2022/12/20 16:17:56 - 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: 1717983500 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 16:17:56 - 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=['jm']), dict(type='UniformSampleFrames', clip_len=100), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ] val_pipeline = [ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['jm']), dict( type='UniformSampleFrames', clip_len=100, num_clips=1, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ] test_pipeline = [ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['jm']), dict( type='UniformSampleFrames', clip_len=100, num_clips=10, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ] train_dataloader = dict( batch_size=16, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=True), dataset=dict( type='RepeatDataset', times=5, dataset=dict( type='PoseDataset', ann_file='data/skeleton/ntu60_2d.pkl', pipeline=[ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['jm']), dict(type='UniformSampleFrames', clip_len=100), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ], split='xsub_train'))) val_dataloader = dict( batch_size=16, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='PoseDataset', ann_file='data/skeleton/ntu60_2d.pkl', pipeline=[ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['jm']), dict( type='UniformSampleFrames', clip_len=100, num_clips=1, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ], split='xsub_val', test_mode=True)) test_dataloader = dict( batch_size=1, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='PoseDataset', ann_file='data/skeleton/ntu60_2d.pkl', pipeline=[ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['jm']), dict( type='UniformSampleFrames', clip_len=100, num_clips=10, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ], split='xsub_val', test_mode=True)) val_evaluator = [dict(type='AccMetric')] test_evaluator = [dict(type='AccMetric')] train_cfg = dict( type='EpochBasedTrainLoop', max_epochs=16, val_begin=1, val_interval=1) val_cfg = dict(type='ValLoop') test_cfg = dict(type='TestLoop') param_scheduler = [ dict( type='CosineAnnealingLR', eta_min=0, T_max=16, by_epoch=True, convert_to_iter_based=True) ] optim_wrapper = dict( optimizer=dict( type='SGD', lr=0.1, momentum=0.9, weight_decay=0.0005, nesterov=True)) auto_scale_lr = dict(enable=False, base_batch_size=128) launcher = 'pytorch' work_dir = './work_dirs/2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d' randomness = dict(seed=None, diff_rank_seed=False, deterministic=False) 2022/12/20 16:17:56 - mmengine - INFO - Result has been saved to /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d/modules_statistic_results.json 2022/12/20 16:17:56 - mmengine - INFO - Hooks will be executed in the following order: before_run: (VERY_HIGH ) RuntimeInfoHook (BELOW_NORMAL) LoggerHook -------------------- before_train: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (VERY_LOW ) CheckpointHook -------------------- before_train_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (NORMAL ) DistSamplerSeedHook -------------------- before_train_iter: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook -------------------- after_train_iter: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- after_train_epoch: (NORMAL ) IterTimerHook (NORMAL ) SyncBuffersHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- before_val_epoch: (NORMAL ) IterTimerHook -------------------- before_val_iter: (NORMAL ) IterTimerHook -------------------- after_val_iter: (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook -------------------- after_val_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook (VERY_LOW ) CheckpointHook -------------------- before_test_epoch: (NORMAL ) IterTimerHook -------------------- before_test_iter: (NORMAL ) IterTimerHook -------------------- after_test_iter: (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook -------------------- after_test_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook -------------------- after_run: (BELOW_NORMAL) LoggerHook -------------------- Name of parameter - Initialization information backbone.data_bn.weight - torch.Size([102]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.data_bn.bias - torch.Size([102]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.conv_d.0.weight - torch.Size([64, 3, 1, 1]): ConvBranchInit backbone.gcn.0.gcn.conv_d.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_d.1.weight - torch.Size([64, 3, 1, 1]): ConvBranchInit backbone.gcn.0.gcn.conv_d.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_d.2.weight - torch.Size([64, 3, 1, 1]): ConvBranchInit backbone.gcn.0.gcn.conv_d.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_a.0.weight - torch.Size([16, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_a.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_a.1.weight - torch.Size([16, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_a.1.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_a.2.weight - torch.Size([16, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_a.2.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_b.0.weight - torch.Size([16, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_b.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_b.1.weight - torch.Size([16, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_b.1.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_b.2.weight - torch.Size([16, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_b.2.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.down.0.weight - torch.Size([64, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.down.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.down.1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.down.1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.bn.weight - torch.Size([64]): ConstantInit: val=1e-06, bias=0 backbone.gcn.0.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.conv.weight - torch.Size([64, 64, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.tcn.conv.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.gcn.conv_d.0.weight - torch.Size([64, 64, 1, 1]): ConvBranchInit backbone.gcn.1.gcn.conv_d.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_d.1.weight - torch.Size([64, 64, 1, 1]): ConvBranchInit backbone.gcn.1.gcn.conv_d.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_d.2.weight - torch.Size([64, 64, 1, 1]): ConvBranchInit backbone.gcn.1.gcn.conv_d.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_a.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_a.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_a.1.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_a.1.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_a.2.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_a.2.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_b.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_b.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_b.1.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_b.1.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_b.2.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_b.2.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.bn.weight - torch.Size([64]): ConstantInit: val=1e-06, bias=0 backbone.gcn.1.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.conv.weight - torch.Size([64, 64, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.tcn.conv.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.gcn.conv_d.0.weight - torch.Size([64, 64, 1, 1]): ConvBranchInit backbone.gcn.2.gcn.conv_d.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_d.1.weight - torch.Size([64, 64, 1, 1]): ConvBranchInit backbone.gcn.2.gcn.conv_d.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_d.2.weight - torch.Size([64, 64, 1, 1]): ConvBranchInit backbone.gcn.2.gcn.conv_d.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_a.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_a.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_a.1.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_a.1.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_a.2.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_a.2.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_b.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_b.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_b.1.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_b.1.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_b.2.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_b.2.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.bn.weight - torch.Size([64]): ConstantInit: val=1e-06, bias=0 backbone.gcn.2.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.conv.weight - torch.Size([64, 64, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.tcn.conv.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.gcn.conv_d.0.weight - torch.Size([64, 64, 1, 1]): ConvBranchInit backbone.gcn.3.gcn.conv_d.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_d.1.weight - torch.Size([64, 64, 1, 1]): ConvBranchInit backbone.gcn.3.gcn.conv_d.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_d.2.weight - torch.Size([64, 64, 1, 1]): ConvBranchInit backbone.gcn.3.gcn.conv_d.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_a.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_a.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_a.1.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_a.1.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_a.2.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_a.2.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_b.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_b.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_b.1.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_b.1.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_b.2.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_b.2.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.bn.weight - torch.Size([64]): ConstantInit: val=1e-06, bias=0 backbone.gcn.3.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.conv.weight - torch.Size([64, 64, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.tcn.conv.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.conv_d.0.weight - torch.Size([128, 64, 1, 1]): ConvBranchInit backbone.gcn.4.gcn.conv_d.0.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_d.1.weight - torch.Size([128, 64, 1, 1]): ConvBranchInit backbone.gcn.4.gcn.conv_d.1.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_d.2.weight - torch.Size([128, 64, 1, 1]): ConvBranchInit backbone.gcn.4.gcn.conv_d.2.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_a.0.weight - torch.Size([32, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_a.0.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_a.1.weight - torch.Size([32, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_a.1.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_a.2.weight - torch.Size([32, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_a.2.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_b.0.weight - torch.Size([32, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_b.0.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_b.1.weight - torch.Size([32, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_b.1.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_b.2.weight - torch.Size([32, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_b.2.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.down.0.weight - torch.Size([128, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.down.0.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.down.1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.down.1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.bn.weight - torch.Size([128]): ConstantInit: val=1e-06, bias=0 backbone.gcn.4.gcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.conv.weight - torch.Size([128, 128, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.tcn.conv.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.tcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.residual.conv.weight - torch.Size([128, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.residual.conv.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.residual.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.residual.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.gcn.conv_d.0.weight - torch.Size([128, 128, 1, 1]): ConvBranchInit backbone.gcn.5.gcn.conv_d.0.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_d.1.weight - torch.Size([128, 128, 1, 1]): ConvBranchInit backbone.gcn.5.gcn.conv_d.1.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_d.2.weight - torch.Size([128, 128, 1, 1]): ConvBranchInit backbone.gcn.5.gcn.conv_d.2.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_a.0.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_a.0.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_a.1.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_a.1.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_a.2.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_a.2.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_b.0.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_b.0.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_b.1.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_b.1.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_b.2.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_b.2.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.bn.weight - torch.Size([128]): ConstantInit: val=1e-06, bias=0 backbone.gcn.5.gcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.conv.weight - torch.Size([128, 128, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.tcn.conv.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.tcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.gcn.conv_d.0.weight - torch.Size([128, 128, 1, 1]): ConvBranchInit backbone.gcn.6.gcn.conv_d.0.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_d.1.weight - torch.Size([128, 128, 1, 1]): ConvBranchInit backbone.gcn.6.gcn.conv_d.1.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_d.2.weight - torch.Size([128, 128, 1, 1]): ConvBranchInit backbone.gcn.6.gcn.conv_d.2.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_a.0.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_a.0.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_a.1.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_a.1.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_a.2.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_a.2.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_b.0.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_b.0.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_b.1.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_b.1.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_b.2.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_b.2.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.bn.weight - torch.Size([128]): ConstantInit: val=1e-06, bias=0 backbone.gcn.6.gcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.conv.weight - torch.Size([128, 128, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.tcn.conv.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.tcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.conv_d.0.weight - torch.Size([256, 128, 1, 1]): ConvBranchInit backbone.gcn.7.gcn.conv_d.0.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_d.1.weight - torch.Size([256, 128, 1, 1]): ConvBranchInit backbone.gcn.7.gcn.conv_d.1.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_d.2.weight - torch.Size([256, 128, 1, 1]): ConvBranchInit backbone.gcn.7.gcn.conv_d.2.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_a.0.weight - torch.Size([64, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_a.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_a.1.weight - torch.Size([64, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_a.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_a.2.weight - torch.Size([64, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_a.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_b.0.weight - torch.Size([64, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_b.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_b.1.weight - torch.Size([64, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_b.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_b.2.weight - torch.Size([64, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_b.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.down.0.weight - torch.Size([256, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.down.0.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.down.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.down.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.bn.weight - torch.Size([256]): ConstantInit: val=1e-06, bias=0 backbone.gcn.7.gcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.conv.weight - torch.Size([256, 256, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.tcn.conv.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.tcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.residual.conv.weight - torch.Size([256, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.residual.conv.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.residual.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.residual.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.gcn.conv_d.0.weight - torch.Size([256, 256, 1, 1]): ConvBranchInit backbone.gcn.8.gcn.conv_d.0.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_d.1.weight - torch.Size([256, 256, 1, 1]): ConvBranchInit backbone.gcn.8.gcn.conv_d.1.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_d.2.weight - torch.Size([256, 256, 1, 1]): ConvBranchInit backbone.gcn.8.gcn.conv_d.2.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_a.0.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_a.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_a.1.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_a.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_a.2.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_a.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_b.0.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_b.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_b.1.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_b.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_b.2.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_b.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.bn.weight - torch.Size([256]): ConstantInit: val=1e-06, bias=0 backbone.gcn.8.gcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.conv.weight - torch.Size([256, 256, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.tcn.conv.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.tcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.gcn.conv_d.0.weight - torch.Size([256, 256, 1, 1]): ConvBranchInit backbone.gcn.9.gcn.conv_d.0.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_d.1.weight - torch.Size([256, 256, 1, 1]): ConvBranchInit backbone.gcn.9.gcn.conv_d.1.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_d.2.weight - torch.Size([256, 256, 1, 1]): ConvBranchInit backbone.gcn.9.gcn.conv_d.2.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_a.0.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_a.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_a.1.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_a.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_a.2.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_a.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_b.0.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_b.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_b.1.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_b.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_b.2.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_b.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.bn.weight - torch.Size([256]): ConstantInit: val=1e-06, bias=0 backbone.gcn.9.gcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.conv.weight - torch.Size([256, 256, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.tcn.conv.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.tcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN cls_head.fc.weight - torch.Size([60, 256]): NormalInit: mean=0, std=0.01, bias=0 cls_head.fc.bias - torch.Size([60]): NormalInit: mean=0, std=0.01, bias=0 2022/12/20 16:18:36 - mmengine - INFO - Checkpoints will be saved to /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d. 2022/12/20 16:18:55 - mmengine - INFO - Epoch(train) [1][ 100/1567] lr: 9.9996e-02 eta: 1:18:14 time: 0.1585 data_time: 0.0077 memory: 1461 loss: 2.9824 top1_acc: 0.1250 top5_acc: 0.4375 loss_cls: 2.9824 2022/12/20 16:19:09 - mmengine - INFO - Epoch(train) [1][ 200/1567] lr: 9.9984e-02 eta: 1:07:40 time: 0.1545 data_time: 0.0072 memory: 1461 loss: 2.2540 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.2540 2022/12/20 16:19:24 - mmengine - INFO - Epoch(train) [1][ 300/1567] lr: 9.9965e-02 eta: 1:06:00 time: 0.1456 data_time: 0.0078 memory: 1461 loss: 1.6355 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.6355 2022/12/20 16:19:38 - mmengine - INFO - Epoch(train) [1][ 400/1567] lr: 9.9938e-02 eta: 1:03:27 time: 0.1382 data_time: 0.0069 memory: 1461 loss: 1.2620 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.2620 2022/12/20 16:19:51 - mmengine - INFO - Epoch(train) [1][ 500/1567] lr: 9.9902e-02 eta: 1:00:41 time: 0.1958 data_time: 0.0077 memory: 1461 loss: 1.3041 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.3041 2022/12/20 16:20:07 - mmengine - INFO - Epoch(train) [1][ 600/1567] lr: 9.9859e-02 eta: 1:01:49 time: 0.1649 data_time: 0.0067 memory: 1461 loss: 1.0476 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.0476 2022/12/20 16:20:23 - mmengine - INFO - Epoch(train) [1][ 700/1567] lr: 9.9808e-02 eta: 1:01:43 time: 0.1817 data_time: 0.0072 memory: 1461 loss: 0.9754 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9754 2022/12/20 16:20:40 - mmengine - INFO - Epoch(train) [1][ 800/1567] lr: 9.9750e-02 eta: 1:02:33 time: 0.1753 data_time: 0.0069 memory: 1461 loss: 0.8549 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.8549 2022/12/20 16:20:54 - mmengine - INFO - Epoch(train) [1][ 900/1567] lr: 9.9683e-02 eta: 1:01:46 time: 0.1297 data_time: 0.0067 memory: 1461 loss: 0.8647 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 0.8647 2022/12/20 16:21:11 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 16:21:11 - mmengine - INFO - Epoch(train) [1][1000/1567] lr: 9.9609e-02 eta: 1:02:04 time: 0.1602 data_time: 0.0069 memory: 1461 loss: 0.6588 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.6588 2022/12/20 16:21:27 - mmengine - INFO - Epoch(train) [1][1100/1567] lr: 9.9527e-02 eta: 1:01:54 time: 0.1595 data_time: 0.0072 memory: 1461 loss: 0.7457 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.7457 2022/12/20 16:21:43 - mmengine - INFO - Epoch(train) [1][1200/1567] lr: 9.9437e-02 eta: 1:01:52 time: 0.1578 data_time: 0.0065 memory: 1461 loss: 0.7429 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.7429 2022/12/20 16:21:59 - mmengine - INFO - Epoch(train) [1][1300/1567] lr: 9.9339e-02 eta: 1:01:45 time: 0.1699 data_time: 0.0070 memory: 1461 loss: 0.7039 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.7039 2022/12/20 16:22:16 - mmengine - INFO - Epoch(train) [1][1400/1567] lr: 9.9234e-02 eta: 1:01:46 time: 0.1614 data_time: 0.0068 memory: 1461 loss: 0.5699 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.5699 2022/12/20 16:22:31 - mmengine - INFO - Epoch(train) [1][1500/1567] lr: 9.9121e-02 eta: 1:01:29 time: 0.1489 data_time: 0.0069 memory: 1461 loss: 0.6255 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.6255 2022/12/20 16:22:42 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 16:22:42 - mmengine - INFO - Epoch(train) [1][1567/1567] lr: 9.9040e-02 eta: 1:01:26 time: 0.2217 data_time: 0.0066 memory: 1461 loss: 0.5519 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.5519 2022/12/20 16:22:42 - mmengine - INFO - Saving checkpoint at 1 epochs 2022/12/20 16:22:48 - mmengine - INFO - Epoch(val) [1][100/129] eta: 0:00:01 time: 0.0952 data_time: 0.0060 memory: 215 2022/12/20 16:22:54 - mmengine - INFO - Epoch(val) [1][129/129] acc/top1: 0.5957 acc/top5: 0.9314 acc/mean1: 0.5956 2022/12/20 16:22:55 - mmengine - INFO - The best checkpoint with 0.5957 acc/top1 at 1 epoch is saved to best_acc/top1_epoch_1.pth. 2022/12/20 16:23:09 - mmengine - INFO - Epoch(train) [2][ 100/1567] lr: 9.8914e-02 eta: 1:00:51 time: 0.1394 data_time: 0.0077 memory: 1461 loss: 0.5641 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5641 2022/12/20 16:23:26 - mmengine - INFO - Epoch(train) [2][ 200/1567] lr: 9.8781e-02 eta: 1:00:45 time: 0.1621 data_time: 0.0064 memory: 1461 loss: 0.5739 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.5739 2022/12/20 16:23:40 - mmengine - INFO - Epoch(train) [2][ 300/1567] lr: 9.8639e-02 eta: 1:00:09 time: 0.1475 data_time: 0.0073 memory: 1461 loss: 0.6381 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.6381 2022/12/20 16:23:55 - mmengine - INFO - Epoch(train) [2][ 400/1567] lr: 9.8491e-02 eta: 0:59:57 time: 0.2221 data_time: 0.0081 memory: 1461 loss: 0.6090 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.6090 2022/12/20 16:24:01 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 16:24:11 - mmengine - INFO - Epoch(train) [2][ 500/1567] lr: 9.8334e-02 eta: 0:59:42 time: 0.1875 data_time: 0.0077 memory: 1461 loss: 0.4417 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4417 2022/12/20 16:24:27 - mmengine - INFO - Epoch(train) [2][ 600/1567] lr: 9.8170e-02 eta: 0:59:32 time: 0.1325 data_time: 0.0072 memory: 1461 loss: 0.4449 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4449 2022/12/20 16:24:43 - mmengine - INFO - Epoch(train) [2][ 700/1567] lr: 9.7998e-02 eta: 0:59:16 time: 0.1834 data_time: 0.0066 memory: 1461 loss: 0.4295 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4295 2022/12/20 16:25:00 - mmengine - INFO - Epoch(train) [2][ 800/1567] lr: 9.7819e-02 eta: 0:59:11 time: 0.1594 data_time: 0.0073 memory: 1461 loss: 0.4575 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4575 2022/12/20 16:25:15 - mmengine - INFO - Epoch(train) [2][ 900/1567] lr: 9.7632e-02 eta: 0:58:52 time: 0.1912 data_time: 0.0074 memory: 1461 loss: 0.4981 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4981 2022/12/20 16:25:32 - mmengine - INFO - Epoch(train) [2][1000/1567] lr: 9.7438e-02 eta: 0:58:48 time: 0.1839 data_time: 0.0067 memory: 1461 loss: 0.4104 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4104 2022/12/20 16:25:46 - mmengine - INFO - Epoch(train) [2][1100/1567] lr: 9.7236e-02 eta: 0:58:20 time: 0.1268 data_time: 0.0070 memory: 1461 loss: 0.3913 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3913 2022/12/20 16:26:03 - mmengine - INFO - Epoch(train) [2][1200/1567] lr: 9.7027e-02 eta: 0:58:16 time: 0.1557 data_time: 0.0064 memory: 1461 loss: 0.3916 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3916 2022/12/20 16:26:19 - mmengine - INFO - Epoch(train) [2][1300/1567] lr: 9.6810e-02 eta: 0:58:01 time: 0.1508 data_time: 0.0066 memory: 1461 loss: 0.4997 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4997 2022/12/20 16:26:35 - mmengine - INFO - Epoch(train) [2][1400/1567] lr: 9.6587e-02 eta: 0:57:52 time: 0.1599 data_time: 0.0068 memory: 1461 loss: 0.4724 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4724 2022/12/20 16:26:41 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 16:26:51 - mmengine - INFO - Epoch(train) [2][1500/1567] lr: 9.6355e-02 eta: 0:57:35 time: 0.1398 data_time: 0.0066 memory: 1461 loss: 0.4028 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4028 2022/12/20 16:27:02 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 16:27:02 - mmengine - INFO - Epoch(train) [2][1567/1567] lr: 9.6196e-02 eta: 0:57:27 time: 0.1642 data_time: 0.0072 memory: 1461 loss: 0.7081 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.7081 2022/12/20 16:27:02 - mmengine - INFO - Saving checkpoint at 2 epochs 2022/12/20 16:27:06 - mmengine - INFO - Epoch(val) [2][100/129] eta: 0:00:00 time: 0.0400 data_time: 0.0065 memory: 215 2022/12/20 16:27:12 - mmengine - INFO - Epoch(val) [2][129/129] acc/top1: 0.7584 acc/top5: 0.9628 acc/mean1: 0.7582 2022/12/20 16:27:12 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_1.pth is removed 2022/12/20 16:27:13 - mmengine - INFO - The best checkpoint with 0.7584 acc/top1 at 2 epoch is saved to best_acc/top1_epoch_2.pth. 2022/12/20 16:27:28 - mmengine - INFO - Epoch(train) [3][ 100/1567] lr: 9.5953e-02 eta: 0:57:05 time: 0.1429 data_time: 0.0071 memory: 1461 loss: 0.3839 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3839 2022/12/20 16:27:44 - mmengine - INFO - Epoch(train) [3][ 200/1567] lr: 9.5703e-02 eta: 0:56:52 time: 0.1580 data_time: 0.0070 memory: 1461 loss: 0.3865 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3865 2022/12/20 16:27:58 - mmengine - INFO - Epoch(train) [3][ 300/1567] lr: 9.5445e-02 eta: 0:56:26 time: 0.1226 data_time: 0.0085 memory: 1461 loss: 0.4538 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4538 2022/12/20 16:28:11 - mmengine - INFO - Epoch(train) [3][ 400/1567] lr: 9.5180e-02 eta: 0:55:54 time: 0.0991 data_time: 0.0070 memory: 1461 loss: 0.3621 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3621 2022/12/20 16:28:27 - mmengine - INFO - Epoch(train) [3][ 500/1567] lr: 9.4908e-02 eta: 0:55:46 time: 0.1651 data_time: 0.0068 memory: 1461 loss: 0.3912 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3912 2022/12/20 16:28:42 - mmengine - INFO - Epoch(train) [3][ 600/1567] lr: 9.4629e-02 eta: 0:55:26 time: 0.1526 data_time: 0.0093 memory: 1461 loss: 0.3860 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3860 2022/12/20 16:28:59 - mmengine - INFO - Epoch(train) [3][ 700/1567] lr: 9.4343e-02 eta: 0:55:16 time: 0.1621 data_time: 0.0067 memory: 1461 loss: 0.3972 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3972 2022/12/20 16:29:14 - mmengine - INFO - Epoch(train) [3][ 800/1567] lr: 9.4050e-02 eta: 0:54:59 time: 0.1287 data_time: 0.0069 memory: 1461 loss: 0.3476 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3476 2022/12/20 16:29:25 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 16:29:31 - mmengine - INFO - Epoch(train) [3][ 900/1567] lr: 9.3750e-02 eta: 0:54:48 time: 0.1463 data_time: 0.0073 memory: 1461 loss: 0.4308 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.4308 2022/12/20 16:29:46 - mmengine - INFO - Epoch(train) [3][1000/1567] lr: 9.3444e-02 eta: 0:54:30 time: 0.1564 data_time: 0.0068 memory: 1461 loss: 0.3039 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3039 2022/12/20 16:30:02 - mmengine - INFO - Epoch(train) [3][1100/1567] lr: 9.3130e-02 eta: 0:54:18 time: 0.1572 data_time: 0.0072 memory: 1461 loss: 0.4917 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4917 2022/12/20 16:30:17 - mmengine - INFO - Epoch(train) [3][1200/1567] lr: 9.2810e-02 eta: 0:54:00 time: 0.1446 data_time: 0.0070 memory: 1461 loss: 0.4191 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4191 2022/12/20 16:30:34 - mmengine - INFO - Epoch(train) [3][1300/1567] lr: 9.2483e-02 eta: 0:53:47 time: 0.1697 data_time: 0.0067 memory: 1461 loss: 0.2960 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2960 2022/12/20 16:30:49 - mmengine - INFO - Epoch(train) [3][1400/1567] lr: 9.2149e-02 eta: 0:53:32 time: 0.1553 data_time: 0.0065 memory: 1461 loss: 0.3741 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.3741 2022/12/20 16:31:06 - mmengine - INFO - Epoch(train) [3][1500/1567] lr: 9.1809e-02 eta: 0:53:21 time: 0.2177 data_time: 0.0065 memory: 1461 loss: 0.3806 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.3806 2022/12/20 16:31:16 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 16:31:16 - mmengine - INFO - Epoch(train) [3][1567/1567] lr: 9.1577e-02 eta: 0:53:07 time: 0.1405 data_time: 0.0071 memory: 1461 loss: 0.5623 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.5623 2022/12/20 16:31:16 - mmengine - INFO - Saving checkpoint at 3 epochs 2022/12/20 16:31:21 - mmengine - INFO - Epoch(val) [3][100/129] eta: 0:00:01 time: 0.0512 data_time: 0.0063 memory: 215 2022/12/20 16:31:25 - mmengine - INFO - Epoch(val) [3][129/129] acc/top1: 0.7519 acc/top5: 0.9598 acc/mean1: 0.7518 2022/12/20 16:31:40 - mmengine - INFO - Epoch(train) [4][ 100/1567] lr: 9.1226e-02 eta: 0:52:49 time: 0.1228 data_time: 0.0084 memory: 1461 loss: 0.2808 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2808 2022/12/20 16:31:54 - mmengine - INFO - Epoch(train) [4][ 200/1567] lr: 9.0868e-02 eta: 0:52:27 time: 0.1231 data_time: 0.0077 memory: 1461 loss: 0.3101 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3101 2022/12/20 16:32:07 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 16:32:07 - mmengine - INFO - Epoch(train) [4][ 300/1567] lr: 9.0504e-02 eta: 0:51:59 time: 0.0955 data_time: 0.0070 memory: 1461 loss: 0.3016 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3016 2022/12/20 16:32:24 - mmengine - INFO - Epoch(train) [4][ 400/1567] lr: 9.0133e-02 eta: 0:51:51 time: 0.1565 data_time: 0.0073 memory: 1461 loss: 0.3535 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3535 2022/12/20 16:32:40 - mmengine - INFO - Epoch(train) [4][ 500/1567] lr: 8.9756e-02 eta: 0:51:36 time: 0.1583 data_time: 0.0064 memory: 1461 loss: 0.2661 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2661 2022/12/20 16:32:57 - mmengine - INFO - Epoch(train) [4][ 600/1567] lr: 8.9373e-02 eta: 0:51:24 time: 0.1651 data_time: 0.0080 memory: 1461 loss: 0.2986 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2986 2022/12/20 16:33:13 - mmengine - INFO - Epoch(train) [4][ 700/1567] lr: 8.8984e-02 eta: 0:51:10 time: 0.1586 data_time: 0.0067 memory: 1461 loss: 0.2553 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2553 2022/12/20 16:33:29 - mmengine - INFO - Epoch(train) [4][ 800/1567] lr: 8.8589e-02 eta: 0:50:57 time: 0.2049 data_time: 0.0066 memory: 1461 loss: 0.2928 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2928 2022/12/20 16:33:46 - mmengine - INFO - Epoch(train) [4][ 900/1567] lr: 8.8187e-02 eta: 0:50:45 time: 0.1715 data_time: 0.0082 memory: 1461 loss: 0.3488 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3488 2022/12/20 16:34:01 - mmengine - INFO - Epoch(train) [4][1000/1567] lr: 8.7780e-02 eta: 0:50:28 time: 0.1518 data_time: 0.0076 memory: 1461 loss: 0.3646 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.3646 2022/12/20 16:34:18 - mmengine - INFO - Epoch(train) [4][1100/1567] lr: 8.7367e-02 eta: 0:50:18 time: 0.1616 data_time: 0.0066 memory: 1461 loss: 0.2526 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2526 2022/12/20 16:34:34 - mmengine - INFO - Epoch(train) [4][1200/1567] lr: 8.6947e-02 eta: 0:50:01 time: 0.1323 data_time: 0.0068 memory: 1461 loss: 0.2775 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2775 2022/12/20 16:34:50 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 16:34:51 - mmengine - INFO - Epoch(train) [4][1300/1567] lr: 8.6522e-02 eta: 0:49:50 time: 0.1595 data_time: 0.0067 memory: 1461 loss: 0.2755 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.2755 2022/12/20 16:35:06 - mmengine - INFO - Epoch(train) [4][1400/1567] lr: 8.6092e-02 eta: 0:49:35 time: 0.1467 data_time: 0.0079 memory: 1461 loss: 0.2500 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2500 2022/12/20 16:35:23 - mmengine - INFO - Epoch(train) [4][1500/1567] lr: 8.5655e-02 eta: 0:49:22 time: 0.1500 data_time: 0.0067 memory: 1461 loss: 0.3089 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3089 2022/12/20 16:35:34 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 16:35:34 - mmengine - INFO - Epoch(train) [4][1567/1567] lr: 8.5360e-02 eta: 0:49:13 time: 0.1418 data_time: 0.0069 memory: 1461 loss: 0.4737 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.4737 2022/12/20 16:35:34 - mmengine - INFO - Saving checkpoint at 4 epochs 2022/12/20 16:35:40 - mmengine - INFO - Epoch(val) [4][100/129] eta: 0:00:01 time: 0.0417 data_time: 0.0067 memory: 215 2022/12/20 16:35:44 - mmengine - INFO - Epoch(val) [4][129/129] acc/top1: 0.7844 acc/top5: 0.9697 acc/mean1: 0.7842 2022/12/20 16:35:44 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_2.pth is removed 2022/12/20 16:35:44 - mmengine - INFO - The best checkpoint with 0.7844 acc/top1 at 4 epoch is saved to best_acc/top1_epoch_4.pth. 2022/12/20 16:36:00 - mmengine - INFO - Epoch(train) [5][ 100/1567] lr: 8.4914e-02 eta: 0:48:58 time: 0.1577 data_time: 0.0079 memory: 1461 loss: 0.2884 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2884 2022/12/20 16:36:15 - mmengine - INFO - Epoch(train) [5][ 200/1567] lr: 8.4463e-02 eta: 0:48:41 time: 0.1428 data_time: 0.0078 memory: 1461 loss: 0.2882 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2882 2022/12/20 16:36:27 - mmengine - INFO - Epoch(train) [5][ 300/1567] lr: 8.4006e-02 eta: 0:48:15 time: 0.1134 data_time: 0.0083 memory: 1461 loss: 0.1742 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1742 2022/12/20 16:36:45 - mmengine - INFO - Epoch(train) [5][ 400/1567] lr: 8.3544e-02 eta: 0:48:05 time: 0.1783 data_time: 0.0066 memory: 1461 loss: 0.3204 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3204 2022/12/20 16:37:01 - mmengine - INFO - Epoch(train) [5][ 500/1567] lr: 8.3077e-02 eta: 0:47:49 time: 0.1503 data_time: 0.0077 memory: 1461 loss: 0.2086 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2086 2022/12/20 16:37:16 - mmengine - INFO - Epoch(train) [5][ 600/1567] lr: 8.2605e-02 eta: 0:47:32 time: 0.1571 data_time: 0.0066 memory: 1461 loss: 0.2461 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2461 2022/12/20 16:37:32 - mmengine - INFO - Epoch(train) [5][ 700/1567] lr: 8.2127e-02 eta: 0:47:19 time: 0.1655 data_time: 0.0069 memory: 1461 loss: 0.3213 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3213 2022/12/20 16:37:37 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 16:37:48 - mmengine - INFO - Epoch(train) [5][ 800/1567] lr: 8.1645e-02 eta: 0:47:02 time: 0.1530 data_time: 0.0069 memory: 1461 loss: 0.2864 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2864 2022/12/20 16:38:04 - mmengine - INFO - Epoch(train) [5][ 900/1567] lr: 8.1157e-02 eta: 0:46:47 time: 0.1542 data_time: 0.0074 memory: 1461 loss: 0.2630 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.2630 2022/12/20 16:38:19 - mmengine - INFO - Epoch(train) [5][1000/1567] lr: 8.0665e-02 eta: 0:46:31 time: 0.1867 data_time: 0.0077 memory: 1461 loss: 0.2579 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.2579 2022/12/20 16:38:35 - mmengine - INFO - Epoch(train) [5][1100/1567] lr: 8.0167e-02 eta: 0:46:15 time: 0.1627 data_time: 0.0072 memory: 1461 loss: 0.2718 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2718 2022/12/20 16:38:50 - mmengine - INFO - Epoch(train) [5][1200/1567] lr: 7.9665e-02 eta: 0:45:58 time: 0.1657 data_time: 0.0072 memory: 1461 loss: 0.2119 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2119 2022/12/20 16:39:07 - mmengine - INFO - Epoch(train) [5][1300/1567] lr: 7.9159e-02 eta: 0:45:45 time: 0.1601 data_time: 0.0070 memory: 1461 loss: 0.2589 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2589 2022/12/20 16:39:21 - mmengine - INFO - Epoch(train) [5][1400/1567] lr: 7.8647e-02 eta: 0:45:27 time: 0.1103 data_time: 0.0069 memory: 1461 loss: 0.2770 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2770 2022/12/20 16:39:39 - mmengine - INFO - Epoch(train) [5][1500/1567] lr: 7.8132e-02 eta: 0:45:15 time: 0.1635 data_time: 0.0071 memory: 1461 loss: 0.2379 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2379 2022/12/20 16:39:49 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 16:39:49 - mmengine - INFO - Epoch(train) [5][1567/1567] lr: 7.7784e-02 eta: 0:45:03 time: 0.1415 data_time: 0.0079 memory: 1461 loss: 0.3716 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.3716 2022/12/20 16:39:49 - mmengine - INFO - Saving checkpoint at 5 epochs 2022/12/20 16:39:53 - mmengine - INFO - Epoch(val) [5][100/129] eta: 0:00:01 time: 0.0508 data_time: 0.0068 memory: 215 2022/12/20 16:39:56 - mmengine - INFO - Epoch(val) [5][129/129] acc/top1: 0.7953 acc/top5: 0.9726 acc/mean1: 0.7952 2022/12/20 16:39:56 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_4.pth is removed 2022/12/20 16:39:56 - mmengine - INFO - The best checkpoint with 0.7953 acc/top1 at 5 epoch is saved to best_acc/top1_epoch_5.pth. 2022/12/20 16:40:11 - mmengine - INFO - Epoch(train) [6][ 100/1567] lr: 7.7261e-02 eta: 0:44:46 time: 0.1505 data_time: 0.0074 memory: 1461 loss: 0.2109 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2109 2022/12/20 16:40:20 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 16:40:25 - mmengine - INFO - Epoch(train) [6][ 200/1567] lr: 7.6733e-02 eta: 0:44:26 time: 0.1473 data_time: 0.0071 memory: 1461 loss: 0.2647 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2647 2022/12/20 16:40:40 - mmengine - INFO - Epoch(train) [6][ 300/1567] lr: 7.6202e-02 eta: 0:44:10 time: 0.1580 data_time: 0.0072 memory: 1461 loss: 0.2261 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2261 2022/12/20 16:40:57 - mmengine - INFO - Epoch(train) [6][ 400/1567] lr: 7.5666e-02 eta: 0:43:56 time: 0.1388 data_time: 0.0068 memory: 1461 loss: 0.3182 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3182 2022/12/20 16:41:13 - mmengine - INFO - Epoch(train) [6][ 500/1567] lr: 7.5126e-02 eta: 0:43:41 time: 0.2017 data_time: 0.0071 memory: 1461 loss: 0.2573 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2573 2022/12/20 16:41:30 - mmengine - INFO - Epoch(train) [6][ 600/1567] lr: 7.4583e-02 eta: 0:43:29 time: 0.1862 data_time: 0.0074 memory: 1461 loss: 0.2814 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2814 2022/12/20 16:41:45 - mmengine - INFO - Epoch(train) [6][ 700/1567] lr: 7.4035e-02 eta: 0:43:11 time: 0.1430 data_time: 0.0074 memory: 1461 loss: 0.2269 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2269 2022/12/20 16:42:02 - mmengine - INFO - Epoch(train) [6][ 800/1567] lr: 7.3484e-02 eta: 0:42:58 time: 0.1538 data_time: 0.0069 memory: 1461 loss: 0.2332 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.2332 2022/12/20 16:42:17 - mmengine - INFO - Epoch(train) [6][ 900/1567] lr: 7.2929e-02 eta: 0:42:42 time: 0.1461 data_time: 0.0069 memory: 1461 loss: 0.2219 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2219 2022/12/20 16:42:35 - mmengine - INFO - Epoch(train) [6][1000/1567] lr: 7.2371e-02 eta: 0:42:29 time: 0.1556 data_time: 0.0067 memory: 1461 loss: 0.2125 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2125 2022/12/20 16:42:49 - mmengine - INFO - Epoch(train) [6][1100/1567] lr: 7.1809e-02 eta: 0:42:12 time: 0.1316 data_time: 0.0072 memory: 1461 loss: 0.2459 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2459 2022/12/20 16:43:00 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 16:43:06 - mmengine - INFO - Epoch(train) [6][1200/1567] lr: 7.1243e-02 eta: 0:41:58 time: 0.1803 data_time: 0.0066 memory: 1461 loss: 0.1791 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1791 2022/12/20 16:43:21 - mmengine - INFO - Epoch(train) [6][1300/1567] lr: 7.0674e-02 eta: 0:41:41 time: 0.1360 data_time: 0.0078 memory: 1461 loss: 0.2352 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2352 2022/12/20 16:43:37 - mmengine - INFO - Epoch(train) [6][1400/1567] lr: 7.0102e-02 eta: 0:41:26 time: 0.1615 data_time: 0.0067 memory: 1461 loss: 0.2650 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2650 2022/12/20 16:43:53 - mmengine - INFO - Epoch(train) [6][1500/1567] lr: 6.9527e-02 eta: 0:41:10 time: 0.1319 data_time: 0.0068 memory: 1461 loss: 0.2534 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2534 2022/12/20 16:44:03 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 16:44:03 - mmengine - INFO - Epoch(train) [6][1567/1567] lr: 6.9140e-02 eta: 0:40:59 time: 0.1758 data_time: 0.0072 memory: 1461 loss: 0.3632 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.3632 2022/12/20 16:44:03 - mmengine - INFO - Saving checkpoint at 6 epochs 2022/12/20 16:44:10 - mmengine - INFO - Epoch(val) [6][100/129] eta: 0:00:01 time: 0.0577 data_time: 0.0061 memory: 215 2022/12/20 16:44:14 - mmengine - INFO - Epoch(val) [6][129/129] acc/top1: 0.7946 acc/top5: 0.9741 acc/mean1: 0.7946 2022/12/20 16:44:28 - mmengine - INFO - Epoch(train) [7][ 100/1567] lr: 6.8560e-02 eta: 0:40:41 time: 0.1545 data_time: 0.0074 memory: 1461 loss: 0.1430 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1430 2022/12/20 16:44:42 - mmengine - INFO - Epoch(train) [7][ 200/1567] lr: 6.7976e-02 eta: 0:40:22 time: 0.0975 data_time: 0.0075 memory: 1461 loss: 0.2214 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2214 2022/12/20 16:44:58 - mmengine - INFO - Epoch(train) [7][ 300/1567] lr: 6.7390e-02 eta: 0:40:07 time: 0.1574 data_time: 0.0068 memory: 1461 loss: 0.1577 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1577 2022/12/20 16:45:13 - mmengine - INFO - Epoch(train) [7][ 400/1567] lr: 6.6802e-02 eta: 0:39:50 time: 0.1232 data_time: 0.0079 memory: 1461 loss: 0.1459 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1459 2022/12/20 16:45:29 - mmengine - INFO - Epoch(train) [7][ 500/1567] lr: 6.6210e-02 eta: 0:39:35 time: 0.1591 data_time: 0.0069 memory: 1461 loss: 0.1727 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1727 2022/12/20 16:45:43 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 16:45:44 - mmengine - INFO - Epoch(train) [7][ 600/1567] lr: 6.5616e-02 eta: 0:39:18 time: 0.1353 data_time: 0.0065 memory: 1461 loss: 0.1399 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1399 2022/12/20 16:46:00 - mmengine - INFO - Epoch(train) [7][ 700/1567] lr: 6.5020e-02 eta: 0:39:03 time: 0.1783 data_time: 0.0072 memory: 1461 loss: 0.1797 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1797 2022/12/20 16:46:15 - mmengine - INFO - Epoch(train) [7][ 800/1567] lr: 6.4421e-02 eta: 0:38:47 time: 0.1424 data_time: 0.0069 memory: 1461 loss: 0.2258 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2258 2022/12/20 16:46:31 - mmengine - INFO - Epoch(train) [7][ 900/1567] lr: 6.3820e-02 eta: 0:38:32 time: 0.1776 data_time: 0.0070 memory: 1461 loss: 0.1925 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.1925 2022/12/20 16:46:46 - mmengine - INFO - Epoch(train) [7][1000/1567] lr: 6.3217e-02 eta: 0:38:16 time: 0.1474 data_time: 0.0071 memory: 1461 loss: 0.1955 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1955 2022/12/20 16:47:03 - mmengine - INFO - Epoch(train) [7][1100/1567] lr: 6.2612e-02 eta: 0:38:01 time: 0.1625 data_time: 0.0066 memory: 1461 loss: 0.1409 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1409 2022/12/20 16:47:18 - mmengine - INFO - Epoch(train) [7][1200/1567] lr: 6.2005e-02 eta: 0:37:44 time: 0.1235 data_time: 0.0084 memory: 1461 loss: 0.1536 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1536 2022/12/20 16:47:34 - mmengine - INFO - Epoch(train) [7][1300/1567] lr: 6.1396e-02 eta: 0:37:30 time: 0.1706 data_time: 0.0066 memory: 1461 loss: 0.1558 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1558 2022/12/20 16:47:48 - mmengine - INFO - Epoch(train) [7][1400/1567] lr: 6.0785e-02 eta: 0:37:12 time: 0.1208 data_time: 0.0069 memory: 1461 loss: 0.1609 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1609 2022/12/20 16:48:03 - mmengine - INFO - Epoch(train) [7][1500/1567] lr: 6.0172e-02 eta: 0:36:56 time: 0.1659 data_time: 0.0071 memory: 1461 loss: 0.1858 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1858 2022/12/20 16:48:13 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 16:48:13 - mmengine - INFO - Epoch(train) [7][1567/1567] lr: 5.9761e-02 eta: 0:36:44 time: 0.1520 data_time: 0.0077 memory: 1461 loss: 0.3637 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.3637 2022/12/20 16:48:13 - mmengine - INFO - Saving checkpoint at 7 epochs 2022/12/20 16:48:18 - mmengine - INFO - Epoch(val) [7][100/129] eta: 0:00:01 time: 0.0572 data_time: 0.0065 memory: 215 2022/12/20 16:48:21 - mmengine - INFO - Epoch(val) [7][129/129] acc/top1: 0.8055 acc/top5: 0.9704 acc/mean1: 0.8055 2022/12/20 16:48:21 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_5.pth is removed 2022/12/20 16:48:22 - mmengine - INFO - The best checkpoint with 0.8055 acc/top1 at 7 epoch is saved to best_acc/top1_epoch_7.pth. 2022/12/20 16:48:27 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 16:48:36 - mmengine - INFO - Epoch(train) [8][ 100/1567] lr: 5.9145e-02 eta: 0:36:26 time: 0.2142 data_time: 0.0081 memory: 1461 loss: 0.1394 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1394 2022/12/20 16:48:53 - mmengine - INFO - Epoch(train) [8][ 200/1567] lr: 5.8529e-02 eta: 0:36:13 time: 0.1482 data_time: 0.0077 memory: 1461 loss: 0.1387 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1387 2022/12/20 16:49:07 - mmengine - INFO - Epoch(train) [8][ 300/1567] lr: 5.7911e-02 eta: 0:35:55 time: 0.1272 data_time: 0.0083 memory: 1461 loss: 0.1454 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1454 2022/12/20 16:49:25 - mmengine - INFO - Epoch(train) [8][ 400/1567] lr: 5.7292e-02 eta: 0:35:42 time: 0.1672 data_time: 0.0082 memory: 1461 loss: 0.1458 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1458 2022/12/20 16:49:39 - mmengine - INFO - Epoch(train) [8][ 500/1567] lr: 5.6671e-02 eta: 0:35:25 time: 0.1185 data_time: 0.0080 memory: 1461 loss: 0.1790 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1790 2022/12/20 16:49:57 - mmengine - INFO - Epoch(train) [8][ 600/1567] lr: 5.6050e-02 eta: 0:35:11 time: 0.1607 data_time: 0.0076 memory: 1461 loss: 0.1323 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1323 2022/12/20 16:50:12 - mmengine - INFO - Epoch(train) [8][ 700/1567] lr: 5.5427e-02 eta: 0:34:55 time: 0.1487 data_time: 0.0092 memory: 1461 loss: 0.1978 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1978 2022/12/20 16:50:28 - mmengine - INFO - Epoch(train) [8][ 800/1567] lr: 5.4804e-02 eta: 0:34:40 time: 0.1746 data_time: 0.0075 memory: 1461 loss: 0.1716 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1716 2022/12/20 16:50:44 - mmengine - INFO - Epoch(train) [8][ 900/1567] lr: 5.4180e-02 eta: 0:34:25 time: 0.1574 data_time: 0.0081 memory: 1461 loss: 0.1682 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1682 2022/12/20 16:51:01 - mmengine - INFO - Epoch(train) [8][1000/1567] lr: 5.3556e-02 eta: 0:34:10 time: 0.1845 data_time: 0.0079 memory: 1461 loss: 0.1490 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1490 2022/12/20 16:51:05 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 16:51:15 - mmengine - INFO - Epoch(train) [8][1100/1567] lr: 5.2930e-02 eta: 0:33:54 time: 0.1348 data_time: 0.0092 memory: 1461 loss: 0.1649 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1649 2022/12/20 16:51:32 - mmengine - INFO - Epoch(train) [8][1200/1567] lr: 5.2305e-02 eta: 0:33:39 time: 0.1521 data_time: 0.0076 memory: 1461 loss: 0.1216 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1216 2022/12/20 16:51:47 - mmengine - INFO - Epoch(train) [8][1300/1567] lr: 5.1679e-02 eta: 0:33:23 time: 0.1429 data_time: 0.0084 memory: 1461 loss: 0.1126 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1126 2022/12/20 16:52:02 - mmengine - INFO - Epoch(train) [8][1400/1567] lr: 5.1052e-02 eta: 0:33:07 time: 0.1836 data_time: 0.0073 memory: 1461 loss: 0.1349 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1349 2022/12/20 16:52:17 - mmengine - INFO - Epoch(train) [8][1500/1567] lr: 5.0426e-02 eta: 0:32:50 time: 0.1479 data_time: 0.0074 memory: 1461 loss: 0.1601 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1601 2022/12/20 16:52:26 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 16:52:26 - mmengine - INFO - Epoch(train) [8][1567/1567] lr: 5.0006e-02 eta: 0:32:38 time: 0.1476 data_time: 0.0071 memory: 1461 loss: 0.3170 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3170 2022/12/20 16:52:26 - mmengine - INFO - Saving checkpoint at 8 epochs 2022/12/20 16:52:31 - mmengine - INFO - Epoch(val) [8][100/129] eta: 0:00:01 time: 0.0329 data_time: 0.0078 memory: 215 2022/12/20 16:52:33 - mmengine - INFO - Epoch(val) [8][129/129] acc/top1: 0.7604 acc/top5: 0.9611 acc/mean1: 0.7602 2022/12/20 16:52:52 - mmengine - INFO - Epoch(train) [9][ 100/1567] lr: 4.9380e-02 eta: 0:32:26 time: 0.1592 data_time: 0.0072 memory: 1461 loss: 0.1067 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1067 2022/12/20 16:53:07 - mmengine - INFO - Epoch(train) [9][ 200/1567] lr: 4.8753e-02 eta: 0:32:10 time: 0.1588 data_time: 0.0068 memory: 1461 loss: 0.1408 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.1408 2022/12/20 16:53:23 - mmengine - INFO - Epoch(train) [9][ 300/1567] lr: 4.8127e-02 eta: 0:31:54 time: 0.1862 data_time: 0.0073 memory: 1461 loss: 0.1048 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1048 2022/12/20 16:53:39 - mmengine - INFO - Epoch(train) [9][ 400/1567] lr: 4.7501e-02 eta: 0:31:39 time: 0.1588 data_time: 0.0069 memory: 1461 loss: 0.1614 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1614 2022/12/20 16:53:49 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 16:53:55 - mmengine - INFO - Epoch(train) [9][ 500/1567] lr: 4.6876e-02 eta: 0:31:24 time: 0.1568 data_time: 0.0067 memory: 1461 loss: 0.1356 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1356 2022/12/20 16:54:11 - mmengine - INFO - Epoch(train) [9][ 600/1567] lr: 4.6251e-02 eta: 0:31:08 time: 0.1304 data_time: 0.0073 memory: 1461 loss: 0.1074 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1074 2022/12/20 16:54:27 - mmengine - INFO - Epoch(train) [9][ 700/1567] lr: 4.5626e-02 eta: 0:30:53 time: 0.1514 data_time: 0.0075 memory: 1461 loss: 0.1432 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1432 2022/12/20 16:54:43 - mmengine - INFO - Epoch(train) [9][ 800/1567] lr: 4.5003e-02 eta: 0:30:38 time: 0.1691 data_time: 0.0073 memory: 1461 loss: 0.1298 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1298 2022/12/20 16:54:59 - mmengine - INFO - Epoch(train) [9][ 900/1567] lr: 4.4380e-02 eta: 0:30:22 time: 0.2036 data_time: 0.0072 memory: 1461 loss: 0.1151 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1151 2022/12/20 16:55:15 - mmengine - INFO - Epoch(train) [9][1000/1567] lr: 4.3757e-02 eta: 0:30:07 time: 0.1560 data_time: 0.0075 memory: 1461 loss: 0.1535 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1535 2022/12/20 16:55:31 - mmengine - INFO - Epoch(train) [9][1100/1567] lr: 4.3136e-02 eta: 0:29:51 time: 0.1508 data_time: 0.0075 memory: 1461 loss: 0.1065 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1065 2022/12/20 16:55:48 - mmengine - INFO - Epoch(train) [9][1200/1567] lr: 4.2516e-02 eta: 0:29:37 time: 0.1513 data_time: 0.0066 memory: 1461 loss: 0.1262 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1262 2022/12/20 16:56:02 - mmengine - INFO - Epoch(train) [9][1300/1567] lr: 4.1897e-02 eta: 0:29:20 time: 0.1316 data_time: 0.0068 memory: 1461 loss: 0.1375 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1375 2022/12/20 16:56:18 - mmengine - INFO - Epoch(train) [9][1400/1567] lr: 4.1280e-02 eta: 0:29:05 time: 0.1644 data_time: 0.0076 memory: 1461 loss: 0.1332 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1332 2022/12/20 16:56:27 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 16:56:32 - mmengine - INFO - Epoch(train) [9][1500/1567] lr: 4.0664e-02 eta: 0:28:47 time: 0.1209 data_time: 0.0071 memory: 1461 loss: 0.1151 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1151 2022/12/20 16:56:41 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 16:56:41 - mmengine - INFO - Epoch(train) [9][1567/1567] lr: 4.0252e-02 eta: 0:28:36 time: 0.1401 data_time: 0.0070 memory: 1461 loss: 0.3207 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.3207 2022/12/20 16:56:41 - mmengine - INFO - Saving checkpoint at 9 epochs 2022/12/20 16:56:45 - mmengine - INFO - Epoch(val) [9][100/129] eta: 0:00:00 time: 0.0293 data_time: 0.0069 memory: 215 2022/12/20 16:56:48 - mmengine - INFO - Epoch(val) [9][129/129] acc/top1: 0.8220 acc/top5: 0.9755 acc/mean1: 0.8220 2022/12/20 16:56:48 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_7.pth is removed 2022/12/20 16:56:49 - mmengine - INFO - The best checkpoint with 0.8220 acc/top1 at 9 epoch is saved to best_acc/top1_epoch_9.pth. 2022/12/20 16:57:05 - mmengine - INFO - Epoch(train) [10][ 100/1567] lr: 3.9638e-02 eta: 0:28:21 time: 0.1536 data_time: 0.0076 memory: 1461 loss: 0.1231 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1231 2022/12/20 16:57:20 - mmengine - INFO - Epoch(train) [10][ 200/1567] lr: 3.9026e-02 eta: 0:28:05 time: 0.1312 data_time: 0.0073 memory: 1461 loss: 0.1198 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1198 2022/12/20 16:57:37 - mmengine - INFO - Epoch(train) [10][ 300/1567] lr: 3.8415e-02 eta: 0:27:50 time: 0.1552 data_time: 0.0071 memory: 1461 loss: 0.0662 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0662 2022/12/20 16:57:52 - mmengine - INFO - Epoch(train) [10][ 400/1567] lr: 3.7807e-02 eta: 0:27:34 time: 0.1297 data_time: 0.0069 memory: 1461 loss: 0.0921 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.0921 2022/12/20 16:58:09 - mmengine - INFO - Epoch(train) [10][ 500/1567] lr: 3.7200e-02 eta: 0:27:19 time: 0.1875 data_time: 0.0075 memory: 1461 loss: 0.1304 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1304 2022/12/20 16:58:24 - mmengine - INFO - Epoch(train) [10][ 600/1567] lr: 3.6596e-02 eta: 0:27:03 time: 0.1614 data_time: 0.0075 memory: 1461 loss: 0.1261 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1261 2022/12/20 16:58:40 - mmengine - INFO - Epoch(train) [10][ 700/1567] lr: 3.5993e-02 eta: 0:26:48 time: 0.1590 data_time: 0.0076 memory: 1461 loss: 0.0942 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0942 2022/12/20 16:58:56 - mmengine - INFO - Epoch(train) [10][ 800/1567] lr: 3.5393e-02 eta: 0:26:32 time: 0.1462 data_time: 0.0071 memory: 1461 loss: 0.0975 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.0975 2022/12/20 16:59:11 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 16:59:12 - mmengine - INFO - Epoch(train) [10][ 900/1567] lr: 3.4795e-02 eta: 0:26:17 time: 0.1711 data_time: 0.0070 memory: 1461 loss: 0.0916 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0916 2022/12/20 16:59:27 - mmengine - INFO - Epoch(train) [10][1000/1567] lr: 3.4199e-02 eta: 0:26:01 time: 0.1366 data_time: 0.0074 memory: 1461 loss: 0.0993 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0993 2022/12/20 16:59:43 - mmengine - INFO - Epoch(train) [10][1100/1567] lr: 3.3606e-02 eta: 0:25:45 time: 0.1816 data_time: 0.0067 memory: 1461 loss: 0.1343 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1343 2022/12/20 16:59:59 - mmengine - INFO - Epoch(train) [10][1200/1567] lr: 3.3015e-02 eta: 0:25:30 time: 0.1500 data_time: 0.0074 memory: 1461 loss: 0.0969 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0969 2022/12/20 17:00:14 - mmengine - INFO - Epoch(train) [10][1300/1567] lr: 3.2428e-02 eta: 0:25:13 time: 0.1516 data_time: 0.0074 memory: 1461 loss: 0.0757 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0757 2022/12/20 17:00:29 - mmengine - INFO - Epoch(train) [10][1400/1567] lr: 3.1842e-02 eta: 0:24:57 time: 0.1562 data_time: 0.0084 memory: 1461 loss: 0.0813 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0813 2022/12/20 17:00:42 - mmengine - INFO - Epoch(train) [10][1500/1567] lr: 3.1260e-02 eta: 0:24:40 time: 0.1298 data_time: 0.0068 memory: 1461 loss: 0.0552 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0552 2022/12/20 17:00:50 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 17:00:50 - mmengine - INFO - Epoch(train) [10][1567/1567] lr: 3.0872e-02 eta: 0:24:28 time: 0.1202 data_time: 0.0073 memory: 1461 loss: 0.2633 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2633 2022/12/20 17:00:50 - mmengine - INFO - Saving checkpoint at 10 epochs 2022/12/20 17:00:55 - mmengine - INFO - Epoch(val) [10][100/129] eta: 0:00:01 time: 0.0255 data_time: 0.0059 memory: 215 2022/12/20 17:01:02 - mmengine - INFO - Epoch(val) [10][129/129] acc/top1: 0.8403 acc/top5: 0.9793 acc/mean1: 0.8402 2022/12/20 17:01:02 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_9.pth is removed 2022/12/20 17:01:03 - mmengine - INFO - The best checkpoint with 0.8403 acc/top1 at 10 epoch is saved to best_acc/top1_epoch_10.pth. 2022/12/20 17:01:17 - mmengine - INFO - Epoch(train) [11][ 100/1567] lr: 3.0294e-02 eta: 0:24:12 time: 0.1559 data_time: 0.0081 memory: 1461 loss: 0.0848 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0848 2022/12/20 17:01:32 - mmengine - INFO - Epoch(train) [11][ 200/1567] lr: 2.9720e-02 eta: 0:23:56 time: 0.1561 data_time: 0.0074 memory: 1461 loss: 0.0480 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0480 2022/12/20 17:01:47 - mmengine - INFO - Epoch(train) [11][ 300/1567] lr: 2.9149e-02 eta: 0:23:40 time: 0.1358 data_time: 0.0084 memory: 1461 loss: 0.0778 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0778 2022/12/20 17:01:52 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 17:02:02 - mmengine - INFO - Epoch(train) [11][ 400/1567] lr: 2.8581e-02 eta: 0:23:24 time: 0.1817 data_time: 0.0077 memory: 1461 loss: 0.0767 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0767 2022/12/20 17:02:18 - mmengine - INFO - Epoch(train) [11][ 500/1567] lr: 2.8017e-02 eta: 0:23:09 time: 0.1291 data_time: 0.0082 memory: 1461 loss: 0.1212 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1212 2022/12/20 17:02:32 - mmengine - INFO - Epoch(train) [11][ 600/1567] lr: 2.7456e-02 eta: 0:22:52 time: 0.1607 data_time: 0.0081 memory: 1461 loss: 0.0636 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0636 2022/12/20 17:02:49 - mmengine - INFO - Epoch(train) [11][ 700/1567] lr: 2.6898e-02 eta: 0:22:37 time: 0.1329 data_time: 0.0084 memory: 1461 loss: 0.0850 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.0850 2022/12/20 17:03:03 - mmengine - INFO - Epoch(train) [11][ 800/1567] lr: 2.6345e-02 eta: 0:22:21 time: 0.1980 data_time: 0.0078 memory: 1461 loss: 0.0550 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0550 2022/12/20 17:03:20 - mmengine - INFO - Epoch(train) [11][ 900/1567] lr: 2.5794e-02 eta: 0:22:06 time: 0.1569 data_time: 0.0074 memory: 1461 loss: 0.0725 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0725 2022/12/20 17:03:33 - mmengine - INFO - Epoch(train) [11][1000/1567] lr: 2.5248e-02 eta: 0:21:49 time: 0.1239 data_time: 0.0073 memory: 1461 loss: 0.0802 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0802 2022/12/20 17:03:50 - mmengine - INFO - Epoch(train) [11][1100/1567] lr: 2.4706e-02 eta: 0:21:35 time: 0.1532 data_time: 0.0074 memory: 1461 loss: 0.0441 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0441 2022/12/20 17:04:04 - mmengine - INFO - Epoch(train) [11][1200/1567] lr: 2.4167e-02 eta: 0:21:18 time: 0.1060 data_time: 0.0073 memory: 1461 loss: 0.0432 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0432 2022/12/20 17:04:19 - mmengine - INFO - Epoch(train) [11][1300/1567] lr: 2.3633e-02 eta: 0:21:02 time: 0.1467 data_time: 0.0069 memory: 1461 loss: 0.0479 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0479 2022/12/20 17:04:24 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 17:04:33 - mmengine - INFO - Epoch(train) [11][1400/1567] lr: 2.3103e-02 eta: 0:20:46 time: 0.1292 data_time: 0.0076 memory: 1461 loss: 0.0919 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0919 2022/12/20 17:04:50 - mmengine - INFO - Epoch(train) [11][1500/1567] lr: 2.2577e-02 eta: 0:20:31 time: 0.1962 data_time: 0.0093 memory: 1461 loss: 0.0538 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0538 2022/12/20 17:04:55 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 17:04:55 - mmengine - INFO - Epoch(train) [11][1567/1567] lr: 2.2227e-02 eta: 0:20:18 time: 0.0766 data_time: 0.0070 memory: 1461 loss: 0.2488 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.2488 2022/12/20 17:04:55 - mmengine - INFO - Saving checkpoint at 11 epochs 2022/12/20 17:04:59 - mmengine - INFO - Epoch(val) [11][100/129] eta: 0:00:00 time: 0.0285 data_time: 0.0068 memory: 215 2022/12/20 17:05:00 - mmengine - INFO - Epoch(val) [11][129/129] acc/top1: 0.8583 acc/top5: 0.9804 acc/mean1: 0.8582 2022/12/20 17:05:00 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_10.pth is removed 2022/12/20 17:05:00 - mmengine - INFO - The best checkpoint with 0.8583 acc/top1 at 11 epoch is saved to best_acc/top1_epoch_11.pth. 2022/12/20 17:05:08 - mmengine - INFO - Epoch(train) [12][ 100/1567] lr: 2.1708e-02 eta: 0:19:59 time: 0.0884 data_time: 0.0075 memory: 1461 loss: 0.0391 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0391 2022/12/20 17:05:17 - mmengine - INFO - Epoch(train) [12][ 200/1567] lr: 2.1194e-02 eta: 0:19:41 time: 0.0870 data_time: 0.0074 memory: 1461 loss: 0.0500 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0500 2022/12/20 17:05:25 - mmengine - INFO - Epoch(train) [12][ 300/1567] lr: 2.0684e-02 eta: 0:19:22 time: 0.0779 data_time: 0.0068 memory: 1461 loss: 0.0177 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0177 2022/12/20 17:05:32 - mmengine - INFO - Epoch(train) [12][ 400/1567] lr: 2.0179e-02 eta: 0:19:03 time: 0.0770 data_time: 0.0072 memory: 1461 loss: 0.0416 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0416 2022/12/20 17:05:40 - mmengine - INFO - Epoch(train) [12][ 500/1567] lr: 1.9678e-02 eta: 0:18:45 time: 0.0808 data_time: 0.0071 memory: 1461 loss: 0.0388 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0388 2022/12/20 17:05:48 - mmengine - INFO - Epoch(train) [12][ 600/1567] lr: 1.9182e-02 eta: 0:18:26 time: 0.0760 data_time: 0.0068 memory: 1461 loss: 0.0689 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0689 2022/12/20 17:05:56 - mmengine - INFO - Epoch(train) [12][ 700/1567] lr: 1.8691e-02 eta: 0:18:08 time: 0.0762 data_time: 0.0069 memory: 1461 loss: 0.0505 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0505 2022/12/20 17:06:01 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 17:06:04 - mmengine - INFO - Epoch(train) [12][ 800/1567] lr: 1.8205e-02 eta: 0:17:50 time: 0.0791 data_time: 0.0069 memory: 1461 loss: 0.0330 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0330 2022/12/20 17:06:14 - mmengine - INFO - Epoch(train) [12][ 900/1567] lr: 1.7724e-02 eta: 0:17:33 time: 0.1942 data_time: 0.0090 memory: 1461 loss: 0.0243 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0243 2022/12/20 17:06:28 - mmengine - INFO - Epoch(train) [12][1000/1567] lr: 1.7248e-02 eta: 0:17:17 time: 0.2153 data_time: 0.0074 memory: 1461 loss: 0.0549 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0549 2022/12/20 17:06:44 - mmengine - INFO - Epoch(train) [12][1100/1567] lr: 1.6778e-02 eta: 0:17:02 time: 0.1460 data_time: 0.0074 memory: 1461 loss: 0.0306 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0306 2022/12/20 17:06:59 - mmengine - INFO - Epoch(train) [12][1200/1567] lr: 1.6312e-02 eta: 0:16:47 time: 0.1951 data_time: 0.0073 memory: 1461 loss: 0.0358 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0358 2022/12/20 17:07:15 - mmengine - INFO - Epoch(train) [12][1300/1567] lr: 1.5852e-02 eta: 0:16:32 time: 0.1327 data_time: 0.0068 memory: 1461 loss: 0.0206 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0206 2022/12/20 17:07:30 - mmengine - INFO - Epoch(train) [12][1400/1567] lr: 1.5397e-02 eta: 0:16:17 time: 0.1597 data_time: 0.0076 memory: 1461 loss: 0.0252 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0252 2022/12/20 17:07:47 - mmengine - INFO - Epoch(train) [12][1500/1567] lr: 1.4947e-02 eta: 0:16:02 time: 0.1427 data_time: 0.0076 memory: 1461 loss: 0.0339 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0339 2022/12/20 17:07:56 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 17:07:56 - mmengine - INFO - Epoch(train) [12][1567/1567] lr: 1.4649e-02 eta: 0:15:52 time: 0.1315 data_time: 0.0070 memory: 1461 loss: 0.2122 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2122 2022/12/20 17:07:56 - mmengine - INFO - Saving checkpoint at 12 epochs 2022/12/20 17:08:01 - mmengine - INFO - Epoch(val) [12][100/129] eta: 0:00:01 time: 0.0508 data_time: 0.0066 memory: 215 2022/12/20 17:08:07 - mmengine - INFO - Epoch(val) [12][129/129] acc/top1: 0.8603 acc/top5: 0.9808 acc/mean1: 0.8602 2022/12/20 17:08:07 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_11.pth is removed 2022/12/20 17:08:07 - mmengine - INFO - The best checkpoint with 0.8603 acc/top1 at 12 epoch is saved to best_acc/top1_epoch_12.pth. 2022/12/20 17:08:24 - mmengine - INFO - Epoch(train) [13][ 100/1567] lr: 1.4209e-02 eta: 0:15:37 time: 0.1387 data_time: 0.0080 memory: 1461 loss: 0.0280 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0280 2022/12/20 17:08:39 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 17:08:39 - mmengine - INFO - Epoch(train) [13][ 200/1567] lr: 1.3774e-02 eta: 0:15:22 time: 0.1899 data_time: 0.0076 memory: 1461 loss: 0.0325 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0325 2022/12/20 17:08:56 - mmengine - INFO - Epoch(train) [13][ 300/1567] lr: 1.3345e-02 eta: 0:15:07 time: 0.1579 data_time: 0.0081 memory: 1461 loss: 0.0241 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0241 2022/12/20 17:09:11 - mmengine - INFO - Epoch(train) [13][ 400/1567] lr: 1.2922e-02 eta: 0:14:52 time: 0.2071 data_time: 0.0070 memory: 1461 loss: 0.0261 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0261 2022/12/20 17:09:27 - mmengine - INFO - Epoch(train) [13][ 500/1567] lr: 1.2505e-02 eta: 0:14:37 time: 0.1571 data_time: 0.0074 memory: 1461 loss: 0.0240 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0240 2022/12/20 17:09:41 - mmengine - INFO - Epoch(train) [13][ 600/1567] lr: 1.2093e-02 eta: 0:14:21 time: 0.2007 data_time: 0.0077 memory: 1461 loss: 0.0157 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0157 2022/12/20 17:09:57 - mmengine - INFO - Epoch(train) [13][ 700/1567] lr: 1.1687e-02 eta: 0:14:06 time: 0.1454 data_time: 0.0073 memory: 1461 loss: 0.0267 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0267 2022/12/20 17:10:11 - mmengine - INFO - Epoch(train) [13][ 800/1567] lr: 1.1288e-02 eta: 0:13:51 time: 0.1449 data_time: 0.0071 memory: 1461 loss: 0.0138 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0138 2022/12/20 17:10:22 - mmengine - INFO - Epoch(train) [13][ 900/1567] lr: 1.0894e-02 eta: 0:13:35 time: 0.1334 data_time: 0.0097 memory: 1461 loss: 0.0262 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0262 2022/12/20 17:10:38 - mmengine - INFO - Epoch(train) [13][1000/1567] lr: 1.0507e-02 eta: 0:13:20 time: 0.1410 data_time: 0.0076 memory: 1461 loss: 0.0356 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0356 2022/12/20 17:10:53 - mmengine - INFO - Epoch(train) [13][1100/1567] lr: 1.0126e-02 eta: 0:13:04 time: 0.1609 data_time: 0.0083 memory: 1461 loss: 0.0171 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0171 2022/12/20 17:11:08 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 17:11:08 - mmengine - INFO - Epoch(train) [13][1200/1567] lr: 9.7512e-03 eta: 0:12:49 time: 0.1310 data_time: 0.0079 memory: 1461 loss: 0.0133 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0133 2022/12/20 17:11:22 - mmengine - INFO - Epoch(train) [13][1300/1567] lr: 9.3826e-03 eta: 0:12:34 time: 0.1142 data_time: 0.0078 memory: 1461 loss: 0.0153 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0153 2022/12/20 17:11:39 - mmengine - INFO - Epoch(train) [13][1400/1567] lr: 9.0204e-03 eta: 0:12:19 time: 0.1405 data_time: 0.0075 memory: 1461 loss: 0.0141 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0141 2022/12/20 17:11:52 - mmengine - INFO - Epoch(train) [13][1500/1567] lr: 8.6647e-03 eta: 0:12:03 time: 0.0862 data_time: 0.0072 memory: 1461 loss: 0.0152 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0152 2022/12/20 17:12:04 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 17:12:04 - mmengine - INFO - Epoch(train) [13][1567/1567] lr: 8.4300e-03 eta: 0:11:53 time: 0.1543 data_time: 0.0080 memory: 1461 loss: 0.2162 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2162 2022/12/20 17:12:04 - mmengine - INFO - Saving checkpoint at 13 epochs 2022/12/20 17:12:09 - mmengine - INFO - Epoch(val) [13][100/129] eta: 0:00:01 time: 0.0666 data_time: 0.0077 memory: 215 2022/12/20 17:12:14 - mmengine - INFO - Epoch(val) [13][129/129] acc/top1: 0.8592 acc/top5: 0.9818 acc/mean1: 0.8591 2022/12/20 17:12:28 - mmengine - INFO - Epoch(train) [14][ 100/1567] lr: 8.0851e-03 eta: 0:11:38 time: 0.1832 data_time: 0.0073 memory: 1461 loss: 0.0262 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0262 2022/12/20 17:12:45 - mmengine - INFO - Epoch(train) [14][ 200/1567] lr: 7.7469e-03 eta: 0:11:23 time: 0.1528 data_time: 0.0081 memory: 1461 loss: 0.0097 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0097 2022/12/20 17:12:59 - mmengine - INFO - Epoch(train) [14][ 300/1567] lr: 7.4152e-03 eta: 0:11:08 time: 0.1513 data_time: 0.0074 memory: 1461 loss: 0.0127 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0127 2022/12/20 17:13:15 - mmengine - INFO - Epoch(train) [14][ 400/1567] lr: 7.0902e-03 eta: 0:10:53 time: 0.1149 data_time: 0.0070 memory: 1461 loss: 0.0104 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0104 2022/12/20 17:13:28 - mmengine - INFO - Epoch(train) [14][ 500/1567] lr: 6.7720e-03 eta: 0:10:37 time: 0.1234 data_time: 0.0075 memory: 1461 loss: 0.0135 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0135 2022/12/20 17:13:44 - mmengine - INFO - Epoch(train) [14][ 600/1567] lr: 6.4606e-03 eta: 0:10:22 time: 0.1542 data_time: 0.0081 memory: 1461 loss: 0.0255 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0255 2022/12/20 17:13:48 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 17:13:58 - mmengine - INFO - Epoch(train) [14][ 700/1567] lr: 6.1560e-03 eta: 0:10:07 time: 0.1494 data_time: 0.0070 memory: 1461 loss: 0.0139 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0139 2022/12/20 17:14:09 - mmengine - INFO - Epoch(train) [14][ 800/1567] lr: 5.8582e-03 eta: 0:09:51 time: 0.1489 data_time: 0.0095 memory: 1461 loss: 0.0181 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0181 2022/12/20 17:14:25 - mmengine - INFO - Epoch(train) [14][ 900/1567] lr: 5.5675e-03 eta: 0:09:36 time: 0.1411 data_time: 0.0093 memory: 1461 loss: 0.0118 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0118 2022/12/20 17:14:40 - mmengine - INFO - Epoch(train) [14][1000/1567] lr: 5.2836e-03 eta: 0:09:20 time: 0.1545 data_time: 0.0074 memory: 1461 loss: 0.0121 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0121 2022/12/20 17:14:57 - mmengine - INFO - Epoch(train) [14][1100/1567] lr: 5.0068e-03 eta: 0:09:06 time: 0.1611 data_time: 0.0073 memory: 1461 loss: 0.0118 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0118 2022/12/20 17:15:13 - mmengine - INFO - Epoch(train) [14][1200/1567] lr: 4.7371e-03 eta: 0:08:51 time: 0.1475 data_time: 0.0084 memory: 1461 loss: 0.0119 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0119 2022/12/20 17:15:29 - mmengine - INFO - Epoch(train) [14][1300/1567] lr: 4.4745e-03 eta: 0:08:36 time: 0.1881 data_time: 0.0077 memory: 1461 loss: 0.0095 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0095 2022/12/20 17:15:45 - mmengine - INFO - Epoch(train) [14][1400/1567] lr: 4.2190e-03 eta: 0:08:20 time: 0.1541 data_time: 0.0076 memory: 1461 loss: 0.0093 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0093 2022/12/20 17:16:00 - mmengine - INFO - Epoch(train) [14][1500/1567] lr: 3.9707e-03 eta: 0:08:05 time: 0.1597 data_time: 0.0073 memory: 1461 loss: 0.0073 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0073 2022/12/20 17:16:11 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 17:16:11 - mmengine - INFO - Epoch(train) [14][1567/1567] lr: 3.8084e-03 eta: 0:07:55 time: 0.1422 data_time: 0.0077 memory: 1461 loss: 0.2513 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2513 2022/12/20 17:16:11 - mmengine - INFO - Saving checkpoint at 14 epochs 2022/12/20 17:16:17 - mmengine - INFO - Epoch(val) [14][100/129] eta: 0:00:01 time: 0.0524 data_time: 0.0069 memory: 215 2022/12/20 17:16:19 - mmengine - INFO - Epoch(val) [14][129/129] acc/top1: 0.8690 acc/top5: 0.9830 acc/mean1: 0.8689 2022/12/20 17:16:19 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_12.pth is removed 2022/12/20 17:16:19 - mmengine - INFO - The best checkpoint with 0.8690 acc/top1 at 14 epoch is saved to best_acc/top1_epoch_14.pth. 2022/12/20 17:16:30 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 17:16:36 - mmengine - INFO - Epoch(train) [15][ 100/1567] lr: 3.5722e-03 eta: 0:07:40 time: 0.1677 data_time: 0.0075 memory: 1461 loss: 0.0116 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0116 2022/12/20 17:16:51 - mmengine - INFO - Epoch(train) [15][ 200/1567] lr: 3.3433e-03 eta: 0:07:25 time: 0.1253 data_time: 0.0076 memory: 1461 loss: 0.0148 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0148 2022/12/20 17:17:08 - mmengine - INFO - Epoch(train) [15][ 300/1567] lr: 3.1217e-03 eta: 0:07:10 time: 0.1570 data_time: 0.0070 memory: 1461 loss: 0.0089 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0089 2022/12/20 17:17:23 - mmengine - INFO - Epoch(train) [15][ 400/1567] lr: 2.9075e-03 eta: 0:06:55 time: 0.1537 data_time: 0.0077 memory: 1461 loss: 0.0073 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0073 2022/12/20 17:17:39 - mmengine - INFO - Epoch(train) [15][ 500/1567] lr: 2.7007e-03 eta: 0:06:40 time: 0.1805 data_time: 0.0075 memory: 1461 loss: 0.0074 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0074 2022/12/20 17:17:53 - mmengine - INFO - Epoch(train) [15][ 600/1567] lr: 2.5013e-03 eta: 0:06:24 time: 0.1557 data_time: 0.0072 memory: 1461 loss: 0.0136 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0136 2022/12/20 17:18:06 - mmengine - INFO - Epoch(train) [15][ 700/1567] lr: 2.3093e-03 eta: 0:06:09 time: 0.0906 data_time: 0.0076 memory: 1461 loss: 0.0094 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0094 2022/12/20 17:18:21 - mmengine - INFO - Epoch(train) [15][ 800/1567] lr: 2.1249e-03 eta: 0:05:54 time: 0.1600 data_time: 0.0074 memory: 1461 loss: 0.0093 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0093 2022/12/20 17:18:37 - mmengine - INFO - Epoch(train) [15][ 900/1567] lr: 1.9479e-03 eta: 0:05:39 time: 0.1452 data_time: 0.0087 memory: 1461 loss: 0.0095 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0095 2022/12/20 17:18:53 - mmengine - INFO - Epoch(train) [15][1000/1567] lr: 1.7785e-03 eta: 0:05:24 time: 0.1760 data_time: 0.0077 memory: 1461 loss: 0.0065 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0065 2022/12/20 17:19:03 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 17:19:08 - mmengine - INFO - Epoch(train) [15][1100/1567] lr: 1.6167e-03 eta: 0:05:08 time: 0.1629 data_time: 0.0079 memory: 1461 loss: 0.0096 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0096 2022/12/20 17:19:25 - mmengine - INFO - Epoch(train) [15][1200/1567] lr: 1.4625e-03 eta: 0:04:53 time: 0.2111 data_time: 0.0078 memory: 1461 loss: 0.0067 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0067 2022/12/20 17:19:40 - mmengine - INFO - Epoch(train) [15][1300/1567] lr: 1.3159e-03 eta: 0:04:38 time: 0.1530 data_time: 0.0081 memory: 1461 loss: 0.0088 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0088 2022/12/20 17:19:56 - mmengine - INFO - Epoch(train) [15][1400/1567] lr: 1.1769e-03 eta: 0:04:23 time: 0.1949 data_time: 0.0075 memory: 1461 loss: 0.0086 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0086 2022/12/20 17:20:12 - mmengine - INFO - Epoch(train) [15][1500/1567] lr: 1.0456e-03 eta: 0:04:08 time: 0.1523 data_time: 0.0078 memory: 1461 loss: 0.0085 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0085 2022/12/20 17:20:23 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 17:20:23 - mmengine - INFO - Epoch(train) [15][1567/1567] lr: 9.6196e-04 eta: 0:03:58 time: 0.1226 data_time: 0.0075 memory: 1461 loss: 0.1933 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.1933 2022/12/20 17:20:23 - mmengine - INFO - Saving checkpoint at 15 epochs 2022/12/20 17:20:29 - mmengine - INFO - Epoch(val) [15][100/129] eta: 0:00:01 time: 0.0587 data_time: 0.0067 memory: 215 2022/12/20 17:20:33 - mmengine - INFO - Epoch(val) [15][129/129] acc/top1: 0.8706 acc/top5: 0.9835 acc/mean1: 0.8705 2022/12/20 17:20:33 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_14.pth is removed 2022/12/20 17:20:33 - mmengine - INFO - The best checkpoint with 0.8706 acc/top1 at 15 epoch is saved to best_acc/top1_epoch_15.pth. 2022/12/20 17:20:49 - mmengine - INFO - Epoch(train) [16][ 100/1567] lr: 8.4351e-04 eta: 0:03:43 time: 0.1600 data_time: 0.0076 memory: 1461 loss: 0.0048 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0048 2022/12/20 17:21:05 - mmengine - INFO - Epoch(train) [16][ 200/1567] lr: 7.3277e-04 eta: 0:03:27 time: 0.1759 data_time: 0.0075 memory: 1461 loss: 0.0079 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0079 2022/12/20 17:21:20 - mmengine - INFO - Epoch(train) [16][ 300/1567] lr: 6.2978e-04 eta: 0:03:12 time: 0.1502 data_time: 0.0071 memory: 1461 loss: 0.0056 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0056 2022/12/20 17:21:35 - mmengine - INFO - Epoch(train) [16][ 400/1567] lr: 5.3453e-04 eta: 0:02:57 time: 0.1560 data_time: 0.0069 memory: 1461 loss: 0.0070 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0070 2022/12/20 17:21:50 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 17:21:51 - mmengine - INFO - Epoch(train) [16][ 500/1567] lr: 4.4705e-04 eta: 0:02:42 time: 0.1495 data_time: 0.0069 memory: 1461 loss: 0.0075 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0075 2022/12/20 17:22:05 - mmengine - INFO - Epoch(train) [16][ 600/1567] lr: 3.6735e-04 eta: 0:02:27 time: 0.1504 data_time: 0.0078 memory: 1461 loss: 0.0091 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0091 2022/12/20 17:22:19 - mmengine - INFO - Epoch(train) [16][ 700/1567] lr: 2.9544e-04 eta: 0:02:11 time: 0.1647 data_time: 0.0078 memory: 1461 loss: 0.0097 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0097 2022/12/20 17:22:35 - mmengine - INFO - Epoch(train) [16][ 800/1567] lr: 2.3134e-04 eta: 0:01:56 time: 0.1352 data_time: 0.0086 memory: 1461 loss: 0.0107 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0107 2022/12/20 17:22:51 - mmengine - INFO - Epoch(train) [16][ 900/1567] lr: 1.7505e-04 eta: 0:01:41 time: 0.1651 data_time: 0.0075 memory: 1461 loss: 0.0087 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0087 2022/12/20 17:23:09 - mmengine - INFO - Epoch(train) [16][1000/1567] lr: 1.2658e-04 eta: 0:01:26 time: 0.1811 data_time: 0.0086 memory: 1461 loss: 0.0093 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0093 2022/12/20 17:23:23 - mmengine - INFO - Epoch(train) [16][1100/1567] lr: 8.5947e-05 eta: 0:01:11 time: 0.1579 data_time: 0.0075 memory: 1461 loss: 0.0086 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0086 2022/12/20 17:23:41 - mmengine - INFO - Epoch(train) [16][1200/1567] lr: 5.3147e-05 eta: 0:00:55 time: 0.1627 data_time: 0.0076 memory: 1461 loss: 0.0061 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0061 2022/12/20 17:23:55 - mmengine - INFO - Epoch(train) [16][1300/1567] lr: 2.8190e-05 eta: 0:00:40 time: 0.1228 data_time: 0.0080 memory: 1461 loss: 0.0061 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0061 2022/12/20 17:24:13 - mmengine - INFO - Epoch(train) [16][1400/1567] lr: 1.1078e-05 eta: 0:00:25 time: 0.1986 data_time: 0.0073 memory: 1461 loss: 0.0073 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0073 2022/12/20 17:24:27 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 17:24:28 - mmengine - INFO - Epoch(train) [16][1500/1567] lr: 1.8150e-06 eta: 0:00:10 time: 0.1501 data_time: 0.0084 memory: 1461 loss: 0.0082 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0082 2022/12/20 17:24:39 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221220_161747 2022/12/20 17:24:39 - mmengine - INFO - Epoch(train) [16][1567/1567] lr: 3.9252e-10 eta: 0:00:00 time: 0.1902 data_time: 0.0072 memory: 1461 loss: 0.1956 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.1956 2022/12/20 17:24:39 - mmengine - INFO - Saving checkpoint at 16 epochs 2022/12/20 17:24:45 - mmengine - INFO - Epoch(val) [16][100/129] eta: 0:00:01 time: 0.0493 data_time: 0.0066 memory: 215 2022/12/20 17:24:49 - mmengine - INFO - Epoch(val) [16][129/129] acc/top1: 0.8731 acc/top5: 0.9840 acc/mean1: 0.8730 2022/12/20 17:24:49 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_15.pth is removed 2022/12/20 17:24:50 - mmengine - INFO - The best checkpoint with 0.8731 acc/top1 at 16 epoch is saved to best_acc/top1_epoch_16.pth.