2022/09/15 15:24:55 - mmengine - INFO - ------------------------------------------------------------ System environment: sys.platform: linux Python: 3.7.13 (default, Mar 29 2022, 02:18:16) [GCC 7.5.0] CUDA available: True numpy_random_seed: 2115998043 GPU 0,1,2,3: NVIDIA A100-SXM4-80GB CUDA_HOME: /mnt/cache/share/cuda-11.1 NVCC: Cuda compilation tools, release 11.1, V11.1.74 GCC: gcc (GCC) 5.4.0 PyTorch: 1.9.0+cu111 PyTorch compiling details: PyTorch built with: - GCC 7.3 - C++ Version: 201402 - Intel(R) Math Kernel Library Version 2020.0.0 Product Build 20191122 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v2.1.2 (Git Hash 98be7e8afa711dc9b66c8ff3504129cb82013cdb) - OpenMP 201511 (a.k.a. OpenMP 4.5) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 11.1 - 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_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 - CuDNN 8.0.5 - Magma 2.5.2 - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.1, CUDNN_VERSION=8.0.5, 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 -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-variable -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=1.9.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, TorchVision: 0.10.0+cu111 OpenCV: 4.5.4 MMEngine: 0.1.0 Runtime environment: cudnn_benchmark: True mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0} dist_cfg: {'backend': 'nccl'} seed: None Distributed launcher: slurm Distributed training: True GPU number: 4 ------------------------------------------------------------ 2022/09/15 15:24:58 - mmengine - INFO - Config: mj_rec_data_root = 'data/rec/Syn90k/' mj_rec_train = dict( type='OCRDataset', data_root='data/rec/Syn90k/', data_prefix=dict(img_path='mnt/ramdisk/max/90kDICT32px'), ann_file='train_labels.json', test_mode=False, pipeline=None) mj_sub_rec_train = dict( type='OCRDataset', data_root='data/rec/Syn90k/', data_prefix=dict(img_path='mnt/ramdisk/max/90kDICT32px'), ann_file='subset_train_labels.json', test_mode=False, pipeline=None) st_data_root = 'data/rec/SynthText/' st_rec_train = dict( type='OCRDataset', data_root='data/rec/SynthText/', data_prefix=dict(img_path='synthtext/SynthText_patch_horizontal'), ann_file='train_labels.json', test_mode=False, pipeline=None) st_an_rec_train = dict( type='OCRDataset', data_root='data/rec/SynthText/', data_prefix=dict(img_path='synthtext/SynthText_patch_horizontal'), ann_file='alphanumeric_train_labels.json', test_mode=False, pipeline=None) st_sub_rec_train = dict( type='OCRDataset', data_root='data/rec/SynthText/', data_prefix=dict(img_path='synthtext/SynthText_patch_horizontal'), ann_file='subset_train_labels.json', test_mode=False, pipeline=None) st_add_rec_data_root = 'data/rec/synthtext_add/' st_add_rec_train = dict( type='OCRDataset', data_root='data/rec/synthtext_add/', ann_file='train_labels.json', test_mode=False, pipeline=None) cocov1_rec_train_data_root = 'data/rec/coco_text_v1' cocov1_rec_train = dict( type='OCRDataset', data_root='data/rec/coco_text_v1', ann_file='train_labels.json', test_mode=False, pipeline=None) cute80_rec_data_root = 'data/rec/ct80/' cute80_rec_test = dict( type='OCRDataset', data_root='data/rec/ct80/', ann_file='test_labels.json', test_mode=True, pipeline=None) iiit5k_rec_data_root = 'data/rec/IIIT5K/' iiit5k_rec_train = dict( type='OCRDataset', data_root='data/rec/IIIT5K/', ann_file='train_labels.json', test_mode=False, pipeline=None) iiit5k_rec_test = dict( type='OCRDataset', data_root='data/rec/IIIT5K/', ann_file='test_labels.json', test_mode=True, pipeline=None) svt_rec_data_root = 'data/rec/svt/' svt_rec_test = dict( type='OCRDataset', data_root='data/rec/svt/', ann_file='test_labels.json', test_mode=True, pipeline=None) svtp_rec_data_root = 'data/rec/svtp/' svtp_rec_test = dict( type='OCRDataset', data_root='data/rec/svtp/', ann_file='test_labels.json', test_mode=True, pipeline=None) ic11_rec_data_root = 'data/rec/icdar_2011/' ic11_rec_train = dict( type='OCRDataset', data_root='data/rec/icdar_2011/', ann_file='train_labels.json', test_mode=False, pipeline=None) ic13_rec_data_root = 'data/rec/icdar_2013/' ic13_rec_train = dict( type='OCRDataset', data_root='data/rec/icdar_2013/', ann_file='train_labels.json', test_mode=False, pipeline=None) ic13_rec_test = dict( type='OCRDataset', data_root='data/rec/icdar_2013/', ann_file='test_labels.json', test_mode=True, pipeline=None) ic15_rec_data_root = 'data/rec/icdar_2015/' ic15_rec_train = dict( type='OCRDataset', data_root='data/rec/icdar_2015/', ann_file='train_labels.json', test_mode=False, pipeline=None) ic15_rec_test = dict( type='OCRDataset', data_root='data/rec/icdar_2015/', ann_file='test_labels.json', test_mode=True, pipeline=None) default_scope = 'mmocr' env_cfg = dict( cudnn_benchmark=True, mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0), dist_cfg=dict(backend='nccl')) randomness = dict(seed=None) default_hooks = dict( timer=dict(type='IterTimerHook'), logger=dict(type='LoggerHook', interval=100), param_scheduler=dict(type='ParamSchedulerHook'), checkpoint=dict( type='CheckpointHook', interval=1, out_dir='sproject:s3://1.0.0rc0_recog_retest'), sampler_seed=dict(type='DistSamplerSeedHook'), sync_buffer=dict(type='SyncBuffersHook'), visualization=dict( type='VisualizationHook', interval=1, enable=False, show=False, draw_gt=False, draw_pred=False)) log_level = 'INFO' log_processor = dict(type='LogProcessor', window_size=10, by_epoch=True) load_from = None resume = False val_evaluator = dict( type='MultiDatasetsEvaluator', metrics=[dict(type='WordMetric', mode=['ignore_case_symbol'])], dataset_prefixes=['CUTE80', 'IIIT5K', 'SVT', 'SVTP', 'IC13', 'IC15']) test_evaluator = dict( type='MultiDatasetsEvaluator', metrics=[dict(type='WordMetric', mode=['ignore_case_symbol'])], dataset_prefixes=['CUTE80', 'IIIT5K', 'SVT', 'SVTP', 'IC13', 'IC15']) vis_backends = [dict(type='LocalVisBackend')] visualizer = dict( type='TextRecogLocalVisualizer', name='visualizer', vis_backends=[dict(type='LocalVisBackend')]) optim_wrapper = dict( type='OptimWrapper', optimizer=dict(type='Adam', lr=0.001)) train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=5, val_interval=1) val_cfg = dict(type='ValLoop') test_cfg = dict(type='TestLoop') param_scheduler = [dict(type='MultiStepLR', milestones=[3, 4], end=5)] dictionary = dict( type='Dictionary', dict_file= 'configs/textrecog/robust_scanner/../../../dicts/english_digits_symbols.txt', with_start=True, with_end=True, same_start_end=True, with_padding=True, with_unknown=True) model = dict( type='RobustScanner', data_preprocessor=dict( type='TextRecogDataPreprocessor', mean=[127, 127, 127], std=[127, 127, 127]), backbone=dict(type='ResNet31OCR'), encoder=dict( type='ChannelReductionEncoder', in_channels=512, out_channels=128), decoder=dict( type='RobustScannerFuser', hybrid_decoder=dict( type='SequenceAttentionDecoder', dim_input=512, dim_model=128), position_decoder=dict( type='PositionAttentionDecoder', dim_input=512, dim_model=128), in_channels=[512, 512], postprocessor=dict(type='AttentionPostprocessor'), module_loss=dict( type='CEModuleLoss', ignore_first_char=True, reduction='mean'), dictionary=dict( type='Dictionary', dict_file= 'configs/textrecog/robust_scanner/../../../dicts/english_digits_symbols.txt', with_start=True, with_end=True, same_start_end=True, with_padding=True, with_unknown=True), max_seq_len=30)) file_client_args = dict(backend='disk') train_pipeline = [ dict( type='LoadImageFromFile', file_client_args=dict(backend='disk'), ignore_empty=True, min_size=2), dict(type='LoadOCRAnnotations', with_text=True), dict( type='RescaleToHeight', height=48, min_width=48, max_width=160, width_divisor=4), dict(type='PadToWidth', width=160), dict( type='PackTextRecogInputs', meta_keys=('img_path', 'ori_shape', 'img_shape', 'valid_ratio')) ] test_pipeline = [ dict(type='LoadImageFromFile', file_client_args=dict(backend='disk')), dict( type='RescaleToHeight', height=48, min_width=48, max_width=160, width_divisor=4), dict(type='PadToWidth', width=160), dict(type='LoadOCRAnnotations', with_text=True), dict( type='PackTextRecogInputs', meta_keys=('img_path', 'ori_shape', 'img_shape', 'valid_ratio')) ] train_list = [ dict( type='RepeatDataset', dataset=dict( type='ConcatDataset', datasets=[ dict( type='OCRDataset', data_root='data/rec/icdar_2011/', ann_file='train_labels.json', test_mode=False, pipeline=None), dict( type='OCRDataset', data_root='data/rec/icdar_2013/', ann_file='train_labels.json', test_mode=False, pipeline=None), dict( type='OCRDataset', data_root='data/rec/icdar_2015/', ann_file='train_labels.json', test_mode=False, pipeline=None), dict( type='OCRDataset', data_root='data/rec/coco_text_v1', ann_file='train_labels.json', test_mode=False, pipeline=None), dict( type='OCRDataset', data_root='data/rec/IIIT5K/', ann_file='train_labels.json', test_mode=False, pipeline=None) ], pipeline=[ dict( type='LoadImageFromFile', file_client_args=dict(backend='disk'), ignore_empty=True, min_size=2), dict(type='LoadOCRAnnotations', with_text=True), dict( type='RescaleToHeight', height=48, min_width=48, max_width=160, width_divisor=4), dict(type='PadToWidth', width=160), dict( type='PackTextRecogInputs', meta_keys=('img_path', 'ori_shape', 'img_shape', 'valid_ratio')) ]), times=20), dict( type='ConcatDataset', datasets=[ dict( type='OCRDataset', data_root='data/rec/Syn90k/', data_prefix=dict(img_path='mnt/ramdisk/max/90kDICT32px'), ann_file='subset_train_labels.json', test_mode=False, pipeline=None), dict( type='OCRDataset', data_root='data/rec/SynthText/', data_prefix=dict( img_path='synthtext/SynthText_patch_horizontal'), ann_file='subset_train_labels.json', test_mode=False, pipeline=None), dict( type='OCRDataset', data_root='data/rec/synthtext_add/', ann_file='train_labels.json', test_mode=False, pipeline=None) ], pipeline=[ dict( type='LoadImageFromFile', file_client_args=dict(backend='disk'), ignore_empty=True, min_size=2), dict(type='LoadOCRAnnotations', with_text=True), dict( type='RescaleToHeight', height=48, min_width=48, max_width=160, width_divisor=4), dict(type='PadToWidth', width=160), dict( type='PackTextRecogInputs', meta_keys=('img_path', 'ori_shape', 'img_shape', 'valid_ratio')) ]) ] test_list = [ dict( type='OCRDataset', data_root='data/rec/ct80/', ann_file='test_labels.json', test_mode=True, pipeline=None), dict( type='OCRDataset', data_root='data/rec/IIIT5K/', ann_file='test_labels.json', test_mode=True, pipeline=None), dict( type='OCRDataset', data_root='data/rec/svt/', ann_file='test_labels.json', test_mode=True, pipeline=None), dict( type='OCRDataset', data_root='data/rec/svtp/', ann_file='test_labels.json', test_mode=True, pipeline=None), dict( type='OCRDataset', data_root='data/rec/icdar_2013/', ann_file='test_labels.json', test_mode=True, pipeline=None), dict( type='OCRDataset', data_root='data/rec/icdar_2015/', ann_file='test_labels.json', test_mode=True, pipeline=None) ] train_dataloader = dict( batch_size=256, num_workers=24, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=True), dataset=dict( type='ConcatDataset', datasets=[ dict( type='RepeatDataset', dataset=dict( type='ConcatDataset', datasets=[ dict( type='OCRDataset', data_root= 'openmmlab:s3://openmmlab/datasets/ocr/recog/icdar_2011', ann_file='train_labels.json', test_mode=False, pipeline=None), dict( type='OCRDataset', data_root= 'openmmlab:s3://openmmlab/datasets/ocr/recog/icdar_2013', ann_file='train_labels.json', test_mode=False, pipeline=None), dict( type='OCRDataset', data_root= 'openmmlab:s3://openmmlab/datasets/ocr/recog/icdar_2015', ann_file='train_labels.json', test_mode=False, pipeline=None), dict( type='OCRDataset', data_root= 'openmmlab:s3://openmmlab/datasets/ocr/recog/coco_text_v1', ann_file='train_labels.json', test_mode=False, pipeline=None), dict( type='OCRDataset', data_root= 'openmmlab:s3://openmmlab/datasets/ocr/recog/IIIT5K', ann_file='train_labels.json', test_mode=False, pipeline=None) ], pipeline=[ dict( type='LoadImageFromFile', file_client_args=dict(backend='petrel'), ignore_empty=True, min_size=2), dict(type='LoadOCRAnnotations', with_text=True), dict( type='RescaleToHeight', height=48, min_width=48, max_width=160, width_divisor=4), dict(type='PadToWidth', width=160), dict( type='PackTextRecogInputs', meta_keys=('img_path', 'ori_shape', 'img_shape', 'valid_ratio')) ]), times=20), dict( type='ConcatDataset', datasets=[ dict( type='OCRDataset', data_root= 'openmmlab:s3://openmmlab/datasets/ocr/recog/Syn90k', data_prefix=dict( img_path='mnt/ramdisk/max/90kDICT32px'), ann_file='subset_train_labels.json', test_mode=False, pipeline=None), dict( type='OCRDataset', data_root= 'openmmlab:s3://openmmlab/datasets/ocr/recog/SynthText', data_prefix=dict( img_path='synthtext/SynthText_patch_horizontal'), ann_file='subset_train_labels.json', test_mode=False, pipeline=None), dict( type='OCRDataset', data_root= 'openmmlab:s3://openmmlab/datasets/ocr/recog/synthtext_add', ann_file='train_labels.json', test_mode=False, pipeline=None) ], pipeline=[ dict( type='LoadImageFromFile', file_client_args=dict(backend='petrel'), ignore_empty=True, min_size=2), dict(type='LoadOCRAnnotations', with_text=True), dict( type='RescaleToHeight', height=48, min_width=48, max_width=160, width_divisor=4), dict(type='PadToWidth', width=160), dict( type='PackTextRecogInputs', meta_keys=('img_path', 'ori_shape', 'img_shape', 'valid_ratio')) ]) ], verify_meta=False)) test_dataloader = dict( batch_size=1, num_workers=4, persistent_workers=True, drop_last=False, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='ConcatDataset', datasets=[ dict( type='OCRDataset', data_root='openmmlab:s3://openmmlab/datasets/ocr/recog/ct80', ann_file='test_labels.json', test_mode=True, pipeline=None), dict( type='OCRDataset', data_root='openmmlab:s3://openmmlab/datasets/ocr/recog/IIIT5K', ann_file='test_labels.json', test_mode=True, pipeline=None), dict( type='OCRDataset', data_root='openmmlab:s3://openmmlab/datasets/ocr/recog/svt', ann_file='test_labels.json', test_mode=True, pipeline=None), dict( type='OCRDataset', data_root='openmmlab:s3://openmmlab/datasets/ocr/recog/svtp', ann_file='test_labels.json', test_mode=True, pipeline=None), dict( type='OCRDataset', data_root= 'openmmlab:s3://openmmlab/datasets/ocr/recog/icdar_2013', ann_file='test_labels.json', test_mode=True, pipeline=None), dict( type='OCRDataset', data_root= 'openmmlab:s3://openmmlab/datasets/ocr/recog/icdar_2015', ann_file='test_labels.json', test_mode=True, pipeline=None) ], pipeline=[ dict( type='LoadImageFromFile', file_client_args=dict(backend='petrel')), dict( type='RescaleToHeight', height=48, min_width=48, max_width=160, width_divisor=4), dict(type='PadToWidth', width=160), dict(type='LoadOCRAnnotations', with_text=True), dict( type='PackTextRecogInputs', meta_keys=('img_path', 'ori_shape', 'img_shape', 'valid_ratio')) ])) val_dataloader = dict( batch_size=1, num_workers=4, persistent_workers=True, drop_last=False, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='ConcatDataset', datasets=[ dict( type='OCRDataset', data_root='openmmlab:s3://openmmlab/datasets/ocr/recog/ct80', ann_file='test_labels.json', test_mode=True, pipeline=None), dict( type='OCRDataset', data_root='openmmlab:s3://openmmlab/datasets/ocr/recog/IIIT5K', ann_file='test_labels.json', test_mode=True, pipeline=None), dict( type='OCRDataset', data_root='openmmlab:s3://openmmlab/datasets/ocr/recog/svt', ann_file='test_labels.json', test_mode=True, pipeline=None), dict( type='OCRDataset', data_root='openmmlab:s3://openmmlab/datasets/ocr/recog/svtp', ann_file='test_labels.json', test_mode=True, pipeline=None), dict( type='OCRDataset', data_root= 'openmmlab:s3://openmmlab/datasets/ocr/recog/icdar_2013', ann_file='test_labels.json', test_mode=True, pipeline=None), dict( type='OCRDataset', data_root= 'openmmlab:s3://openmmlab/datasets/ocr/recog/icdar_2015', ann_file='test_labels.json', test_mode=True, pipeline=None) ], pipeline=[ dict( type='LoadImageFromFile', file_client_args=dict(backend='petrel')), dict( type='RescaleToHeight', height=48, min_width=48, max_width=160, width_divisor=4), dict(type='PadToWidth', width=160), dict(type='LoadOCRAnnotations', with_text=True), dict( type='PackTextRecogInputs', meta_keys=('img_path', 'ori_shape', 'img_shape', 'valid_ratio')) ])) launcher = 'slurm' work_dir = './work_dirs/robustscanner_resnet31_5e_st-sub_mj-sub_sa_real' Name of parameter - Initialization information backbone.conv1_1.weight - torch.Size([64, 3, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.conv1_1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.bn1_1.weight - torch.Size([64]): UniformInit: a=0, b=1, bias=0 backbone.bn1_1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RobustScanner backbone.conv1_2.weight - torch.Size([128, 64, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.conv1_2.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.bn1_2.weight - torch.Size([128]): UniformInit: a=0, b=1, bias=0 backbone.bn1_2.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RobustScanner backbone.block2.0.conv1.weight - torch.Size([256, 128, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.block2.0.conv2.weight - torch.Size([256, 256, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.block2.0.bn1.weight - torch.Size([256]): UniformInit: a=0, b=1, bias=0 backbone.block2.0.bn1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RobustScanner backbone.block2.0.bn2.weight - torch.Size([256]): UniformInit: a=0, b=1, bias=0 backbone.block2.0.bn2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RobustScanner backbone.block2.0.downsample.0.weight - torch.Size([256, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.block2.0.downsample.1.weight - torch.Size([256]): UniformInit: a=0, b=1, bias=0 backbone.block2.0.downsample.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RobustScanner backbone.conv2.weight - torch.Size([256, 256, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.conv2.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.bn2.weight - torch.Size([256]): UniformInit: a=0, b=1, bias=0 backbone.bn2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RobustScanner backbone.block3.0.conv1.weight - torch.Size([256, 256, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.block3.0.conv2.weight - torch.Size([256, 256, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.block3.0.bn1.weight - torch.Size([256]): UniformInit: a=0, b=1, bias=0 backbone.block3.0.bn1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RobustScanner backbone.block3.0.bn2.weight - torch.Size([256]): UniformInit: a=0, b=1, bias=0 backbone.block3.0.bn2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RobustScanner backbone.block3.1.conv1.weight - torch.Size([256, 256, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.block3.1.conv2.weight - torch.Size([256, 256, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.block3.1.bn1.weight - torch.Size([256]): UniformInit: a=0, b=1, bias=0 backbone.block3.1.bn1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RobustScanner backbone.block3.1.bn2.weight - torch.Size([256]): UniformInit: a=0, b=1, bias=0 backbone.block3.1.bn2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RobustScanner backbone.conv3.weight - torch.Size([256, 256, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.conv3.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.bn3.weight - torch.Size([256]): UniformInit: a=0, b=1, bias=0 backbone.bn3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RobustScanner backbone.block4.0.conv1.weight - torch.Size([512, 256, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.block4.0.conv2.weight - torch.Size([512, 512, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.block4.0.bn1.weight - torch.Size([512]): UniformInit: a=0, b=1, bias=0 backbone.block4.0.bn1.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of RobustScanner backbone.block4.0.bn2.weight - torch.Size([512]): UniformInit: a=0, b=1, bias=0 backbone.block4.0.bn2.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of RobustScanner backbone.block4.0.downsample.0.weight - torch.Size([512, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.block4.0.downsample.1.weight - torch.Size([512]): UniformInit: a=0, b=1, bias=0 backbone.block4.0.downsample.1.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of RobustScanner backbone.block4.1.conv1.weight - torch.Size([512, 512, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.block4.1.conv2.weight - torch.Size([512, 512, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.block4.1.bn1.weight - torch.Size([512]): UniformInit: a=0, b=1, bias=0 backbone.block4.1.bn1.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of RobustScanner backbone.block4.1.bn2.weight - torch.Size([512]): UniformInit: a=0, b=1, bias=0 backbone.block4.1.bn2.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of RobustScanner backbone.block4.2.conv1.weight - torch.Size([512, 512, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.block4.2.conv2.weight - torch.Size([512, 512, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.block4.2.bn1.weight - torch.Size([512]): UniformInit: a=0, b=1, bias=0 backbone.block4.2.bn1.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of RobustScanner backbone.block4.2.bn2.weight - torch.Size([512]): UniformInit: a=0, b=1, bias=0 backbone.block4.2.bn2.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of RobustScanner backbone.block4.3.conv1.weight - torch.Size([512, 512, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.block4.3.conv2.weight - torch.Size([512, 512, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.block4.3.bn1.weight - torch.Size([512]): UniformInit: a=0, b=1, bias=0 backbone.block4.3.bn1.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of RobustScanner backbone.block4.3.bn2.weight - torch.Size([512]): UniformInit: a=0, b=1, bias=0 backbone.block4.3.bn2.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of RobustScanner backbone.block4.4.conv1.weight - torch.Size([512, 512, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.block4.4.conv2.weight - torch.Size([512, 512, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.block4.4.bn1.weight - torch.Size([512]): UniformInit: a=0, b=1, bias=0 backbone.block4.4.bn1.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of RobustScanner backbone.block4.4.bn2.weight - torch.Size([512]): UniformInit: a=0, b=1, bias=0 backbone.block4.4.bn2.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of RobustScanner backbone.conv4.weight - torch.Size([512, 512, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.conv4.bias - torch.Size([512]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.bn4.weight - torch.Size([512]): UniformInit: a=0, b=1, bias=0 backbone.bn4.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of RobustScanner backbone.block5.0.conv1.weight - torch.Size([512, 512, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.block5.0.conv2.weight - torch.Size([512, 512, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.block5.0.bn1.weight - torch.Size([512]): UniformInit: a=0, b=1, bias=0 backbone.block5.0.bn1.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of RobustScanner backbone.block5.0.bn2.weight - torch.Size([512]): UniformInit: a=0, b=1, bias=0 backbone.block5.0.bn2.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of RobustScanner backbone.block5.1.conv1.weight - torch.Size([512, 512, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.block5.1.conv2.weight - torch.Size([512, 512, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.block5.1.bn1.weight - torch.Size([512]): UniformInit: a=0, b=1, bias=0 backbone.block5.1.bn1.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of RobustScanner backbone.block5.1.bn2.weight - torch.Size([512]): UniformInit: a=0, b=1, bias=0 backbone.block5.1.bn2.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of RobustScanner backbone.block5.2.conv1.weight - torch.Size([512, 512, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.block5.2.conv2.weight - torch.Size([512, 512, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.block5.2.bn1.weight - torch.Size([512]): UniformInit: a=0, b=1, bias=0 backbone.block5.2.bn1.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of RobustScanner backbone.block5.2.bn2.weight - torch.Size([512]): UniformInit: a=0, b=1, bias=0 backbone.block5.2.bn2.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of RobustScanner backbone.conv5.weight - torch.Size([512, 512, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.conv5.bias - torch.Size([512]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.bn5.weight - torch.Size([512]): UniformInit: a=0, b=1, bias=0 backbone.bn5.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of RobustScanner encoder.layer.weight - torch.Size([128, 512, 1, 1]): XavierInit: gain=1, distribution=normal, bias=0 encoder.layer.bias - torch.Size([128]): XavierInit: gain=1, distribution=normal, bias=0 decoder.hybrid_decoder.embedding.weight - torch.Size([93, 128]): The value is the same before and after calling `init_weights` of RobustScanner decoder.hybrid_decoder.sequence_layer.weight_ih_l0 - torch.Size([512, 128]): The value is the same before and after calling `init_weights` of RobustScanner decoder.hybrid_decoder.sequence_layer.weight_hh_l0 - torch.Size([512, 128]): The value is the same before and after calling `init_weights` of RobustScanner decoder.hybrid_decoder.sequence_layer.bias_ih_l0 - torch.Size([512]): The value is the same before and after calling `init_weights` of RobustScanner decoder.hybrid_decoder.sequence_layer.bias_hh_l0 - torch.Size([512]): The value is the same before and after calling `init_weights` of RobustScanner decoder.hybrid_decoder.sequence_layer.weight_ih_l1 - torch.Size([512, 128]): The value is the same before and after calling `init_weights` of RobustScanner decoder.hybrid_decoder.sequence_layer.weight_hh_l1 - torch.Size([512, 128]): The value is the same before and after calling `init_weights` of RobustScanner decoder.hybrid_decoder.sequence_layer.bias_ih_l1 - torch.Size([512]): The value is the same before and after calling `init_weights` of RobustScanner decoder.hybrid_decoder.sequence_layer.bias_hh_l1 - torch.Size([512]): The value is the same before and after calling `init_weights` of RobustScanner decoder.position_decoder.embedding.weight - torch.Size([31, 128]): The value is the same before and after calling `init_weights` of RobustScanner decoder.position_decoder.position_aware_module.rnn.weight_ih_l0 - torch.Size([512, 128]): The value is the same before and after calling `init_weights` of RobustScanner decoder.position_decoder.position_aware_module.rnn.weight_hh_l0 - torch.Size([512, 128]): The value is the same before and after calling `init_weights` of RobustScanner decoder.position_decoder.position_aware_module.rnn.bias_ih_l0 - torch.Size([512]): The value is the same before and after calling `init_weights` of RobustScanner decoder.position_decoder.position_aware_module.rnn.bias_hh_l0 - torch.Size([512]): The value is the same before and after calling `init_weights` of RobustScanner decoder.position_decoder.position_aware_module.rnn.weight_ih_l1 - torch.Size([512, 128]): The value is the same before and after calling `init_weights` of RobustScanner decoder.position_decoder.position_aware_module.rnn.weight_hh_l1 - torch.Size([512, 128]): The value is the same before and after calling `init_weights` of RobustScanner decoder.position_decoder.position_aware_module.rnn.bias_ih_l1 - torch.Size([512]): The value is the same before and after calling `init_weights` of RobustScanner decoder.position_decoder.position_aware_module.rnn.bias_hh_l1 - torch.Size([512]): The value is the same before and after calling `init_weights` of RobustScanner decoder.position_decoder.position_aware_module.mixer.0.weight - torch.Size([128, 128, 3, 3]): The value is the same before and after calling `init_weights` of RobustScanner decoder.position_decoder.position_aware_module.mixer.0.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RobustScanner decoder.position_decoder.position_aware_module.mixer.2.weight - torch.Size([128, 128, 3, 3]): The value is the same before and after calling `init_weights` of RobustScanner decoder.position_decoder.position_aware_module.mixer.2.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RobustScanner decoder.linear_layer.weight - torch.Size([1024, 1024]): The value is the same before and after calling `init_weights` of RobustScanner decoder.linear_layer.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of RobustScanner decoder.prediction.weight - torch.Size([93, 512]): The value is the same before and after calling `init_weights` of RobustScanner decoder.prediction.bias - torch.Size([93]): The value is the same before and after calling `init_weights` of RobustScanner 2022/09/15 15:26:55 - mmengine - INFO - Checkpoints will be saved to sproject:s3://1.0.0rc0_recog_retest/robustscanner_resnet31_5e_st-sub_mj-sub_sa_real by PetrelBackend. 2022/09/15 15:39:34 - mmengine - INFO - Epoch(train) [1][100/6912] lr: 1.0000e-03 eta: 3 days, 0:39:57 time: 0.6658 data_time: 0.0607 memory: 28705 loss_ce: 2.7341 loss: 2.7341 2022/09/15 15:40:34 - mmengine - INFO - Epoch(train) [1][200/6912] lr: 1.0000e-03 eta: 1 day, 15:05:08 time: 0.7542 data_time: 0.1538 memory: 15027 loss_ce: 2.5022 loss: 2.5022 2022/09/15 15:41:32 - mmengine - INFO - Epoch(train) [1][300/6912] lr: 1.0000e-03 eta: 1 day, 3:49:59 time: 0.6365 data_time: 0.1390 memory: 15027 loss_ce: 2.3090 loss: 2.3090 2022/09/15 15:42:30 - mmengine - INFO - Epoch(train) [1][400/6912] lr: 1.0000e-03 eta: 22:11:34 time: 0.5132 data_time: 0.0419 memory: 15027 loss_ce: 1.4760 loss: 1.4760 2022/09/15 15:43:31 - mmengine - INFO - Epoch(train) [1][500/6912] lr: 1.0000e-03 eta: 18:51:26 time: 0.7810 data_time: 0.0190 memory: 15027 loss_ce: 0.8790 loss: 0.8790 2022/09/15 15:44:30 - mmengine - INFO - Epoch(train) [1][600/6912] lr: 1.0000e-03 eta: 16:35:11 time: 0.4770 data_time: 0.0108 memory: 15027 loss_ce: 0.7241 loss: 0.7241 2022/09/15 15:45:30 - mmengine - INFO - Epoch(train) [1][700/6912] lr: 1.0000e-03 eta: 14:58:44 time: 0.6321 data_time: 0.0587 memory: 15027 loss_ce: 0.6050 loss: 0.6050 2022/09/15 15:46:31 - mmengine - INFO - Epoch(train) [1][800/6912] lr: 1.0000e-03 eta: 13:47:01 time: 0.9288 data_time: 0.2225 memory: 15027 loss_ce: 0.5152 loss: 0.5152 2022/09/15 15:47:29 - mmengine - INFO - Epoch(train) [1][900/6912] lr: 1.0000e-03 eta: 12:49:08 time: 0.6059 data_time: 0.1113 memory: 15027 loss_ce: 0.5184 loss: 0.5184 2022/09/15 15:48:27 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 15:48:27 - mmengine - INFO - Epoch(train) [1][1000/6912] lr: 1.0000e-03 eta: 12:02:43 time: 0.4638 data_time: 0.0158 memory: 15027 loss_ce: 0.4573 loss: 0.4573 2022/09/15 15:49:26 - mmengine - INFO - Epoch(train) [1][1100/6912] lr: 1.0000e-03 eta: 11:24:52 time: 0.4595 data_time: 0.0152 memory: 15027 loss_ce: 0.4457 loss: 0.4457 2022/09/15 15:50:25 - mmengine - INFO - Epoch(train) [1][1200/6912] lr: 1.0000e-03 eta: 10:53:19 time: 0.5325 data_time: 0.0291 memory: 15027 loss_ce: 0.4105 loss: 0.4105 2022/09/15 15:51:26 - mmengine - INFO - Epoch(train) [1][1300/6912] lr: 1.0000e-03 eta: 10:27:06 time: 0.6414 data_time: 0.0632 memory: 15027 loss_ce: 0.4258 loss: 0.4258 2022/09/15 15:52:27 - mmengine - INFO - Epoch(train) [1][1400/6912] lr: 1.0000e-03 eta: 10:04:43 time: 0.7907 data_time: 0.1596 memory: 15027 loss_ce: 0.3997 loss: 0.3997 2022/09/15 15:53:25 - mmengine - INFO - Epoch(train) [1][1500/6912] lr: 1.0000e-03 eta: 9:44:11 time: 0.6117 data_time: 0.1193 memory: 15027 loss_ce: 0.3503 loss: 0.3503 2022/09/15 15:54:23 - mmengine - INFO - Epoch(train) [1][1600/6912] lr: 1.0000e-03 eta: 9:26:00 time: 0.4454 data_time: 0.0170 memory: 15027 loss_ce: 0.3678 loss: 0.3678 2022/09/15 15:55:23 - mmengine - INFO - Epoch(train) [1][1700/6912] lr: 1.0000e-03 eta: 9:10:08 time: 0.4929 data_time: 0.0535 memory: 15027 loss_ce: 0.3916 loss: 0.3916 2022/09/15 15:56:22 - mmengine - INFO - Epoch(train) [1][1800/6912] lr: 1.0000e-03 eta: 8:55:53 time: 0.4823 data_time: 0.0092 memory: 15027 loss_ce: 0.3661 loss: 0.3661 2022/09/15 15:57:22 - mmengine - INFO - Epoch(train) [1][1900/6912] lr: 1.0000e-03 eta: 8:43:31 time: 0.6390 data_time: 0.0637 memory: 15027 loss_ce: 0.3489 loss: 0.3489 2022/09/15 15:58:22 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 15:58:22 - mmengine - INFO - Epoch(train) [1][2000/6912] lr: 1.0000e-03 eta: 8:31:56 time: 0.7415 data_time: 0.1394 memory: 15027 loss_ce: 0.3162 loss: 0.3162 2022/09/15 15:59:20 - mmengine - INFO - Epoch(train) [1][2100/6912] lr: 1.0000e-03 eta: 8:21:03 time: 0.6165 data_time: 0.1366 memory: 15027 loss_ce: 0.3288 loss: 0.3288 2022/09/15 16:00:20 - mmengine - INFO - Epoch(train) [1][2200/6912] lr: 1.0000e-03 eta: 8:11:36 time: 0.4617 data_time: 0.0170 memory: 15027 loss_ce: 0.2925 loss: 0.2925 2022/09/15 16:01:17 - mmengine - INFO - Epoch(train) [1][2300/6912] lr: 1.0000e-03 eta: 8:02:10 time: 0.4585 data_time: 0.0164 memory: 15027 loss_ce: 0.3192 loss: 0.3192 2022/09/15 16:02:16 - mmengine - INFO - Epoch(train) [1][2400/6912] lr: 1.0000e-03 eta: 7:53:42 time: 0.4793 data_time: 0.0104 memory: 15027 loss_ce: 0.2992 loss: 0.2992 2022/09/15 16:03:17 - mmengine - INFO - Epoch(train) [1][2500/6912] lr: 1.0000e-03 eta: 7:46:18 time: 0.6585 data_time: 0.0833 memory: 15027 loss_ce: 0.2967 loss: 0.2967 2022/09/15 16:04:17 - mmengine - INFO - Epoch(train) [1][2600/6912] lr: 1.0000e-03 eta: 7:39:17 time: 0.7378 data_time: 0.1729 memory: 15027 loss_ce: 0.2937 loss: 0.2937 2022/09/15 16:05:16 - mmengine - INFO - Epoch(train) [1][2700/6912] lr: 1.0000e-03 eta: 7:32:29 time: 0.6234 data_time: 0.1383 memory: 15027 loss_ce: 0.2876 loss: 0.2876 2022/09/15 16:06:15 - mmengine - INFO - Epoch(train) [1][2800/6912] lr: 1.0000e-03 eta: 7:26:08 time: 0.4439 data_time: 0.0170 memory: 15027 loss_ce: 0.2755 loss: 0.2755 2022/09/15 16:07:13 - mmengine - INFO - Epoch(train) [1][2900/6912] lr: 1.0000e-03 eta: 7:20:03 time: 0.4892 data_time: 0.0156 memory: 15027 loss_ce: 0.2904 loss: 0.2904 2022/09/15 16:08:12 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 16:08:12 - mmengine - INFO - Epoch(train) [1][3000/6912] lr: 1.0000e-03 eta: 7:14:17 time: 0.5066 data_time: 0.0102 memory: 15027 loss_ce: 0.2778 loss: 0.2778 2022/09/15 16:09:13 - mmengine - INFO - Epoch(train) [1][3100/6912] lr: 1.0000e-03 eta: 7:09:19 time: 0.6675 data_time: 0.0918 memory: 15027 loss_ce: 0.2610 loss: 0.2610 2022/09/15 16:10:13 - mmengine - INFO - Epoch(train) [1][3200/6912] lr: 1.0000e-03 eta: 7:04:16 time: 0.7545 data_time: 0.1603 memory: 15027 loss_ce: 0.2584 loss: 0.2584 2022/09/15 16:11:11 - mmengine - INFO - Epoch(train) [1][3300/6912] lr: 1.0000e-03 eta: 6:59:23 time: 0.6390 data_time: 0.1377 memory: 15027 loss_ce: 0.2701 loss: 0.2701 2022/09/15 16:12:09 - mmengine - INFO - Epoch(train) [1][3400/6912] lr: 1.0000e-03 eta: 6:54:35 time: 0.4465 data_time: 0.0167 memory: 15027 loss_ce: 0.2513 loss: 0.2513 2022/09/15 16:13:08 - mmengine - INFO - Epoch(train) [1][3500/6912] lr: 1.0000e-03 eta: 6:50:09 time: 0.4883 data_time: 0.0183 memory: 15027 loss_ce: 0.2323 loss: 0.2323 2022/09/15 16:14:07 - mmengine - INFO - Epoch(train) [1][3600/6912] lr: 1.0000e-03 eta: 6:45:58 time: 0.4953 data_time: 0.0094 memory: 15027 loss_ce: 0.2596 loss: 0.2596 2022/09/15 16:15:07 - mmengine - INFO - Epoch(train) [1][3700/6912] lr: 1.0000e-03 eta: 6:42:04 time: 0.6343 data_time: 0.0592 memory: 15027 loss_ce: 0.2703 loss: 0.2703 2022/09/15 16:16:06 - mmengine - INFO - Epoch(train) [1][3800/6912] lr: 1.0000e-03 eta: 6:38:11 time: 0.7455 data_time: 0.1566 memory: 15027 loss_ce: 0.2445 loss: 0.2445 2022/09/15 16:17:05 - mmengine - INFO - Epoch(train) [1][3900/6912] lr: 1.0000e-03 eta: 6:34:19 time: 0.6162 data_time: 0.1553 memory: 15027 loss_ce: 0.2075 loss: 0.2075 2022/09/15 16:18:03 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 16:18:03 - mmengine - INFO - Epoch(train) [1][4000/6912] lr: 1.0000e-03 eta: 6:30:41 time: 0.4619 data_time: 0.0186 memory: 15027 loss_ce: 0.2484 loss: 0.2484 2022/09/15 16:19:02 - mmengine - INFO - Epoch(train) [1][4100/6912] lr: 1.0000e-03 eta: 6:27:13 time: 0.4641 data_time: 0.0170 memory: 15027 loss_ce: 0.2388 loss: 0.2388 2022/09/15 16:20:01 - mmengine - INFO - Epoch(train) [1][4200/6912] lr: 1.0000e-03 eta: 6:23:48 time: 0.4702 data_time: 0.0096 memory: 15027 loss_ce: 0.2278 loss: 0.2278 2022/09/15 16:21:00 - mmengine - INFO - Epoch(train) [1][4300/6912] lr: 1.0000e-03 eta: 6:20:36 time: 0.6207 data_time: 0.0713 memory: 15027 loss_ce: 0.2148 loss: 0.2148 2022/09/15 16:21:58 - mmengine - INFO - Epoch(train) [1][4400/6912] lr: 1.0000e-03 eta: 6:17:24 time: 0.6909 data_time: 0.1456 memory: 15027 loss_ce: 0.2177 loss: 0.2177 2022/09/15 16:22:56 - mmengine - INFO - Epoch(train) [1][4500/6912] lr: 1.0000e-03 eta: 6:14:10 time: 0.6354 data_time: 0.1312 memory: 15027 loss_ce: 0.2262 loss: 0.2262 2022/09/15 16:23:53 - mmengine - INFO - Epoch(train) [1][4600/6912] lr: 1.0000e-03 eta: 6:11:02 time: 0.4748 data_time: 0.0317 memory: 15027 loss_ce: 0.2302 loss: 0.2302 2022/09/15 16:24:50 - mmengine - INFO - Epoch(train) [1][4700/6912] lr: 1.0000e-03 eta: 6:07:58 time: 0.4747 data_time: 0.0160 memory: 15027 loss_ce: 0.2378 loss: 0.2378 2022/09/15 16:25:49 - mmengine - INFO - Epoch(train) [1][4800/6912] lr: 1.0000e-03 eta: 6:05:10 time: 0.5081 data_time: 0.0100 memory: 15027 loss_ce: 0.1958 loss: 0.1958 2022/09/15 16:26:48 - mmengine - INFO - Epoch(train) [1][4900/6912] lr: 1.0000e-03 eta: 6:02:28 time: 0.6373 data_time: 0.0727 memory: 15027 loss_ce: 0.2140 loss: 0.2140 2022/09/15 16:27:47 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 16:27:47 - mmengine - INFO - Epoch(train) [1][5000/6912] lr: 1.0000e-03 eta: 5:59:50 time: 0.7457 data_time: 0.1553 memory: 15027 loss_ce: 0.1858 loss: 0.1858 2022/09/15 16:28:46 - mmengine - INFO - Epoch(train) [1][5100/6912] lr: 1.0000e-03 eta: 5:57:14 time: 0.6626 data_time: 0.1315 memory: 15027 loss_ce: 0.2028 loss: 0.2028 2022/09/15 16:29:43 - mmengine - INFO - Epoch(train) [1][5200/6912] lr: 1.0000e-03 eta: 5:54:36 time: 0.4683 data_time: 0.0155 memory: 15027 loss_ce: 0.1907 loss: 0.1907 2022/09/15 16:30:41 - mmengine - INFO - Epoch(train) [1][5300/6912] lr: 1.0000e-03 eta: 5:52:03 time: 0.4893 data_time: 0.0150 memory: 15027 loss_ce: 0.2148 loss: 0.2148 2022/09/15 16:31:39 - mmengine - INFO - Epoch(train) [1][5400/6912] lr: 1.0000e-03 eta: 5:49:33 time: 0.4845 data_time: 0.0092 memory: 15027 loss_ce: 0.2157 loss: 0.2157 2022/09/15 16:32:39 - mmengine - INFO - Epoch(train) [1][5500/6912] lr: 1.0000e-03 eta: 5:47:17 time: 0.6439 data_time: 0.0608 memory: 15027 loss_ce: 0.2165 loss: 0.2165 2022/09/15 16:33:38 - mmengine - INFO - Epoch(train) [1][5600/6912] lr: 1.0000e-03 eta: 5:45:03 time: 0.7598 data_time: 0.1548 memory: 15027 loss_ce: 0.2048 loss: 0.2048 2022/09/15 16:34:36 - mmengine - INFO - Epoch(train) [1][5700/6912] lr: 1.0000e-03 eta: 5:42:42 time: 0.6299 data_time: 0.1366 memory: 15027 loss_ce: 0.1911 loss: 0.1911 2022/09/15 16:35:35 - mmengine - INFO - Epoch(train) [1][5800/6912] lr: 1.0000e-03 eta: 5:40:30 time: 0.4545 data_time: 0.0168 memory: 15027 loss_ce: 0.1953 loss: 0.1953 2022/09/15 16:36:33 - mmengine - INFO - Epoch(train) [1][5900/6912] lr: 1.0000e-03 eta: 5:38:15 time: 0.4698 data_time: 0.0282 memory: 15027 loss_ce: 0.1838 loss: 0.1838 2022/09/15 16:37:31 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 16:37:31 - mmengine - INFO - Epoch(train) [1][6000/6912] lr: 1.0000e-03 eta: 5:36:05 time: 0.4822 data_time: 0.0094 memory: 15027 loss_ce: 0.2024 loss: 0.2024 2022/09/15 16:38:34 - mmengine - INFO - Epoch(train) [1][6100/6912] lr: 1.0000e-03 eta: 5:34:15 time: 0.7023 data_time: 0.0669 memory: 15027 loss_ce: 0.1932 loss: 0.1932 2022/09/15 16:39:33 - mmengine - INFO - Epoch(train) [1][6200/6912] lr: 1.0000e-03 eta: 5:32:15 time: 0.7692 data_time: 0.1916 memory: 15027 loss_ce: 0.2202 loss: 0.2202 2022/09/15 16:40:32 - mmengine - INFO - Epoch(train) [1][6300/6912] lr: 1.0000e-03 eta: 5:30:11 time: 0.6132 data_time: 0.1324 memory: 15027 loss_ce: 0.1834 loss: 0.1834 2022/09/15 16:41:30 - mmengine - INFO - Epoch(train) [1][6400/6912] lr: 1.0000e-03 eta: 5:28:11 time: 0.4396 data_time: 0.0173 memory: 15027 loss_ce: 0.1665 loss: 0.1665 2022/09/15 16:42:28 - mmengine - INFO - Epoch(train) [1][6500/6912] lr: 1.0000e-03 eta: 5:26:07 time: 0.4584 data_time: 0.0156 memory: 15027 loss_ce: 0.1950 loss: 0.1950 2022/09/15 16:43:26 - mmengine - INFO - Epoch(train) [1][6600/6912] lr: 1.0000e-03 eta: 5:24:08 time: 0.4992 data_time: 0.0087 memory: 15027 loss_ce: 0.1688 loss: 0.1688 2022/09/15 16:44:27 - mmengine - INFO - Epoch(train) [1][6700/6912] lr: 1.0000e-03 eta: 5:22:24 time: 0.6495 data_time: 0.0667 memory: 15027 loss_ce: 0.1867 loss: 0.1867 2022/09/15 16:45:26 - mmengine - INFO - Epoch(train) [1][6800/6912] lr: 1.0000e-03 eta: 5:20:32 time: 0.7183 data_time: 0.1528 memory: 15027 loss_ce: 0.1654 loss: 0.1654 2022/09/15 16:46:22 - mmengine - INFO - Epoch(train) [1][6900/6912] lr: 1.0000e-03 eta: 5:18:31 time: 0.5404 data_time: 0.1029 memory: 15027 loss_ce: 0.1764 loss: 0.1764 2022/09/15 16:46:30 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 16:46:30 - mmengine - INFO - Saving checkpoint at 1 epochs 2022/09/15 16:49:39 - mmengine - INFO - Epoch(val) [1][100/1918] eta: 0:01:22 time: 0.0452 data_time: 0.0006 memory: 18683 2022/09/15 16:49:43 - mmengine - INFO - Epoch(val) [1][200/1918] eta: 0:01:31 time: 0.0532 data_time: 0.0019 memory: 951 2022/09/15 16:49:48 - mmengine - INFO - Epoch(val) [1][300/1918] eta: 0:01:13 time: 0.0454 data_time: 0.0007 memory: 951 2022/09/15 16:49:53 - mmengine - INFO - Epoch(val) [1][400/1918] eta: 0:01:07 time: 0.0447 data_time: 0.0006 memory: 951 2022/09/15 16:49:58 - mmengine - INFO - Epoch(val) [1][500/1918] eta: 0:01:07 time: 0.0476 data_time: 0.0006 memory: 951 2022/09/15 16:50:03 - mmengine - INFO - Epoch(val) [1][600/1918] eta: 0:01:05 time: 0.0499 data_time: 0.0011 memory: 951 2022/09/15 16:50:08 - mmengine - INFO - Epoch(val) [1][700/1918] eta: 0:00:54 time: 0.0447 data_time: 0.0007 memory: 951 2022/09/15 16:50:12 - mmengine - INFO - Epoch(val) [1][800/1918] eta: 0:00:51 time: 0.0465 data_time: 0.0006 memory: 951 2022/09/15 16:50:17 - mmengine - INFO - Epoch(val) [1][900/1918] eta: 0:00:46 time: 0.0459 data_time: 0.0006 memory: 951 2022/09/15 16:50:22 - mmengine - INFO - Epoch(val) [1][1000/1918] eta: 0:00:41 time: 0.0447 data_time: 0.0006 memory: 951 2022/09/15 16:50:27 - mmengine - INFO - Epoch(val) [1][1100/1918] eta: 0:00:36 time: 0.0443 data_time: 0.0006 memory: 951 2022/09/15 16:50:32 - mmengine - INFO - Epoch(val) [1][1200/1918] eta: 0:00:33 time: 0.0462 data_time: 0.0006 memory: 951 2022/09/15 16:50:37 - mmengine - INFO - Epoch(val) [1][1300/1918] eta: 0:00:32 time: 0.0524 data_time: 0.0007 memory: 951 2022/09/15 16:50:42 - mmengine - INFO - Epoch(val) [1][1400/1918] eta: 0:00:23 time: 0.0459 data_time: 0.0007 memory: 951 2022/09/15 16:50:47 - mmengine - INFO - Epoch(val) [1][1500/1918] eta: 0:00:19 time: 0.0478 data_time: 0.0006 memory: 951 2022/09/15 16:50:52 - mmengine - INFO - Epoch(val) [1][1600/1918] eta: 0:00:15 time: 0.0482 data_time: 0.0007 memory: 951 2022/09/15 16:50:57 - mmengine - INFO - Epoch(val) [1][1700/1918] eta: 0:00:10 time: 0.0460 data_time: 0.0007 memory: 951 2022/09/15 16:51:01 - mmengine - INFO - Epoch(val) [1][1800/1918] eta: 0:00:05 time: 0.0452 data_time: 0.0006 memory: 951 2022/09/15 16:51:05 - mmengine - INFO - Epoch(val) [1][1900/1918] eta: 0:00:00 time: 0.0431 data_time: 0.0006 memory: 951 2022/09/15 16:51:07 - mmengine - INFO - Epoch(val) [1][1918/1918] CUTE80/recog/word_acc_ignore_case_symbol: 0.8576 IIIT5K/recog/word_acc_ignore_case_symbol: 0.9297 SVT/recog/word_acc_ignore_case_symbol: 0.8532 SVTP/recog/word_acc_ignore_case_symbol: 0.7690 IC13/recog/word_acc_ignore_case_symbol: 0.9182 IC15/recog/word_acc_ignore_case_symbol: 0.7241 2022/09/15 16:52:02 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 16:52:10 - mmengine - INFO - Epoch(train) [2][100/6912] lr: 1.0000e-03 eta: 5:16:35 time: 0.6651 data_time: 0.0654 memory: 15027 loss_ce: 0.1638 loss: 0.1638 2022/09/15 16:53:09 - mmengine - INFO - Epoch(train) [2][200/6912] lr: 1.0000e-03 eta: 5:14:47 time: 0.7790 data_time: 0.1457 memory: 15027 loss_ce: 0.1563 loss: 0.1563 2022/09/15 16:54:07 - mmengine - INFO - Epoch(train) [2][300/6912] lr: 1.0000e-03 eta: 5:12:57 time: 0.6026 data_time: 0.0913 memory: 15027 loss_ce: 0.1699 loss: 0.1699 2022/09/15 16:55:05 - mmengine - INFO - Epoch(train) [2][400/6912] lr: 1.0000e-03 eta: 5:11:09 time: 0.4655 data_time: 0.0393 memory: 15027 loss_ce: 0.1784 loss: 0.1784 2022/09/15 16:56:02 - mmengine - INFO - Epoch(train) [2][500/6912] lr: 1.0000e-03 eta: 5:09:19 time: 0.4494 data_time: 0.0179 memory: 15027 loss_ce: 0.1597 loss: 0.1597 2022/09/15 16:56:59 - mmengine - INFO - Epoch(train) [2][600/6912] lr: 1.0000e-03 eta: 5:07:29 time: 0.4360 data_time: 0.0030 memory: 15027 loss_ce: 0.1726 loss: 0.1726 2022/09/15 16:57:57 - mmengine - INFO - Epoch(train) [2][700/6912] lr: 1.0000e-03 eta: 5:05:47 time: 0.6502 data_time: 0.0769 memory: 15027 loss_ce: 0.1524 loss: 0.1524 2022/09/15 16:58:55 - mmengine - INFO - Epoch(train) [2][800/6912] lr: 1.0000e-03 eta: 5:04:02 time: 0.7714 data_time: 0.1729 memory: 15027 loss_ce: 0.1629 loss: 0.1629 2022/09/15 16:59:52 - mmengine - INFO - Epoch(train) [2][900/6912] lr: 1.0000e-03 eta: 5:02:18 time: 0.5955 data_time: 0.1049 memory: 15027 loss_ce: 0.1613 loss: 0.1613 2022/09/15 17:00:49 - mmengine - INFO - Epoch(train) [2][1000/6912] lr: 1.0000e-03 eta: 5:00:33 time: 0.4402 data_time: 0.0442 memory: 15027 loss_ce: 0.1496 loss: 0.1496 2022/09/15 17:01:40 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 17:01:46 - mmengine - INFO - Epoch(train) [2][1100/6912] lr: 1.0000e-03 eta: 4:58:49 time: 0.4417 data_time: 0.0158 memory: 15027 loss_ce: 0.1499 loss: 0.1499 2022/09/15 17:02:42 - mmengine - INFO - Epoch(train) [2][1200/6912] lr: 1.0000e-03 eta: 4:57:05 time: 0.4232 data_time: 0.0027 memory: 15027 loss_ce: 0.1512 loss: 0.1512 2022/09/15 17:03:42 - mmengine - INFO - Epoch(train) [2][1300/6912] lr: 1.0000e-03 eta: 4:55:33 time: 0.6326 data_time: 0.0618 memory: 15027 loss_ce: 0.1568 loss: 0.1568 2022/09/15 17:04:40 - mmengine - INFO - Epoch(train) [2][1400/6912] lr: 1.0000e-03 eta: 4:53:57 time: 0.7716 data_time: 0.1434 memory: 15027 loss_ce: 0.1429 loss: 0.1429 2022/09/15 17:05:38 - mmengine - INFO - Epoch(train) [2][1500/6912] lr: 1.0000e-03 eta: 4:52:21 time: 0.6629 data_time: 0.1084 memory: 15027 loss_ce: 0.1550 loss: 0.1550 2022/09/15 17:06:36 - mmengine - INFO - Epoch(train) [2][1600/6912] lr: 1.0000e-03 eta: 4:50:45 time: 0.4464 data_time: 0.0268 memory: 15027 loss_ce: 0.1687 loss: 0.1687 2022/09/15 17:07:33 - mmengine - INFO - Epoch(train) [2][1700/6912] lr: 1.0000e-03 eta: 4:49:10 time: 0.4150 data_time: 0.0157 memory: 15027 loss_ce: 0.1437 loss: 0.1437 2022/09/15 17:08:34 - mmengine - INFO - Epoch(train) [2][1800/6912] lr: 1.0000e-03 eta: 4:47:45 time: 0.4368 data_time: 0.0029 memory: 15027 loss_ce: 0.1646 loss: 0.1646 2022/09/15 17:09:33 - mmengine - INFO - Epoch(train) [2][1900/6912] lr: 1.0000e-03 eta: 4:46:16 time: 0.6391 data_time: 0.0813 memory: 15027 loss_ce: 0.1516 loss: 0.1516 2022/09/15 17:10:33 - mmengine - INFO - Epoch(train) [2][2000/6912] lr: 1.0000e-03 eta: 4:44:49 time: 0.7869 data_time: 0.1653 memory: 15027 loss_ce: 0.1400 loss: 0.1400 2022/09/15 17:11:22 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 17:11:31 - mmengine - INFO - Epoch(train) [2][2100/6912] lr: 1.0000e-03 eta: 4:43:18 time: 0.6401 data_time: 0.1057 memory: 15027 loss_ce: 0.1519 loss: 0.1519 2022/09/15 17:12:30 - mmengine - INFO - Epoch(train) [2][2200/6912] lr: 1.0000e-03 eta: 4:41:50 time: 0.4282 data_time: 0.0285 memory: 15027 loss_ce: 0.1502 loss: 0.1502 2022/09/15 17:13:28 - mmengine - INFO - Epoch(train) [2][2300/6912] lr: 1.0000e-03 eta: 4:40:21 time: 0.4195 data_time: 0.0165 memory: 15027 loss_ce: 0.1563 loss: 0.1563 2022/09/15 17:14:26 - mmengine - INFO - Epoch(train) [2][2400/6912] lr: 1.0000e-03 eta: 4:38:52 time: 0.4244 data_time: 0.0030 memory: 15027 loss_ce: 0.1413 loss: 0.1413 2022/09/15 17:15:26 - mmengine - INFO - Epoch(train) [2][2500/6912] lr: 1.0000e-03 eta: 4:37:28 time: 0.7015 data_time: 0.0798 memory: 15027 loss_ce: 0.1584 loss: 0.1584 2022/09/15 17:16:26 - mmengine - INFO - Epoch(train) [2][2600/6912] lr: 1.0000e-03 eta: 4:36:05 time: 0.7934 data_time: 0.1472 memory: 15027 loss_ce: 0.1378 loss: 0.1378 2022/09/15 17:17:23 - mmengine - INFO - Epoch(train) [2][2700/6912] lr: 1.0000e-03 eta: 4:34:37 time: 0.6073 data_time: 0.1081 memory: 15027 loss_ce: 0.1343 loss: 0.1343 2022/09/15 17:18:21 - mmengine - INFO - Epoch(train) [2][2800/6912] lr: 1.0000e-03 eta: 4:33:11 time: 0.4655 data_time: 0.0374 memory: 15027 loss_ce: 0.1577 loss: 0.1577 2022/09/15 17:19:19 - mmengine - INFO - Epoch(train) [2][2900/6912] lr: 1.0000e-03 eta: 4:31:43 time: 0.4307 data_time: 0.0155 memory: 15027 loss_ce: 0.1399 loss: 0.1399 2022/09/15 17:20:17 - mmengine - INFO - Epoch(train) [2][3000/6912] lr: 1.0000e-03 eta: 4:30:17 time: 0.4454 data_time: 0.0030 memory: 15027 loss_ce: 0.1640 loss: 0.1640 2022/09/15 17:21:10 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 17:21:17 - mmengine - INFO - Epoch(train) [2][3100/6912] lr: 1.0000e-03 eta: 4:28:59 time: 0.6781 data_time: 0.0949 memory: 15027 loss_ce: 0.1517 loss: 0.1517 2022/09/15 17:22:16 - mmengine - INFO - Epoch(train) [2][3200/6912] lr: 1.0000e-03 eta: 4:27:37 time: 0.7384 data_time: 0.1452 memory: 15027 loss_ce: 0.1328 loss: 0.1328 2022/09/15 17:23:17 - mmengine - INFO - Epoch(train) [2][3300/6912] lr: 1.0000e-03 eta: 4:26:19 time: 0.6175 data_time: 0.1089 memory: 15027 loss_ce: 0.1355 loss: 0.1355 2022/09/15 17:24:15 - mmengine - INFO - Epoch(train) [2][3400/6912] lr: 1.0000e-03 eta: 4:24:56 time: 0.4699 data_time: 0.0404 memory: 15027 loss_ce: 0.1361 loss: 0.1361 2022/09/15 17:25:13 - mmengine - INFO - Epoch(train) [2][3500/6912] lr: 1.0000e-03 eta: 4:23:33 time: 0.4476 data_time: 0.0185 memory: 15027 loss_ce: 0.1258 loss: 0.1258 2022/09/15 17:26:12 - mmengine - INFO - Epoch(train) [2][3600/6912] lr: 1.0000e-03 eta: 4:22:12 time: 0.4263 data_time: 0.0028 memory: 15027 loss_ce: 0.1375 loss: 0.1375 2022/09/15 17:27:12 - mmengine - INFO - Epoch(train) [2][3700/6912] lr: 1.0000e-03 eta: 4:20:54 time: 0.6314 data_time: 0.0824 memory: 15027 loss_ce: 0.1396 loss: 0.1396 2022/09/15 17:28:12 - mmengine - INFO - Epoch(train) [2][3800/6912] lr: 1.0000e-03 eta: 4:19:38 time: 0.7899 data_time: 0.1282 memory: 15027 loss_ce: 0.1239 loss: 0.1239 2022/09/15 17:29:11 - mmengine - INFO - Epoch(train) [2][3900/6912] lr: 1.0000e-03 eta: 4:18:19 time: 0.5814 data_time: 0.1050 memory: 15027 loss_ce: 0.1365 loss: 0.1365 2022/09/15 17:30:09 - mmengine - INFO - Epoch(train) [2][4000/6912] lr: 1.0000e-03 eta: 4:16:57 time: 0.4747 data_time: 0.0614 memory: 15027 loss_ce: 0.1303 loss: 0.1303 2022/09/15 17:31:00 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 17:31:06 - mmengine - INFO - Epoch(train) [2][4100/6912] lr: 1.0000e-03 eta: 4:15:33 time: 0.4436 data_time: 0.0312 memory: 15027 loss_ce: 0.1335 loss: 0.1335 2022/09/15 17:32:03 - mmengine - INFO - Epoch(train) [2][4200/6912] lr: 1.0000e-03 eta: 4:14:12 time: 0.4315 data_time: 0.0032 memory: 15027 loss_ce: 0.1287 loss: 0.1287 2022/09/15 17:33:03 - mmengine - INFO - Epoch(train) [2][4300/6912] lr: 1.0000e-03 eta: 4:12:56 time: 0.6469 data_time: 0.0641 memory: 15027 loss_ce: 0.1367 loss: 0.1367 2022/09/15 17:34:02 - mmengine - INFO - Epoch(train) [2][4400/6912] lr: 1.0000e-03 eta: 4:11:39 time: 0.7651 data_time: 0.1197 memory: 15027 loss_ce: 0.1301 loss: 0.1301 2022/09/15 17:34:59 - mmengine - INFO - Epoch(train) [2][4500/6912] lr: 1.0000e-03 eta: 4:10:18 time: 0.6053 data_time: 0.1055 memory: 15027 loss_ce: 0.1301 loss: 0.1301 2022/09/15 17:35:57 - mmengine - INFO - Epoch(train) [2][4600/6912] lr: 1.0000e-03 eta: 4:08:59 time: 0.4552 data_time: 0.0446 memory: 15027 loss_ce: 0.1314 loss: 0.1314 2022/09/15 17:36:54 - mmengine - INFO - Epoch(train) [2][4700/6912] lr: 1.0000e-03 eta: 4:07:39 time: 0.4461 data_time: 0.0163 memory: 15027 loss_ce: 0.1137 loss: 0.1137 2022/09/15 17:37:51 - mmengine - INFO - Epoch(train) [2][4800/6912] lr: 1.0000e-03 eta: 4:06:20 time: 0.4344 data_time: 0.0037 memory: 15027 loss_ce: 0.1173 loss: 0.1173 2022/09/15 17:38:51 - mmengine - INFO - Epoch(train) [2][4900/6912] lr: 1.0000e-03 eta: 4:05:05 time: 0.6120 data_time: 0.0864 memory: 15027 loss_ce: 0.1250 loss: 0.1250 2022/09/15 17:39:49 - mmengine - INFO - Epoch(train) [2][5000/6912] lr: 1.0000e-03 eta: 4:03:49 time: 0.7423 data_time: 0.1212 memory: 15027 loss_ce: 0.1365 loss: 0.1365 2022/09/15 17:40:39 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 17:40:48 - mmengine - INFO - Epoch(train) [2][5100/6912] lr: 1.0000e-03 eta: 4:02:32 time: 0.6132 data_time: 0.1052 memory: 15027 loss_ce: 0.1159 loss: 0.1159 2022/09/15 17:41:45 - mmengine - INFO - Epoch(train) [2][5200/6912] lr: 1.0000e-03 eta: 4:01:14 time: 0.4755 data_time: 0.0620 memory: 15027 loss_ce: 0.1233 loss: 0.1233 2022/09/15 17:42:43 - mmengine - INFO - Epoch(train) [2][5300/6912] lr: 1.0000e-03 eta: 3:59:58 time: 0.4668 data_time: 0.0521 memory: 15027 loss_ce: 0.1325 loss: 0.1325 2022/09/15 17:43:41 - mmengine - INFO - Epoch(train) [2][5400/6912] lr: 1.0000e-03 eta: 3:58:43 time: 0.4827 data_time: 0.0035 memory: 15027 loss_ce: 0.1248 loss: 0.1248 2022/09/15 17:44:41 - mmengine - INFO - Epoch(train) [2][5500/6912] lr: 1.0000e-03 eta: 3:57:30 time: 0.6570 data_time: 0.0657 memory: 15027 loss_ce: 0.1216 loss: 0.1216 2022/09/15 17:45:40 - mmengine - INFO - Epoch(train) [2][5600/6912] lr: 1.0000e-03 eta: 3:56:16 time: 0.7507 data_time: 0.1232 memory: 15027 loss_ce: 0.1360 loss: 0.1360 2022/09/15 17:46:38 - mmengine - INFO - Epoch(train) [2][5700/6912] lr: 1.0000e-03 eta: 3:55:00 time: 0.5973 data_time: 0.1036 memory: 15027 loss_ce: 0.1234 loss: 0.1234 2022/09/15 17:47:36 - mmengine - INFO - Epoch(train) [2][5800/6912] lr: 1.0000e-03 eta: 3:53:46 time: 0.4562 data_time: 0.0451 memory: 15027 loss_ce: 0.1293 loss: 0.1293 2022/09/15 17:48:33 - mmengine - INFO - Epoch(train) [2][5900/6912] lr: 1.0000e-03 eta: 3:52:29 time: 0.4322 data_time: 0.0171 memory: 15027 loss_ce: 0.1335 loss: 0.1335 2022/09/15 17:49:30 - mmengine - INFO - Epoch(train) [2][6000/6912] lr: 1.0000e-03 eta: 3:51:13 time: 0.4255 data_time: 0.0029 memory: 15027 loss_ce: 0.1289 loss: 0.1289 2022/09/15 17:50:22 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 17:50:29 - mmengine - INFO - Epoch(train) [2][6100/6912] lr: 1.0000e-03 eta: 3:50:01 time: 0.5973 data_time: 0.0801 memory: 15027 loss_ce: 0.1162 loss: 0.1162 2022/09/15 17:51:27 - mmengine - INFO - Epoch(train) [2][6200/6912] lr: 1.0000e-03 eta: 3:48:47 time: 0.7127 data_time: 0.1234 memory: 15027 loss_ce: 0.1031 loss: 0.1031 2022/09/15 17:52:25 - mmengine - INFO - Epoch(train) [2][6300/6912] lr: 1.0000e-03 eta: 3:47:34 time: 0.6675 data_time: 0.1110 memory: 15027 loss_ce: 0.1203 loss: 0.1203 2022/09/15 17:53:22 - mmengine - INFO - Epoch(train) [2][6400/6912] lr: 1.0000e-03 eta: 3:46:18 time: 0.4888 data_time: 0.0717 memory: 15027 loss_ce: 0.1113 loss: 0.1113 2022/09/15 17:54:19 - mmengine - INFO - Epoch(train) [2][6500/6912] lr: 1.0000e-03 eta: 3:45:03 time: 0.4561 data_time: 0.0386 memory: 15027 loss_ce: 0.1259 loss: 0.1259 2022/09/15 17:55:16 - mmengine - INFO - Epoch(train) [2][6600/6912] lr: 1.0000e-03 eta: 3:43:49 time: 0.4234 data_time: 0.0031 memory: 15027 loss_ce: 0.1356 loss: 0.1356 2022/09/15 17:56:15 - mmengine - INFO - Epoch(train) [2][6700/6912] lr: 1.0000e-03 eta: 3:42:38 time: 0.5969 data_time: 0.0630 memory: 15027 loss_ce: 0.1111 loss: 0.1111 2022/09/15 17:57:13 - mmengine - INFO - Epoch(train) [2][6800/6912] lr: 1.0000e-03 eta: 3:41:25 time: 0.7092 data_time: 0.1176 memory: 15027 loss_ce: 0.1212 loss: 0.1212 2022/09/15 17:58:09 - mmengine - INFO - Epoch(train) [2][6900/6912] lr: 1.0000e-03 eta: 3:40:10 time: 0.5545 data_time: 0.0719 memory: 15027 loss_ce: 0.1261 loss: 0.1261 2022/09/15 17:58:14 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 17:58:14 - mmengine - INFO - Saving checkpoint at 2 epochs 2022/09/15 17:58:34 - mmengine - INFO - Epoch(val) [2][100/1918] eta: 0:01:27 time: 0.0479 data_time: 0.0006 memory: 15027 2022/09/15 17:58:39 - mmengine - INFO - Epoch(val) [2][200/1918] eta: 0:01:17 time: 0.0449 data_time: 0.0005 memory: 951 2022/09/15 17:58:44 - mmengine - INFO - Epoch(val) [2][300/1918] eta: 0:01:14 time: 0.0459 data_time: 0.0006 memory: 951 2022/09/15 17:58:48 - mmengine - INFO - Epoch(val) [2][400/1918] eta: 0:01:08 time: 0.0448 data_time: 0.0005 memory: 951 2022/09/15 17:58:53 - mmengine - INFO - Epoch(val) [2][500/1918] eta: 0:01:06 time: 0.0471 data_time: 0.0006 memory: 951 2022/09/15 17:58:58 - mmengine - INFO - Epoch(val) [2][600/1918] eta: 0:01:00 time: 0.0462 data_time: 0.0006 memory: 951 2022/09/15 17:59:03 - mmengine - INFO - Epoch(val) [2][700/1918] eta: 0:00:52 time: 0.0432 data_time: 0.0005 memory: 951 2022/09/15 17:59:07 - mmengine - INFO - Epoch(val) [2][800/1918] eta: 0:00:55 time: 0.0494 data_time: 0.0006 memory: 951 2022/09/15 17:59:12 - mmengine - INFO - Epoch(val) [2][900/1918] eta: 0:00:47 time: 0.0469 data_time: 0.0008 memory: 951 2022/09/15 17:59:17 - mmengine - INFO - Epoch(val) [2][1000/1918] eta: 0:00:43 time: 0.0470 data_time: 0.0005 memory: 951 2022/09/15 17:59:22 - mmengine - INFO - Epoch(val) [2][1100/1918] eta: 0:00:45 time: 0.0551 data_time: 0.0009 memory: 951 2022/09/15 17:59:27 - mmengine - INFO - Epoch(val) [2][1200/1918] eta: 0:00:35 time: 0.0494 data_time: 0.0006 memory: 951 2022/09/15 17:59:32 - mmengine - INFO - Epoch(val) [2][1300/1918] eta: 0:00:30 time: 0.0494 data_time: 0.0006 memory: 951 2022/09/15 17:59:36 - mmengine - INFO - Epoch(val) [2][1400/1918] eta: 0:00:24 time: 0.0471 data_time: 0.0005 memory: 951 2022/09/15 17:59:41 - mmengine - INFO - Epoch(val) [2][1500/1918] eta: 0:00:20 time: 0.0493 data_time: 0.0006 memory: 951 2022/09/15 17:59:46 - mmengine - INFO - Epoch(val) [2][1600/1918] eta: 0:00:15 time: 0.0476 data_time: 0.0006 memory: 951 2022/09/15 17:59:51 - mmengine - INFO - Epoch(val) [2][1700/1918] eta: 0:00:11 time: 0.0544 data_time: 0.0007 memory: 951 2022/09/15 17:59:55 - mmengine - INFO - Epoch(val) [2][1800/1918] eta: 0:00:05 time: 0.0437 data_time: 0.0005 memory: 951 2022/09/15 18:00:00 - mmengine - INFO - Epoch(val) [2][1900/1918] eta: 0:00:00 time: 0.0433 data_time: 0.0005 memory: 951 2022/09/15 18:00:05 - mmengine - INFO - Epoch(val) [2][1918/1918] CUTE80/recog/word_acc_ignore_case_symbol: 0.8715 IIIT5K/recog/word_acc_ignore_case_symbol: 0.9337 SVT/recog/word_acc_ignore_case_symbol: 0.8501 SVTP/recog/word_acc_ignore_case_symbol: 0.7566 IC13/recog/word_acc_ignore_case_symbol: 0.9172 IC15/recog/word_acc_ignore_case_symbol: 0.7366 2022/09/15 18:01:08 - mmengine - INFO - Epoch(train) [3][100/6912] lr: 1.0000e-03 eta: 3:38:53 time: 0.6417 data_time: 0.1082 memory: 15027 loss_ce: 0.1019 loss: 0.1019 2022/09/15 18:01:54 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 18:02:09 - mmengine - INFO - Epoch(train) [3][200/6912] lr: 1.0000e-03 eta: 3:37:45 time: 0.6803 data_time: 0.1568 memory: 15027 loss_ce: 0.1155 loss: 0.1155 2022/09/15 18:03:09 - mmengine - INFO - Epoch(train) [3][300/6912] lr: 1.0000e-03 eta: 3:36:36 time: 0.6321 data_time: 0.0757 memory: 15027 loss_ce: 0.1225 loss: 0.1225 2022/09/15 18:04:09 - mmengine - INFO - Epoch(train) [3][400/6912] lr: 1.0000e-03 eta: 3:35:28 time: 0.5530 data_time: 0.0030 memory: 15027 loss_ce: 0.1035 loss: 0.1035 2022/09/15 18:05:09 - mmengine - INFO - Epoch(train) [3][500/6912] lr: 1.0000e-03 eta: 3:34:18 time: 0.5205 data_time: 0.0207 memory: 15027 loss_ce: 0.1120 loss: 0.1120 2022/09/15 18:06:08 - mmengine - INFO - Epoch(train) [3][600/6912] lr: 1.0000e-03 eta: 3:33:09 time: 0.4198 data_time: 0.0232 memory: 15027 loss_ce: 0.1252 loss: 0.1252 2022/09/15 18:07:10 - mmengine - INFO - Epoch(train) [3][700/6912] lr: 1.0000e-03 eta: 3:32:03 time: 0.6097 data_time: 0.0967 memory: 15027 loss_ce: 0.1073 loss: 0.1073 2022/09/15 18:08:10 - mmengine - INFO - Epoch(train) [3][800/6912] lr: 1.0000e-03 eta: 3:30:54 time: 0.6505 data_time: 0.1484 memory: 15027 loss_ce: 0.1102 loss: 0.1102 2022/09/15 18:09:10 - mmengine - INFO - Epoch(train) [3][900/6912] lr: 1.0000e-03 eta: 3:29:47 time: 0.6725 data_time: 0.0708 memory: 15027 loss_ce: 0.1175 loss: 0.1175 2022/09/15 18:10:09 - mmengine - INFO - Epoch(train) [3][1000/6912] lr: 1.0000e-03 eta: 3:28:38 time: 0.5546 data_time: 0.0031 memory: 15027 loss_ce: 0.1293 loss: 0.1293 2022/09/15 18:11:09 - mmengine - INFO - Epoch(train) [3][1100/6912] lr: 1.0000e-03 eta: 3:27:29 time: 0.5192 data_time: 0.0213 memory: 15027 loss_ce: 0.1214 loss: 0.1214 2022/09/15 18:11:54 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 18:12:08 - mmengine - INFO - Epoch(train) [3][1200/6912] lr: 1.0000e-03 eta: 3:26:20 time: 0.4246 data_time: 0.0224 memory: 15027 loss_ce: 0.1054 loss: 0.1054 2022/09/15 18:13:09 - mmengine - INFO - Epoch(train) [3][1300/6912] lr: 1.0000e-03 eta: 3:25:15 time: 0.6094 data_time: 0.0902 memory: 15027 loss_ce: 0.1010 loss: 0.1010 2022/09/15 18:14:10 - mmengine - INFO - Epoch(train) [3][1400/6912] lr: 1.0000e-03 eta: 3:24:07 time: 0.6979 data_time: 0.1486 memory: 15027 loss_ce: 0.1362 loss: 0.1362 2022/09/15 18:15:11 - mmengine - INFO - Epoch(train) [3][1500/6912] lr: 1.0000e-03 eta: 3:23:01 time: 0.6596 data_time: 0.0852 memory: 15027 loss_ce: 0.1144 loss: 0.1144 2022/09/15 18:16:11 - mmengine - INFO - Epoch(train) [3][1600/6912] lr: 1.0000e-03 eta: 3:21:54 time: 0.5568 data_time: 0.0030 memory: 15027 loss_ce: 0.1085 loss: 0.1085 2022/09/15 18:17:10 - mmengine - INFO - Epoch(train) [3][1700/6912] lr: 1.0000e-03 eta: 3:20:46 time: 0.5382 data_time: 0.0243 memory: 15027 loss_ce: 0.0952 loss: 0.0952 2022/09/15 18:18:10 - mmengine - INFO - Epoch(train) [3][1800/6912] lr: 1.0000e-03 eta: 3:19:38 time: 0.4186 data_time: 0.0211 memory: 15027 loss_ce: 0.1128 loss: 0.1128 2022/09/15 18:19:12 - mmengine - INFO - Epoch(train) [3][1900/6912] lr: 1.0000e-03 eta: 3:18:33 time: 0.5855 data_time: 0.0755 memory: 15027 loss_ce: 0.1097 loss: 0.1097 2022/09/15 18:20:12 - mmengine - INFO - Epoch(train) [3][2000/6912] lr: 1.0000e-03 eta: 3:17:26 time: 0.6808 data_time: 0.1632 memory: 15027 loss_ce: 0.0996 loss: 0.0996 2022/09/15 18:21:14 - mmengine - INFO - Epoch(train) [3][2100/6912] lr: 1.0000e-03 eta: 3:16:21 time: 0.6186 data_time: 0.0579 memory: 15027 loss_ce: 0.1097 loss: 0.1097 2022/09/15 18:21:59 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 18:22:14 - mmengine - INFO - Epoch(train) [3][2200/6912] lr: 1.0000e-03 eta: 3:15:14 time: 0.5977 data_time: 0.0043 memory: 15027 loss_ce: 0.1023 loss: 0.1023 2022/09/15 18:23:14 - mmengine - INFO - Epoch(train) [3][2300/6912] lr: 1.0000e-03 eta: 3:14:08 time: 0.5573 data_time: 0.0256 memory: 15027 loss_ce: 0.1121 loss: 0.1121 2022/09/15 18:24:14 - mmengine - INFO - Epoch(train) [3][2400/6912] lr: 1.0000e-03 eta: 3:13:01 time: 0.4391 data_time: 0.0364 memory: 15027 loss_ce: 0.1009 loss: 0.1009 2022/09/15 18:25:16 - mmengine - INFO - Epoch(train) [3][2500/6912] lr: 1.0000e-03 eta: 3:11:56 time: 0.6021 data_time: 0.0906 memory: 15027 loss_ce: 0.1071 loss: 0.1071 2022/09/15 18:26:17 - mmengine - INFO - Epoch(train) [3][2600/6912] lr: 1.0000e-03 eta: 3:10:50 time: 0.7081 data_time: 0.1566 memory: 15027 loss_ce: 0.1087 loss: 0.1087 2022/09/15 18:27:18 - mmengine - INFO - Epoch(train) [3][2700/6912] lr: 1.0000e-03 eta: 3:09:45 time: 0.6598 data_time: 0.0731 memory: 15027 loss_ce: 0.1218 loss: 0.1218 2022/09/15 18:28:18 - mmengine - INFO - Epoch(train) [3][2800/6912] lr: 1.0000e-03 eta: 3:08:39 time: 0.6147 data_time: 0.0032 memory: 15027 loss_ce: 0.1009 loss: 0.1009 2022/09/15 18:29:19 - mmengine - INFO - Epoch(train) [3][2900/6912] lr: 1.0000e-03 eta: 3:07:33 time: 0.5508 data_time: 0.0383 memory: 15027 loss_ce: 0.1031 loss: 0.1031 2022/09/15 18:30:18 - mmengine - INFO - Epoch(train) [3][3000/6912] lr: 1.0000e-03 eta: 3:06:26 time: 0.4209 data_time: 0.0228 memory: 15027 loss_ce: 0.1004 loss: 0.1004 2022/09/15 18:31:20 - mmengine - INFO - Epoch(train) [3][3100/6912] lr: 1.0000e-03 eta: 3:05:22 time: 0.5971 data_time: 0.0880 memory: 15027 loss_ce: 0.1068 loss: 0.1068 2022/09/15 18:32:06 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 18:32:20 - mmengine - INFO - Epoch(train) [3][3200/6912] lr: 1.0000e-03 eta: 3:04:16 time: 0.6954 data_time: 0.1569 memory: 15027 loss_ce: 0.1035 loss: 0.1035 2022/09/15 18:33:21 - mmengine - INFO - Epoch(train) [3][3300/6912] lr: 1.0000e-03 eta: 3:03:11 time: 0.6775 data_time: 0.0762 memory: 15027 loss_ce: 0.1043 loss: 0.1043 2022/09/15 18:34:21 - mmengine - INFO - Epoch(train) [3][3400/6912] lr: 1.0000e-03 eta: 3:02:04 time: 0.5724 data_time: 0.0032 memory: 15027 loss_ce: 0.1071 loss: 0.1071 2022/09/15 18:35:21 - mmengine - INFO - Epoch(train) [3][3500/6912] lr: 1.0000e-03 eta: 3:00:58 time: 0.5468 data_time: 0.0215 memory: 15027 loss_ce: 0.1075 loss: 0.1075 2022/09/15 18:36:26 - mmengine - INFO - Epoch(train) [3][3600/6912] lr: 1.0000e-03 eta: 2:59:57 time: 0.4298 data_time: 0.0224 memory: 15027 loss_ce: 0.1084 loss: 0.1084 2022/09/15 18:37:33 - mmengine - INFO - Epoch(train) [3][3700/6912] lr: 1.0000e-03 eta: 2:58:58 time: 0.5850 data_time: 0.0803 memory: 15027 loss_ce: 0.1086 loss: 0.1086 2022/09/15 18:38:39 - mmengine - INFO - Epoch(train) [3][3800/6912] lr: 1.0000e-03 eta: 2:57:58 time: 0.7330 data_time: 0.1699 memory: 15027 loss_ce: 0.0947 loss: 0.0947 2022/09/15 18:39:45 - mmengine - INFO - Epoch(train) [3][3900/6912] lr: 1.0000e-03 eta: 2:56:58 time: 0.7566 data_time: 0.0623 memory: 15027 loss_ce: 0.1017 loss: 0.1017 2022/09/15 18:40:51 - mmengine - INFO - Epoch(train) [3][4000/6912] lr: 1.0000e-03 eta: 2:55:58 time: 0.6995 data_time: 0.0032 memory: 15027 loss_ce: 0.1189 loss: 0.1189 2022/09/15 18:41:57 - mmengine - INFO - Epoch(train) [3][4100/6912] lr: 1.0000e-03 eta: 2:54:57 time: 0.5857 data_time: 0.0227 memory: 15027 loss_ce: 0.1055 loss: 0.1055 2022/09/15 18:42:47 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 18:43:03 - mmengine - INFO - Epoch(train) [3][4200/6912] lr: 1.0000e-03 eta: 2:53:56 time: 0.4298 data_time: 0.0224 memory: 15027 loss_ce: 0.0995 loss: 0.0995 2022/09/15 18:44:11 - mmengine - INFO - Epoch(train) [3][4300/6912] lr: 1.0000e-03 eta: 2:52:58 time: 0.6600 data_time: 0.1173 memory: 15027 loss_ce: 0.0967 loss: 0.0967 2022/09/15 18:45:17 - mmengine - INFO - Epoch(train) [3][4400/6912] lr: 1.0000e-03 eta: 2:51:57 time: 0.7230 data_time: 0.1582 memory: 15027 loss_ce: 0.1109 loss: 0.1109 2022/09/15 18:46:23 - mmengine - INFO - Epoch(train) [3][4500/6912] lr: 1.0000e-03 eta: 2:50:57 time: 0.7315 data_time: 0.0604 memory: 15027 loss_ce: 0.0990 loss: 0.0990 2022/09/15 18:47:31 - mmengine - INFO - Epoch(train) [3][4600/6912] lr: 1.0000e-03 eta: 2:49:57 time: 0.7368 data_time: 0.0039 memory: 15027 loss_ce: 0.1069 loss: 0.1069 2022/09/15 18:48:37 - mmengine - INFO - Epoch(train) [3][4700/6912] lr: 1.0000e-03 eta: 2:48:57 time: 0.5994 data_time: 0.0241 memory: 15027 loss_ce: 0.0960 loss: 0.0960 2022/09/15 18:49:42 - mmengine - INFO - Epoch(train) [3][4800/6912] lr: 1.0000e-03 eta: 2:47:55 time: 0.4319 data_time: 0.0249 memory: 15027 loss_ce: 0.0995 loss: 0.0995 2022/09/15 18:50:50 - mmengine - INFO - Epoch(train) [3][4900/6912] lr: 1.0000e-03 eta: 2:46:56 time: 0.6311 data_time: 0.1088 memory: 15027 loss_ce: 0.1013 loss: 0.1013 2022/09/15 18:51:56 - mmengine - INFO - Epoch(train) [3][5000/6912] lr: 1.0000e-03 eta: 2:45:55 time: 0.7247 data_time: 0.1763 memory: 15027 loss_ce: 0.0960 loss: 0.0960 2022/09/15 18:53:04 - mmengine - INFO - Epoch(train) [3][5100/6912] lr: 1.0000e-03 eta: 2:44:56 time: 0.7716 data_time: 0.0833 memory: 15027 loss_ce: 0.1193 loss: 0.1193 2022/09/15 18:53:55 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 18:54:11 - mmengine - INFO - Epoch(train) [3][5200/6912] lr: 1.0000e-03 eta: 2:43:55 time: 0.6565 data_time: 0.0036 memory: 15027 loss_ce: 0.1027 loss: 0.1027 2022/09/15 18:55:16 - mmengine - INFO - Epoch(train) [3][5300/6912] lr: 1.0000e-03 eta: 2:42:53 time: 0.5830 data_time: 0.0216 memory: 15027 loss_ce: 0.1040 loss: 0.1040 2022/09/15 18:56:22 - mmengine - INFO - Epoch(train) [3][5400/6912] lr: 1.0000e-03 eta: 2:41:52 time: 0.4331 data_time: 0.0229 memory: 15027 loss_ce: 0.1138 loss: 0.1138 2022/09/15 18:57:31 - mmengine - INFO - Epoch(train) [3][5500/6912] lr: 1.0000e-03 eta: 2:40:53 time: 0.6320 data_time: 0.1057 memory: 15027 loss_ce: 0.1076 loss: 0.1076 2022/09/15 18:58:38 - mmengine - INFO - Epoch(train) [3][5600/6912] lr: 1.0000e-03 eta: 2:39:53 time: 0.7564 data_time: 0.1976 memory: 15027 loss_ce: 0.0926 loss: 0.0926 2022/09/15 18:59:47 - mmengine - INFO - Epoch(train) [3][5700/6912] lr: 1.0000e-03 eta: 2:38:54 time: 0.7755 data_time: 0.0818 memory: 15027 loss_ce: 0.1162 loss: 0.1162 2022/09/15 19:00:52 - mmengine - INFO - Epoch(train) [3][5800/6912] lr: 1.0000e-03 eta: 2:37:52 time: 0.6796 data_time: 0.0036 memory: 15027 loss_ce: 0.1048 loss: 0.1048 2022/09/15 19:01:59 - mmengine - INFO - Epoch(train) [3][5900/6912] lr: 1.0000e-03 eta: 2:36:50 time: 0.5945 data_time: 0.0272 memory: 15027 loss_ce: 0.1173 loss: 0.1173 2022/09/15 19:03:06 - mmengine - INFO - Epoch(train) [3][6000/6912] lr: 1.0000e-03 eta: 2:35:50 time: 0.4469 data_time: 0.0267 memory: 15027 loss_ce: 0.1146 loss: 0.1146 2022/09/15 19:04:14 - mmengine - INFO - Epoch(train) [3][6100/6912] lr: 1.0000e-03 eta: 2:34:50 time: 0.6330 data_time: 0.0880 memory: 15027 loss_ce: 0.0967 loss: 0.0967 2022/09/15 19:05:06 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 19:05:24 - mmengine - INFO - Epoch(train) [3][6200/6912] lr: 1.0000e-03 eta: 2:33:51 time: 0.7897 data_time: 0.2085 memory: 15027 loss_ce: 0.0992 loss: 0.0992 2022/09/15 19:06:31 - mmengine - INFO - Epoch(train) [3][6300/6912] lr: 1.0000e-03 eta: 2:32:50 time: 0.7500 data_time: 0.0673 memory: 15027 loss_ce: 0.1147 loss: 0.1147 2022/09/15 19:07:37 - mmengine - INFO - Epoch(train) [3][6400/6912] lr: 1.0000e-03 eta: 2:31:49 time: 0.7052 data_time: 0.0061 memory: 15027 loss_ce: 0.1011 loss: 0.1011 2022/09/15 19:08:45 - mmengine - INFO - Epoch(train) [3][6500/6912] lr: 1.0000e-03 eta: 2:30:48 time: 0.6263 data_time: 0.0275 memory: 15027 loss_ce: 0.1031 loss: 0.1031 2022/09/15 19:09:51 - mmengine - INFO - Epoch(train) [3][6600/6912] lr: 1.0000e-03 eta: 2:29:46 time: 0.4569 data_time: 0.0478 memory: 15027 loss_ce: 0.0978 loss: 0.0978 2022/09/15 19:11:00 - mmengine - INFO - Epoch(train) [3][6700/6912] lr: 1.0000e-03 eta: 2:28:46 time: 0.6373 data_time: 0.1053 memory: 15027 loss_ce: 0.1045 loss: 0.1045 2022/09/15 19:12:07 - mmengine - INFO - Epoch(train) [3][6800/6912] lr: 1.0000e-03 eta: 2:27:45 time: 0.7222 data_time: 0.1433 memory: 15027 loss_ce: 0.0927 loss: 0.0927 2022/09/15 19:13:12 - mmengine - INFO - Epoch(train) [3][6900/6912] lr: 1.0000e-03 eta: 2:26:42 time: 0.6114 data_time: 0.0585 memory: 15027 loss_ce: 0.0960 loss: 0.0960 2022/09/15 19:13:17 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 19:13:18 - mmengine - INFO - Saving checkpoint at 3 epochs 2022/09/15 19:13:44 - mmengine - INFO - Epoch(val) [3][100/1918] eta: 0:01:29 time: 0.0494 data_time: 0.0007 memory: 15027 2022/09/15 19:13:49 - mmengine - INFO - Epoch(val) [3][200/1918] eta: 0:01:26 time: 0.0504 data_time: 0.0008 memory: 951 2022/09/15 19:13:55 - mmengine - INFO - Epoch(val) [3][300/1918] eta: 0:01:25 time: 0.0529 data_time: 0.0012 memory: 951 2022/09/15 19:13:59 - mmengine - INFO - Epoch(val) [3][400/1918] eta: 0:01:10 time: 0.0466 data_time: 0.0007 memory: 951 2022/09/15 19:14:04 - mmengine - INFO - Epoch(val) [3][500/1918] eta: 0:01:09 time: 0.0488 data_time: 0.0007 memory: 951 2022/09/15 19:14:09 - mmengine - INFO - Epoch(val) [3][600/1918] eta: 0:01:04 time: 0.0490 data_time: 0.0007 memory: 951 2022/09/15 19:14:14 - mmengine - INFO - Epoch(val) [3][700/1918] eta: 0:00:58 time: 0.0480 data_time: 0.0007 memory: 951 2022/09/15 19:14:19 - mmengine - INFO - Epoch(val) [3][800/1918] eta: 0:01:00 time: 0.0545 data_time: 0.0008 memory: 951 2022/09/15 19:14:24 - mmengine - INFO - Epoch(val) [3][900/1918] eta: 0:00:45 time: 0.0446 data_time: 0.0007 memory: 951 2022/09/15 19:14:29 - mmengine - INFO - Epoch(val) [3][1000/1918] eta: 0:00:50 time: 0.0555 data_time: 0.0007 memory: 951 2022/09/15 19:14:34 - mmengine - INFO - Epoch(val) [3][1100/1918] eta: 0:00:40 time: 0.0498 data_time: 0.0009 memory: 951 2022/09/15 19:14:39 - mmengine - INFO - Epoch(val) [3][1200/1918] eta: 0:00:33 time: 0.0463 data_time: 0.0007 memory: 951 2022/09/15 19:14:44 - mmengine - INFO - Epoch(val) [3][1300/1918] eta: 0:00:33 time: 0.0541 data_time: 0.0020 memory: 951 2022/09/15 19:14:49 - mmengine - INFO - Epoch(val) [3][1400/1918] eta: 0:00:27 time: 0.0530 data_time: 0.0008 memory: 951 2022/09/15 19:14:54 - mmengine - INFO - Epoch(val) [3][1500/1918] eta: 0:00:18 time: 0.0443 data_time: 0.0006 memory: 951 2022/09/15 19:14:59 - mmengine - INFO - Epoch(val) [3][1600/1918] eta: 0:00:15 time: 0.0484 data_time: 0.0009 memory: 951 2022/09/15 19:15:04 - mmengine - INFO - Epoch(val) [3][1700/1918] eta: 0:00:11 time: 0.0540 data_time: 0.0008 memory: 951 2022/09/15 19:15:09 - mmengine - INFO - Epoch(val) [3][1800/1918] eta: 0:00:05 time: 0.0467 data_time: 0.0007 memory: 951 2022/09/15 19:15:14 - mmengine - INFO - Epoch(val) [3][1900/1918] eta: 0:00:00 time: 0.0427 data_time: 0.0006 memory: 951 2022/09/15 19:15:15 - mmengine - INFO - Epoch(val) [3][1918/1918] CUTE80/recog/word_acc_ignore_case_symbol: 0.8750 IIIT5K/recog/word_acc_ignore_case_symbol: 0.9383 SVT/recog/word_acc_ignore_case_symbol: 0.8655 SVTP/recog/word_acc_ignore_case_symbol: 0.7876 IC13/recog/word_acc_ignore_case_symbol: 0.9212 IC15/recog/word_acc_ignore_case_symbol: 0.7453 2022/09/15 19:16:23 - mmengine - INFO - Epoch(train) [4][100/6912] lr: 1.0000e-04 eta: 2:25:32 time: 0.7319 data_time: 0.1400 memory: 15027 loss_ce: 0.0775 loss: 0.0775 2022/09/15 19:17:28 - mmengine - INFO - Epoch(train) [4][200/6912] lr: 1.0000e-04 eta: 2:24:29 time: 0.9049 data_time: 0.1644 memory: 15027 loss_ce: 0.0797 loss: 0.0797 2022/09/15 19:18:05 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 19:18:31 - mmengine - INFO - Epoch(train) [4][300/6912] lr: 1.0000e-04 eta: 2:23:25 time: 0.8428 data_time: 0.1577 memory: 15027 loss_ce: 0.0687 loss: 0.0687 2022/09/15 19:19:33 - mmengine - INFO - Epoch(train) [4][400/6912] lr: 1.0000e-04 eta: 2:22:20 time: 0.5568 data_time: 0.0377 memory: 15027 loss_ce: 0.0883 loss: 0.0883 2022/09/15 19:20:36 - mmengine - INFO - Epoch(train) [4][500/6912] lr: 1.0000e-04 eta: 2:21:16 time: 0.4582 data_time: 0.0557 memory: 15027 loss_ce: 0.0780 loss: 0.0780 2022/09/15 19:21:40 - mmengine - INFO - Epoch(train) [4][600/6912] lr: 1.0000e-04 eta: 2:20:13 time: 0.4876 data_time: 0.0216 memory: 15027 loss_ce: 0.0741 loss: 0.0741 2022/09/15 19:22:44 - mmengine - INFO - Epoch(train) [4][700/6912] lr: 1.0000e-04 eta: 2:19:10 time: 0.6401 data_time: 0.1499 memory: 15027 loss_ce: 0.0698 loss: 0.0698 2022/09/15 19:23:51 - mmengine - INFO - Epoch(train) [4][800/6912] lr: 1.0000e-04 eta: 2:18:08 time: 0.8748 data_time: 0.1423 memory: 15027 loss_ce: 0.0816 loss: 0.0816 2022/09/15 19:24:55 - mmengine - INFO - Epoch(train) [4][900/6912] lr: 1.0000e-04 eta: 2:17:04 time: 0.8180 data_time: 0.1749 memory: 15027 loss_ce: 0.0741 loss: 0.0741 2022/09/15 19:25:56 - mmengine - INFO - Epoch(train) [4][1000/6912] lr: 1.0000e-04 eta: 2:15:59 time: 0.5284 data_time: 0.0511 memory: 15027 loss_ce: 0.0754 loss: 0.0754 2022/09/15 19:27:00 - mmengine - INFO - Epoch(train) [4][1100/6912] lr: 1.0000e-04 eta: 2:14:56 time: 0.5257 data_time: 0.0892 memory: 15027 loss_ce: 0.0828 loss: 0.0828 2022/09/15 19:28:03 - mmengine - INFO - Epoch(train) [4][1200/6912] lr: 1.0000e-04 eta: 2:13:52 time: 0.4273 data_time: 0.0206 memory: 15027 loss_ce: 0.0619 loss: 0.0619 2022/09/15 19:28:44 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 19:29:07 - mmengine - INFO - Epoch(train) [4][1300/6912] lr: 1.0000e-04 eta: 2:12:49 time: 0.6414 data_time: 0.1449 memory: 15027 loss_ce: 0.0697 loss: 0.0697 2022/09/15 19:30:14 - mmengine - INFO - Epoch(train) [4][1400/6912] lr: 1.0000e-04 eta: 2:11:47 time: 0.8971 data_time: 0.1406 memory: 15027 loss_ce: 0.0656 loss: 0.0656 2022/09/15 19:31:17 - mmengine - INFO - Epoch(train) [4][1500/6912] lr: 1.0000e-04 eta: 2:10:43 time: 0.7936 data_time: 0.1597 memory: 15027 loss_ce: 0.0696 loss: 0.0696 2022/09/15 19:32:19 - mmengine - INFO - Epoch(train) [4][1600/6912] lr: 1.0000e-04 eta: 2:09:38 time: 0.5322 data_time: 0.0478 memory: 15027 loss_ce: 0.0665 loss: 0.0665 2022/09/15 19:33:23 - mmengine - INFO - Epoch(train) [4][1700/6912] lr: 1.0000e-04 eta: 2:08:35 time: 0.4986 data_time: 0.0794 memory: 15027 loss_ce: 0.0652 loss: 0.0652 2022/09/15 19:34:26 - mmengine - INFO - Epoch(train) [4][1800/6912] lr: 1.0000e-04 eta: 2:07:31 time: 0.4403 data_time: 0.0187 memory: 15027 loss_ce: 0.0696 loss: 0.0696 2022/09/15 19:35:31 - mmengine - INFO - Epoch(train) [4][1900/6912] lr: 1.0000e-04 eta: 2:06:28 time: 0.7509 data_time: 0.1662 memory: 15027 loss_ce: 0.0604 loss: 0.0604 2022/09/15 19:36:36 - mmengine - INFO - Epoch(train) [4][2000/6912] lr: 1.0000e-04 eta: 2:05:25 time: 0.8483 data_time: 0.1401 memory: 15027 loss_ce: 0.0709 loss: 0.0709 2022/09/15 19:37:40 - mmengine - INFO - Epoch(train) [4][2100/6912] lr: 1.0000e-04 eta: 2:04:21 time: 0.7973 data_time: 0.1497 memory: 15027 loss_ce: 0.0668 loss: 0.0668 2022/09/15 19:38:43 - mmengine - INFO - Epoch(train) [4][2200/6912] lr: 1.0000e-04 eta: 2:03:17 time: 0.5867 data_time: 0.0708 memory: 15027 loss_ce: 0.0709 loss: 0.0709 2022/09/15 19:39:25 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 19:39:46 - mmengine - INFO - Epoch(train) [4][2300/6912] lr: 1.0000e-04 eta: 2:02:14 time: 0.4696 data_time: 0.0638 memory: 15027 loss_ce: 0.0660 loss: 0.0660 2022/09/15 19:40:48 - mmengine - INFO - Epoch(train) [4][2400/6912] lr: 1.0000e-04 eta: 2:01:09 time: 0.4191 data_time: 0.0181 memory: 15027 loss_ce: 0.0666 loss: 0.0666 2022/09/15 19:41:52 - mmengine - INFO - Epoch(train) [4][2500/6912] lr: 1.0000e-04 eta: 2:00:06 time: 0.6350 data_time: 0.1376 memory: 15027 loss_ce: 0.0750 loss: 0.0750 2022/09/15 19:42:56 - mmengine - INFO - Epoch(train) [4][2600/6912] lr: 1.0000e-04 eta: 1:59:02 time: 0.8763 data_time: 0.1552 memory: 15027 loss_ce: 0.0708 loss: 0.0708 2022/09/15 19:43:59 - mmengine - INFO - Epoch(train) [4][2700/6912] lr: 1.0000e-04 eta: 1:57:58 time: 0.7539 data_time: 0.1436 memory: 15027 loss_ce: 0.0649 loss: 0.0649 2022/09/15 19:45:02 - mmengine - INFO - Epoch(train) [4][2800/6912] lr: 1.0000e-04 eta: 1:56:54 time: 0.5666 data_time: 0.0478 memory: 15027 loss_ce: 0.0760 loss: 0.0760 2022/09/15 19:46:04 - mmengine - INFO - Epoch(train) [4][2900/6912] lr: 1.0000e-04 eta: 1:55:50 time: 0.4709 data_time: 0.0673 memory: 15027 loss_ce: 0.0708 loss: 0.0708 2022/09/15 19:47:06 - mmengine - INFO - Epoch(train) [4][3000/6912] lr: 1.0000e-04 eta: 1:54:46 time: 0.4397 data_time: 0.0169 memory: 15027 loss_ce: 0.0615 loss: 0.0615 2022/09/15 19:48:10 - mmengine - INFO - Epoch(train) [4][3100/6912] lr: 1.0000e-04 eta: 1:53:42 time: 0.6217 data_time: 0.1077 memory: 15027 loss_ce: 0.0658 loss: 0.0658 2022/09/15 19:49:15 - mmengine - INFO - Epoch(train) [4][3200/6912] lr: 1.0000e-04 eta: 1:52:39 time: 0.8017 data_time: 0.1166 memory: 15027 loss_ce: 0.0736 loss: 0.0736 2022/09/15 19:49:53 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 19:50:18 - mmengine - INFO - Epoch(train) [4][3300/6912] lr: 1.0000e-04 eta: 1:51:35 time: 0.8414 data_time: 0.1366 memory: 15027 loss_ce: 0.0759 loss: 0.0759 2022/09/15 19:51:20 - mmengine - INFO - Epoch(train) [4][3400/6912] lr: 1.0000e-04 eta: 1:50:31 time: 0.5987 data_time: 0.0502 memory: 15027 loss_ce: 0.0592 loss: 0.0592 2022/09/15 19:52:22 - mmengine - INFO - Epoch(train) [4][3500/6912] lr: 1.0000e-04 eta: 1:49:27 time: 0.4729 data_time: 0.0628 memory: 15027 loss_ce: 0.0716 loss: 0.0716 2022/09/15 19:53:24 - mmengine - INFO - Epoch(train) [4][3600/6912] lr: 1.0000e-04 eta: 1:48:22 time: 0.4278 data_time: 0.0188 memory: 15027 loss_ce: 0.0558 loss: 0.0558 2022/09/15 19:54:29 - mmengine - INFO - Epoch(train) [4][3700/6912] lr: 1.0000e-04 eta: 1:47:19 time: 0.6654 data_time: 0.1483 memory: 15027 loss_ce: 0.0691 loss: 0.0691 2022/09/15 19:55:33 - mmengine - INFO - Epoch(train) [4][3800/6912] lr: 1.0000e-04 eta: 1:46:16 time: 0.8449 data_time: 0.1370 memory: 15027 loss_ce: 0.0656 loss: 0.0656 2022/09/15 19:56:35 - mmengine - INFO - Epoch(train) [4][3900/6912] lr: 1.0000e-04 eta: 1:45:11 time: 0.8081 data_time: 0.1622 memory: 15027 loss_ce: 0.0663 loss: 0.0663 2022/09/15 19:57:37 - mmengine - INFO - Epoch(train) [4][4000/6912] lr: 1.0000e-04 eta: 1:44:07 time: 0.5727 data_time: 0.0446 memory: 15027 loss_ce: 0.0678 loss: 0.0678 2022/09/15 19:58:40 - mmengine - INFO - Epoch(train) [4][4100/6912] lr: 1.0000e-04 eta: 1:43:03 time: 0.4777 data_time: 0.0722 memory: 15027 loss_ce: 0.0697 loss: 0.0697 2022/09/15 19:59:42 - mmengine - INFO - Epoch(train) [4][4200/6912] lr: 1.0000e-04 eta: 1:41:59 time: 0.4291 data_time: 0.0175 memory: 15027 loss_ce: 0.0581 loss: 0.0581 2022/09/15 20:00:23 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 20:00:46 - mmengine - INFO - Epoch(train) [4][4300/6912] lr: 1.0000e-04 eta: 1:40:56 time: 0.6319 data_time: 0.1205 memory: 15027 loss_ce: 0.0616 loss: 0.0616 2022/09/15 20:01:50 - mmengine - INFO - Epoch(train) [4][4400/6912] lr: 1.0000e-04 eta: 1:39:52 time: 0.7788 data_time: 0.1149 memory: 15027 loss_ce: 0.0709 loss: 0.0709 2022/09/15 20:02:53 - mmengine - INFO - Epoch(train) [4][4500/6912] lr: 1.0000e-04 eta: 1:38:48 time: 0.8374 data_time: 0.1310 memory: 15027 loss_ce: 0.0789 loss: 0.0789 2022/09/15 20:03:56 - mmengine - INFO - Epoch(train) [4][4600/6912] lr: 1.0000e-04 eta: 1:37:45 time: 0.5684 data_time: 0.0449 memory: 15027 loss_ce: 0.0736 loss: 0.0736 2022/09/15 20:04:59 - mmengine - INFO - Epoch(train) [4][4700/6912] lr: 1.0000e-04 eta: 1:36:41 time: 0.4732 data_time: 0.0668 memory: 15027 loss_ce: 0.0763 loss: 0.0763 2022/09/15 20:06:01 - mmengine - INFO - Epoch(train) [4][4800/6912] lr: 1.0000e-04 eta: 1:35:37 time: 0.4175 data_time: 0.0160 memory: 15027 loss_ce: 0.0664 loss: 0.0664 2022/09/15 20:07:06 - mmengine - INFO - Epoch(train) [4][4900/6912] lr: 1.0000e-04 eta: 1:34:34 time: 0.6446 data_time: 0.1443 memory: 15027 loss_ce: 0.0554 loss: 0.0554 2022/09/15 20:08:10 - mmengine - INFO - Epoch(train) [4][5000/6912] lr: 1.0000e-04 eta: 1:33:30 time: 0.8853 data_time: 0.1491 memory: 15027 loss_ce: 0.0652 loss: 0.0652 2022/09/15 20:09:14 - mmengine - INFO - Epoch(train) [4][5100/6912] lr: 1.0000e-04 eta: 1:32:27 time: 0.7953 data_time: 0.1662 memory: 15027 loss_ce: 0.0534 loss: 0.0534 2022/09/15 20:10:17 - mmengine - INFO - Epoch(train) [4][5200/6912] lr: 1.0000e-04 eta: 1:31:23 time: 0.5633 data_time: 0.0480 memory: 15027 loss_ce: 0.0631 loss: 0.0631 2022/09/15 20:10:59 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 20:11:20 - mmengine - INFO - Epoch(train) [4][5300/6912] lr: 1.0000e-04 eta: 1:30:19 time: 0.4899 data_time: 0.0637 memory: 15027 loss_ce: 0.0636 loss: 0.0636 2022/09/15 20:12:23 - mmengine - INFO - Epoch(train) [4][5400/6912] lr: 1.0000e-04 eta: 1:29:15 time: 0.4247 data_time: 0.0173 memory: 15027 loss_ce: 0.0629 loss: 0.0629 2022/09/15 20:13:28 - mmengine - INFO - Epoch(train) [4][5500/6912] lr: 1.0000e-04 eta: 1:28:12 time: 0.6461 data_time: 0.1317 memory: 15027 loss_ce: 0.0724 loss: 0.0724 2022/09/15 20:14:33 - mmengine - INFO - Epoch(train) [4][5600/6912] lr: 1.0000e-04 eta: 1:27:09 time: 0.8057 data_time: 0.1091 memory: 15027 loss_ce: 0.0667 loss: 0.0667 2022/09/15 20:15:37 - mmengine - INFO - Epoch(train) [4][5700/6912] lr: 1.0000e-04 eta: 1:26:06 time: 0.8194 data_time: 0.1345 memory: 15027 loss_ce: 0.0625 loss: 0.0625 2022/09/15 20:16:39 - mmengine - INFO - Epoch(train) [4][5800/6912] lr: 1.0000e-04 eta: 1:25:02 time: 0.5506 data_time: 0.0490 memory: 15027 loss_ce: 0.0590 loss: 0.0590 2022/09/15 20:17:43 - mmengine - INFO - Epoch(train) [4][5900/6912] lr: 1.0000e-04 eta: 1:23:58 time: 0.4579 data_time: 0.0591 memory: 15027 loss_ce: 0.0644 loss: 0.0644 2022/09/15 20:18:45 - mmengine - INFO - Epoch(train) [4][6000/6912] lr: 1.0000e-04 eta: 1:22:54 time: 0.4248 data_time: 0.0175 memory: 15027 loss_ce: 0.0819 loss: 0.0819 2022/09/15 20:19:50 - mmengine - INFO - Epoch(train) [4][6100/6912] lr: 1.0000e-04 eta: 1:21:51 time: 0.6450 data_time: 0.1349 memory: 15027 loss_ce: 0.0585 loss: 0.0585 2022/09/15 20:20:54 - mmengine - INFO - Epoch(train) [4][6200/6912] lr: 1.0000e-04 eta: 1:20:48 time: 0.8507 data_time: 0.1335 memory: 15027 loss_ce: 0.0670 loss: 0.0670 2022/09/15 20:21:32 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 20:21:57 - mmengine - INFO - Epoch(train) [4][6300/6912] lr: 1.0000e-04 eta: 1:19:44 time: 0.8556 data_time: 0.1533 memory: 15027 loss_ce: 0.0673 loss: 0.0673 2022/09/15 20:22:59 - mmengine - INFO - Epoch(train) [4][6400/6912] lr: 1.0000e-04 eta: 1:18:40 time: 0.5856 data_time: 0.0492 memory: 15027 loss_ce: 0.0673 loss: 0.0673 2022/09/15 20:24:01 - mmengine - INFO - Epoch(train) [4][6500/6912] lr: 1.0000e-04 eta: 1:17:36 time: 0.4708 data_time: 0.0561 memory: 15027 loss_ce: 0.0594 loss: 0.0594 2022/09/15 20:25:03 - mmengine - INFO - Epoch(train) [4][6600/6912] lr: 1.0000e-04 eta: 1:16:32 time: 0.4330 data_time: 0.0218 memory: 15027 loss_ce: 0.0599 loss: 0.0599 2022/09/15 20:26:07 - mmengine - INFO - Epoch(train) [4][6700/6912] lr: 1.0000e-04 eta: 1:15:28 time: 0.5973 data_time: 0.1143 memory: 15027 loss_ce: 0.0692 loss: 0.0692 2022/09/15 20:27:11 - mmengine - INFO - Epoch(train) [4][6800/6912] lr: 1.0000e-04 eta: 1:14:25 time: 0.8169 data_time: 0.1144 memory: 15027 loss_ce: 0.0554 loss: 0.0554 2022/09/15 20:28:12 - mmengine - INFO - Epoch(train) [4][6900/6912] lr: 1.0000e-04 eta: 1:13:21 time: 0.6449 data_time: 0.0927 memory: 15027 loss_ce: 0.0726 loss: 0.0726 2022/09/15 20:28:17 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 20:28:17 - mmengine - INFO - Saving checkpoint at 4 epochs 2022/09/15 20:28:38 - mmengine - INFO - Epoch(val) [4][100/1918] eta: 0:01:38 time: 0.0542 data_time: 0.0008 memory: 15027 2022/09/15 20:28:43 - mmengine - INFO - Epoch(val) [4][200/1918] eta: 0:01:36 time: 0.0560 data_time: 0.0008 memory: 951 2022/09/15 20:28:48 - mmengine - INFO - Epoch(val) [4][300/1918] eta: 0:01:27 time: 0.0540 data_time: 0.0016 memory: 951 2022/09/15 20:28:53 - mmengine - INFO - Epoch(val) [4][400/1918] eta: 0:01:23 time: 0.0547 data_time: 0.0008 memory: 951 2022/09/15 20:28:58 - mmengine - INFO - Epoch(val) [4][500/1918] eta: 0:01:04 time: 0.0455 data_time: 0.0007 memory: 951 2022/09/15 20:29:03 - mmengine - INFO - Epoch(val) [4][600/1918] eta: 0:01:04 time: 0.0488 data_time: 0.0006 memory: 951 2022/09/15 20:29:09 - mmengine - INFO - Epoch(val) [4][700/1918] eta: 0:01:01 time: 0.0502 data_time: 0.0007 memory: 951 2022/09/15 20:29:13 - mmengine - INFO - Epoch(val) [4][800/1918] eta: 0:00:52 time: 0.0473 data_time: 0.0008 memory: 951 2022/09/15 20:29:19 - mmengine - INFO - Epoch(val) [4][900/1918] eta: 0:00:55 time: 0.0540 data_time: 0.0010 memory: 951 2022/09/15 20:29:24 - mmengine - INFO - Epoch(val) [4][1000/1918] eta: 0:00:47 time: 0.0522 data_time: 0.0008 memory: 951 2022/09/15 20:29:29 - mmengine - INFO - Epoch(val) [4][1100/1918] eta: 0:00:37 time: 0.0455 data_time: 0.0007 memory: 951 2022/09/15 20:29:34 - mmengine - INFO - Epoch(val) [4][1200/1918] eta: 0:00:33 time: 0.0466 data_time: 0.0010 memory: 951 2022/09/15 20:29:39 - mmengine - INFO - Epoch(val) [4][1300/1918] eta: 0:00:31 time: 0.0502 data_time: 0.0007 memory: 951 2022/09/15 20:29:44 - mmengine - INFO - Epoch(val) [4][1400/1918] eta: 0:00:27 time: 0.0522 data_time: 0.0008 memory: 951 2022/09/15 20:29:49 - mmengine - INFO - Epoch(val) [4][1500/1918] eta: 0:00:18 time: 0.0439 data_time: 0.0006 memory: 951 2022/09/15 20:29:54 - mmengine - INFO - Epoch(val) [4][1600/1918] eta: 0:00:14 time: 0.0468 data_time: 0.0006 memory: 951 2022/09/15 20:29:58 - mmengine - INFO - Epoch(val) [4][1700/1918] eta: 0:00:10 time: 0.0475 data_time: 0.0007 memory: 951 2022/09/15 20:30:03 - mmengine - INFO - Epoch(val) [4][1800/1918] eta: 0:00:05 time: 0.0439 data_time: 0.0006 memory: 951 2022/09/15 20:30:08 - mmengine - INFO - Epoch(val) [4][1900/1918] eta: 0:00:00 time: 0.0429 data_time: 0.0006 memory: 951 2022/09/15 20:30:09 - mmengine - INFO - Epoch(val) [4][1918/1918] CUTE80/recog/word_acc_ignore_case_symbol: 0.8924 IIIT5K/recog/word_acc_ignore_case_symbol: 0.9510 SVT/recog/word_acc_ignore_case_symbol: 0.8825 SVTP/recog/word_acc_ignore_case_symbol: 0.7969 IC13/recog/word_acc_ignore_case_symbol: 0.9291 IC15/recog/word_acc_ignore_case_symbol: 0.7593 2022/09/15 20:31:17 - mmengine - INFO - Epoch(train) [5][100/6912] lr: 1.0000e-05 eta: 1:12:10 time: 0.7231 data_time: 0.1482 memory: 15027 loss_ce: 0.0617 loss: 0.0617 2022/09/15 20:32:22 - mmengine - INFO - Epoch(train) [5][200/6912] lr: 1.0000e-05 eta: 1:11:06 time: 0.8553 data_time: 0.1803 memory: 15027 loss_ce: 0.0669 loss: 0.0669 2022/09/15 20:33:24 - mmengine - INFO - Epoch(train) [5][300/6912] lr: 1.0000e-05 eta: 1:10:02 time: 0.7472 data_time: 0.1092 memory: 15027 loss_ce: 0.0600 loss: 0.0600 2022/09/15 20:33:55 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 20:34:26 - mmengine - INFO - Epoch(train) [5][400/6912] lr: 1.0000e-05 eta: 1:08:59 time: 0.6222 data_time: 0.0951 memory: 15027 loss_ce: 0.0642 loss: 0.0642 2022/09/15 20:35:28 - mmengine - INFO - Epoch(train) [5][500/6912] lr: 1.0000e-05 eta: 1:07:55 time: 0.4533 data_time: 0.0054 memory: 15027 loss_ce: 0.0534 loss: 0.0534 2022/09/15 20:36:30 - mmengine - INFO - Epoch(train) [5][600/6912] lr: 1.0000e-05 eta: 1:06:51 time: 0.4514 data_time: 0.0036 memory: 15027 loss_ce: 0.0552 loss: 0.0552 2022/09/15 20:37:34 - mmengine - INFO - Epoch(train) [5][700/6912] lr: 1.0000e-05 eta: 1:05:47 time: 0.6637 data_time: 0.1147 memory: 15027 loss_ce: 0.0554 loss: 0.0554 2022/09/15 20:38:39 - mmengine - INFO - Epoch(train) [5][800/6912] lr: 1.0000e-05 eta: 1:04:44 time: 0.8303 data_time: 0.1928 memory: 15027 loss_ce: 0.0577 loss: 0.0577 2022/09/15 20:39:41 - mmengine - INFO - Epoch(train) [5][900/6912] lr: 1.0000e-05 eta: 1:03:40 time: 0.7331 data_time: 0.1063 memory: 15027 loss_ce: 0.0442 loss: 0.0442 2022/09/15 20:40:44 - mmengine - INFO - Epoch(train) [5][1000/6912] lr: 1.0000e-05 eta: 1:02:36 time: 0.6355 data_time: 0.1070 memory: 15027 loss_ce: 0.0540 loss: 0.0540 2022/09/15 20:41:47 - mmengine - INFO - Epoch(train) [5][1100/6912] lr: 1.0000e-05 eta: 1:01:33 time: 0.5077 data_time: 0.0037 memory: 15027 loss_ce: 0.0587 loss: 0.0587 2022/09/15 20:42:48 - mmengine - INFO - Epoch(train) [5][1200/6912] lr: 1.0000e-05 eta: 1:00:29 time: 0.4252 data_time: 0.0053 memory: 15027 loss_ce: 0.0639 loss: 0.0639 2022/09/15 20:43:53 - mmengine - INFO - Epoch(train) [5][1300/6912] lr: 1.0000e-05 eta: 0:59:25 time: 0.6029 data_time: 0.0882 memory: 15027 loss_ce: 0.0549 loss: 0.0549 2022/09/15 20:44:27 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 20:44:58 - mmengine - INFO - Epoch(train) [5][1400/6912] lr: 1.0000e-05 eta: 0:58:22 time: 0.8909 data_time: 0.1984 memory: 15027 loss_ce: 0.0497 loss: 0.0497 2022/09/15 20:46:00 - mmengine - INFO - Epoch(train) [5][1500/6912] lr: 1.0000e-05 eta: 0:57:18 time: 0.7198 data_time: 0.0832 memory: 15027 loss_ce: 0.0575 loss: 0.0575 2022/09/15 20:47:02 - mmengine - INFO - Epoch(train) [5][1600/6912] lr: 1.0000e-05 eta: 0:56:15 time: 0.6505 data_time: 0.1125 memory: 15027 loss_ce: 0.0631 loss: 0.0631 2022/09/15 20:48:04 - mmengine - INFO - Epoch(train) [5][1700/6912] lr: 1.0000e-05 eta: 0:55:11 time: 0.4623 data_time: 0.0053 memory: 15027 loss_ce: 0.0627 loss: 0.0627 2022/09/15 20:49:05 - mmengine - INFO - Epoch(train) [5][1800/6912] lr: 1.0000e-05 eta: 0:54:07 time: 0.4274 data_time: 0.0034 memory: 15027 loss_ce: 0.0512 loss: 0.0512 2022/09/15 20:50:09 - mmengine - INFO - Epoch(train) [5][1900/6912] lr: 1.0000e-05 eta: 0:53:03 time: 0.6130 data_time: 0.1123 memory: 15027 loss_ce: 0.0609 loss: 0.0609 2022/09/15 20:51:13 - mmengine - INFO - Epoch(train) [5][2000/6912] lr: 1.0000e-05 eta: 0:52:00 time: 0.8449 data_time: 0.1984 memory: 15027 loss_ce: 0.0604 loss: 0.0604 2022/09/15 20:52:15 - mmengine - INFO - Epoch(train) [5][2100/6912] lr: 1.0000e-05 eta: 0:50:56 time: 0.7376 data_time: 0.1119 memory: 15027 loss_ce: 0.0520 loss: 0.0520 2022/09/15 20:53:18 - mmengine - INFO - Epoch(train) [5][2200/6912] lr: 1.0000e-05 eta: 0:49:52 time: 0.6486 data_time: 0.0873 memory: 15027 loss_ce: 0.0649 loss: 0.0649 2022/09/15 20:54:20 - mmengine - INFO - Epoch(train) [5][2300/6912] lr: 1.0000e-05 eta: 0:48:49 time: 0.4806 data_time: 0.0040 memory: 15027 loss_ce: 0.0689 loss: 0.0689 2022/09/15 20:54:53 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 20:55:22 - mmengine - INFO - Epoch(train) [5][2400/6912] lr: 1.0000e-05 eta: 0:47:45 time: 0.4285 data_time: 0.0035 memory: 15027 loss_ce: 0.0557 loss: 0.0557 2022/09/15 20:56:26 - mmengine - INFO - Epoch(train) [5][2500/6912] lr: 1.0000e-05 eta: 0:46:42 time: 0.6399 data_time: 0.0893 memory: 15027 loss_ce: 0.0483 loss: 0.0483 2022/09/15 20:57:30 - mmengine - INFO - Epoch(train) [5][2600/6912] lr: 1.0000e-05 eta: 0:45:38 time: 0.8522 data_time: 0.2207 memory: 15027 loss_ce: 0.0643 loss: 0.0643 2022/09/15 20:58:31 - mmengine - INFO - Epoch(train) [5][2700/6912] lr: 1.0000e-05 eta: 0:44:34 time: 0.7245 data_time: 0.0890 memory: 15027 loss_ce: 0.0512 loss: 0.0512 2022/09/15 20:59:35 - mmengine - INFO - Epoch(train) [5][2800/6912] lr: 1.0000e-05 eta: 0:43:31 time: 0.6554 data_time: 0.1117 memory: 15027 loss_ce: 0.0549 loss: 0.0549 2022/09/15 21:00:37 - mmengine - INFO - Epoch(train) [5][2900/6912] lr: 1.0000e-05 eta: 0:42:27 time: 0.4850 data_time: 0.0038 memory: 15027 loss_ce: 0.0591 loss: 0.0591 2022/09/15 21:01:38 - mmengine - INFO - Epoch(train) [5][3000/6912] lr: 1.0000e-05 eta: 0:41:23 time: 0.4277 data_time: 0.0035 memory: 15027 loss_ce: 0.0574 loss: 0.0574 2022/09/15 21:02:43 - mmengine - INFO - Epoch(train) [5][3100/6912] lr: 1.0000e-05 eta: 0:40:20 time: 0.6277 data_time: 0.1080 memory: 15027 loss_ce: 0.0508 loss: 0.0508 2022/09/15 21:03:48 - mmengine - INFO - Epoch(train) [5][3200/6912] lr: 1.0000e-05 eta: 0:39:17 time: 0.8810 data_time: 0.2065 memory: 15027 loss_ce: 0.0602 loss: 0.0602 2022/09/15 21:04:49 - mmengine - INFO - Epoch(train) [5][3300/6912] lr: 1.0000e-05 eta: 0:38:13 time: 0.7475 data_time: 0.1335 memory: 15027 loss_ce: 0.0508 loss: 0.0508 2022/09/15 21:05:21 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 21:05:52 - mmengine - INFO - Epoch(train) [5][3400/6912] lr: 1.0000e-05 eta: 0:37:09 time: 0.6711 data_time: 0.0934 memory: 15027 loss_ce: 0.0659 loss: 0.0659 2022/09/15 21:06:55 - mmengine - INFO - Epoch(train) [5][3500/6912] lr: 1.0000e-05 eta: 0:36:06 time: 0.4865 data_time: 0.0033 memory: 15027 loss_ce: 0.0432 loss: 0.0432 2022/09/15 21:07:55 - mmengine - INFO - Epoch(train) [5][3600/6912] lr: 1.0000e-05 eta: 0:35:02 time: 0.4309 data_time: 0.0042 memory: 15027 loss_ce: 0.0482 loss: 0.0482 2022/09/15 21:08:59 - mmengine - INFO - Epoch(train) [5][3700/6912] lr: 1.0000e-05 eta: 0:33:59 time: 0.6330 data_time: 0.0893 memory: 15027 loss_ce: 0.0513 loss: 0.0513 2022/09/15 21:10:04 - mmengine - INFO - Epoch(train) [5][3800/6912] lr: 1.0000e-05 eta: 0:32:55 time: 0.8510 data_time: 0.1939 memory: 15027 loss_ce: 0.0606 loss: 0.0606 2022/09/15 21:11:04 - mmengine - INFO - Epoch(train) [5][3900/6912] lr: 1.0000e-05 eta: 0:31:51 time: 0.7442 data_time: 0.1054 memory: 15027 loss_ce: 0.0593 loss: 0.0593 2022/09/15 21:12:08 - mmengine - INFO - Epoch(train) [5][4000/6912] lr: 1.0000e-05 eta: 0:30:48 time: 0.6393 data_time: 0.1174 memory: 15027 loss_ce: 0.0530 loss: 0.0530 2022/09/15 21:13:11 - mmengine - INFO - Epoch(train) [5][4100/6912] lr: 1.0000e-05 eta: 0:29:44 time: 0.4962 data_time: 0.0051 memory: 15027 loss_ce: 0.0599 loss: 0.0599 2022/09/15 21:14:12 - mmengine - INFO - Epoch(train) [5][4200/6912] lr: 1.0000e-05 eta: 0:28:41 time: 0.4324 data_time: 0.0041 memory: 15027 loss_ce: 0.0574 loss: 0.0574 2022/09/15 21:15:17 - mmengine - INFO - Epoch(train) [5][4300/6912] lr: 1.0000e-05 eta: 0:27:37 time: 0.6460 data_time: 0.1182 memory: 15027 loss_ce: 0.0634 loss: 0.0634 2022/09/15 21:15:52 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 21:16:22 - mmengine - INFO - Epoch(train) [5][4400/6912] lr: 1.0000e-05 eta: 0:26:34 time: 0.7969 data_time: 0.1769 memory: 15027 loss_ce: 0.0566 loss: 0.0566 2022/09/15 21:17:23 - mmengine - INFO - Epoch(train) [5][4500/6912] lr: 1.0000e-05 eta: 0:25:30 time: 0.7512 data_time: 0.0915 memory: 15027 loss_ce: 0.0647 loss: 0.0647 2022/09/15 21:18:26 - mmengine - INFO - Epoch(train) [5][4600/6912] lr: 1.0000e-05 eta: 0:24:27 time: 0.6298 data_time: 0.0904 memory: 15027 loss_ce: 0.0573 loss: 0.0573 2022/09/15 21:19:29 - mmengine - INFO - Epoch(train) [5][4700/6912] lr: 1.0000e-05 eta: 0:23:23 time: 0.4729 data_time: 0.0042 memory: 15027 loss_ce: 0.0445 loss: 0.0445 2022/09/15 21:20:30 - mmengine - INFO - Epoch(train) [5][4800/6912] lr: 1.0000e-05 eta: 0:22:20 time: 0.4335 data_time: 0.0050 memory: 15027 loss_ce: 0.0623 loss: 0.0623 2022/09/15 21:21:36 - mmengine - INFO - Epoch(train) [5][4900/6912] lr: 1.0000e-05 eta: 0:21:16 time: 0.6514 data_time: 0.1189 memory: 15027 loss_ce: 0.0592 loss: 0.0592 2022/09/15 21:22:40 - mmengine - INFO - Epoch(train) [5][5000/6912] lr: 1.0000e-05 eta: 0:20:13 time: 0.8340 data_time: 0.1890 memory: 15027 loss_ce: 0.0602 loss: 0.0602 2022/09/15 21:23:42 - mmengine - INFO - Epoch(train) [5][5100/6912] lr: 1.0000e-05 eta: 0:19:09 time: 0.7633 data_time: 0.1119 memory: 15027 loss_ce: 0.0602 loss: 0.0602 2022/09/15 21:24:46 - mmengine - INFO - Epoch(train) [5][5200/6912] lr: 1.0000e-05 eta: 0:18:06 time: 0.6937 data_time: 0.1241 memory: 15027 loss_ce: 0.0590 loss: 0.0590 2022/09/15 21:25:49 - mmengine - INFO - Epoch(train) [5][5300/6912] lr: 1.0000e-05 eta: 0:17:02 time: 0.4614 data_time: 0.0037 memory: 15027 loss_ce: 0.0521 loss: 0.0521 2022/09/15 21:26:20 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 21:26:50 - mmengine - INFO - Epoch(train) [5][5400/6912] lr: 1.0000e-05 eta: 0:15:59 time: 0.4440 data_time: 0.0045 memory: 15027 loss_ce: 0.0644 loss: 0.0644 2022/09/15 21:27:55 - mmengine - INFO - Epoch(train) [5][5500/6912] lr: 1.0000e-05 eta: 0:14:56 time: 0.6235 data_time: 0.0861 memory: 15027 loss_ce: 0.0605 loss: 0.0605 2022/09/15 21:28:59 - mmengine - INFO - Epoch(train) [5][5600/6912] lr: 1.0000e-05 eta: 0:13:52 time: 0.8450 data_time: 0.2052 memory: 15027 loss_ce: 0.0625 loss: 0.0625 2022/09/15 21:30:01 - mmengine - INFO - Epoch(train) [5][5700/6912] lr: 1.0000e-05 eta: 0:12:49 time: 0.7127 data_time: 0.0897 memory: 15027 loss_ce: 0.0383 loss: 0.0383 2022/09/15 21:31:03 - mmengine - INFO - Epoch(train) [5][5800/6912] lr: 1.0000e-05 eta: 0:11:45 time: 0.6527 data_time: 0.1192 memory: 15027 loss_ce: 0.0516 loss: 0.0516 2022/09/15 21:32:05 - mmengine - INFO - Epoch(train) [5][5900/6912] lr: 1.0000e-05 eta: 0:10:42 time: 0.4764 data_time: 0.0035 memory: 15027 loss_ce: 0.0638 loss: 0.0638 2022/09/15 21:33:06 - mmengine - INFO - Epoch(train) [5][6000/6912] lr: 1.0000e-05 eta: 0:09:38 time: 0.4564 data_time: 0.0040 memory: 15027 loss_ce: 0.0587 loss: 0.0587 2022/09/15 21:34:11 - mmengine - INFO - Epoch(train) [5][6100/6912] lr: 1.0000e-05 eta: 0:08:35 time: 0.6156 data_time: 0.1171 memory: 15027 loss_ce: 0.0573 loss: 0.0573 2022/09/15 21:35:15 - mmengine - INFO - Epoch(train) [5][6200/6912] lr: 1.0000e-05 eta: 0:07:31 time: 0.8077 data_time: 0.1773 memory: 15027 loss_ce: 0.0513 loss: 0.0513 2022/09/15 21:36:18 - mmengine - INFO - Epoch(train) [5][6300/6912] lr: 1.0000e-05 eta: 0:06:28 time: 0.7863 data_time: 0.1164 memory: 15027 loss_ce: 0.0614 loss: 0.0614 2022/09/15 21:36:50 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 21:37:21 - mmengine - INFO - Epoch(train) [5][6400/6912] lr: 1.0000e-05 eta: 0:05:24 time: 0.6508 data_time: 0.0914 memory: 15027 loss_ce: 0.0513 loss: 0.0513 2022/09/15 21:38:23 - mmengine - INFO - Epoch(train) [5][6500/6912] lr: 1.0000e-05 eta: 0:04:21 time: 0.4650 data_time: 0.0038 memory: 15027 loss_ce: 0.0510 loss: 0.0510 2022/09/15 21:39:24 - mmengine - INFO - Epoch(train) [5][6600/6912] lr: 1.0000e-05 eta: 0:03:17 time: 0.4353 data_time: 0.0036 memory: 15027 loss_ce: 0.0695 loss: 0.0695 2022/09/15 21:40:30 - mmengine - INFO - Epoch(train) [5][6700/6912] lr: 1.0000e-05 eta: 0:02:14 time: 0.6079 data_time: 0.0874 memory: 15027 loss_ce: 0.0642 loss: 0.0642 2022/09/15 21:41:33 - mmengine - INFO - Epoch(train) [5][6800/6912] lr: 1.0000e-05 eta: 0:01:11 time: 0.8397 data_time: 0.1674 memory: 15027 loss_ce: 0.0567 loss: 0.0567 2022/09/15 21:42:33 - mmengine - INFO - Epoch(train) [5][6900/6912] lr: 1.0000e-05 eta: 0:00:07 time: 0.6135 data_time: 0.0609 memory: 15027 loss_ce: 0.0522 loss: 0.0522 2022/09/15 21:42:39 - mmengine - INFO - Exp name: robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447 2022/09/15 21:42:39 - mmengine - INFO - Saving checkpoint at 5 epochs 2022/09/15 21:43:02 - mmengine - INFO - Epoch(val) [5][100/1918] eta: 0:01:45 time: 0.0578 data_time: 0.0009 memory: 15027 2022/09/15 21:43:07 - mmengine - INFO - Epoch(val) [5][200/1918] eta: 0:01:28 time: 0.0515 data_time: 0.0008 memory: 951 2022/09/15 21:43:13 - mmengine - INFO - Epoch(val) [5][300/1918] eta: 0:01:28 time: 0.0549 data_time: 0.0008 memory: 951 2022/09/15 21:43:18 - mmengine - INFO - Epoch(val) [5][400/1918] eta: 0:01:25 time: 0.0563 data_time: 0.0008 memory: 951 2022/09/15 21:43:23 - mmengine - INFO - Epoch(val) [5][500/1918] eta: 0:01:20 time: 0.0567 data_time: 0.0009 memory: 951 2022/09/15 21:43:29 - mmengine - INFO - Epoch(val) [5][600/1918] eta: 0:01:05 time: 0.0497 data_time: 0.0008 memory: 951 2022/09/15 21:43:34 - mmengine - INFO - Epoch(val) [5][700/1918] eta: 0:01:02 time: 0.0515 data_time: 0.0009 memory: 951 2022/09/15 21:43:40 - mmengine - INFO - Epoch(val) [5][800/1918] eta: 0:00:56 time: 0.0502 data_time: 0.0008 memory: 951 2022/09/15 21:43:45 - mmengine - INFO - Epoch(val) [5][900/1918] eta: 0:00:54 time: 0.0537 data_time: 0.0008 memory: 951 2022/09/15 21:43:50 - mmengine - INFO - Epoch(val) [5][1000/1918] eta: 0:00:48 time: 0.0531 data_time: 0.0009 memory: 951 2022/09/15 21:43:56 - mmengine - INFO - Epoch(val) [5][1100/1918] eta: 0:00:45 time: 0.0560 data_time: 0.0008 memory: 951 2022/09/15 21:44:01 - mmengine - INFO - Epoch(val) [5][1200/1918] eta: 0:00:37 time: 0.0524 data_time: 0.0008 memory: 951 2022/09/15 21:44:07 - mmengine - INFO - Epoch(val) [5][1300/1918] eta: 0:00:33 time: 0.0539 data_time: 0.0009 memory: 951 2022/09/15 21:44:12 - mmengine - INFO - Epoch(val) [5][1400/1918] eta: 0:00:32 time: 0.0618 data_time: 0.0010 memory: 951 2022/09/15 21:44:17 - mmengine - INFO - Epoch(val) [5][1500/1918] eta: 0:00:22 time: 0.0540 data_time: 0.0008 memory: 951 2022/09/15 21:44:23 - mmengine - INFO - Epoch(val) [5][1600/1918] eta: 0:00:16 time: 0.0507 data_time: 0.0008 memory: 951 2022/09/15 21:44:28 - mmengine - INFO - Epoch(val) [5][1700/1918] eta: 0:00:09 time: 0.0457 data_time: 0.0007 memory: 951 2022/09/15 21:44:33 - mmengine - INFO - Epoch(val) [5][1800/1918] eta: 0:00:05 time: 0.0484 data_time: 0.0008 memory: 951 2022/09/15 21:44:38 - mmengine - INFO - Epoch(val) [5][1900/1918] eta: 0:00:00 time: 0.0490 data_time: 0.0009 memory: 951 2022/09/15 21:44:39 - mmengine - INFO - Epoch(val) [5][1918/1918] CUTE80/recog/word_acc_ignore_case_symbol: 0.8715 IIIT5K/recog/word_acc_ignore_case_symbol: 0.9510 SVT/recog/word_acc_ignore_case_symbol: 0.8934 SVTP/recog/word_acc_ignore_case_symbol: 0.8078 IC13/recog/word_acc_ignore_case_symbol: 0.9320 IC15/recog/word_acc_ignore_case_symbol: 0.7559