2022/11/28 14:24:06 - 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: 1011338256 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 14:24:06 - 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=['jm']), 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=['jm']), dict( type='UniformSampleFrames', clip_len=100, num_clips=1, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ] test_pipeline = [ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['jm']), dict( type='UniformSampleFrames', clip_len=100, num_clips=10, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ] train_dataloader = dict( batch_size=16, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=True), dataset=dict( type='RepeatDataset', times=5, dataset=dict( type='PoseDataset', ann_file='data/skeleton/ntu60_2d.pkl', pipeline=[ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['jm']), dict(type='UniformSampleFrames', clip_len=100), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ], split='xsub_train'))) val_dataloader = dict( batch_size=16, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='PoseDataset', ann_file='data/skeleton/ntu60_2d.pkl', pipeline=[ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['jm']), dict( type='UniformSampleFrames', clip_len=100, num_clips=1, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ], split='xsub_val', test_mode=True)) test_dataloader = dict( batch_size=1, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='PoseDataset', ann_file='data/skeleton/ntu60_2d.pkl', pipeline=[ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['jm']), dict( type='UniformSampleFrames', clip_len=100, num_clips=10, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ], split='xsub_val', test_mode=True)) val_evaluator = [dict(type='AccMetric')] test_evaluator = [dict(type='AccMetric')] train_cfg = dict( type='EpochBasedTrainLoop', max_epochs=16, val_begin=1, val_interval=1) val_cfg = dict(type='ValLoop') test_cfg = dict(type='TestLoop') param_scheduler = [ dict( type='CosineAnnealingLR', eta_min=0, T_max=16, by_epoch=True, convert_to_iter_based=True) ] optim_wrapper = dict( optimizer=dict( type='SGD', lr=0.1, momentum=0.9, weight_decay=0.0005, nesterov=True)) auto_scale_lr = dict(enable=False, base_batch_size=128) launcher = 'pytorch' work_dir = './work_dirs/stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d' randomness = dict(seed=None, diff_rank_seed=False, deterministic=False) 2022/11/28 14:24:06 - mmengine - INFO - Result has been saved to /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-motion-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 2022/11/28 14:24:38 - mmengine - INFO - Checkpoints will be saved to /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d. 2022/11/28 14:24:43 - mmengine - INFO - Epoch(train) [1][100/1567] lr: 9.9996e-02 eta: 0:21:55 time: 0.0336 data_time: 0.0060 memory: 1253 loss: 2.9743 top1_acc: 0.0000 top5_acc: 0.3125 loss_cls: 2.9743 2022/11/28 14:24:46 - mmengine - INFO - Epoch(train) [1][200/1567] lr: 9.9984e-02 eta: 0:17:59 time: 0.0342 data_time: 0.0059 memory: 1253 loss: 2.3750 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.3750 2022/11/28 14:24:50 - mmengine - INFO - Epoch(train) [1][300/1567] lr: 9.9965e-02 eta: 0:16:38 time: 0.0338 data_time: 0.0059 memory: 1253 loss: 1.8116 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.8116 2022/11/28 14:24:53 - mmengine - INFO - Epoch(train) [1][400/1567] lr: 9.9938e-02 eta: 0:15:55 time: 0.0341 data_time: 0.0058 memory: 1253 loss: 1.4046 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.4046 2022/11/28 14:24:56 - mmengine - INFO - Epoch(train) [1][500/1567] lr: 9.9902e-02 eta: 0:15:29 time: 0.0340 data_time: 0.0059 memory: 1253 loss: 1.3231 top1_acc: 0.5000 top5_acc: 1.0000 loss_cls: 1.3231 2022/11/28 14:25:00 - mmengine - INFO - Epoch(train) [1][600/1567] lr: 9.9859e-02 eta: 0:15:08 time: 0.0335 data_time: 0.0059 memory: 1253 loss: 1.1084 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.1084 2022/11/28 14:25:03 - mmengine - INFO - Epoch(train) [1][700/1567] lr: 9.9808e-02 eta: 0:14:54 time: 0.0336 data_time: 0.0059 memory: 1253 loss: 1.0031 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 1.0031 2022/11/28 14:25:07 - mmengine - INFO - Epoch(train) [1][800/1567] lr: 9.9750e-02 eta: 0:14:43 time: 0.0339 data_time: 0.0059 memory: 1253 loss: 0.9392 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9392 2022/11/28 14:25:10 - mmengine - INFO - Epoch(train) [1][900/1567] lr: 9.9683e-02 eta: 0:14:32 time: 0.0338 data_time: 0.0059 memory: 1253 loss: 0.8766 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8766 2022/11/28 14:25:13 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:25:13 - mmengine - INFO - Epoch(train) [1][1000/1567] lr: 9.9609e-02 eta: 0:14:23 time: 0.0337 data_time: 0.0058 memory: 1253 loss: 0.7598 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.7598 2022/11/28 14:25:17 - mmengine - INFO - Epoch(train) [1][1100/1567] lr: 9.9527e-02 eta: 0:14:15 time: 0.0337 data_time: 0.0059 memory: 1253 loss: 0.8635 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.8635 2022/11/28 14:25:20 - mmengine - INFO - Epoch(train) [1][1200/1567] lr: 9.9437e-02 eta: 0:14:07 time: 0.0333 data_time: 0.0059 memory: 1253 loss: 0.9243 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.9243 2022/11/28 14:25:24 - mmengine - INFO - Epoch(train) [1][1300/1567] lr: 9.9339e-02 eta: 0:14:00 time: 0.0338 data_time: 0.0059 memory: 1253 loss: 0.7854 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.7854 2022/11/28 14:25:27 - mmengine - INFO - Epoch(train) [1][1400/1567] lr: 9.9234e-02 eta: 0:13:54 time: 0.0335 data_time: 0.0059 memory: 1253 loss: 0.7231 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.7231 2022/11/28 14:25:30 - mmengine - INFO - Epoch(train) [1][1500/1567] lr: 9.9121e-02 eta: 0:13:48 time: 0.0333 data_time: 0.0059 memory: 1253 loss: 0.7104 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.7104 2022/11/28 14:25:33 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:25:33 - mmengine - INFO - Epoch(train) [1][1567/1567] lr: 9.9040e-02 eta: 0:13:45 time: 0.0354 data_time: 0.0057 memory: 1253 loss: 0.8541 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.8541 2022/11/28 14:25:33 - mmengine - INFO - Saving checkpoint at 1 epochs 2022/11/28 14:25:35 - mmengine - INFO - Epoch(val) [1][100/129] eta: 0:00:00 time: 0.0148 data_time: 0.0057 memory: 262 2022/11/28 14:25:35 - mmengine - INFO - Epoch(val) [1][129/129] acc/top1: 0.5520 acc/top5: 0.8738 acc/mean1: 0.5517 2022/11/28 14:25:36 - mmengine - INFO - The best checkpoint with 0.5520 acc/top1 at 1 epoch is saved to best_acc/top1_epoch_1.pth. 2022/11/28 14:25:39 - mmengine - INFO - Epoch(train) [2][100/1567] lr: 9.8914e-02 eta: 0:13:42 time: 0.0343 data_time: 0.0059 memory: 1253 loss: 0.5683 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5683 2022/11/28 14:25:43 - mmengine - INFO - Epoch(train) [2][200/1567] lr: 9.8781e-02 eta: 0:13:37 time: 0.0337 data_time: 0.0060 memory: 1253 loss: 0.7007 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.7007 2022/11/28 14:25:46 - mmengine - INFO - Epoch(train) [2][300/1567] lr: 9.8639e-02 eta: 0:13:32 time: 0.0334 data_time: 0.0060 memory: 1253 loss: 0.6005 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.6005 2022/11/28 14:25:49 - mmengine - INFO - Epoch(train) [2][400/1567] lr: 9.8491e-02 eta: 0:13:27 time: 0.0351 data_time: 0.0059 memory: 1253 loss: 0.5513 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5513 2022/11/28 14:25:51 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:25:53 - mmengine - INFO - Epoch(train) [2][500/1567] lr: 9.8334e-02 eta: 0:13:24 time: 0.0346 data_time: 0.0059 memory: 1253 loss: 0.6716 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.6716 2022/11/28 14:25:56 - mmengine - INFO - Epoch(train) [2][600/1567] lr: 9.8170e-02 eta: 0:13:20 time: 0.0336 data_time: 0.0060 memory: 1253 loss: 0.5860 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5860 2022/11/28 14:26:00 - mmengine - INFO - Epoch(train) [2][700/1567] lr: 9.7998e-02 eta: 0:13:15 time: 0.0333 data_time: 0.0059 memory: 1253 loss: 0.7267 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.7267 2022/11/28 14:26:03 - mmengine - INFO - Epoch(train) [2][800/1567] lr: 9.7819e-02 eta: 0:13:10 time: 0.0335 data_time: 0.0061 memory: 1253 loss: 0.5230 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5230 2022/11/28 14:26:06 - mmengine - INFO - Epoch(train) [2][900/1567] lr: 9.7632e-02 eta: 0:13:06 time: 0.0336 data_time: 0.0060 memory: 1253 loss: 0.6181 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.6181 2022/11/28 14:26:10 - mmengine - INFO - Epoch(train) [2][1000/1567] lr: 9.7438e-02 eta: 0:13:02 time: 0.0339 data_time: 0.0063 memory: 1253 loss: 0.5777 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5777 2022/11/28 14:26:13 - mmengine - INFO - Epoch(train) [2][1100/1567] lr: 9.7236e-02 eta: 0:12:59 time: 0.0361 data_time: 0.0061 memory: 1253 loss: 0.5165 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.5165 2022/11/28 14:26:17 - mmengine - INFO - Epoch(train) [2][1200/1567] lr: 9.7027e-02 eta: 0:12:56 time: 0.0340 data_time: 0.0061 memory: 1253 loss: 0.5628 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.5628 2022/11/28 14:26:20 - mmengine - INFO - Epoch(train) [2][1300/1567] lr: 9.6810e-02 eta: 0:12:52 time: 0.0360 data_time: 0.0060 memory: 1253 loss: 0.5675 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5675 2022/11/28 14:26:24 - mmengine - INFO - Epoch(train) [2][1400/1567] lr: 9.6587e-02 eta: 0:12:49 time: 0.0355 data_time: 0.0064 memory: 1253 loss: 0.5938 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.5938 2022/11/28 14:26:25 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:26:27 - mmengine - INFO - Epoch(train) [2][1500/1567] lr: 9.6355e-02 eta: 0:12:45 time: 0.0340 data_time: 0.0060 memory: 1253 loss: 0.4752 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4752 2022/11/28 14:26:30 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:26:30 - mmengine - INFO - Epoch(train) [2][1567/1567] lr: 9.6196e-02 eta: 0:12:43 time: 0.0343 data_time: 0.0058 memory: 1253 loss: 0.7184 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.7184 2022/11/28 14:26:30 - mmengine - INFO - Saving checkpoint at 2 epochs 2022/11/28 14:26:32 - mmengine - INFO - Epoch(val) [2][100/129] eta: 0:00:00 time: 0.0150 data_time: 0.0059 memory: 262 2022/11/28 14:26:32 - mmengine - INFO - Epoch(val) [2][129/129] acc/top1: 0.5144 acc/top5: 0.8290 acc/mean1: 0.5140 2022/11/28 14:26:36 - mmengine - INFO - Epoch(train) [3][100/1567] lr: 9.5953e-02 eta: 0:12:39 time: 0.0344 data_time: 0.0060 memory: 1253 loss: 0.5576 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.5576 2022/11/28 14:26:39 - mmengine - INFO - Epoch(train) [3][200/1567] lr: 9.5703e-02 eta: 0:12:36 time: 0.0347 data_time: 0.0065 memory: 1253 loss: 0.4930 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4930 2022/11/28 14:26:43 - mmengine - INFO - Epoch(train) [3][300/1567] lr: 9.5445e-02 eta: 0:12:32 time: 0.0345 data_time: 0.0063 memory: 1253 loss: 0.6450 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.6450 2022/11/28 14:26:46 - mmengine - INFO - Epoch(train) [3][400/1567] lr: 9.5180e-02 eta: 0:12:28 time: 0.0336 data_time: 0.0062 memory: 1253 loss: 0.5031 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.5031 2022/11/28 14:26:49 - mmengine - INFO - Epoch(train) [3][500/1567] lr: 9.4908e-02 eta: 0:12:24 time: 0.0334 data_time: 0.0060 memory: 1253 loss: 0.5709 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5709 2022/11/28 14:26:53 - mmengine - INFO - Epoch(train) [3][600/1567] lr: 9.4629e-02 eta: 0:12:20 time: 0.0335 data_time: 0.0060 memory: 1253 loss: 0.5276 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5276 2022/11/28 14:26:56 - mmengine - INFO - Epoch(train) [3][700/1567] lr: 9.4343e-02 eta: 0:12:16 time: 0.0347 data_time: 0.0060 memory: 1253 loss: 0.5134 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5134 2022/11/28 14:27:00 - mmengine - INFO - Epoch(train) [3][800/1567] lr: 9.4050e-02 eta: 0:12:13 time: 0.0340 data_time: 0.0061 memory: 1253 loss: 0.4979 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4979 2022/11/28 14:27:02 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:27:03 - mmengine - INFO - Epoch(train) [3][900/1567] lr: 9.3750e-02 eta: 0:12:09 time: 0.0340 data_time: 0.0063 memory: 1253 loss: 0.4838 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4838 2022/11/28 14:27:07 - mmengine - INFO - Epoch(train) [3][1000/1567] lr: 9.3444e-02 eta: 0:12:05 time: 0.0331 data_time: 0.0060 memory: 1253 loss: 0.4642 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4642 2022/11/28 14:27:10 - mmengine - INFO - Epoch(train) [3][1100/1567] lr: 9.3130e-02 eta: 0:12:01 time: 0.0344 data_time: 0.0061 memory: 1253 loss: 0.4435 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4435 2022/11/28 14:27:13 - mmengine - INFO - Epoch(train) [3][1200/1567] lr: 9.2810e-02 eta: 0:11:57 time: 0.0333 data_time: 0.0061 memory: 1253 loss: 0.4382 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4382 2022/11/28 14:27:17 - mmengine - INFO - Epoch(train) [3][1300/1567] lr: 9.2483e-02 eta: 0:11:54 time: 0.0335 data_time: 0.0060 memory: 1253 loss: 0.4062 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.4062 2022/11/28 14:27:20 - mmengine - INFO - Epoch(train) [3][1400/1567] lr: 9.2149e-02 eta: 0:11:50 time: 0.0332 data_time: 0.0060 memory: 1253 loss: 0.4054 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4054 2022/11/28 14:27:23 - mmengine - INFO - Epoch(train) [3][1500/1567] lr: 9.1809e-02 eta: 0:11:46 time: 0.0331 data_time: 0.0060 memory: 1253 loss: 0.4725 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4725 2022/11/28 14:27:26 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:27:26 - mmengine - INFO - Epoch(train) [3][1567/1567] lr: 9.1577e-02 eta: 0:11:43 time: 0.0325 data_time: 0.0058 memory: 1253 loss: 0.7655 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.7655 2022/11/28 14:27:26 - mmengine - INFO - Saving checkpoint at 3 epochs 2022/11/28 14:27:28 - mmengine - INFO - Epoch(val) [3][100/129] eta: 0:00:00 time: 0.0148 data_time: 0.0057 memory: 262 2022/11/28 14:27:28 - mmengine - INFO - Epoch(val) [3][129/129] acc/top1: 0.4428 acc/top5: 0.8006 acc/mean1: 0.4423 2022/11/28 14:27:32 - mmengine - INFO - Epoch(train) [4][100/1567] lr: 9.1226e-02 eta: 0:11:40 time: 0.0348 data_time: 0.0064 memory: 1253 loss: 0.4293 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4293 2022/11/28 14:27:35 - mmengine - INFO - Epoch(train) [4][200/1567] lr: 9.0868e-02 eta: 0:11:37 time: 0.0337 data_time: 0.0060 memory: 1253 loss: 0.4624 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4624 2022/11/28 14:27:39 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:27:39 - mmengine - INFO - Epoch(train) [4][300/1567] lr: 9.0504e-02 eta: 0:11:33 time: 0.0342 data_time: 0.0062 memory: 1253 loss: 0.4580 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4580 2022/11/28 14:27:42 - mmengine - INFO - Epoch(train) [4][400/1567] lr: 9.0133e-02 eta: 0:11:29 time: 0.0333 data_time: 0.0060 memory: 1253 loss: 0.5396 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.5396 2022/11/28 14:27:45 - mmengine - INFO - Epoch(train) [4][500/1567] lr: 8.9756e-02 eta: 0:11:25 time: 0.0332 data_time: 0.0060 memory: 1253 loss: 0.4451 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4451 2022/11/28 14:27:49 - mmengine - INFO - Epoch(train) [4][600/1567] lr: 8.9373e-02 eta: 0:11:22 time: 0.0353 data_time: 0.0060 memory: 1253 loss: 0.4709 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4709 2022/11/28 14:27:52 - mmengine - INFO - Epoch(train) [4][700/1567] lr: 8.8984e-02 eta: 0:11:19 time: 0.0348 data_time: 0.0060 memory: 1253 loss: 0.5184 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.5184 2022/11/28 14:27:56 - mmengine - INFO - Epoch(train) [4][800/1567] lr: 8.8589e-02 eta: 0:11:15 time: 0.0339 data_time: 0.0060 memory: 1253 loss: 0.4464 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4464 2022/11/28 14:27:59 - mmengine - INFO - Epoch(train) [4][900/1567] lr: 8.8187e-02 eta: 0:11:12 time: 0.0340 data_time: 0.0060 memory: 1253 loss: 0.4315 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4315 2022/11/28 14:28:03 - mmengine - INFO - Epoch(train) [4][1000/1567] lr: 8.7780e-02 eta: 0:11:08 time: 0.0337 data_time: 0.0060 memory: 1253 loss: 0.4068 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4068 2022/11/28 14:28:06 - mmengine - INFO - Epoch(train) [4][1100/1567] lr: 8.7367e-02 eta: 0:11:04 time: 0.0340 data_time: 0.0062 memory: 1253 loss: 0.4070 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4070 2022/11/28 14:28:09 - mmengine - INFO - Epoch(train) [4][1200/1567] lr: 8.6947e-02 eta: 0:11:01 time: 0.0347 data_time: 0.0068 memory: 1253 loss: 0.4754 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4754 2022/11/28 14:28:13 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:28:13 - mmengine - INFO - Epoch(train) [4][1300/1567] lr: 8.6522e-02 eta: 0:10:57 time: 0.0337 data_time: 0.0061 memory: 1253 loss: 0.4006 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4006 2022/11/28 14:28:16 - mmengine - INFO - Epoch(train) [4][1400/1567] lr: 8.6092e-02 eta: 0:10:54 time: 0.0339 data_time: 0.0061 memory: 1253 loss: 0.4490 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4490 2022/11/28 14:28:20 - mmengine - INFO - Epoch(train) [4][1500/1567] lr: 8.5655e-02 eta: 0:10:50 time: 0.0333 data_time: 0.0061 memory: 1253 loss: 0.3995 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3995 2022/11/28 14:28:22 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:28:22 - mmengine - INFO - Epoch(train) [4][1567/1567] lr: 8.5360e-02 eta: 0:10:48 time: 0.0329 data_time: 0.0058 memory: 1253 loss: 0.5416 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.5416 2022/11/28 14:28:22 - mmengine - INFO - Saving checkpoint at 4 epochs 2022/11/28 14:28:24 - mmengine - INFO - Epoch(val) [4][100/129] eta: 0:00:00 time: 0.0157 data_time: 0.0062 memory: 262 2022/11/28 14:28:24 - mmengine - INFO - Epoch(val) [4][129/129] acc/top1: 0.6543 acc/top5: 0.9187 acc/mean1: 0.6541 2022/11/28 14:28:24 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_1.pth is removed 2022/11/28 14:28:25 - mmengine - INFO - The best checkpoint with 0.6543 acc/top1 at 4 epoch is saved to best_acc/top1_epoch_4.pth. 2022/11/28 14:28:28 - mmengine - INFO - Epoch(train) [5][100/1567] lr: 8.4914e-02 eta: 0:10:44 time: 0.0334 data_time: 0.0060 memory: 1253 loss: 0.3324 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.3324 2022/11/28 14:28:32 - mmengine - INFO - Epoch(train) [5][200/1567] lr: 8.4463e-02 eta: 0:10:40 time: 0.0341 data_time: 0.0060 memory: 1253 loss: 0.4240 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4240 2022/11/28 14:28:35 - mmengine - INFO - Epoch(train) [5][300/1567] lr: 8.4006e-02 eta: 0:10:37 time: 0.0332 data_time: 0.0060 memory: 1253 loss: 0.3793 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3793 2022/11/28 14:28:38 - mmengine - INFO - Epoch(train) [5][400/1567] lr: 8.3544e-02 eta: 0:10:33 time: 0.0345 data_time: 0.0060 memory: 1253 loss: 0.3391 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3391 2022/11/28 14:28:42 - mmengine - INFO - Epoch(train) [5][500/1567] lr: 8.3077e-02 eta: 0:10:30 time: 0.0355 data_time: 0.0067 memory: 1253 loss: 0.4238 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4238 2022/11/28 14:28:45 - mmengine - INFO - Epoch(train) [5][600/1567] lr: 8.2605e-02 eta: 0:10:27 time: 0.0335 data_time: 0.0061 memory: 1253 loss: 0.2829 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2829 2022/11/28 14:28:49 - mmengine - INFO - Epoch(train) [5][700/1567] lr: 8.2127e-02 eta: 0:10:23 time: 0.0338 data_time: 0.0060 memory: 1253 loss: 0.4023 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4023 2022/11/28 14:28:50 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:28:52 - mmengine - INFO - Epoch(train) [5][800/1567] lr: 8.1645e-02 eta: 0:10:20 time: 0.0333 data_time: 0.0060 memory: 1253 loss: 0.4192 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4192 2022/11/28 14:28:56 - mmengine - INFO - Epoch(train) [5][900/1567] lr: 8.1157e-02 eta: 0:10:16 time: 0.0351 data_time: 0.0069 memory: 1253 loss: 0.4056 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.4056 2022/11/28 14:28:59 - mmengine - INFO - Epoch(train) [5][1000/1567] lr: 8.0665e-02 eta: 0:10:13 time: 0.0333 data_time: 0.0060 memory: 1253 loss: 0.3294 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3294 2022/11/28 14:29:03 - mmengine - INFO - Epoch(train) [5][1100/1567] lr: 8.0167e-02 eta: 0:10:09 time: 0.0345 data_time: 0.0060 memory: 1253 loss: 0.3597 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3597 2022/11/28 14:29:06 - mmengine - INFO - Epoch(train) [5][1200/1567] lr: 7.9665e-02 eta: 0:10:05 time: 0.0331 data_time: 0.0060 memory: 1253 loss: 0.4161 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4161 2022/11/28 14:29:09 - mmengine - INFO - Epoch(train) [5][1300/1567] lr: 7.9159e-02 eta: 0:10:02 time: 0.0351 data_time: 0.0060 memory: 1253 loss: 0.3290 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3290 2022/11/28 14:29:13 - mmengine - INFO - Epoch(train) [5][1400/1567] lr: 7.8647e-02 eta: 0:09:59 time: 0.0351 data_time: 0.0060 memory: 1253 loss: 0.3556 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3556 2022/11/28 14:29:16 - mmengine - INFO - Epoch(train) [5][1500/1567] lr: 7.8132e-02 eta: 0:09:55 time: 0.0335 data_time: 0.0060 memory: 1253 loss: 0.4189 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4189 2022/11/28 14:29:18 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:29:18 - mmengine - INFO - Epoch(train) [5][1567/1567] lr: 7.7784e-02 eta: 0:09:53 time: 0.0328 data_time: 0.0059 memory: 1253 loss: 0.5270 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.5270 2022/11/28 14:29:18 - mmengine - INFO - Saving checkpoint at 5 epochs 2022/11/28 14:29:20 - mmengine - INFO - Epoch(val) [5][100/129] eta: 0:00:00 time: 0.0148 data_time: 0.0057 memory: 262 2022/11/28 14:29:21 - mmengine - INFO - Epoch(val) [5][129/129] acc/top1: 0.5156 acc/top5: 0.8816 acc/mean1: 0.5155 2022/11/28 14:29:25 - mmengine - INFO - Epoch(train) [6][100/1567] lr: 7.7261e-02 eta: 0:09:49 time: 0.0357 data_time: 0.0061 memory: 1253 loss: 0.3970 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3970 2022/11/28 14:29:27 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:29:28 - mmengine - INFO - Epoch(train) [6][200/1567] lr: 7.6733e-02 eta: 0:09:46 time: 0.0343 data_time: 0.0061 memory: 1253 loss: 0.4549 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.4549 2022/11/28 14:29:31 - mmengine - INFO - Epoch(train) [6][300/1567] lr: 7.6202e-02 eta: 0:09:42 time: 0.0347 data_time: 0.0060 memory: 1253 loss: 0.3413 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3413 2022/11/28 14:29:35 - mmengine - INFO - Epoch(train) [6][400/1567] lr: 7.5666e-02 eta: 0:09:39 time: 0.0351 data_time: 0.0061 memory: 1253 loss: 0.2870 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2870 2022/11/28 14:29:38 - mmengine - INFO - Epoch(train) [6][500/1567] lr: 7.5126e-02 eta: 0:09:36 time: 0.0338 data_time: 0.0061 memory: 1253 loss: 0.3523 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3523 2022/11/28 14:29:42 - mmengine - INFO - Epoch(train) [6][600/1567] lr: 7.4583e-02 eta: 0:09:32 time: 0.0355 data_time: 0.0062 memory: 1253 loss: 0.2814 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2814 2022/11/28 14:29:45 - mmengine - INFO - Epoch(train) [6][700/1567] lr: 7.4035e-02 eta: 0:09:29 time: 0.0349 data_time: 0.0059 memory: 1253 loss: 0.3380 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3380 2022/11/28 14:29:49 - mmengine - INFO - Epoch(train) [6][800/1567] lr: 7.3484e-02 eta: 0:09:26 time: 0.0360 data_time: 0.0060 memory: 1253 loss: 0.3636 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3636 2022/11/28 14:29:52 - mmengine - INFO - Epoch(train) [6][900/1567] lr: 7.2929e-02 eta: 0:09:22 time: 0.0336 data_time: 0.0060 memory: 1253 loss: 0.3673 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.3673 2022/11/28 14:29:56 - mmengine - INFO - Epoch(train) [6][1000/1567] lr: 7.2371e-02 eta: 0:09:19 time: 0.0354 data_time: 0.0060 memory: 1253 loss: 0.2871 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2871 2022/11/28 14:29:59 - mmengine - INFO - Epoch(train) [6][1100/1567] lr: 7.1809e-02 eta: 0:09:16 time: 0.0342 data_time: 0.0060 memory: 1253 loss: 0.3006 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.3006 2022/11/28 14:30:02 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:30:03 - mmengine - INFO - Epoch(train) [6][1200/1567] lr: 7.1243e-02 eta: 0:09:12 time: 0.0342 data_time: 0.0062 memory: 1253 loss: 0.4025 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4025 2022/11/28 14:30:06 - mmengine - INFO - Epoch(train) [6][1300/1567] lr: 7.0674e-02 eta: 0:09:09 time: 0.0334 data_time: 0.0059 memory: 1253 loss: 0.3866 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3866 2022/11/28 14:30:10 - mmengine - INFO - Epoch(train) [6][1400/1567] lr: 7.0102e-02 eta: 0:09:05 time: 0.0354 data_time: 0.0060 memory: 1253 loss: 0.3541 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3541 2022/11/28 14:30:13 - mmengine - INFO - Epoch(train) [6][1500/1567] lr: 6.9527e-02 eta: 0:09:02 time: 0.0340 data_time: 0.0062 memory: 1253 loss: 0.3291 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3291 2022/11/28 14:30:15 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:30:15 - mmengine - INFO - Epoch(train) [6][1567/1567] lr: 6.9140e-02 eta: 0:08:59 time: 0.0327 data_time: 0.0057 memory: 1253 loss: 0.5231 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.5231 2022/11/28 14:30:15 - mmengine - INFO - Saving checkpoint at 6 epochs 2022/11/28 14:30:17 - mmengine - INFO - Epoch(val) [6][100/129] eta: 0:00:00 time: 0.0149 data_time: 0.0058 memory: 262 2022/11/28 14:30:18 - mmengine - INFO - Epoch(val) [6][129/129] acc/top1: 0.6845 acc/top5: 0.9475 acc/mean1: 0.6843 2022/11/28 14:30:18 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_4.pth is removed 2022/11/28 14:30:18 - mmengine - INFO - The best checkpoint with 0.6845 acc/top1 at 6 epoch is saved to best_acc/top1_epoch_6.pth. 2022/11/28 14:30:22 - mmengine - INFO - Epoch(train) [7][100/1567] lr: 6.8560e-02 eta: 0:08:56 time: 0.0340 data_time: 0.0060 memory: 1253 loss: 0.3594 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3594 2022/11/28 14:30:25 - mmengine - INFO - Epoch(train) [7][200/1567] lr: 6.7976e-02 eta: 0:08:53 time: 0.0348 data_time: 0.0061 memory: 1253 loss: 0.2911 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2911 2022/11/28 14:30:29 - mmengine - INFO - Epoch(train) [7][300/1567] lr: 6.7390e-02 eta: 0:08:49 time: 0.0342 data_time: 0.0060 memory: 1253 loss: 0.3318 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3318 2022/11/28 14:30:32 - mmengine - INFO - Epoch(train) [7][400/1567] lr: 6.6802e-02 eta: 0:08:46 time: 0.0346 data_time: 0.0059 memory: 1253 loss: 0.3711 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3711 2022/11/28 14:30:36 - mmengine - INFO - Epoch(train) [7][500/1567] lr: 6.6210e-02 eta: 0:08:42 time: 0.0338 data_time: 0.0061 memory: 1253 loss: 0.3123 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.3123 2022/11/28 14:30:39 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:30:39 - mmengine - INFO - Epoch(train) [7][600/1567] lr: 6.5616e-02 eta: 0:08:39 time: 0.0349 data_time: 0.0062 memory: 1253 loss: 0.2856 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2856 2022/11/28 14:30:43 - mmengine - INFO - Epoch(train) [7][700/1567] lr: 6.5020e-02 eta: 0:08:36 time: 0.0349 data_time: 0.0060 memory: 1253 loss: 0.3788 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3788 2022/11/28 14:30:46 - mmengine - INFO - Epoch(train) [7][800/1567] lr: 6.4421e-02 eta: 0:08:32 time: 0.0337 data_time: 0.0061 memory: 1253 loss: 0.3623 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3623 2022/11/28 14:30:50 - mmengine - INFO - Epoch(train) [7][900/1567] lr: 6.3820e-02 eta: 0:08:29 time: 0.0359 data_time: 0.0068 memory: 1253 loss: 0.2956 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2956 2022/11/28 14:30:53 - mmengine - INFO - Epoch(train) [7][1000/1567] lr: 6.3217e-02 eta: 0:08:25 time: 0.0345 data_time: 0.0059 memory: 1253 loss: 0.2543 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2543 2022/11/28 14:30:56 - mmengine - INFO - Epoch(train) [7][1100/1567] lr: 6.2612e-02 eta: 0:08:22 time: 0.0339 data_time: 0.0061 memory: 1253 loss: 0.2468 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2468 2022/11/28 14:31:00 - mmengine - INFO - Epoch(train) [7][1200/1567] lr: 6.2005e-02 eta: 0:08:18 time: 0.0341 data_time: 0.0060 memory: 1253 loss: 0.3844 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3844 2022/11/28 14:31:03 - mmengine - INFO - Epoch(train) [7][1300/1567] lr: 6.1396e-02 eta: 0:08:15 time: 0.0338 data_time: 0.0060 memory: 1253 loss: 0.2505 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2505 2022/11/28 14:31:07 - mmengine - INFO - Epoch(train) [7][1400/1567] lr: 6.0785e-02 eta: 0:08:11 time: 0.0358 data_time: 0.0061 memory: 1253 loss: 0.2697 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2697 2022/11/28 14:31:10 - mmengine - INFO - Epoch(train) [7][1500/1567] lr: 6.0172e-02 eta: 0:08:08 time: 0.0346 data_time: 0.0060 memory: 1253 loss: 0.2475 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2475 2022/11/28 14:31:13 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:31:13 - mmengine - INFO - Epoch(train) [7][1567/1567] lr: 5.9761e-02 eta: 0:08:06 time: 0.0339 data_time: 0.0058 memory: 1253 loss: 0.4651 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.4651 2022/11/28 14:31:13 - mmengine - INFO - Saving checkpoint at 7 epochs 2022/11/28 14:31:14 - mmengine - INFO - Epoch(val) [7][100/129] eta: 0:00:00 time: 0.0149 data_time: 0.0057 memory: 262 2022/11/28 14:31:15 - mmengine - INFO - Epoch(val) [7][129/129] acc/top1: 0.6967 acc/top5: 0.9325 acc/mean1: 0.6965 2022/11/28 14:31:15 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_6.pth is removed 2022/11/28 14:31:15 - mmengine - INFO - The best checkpoint with 0.6967 acc/top1 at 7 epoch is saved to best_acc/top1_epoch_7.pth. 2022/11/28 14:31:16 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:31:19 - mmengine - INFO - Epoch(train) [8][100/1567] lr: 5.9145e-02 eta: 0:08:02 time: 0.0342 data_time: 0.0060 memory: 1253 loss: 0.2514 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2514 2022/11/28 14:31:22 - mmengine - INFO - Epoch(train) [8][200/1567] lr: 5.8529e-02 eta: 0:07:59 time: 0.0341 data_time: 0.0067 memory: 1253 loss: 0.2354 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2354 2022/11/28 14:31:26 - mmengine - INFO - Epoch(train) [8][300/1567] lr: 5.7911e-02 eta: 0:07:55 time: 0.0349 data_time: 0.0061 memory: 1253 loss: 0.3047 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3047 2022/11/28 14:31:29 - mmengine - INFO - Epoch(train) [8][400/1567] lr: 5.7292e-02 eta: 0:07:52 time: 0.0340 data_time: 0.0060 memory: 1253 loss: 0.2939 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.2939 2022/11/28 14:31:33 - mmengine - INFO - Epoch(train) [8][500/1567] lr: 5.6671e-02 eta: 0:07:48 time: 0.0345 data_time: 0.0061 memory: 1253 loss: 0.2588 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2588 2022/11/28 14:31:36 - mmengine - INFO - Epoch(train) [8][600/1567] lr: 5.6050e-02 eta: 0:07:45 time: 0.0339 data_time: 0.0062 memory: 1253 loss: 0.2789 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2789 2022/11/28 14:31:39 - mmengine - INFO - Epoch(train) [8][700/1567] lr: 5.5427e-02 eta: 0:07:42 time: 0.0359 data_time: 0.0068 memory: 1253 loss: 0.2639 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2639 2022/11/28 14:31:43 - mmengine - INFO - Epoch(train) [8][800/1567] lr: 5.4804e-02 eta: 0:07:38 time: 0.0344 data_time: 0.0063 memory: 1253 loss: 0.2465 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2465 2022/11/28 14:31:46 - mmengine - INFO - Epoch(train) [8][900/1567] lr: 5.4180e-02 eta: 0:07:35 time: 0.0338 data_time: 0.0063 memory: 1253 loss: 0.2876 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2876 2022/11/28 14:31:50 - mmengine - INFO - Epoch(train) [8][1000/1567] lr: 5.3556e-02 eta: 0:07:31 time: 0.0338 data_time: 0.0060 memory: 1253 loss: 0.2554 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2554 2022/11/28 14:31:51 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:31:53 - mmengine - INFO - Epoch(train) [8][1100/1567] lr: 5.2930e-02 eta: 0:07:28 time: 0.0338 data_time: 0.0060 memory: 1253 loss: 0.1827 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1827 2022/11/28 14:31:57 - mmengine - INFO - Epoch(train) [8][1200/1567] lr: 5.2305e-02 eta: 0:07:24 time: 0.0354 data_time: 0.0065 memory: 1253 loss: 0.2133 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2133 2022/11/28 14:32:00 - mmengine - INFO - Epoch(train) [8][1300/1567] lr: 5.1679e-02 eta: 0:07:21 time: 0.0352 data_time: 0.0061 memory: 1253 loss: 0.2839 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.2839 2022/11/28 14:32:04 - mmengine - INFO - Epoch(train) [8][1400/1567] lr: 5.1052e-02 eta: 0:07:18 time: 0.0350 data_time: 0.0061 memory: 1253 loss: 0.2867 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2867 2022/11/28 14:32:07 - mmengine - INFO - Epoch(train) [8][1500/1567] lr: 5.0426e-02 eta: 0:07:14 time: 0.0340 data_time: 0.0060 memory: 1253 loss: 0.2816 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2816 2022/11/28 14:32:09 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:32:09 - mmengine - INFO - Epoch(train) [8][1567/1567] lr: 5.0006e-02 eta: 0:07:12 time: 0.0343 data_time: 0.0060 memory: 1253 loss: 0.3969 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.3969 2022/11/28 14:32:09 - mmengine - INFO - Saving checkpoint at 8 epochs 2022/11/28 14:32:11 - mmengine - INFO - Epoch(val) [8][100/129] eta: 0:00:00 time: 0.0150 data_time: 0.0058 memory: 262 2022/11/28 14:32:12 - mmengine - INFO - Epoch(val) [8][129/129] acc/top1: 0.8018 acc/top5: 0.9720 acc/mean1: 0.8017 2022/11/28 14:32:12 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_7.pth is removed 2022/11/28 14:32:12 - mmengine - INFO - The best checkpoint with 0.8018 acc/top1 at 8 epoch is saved to best_acc/top1_epoch_8.pth. 2022/11/28 14:32:16 - mmengine - INFO - Epoch(train) [9][100/1567] lr: 4.9380e-02 eta: 0:07:08 time: 0.0353 data_time: 0.0059 memory: 1253 loss: 0.2162 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2162 2022/11/28 14:32:20 - mmengine - INFO - Epoch(train) [9][200/1567] lr: 4.8753e-02 eta: 0:07:05 time: 0.0347 data_time: 0.0060 memory: 1253 loss: 0.2229 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2229 2022/11/28 14:32:23 - mmengine - INFO - Epoch(train) [9][300/1567] lr: 4.8127e-02 eta: 0:07:02 time: 0.0337 data_time: 0.0061 memory: 1253 loss: 0.2758 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2758 2022/11/28 14:32:26 - mmengine - INFO - Epoch(train) [9][400/1567] lr: 4.7501e-02 eta: 0:06:58 time: 0.0352 data_time: 0.0064 memory: 1253 loss: 0.2420 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2420 2022/11/28 14:32:29 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:32:30 - mmengine - INFO - Epoch(train) [9][500/1567] lr: 4.6876e-02 eta: 0:06:55 time: 0.0351 data_time: 0.0061 memory: 1253 loss: 0.1734 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1734 2022/11/28 14:32:33 - mmengine - INFO - Epoch(train) [9][600/1567] lr: 4.6251e-02 eta: 0:06:51 time: 0.0343 data_time: 0.0061 memory: 1253 loss: 0.2608 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2608 2022/11/28 14:32:37 - mmengine - INFO - Epoch(train) [9][700/1567] lr: 4.5626e-02 eta: 0:06:48 time: 0.0350 data_time: 0.0059 memory: 1253 loss: 0.2007 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2007 2022/11/28 14:32:40 - mmengine - INFO - Epoch(train) [9][800/1567] lr: 4.5003e-02 eta: 0:06:44 time: 0.0358 data_time: 0.0061 memory: 1253 loss: 0.1830 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1830 2022/11/28 14:32:44 - mmengine - INFO - Epoch(train) [9][900/1567] lr: 4.4380e-02 eta: 0:06:41 time: 0.0354 data_time: 0.0064 memory: 1253 loss: 0.1680 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1680 2022/11/28 14:32:48 - mmengine - INFO - Epoch(train) [9][1000/1567] lr: 4.3757e-02 eta: 0:06:38 time: 0.0346 data_time: 0.0060 memory: 1253 loss: 0.2558 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2558 2022/11/28 14:32:51 - mmengine - INFO - Epoch(train) [9][1100/1567] lr: 4.3136e-02 eta: 0:06:34 time: 0.0341 data_time: 0.0061 memory: 1253 loss: 0.2557 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2557 2022/11/28 14:32:54 - mmengine - INFO - Epoch(train) [9][1200/1567] lr: 4.2516e-02 eta: 0:06:31 time: 0.0343 data_time: 0.0061 memory: 1253 loss: 0.1666 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1666 2022/11/28 14:32:58 - mmengine - INFO - Epoch(train) [9][1300/1567] lr: 4.1897e-02 eta: 0:06:27 time: 0.0335 data_time: 0.0059 memory: 1253 loss: 0.3101 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3101 2022/11/28 14:33:01 - mmengine - INFO - Epoch(train) [9][1400/1567] lr: 4.1280e-02 eta: 0:06:24 time: 0.0349 data_time: 0.0060 memory: 1253 loss: 0.2157 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2157 2022/11/28 14:33:04 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:33:05 - mmengine - INFO - Epoch(train) [9][1500/1567] lr: 4.0664e-02 eta: 0:06:21 time: 0.0336 data_time: 0.0060 memory: 1253 loss: 0.2837 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2837 2022/11/28 14:33:07 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:33:07 - mmengine - INFO - Epoch(train) [9][1567/1567] lr: 4.0252e-02 eta: 0:06:18 time: 0.0329 data_time: 0.0058 memory: 1253 loss: 0.3559 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.3559 2022/11/28 14:33:07 - mmengine - INFO - Saving checkpoint at 9 epochs 2022/11/28 14:33:09 - mmengine - INFO - Epoch(val) [9][100/129] eta: 0:00:00 time: 0.0153 data_time: 0.0062 memory: 262 2022/11/28 14:33:10 - mmengine - INFO - Epoch(val) [9][129/129] acc/top1: 0.7484 acc/top5: 0.9537 acc/mean1: 0.7483 2022/11/28 14:33:13 - mmengine - INFO - Epoch(train) [10][100/1567] lr: 3.9638e-02 eta: 0:06:15 time: 0.0340 data_time: 0.0060 memory: 1253 loss: 0.1789 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1789 2022/11/28 14:33:17 - mmengine - INFO - Epoch(train) [10][200/1567] lr: 3.9026e-02 eta: 0:06:11 time: 0.0342 data_time: 0.0060 memory: 1253 loss: 0.1967 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1967 2022/11/28 14:33:20 - mmengine - INFO - Epoch(train) [10][300/1567] lr: 3.8415e-02 eta: 0:06:08 time: 0.0353 data_time: 0.0063 memory: 1253 loss: 0.1716 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1716 2022/11/28 14:33:24 - mmengine - INFO - Epoch(train) [10][400/1567] lr: 3.7807e-02 eta: 0:06:04 time: 0.0354 data_time: 0.0061 memory: 1253 loss: 0.2170 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2170 2022/11/28 14:33:27 - mmengine - INFO - Epoch(train) [10][500/1567] lr: 3.7200e-02 eta: 0:06:01 time: 0.0348 data_time: 0.0060 memory: 1253 loss: 0.1614 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1614 2022/11/28 14:33:31 - mmengine - INFO - Epoch(train) [10][600/1567] lr: 3.6596e-02 eta: 0:05:58 time: 0.0348 data_time: 0.0060 memory: 1253 loss: 0.1713 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1713 2022/11/28 14:33:34 - mmengine - INFO - Epoch(train) [10][700/1567] lr: 3.5993e-02 eta: 0:05:54 time: 0.0336 data_time: 0.0061 memory: 1253 loss: 0.2126 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2126 2022/11/28 14:33:37 - mmengine - INFO - Epoch(train) [10][800/1567] lr: 3.5393e-02 eta: 0:05:51 time: 0.0343 data_time: 0.0060 memory: 1253 loss: 0.1356 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1356 2022/11/28 14:33:41 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:33:41 - mmengine - INFO - Epoch(train) [10][900/1567] lr: 3.4795e-02 eta: 0:05:47 time: 0.0352 data_time: 0.0060 memory: 1253 loss: 0.1397 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1397 2022/11/28 14:33:44 - mmengine - INFO - Epoch(train) [10][1000/1567] lr: 3.4199e-02 eta: 0:05:44 time: 0.0336 data_time: 0.0060 memory: 1253 loss: 0.1696 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1696 2022/11/28 14:33:48 - mmengine - INFO - Epoch(train) [10][1100/1567] lr: 3.3606e-02 eta: 0:05:40 time: 0.0340 data_time: 0.0060 memory: 1253 loss: 0.1516 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1516 2022/11/28 14:33:51 - mmengine - INFO - Epoch(train) [10][1200/1567] lr: 3.3015e-02 eta: 0:05:37 time: 0.0337 data_time: 0.0060 memory: 1253 loss: 0.2039 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2039 2022/11/28 14:33:55 - mmengine - INFO - Epoch(train) [10][1300/1567] lr: 3.2428e-02 eta: 0:05:33 time: 0.0340 data_time: 0.0060 memory: 1253 loss: 0.1917 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1917 2022/11/28 14:33:58 - mmengine - INFO - Epoch(train) [10][1400/1567] lr: 3.1842e-02 eta: 0:05:30 time: 0.0338 data_time: 0.0060 memory: 1253 loss: 0.1659 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1659 2022/11/28 14:34:01 - mmengine - INFO - Epoch(train) [10][1500/1567] lr: 3.1260e-02 eta: 0:05:26 time: 0.0337 data_time: 0.0060 memory: 1253 loss: 0.1446 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.1446 2022/11/28 14:34:04 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:34:04 - mmengine - INFO - Epoch(train) [10][1567/1567] lr: 3.0872e-02 eta: 0:05:24 time: 0.0339 data_time: 0.0059 memory: 1253 loss: 0.2511 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2511 2022/11/28 14:34:04 - mmengine - INFO - Saving checkpoint at 10 epochs 2022/11/28 14:34:06 - mmengine - INFO - Epoch(val) [10][100/129] eta: 0:00:00 time: 0.0149 data_time: 0.0058 memory: 262 2022/11/28 14:34:06 - mmengine - INFO - Epoch(val) [10][129/129] acc/top1: 0.7700 acc/top5: 0.9743 acc/mean1: 0.7698 2022/11/28 14:34:10 - mmengine - INFO - Epoch(train) [11][100/1567] lr: 3.0294e-02 eta: 0:05:21 time: 0.0341 data_time: 0.0060 memory: 1253 loss: 0.1294 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1294 2022/11/28 14:34:13 - mmengine - INFO - Epoch(train) [11][200/1567] lr: 2.9720e-02 eta: 0:05:17 time: 0.0357 data_time: 0.0062 memory: 1253 loss: 0.1688 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1688 2022/11/28 14:34:17 - mmengine - INFO - Epoch(train) [11][300/1567] lr: 2.9149e-02 eta: 0:05:14 time: 0.0345 data_time: 0.0067 memory: 1253 loss: 0.1469 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1469 2022/11/28 14:34:18 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:34:20 - mmengine - INFO - Epoch(train) [11][400/1567] lr: 2.8581e-02 eta: 0:05:10 time: 0.0333 data_time: 0.0060 memory: 1253 loss: 0.1546 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1546 2022/11/28 14:34:23 - mmengine - INFO - Epoch(train) [11][500/1567] lr: 2.8017e-02 eta: 0:05:07 time: 0.0331 data_time: 0.0060 memory: 1253 loss: 0.1235 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1235 2022/11/28 14:34:27 - mmengine - INFO - Epoch(train) [11][600/1567] lr: 2.7456e-02 eta: 0:05:03 time: 0.0351 data_time: 0.0061 memory: 1253 loss: 0.1365 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1365 2022/11/28 14:34:30 - mmengine - INFO - Epoch(train) [11][700/1567] lr: 2.6898e-02 eta: 0:05:00 time: 0.0338 data_time: 0.0059 memory: 1253 loss: 0.1154 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1154 2022/11/28 14:34:34 - mmengine - INFO - Epoch(train) [11][800/1567] lr: 2.6345e-02 eta: 0:04:56 time: 0.0334 data_time: 0.0060 memory: 1253 loss: 0.0931 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0931 2022/11/28 14:34:37 - mmengine - INFO - Epoch(train) [11][900/1567] lr: 2.5794e-02 eta: 0:04:53 time: 0.0335 data_time: 0.0060 memory: 1253 loss: 0.1228 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1228 2022/11/28 14:34:41 - mmengine - INFO - Epoch(train) [11][1000/1567] lr: 2.5248e-02 eta: 0:04:49 time: 0.0355 data_time: 0.0060 memory: 1253 loss: 0.0905 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0905 2022/11/28 14:34:44 - mmengine - INFO - Epoch(train) [11][1100/1567] lr: 2.4706e-02 eta: 0:04:46 time: 0.0334 data_time: 0.0060 memory: 1253 loss: 0.1678 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1678 2022/11/28 14:34:47 - mmengine - INFO - Epoch(train) [11][1200/1567] lr: 2.4167e-02 eta: 0:04:42 time: 0.0339 data_time: 0.0060 memory: 1253 loss: 0.1394 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1394 2022/11/28 14:34:51 - mmengine - INFO - Epoch(train) [11][1300/1567] lr: 2.3633e-02 eta: 0:04:39 time: 0.0333 data_time: 0.0060 memory: 1253 loss: 0.1090 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1090 2022/11/28 14:34:52 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:34:54 - mmengine - INFO - Epoch(train) [11][1400/1567] lr: 2.3103e-02 eta: 0:04:36 time: 0.0364 data_time: 0.0060 memory: 1253 loss: 0.1179 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1179 2022/11/28 14:34:58 - mmengine - INFO - Epoch(train) [11][1500/1567] lr: 2.2577e-02 eta: 0:04:32 time: 0.0344 data_time: 0.0060 memory: 1253 loss: 0.1537 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1537 2022/11/28 14:35:00 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:35:00 - mmengine - INFO - Epoch(train) [11][1567/1567] lr: 2.2227e-02 eta: 0:04:30 time: 0.0342 data_time: 0.0057 memory: 1253 loss: 0.2663 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.2663 2022/11/28 14:35:00 - mmengine - INFO - Saving checkpoint at 11 epochs 2022/11/28 14:35:02 - mmengine - INFO - Epoch(val) [11][100/129] eta: 0:00:00 time: 0.0148 data_time: 0.0058 memory: 262 2022/11/28 14:35:03 - mmengine - INFO - Epoch(val) [11][129/129] acc/top1: 0.8335 acc/top5: 0.9823 acc/mean1: 0.8334 2022/11/28 14:35:03 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_8.pth is removed 2022/11/28 14:35:03 - mmengine - INFO - The best checkpoint with 0.8335 acc/top1 at 11 epoch is saved to best_acc/top1_epoch_11.pth. 2022/11/28 14:35:07 - mmengine - INFO - Epoch(train) [12][100/1567] lr: 2.1708e-02 eta: 0:04:26 time: 0.0338 data_time: 0.0060 memory: 1253 loss: 0.0937 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.0937 2022/11/28 14:35:10 - mmengine - INFO - Epoch(train) [12][200/1567] lr: 2.1194e-02 eta: 0:04:23 time: 0.0344 data_time: 0.0068 memory: 1253 loss: 0.1281 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1281 2022/11/28 14:35:14 - mmengine - INFO - Epoch(train) [12][300/1567] lr: 2.0684e-02 eta: 0:04:20 time: 0.0343 data_time: 0.0062 memory: 1253 loss: 0.1199 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1199 2022/11/28 14:35:17 - mmengine - INFO - Epoch(train) [12][400/1567] lr: 2.0179e-02 eta: 0:04:16 time: 0.0351 data_time: 0.0059 memory: 1253 loss: 0.1075 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1075 2022/11/28 14:35:21 - mmengine - INFO - Epoch(train) [12][500/1567] lr: 1.9678e-02 eta: 0:04:13 time: 0.0347 data_time: 0.0059 memory: 1253 loss: 0.1392 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1392 2022/11/28 14:35:24 - mmengine - INFO - Epoch(train) [12][600/1567] lr: 1.9182e-02 eta: 0:04:09 time: 0.0344 data_time: 0.0061 memory: 1253 loss: 0.1122 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1122 2022/11/28 14:35:27 - mmengine - INFO - Epoch(train) [12][700/1567] lr: 1.8691e-02 eta: 0:04:06 time: 0.0340 data_time: 0.0059 memory: 1253 loss: 0.0987 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0987 2022/11/28 14:35:30 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:35:31 - mmengine - INFO - Epoch(train) [12][800/1567] lr: 1.8205e-02 eta: 0:04:02 time: 0.0335 data_time: 0.0060 memory: 1253 loss: 0.0685 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0685 2022/11/28 14:35:34 - mmengine - INFO - Epoch(train) [12][900/1567] lr: 1.7724e-02 eta: 0:03:59 time: 0.0353 data_time: 0.0061 memory: 1253 loss: 0.0837 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0837 2022/11/28 14:35:38 - mmengine - INFO - Epoch(train) [12][1000/1567] lr: 1.7248e-02 eta: 0:03:55 time: 0.0340 data_time: 0.0059 memory: 1253 loss: 0.1103 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1103 2022/11/28 14:35:41 - mmengine - INFO - Epoch(train) [12][1100/1567] lr: 1.6778e-02 eta: 0:03:52 time: 0.0343 data_time: 0.0066 memory: 1253 loss: 0.0718 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0718 2022/11/28 14:35:45 - mmengine - INFO - Epoch(train) [12][1200/1567] lr: 1.6312e-02 eta: 0:03:48 time: 0.0357 data_time: 0.0060 memory: 1253 loss: 0.0836 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0836 2022/11/28 14:35:48 - mmengine - INFO - Epoch(train) [12][1300/1567] lr: 1.5852e-02 eta: 0:03:45 time: 0.0339 data_time: 0.0059 memory: 1253 loss: 0.0701 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0701 2022/11/28 14:35:52 - mmengine - INFO - Epoch(train) [12][1400/1567] lr: 1.5397e-02 eta: 0:03:42 time: 0.0339 data_time: 0.0059 memory: 1253 loss: 0.1001 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1001 2022/11/28 14:35:55 - mmengine - INFO - Epoch(train) [12][1500/1567] lr: 1.4947e-02 eta: 0:03:38 time: 0.0341 data_time: 0.0059 memory: 1253 loss: 0.0943 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0943 2022/11/28 14:35:57 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:35:57 - mmengine - INFO - Epoch(train) [12][1567/1567] lr: 1.4649e-02 eta: 0:03:36 time: 0.0332 data_time: 0.0058 memory: 1253 loss: 0.2354 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2354 2022/11/28 14:35:57 - mmengine - INFO - Saving checkpoint at 12 epochs 2022/11/28 14:35:59 - mmengine - INFO - Epoch(val) [12][100/129] eta: 0:00:00 time: 0.0146 data_time: 0.0057 memory: 262 2022/11/28 14:36:00 - mmengine - INFO - Epoch(val) [12][129/129] acc/top1: 0.8162 acc/top5: 0.9760 acc/mean1: 0.8161 2022/11/28 14:36:03 - mmengine - INFO - Epoch(train) [13][100/1567] lr: 1.4209e-02 eta: 0:03:32 time: 0.0341 data_time: 0.0059 memory: 1253 loss: 0.0552 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0552 2022/11/28 14:36:07 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:36:07 - mmengine - INFO - Epoch(train) [13][200/1567] lr: 1.3774e-02 eta: 0:03:29 time: 0.0341 data_time: 0.0058 memory: 1253 loss: 0.0614 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0614 2022/11/28 14:36:10 - mmengine - INFO - Epoch(train) [13][300/1567] lr: 1.3345e-02 eta: 0:03:25 time: 0.0356 data_time: 0.0059 memory: 1253 loss: 0.0436 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0436 2022/11/28 14:36:14 - mmengine - INFO - Epoch(train) [13][400/1567] lr: 1.2922e-02 eta: 0:03:22 time: 0.0343 data_time: 0.0058 memory: 1253 loss: 0.0716 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0716 2022/11/28 14:36:17 - mmengine - INFO - Epoch(train) [13][500/1567] lr: 1.2505e-02 eta: 0:03:19 time: 0.0347 data_time: 0.0063 memory: 1253 loss: 0.0620 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0620 2022/11/28 14:36:21 - mmengine - INFO - Epoch(train) [13][600/1567] lr: 1.2093e-02 eta: 0:03:15 time: 0.0345 data_time: 0.0064 memory: 1253 loss: 0.0513 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0513 2022/11/28 14:36:24 - mmengine - INFO - Epoch(train) [13][700/1567] lr: 1.1687e-02 eta: 0:03:12 time: 0.0358 data_time: 0.0059 memory: 1253 loss: 0.0538 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0538 2022/11/28 14:36:28 - mmengine - INFO - Epoch(train) [13][800/1567] lr: 1.1288e-02 eta: 0:03:08 time: 0.0358 data_time: 0.0062 memory: 1253 loss: 0.0477 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0477 2022/11/28 14:36:31 - mmengine - INFO - Epoch(train) [13][900/1567] lr: 1.0894e-02 eta: 0:03:05 time: 0.0337 data_time: 0.0062 memory: 1253 loss: 0.0329 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0329 2022/11/28 14:36:35 - mmengine - INFO - Epoch(train) [13][1000/1567] lr: 1.0507e-02 eta: 0:03:01 time: 0.0345 data_time: 0.0059 memory: 1253 loss: 0.0839 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0839 2022/11/28 14:36:38 - mmengine - INFO - Epoch(train) [13][1100/1567] lr: 1.0126e-02 eta: 0:02:58 time: 0.0336 data_time: 0.0059 memory: 1253 loss: 0.0221 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0221 2022/11/28 14:36:41 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:36:42 - mmengine - INFO - Epoch(train) [13][1200/1567] lr: 9.7512e-03 eta: 0:02:54 time: 0.0355 data_time: 0.0060 memory: 1253 loss: 0.0644 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0644 2022/11/28 14:36:45 - mmengine - INFO - Epoch(train) [13][1300/1567] lr: 9.3826e-03 eta: 0:02:51 time: 0.0337 data_time: 0.0058 memory: 1253 loss: 0.0585 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0585 2022/11/28 14:36:49 - mmengine - INFO - Epoch(train) [13][1400/1567] lr: 9.0204e-03 eta: 0:02:48 time: 0.0346 data_time: 0.0059 memory: 1253 loss: 0.0388 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0388 2022/11/28 14:36:52 - mmengine - INFO - Epoch(train) [13][1500/1567] lr: 8.6647e-03 eta: 0:02:44 time: 0.0347 data_time: 0.0059 memory: 1253 loss: 0.0458 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0458 2022/11/28 14:36:54 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:36:54 - mmengine - INFO - Epoch(train) [13][1567/1567] lr: 8.4300e-03 eta: 0:02:42 time: 0.0335 data_time: 0.0061 memory: 1253 loss: 0.2286 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.2286 2022/11/28 14:36:54 - mmengine - INFO - Saving checkpoint at 13 epochs 2022/11/28 14:36:56 - mmengine - INFO - Epoch(val) [13][100/129] eta: 0:00:00 time: 0.0146 data_time: 0.0056 memory: 262 2022/11/28 14:36:57 - mmengine - INFO - Epoch(val) [13][129/129] acc/top1: 0.8514 acc/top5: 0.9831 acc/mean1: 0.8513 2022/11/28 14:36:57 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_11.pth is removed 2022/11/28 14:36:57 - mmengine - INFO - The best checkpoint with 0.8514 acc/top1 at 13 epoch is saved to best_acc/top1_epoch_13.pth. 2022/11/28 14:37:01 - mmengine - INFO - Epoch(train) [14][100/1567] lr: 8.0851e-03 eta: 0:02:38 time: 0.0354 data_time: 0.0059 memory: 1253 loss: 0.0446 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0446 2022/11/28 14:37:04 - mmengine - INFO - Epoch(train) [14][200/1567] lr: 7.7469e-03 eta: 0:02:35 time: 0.0350 data_time: 0.0059 memory: 1253 loss: 0.0357 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0357 2022/11/28 14:37:08 - mmengine - INFO - Epoch(train) [14][300/1567] lr: 7.4152e-03 eta: 0:02:31 time: 0.0354 data_time: 0.0060 memory: 1253 loss: 0.0480 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0480 2022/11/28 14:37:11 - mmengine - INFO - Epoch(train) [14][400/1567] lr: 7.0902e-03 eta: 0:02:28 time: 0.0344 data_time: 0.0059 memory: 1253 loss: 0.0289 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0289 2022/11/28 14:37:15 - mmengine - INFO - Epoch(train) [14][500/1567] lr: 6.7720e-03 eta: 0:02:25 time: 0.0343 data_time: 0.0059 memory: 1253 loss: 0.0314 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0314 2022/11/28 14:37:18 - mmengine - INFO - Epoch(train) [14][600/1567] lr: 6.4606e-03 eta: 0:02:21 time: 0.0342 data_time: 0.0059 memory: 1253 loss: 0.0359 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0359 2022/11/28 14:37:19 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:37:21 - mmengine - INFO - Epoch(train) [14][700/1567] lr: 6.1560e-03 eta: 0:02:18 time: 0.0353 data_time: 0.0059 memory: 1253 loss: 0.0483 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0483 2022/11/28 14:37:25 - mmengine - INFO - Epoch(train) [14][800/1567] lr: 5.8582e-03 eta: 0:02:14 time: 0.0341 data_time: 0.0059 memory: 1253 loss: 0.0662 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0662 2022/11/28 14:37:28 - mmengine - INFO - Epoch(train) [14][900/1567] lr: 5.5675e-03 eta: 0:02:11 time: 0.0351 data_time: 0.0060 memory: 1253 loss: 0.0527 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0527 2022/11/28 14:37:32 - mmengine - INFO - Epoch(train) [14][1000/1567] lr: 5.2836e-03 eta: 0:02:07 time: 0.0352 data_time: 0.0060 memory: 1253 loss: 0.0405 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0405 2022/11/28 14:37:35 - mmengine - INFO - Epoch(train) [14][1100/1567] lr: 5.0068e-03 eta: 0:02:04 time: 0.0341 data_time: 0.0059 memory: 1253 loss: 0.0327 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0327 2022/11/28 14:37:39 - mmengine - INFO - Epoch(train) [14][1200/1567] lr: 4.7371e-03 eta: 0:02:00 time: 0.0342 data_time: 0.0061 memory: 1253 loss: 0.0433 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0433 2022/11/28 14:37:42 - mmengine - INFO - Epoch(train) [14][1300/1567] lr: 4.4745e-03 eta: 0:01:57 time: 0.0339 data_time: 0.0059 memory: 1253 loss: 0.0201 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0201 2022/11/28 14:37:46 - mmengine - INFO - Epoch(train) [14][1400/1567] lr: 4.2190e-03 eta: 0:01:53 time: 0.0336 data_time: 0.0059 memory: 1253 loss: 0.0294 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.0294 2022/11/28 14:37:49 - mmengine - INFO - Epoch(train) [14][1500/1567] lr: 3.9707e-03 eta: 0:01:50 time: 0.0337 data_time: 0.0059 memory: 1253 loss: 0.0366 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0366 2022/11/28 14:37:51 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:37:51 - mmengine - INFO - Epoch(train) [14][1567/1567] lr: 3.8084e-03 eta: 0:01:48 time: 0.0344 data_time: 0.0057 memory: 1253 loss: 0.2091 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2091 2022/11/28 14:37:51 - mmengine - INFO - Saving checkpoint at 14 epochs 2022/11/28 14:37:53 - mmengine - INFO - Epoch(val) [14][100/129] eta: 0:00:00 time: 0.0147 data_time: 0.0056 memory: 262 2022/11/28 14:37:54 - mmengine - INFO - Epoch(val) [14][129/129] acc/top1: 0.8503 acc/top5: 0.9840 acc/mean1: 0.8502 2022/11/28 14:37:56 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:37:57 - mmengine - INFO - Epoch(train) [15][100/1567] lr: 3.5722e-03 eta: 0:01:44 time: 0.0341 data_time: 0.0058 memory: 1253 loss: 0.0310 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0310 2022/11/28 14:38:01 - mmengine - INFO - Epoch(train) [15][200/1567] lr: 3.3433e-03 eta: 0:01:41 time: 0.0339 data_time: 0.0060 memory: 1253 loss: 0.0496 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0496 2022/11/28 14:38:04 - mmengine - INFO - Epoch(train) [15][300/1567] lr: 3.1217e-03 eta: 0:01:37 time: 0.0338 data_time: 0.0066 memory: 1253 loss: 0.0205 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0205 2022/11/28 14:38:07 - mmengine - INFO - Epoch(train) [15][400/1567] lr: 2.9075e-03 eta: 0:01:34 time: 0.0339 data_time: 0.0058 memory: 1253 loss: 0.0252 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0252 2022/11/28 14:38:11 - mmengine - INFO - Epoch(train) [15][500/1567] lr: 2.7007e-03 eta: 0:01:30 time: 0.0343 data_time: 0.0062 memory: 1253 loss: 0.0224 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0224 2022/11/28 14:38:14 - mmengine - INFO - Epoch(train) [15][600/1567] lr: 2.5013e-03 eta: 0:01:27 time: 0.0342 data_time: 0.0059 memory: 1253 loss: 0.0215 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0215 2022/11/28 14:38:18 - mmengine - INFO - Epoch(train) [15][700/1567] lr: 2.3093e-03 eta: 0:01:24 time: 0.0352 data_time: 0.0061 memory: 1253 loss: 0.0153 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0153 2022/11/28 14:38:21 - mmengine - INFO - Epoch(train) [15][800/1567] lr: 2.1249e-03 eta: 0:01:20 time: 0.0343 data_time: 0.0059 memory: 1253 loss: 0.0303 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0303 2022/11/28 14:38:25 - mmengine - INFO - Epoch(train) [15][900/1567] lr: 1.9479e-03 eta: 0:01:17 time: 0.0352 data_time: 0.0059 memory: 1253 loss: 0.0145 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0145 2022/11/28 14:38:28 - mmengine - INFO - Epoch(train) [15][1000/1567] lr: 1.7785e-03 eta: 0:01:13 time: 0.0361 data_time: 0.0058 memory: 1253 loss: 0.0209 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0209 2022/11/28 14:38:31 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:38:32 - mmengine - INFO - Epoch(train) [15][1100/1567] lr: 1.6167e-03 eta: 0:01:10 time: 0.0349 data_time: 0.0060 memory: 1253 loss: 0.0252 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0252 2022/11/28 14:38:35 - mmengine - INFO - Epoch(train) [15][1200/1567] lr: 1.4625e-03 eta: 0:01:06 time: 0.0341 data_time: 0.0058 memory: 1253 loss: 0.0214 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0214 2022/11/28 14:38:39 - mmengine - INFO - Epoch(train) [15][1300/1567] lr: 1.3159e-03 eta: 0:01:03 time: 0.0351 data_time: 0.0061 memory: 1253 loss: 0.0095 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0095 2022/11/28 14:38:42 - mmengine - INFO - Epoch(train) [15][1400/1567] lr: 1.1769e-03 eta: 0:00:59 time: 0.0344 data_time: 0.0059 memory: 1253 loss: 0.0260 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0260 2022/11/28 14:38:46 - mmengine - INFO - Epoch(train) [15][1500/1567] lr: 1.0456e-03 eta: 0:00:56 time: 0.0343 data_time: 0.0059 memory: 1253 loss: 0.0257 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0257 2022/11/28 14:38:48 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:38:48 - mmengine - INFO - Epoch(train) [15][1567/1567] lr: 9.6196e-04 eta: 0:00:54 time: 0.0337 data_time: 0.0056 memory: 1253 loss: 0.1695 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1695 2022/11/28 14:38:48 - mmengine - INFO - Saving checkpoint at 15 epochs 2022/11/28 14:38:50 - mmengine - INFO - Epoch(val) [15][100/129] eta: 0:00:00 time: 0.0145 data_time: 0.0056 memory: 262 2022/11/28 14:38:51 - mmengine - INFO - Epoch(val) [15][129/129] acc/top1: 0.8565 acc/top5: 0.9851 acc/mean1: 0.8564 2022/11/28 14:38:51 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_13.pth is removed 2022/11/28 14:38:51 - mmengine - INFO - The best checkpoint with 0.8565 acc/top1 at 15 epoch is saved to best_acc/top1_epoch_15.pth. 2022/11/28 14:38:55 - mmengine - INFO - Epoch(train) [16][100/1567] lr: 8.4351e-04 eta: 0:00:50 time: 0.0350 data_time: 0.0059 memory: 1253 loss: 0.0166 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0166 2022/11/28 14:38:58 - mmengine - INFO - Epoch(train) [16][200/1567] lr: 7.3277e-04 eta: 0:00:47 time: 0.0342 data_time: 0.0060 memory: 1253 loss: 0.0120 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0120 2022/11/28 14:39:02 - mmengine - INFO - Epoch(train) [16][300/1567] lr: 6.2978e-04 eta: 0:00:43 time: 0.0351 data_time: 0.0060 memory: 1253 loss: 0.0273 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0273 2022/11/28 14:39:05 - mmengine - INFO - Epoch(train) [16][400/1567] lr: 5.3453e-04 eta: 0:00:40 time: 0.0347 data_time: 0.0060 memory: 1253 loss: 0.0279 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0279 2022/11/28 14:39:08 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:39:09 - mmengine - INFO - Epoch(train) [16][500/1567] lr: 4.4705e-04 eta: 0:00:36 time: 0.0351 data_time: 0.0061 memory: 1253 loss: 0.0244 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0244 2022/11/28 14:39:12 - mmengine - INFO - Epoch(train) [16][600/1567] lr: 3.6735e-04 eta: 0:00:33 time: 0.0337 data_time: 0.0059 memory: 1253 loss: 0.0146 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0146 2022/11/28 14:39:16 - mmengine - INFO - Epoch(train) [16][700/1567] lr: 2.9544e-04 eta: 0:00:29 time: 0.0341 data_time: 0.0058 memory: 1253 loss: 0.0289 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0289 2022/11/28 14:39:19 - mmengine - INFO - Epoch(train) [16][800/1567] lr: 2.3134e-04 eta: 0:00:26 time: 0.0337 data_time: 0.0060 memory: 1253 loss: 0.0138 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0138 2022/11/28 14:39:22 - mmengine - INFO - Epoch(train) [16][900/1567] lr: 1.7505e-04 eta: 0:00:23 time: 0.0340 data_time: 0.0059 memory: 1253 loss: 0.0105 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0105 2022/11/28 14:39:26 - mmengine - INFO - Epoch(train) [16][1000/1567] lr: 1.2658e-04 eta: 0:00:19 time: 0.0359 data_time: 0.0058 memory: 1253 loss: 0.0129 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0129 2022/11/28 14:39:29 - mmengine - INFO - Epoch(train) [16][1100/1567] lr: 8.5947e-05 eta: 0:00:16 time: 0.0338 data_time: 0.0059 memory: 1253 loss: 0.0281 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0281 2022/11/28 14:39:33 - mmengine - INFO - Epoch(train) [16][1200/1567] lr: 5.3147e-05 eta: 0:00:12 time: 0.0343 data_time: 0.0060 memory: 1253 loss: 0.0184 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0184 2022/11/28 14:39:36 - mmengine - INFO - Epoch(train) [16][1300/1567] lr: 2.8190e-05 eta: 0:00:09 time: 0.0341 data_time: 0.0059 memory: 1253 loss: 0.0233 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0233 2022/11/28 14:39:40 - mmengine - INFO - Epoch(train) [16][1400/1567] lr: 1.1078e-05 eta: 0:00:05 time: 0.0339 data_time: 0.0058 memory: 1253 loss: 0.0202 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0202 2022/11/28 14:39:43 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:39:43 - mmengine - INFO - Epoch(train) [16][1500/1567] lr: 1.8150e-06 eta: 0:00:02 time: 0.0338 data_time: 0.0062 memory: 1253 loss: 0.0142 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0142 2022/11/28 14:39:45 - mmengine - INFO - Exp name: stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221128_142359 2022/11/28 14:39:45 - mmengine - INFO - Epoch(train) [16][1567/1567] lr: 3.9252e-10 eta: 0:00:00 time: 0.0334 data_time: 0.0060 memory: 1253 loss: 0.1588 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1588 2022/11/28 14:39:45 - mmengine - INFO - Saving checkpoint at 16 epochs 2022/11/28 14:39:47 - mmengine - INFO - Epoch(val) [16][100/129] eta: 0:00:00 time: 0.0146 data_time: 0.0056 memory: 262 2022/11/28 14:39:48 - mmengine - INFO - Epoch(val) [16][129/129] acc/top1: 0.8592 acc/top5: 0.9857 acc/mean1: 0.8591 2022/11/28 14:39:48 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_15.pth is removed 2022/11/28 14:39:48 - mmengine - INFO - The best checkpoint with 0.8592 acc/top1 at 16 epoch is saved to best_acc/top1_epoch_16.pth.