mmengine - INFO - Epoch(train) [9][1567/1567] lr: 4.0252e-02 eta: 0:08:09 time: 0.0435 data_time: 0.0070 memory: 1793 loss: 0.3807 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.3807 2022/11/28 01:06:38 - mmengine - INFO - Saving checkpoint at 9 epochs 2022/11/28 01:06:42 - mmengine - INFO - Epoch(val) [9][100/129] eta: 0:00:01 time: 0.0339 data_time: 0.0205 memory: 364 2022/11/28 01:06:43 - mmengine - INFO - Epoch(val) [9][129/129] acc/top1: 0.8191 acc/top5: 0.9663 acc/mean1: 0.8191 2022/11/28 01:06:43 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_8.pth is removed 2022/11/28 01:06:44 - mmengine - INFO - The best checkpoint with 0.8191 acc/top1 at 9 epoch is saved to best_acc/top1_epoch_9.pth. 2022/11/28 01:06:48 - mmengine - INFO - Epoch(train) [10][100/1567] lr: 3.9638e-02 eta: 0:08:05 time: 0.0441 data_time: 0.0073 memory: 1793 loss: 0.1659 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1659 2022/11/28 01:06:53 - mmengine - INFO - Epoch(train) [10][200/1567] lr: 3.9026e-02 eta: 0:08:00 time: 0.0446 data_time: 0.0072 memory: 1793 loss: 0.2039 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2039 2022/11/28 01:06:57 - mmengine - INFO - Epoch(train) [10][300/1567] lr: 3.8415e-02 eta: 0:07:56 time: 0.0445 data_time: 0.0071 memory: 1793 loss: 0.1753 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1753 2022/11/28 01:07:02 - mmengine - INFO - Epoch(train) [10][400/1567] lr: 3.7807e-02 eta: 0:07:52 time: 0.0447 data_time: 0.0080 memory: 1793 loss: 0.2079 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2079 2022/11/28 01:07:06 - mmengine - INFO - Epoch(train) [10][500/1567] lr: 3.7200e-02 eta: 0:07:47 time: 0.0454 data_time: 0.0077 memory: 1793 loss: 0.1606 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1606 2022/11/28 01:07:11 - mmengine - INFO - Epoch(train) [10][600/1567] lr: 3.6596e-02 eta: 0:07:43 time: 0.0443 data_time: 0.0065 memory: 1793 loss: 0.2372 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2372 2022/11/28 01:07:15 - mmengine - INFO - Epoch(train) [10][700/1567] lr: 3.5993e-02 eta: 0:07:38 time: 0.0442 data_time: 0.0071 memory: 1793 loss: 0.1520 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1520 2022/11/28 01:07:20 - mmengine - INFO - Epoch(train) [10][800/1567] lr: 3.5393e-02 eta: 0:07:34 time: 0.0437 data_time: 0.0067 memory: 1793 loss: 0.1737 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1737 2022/11/28 01:07:24 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 01:07:24 - mmengine - INFO - Epoch(train) [10][900/1567] lr: 3.4795e-02 eta: 0:07:29 time: 0.0446 data_time: 0.0069 memory: 1793 loss: 0.1847 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1847 2022/11/28 01:07:29 - mmengine - INFO - Epoch(train) [10][1000/1567] lr: 3.4199e-02 eta: 0:07:25 time: 0.0461 data_time: 0.0079 memory: 1793 loss: 0.1974 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1974 2022/11/28 01:07:33 - mmengine - INFO - Epoch(train) [10][1100/1567] lr: 3.3606e-02 eta: 0:07:20 time: 0.0444 data_time: 0.0072 memory: 1793 loss: 0.2005 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2005 2022/11/28 01:07:38 - mmengine - INFO - Epoch(train) [10][1200/1567] lr: 3.3015e-02 eta: 0:07:16 time: 0.0447 data_time: 0.0073 memory: 1793 loss: 0.1951 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1951 2022/11/28 01:07:42 - mmengine - INFO - Epoch(train) [10][1300/1567] lr: 3.2428e-02 eta: 0:07:11 time: 0.0439 data_time: 0.0070 memory: 1793 loss: 0.2155 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2155 2022/11/28 01:07:47 - mmengine - INFO - Epoch(train) [10][1400/1567] lr: 3.1842e-02 eta: 0:07:07 time: 0.0475 data_time: 0.0074 memory: 1793 loss: 0.1720 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1720 2022/11/28 01:07:51 - mmengine - INFO - Epoch(train) [10][1500/1567] lr: 3.1260e-02 eta: 0:07:02 time: 0.0440 data_time: 0.0070 memory: 1793 loss: 0.1605 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1605 2022/11/28 01:07:54 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 01:07:54 - mmengine - INFO - Epoch(train) [10][1567/1567] lr: 3.0872e-02 eta: 0:06:59 time: 0.0429 data_time: 0.0069 memory: 1793 loss: 0.3535 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.3535 2022/11/28 01:07:54 - mmengine - INFO - Saving checkpoint at 10 epochs 2022/11/28 01:07:58 - mmengine - INFO - Epoch(val) [10][100/129] eta: 0:00:01 time: 0.0339 data_time: 0.0204 memory: 364 2022/11/28 01:07:59 - mmengine - INFO - Epoch(val) [10][129/129] acc/top1: 0.8489 acc/top5: 0.9694 acc/mean1: 0.8487 2022/11/28 01:07:59 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_9.pth is removed 2022/11/28 01:08:00 - mmengine - INFO - The best checkpoint with 0.8489 acc/top1 at 10 epoch is saved to best_acc/top1_epoch_10.pth. 2022/11/28 01:08:04 - mmengine - INFO - Epoch(train) [11][100/1567] lr: 3.0294e-02 eta: 0:06:55 time: 0.0441 data_time: 0.0074 memory: 1793 loss: 0.1204 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1204 2022/11/28 01:08:09 - mmengine - INFO - Epoch(train) [11][200/1567] lr: 2.9720e-02 eta: 0:06:51 time: 0.0449 data_time: 0.0075 memory: 1793 loss: 0.1399 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1399 2022/11/28 01:08:13 - mmengine - INFO - Epoch(train) [11][300/1567] lr: 2.9149e-02 eta: 0:06:46 time: 0.0472 data_time: 0.0074 memory: 1793 loss: 0.1370 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1370 2022/11/28 01:08:15 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 01:08:18 - mmengine - INFO - Epoch(train) [11][400/1567] lr: 2.8581e-02 eta: 0:06:42 time: 0.0450 data_time: 0.0076 memory: 1793 loss: 0.1158 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1158 2022/11/28 01:08:22 - mmengine - INFO - Epoch(train) [11][500/1567] lr: 2.8017e-02 eta: 0:06:37 time: 0.0455 data_time: 0.0072 memory: 1793 loss: 0.1411 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1411 2022/11/28 01:08:27 - mmengine - INFO - Epoch(train) [11][600/1567] lr: 2.7456e-02 eta: 0:06:33 time: 0.0443 data_time: 0.0070 memory: 1793 loss: 0.1256 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1256 2022/11/28 01:08:31 - mmengine - INFO - Epoch(train) [11][700/1567] lr: 2.6898e-02 eta: 0:06:28 time: 0.0444 data_time: 0.0074 memory: 1793 loss: 0.1341 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1341 2022/11/28 01:08:36 - mmengine - INFO - Epoch(train) [11][800/1567] lr: 2.6345e-02 eta: 0:06:24 time: 0.0445 data_time: 0.0076 memory: 1793 loss: 0.1336 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1336 2022/11/28 01:08:40 - mmengine - INFO - Epoch(train) [11][900/1567] lr: 2.5794e-02 eta: 0:06:20 time: 0.0452 data_time: 0.0078 memory: 1793 loss: 0.1261 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1261 2022/11/28 01:08:45 - mmengine - INFO - Epoch(train) [11][1000/1567] lr: 2.5248e-02 eta: 0:06:15 time: 0.0450 data_time: 0.0078 memory: 1793 loss: 0.1153 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1153 2022/11/28 01:08:49 - mmengine - INFO - Epoch(train) [11][1100/1567] lr: 2.4706e-02 eta: 0:06:11 time: 0.0451 data_time: 0.0079 memory: 1793 loss: 0.1291 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1291 2022/11/28 01:08:54 - mmengine - INFO - Epoch(train) [11][1200/1567] lr: 2.4167e-02 eta: 0:06:06 time: 0.0446 data_time: 0.0072 memory: 1793 loss: 0.0752 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0752 2022/11/28 01:08:58 - mmengine - INFO - Epoch(train) [11][1300/1567] lr: 2.3633e-02 eta: 0:06:02 time: 0.0457 data_time: 0.0075 memory: 1793 loss: 0.1140 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1140 2022/11/28 01:09:00 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 01:09:03 - mmengine - INFO - Epoch(train) [11][1400/1567] lr: 2.3103e-02 eta: 0:05:57 time: 0.0446 data_time: 0.0073 memory: 1793 loss: 0.1010 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1010 2022/11/28 01:09:07 - mmengine - INFO - Epoch(train) [11][1500/1567] lr: 2.2577e-02 eta: 0:05:53 time: 0.0454 data_time: 0.0070 memory: 1793 loss: 0.1147 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.1147 2022/11/28 01:09:10 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 01:09:10 - mmengine - INFO - Epoch(train) [11][1567/1567] lr: 2.2227e-02 eta: 0:05:50 time: 0.0431 data_time: 0.0073 memory: 1793 loss: 0.2146 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.2146 2022/11/28 01:09:10 - mmengine - INFO - Saving checkpoint at 11 epochs 2022/11/28 01:09:14 - mmengine - INFO - Epoch(val) [11][100/129] eta: 0:00:01 time: 0.0339 data_time: 0.0206 memory: 364 2022/11/28 01:09:15 - mmengine - INFO - Epoch(val) [11][129/129] acc/top1: 0.8435 acc/top5: 0.9729 acc/mean1: 0.8434 2022/11/28 01:09:20 - mmengine - INFO - Epoch(train) [12][100/1567] lr: 2.1708e-02 eta: 0:05:45 time: 0.0460 data_time: 0.0069 memory: 1793 loss: 0.0692 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0692 2022/11/28 01:09:25 - mmengine - INFO - Epoch(train) [12][200/1567] lr: 2.1194e-02 eta: 0:05:41 time: 0.0466 data_time: 0.0070 memory: 1793 loss: 0.0971 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0971 2022/11/28 01:09:29 - mmengine - INFO - Epoch(train) [12][300/1567] lr: 2.0684e-02 eta: 0:05:36 time: 0.0448 data_time: 0.0075 memory: 1793 loss: 0.0688 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0688 2022/11/28 01:09:34 - mmengine - INFO - Epoch(train) [12][400/1567] lr: 2.0179e-02 eta: 0:05:32 time: 0.0447 data_time: 0.0069 memory: 1793 loss: 0.0763 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0763 2022/11/28 01:09:38 - mmengine - INFO - Epoch(train) [12][500/1567] lr: 1.9678e-02 eta: 0:05:28 time: 0.0447 data_time: 0.0069 memory: 1793 loss: 0.0734 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0734 2022/11/28 01:09:43 - mmengine - INFO - Epoch(train) [12][600/1567] lr: 1.9182e-02 eta: 0:05:23 time: 0.0462 data_time: 0.0088 memory: 1793 loss: 0.0633 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0633 2022/11/28 01:09:47 - mmengine - INFO - Epoch(train) [12][700/1567] lr: 1.8691e-02 eta: 0:05:19 time: 0.0442 data_time: 0.0069 memory: 1793 loss: 0.0636 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0636 2022/11/28 01:09:50 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 01:09:52 - mmengine - INFO - Epoch(train) [12][800/1567] lr: 1.8205e-02 eta: 0:05:14 time: 0.0454 data_time: 0.0073 memory: 1793 loss: 0.0629 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0629 2022/11/28 01:09:56 - mmengine - INFO - Epoch(train) [12][900/1567] lr: 1.7724e-02 eta: 0:05:10 time: 0.0442 data_time: 0.0068 memory: 1793 loss: 0.0643 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0643 2022/11/28 01:10:01 - mmengine - INFO - Epoch(train) [12][1000/1567] lr: 1.7248e-02 eta: 0:05:05 time: 0.0448 data_time: 0.0066 memory: 1793 loss: 0.0686 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0686 2022/11/28 01:10:05 - mmengine - INFO - Epoch(train) [12][1100/1567] lr: 1.6778e-02 eta: 0:05:01 time: 0.0451 data_time: 0.0075 memory: 1793 loss: 0.0677 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0677 2022/11/28 01:10:10 - mmengine - INFO - Epoch(train) [12][1200/1567] lr: 1.6312e-02 eta: 0:04:56 time: 0.0451 data_time: 0.0076 memory: 1793 loss: 0.0421 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0421 2022/11/28 01:10:14 - mmengine - INFO - Epoch(train) [12][1300/1567] lr: 1.5852e-02 eta: 0:04:52 time: 0.0464 data_time: 0.0071 memory: 1793 loss: 0.0360 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0360 2022/11/28 01:10:19 - mmengine - INFO - Epoch(train) [12][1400/1567] lr: 1.5397e-02 eta: 0:04:47 time: 0.0446 data_time: 0.0070 memory: 1793 loss: 0.0338 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0338 2022/11/28 01:10:23 - mmengine - INFO - Epoch(train) [12][1500/1567] lr: 1.4947e-02 eta: 0:04:43 time: 0.0444 data_time: 0.0070 memory: 1793 loss: 0.0552 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0552 2022/11/28 01:10:26 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 01:10:26 - mmengine - INFO - Epoch(train) [12][1567/1567] lr: 1.4649e-02 eta: 0:04:40 time: 0.0441 data_time: 0.0069 memory: 1793 loss: 0.2008 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.2008 2022/11/28 01:10:26 - mmengine - INFO - Saving checkpoint at 12 epochs 2022/11/28 01:10:30 - mmengine - INFO - Epoch(val) [12][100/129] eta: 0:00:01 time: 0.0336 data_time: 0.0203 memory: 364 2022/11/28 01:10:31 - mmengine - INFO - Epoch(val) [12][129/129] acc/top1: 0.8570 acc/top5: 0.9737 acc/mean1: 0.8569 2022/11/28 01:10:31 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_10.pth is removed 2022/11/28 01:10:31 - mmengine - INFO - The best checkpoint with 0.8570 acc/top1 at 12 epoch is saved to best_acc/top1_epoch_12.pth. 2022/11/28 01:10:36 - mmengine - INFO - Epoch(train) [13][100/1567] lr: 1.4209e-02 eta: 0:04:35 time: 0.0445 data_time: 0.0067 memory: 1793 loss: 0.0387 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0387 2022/11/28 01:10:40 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 01:10:41 - mmengine - INFO - Epoch(train) [13][200/1567] lr: 1.3774e-02 eta: 0:04:31 time: 0.0439 data_time: 0.0070 memory: 1793 loss: 0.0391 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0391 2022/11/28 01:10:45 - mmengine - INFO - Epoch(train) [13][300/1567] lr: 1.3345e-02 eta: 0:04:27 time: 0.0443 data_time: 0.0072 memory: 1793 loss: 0.0518 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0518 2022/11/28 01:10:50 - mmengine - INFO - Epoch(train) [13][400/1567] lr: 1.2922e-02 eta: 0:04:22 time: 0.0439 data_time: 0.0069 memory: 1793 loss: 0.0346 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0346 2022/11/28 01:10:54 - mmengine - INFO - Epoch(train) [13][500/1567] lr: 1.2505e-02 eta: 0:04:18 time: 0.0441 data_time: 0.0069 memory: 1793 loss: 0.0253 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0253 2022/11/28 01:10:59 - mmengine - INFO - Epoch(train) [13][600/1567] lr: 1.2093e-02 eta: 0:04:13 time: 0.0447 data_time: 0.0074 memory: 1793 loss: 0.0290 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0290 2022/11/28 01:11:03 - mmengine - INFO - Epoch(train) [13][700/1567] lr: 1.1687e-02 eta: 0:04:09 time: 0.0473 data_time: 0.0072 memory: 1793 loss: 0.0249 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0249 2022/11/28 01:11:08 - mmengine - INFO - Epoch(train) [13][800/1567] lr: 1.1288e-02 eta: 0:04:04 time: 0.0449 data_time: 0.0069 memory: 1793 loss: 0.0231 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0231 2022/11/28 01:11:12 - mmengine - INFO - Epoch(train) [13][900/1567] lr: 1.0894e-02 eta: 0:04:00 time: 0.0448 data_time: 0.0070 memory: 1793 loss: 0.0252 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0252 2022/11/28 01:11:17 - mmengine - INFO - Epoch(train) [13][1000/1567] lr: 1.0507e-02 eta: 0:03:55 time: 0.0447 data_time: 0.0073 memory: 1793 loss: 0.0224 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0224 2022/11/28 01:11:21 - mmengine - INFO - Epoch(train) [13][1100/1567] lr: 1.0126e-02 eta: 0:03:51 time: 0.0459 data_time: 0.0073 memory: 1793 loss: 0.0299 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0299 2022/11/28 01:11:26 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 01:11:26 - mmengine - INFO - Epoch(train) [13][1200/1567] lr: 9.7512e-03 eta: 0:03:46 time: 0.0467 data_time: 0.0068 memory: 1793 loss: 0.0213 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0213 2022/11/28 01:11:30 - mmengine - INFO - Epoch(train) [13][1300/1567] lr: 9.3826e-03 eta: 0:03:42 time: 0.0452 data_time: 0.0071 memory: 1793 loss: 0.0258 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0258 2022/11/28 01:11:35 - mmengine - INFO - Epoch(train) [13][1400/1567] lr: 9.0204e-03 eta: 0:03:37 time: 0.0449 data_time: 0.0078 memory: 1793 loss: 0.0168 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0168 2022/11/28 01:11:40 - mmengine - INFO - Epoch(train) [13][1500/1567] lr: 8.6647e-03 eta: 0:03:33 time: 0.0446 data_time: 0.0075 memory: 1793 loss: 0.0183 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0183 2022/11/28 01:11:43 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 01:11:43 - mmengine - INFO - Epoch(train) [13][1567/1567] lr: 8.4300e-03 eta: 0:03:30 time: 0.0432 data_time: 0.0070 memory: 1793 loss: 0.1849 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.1849 2022/11/28 01:11:43 - mmengine - INFO - Saving checkpoint at 13 epochs 2022/11/28 01:11:47 - mmengine - INFO - Epoch(val) [13][100/129] eta: 0:00:01 time: 0.0346 data_time: 0.0210 memory: 364 2022/11/28 01:11:48 - mmengine - INFO - Epoch(val) [13][129/129] acc/top1: 0.8652 acc/top5: 0.9738 acc/mean1: 0.8651 2022/11/28 01:11:48 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_12.pth is removed 2022/11/28 01:11:48 - mmengine - INFO - The best checkpoint with 0.8652 acc/top1 at 13 epoch is saved to best_acc/top1_epoch_13.pth. 2022/11/28 01:11:53 - mmengine - INFO - Epoch(train) [14][100/1567] lr: 8.0851e-03 eta: 0:03:26 time: 0.0450 data_time: 0.0071 memory: 1793 loss: 0.0187 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0187 2022/11/28 01:11:58 - mmengine - INFO - Epoch(train) [14][200/1567] lr: 7.7469e-03 eta: 0:03:21 time: 0.0476 data_time: 0.0077 memory: 1793 loss: 0.0153 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0153 2022/11/28 01:12:02 - mmengine - INFO - Epoch(train) [14][300/1567] lr: 7.4152e-03 eta: 0:03:17 time: 0.0466 data_time: 0.0079 memory: 1793 loss: 0.0140 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0140 2022/11/28 01:12:07 - mmengine - INFO - Epoch(train) [14][400/1567] lr: 7.0902e-03 eta: 0:03:12 time: 0.0442 data_time: 0.0068 memory: 1793 loss: 0.0168 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0168 2022/11/28 01:12:11 - mmengine - INFO - Epoch(train) [14][500/1567] lr: 6.7720e-03 eta: 0:03:08 time: 0.0440 data_time: 0.0069 memory: 1793 loss: 0.0135 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0135 2022/11/28 01:12:16 - mmengine - INFO - Epoch(train) [14][600/1567] lr: 6.4606e-03 eta: 0:03:03 time: 0.0441 data_time: 0.0066 memory: 1793 loss: 0.0137 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0137 2022/11/28 01:12:17 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 01:12:20 - mmengine - INFO - Epoch(train) [14][700/1567] lr: 6.1560e-03 eta: 0:02:59 time: 0.0445 data_time: 0.0065 memory: 1793 loss: 0.0107 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0107 2022/11/28 01:12:25 - mmengine - INFO - Epoch(train) [14][800/1567] lr: 5.8582e-03 eta: 0:02:54 time: 0.0474 data_time: 0.0075 memory: 1793 loss: 0.0166 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0166 2022/11/28 01:12:29 - mmengine - INFO - Epoch(train) [14][900/1567] lr: 5.5675e-03 eta: 0:02:50 time: 0.0444 data_time: 0.0070 memory: 1793 loss: 0.0093 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0093 2022/11/28 01:12:34 - mmengine - INFO - Epoch(train) [14][1000/1567] lr: 5.2836e-03 eta: 0:02:45 time: 0.0448 data_time: 0.0078 memory: 1793 loss: 0.0159 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0159 2022/11/28 01:12:39 - mmengine - INFO - Epoch(train) [14][1100/1567] lr: 5.0068e-03 eta: 0:02:41 time: 0.0440 data_time: 0.0065 memory: 1793 loss: 0.0169 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0169 2022/11/28 01:12:43 - mmengine - INFO - Epoch(train) [14][1200/1567] lr: 4.7371e-03 eta: 0:02:36 time: 0.0458 data_time: 0.0086 memory: 1793 loss: 0.0152 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0152 2022/11/28 01:12:48 - mmengine - INFO - Epoch(train) [14][1300/1567] lr: 4.4745e-03 eta: 0:02:32 time: 0.0448 data_time: 0.0070 memory: 1793 loss: 0.0115 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0115 2022/11/28 01:12:52 - mmengine - INFO - Epoch(train) [14][1400/1567] lr: 4.2190e-03 eta: 0:02:27 time: 0.0449 data_time: 0.0070 memory: 1793 loss: 0.0099 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0099 2022/11/28 01:12:56 - mmengine - INFO - Epoch(train) [14][1500/1567] lr: 3.9707e-03 eta: 0:02:23 time: 0.0444 data_time: 0.0067 memory: 1793 loss: 0.0110 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0110 2022/11/28 01:13:00 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 01:13:00 - mmengine - INFO - Epoch(train) [14][1567/1567] lr: 3.8084e-03 eta: 0:02:20 time: 0.0447 data_time: 0.0064 memory: 1793 loss: 0.1887 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.1887 2022/11/28 01:13:00 - mmengine - INFO - Saving checkpoint at 14 epochs 2022/11/28 01:13:04 - mmengine - INFO - Epoch(val) [14][100/129] eta: 0:00:01 time: 0.0342 data_time: 0.0208 memory: 364 2022/11/28 01:13:05 - mmengine - INFO - Epoch(val) [14][129/129] acc/top1: 0.8722 acc/top5: 0.9766 acc/mean1: 0.8721 2022/11/28 01:13:05 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_13.pth is removed 2022/11/28 01:13:05 - mmengine - INFO - The best checkpoint with 0.8722 acc/top1 at 14 epoch is saved to best_acc/top1_epoch_14.pth. 2022/11/28 01:13:08 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 01:13:10 - mmengine - INFO - Epoch(train) [15][100/1567] lr: 3.5722e-03 eta: 0:02:16 time: 0.0459 data_time: 0.0073 memory: 1793 loss: 0.0180 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0180 2022/11/28 01:13:14 - mmengine - INFO - Epoch(train) [15][200/1567] lr: 3.3433e-03 eta: 0:02:11 time: 0.0455 data_time: 0.0074 memory: 1793 loss: 0.0144 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0144 2022/11/28 01:13:19 - mmengine - INFO - Epoch(train) [15][300/1567] lr: 3.1217e-03 eta: 0:02:07 time: 0.0451 data_time: 0.0076 memory: 1793 loss: 0.0125 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0125 2022/11/28 01:13:24 - mmengine - INFO - Epoch(train) [15][400/1567] lr: 2.9075e-03 eta: 0:02:02 time: 0.0446 data_time: 0.0071 memory: 1793 loss: 0.0088 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0088 2022/11/28 01:13:28 - mmengine - INFO - Epoch(train) [15][500/1567] lr: 2.7007e-03 eta: 0:01:58 time: 0.0444 data_time: 0.0070 memory: 1793 loss: 0.0106 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0106 2022/11/28 01:13:33 - mmengine - INFO - Epoch(train) [15][600/1567] lr: 2.5013e-03 eta: 0:01:53 time: 0.0450 data_time: 0.0071 memory: 1793 loss: 0.0135 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0135 2022/11/28 01:13:37 - mmengine - INFO - Epoch(train) [15][700/1567] lr: 2.3093e-03 eta: 0:01:49 time: 0.0458 data_time: 0.0067 memory: 1793 loss: 0.0127 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0127 2022/11/28 01:13:42 - mmengine - INFO - Epoch(train) [15][800/1567] lr: 2.1249e-03 eta: 0:01:44 time: 0.0446 data_time: 0.0065 memory: 1793 loss: 0.0143 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0143 2022/11/28 01:13:46 - mmengine - INFO - Epoch(train) [15][900/1567] lr: 1.9479e-03 eta: 0:01:40 time: 0.0450 data_time: 0.0066 memory: 1793 loss: 0.0107 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0107 2022/11/28 01:13:51 - mmengine - INFO - Epoch(train) [15][1000/1567] lr: 1.7785e-03 eta: 0:01:35 time: 0.0450 data_time: 0.0075 memory: 1793 loss: 0.0093 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0093 2022/11/28 01:13:54 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 01:13:55 - mmengine - INFO - Epoch(train) [15][1100/1567] lr: 1.6167e-03 eta: 0:01:31 time: 0.0451 data_time: 0.0071 memory: 1793 loss: 0.0118 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0118 2022/11/28 01:14:00 - mmengine - INFO - Epoch(train) [15][1200/1567] lr: 1.4625e-03 eta: 0:01:26 time: 0.0445 data_time: 0.0069 memory: 1793 loss: 0.0145 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0145 2022/11/28 01:14:04 - mmengine - INFO - Epoch(train) [15][1300/1567] lr: 1.3159e-03 eta: 0:01:22 time: 0.0449 data_time: 0.0066 memory: 1793 loss: 0.0074 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0074 2022/11/28 01:14:09 - mmengine - INFO - Epoch(train) [15][1400/1567] lr: 1.1769e-03 eta: 0:01:17 time: 0.0451 data_time: 0.0071 memory: 1793 loss: 0.0101 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0101 2022/11/28 01:14:13 - mmengine - INFO - Epoch(train) [15][1500/1567] lr: 1.0456e-03 eta: 0:01:13 time: 0.0472 data_time: 0.0071 memory: 1793 loss: 0.0116 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0116 2022/11/28 01:14:16 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 01:14:16 - mmengine - INFO - Epoch(train) [15][1567/1567] lr: 9.6196e-04 eta: 0:01:10 time: 0.0430 data_time: 0.0065 memory: 1793 loss: 0.1362 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1362 2022/11/28 01:14:16 - mmengine - INFO - Saving checkpoint at 15 epochs 2022/11/28 01:14:20 - mmengine - INFO - Epoch(val) [15][100/129] eta: 0:00:01 time: 0.0338 data_time: 0.0204 memory: 364 2022/11/28 01:14:22 - mmengine - INFO - Epoch(val) [15][129/129] acc/top1: 0.8757 acc/top5: 0.9774 acc/mean1: 0.8756 2022/11/28 01:14:22 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_14.pth is removed 2022/11/28 01:14:22 - mmengine - INFO - The best checkpoint with 0.8757 acc/top1 at 15 epoch is saved to best_acc/top1_epoch_15.pth. 2022/11/28 01:14:27 - mmengine - INFO - Epoch(train) [16][100/1567] lr: 8.4351e-04 eta: 0:01:05 time: 0.0446 data_time: 0.0073 memory: 1793 loss: 0.0113 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0113 2022/11/28 01:14:31 - mmengine - INFO - Epoch(train) [16][200/1567] lr: 7.3277e-04 eta: 0:01:01 time: 0.0455 data_time: 0.0069 memory: 1793 loss: 0.0156 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0156 2022/11/28 01:14:36 - mmengine - INFO - Epoch(train) [16][300/1567] lr: 6.2978e-04 eta: 0:00:56 time: 0.0447 data_time: 0.0068 memory: 1793 loss: 0.0114 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0114 2022/11/28 01:14:40 - mmengine - INFO - Epoch(train) [16][400/1567] lr: 5.3453e-04 eta: 0:00:52 time: 0.0443 data_time: 0.0072 memory: 1793 loss: 0.0095 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0095 2022/11/28 01:14:45 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 01:14:45 - mmengine - INFO - Epoch(train) [16][500/1567] lr: 4.4705e-04 eta: 0:00:47 time: 0.0444 data_time: 0.0073 memory: 1793 loss: 0.0124 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0124 2022/11/28 01:14:49 - mmengine - INFO - Epoch(train) [16][600/1567] lr: 3.6735e-04 eta: 0:00:43 time: 0.0450 data_time: 0.0081 memory: 1793 loss: 0.0102 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0102 2022/11/28 01:14:54 - mmengine - INFO - Epoch(train) [16][700/1567] lr: 2.9544e-04 eta: 0:00:38 time: 0.0449 data_time: 0.0073 memory: 1793 loss: 0.0108 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0108 2022/11/28 01:14:58 - mmengine - INFO - Epoch(train) [16][800/1567] lr: 2.3134e-04 eta: 0:00:34 time: 0.0455 data_time: 0.0073 memory: 1793 loss: 0.0092 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0092 2022/11/28 01:15:03 - mmengine - INFO - Epoch(train) [16][900/1567] lr: 1.7505e-04 eta: 0:00:29 time: 0.0447 data_time: 0.0072 memory: 1793 loss: 0.0104 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0104 2022/11/28 01:15:07 - mmengine - INFO - Epoch(train) [16][1000/1567] lr: 1.2658e-04 eta: 0:00:25 time: 0.0446 data_time: 0.0072 memory: 1793 loss: 0.0100 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0100 2022/11/28 01:15:12 - mmengine - INFO - Epoch(train) [16][1100/1567] lr: 8.5947e-05 eta: 0:00:20 time: 0.0448 data_time: 0.0068 memory: 1793 loss: 0.0086 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0086 2022/11/28 01:15:16 - mmengine - INFO - Epoch(train) [16][1200/1567] lr: 5.3147e-05 eta: 0:00:16 time: 0.0450 data_time: 0.0070 memory: 1793 loss: 0.0125 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0125 2022/11/28 01:15:21 - mmengine - INFO - Epoch(train) [16][1300/1567] lr: 2.8190e-05 eta: 0:00:11 time: 0.0447 data_time: 0.0073 memory: 1793 loss: 0.0098 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0098 2022/11/28 01:15:25 - mmengine - INFO - Epoch(train) [16][1400/1567] lr: 1.1078e-05 eta: 0:00:07 time: 0.0447 data_time: 0.0066 memory: 1793 loss: 0.0085 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0085 2022/11/28 01:15:30 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 01:15:30 - mmengine - INFO - Epoch(train) [16][1500/1567] lr: 1.8150e-06 eta: 0:00:03 time: 0.0449 data_time: 0.0074 memory: 1793 loss: 0.0082 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0082 2022/11/28 01:15:33 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221128_005438 2022/11/28 01:15:33 - mmengine - INFO - Epoch(train) [16][1567/1567] lr: 3.9252e-10 eta: 0:00:00 time: 0.0436 data_time: 0.0068 memory: 1793 loss: 0.2076 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2076 2022/11/28 01:15:33 - mmengine - INFO - Saving checkpoint at 16 epochs 2022/11/28 01:15:37 - mmengine - INFO - Epoch(val) [16][100/129] eta: 0:00:01 time: 0.0375 data_time: 0.0241 memory: 364 2022/11/28 01:15:38 - mmengine - INFO - Epoch(val) [16][129/129] acc/top1: 0.8751 acc/top5: 0.9772 acc/mean1: 0.8750