2022/12/20 17:26:46 - 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: 826524205 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 17:26:46 - 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=['bm']), 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=['bm']), dict( type='UniformSampleFrames', clip_len=100, num_clips=1, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ] test_pipeline = [ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['bm']), dict( type='UniformSampleFrames', clip_len=100, num_clips=10, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ] train_dataloader = dict( batch_size=16, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=True), dataset=dict( type='RepeatDataset', times=5, dataset=dict( type='PoseDataset', ann_file='data/skeleton/ntu60_2d.pkl', pipeline=[ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['bm']), dict(type='UniformSampleFrames', clip_len=100), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ], split='xsub_train'))) val_dataloader = dict( batch_size=16, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='PoseDataset', ann_file='data/skeleton/ntu60_2d.pkl', pipeline=[ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['bm']), dict( type='UniformSampleFrames', clip_len=100, num_clips=1, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ], split='xsub_val', test_mode=True)) test_dataloader = dict( batch_size=1, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='PoseDataset', ann_file='data/skeleton/ntu60_2d.pkl', pipeline=[ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['bm']), dict( type='UniformSampleFrames', clip_len=100, num_clips=10, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ], split='xsub_val', test_mode=True)) val_evaluator = [dict(type='AccMetric')] test_evaluator = [dict(type='AccMetric')] train_cfg = dict( type='EpochBasedTrainLoop', max_epochs=16, val_begin=1, val_interval=1) val_cfg = dict(type='ValLoop') test_cfg = dict(type='TestLoop') param_scheduler = [ dict( type='CosineAnnealingLR', eta_min=0, T_max=16, by_epoch=True, convert_to_iter_based=True) ] optim_wrapper = dict( optimizer=dict( type='SGD', lr=0.1, momentum=0.9, weight_decay=0.0005, nesterov=True)) auto_scale_lr = dict(enable=False, base_batch_size=128) launcher = 'pytorch' work_dir = './work_dirs/2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d' randomness = dict(seed=None, diff_rank_seed=False, deterministic=False) 2022/12/20 17:26:46 - mmengine - INFO - Result has been saved to /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d/modules_statistic_results.json 2022/12/20 17:26:47 - 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 17:27:28 - mmengine - INFO - Checkpoints will be saved to /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d. 2022/12/20 17:27:45 - mmengine - INFO - Epoch(train) [1][ 100/1567] lr: 9.9996e-02 eta: 1:09:21 time: 0.1377 data_time: 0.0076 memory: 1461 loss: 2.9875 top1_acc: 0.1250 top5_acc: 0.4375 loss_cls: 2.9875 2022/12/20 17:28:01 - mmengine - INFO - Epoch(train) [1][ 200/1567] lr: 9.9984e-02 eta: 1:07:04 time: 0.1451 data_time: 0.0077 memory: 1461 loss: 2.4617 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.4617 2022/12/20 17:28:14 - mmengine - INFO - Epoch(train) [1][ 300/1567] lr: 9.9965e-02 eta: 1:03:25 time: 0.1179 data_time: 0.0077 memory: 1461 loss: 1.8558 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.8558 2022/12/20 17:28:27 - mmengine - INFO - Epoch(train) [1][ 400/1567] lr: 9.9938e-02 eta: 0:59:54 time: 0.0936 data_time: 0.0077 memory: 1461 loss: 1.5393 top1_acc: 0.4375 top5_acc: 1.0000 loss_cls: 1.5393 2022/12/20 17:28:44 - mmengine - INFO - Epoch(train) [1][ 500/1567] lr: 9.9902e-02 eta: 1:01:56 time: 0.1653 data_time: 0.0076 memory: 1461 loss: 1.3439 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.3439 2022/12/20 17:28:59 - mmengine - INFO - Epoch(train) [1][ 600/1567] lr: 9.9859e-02 eta: 1:01:22 time: 0.1295 data_time: 0.0079 memory: 1461 loss: 1.1361 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.1361 2022/12/20 17:29:16 - mmengine - INFO - Epoch(train) [1][ 700/1567] lr: 9.9808e-02 eta: 1:02:18 time: 0.1773 data_time: 0.0078 memory: 1461 loss: 0.9795 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.9795 2022/12/20 17:29:31 - mmengine - INFO - Epoch(train) [1][ 800/1567] lr: 9.9750e-02 eta: 1:02:11 time: 0.1404 data_time: 0.0076 memory: 1461 loss: 0.8909 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 0.8909 2022/12/20 17:29:48 - mmengine - INFO - Epoch(train) [1][ 900/1567] lr: 9.9683e-02 eta: 1:02:27 time: 0.1916 data_time: 0.0070 memory: 1461 loss: 0.7727 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.7727 2022/12/20 17:30:03 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 17:30:03 - mmengine - INFO - Epoch(train) [1][1000/1567] lr: 9.9609e-02 eta: 1:02:02 time: 0.1542 data_time: 0.0072 memory: 1461 loss: 0.6907 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6907 2022/12/20 17:30:19 - mmengine - INFO - Epoch(train) [1][1100/1567] lr: 9.9527e-02 eta: 1:02:11 time: 0.1704 data_time: 0.0076 memory: 1461 loss: 0.6289 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.6289 2022/12/20 17:30:35 - mmengine - INFO - Epoch(train) [1][1200/1567] lr: 9.9437e-02 eta: 1:01:45 time: 0.1557 data_time: 0.0074 memory: 1461 loss: 0.6219 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.6219 2022/12/20 17:30:51 - mmengine - INFO - Epoch(train) [1][1300/1567] lr: 9.9339e-02 eta: 1:01:48 time: 0.1634 data_time: 0.0078 memory: 1461 loss: 0.6034 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.6034 2022/12/20 17:31:06 - mmengine - INFO - Epoch(train) [1][1400/1567] lr: 9.9234e-02 eta: 1:01:27 time: 0.1629 data_time: 0.0082 memory: 1461 loss: 0.5396 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5396 2022/12/20 17:31:22 - mmengine - INFO - Epoch(train) [1][1500/1567] lr: 9.9121e-02 eta: 1:01:20 time: 0.1656 data_time: 0.0074 memory: 1461 loss: 0.5747 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5747 2022/12/20 17:31:33 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 17:31:33 - mmengine - INFO - Epoch(train) [1][1567/1567] lr: 9.9040e-02 eta: 1:01:14 time: 0.1466 data_time: 0.0070 memory: 1461 loss: 0.6833 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.6833 2022/12/20 17:31:33 - mmengine - INFO - Saving checkpoint at 1 epochs 2022/12/20 17:31:39 - mmengine - INFO - Epoch(val) [1][100/129] eta: 0:00:01 time: 0.0436 data_time: 0.0068 memory: 215 2022/12/20 17:31:41 - mmengine - INFO - Epoch(val) [1][129/129] acc/top1: 0.6021 acc/top5: 0.9298 acc/mean1: 0.6020 2022/12/20 17:31:41 - mmengine - INFO - The best checkpoint with 0.6021 acc/top1 at 1 epoch is saved to best_acc/top1_epoch_1.pth. 2022/12/20 17:31:58 - mmengine - INFO - Epoch(train) [2][ 100/1567] lr: 9.8914e-02 eta: 1:01:09 time: 0.1272 data_time: 0.0076 memory: 1461 loss: 0.5966 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5966 2022/12/20 17:32:12 - mmengine - INFO - Epoch(train) [2][ 200/1567] lr: 9.8781e-02 eta: 1:00:28 time: 0.1432 data_time: 0.0080 memory: 1461 loss: 0.4470 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4470 2022/12/20 17:32:23 - mmengine - INFO - Epoch(train) [2][ 300/1567] lr: 9.8639e-02 eta: 0:59:21 time: 0.1133 data_time: 0.0087 memory: 1461 loss: 0.5484 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.5484 2022/12/20 17:32:41 - mmengine - INFO - Epoch(train) [2][ 400/1567] lr: 9.8491e-02 eta: 0:59:32 time: 0.1669 data_time: 0.0075 memory: 1461 loss: 0.4508 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.4508 2022/12/20 17:32:46 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 17:32:55 - mmengine - INFO - Epoch(train) [2][ 500/1567] lr: 9.8334e-02 eta: 0:59:00 time: 0.1004 data_time: 0.0071 memory: 1461 loss: 0.4293 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4293 2022/12/20 17:33:11 - mmengine - INFO - Epoch(train) [2][ 600/1567] lr: 9.8170e-02 eta: 0:58:59 time: 0.1645 data_time: 0.0077 memory: 1461 loss: 0.4953 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4953 2022/12/20 17:33:26 - mmengine - INFO - Epoch(train) [2][ 700/1567] lr: 9.7998e-02 eta: 0:58:37 time: 0.1389 data_time: 0.0071 memory: 1461 loss: 0.4935 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4935 2022/12/20 17:33:43 - mmengine - INFO - Epoch(train) [2][ 800/1567] lr: 9.7819e-02 eta: 0:58:37 time: 0.1877 data_time: 0.0073 memory: 1461 loss: 0.4385 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.4385 2022/12/20 17:33:58 - mmengine - INFO - Epoch(train) [2][ 900/1567] lr: 9.7632e-02 eta: 0:58:16 time: 0.1529 data_time: 0.0079 memory: 1461 loss: 0.4933 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4933 2022/12/20 17:34:15 - mmengine - INFO - Epoch(train) [2][1000/1567] lr: 9.7438e-02 eta: 0:58:11 time: 0.1955 data_time: 0.0073 memory: 1461 loss: 0.3812 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3812 2022/12/20 17:34:31 - mmengine - INFO - Epoch(train) [2][1100/1567] lr: 9.7236e-02 eta: 0:57:59 time: 0.1300 data_time: 0.0081 memory: 1461 loss: 0.5653 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5653 2022/12/20 17:34:46 - mmengine - INFO - Epoch(train) [2][1200/1567] lr: 9.7027e-02 eta: 0:57:39 time: 0.1532 data_time: 0.0070 memory: 1461 loss: 0.4159 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4159 2022/12/20 17:35:02 - mmengine - INFO - Epoch(train) [2][1300/1567] lr: 9.6810e-02 eta: 0:57:31 time: 0.1807 data_time: 0.0075 memory: 1461 loss: 0.5310 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.5310 2022/12/20 17:35:17 - mmengine - INFO - Epoch(train) [2][1400/1567] lr: 9.6587e-02 eta: 0:57:10 time: 0.1554 data_time: 0.0076 memory: 1461 loss: 0.4233 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4233 2022/12/20 17:35:23 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 17:35:32 - mmengine - INFO - Epoch(train) [2][1500/1567] lr: 9.6355e-02 eta: 0:56:54 time: 0.1375 data_time: 0.0072 memory: 1461 loss: 0.4464 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4464 2022/12/20 17:35:42 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 17:35:42 - mmengine - INFO - Epoch(train) [2][1567/1567] lr: 9.6196e-02 eta: 0:56:38 time: 0.1279 data_time: 0.0068 memory: 1461 loss: 0.5070 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.5070 2022/12/20 17:35:42 - mmengine - INFO - Saving checkpoint at 2 epochs 2022/12/20 17:35:48 - mmengine - INFO - Epoch(val) [2][100/129] eta: 0:00:01 time: 0.0465 data_time: 0.0061 memory: 215 2022/12/20 17:35:51 - mmengine - INFO - Epoch(val) [2][129/129] acc/top1: 0.7248 acc/top5: 0.9567 acc/mean1: 0.7247 2022/12/20 17:35:51 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_1.pth is removed 2022/12/20 17:35:51 - mmengine - INFO - The best checkpoint with 0.7248 acc/top1 at 2 epoch is saved to best_acc/top1_epoch_2.pth. 2022/12/20 17:36:07 - mmengine - INFO - Epoch(train) [3][ 100/1567] lr: 9.5953e-02 eta: 0:56:21 time: 0.1170 data_time: 0.0077 memory: 1461 loss: 0.4072 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4072 2022/12/20 17:36:20 - mmengine - INFO - Epoch(train) [3][ 200/1567] lr: 9.5703e-02 eta: 0:55:52 time: 0.1014 data_time: 0.0096 memory: 1461 loss: 0.4748 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.4748 2022/12/20 17:36:38 - mmengine - INFO - Epoch(train) [3][ 300/1567] lr: 9.5445e-02 eta: 0:55:52 time: 0.1858 data_time: 0.0070 memory: 1461 loss: 0.3221 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3221 2022/12/20 17:36:54 - mmengine - INFO - Epoch(train) [3][ 400/1567] lr: 9.5180e-02 eta: 0:55:37 time: 0.1547 data_time: 0.0077 memory: 1461 loss: 0.4082 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4082 2022/12/20 17:37:10 - mmengine - INFO - Epoch(train) [3][ 500/1567] lr: 9.4908e-02 eta: 0:55:26 time: 0.1518 data_time: 0.0078 memory: 1461 loss: 0.4266 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4266 2022/12/20 17:37:27 - mmengine - INFO - Epoch(train) [3][ 600/1567] lr: 9.4629e-02 eta: 0:55:18 time: 0.1707 data_time: 0.0087 memory: 1461 loss: 0.3181 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3181 2022/12/20 17:37:42 - mmengine - INFO - Epoch(train) [3][ 700/1567] lr: 9.4343e-02 eta: 0:55:02 time: 0.1657 data_time: 0.0081 memory: 1461 loss: 0.3550 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3550 2022/12/20 17:37:58 - mmengine - INFO - Epoch(train) [3][ 800/1567] lr: 9.4050e-02 eta: 0:54:50 time: 0.1511 data_time: 0.0072 memory: 1461 loss: 0.3454 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3454 2022/12/20 17:38:08 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 17:38:14 - mmengine - INFO - Epoch(train) [3][ 900/1567] lr: 9.3750e-02 eta: 0:54:36 time: 0.1999 data_time: 0.0070 memory: 1461 loss: 0.2907 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2907 2022/12/20 17:38:31 - mmengine - INFO - Epoch(train) [3][1000/1567] lr: 9.3444e-02 eta: 0:54:27 time: 0.1635 data_time: 0.0074 memory: 1461 loss: 0.3753 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3753 2022/12/20 17:38:46 - mmengine - INFO - Epoch(train) [3][1100/1567] lr: 9.3130e-02 eta: 0:54:08 time: 0.1224 data_time: 0.0073 memory: 1461 loss: 0.3260 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.3260 2022/12/20 17:39:03 - mmengine - INFO - Epoch(train) [3][1200/1567] lr: 9.2810e-02 eta: 0:53:59 time: 0.1408 data_time: 0.0077 memory: 1461 loss: 0.3626 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3626 2022/12/20 17:39:18 - mmengine - INFO - Epoch(train) [3][1300/1567] lr: 9.2483e-02 eta: 0:53:43 time: 0.1451 data_time: 0.0083 memory: 1461 loss: 0.4027 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4027 2022/12/20 17:39:36 - mmengine - INFO - Epoch(train) [3][1400/1567] lr: 9.2149e-02 eta: 0:53:34 time: 0.1941 data_time: 0.0070 memory: 1461 loss: 0.2720 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2720 2022/12/20 17:39:51 - mmengine - INFO - Epoch(train) [3][1500/1567] lr: 9.1809e-02 eta: 0:53:18 time: 0.1353 data_time: 0.0070 memory: 1461 loss: 0.3285 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3285 2022/12/20 17:40:01 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 17:40:01 - mmengine - INFO - Epoch(train) [3][1567/1567] lr: 9.1577e-02 eta: 0:53:03 time: 0.1711 data_time: 0.0067 memory: 1461 loss: 0.5610 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.5610 2022/12/20 17:40:01 - mmengine - INFO - Saving checkpoint at 3 epochs 2022/12/20 17:40:06 - mmengine - INFO - Epoch(val) [3][100/129] eta: 0:00:01 time: 0.0961 data_time: 0.0062 memory: 215 2022/12/20 17:40:12 - mmengine - INFO - Epoch(val) [3][129/129] acc/top1: 0.7275 acc/top5: 0.9562 acc/mean1: 0.7274 2022/12/20 17:40:12 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_2.pth is removed 2022/12/20 17:40:12 - mmengine - INFO - The best checkpoint with 0.7275 acc/top1 at 3 epoch is saved to best_acc/top1_epoch_3.pth. 2022/12/20 17:40:27 - mmengine - INFO - Epoch(train) [4][ 100/1567] lr: 9.1226e-02 eta: 0:52:44 time: 0.1277 data_time: 0.0075 memory: 1461 loss: 0.2518 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2518 2022/12/20 17:40:40 - mmengine - INFO - Epoch(train) [4][ 200/1567] lr: 9.0868e-02 eta: 0:52:19 time: 0.1053 data_time: 0.0081 memory: 1461 loss: 0.3216 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3216 2022/12/20 17:40:59 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 17:40:59 - mmengine - INFO - Epoch(train) [4][ 300/1567] lr: 9.0504e-02 eta: 0:52:16 time: 0.1586 data_time: 0.0078 memory: 1461 loss: 0.3154 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.3154 2022/12/20 17:41:14 - mmengine - INFO - Epoch(train) [4][ 400/1567] lr: 9.0133e-02 eta: 0:51:56 time: 0.1378 data_time: 0.0084 memory: 1461 loss: 0.3123 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3123 2022/12/20 17:41:30 - mmengine - INFO - Epoch(train) [4][ 500/1567] lr: 8.9756e-02 eta: 0:51:45 time: 0.1908 data_time: 0.0075 memory: 1461 loss: 0.2533 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2533 2022/12/20 17:41:46 - mmengine - INFO - Epoch(train) [4][ 600/1567] lr: 8.9373e-02 eta: 0:51:28 time: 0.1477 data_time: 0.0089 memory: 1461 loss: 0.2690 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2690 2022/12/20 17:42:02 - mmengine - INFO - Epoch(train) [4][ 700/1567] lr: 8.8984e-02 eta: 0:51:16 time: 0.1635 data_time: 0.0074 memory: 1461 loss: 0.3665 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3665 2022/12/20 17:42:18 - mmengine - INFO - Epoch(train) [4][ 800/1567] lr: 8.8589e-02 eta: 0:51:02 time: 0.1573 data_time: 0.0080 memory: 1461 loss: 0.2892 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2892 2022/12/20 17:42:34 - mmengine - INFO - Epoch(train) [4][ 900/1567] lr: 8.8187e-02 eta: 0:50:48 time: 0.2256 data_time: 0.0072 memory: 1461 loss: 0.3072 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3072 2022/12/20 17:42:52 - mmengine - INFO - Epoch(train) [4][1000/1567] lr: 8.7780e-02 eta: 0:50:37 time: 0.1576 data_time: 0.0072 memory: 1461 loss: 0.3722 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3722 2022/12/20 17:43:07 - mmengine - INFO - Epoch(train) [4][1100/1567] lr: 8.7367e-02 eta: 0:50:19 time: 0.2093 data_time: 0.0077 memory: 1461 loss: 0.3277 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3277 2022/12/20 17:43:24 - mmengine - INFO - Epoch(train) [4][1200/1567] lr: 8.6947e-02 eta: 0:50:08 time: 0.1512 data_time: 0.0073 memory: 1461 loss: 0.3041 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3041 2022/12/20 17:43:38 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 17:43:38 - mmengine - INFO - Epoch(train) [4][1300/1567] lr: 8.6522e-02 eta: 0:49:49 time: 0.1401 data_time: 0.0073 memory: 1461 loss: 0.3862 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3862 2022/12/20 17:43:56 - mmengine - INFO - Epoch(train) [4][1400/1567] lr: 8.6092e-02 eta: 0:49:40 time: 0.1698 data_time: 0.0067 memory: 1461 loss: 0.3392 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3392 2022/12/20 17:44:10 - mmengine - INFO - Epoch(train) [4][1500/1567] lr: 8.5655e-02 eta: 0:49:19 time: 0.1137 data_time: 0.0072 memory: 1461 loss: 0.3055 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3055 2022/12/20 17:44:21 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 17:44:21 - mmengine - INFO - Epoch(train) [4][1567/1567] lr: 8.5360e-02 eta: 0:49:10 time: 0.1941 data_time: 0.0064 memory: 1461 loss: 0.3441 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.3441 2022/12/20 17:44:21 - mmengine - INFO - Saving checkpoint at 4 epochs 2022/12/20 17:44:27 - mmengine - INFO - Epoch(val) [4][100/129] eta: 0:00:01 time: 0.0576 data_time: 0.0066 memory: 215 2022/12/20 17:44:30 - mmengine - INFO - Epoch(val) [4][129/129] acc/top1: 0.7730 acc/top5: 0.9721 acc/mean1: 0.7729 2022/12/20 17:44:30 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_3.pth is removed 2022/12/20 17:44:31 - mmengine - INFO - The best checkpoint with 0.7730 acc/top1 at 4 epoch is saved to best_acc/top1_epoch_4.pth. 2022/12/20 17:44:44 - mmengine - INFO - Epoch(train) [5][ 100/1567] lr: 8.4914e-02 eta: 0:48:47 time: 0.1470 data_time: 0.0076 memory: 1461 loss: 0.2745 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2745 2022/12/20 17:44:54 - mmengine - INFO - Epoch(train) [5][ 200/1567] lr: 8.4463e-02 eta: 0:48:16 time: 0.0961 data_time: 0.0089 memory: 1461 loss: 0.3093 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.3093 2022/12/20 17:45:09 - mmengine - INFO - Epoch(train) [5][ 300/1567] lr: 8.4006e-02 eta: 0:47:59 time: 0.1805 data_time: 0.0082 memory: 1461 loss: 0.2400 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2400 2022/12/20 17:45:27 - mmengine - INFO - Epoch(train) [5][ 400/1567] lr: 8.3544e-02 eta: 0:47:48 time: 0.1688 data_time: 0.0077 memory: 1461 loss: 0.3522 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.3522 2022/12/20 17:45:40 - mmengine - INFO - Epoch(train) [5][ 500/1567] lr: 8.3077e-02 eta: 0:47:27 time: 0.1212 data_time: 0.0076 memory: 1461 loss: 0.2884 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2884 2022/12/20 17:45:58 - mmengine - INFO - Epoch(train) [5][ 600/1567] lr: 8.2605e-02 eta: 0:47:18 time: 0.1569 data_time: 0.0071 memory: 1461 loss: 0.2749 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2749 2022/12/20 17:46:13 - mmengine - INFO - Epoch(train) [5][ 700/1567] lr: 8.2127e-02 eta: 0:46:59 time: 0.1535 data_time: 0.0075 memory: 1461 loss: 0.3095 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3095 2022/12/20 17:46:18 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 17:46:29 - mmengine - INFO - Epoch(train) [5][ 800/1567] lr: 8.1645e-02 eta: 0:46:45 time: 0.1629 data_time: 0.0075 memory: 1461 loss: 0.3565 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3565 2022/12/20 17:46:43 - mmengine - INFO - Epoch(train) [5][ 900/1567] lr: 8.1157e-02 eta: 0:46:27 time: 0.1536 data_time: 0.0077 memory: 1461 loss: 0.2313 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2313 2022/12/20 17:47:00 - mmengine - INFO - Epoch(train) [5][1000/1567] lr: 8.0665e-02 eta: 0:46:14 time: 0.1677 data_time: 0.0078 memory: 1461 loss: 0.2608 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2608 2022/12/20 17:47:14 - mmengine - INFO - Epoch(train) [5][1100/1567] lr: 8.0167e-02 eta: 0:45:55 time: 0.1469 data_time: 0.0073 memory: 1461 loss: 0.2370 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2370 2022/12/20 17:47:30 - mmengine - INFO - Epoch(train) [5][1200/1567] lr: 7.9665e-02 eta: 0:45:41 time: 0.1583 data_time: 0.0072 memory: 1461 loss: 0.2628 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2628 2022/12/20 17:47:45 - mmengine - INFO - Epoch(train) [5][1300/1567] lr: 7.9159e-02 eta: 0:45:23 time: 0.1374 data_time: 0.0074 memory: 1461 loss: 0.2410 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2410 2022/12/20 17:48:02 - mmengine - INFO - Epoch(train) [5][1400/1567] lr: 7.8647e-02 eta: 0:45:11 time: 0.1719 data_time: 0.0078 memory: 1461 loss: 0.3390 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.3390 2022/12/20 17:48:16 - mmengine - INFO - Epoch(train) [5][1500/1567] lr: 7.8132e-02 eta: 0:44:51 time: 0.1501 data_time: 0.0077 memory: 1461 loss: 0.2480 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2480 2022/12/20 17:48:26 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 17:48:26 - mmengine - INFO - Epoch(train) [5][1567/1567] lr: 7.7784e-02 eta: 0:44:40 time: 0.1493 data_time: 0.0068 memory: 1461 loss: 0.4484 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.4484 2022/12/20 17:48:26 - mmengine - INFO - Saving checkpoint at 5 epochs 2022/12/20 17:48:31 - mmengine - INFO - Epoch(val) [5][100/129] eta: 0:00:01 time: 0.0564 data_time: 0.0063 memory: 215 2022/12/20 17:48:35 - mmengine - INFO - Epoch(val) [5][129/129] acc/top1: 0.7556 acc/top5: 0.9625 acc/mean1: 0.7555 2022/12/20 17:48:48 - mmengine - INFO - Epoch(train) [6][ 100/1567] lr: 7.7261e-02 eta: 0:44:20 time: 0.1418 data_time: 0.0066 memory: 1461 loss: 0.2148 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2148 2022/12/20 17:48:56 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 17:49:03 - mmengine - INFO - Epoch(train) [6][ 200/1567] lr: 7.6733e-02 eta: 0:44:02 time: 0.1957 data_time: 0.0079 memory: 1461 loss: 0.2810 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.2810 2022/12/20 17:49:18 - mmengine - INFO - Epoch(train) [6][ 300/1567] lr: 7.6202e-02 eta: 0:43:47 time: 0.1493 data_time: 0.0070 memory: 1461 loss: 0.2238 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2238 2022/12/20 17:49:33 - mmengine - INFO - Epoch(train) [6][ 400/1567] lr: 7.5666e-02 eta: 0:43:29 time: 0.1820 data_time: 0.0073 memory: 1461 loss: 0.2074 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2074 2022/12/20 17:49:49 - mmengine - INFO - Epoch(train) [6][ 500/1567] lr: 7.5126e-02 eta: 0:43:14 time: 0.1583 data_time: 0.0076 memory: 1461 loss: 0.1914 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1914 2022/12/20 17:50:03 - mmengine - INFO - Epoch(train) [6][ 600/1567] lr: 7.4583e-02 eta: 0:42:57 time: 0.2037 data_time: 0.0075 memory: 1461 loss: 0.1546 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1546 2022/12/20 17:50:19 - mmengine - INFO - Epoch(train) [6][ 700/1567] lr: 7.4035e-02 eta: 0:42:43 time: 0.1542 data_time: 0.0071 memory: 1461 loss: 0.2848 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2848 2022/12/20 17:50:33 - mmengine - INFO - Epoch(train) [6][ 800/1567] lr: 7.3484e-02 eta: 0:42:24 time: 0.1877 data_time: 0.0074 memory: 1461 loss: 0.2871 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2871 2022/12/20 17:50:49 - mmengine - INFO - Epoch(train) [6][ 900/1567] lr: 7.2929e-02 eta: 0:42:10 time: 0.1490 data_time: 0.0075 memory: 1461 loss: 0.2909 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.2909 2022/12/20 17:51:03 - mmengine - INFO - Epoch(train) [6][1000/1567] lr: 7.2371e-02 eta: 0:41:51 time: 0.0893 data_time: 0.0069 memory: 1461 loss: 0.1908 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1908 2022/12/20 17:51:20 - mmengine - INFO - Epoch(train) [6][1100/1567] lr: 7.1809e-02 eta: 0:41:39 time: 0.1516 data_time: 0.0076 memory: 1461 loss: 0.1854 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1854 2022/12/20 17:51:30 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 17:51:34 - mmengine - INFO - Epoch(train) [6][1200/1567] lr: 7.1243e-02 eta: 0:41:20 time: 0.1139 data_time: 0.0073 memory: 1461 loss: 0.1591 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1591 2022/12/20 17:51:50 - mmengine - INFO - Epoch(train) [6][1300/1567] lr: 7.0674e-02 eta: 0:41:05 time: 0.1327 data_time: 0.0069 memory: 1461 loss: 0.2012 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2012 2022/12/20 17:52:04 - mmengine - INFO - Epoch(train) [6][1400/1567] lr: 7.0102e-02 eta: 0:40:47 time: 0.1156 data_time: 0.0069 memory: 1461 loss: 0.3097 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3097 2022/12/20 17:52:19 - mmengine - INFO - Epoch(train) [6][1500/1567] lr: 6.9527e-02 eta: 0:40:31 time: 0.1378 data_time: 0.0067 memory: 1461 loss: 0.2230 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2230 2022/12/20 17:52:28 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 17:52:28 - mmengine - INFO - Epoch(train) [6][1567/1567] lr: 6.9140e-02 eta: 0:40:19 time: 0.1416 data_time: 0.0070 memory: 1461 loss: 0.4056 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.4056 2022/12/20 17:52:28 - mmengine - INFO - Saving checkpoint at 6 epochs 2022/12/20 17:52:33 - mmengine - INFO - Epoch(val) [6][100/129] eta: 0:00:01 time: 0.0319 data_time: 0.0063 memory: 215 2022/12/20 17:52:35 - mmengine - INFO - Epoch(val) [6][129/129] acc/top1: 0.7555 acc/top5: 0.9487 acc/mean1: 0.7555 2022/12/20 17:52:52 - mmengine - INFO - Epoch(train) [7][ 100/1567] lr: 6.8560e-02 eta: 0:40:05 time: 0.2099 data_time: 0.0071 memory: 1461 loss: 0.2387 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2387 2022/12/20 17:53:07 - mmengine - INFO - Epoch(train) [7][ 200/1567] lr: 6.7976e-02 eta: 0:39:50 time: 0.1372 data_time: 0.0074 memory: 1461 loss: 0.2599 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2599 2022/12/20 17:53:23 - mmengine - INFO - Epoch(train) [7][ 300/1567] lr: 6.7390e-02 eta: 0:39:35 time: 0.1704 data_time: 0.0071 memory: 1461 loss: 0.2020 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2020 2022/12/20 17:53:39 - mmengine - INFO - Epoch(train) [7][ 400/1567] lr: 6.6802e-02 eta: 0:39:21 time: 0.1568 data_time: 0.0074 memory: 1461 loss: 0.2251 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2251 2022/12/20 17:53:55 - mmengine - INFO - Epoch(train) [7][ 500/1567] lr: 6.6210e-02 eta: 0:39:05 time: 0.1853 data_time: 0.0072 memory: 1461 loss: 0.2155 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2155 2022/12/20 17:54:11 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 17:54:11 - mmengine - INFO - Epoch(train) [7][ 600/1567] lr: 6.5616e-02 eta: 0:38:51 time: 0.1527 data_time: 0.0079 memory: 1461 loss: 0.1999 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1999 2022/12/20 17:54:25 - mmengine - INFO - Epoch(train) [7][ 700/1567] lr: 6.5020e-02 eta: 0:38:33 time: 0.1277 data_time: 0.0072 memory: 1461 loss: 0.2100 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2100 2022/12/20 17:54:42 - mmengine - INFO - Epoch(train) [7][ 800/1567] lr: 6.4421e-02 eta: 0:38:20 time: 0.1619 data_time: 0.0077 memory: 1461 loss: 0.2090 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2090 2022/12/20 17:54:57 - mmengine - INFO - Epoch(train) [7][ 900/1567] lr: 6.3820e-02 eta: 0:38:04 time: 0.1427 data_time: 0.0080 memory: 1461 loss: 0.1808 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1808 2022/12/20 17:55:14 - mmengine - INFO - Epoch(train) [7][1000/1567] lr: 6.3217e-02 eta: 0:37:50 time: 0.1566 data_time: 0.0074 memory: 1461 loss: 0.1769 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1769 2022/12/20 17:55:29 - mmengine - INFO - Epoch(train) [7][1100/1567] lr: 6.2612e-02 eta: 0:37:34 time: 0.1443 data_time: 0.0077 memory: 1461 loss: 0.1641 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1641 2022/12/20 17:55:45 - mmengine - INFO - Epoch(train) [7][1200/1567] lr: 6.2005e-02 eta: 0:37:20 time: 0.1783 data_time: 0.0070 memory: 1461 loss: 0.1794 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1794 2022/12/20 17:56:01 - mmengine - INFO - Epoch(train) [7][1300/1567] lr: 6.1396e-02 eta: 0:37:04 time: 0.1686 data_time: 0.0074 memory: 1461 loss: 0.2171 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2171 2022/12/20 17:56:16 - mmengine - INFO - Epoch(train) [7][1400/1567] lr: 6.0785e-02 eta: 0:36:49 time: 0.1489 data_time: 0.0073 memory: 1461 loss: 0.2128 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2128 2022/12/20 17:56:31 - mmengine - INFO - Epoch(train) [7][1500/1567] lr: 6.0172e-02 eta: 0:36:32 time: 0.1426 data_time: 0.0070 memory: 1461 loss: 0.2461 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2461 2022/12/20 17:56:40 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 17:56:40 - mmengine - INFO - Epoch(train) [7][1567/1567] lr: 5.9761e-02 eta: 0:36:20 time: 0.1354 data_time: 0.0067 memory: 1461 loss: 0.3894 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.3894 2022/12/20 17:56:40 - mmengine - INFO - Saving checkpoint at 7 epochs 2022/12/20 17:56:44 - mmengine - INFO - Epoch(val) [7][100/129] eta: 0:00:01 time: 0.0313 data_time: 0.0076 memory: 215 2022/12/20 17:56:45 - mmengine - INFO - Epoch(val) [7][129/129] acc/top1: 0.8248 acc/top5: 0.9786 acc/mean1: 0.8246 2022/12/20 17:56:45 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_4.pth is removed 2022/12/20 17:56:46 - mmengine - INFO - The best checkpoint with 0.8248 acc/top1 at 7 epoch is saved to best_acc/top1_epoch_7.pth. 2022/12/20 17:56:51 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 17:57:02 - mmengine - INFO - Epoch(train) [8][ 100/1567] lr: 5.9145e-02 eta: 0:36:05 time: 0.1282 data_time: 0.0076 memory: 1461 loss: 0.1529 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1529 2022/12/20 17:57:16 - mmengine - INFO - Epoch(train) [8][ 200/1567] lr: 5.8529e-02 eta: 0:35:47 time: 0.1371 data_time: 0.0072 memory: 1461 loss: 0.1633 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1633 2022/12/20 17:57:31 - mmengine - INFO - Epoch(train) [8][ 300/1567] lr: 5.7911e-02 eta: 0:35:31 time: 0.1350 data_time: 0.0077 memory: 1461 loss: 0.2136 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2136 2022/12/20 17:57:45 - mmengine - INFO - Epoch(train) [8][ 400/1567] lr: 5.7292e-02 eta: 0:35:14 time: 0.1343 data_time: 0.0078 memory: 1461 loss: 0.1816 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1816 2022/12/20 17:58:00 - mmengine - INFO - Epoch(train) [8][ 500/1567] lr: 5.6671e-02 eta: 0:34:58 time: 0.1566 data_time: 0.0081 memory: 1461 loss: 0.2026 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2026 2022/12/20 17:58:14 - mmengine - INFO - Epoch(train) [8][ 600/1567] lr: 5.6050e-02 eta: 0:34:41 time: 0.1244 data_time: 0.0075 memory: 1461 loss: 0.2186 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2186 2022/12/20 17:58:29 - mmengine - INFO - Epoch(train) [8][ 700/1567] lr: 5.5427e-02 eta: 0:34:25 time: 0.1288 data_time: 0.0076 memory: 1461 loss: 0.1493 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1493 2022/12/20 17:58:44 - mmengine - INFO - Epoch(train) [8][ 800/1567] lr: 5.4804e-02 eta: 0:34:09 time: 0.1407 data_time: 0.0077 memory: 1461 loss: 0.1497 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1497 2022/12/20 17:58:59 - mmengine - INFO - Epoch(train) [8][ 900/1567] lr: 5.4180e-02 eta: 0:33:53 time: 0.1402 data_time: 0.0081 memory: 1461 loss: 0.1644 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1644 2022/12/20 17:59:14 - mmengine - INFO - Epoch(train) [8][1000/1567] lr: 5.3556e-02 eta: 0:33:37 time: 0.1568 data_time: 0.0076 memory: 1461 loss: 0.1625 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1625 2022/12/20 17:59:17 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 17:59:28 - mmengine - INFO - Epoch(train) [8][1100/1567] lr: 5.2930e-02 eta: 0:33:20 time: 0.1500 data_time: 0.0082 memory: 1461 loss: 0.1602 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1602 2022/12/20 17:59:42 - mmengine - INFO - Epoch(train) [8][1200/1567] lr: 5.2305e-02 eta: 0:33:04 time: 0.1511 data_time: 0.0072 memory: 1461 loss: 0.1224 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1224 2022/12/20 17:59:56 - mmengine - INFO - Epoch(train) [8][1300/1567] lr: 5.1679e-02 eta: 0:32:47 time: 0.1199 data_time: 0.0069 memory: 1461 loss: 0.1400 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1400 2022/12/20 18:00:09 - mmengine - INFO - Epoch(train) [8][1400/1567] lr: 5.1052e-02 eta: 0:32:30 time: 0.1397 data_time: 0.0068 memory: 1461 loss: 0.1791 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.1791 2022/12/20 18:00:22 - mmengine - INFO - Epoch(train) [8][1500/1567] lr: 5.0426e-02 eta: 0:32:11 time: 0.0909 data_time: 0.0083 memory: 1461 loss: 0.1582 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1582 2022/12/20 18:00:33 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 18:00:33 - mmengine - INFO - Epoch(train) [8][1567/1567] lr: 5.0006e-02 eta: 0:32:02 time: 0.1484 data_time: 0.0070 memory: 1461 loss: 0.2857 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2857 2022/12/20 18:00:33 - mmengine - INFO - Saving checkpoint at 8 epochs 2022/12/20 18:00:39 - mmengine - INFO - Epoch(val) [8][100/129] eta: 0:00:01 time: 0.0298 data_time: 0.0068 memory: 215 2022/12/20 18:00:44 - mmengine - INFO - Epoch(val) [8][129/129] acc/top1: 0.8094 acc/top5: 0.9703 acc/mean1: 0.8093 2022/12/20 18:00:59 - mmengine - INFO - Epoch(train) [9][ 100/1567] lr: 4.9380e-02 eta: 0:31:46 time: 0.1923 data_time: 0.0074 memory: 1461 loss: 0.1551 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1551 2022/12/20 18:01:16 - mmengine - INFO - Epoch(train) [9][ 200/1567] lr: 4.8753e-02 eta: 0:31:32 time: 0.1784 data_time: 0.0082 memory: 1461 loss: 0.1468 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1468 2022/12/20 18:01:31 - mmengine - INFO - Epoch(train) [9][ 300/1567] lr: 4.8127e-02 eta: 0:31:17 time: 0.1419 data_time: 0.0071 memory: 1461 loss: 0.1031 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1031 2022/12/20 18:01:47 - mmengine - INFO - Epoch(train) [9][ 400/1567] lr: 4.7501e-02 eta: 0:31:02 time: 0.1783 data_time: 0.0070 memory: 1461 loss: 0.1328 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1328 2022/12/20 18:01:57 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 18:02:02 - mmengine - INFO - Epoch(train) [9][ 500/1567] lr: 4.6876e-02 eta: 0:30:46 time: 0.1260 data_time: 0.0074 memory: 1461 loss: 0.1968 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1968 2022/12/20 18:02:18 - mmengine - INFO - Epoch(train) [9][ 600/1567] lr: 4.6251e-02 eta: 0:30:31 time: 0.1484 data_time: 0.0071 memory: 1461 loss: 0.1771 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1771 2022/12/20 18:02:33 - mmengine - INFO - Epoch(train) [9][ 700/1567] lr: 4.5626e-02 eta: 0:30:16 time: 0.1478 data_time: 0.0073 memory: 1461 loss: 0.1176 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1176 2022/12/20 18:02:49 - mmengine - INFO - Epoch(train) [9][ 800/1567] lr: 4.5003e-02 eta: 0:30:01 time: 0.1612 data_time: 0.0073 memory: 1461 loss: 0.1861 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1861 2022/12/20 18:03:05 - mmengine - INFO - Epoch(train) [9][ 900/1567] lr: 4.4380e-02 eta: 0:29:46 time: 0.1692 data_time: 0.0074 memory: 1461 loss: 0.0877 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0877 2022/12/20 18:03:21 - mmengine - INFO - Epoch(train) [9][1000/1567] lr: 4.3757e-02 eta: 0:29:32 time: 0.2040 data_time: 0.0074 memory: 1461 loss: 0.1590 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1590 2022/12/20 18:03:37 - mmengine - INFO - Epoch(train) [9][1100/1567] lr: 4.3136e-02 eta: 0:29:16 time: 0.1563 data_time: 0.0070 memory: 1461 loss: 0.1525 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1525 2022/12/20 18:03:51 - mmengine - INFO - Epoch(train) [9][1200/1567] lr: 4.2516e-02 eta: 0:29:00 time: 0.1665 data_time: 0.0068 memory: 1461 loss: 0.1393 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1393 2022/12/20 18:04:07 - mmengine - INFO - Epoch(train) [9][1300/1567] lr: 4.1897e-02 eta: 0:28:46 time: 0.1597 data_time: 0.0069 memory: 1461 loss: 0.1351 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1351 2022/12/20 18:04:21 - mmengine - INFO - Epoch(train) [9][1400/1567] lr: 4.1280e-02 eta: 0:28:29 time: 0.1355 data_time: 0.0066 memory: 1461 loss: 0.1333 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1333 2022/12/20 18:04:29 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 18:04:35 - mmengine - INFO - Epoch(train) [9][1500/1567] lr: 4.0664e-02 eta: 0:28:12 time: 0.2244 data_time: 0.0084 memory: 1461 loss: 0.1409 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1409 2022/12/20 18:04:45 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 18:04:45 - mmengine - INFO - Epoch(train) [9][1567/1567] lr: 4.0252e-02 eta: 0:28:02 time: 0.1368 data_time: 0.0071 memory: 1461 loss: 0.2694 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2694 2022/12/20 18:04:45 - mmengine - INFO - Saving checkpoint at 9 epochs 2022/12/20 18:04:51 - mmengine - INFO - Epoch(val) [9][100/129] eta: 0:00:01 time: 0.0704 data_time: 0.0075 memory: 215 2022/12/20 18:04:55 - mmengine - INFO - Epoch(val) [9][129/129] acc/top1: 0.8462 acc/top5: 0.9838 acc/mean1: 0.8460 2022/12/20 18:04:55 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_7.pth is removed 2022/12/20 18:04:55 - mmengine - INFO - The best checkpoint with 0.8462 acc/top1 at 9 epoch is saved to best_acc/top1_epoch_9.pth. 2022/12/20 18:05:11 - mmengine - INFO - Epoch(train) [10][ 100/1567] lr: 3.9638e-02 eta: 0:27:47 time: 0.1597 data_time: 0.0073 memory: 1461 loss: 0.1123 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1123 2022/12/20 18:05:27 - mmengine - INFO - Epoch(train) [10][ 200/1567] lr: 3.9026e-02 eta: 0:27:32 time: 0.1562 data_time: 0.0077 memory: 1461 loss: 0.1031 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1031 2022/12/20 18:05:43 - mmengine - INFO - Epoch(train) [10][ 300/1567] lr: 3.8415e-02 eta: 0:27:17 time: 0.1974 data_time: 0.0078 memory: 1461 loss: 0.1697 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1697 2022/12/20 18:05:59 - mmengine - INFO - Epoch(train) [10][ 400/1567] lr: 3.7807e-02 eta: 0:27:03 time: 0.1600 data_time: 0.0079 memory: 1461 loss: 0.1038 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1038 2022/12/20 18:06:15 - mmengine - INFO - Epoch(train) [10][ 500/1567] lr: 3.7200e-02 eta: 0:26:47 time: 0.1704 data_time: 0.0071 memory: 1461 loss: 0.0949 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0949 2022/12/20 18:06:32 - mmengine - INFO - Epoch(train) [10][ 600/1567] lr: 3.6596e-02 eta: 0:26:33 time: 0.1576 data_time: 0.0075 memory: 1461 loss: 0.0996 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0996 2022/12/20 18:06:47 - mmengine - INFO - Epoch(train) [10][ 700/1567] lr: 3.5993e-02 eta: 0:26:18 time: 0.1291 data_time: 0.0072 memory: 1461 loss: 0.1086 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1086 2022/12/20 18:07:04 - mmengine - INFO - Epoch(train) [10][ 800/1567] lr: 3.5393e-02 eta: 0:26:04 time: 0.1917 data_time: 0.0073 memory: 1461 loss: 0.1203 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1203 2022/12/20 18:07:19 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 18:07:20 - mmengine - INFO - Epoch(train) [10][ 900/1567] lr: 3.4795e-02 eta: 0:25:48 time: 0.1562 data_time: 0.0083 memory: 1461 loss: 0.1078 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1078 2022/12/20 18:07:36 - mmengine - INFO - Epoch(train) [10][1000/1567] lr: 3.4199e-02 eta: 0:25:34 time: 0.1542 data_time: 0.0070 memory: 1461 loss: 0.0870 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0870 2022/12/20 18:07:51 - mmengine - INFO - Epoch(train) [10][1100/1567] lr: 3.3606e-02 eta: 0:25:18 time: 0.1499 data_time: 0.0069 memory: 1461 loss: 0.1146 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1146 2022/12/20 18:08:07 - mmengine - INFO - Epoch(train) [10][1200/1567] lr: 3.3015e-02 eta: 0:25:03 time: 0.1599 data_time: 0.0070 memory: 1461 loss: 0.1149 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1149 2022/12/20 18:08:21 - mmengine - INFO - Epoch(train) [10][1300/1567] lr: 3.2428e-02 eta: 0:24:47 time: 0.1282 data_time: 0.0066 memory: 1461 loss: 0.1023 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1023 2022/12/20 18:08:36 - mmengine - INFO - Epoch(train) [10][1400/1567] lr: 3.1842e-02 eta: 0:24:31 time: 0.1309 data_time: 0.0095 memory: 1461 loss: 0.1025 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1025 2022/12/20 18:08:50 - mmengine - INFO - Epoch(train) [10][1500/1567] lr: 3.1260e-02 eta: 0:24:15 time: 0.1586 data_time: 0.0085 memory: 1461 loss: 0.1192 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1192 2022/12/20 18:09:00 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 18:09:00 - mmengine - INFO - Epoch(train) [10][1567/1567] lr: 3.0872e-02 eta: 0:24:05 time: 0.1301 data_time: 0.0077 memory: 1461 loss: 0.2998 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.2998 2022/12/20 18:09:00 - mmengine - INFO - Saving checkpoint at 10 epochs 2022/12/20 18:09:07 - mmengine - INFO - Epoch(val) [10][100/129] eta: 0:00:01 time: 0.0325 data_time: 0.0071 memory: 215 2022/12/20 18:09:08 - mmengine - INFO - Epoch(val) [10][129/129] acc/top1: 0.8342 acc/top5: 0.9753 acc/mean1: 0.8342 2022/12/20 18:09:25 - mmengine - INFO - Epoch(train) [11][ 100/1567] lr: 3.0294e-02 eta: 0:23:50 time: 0.1692 data_time: 0.0071 memory: 1461 loss: 0.0710 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0710 2022/12/20 18:09:40 - mmengine - INFO - Epoch(train) [11][ 200/1567] lr: 2.9720e-02 eta: 0:23:35 time: 0.1341 data_time: 0.0073 memory: 1461 loss: 0.1048 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1048 2022/12/20 18:09:57 - mmengine - INFO - Epoch(train) [11][ 300/1567] lr: 2.9149e-02 eta: 0:23:20 time: 0.1773 data_time: 0.0077 memory: 1461 loss: 0.0773 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0773 2022/12/20 18:10:01 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 18:10:11 - mmengine - INFO - Epoch(train) [11][ 400/1567] lr: 2.8581e-02 eta: 0:23:04 time: 0.1269 data_time: 0.0078 memory: 1461 loss: 0.0909 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0909 2022/12/20 18:10:27 - mmengine - INFO - Epoch(train) [11][ 500/1567] lr: 2.8017e-02 eta: 0:22:49 time: 0.1597 data_time: 0.0071 memory: 1461 loss: 0.0922 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0922 2022/12/20 18:10:42 - mmengine - INFO - Epoch(train) [11][ 600/1567] lr: 2.7456e-02 eta: 0:22:33 time: 0.1322 data_time: 0.0082 memory: 1461 loss: 0.0708 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0708 2022/12/20 18:10:58 - mmengine - INFO - Epoch(train) [11][ 700/1567] lr: 2.6898e-02 eta: 0:22:18 time: 0.1649 data_time: 0.0082 memory: 1461 loss: 0.0884 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0884 2022/12/20 18:11:13 - mmengine - INFO - Epoch(train) [11][ 800/1567] lr: 2.6345e-02 eta: 0:22:03 time: 0.1385 data_time: 0.0078 memory: 1461 loss: 0.1069 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1069 2022/12/20 18:11:30 - mmengine - INFO - Epoch(train) [11][ 900/1567] lr: 2.5794e-02 eta: 0:21:48 time: 0.1612 data_time: 0.0067 memory: 1461 loss: 0.0742 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0742 2022/12/20 18:11:44 - mmengine - INFO - Epoch(train) [11][1000/1567] lr: 2.5248e-02 eta: 0:21:32 time: 0.1481 data_time: 0.0067 memory: 1461 loss: 0.0602 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0602 2022/12/20 18:11:59 - mmengine - INFO - Epoch(train) [11][1100/1567] lr: 2.4706e-02 eta: 0:21:17 time: 0.1518 data_time: 0.0070 memory: 1461 loss: 0.0636 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0636 2022/12/20 18:12:13 - mmengine - INFO - Epoch(train) [11][1200/1567] lr: 2.4167e-02 eta: 0:21:00 time: 0.1384 data_time: 0.0068 memory: 1461 loss: 0.0407 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0407 2022/12/20 18:12:25 - mmengine - INFO - Epoch(train) [11][1300/1567] lr: 2.3633e-02 eta: 0:20:44 time: 0.1136 data_time: 0.0083 memory: 1461 loss: 0.0925 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0925 2022/12/20 18:12:31 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 18:12:43 - mmengine - INFO - Epoch(train) [11][1400/1567] lr: 2.3103e-02 eta: 0:20:29 time: 0.1466 data_time: 0.0079 memory: 1461 loss: 0.0314 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0314 2022/12/20 18:12:58 - mmengine - INFO - Epoch(train) [11][1500/1567] lr: 2.2577e-02 eta: 0:20:14 time: 0.1262 data_time: 0.0077 memory: 1461 loss: 0.0525 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0525 2022/12/20 18:13:09 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 18:13:09 - mmengine - INFO - Epoch(train) [11][1567/1567] lr: 2.2227e-02 eta: 0:20:04 time: 0.1454 data_time: 0.0069 memory: 1461 loss: 0.2825 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2825 2022/12/20 18:13:09 - mmengine - INFO - Saving checkpoint at 11 epochs 2022/12/20 18:13:16 - mmengine - INFO - Epoch(val) [11][100/129] eta: 0:00:01 time: 0.0588 data_time: 0.0067 memory: 215 2022/12/20 18:13:18 - mmengine - INFO - Epoch(val) [11][129/129] acc/top1: 0.8604 acc/top5: 0.9825 acc/mean1: 0.8604 2022/12/20 18:13:18 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_9.pth is removed 2022/12/20 18:13:19 - mmengine - INFO - The best checkpoint with 0.8604 acc/top1 at 11 epoch is saved to best_acc/top1_epoch_11.pth. 2022/12/20 18:13:34 - mmengine - INFO - Epoch(train) [12][ 100/1567] lr: 2.1708e-02 eta: 0:19:48 time: 0.1503 data_time: 0.0073 memory: 1461 loss: 0.0660 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0660 2022/12/20 18:13:50 - mmengine - INFO - Epoch(train) [12][ 200/1567] lr: 2.1194e-02 eta: 0:19:33 time: 0.1591 data_time: 0.0073 memory: 1461 loss: 0.0519 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0519 2022/12/20 18:14:05 - mmengine - INFO - Epoch(train) [12][ 300/1567] lr: 2.0684e-02 eta: 0:19:18 time: 0.1760 data_time: 0.0072 memory: 1461 loss: 0.0629 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0629 2022/12/20 18:14:22 - mmengine - INFO - Epoch(train) [12][ 400/1567] lr: 2.0179e-02 eta: 0:19:03 time: 0.1656 data_time: 0.0075 memory: 1461 loss: 0.0667 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0667 2022/12/20 18:14:37 - mmengine - INFO - Epoch(train) [12][ 500/1567] lr: 1.9678e-02 eta: 0:18:48 time: 0.1478 data_time: 0.0080 memory: 1461 loss: 0.0662 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0662 2022/12/20 18:14:54 - mmengine - INFO - Epoch(train) [12][ 600/1567] lr: 1.9182e-02 eta: 0:18:33 time: 0.1503 data_time: 0.0075 memory: 1461 loss: 0.0637 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0637 2022/12/20 18:15:10 - mmengine - INFO - Epoch(train) [12][ 700/1567] lr: 1.8691e-02 eta: 0:18:17 time: 0.1267 data_time: 0.0076 memory: 1461 loss: 0.0620 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0620 2022/12/20 18:15:20 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 18:15:26 - mmengine - INFO - Epoch(train) [12][ 800/1567] lr: 1.8205e-02 eta: 0:18:03 time: 0.1304 data_time: 0.0071 memory: 1461 loss: 0.0934 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0934 2022/12/20 18:15:41 - mmengine - INFO - Epoch(train) [12][ 900/1567] lr: 1.7724e-02 eta: 0:17:47 time: 0.1567 data_time: 0.0076 memory: 1461 loss: 0.0684 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0684 2022/12/20 18:15:57 - mmengine - INFO - Epoch(train) [12][1000/1567] lr: 1.7248e-02 eta: 0:17:32 time: 0.1262 data_time: 0.0068 memory: 1461 loss: 0.0393 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0393 2022/12/20 18:16:11 - mmengine - INFO - Epoch(train) [12][1100/1567] lr: 1.6778e-02 eta: 0:17:16 time: 0.1416 data_time: 0.0073 memory: 1461 loss: 0.0672 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0672 2022/12/20 18:16:24 - mmengine - INFO - Epoch(train) [12][1200/1567] lr: 1.6312e-02 eta: 0:17:00 time: 0.0947 data_time: 0.0080 memory: 1461 loss: 0.0499 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0499 2022/12/20 18:16:41 - mmengine - INFO - Epoch(train) [12][1300/1567] lr: 1.5852e-02 eta: 0:16:45 time: 0.1577 data_time: 0.0078 memory: 1461 loss: 0.0369 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0369 2022/12/20 18:16:56 - mmengine - INFO - Epoch(train) [12][1400/1567] lr: 1.5397e-02 eta: 0:16:29 time: 0.1463 data_time: 0.0077 memory: 1461 loss: 0.0336 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0336 2022/12/20 18:17:14 - mmengine - INFO - Epoch(train) [12][1500/1567] lr: 1.4947e-02 eta: 0:16:15 time: 0.1598 data_time: 0.0073 memory: 1461 loss: 0.0378 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0378 2022/12/20 18:17:24 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 18:17:24 - mmengine - INFO - Epoch(train) [12][1567/1567] lr: 1.4649e-02 eta: 0:16:05 time: 0.1618 data_time: 0.0075 memory: 1461 loss: 0.2771 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2771 2022/12/20 18:17:24 - mmengine - INFO - Saving checkpoint at 12 epochs 2022/12/20 18:17:32 - mmengine - INFO - Epoch(val) [12][100/129] eta: 0:00:02 time: 0.0495 data_time: 0.0071 memory: 215 2022/12/20 18:17:33 - mmengine - INFO - Epoch(val) [12][129/129] acc/top1: 0.8522 acc/top5: 0.9793 acc/mean1: 0.8522 2022/12/20 18:17:50 - mmengine - INFO - Epoch(train) [13][ 100/1567] lr: 1.4209e-02 eta: 0:15:50 time: 0.1452 data_time: 0.0076 memory: 1461 loss: 0.0516 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0516 2022/12/20 18:18:05 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 18:18:06 - mmengine - INFO - Epoch(train) [13][ 200/1567] lr: 1.3774e-02 eta: 0:15:34 time: 0.1503 data_time: 0.0076 memory: 1461 loss: 0.0393 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0393 2022/12/20 18:18:22 - mmengine - INFO - Epoch(train) [13][ 300/1567] lr: 1.3345e-02 eta: 0:15:19 time: 0.1610 data_time: 0.0072 memory: 1461 loss: 0.0284 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0284 2022/12/20 18:18:38 - mmengine - INFO - Epoch(train) [13][ 400/1567] lr: 1.2922e-02 eta: 0:15:04 time: 0.1581 data_time: 0.0082 memory: 1461 loss: 0.0268 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0268 2022/12/20 18:18:55 - mmengine - INFO - Epoch(train) [13][ 500/1567] lr: 1.2505e-02 eta: 0:14:49 time: 0.1589 data_time: 0.0072 memory: 1461 loss: 0.0502 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0502 2022/12/20 18:19:11 - mmengine - INFO - Epoch(train) [13][ 600/1567] lr: 1.2093e-02 eta: 0:14:34 time: 0.1502 data_time: 0.0074 memory: 1461 loss: 0.0298 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0298 2022/12/20 18:19:27 - mmengine - INFO - Epoch(train) [13][ 700/1567] lr: 1.1687e-02 eta: 0:14:19 time: 0.2177 data_time: 0.0070 memory: 1461 loss: 0.0266 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0266 2022/12/20 18:19:43 - mmengine - INFO - Epoch(train) [13][ 800/1567] lr: 1.1288e-02 eta: 0:14:03 time: 0.1529 data_time: 0.0071 memory: 1461 loss: 0.0286 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0286 2022/12/20 18:19:58 - mmengine - INFO - Epoch(train) [13][ 900/1567] lr: 1.0894e-02 eta: 0:13:48 time: 0.1701 data_time: 0.0070 memory: 1461 loss: 0.0450 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0450 2022/12/20 18:20:14 - mmengine - INFO - Epoch(train) [13][1000/1567] lr: 1.0507e-02 eta: 0:13:32 time: 0.1469 data_time: 0.0070 memory: 1461 loss: 0.0231 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0231 2022/12/20 18:20:27 - mmengine - INFO - Epoch(train) [13][1100/1567] lr: 1.0126e-02 eta: 0:13:16 time: 0.1407 data_time: 0.0068 memory: 1461 loss: 0.0241 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0241 2022/12/20 18:20:40 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 18:20:41 - mmengine - INFO - Epoch(train) [13][1200/1567] lr: 9.7512e-03 eta: 0:13:01 time: 0.2251 data_time: 0.0085 memory: 1461 loss: 0.0305 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0305 2022/12/20 18:20:57 - mmengine - INFO - Epoch(train) [13][1300/1567] lr: 9.3826e-03 eta: 0:12:45 time: 0.1527 data_time: 0.0080 memory: 1461 loss: 0.0304 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0304 2022/12/20 18:21:12 - mmengine - INFO - Epoch(train) [13][1400/1567] lr: 9.0204e-03 eta: 0:12:30 time: 0.1895 data_time: 0.0070 memory: 1461 loss: 0.0245 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0245 2022/12/20 18:21:29 - mmengine - INFO - Epoch(train) [13][1500/1567] lr: 8.6647e-03 eta: 0:12:15 time: 0.1522 data_time: 0.0077 memory: 1461 loss: 0.0263 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0263 2022/12/20 18:21:38 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 18:21:38 - mmengine - INFO - Epoch(train) [13][1567/1567] lr: 8.4300e-03 eta: 0:12:04 time: 0.1396 data_time: 0.0074 memory: 1461 loss: 0.2159 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2159 2022/12/20 18:21:38 - mmengine - INFO - Saving checkpoint at 13 epochs 2022/12/20 18:21:42 - mmengine - INFO - Epoch(val) [13][100/129] eta: 0:00:00 time: 0.0291 data_time: 0.0064 memory: 215 2022/12/20 18:21:48 - mmengine - INFO - Epoch(val) [13][129/129] acc/top1: 0.8692 acc/top5: 0.9854 acc/mean1: 0.8692 2022/12/20 18:21:48 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_11.pth is removed 2022/12/20 18:21:48 - mmengine - INFO - The best checkpoint with 0.8692 acc/top1 at 13 epoch is saved to best_acc/top1_epoch_13.pth. 2022/12/20 18:22:05 - mmengine - INFO - Epoch(train) [14][ 100/1567] lr: 8.0851e-03 eta: 0:11:49 time: 0.1399 data_time: 0.0072 memory: 1461 loss: 0.0224 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0224 2022/12/20 18:22:20 - mmengine - INFO - Epoch(train) [14][ 200/1567] lr: 7.7469e-03 eta: 0:11:34 time: 0.1932 data_time: 0.0074 memory: 1461 loss: 0.0219 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0219 2022/12/20 18:22:37 - mmengine - INFO - Epoch(train) [14][ 300/1567] lr: 7.4152e-03 eta: 0:11:18 time: 0.1622 data_time: 0.0073 memory: 1461 loss: 0.0101 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0101 2022/12/20 18:22:52 - mmengine - INFO - Epoch(train) [14][ 400/1567] lr: 7.0902e-03 eta: 0:11:03 time: 0.1679 data_time: 0.0071 memory: 1461 loss: 0.0185 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0185 2022/12/20 18:23:10 - mmengine - INFO - Epoch(train) [14][ 500/1567] lr: 6.7720e-03 eta: 0:10:48 time: 0.1535 data_time: 0.0075 memory: 1461 loss: 0.0128 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0128 2022/12/20 18:23:24 - mmengine - INFO - Epoch(train) [14][ 600/1567] lr: 6.4606e-03 eta: 0:10:32 time: 0.1362 data_time: 0.0073 memory: 1461 loss: 0.0193 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0193 2022/12/20 18:23:29 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 18:23:41 - mmengine - INFO - Epoch(train) [14][ 700/1567] lr: 6.1560e-03 eta: 0:10:17 time: 0.1571 data_time: 0.0072 memory: 1461 loss: 0.0222 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0222 2022/12/20 18:23:56 - mmengine - INFO - Epoch(train) [14][ 800/1567] lr: 5.8582e-03 eta: 0:10:02 time: 0.1459 data_time: 0.0074 memory: 1461 loss: 0.0171 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0171 2022/12/20 18:24:11 - mmengine - INFO - Epoch(train) [14][ 900/1567] lr: 5.5675e-03 eta: 0:09:46 time: 0.1559 data_time: 0.0076 memory: 1461 loss: 0.0158 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0158 2022/12/20 18:24:25 - mmengine - INFO - Epoch(train) [14][1000/1567] lr: 5.2836e-03 eta: 0:09:30 time: 0.1183 data_time: 0.0076 memory: 1461 loss: 0.0143 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0143 2022/12/20 18:24:41 - mmengine - INFO - Epoch(train) [14][1100/1567] lr: 5.0068e-03 eta: 0:09:15 time: 0.2191 data_time: 0.0075 memory: 1461 loss: 0.0124 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0124 2022/12/20 18:24:55 - mmengine - INFO - Epoch(train) [14][1200/1567] lr: 4.7371e-03 eta: 0:09:00 time: 0.1961 data_time: 0.0077 memory: 1461 loss: 0.0228 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0228 2022/12/20 18:25:12 - mmengine - INFO - Epoch(train) [14][1300/1567] lr: 4.4745e-03 eta: 0:08:44 time: 0.1706 data_time: 0.0074 memory: 1461 loss: 0.0221 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0221 2022/12/20 18:25:28 - mmengine - INFO - Epoch(train) [14][1400/1567] lr: 4.2190e-03 eta: 0:08:29 time: 0.2069 data_time: 0.0071 memory: 1461 loss: 0.0201 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0201 2022/12/20 18:25:45 - mmengine - INFO - Epoch(train) [14][1500/1567] lr: 3.9707e-03 eta: 0:08:14 time: 0.1442 data_time: 0.0074 memory: 1461 loss: 0.0148 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0148 2022/12/20 18:25:55 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 18:25:55 - mmengine - INFO - Epoch(train) [14][1567/1567] lr: 3.8084e-03 eta: 0:08:03 time: 0.1495 data_time: 0.0072 memory: 1461 loss: 0.2234 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2234 2022/12/20 18:25:55 - mmengine - INFO - Saving checkpoint at 14 epochs 2022/12/20 18:26:02 - mmengine - INFO - Epoch(val) [14][100/129] eta: 0:00:02 time: 0.0325 data_time: 0.0063 memory: 215 2022/12/20 18:26:03 - mmengine - INFO - Epoch(val) [14][129/129] acc/top1: 0.8791 acc/top5: 0.9868 acc/mean1: 0.8790 2022/12/20 18:26:03 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_13.pth is removed 2022/12/20 18:26:04 - mmengine - INFO - The best checkpoint with 0.8791 acc/top1 at 14 epoch is saved to best_acc/top1_epoch_14.pth. 2022/12/20 18:26:15 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 18:26:21 - mmengine - INFO - Epoch(train) [15][ 100/1567] lr: 3.5722e-03 eta: 0:07:48 time: 0.1722 data_time: 0.0074 memory: 1461 loss: 0.0170 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0170 2022/12/20 18:26:36 - mmengine - INFO - Epoch(train) [15][ 200/1567] lr: 3.3433e-03 eta: 0:07:33 time: 0.1790 data_time: 0.0069 memory: 1461 loss: 0.0139 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0139 2022/12/20 18:26:52 - mmengine - INFO - Epoch(train) [15][ 300/1567] lr: 3.1217e-03 eta: 0:07:17 time: 0.1593 data_time: 0.0075 memory: 1461 loss: 0.0217 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0217 2022/12/20 18:27:08 - mmengine - INFO - Epoch(train) [15][ 400/1567] lr: 2.9075e-03 eta: 0:07:02 time: 0.1580 data_time: 0.0074 memory: 1461 loss: 0.0179 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0179 2022/12/20 18:27:25 - mmengine - INFO - Epoch(train) [15][ 500/1567] lr: 2.7007e-03 eta: 0:06:47 time: 0.1531 data_time: 0.0079 memory: 1461 loss: 0.0148 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0148 2022/12/20 18:27:39 - mmengine - INFO - Epoch(train) [15][ 600/1567] lr: 2.5013e-03 eta: 0:06:31 time: 0.1333 data_time: 0.0078 memory: 1461 loss: 0.0173 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0173 2022/12/20 18:27:57 - mmengine - INFO - Epoch(train) [15][ 700/1567] lr: 2.3093e-03 eta: 0:06:16 time: 0.1666 data_time: 0.0067 memory: 1461 loss: 0.0118 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0118 2022/12/20 18:28:12 - mmengine - INFO - Epoch(train) [15][ 800/1567] lr: 2.1249e-03 eta: 0:06:00 time: 0.1402 data_time: 0.0071 memory: 1461 loss: 0.0219 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0219 2022/12/20 18:28:28 - mmengine - INFO - Epoch(train) [15][ 900/1567] lr: 1.9479e-03 eta: 0:05:45 time: 0.1545 data_time: 0.0066 memory: 1461 loss: 0.0083 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0083 2022/12/20 18:28:43 - mmengine - INFO - Epoch(train) [15][1000/1567] lr: 1.7785e-03 eta: 0:05:29 time: 0.1348 data_time: 0.0071 memory: 1461 loss: 0.0097 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0097 2022/12/20 18:28:51 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 18:28:55 - mmengine - INFO - Epoch(train) [15][1100/1567] lr: 1.6167e-03 eta: 0:05:14 time: 0.0818 data_time: 0.0077 memory: 1461 loss: 0.0144 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0144 2022/12/20 18:29:09 - mmengine - INFO - Epoch(train) [15][1200/1567] lr: 1.4625e-03 eta: 0:04:58 time: 0.1858 data_time: 0.0071 memory: 1461 loss: 0.0158 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0158 2022/12/20 18:29:23 - mmengine - INFO - Epoch(train) [15][1300/1567] lr: 1.3159e-03 eta: 0:04:43 time: 0.1377 data_time: 0.0079 memory: 1461 loss: 0.0091 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0091 2022/12/20 18:29:38 - mmengine - INFO - Epoch(train) [15][1400/1567] lr: 1.1769e-03 eta: 0:04:27 time: 0.1857 data_time: 0.0073 memory: 1461 loss: 0.0131 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0131 2022/12/20 18:29:52 - mmengine - INFO - Epoch(train) [15][1500/1567] lr: 1.0456e-03 eta: 0:04:12 time: 0.1233 data_time: 0.0075 memory: 1461 loss: 0.0197 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0197 2022/12/20 18:30:02 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 18:30:02 - mmengine - INFO - Epoch(train) [15][1567/1567] lr: 9.6196e-04 eta: 0:04:01 time: 0.1871 data_time: 0.0070 memory: 1461 loss: 0.1955 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.1955 2022/12/20 18:30:02 - mmengine - INFO - Saving checkpoint at 15 epochs 2022/12/20 18:30:08 - mmengine - INFO - Epoch(val) [15][100/129] eta: 0:00:01 time: 0.0310 data_time: 0.0071 memory: 215 2022/12/20 18:30:12 - mmengine - INFO - Epoch(val) [15][129/129] acc/top1: 0.8809 acc/top5: 0.9868 acc/mean1: 0.8809 2022/12/20 18:30:12 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_14.pth is removed 2022/12/20 18:30:13 - mmengine - INFO - The best checkpoint with 0.8809 acc/top1 at 15 epoch is saved to best_acc/top1_epoch_15.pth. 2022/12/20 18:30:27 - mmengine - INFO - Epoch(train) [16][ 100/1567] lr: 8.4351e-04 eta: 0:03:46 time: 0.0868 data_time: 0.0069 memory: 1461 loss: 0.0158 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0158 2022/12/20 18:30:43 - mmengine - INFO - Epoch(train) [16][ 200/1567] lr: 7.3277e-04 eta: 0:03:30 time: 0.1634 data_time: 0.0078 memory: 1461 loss: 0.0096 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0096 2022/12/20 18:30:57 - mmengine - INFO - Epoch(train) [16][ 300/1567] lr: 6.2978e-04 eta: 0:03:15 time: 0.1225 data_time: 0.0073 memory: 1461 loss: 0.0120 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0120 2022/12/20 18:31:12 - mmengine - INFO - Epoch(train) [16][ 400/1567] lr: 5.3453e-04 eta: 0:02:59 time: 0.1399 data_time: 0.0073 memory: 1461 loss: 0.0096 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0096 2022/12/20 18:31:27 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 18:31:27 - mmengine - INFO - Epoch(train) [16][ 500/1567] lr: 4.4705e-04 eta: 0:02:44 time: 0.1461 data_time: 0.0076 memory: 1461 loss: 0.0088 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0088 2022/12/20 18:31:42 - mmengine - INFO - Epoch(train) [16][ 600/1567] lr: 3.6735e-04 eta: 0:02:28 time: 0.1524 data_time: 0.0068 memory: 1461 loss: 0.0083 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0083 2022/12/20 18:31:56 - mmengine - INFO - Epoch(train) [16][ 700/1567] lr: 2.9544e-04 eta: 0:02:13 time: 0.1465 data_time: 0.0067 memory: 1461 loss: 0.0118 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0118 2022/12/20 18:32:10 - mmengine - INFO - Epoch(train) [16][ 800/1567] lr: 2.3134e-04 eta: 0:01:58 time: 0.1304 data_time: 0.0069 memory: 1461 loss: 0.0074 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0074 2022/12/20 18:32:23 - mmengine - INFO - Epoch(train) [16][ 900/1567] lr: 1.7505e-04 eta: 0:01:42 time: 0.1193 data_time: 0.0067 memory: 1461 loss: 0.0211 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0211 2022/12/20 18:32:36 - mmengine - INFO - Epoch(train) [16][1000/1567] lr: 1.2658e-04 eta: 0:01:27 time: 0.1385 data_time: 0.0087 memory: 1461 loss: 0.0089 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0089 2022/12/20 18:32:53 - mmengine - INFO - Epoch(train) [16][1100/1567] lr: 8.5947e-05 eta: 0:01:11 time: 0.1585 data_time: 0.0073 memory: 1461 loss: 0.0129 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0129 2022/12/20 18:33:09 - mmengine - INFO - Epoch(train) [16][1200/1567] lr: 5.3147e-05 eta: 0:00:56 time: 0.1604 data_time: 0.0076 memory: 1461 loss: 0.0055 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0055 2022/12/20 18:33:26 - mmengine - INFO - Epoch(train) [16][1300/1567] lr: 2.8190e-05 eta: 0:00:41 time: 0.1572 data_time: 0.0078 memory: 1461 loss: 0.0094 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0094 2022/12/20 18:33:42 - mmengine - INFO - Epoch(train) [16][1400/1567] lr: 1.1078e-05 eta: 0:00:25 time: 0.1389 data_time: 0.0077 memory: 1461 loss: 0.0085 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0085 2022/12/20 18:33:58 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 18:33:58 - mmengine - INFO - Epoch(train) [16][1500/1567] lr: 1.8150e-06 eta: 0:00:10 time: 0.1711 data_time: 0.0078 memory: 1461 loss: 0.0075 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0075 2022/12/20 18:34:09 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_172637 2022/12/20 18:34:09 - mmengine - INFO - Epoch(train) [16][1567/1567] lr: 3.9252e-10 eta: 0:00:00 time: 0.1525 data_time: 0.0069 memory: 1461 loss: 0.2142 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2142 2022/12/20 18:34:09 - mmengine - INFO - Saving checkpoint at 16 epochs 2022/12/20 18:34:14 - mmengine - INFO - Epoch(val) [16][100/129] eta: 0:00:01 time: 0.0530 data_time: 0.0068 memory: 215 2022/12/20 18:34:16 - mmengine - INFO - Epoch(val) [16][129/129] acc/top1: 0.8808 acc/top5: 0.9868 acc/mean1: 0.8807