2022/11/29 20:01:39 - 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: 647774005 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 ------------------------------------------------------------ 2022/11/29 20:01:39 - 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='coco', mode='stgcn_spatial')), cls_head=dict(type='GCNHead', num_classes=60, in_channels=256)) dataset_type = 'PoseDataset' ann_file = 'data/skeleton/ntu60_2d.pkl' train_pipeline = [ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['j']), dict(type='UniformSampleFrames', clip_len=100), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ] val_pipeline = [ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', 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='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', 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_2d.pkl', pipeline=[ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', 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_2d.pkl', pipeline=[ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', 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_2d.pkl', pipeline=[ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', 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 = 'pytorch' work_dir = './work_dirs/stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d' randomness = dict(seed=None, diff_rank_seed=False, deterministic=False) 2022/11/29 20:01:39 - mmengine - INFO - Result has been saved to /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/modules_statistic_results.json Name of parameter - Initialization information data_bn.weight - torch.Size([51]): The value is the same before and after calling `init_weights` of STGCN data_bn.bias - torch.Size([51]): The value is the same before and after calling `init_weights` of STGCN gcn.0.gcn.PA - torch.Size([3, 17, 17]): 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, 17, 17]): 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, 17, 17]): 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, 17, 17]): 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, 17, 17]): 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, 17, 17]): 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, 17, 17]): 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, 17, 17]): 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, 17, 17]): 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, 17, 17]): 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 2022/11/29 20:02:11 - mmengine - INFO - Checkpoints will be saved to /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d. 2022/11/29 20:02:17 - mmengine - INFO - Epoch(train) [1][100/1567] lr: 9.9996e-02 eta: 0:26:05 time: 0.0341 data_time: 0.0067 memory: 1253 loss: 2.7610 top1_acc: 0.1875 top5_acc: 0.3125 loss_cls: 2.7610 2022/11/29 20:02:21 - mmengine - INFO - Epoch(train) [1][200/1567] lr: 9.9984e-02 eta: 0:20:11 time: 0.0347 data_time: 0.0068 memory: 1253 loss: 2.0631 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.0631 2022/11/29 20:02:24 - mmengine - INFO - Epoch(train) [1][300/1567] lr: 9.9965e-02 eta: 0:18:13 time: 0.0350 data_time: 0.0078 memory: 1253 loss: 1.7869 top1_acc: 0.3125 top5_acc: 0.8125 loss_cls: 1.7869 2022/11/29 20:02:28 - mmengine - INFO - Epoch(train) [1][400/1567] lr: 9.9938e-02 eta: 0:17:11 time: 0.0350 data_time: 0.0075 memory: 1253 loss: 1.4692 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 1.4692 2022/11/29 20:02:31 - mmengine - INFO - Epoch(train) [1][500/1567] lr: 9.9902e-02 eta: 0:16:33 time: 0.0350 data_time: 0.0079 memory: 1253 loss: 1.1935 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.1935 2022/11/29 20:02:35 - mmengine - INFO - Epoch(train) [1][600/1567] lr: 9.9859e-02 eta: 0:16:06 time: 0.0344 data_time: 0.0067 memory: 1253 loss: 1.0898 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0898 2022/11/29 20:02:38 - mmengine - INFO - Epoch(train) [1][700/1567] lr: 9.9808e-02 eta: 0:15:45 time: 0.0344 data_time: 0.0069 memory: 1253 loss: 0.9859 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.9859 2022/11/29 20:02:42 - mmengine - INFO - Epoch(train) [1][800/1567] lr: 9.9750e-02 eta: 0:15:27 time: 0.0341 data_time: 0.0062 memory: 1253 loss: 0.9657 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.9657 2022/11/29 20:02:45 - mmengine - INFO - Epoch(train) [1][900/1567] lr: 9.9683e-02 eta: 0:15:12 time: 0.0341 data_time: 0.0062 memory: 1253 loss: 0.8800 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.8800 2022/11/29 20:02:49 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:02:49 - mmengine - INFO - Epoch(train) [1][1000/1567] lr: 9.9609e-02 eta: 0:15:00 time: 0.0335 data_time: 0.0061 memory: 1253 loss: 0.8588 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.8588 2022/11/29 20:02:52 - mmengine - INFO - Epoch(train) [1][1100/1567] lr: 9.9527e-02 eta: 0:14:52 time: 0.0343 data_time: 0.0064 memory: 1253 loss: 0.6901 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.6901 2022/11/29 20:02:56 - mmengine - INFO - Epoch(train) [1][1200/1567] lr: 9.9437e-02 eta: 0:14:42 time: 0.0338 data_time: 0.0061 memory: 1253 loss: 0.7632 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.7632 2022/11/29 20:02:59 - mmengine - INFO - Epoch(train) [1][1300/1567] lr: 9.9339e-02 eta: 0:14:33 time: 0.0338 data_time: 0.0062 memory: 1253 loss: 0.6814 top1_acc: 0.4375 top5_acc: 1.0000 loss_cls: 0.6814 2022/11/29 20:03:02 - mmengine - INFO - Epoch(train) [1][1400/1567] lr: 9.9234e-02 eta: 0:14:24 time: 0.0338 data_time: 0.0061 memory: 1253 loss: 0.7012 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.7012 2022/11/29 20:03:06 - mmengine - INFO - Epoch(train) [1][1500/1567] lr: 9.9121e-02 eta: 0:14:17 time: 0.0339 data_time: 0.0062 memory: 1253 loss: 0.6382 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.6382 2022/11/29 20:03:08 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:03:08 - mmengine - INFO - Epoch(train) [1][1567/1567] lr: 9.9040e-02 eta: 0:14:12 time: 0.0354 data_time: 0.0060 memory: 1253 loss: 0.7594 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.7594 2022/11/29 20:03:08 - mmengine - INFO - Saving checkpoint at 1 epochs 2022/11/29 20:03:10 - mmengine - INFO - Epoch(val) [1][100/129] eta: 0:00:00 time: 0.0165 data_time: 0.0071 memory: 262 2022/11/29 20:03:11 - mmengine - INFO - Epoch(val) [1][129/129] acc/top1: 0.5511 acc/top5: 0.9314 acc/mean1: 0.5508 2022/11/29 20:03:11 - mmengine - INFO - The best checkpoint with 0.5511 acc/top1 at 1 epoch is saved to best_acc/top1_epoch_1.pth. 2022/11/29 20:03:15 - mmengine - INFO - Epoch(train) [2][100/1567] lr: 9.8914e-02 eta: 0:14:07 time: 0.0340 data_time: 0.0062 memory: 1253 loss: 0.6937 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.6937 2022/11/29 20:03:18 - mmengine - INFO - Epoch(train) [2][200/1567] lr: 9.8781e-02 eta: 0:14:00 time: 0.0337 data_time: 0.0061 memory: 1253 loss: 0.6279 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6279 2022/11/29 20:03:21 - mmengine - INFO - Epoch(train) [2][300/1567] lr: 9.8639e-02 eta: 0:13:54 time: 0.0345 data_time: 0.0062 memory: 1253 loss: 0.6486 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.6486 2022/11/29 20:03:25 - mmengine - INFO - Epoch(train) [2][400/1567] lr: 9.8491e-02 eta: 0:13:48 time: 0.0336 data_time: 0.0062 memory: 1253 loss: 0.6338 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.6338 2022/11/29 20:03:26 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:03:28 - mmengine - INFO - Epoch(train) [2][500/1567] lr: 9.8334e-02 eta: 0:13:42 time: 0.0337 data_time: 0.0061 memory: 1253 loss: 0.4775 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4775 2022/11/29 20:03:32 - mmengine - INFO - Epoch(train) [2][600/1567] lr: 9.8170e-02 eta: 0:13:36 time: 0.0338 data_time: 0.0062 memory: 1253 loss: 0.4943 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.4943 2022/11/29 20:03:35 - mmengine - INFO - Epoch(train) [2][700/1567] lr: 9.7998e-02 eta: 0:13:31 time: 0.0348 data_time: 0.0062 memory: 1253 loss: 0.6287 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.6287 2022/11/29 20:03:38 - mmengine - INFO - Epoch(train) [2][800/1567] lr: 9.7819e-02 eta: 0:13:27 time: 0.0342 data_time: 0.0065 memory: 1253 loss: 0.5265 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5265 2022/11/29 20:03:42 - mmengine - INFO - Epoch(train) [2][900/1567] lr: 9.7632e-02 eta: 0:13:22 time: 0.0340 data_time: 0.0061 memory: 1253 loss: 0.5788 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.5788 2022/11/29 20:03:45 - mmengine - INFO - Epoch(train) [2][1000/1567] lr: 9.7438e-02 eta: 0:13:17 time: 0.0346 data_time: 0.0073 memory: 1253 loss: 0.5720 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5720 2022/11/29 20:03:49 - mmengine - INFO - Epoch(train) [2][1100/1567] lr: 9.7236e-02 eta: 0:13:12 time: 0.0335 data_time: 0.0061 memory: 1253 loss: 0.5705 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5705 2022/11/29 20:03:52 - mmengine - INFO - Epoch(train) [2][1200/1567] lr: 9.7027e-02 eta: 0:13:08 time: 0.0347 data_time: 0.0062 memory: 1253 loss: 0.4888 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4888 2022/11/29 20:03:56 - mmengine - INFO - Epoch(train) [2][1300/1567] lr: 9.6810e-02 eta: 0:13:04 time: 0.0338 data_time: 0.0061 memory: 1253 loss: 0.4743 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4743 2022/11/29 20:03:59 - mmengine - INFO - Epoch(train) [2][1400/1567] lr: 9.6587e-02 eta: 0:13:00 time: 0.0344 data_time: 0.0072 memory: 1253 loss: 0.4445 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4445 2022/11/29 20:04:00 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:04:02 - mmengine - INFO - Epoch(train) [2][1500/1567] lr: 9.6355e-02 eta: 0:12:55 time: 0.0338 data_time: 0.0061 memory: 1253 loss: 0.5247 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5247 2022/11/29 20:04:05 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:04:05 - mmengine - INFO - Epoch(train) [2][1567/1567] lr: 9.6196e-02 eta: 0:12:52 time: 0.0341 data_time: 0.0062 memory: 1253 loss: 0.4769 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.4769 2022/11/29 20:04:05 - mmengine - INFO - Saving checkpoint at 2 epochs 2022/11/29 20:04:07 - mmengine - INFO - Epoch(val) [2][100/129] eta: 0:00:00 time: 0.0150 data_time: 0.0059 memory: 262 2022/11/29 20:04:07 - mmengine - INFO - Epoch(val) [2][129/129] acc/top1: 0.7180 acc/top5: 0.9608 acc/mean1: 0.7179 2022/11/29 20:04:07 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_1.pth is removed 2022/11/29 20:04:08 - mmengine - INFO - The best checkpoint with 0.7180 acc/top1 at 2 epoch is saved to best_acc/top1_epoch_2.pth. 2022/11/29 20:04:11 - mmengine - INFO - Epoch(train) [3][100/1567] lr: 9.5953e-02 eta: 0:12:49 time: 0.0349 data_time: 0.0068 memory: 1253 loss: 0.4676 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4676 2022/11/29 20:04:15 - mmengine - INFO - Epoch(train) [3][200/1567] lr: 9.5703e-02 eta: 0:12:45 time: 0.0339 data_time: 0.0063 memory: 1253 loss: 0.5194 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5194 2022/11/29 20:04:18 - mmengine - INFO - Epoch(train) [3][300/1567] lr: 9.5445e-02 eta: 0:12:41 time: 0.0345 data_time: 0.0062 memory: 1253 loss: 0.4516 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.4516 2022/11/29 20:04:22 - mmengine - INFO - Epoch(train) [3][400/1567] lr: 9.5180e-02 eta: 0:12:37 time: 0.0341 data_time: 0.0062 memory: 1253 loss: 0.4957 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4957 2022/11/29 20:04:25 - mmengine - INFO - Epoch(train) [3][500/1567] lr: 9.4908e-02 eta: 0:12:33 time: 0.0337 data_time: 0.0062 memory: 1253 loss: 0.4649 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4649 2022/11/29 20:04:29 - mmengine - INFO - Epoch(train) [3][600/1567] lr: 9.4629e-02 eta: 0:12:29 time: 0.0345 data_time: 0.0063 memory: 1253 loss: 0.4743 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4743 2022/11/29 20:04:32 - mmengine - INFO - Epoch(train) [3][700/1567] lr: 9.4343e-02 eta: 0:12:25 time: 0.0339 data_time: 0.0062 memory: 1253 loss: 0.4953 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.4953 2022/11/29 20:04:35 - mmengine - INFO - Epoch(train) [3][800/1567] lr: 9.4050e-02 eta: 0:12:21 time: 0.0349 data_time: 0.0064 memory: 1253 loss: 0.3875 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3875 2022/11/29 20:04:38 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:04:39 - mmengine - INFO - Epoch(train) [3][900/1567] lr: 9.3750e-02 eta: 0:12:17 time: 0.0338 data_time: 0.0062 memory: 1253 loss: 0.4279 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4279 2022/11/29 20:04:42 - mmengine - INFO - Epoch(train) [3][1000/1567] lr: 9.3444e-02 eta: 0:12:13 time: 0.0336 data_time: 0.0062 memory: 1253 loss: 0.4471 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4471 2022/11/29 20:04:46 - mmengine - INFO - Epoch(train) [3][1100/1567] lr: 9.3130e-02 eta: 0:12:09 time: 0.0338 data_time: 0.0063 memory: 1253 loss: 0.4611 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4611 2022/11/29 20:04:49 - mmengine - INFO - Epoch(train) [3][1200/1567] lr: 9.2810e-02 eta: 0:12:05 time: 0.0348 data_time: 0.0062 memory: 1253 loss: 0.4446 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4446 2022/11/29 20:04:52 - mmengine - INFO - Epoch(train) [3][1300/1567] lr: 9.2483e-02 eta: 0:12:02 time: 0.0346 data_time: 0.0062 memory: 1253 loss: 0.4297 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4297 2022/11/29 20:04:56 - mmengine - INFO - Epoch(train) [3][1400/1567] lr: 9.2149e-02 eta: 0:11:58 time: 0.0342 data_time: 0.0063 memory: 1253 loss: 0.5381 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.5381 2022/11/29 20:04:59 - mmengine - INFO - Epoch(train) [3][1500/1567] lr: 9.1809e-02 eta: 0:11:54 time: 0.0334 data_time: 0.0063 memory: 1253 loss: 0.4786 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4786 2022/11/29 20:05:02 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:05:02 - mmengine - INFO - Epoch(train) [3][1567/1567] lr: 9.1577e-02 eta: 0:11:51 time: 0.0332 data_time: 0.0060 memory: 1253 loss: 0.5436 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.5436 2022/11/29 20:05:02 - mmengine - INFO - Saving checkpoint at 3 epochs 2022/11/29 20:05:03 - mmengine - INFO - Epoch(val) [3][100/129] eta: 0:00:00 time: 0.0150 data_time: 0.0058 memory: 262 2022/11/29 20:05:04 - mmengine - INFO - Epoch(val) [3][129/129] acc/top1: 0.6522 acc/top5: 0.9307 acc/mean1: 0.6523 2022/11/29 20:05:08 - mmengine - INFO - Epoch(train) [4][100/1567] lr: 9.1226e-02 eta: 0:11:48 time: 0.0348 data_time: 0.0062 memory: 1253 loss: 0.4601 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4601 2022/11/29 20:05:11 - mmengine - INFO - Epoch(train) [4][200/1567] lr: 9.0868e-02 eta: 0:11:44 time: 0.0335 data_time: 0.0062 memory: 1253 loss: 0.4021 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4021 2022/11/29 20:05:14 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:05:14 - mmengine - INFO - Epoch(train) [4][300/1567] lr: 9.0504e-02 eta: 0:11:40 time: 0.0336 data_time: 0.0063 memory: 1253 loss: 0.4340 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4340 2022/11/29 20:05:18 - mmengine - INFO - Epoch(train) [4][400/1567] lr: 9.0133e-02 eta: 0:11:36 time: 0.0335 data_time: 0.0062 memory: 1253 loss: 0.4546 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4546 2022/11/29 20:05:21 - mmengine - INFO - Epoch(train) [4][500/1567] lr: 8.9756e-02 eta: 0:11:33 time: 0.0352 data_time: 0.0070 memory: 1253 loss: 0.3652 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3652 2022/11/29 20:05:25 - mmengine - INFO - Epoch(train) [4][600/1567] lr: 8.9373e-02 eta: 0:11:29 time: 0.0343 data_time: 0.0063 memory: 1253 loss: 0.4662 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4662 2022/11/29 20:05:28 - mmengine - INFO - Epoch(train) [4][700/1567] lr: 8.8984e-02 eta: 0:11:25 time: 0.0349 data_time: 0.0062 memory: 1253 loss: 0.3960 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3960 2022/11/29 20:05:32 - mmengine - INFO - Epoch(train) [4][800/1567] lr: 8.8589e-02 eta: 0:11:22 time: 0.0346 data_time: 0.0063 memory: 1253 loss: 0.4187 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4187 2022/11/29 20:05:35 - mmengine - INFO - Epoch(train) [4][900/1567] lr: 8.8187e-02 eta: 0:11:18 time: 0.0353 data_time: 0.0063 memory: 1253 loss: 0.4003 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4003 2022/11/29 20:05:38 - mmengine - INFO - Epoch(train) [4][1000/1567] lr: 8.7780e-02 eta: 0:11:14 time: 0.0338 data_time: 0.0064 memory: 1253 loss: 0.3597 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3597 2022/11/29 20:05:42 - mmengine - INFO - Epoch(train) [4][1100/1567] lr: 8.7367e-02 eta: 0:11:11 time: 0.0339 data_time: 0.0066 memory: 1253 loss: 0.3485 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3485 2022/11/29 20:05:45 - mmengine - INFO - Epoch(train) [4][1200/1567] lr: 8.6947e-02 eta: 0:11:07 time: 0.0338 data_time: 0.0065 memory: 1253 loss: 0.4264 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4264 2022/11/29 20:05:49 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:05:49 - mmengine - INFO - Epoch(train) [4][1300/1567] lr: 8.6522e-02 eta: 0:11:03 time: 0.0337 data_time: 0.0066 memory: 1253 loss: 0.3283 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.3283 2022/11/29 20:05:52 - mmengine - INFO - Epoch(train) [4][1400/1567] lr: 8.6092e-02 eta: 0:11:00 time: 0.0350 data_time: 0.0062 memory: 1253 loss: 0.3448 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3448 2022/11/29 20:05:56 - mmengine - INFO - Epoch(train) [4][1500/1567] lr: 8.5655e-02 eta: 0:10:56 time: 0.0342 data_time: 0.0063 memory: 1253 loss: 0.3529 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3529 2022/11/29 20:05:58 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:05:58 - mmengine - INFO - Epoch(train) [4][1567/1567] lr: 8.5360e-02 eta: 0:10:53 time: 0.0338 data_time: 0.0059 memory: 1253 loss: 0.6070 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.6070 2022/11/29 20:05:58 - mmengine - INFO - Saving checkpoint at 4 epochs 2022/11/29 20:06:00 - mmengine - INFO - Epoch(val) [4][100/129] eta: 0:00:00 time: 0.0150 data_time: 0.0060 memory: 262 2022/11/29 20:06:00 - mmengine - INFO - Epoch(val) [4][129/129] acc/top1: 0.7001 acc/top5: 0.9563 acc/mean1: 0.6998 2022/11/29 20:06:04 - mmengine - INFO - Epoch(train) [5][100/1567] lr: 8.4914e-02 eta: 0:10:50 time: 0.0347 data_time: 0.0062 memory: 1253 loss: 0.3167 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3167 2022/11/29 20:06:07 - mmengine - INFO - Epoch(train) [5][200/1567] lr: 8.4463e-02 eta: 0:10:47 time: 0.0334 data_time: 0.0062 memory: 1253 loss: 0.4125 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4125 2022/11/29 20:06:11 - mmengine - INFO - Epoch(train) [5][300/1567] lr: 8.4006e-02 eta: 0:10:43 time: 0.0335 data_time: 0.0063 memory: 1253 loss: 0.4454 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4454 2022/11/29 20:06:14 - mmengine - INFO - Epoch(train) [5][400/1567] lr: 8.3544e-02 eta: 0:10:39 time: 0.0337 data_time: 0.0062 memory: 1253 loss: 0.4261 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4261 2022/11/29 20:06:17 - mmengine - INFO - Epoch(train) [5][500/1567] lr: 8.3077e-02 eta: 0:10:35 time: 0.0334 data_time: 0.0062 memory: 1253 loss: 0.3401 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3401 2022/11/29 20:06:21 - mmengine - INFO - Epoch(train) [5][600/1567] lr: 8.2605e-02 eta: 0:10:32 time: 0.0347 data_time: 0.0064 memory: 1253 loss: 0.3291 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3291 2022/11/29 20:06:24 - mmengine - INFO - Epoch(train) [5][700/1567] lr: 8.2127e-02 eta: 0:10:28 time: 0.0338 data_time: 0.0062 memory: 1253 loss: 0.3374 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3374 2022/11/29 20:06:25 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:06:28 - mmengine - INFO - Epoch(train) [5][800/1567] lr: 8.1645e-02 eta: 0:10:24 time: 0.0333 data_time: 0.0062 memory: 1253 loss: 0.2378 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2378 2022/11/29 20:06:31 - mmengine - INFO - Epoch(train) [5][900/1567] lr: 8.1157e-02 eta: 0:10:20 time: 0.0333 data_time: 0.0062 memory: 1253 loss: 0.3823 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3823 2022/11/29 20:06:34 - mmengine - INFO - Epoch(train) [5][1000/1567] lr: 8.0665e-02 eta: 0:10:17 time: 0.0347 data_time: 0.0064 memory: 1253 loss: 0.3281 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3281 2022/11/29 20:06:38 - mmengine - INFO - Epoch(train) [5][1100/1567] lr: 8.0167e-02 eta: 0:10:13 time: 0.0349 data_time: 0.0070 memory: 1253 loss: 0.3616 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.3616 2022/11/29 20:06:41 - mmengine - INFO - Epoch(train) [5][1200/1567] lr: 7.9665e-02 eta: 0:10:10 time: 0.0348 data_time: 0.0062 memory: 1253 loss: 0.3084 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3084 2022/11/29 20:06:45 - mmengine - INFO - Epoch(train) [5][1300/1567] lr: 7.9159e-02 eta: 0:10:06 time: 0.0342 data_time: 0.0061 memory: 1253 loss: 0.2835 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2835 2022/11/29 20:06:48 - mmengine - INFO - Epoch(train) [5][1400/1567] lr: 7.8647e-02 eta: 0:10:03 time: 0.0335 data_time: 0.0062 memory: 1253 loss: 0.2789 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2789 2022/11/29 20:06:52 - mmengine - INFO - Epoch(train) [5][1500/1567] lr: 7.8132e-02 eta: 0:09:59 time: 0.0343 data_time: 0.0062 memory: 1253 loss: 0.2989 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2989 2022/11/29 20:06:54 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:06:54 - mmengine - INFO - Epoch(train) [5][1567/1567] lr: 7.7784e-02 eta: 0:09:57 time: 0.0336 data_time: 0.0059 memory: 1253 loss: 0.4841 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.4841 2022/11/29 20:06:54 - mmengine - INFO - Saving checkpoint at 5 epochs 2022/11/29 20:06:56 - mmengine - INFO - Epoch(val) [5][100/129] eta: 0:00:00 time: 0.0150 data_time: 0.0059 memory: 262 2022/11/29 20:06:56 - mmengine - INFO - Epoch(val) [5][129/129] acc/top1: 0.7349 acc/top5: 0.9446 acc/mean1: 0.7350 2022/11/29 20:06:56 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_2.pth is removed 2022/11/29 20:06:57 - mmengine - INFO - The best checkpoint with 0.7349 acc/top1 at 5 epoch is saved to best_acc/top1_epoch_5.pth. 2022/11/29 20:07:00 - mmengine - INFO - Epoch(train) [6][100/1567] lr: 7.7261e-02 eta: 0:09:53 time: 0.0341 data_time: 0.0062 memory: 1253 loss: 0.3447 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3447 2022/11/29 20:07:03 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:07:04 - mmengine - INFO - Epoch(train) [6][200/1567] lr: 7.6733e-02 eta: 0:09:50 time: 0.0340 data_time: 0.0062 memory: 1253 loss: 0.3463 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3463 2022/11/29 20:07:07 - mmengine - INFO - Epoch(train) [6][300/1567] lr: 7.6202e-02 eta: 0:09:46 time: 0.0345 data_time: 0.0063 memory: 1253 loss: 0.2577 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.2577 2022/11/29 20:07:11 - mmengine - INFO - Epoch(train) [6][400/1567] lr: 7.5666e-02 eta: 0:09:43 time: 0.0341 data_time: 0.0062 memory: 1253 loss: 0.2472 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2472 2022/11/29 20:07:14 - mmengine - INFO - Epoch(train) [6][500/1567] lr: 7.5126e-02 eta: 0:09:39 time: 0.0339 data_time: 0.0062 memory: 1253 loss: 0.2883 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2883 2022/11/29 20:07:17 - mmengine - INFO - Epoch(train) [6][600/1567] lr: 7.4583e-02 eta: 0:09:36 time: 0.0339 data_time: 0.0063 memory: 1253 loss: 0.3584 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.3584 2022/11/29 20:07:21 - mmengine - INFO - Epoch(train) [6][700/1567] lr: 7.4035e-02 eta: 0:09:32 time: 0.0351 data_time: 0.0062 memory: 1253 loss: 0.2590 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2590 2022/11/29 20:07:24 - mmengine - INFO - Epoch(train) [6][800/1567] lr: 7.3484e-02 eta: 0:09:29 time: 0.0334 data_time: 0.0062 memory: 1253 loss: 0.3033 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3033 2022/11/29 20:07:28 - mmengine - INFO - Epoch(train) [6][900/1567] lr: 7.2929e-02 eta: 0:09:25 time: 0.0333 data_time: 0.0062 memory: 1253 loss: 0.2791 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2791 2022/11/29 20:07:31 - mmengine - INFO - Epoch(train) [6][1000/1567] lr: 7.2371e-02 eta: 0:09:21 time: 0.0334 data_time: 0.0062 memory: 1253 loss: 0.2432 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2432 2022/11/29 20:07:34 - mmengine - INFO - Epoch(train) [6][1100/1567] lr: 7.1809e-02 eta: 0:09:18 time: 0.0349 data_time: 0.0063 memory: 1253 loss: 0.2858 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2858 2022/11/29 20:07:37 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:07:38 - mmengine - INFO - Epoch(train) [6][1200/1567] lr: 7.1243e-02 eta: 0:09:14 time: 0.0349 data_time: 0.0063 memory: 1253 loss: 0.2887 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2887 2022/11/29 20:07:41 - mmengine - INFO - Epoch(train) [6][1300/1567] lr: 7.0674e-02 eta: 0:09:11 time: 0.0340 data_time: 0.0062 memory: 1253 loss: 0.3421 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3421 2022/11/29 20:07:45 - mmengine - INFO - Epoch(train) [6][1400/1567] lr: 7.0102e-02 eta: 0:09:07 time: 0.0342 data_time: 0.0063 memory: 1253 loss: 0.2921 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2921 2022/11/29 20:07:48 - mmengine - INFO - Epoch(train) [6][1500/1567] lr: 6.9527e-02 eta: 0:09:04 time: 0.0335 data_time: 0.0063 memory: 1253 loss: 0.2753 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2753 2022/11/29 20:07:51 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:07:51 - mmengine - INFO - Epoch(train) [6][1567/1567] lr: 6.9140e-02 eta: 0:09:02 time: 0.0345 data_time: 0.0066 memory: 1253 loss: 0.4423 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.4423 2022/11/29 20:07:51 - mmengine - INFO - Saving checkpoint at 6 epochs 2022/11/29 20:07:53 - mmengine - INFO - Epoch(val) [6][100/129] eta: 0:00:00 time: 0.0148 data_time: 0.0058 memory: 262 2022/11/29 20:07:53 - mmengine - INFO - Epoch(val) [6][129/129] acc/top1: 0.7927 acc/top5: 0.9718 acc/mean1: 0.7926 2022/11/29 20:07:53 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_5.pth is removed 2022/11/29 20:07:54 - mmengine - INFO - The best checkpoint with 0.7927 acc/top1 at 6 epoch is saved to best_acc/top1_epoch_6.pth. 2022/11/29 20:07:57 - mmengine - INFO - Epoch(train) [7][100/1567] lr: 6.8560e-02 eta: 0:08:58 time: 0.0355 data_time: 0.0062 memory: 1253 loss: 0.2101 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2101 2022/11/29 20:08:01 - mmengine - INFO - Epoch(train) [7][200/1567] lr: 6.7976e-02 eta: 0:08:55 time: 0.0347 data_time: 0.0063 memory: 1253 loss: 0.2284 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2284 2022/11/29 20:08:04 - mmengine - INFO - Epoch(train) [7][300/1567] lr: 6.7390e-02 eta: 0:08:52 time: 0.0345 data_time: 0.0062 memory: 1253 loss: 0.2639 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2639 2022/11/29 20:08:08 - mmengine - INFO - Epoch(train) [7][400/1567] lr: 6.6802e-02 eta: 0:08:48 time: 0.0345 data_time: 0.0066 memory: 1253 loss: 0.1970 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1970 2022/11/29 20:08:11 - mmengine - INFO - Epoch(train) [7][500/1567] lr: 6.6210e-02 eta: 0:08:45 time: 0.0341 data_time: 0.0065 memory: 1253 loss: 0.2500 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2500 2022/11/29 20:08:14 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:08:15 - mmengine - INFO - Epoch(train) [7][600/1567] lr: 6.5616e-02 eta: 0:08:41 time: 0.0345 data_time: 0.0063 memory: 1253 loss: 0.2240 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2240 2022/11/29 20:08:18 - mmengine - INFO - Epoch(train) [7][700/1567] lr: 6.5020e-02 eta: 0:08:38 time: 0.0367 data_time: 0.0062 memory: 1253 loss: 0.3211 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3211 2022/11/29 20:08:22 - mmengine - INFO - Epoch(train) [7][800/1567] lr: 6.4421e-02 eta: 0:08:34 time: 0.0352 data_time: 0.0062 memory: 1253 loss: 0.2853 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.2853 2022/11/29 20:08:25 - mmengine - INFO - Epoch(train) [7][900/1567] lr: 6.3820e-02 eta: 0:08:31 time: 0.0347 data_time: 0.0063 memory: 1253 loss: 0.2931 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2931 2022/11/29 20:08:29 - mmengine - INFO - Epoch(train) [7][1000/1567] lr: 6.3217e-02 eta: 0:08:28 time: 0.0345 data_time: 0.0062 memory: 1253 loss: 0.2784 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2784 2022/11/29 20:08:32 - mmengine - INFO - Epoch(train) [7][1100/1567] lr: 6.2612e-02 eta: 0:08:24 time: 0.0343 data_time: 0.0063 memory: 1253 loss: 0.2420 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2420 2022/11/29 20:08:36 - mmengine - INFO - Epoch(train) [7][1200/1567] lr: 6.2005e-02 eta: 0:08:21 time: 0.0352 data_time: 0.0063 memory: 1253 loss: 0.2823 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2823 2022/11/29 20:08:39 - mmengine - INFO - Epoch(train) [7][1300/1567] lr: 6.1396e-02 eta: 0:08:17 time: 0.0344 data_time: 0.0062 memory: 1253 loss: 0.2388 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.2388 2022/11/29 20:08:42 - mmengine - INFO - Epoch(train) [7][1400/1567] lr: 6.0785e-02 eta: 0:08:14 time: 0.0349 data_time: 0.0065 memory: 1253 loss: 0.2328 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2328 2022/11/29 20:08:46 - mmengine - INFO - Epoch(train) [7][1500/1567] lr: 6.0172e-02 eta: 0:08:10 time: 0.0351 data_time: 0.0063 memory: 1253 loss: 0.2390 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2390 2022/11/29 20:08:48 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:08:48 - mmengine - INFO - Epoch(train) [7][1567/1567] lr: 5.9761e-02 eta: 0:08:08 time: 0.0348 data_time: 0.0062 memory: 1253 loss: 0.4665 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.4665 2022/11/29 20:08:48 - mmengine - INFO - Saving checkpoint at 7 epochs 2022/11/29 20:08:50 - mmengine - INFO - Epoch(val) [7][100/129] eta: 0:00:00 time: 0.0153 data_time: 0.0061 memory: 262 2022/11/29 20:08:51 - mmengine - INFO - Epoch(val) [7][129/129] acc/top1: 0.7856 acc/top5: 0.9725 acc/mean1: 0.7854 2022/11/29 20:08:52 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:08:54 - mmengine - INFO - Epoch(train) [8][100/1567] lr: 5.9145e-02 eta: 0:08:05 time: 0.0350 data_time: 0.0062 memory: 1253 loss: 0.2576 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2576 2022/11/29 20:08:58 - mmengine - INFO - Epoch(train) [8][200/1567] lr: 5.8529e-02 eta: 0:08:01 time: 0.0346 data_time: 0.0063 memory: 1253 loss: 0.2270 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2270 2022/11/29 20:09:01 - mmengine - INFO - Epoch(train) [8][300/1567] lr: 5.7911e-02 eta: 0:07:58 time: 0.0354 data_time: 0.0063 memory: 1253 loss: 0.2608 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2608 2022/11/29 20:09:05 - mmengine - INFO - Epoch(train) [8][400/1567] lr: 5.7292e-02 eta: 0:07:54 time: 0.0355 data_time: 0.0067 memory: 1253 loss: 0.2888 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2888 2022/11/29 20:09:08 - mmengine - INFO - Epoch(train) [8][500/1567] lr: 5.6671e-02 eta: 0:07:51 time: 0.0349 data_time: 0.0072 memory: 1253 loss: 0.2799 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2799 2022/11/29 20:09:12 - mmengine - INFO - Epoch(train) [8][600/1567] lr: 5.6050e-02 eta: 0:07:47 time: 0.0350 data_time: 0.0064 memory: 1253 loss: 0.2535 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2535 2022/11/29 20:09:15 - mmengine - INFO - Epoch(train) [8][700/1567] lr: 5.5427e-02 eta: 0:07:44 time: 0.0355 data_time: 0.0063 memory: 1253 loss: 0.2337 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2337 2022/11/29 20:09:19 - mmengine - INFO - Epoch(train) [8][800/1567] lr: 5.4804e-02 eta: 0:07:41 time: 0.0348 data_time: 0.0063 memory: 1253 loss: 0.2307 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2307 2022/11/29 20:09:23 - mmengine - INFO - Epoch(train) [8][900/1567] lr: 5.4180e-02 eta: 0:07:37 time: 0.0344 data_time: 0.0063 memory: 1253 loss: 0.2385 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2385 2022/11/29 20:09:26 - mmengine - INFO - Epoch(train) [8][1000/1567] lr: 5.3556e-02 eta: 0:07:34 time: 0.0343 data_time: 0.0068 memory: 1253 loss: 0.2295 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2295 2022/11/29 20:09:27 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:09:29 - mmengine - INFO - Epoch(train) [8][1100/1567] lr: 5.2930e-02 eta: 0:07:30 time: 0.0342 data_time: 0.0063 memory: 1253 loss: 0.1834 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1834 2022/11/29 20:09:33 - mmengine - INFO - Epoch(train) [8][1200/1567] lr: 5.2305e-02 eta: 0:07:27 time: 0.0336 data_time: 0.0064 memory: 1253 loss: 0.2073 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2073 2022/11/29 20:09:36 - mmengine - INFO - Epoch(train) [8][1300/1567] lr: 5.1679e-02 eta: 0:07:23 time: 0.0348 data_time: 0.0062 memory: 1253 loss: 0.2522 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2522 2022/11/29 20:09:40 - mmengine - INFO - Epoch(train) [8][1400/1567] lr: 5.1052e-02 eta: 0:07:20 time: 0.0346 data_time: 0.0062 memory: 1253 loss: 0.1481 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1481 2022/11/29 20:09:43 - mmengine - INFO - Epoch(train) [8][1500/1567] lr: 5.0426e-02 eta: 0:07:16 time: 0.0342 data_time: 0.0063 memory: 1253 loss: 0.1991 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1991 2022/11/29 20:09:45 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:09:45 - mmengine - INFO - Epoch(train) [8][1567/1567] lr: 5.0006e-02 eta: 0:07:14 time: 0.0334 data_time: 0.0060 memory: 1253 loss: 0.4101 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.4101 2022/11/29 20:09:45 - mmengine - INFO - Saving checkpoint at 8 epochs 2022/11/29 20:09:47 - mmengine - INFO - Epoch(val) [8][100/129] eta: 0:00:00 time: 0.0151 data_time: 0.0059 memory: 262 2022/11/29 20:09:48 - mmengine - INFO - Epoch(val) [8][129/129] acc/top1: 0.7715 acc/top5: 0.9674 acc/mean1: 0.7714 2022/11/29 20:09:52 - mmengine - INFO - Epoch(train) [9][100/1567] lr: 4.9380e-02 eta: 0:07:11 time: 0.0349 data_time: 0.0063 memory: 1253 loss: 0.1868 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1868 2022/11/29 20:09:55 - mmengine - INFO - Epoch(train) [9][200/1567] lr: 4.8753e-02 eta: 0:07:07 time: 0.0342 data_time: 0.0062 memory: 1253 loss: 0.1733 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1733 2022/11/29 20:09:59 - mmengine - INFO - Epoch(train) [9][300/1567] lr: 4.8127e-02 eta: 0:07:04 time: 0.0342 data_time: 0.0062 memory: 1253 loss: 0.1298 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1298 2022/11/29 20:10:02 - mmengine - INFO - Epoch(train) [9][400/1567] lr: 4.7501e-02 eta: 0:07:00 time: 0.0343 data_time: 0.0062 memory: 1253 loss: 0.1765 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1765 2022/11/29 20:10:04 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:10:06 - mmengine - INFO - Epoch(train) [9][500/1567] lr: 4.6876e-02 eta: 0:06:57 time: 0.0349 data_time: 0.0070 memory: 1253 loss: 0.2232 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2232 2022/11/29 20:10:09 - mmengine - INFO - Epoch(train) [9][600/1567] lr: 4.6251e-02 eta: 0:06:53 time: 0.0349 data_time: 0.0067 memory: 1253 loss: 0.1548 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1548 2022/11/29 20:10:13 - mmengine - INFO - Epoch(train) [9][700/1567] lr: 4.5626e-02 eta: 0:06:50 time: 0.0341 data_time: 0.0065 memory: 1253 loss: 0.2164 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2164 2022/11/29 20:10:16 - mmengine - INFO - Epoch(train) [9][800/1567] lr: 4.5003e-02 eta: 0:06:46 time: 0.0341 data_time: 0.0064 memory: 1253 loss: 0.2113 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2113 2022/11/29 20:10:20 - mmengine - INFO - Epoch(train) [9][900/1567] lr: 4.4380e-02 eta: 0:06:43 time: 0.0355 data_time: 0.0063 memory: 1253 loss: 0.1956 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1956 2022/11/29 20:10:23 - mmengine - INFO - Epoch(train) [9][1000/1567] lr: 4.3757e-02 eta: 0:06:39 time: 0.0351 data_time: 0.0063 memory: 1253 loss: 0.1414 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1414 2022/11/29 20:10:27 - mmengine - INFO - Epoch(train) [9][1100/1567] lr: 4.3136e-02 eta: 0:06:36 time: 0.0345 data_time: 0.0065 memory: 1253 loss: 0.1589 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1589 2022/11/29 20:10:30 - mmengine - INFO - Epoch(train) [9][1200/1567] lr: 4.2516e-02 eta: 0:06:33 time: 0.0345 data_time: 0.0063 memory: 1253 loss: 0.1648 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1648 2022/11/29 20:10:34 - mmengine - INFO - Epoch(train) [9][1300/1567] lr: 4.1897e-02 eta: 0:06:29 time: 0.0339 data_time: 0.0062 memory: 1253 loss: 0.1746 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1746 2022/11/29 20:10:37 - mmengine - INFO - Epoch(train) [9][1400/1567] lr: 4.1280e-02 eta: 0:06:26 time: 0.0345 data_time: 0.0062 memory: 1253 loss: 0.1410 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1410 2022/11/29 20:10:39 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:10:40 - mmengine - INFO - Epoch(train) [9][1500/1567] lr: 4.0664e-02 eta: 0:06:22 time: 0.0345 data_time: 0.0062 memory: 1253 loss: 0.1564 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1564 2022/11/29 20:10:43 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:10:43 - mmengine - INFO - Epoch(train) [9][1567/1567] lr: 4.0252e-02 eta: 0:06:20 time: 0.0337 data_time: 0.0060 memory: 1253 loss: 0.3111 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.3111 2022/11/29 20:10:43 - mmengine - INFO - Saving checkpoint at 9 epochs 2022/11/29 20:10:45 - mmengine - INFO - Epoch(val) [9][100/129] eta: 0:00:00 time: 0.0150 data_time: 0.0059 memory: 262 2022/11/29 20:10:45 - mmengine - INFO - Epoch(val) [9][129/129] acc/top1: 0.7799 acc/top5: 0.9621 acc/mean1: 0.7800 2022/11/29 20:10:49 - mmengine - INFO - Epoch(train) [10][100/1567] lr: 3.9638e-02 eta: 0:06:16 time: 0.0356 data_time: 0.0062 memory: 1253 loss: 0.1439 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1439 2022/11/29 20:10:53 - mmengine - INFO - Epoch(train) [10][200/1567] lr: 3.9026e-02 eta: 0:06:13 time: 0.0346 data_time: 0.0063 memory: 1253 loss: 0.1834 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1834 2022/11/29 20:10:56 - mmengine - INFO - Epoch(train) [10][300/1567] lr: 3.8415e-02 eta: 0:06:10 time: 0.0339 data_time: 0.0063 memory: 1253 loss: 0.1766 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.1766 2022/11/29 20:10:59 - mmengine - INFO - Epoch(train) [10][400/1567] lr: 3.7807e-02 eta: 0:06:06 time: 0.0339 data_time: 0.0063 memory: 1253 loss: 0.1467 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1467 2022/11/29 20:11:03 - mmengine - INFO - Epoch(train) [10][500/1567] lr: 3.7200e-02 eta: 0:06:03 time: 0.0339 data_time: 0.0062 memory: 1253 loss: 0.1494 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1494 2022/11/29 20:11:06 - mmengine - INFO - Epoch(train) [10][600/1567] lr: 3.6596e-02 eta: 0:05:59 time: 0.0355 data_time: 0.0063 memory: 1253 loss: 0.1395 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1395 2022/11/29 20:11:10 - mmengine - INFO - Epoch(train) [10][700/1567] lr: 3.5993e-02 eta: 0:05:56 time: 0.0349 data_time: 0.0062 memory: 1253 loss: 0.1177 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1177 2022/11/29 20:11:13 - mmengine - INFO - Epoch(train) [10][800/1567] lr: 3.5393e-02 eta: 0:05:52 time: 0.0353 data_time: 0.0062 memory: 1253 loss: 0.1389 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1389 2022/11/29 20:11:17 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:11:17 - mmengine - INFO - Epoch(train) [10][900/1567] lr: 3.4795e-02 eta: 0:05:49 time: 0.0347 data_time: 0.0063 memory: 1253 loss: 0.1268 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1268 2022/11/29 20:11:20 - mmengine - INFO - Epoch(train) [10][1000/1567] lr: 3.4199e-02 eta: 0:05:45 time: 0.0361 data_time: 0.0063 memory: 1253 loss: 0.0942 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0942 2022/11/29 20:11:24 - mmengine - INFO - Epoch(train) [10][1100/1567] lr: 3.3606e-02 eta: 0:05:42 time: 0.0338 data_time: 0.0064 memory: 1253 loss: 0.1402 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1402 2022/11/29 20:11:27 - mmengine - INFO - Epoch(train) [10][1200/1567] lr: 3.3015e-02 eta: 0:05:38 time: 0.0342 data_time: 0.0062 memory: 1253 loss: 0.0965 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0965 2022/11/29 20:11:31 - mmengine - INFO - Epoch(train) [10][1300/1567] lr: 3.2428e-02 eta: 0:05:35 time: 0.0347 data_time: 0.0062 memory: 1253 loss: 0.0926 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0926 2022/11/29 20:11:34 - mmengine - INFO - Epoch(train) [10][1400/1567] lr: 3.1842e-02 eta: 0:05:31 time: 0.0343 data_time: 0.0063 memory: 1253 loss: 0.1374 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1374 2022/11/29 20:11:38 - mmengine - INFO - Epoch(train) [10][1500/1567] lr: 3.1260e-02 eta: 0:05:28 time: 0.0347 data_time: 0.0062 memory: 1253 loss: 0.1056 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1056 2022/11/29 20:11:40 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:11:40 - mmengine - INFO - Epoch(train) [10][1567/1567] lr: 3.0872e-02 eta: 0:05:26 time: 0.0340 data_time: 0.0060 memory: 1253 loss: 0.2819 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2819 2022/11/29 20:11:40 - mmengine - INFO - Saving checkpoint at 10 epochs 2022/11/29 20:11:42 - mmengine - INFO - Epoch(val) [10][100/129] eta: 0:00:00 time: 0.0149 data_time: 0.0059 memory: 262 2022/11/29 20:11:42 - mmengine - INFO - Epoch(val) [10][129/129] acc/top1: 0.8160 acc/top5: 0.9790 acc/mean1: 0.8159 2022/11/29 20:11:42 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_6.pth is removed 2022/11/29 20:11:43 - mmengine - INFO - The best checkpoint with 0.8160 acc/top1 at 10 epoch is saved to best_acc/top1_epoch_10.pth. 2022/11/29 20:11:46 - mmengine - INFO - Epoch(train) [11][100/1567] lr: 3.0294e-02 eta: 0:05:22 time: 0.0343 data_time: 0.0062 memory: 1253 loss: 0.1083 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1083 2022/11/29 20:11:50 - mmengine - INFO - Epoch(train) [11][200/1567] lr: 2.9720e-02 eta: 0:05:19 time: 0.0355 data_time: 0.0073 memory: 1253 loss: 0.0983 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.0983 2022/11/29 20:11:53 - mmengine - INFO - Epoch(train) [11][300/1567] lr: 2.9149e-02 eta: 0:05:15 time: 0.0345 data_time: 0.0065 memory: 1253 loss: 0.1222 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1222 2022/11/29 20:11:54 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:11:56 - mmengine - INFO - Epoch(train) [11][400/1567] lr: 2.8581e-02 eta: 0:05:12 time: 0.0338 data_time: 0.0062 memory: 1253 loss: 0.1080 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1080 2022/11/29 20:12:00 - mmengine - INFO - Epoch(train) [11][500/1567] lr: 2.8017e-02 eta: 0:05:08 time: 0.0339 data_time: 0.0063 memory: 1253 loss: 0.1047 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1047 2022/11/29 20:12:03 - mmengine - INFO - Epoch(train) [11][600/1567] lr: 2.7456e-02 eta: 0:05:05 time: 0.0344 data_time: 0.0063 memory: 1253 loss: 0.0784 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0784 2022/11/29 20:12:07 - mmengine - INFO - Epoch(train) [11][700/1567] lr: 2.6898e-02 eta: 0:05:01 time: 0.0351 data_time: 0.0062 memory: 1253 loss: 0.0869 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0869 2022/11/29 20:12:10 - mmengine - INFO - Epoch(train) [11][800/1567] lr: 2.6345e-02 eta: 0:04:58 time: 0.0339 data_time: 0.0063 memory: 1253 loss: 0.0826 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0826 2022/11/29 20:12:14 - mmengine - INFO - Epoch(train) [11][900/1567] lr: 2.5794e-02 eta: 0:04:54 time: 0.0344 data_time: 0.0063 memory: 1253 loss: 0.0738 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0738 2022/11/29 20:12:17 - mmengine - INFO - Epoch(train) [11][1000/1567] lr: 2.5248e-02 eta: 0:04:51 time: 0.0338 data_time: 0.0062 memory: 1253 loss: 0.0636 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0636 2022/11/29 20:12:21 - mmengine - INFO - Epoch(train) [11][1100/1567] lr: 2.4706e-02 eta: 0:04:47 time: 0.0361 data_time: 0.0065 memory: 1253 loss: 0.0851 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0851 2022/11/29 20:12:24 - mmengine - INFO - Epoch(train) [11][1200/1567] lr: 2.4167e-02 eta: 0:04:44 time: 0.0348 data_time: 0.0062 memory: 1253 loss: 0.0616 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0616 2022/11/29 20:12:28 - mmengine - INFO - Epoch(train) [11][1300/1567] lr: 2.3633e-02 eta: 0:04:40 time: 0.0343 data_time: 0.0065 memory: 1253 loss: 0.0575 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0575 2022/11/29 20:12:29 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:12:31 - mmengine - INFO - Epoch(train) [11][1400/1567] lr: 2.3103e-02 eta: 0:04:37 time: 0.0342 data_time: 0.0063 memory: 1253 loss: 0.0979 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0979 2022/11/29 20:12:35 - mmengine - INFO - Epoch(train) [11][1500/1567] lr: 2.2577e-02 eta: 0:04:33 time: 0.0371 data_time: 0.0065 memory: 1253 loss: 0.0704 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0704 2022/11/29 20:12:37 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:12:37 - mmengine - INFO - Epoch(train) [11][1567/1567] lr: 2.2227e-02 eta: 0:04:31 time: 0.0347 data_time: 0.0061 memory: 1253 loss: 0.2809 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2809 2022/11/29 20:12:37 - mmengine - INFO - Saving checkpoint at 11 epochs 2022/11/29 20:12:39 - mmengine - INFO - Epoch(val) [11][100/129] eta: 0:00:00 time: 0.0151 data_time: 0.0059 memory: 262 2022/11/29 20:12:40 - mmengine - INFO - Epoch(val) [11][129/129] acc/top1: 0.8495 acc/top5: 0.9831 acc/mean1: 0.8494 2022/11/29 20:12:40 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_10.pth is removed 2022/11/29 20:12:40 - mmengine - INFO - The best checkpoint with 0.8495 acc/top1 at 11 epoch is saved to best_acc/top1_epoch_11.pth. 2022/11/29 20:12:43 - mmengine - INFO - Epoch(train) [12][100/1567] lr: 2.1708e-02 eta: 0:04:28 time: 0.0348 data_time: 0.0063 memory: 1253 loss: 0.0635 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.0635 2022/11/29 20:12:47 - mmengine - INFO - Epoch(train) [12][200/1567] lr: 2.1194e-02 eta: 0:04:24 time: 0.0352 data_time: 0.0063 memory: 1253 loss: 0.0643 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0643 2022/11/29 20:12:51 - mmengine - INFO - Epoch(train) [12][300/1567] lr: 2.0684e-02 eta: 0:04:21 time: 0.0371 data_time: 0.0072 memory: 1253 loss: 0.0638 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0638 2022/11/29 20:12:54 - mmengine - INFO - Epoch(train) [12][400/1567] lr: 2.0179e-02 eta: 0:04:17 time: 0.0353 data_time: 0.0063 memory: 1253 loss: 0.0613 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0613 2022/11/29 20:12:58 - mmengine - INFO - Epoch(train) [12][500/1567] lr: 1.9678e-02 eta: 0:04:14 time: 0.0345 data_time: 0.0064 memory: 1253 loss: 0.0576 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0576 2022/11/29 20:13:01 - mmengine - INFO - Epoch(train) [12][600/1567] lr: 1.9182e-02 eta: 0:04:11 time: 0.0350 data_time: 0.0068 memory: 1253 loss: 0.0370 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0370 2022/11/29 20:13:05 - mmengine - INFO - Epoch(train) [12][700/1567] lr: 1.8691e-02 eta: 0:04:07 time: 0.0360 data_time: 0.0067 memory: 1253 loss: 0.0532 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0532 2022/11/29 20:13:07 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:13:08 - mmengine - INFO - Epoch(train) [12][800/1567] lr: 1.8205e-02 eta: 0:04:04 time: 0.0351 data_time: 0.0068 memory: 1253 loss: 0.0338 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0338 2022/11/29 20:13:12 - mmengine - INFO - Epoch(train) [12][900/1567] lr: 1.7724e-02 eta: 0:04:00 time: 0.0341 data_time: 0.0063 memory: 1253 loss: 0.0460 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0460 2022/11/29 20:13:15 - mmengine - INFO - Epoch(train) [12][1000/1567] lr: 1.7248e-02 eta: 0:03:57 time: 0.0340 data_time: 0.0063 memory: 1253 loss: 0.0477 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0477 2022/11/29 20:13:18 - mmengine - INFO - Epoch(train) [12][1100/1567] lr: 1.6778e-02 eta: 0:03:53 time: 0.0343 data_time: 0.0063 memory: 1253 loss: 0.0303 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0303 2022/11/29 20:13:22 - mmengine - INFO - Epoch(train) [12][1200/1567] lr: 1.6312e-02 eta: 0:03:50 time: 0.0357 data_time: 0.0072 memory: 1253 loss: 0.0332 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0332 2022/11/29 20:13:26 - mmengine - INFO - Epoch(train) [12][1300/1567] lr: 1.5852e-02 eta: 0:03:46 time: 0.0351 data_time: 0.0071 memory: 1253 loss: 0.0313 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0313 2022/11/29 20:13:29 - mmengine - INFO - Epoch(train) [12][1400/1567] lr: 1.5397e-02 eta: 0:03:43 time: 0.0354 data_time: 0.0069 memory: 1253 loss: 0.0280 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0280 2022/11/29 20:13:33 - mmengine - INFO - Epoch(train) [12][1500/1567] lr: 1.4947e-02 eta: 0:03:39 time: 0.0350 data_time: 0.0068 memory: 1253 loss: 0.0241 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0241 2022/11/29 20:13:35 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:13:35 - mmengine - INFO - Epoch(train) [12][1567/1567] lr: 1.4649e-02 eta: 0:03:37 time: 0.0352 data_time: 0.0066 memory: 1253 loss: 0.2070 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.2070 2022/11/29 20:13:35 - mmengine - INFO - Saving checkpoint at 12 epochs 2022/11/29 20:13:37 - mmengine - INFO - Epoch(val) [12][100/129] eta: 0:00:00 time: 0.0151 data_time: 0.0059 memory: 262 2022/11/29 20:13:38 - mmengine - INFO - Epoch(val) [12][129/129] acc/top1: 0.8610 acc/top5: 0.9841 acc/mean1: 0.8609 2022/11/29 20:13:38 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_11.pth is removed 2022/11/29 20:13:38 - mmengine - INFO - The best checkpoint with 0.8610 acc/top1 at 12 epoch is saved to best_acc/top1_epoch_12.pth. 2022/11/29 20:13:42 - mmengine - INFO - Epoch(train) [13][100/1567] lr: 1.4209e-02 eta: 0:03:34 time: 0.0349 data_time: 0.0063 memory: 1253 loss: 0.0286 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0286 2022/11/29 20:13:45 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:13:45 - mmengine - INFO - Epoch(train) [13][200/1567] lr: 1.3774e-02 eta: 0:03:30 time: 0.0348 data_time: 0.0064 memory: 1253 loss: 0.0277 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0277 2022/11/29 20:13:48 - mmengine - INFO - Epoch(train) [13][300/1567] lr: 1.3345e-02 eta: 0:03:27 time: 0.0344 data_time: 0.0063 memory: 1253 loss: 0.0274 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0274 2022/11/29 20:13:52 - mmengine - INFO - Epoch(train) [13][400/1567] lr: 1.2922e-02 eta: 0:03:23 time: 0.0353 data_time: 0.0063 memory: 1253 loss: 0.0232 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0232 2022/11/29 20:13:56 - mmengine - INFO - Epoch(train) [13][500/1567] lr: 1.2505e-02 eta: 0:03:20 time: 0.0350 data_time: 0.0063 memory: 1253 loss: 0.0255 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0255 2022/11/29 20:13:59 - mmengine - INFO - Epoch(train) [13][600/1567] lr: 1.2093e-02 eta: 0:03:16 time: 0.0347 data_time: 0.0063 memory: 1253 loss: 0.0176 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0176 2022/11/29 20:14:03 - mmengine - INFO - Epoch(train) [13][700/1567] lr: 1.1687e-02 eta: 0:03:13 time: 0.0349 data_time: 0.0063 memory: 1253 loss: 0.0178 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0178 2022/11/29 20:14:06 - mmengine - INFO - Epoch(train) [13][800/1567] lr: 1.1288e-02 eta: 0:03:09 time: 0.0355 data_time: 0.0063 memory: 1253 loss: 0.0248 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0248 2022/11/29 20:14:10 - mmengine - INFO - Epoch(train) [13][900/1567] lr: 1.0894e-02 eta: 0:03:06 time: 0.0355 data_time: 0.0064 memory: 1253 loss: 0.0170 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0170 2022/11/29 20:14:13 - mmengine - INFO - Epoch(train) [13][1000/1567] lr: 1.0507e-02 eta: 0:03:02 time: 0.0342 data_time: 0.0062 memory: 1253 loss: 0.0197 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0197 2022/11/29 20:14:17 - mmengine - INFO - Epoch(train) [13][1100/1567] lr: 1.0126e-02 eta: 0:02:59 time: 0.0354 data_time: 0.0064 memory: 1253 loss: 0.0169 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0169 2022/11/29 20:14:20 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:14:20 - mmengine - INFO - Epoch(train) [13][1200/1567] lr: 9.7512e-03 eta: 0:02:56 time: 0.0371 data_time: 0.0071 memory: 1253 loss: 0.0207 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0207 2022/11/29 20:14:24 - mmengine - INFO - Epoch(train) [13][1300/1567] lr: 9.3826e-03 eta: 0:02:52 time: 0.0356 data_time: 0.0066 memory: 1253 loss: 0.0241 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0241 2022/11/29 20:14:27 - mmengine - INFO - Epoch(train) [13][1400/1567] lr: 9.0204e-03 eta: 0:02:49 time: 0.0345 data_time: 0.0063 memory: 1253 loss: 0.0186 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0186 2022/11/29 20:14:31 - mmengine - INFO - Epoch(train) [13][1500/1567] lr: 8.6647e-03 eta: 0:02:45 time: 0.0345 data_time: 0.0066 memory: 1253 loss: 0.0158 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0158 2022/11/29 20:14:33 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:14:33 - mmengine - INFO - Epoch(train) [13][1567/1567] lr: 8.4300e-03 eta: 0:02:43 time: 0.0340 data_time: 0.0063 memory: 1253 loss: 0.2113 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2113 2022/11/29 20:14:33 - mmengine - INFO - Saving checkpoint at 13 epochs 2022/11/29 20:14:35 - mmengine - INFO - Epoch(val) [13][100/129] eta: 0:00:00 time: 0.0159 data_time: 0.0063 memory: 262 2022/11/29 20:14:35 - mmengine - INFO - Epoch(val) [13][129/129] acc/top1: 0.8724 acc/top5: 0.9877 acc/mean1: 0.8723 2022/11/29 20:14:36 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_12.pth is removed 2022/11/29 20:14:36 - mmengine - INFO - The best checkpoint with 0.8724 acc/top1 at 13 epoch is saved to best_acc/top1_epoch_13.pth. 2022/11/29 20:14:39 - mmengine - INFO - Epoch(train) [14][100/1567] lr: 8.0851e-03 eta: 0:02:39 time: 0.0344 data_time: 0.0063 memory: 1253 loss: 0.0155 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0155 2022/11/29 20:14:43 - mmengine - INFO - Epoch(train) [14][200/1567] lr: 7.7469e-03 eta: 0:02:36 time: 0.0357 data_time: 0.0064 memory: 1253 loss: 0.0123 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0123 2022/11/29 20:14:46 - mmengine - INFO - Epoch(train) [14][300/1567] lr: 7.4152e-03 eta: 0:02:32 time: 0.0360 data_time: 0.0064 memory: 1253 loss: 0.0152 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0152 2022/11/29 20:14:50 - mmengine - INFO - Epoch(train) [14][400/1567] lr: 7.0902e-03 eta: 0:02:29 time: 0.0376 data_time: 0.0070 memory: 1253 loss: 0.0150 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0150 2022/11/29 20:14:54 - mmengine - INFO - Epoch(train) [14][500/1567] lr: 6.7720e-03 eta: 0:02:25 time: 0.0353 data_time: 0.0063 memory: 1253 loss: 0.0109 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0109 2022/11/29 20:14:57 - mmengine - INFO - Epoch(train) [14][600/1567] lr: 6.4606e-03 eta: 0:02:22 time: 0.0347 data_time: 0.0064 memory: 1253 loss: 0.0108 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0108 2022/11/29 20:14:58 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:15:01 - mmengine - INFO - Epoch(train) [14][700/1567] lr: 6.1560e-03 eta: 0:02:19 time: 0.0343 data_time: 0.0063 memory: 1253 loss: 0.0154 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0154 2022/11/29 20:15:04 - mmengine - INFO - Epoch(train) [14][800/1567] lr: 5.8582e-03 eta: 0:02:15 time: 0.0351 data_time: 0.0064 memory: 1253 loss: 0.0092 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0092 2022/11/29 20:15:08 - mmengine - INFO - Epoch(train) [14][900/1567] lr: 5.5675e-03 eta: 0:02:12 time: 0.0350 data_time: 0.0064 memory: 1253 loss: 0.0132 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0132 2022/11/29 20:15:11 - mmengine - INFO - Epoch(train) [14][1000/1567] lr: 5.2836e-03 eta: 0:02:08 time: 0.0352 data_time: 0.0063 memory: 1253 loss: 0.0099 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0099 2022/11/29 20:15:15 - mmengine - INFO - Epoch(train) [14][1100/1567] lr: 5.0068e-03 eta: 0:02:05 time: 0.0349 data_time: 0.0064 memory: 1253 loss: 0.0081 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0081 2022/11/29 20:15:18 - mmengine - INFO - Epoch(train) [14][1200/1567] lr: 4.7371e-03 eta: 0:02:01 time: 0.0349 data_time: 0.0064 memory: 1253 loss: 0.0105 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0105 2022/11/29 20:15:22 - mmengine - INFO - Epoch(train) [14][1300/1567] lr: 4.4745e-03 eta: 0:01:58 time: 0.0354 data_time: 0.0071 memory: 1253 loss: 0.0109 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0109 2022/11/29 20:15:25 - mmengine - INFO - Epoch(train) [14][1400/1567] lr: 4.2190e-03 eta: 0:01:54 time: 0.0354 data_time: 0.0063 memory: 1253 loss: 0.0083 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0083 2022/11/29 20:15:29 - mmengine - INFO - Epoch(train) [14][1500/1567] lr: 3.9707e-03 eta: 0:01:51 time: 0.0346 data_time: 0.0065 memory: 1253 loss: 0.0076 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0076 2022/11/29 20:15:31 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:15:31 - mmengine - INFO - Epoch(train) [14][1567/1567] lr: 3.8084e-03 eta: 0:01:48 time: 0.0342 data_time: 0.0061 memory: 1253 loss: 0.2041 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2041 2022/11/29 20:15:31 - mmengine - INFO - Saving checkpoint at 14 epochs 2022/11/29 20:15:33 - mmengine - INFO - Epoch(val) [14][100/129] eta: 0:00:00 time: 0.0150 data_time: 0.0059 memory: 262 2022/11/29 20:15:34 - mmengine - INFO - Epoch(val) [14][129/129] acc/top1: 0.8842 acc/top5: 0.9880 acc/mean1: 0.8840 2022/11/29 20:15:34 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_13.pth is removed 2022/11/29 20:15:34 - mmengine - INFO - The best checkpoint with 0.8842 acc/top1 at 14 epoch is saved to best_acc/top1_epoch_14.pth. 2022/11/29 20:15:36 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:15:38 - mmengine - INFO - Epoch(train) [15][100/1567] lr: 3.5722e-03 eta: 0:01:45 time: 0.0351 data_time: 0.0062 memory: 1253 loss: 0.0118 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0118 2022/11/29 20:15:41 - mmengine - INFO - Epoch(train) [15][200/1567] lr: 3.3433e-03 eta: 0:01:42 time: 0.0348 data_time: 0.0072 memory: 1253 loss: 0.0114 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0114 2022/11/29 20:15:45 - mmengine - INFO - Epoch(train) [15][300/1567] lr: 3.1217e-03 eta: 0:01:38 time: 0.0348 data_time: 0.0068 memory: 1253 loss: 0.0087 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0087 2022/11/29 20:15:48 - mmengine - INFO - Epoch(train) [15][400/1567] lr: 2.9075e-03 eta: 0:01:35 time: 0.0354 data_time: 0.0063 memory: 1253 loss: 0.0085 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0085 2022/11/29 20:15:52 - mmengine - INFO - Epoch(train) [15][500/1567] lr: 2.7007e-03 eta: 0:01:31 time: 0.0350 data_time: 0.0063 memory: 1253 loss: 0.0072 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0072 2022/11/29 20:15:55 - mmengine - INFO - Epoch(train) [15][600/1567] lr: 2.5013e-03 eta: 0:01:28 time: 0.0348 data_time: 0.0064 memory: 1253 loss: 0.0106 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0106 2022/11/29 20:15:59 - mmengine - INFO - Epoch(train) [15][700/1567] lr: 2.3093e-03 eta: 0:01:24 time: 0.0348 data_time: 0.0063 memory: 1253 loss: 0.0129 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0129 2022/11/29 20:16:02 - mmengine - INFO - Epoch(train) [15][800/1567] lr: 2.1249e-03 eta: 0:01:21 time: 0.0343 data_time: 0.0063 memory: 1253 loss: 0.0095 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0095 2022/11/29 20:16:06 - mmengine - INFO - Epoch(train) [15][900/1567] lr: 1.9479e-03 eta: 0:01:17 time: 0.0353 data_time: 0.0063 memory: 1253 loss: 0.0062 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0062 2022/11/29 20:16:10 - mmengine - INFO - Epoch(train) [15][1000/1567] lr: 1.7785e-03 eta: 0:01:14 time: 0.0342 data_time: 0.0063 memory: 1253 loss: 0.0065 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0065 2022/11/29 20:16:12 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:16:13 - mmengine - INFO - Epoch(train) [15][1100/1567] lr: 1.6167e-03 eta: 0:01:10 time: 0.0344 data_time: 0.0064 memory: 1253 loss: 0.0085 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0085 2022/11/29 20:16:16 - mmengine - INFO - Epoch(train) [15][1200/1567] lr: 1.4625e-03 eta: 0:01:07 time: 0.0347 data_time: 0.0067 memory: 1253 loss: 0.0093 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0093 2022/11/29 20:16:20 - mmengine - INFO - Epoch(train) [15][1300/1567] lr: 1.3159e-03 eta: 0:01:03 time: 0.0369 data_time: 0.0071 memory: 1253 loss: 0.0091 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0091 2022/11/29 20:16:23 - mmengine - INFO - Epoch(train) [15][1400/1567] lr: 1.1769e-03 eta: 0:01:00 time: 0.0350 data_time: 0.0063 memory: 1253 loss: 0.0102 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0102 2022/11/29 20:16:27 - mmengine - INFO - Epoch(train) [15][1500/1567] lr: 1.0456e-03 eta: 0:00:56 time: 0.0356 data_time: 0.0064 memory: 1253 loss: 0.0105 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0105 2022/11/29 20:16:29 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:16:29 - mmengine - INFO - Epoch(train) [15][1567/1567] lr: 9.6196e-04 eta: 0:00:54 time: 0.0343 data_time: 0.0063 memory: 1253 loss: 0.1475 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1475 2022/11/29 20:16:29 - mmengine - INFO - Saving checkpoint at 15 epochs 2022/11/29 20:16:31 - mmengine - INFO - Epoch(val) [15][100/129] eta: 0:00:00 time: 0.0152 data_time: 0.0059 memory: 262 2022/11/29 20:16:32 - mmengine - INFO - Epoch(val) [15][129/129] acc/top1: 0.8842 acc/top5: 0.9884 acc/mean1: 0.8840 2022/11/29 20:16:36 - mmengine - INFO - Epoch(train) [16][100/1567] lr: 8.4351e-04 eta: 0:00:51 time: 0.0353 data_time: 0.0064 memory: 1253 loss: 0.0106 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0106 2022/11/29 20:16:39 - mmengine - INFO - Epoch(train) [16][200/1567] lr: 7.3277e-04 eta: 0:00:47 time: 0.0350 data_time: 0.0064 memory: 1253 loss: 0.0114 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0114 2022/11/29 20:16:43 - mmengine - INFO - Epoch(train) [16][300/1567] lr: 6.2978e-04 eta: 0:00:44 time: 0.0350 data_time: 0.0064 memory: 1253 loss: 0.0067 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0067 2022/11/29 20:16:46 - mmengine - INFO - Epoch(train) [16][400/1567] lr: 5.3453e-04 eta: 0:00:40 time: 0.0349 data_time: 0.0066 memory: 1253 loss: 0.0080 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0080 2022/11/29 20:16:49 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:16:50 - mmengine - INFO - Epoch(train) [16][500/1567] lr: 4.4705e-04 eta: 0:00:37 time: 0.0364 data_time: 0.0071 memory: 1253 loss: 0.0073 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0073 2022/11/29 20:16:53 - mmengine - INFO - Epoch(train) [16][600/1567] lr: 3.6735e-04 eta: 0:00:33 time: 0.0351 data_time: 0.0063 memory: 1253 loss: 0.0069 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0069 2022/11/29 20:16:57 - mmengine - INFO - Epoch(train) [16][700/1567] lr: 2.9544e-04 eta: 0:00:30 time: 0.0352 data_time: 0.0063 memory: 1253 loss: 0.0083 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0083 2022/11/29 20:17:00 - mmengine - INFO - Epoch(train) [16][800/1567] lr: 2.3134e-04 eta: 0:00:26 time: 0.0348 data_time: 0.0064 memory: 1253 loss: 0.0083 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0083 2022/11/29 20:17:04 - mmengine - INFO - Epoch(train) [16][900/1567] lr: 1.7505e-04 eta: 0:00:23 time: 0.0343 data_time: 0.0064 memory: 1253 loss: 0.0093 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0093 2022/11/29 20:17:07 - mmengine - INFO - Epoch(train) [16][1000/1567] lr: 1.2658e-04 eta: 0:00:19 time: 0.0353 data_time: 0.0063 memory: 1253 loss: 0.0067 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0067 2022/11/29 20:17:11 - mmengine - INFO - Epoch(train) [16][1100/1567] lr: 8.5947e-05 eta: 0:00:16 time: 0.0342 data_time: 0.0064 memory: 1253 loss: 0.0091 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0091 2022/11/29 20:17:14 - mmengine - INFO - Epoch(train) [16][1200/1567] lr: 5.3147e-05 eta: 0:00:12 time: 0.0345 data_time: 0.0063 memory: 1253 loss: 0.0097 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0097 2022/11/29 20:17:18 - mmengine - INFO - Epoch(train) [16][1300/1567] lr: 2.8190e-05 eta: 0:00:09 time: 0.0347 data_time: 0.0063 memory: 1253 loss: 0.0070 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0070 2022/11/29 20:17:21 - mmengine - INFO - Epoch(train) [16][1400/1567] lr: 1.1078e-05 eta: 0:00:05 time: 0.0353 data_time: 0.0063 memory: 1253 loss: 0.0143 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0143 2022/11/29 20:17:25 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:17:25 - mmengine - INFO - Epoch(train) [16][1500/1567] lr: 1.8150e-06 eta: 0:00:02 time: 0.0346 data_time: 0.0064 memory: 1253 loss: 0.0090 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0090 2022/11/29 20:17:27 - mmengine - INFO - Exp name: stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221129_200132 2022/11/29 20:17:27 - mmengine - INFO - Epoch(train) [16][1567/1567] lr: 3.9252e-10 eta: 0:00:00 time: 0.0342 data_time: 0.0061 memory: 1253 loss: 0.1810 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1810 2022/11/29 20:17:27 - mmengine - INFO - Saving checkpoint at 16 epochs 2022/11/29 20:17:29 - mmengine - INFO - Epoch(val) [16][100/129] eta: 0:00:00 time: 0.0150 data_time: 0.0059 memory: 262 2022/11/29 20:17:30 - mmengine - INFO - Epoch(val) [16][129/129] acc/top1: 0.8855 acc/top5: 0.9878 acc/mean1: 0.8854 2022/11/29 20:17:30 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_14.pth is removed 2022/11/29 20:17:30 - mmengine - INFO - The best checkpoint with 0.8855 acc/top1 at 16 epoch is saved to best_acc/top1_epoch_16.pth.