2022/11/28 12:27:29 - 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: 723147735 GPU 0,1,2,3,4,5,6,7: NVIDIA A100-SXM4-80GB CUDA_HOME: /mnt/petrelfs/share/cuda-11.3 NVCC: Cuda compilation tools, release 11.3, V11.3.109 GCC: gcc (GCC) 5.4.0 PyTorch: 1.11.0 PyTorch compiling details: PyTorch built with: - GCC 7.3 - C++ Version: 201402 - Intel(R) oneAPI Math Kernel Library Version 2021.4-Product Build 20210904 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v2.5.2 (Git Hash a9302535553c73243c632ad3c4c80beec3d19a1e) - OpenMP 201511 (a.k.a. OpenMP 4.5) - LAPACK is enabled (usually provided by MKL) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 11.3 - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_37,code=compute_37 - CuDNN 8.2 - Magma 2.5.2 - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.3, CUDNN_VERSION=8.2.0, CXX_COMPILER=/opt/rh/devtoolset-7/root/usr/bin/c++, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.11.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=OFF, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, TorchVision: 0.12.0 OpenCV: 4.6.0 MMEngine: 0.3.1 Runtime environment: cudnn_benchmark: False mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0} dist_cfg: {'backend': 'nccl'} seed: None diff_rank_seed: False deterministic: False Distributed launcher: pytorch Distributed training: True GPU number: 8 ------------------------------------------------------------ 2022/11/28 12:27:29 - 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=['bm']), 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=['bm']), 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=['bm']), 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=['bm']), 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=['bm']), 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=['bm']), 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-motion-u100-80e_ntu60-xsub-keypoint-3d' randomness = dict(seed=None, diff_rank_seed=False, deterministic=False) 2022/11/28 12:27:29 - mmengine - INFO - Result has been saved to /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d/modules_statistic_results.json Name of parameter - Initialization information data_bn.weight - torch.Size([75]): The value is the same before and after calling `init_weights` of STGCN data_bn.bias - torch.Size([75]): The value is the same before and after calling `init_weights` of STGCN gcn.0.gcn.PA - torch.Size([3, 25, 25]): The value is the same before and after calling `init_weights` of STGCN gcn.0.gcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.0.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.0.gcn.conv.weight - torch.Size([192, 3, 1, 1]): The value is the same before and after calling `init_weights` of STGCN gcn.0.gcn.conv.bias - torch.Size([192]): The value is the same before and after calling `init_weights` of STGCN gcn.0.tcn.conv.weight - torch.Size([64, 64, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.0.tcn.conv.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.0.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.0.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.1.gcn.PA - torch.Size([3, 25, 25]): The value is the same before and after calling `init_weights` of STGCN gcn.1.gcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.1.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.1.gcn.conv.weight - torch.Size([192, 64, 1, 1]): The value is the same before and after calling `init_weights` of STGCN gcn.1.gcn.conv.bias - torch.Size([192]): The value is the same before and after calling `init_weights` of STGCN gcn.1.tcn.conv.weight - torch.Size([64, 64, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.1.tcn.conv.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.1.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.1.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.2.gcn.PA - torch.Size([3, 25, 25]): The value is the same before and after calling `init_weights` of STGCN gcn.2.gcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.2.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.2.gcn.conv.weight - torch.Size([192, 64, 1, 1]): The value is the same before and after calling `init_weights` of STGCN gcn.2.gcn.conv.bias - torch.Size([192]): The value is the same before and after calling `init_weights` of STGCN gcn.2.tcn.conv.weight - torch.Size([64, 64, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.2.tcn.conv.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.2.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.2.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.3.gcn.PA - torch.Size([3, 25, 25]): The value is the same before and after calling `init_weights` of STGCN gcn.3.gcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.3.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.3.gcn.conv.weight - torch.Size([192, 64, 1, 1]): The value is the same before and after calling `init_weights` of STGCN gcn.3.gcn.conv.bias - torch.Size([192]): The value is the same before and after calling `init_weights` of STGCN gcn.3.tcn.conv.weight - torch.Size([64, 64, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.3.tcn.conv.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.3.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.3.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.4.gcn.PA - torch.Size([3, 25, 25]): The value is the same before and after calling `init_weights` of STGCN gcn.4.gcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.4.gcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.4.gcn.conv.weight - torch.Size([384, 64, 1, 1]): The value is the same before and after calling `init_weights` of STGCN gcn.4.gcn.conv.bias - torch.Size([384]): The value is the same before and after calling `init_weights` of STGCN gcn.4.tcn.conv.weight - torch.Size([128, 128, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.4.tcn.conv.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.4.tcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.4.tcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.4.residual.conv.weight - torch.Size([128, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.4.residual.conv.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.4.residual.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.4.residual.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.5.gcn.PA - torch.Size([3, 25, 25]): The value is the same before and after calling `init_weights` of STGCN gcn.5.gcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.5.gcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.5.gcn.conv.weight - torch.Size([384, 128, 1, 1]): The value is the same before and after calling `init_weights` of STGCN gcn.5.gcn.conv.bias - torch.Size([384]): The value is the same before and after calling `init_weights` of STGCN gcn.5.tcn.conv.weight - torch.Size([128, 128, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.5.tcn.conv.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.5.tcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.5.tcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.6.gcn.PA - torch.Size([3, 25, 25]): The value is the same before and after calling `init_weights` of STGCN gcn.6.gcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.6.gcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.6.gcn.conv.weight - torch.Size([384, 128, 1, 1]): The value is the same before and after calling `init_weights` of STGCN gcn.6.gcn.conv.bias - torch.Size([384]): The value is the same before and after calling `init_weights` of STGCN gcn.6.tcn.conv.weight - torch.Size([128, 128, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.6.tcn.conv.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.6.tcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.6.tcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.7.gcn.PA - torch.Size([3, 25, 25]): The value is the same before and after calling `init_weights` of STGCN gcn.7.gcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.7.gcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.7.gcn.conv.weight - torch.Size([768, 128, 1, 1]): The value is the same before and after calling `init_weights` of STGCN gcn.7.gcn.conv.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of STGCN gcn.7.tcn.conv.weight - torch.Size([256, 256, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.7.tcn.conv.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.7.tcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.7.tcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.7.residual.conv.weight - torch.Size([256, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.7.residual.conv.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.7.residual.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.7.residual.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.8.gcn.PA - torch.Size([3, 25, 25]): The value is the same before and after calling `init_weights` of STGCN gcn.8.gcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.8.gcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.8.gcn.conv.weight - torch.Size([768, 256, 1, 1]): The value is the same before and after calling `init_weights` of STGCN gcn.8.gcn.conv.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of STGCN gcn.8.tcn.conv.weight - torch.Size([256, 256, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.8.tcn.conv.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.8.tcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.8.tcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.9.gcn.PA - torch.Size([3, 25, 25]): The value is the same before and after calling `init_weights` of STGCN gcn.9.gcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.9.gcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.9.gcn.conv.weight - torch.Size([768, 256, 1, 1]): The value is the same before and after calling `init_weights` of STGCN gcn.9.gcn.conv.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of STGCN gcn.9.tcn.conv.weight - torch.Size([256, 256, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.9.tcn.conv.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.9.tcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.9.tcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN Name of parameter - Initialization information fc.weight - torch.Size([60, 256]): NormalInit: mean=0, std=0.01, bias=0 fc.bias - torch.Size([60]): NormalInit: mean=0, std=0.01, bias=0 2022/11/28 12:28:08 - mmengine - INFO - Checkpoints will be saved to /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d. 2022/11/28 12:28:14 - mmengine - INFO - Epoch(train) [1][100/1567] lr: 9.9996e-02 eta: 0:25:40 time: 0.0454 data_time: 0.0081 memory: 1793 loss: 3.1631 top1_acc: 0.0000 top5_acc: 0.3750 loss_cls: 3.1631 2022/11/28 12:28:18 - mmengine - INFO - Epoch(train) [1][200/1567] lr: 9.9984e-02 eta: 0:21:46 time: 0.0429 data_time: 0.0060 memory: 1793 loss: 2.1068 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.1068 2022/11/28 12:28:23 - mmengine - INFO - Epoch(train) [1][300/1567] lr: 9.9965e-02 eta: 0:20:23 time: 0.0425 data_time: 0.0059 memory: 1793 loss: 1.6204 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.6204 2022/11/28 12:28:27 - mmengine - INFO - Epoch(train) [1][400/1567] lr: 9.9938e-02 eta: 0:19:41 time: 0.0430 data_time: 0.0060 memory: 1793 loss: 1.3971 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.3971 2022/11/28 12:28:31 - mmengine - INFO - Epoch(train) [1][500/1567] lr: 9.9902e-02 eta: 0:19:12 time: 0.0431 data_time: 0.0066 memory: 1793 loss: 1.3596 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.3596 2022/11/28 12:28:36 - mmengine - INFO - Epoch(train) [1][600/1567] lr: 9.9859e-02 eta: 0:18:56 time: 0.0428 data_time: 0.0060 memory: 1793 loss: 1.2972 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.2972 2022/11/28 12:28:40 - mmengine - INFO - Epoch(train) [1][700/1567] lr: 9.9808e-02 eta: 0:18:40 time: 0.0429 data_time: 0.0067 memory: 1793 loss: 1.1013 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.1013 2022/11/28 12:28:44 - mmengine - INFO - Epoch(train) [1][800/1567] lr: 9.9750e-02 eta: 0:18:27 time: 0.0430 data_time: 0.0064 memory: 1793 loss: 0.9653 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.9653 2022/11/28 12:28:49 - mmengine - INFO - Epoch(train) [1][900/1567] lr: 9.9683e-02 eta: 0:18:15 time: 0.0428 data_time: 0.0060 memory: 1793 loss: 1.0992 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0992 2022/11/28 12:28:53 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:28:53 - mmengine - INFO - Epoch(train) [1][1000/1567] lr: 9.9609e-02 eta: 0:18:04 time: 0.0426 data_time: 0.0060 memory: 1793 loss: 1.1224 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.1224 2022/11/28 12:28:57 - mmengine - INFO - Epoch(train) [1][1100/1567] lr: 9.9527e-02 eta: 0:17:55 time: 0.0429 data_time: 0.0064 memory: 1793 loss: 0.9197 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9197 2022/11/28 12:29:01 - mmengine - INFO - Epoch(train) [1][1200/1567] lr: 9.9437e-02 eta: 0:17:46 time: 0.0425 data_time: 0.0060 memory: 1793 loss: 1.0570 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.0570 2022/11/28 12:29:06 - mmengine - INFO - Epoch(train) [1][1300/1567] lr: 9.9339e-02 eta: 0:17:39 time: 0.0424 data_time: 0.0060 memory: 1793 loss: 0.8921 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.8921 2022/11/28 12:29:10 - mmengine - INFO - Epoch(train) [1][1400/1567] lr: 9.9234e-02 eta: 0:17:32 time: 0.0426 data_time: 0.0059 memory: 1793 loss: 0.9543 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9543 2022/11/28 12:29:14 - mmengine - INFO - Epoch(train) [1][1500/1567] lr: 9.9121e-02 eta: 0:17:25 time: 0.0425 data_time: 0.0060 memory: 1793 loss: 0.8621 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.8621 2022/11/28 12:29:17 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:29:17 - mmengine - INFO - Epoch(train) [1][1567/1567] lr: 9.9040e-02 eta: 0:17:20 time: 0.0425 data_time: 0.0058 memory: 1793 loss: 0.9813 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.9813 2022/11/28 12:29:17 - mmengine - INFO - Saving checkpoint at 1 epochs 2022/11/28 12:29:21 - mmengine - INFO - Epoch(val) [1][100/129] eta: 0:00:01 time: 0.0335 data_time: 0.0203 memory: 364 2022/11/28 12:29:22 - mmengine - INFO - Epoch(val) [1][129/129] acc/top1: 0.5817 acc/top5: 0.8747 acc/mean1: 0.5818 2022/11/28 12:29:23 - mmengine - INFO - The best checkpoint with 0.5817 acc/top1 at 1 epoch is saved to best_acc/top1_epoch_1.pth. 2022/11/28 12:29:27 - mmengine - INFO - Epoch(train) [2][100/1567] lr: 9.8914e-02 eta: 0:17:17 time: 0.0456 data_time: 0.0061 memory: 1793 loss: 0.8114 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.8114 2022/11/28 12:29:32 - mmengine - INFO - Epoch(train) [2][200/1567] lr: 9.8781e-02 eta: 0:17:11 time: 0.0432 data_time: 0.0062 memory: 1793 loss: 0.8128 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8128 2022/11/28 12:29:36 - mmengine - INFO - Epoch(train) [2][300/1567] lr: 9.8639e-02 eta: 0:17:06 time: 0.0446 data_time: 0.0067 memory: 1793 loss: 0.8385 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.8385 2022/11/28 12:29:40 - mmengine - INFO - Epoch(train) [2][400/1567] lr: 9.8491e-02 eta: 0:17:02 time: 0.0431 data_time: 0.0060 memory: 1793 loss: 0.9194 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.9194 2022/11/28 12:29:42 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:29:45 - mmengine - INFO - Epoch(train) [2][500/1567] lr: 9.8334e-02 eta: 0:16:57 time: 0.0430 data_time: 0.0067 memory: 1793 loss: 0.6721 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.6721 2022/11/28 12:29:49 - mmengine - INFO - Epoch(train) [2][600/1567] lr: 9.8170e-02 eta: 0:16:51 time: 0.0426 data_time: 0.0060 memory: 1793 loss: 0.7752 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.7752 2022/11/28 12:29:53 - mmengine - INFO - Epoch(train) [2][700/1567] lr: 9.7998e-02 eta: 0:16:45 time: 0.0427 data_time: 0.0060 memory: 1793 loss: 0.8541 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.8541 2022/11/28 12:29:58 - mmengine - INFO - Epoch(train) [2][800/1567] lr: 9.7819e-02 eta: 0:16:42 time: 0.0464 data_time: 0.0061 memory: 1793 loss: 0.7121 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.7121 2022/11/28 12:30:02 - mmengine - INFO - Epoch(train) [2][900/1567] lr: 9.7632e-02 eta: 0:16:37 time: 0.0472 data_time: 0.0074 memory: 1793 loss: 0.6767 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.6767 2022/11/28 12:30:07 - mmengine - INFO - Epoch(train) [2][1000/1567] lr: 9.7438e-02 eta: 0:16:33 time: 0.0436 data_time: 0.0060 memory: 1793 loss: 0.8289 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.8289 2022/11/28 12:30:11 - mmengine - INFO - Epoch(train) [2][1100/1567] lr: 9.7236e-02 eta: 0:16:28 time: 0.0432 data_time: 0.0065 memory: 1793 loss: 0.7344 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.7344 2022/11/28 12:30:15 - mmengine - INFO - Epoch(train) [2][1200/1567] lr: 9.7027e-02 eta: 0:16:23 time: 0.0430 data_time: 0.0060 memory: 1793 loss: 0.7143 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.7143 2022/11/28 12:30:20 - mmengine - INFO - Epoch(train) [2][1300/1567] lr: 9.6810e-02 eta: 0:16:18 time: 0.0432 data_time: 0.0060 memory: 1793 loss: 0.6508 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.6508 2022/11/28 12:30:24 - mmengine - INFO - Epoch(train) [2][1400/1567] lr: 9.6587e-02 eta: 0:16:13 time: 0.0464 data_time: 0.0065 memory: 1793 loss: 0.7126 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.7126 2022/11/28 12:30:25 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:30:28 - mmengine - INFO - Epoch(train) [2][1500/1567] lr: 9.6355e-02 eta: 0:16:08 time: 0.0428 data_time: 0.0061 memory: 1793 loss: 0.6005 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.6005 2022/11/28 12:30:31 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:30:31 - mmengine - INFO - Epoch(train) [2][1567/1567] lr: 9.6196e-02 eta: 0:16:05 time: 0.0418 data_time: 0.0058 memory: 1793 loss: 0.7763 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.7763 2022/11/28 12:30:31 - mmengine - INFO - Saving checkpoint at 2 epochs 2022/11/28 12:30:35 - mmengine - INFO - Epoch(val) [2][100/129] eta: 0:00:01 time: 0.0334 data_time: 0.0201 memory: 364 2022/11/28 12:30:36 - mmengine - INFO - Epoch(val) [2][129/129] acc/top1: 0.6366 acc/top5: 0.9209 acc/mean1: 0.6365 2022/11/28 12:30:36 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_1.pth is removed 2022/11/28 12:30:37 - mmengine - INFO - The best checkpoint with 0.6366 acc/top1 at 2 epoch is saved to best_acc/top1_epoch_2.pth. 2022/11/28 12:30:41 - mmengine - INFO - Epoch(train) [3][100/1567] lr: 9.5953e-02 eta: 0:16:01 time: 0.0433 data_time: 0.0061 memory: 1793 loss: 0.6778 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.6778 2022/11/28 12:30:45 - mmengine - INFO - Epoch(train) [3][200/1567] lr: 9.5703e-02 eta: 0:15:56 time: 0.0435 data_time: 0.0061 memory: 1793 loss: 0.7409 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.7409 2022/11/28 12:30:50 - mmengine - INFO - Epoch(train) [3][300/1567] lr: 9.5445e-02 eta: 0:15:52 time: 0.0433 data_time: 0.0060 memory: 1793 loss: 0.8094 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 0.8094 2022/11/28 12:30:54 - mmengine - INFO - Epoch(train) [3][400/1567] lr: 9.5180e-02 eta: 0:15:47 time: 0.0459 data_time: 0.0064 memory: 1793 loss: 0.6548 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.6548 2022/11/28 12:30:58 - mmengine - INFO - Epoch(train) [3][500/1567] lr: 9.4908e-02 eta: 0:15:42 time: 0.0427 data_time: 0.0061 memory: 1793 loss: 0.5537 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5537 2022/11/28 12:31:03 - mmengine - INFO - Epoch(train) [3][600/1567] lr: 9.4629e-02 eta: 0:15:38 time: 0.0430 data_time: 0.0061 memory: 1793 loss: 0.6508 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.6508 2022/11/28 12:31:07 - mmengine - INFO - Epoch(train) [3][700/1567] lr: 9.4343e-02 eta: 0:15:33 time: 0.0431 data_time: 0.0062 memory: 1793 loss: 0.7079 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.7079 2022/11/28 12:31:12 - mmengine - INFO - Epoch(train) [3][800/1567] lr: 9.4050e-02 eta: 0:15:29 time: 0.0434 data_time: 0.0060 memory: 1793 loss: 0.6141 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.6141 2022/11/28 12:31:14 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:31:16 - mmengine - INFO - Epoch(train) [3][900/1567] lr: 9.3750e-02 eta: 0:15:25 time: 0.0467 data_time: 0.0061 memory: 1793 loss: 0.6748 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.6748 2022/11/28 12:31:20 - mmengine - INFO - Epoch(train) [3][1000/1567] lr: 9.3444e-02 eta: 0:15:20 time: 0.0431 data_time: 0.0061 memory: 1793 loss: 0.7130 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.7130 2022/11/28 12:31:25 - mmengine - INFO - Epoch(train) [3][1100/1567] lr: 9.3130e-02 eta: 0:15:15 time: 0.0433 data_time: 0.0060 memory: 1793 loss: 0.6929 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.6929 2022/11/28 12:31:29 - mmengine - INFO - Epoch(train) [3][1200/1567] lr: 9.2810e-02 eta: 0:15:11 time: 0.0432 data_time: 0.0061 memory: 1793 loss: 0.6494 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.6494 2022/11/28 12:31:33 - mmengine - INFO - Epoch(train) [3][1300/1567] lr: 9.2483e-02 eta: 0:15:06 time: 0.0435 data_time: 0.0067 memory: 1793 loss: 0.5941 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.5941 2022/11/28 12:31:38 - mmengine - INFO - Epoch(train) [3][1400/1567] lr: 9.2149e-02 eta: 0:15:02 time: 0.0434 data_time: 0.0060 memory: 1793 loss: 0.5610 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.5610 2022/11/28 12:31:42 - mmengine - INFO - Epoch(train) [3][1500/1567] lr: 9.1809e-02 eta: 0:14:57 time: 0.0432 data_time: 0.0065 memory: 1793 loss: 0.6190 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.6190 2022/11/28 12:31:45 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:31:45 - mmengine - INFO - Epoch(train) [3][1567/1567] lr: 9.1577e-02 eta: 0:14:54 time: 0.0417 data_time: 0.0059 memory: 1793 loss: 0.6064 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.6064 2022/11/28 12:31:45 - mmengine - INFO - Saving checkpoint at 3 epochs 2022/11/28 12:31:49 - mmengine - INFO - Epoch(val) [3][100/129] eta: 0:00:01 time: 0.0332 data_time: 0.0199 memory: 364 2022/11/28 12:31:50 - mmengine - INFO - Epoch(val) [3][129/129] acc/top1: 0.4359 acc/top5: 0.7690 acc/mean1: 0.4357 2022/11/28 12:31:55 - mmengine - INFO - Epoch(train) [4][100/1567] lr: 9.1226e-02 eta: 0:14:50 time: 0.0441 data_time: 0.0066 memory: 1793 loss: 0.7094 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.7094 2022/11/28 12:31:59 - mmengine - INFO - Epoch(train) [4][200/1567] lr: 9.0868e-02 eta: 0:14:46 time: 0.0442 data_time: 0.0071 memory: 1793 loss: 0.6299 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.6299 2022/11/28 12:32:03 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:32:03 - mmengine - INFO - Epoch(train) [4][300/1567] lr: 9.0504e-02 eta: 0:14:41 time: 0.0428 data_time: 0.0061 memory: 1793 loss: 0.6492 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6492 2022/11/28 12:32:08 - mmengine - INFO - Epoch(train) [4][400/1567] lr: 9.0133e-02 eta: 0:14:36 time: 0.0431 data_time: 0.0060 memory: 1793 loss: 0.5340 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.5340 2022/11/28 12:32:12 - mmengine - INFO - Epoch(train) [4][500/1567] lr: 8.9756e-02 eta: 0:14:32 time: 0.0461 data_time: 0.0061 memory: 1793 loss: 0.5147 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5147 2022/11/28 12:32:16 - mmengine - INFO - Epoch(train) [4][600/1567] lr: 8.9373e-02 eta: 0:14:27 time: 0.0432 data_time: 0.0061 memory: 1793 loss: 0.6452 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.6452 2022/11/28 12:32:21 - mmengine - INFO - Epoch(train) [4][700/1567] lr: 8.8984e-02 eta: 0:14:23 time: 0.0434 data_time: 0.0060 memory: 1793 loss: 0.5145 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.5145 2022/11/28 12:32:25 - mmengine - INFO - Epoch(train) [4][800/1567] lr: 8.8589e-02 eta: 0:14:18 time: 0.0431 data_time: 0.0061 memory: 1793 loss: 0.6758 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.6758 2022/11/28 12:32:29 - mmengine - INFO - Epoch(train) [4][900/1567] lr: 8.8187e-02 eta: 0:14:14 time: 0.0431 data_time: 0.0061 memory: 1793 loss: 0.5612 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.5612 2022/11/28 12:32:34 - mmengine - INFO - Epoch(train) [4][1000/1567] lr: 8.7780e-02 eta: 0:14:09 time: 0.0455 data_time: 0.0060 memory: 1793 loss: 0.6706 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.6706 2022/11/28 12:32:38 - mmengine - INFO - Epoch(train) [4][1100/1567] lr: 8.7367e-02 eta: 0:14:04 time: 0.0431 data_time: 0.0061 memory: 1793 loss: 0.6169 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.6169 2022/11/28 12:32:43 - mmengine - INFO - Epoch(train) [4][1200/1567] lr: 8.6947e-02 eta: 0:14:00 time: 0.0437 data_time: 0.0065 memory: 1793 loss: 0.5916 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5916 2022/11/28 12:32:47 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:32:47 - mmengine - INFO - Epoch(train) [4][1300/1567] lr: 8.6522e-02 eta: 0:13:56 time: 0.0438 data_time: 0.0062 memory: 1793 loss: 0.6252 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.6252 2022/11/28 12:32:51 - mmengine - INFO - Epoch(train) [4][1400/1567] lr: 8.6092e-02 eta: 0:13:51 time: 0.0436 data_time: 0.0064 memory: 1793 loss: 0.5150 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5150 2022/11/28 12:32:56 - mmengine - INFO - Epoch(train) [4][1500/1567] lr: 8.5655e-02 eta: 0:13:47 time: 0.0433 data_time: 0.0060 memory: 1793 loss: 0.5916 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5916 2022/11/28 12:32:59 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:32:59 - mmengine - INFO - Epoch(train) [4][1567/1567] lr: 8.5360e-02 eta: 0:13:44 time: 0.0420 data_time: 0.0062 memory: 1793 loss: 0.5760 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.5760 2022/11/28 12:32:59 - mmengine - INFO - Saving checkpoint at 4 epochs 2022/11/28 12:33:02 - mmengine - INFO - Epoch(val) [4][100/129] eta: 0:00:01 time: 0.0335 data_time: 0.0203 memory: 364 2022/11/28 12:33:04 - mmengine - INFO - Epoch(val) [4][129/129] acc/top1: 0.6106 acc/top5: 0.8783 acc/mean1: 0.6105 2022/11/28 12:33:08 - mmengine - INFO - Epoch(train) [5][100/1567] lr: 8.4914e-02 eta: 0:13:40 time: 0.0433 data_time: 0.0062 memory: 1793 loss: 0.4733 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4733 2022/11/28 12:33:12 - mmengine - INFO - Epoch(train) [5][200/1567] lr: 8.4463e-02 eta: 0:13:36 time: 0.0461 data_time: 0.0061 memory: 1793 loss: 0.4307 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4307 2022/11/28 12:33:17 - mmengine - INFO - Epoch(train) [5][300/1567] lr: 8.4006e-02 eta: 0:13:31 time: 0.0436 data_time: 0.0067 memory: 1793 loss: 0.6232 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.6232 2022/11/28 12:33:21 - mmengine - INFO - Epoch(train) [5][400/1567] lr: 8.3544e-02 eta: 0:13:27 time: 0.0434 data_time: 0.0065 memory: 1793 loss: 0.5768 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5768 2022/11/28 12:33:26 - mmengine - INFO - Epoch(train) [5][500/1567] lr: 8.3077e-02 eta: 0:13:22 time: 0.0432 data_time: 0.0061 memory: 1793 loss: 0.4789 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4789 2022/11/28 12:33:30 - mmengine - INFO - Epoch(train) [5][600/1567] lr: 8.2605e-02 eta: 0:13:18 time: 0.0432 data_time: 0.0061 memory: 1793 loss: 0.5021 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5021 2022/11/28 12:33:34 - mmengine - INFO - Epoch(train) [5][700/1567] lr: 8.2127e-02 eta: 0:13:13 time: 0.0427 data_time: 0.0061 memory: 1793 loss: 0.5092 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.5092 2022/11/28 12:33:36 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:33:39 - mmengine - INFO - Epoch(train) [5][800/1567] lr: 8.1645e-02 eta: 0:13:09 time: 0.0427 data_time: 0.0061 memory: 1793 loss: 0.5034 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5034 2022/11/28 12:33:43 - mmengine - INFO - Epoch(train) [5][900/1567] lr: 8.1157e-02 eta: 0:13:04 time: 0.0427 data_time: 0.0062 memory: 1793 loss: 0.5588 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5588 2022/11/28 12:33:47 - mmengine - INFO - Epoch(train) [5][1000/1567] lr: 8.0665e-02 eta: 0:13:00 time: 0.0443 data_time: 0.0062 memory: 1793 loss: 0.5894 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.5894 2022/11/28 12:33:51 - mmengine - INFO - Epoch(train) [5][1100/1567] lr: 8.0167e-02 eta: 0:12:55 time: 0.0431 data_time: 0.0061 memory: 1793 loss: 0.4815 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.4815 2022/11/28 12:33:56 - mmengine - INFO - Epoch(train) [5][1200/1567] lr: 7.9665e-02 eta: 0:12:50 time: 0.0432 data_time: 0.0061 memory: 1793 loss: 0.4851 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4851 2022/11/28 12:34:00 - mmengine - INFO - Epoch(train) [5][1300/1567] lr: 7.9159e-02 eta: 0:12:46 time: 0.0431 data_time: 0.0060 memory: 1793 loss: 0.4565 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4565 2022/11/28 12:34:04 - mmengine - INFO - Epoch(train) [5][1400/1567] lr: 7.8647e-02 eta: 0:12:41 time: 0.0435 data_time: 0.0062 memory: 1793 loss: 0.5372 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.5372 2022/11/28 12:34:09 - mmengine - INFO - Epoch(train) [5][1500/1567] lr: 7.8132e-02 eta: 0:12:37 time: 0.0440 data_time: 0.0062 memory: 1793 loss: 0.5083 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.5083 2022/11/28 12:34:12 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:34:12 - mmengine - INFO - Epoch(train) [5][1567/1567] lr: 7.7784e-02 eta: 0:12:34 time: 0.0417 data_time: 0.0058 memory: 1793 loss: 0.5723 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.5723 2022/11/28 12:34:12 - mmengine - INFO - Saving checkpoint at 5 epochs 2022/11/28 12:34:15 - mmengine - INFO - Epoch(val) [5][100/129] eta: 0:00:01 time: 0.0334 data_time: 0.0201 memory: 364 2022/11/28 12:34:17 - mmengine - INFO - Epoch(val) [5][129/129] acc/top1: 0.6094 acc/top5: 0.8932 acc/mean1: 0.6095 2022/11/28 12:34:21 - mmengine - INFO - Epoch(train) [6][100/1567] lr: 7.7261e-02 eta: 0:12:30 time: 0.0427 data_time: 0.0063 memory: 1793 loss: 0.4837 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.4837 2022/11/28 12:34:24 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:34:25 - mmengine - INFO - Epoch(train) [6][200/1567] lr: 7.6733e-02 eta: 0:12:25 time: 0.0432 data_time: 0.0066 memory: 1793 loss: 0.4640 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.4640 2022/11/28 12:34:30 - mmengine - INFO - Epoch(train) [6][300/1567] lr: 7.6202e-02 eta: 0:12:21 time: 0.0429 data_time: 0.0061 memory: 1793 loss: 0.4841 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4841 2022/11/28 12:34:34 - mmengine - INFO - Epoch(train) [6][400/1567] lr: 7.5666e-02 eta: 0:12:16 time: 0.0432 data_time: 0.0061 memory: 1793 loss: 0.4766 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4766 2022/11/28 12:34:38 - mmengine - INFO - Epoch(train) [6][500/1567] lr: 7.5126e-02 eta: 0:12:12 time: 0.0433 data_time: 0.0061 memory: 1793 loss: 0.4968 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4968 2022/11/28 12:34:43 - mmengine - INFO - Epoch(train) [6][600/1567] lr: 7.4583e-02 eta: 0:12:07 time: 0.0435 data_time: 0.0068 memory: 1793 loss: 0.5373 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5373 2022/11/28 12:34:47 - mmengine - INFO - Epoch(train) [6][700/1567] lr: 7.4035e-02 eta: 0:12:03 time: 0.0434 data_time: 0.0064 memory: 1793 loss: 0.4894 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4894 2022/11/28 12:34:51 - mmengine - INFO - Epoch(train) [6][800/1567] lr: 7.3484e-02 eta: 0:11:58 time: 0.0424 data_time: 0.0061 memory: 1793 loss: 0.3783 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3783 2022/11/28 12:34:56 - mmengine - INFO - Epoch(train) [6][900/1567] lr: 7.2929e-02 eta: 0:11:54 time: 0.0432 data_time: 0.0061 memory: 1793 loss: 0.4552 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4552 2022/11/28 12:35:00 - mmengine - INFO - Epoch(train) [6][1000/1567] lr: 7.2371e-02 eta: 0:11:49 time: 0.0432 data_time: 0.0061 memory: 1793 loss: 0.4181 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.4181 2022/11/28 12:35:04 - mmengine - INFO - Epoch(train) [6][1100/1567] lr: 7.1809e-02 eta: 0:11:45 time: 0.0430 data_time: 0.0061 memory: 1793 loss: 0.3947 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3947 2022/11/28 12:35:07 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:35:09 - mmengine - INFO - Epoch(train) [6][1200/1567] lr: 7.1243e-02 eta: 0:11:41 time: 0.0432 data_time: 0.0061 memory: 1793 loss: 0.3920 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.3920 2022/11/28 12:35:13 - mmengine - INFO - Epoch(train) [6][1300/1567] lr: 7.0674e-02 eta: 0:11:36 time: 0.0430 data_time: 0.0061 memory: 1793 loss: 0.4459 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.4459 2022/11/28 12:35:17 - mmengine - INFO - Epoch(train) [6][1400/1567] lr: 7.0102e-02 eta: 0:11:32 time: 0.0434 data_time: 0.0062 memory: 1793 loss: 0.3903 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3903 2022/11/28 12:35:22 - mmengine - INFO - Epoch(train) [6][1500/1567] lr: 6.9527e-02 eta: 0:11:27 time: 0.0430 data_time: 0.0066 memory: 1793 loss: 0.3807 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3807 2022/11/28 12:35:25 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:35:25 - mmengine - INFO - Epoch(train) [6][1567/1567] lr: 6.9140e-02 eta: 0:11:24 time: 0.0422 data_time: 0.0063 memory: 1793 loss: 0.5364 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.5364 2022/11/28 12:35:25 - mmengine - INFO - Saving checkpoint at 6 epochs 2022/11/28 12:35:28 - mmengine - INFO - Epoch(val) [6][100/129] eta: 0:00:01 time: 0.0339 data_time: 0.0207 memory: 364 2022/11/28 12:35:30 - mmengine - INFO - Epoch(val) [6][129/129] acc/top1: 0.6581 acc/top5: 0.9094 acc/mean1: 0.6579 2022/11/28 12:35:30 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_2.pth is removed 2022/11/28 12:35:30 - mmengine - INFO - The best checkpoint with 0.6581 acc/top1 at 6 epoch is saved to best_acc/top1_epoch_6.pth. 2022/11/28 12:35:34 - mmengine - INFO - Epoch(train) [7][100/1567] lr: 6.8560e-02 eta: 0:11:20 time: 0.0431 data_time: 0.0061 memory: 1793 loss: 0.3734 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3734 2022/11/28 12:35:39 - mmengine - INFO - Epoch(train) [7][200/1567] lr: 6.7976e-02 eta: 0:11:16 time: 0.0449 data_time: 0.0076 memory: 1793 loss: 0.4661 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.4661 2022/11/28 12:35:43 - mmengine - INFO - Epoch(train) [7][300/1567] lr: 6.7390e-02 eta: 0:11:11 time: 0.0430 data_time: 0.0061 memory: 1793 loss: 0.4059 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4059 2022/11/28 12:35:47 - mmengine - INFO - Epoch(train) [7][400/1567] lr: 6.6802e-02 eta: 0:11:07 time: 0.0429 data_time: 0.0061 memory: 1793 loss: 0.4115 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.4115 2022/11/28 12:35:52 - mmengine - INFO - Epoch(train) [7][500/1567] lr: 6.6210e-02 eta: 0:11:02 time: 0.0431 data_time: 0.0061 memory: 1793 loss: 0.5166 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.5166 2022/11/28 12:35:56 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:35:56 - mmengine - INFO - Epoch(train) [7][600/1567] lr: 6.5616e-02 eta: 0:10:58 time: 0.0439 data_time: 0.0065 memory: 1793 loss: 0.3971 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3971 2022/11/28 12:36:01 - mmengine - INFO - Epoch(train) [7][700/1567] lr: 6.5020e-02 eta: 0:10:54 time: 0.0433 data_time: 0.0062 memory: 1793 loss: 0.4542 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4542 2022/11/28 12:36:05 - mmengine - INFO - Epoch(train) [7][800/1567] lr: 6.4421e-02 eta: 0:10:49 time: 0.0433 data_time: 0.0061 memory: 1793 loss: 0.4654 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.4654 2022/11/28 12:36:09 - mmengine - INFO - Epoch(train) [7][900/1567] lr: 6.3820e-02 eta: 0:10:45 time: 0.0448 data_time: 0.0062 memory: 1793 loss: 0.3002 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3002 2022/11/28 12:36:14 - mmengine - INFO - Epoch(train) [7][1000/1567] lr: 6.3217e-02 eta: 0:10:41 time: 0.0435 data_time: 0.0061 memory: 1793 loss: 0.3268 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3268 2022/11/28 12:36:18 - mmengine - INFO - Epoch(train) [7][1100/1567] lr: 6.2612e-02 eta: 0:10:36 time: 0.0455 data_time: 0.0064 memory: 1793 loss: 0.4228 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4228 2022/11/28 12:36:22 - mmengine - INFO - Epoch(train) [7][1200/1567] lr: 6.2005e-02 eta: 0:10:32 time: 0.0444 data_time: 0.0061 memory: 1793 loss: 0.3920 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3920 2022/11/28 12:36:27 - mmengine - INFO - Epoch(train) [7][1300/1567] lr: 6.1396e-02 eta: 0:10:27 time: 0.0432 data_time: 0.0061 memory: 1793 loss: 0.4139 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4139 2022/11/28 12:36:31 - mmengine - INFO - Epoch(train) [7][1400/1567] lr: 6.0785e-02 eta: 0:10:23 time: 0.0433 data_time: 0.0067 memory: 1793 loss: 0.3339 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3339 2022/11/28 12:36:35 - mmengine - INFO - Epoch(train) [7][1500/1567] lr: 6.0172e-02 eta: 0:10:19 time: 0.0435 data_time: 0.0067 memory: 1793 loss: 0.4206 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4206 2022/11/28 12:36:38 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:36:38 - mmengine - INFO - Epoch(train) [7][1567/1567] lr: 5.9761e-02 eta: 0:10:16 time: 0.0423 data_time: 0.0064 memory: 1793 loss: 0.5682 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.5682 2022/11/28 12:36:38 - mmengine - INFO - Saving checkpoint at 7 epochs 2022/11/28 12:36:42 - mmengine - INFO - Epoch(val) [7][100/129] eta: 0:00:01 time: 0.0335 data_time: 0.0203 memory: 364 2022/11/28 12:36:43 - mmengine - INFO - Epoch(val) [7][129/129] acc/top1: 0.7075 acc/top5: 0.9284 acc/mean1: 0.7073 2022/11/28 12:36:43 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_6.pth is removed 2022/11/28 12:36:44 - mmengine - INFO - The best checkpoint with 0.7075 acc/top1 at 7 epoch is saved to best_acc/top1_epoch_7.pth. 2022/11/28 12:36:45 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:36:48 - mmengine - INFO - Epoch(train) [8][100/1567] lr: 5.9145e-02 eta: 0:10:12 time: 0.0456 data_time: 0.0061 memory: 1793 loss: 0.3374 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.3374 2022/11/28 12:36:53 - mmengine - INFO - Epoch(train) [8][200/1567] lr: 5.8529e-02 eta: 0:10:07 time: 0.0434 data_time: 0.0061 memory: 1793 loss: 0.3529 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3529 2022/11/28 12:36:57 - mmengine - INFO - Epoch(train) [8][300/1567] lr: 5.7911e-02 eta: 0:10:03 time: 0.0435 data_time: 0.0068 memory: 1793 loss: 0.3288 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3288 2022/11/28 12:37:01 - mmengine - INFO - Epoch(train) [8][400/1567] lr: 5.7292e-02 eta: 0:09:58 time: 0.0432 data_time: 0.0062 memory: 1793 loss: 0.3787 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.3787 2022/11/28 12:37:06 - mmengine - INFO - Epoch(train) [8][500/1567] lr: 5.6671e-02 eta: 0:09:54 time: 0.0430 data_time: 0.0061 memory: 1793 loss: 0.3727 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.3727 2022/11/28 12:37:10 - mmengine - INFO - Epoch(train) [8][600/1567] lr: 5.6050e-02 eta: 0:09:50 time: 0.0436 data_time: 0.0062 memory: 1793 loss: 0.4746 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.4746 2022/11/28 12:37:15 - mmengine - INFO - Epoch(train) [8][700/1567] lr: 5.5427e-02 eta: 0:09:45 time: 0.0434 data_time: 0.0062 memory: 1793 loss: 0.3581 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3581 2022/11/28 12:37:19 - mmengine - INFO - Epoch(train) [8][800/1567] lr: 5.4804e-02 eta: 0:09:41 time: 0.0431 data_time: 0.0061 memory: 1793 loss: 0.2976 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2976 2022/11/28 12:37:23 - mmengine - INFO - Epoch(train) [8][900/1567] lr: 5.4180e-02 eta: 0:09:37 time: 0.0435 data_time: 0.0061 memory: 1793 loss: 0.4340 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4340 2022/11/28 12:37:28 - mmengine - INFO - Epoch(train) [8][1000/1567] lr: 5.3556e-02 eta: 0:09:32 time: 0.0435 data_time: 0.0061 memory: 1793 loss: 0.3978 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3978 2022/11/28 12:37:29 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:37:32 - mmengine - INFO - Epoch(train) [8][1100/1567] lr: 5.2930e-02 eta: 0:09:28 time: 0.0437 data_time: 0.0062 memory: 1793 loss: 0.4119 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4119 2022/11/28 12:37:36 - mmengine - INFO - Epoch(train) [8][1200/1567] lr: 5.2305e-02 eta: 0:09:23 time: 0.0433 data_time: 0.0061 memory: 1793 loss: 0.3194 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3194 2022/11/28 12:37:41 - mmengine - INFO - Epoch(train) [8][1300/1567] lr: 5.1679e-02 eta: 0:09:19 time: 0.0436 data_time: 0.0061 memory: 1793 loss: 0.3822 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.3822 2022/11/28 12:37:45 - mmengine - INFO - Epoch(train) [8][1400/1567] lr: 5.1052e-02 eta: 0:09:15 time: 0.0435 data_time: 0.0062 memory: 1793 loss: 0.3020 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3020 2022/11/28 12:37:49 - mmengine - INFO - Epoch(train) [8][1500/1567] lr: 5.0426e-02 eta: 0:09:10 time: 0.0438 data_time: 0.0062 memory: 1793 loss: 0.3846 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3846 2022/11/28 12:37:52 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:37:52 - mmengine - INFO - Epoch(train) [8][1567/1567] lr: 5.0006e-02 eta: 0:09:07 time: 0.0423 data_time: 0.0060 memory: 1793 loss: 0.3989 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.3989 2022/11/28 12:37:52 - mmengine - INFO - Saving checkpoint at 8 epochs 2022/11/28 12:37:56 - mmengine - INFO - Epoch(val) [8][100/129] eta: 0:00:01 time: 0.0336 data_time: 0.0204 memory: 364 2022/11/28 12:37:57 - mmengine - INFO - Epoch(val) [8][129/129] acc/top1: 0.7770 acc/top5: 0.9512 acc/mean1: 0.7769 2022/11/28 12:37:57 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_7.pth is removed 2022/11/28 12:37:58 - mmengine - INFO - The best checkpoint with 0.7770 acc/top1 at 8 epoch is saved to best_acc/top1_epoch_8.pth. 2022/11/28 12:38:03 - mmengine - INFO - Epoch(train) [9][100/1567] lr: 4.9380e-02 eta: 0:09:03 time: 0.0433 data_time: 0.0062 memory: 1793 loss: 0.3365 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3365 2022/11/28 12:38:07 - mmengine - INFO - Epoch(train) [9][200/1567] lr: 4.8753e-02 eta: 0:08:59 time: 0.0432 data_time: 0.0061 memory: 1793 loss: 0.4200 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.4200 2022/11/28 12:38:11 - mmengine - INFO - Epoch(train) [9][300/1567] lr: 4.8127e-02 eta: 0:08:55 time: 0.0440 data_time: 0.0065 memory: 1793 loss: 0.3652 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3652 2022/11/28 12:38:16 - mmengine - INFO - Epoch(train) [9][400/1567] lr: 4.7501e-02 eta: 0:08:50 time: 0.0428 data_time: 0.0061 memory: 1793 loss: 0.3185 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3185 2022/11/28 12:38:19 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:38:20 - mmengine - INFO - Epoch(train) [9][500/1567] lr: 4.6876e-02 eta: 0:08:46 time: 0.0430 data_time: 0.0062 memory: 1793 loss: 0.3191 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.3191 2022/11/28 12:38:25 - mmengine - INFO - Epoch(train) [9][600/1567] lr: 4.6251e-02 eta: 0:08:41 time: 0.0431 data_time: 0.0064 memory: 1793 loss: 0.3466 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.3466 2022/11/28 12:38:29 - mmengine - INFO - Epoch(train) [9][700/1567] lr: 4.5626e-02 eta: 0:08:37 time: 0.0436 data_time: 0.0071 memory: 1793 loss: 0.3255 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3255 2022/11/28 12:38:33 - mmengine - INFO - Epoch(train) [9][800/1567] lr: 4.5003e-02 eta: 0:08:33 time: 0.0458 data_time: 0.0083 memory: 1793 loss: 0.2535 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2535 2022/11/28 12:38:38 - mmengine - INFO - Epoch(train) [9][900/1567] lr: 4.4380e-02 eta: 0:08:28 time: 0.0432 data_time: 0.0061 memory: 1793 loss: 0.2675 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2675 2022/11/28 12:38:42 - mmengine - INFO - Epoch(train) [9][1000/1567] lr: 4.3757e-02 eta: 0:08:24 time: 0.0431 data_time: 0.0061 memory: 1793 loss: 0.2761 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2761 2022/11/28 12:38:46 - mmengine - INFO - Epoch(train) [9][1100/1567] lr: 4.3136e-02 eta: 0:08:20 time: 0.0432 data_time: 0.0062 memory: 1793 loss: 0.2592 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2592 2022/11/28 12:38:51 - mmengine - INFO - Epoch(train) [9][1200/1567] lr: 4.2516e-02 eta: 0:08:15 time: 0.0431 data_time: 0.0062 memory: 1793 loss: 0.3049 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3049 2022/11/28 12:38:55 - mmengine - INFO - Epoch(train) [9][1300/1567] lr: 4.1897e-02 eta: 0:08:11 time: 0.0447 data_time: 0.0065 memory: 1793 loss: 0.3559 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.3559 2022/11/28 12:39:00 - mmengine - INFO - Epoch(train) [9][1400/1567] lr: 4.1280e-02 eta: 0:08:06 time: 0.0438 data_time: 0.0065 memory: 1793 loss: 0.2378 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2378 2022/11/28 12:39:02 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:39:04 - mmengine - INFO - Epoch(train) [9][1500/1567] lr: 4.0664e-02 eta: 0:08:02 time: 0.0450 data_time: 0.0061 memory: 1793 loss: 0.2709 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2709 2022/11/28 12:39:07 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:39:07 - mmengine - INFO - Epoch(train) [9][1567/1567] lr: 4.0252e-02 eta: 0:07:59 time: 0.0425 data_time: 0.0060 memory: 1793 loss: 0.4256 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.4256 2022/11/28 12:39:07 - mmengine - INFO - Saving checkpoint at 9 epochs 2022/11/28 12:39:11 - mmengine - INFO - Epoch(val) [9][100/129] eta: 0:00:01 time: 0.0339 data_time: 0.0206 memory: 364 2022/11/28 12:39:12 - mmengine - INFO - Epoch(val) [9][129/129] acc/top1: 0.7515 acc/top5: 0.9370 acc/mean1: 0.7516 2022/11/28 12:39:17 - mmengine - INFO - Epoch(train) [10][100/1567] lr: 3.9638e-02 eta: 0:07:55 time: 0.0433 data_time: 0.0062 memory: 1793 loss: 0.2173 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2173 2022/11/28 12:39:21 - mmengine - INFO - Epoch(train) [10][200/1567] lr: 3.9026e-02 eta: 0:07:51 time: 0.0432 data_time: 0.0062 memory: 1793 loss: 0.3539 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3539 2022/11/28 12:39:25 - mmengine - INFO - Epoch(train) [10][300/1567] lr: 3.8415e-02 eta: 0:07:46 time: 0.0434 data_time: 0.0061 memory: 1793 loss: 0.2643 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2643 2022/11/28 12:39:30 - mmengine - INFO - Epoch(train) [10][400/1567] lr: 3.7807e-02 eta: 0:07:42 time: 0.0429 data_time: 0.0062 memory: 1793 loss: 0.2541 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2541 2022/11/28 12:39:34 - mmengine - INFO - Epoch(train) [10][500/1567] lr: 3.7200e-02 eta: 0:07:38 time: 0.0431 data_time: 0.0062 memory: 1793 loss: 0.2341 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2341 2022/11/28 12:39:38 - mmengine - INFO - Epoch(train) [10][600/1567] lr: 3.6596e-02 eta: 0:07:33 time: 0.0435 data_time: 0.0068 memory: 1793 loss: 0.2985 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2985 2022/11/28 12:39:43 - mmengine - INFO - Epoch(train) [10][700/1567] lr: 3.5993e-02 eta: 0:07:29 time: 0.0435 data_time: 0.0061 memory: 1793 loss: 0.2710 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2710 2022/11/28 12:39:47 - mmengine - INFO - Epoch(train) [10][800/1567] lr: 3.5393e-02 eta: 0:07:24 time: 0.0438 data_time: 0.0062 memory: 1793 loss: 0.2066 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2066 2022/11/28 12:39:52 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:39:52 - mmengine - INFO - Epoch(train) [10][900/1567] lr: 3.4795e-02 eta: 0:07:20 time: 0.0443 data_time: 0.0072 memory: 1793 loss: 0.2322 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2322 2022/11/28 12:39:56 - mmengine - INFO - Epoch(train) [10][1000/1567] lr: 3.4199e-02 eta: 0:07:16 time: 0.0440 data_time: 0.0061 memory: 1793 loss: 0.2970 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2970 2022/11/28 12:40:01 - mmengine - INFO - Epoch(train) [10][1100/1567] lr: 3.3606e-02 eta: 0:07:11 time: 0.0432 data_time: 0.0061 memory: 1793 loss: 0.1818 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1818 2022/11/28 12:40:05 - mmengine - INFO - Epoch(train) [10][1200/1567] lr: 3.3015e-02 eta: 0:07:07 time: 0.0433 data_time: 0.0061 memory: 1793 loss: 0.1803 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1803 2022/11/28 12:40:09 - mmengine - INFO - Epoch(train) [10][1300/1567] lr: 3.2428e-02 eta: 0:07:03 time: 0.0441 data_time: 0.0063 memory: 1793 loss: 0.2220 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2220 2022/11/28 12:40:14 - mmengine - INFO - Epoch(train) [10][1400/1567] lr: 3.1842e-02 eta: 0:06:58 time: 0.0438 data_time: 0.0062 memory: 1793 loss: 0.2589 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2589 2022/11/28 12:40:18 - mmengine - INFO - Epoch(train) [10][1500/1567] lr: 3.1260e-02 eta: 0:06:54 time: 0.0443 data_time: 0.0068 memory: 1793 loss: 0.1923 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1923 2022/11/28 12:40:21 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:40:21 - mmengine - INFO - Epoch(train) [10][1567/1567] lr: 3.0872e-02 eta: 0:06:51 time: 0.0431 data_time: 0.0068 memory: 1793 loss: 0.3621 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.3621 2022/11/28 12:40:21 - mmengine - INFO - Saving checkpoint at 10 epochs 2022/11/28 12:40:25 - mmengine - INFO - Epoch(val) [10][100/129] eta: 0:00:00 time: 0.0331 data_time: 0.0195 memory: 364 2022/11/28 12:40:26 - mmengine - INFO - Epoch(val) [10][129/129] acc/top1: 0.7778 acc/top5: 0.9441 acc/mean1: 0.7777 2022/11/28 12:40:26 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_8.pth is removed 2022/11/28 12:40:26 - mmengine - INFO - The best checkpoint with 0.7778 acc/top1 at 10 epoch is saved to best_acc/top1_epoch_10.pth. 2022/11/28 12:40:31 - mmengine - INFO - Epoch(train) [11][100/1567] lr: 3.0294e-02 eta: 0:06:47 time: 0.0436 data_time: 0.0072 memory: 1793 loss: 0.1600 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1600 2022/11/28 12:40:35 - mmengine - INFO - Epoch(train) [11][200/1567] lr: 2.9720e-02 eta: 0:06:42 time: 0.0432 data_time: 0.0064 memory: 1793 loss: 0.1682 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1682 2022/11/28 12:40:40 - mmengine - INFO - Epoch(train) [11][300/1567] lr: 2.9149e-02 eta: 0:06:38 time: 0.0433 data_time: 0.0066 memory: 1793 loss: 0.2251 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2251 2022/11/28 12:40:41 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:40:44 - mmengine - INFO - Epoch(train) [11][400/1567] lr: 2.8581e-02 eta: 0:06:34 time: 0.0432 data_time: 0.0067 memory: 1793 loss: 0.2077 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2077 2022/11/28 12:40:48 - mmengine - INFO - Epoch(train) [11][500/1567] lr: 2.8017e-02 eta: 0:06:29 time: 0.0433 data_time: 0.0067 memory: 1793 loss: 0.2172 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2172 2022/11/28 12:40:53 - mmengine - INFO - Epoch(train) [11][600/1567] lr: 2.7456e-02 eta: 0:06:25 time: 0.0437 data_time: 0.0062 memory: 1793 loss: 0.1662 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1662 2022/11/28 12:40:57 - mmengine - INFO - Epoch(train) [11][700/1567] lr: 2.6898e-02 eta: 0:06:20 time: 0.0437 data_time: 0.0061 memory: 1793 loss: 0.1734 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1734 2022/11/28 12:41:02 - mmengine - INFO - Epoch(train) [11][800/1567] lr: 2.6345e-02 eta: 0:06:16 time: 0.0446 data_time: 0.0062 memory: 1793 loss: 0.1818 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1818 2022/11/28 12:41:06 - mmengine - INFO - Epoch(train) [11][900/1567] lr: 2.5794e-02 eta: 0:06:12 time: 0.0431 data_time: 0.0066 memory: 1793 loss: 0.1981 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1981 2022/11/28 12:41:11 - mmengine - INFO - Epoch(train) [11][1000/1567] lr: 2.5248e-02 eta: 0:06:07 time: 0.0453 data_time: 0.0063 memory: 1793 loss: 0.1558 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1558 2022/11/28 12:41:15 - mmengine - INFO - Epoch(train) [11][1100/1567] lr: 2.4706e-02 eta: 0:06:03 time: 0.0435 data_time: 0.0061 memory: 1793 loss: 0.1882 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1882 2022/11/28 12:41:19 - mmengine - INFO - Epoch(train) [11][1200/1567] lr: 2.4167e-02 eta: 0:05:59 time: 0.0447 data_time: 0.0068 memory: 1793 loss: 0.1846 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1846 2022/11/28 12:41:24 - mmengine - INFO - Epoch(train) [11][1300/1567] lr: 2.3633e-02 eta: 0:05:54 time: 0.0440 data_time: 0.0067 memory: 1793 loss: 0.2249 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2249 2022/11/28 12:41:25 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:41:28 - mmengine - INFO - Epoch(train) [11][1400/1567] lr: 2.3103e-02 eta: 0:05:50 time: 0.0443 data_time: 0.0068 memory: 1793 loss: 0.1541 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1541 2022/11/28 12:41:33 - mmengine - INFO - Epoch(train) [11][1500/1567] lr: 2.2577e-02 eta: 0:05:46 time: 0.0433 data_time: 0.0061 memory: 1793 loss: 0.1570 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1570 2022/11/28 12:41:36 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:41:36 - mmengine - INFO - Epoch(train) [11][1567/1567] lr: 2.2227e-02 eta: 0:05:43 time: 0.0426 data_time: 0.0065 memory: 1793 loss: 0.3311 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.3311 2022/11/28 12:41:36 - mmengine - INFO - Saving checkpoint at 11 epochs 2022/11/28 12:41:39 - mmengine - INFO - Epoch(val) [11][100/129] eta: 0:00:01 time: 0.0339 data_time: 0.0207 memory: 364 2022/11/28 12:41:41 - mmengine - INFO - Epoch(val) [11][129/129] acc/top1: 0.8094 acc/top5: 0.9591 acc/mean1: 0.8093 2022/11/28 12:41:41 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_10.pth is removed 2022/11/28 12:41:41 - mmengine - INFO - The best checkpoint with 0.8094 acc/top1 at 11 epoch is saved to best_acc/top1_epoch_11.pth. 2022/11/28 12:41:45 - mmengine - INFO - Epoch(train) [12][100/1567] lr: 2.1708e-02 eta: 0:05:38 time: 0.0436 data_time: 0.0067 memory: 1793 loss: 0.1809 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1809 2022/11/28 12:41:50 - mmengine - INFO - Epoch(train) [12][200/1567] lr: 2.1194e-02 eta: 0:05:34 time: 0.0434 data_time: 0.0062 memory: 1793 loss: 0.1671 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1671 2022/11/28 12:41:54 - mmengine - INFO - Epoch(train) [12][300/1567] lr: 2.0684e-02 eta: 0:05:30 time: 0.0439 data_time: 0.0062 memory: 1793 loss: 0.1513 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1513 2022/11/28 12:41:59 - mmengine - INFO - Epoch(train) [12][400/1567] lr: 2.0179e-02 eta: 0:05:25 time: 0.0440 data_time: 0.0061 memory: 1793 loss: 0.1477 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1477 2022/11/28 12:42:03 - mmengine - INFO - Epoch(train) [12][500/1567] lr: 1.9678e-02 eta: 0:05:21 time: 0.0435 data_time: 0.0062 memory: 1793 loss: 0.1454 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1454 2022/11/28 12:42:07 - mmengine - INFO - Epoch(train) [12][600/1567] lr: 1.9182e-02 eta: 0:05:16 time: 0.0434 data_time: 0.0062 memory: 1793 loss: 0.1520 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1520 2022/11/28 12:42:12 - mmengine - INFO - Epoch(train) [12][700/1567] lr: 1.8691e-02 eta: 0:05:12 time: 0.0434 data_time: 0.0061 memory: 1793 loss: 0.1520 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1520 2022/11/28 12:42:14 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:42:16 - mmengine - INFO - Epoch(train) [12][800/1567] lr: 1.8205e-02 eta: 0:05:08 time: 0.0435 data_time: 0.0066 memory: 1793 loss: 0.1723 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1723 2022/11/28 12:42:21 - mmengine - INFO - Epoch(train) [12][900/1567] lr: 1.7724e-02 eta: 0:05:03 time: 0.0444 data_time: 0.0069 memory: 1793 loss: 0.1029 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1029 2022/11/28 12:42:25 - mmengine - INFO - Epoch(train) [12][1000/1567] lr: 1.7248e-02 eta: 0:04:59 time: 0.0442 data_time: 0.0064 memory: 1793 loss: 0.1526 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1526 2022/11/28 12:42:29 - mmengine - INFO - Epoch(train) [12][1100/1567] lr: 1.6778e-02 eta: 0:04:55 time: 0.0440 data_time: 0.0063 memory: 1793 loss: 0.1722 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1722 2022/11/28 12:42:34 - mmengine - INFO - Epoch(train) [12][1200/1567] lr: 1.6312e-02 eta: 0:04:50 time: 0.0459 data_time: 0.0066 memory: 1793 loss: 0.1236 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1236 2022/11/28 12:42:38 - mmengine - INFO - Epoch(train) [12][1300/1567] lr: 1.5852e-02 eta: 0:04:46 time: 0.0438 data_time: 0.0062 memory: 1793 loss: 0.1035 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1035 2022/11/28 12:42:43 - mmengine - INFO - Epoch(train) [12][1400/1567] lr: 1.5397e-02 eta: 0:04:41 time: 0.0439 data_time: 0.0063 memory: 1793 loss: 0.1166 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1166 2022/11/28 12:42:47 - mmengine - INFO - Epoch(train) [12][1500/1567] lr: 1.4947e-02 eta: 0:04:37 time: 0.0449 data_time: 0.0070 memory: 1793 loss: 0.1124 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1124 2022/11/28 12:42:50 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:42:50 - mmengine - INFO - Epoch(train) [12][1567/1567] lr: 1.4649e-02 eta: 0:04:34 time: 0.0432 data_time: 0.0059 memory: 1793 loss: 0.2795 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.2795 2022/11/28 12:42:50 - mmengine - INFO - Saving checkpoint at 12 epochs 2022/11/28 12:42:54 - mmengine - INFO - Epoch(val) [12][100/129] eta: 0:00:01 time: 0.0343 data_time: 0.0209 memory: 364 2022/11/28 12:42:55 - mmengine - INFO - Epoch(val) [12][129/129] acc/top1: 0.8261 acc/top5: 0.9648 acc/mean1: 0.8260 2022/11/28 12:42:55 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_11.pth is removed 2022/11/28 12:42:55 - mmengine - INFO - The best checkpoint with 0.8261 acc/top1 at 12 epoch is saved to best_acc/top1_epoch_12.pth. 2022/11/28 12:43:00 - mmengine - INFO - Epoch(train) [13][100/1567] lr: 1.4209e-02 eta: 0:04:30 time: 0.0438 data_time: 0.0060 memory: 1793 loss: 0.1163 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1163 2022/11/28 12:43:04 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:43:04 - mmengine - INFO - Epoch(train) [13][200/1567] lr: 1.3774e-02 eta: 0:04:25 time: 0.0429 data_time: 0.0062 memory: 1793 loss: 0.0993 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0993 2022/11/28 12:43:09 - mmengine - INFO - Epoch(train) [13][300/1567] lr: 1.3345e-02 eta: 0:04:21 time: 0.0442 data_time: 0.0064 memory: 1793 loss: 0.0934 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0934 2022/11/28 12:43:13 - mmengine - INFO - Epoch(train) [13][400/1567] lr: 1.2922e-02 eta: 0:04:17 time: 0.0448 data_time: 0.0061 memory: 1793 loss: 0.1242 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1242 2022/11/28 12:43:18 - mmengine - INFO - Epoch(train) [13][500/1567] lr: 1.2505e-02 eta: 0:04:12 time: 0.0487 data_time: 0.0062 memory: 1793 loss: 0.1012 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1012 2022/11/28 12:43:22 - mmengine - INFO - Epoch(train) [13][600/1567] lr: 1.2093e-02 eta: 0:04:08 time: 0.0442 data_time: 0.0062 memory: 1793 loss: 0.0650 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0650 2022/11/28 12:43:27 - mmengine - INFO - Epoch(train) [13][700/1567] lr: 1.1687e-02 eta: 0:04:04 time: 0.0437 data_time: 0.0062 memory: 1793 loss: 0.0662 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0662 2022/11/28 12:43:31 - mmengine - INFO - Epoch(train) [13][800/1567] lr: 1.1288e-02 eta: 0:03:59 time: 0.0435 data_time: 0.0062 memory: 1793 loss: 0.0734 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0734 2022/11/28 12:43:35 - mmengine - INFO - Epoch(train) [13][900/1567] lr: 1.0894e-02 eta: 0:03:55 time: 0.0437 data_time: 0.0066 memory: 1793 loss: 0.0992 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.0992 2022/11/28 12:43:40 - mmengine - INFO - Epoch(train) [13][1000/1567] lr: 1.0507e-02 eta: 0:03:51 time: 0.0441 data_time: 0.0063 memory: 1793 loss: 0.0851 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0851 2022/11/28 12:43:44 - mmengine - INFO - Epoch(train) [13][1100/1567] lr: 1.0126e-02 eta: 0:03:46 time: 0.0436 data_time: 0.0065 memory: 1793 loss: 0.0911 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0911 2022/11/28 12:43:49 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:43:49 - mmengine - INFO - Epoch(train) [13][1200/1567] lr: 9.7512e-03 eta: 0:03:42 time: 0.0443 data_time: 0.0064 memory: 1793 loss: 0.0774 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0774 2022/11/28 12:43:53 - mmengine - INFO - Epoch(train) [13][1300/1567] lr: 9.3826e-03 eta: 0:03:37 time: 0.0436 data_time: 0.0062 memory: 1793 loss: 0.0883 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0883 2022/11/28 12:43:58 - mmengine - INFO - Epoch(train) [13][1400/1567] lr: 9.0204e-03 eta: 0:03:33 time: 0.0439 data_time: 0.0062 memory: 1793 loss: 0.0711 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0711 2022/11/28 12:44:02 - mmengine - INFO - Epoch(train) [13][1500/1567] lr: 8.6647e-03 eta: 0:03:29 time: 0.0440 data_time: 0.0065 memory: 1793 loss: 0.0550 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0550 2022/11/28 12:44:05 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:44:05 - mmengine - INFO - Epoch(train) [13][1567/1567] lr: 8.4300e-03 eta: 0:03:26 time: 0.0428 data_time: 0.0061 memory: 1793 loss: 0.2009 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.2009 2022/11/28 12:44:05 - mmengine - INFO - Saving checkpoint at 13 epochs 2022/11/28 12:44:09 - mmengine - INFO - Epoch(val) [13][100/129] eta: 0:00:01 time: 0.0341 data_time: 0.0208 memory: 364 2022/11/28 12:44:10 - mmengine - INFO - Epoch(val) [13][129/129] acc/top1: 0.8329 acc/top5: 0.9658 acc/mean1: 0.8328 2022/11/28 12:44:10 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_12.pth is removed 2022/11/28 12:44:10 - mmengine - INFO - The best checkpoint with 0.8329 acc/top1 at 13 epoch is saved to best_acc/top1_epoch_13.pth. 2022/11/28 12:44:15 - mmengine - INFO - Epoch(train) [14][100/1567] lr: 8.0851e-03 eta: 0:03:21 time: 0.0461 data_time: 0.0083 memory: 1793 loss: 0.0606 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.0606 2022/11/28 12:44:19 - mmengine - INFO - Epoch(train) [14][200/1567] lr: 7.7469e-03 eta: 0:03:17 time: 0.0463 data_time: 0.0087 memory: 1793 loss: 0.0772 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0772 2022/11/28 12:44:24 - mmengine - INFO - Epoch(train) [14][300/1567] lr: 7.4152e-03 eta: 0:03:13 time: 0.0457 data_time: 0.0062 memory: 1793 loss: 0.0382 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0382 2022/11/28 12:44:28 - mmengine - INFO - Epoch(train) [14][400/1567] lr: 7.0902e-03 eta: 0:03:08 time: 0.0433 data_time: 0.0061 memory: 1793 loss: 0.0946 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0946 2022/11/28 12:44:33 - mmengine - INFO - Epoch(train) [14][500/1567] lr: 6.7720e-03 eta: 0:03:04 time: 0.0442 data_time: 0.0062 memory: 1793 loss: 0.0586 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0586 2022/11/28 12:44:37 - mmengine - INFO - Epoch(train) [14][600/1567] lr: 6.4606e-03 eta: 0:02:59 time: 0.0434 data_time: 0.0061 memory: 1793 loss: 0.0631 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0631 2022/11/28 12:44:38 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:44:42 - mmengine - INFO - Epoch(train) [14][700/1567] lr: 6.1560e-03 eta: 0:02:55 time: 0.0437 data_time: 0.0063 memory: 1793 loss: 0.0380 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0380 2022/11/28 12:44:46 - mmengine - INFO - Epoch(train) [14][800/1567] lr: 5.8582e-03 eta: 0:02:51 time: 0.0438 data_time: 0.0069 memory: 1793 loss: 0.0273 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0273 2022/11/28 12:44:50 - mmengine - INFO - Epoch(train) [14][900/1567] lr: 5.5675e-03 eta: 0:02:46 time: 0.0443 data_time: 0.0062 memory: 1793 loss: 0.0352 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0352 2022/11/28 12:44:55 - mmengine - INFO - Epoch(train) [14][1000/1567] lr: 5.2836e-03 eta: 0:02:42 time: 0.0458 data_time: 0.0062 memory: 1793 loss: 0.0362 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0362 2022/11/28 12:44:59 - mmengine - INFO - Epoch(train) [14][1100/1567] lr: 5.0068e-03 eta: 0:02:38 time: 0.0440 data_time: 0.0062 memory: 1793 loss: 0.0348 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0348 2022/11/28 12:45:04 - mmengine - INFO - Epoch(train) [14][1200/1567] lr: 4.7371e-03 eta: 0:02:33 time: 0.0442 data_time: 0.0074 memory: 1793 loss: 0.0234 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0234 2022/11/28 12:45:08 - mmengine - INFO - Epoch(train) [14][1300/1567] lr: 4.4745e-03 eta: 0:02:29 time: 0.0437 data_time: 0.0063 memory: 1793 loss: 0.0350 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0350 2022/11/28 12:45:13 - mmengine - INFO - Epoch(train) [14][1400/1567] lr: 4.2190e-03 eta: 0:02:24 time: 0.0438 data_time: 0.0064 memory: 1793 loss: 0.0348 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0348 2022/11/28 12:45:17 - mmengine - INFO - Epoch(train) [14][1500/1567] lr: 3.9707e-03 eta: 0:02:20 time: 0.0438 data_time: 0.0062 memory: 1793 loss: 0.0510 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0510 2022/11/28 12:45:20 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:45:20 - mmengine - INFO - Epoch(train) [14][1567/1567] lr: 3.8084e-03 eta: 0:02:17 time: 0.0425 data_time: 0.0061 memory: 1793 loss: 0.1814 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.1814 2022/11/28 12:45:20 - mmengine - INFO - Saving checkpoint at 14 epochs 2022/11/28 12:45:24 - mmengine - INFO - Epoch(val) [14][100/129] eta: 0:00:01 time: 0.0338 data_time: 0.0205 memory: 364 2022/11/28 12:45:25 - mmengine - INFO - Epoch(val) [14][129/129] acc/top1: 0.8422 acc/top5: 0.9676 acc/mean1: 0.8421 2022/11/28 12:45:25 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_13.pth is removed 2022/11/28 12:45:26 - mmengine - INFO - The best checkpoint with 0.8422 acc/top1 at 14 epoch is saved to best_acc/top1_epoch_14.pth. 2022/11/28 12:45:28 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:45:30 - mmengine - INFO - Epoch(train) [15][100/1567] lr: 3.5722e-03 eta: 0:02:13 time: 0.0435 data_time: 0.0062 memory: 1793 loss: 0.0253 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0253 2022/11/28 12:45:34 - mmengine - INFO - Epoch(train) [15][200/1567] lr: 3.3433e-03 eta: 0:02:08 time: 0.0435 data_time: 0.0061 memory: 1793 loss: 0.0266 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0266 2022/11/28 12:45:39 - mmengine - INFO - Epoch(train) [15][300/1567] lr: 3.1217e-03 eta: 0:02:04 time: 0.0452 data_time: 0.0073 memory: 1793 loss: 0.0161 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0161 2022/11/28 12:45:43 - mmengine - INFO - Epoch(train) [15][400/1567] lr: 2.9075e-03 eta: 0:02:00 time: 0.0436 data_time: 0.0062 memory: 1793 loss: 0.0319 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0319 2022/11/28 12:45:48 - mmengine - INFO - Epoch(train) [15][500/1567] lr: 2.7007e-03 eta: 0:01:55 time: 0.0442 data_time: 0.0069 memory: 1793 loss: 0.0361 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0361 2022/11/28 12:45:52 - mmengine - INFO - Epoch(train) [15][600/1567] lr: 2.5013e-03 eta: 0:01:51 time: 0.0468 data_time: 0.0062 memory: 1793 loss: 0.0282 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0282 2022/11/28 12:45:57 - mmengine - INFO - Epoch(train) [15][700/1567] lr: 2.3093e-03 eta: 0:01:46 time: 0.0437 data_time: 0.0064 memory: 1793 loss: 0.0155 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0155 2022/11/28 12:46:01 - mmengine - INFO - Epoch(train) [15][800/1567] lr: 2.1249e-03 eta: 0:01:42 time: 0.0434 data_time: 0.0061 memory: 1793 loss: 0.0337 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0337 2022/11/28 12:46:06 - mmengine - INFO - Epoch(train) [15][900/1567] lr: 1.9479e-03 eta: 0:01:38 time: 0.0437 data_time: 0.0063 memory: 1793 loss: 0.0377 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0377 2022/11/28 12:46:10 - mmengine - INFO - Epoch(train) [15][1000/1567] lr: 1.7785e-03 eta: 0:01:33 time: 0.0431 data_time: 0.0062 memory: 1793 loss: 0.0206 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0206 2022/11/28 12:46:13 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:46:14 - mmengine - INFO - Epoch(train) [15][1100/1567] lr: 1.6167e-03 eta: 0:01:29 time: 0.0435 data_time: 0.0061 memory: 1793 loss: 0.0192 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0192 2022/11/28 12:46:19 - mmengine - INFO - Epoch(train) [15][1200/1567] lr: 1.4625e-03 eta: 0:01:24 time: 0.0437 data_time: 0.0063 memory: 1793 loss: 0.0367 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0367 2022/11/28 12:46:23 - mmengine - INFO - Epoch(train) [15][1300/1567] lr: 1.3159e-03 eta: 0:01:20 time: 0.0432 data_time: 0.0062 memory: 1793 loss: 0.0231 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0231 2022/11/28 12:46:28 - mmengine - INFO - Epoch(train) [15][1400/1567] lr: 1.1769e-03 eta: 0:01:16 time: 0.0449 data_time: 0.0061 memory: 1793 loss: 0.0227 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0227 2022/11/28 12:46:32 - mmengine - INFO - Epoch(train) [15][1500/1567] lr: 1.0456e-03 eta: 0:01:11 time: 0.0444 data_time: 0.0067 memory: 1793 loss: 0.0181 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0181 2022/11/28 12:46:35 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:46:35 - mmengine - INFO - Epoch(train) [15][1567/1567] lr: 9.6196e-04 eta: 0:01:08 time: 0.0423 data_time: 0.0060 memory: 1793 loss: 0.1884 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.1884 2022/11/28 12:46:35 - mmengine - INFO - Saving checkpoint at 15 epochs 2022/11/28 12:46:39 - mmengine - INFO - Epoch(val) [15][100/129] eta: 0:00:00 time: 0.0337 data_time: 0.0203 memory: 364 2022/11/28 12:46:40 - mmengine - INFO - Epoch(val) [15][129/129] acc/top1: 0.8512 acc/top5: 0.9703 acc/mean1: 0.8511 2022/11/28 12:46:40 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_14.pth is removed 2022/11/28 12:46:40 - mmengine - INFO - The best checkpoint with 0.8512 acc/top1 at 15 epoch is saved to best_acc/top1_epoch_15.pth. 2022/11/28 12:46:45 - mmengine - INFO - Epoch(train) [16][100/1567] lr: 8.4351e-04 eta: 0:01:04 time: 0.0441 data_time: 0.0062 memory: 1793 loss: 0.0344 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0344 2022/11/28 12:46:49 - mmengine - INFO - Epoch(train) [16][200/1567] lr: 7.3277e-04 eta: 0:01:00 time: 0.0436 data_time: 0.0063 memory: 1793 loss: 0.0177 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0177 2022/11/28 12:46:53 - mmengine - INFO - Epoch(train) [16][300/1567] lr: 6.2978e-04 eta: 0:00:55 time: 0.0447 data_time: 0.0062 memory: 1793 loss: 0.0256 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0256 2022/11/28 12:46:58 - mmengine - INFO - Epoch(train) [16][400/1567] lr: 5.3453e-04 eta: 0:00:51 time: 0.0437 data_time: 0.0062 memory: 1793 loss: 0.0198 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0198 2022/11/28 12:47:02 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:47:02 - mmengine - INFO - Epoch(train) [16][500/1567] lr: 4.4705e-04 eta: 0:00:46 time: 0.0444 data_time: 0.0063 memory: 1793 loss: 0.0293 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0293 2022/11/28 12:47:07 - mmengine - INFO - Epoch(train) [16][600/1567] lr: 3.6735e-04 eta: 0:00:42 time: 0.0442 data_time: 0.0062 memory: 1793 loss: 0.0316 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0316 2022/11/28 12:47:11 - mmengine - INFO - Epoch(train) [16][700/1567] lr: 2.9544e-04 eta: 0:00:38 time: 0.0436 data_time: 0.0062 memory: 1793 loss: 0.0122 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0122 2022/11/28 12:47:16 - mmengine - INFO - Epoch(train) [16][800/1567] lr: 2.3134e-04 eta: 0:00:33 time: 0.0434 data_time: 0.0062 memory: 1793 loss: 0.0228 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0228 2022/11/28 12:47:20 - mmengine - INFO - Epoch(train) [16][900/1567] lr: 1.7505e-04 eta: 0:00:29 time: 0.0434 data_time: 0.0062 memory: 1793 loss: 0.0136 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0136 2022/11/28 12:47:24 - mmengine - INFO - Epoch(train) [16][1000/1567] lr: 1.2658e-04 eta: 0:00:24 time: 0.0457 data_time: 0.0062 memory: 1793 loss: 0.0301 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0301 2022/11/28 12:47:29 - mmengine - INFO - Epoch(train) [16][1100/1567] lr: 8.5947e-05 eta: 0:00:20 time: 0.0439 data_time: 0.0062 memory: 1793 loss: 0.0291 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0291 2022/11/28 12:47:33 - mmengine - INFO - Epoch(train) [16][1200/1567] lr: 5.3147e-05 eta: 0:00:16 time: 0.0442 data_time: 0.0062 memory: 1793 loss: 0.0213 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0213 2022/11/28 12:47:37 - mmengine - INFO - Epoch(train) [16][1300/1567] lr: 2.8190e-05 eta: 0:00:11 time: 0.0434 data_time: 0.0061 memory: 1793 loss: 0.0280 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0280 2022/11/28 12:47:42 - mmengine - INFO - Epoch(train) [16][1400/1567] lr: 1.1078e-05 eta: 0:00:07 time: 0.0442 data_time: 0.0064 memory: 1793 loss: 0.0455 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0455 2022/11/28 12:47:46 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:47:46 - mmengine - INFO - Epoch(train) [16][1500/1567] lr: 1.8150e-06 eta: 0:00:02 time: 0.0435 data_time: 0.0062 memory: 1793 loss: 0.0178 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0178 2022/11/28 12:47:49 - mmengine - INFO - Exp name: stgcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221128_122723 2022/11/28 12:47:49 - mmengine - INFO - Epoch(train) [16][1567/1567] lr: 3.9252e-10 eta: 0:00:00 time: 0.0427 data_time: 0.0062 memory: 1793 loss: 0.1571 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1571 2022/11/28 12:47:49 - mmengine - INFO - Saving checkpoint at 16 epochs 2022/11/28 12:47:53 - mmengine - INFO - Epoch(val) [16][100/129] eta: 0:00:00 time: 0.0334 data_time: 0.0203 memory: 364 2022/11/28 12:47:54 - mmengine - INFO - Epoch(val) [16][129/129] acc/top1: 0.8467 acc/top5: 0.9702 acc/mean1: 0.8466