2022/12/20 15:07:55 - 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: 848245519 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: 0.3.2 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 ------------------------------------------------------------ 2022/12/20 15:07:55 - 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='AAGCN', graph_cfg=dict(layout='coco', mode='spatial'), stage_cfgs=dict(gcn_attention=False)), 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=['b']), 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=['b']), dict( type='UniformSampleFrames', clip_len=100, num_clips=1, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ] test_pipeline = [ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['b']), dict( type='UniformSampleFrames', clip_len=100, num_clips=10, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ] train_dataloader = dict( batch_size=16, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=True), dataset=dict( type='RepeatDataset', times=5, dataset=dict( type='PoseDataset', ann_file='data/skeleton/ntu60_2d.pkl', pipeline=[ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['b']), dict(type='UniformSampleFrames', clip_len=100), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ], split='xsub_train'))) val_dataloader = dict( batch_size=16, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='PoseDataset', ann_file='data/skeleton/ntu60_2d.pkl', pipeline=[ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['b']), dict( type='UniformSampleFrames', clip_len=100, num_clips=1, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ], split='xsub_val', test_mode=True)) test_dataloader = dict( batch_size=1, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='PoseDataset', ann_file='data/skeleton/ntu60_2d.pkl', pipeline=[ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['b']), dict( type='UniformSampleFrames', clip_len=100, num_clips=10, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ], split='xsub_val', test_mode=True)) val_evaluator = [dict(type='AccMetric')] test_evaluator = [dict(type='AccMetric')] train_cfg = dict( type='EpochBasedTrainLoop', max_epochs=16, val_begin=1, val_interval=1) val_cfg = dict(type='ValLoop') test_cfg = dict(type='TestLoop') param_scheduler = [ dict( type='CosineAnnealingLR', eta_min=0, T_max=16, by_epoch=True, convert_to_iter_based=True) ] optim_wrapper = dict( optimizer=dict( type='SGD', lr=0.1, momentum=0.9, weight_decay=0.0005, nesterov=True)) auto_scale_lr = dict(enable=False, base_batch_size=128) launcher = 'pytorch' work_dir = './work_dirs/2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d' randomness = dict(seed=None, diff_rank_seed=False, deterministic=False) 2022/12/20 15:07:55 - mmengine - INFO - Result has been saved to /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d/modules_statistic_results.json 2022/12/20 15:07:56 - mmengine - INFO - Hooks will be executed in the following order: before_run: (VERY_HIGH ) RuntimeInfoHook (BELOW_NORMAL) LoggerHook -------------------- before_train: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (VERY_LOW ) CheckpointHook -------------------- before_train_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (NORMAL ) DistSamplerSeedHook -------------------- before_train_iter: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook -------------------- after_train_iter: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- after_train_epoch: (NORMAL ) IterTimerHook (NORMAL ) SyncBuffersHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- before_val_epoch: (NORMAL ) IterTimerHook -------------------- before_val_iter: (NORMAL ) IterTimerHook -------------------- after_val_iter: (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook -------------------- after_val_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook (VERY_LOW ) CheckpointHook -------------------- before_test_epoch: (NORMAL ) IterTimerHook -------------------- before_test_iter: (NORMAL ) IterTimerHook -------------------- after_test_iter: (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook -------------------- after_test_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook -------------------- after_run: (BELOW_NORMAL) LoggerHook -------------------- Name of parameter - Initialization information backbone.data_bn.weight - torch.Size([102]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.data_bn.bias - torch.Size([102]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.conv_d.0.weight - torch.Size([64, 3, 1, 1]): ConvBranchInit backbone.gcn.0.gcn.conv_d.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_d.1.weight - torch.Size([64, 3, 1, 1]): ConvBranchInit backbone.gcn.0.gcn.conv_d.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_d.2.weight - torch.Size([64, 3, 1, 1]): ConvBranchInit backbone.gcn.0.gcn.conv_d.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_a.0.weight - torch.Size([16, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_a.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_a.1.weight - torch.Size([16, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_a.1.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_a.2.weight - torch.Size([16, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_a.2.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_b.0.weight - torch.Size([16, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_b.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_b.1.weight - torch.Size([16, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_b.1.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_b.2.weight - torch.Size([16, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_b.2.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.down.0.weight - torch.Size([64, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.down.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.down.1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.down.1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.bn.weight - torch.Size([64]): ConstantInit: val=1e-06, bias=0 backbone.gcn.0.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.conv.weight - torch.Size([64, 64, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.tcn.conv.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.gcn.conv_d.0.weight - torch.Size([64, 64, 1, 1]): ConvBranchInit backbone.gcn.1.gcn.conv_d.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_d.1.weight - torch.Size([64, 64, 1, 1]): ConvBranchInit backbone.gcn.1.gcn.conv_d.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_d.2.weight - torch.Size([64, 64, 1, 1]): ConvBranchInit backbone.gcn.1.gcn.conv_d.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_a.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_a.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_a.1.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_a.1.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_a.2.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_a.2.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_b.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_b.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_b.1.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_b.1.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_b.2.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_b.2.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.bn.weight - torch.Size([64]): ConstantInit: val=1e-06, bias=0 backbone.gcn.1.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.conv.weight - torch.Size([64, 64, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.tcn.conv.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.gcn.conv_d.0.weight - torch.Size([64, 64, 1, 1]): ConvBranchInit backbone.gcn.2.gcn.conv_d.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_d.1.weight - torch.Size([64, 64, 1, 1]): ConvBranchInit backbone.gcn.2.gcn.conv_d.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_d.2.weight - torch.Size([64, 64, 1, 1]): ConvBranchInit backbone.gcn.2.gcn.conv_d.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_a.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_a.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_a.1.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_a.1.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_a.2.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_a.2.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_b.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_b.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_b.1.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_b.1.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_b.2.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_b.2.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.bn.weight - torch.Size([64]): ConstantInit: val=1e-06, bias=0 backbone.gcn.2.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.conv.weight - torch.Size([64, 64, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.tcn.conv.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.gcn.conv_d.0.weight - torch.Size([64, 64, 1, 1]): ConvBranchInit backbone.gcn.3.gcn.conv_d.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_d.1.weight - torch.Size([64, 64, 1, 1]): ConvBranchInit backbone.gcn.3.gcn.conv_d.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_d.2.weight - torch.Size([64, 64, 1, 1]): ConvBranchInit backbone.gcn.3.gcn.conv_d.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_a.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_a.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_a.1.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_a.1.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_a.2.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_a.2.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_b.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_b.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_b.1.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_b.1.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_b.2.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_b.2.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.bn.weight - torch.Size([64]): ConstantInit: val=1e-06, bias=0 backbone.gcn.3.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.conv.weight - torch.Size([64, 64, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.tcn.conv.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.conv_d.0.weight - torch.Size([128, 64, 1, 1]): ConvBranchInit backbone.gcn.4.gcn.conv_d.0.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_d.1.weight - torch.Size([128, 64, 1, 1]): ConvBranchInit backbone.gcn.4.gcn.conv_d.1.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_d.2.weight - torch.Size([128, 64, 1, 1]): ConvBranchInit backbone.gcn.4.gcn.conv_d.2.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_a.0.weight - torch.Size([32, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_a.0.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_a.1.weight - torch.Size([32, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_a.1.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_a.2.weight - torch.Size([32, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_a.2.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_b.0.weight - torch.Size([32, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_b.0.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_b.1.weight - torch.Size([32, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_b.1.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_b.2.weight - torch.Size([32, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_b.2.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.down.0.weight - torch.Size([128, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.down.0.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.down.1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.down.1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.bn.weight - torch.Size([128]): ConstantInit: val=1e-06, bias=0 backbone.gcn.4.gcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.conv.weight - torch.Size([128, 128, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.tcn.conv.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.tcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.residual.conv.weight - torch.Size([128, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.residual.conv.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.residual.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.residual.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.gcn.conv_d.0.weight - torch.Size([128, 128, 1, 1]): ConvBranchInit backbone.gcn.5.gcn.conv_d.0.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_d.1.weight - torch.Size([128, 128, 1, 1]): ConvBranchInit backbone.gcn.5.gcn.conv_d.1.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_d.2.weight - torch.Size([128, 128, 1, 1]): ConvBranchInit backbone.gcn.5.gcn.conv_d.2.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_a.0.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_a.0.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_a.1.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_a.1.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_a.2.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_a.2.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_b.0.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_b.0.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_b.1.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_b.1.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_b.2.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_b.2.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.bn.weight - torch.Size([128]): ConstantInit: val=1e-06, bias=0 backbone.gcn.5.gcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.conv.weight - torch.Size([128, 128, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.tcn.conv.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.tcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.gcn.conv_d.0.weight - torch.Size([128, 128, 1, 1]): ConvBranchInit backbone.gcn.6.gcn.conv_d.0.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_d.1.weight - torch.Size([128, 128, 1, 1]): ConvBranchInit backbone.gcn.6.gcn.conv_d.1.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_d.2.weight - torch.Size([128, 128, 1, 1]): ConvBranchInit backbone.gcn.6.gcn.conv_d.2.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_a.0.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_a.0.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_a.1.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_a.1.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_a.2.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_a.2.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_b.0.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_b.0.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_b.1.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_b.1.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_b.2.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_b.2.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.bn.weight - torch.Size([128]): ConstantInit: val=1e-06, bias=0 backbone.gcn.6.gcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.conv.weight - torch.Size([128, 128, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.tcn.conv.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.tcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.conv_d.0.weight - torch.Size([256, 128, 1, 1]): ConvBranchInit backbone.gcn.7.gcn.conv_d.0.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_d.1.weight - torch.Size([256, 128, 1, 1]): ConvBranchInit backbone.gcn.7.gcn.conv_d.1.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_d.2.weight - torch.Size([256, 128, 1, 1]): ConvBranchInit backbone.gcn.7.gcn.conv_d.2.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_a.0.weight - torch.Size([64, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_a.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_a.1.weight - torch.Size([64, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_a.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_a.2.weight - torch.Size([64, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_a.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_b.0.weight - torch.Size([64, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_b.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_b.1.weight - torch.Size([64, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_b.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_b.2.weight - torch.Size([64, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_b.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.down.0.weight - torch.Size([256, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.down.0.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.down.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.down.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.bn.weight - torch.Size([256]): ConstantInit: val=1e-06, bias=0 backbone.gcn.7.gcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.conv.weight - torch.Size([256, 256, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.tcn.conv.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.tcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.residual.conv.weight - torch.Size([256, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.residual.conv.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.residual.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.residual.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.gcn.conv_d.0.weight - torch.Size([256, 256, 1, 1]): ConvBranchInit backbone.gcn.8.gcn.conv_d.0.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_d.1.weight - torch.Size([256, 256, 1, 1]): ConvBranchInit backbone.gcn.8.gcn.conv_d.1.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_d.2.weight - torch.Size([256, 256, 1, 1]): ConvBranchInit backbone.gcn.8.gcn.conv_d.2.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_a.0.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_a.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_a.1.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_a.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_a.2.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_a.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_b.0.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_b.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_b.1.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_b.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_b.2.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_b.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.bn.weight - torch.Size([256]): ConstantInit: val=1e-06, bias=0 backbone.gcn.8.gcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.conv.weight - torch.Size([256, 256, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.tcn.conv.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.tcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.gcn.conv_d.0.weight - torch.Size([256, 256, 1, 1]): ConvBranchInit backbone.gcn.9.gcn.conv_d.0.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_d.1.weight - torch.Size([256, 256, 1, 1]): ConvBranchInit backbone.gcn.9.gcn.conv_d.1.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_d.2.weight - torch.Size([256, 256, 1, 1]): ConvBranchInit backbone.gcn.9.gcn.conv_d.2.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_a.0.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_a.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_a.1.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_a.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_a.2.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_a.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_b.0.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_b.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_b.1.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_b.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_b.2.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_b.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.bn.weight - torch.Size([256]): ConstantInit: val=1e-06, bias=0 backbone.gcn.9.gcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.conv.weight - torch.Size([256, 256, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.tcn.conv.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.tcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN cls_head.fc.weight - torch.Size([60, 256]): NormalInit: mean=0, std=0.01, bias=0 cls_head.fc.bias - torch.Size([60]): NormalInit: mean=0, std=0.01, bias=0 2022/12/20 15:08:38 - mmengine - INFO - Checkpoints will be saved to /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d. 2022/12/20 15:08:57 - mmengine - INFO - Epoch(train) [1][ 100/1567] lr: 9.9996e-02 eta: 1:21:35 time: 0.1714 data_time: 0.0069 memory: 1461 loss: 3.0909 top1_acc: 0.3125 top5_acc: 0.8125 loss_cls: 3.0909 2022/12/20 15:09:11 - mmengine - INFO - Epoch(train) [1][ 200/1567] lr: 9.9984e-02 eta: 1:09:25 time: 0.1729 data_time: 0.0070 memory: 1461 loss: 2.1980 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.1980 2022/12/20 15:09:28 - mmengine - INFO - Epoch(train) [1][ 300/1567] lr: 9.9965e-02 eta: 1:09:19 time: 0.1531 data_time: 0.0077 memory: 1461 loss: 1.6966 top1_acc: 0.3750 top5_acc: 0.8750 loss_cls: 1.6966 2022/12/20 15:09:41 - mmengine - INFO - Epoch(train) [1][ 400/1567] lr: 9.9938e-02 eta: 1:05:30 time: 0.0962 data_time: 0.0070 memory: 1461 loss: 1.4093 top1_acc: 0.3125 top5_acc: 0.8750 loss_cls: 1.4093 2022/12/20 15:09:59 - mmengine - INFO - Epoch(train) [1][ 500/1567] lr: 9.9902e-02 eta: 1:06:20 time: 0.1909 data_time: 0.0074 memory: 1461 loss: 1.0360 top1_acc: 0.5000 top5_acc: 1.0000 loss_cls: 1.0360 2022/12/20 15:10:13 - mmengine - INFO - Epoch(train) [1][ 600/1567] lr: 9.9859e-02 eta: 1:05:01 time: 0.1235 data_time: 0.0077 memory: 1461 loss: 1.0702 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.0702 2022/12/20 15:10:28 - mmengine - INFO - Epoch(train) [1][ 700/1567] lr: 9.9808e-02 eta: 1:04:22 time: 0.1242 data_time: 0.0074 memory: 1461 loss: 0.7648 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.7648 2022/12/20 15:10:44 - mmengine - INFO - Epoch(train) [1][ 800/1567] lr: 9.9750e-02 eta: 1:04:02 time: 0.1433 data_time: 0.0071 memory: 1461 loss: 0.8066 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.8066 2022/12/20 15:10:59 - mmengine - INFO - Epoch(train) [1][ 900/1567] lr: 9.9683e-02 eta: 1:03:19 time: 0.1720 data_time: 0.0073 memory: 1461 loss: 0.8264 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8264 2022/12/20 15:11:15 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 15:11:15 - mmengine - INFO - Epoch(train) [1][1000/1567] lr: 9.9609e-02 eta: 1:03:08 time: 0.1413 data_time: 0.0067 memory: 1461 loss: 0.7405 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.7405 2022/12/20 15:11:29 - mmengine - INFO - Epoch(train) [1][1100/1567] lr: 9.9527e-02 eta: 1:02:27 time: 0.1704 data_time: 0.0070 memory: 1461 loss: 0.6753 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.6753 2022/12/20 15:11:44 - mmengine - INFO - Epoch(train) [1][1200/1567] lr: 9.9437e-02 eta: 1:01:52 time: 0.1391 data_time: 0.0080 memory: 1461 loss: 0.7518 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.7518 2022/12/20 15:11:57 - mmengine - INFO - Epoch(train) [1][1300/1567] lr: 9.9339e-02 eta: 1:00:49 time: 0.1304 data_time: 0.0070 memory: 1461 loss: 0.5809 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5809 2022/12/20 15:12:10 - mmengine - INFO - Epoch(train) [1][1400/1567] lr: 9.9234e-02 eta: 0:59:56 time: 0.1569 data_time: 0.0084 memory: 1461 loss: 0.6268 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.6268 2022/12/20 15:12:26 - mmengine - INFO - Epoch(train) [1][1500/1567] lr: 9.9121e-02 eta: 0:59:50 time: 0.1468 data_time: 0.0072 memory: 1461 loss: 0.5329 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.5329 2022/12/20 15:12:35 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 15:12:35 - mmengine - INFO - Epoch(train) [1][1567/1567] lr: 9.9040e-02 eta: 0:59:24 time: 0.1249 data_time: 0.0078 memory: 1461 loss: 0.6787 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.6787 2022/12/20 15:12:35 - mmengine - INFO - Saving checkpoint at 1 epochs 2022/12/20 15:12:41 - mmengine - INFO - Epoch(val) [1][100/129] eta: 0:00:01 time: 0.0486 data_time: 0.0067 memory: 215 2022/12/20 15:12:44 - mmengine - INFO - Epoch(val) [1][129/129] acc/top1: 0.6458 acc/top5: 0.9424 acc/mean1: 0.6458 2022/12/20 15:12:45 - mmengine - INFO - The best checkpoint with 0.6458 acc/top1 at 1 epoch is saved to best_acc/top1_epoch_1.pth. 2022/12/20 15:13:00 - mmengine - INFO - Epoch(train) [2][ 100/1567] lr: 9.8914e-02 eta: 0:59:16 time: 0.1532 data_time: 0.0081 memory: 1461 loss: 0.3939 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3939 2022/12/20 15:13:16 - mmengine - INFO - Epoch(train) [2][ 200/1567] lr: 9.8781e-02 eta: 0:59:11 time: 0.1903 data_time: 0.0074 memory: 1461 loss: 0.5405 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5405 2022/12/20 15:13:32 - mmengine - INFO - Epoch(train) [2][ 300/1567] lr: 9.8639e-02 eta: 0:59:06 time: 0.1571 data_time: 0.0073 memory: 1461 loss: 0.5542 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.5542 2022/12/20 15:13:48 - mmengine - INFO - Epoch(train) [2][ 400/1567] lr: 9.8491e-02 eta: 0:58:51 time: 0.1631 data_time: 0.0074 memory: 1461 loss: 0.4135 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4135 2022/12/20 15:13:53 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 15:14:04 - mmengine - INFO - Epoch(train) [2][ 500/1567] lr: 9.8334e-02 eta: 0:58:52 time: 0.1522 data_time: 0.0079 memory: 1461 loss: 0.4481 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4481 2022/12/20 15:14:19 - mmengine - INFO - Epoch(train) [2][ 600/1567] lr: 9.8170e-02 eta: 0:58:33 time: 0.1863 data_time: 0.0073 memory: 1461 loss: 0.4799 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4799 2022/12/20 15:14:36 - mmengine - INFO - Epoch(train) [2][ 700/1567] lr: 9.7998e-02 eta: 0:58:33 time: 0.1495 data_time: 0.0073 memory: 1461 loss: 0.4360 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4360 2022/12/20 15:14:50 - mmengine - INFO - Epoch(train) [2][ 800/1567] lr: 9.7819e-02 eta: 0:58:03 time: 0.1216 data_time: 0.0073 memory: 1461 loss: 0.4130 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4130 2022/12/20 15:15:08 - mmengine - INFO - Epoch(train) [2][ 900/1567] lr: 9.7632e-02 eta: 0:58:10 time: 0.1932 data_time: 0.0070 memory: 1461 loss: 0.4668 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4668 2022/12/20 15:15:22 - mmengine - INFO - Epoch(train) [2][1000/1567] lr: 9.7438e-02 eta: 0:57:41 time: 0.1425 data_time: 0.0068 memory: 1461 loss: 0.3787 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3787 2022/12/20 15:15:38 - mmengine - INFO - Epoch(train) [2][1100/1567] lr: 9.7236e-02 eta: 0:57:29 time: 0.1537 data_time: 0.0086 memory: 1461 loss: 0.3896 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3896 2022/12/20 15:15:51 - mmengine - INFO - Epoch(train) [2][1200/1567] lr: 9.7027e-02 eta: 0:56:59 time: 0.1403 data_time: 0.0068 memory: 1461 loss: 0.4520 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.4520 2022/12/20 15:16:05 - mmengine - INFO - Epoch(train) [2][1300/1567] lr: 9.6810e-02 eta: 0:56:30 time: 0.1136 data_time: 0.0079 memory: 1461 loss: 0.4431 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4431 2022/12/20 15:16:22 - mmengine - INFO - Epoch(train) [2][1400/1567] lr: 9.6587e-02 eta: 0:56:30 time: 0.1850 data_time: 0.0081 memory: 1461 loss: 0.4063 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.4063 2022/12/20 15:16:27 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 15:16:37 - mmengine - INFO - Epoch(train) [2][1500/1567] lr: 9.6355e-02 eta: 0:56:14 time: 0.1262 data_time: 0.0079 memory: 1461 loss: 0.3778 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.3778 2022/12/20 15:16:47 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 15:16:47 - mmengine - INFO - Epoch(train) [2][1567/1567] lr: 9.6196e-02 eta: 0:56:01 time: 0.1939 data_time: 0.0074 memory: 1461 loss: 0.6195 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.6195 2022/12/20 15:16:47 - mmengine - INFO - Saving checkpoint at 2 epochs 2022/12/20 15:16:56 - mmengine - INFO - Epoch(val) [2][100/129] eta: 0:00:02 time: 0.1135 data_time: 0.0064 memory: 215 2022/12/20 15:16:59 - mmengine - INFO - Epoch(val) [2][129/129] acc/top1: 0.7235 acc/top5: 0.9635 acc/mean1: 0.7231 2022/12/20 15:16:59 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_1.pth is removed 2022/12/20 15:17:00 - mmengine - INFO - The best checkpoint with 0.7235 acc/top1 at 2 epoch is saved to best_acc/top1_epoch_2.pth. 2022/12/20 15:17:14 - mmengine - INFO - Epoch(train) [3][ 100/1567] lr: 9.5953e-02 eta: 0:55:41 time: 0.1531 data_time: 0.0076 memory: 1461 loss: 0.4104 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4104 2022/12/20 15:17:30 - mmengine - INFO - Epoch(train) [3][ 200/1567] lr: 9.5703e-02 eta: 0:55:27 time: 0.1578 data_time: 0.0073 memory: 1461 loss: 0.3781 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3781 2022/12/20 15:17:46 - mmengine - INFO - Epoch(train) [3][ 300/1567] lr: 9.5445e-02 eta: 0:55:16 time: 0.1563 data_time: 0.0081 memory: 1461 loss: 0.3143 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3143 2022/12/20 15:18:01 - mmengine - INFO - Epoch(train) [3][ 400/1567] lr: 9.5180e-02 eta: 0:55:00 time: 0.1535 data_time: 0.0074 memory: 1461 loss: 0.3261 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3261 2022/12/20 15:18:17 - mmengine - INFO - Epoch(train) [3][ 500/1567] lr: 9.4908e-02 eta: 0:54:48 time: 0.1459 data_time: 0.0082 memory: 1461 loss: 0.2922 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2922 2022/12/20 15:18:32 - mmengine - INFO - Epoch(train) [3][ 600/1567] lr: 9.4629e-02 eta: 0:54:32 time: 0.2112 data_time: 0.0073 memory: 1461 loss: 0.3194 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3194 2022/12/20 15:18:48 - mmengine - INFO - Epoch(train) [3][ 700/1567] lr: 9.4343e-02 eta: 0:54:20 time: 0.1607 data_time: 0.0073 memory: 1461 loss: 0.3045 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3045 2022/12/20 15:19:02 - mmengine - INFO - Epoch(train) [3][ 800/1567] lr: 9.4050e-02 eta: 0:53:57 time: 0.1495 data_time: 0.0072 memory: 1461 loss: 0.3638 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3638 2022/12/20 15:19:14 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 15:19:19 - mmengine - INFO - Epoch(train) [3][ 900/1567] lr: 9.3750e-02 eta: 0:53:52 time: 0.1668 data_time: 0.0067 memory: 1461 loss: 0.3008 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3008 2022/12/20 15:19:33 - mmengine - INFO - Epoch(train) [3][1000/1567] lr: 9.3444e-02 eta: 0:53:29 time: 0.1737 data_time: 0.0071 memory: 1461 loss: 0.3315 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3315 2022/12/20 15:19:49 - mmengine - INFO - Epoch(train) [3][1100/1567] lr: 9.3130e-02 eta: 0:53:16 time: 0.1674 data_time: 0.0075 memory: 1461 loss: 0.2721 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2721 2022/12/20 15:20:02 - mmengine - INFO - Epoch(train) [3][1200/1567] lr: 9.2810e-02 eta: 0:52:50 time: 0.1428 data_time: 0.0066 memory: 1461 loss: 0.2162 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2162 2022/12/20 15:20:15 - mmengine - INFO - Epoch(train) [3][1300/1567] lr: 9.2483e-02 eta: 0:52:26 time: 0.1457 data_time: 0.0080 memory: 1461 loss: 0.2678 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2678 2022/12/20 15:20:33 - mmengine - INFO - Epoch(train) [3][1400/1567] lr: 9.2149e-02 eta: 0:52:19 time: 0.1463 data_time: 0.0074 memory: 1461 loss: 0.2827 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2827 2022/12/20 15:20:47 - mmengine - INFO - Epoch(train) [3][1500/1567] lr: 9.1809e-02 eta: 0:51:58 time: 0.1270 data_time: 0.0073 memory: 1461 loss: 0.2482 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2482 2022/12/20 15:20:59 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 15:20:59 - mmengine - INFO - Epoch(train) [3][1567/1567] lr: 9.1577e-02 eta: 0:51:56 time: 0.1713 data_time: 0.0074 memory: 1461 loss: 0.4631 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.4631 2022/12/20 15:20:59 - mmengine - INFO - Saving checkpoint at 3 epochs 2022/12/20 15:21:07 - mmengine - INFO - Epoch(val) [3][100/129] eta: 0:00:02 time: 0.0720 data_time: 0.0068 memory: 215 2022/12/20 15:21:10 - mmengine - INFO - Epoch(val) [3][129/129] acc/top1: 0.7621 acc/top5: 0.9769 acc/mean1: 0.7619 2022/12/20 15:21:10 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_2.pth is removed 2022/12/20 15:21:10 - mmengine - INFO - The best checkpoint with 0.7621 acc/top1 at 3 epoch is saved to best_acc/top1_epoch_3.pth. 2022/12/20 15:21:26 - mmengine - INFO - Epoch(train) [4][ 100/1567] lr: 9.1226e-02 eta: 0:51:40 time: 0.1509 data_time: 0.0071 memory: 1461 loss: 0.2303 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2303 2022/12/20 15:21:42 - mmengine - INFO - Epoch(train) [4][ 200/1567] lr: 9.0868e-02 eta: 0:51:30 time: 0.1356 data_time: 0.0077 memory: 1461 loss: 0.2668 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2668 2022/12/20 15:21:57 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 15:21:57 - mmengine - INFO - Epoch(train) [4][ 300/1567] lr: 9.0504e-02 eta: 0:51:12 time: 0.1890 data_time: 0.0072 memory: 1461 loss: 0.2532 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2532 2022/12/20 15:22:14 - mmengine - INFO - Epoch(train) [4][ 400/1567] lr: 9.0133e-02 eta: 0:51:03 time: 0.1687 data_time: 0.0074 memory: 1461 loss: 0.2630 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2630 2022/12/20 15:22:28 - mmengine - INFO - Epoch(train) [4][ 500/1567] lr: 8.9756e-02 eta: 0:50:44 time: 0.1142 data_time: 0.0079 memory: 1461 loss: 0.2111 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2111 2022/12/20 15:22:46 - mmengine - INFO - Epoch(train) [4][ 600/1567] lr: 8.9373e-02 eta: 0:50:37 time: 0.1919 data_time: 0.0075 memory: 1461 loss: 0.2748 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2748 2022/12/20 15:23:00 - mmengine - INFO - Epoch(train) [4][ 700/1567] lr: 8.8984e-02 eta: 0:50:19 time: 0.1564 data_time: 0.0074 memory: 1461 loss: 0.2598 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2598 2022/12/20 15:23:16 - mmengine - INFO - Epoch(train) [4][ 800/1567] lr: 8.8589e-02 eta: 0:50:05 time: 0.1480 data_time: 0.0071 memory: 1461 loss: 0.2172 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2172 2022/12/20 15:23:31 - mmengine - INFO - Epoch(train) [4][ 900/1567] lr: 8.8187e-02 eta: 0:49:49 time: 0.1327 data_time: 0.0080 memory: 1461 loss: 0.1854 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1854 2022/12/20 15:23:47 - mmengine - INFO - Epoch(train) [4][1000/1567] lr: 8.7780e-02 eta: 0:49:35 time: 0.1541 data_time: 0.0065 memory: 1461 loss: 0.2614 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2614 2022/12/20 15:24:02 - mmengine - INFO - Epoch(train) [4][1100/1567] lr: 8.7367e-02 eta: 0:49:18 time: 0.1495 data_time: 0.0072 memory: 1461 loss: 0.2750 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2750 2022/12/20 15:24:16 - mmengine - INFO - Epoch(train) [4][1200/1567] lr: 8.6947e-02 eta: 0:48:58 time: 0.1562 data_time: 0.0095 memory: 1461 loss: 0.2945 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2945 2022/12/20 15:24:33 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 15:24:33 - mmengine - INFO - Epoch(train) [4][1300/1567] lr: 8.6522e-02 eta: 0:48:48 time: 0.1870 data_time: 0.0078 memory: 1461 loss: 0.2422 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2422 2022/12/20 15:24:48 - mmengine - INFO - Epoch(train) [4][1400/1567] lr: 8.6092e-02 eta: 0:48:31 time: 0.1415 data_time: 0.0076 memory: 1461 loss: 0.2078 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2078 2022/12/20 15:25:03 - mmengine - INFO - Epoch(train) [4][1500/1567] lr: 8.5655e-02 eta: 0:48:14 time: 0.1494 data_time: 0.0071 memory: 1461 loss: 0.2525 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2525 2022/12/20 15:25:13 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 15:25:13 - mmengine - INFO - Epoch(train) [4][1567/1567] lr: 8.5360e-02 eta: 0:48:06 time: 0.1358 data_time: 0.0072 memory: 1461 loss: 0.3554 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.3554 2022/12/20 15:25:13 - mmengine - INFO - Saving checkpoint at 4 epochs 2022/12/20 15:25:19 - mmengine - INFO - Epoch(val) [4][100/129] eta: 0:00:01 time: 0.0589 data_time: 0.0071 memory: 215 2022/12/20 15:25:21 - mmengine - INFO - Epoch(val) [4][129/129] acc/top1: 0.8334 acc/top5: 0.9867 acc/mean1: 0.8333 2022/12/20 15:25:21 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_3.pth is removed 2022/12/20 15:25:22 - mmengine - INFO - The best checkpoint with 0.8334 acc/top1 at 4 epoch is saved to best_acc/top1_epoch_4.pth. 2022/12/20 15:25:39 - mmengine - INFO - Epoch(train) [5][ 100/1567] lr: 8.4914e-02 eta: 0:47:57 time: 0.2031 data_time: 0.0078 memory: 1461 loss: 0.2588 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2588 2022/12/20 15:25:54 - mmengine - INFO - Epoch(train) [5][ 200/1567] lr: 8.4463e-02 eta: 0:47:39 time: 0.1500 data_time: 0.0074 memory: 1461 loss: 0.2674 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2674 2022/12/20 15:26:09 - mmengine - INFO - Epoch(train) [5][ 300/1567] lr: 8.4006e-02 eta: 0:47:25 time: 0.1478 data_time: 0.0076 memory: 1461 loss: 0.2250 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2250 2022/12/20 15:26:25 - mmengine - INFO - Epoch(train) [5][ 400/1567] lr: 8.3544e-02 eta: 0:47:09 time: 0.1432 data_time: 0.0074 memory: 1461 loss: 0.2571 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2571 2022/12/20 15:26:40 - mmengine - INFO - Epoch(train) [5][ 500/1567] lr: 8.3077e-02 eta: 0:46:54 time: 0.2068 data_time: 0.0074 memory: 1461 loss: 0.2527 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2527 2022/12/20 15:26:55 - mmengine - INFO - Epoch(train) [5][ 600/1567] lr: 8.2605e-02 eta: 0:46:38 time: 0.1509 data_time: 0.0075 memory: 1461 loss: 0.2398 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2398 2022/12/20 15:27:11 - mmengine - INFO - Epoch(train) [5][ 700/1567] lr: 8.2127e-02 eta: 0:46:22 time: 0.1541 data_time: 0.0074 memory: 1461 loss: 0.1905 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.1905 2022/12/20 15:27:16 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 15:27:26 - mmengine - INFO - Epoch(train) [5][ 800/1567] lr: 8.1645e-02 eta: 0:46:07 time: 0.1526 data_time: 0.0075 memory: 1461 loss: 0.2212 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2212 2022/12/20 15:27:41 - mmengine - INFO - Epoch(train) [5][ 900/1567] lr: 8.1157e-02 eta: 0:45:49 time: 0.1363 data_time: 0.0072 memory: 1461 loss: 0.2045 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2045 2022/12/20 15:27:55 - mmengine - INFO - Epoch(train) [5][1000/1567] lr: 8.0665e-02 eta: 0:45:33 time: 0.1422 data_time: 0.0077 memory: 1461 loss: 0.1961 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.1961 2022/12/20 15:28:09 - mmengine - INFO - Epoch(train) [5][1100/1567] lr: 8.0167e-02 eta: 0:45:13 time: 0.1415 data_time: 0.0069 memory: 1461 loss: 0.2158 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2158 2022/12/20 15:28:23 - mmengine - INFO - Epoch(train) [5][1200/1567] lr: 7.9665e-02 eta: 0:44:56 time: 0.1851 data_time: 0.0075 memory: 1461 loss: 0.1727 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1727 2022/12/20 15:28:38 - mmengine - INFO - Epoch(train) [5][1300/1567] lr: 7.9159e-02 eta: 0:44:39 time: 0.1321 data_time: 0.0077 memory: 1461 loss: 0.1680 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1680 2022/12/20 15:28:53 - mmengine - INFO - Epoch(train) [5][1400/1567] lr: 7.8647e-02 eta: 0:44:23 time: 0.1572 data_time: 0.0078 memory: 1461 loss: 0.2372 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2372 2022/12/20 15:29:08 - mmengine - INFO - Epoch(train) [5][1500/1567] lr: 7.8132e-02 eta: 0:44:08 time: 0.1533 data_time: 0.0078 memory: 1461 loss: 0.1690 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1690 2022/12/20 15:29:17 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 15:29:17 - mmengine - INFO - Epoch(train) [5][1567/1567] lr: 7.7784e-02 eta: 0:43:55 time: 0.1129 data_time: 0.0075 memory: 1461 loss: 0.3541 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.3541 2022/12/20 15:29:17 - mmengine - INFO - Saving checkpoint at 5 epochs 2022/12/20 15:29:25 - mmengine - INFO - Epoch(val) [5][100/129] eta: 0:00:02 time: 0.1161 data_time: 0.0062 memory: 215 2022/12/20 15:29:28 - mmengine - INFO - Epoch(val) [5][129/129] acc/top1: 0.8353 acc/top5: 0.9834 acc/mean1: 0.8353 2022/12/20 15:29:28 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_4.pth is removed 2022/12/20 15:29:29 - mmengine - INFO - The best checkpoint with 0.8353 acc/top1 at 5 epoch is saved to best_acc/top1_epoch_5.pth. 2022/12/20 15:29:44 - mmengine - INFO - Epoch(train) [6][ 100/1567] lr: 7.7261e-02 eta: 0:43:40 time: 0.1338 data_time: 0.0075 memory: 1461 loss: 0.2321 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2321 2022/12/20 15:29:53 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 15:29:59 - mmengine - INFO - Epoch(train) [6][ 200/1567] lr: 7.6733e-02 eta: 0:43:24 time: 0.1747 data_time: 0.0075 memory: 1461 loss: 0.1105 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1105 2022/12/20 15:30:15 - mmengine - INFO - Epoch(train) [6][ 300/1567] lr: 7.6202e-02 eta: 0:43:10 time: 0.1641 data_time: 0.0084 memory: 1461 loss: 0.1692 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1692 2022/12/20 15:30:29 - mmengine - INFO - Epoch(train) [6][ 400/1567] lr: 7.5666e-02 eta: 0:42:52 time: 0.1521 data_time: 0.0076 memory: 1461 loss: 0.2541 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2541 2022/12/20 15:30:46 - mmengine - INFO - Epoch(train) [6][ 500/1567] lr: 7.5126e-02 eta: 0:42:40 time: 0.1468 data_time: 0.0077 memory: 1461 loss: 0.1257 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1257 2022/12/20 15:31:01 - mmengine - INFO - Epoch(train) [6][ 600/1567] lr: 7.4583e-02 eta: 0:42:24 time: 0.1987 data_time: 0.0071 memory: 1461 loss: 0.1617 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1617 2022/12/20 15:31:17 - mmengine - INFO - Epoch(train) [6][ 700/1567] lr: 7.4035e-02 eta: 0:42:10 time: 0.1547 data_time: 0.0066 memory: 1461 loss: 0.1734 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1734 2022/12/20 15:31:31 - mmengine - INFO - Epoch(train) [6][ 800/1567] lr: 7.3484e-02 eta: 0:41:52 time: 0.1305 data_time: 0.0071 memory: 1461 loss: 0.1538 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1538 2022/12/20 15:31:46 - mmengine - INFO - Epoch(train) [6][ 900/1567] lr: 7.2929e-02 eta: 0:41:37 time: 0.1472 data_time: 0.0071 memory: 1461 loss: 0.1761 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1761 2022/12/20 15:32:00 - mmengine - INFO - Epoch(train) [6][1000/1567] lr: 7.2371e-02 eta: 0:41:18 time: 0.1449 data_time: 0.0073 memory: 1461 loss: 0.1258 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1258 2022/12/20 15:32:14 - mmengine - INFO - Epoch(train) [6][1100/1567] lr: 7.1809e-02 eta: 0:41:02 time: 0.2171 data_time: 0.0086 memory: 1461 loss: 0.2230 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2230 2022/12/20 15:32:25 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 15:32:30 - mmengine - INFO - Epoch(train) [6][1200/1567] lr: 7.1243e-02 eta: 0:40:47 time: 0.1419 data_time: 0.0079 memory: 1461 loss: 0.1849 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1849 2022/12/20 15:32:43 - mmengine - INFO - Epoch(train) [6][1300/1567] lr: 7.0674e-02 eta: 0:40:29 time: 0.1170 data_time: 0.0073 memory: 1461 loss: 0.1787 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1787 2022/12/20 15:33:00 - mmengine - INFO - Epoch(train) [6][1400/1567] lr: 7.0102e-02 eta: 0:40:16 time: 0.1467 data_time: 0.0081 memory: 1461 loss: 0.2009 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2009 2022/12/20 15:33:13 - mmengine - INFO - Epoch(train) [6][1500/1567] lr: 6.9527e-02 eta: 0:39:57 time: 0.0856 data_time: 0.0070 memory: 1461 loss: 0.1444 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1444 2022/12/20 15:33:25 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 15:33:25 - mmengine - INFO - Epoch(train) [6][1567/1567] lr: 6.9140e-02 eta: 0:39:49 time: 0.1585 data_time: 0.0076 memory: 1461 loss: 0.2947 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.2947 2022/12/20 15:33:25 - mmengine - INFO - Saving checkpoint at 6 epochs 2022/12/20 15:33:31 - mmengine - INFO - Epoch(val) [6][100/129] eta: 0:00:01 time: 0.0520 data_time: 0.0071 memory: 215 2022/12/20 15:33:33 - mmengine - INFO - Epoch(val) [6][129/129] acc/top1: 0.8502 acc/top5: 0.9801 acc/mean1: 0.8501 2022/12/20 15:33:33 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_5.pth is removed 2022/12/20 15:33:34 - mmengine - INFO - The best checkpoint with 0.8502 acc/top1 at 6 epoch is saved to best_acc/top1_epoch_6.pth. 2022/12/20 15:33:50 - mmengine - INFO - Epoch(train) [7][ 100/1567] lr: 6.8560e-02 eta: 0:39:35 time: 0.1842 data_time: 0.0071 memory: 1461 loss: 0.1577 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1577 2022/12/20 15:34:05 - mmengine - INFO - Epoch(train) [7][ 200/1567] lr: 6.7976e-02 eta: 0:39:20 time: 0.1389 data_time: 0.0072 memory: 1461 loss: 0.1858 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1858 2022/12/20 15:34:20 - mmengine - INFO - Epoch(train) [7][ 300/1567] lr: 6.7390e-02 eta: 0:39:04 time: 0.1634 data_time: 0.0073 memory: 1461 loss: 0.1485 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.1485 2022/12/20 15:34:36 - mmengine - INFO - Epoch(train) [7][ 400/1567] lr: 6.6802e-02 eta: 0:38:50 time: 0.1606 data_time: 0.0090 memory: 1461 loss: 0.1422 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1422 2022/12/20 15:34:50 - mmengine - INFO - Epoch(train) [7][ 500/1567] lr: 6.6210e-02 eta: 0:38:33 time: 0.1653 data_time: 0.0071 memory: 1461 loss: 0.1566 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1566 2022/12/20 15:35:05 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 15:35:06 - mmengine - INFO - Epoch(train) [7][ 600/1567] lr: 6.5616e-02 eta: 0:38:18 time: 0.1165 data_time: 0.0071 memory: 1461 loss: 0.1220 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1220 2022/12/20 15:35:19 - mmengine - INFO - Epoch(train) [7][ 700/1567] lr: 6.5020e-02 eta: 0:38:01 time: 0.1627 data_time: 0.0073 memory: 1461 loss: 0.1026 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1026 2022/12/20 15:35:34 - mmengine - INFO - Epoch(train) [7][ 800/1567] lr: 6.4421e-02 eta: 0:37:45 time: 0.1325 data_time: 0.0078 memory: 1461 loss: 0.1434 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1434 2022/12/20 15:35:47 - mmengine - INFO - Epoch(train) [7][ 900/1567] lr: 6.3820e-02 eta: 0:37:27 time: 0.1355 data_time: 0.0075 memory: 1461 loss: 0.1795 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1795 2022/12/20 15:36:01 - mmengine - INFO - Epoch(train) [7][1000/1567] lr: 6.3217e-02 eta: 0:37:09 time: 0.1699 data_time: 0.0083 memory: 1461 loss: 0.1223 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1223 2022/12/20 15:36:19 - mmengine - INFO - Epoch(train) [7][1100/1567] lr: 6.2612e-02 eta: 0:36:58 time: 0.1869 data_time: 0.0070 memory: 1461 loss: 0.1100 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1100 2022/12/20 15:36:33 - mmengine - INFO - Epoch(train) [7][1200/1567] lr: 6.2005e-02 eta: 0:36:40 time: 0.1622 data_time: 0.0074 memory: 1461 loss: 0.0887 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0887 2022/12/20 15:36:50 - mmengine - INFO - Epoch(train) [7][1300/1567] lr: 6.1396e-02 eta: 0:36:28 time: 0.1878 data_time: 0.0071 memory: 1461 loss: 0.1273 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1273 2022/12/20 15:37:05 - mmengine - INFO - Epoch(train) [7][1400/1567] lr: 6.0785e-02 eta: 0:36:12 time: 0.1395 data_time: 0.0078 memory: 1461 loss: 0.1781 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1781 2022/12/20 15:37:22 - mmengine - INFO - Epoch(train) [7][1500/1567] lr: 6.0172e-02 eta: 0:36:00 time: 0.2188 data_time: 0.0072 memory: 1461 loss: 0.1599 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1599 2022/12/20 15:37:33 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 15:37:33 - mmengine - INFO - Epoch(train) [7][1567/1567] lr: 5.9761e-02 eta: 0:35:51 time: 0.1463 data_time: 0.0074 memory: 1461 loss: 0.3539 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.3539 2022/12/20 15:37:33 - mmengine - INFO - Saving checkpoint at 7 epochs 2022/12/20 15:37:39 - mmengine - INFO - Epoch(val) [7][100/129] eta: 0:00:01 time: 0.0334 data_time: 0.0073 memory: 215 2022/12/20 15:37:42 - mmengine - INFO - Epoch(val) [7][129/129] acc/top1: 0.8684 acc/top5: 0.9870 acc/mean1: 0.8684 2022/12/20 15:37:42 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_6.pth is removed 2022/12/20 15:37:43 - mmengine - INFO - The best checkpoint with 0.8684 acc/top1 at 7 epoch is saved to best_acc/top1_epoch_7.pth. 2022/12/20 15:37:48 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 15:38:01 - mmengine - INFO - Epoch(train) [8][ 100/1567] lr: 5.9145e-02 eta: 0:35:39 time: 0.1914 data_time: 0.0075 memory: 1461 loss: 0.1010 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1010 2022/12/20 15:38:16 - mmengine - INFO - Epoch(train) [8][ 200/1567] lr: 5.8529e-02 eta: 0:35:23 time: 0.1446 data_time: 0.0076 memory: 1461 loss: 0.1293 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1293 2022/12/20 15:38:34 - mmengine - INFO - Epoch(train) [8][ 300/1567] lr: 5.7911e-02 eta: 0:35:11 time: 0.2134 data_time: 0.0070 memory: 1461 loss: 0.1041 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1041 2022/12/20 15:38:49 - mmengine - INFO - Epoch(train) [8][ 400/1567] lr: 5.7292e-02 eta: 0:34:56 time: 0.1325 data_time: 0.0078 memory: 1461 loss: 0.0850 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0850 2022/12/20 15:39:05 - mmengine - INFO - Epoch(train) [8][ 500/1567] lr: 5.6671e-02 eta: 0:34:41 time: 0.1676 data_time: 0.0075 memory: 1461 loss: 0.1088 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1088 2022/12/20 15:39:21 - mmengine - INFO - Epoch(train) [8][ 600/1567] lr: 5.6050e-02 eta: 0:34:27 time: 0.1288 data_time: 0.0078 memory: 1461 loss: 0.1413 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1413 2022/12/20 15:39:36 - mmengine - INFO - Epoch(train) [8][ 700/1567] lr: 5.5427e-02 eta: 0:34:11 time: 0.1465 data_time: 0.0068 memory: 1461 loss: 0.1077 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1077 2022/12/20 15:39:52 - mmengine - INFO - Epoch(train) [8][ 800/1567] lr: 5.4804e-02 eta: 0:33:56 time: 0.1260 data_time: 0.0067 memory: 1461 loss: 0.1351 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1351 2022/12/20 15:40:05 - mmengine - INFO - Epoch(train) [8][ 900/1567] lr: 5.4180e-02 eta: 0:33:39 time: 0.1412 data_time: 0.0079 memory: 1461 loss: 0.1037 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1037 2022/12/20 15:40:20 - mmengine - INFO - Epoch(train) [8][1000/1567] lr: 5.3556e-02 eta: 0:33:23 time: 0.2332 data_time: 0.0082 memory: 1461 loss: 0.1139 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1139 2022/12/20 15:40:25 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 15:40:36 - mmengine - INFO - Epoch(train) [8][1100/1567] lr: 5.2930e-02 eta: 0:33:09 time: 0.1646 data_time: 0.0074 memory: 1461 loss: 0.1219 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1219 2022/12/20 15:40:50 - mmengine - INFO - Epoch(train) [8][1200/1567] lr: 5.2305e-02 eta: 0:32:52 time: 0.1189 data_time: 0.0077 memory: 1461 loss: 0.0956 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0956 2022/12/20 15:41:08 - mmengine - INFO - Epoch(train) [8][1300/1567] lr: 5.1679e-02 eta: 0:32:39 time: 0.1599 data_time: 0.0073 memory: 1461 loss: 0.0966 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0966 2022/12/20 15:41:23 - mmengine - INFO - Epoch(train) [8][1400/1567] lr: 5.1052e-02 eta: 0:32:24 time: 0.1486 data_time: 0.0076 memory: 1461 loss: 0.1088 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1088 2022/12/20 15:41:39 - mmengine - INFO - Epoch(train) [8][1500/1567] lr: 5.0426e-02 eta: 0:32:10 time: 0.1570 data_time: 0.0070 memory: 1461 loss: 0.1069 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1069 2022/12/20 15:41:50 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 15:41:50 - mmengine - INFO - Epoch(train) [8][1567/1567] lr: 5.0006e-02 eta: 0:32:00 time: 0.1380 data_time: 0.0079 memory: 1461 loss: 0.2612 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.2612 2022/12/20 15:41:50 - mmengine - INFO - Saving checkpoint at 8 epochs 2022/12/20 15:41:56 - mmengine - INFO - Epoch(val) [8][100/129] eta: 0:00:01 time: 0.0284 data_time: 0.0069 memory: 215 2022/12/20 15:41:58 - mmengine - INFO - Epoch(val) [8][129/129] acc/top1: 0.8686 acc/top5: 0.9874 acc/mean1: 0.8685 2022/12/20 15:41:58 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_7.pth is removed 2022/12/20 15:41:58 - mmengine - INFO - The best checkpoint with 0.8686 acc/top1 at 8 epoch is saved to best_acc/top1_epoch_8.pth. 2022/12/20 15:42:15 - mmengine - INFO - Epoch(train) [9][ 100/1567] lr: 4.9380e-02 eta: 0:31:46 time: 0.1595 data_time: 0.0077 memory: 1461 loss: 0.0777 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0777 2022/12/20 15:42:30 - mmengine - INFO - Epoch(train) [9][ 200/1567] lr: 4.8753e-02 eta: 0:31:30 time: 0.1393 data_time: 0.0075 memory: 1461 loss: 0.1252 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1252 2022/12/20 15:42:47 - mmengine - INFO - Epoch(train) [9][ 300/1567] lr: 4.8127e-02 eta: 0:31:16 time: 0.1648 data_time: 0.0071 memory: 1461 loss: 0.1182 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1182 2022/12/20 15:43:02 - mmengine - INFO - Epoch(train) [9][ 400/1567] lr: 4.7501e-02 eta: 0:31:01 time: 0.1429 data_time: 0.0077 memory: 1461 loss: 0.0949 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0949 2022/12/20 15:43:12 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 15:43:18 - mmengine - INFO - Epoch(train) [9][ 500/1567] lr: 4.6876e-02 eta: 0:30:47 time: 0.1702 data_time: 0.0079 memory: 1461 loss: 0.1126 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1126 2022/12/20 15:43:33 - mmengine - INFO - Epoch(train) [9][ 600/1567] lr: 4.6251e-02 eta: 0:30:31 time: 0.1310 data_time: 0.0075 memory: 1461 loss: 0.1033 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1033 2022/12/20 15:43:48 - mmengine - INFO - Epoch(train) [9][ 700/1567] lr: 4.5626e-02 eta: 0:30:15 time: 0.1732 data_time: 0.0070 memory: 1461 loss: 0.0906 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0906 2022/12/20 15:44:03 - mmengine - INFO - Epoch(train) [9][ 800/1567] lr: 4.5003e-02 eta: 0:29:59 time: 0.1390 data_time: 0.0080 memory: 1461 loss: 0.0845 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0845 2022/12/20 15:44:16 - mmengine - INFO - Epoch(train) [9][ 900/1567] lr: 4.4380e-02 eta: 0:29:42 time: 0.1487 data_time: 0.0081 memory: 1461 loss: 0.1348 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1348 2022/12/20 15:44:31 - mmengine - INFO - Epoch(train) [9][1000/1567] lr: 4.3757e-02 eta: 0:29:26 time: 0.0994 data_time: 0.0085 memory: 1461 loss: 0.0761 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0761 2022/12/20 15:44:48 - mmengine - INFO - Epoch(train) [9][1100/1567] lr: 4.3136e-02 eta: 0:29:12 time: 0.1643 data_time: 0.0073 memory: 1461 loss: 0.1081 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1081 2022/12/20 15:45:03 - mmengine - INFO - Epoch(train) [9][1200/1567] lr: 4.2516e-02 eta: 0:28:56 time: 0.1388 data_time: 0.0081 memory: 1461 loss: 0.0848 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0848 2022/12/20 15:45:20 - mmengine - INFO - Epoch(train) [9][1300/1567] lr: 4.1897e-02 eta: 0:28:43 time: 0.1834 data_time: 0.0071 memory: 1461 loss: 0.1154 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1154 2022/12/20 15:45:34 - mmengine - INFO - Epoch(train) [9][1400/1567] lr: 4.1280e-02 eta: 0:28:27 time: 0.1586 data_time: 0.0081 memory: 1461 loss: 0.1122 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1122 2022/12/20 15:45:45 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 15:45:51 - mmengine - INFO - Epoch(train) [9][1500/1567] lr: 4.0664e-02 eta: 0:28:12 time: 0.1497 data_time: 0.0074 memory: 1461 loss: 0.0665 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0665 2022/12/20 15:46:01 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 15:46:01 - mmengine - INFO - Epoch(train) [9][1567/1567] lr: 4.0252e-02 eta: 0:28:02 time: 0.1427 data_time: 0.0073 memory: 1461 loss: 0.3053 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.3053 2022/12/20 15:46:01 - mmengine - INFO - Saving checkpoint at 9 epochs 2022/12/20 15:46:07 - mmengine - INFO - Epoch(val) [9][100/129] eta: 0:00:01 time: 0.0284 data_time: 0.0070 memory: 215 2022/12/20 15:46:10 - mmengine - INFO - Epoch(val) [9][129/129] acc/top1: 0.8777 acc/top5: 0.9879 acc/mean1: 0.8775 2022/12/20 15:46:10 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_8.pth is removed 2022/12/20 15:46:11 - mmengine - INFO - The best checkpoint with 0.8777 acc/top1 at 9 epoch is saved to best_acc/top1_epoch_9.pth. 2022/12/20 15:46:27 - mmengine - INFO - Epoch(train) [10][ 100/1567] lr: 3.9638e-02 eta: 0:27:47 time: 0.1357 data_time: 0.0076 memory: 1461 loss: 0.0606 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0606 2022/12/20 15:46:41 - mmengine - INFO - Epoch(train) [10][ 200/1567] lr: 3.9026e-02 eta: 0:27:31 time: 0.1138 data_time: 0.0075 memory: 1461 loss: 0.1006 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1006 2022/12/20 15:46:58 - mmengine - INFO - Epoch(train) [10][ 300/1567] lr: 3.8415e-02 eta: 0:27:17 time: 0.1583 data_time: 0.0073 memory: 1461 loss: 0.0546 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0546 2022/12/20 15:47:14 - mmengine - INFO - Epoch(train) [10][ 400/1567] lr: 3.7807e-02 eta: 0:27:02 time: 0.1592 data_time: 0.0074 memory: 1461 loss: 0.0736 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0736 2022/12/20 15:47:30 - mmengine - INFO - Epoch(train) [10][ 500/1567] lr: 3.7200e-02 eta: 0:26:47 time: 0.1747 data_time: 0.0071 memory: 1461 loss: 0.0656 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0656 2022/12/20 15:47:44 - mmengine - INFO - Epoch(train) [10][ 600/1567] lr: 3.6596e-02 eta: 0:26:31 time: 0.1493 data_time: 0.0073 memory: 1461 loss: 0.0552 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0552 2022/12/20 15:48:00 - mmengine - INFO - Epoch(train) [10][ 700/1567] lr: 3.5993e-02 eta: 0:26:16 time: 0.1511 data_time: 0.0071 memory: 1461 loss: 0.0751 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.0751 2022/12/20 15:48:14 - mmengine - INFO - Epoch(train) [10][ 800/1567] lr: 3.5393e-02 eta: 0:26:00 time: 0.1358 data_time: 0.0080 memory: 1461 loss: 0.0536 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0536 2022/12/20 15:48:27 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 15:48:27 - mmengine - INFO - Epoch(train) [10][ 900/1567] lr: 3.4795e-02 eta: 0:25:43 time: 0.0885 data_time: 0.0076 memory: 1461 loss: 0.0586 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0586 2022/12/20 15:48:42 - mmengine - INFO - Epoch(train) [10][1000/1567] lr: 3.4199e-02 eta: 0:25:27 time: 0.1239 data_time: 0.0080 memory: 1461 loss: 0.0948 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0948 2022/12/20 15:48:58 - mmengine - INFO - Epoch(train) [10][1100/1567] lr: 3.3606e-02 eta: 0:25:12 time: 0.1271 data_time: 0.0076 memory: 1461 loss: 0.0678 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0678 2022/12/20 15:49:14 - mmengine - INFO - Epoch(train) [10][1200/1567] lr: 3.3015e-02 eta: 0:24:58 time: 0.1668 data_time: 0.0079 memory: 1461 loss: 0.0358 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0358 2022/12/20 15:49:30 - mmengine - INFO - Epoch(train) [10][1300/1567] lr: 3.2428e-02 eta: 0:24:42 time: 0.1364 data_time: 0.0084 memory: 1461 loss: 0.0382 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0382 2022/12/20 15:49:46 - mmengine - INFO - Epoch(train) [10][1400/1567] lr: 3.1842e-02 eta: 0:24:27 time: 0.1606 data_time: 0.0076 memory: 1461 loss: 0.0428 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0428 2022/12/20 15:50:02 - mmengine - INFO - Epoch(train) [10][1500/1567] lr: 3.1260e-02 eta: 0:24:12 time: 0.1580 data_time: 0.0074 memory: 1461 loss: 0.0690 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.0690 2022/12/20 15:50:12 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 15:50:12 - mmengine - INFO - Epoch(train) [10][1567/1567] lr: 3.0872e-02 eta: 0:24:02 time: 0.2083 data_time: 0.0073 memory: 1461 loss: 0.2664 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2664 2022/12/20 15:50:12 - mmengine - INFO - Saving checkpoint at 10 epochs 2022/12/20 15:50:15 - mmengine - INFO - Epoch(val) [10][100/129] eta: 0:00:00 time: 0.0448 data_time: 0.0065 memory: 215 2022/12/20 15:50:23 - mmengine - INFO - Epoch(val) [10][129/129] acc/top1: 0.8777 acc/top5: 0.9889 acc/mean1: 0.8776 2022/12/20 15:50:23 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_9.pth is removed 2022/12/20 15:50:24 - mmengine - INFO - The best checkpoint with 0.8777 acc/top1 at 10 epoch is saved to best_acc/top1_epoch_10.pth. 2022/12/20 15:50:40 - mmengine - INFO - Epoch(train) [11][ 100/1567] lr: 3.0294e-02 eta: 0:23:47 time: 0.1476 data_time: 0.0081 memory: 1461 loss: 0.0657 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0657 2022/12/20 15:50:56 - mmengine - INFO - Epoch(train) [11][ 200/1567] lr: 2.9720e-02 eta: 0:23:32 time: 0.1534 data_time: 0.0072 memory: 1461 loss: 0.0601 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0601 2022/12/20 15:51:11 - mmengine - INFO - Epoch(train) [11][ 300/1567] lr: 2.9149e-02 eta: 0:23:17 time: 0.1590 data_time: 0.0075 memory: 1461 loss: 0.0669 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0669 2022/12/20 15:51:16 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 15:51:27 - mmengine - INFO - Epoch(train) [11][ 400/1567] lr: 2.8581e-02 eta: 0:23:02 time: 0.1988 data_time: 0.0073 memory: 1461 loss: 0.0435 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0435 2022/12/20 15:51:43 - mmengine - INFO - Epoch(train) [11][ 500/1567] lr: 2.8017e-02 eta: 0:22:47 time: 0.1497 data_time: 0.0073 memory: 1461 loss: 0.0384 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0384 2022/12/20 15:51:57 - mmengine - INFO - Epoch(train) [11][ 600/1567] lr: 2.7456e-02 eta: 0:22:31 time: 0.1530 data_time: 0.0070 memory: 1461 loss: 0.0519 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0519 2022/12/20 15:52:12 - mmengine - INFO - Epoch(train) [11][ 700/1567] lr: 2.6898e-02 eta: 0:22:15 time: 0.1422 data_time: 0.0080 memory: 1461 loss: 0.0340 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0340 2022/12/20 15:52:26 - mmengine - INFO - Epoch(train) [11][ 800/1567] lr: 2.6345e-02 eta: 0:21:59 time: 0.1482 data_time: 0.0069 memory: 1461 loss: 0.0374 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0374 2022/12/20 15:52:40 - mmengine - INFO - Epoch(train) [11][ 900/1567] lr: 2.5794e-02 eta: 0:21:43 time: 0.1660 data_time: 0.0082 memory: 1461 loss: 0.0476 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0476 2022/12/20 15:52:58 - mmengine - INFO - Epoch(train) [11][1000/1567] lr: 2.5248e-02 eta: 0:21:29 time: 0.1528 data_time: 0.0077 memory: 1461 loss: 0.0271 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0271 2022/12/20 15:53:13 - mmengine - INFO - Epoch(train) [11][1100/1567] lr: 2.4706e-02 eta: 0:21:13 time: 0.2027 data_time: 0.0072 memory: 1461 loss: 0.0398 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0398 2022/12/20 15:53:30 - mmengine - INFO - Epoch(train) [11][1200/1567] lr: 2.4167e-02 eta: 0:20:59 time: 0.1783 data_time: 0.0069 memory: 1461 loss: 0.0408 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0408 2022/12/20 15:53:44 - mmengine - INFO - Epoch(train) [11][1300/1567] lr: 2.3633e-02 eta: 0:20:43 time: 0.1236 data_time: 0.0075 memory: 1461 loss: 0.0464 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0464 2022/12/20 15:53:50 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 15:54:02 - mmengine - INFO - Epoch(train) [11][1400/1567] lr: 2.3103e-02 eta: 0:20:29 time: 0.1602 data_time: 0.0073 memory: 1461 loss: 0.0277 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0277 2022/12/20 15:54:16 - mmengine - INFO - Epoch(train) [11][1500/1567] lr: 2.2577e-02 eta: 0:20:13 time: 0.1222 data_time: 0.0085 memory: 1461 loss: 0.0400 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0400 2022/12/20 15:54:28 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 15:54:28 - mmengine - INFO - Epoch(train) [11][1567/1567] lr: 2.2227e-02 eta: 0:20:03 time: 0.1509 data_time: 0.0070 memory: 1461 loss: 0.2001 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2001 2022/12/20 15:54:28 - mmengine - INFO - Saving checkpoint at 11 epochs 2022/12/20 15:54:34 - mmengine - INFO - Epoch(val) [11][100/129] eta: 0:00:01 time: 0.0839 data_time: 0.0069 memory: 215 2022/12/20 15:54:40 - mmengine - INFO - Epoch(val) [11][129/129] acc/top1: 0.8896 acc/top5: 0.9891 acc/mean1: 0.8895 2022/12/20 15:54:40 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_10.pth is removed 2022/12/20 15:54:40 - mmengine - INFO - The best checkpoint with 0.8896 acc/top1 at 11 epoch is saved to best_acc/top1_epoch_11.pth. 2022/12/20 15:54:56 - mmengine - INFO - Epoch(train) [12][ 100/1567] lr: 2.1708e-02 eta: 0:19:48 time: 0.1497 data_time: 0.0080 memory: 1461 loss: 0.0297 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0297 2022/12/20 15:55:13 - mmengine - INFO - Epoch(train) [12][ 200/1567] lr: 2.1194e-02 eta: 0:19:34 time: 0.1854 data_time: 0.0071 memory: 1461 loss: 0.0321 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0321 2022/12/20 15:55:29 - mmengine - INFO - Epoch(train) [12][ 300/1567] lr: 2.0684e-02 eta: 0:19:18 time: 0.1226 data_time: 0.0075 memory: 1461 loss: 0.0163 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0163 2022/12/20 15:55:46 - mmengine - INFO - Epoch(train) [12][ 400/1567] lr: 2.0179e-02 eta: 0:19:04 time: 0.1686 data_time: 0.0069 memory: 1461 loss: 0.0221 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0221 2022/12/20 15:56:02 - mmengine - INFO - Epoch(train) [12][ 500/1567] lr: 1.9678e-02 eta: 0:18:48 time: 0.1509 data_time: 0.0082 memory: 1461 loss: 0.0263 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0263 2022/12/20 15:56:17 - mmengine - INFO - Epoch(train) [12][ 600/1567] lr: 1.9182e-02 eta: 0:18:33 time: 0.1591 data_time: 0.0072 memory: 1461 loss: 0.0178 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0178 2022/12/20 15:56:32 - mmengine - INFO - Epoch(train) [12][ 700/1567] lr: 1.8691e-02 eta: 0:18:17 time: 0.1509 data_time: 0.0071 memory: 1461 loss: 0.0362 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0362 2022/12/20 15:56:40 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 15:56:45 - mmengine - INFO - Epoch(train) [12][ 800/1567] lr: 1.8205e-02 eta: 0:18:01 time: 0.1535 data_time: 0.0076 memory: 1461 loss: 0.0206 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0206 2022/12/20 15:57:01 - mmengine - INFO - Epoch(train) [12][ 900/1567] lr: 1.7724e-02 eta: 0:17:46 time: 0.1767 data_time: 0.0076 memory: 1461 loss: 0.0178 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0178 2022/12/20 15:57:18 - mmengine - INFO - Epoch(train) [12][1000/1567] lr: 1.7248e-02 eta: 0:17:31 time: 0.1773 data_time: 0.0073 memory: 1461 loss: 0.0289 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0289 2022/12/20 15:57:32 - mmengine - INFO - Epoch(train) [12][1100/1567] lr: 1.6778e-02 eta: 0:17:15 time: 0.1510 data_time: 0.0073 memory: 1461 loss: 0.0315 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0315 2022/12/20 15:57:50 - mmengine - INFO - Epoch(train) [12][1200/1567] lr: 1.6312e-02 eta: 0:17:01 time: 0.1607 data_time: 0.0077 memory: 1461 loss: 0.0345 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0345 2022/12/20 15:58:04 - mmengine - INFO - Epoch(train) [12][1300/1567] lr: 1.5852e-02 eta: 0:16:45 time: 0.1802 data_time: 0.0071 memory: 1461 loss: 0.0145 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0145 2022/12/20 15:58:21 - mmengine - INFO - Epoch(train) [12][1400/1567] lr: 1.5397e-02 eta: 0:16:30 time: 0.1821 data_time: 0.0078 memory: 1461 loss: 0.0151 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0151 2022/12/20 15:58:36 - mmengine - INFO - Epoch(train) [12][1500/1567] lr: 1.4947e-02 eta: 0:16:14 time: 0.1338 data_time: 0.0073 memory: 1461 loss: 0.0174 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0174 2022/12/20 15:58:46 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 15:58:46 - mmengine - INFO - Epoch(train) [12][1567/1567] lr: 1.4649e-02 eta: 0:16:04 time: 0.1502 data_time: 0.0078 memory: 1461 loss: 0.1969 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1969 2022/12/20 15:58:46 - mmengine - INFO - Saving checkpoint at 12 epochs 2022/12/20 15:58:52 - mmengine - INFO - Epoch(val) [12][100/129] eta: 0:00:01 time: 0.0709 data_time: 0.0069 memory: 215 2022/12/20 15:58:57 - mmengine - INFO - Epoch(val) [12][129/129] acc/top1: 0.9006 acc/top5: 0.9903 acc/mean1: 0.9005 2022/12/20 15:58:57 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_11.pth is removed 2022/12/20 15:58:58 - mmengine - INFO - The best checkpoint with 0.9006 acc/top1 at 12 epoch is saved to best_acc/top1_epoch_12.pth. 2022/12/20 15:59:14 - mmengine - INFO - Epoch(train) [13][ 100/1567] lr: 1.4209e-02 eta: 0:15:49 time: 0.2031 data_time: 0.0073 memory: 1461 loss: 0.0156 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0156 2022/12/20 15:59:29 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 15:59:30 - mmengine - INFO - Epoch(train) [13][ 200/1567] lr: 1.3774e-02 eta: 0:15:34 time: 0.1614 data_time: 0.0074 memory: 1461 loss: 0.0254 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0254 2022/12/20 15:59:45 - mmengine - INFO - Epoch(train) [13][ 300/1567] lr: 1.3345e-02 eta: 0:15:18 time: 0.1493 data_time: 0.0070 memory: 1461 loss: 0.0097 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0097 2022/12/20 16:00:02 - mmengine - INFO - Epoch(train) [13][ 400/1567] lr: 1.2922e-02 eta: 0:15:03 time: 0.1814 data_time: 0.0070 memory: 1461 loss: 0.0094 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0094 2022/12/20 16:00:15 - mmengine - INFO - Epoch(train) [13][ 500/1567] lr: 1.2505e-02 eta: 0:14:47 time: 0.1481 data_time: 0.0070 memory: 1461 loss: 0.0096 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0096 2022/12/20 16:00:31 - mmengine - INFO - Epoch(train) [13][ 600/1567] lr: 1.2093e-02 eta: 0:14:32 time: 0.1599 data_time: 0.0074 memory: 1461 loss: 0.0104 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0104 2022/12/20 16:00:45 - mmengine - INFO - Epoch(train) [13][ 700/1567] lr: 1.1687e-02 eta: 0:14:16 time: 0.1288 data_time: 0.0068 memory: 1461 loss: 0.0082 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0082 2022/12/20 16:00:59 - mmengine - INFO - Epoch(train) [13][ 800/1567] lr: 1.1288e-02 eta: 0:14:01 time: 0.2203 data_time: 0.0082 memory: 1461 loss: 0.0056 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0056 2022/12/20 16:01:16 - mmengine - INFO - Epoch(train) [13][ 900/1567] lr: 1.0894e-02 eta: 0:13:46 time: 0.1656 data_time: 0.0082 memory: 1461 loss: 0.0090 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0090 2022/12/20 16:01:30 - mmengine - INFO - Epoch(train) [13][1000/1567] lr: 1.0507e-02 eta: 0:13:30 time: 0.1318 data_time: 0.0072 memory: 1461 loss: 0.0137 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0137 2022/12/20 16:01:47 - mmengine - INFO - Epoch(train) [13][1100/1567] lr: 1.0126e-02 eta: 0:13:15 time: 0.1492 data_time: 0.0084 memory: 1461 loss: 0.0081 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0081 2022/12/20 16:02:02 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 16:02:03 - mmengine - INFO - Epoch(train) [13][1200/1567] lr: 9.7512e-03 eta: 0:13:00 time: 0.1566 data_time: 0.0079 memory: 1461 loss: 0.0135 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0135 2022/12/20 16:02:19 - mmengine - INFO - Epoch(train) [13][1300/1567] lr: 9.3826e-03 eta: 0:12:44 time: 0.1687 data_time: 0.0076 memory: 1461 loss: 0.0085 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0085 2022/12/20 16:02:35 - mmengine - INFO - Epoch(train) [13][1400/1567] lr: 9.0204e-03 eta: 0:12:29 time: 0.1607 data_time: 0.0077 memory: 1461 loss: 0.0098 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0098 2022/12/20 16:02:52 - mmengine - INFO - Epoch(train) [13][1500/1567] lr: 8.6647e-03 eta: 0:12:14 time: 0.1615 data_time: 0.0080 memory: 1461 loss: 0.0069 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0069 2022/12/20 16:03:03 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 16:03:03 - mmengine - INFO - Epoch(train) [13][1567/1567] lr: 8.4300e-03 eta: 0:12:04 time: 0.1549 data_time: 0.0071 memory: 1461 loss: 0.1936 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.1936 2022/12/20 16:03:03 - mmengine - INFO - Saving checkpoint at 13 epochs 2022/12/20 16:03:08 - mmengine - INFO - Epoch(val) [13][100/129] eta: 0:00:01 time: 0.0679 data_time: 0.0068 memory: 215 2022/12/20 16:03:11 - mmengine - INFO - Epoch(val) [13][129/129] acc/top1: 0.9103 acc/top5: 0.9910 acc/mean1: 0.9102 2022/12/20 16:03:11 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_12.pth is removed 2022/12/20 16:03:11 - mmengine - INFO - The best checkpoint with 0.9103 acc/top1 at 13 epoch is saved to best_acc/top1_epoch_13.pth. 2022/12/20 16:03:28 - mmengine - INFO - Epoch(train) [14][ 100/1567] lr: 8.0851e-03 eta: 0:11:49 time: 0.1459 data_time: 0.0086 memory: 1461 loss: 0.0080 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0080 2022/12/20 16:03:44 - mmengine - INFO - Epoch(train) [14][ 200/1567] lr: 7.7469e-03 eta: 0:11:34 time: 0.1588 data_time: 0.0077 memory: 1461 loss: 0.0081 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0081 2022/12/20 16:04:01 - mmengine - INFO - Epoch(train) [14][ 300/1567] lr: 7.4152e-03 eta: 0:11:18 time: 0.1782 data_time: 0.0072 memory: 1461 loss: 0.0063 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0063 2022/12/20 16:04:16 - mmengine - INFO - Epoch(train) [14][ 400/1567] lr: 7.0902e-03 eta: 0:11:03 time: 0.1550 data_time: 0.0069 memory: 1461 loss: 0.0084 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0084 2022/12/20 16:04:32 - mmengine - INFO - Epoch(train) [14][ 500/1567] lr: 6.7720e-03 eta: 0:10:48 time: 0.1802 data_time: 0.0068 memory: 1461 loss: 0.0080 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0080 2022/12/20 16:04:45 - mmengine - INFO - Epoch(train) [14][ 600/1567] lr: 6.4606e-03 eta: 0:10:32 time: 0.1514 data_time: 0.0075 memory: 1461 loss: 0.0060 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0060 2022/12/20 16:04:49 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 16:04:58 - mmengine - INFO - Epoch(train) [14][ 700/1567] lr: 6.1560e-03 eta: 0:10:16 time: 0.1008 data_time: 0.0097 memory: 1461 loss: 0.0075 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0075 2022/12/20 16:05:14 - mmengine - INFO - Epoch(train) [14][ 800/1567] lr: 5.8582e-03 eta: 0:10:01 time: 0.1531 data_time: 0.0077 memory: 1461 loss: 0.0127 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0127 2022/12/20 16:05:29 - mmengine - INFO - Epoch(train) [14][ 900/1567] lr: 5.5675e-03 eta: 0:09:45 time: 0.1518 data_time: 0.0082 memory: 1461 loss: 0.0173 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0173 2022/12/20 16:05:45 - mmengine - INFO - Epoch(train) [14][1000/1567] lr: 5.2836e-03 eta: 0:09:30 time: 0.2102 data_time: 0.0071 memory: 1461 loss: 0.0048 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0048 2022/12/20 16:06:01 - mmengine - INFO - Epoch(train) [14][1100/1567] lr: 5.0068e-03 eta: 0:09:15 time: 0.1541 data_time: 0.0074 memory: 1461 loss: 0.0061 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0061 2022/12/20 16:06:17 - mmengine - INFO - Epoch(train) [14][1200/1567] lr: 4.7371e-03 eta: 0:08:59 time: 0.1579 data_time: 0.0072 memory: 1461 loss: 0.0054 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0054 2022/12/20 16:06:34 - mmengine - INFO - Epoch(train) [14][1300/1567] lr: 4.4745e-03 eta: 0:08:44 time: 0.1652 data_time: 0.0082 memory: 1461 loss: 0.0063 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0063 2022/12/20 16:06:49 - mmengine - INFO - Epoch(train) [14][1400/1567] lr: 4.2190e-03 eta: 0:08:28 time: 0.1733 data_time: 0.0073 memory: 1461 loss: 0.0103 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0103 2022/12/20 16:07:06 - mmengine - INFO - Epoch(train) [14][1500/1567] lr: 3.9707e-03 eta: 0:08:13 time: 0.1504 data_time: 0.0074 memory: 1461 loss: 0.0076 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0076 2022/12/20 16:07:16 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 16:07:16 - mmengine - INFO - Epoch(train) [14][1567/1567] lr: 3.8084e-03 eta: 0:08:03 time: 0.1530 data_time: 0.0073 memory: 1461 loss: 0.1654 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1654 2022/12/20 16:07:16 - mmengine - INFO - Saving checkpoint at 14 epochs 2022/12/20 16:07:22 - mmengine - INFO - Epoch(val) [14][100/129] eta: 0:00:01 time: 0.1177 data_time: 0.0066 memory: 215 2022/12/20 16:07:25 - mmengine - INFO - Epoch(val) [14][129/129] acc/top1: 0.9130 acc/top5: 0.9922 acc/mean1: 0.9129 2022/12/20 16:07:25 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_13.pth is removed 2022/12/20 16:07:25 - mmengine - INFO - The best checkpoint with 0.9130 acc/top1 at 14 epoch is saved to best_acc/top1_epoch_14.pth. 2022/12/20 16:07:36 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 16:07:42 - mmengine - INFO - Epoch(train) [15][ 100/1567] lr: 3.5722e-03 eta: 0:07:48 time: 0.1625 data_time: 0.0075 memory: 1461 loss: 0.0053 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0053 2022/12/20 16:07:58 - mmengine - INFO - Epoch(train) [15][ 200/1567] lr: 3.3433e-03 eta: 0:07:32 time: 0.1839 data_time: 0.0074 memory: 1461 loss: 0.0060 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0060 2022/12/20 16:08:15 - mmengine - INFO - Epoch(train) [15][ 300/1567] lr: 3.1217e-03 eta: 0:07:17 time: 0.1409 data_time: 0.0075 memory: 1461 loss: 0.0060 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0060 2022/12/20 16:08:29 - mmengine - INFO - Epoch(train) [15][ 400/1567] lr: 2.9075e-03 eta: 0:07:01 time: 0.1183 data_time: 0.0070 memory: 1461 loss: 0.0086 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0086 2022/12/20 16:08:45 - mmengine - INFO - Epoch(train) [15][ 500/1567] lr: 2.7007e-03 eta: 0:06:46 time: 0.1376 data_time: 0.0072 memory: 1461 loss: 0.0069 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0069 2022/12/20 16:08:59 - mmengine - INFO - Epoch(train) [15][ 600/1567] lr: 2.5013e-03 eta: 0:06:30 time: 0.1216 data_time: 0.0076 memory: 1461 loss: 0.0059 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0059 2022/12/20 16:09:11 - mmengine - INFO - Epoch(train) [15][ 700/1567] lr: 2.3093e-03 eta: 0:06:15 time: 0.0910 data_time: 0.0075 memory: 1461 loss: 0.0057 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0057 2022/12/20 16:09:28 - mmengine - INFO - Epoch(train) [15][ 800/1567] lr: 2.1249e-03 eta: 0:05:59 time: 0.1564 data_time: 0.0075 memory: 1461 loss: 0.0077 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0077 2022/12/20 16:09:43 - mmengine - INFO - Epoch(train) [15][ 900/1567] lr: 1.9479e-03 eta: 0:05:44 time: 0.1287 data_time: 0.0077 memory: 1461 loss: 0.0068 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0068 2022/12/20 16:10:00 - mmengine - INFO - Epoch(train) [15][1000/1567] lr: 1.7785e-03 eta: 0:05:29 time: 0.1694 data_time: 0.0083 memory: 1461 loss: 0.0123 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0123 2022/12/20 16:10:10 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 16:10:15 - mmengine - INFO - Epoch(train) [15][1100/1567] lr: 1.6167e-03 eta: 0:05:13 time: 0.1410 data_time: 0.0076 memory: 1461 loss: 0.0070 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0070 2022/12/20 16:10:31 - mmengine - INFO - Epoch(train) [15][1200/1567] lr: 1.4625e-03 eta: 0:04:58 time: 0.2068 data_time: 0.0070 memory: 1461 loss: 0.0052 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0052 2022/12/20 16:10:47 - mmengine - INFO - Epoch(train) [15][1300/1567] lr: 1.3159e-03 eta: 0:04:43 time: 0.1589 data_time: 0.0079 memory: 1461 loss: 0.0052 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0052 2022/12/20 16:11:02 - mmengine - INFO - Epoch(train) [15][1400/1567] lr: 1.1769e-03 eta: 0:04:27 time: 0.1553 data_time: 0.0074 memory: 1461 loss: 0.0047 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0047 2022/12/20 16:11:19 - mmengine - INFO - Epoch(train) [15][1500/1567] lr: 1.0456e-03 eta: 0:04:12 time: 0.1615 data_time: 0.0072 memory: 1461 loss: 0.0056 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0056 2022/12/20 16:11:29 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 16:11:29 - mmengine - INFO - Epoch(train) [15][1567/1567] lr: 9.6196e-04 eta: 0:04:01 time: 0.1370 data_time: 0.0078 memory: 1461 loss: 0.1840 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.1840 2022/12/20 16:11:29 - mmengine - INFO - Saving checkpoint at 15 epochs 2022/12/20 16:11:35 - mmengine - INFO - Epoch(val) [15][100/129] eta: 0:00:01 time: 0.0298 data_time: 0.0065 memory: 215 2022/12/20 16:11:38 - mmengine - INFO - Epoch(val) [15][129/129] acc/top1: 0.9133 acc/top5: 0.9922 acc/mean1: 0.9132 2022/12/20 16:11:38 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_14.pth is removed 2022/12/20 16:11:38 - mmengine - INFO - The best checkpoint with 0.9133 acc/top1 at 15 epoch is saved to best_acc/top1_epoch_15.pth. 2022/12/20 16:11:55 - mmengine - INFO - Epoch(train) [16][ 100/1567] lr: 8.4351e-04 eta: 0:03:46 time: 0.1595 data_time: 0.0074 memory: 1461 loss: 0.0071 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0071 2022/12/20 16:12:09 - mmengine - INFO - Epoch(train) [16][ 200/1567] lr: 7.3277e-04 eta: 0:03:30 time: 0.1860 data_time: 0.0073 memory: 1461 loss: 0.0078 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0078 2022/12/20 16:12:26 - mmengine - INFO - Epoch(train) [16][ 300/1567] lr: 6.2978e-04 eta: 0:03:15 time: 0.1865 data_time: 0.0067 memory: 1461 loss: 0.0060 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0060 2022/12/20 16:12:41 - mmengine - INFO - Epoch(train) [16][ 400/1567] lr: 5.3453e-04 eta: 0:03:00 time: 0.1452 data_time: 0.0070 memory: 1461 loss: 0.0062 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0062 2022/12/20 16:12:57 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 16:12:57 - mmengine - INFO - Epoch(train) [16][ 500/1567] lr: 4.4705e-04 eta: 0:02:44 time: 0.1754 data_time: 0.0072 memory: 1461 loss: 0.0064 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0064 2022/12/20 16:13:11 - mmengine - INFO - Epoch(train) [16][ 600/1567] lr: 3.6735e-04 eta: 0:02:29 time: 0.1450 data_time: 0.0074 memory: 1461 loss: 0.0057 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0057 2022/12/20 16:13:24 - mmengine - INFO - Epoch(train) [16][ 700/1567] lr: 2.9544e-04 eta: 0:02:13 time: 0.1372 data_time: 0.0101 memory: 1461 loss: 0.0067 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0067 2022/12/20 16:13:42 - mmengine - INFO - Epoch(train) [16][ 800/1567] lr: 2.3134e-04 eta: 0:01:58 time: 0.1920 data_time: 0.0073 memory: 1461 loss: 0.0061 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0061 2022/12/20 16:13:57 - mmengine - INFO - Epoch(train) [16][ 900/1567] lr: 1.7505e-04 eta: 0:01:42 time: 0.1570 data_time: 0.0090 memory: 1461 loss: 0.0064 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0064 2022/12/20 16:14:14 - mmengine - INFO - Epoch(train) [16][1000/1567] lr: 1.2658e-04 eta: 0:01:27 time: 0.1717 data_time: 0.0071 memory: 1461 loss: 0.0061 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0061 2022/12/20 16:14:29 - mmengine - INFO - Epoch(train) [16][1100/1567] lr: 8.5947e-05 eta: 0:01:12 time: 0.1522 data_time: 0.0078 memory: 1461 loss: 0.0074 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0074 2022/12/20 16:14:46 - mmengine - INFO - Epoch(train) [16][1200/1567] lr: 5.3147e-05 eta: 0:00:56 time: 0.1594 data_time: 0.0073 memory: 1461 loss: 0.0065 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0065 2022/12/20 16:15:02 - mmengine - INFO - Epoch(train) [16][1300/1567] lr: 2.8190e-05 eta: 0:00:41 time: 0.1463 data_time: 0.0083 memory: 1461 loss: 0.0072 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0072 2022/12/20 16:15:18 - mmengine - INFO - Epoch(train) [16][1400/1567] lr: 1.1078e-05 eta: 0:00:25 time: 0.2134 data_time: 0.0076 memory: 1461 loss: 0.0054 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0054 2022/12/20 16:15:34 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 16:15:34 - mmengine - INFO - Epoch(train) [16][1500/1567] lr: 1.8150e-06 eta: 0:00:10 time: 0.1658 data_time: 0.0075 memory: 1461 loss: 0.0071 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0071 2022/12/20 16:15:44 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221220_150747 2022/12/20 16:15:44 - mmengine - INFO - Epoch(train) [16][1567/1567] lr: 3.9252e-10 eta: 0:00:00 time: 0.1312 data_time: 0.0071 memory: 1461 loss: 0.2334 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2334 2022/12/20 16:15:44 - mmengine - INFO - Saving checkpoint at 16 epochs 2022/12/20 16:15:48 - mmengine - INFO - Epoch(val) [16][100/129] eta: 0:00:01 time: 0.0396 data_time: 0.0067 memory: 215 2022/12/20 16:15:55 - mmengine - INFO - Epoch(val) [16][129/129] acc/top1: 0.9121 acc/top5: 0.9926 acc/mean1: 0.9120