2023/03/03 10:30:43 - mmengine - INFO - ------------------------------------------------------------ System environment: sys.platform: linux Python: 3.10.8 (main, Nov 24 2022, 14:13:03) [GCC 11.2.0] CUDA available: True numpy_random_seed: 42 GPU 0,1,2,3: NVIDIA A100-SXM4-80GB CUDA_HOME: None GCC: gcc (GCC) 4.8.5 20150623 (Red Hat 4.8.5-44) PyTorch: 1.12.1 PyTorch compiling details: PyTorch built with: - GCC 9.3 - C++ Version: 201402 - Intel(R) oneAPI Math Kernel Library Version 2021.4-Product Build 20210904 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v2.6.0 (Git Hash 52b5f107dd9cf10910aaa19cb47f3abf9b349815) - OpenMP 201511 (a.k.a. OpenMP 4.5) - LAPACK is enabled (usually provided by MKL) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 11.3 - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_37,code=compute_37 - CuDNN 8.3.2 (built against CUDA 11.5) - Magma 2.5.2 - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.3, CUDNN_VERSION=8.3.2, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -fabi-version=11 -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.12.1, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=OFF, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, TorchVision: 0.13.1 OpenCV: 4.7.0 MMEngine: 0.6.0 Runtime environment: cudnn_benchmark: False mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0} dist_cfg: {'backend': 'nccl'} seed: 42 Distributed launcher: pytorch Distributed training: True GPU number: 4 ------------------------------------------------------------ 2023/03/03 10:30:45 - mmengine - INFO - Config: custom_imports = dict(imports=['spts'], allow_failed_imports=False) file_client_args = dict(backend='disk') dictionary = dict( type='SPTSDictionary', dict_file= 'mmocr/projects/SPTS/config/spts/../../dicts/spts.txt', with_start=True, with_end=True, with_seq_end=True, same_start_end=False, with_padding=True, with_unknown=True, unknown_token=None) num_bins = 1000 model = dict( type='SPTS', data_preprocessor=dict( type='TextDetDataPreprocessor', mean=[0, 0, 0], std=[255, 255, 255], bgr_to_rgb=True), backbone=dict( type='mmdet.ResNet', depth=50, num_stages=4, out_indices=(3, ), frozen_stages=-1, norm_cfg=dict(type='BN', requires_grad=False), norm_eval=True, init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50'), style='pytorch'), encoder=dict(type='SPTSEncoder', d_backbone=2048, d_model=256), decoder=dict( type='SPTSDecoder', dictionary=dict( type='SPTSDictionary', dict_file= 'mmocr/projects/SPTS/config/spts/../../dicts/spts.txt', with_start=True, with_end=True, with_seq_end=True, same_start_end=False, with_padding=True, with_unknown=True, unknown_token=None), num_bins=1000, d_model=256, dropout=0.1, max_num_text=60, module_loss=dict( type='SPTSModuleLoss', num_bins=1000, ignore_first_char=True), postprocessor=dict(type='SPTSPostprocessor', num_bins=1000))) test_pipeline = [ dict(type='LoadImageFromFile', color_type='color_ignore_orientation'), dict( type='RescaleToShortSide', short_side_lens=[1000], long_side_bound=1824), dict( type='LoadOCRAnnotationsWithBezier', with_bbox=True, with_label=True, with_polygon=True, with_text=True), dict( type='PackTextDetInputs', meta_keys=('img_path', 'ori_shape', 'img_shape', 'scale_factor')) ] train_pipeline = [ dict(type='LoadImageFromFile', color_type='color_ignore_orientation'), dict( type='LoadOCRAnnotationsWithBezier', with_bbox=True, with_label=True, with_polygon=True, with_text=True), dict(type='FixInvalidPolygon'), dict(type='RemoveIgnored'), dict(type='RandomCrop', min_side_ratio=0.5), dict( type='RandomApply', transforms=[ dict( type='RandomRotate', max_angle=30, pad_with_fixed_color=True, use_canvas=True) ], prob=0.3), dict(type='FixInvalidPolygon'), dict( type='RandomChoiceResize', scales=[(640, 1600), (672, 1600), (704, 1600), (736, 1600), (768, 1600), (800, 1600), (832, 1600), (864, 1600), (896, 1600)], keep_ratio=True), dict( type='RandomApply', transforms=[ dict( type='TorchVisionWrapper', op='ColorJitter', brightness=0.5, contrast=0.5, saturation=0.5, hue=0.5) ], prob=0.5), dict( type='PackTextDetInputs', meta_keys=('img_path', 'ori_shape', 'img_shape', 'scale_factor')) ] totaltext_textspotting_data_root = 'mmocr_data/totaltext' totaltext_textspotting_train = dict( type='OCRDataset', data_root='mmocr_data/totaltext', ann_file='textspotting_train.json', filter_cfg=dict(filter_empty_gt=True, min_size=32), pipeline=[ dict(type='LoadImageFromFile', color_type='color_ignore_orientation'), dict( type='LoadOCRAnnotationsWithBezier', with_bbox=True, with_label=True, with_polygon=True, with_text=True), dict(type='FixInvalidPolygon'), dict(type='RemoveIgnored'), dict(type='RandomCrop', min_side_ratio=0.5), dict( type='RandomApply', transforms=[ dict( type='RandomRotate', max_angle=30, pad_with_fixed_color=True, use_canvas=True) ], prob=0.3), dict(type='FixInvalidPolygon'), dict( type='RandomChoiceResize', scales=[(640, 1600), (672, 1600), (704, 1600), (736, 1600), (768, 1600), (800, 1600), (832, 1600), (864, 1600), (896, 1600)], keep_ratio=True), dict( type='RandomApply', transforms=[ dict( type='TorchVisionWrapper', op='ColorJitter', brightness=0.5, contrast=0.5, saturation=0.5, hue=0.5) ], prob=0.5), dict( type='PackTextDetInputs', meta_keys=('img_path', 'ori_shape', 'img_shape', 'scale_factor')) ]) totaltext_textspotting_test = dict( type='OCRDataset', data_root='mmocr_data/totaltext', ann_file='textspotting_test.json', test_mode=True, pipeline=[ dict(type='LoadImageFromFile', color_type='color_ignore_orientation'), dict( type='RescaleToShortSide', short_side_lens=[1000], long_side_bound=1824), dict( type='LoadOCRAnnotationsWithBezier', with_bbox=True, with_label=True, with_polygon=True, with_text=True), dict( type='PackTextDetInputs', meta_keys=('img_path', 'ori_shape', 'img_shape', 'scale_factor')) ]) default_scope = 'mmocr' env_cfg = dict( cudnn_benchmark=False, mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0), dist_cfg=dict(backend='nccl')) randomness = dict(seed=42) default_hooks = dict( timer=dict(type='IterTimerHook'), logger=dict(type='LoggerHook', interval=10), param_scheduler=dict(type='ParamSchedulerHook'), checkpoint=dict( type='CheckpointHook', save_best='none/hmean', rule='greater'), 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 = 'work_dirs/spts_resnet50_150e_pretrain-spts-2/epoch_150.pth' resume = False val_evaluator = [ dict( type='E2EPointMetric', prefix='none', word_spotting=True, match_dist_thr=0.4), dict( type='E2EPointMetric', prefix='full', lexicon_path='data/totaltext/lexicons/weak_voc_new.txt', pair_path='data/totaltext/lexicons/weak_voc_pair_list.txt', word_spotting=True, match_dist_thr=0.4) ] test_evaluator = [ dict( type='E2EPointMetric', prefix='none', word_spotting=True, match_dist_thr=0.4), dict( type='E2EPointMetric', prefix='full', lexicon_path='data/totaltext/lexicons/weak_voc_new.txt', pair_path='data/totaltext/lexicons/weak_voc_pair_list.txt', word_spotting=True, match_dist_thr=0.4) ] vis_backends = [dict(type='LocalVisBackend')] visualizer = dict( type='TextSpottingLocalVisualizer', name='visualizer', vis_backends=[dict(type='LocalVisBackend')]) num_epochs = 200 lr = 1e-05 optim_wrapper = dict( type='AmpOptimWrapper', accumulative_counts=2, optimizer=dict(type='AdamW', lr=1e-05, weight_decay=0.0001), paramwise_cfg=dict(custom_keys=dict(backbone=dict(lr_mult=0.1))), loss_scale='dynamic') train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=200, val_interval=10) val_cfg = dict(type='ValLoop') test_cfg = dict(type='TestLoop') train_dataloader = dict( batch_size=8, num_workers=8, persistent_workers=True, pin_memory=True, sampler=dict(type='RepeatAugSampler', shuffle=True, num_repeats=2), dataset=dict( type='OCRDataset', data_root='mmocr_data/totaltext', ann_file='textspotting_train.json', filter_cfg=dict(filter_empty_gt=True, min_size=32), pipeline=[ dict( type='LoadImageFromFile', color_type='color_ignore_orientation'), dict( type='LoadOCRAnnotationsWithBezier', with_bbox=True, with_label=True, with_polygon=True, with_text=True), dict(type='FixInvalidPolygon'), dict(type='RemoveIgnored'), dict(type='RandomCrop', min_side_ratio=0.5), dict( type='RandomApply', transforms=[ dict( type='RandomRotate', max_angle=30, pad_with_fixed_color=True, use_canvas=True) ], prob=0.3), dict(type='FixInvalidPolygon'), dict( type='RandomChoiceResize', scales=[(640, 1600), (672, 1600), (704, 1600), (736, 1600), (768, 1600), (800, 1600), (832, 1600), (864, 1600), (896, 1600)], keep_ratio=True), dict( type='RandomApply', transforms=[ dict( type='TorchVisionWrapper', op='ColorJitter', brightness=0.5, contrast=0.5, saturation=0.5, hue=0.5) ], prob=0.5), dict( type='PackTextDetInputs', meta_keys=('img_path', 'ori_shape', 'img_shape', 'scale_factor')) ])) val_dataloader = dict( batch_size=1, num_workers=4, persistent_workers=True, pin_memory=True, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='OCRDataset', data_root='mmocr_data/totaltext', ann_file='textspotting_test.json', test_mode=True, pipeline=[ dict( type='LoadImageFromFile', color_type='color_ignore_orientation'), dict( type='RescaleToShortSide', short_side_lens=[1000], long_side_bound=1824), dict( type='LoadOCRAnnotationsWithBezier', with_bbox=True, with_label=True, with_polygon=True, with_text=True), dict( type='PackTextDetInputs', meta_keys=('img_path', 'ori_shape', 'img_shape', 'scale_factor')) ])) test_dataloader = dict( batch_size=1, num_workers=4, persistent_workers=True, pin_memory=True, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='OCRDataset', data_root='mmocr_data/totaltext', ann_file='textspotting_test.json', test_mode=True, pipeline=[ dict( type='LoadImageFromFile', color_type='color_ignore_orientation'), dict( type='RescaleToShortSide', short_side_lens=[1000], long_side_bound=1824), dict( type='LoadOCRAnnotationsWithBezier', with_bbox=True, with_label=True, with_polygon=True, with_text=True), dict( type='PackTextDetInputs', meta_keys=('img_path', 'ori_shape', 'img_shape', 'scale_factor')) ])) launcher = 'pytorch' work_dir = './work_dirs/spts_resnet50_350e_totaltext' 2023/03/03 10:30:45 - mmengine - WARNING - The "visualizer" registry in mmocr did not set import location. Fallback to call `mmocr.utils.register_all_modules` instead. 2023/03/03 10:30:45 - mmengine - WARNING - The "vis_backend" registry in mmocr did not set import location. Fallback to call `mmocr.utils.register_all_modules` instead. 2023/03/03 10:30:47 - mmengine - WARNING - The "model" registry in mmocr did not set import location. Fallback to call `mmocr.utils.register_all_modules` instead. 2023/03/03 10:30:47 - mmengine - WARNING - The "task util" registry in mmocr did not set import location. Fallback to call `mmocr.utils.register_all_modules` instead. 2023/03/03 10:30:47 - mmengine - WARNING - The "hook" registry in mmocr did not set import location. Fallback to call `mmocr.utils.register_all_modules` instead. 2023/03/03 10:30:47 - mmengine - INFO - Hooks will be executed in the following order: before_run: (VERY_HIGH ) RuntimeInfoHook (BELOW_NORMAL) LoggerHook -------------------- before_train: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (VERY_LOW ) CheckpointHook -------------------- before_train_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (NORMAL ) DistSamplerSeedHook -------------------- before_train_iter: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook -------------------- after_train_iter: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- after_train_epoch: (NORMAL ) IterTimerHook (NORMAL ) SyncBuffersHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- before_val_epoch: (NORMAL ) IterTimerHook -------------------- before_val_iter: (NORMAL ) IterTimerHook -------------------- after_val_iter: (NORMAL ) IterTimerHook (NORMAL ) VisualizationHook (BELOW_NORMAL) LoggerHook -------------------- after_val_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- before_test_epoch: (NORMAL ) IterTimerHook -------------------- before_test_iter: (NORMAL ) IterTimerHook -------------------- after_test_iter: (NORMAL ) IterTimerHook (NORMAL ) VisualizationHook (BELOW_NORMAL) LoggerHook -------------------- after_test_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook -------------------- after_run: (BELOW_NORMAL) LoggerHook -------------------- 2023/03/03 10:30:49 - mmengine - WARNING - The "loop" registry in mmocr did not set import location. Fallback to call `mmocr.utils.register_all_modules` instead. 2023/03/03 10:30:49 - mmengine - WARNING - The "dataset" registry in mmocr did not set import location. Fallback to call `mmocr.utils.register_all_modules` instead. 2023/03/03 10:30:49 - mmengine - WARNING - The "transform" registry in mmocr did not set import location. Fallback to call `mmocr.utils.register_all_modules` instead. 2023/03/03 10:30:49 - mmengine - WARNING - The "data sampler" registry in mmocr did not set import location. Fallback to call `mmocr.utils.register_all_modules` instead. 2023/03/03 10:30:49 - mmengine - WARNING - The "optimizer constructor" registry in mmocr did not set import location. Fallback to call `mmocr.utils.register_all_modules` instead. 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.conv1.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.conv1.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.conv1.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer1.0.conv1.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer1.0.conv1.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer1.0.conv1.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer1.0.conv2.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer1.0.conv2.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer1.0.conv2.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer1.0.conv3.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer1.0.conv3.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer1.0.conv3.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer1.0.downsample.0.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer1.0.downsample.0.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer1.0.downsample.0.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer1.1.conv1.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer1.1.conv1.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer1.1.conv1.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer1.1.conv2.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer1.1.conv2.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer1.1.conv2.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer1.1.conv3.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer1.1.conv3.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer1.1.conv3.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer1.2.conv1.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer1.2.conv1.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer1.2.conv1.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer1.2.conv2.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer1.2.conv2.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer1.2.conv2.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer1.2.conv3.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer1.2.conv3.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer1.2.conv3.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.0.conv1.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.0.conv1.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.0.conv1.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.0.conv2.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.0.conv2.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.0.conv2.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.0.conv3.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.0.conv3.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.0.conv3.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.0.downsample.0.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.0.downsample.0.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.0.downsample.0.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.1.conv1.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.1.conv1.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.1.conv1.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.1.conv2.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.1.conv2.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.1.conv2.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.1.conv3.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.1.conv3.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.1.conv3.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.2.conv1.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.2.conv1.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.2.conv1.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.2.conv2.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.2.conv2.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.2.conv2.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.2.conv3.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.2.conv3.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.2.conv3.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.3.conv1.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.3.conv1.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.3.conv1.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.3.conv2.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.3.conv2.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.3.conv2.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.3.conv3.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.3.conv3.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer2.3.conv3.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.0.conv1.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.0.conv1.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.0.conv1.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.0.conv2.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.0.conv2.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.0.conv2.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.0.conv3.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.0.conv3.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.0.conv3.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.0.downsample.0.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.0.downsample.0.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.0.downsample.0.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.1.conv1.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.1.conv1.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.1.conv1.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.1.conv2.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.1.conv2.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.1.conv2.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.1.conv3.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.1.conv3.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.1.conv3.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.2.conv1.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.2.conv1.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.2.conv1.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.2.conv2.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.2.conv2.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.2.conv2.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.2.conv3.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.2.conv3.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.2.conv3.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.3.conv1.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.3.conv1.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.3.conv1.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.3.conv2.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.3.conv2.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.3.conv2.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.3.conv3.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.3.conv3.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.3.conv3.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.4.conv1.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.4.conv1.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.4.conv1.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.4.conv2.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.4.conv2.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.4.conv2.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.4.conv3.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.4.conv3.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.4.conv3.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.5.conv1.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.5.conv1.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.5.conv1.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.5.conv2.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.5.conv2.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.5.conv2.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.5.conv3.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.5.conv3.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer3.5.conv3.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer4.0.conv1.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer4.0.conv1.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer4.0.conv1.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer4.0.conv2.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer4.0.conv2.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer4.0.conv2.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer4.0.conv3.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer4.0.conv3.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer4.0.conv3.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer4.0.downsample.0.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer4.0.downsample.0.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer4.0.downsample.0.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer4.1.conv1.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer4.1.conv1.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer4.1.conv1.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer4.1.conv2.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer4.1.conv2.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer4.1.conv2.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer4.1.conv3.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer4.1.conv3.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer4.1.conv3.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer4.2.conv1.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer4.2.conv1.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer4.2.conv1.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer4.2.conv2.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer4.2.conv2.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer4.2.conv2.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer4.2.conv3.weight:lr=1.0000000000000002e-06 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer4.2.conv3.weight:weight_decay=0.0001 2023/03/03 10:30:49 - mmengine - INFO - paramwise_options -- backbone.layer4.2.conv3.weight:lr_mult=0.1 2023/03/03 10:30:49 - mmengine - WARNING - The "optimizer" registry in mmocr did not set import location. Fallback to call `mmocr.utils.register_all_modules` instead. 2023/03/03 10:30:49 - mmengine - WARNING - The "optim wrapper" registry in mmocr did not set import location. Fallback to call `mmocr.utils.register_all_modules` instead. 2023/03/03 10:30:49 - mmengine - WARNING - The "metric" registry in mmocr did not set import location. Fallback to call `mmocr.utils.register_all_modules` instead. 2023/03/03 10:30:51 - mmengine - WARNING - The "weight initializer" registry in mmocr did not set import location. Fallback to call `mmocr.utils.register_all_modules` instead. 2023/03/03 10:30:51 - mmengine - INFO - load model from: torchvision://resnet50 2023/03/03 10:30:51 - mmengine - INFO - Loads checkpoint by torchvision backend from path: torchvision://resnet50 2023/03/03 10:30:51 - mmengine - WARNING - The model and loaded state dict do not match exactly unexpected key in source state_dict: fc.weight, fc.bias Name of parameter - Initialization information backbone.conv1.weight - torch.Size([64, 3, 7, 7]): PretrainedInit: load from torchvision://resnet50 backbone.bn1.weight - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.bn1.bias - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.conv1.weight - torch.Size([64, 64, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.bn1.weight - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.bn1.bias - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.bn2.weight - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.bn2.bias - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.bn3.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.bn3.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.downsample.0.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.downsample.1.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.downsample.1.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.conv1.weight - torch.Size([64, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.bn1.weight - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.bn1.bias - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.bn2.weight - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.bn2.bias - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.bn3.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.bn3.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.conv1.weight - torch.Size([64, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.bn1.weight - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.bn1.bias - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.bn2.weight - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.bn2.bias - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.bn3.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.bn3.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.conv1.weight - torch.Size([128, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.bn1.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.bn1.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.bn2.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.bn2.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.conv3.weight - torch.Size([512, 128, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.bn3.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.bn3.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.downsample.0.weight - torch.Size([512, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.downsample.1.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.downsample.1.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.conv1.weight - torch.Size([128, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.bn1.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.bn1.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.bn2.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.bn2.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.conv3.weight - torch.Size([512, 128, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.bn3.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.bn3.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.conv1.weight - torch.Size([128, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.bn1.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.bn1.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.bn2.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.bn2.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.conv3.weight - torch.Size([512, 128, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.bn3.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.bn3.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.conv1.weight - torch.Size([128, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.bn1.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.bn1.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.bn2.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.bn2.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.conv3.weight - torch.Size([512, 128, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.bn3.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.bn3.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.conv1.weight - torch.Size([256, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.bn1.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.bn1.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.bn2.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.bn2.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.bn3.weight - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.bn3.bias - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.downsample.0.weight - torch.Size([1024, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.downsample.1.weight - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.downsample.1.bias - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.bn1.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.bn1.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.bn2.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.bn2.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.bn3.weight - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.bn3.bias - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.bn1.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.bn1.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.bn2.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.bn2.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.bn3.weight - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.bn3.bias - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.bn1.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.bn1.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.bn2.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.bn2.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.bn3.weight - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.bn3.bias - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.bn1.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.bn1.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.bn2.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.bn2.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.bn3.weight - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.bn3.bias - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.bn1.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.bn1.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.bn2.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.bn2.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.bn3.weight - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.bn3.bias - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.conv1.weight - torch.Size([512, 1024, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.bn1.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.bn1.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.conv2.weight - torch.Size([512, 512, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.bn2.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.bn2.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.conv3.weight - torch.Size([2048, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.bn3.weight - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.bn3.bias - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.downsample.0.weight - torch.Size([2048, 1024, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.downsample.1.weight - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.downsample.1.bias - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.conv1.weight - torch.Size([512, 2048, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.bn1.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.bn1.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.conv2.weight - torch.Size([512, 512, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.bn2.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.bn2.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.conv3.weight - torch.Size([2048, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.bn3.weight - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.bn3.bias - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.conv1.weight - torch.Size([512, 2048, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.bn1.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.bn1.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.conv2.weight - torch.Size([512, 512, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.bn2.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.bn2.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.conv3.weight - torch.Size([2048, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.bn3.weight - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.bn3.bias - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 encoder.input_proj.weight - torch.Size([256, 2048, 1, 1]): The value is the same before and after calling `init_weights` of SPTS encoder.input_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.embedding.word_embeddings.weight - torch.Size([1100, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.embedding.position_embeddings.weight - torch.Size([1621, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.embedding.LayerNorm.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.embedding.LayerNorm.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.vocab_embed.layer-0.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.vocab_embed.layer-0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.vocab_embed.layer-1.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.vocab_embed.layer-1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.vocab_embed.layer-2.weight - torch.Size([1100, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.vocab_embed.layer-2.bias - torch.Size([1100]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.0.self_attn.in_proj_weight - torch.Size([768, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.0.self_attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.0.self_attn.out_proj.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.0.self_attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.0.linear1.weight - torch.Size([1024, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.0.linear1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.0.linear2.weight - torch.Size([256, 1024]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.0.linear2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.0.norm1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.0.norm1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.0.norm2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.0.norm2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.1.self_attn.in_proj_weight - torch.Size([768, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.1.self_attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.1.self_attn.out_proj.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.1.self_attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.1.linear1.weight - torch.Size([1024, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.1.linear1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.1.linear2.weight - torch.Size([256, 1024]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.1.linear2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.1.norm1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.1.norm1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.1.norm2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.1.norm2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.2.self_attn.in_proj_weight - torch.Size([768, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.2.self_attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.2.self_attn.out_proj.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.2.self_attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.2.linear1.weight - torch.Size([1024, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.2.linear1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.2.linear2.weight - torch.Size([256, 1024]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.2.linear2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.2.norm1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.2.norm1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.2.norm2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.2.norm2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.3.self_attn.in_proj_weight - torch.Size([768, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.3.self_attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.3.self_attn.out_proj.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.3.self_attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.3.linear1.weight - torch.Size([1024, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.3.linear1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.3.linear2.weight - torch.Size([256, 1024]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.3.linear2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.3.norm1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.3.norm1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.3.norm2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.3.norm2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.4.self_attn.in_proj_weight - torch.Size([768, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.4.self_attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.4.self_attn.out_proj.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.4.self_attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.4.linear1.weight - torch.Size([1024, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.4.linear1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.4.linear2.weight - torch.Size([256, 1024]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.4.linear2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.4.norm1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.4.norm1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.4.norm2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.4.norm2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.5.self_attn.in_proj_weight - torch.Size([768, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.5.self_attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.5.self_attn.out_proj.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.5.self_attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.5.linear1.weight - torch.Size([1024, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.5.linear1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.5.linear2.weight - torch.Size([256, 1024]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.5.linear2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.5.norm1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.5.norm1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.5.norm2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.layers.5.norm2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.norm.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.encoder.norm.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.0.self_attn.in_proj_weight - torch.Size([768, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.0.self_attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.0.self_attn.out_proj.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.0.self_attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.0.multihead_attn.in_proj_weight - torch.Size([768, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.0.multihead_attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.0.multihead_attn.out_proj.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.0.multihead_attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.0.linear1.weight - torch.Size([1024, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.0.linear1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.0.linear2.weight - torch.Size([256, 1024]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.0.linear2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.0.norm1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.0.norm1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.0.norm2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.0.norm2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.0.norm3.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.0.norm3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.1.self_attn.in_proj_weight - torch.Size([768, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.1.self_attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.1.self_attn.out_proj.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.1.self_attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.1.multihead_attn.in_proj_weight - torch.Size([768, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.1.multihead_attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.1.multihead_attn.out_proj.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.1.multihead_attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.1.linear1.weight - torch.Size([1024, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.1.linear1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.1.linear2.weight - torch.Size([256, 1024]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.1.linear2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.1.norm1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.1.norm1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.1.norm2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.1.norm2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.1.norm3.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.1.norm3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.2.self_attn.in_proj_weight - torch.Size([768, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.2.self_attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.2.self_attn.out_proj.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.2.self_attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.2.multihead_attn.in_proj_weight - torch.Size([768, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.2.multihead_attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.2.multihead_attn.out_proj.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.2.multihead_attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.2.linear1.weight - torch.Size([1024, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.2.linear1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.2.linear2.weight - torch.Size([256, 1024]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.2.linear2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.2.norm1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.2.norm1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.2.norm2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.2.norm2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.2.norm3.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.2.norm3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.3.self_attn.in_proj_weight - torch.Size([768, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.3.self_attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.3.self_attn.out_proj.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.3.self_attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.3.multihead_attn.in_proj_weight - torch.Size([768, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.3.multihead_attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.3.multihead_attn.out_proj.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.3.multihead_attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.3.linear1.weight - torch.Size([1024, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.3.linear1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.3.linear2.weight - torch.Size([256, 1024]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.3.linear2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.3.norm1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.3.norm1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.3.norm2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.3.norm2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.3.norm3.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.3.norm3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.4.self_attn.in_proj_weight - torch.Size([768, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.4.self_attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.4.self_attn.out_proj.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.4.self_attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.4.multihead_attn.in_proj_weight - torch.Size([768, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.4.multihead_attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.4.multihead_attn.out_proj.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.4.multihead_attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.4.linear1.weight - torch.Size([1024, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.4.linear1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.4.linear2.weight - torch.Size([256, 1024]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.4.linear2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.4.norm1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.4.norm1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.4.norm2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.4.norm2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.4.norm3.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.4.norm3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.5.self_attn.in_proj_weight - torch.Size([768, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.5.self_attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.5.self_attn.out_proj.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.5.self_attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.5.multihead_attn.in_proj_weight - torch.Size([768, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.5.multihead_attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.5.multihead_attn.out_proj.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.5.multihead_attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.5.linear1.weight - torch.Size([1024, 256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.5.linear1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.5.linear2.weight - torch.Size([256, 1024]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.5.linear2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.5.norm1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.5.norm1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.5.norm2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.5.norm2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.5.norm3.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.layers.5.norm3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.norm.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS decoder.decoder.norm.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SPTS 2023/03/03 10:30:51 - mmengine - INFO - Load checkpoint from work_dirs/spts_resnet50_150e_pretrain-spts-2/epoch_150.pth 2023/03/03 10:30:51 - mmengine - WARNING - Gradient accumulative may slightly decrease performance because the model has BatchNorm layers. 2023/03/03 10:30:51 - mmengine - INFO - Checkpoints will be saved to mmocr/projects/SPTS/work_dirs/spts_resnet50_350e_totaltext. 2023/03/03 10:31:04 - mmengine - INFO - Epoch(train) [1][10/79] lr: 1.0000e-06 eta: 5:22:22 time: 1.2250 data_time: 0.2060 memory: 39124 loss: 0.1994 loss_ce: 0.1994 2023/03/03 10:31:09 - mmengine - INFO - Epoch(train) [1][20/79] lr: 1.0000e-06 eta: 3:53:58 time: 0.5543 data_time: 0.0017 memory: 28461 loss: 0.1910 loss_ce: 0.1910 2023/03/03 10:31:14 - mmengine - INFO - Epoch(train) [1][30/79] lr: 1.0000e-06 eta: 3:17:49 time: 0.4788 data_time: 0.0017 memory: 34239 loss: 0.2028 loss_ce: 0.2028 2023/03/03 10:31:18 - mmengine - INFO - Epoch(train) [1][40/79] lr: 1.0000e-06 eta: 2:56:39 time: 0.4322 data_time: 0.0017 memory: 40233 loss: 0.1589 loss_ce: 0.1589 2023/03/03 10:31:23 - mmengine - INFO - Epoch(train) [1][50/79] lr: 1.0000e-06 eta: 2:48:28 time: 0.5188 data_time: 0.0016 memory: 35028 loss: 0.1859 loss_ce: 0.1859 2023/03/03 10:31:28 - mmengine - INFO - Epoch(train) [1][60/79] lr: 1.0000e-06 eta: 2:42:20 time: 0.5038 data_time: 0.0017 memory: 39610 loss: 0.1639 loss_ce: 0.1639 2023/03/03 10:31:34 - mmengine - INFO - Epoch(train) [1][70/79] lr: 1.0000e-06 eta: 2:38:29 time: 0.5190 data_time: 0.0014 memory: 41404 loss: 0.1429 loss_ce: 0.1429 2023/03/03 10:31:38 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 10:31:43 - mmengine - INFO - Epoch(train) [2][10/79] lr: 1.0000e-06 eta: 2:31:38 time: 0.5169 data_time: 0.0644 memory: 38336 loss: 0.1725 loss_ce: 0.1725 2023/03/03 10:31:47 - mmengine - INFO - Epoch(train) [2][20/79] lr: 1.0000e-06 eta: 2:28:30 time: 0.4641 data_time: 0.0015 memory: 37886 loss: 0.1572 loss_ce: 0.1572 2023/03/03 10:31:52 - mmengine - INFO - Epoch(train) [2][30/79] lr: 1.0000e-06 eta: 2:25:13 time: 0.4348 data_time: 0.0016 memory: 37933 loss: 0.1748 loss_ce: 0.1748 2023/03/03 10:31:56 - mmengine - INFO - Epoch(train) [2][40/79] lr: 1.0000e-06 eta: 2:22:09 time: 0.4198 data_time: 0.0015 memory: 26438 loss: 0.1546 loss_ce: 0.1546 2023/03/03 10:32:01 - mmengine - INFO - Epoch(train) [2][50/79] lr: 1.0000e-06 eta: 2:20:09 time: 0.4492 data_time: 0.0015 memory: 28605 loss: 0.1421 loss_ce: 0.1421 2023/03/03 10:32:06 - mmengine - INFO - Epoch(train) [2][60/79] lr: 1.0000e-06 eta: 2:19:28 time: 0.5056 data_time: 0.0014 memory: 39954 loss: 0.1675 loss_ce: 0.1675 2023/03/03 10:32:10 - mmengine - INFO - Epoch(train) [2][70/79] lr: 1.0000e-06 eta: 2:17:36 time: 0.4321 data_time: 0.0012 memory: 32896 loss: 0.1416 loss_ce: 0.1416 2023/03/03 10:32:14 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 10:32:20 - mmengine - INFO - Epoch(train) [3][10/79] lr: 1.0000e-06 eta: 2:17:32 time: 0.5764 data_time: 0.0493 memory: 42016 loss: 0.1585 loss_ce: 0.1585 2023/03/03 10:32:25 - mmengine - INFO - Epoch(train) [3][20/79] lr: 1.0000e-06 eta: 2:16:54 time: 0.4906 data_time: 0.0014 memory: 38851 loss: 0.1495 loss_ce: 0.1495 2023/03/03 10:32:30 - mmengine - INFO - Epoch(train) [3][30/79] lr: 1.0000e-06 eta: 2:17:04 time: 0.5439 data_time: 0.0013 memory: 45681 loss: 0.1507 loss_ce: 0.1507 2023/03/03 10:32:35 - mmengine - INFO - Epoch(train) [3][40/79] lr: 1.0000e-06 eta: 2:15:59 time: 0.4519 data_time: 0.0013 memory: 36577 loss: 0.1627 loss_ce: 0.1627 2023/03/03 10:32:39 - mmengine - INFO - Epoch(train) [3][50/79] lr: 1.0000e-06 eta: 2:15:01 time: 0.4514 data_time: 0.0014 memory: 26158 loss: 0.1611 loss_ce: 0.1611 2023/03/03 10:32:44 - mmengine - INFO - Epoch(train) [3][60/79] lr: 1.0000e-06 eta: 2:14:34 time: 0.4892 data_time: 0.0014 memory: 31251 loss: 0.1459 loss_ce: 0.1459 2023/03/03 10:32:49 - mmengine - INFO - Epoch(train) [3][70/79] lr: 1.0000e-06 eta: 2:14:07 time: 0.4861 data_time: 0.0013 memory: 39954 loss: 0.1338 loss_ce: 0.1338 2023/03/03 10:32:53 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 10:32:58 - mmengine - INFO - Epoch(train) [4][10/79] lr: 1.0000e-06 eta: 2:12:57 time: 0.5069 data_time: 0.0615 memory: 39371 loss: 0.1241 loss_ce: 0.1241 2023/03/03 10:33:03 - mmengine - INFO - Epoch(train) [4][20/79] lr: 1.0000e-06 eta: 2:12:21 time: 0.4614 data_time: 0.0013 memory: 36093 loss: 0.1381 loss_ce: 0.1381 2023/03/03 10:33:07 - mmengine - INFO - Epoch(train) [4][30/79] lr: 1.0000e-06 eta: 2:11:31 time: 0.4347 data_time: 0.0014 memory: 38851 loss: 0.1484 loss_ce: 0.1484 2023/03/03 10:33:12 - mmengine - INFO - Epoch(train) [4][40/79] lr: 1.0000e-06 eta: 2:11:06 time: 0.4714 data_time: 0.0014 memory: 41694 loss: 0.1527 loss_ce: 0.1527 2023/03/03 10:33:17 - mmengine - INFO - Epoch(train) [4][50/79] lr: 1.0000e-06 eta: 2:10:51 time: 0.4896 data_time: 0.0014 memory: 33423 loss: 0.1254 loss_ce: 0.1254 2023/03/03 10:33:22 - mmengine - INFO - Epoch(train) [4][60/79] lr: 1.0000e-06 eta: 2:10:41 time: 0.4957 data_time: 0.0014 memory: 34573 loss: 0.1512 loss_ce: 0.1512 2023/03/03 10:33:26 - mmengine - INFO - Epoch(train) [4][70/79] lr: 1.0000e-06 eta: 2:10:03 time: 0.4413 data_time: 0.0013 memory: 37933 loss: 0.1588 loss_ce: 0.1588 2023/03/03 10:33:31 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 10:33:36 - mmengine - INFO - Epoch(train) [5][10/79] lr: 1.0000e-06 eta: 2:10:39 time: 0.5524 data_time: 0.0752 memory: 42756 loss: 0.1458 loss_ce: 0.1458 2023/03/03 10:33:41 - mmengine - INFO - Epoch(train) [5][20/79] lr: 1.0000e-06 eta: 2:10:31 time: 0.4984 data_time: 0.0013 memory: 32885 loss: 0.1340 loss_ce: 0.1340 2023/03/03 10:33:47 - mmengine - INFO - Epoch(train) [5][30/79] lr: 1.0000e-06 eta: 2:10:43 time: 0.5455 data_time: 0.0013 memory: 50587 loss: 0.1360 loss_ce: 0.1360 2023/03/03 10:33:51 - mmengine - INFO - Epoch(train) [5][40/79] lr: 1.0000e-06 eta: 2:10:13 time: 0.4514 data_time: 0.0013 memory: 35449 loss: 0.1321 loss_ce: 0.1321 2023/03/03 10:33:56 - mmengine - INFO - Epoch(train) [5][50/79] lr: 1.0000e-06 eta: 2:10:08 time: 0.5046 data_time: 0.0017 memory: 39955 loss: 0.1405 loss_ce: 0.1405 2023/03/03 10:34:01 - mmengine - INFO - Epoch(train) [5][60/79] lr: 1.0000e-06 eta: 2:09:57 time: 0.4927 data_time: 0.0014 memory: 43937 loss: 0.1442 loss_ce: 0.1442 2023/03/03 10:34:06 - mmengine - INFO - Epoch(train) [5][70/79] lr: 1.0000e-06 eta: 2:09:35 time: 0.4618 data_time: 0.0013 memory: 41714 loss: 0.1372 loss_ce: 0.1372 2023/03/03 10:34:10 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 10:34:16 - mmengine - INFO - Epoch(train) [6][10/79] lr: 1.0000e-06 eta: 2:09:29 time: 0.5483 data_time: 0.0503 memory: 40733 loss: 0.1458 loss_ce: 0.1458 2023/03/03 10:34:20 - mmengine - INFO - Epoch(train) [6][20/79] lr: 1.0000e-06 eta: 2:08:57 time: 0.4324 data_time: 0.0014 memory: 26704 loss: 0.1284 loss_ce: 0.1284 2023/03/03 10:34:25 - mmengine - INFO - Epoch(train) [6][30/79] lr: 1.0000e-06 eta: 2:08:50 time: 0.4956 data_time: 0.0014 memory: 34559 loss: 0.1360 loss_ce: 0.1360 2023/03/03 10:34:30 - mmengine - INFO - Epoch(train) [6][40/79] lr: 1.0000e-06 eta: 2:08:28 time: 0.4549 data_time: 0.0014 memory: 29092 loss: 0.1689 loss_ce: 0.1689 2023/03/03 10:34:34 - mmengine - INFO - Epoch(train) [6][50/79] lr: 1.0000e-06 eta: 2:08:12 time: 0.4715 data_time: 0.0014 memory: 40235 loss: 0.1347 loss_ce: 0.1347 2023/03/03 10:34:38 - mmengine - INFO - Epoch(train) [6][60/79] lr: 1.0000e-06 eta: 2:07:35 time: 0.4066 data_time: 0.0014 memory: 34767 loss: 0.1338 loss_ce: 0.1338 2023/03/03 10:34:43 - mmengine - INFO - Epoch(train) [6][70/79] lr: 1.0000e-06 eta: 2:07:31 time: 0.4994 data_time: 0.0015 memory: 39915 loss: 0.1597 loss_ce: 0.1597 2023/03/03 10:34:48 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 10:34:53 - mmengine - INFO - Epoch(train) [7][10/79] lr: 1.0000e-06 eta: 2:07:24 time: 0.5278 data_time: 0.0487 memory: 37933 loss: 0.1461 loss_ce: 0.1461 2023/03/03 10:34:57 - mmengine - INFO - Epoch(train) [7][20/79] lr: 1.0000e-06 eta: 2:07:06 time: 0.4569 data_time: 0.0014 memory: 42095 loss: 0.1395 loss_ce: 0.1395 2023/03/03 10:35:03 - mmengine - INFO - Epoch(train) [7][30/79] lr: 1.0000e-06 eta: 2:07:14 time: 0.5417 data_time: 0.0014 memory: 48557 loss: 0.1327 loss_ce: 0.1327 2023/03/03 10:35:08 - mmengine - INFO - Epoch(train) [7][40/79] lr: 1.0000e-06 eta: 2:07:07 time: 0.4936 data_time: 0.0014 memory: 42288 loss: 0.1530 loss_ce: 0.1530 2023/03/03 10:35:12 - mmengine - INFO - Epoch(train) [7][50/79] lr: 1.0000e-06 eta: 2:06:52 time: 0.4643 data_time: 0.0014 memory: 30842 loss: 0.1330 loss_ce: 0.1330 2023/03/03 10:35:17 - mmengine - INFO - Epoch(train) [7][60/79] lr: 1.0000e-06 eta: 2:06:29 time: 0.4329 data_time: 0.0015 memory: 39034 loss: 0.1532 loss_ce: 0.1532 2023/03/03 10:35:22 - mmengine - INFO - Epoch(train) [7][70/79] lr: 1.0000e-06 eta: 2:06:21 time: 0.4865 data_time: 0.0013 memory: 36803 loss: 0.1393 loss_ce: 0.1393 2023/03/03 10:35:25 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 10:35:30 - mmengine - INFO - Epoch(train) [8][10/79] lr: 1.0000e-06 eta: 2:05:42 time: 0.4625 data_time: 0.0463 memory: 40235 loss: 0.1348 loss_ce: 0.1348 2023/03/03 10:35:35 - mmengine - INFO - Epoch(train) [8][20/79] lr: 1.0000e-06 eta: 2:05:50 time: 0.5412 data_time: 0.0014 memory: 41859 loss: 0.1529 loss_ce: 0.1529 2023/03/03 10:35:40 - mmengine - INFO - Epoch(train) [8][30/79] lr: 1.0000e-06 eta: 2:05:39 time: 0.4740 data_time: 0.0014 memory: 39700 loss: 0.1514 loss_ce: 0.1514 2023/03/03 10:35:45 - mmengine - INFO - Epoch(train) [8][40/79] lr: 1.0000e-06 eta: 2:05:32 time: 0.4874 data_time: 0.0014 memory: 35851 loss: 0.1419 loss_ce: 0.1419 2023/03/03 10:35:50 - mmengine - INFO - Epoch(train) [8][50/79] lr: 1.0000e-06 eta: 2:05:31 time: 0.5103 data_time: 0.0017 memory: 38332 loss: 0.1450 loss_ce: 0.1450 2023/03/03 10:35:55 - mmengine - INFO - Epoch(train) [8][60/79] lr: 1.0000e-06 eta: 2:05:16 time: 0.4581 data_time: 0.0014 memory: 45645 loss: 0.1423 loss_ce: 0.1423 2023/03/03 10:35:59 - mmengine - INFO - Epoch(train) [8][70/79] lr: 1.0000e-06 eta: 2:04:47 time: 0.3929 data_time: 0.0013 memory: 41714 loss: 0.1548 loss_ce: 0.1548 2023/03/03 10:36:02 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 10:36:07 - mmengine - INFO - Epoch(train) [9][10/79] lr: 1.0000e-06 eta: 2:04:22 time: 0.5195 data_time: 0.0418 memory: 37933 loss: 0.1497 loss_ce: 0.1497 2023/03/03 10:36:12 - mmengine - INFO - Epoch(train) [9][20/79] lr: 1.0000e-06 eta: 2:04:14 time: 0.4783 data_time: 0.0014 memory: 31087 loss: 0.1484 loss_ce: 0.1484 2023/03/03 10:36:17 - mmengine - INFO - Epoch(train) [9][30/79] lr: 1.0000e-06 eta: 2:04:05 time: 0.4737 data_time: 0.0014 memory: 39392 loss: 0.1252 loss_ce: 0.1252 2023/03/03 10:36:22 - mmengine - INFO - Epoch(train) [9][40/79] lr: 1.0000e-06 eta: 2:03:52 time: 0.4561 data_time: 0.0014 memory: 37125 loss: 0.1272 loss_ce: 0.1272 2023/03/03 10:36:26 - mmengine - INFO - Epoch(train) [9][50/79] lr: 1.0000e-06 eta: 2:03:47 time: 0.4891 data_time: 0.0014 memory: 30634 loss: 0.1463 loss_ce: 0.1463 2023/03/03 10:36:31 - mmengine - INFO - Epoch(train) [9][60/79] lr: 1.0000e-06 eta: 2:03:36 time: 0.4642 data_time: 0.0013 memory: 29567 loss: 0.1208 loss_ce: 0.1208 2023/03/03 10:36:36 - mmengine - INFO - Epoch(train) [9][70/79] lr: 1.0000e-06 eta: 2:03:29 time: 0.4835 data_time: 0.0013 memory: 39955 loss: 0.1450 loss_ce: 0.1450 2023/03/03 10:36:40 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 10:36:45 - mmengine - INFO - Epoch(train) [10][10/79] lr: 1.0000e-06 eta: 2:03:15 time: 0.4984 data_time: 0.0375 memory: 38845 loss: 0.1638 loss_ce: 0.1638 2023/03/03 10:36:50 - mmengine - INFO - Epoch(train) [10][20/79] lr: 1.0000e-06 eta: 2:03:04 time: 0.4576 data_time: 0.0013 memory: 37933 loss: 0.1338 loss_ce: 0.1338 2023/03/03 10:36:54 - mmengine - INFO - Epoch(train) [10][30/79] lr: 1.0000e-06 eta: 2:02:52 time: 0.4579 data_time: 0.0014 memory: 35471 loss: 0.1432 loss_ce: 0.1432 2023/03/03 10:36:59 - mmengine - INFO - Epoch(train) [10][40/79] lr: 1.0000e-06 eta: 2:02:47 time: 0.4900 data_time: 0.0014 memory: 36038 loss: 0.1270 loss_ce: 0.1270 2023/03/03 10:37:04 - mmengine - INFO - Epoch(train) [10][50/79] lr: 1.0000e-06 eta: 2:02:49 time: 0.5234 data_time: 0.0013 memory: 40544 loss: 0.1332 loss_ce: 0.1332 2023/03/03 10:37:08 - mmengine - INFO - Epoch(train) [10][60/79] lr: 1.0000e-06 eta: 2:02:29 time: 0.4142 data_time: 0.0014 memory: 32403 loss: 0.1281 loss_ce: 0.1281 2023/03/03 10:37:13 - mmengine - INFO - Epoch(train) [10][70/79] lr: 1.0000e-06 eta: 2:02:13 time: 0.4280 data_time: 0.0013 memory: 39444 loss: 0.1324 loss_ce: 0.1324 2023/03/03 10:37:17 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 10:37:30 - mmengine - INFO - Epoch(val) [10][10/75] eta: 0:01:24 time: 1.3070 data_time: 0.0246 memory: 33326 2023/03/03 10:38:13 - mmengine - INFO - Epoch(val) [10][20/75] eta: 0:02:34 time: 4.3243 data_time: 0.0004 memory: 1077 2023/03/03 10:38:34 - mmengine - INFO - Epoch(val) [10][30/75] eta: 0:01:55 time: 2.0701 data_time: 0.0003 memory: 1020 2023/03/03 10:39:09 - mmengine - INFO - Epoch(val) [10][40/75] eta: 0:01:38 time: 3.5377 data_time: 0.0003 memory: 1019 2023/03/03 10:39:24 - mmengine - INFO - Epoch(val) [10][50/75] eta: 0:01:03 time: 1.5152 data_time: 0.0003 memory: 1077 2023/03/03 10:40:34 - mmengine - INFO - Epoch(val) [10][60/75] eta: 0:00:49 time: 6.9609 data_time: 0.0003 memory: 1045 2023/03/03 10:41:32 - mmengine - INFO - Epoch(val) [10][70/75] eta: 0:00:18 time: 5.7752 data_time: 0.0004 memory: 1077 2023/03/03 10:41:45 - mmengine - INFO - text score threshold: 0.80, recall: 0.6751, precision: 0.7446, hmean: 0.7081 2023/03/03 10:41:45 - mmengine - INFO - text score threshold: 0.81, recall: 0.6745, precision: 0.7540, hmean: 0.7121 2023/03/03 10:41:45 - mmengine - INFO - text score threshold: 0.82, recall: 0.6718, precision: 0.7621, hmean: 0.7141 2023/03/03 10:41:45 - mmengine - INFO - text score threshold: 0.83, recall: 0.6718, precision: 0.7655, hmean: 0.7156 2023/03/03 10:41:45 - mmengine - INFO - text score threshold: 0.84, recall: 0.6690, precision: 0.7715, hmean: 0.7166 2023/03/03 10:41:45 - mmengine - INFO - text score threshold: 0.85, recall: 0.6679, precision: 0.7781, hmean: 0.7188 2023/03/03 10:41:45 - mmengine - INFO - text score threshold: 0.86, recall: 0.6647, precision: 0.7843, hmean: 0.7195 2023/03/03 10:41:45 - mmengine - INFO - text score threshold: 0.87, recall: 0.6647, precision: 0.7951, hmean: 0.7241 2023/03/03 10:41:45 - mmengine - INFO - text score threshold: 0.88, recall: 0.6636, precision: 0.8023, hmean: 0.7263 2023/03/03 10:41:45 - mmengine - INFO - text score threshold: 0.89, recall: 0.6619, precision: 0.8110, hmean: 0.7289 2023/03/03 10:41:45 - mmengine - INFO - text score threshold: 0.90, recall: 0.6570, precision: 0.8176, hmean: 0.7285 2023/03/03 10:41:45 - mmengine - INFO - text score threshold: 0.91, recall: 0.6531, precision: 0.8252, hmean: 0.7292 2023/03/03 10:41:45 - mmengine - INFO - text score threshold: 0.92, recall: 0.6482, precision: 0.8317, hmean: 0.7286 2023/03/03 10:41:45 - mmengine - INFO - text score threshold: 0.93, recall: 0.6383, precision: 0.8379, hmean: 0.7246 2023/03/03 10:41:45 - mmengine - INFO - text score threshold: 0.94, recall: 0.6284, precision: 0.8475, hmean: 0.7217 2023/03/03 10:41:45 - mmengine - INFO - text score threshold: 0.95, recall: 0.6164, precision: 0.8527, hmean: 0.7155 2023/03/03 10:41:45 - mmengine - INFO - text score threshold: 0.96, recall: 0.6032, precision: 0.8599, hmean: 0.7090 2023/03/03 10:41:45 - mmengine - INFO - text score threshold: 0.97, recall: 0.5884, precision: 0.8730, hmean: 0.7030 2023/03/03 10:41:45 - mmengine - INFO - text score threshold: 0.98, recall: 0.5620, precision: 0.8850, hmean: 0.6875 2023/03/03 10:41:45 - mmengine - INFO - text score threshold: 0.99, recall: 0.5181, precision: 0.9008, hmean: 0.6578 2023/03/03 10:41:55 - mmengine - INFO - text score threshold: 0.80, recall: 0.7623, precision: 0.8730, hmean: 0.8139 2023/03/03 10:41:55 - mmengine - INFO - text score threshold: 0.81, recall: 0.7591, precision: 0.8787, hmean: 0.8145 2023/03/03 10:41:55 - mmengine - INFO - text score threshold: 0.82, recall: 0.7552, precision: 0.8866, hmean: 0.8156 2023/03/03 10:41:55 - mmengine - INFO - text score threshold: 0.83, recall: 0.7547, precision: 0.8888, hmean: 0.8163 2023/03/03 10:41:55 - mmengine - INFO - text score threshold: 0.84, recall: 0.7492, precision: 0.8927, hmean: 0.8147 2023/03/03 10:41:55 - mmengine - INFO - text score threshold: 0.85, recall: 0.7470, precision: 0.8978, hmean: 0.8155 2023/03/03 10:41:55 - mmengine - INFO - text score threshold: 0.86, recall: 0.7404, precision: 0.8999, hmean: 0.8124 2023/03/03 10:41:55 - mmengine - INFO - text score threshold: 0.87, recall: 0.7344, precision: 0.9034, hmean: 0.8102 2023/03/03 10:41:55 - mmengine - INFO - text score threshold: 0.88, recall: 0.7305, precision: 0.9079, hmean: 0.8096 2023/03/03 10:41:55 - mmengine - INFO - text score threshold: 0.89, recall: 0.7256, precision: 0.9130, hmean: 0.8086 2023/03/03 10:41:55 - mmengine - INFO - text score threshold: 0.90, recall: 0.7168, precision: 0.9152, hmean: 0.8039 2023/03/03 10:41:55 - mmengine - INFO - text score threshold: 0.91, recall: 0.7086, precision: 0.9169, hmean: 0.7994 2023/03/03 10:41:55 - mmengine - INFO - text score threshold: 0.92, recall: 0.7009, precision: 0.9207, hmean: 0.7959 2023/03/03 10:41:55 - mmengine - INFO - text score threshold: 0.93, recall: 0.6866, precision: 0.9226, hmean: 0.7873 2023/03/03 10:41:55 - mmengine - INFO - text score threshold: 0.94, recall: 0.6707, precision: 0.9258, hmean: 0.7778 2023/03/03 10:41:55 - mmengine - INFO - text score threshold: 0.95, recall: 0.6548, precision: 0.9277, hmean: 0.7677 2023/03/03 10:41:55 - mmengine - INFO - text score threshold: 0.96, recall: 0.6356, precision: 0.9286, hmean: 0.7546 2023/03/03 10:41:55 - mmengine - INFO - text score threshold: 0.97, recall: 0.6147, precision: 0.9333, hmean: 0.7412 2023/03/03 10:41:55 - mmengine - INFO - text score threshold: 0.98, recall: 0.5823, precision: 0.9389, hmean: 0.7188 2023/03/03 10:41:55 - mmengine - INFO - text score threshold: 0.99, recall: 0.5324, precision: 0.9491, hmean: 0.6821 2023/03/03 10:41:55 - mmengine - INFO - Epoch(val) [10][75/75] none/precision: 0.8252 none/recall: 0.6531 none/hmean: 0.7292 full/precision: 0.8888 full/recall: 0.7547 full/hmean: 0.8163 2023/03/03 10:41:57 - mmengine - INFO - The best checkpoint with 0.7292 none/hmean at 10 epoch is saved to best_none/hmean_epoch_10.pth. 2023/03/03 10:42:02 - mmengine - INFO - Epoch(train) [11][10/79] lr: 1.0000e-06 eta: 2:02:02 time: 0.5002 data_time: 0.0433 memory: 26704 loss: 0.1374 loss_ce: 0.1374 2023/03/03 10:42:06 - mmengine - INFO - Epoch(train) [11][20/79] lr: 1.0000e-06 eta: 2:01:56 time: 0.4803 data_time: 0.0014 memory: 37933 loss: 0.1478 loss_ce: 0.1478 2023/03/03 10:42:11 - mmengine - INFO - Epoch(train) [11][30/79] lr: 1.0000e-06 eta: 2:01:50 time: 0.4819 data_time: 0.0014 memory: 38399 loss: 0.1349 loss_ce: 0.1349 2023/03/03 10:42:16 - mmengine - INFO - Epoch(train) [11][40/79] lr: 1.0000e-06 eta: 2:01:50 time: 0.5169 data_time: 0.0014 memory: 36494 loss: 0.1163 loss_ce: 0.1163 2023/03/03 10:42:21 - mmengine - INFO - Epoch(train) [11][50/79] lr: 1.0000e-06 eta: 2:01:41 time: 0.4662 data_time: 0.0015 memory: 41411 loss: 0.1305 loss_ce: 0.1305 2023/03/03 10:42:25 - mmengine - INFO - Epoch(train) [11][60/79] lr: 1.0000e-06 eta: 2:01:27 time: 0.4347 data_time: 0.0015 memory: 34693 loss: 0.1337 loss_ce: 0.1337 2023/03/03 10:42:30 - mmengine - INFO - Epoch(train) [11][70/79] lr: 1.0000e-06 eta: 2:01:14 time: 0.4434 data_time: 0.0013 memory: 38080 loss: 0.1354 loss_ce: 0.1354 2023/03/03 10:42:34 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 10:42:39 - mmengine - INFO - Epoch(train) [12][10/79] lr: 1.0000e-06 eta: 2:00:59 time: 0.4654 data_time: 0.0560 memory: 34398 loss: 0.1241 loss_ce: 0.1241 2023/03/03 10:42:44 - mmengine - INFO - Epoch(train) [12][20/79] lr: 1.0000e-06 eta: 2:00:54 time: 0.4890 data_time: 0.0014 memory: 39389 loss: 0.1445 loss_ce: 0.1445 2023/03/03 10:42:48 - mmengine - INFO - Epoch(train) [12][30/79] lr: 1.0000e-06 eta: 2:00:46 time: 0.4642 data_time: 0.0014 memory: 27281 loss: 0.1621 loss_ce: 0.1621 2023/03/03 10:42:53 - mmengine - INFO - Epoch(train) [12][40/79] lr: 1.0000e-06 eta: 2:00:38 time: 0.4701 data_time: 0.0013 memory: 38080 loss: 0.1237 loss_ce: 0.1237 2023/03/03 10:42:58 - mmengine - INFO - Epoch(train) [12][50/79] lr: 1.0000e-06 eta: 2:00:29 time: 0.4596 data_time: 0.0014 memory: 33487 loss: 0.1582 loss_ce: 0.1582 2023/03/03 10:43:03 - mmengine - INFO - Epoch(train) [12][60/79] lr: 1.0000e-06 eta: 2:00:26 time: 0.4947 data_time: 0.0014 memory: 28709 loss: 0.1332 loss_ce: 0.1332 2023/03/03 10:43:08 - mmengine - INFO - Epoch(train) [12][70/79] lr: 1.0000e-06 eta: 2:00:26 time: 0.5192 data_time: 0.0013 memory: 31911 loss: 0.1492 loss_ce: 0.1492 2023/03/03 10:43:12 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 10:43:18 - mmengine - INFO - Epoch(train) [13][10/79] lr: 1.0000e-06 eta: 2:00:27 time: 0.5460 data_time: 0.1011 memory: 43392 loss: 0.1272 loss_ce: 0.1272 2023/03/03 10:43:23 - mmengine - INFO - Epoch(train) [13][20/79] lr: 1.0000e-06 eta: 2:00:25 time: 0.5010 data_time: 0.0014 memory: 40053 loss: 0.1402 loss_ce: 0.1402 2023/03/03 10:43:27 - mmengine - INFO - Epoch(train) [13][30/79] lr: 1.0000e-06 eta: 2:00:14 time: 0.4525 data_time: 0.0014 memory: 31363 loss: 0.1365 loss_ce: 0.1365 2023/03/03 10:43:32 - mmengine - INFO - Epoch(train) [13][40/79] lr: 1.0000e-06 eta: 2:00:14 time: 0.5152 data_time: 0.0014 memory: 36094 loss: 0.1424 loss_ce: 0.1424 2023/03/03 10:43:37 - mmengine - INFO - Epoch(train) [13][50/79] lr: 1.0000e-06 eta: 2:00:09 time: 0.4886 data_time: 0.0014 memory: 30766 loss: 0.1331 loss_ce: 0.1331 2023/03/03 10:43:38 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 10:43:42 - mmengine - INFO - Epoch(train) [13][60/79] lr: 1.0000e-06 eta: 2:00:01 time: 0.4643 data_time: 0.0014 memory: 35418 loss: 0.1275 loss_ce: 0.1275 2023/03/03 10:43:47 - mmengine - INFO - Epoch(train) [13][70/79] lr: 1.0000e-06 eta: 1:59:53 time: 0.4683 data_time: 0.0015 memory: 40235 loss: 0.1321 loss_ce: 0.1321 2023/03/03 10:43:50 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 10:43:55 - mmengine - INFO - Epoch(train) [14][10/79] lr: 1.0000e-06 eta: 1:59:36 time: 0.4931 data_time: 0.0709 memory: 37040 loss: 0.1596 loss_ce: 0.1596 2023/03/03 10:44:00 - mmengine - INFO - Epoch(train) [14][20/79] lr: 1.0000e-06 eta: 1:59:26 time: 0.4529 data_time: 0.0015 memory: 30916 loss: 0.1385 loss_ce: 0.1385 2023/03/03 10:44:04 - mmengine - INFO - Epoch(train) [14][30/79] lr: 1.0000e-06 eta: 1:59:18 time: 0.4637 data_time: 0.0014 memory: 38155 loss: 0.1542 loss_ce: 0.1542 2023/03/03 10:44:09 - mmengine - INFO - Epoch(train) [14][40/79] lr: 1.0000e-06 eta: 1:59:06 time: 0.4285 data_time: 0.0014 memory: 38332 loss: 0.1280 loss_ce: 0.1280 2023/03/03 10:44:13 - mmengine - INFO - Epoch(train) [14][50/79] lr: 1.0000e-06 eta: 1:58:53 time: 0.4254 data_time: 0.0014 memory: 29963 loss: 0.1424 loss_ce: 0.1424 2023/03/03 10:44:17 - mmengine - INFO - Epoch(train) [14][60/79] lr: 1.0000e-06 eta: 1:58:44 time: 0.4545 data_time: 0.0014 memory: 37891 loss: 0.1458 loss_ce: 0.1458 2023/03/03 10:44:22 - mmengine - INFO - Epoch(train) [14][70/79] lr: 1.0000e-06 eta: 1:58:36 time: 0.4661 data_time: 0.0014 memory: 40816 loss: 0.1396 loss_ce: 0.1396 2023/03/03 10:44:26 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 10:44:33 - mmengine - INFO - Epoch(train) [15][10/79] lr: 1.0000e-06 eta: 1:58:44 time: 0.6237 data_time: 0.0576 memory: 41411 loss: 0.1344 loss_ce: 0.1344 2023/03/03 10:44:37 - mmengine - INFO - Epoch(train) [15][20/79] lr: 1.0000e-06 eta: 1:58:38 time: 0.4732 data_time: 0.0014 memory: 47665 loss: 0.1355 loss_ce: 0.1355 2023/03/03 10:44:42 - mmengine - INFO - Epoch(train) [15][30/79] lr: 1.0000e-06 eta: 1:58:31 time: 0.4697 data_time: 0.0014 memory: 35471 loss: 0.1560 loss_ce: 0.1560 2023/03/03 10:44:47 - mmengine - INFO - Epoch(train) [15][40/79] lr: 1.0000e-06 eta: 1:58:26 time: 0.4854 data_time: 0.0015 memory: 41607 loss: 0.1191 loss_ce: 0.1191 2023/03/03 10:44:52 - mmengine - INFO - Epoch(train) [15][50/79] lr: 1.0000e-06 eta: 1:58:18 time: 0.4637 data_time: 0.0014 memory: 32867 loss: 0.1376 loss_ce: 0.1376 2023/03/03 10:44:56 - mmengine - INFO - Epoch(train) [15][60/79] lr: 1.0000e-06 eta: 1:58:11 time: 0.4654 data_time: 0.0014 memory: 36734 loss: 0.1414 loss_ce: 0.1414 2023/03/03 10:45:01 - mmengine - INFO - Epoch(train) [15][70/79] lr: 1.0000e-06 eta: 1:58:00 time: 0.4329 data_time: 0.0014 memory: 39669 loss: 0.1411 loss_ce: 0.1411 2023/03/03 10:45:05 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 10:45:10 - mmengine - INFO - Epoch(train) [16][10/79] lr: 1.0000e-06 eta: 1:57:52 time: 0.4838 data_time: 0.0684 memory: 40235 loss: 0.1185 loss_ce: 0.1185 2023/03/03 10:45:15 - mmengine - INFO - Epoch(train) [16][20/79] lr: 1.0000e-06 eta: 1:57:50 time: 0.5045 data_time: 0.0014 memory: 35610 loss: 0.1430 loss_ce: 0.1430 2023/03/03 10:45:20 - mmengine - INFO - Epoch(train) [16][30/79] lr: 1.0000e-06 eta: 1:57:49 time: 0.5153 data_time: 0.0014 memory: 39389 loss: 0.1442 loss_ce: 0.1442 2023/03/03 10:45:25 - mmengine - INFO - Epoch(train) [16][40/79] lr: 1.0000e-06 eta: 1:57:44 time: 0.4911 data_time: 0.0015 memory: 39124 loss: 0.1455 loss_ce: 0.1455 2023/03/03 10:45:30 - mmengine - INFO - Epoch(train) [16][50/79] lr: 1.0000e-06 eta: 1:57:40 time: 0.4880 data_time: 0.0014 memory: 40235 loss: 0.1469 loss_ce: 0.1469 2023/03/03 10:45:34 - mmengine - INFO - Epoch(train) [16][60/79] lr: 1.0000e-06 eta: 1:57:32 time: 0.4591 data_time: 0.0014 memory: 41411 loss: 0.1470 loss_ce: 0.1470 2023/03/03 10:45:40 - mmengine - INFO - Epoch(train) [16][70/79] lr: 1.0000e-06 eta: 1:57:39 time: 0.5875 data_time: 0.0013 memory: 37822 loss: 0.1393 loss_ce: 0.1393 2023/03/03 10:45:44 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 10:45:49 - mmengine - INFO - Epoch(train) [17][10/79] lr: 1.0000e-06 eta: 1:57:25 time: 0.5134 data_time: 0.0673 memory: 44612 loss: 0.1336 loss_ce: 0.1336 2023/03/03 10:45:53 - mmengine - INFO - Epoch(train) [17][20/79] lr: 1.0000e-06 eta: 1:57:12 time: 0.4143 data_time: 0.0014 memory: 37933 loss: 0.1402 loss_ce: 0.1402 2023/03/03 10:45:57 - mmengine - INFO - Epoch(train) [17][30/79] lr: 1.0000e-06 eta: 1:57:00 time: 0.4164 data_time: 0.0014 memory: 36834 loss: 0.1265 loss_ce: 0.1265 2023/03/03 10:46:02 - mmengine - INFO - Epoch(train) [17][40/79] lr: 1.0000e-06 eta: 1:56:53 time: 0.4687 data_time: 0.0014 memory: 42289 loss: 0.1254 loss_ce: 0.1254 2023/03/03 10:46:07 - mmengine - INFO - Epoch(train) [17][50/79] lr: 1.0000e-06 eta: 1:56:47 time: 0.4727 data_time: 0.0014 memory: 29730 loss: 0.1431 loss_ce: 0.1431 2023/03/03 10:46:11 - mmengine - INFO - Epoch(train) [17][60/79] lr: 1.0000e-06 eta: 1:56:38 time: 0.4461 data_time: 0.0014 memory: 25133 loss: 0.1489 loss_ce: 0.1489 2023/03/03 10:46:16 - mmengine - INFO - Epoch(train) [17][70/79] lr: 1.0000e-06 eta: 1:56:32 time: 0.4684 data_time: 0.0013 memory: 38894 loss: 0.1367 loss_ce: 0.1367 2023/03/03 10:46:20 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 10:46:26 - mmengine - INFO - Epoch(train) [18][10/79] lr: 1.0000e-06 eta: 1:56:33 time: 0.6008 data_time: 0.0608 memory: 39955 loss: 0.1204 loss_ce: 0.1204 2023/03/03 10:46:31 - mmengine - INFO - Epoch(train) [18][20/79] lr: 1.0000e-06 eta: 1:56:25 time: 0.4580 data_time: 0.0014 memory: 34943 loss: 0.1336 loss_ce: 0.1336 2023/03/03 10:46:35 - mmengine - INFO - Epoch(train) [18][30/79] lr: 1.0000e-06 eta: 1:56:19 time: 0.4715 data_time: 0.0015 memory: 38587 loss: 0.1579 loss_ce: 0.1579 2023/03/03 10:46:40 - mmengine - INFO - Epoch(train) [18][40/79] lr: 1.0000e-06 eta: 1:56:10 time: 0.4392 data_time: 0.0014 memory: 30244 loss: 0.1342 loss_ce: 0.1342 2023/03/03 10:46:45 - mmengine - INFO - Epoch(train) [18][50/79] lr: 1.0000e-06 eta: 1:56:06 time: 0.4900 data_time: 0.0015 memory: 38334 loss: 0.1350 loss_ce: 0.1350 2023/03/03 10:46:50 - mmengine - INFO - Epoch(train) [18][60/79] lr: 1.0000e-06 eta: 1:56:04 time: 0.5115 data_time: 0.0014 memory: 38332 loss: 0.1327 loss_ce: 0.1327 2023/03/03 10:46:54 - mmengine - INFO - Epoch(train) [18][70/79] lr: 1.0000e-06 eta: 1:55:51 time: 0.4090 data_time: 0.0013 memory: 42017 loss: 0.1310 loss_ce: 0.1310 2023/03/03 10:46:58 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 10:47:03 - mmengine - INFO - Epoch(train) [19][10/79] lr: 1.0000e-06 eta: 1:55:43 time: 0.5172 data_time: 0.0849 memory: 38845 loss: 0.1268 loss_ce: 0.1268 2023/03/03 10:47:08 - mmengine - INFO - Epoch(train) [19][20/79] lr: 1.0000e-06 eta: 1:55:37 time: 0.4706 data_time: 0.0014 memory: 36230 loss: 0.1462 loss_ce: 0.1462 2023/03/03 10:47:12 - mmengine - INFO - Epoch(train) [19][30/79] lr: 1.0000e-06 eta: 1:55:29 time: 0.4550 data_time: 0.0016 memory: 37301 loss: 0.1431 loss_ce: 0.1431 2023/03/03 10:47:17 - mmengine - INFO - Epoch(train) [19][40/79] lr: 1.0000e-06 eta: 1:55:25 time: 0.4873 data_time: 0.0015 memory: 39955 loss: 0.1226 loss_ce: 0.1226 2023/03/03 10:47:22 - mmengine - INFO - Epoch(train) [19][50/79] lr: 1.0000e-06 eta: 1:55:19 time: 0.4726 data_time: 0.0015 memory: 39990 loss: 0.1259 loss_ce: 0.1259 2023/03/03 10:47:27 - mmengine - INFO - Epoch(train) [19][60/79] lr: 1.0000e-06 eta: 1:55:13 time: 0.4658 data_time: 0.0014 memory: 25099 loss: 0.1534 loss_ce: 0.1534 2023/03/03 10:47:32 - mmengine - INFO - Epoch(train) [19][70/79] lr: 1.0000e-06 eta: 1:55:10 time: 0.5078 data_time: 0.0014 memory: 34462 loss: 0.1436 loss_ce: 0.1436 2023/03/03 10:47:36 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 10:47:41 - mmengine - INFO - Epoch(train) [20][10/79] lr: 1.0000e-06 eta: 1:55:04 time: 0.5197 data_time: 0.0499 memory: 38058 loss: 0.1382 loss_ce: 0.1382 2023/03/03 10:47:46 - mmengine - INFO - Epoch(train) [20][20/79] lr: 1.0000e-06 eta: 1:54:58 time: 0.4719 data_time: 0.0014 memory: 38587 loss: 0.1298 loss_ce: 0.1298 2023/03/03 10:47:51 - mmengine - INFO - Epoch(train) [20][30/79] lr: 1.0000e-06 eta: 1:54:53 time: 0.4767 data_time: 0.0016 memory: 41755 loss: 0.1400 loss_ce: 0.1400 2023/03/03 10:47:56 - mmengine - INFO - Epoch(train) [20][40/79] lr: 1.0000e-06 eta: 1:54:49 time: 0.4915 data_time: 0.0017 memory: 38058 loss: 0.1441 loss_ce: 0.1441 2023/03/03 10:48:00 - mmengine - INFO - Epoch(train) [20][50/79] lr: 1.0000e-06 eta: 1:54:39 time: 0.4350 data_time: 0.0014 memory: 31514 loss: 0.1368 loss_ce: 0.1368 2023/03/03 10:48:05 - mmengine - INFO - Epoch(train) [20][60/79] lr: 1.0000e-06 eta: 1:54:35 time: 0.4888 data_time: 0.0015 memory: 37933 loss: 0.1260 loss_ce: 0.1260 2023/03/03 10:48:10 - mmengine - INFO - Epoch(train) [20][70/79] lr: 1.0000e-06 eta: 1:54:29 time: 0.4674 data_time: 0.0015 memory: 27871 loss: 0.1583 loss_ce: 0.1583 2023/03/03 10:48:14 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 10:48:26 - mmengine - INFO - Epoch(val) [20][10/75] eta: 0:01:22 time: 1.2646 data_time: 0.0036 memory: 27029 2023/03/03 10:49:04 - mmengine - INFO - Epoch(val) [20][20/75] eta: 0:02:18 time: 3.7696 data_time: 0.0004 memory: 1077 2023/03/03 10:49:25 - mmengine - INFO - Epoch(val) [20][30/75] eta: 0:01:46 time: 2.0857 data_time: 0.0003 memory: 1020 2023/03/03 10:49:41 - mmengine - INFO - Epoch(val) [20][40/75] eta: 0:01:16 time: 1.6513 data_time: 0.0003 memory: 1019 2023/03/03 10:49:58 - mmengine - INFO - Epoch(val) [20][50/75] eta: 0:00:51 time: 1.6252 data_time: 0.0003 memory: 1077 2023/03/03 10:50:44 - mmengine - INFO - Epoch(val) [20][60/75] eta: 0:00:37 time: 4.5964 data_time: 0.0003 memory: 1045 2023/03/03 10:51:26 - mmengine - INFO - Epoch(val) [20][70/75] eta: 0:00:13 time: 4.2526 data_time: 0.0003 memory: 1077 2023/03/03 10:51:40 - mmengine - INFO - text score threshold: 0.80, recall: 0.6734, precision: 0.7528, hmean: 0.7109 2023/03/03 10:51:40 - mmengine - INFO - text score threshold: 0.81, recall: 0.6723, precision: 0.7599, hmean: 0.7135 2023/03/03 10:51:40 - mmengine - INFO - text score threshold: 0.82, recall: 0.6718, precision: 0.7645, hmean: 0.7152 2023/03/03 10:51:40 - mmengine - INFO - text score threshold: 0.83, recall: 0.6707, precision: 0.7695, hmean: 0.7167 2023/03/03 10:51:40 - mmengine - INFO - text score threshold: 0.84, recall: 0.6685, precision: 0.7758, hmean: 0.7182 2023/03/03 10:51:40 - mmengine - INFO - text score threshold: 0.85, recall: 0.6679, precision: 0.7816, hmean: 0.7203 2023/03/03 10:51:40 - mmengine - INFO - text score threshold: 0.86, recall: 0.6647, precision: 0.7864, hmean: 0.7204 2023/03/03 10:51:40 - mmengine - INFO - text score threshold: 0.87, recall: 0.6630, precision: 0.7942, hmean: 0.7227 2023/03/03 10:51:40 - mmengine - INFO - text score threshold: 0.88, recall: 0.6608, precision: 0.8016, hmean: 0.7244 2023/03/03 10:51:40 - mmengine - INFO - text score threshold: 0.89, recall: 0.6564, precision: 0.8114, hmean: 0.7257 2023/03/03 10:51:40 - mmengine - INFO - text score threshold: 0.90, recall: 0.6515, precision: 0.8130, hmean: 0.7233 2023/03/03 10:51:40 - mmengine - INFO - text score threshold: 0.91, recall: 0.6487, precision: 0.8203, hmean: 0.7245 2023/03/03 10:51:40 - mmengine - INFO - text score threshold: 0.92, recall: 0.6443, precision: 0.8314, hmean: 0.7260 2023/03/03 10:51:40 - mmengine - INFO - text score threshold: 0.93, recall: 0.6372, precision: 0.8407, hmean: 0.7249 2023/03/03 10:51:40 - mmengine - INFO - text score threshold: 0.94, recall: 0.6262, precision: 0.8483, hmean: 0.7206 2023/03/03 10:51:40 - mmengine - INFO - text score threshold: 0.95, recall: 0.6186, precision: 0.8577, hmean: 0.7188 2023/03/03 10:51:40 - mmengine - INFO - text score threshold: 0.96, recall: 0.6021, precision: 0.8679, hmean: 0.7110 2023/03/03 10:51:40 - mmengine - INFO - text score threshold: 0.97, recall: 0.5878, precision: 0.8771, hmean: 0.7039 2023/03/03 10:51:40 - mmengine - INFO - text score threshold: 0.98, recall: 0.5626, precision: 0.8882, hmean: 0.6888 2023/03/03 10:51:40 - mmengine - INFO - text score threshold: 0.99, recall: 0.5154, precision: 0.9038, hmean: 0.6564 2023/03/03 10:51:50 - mmengine - INFO - text score threshold: 0.80, recall: 0.7629, precision: 0.8848, hmean: 0.8193 2023/03/03 10:51:50 - mmengine - INFO - text score threshold: 0.81, recall: 0.7596, precision: 0.8895, hmean: 0.8194 2023/03/03 10:51:50 - mmengine - INFO - text score threshold: 0.82, recall: 0.7574, precision: 0.8915, hmean: 0.8190 2023/03/03 10:51:50 - mmengine - INFO - text score threshold: 0.83, recall: 0.7536, precision: 0.8939, hmean: 0.8177 2023/03/03 10:51:50 - mmengine - INFO - text score threshold: 0.84, recall: 0.7475, precision: 0.8955, hmean: 0.8148 2023/03/03 10:51:50 - mmengine - INFO - text score threshold: 0.85, recall: 0.7442, precision: 0.8980, hmean: 0.8139 2023/03/03 10:51:50 - mmengine - INFO - text score threshold: 0.86, recall: 0.7393, precision: 0.9004, hmean: 0.8119 2023/03/03 10:51:50 - mmengine - INFO - text score threshold: 0.87, recall: 0.7355, precision: 0.9054, hmean: 0.8116 2023/03/03 10:51:50 - mmengine - INFO - text score threshold: 0.88, recall: 0.7283, precision: 0.9077, hmean: 0.8082 2023/03/03 10:51:50 - mmengine - INFO - text score threshold: 0.89, recall: 0.7184, precision: 0.9122, hmean: 0.8038 2023/03/03 10:51:50 - mmengine - INFO - text score threshold: 0.90, recall: 0.7113, precision: 0.9120, hmean: 0.7993 2023/03/03 10:51:50 - mmengine - INFO - text score threshold: 0.91, recall: 0.7042, precision: 0.9151, hmean: 0.7959 2023/03/03 10:51:50 - mmengine - INFO - text score threshold: 0.92, recall: 0.6959, precision: 0.9215, hmean: 0.7930 2023/03/03 10:51:50 - mmengine - INFO - text score threshold: 0.93, recall: 0.6828, precision: 0.9249, hmean: 0.7856 2023/03/03 10:51:50 - mmengine - INFO - text score threshold: 0.94, recall: 0.6674, precision: 0.9275, hmean: 0.7763 2023/03/03 10:51:50 - mmengine - INFO - text score threshold: 0.95, recall: 0.6537, precision: 0.9283, hmean: 0.7671 2023/03/03 10:51:50 - mmengine - INFO - text score threshold: 0.96, recall: 0.6334, precision: 0.9352, hmean: 0.7552 2023/03/03 10:51:50 - mmengine - INFO - text score threshold: 0.97, recall: 0.6136, precision: 0.9387, hmean: 0.7421 2023/03/03 10:51:50 - mmengine - INFO - text score threshold: 0.98, recall: 0.5834, precision: 0.9440, hmean: 0.7212 2023/03/03 10:51:50 - mmengine - INFO - text score threshold: 0.99, recall: 0.5291, precision: 0.9516, hmean: 0.6801 2023/03/03 10:51:50 - mmengine - INFO - Epoch(val) [20][75/75] none/precision: 0.8314 none/recall: 0.6443 none/hmean: 0.7260 full/precision: 0.8895 full/recall: 0.7596 full/hmean: 0.8194 2023/03/03 10:51:56 - mmengine - INFO - Epoch(train) [21][10/79] lr: 1.0000e-06 eta: 1:54:22 time: 0.5500 data_time: 0.0714 memory: 35583 loss: 0.1266 loss_ce: 0.1266 2023/03/03 10:52:00 - mmengine - INFO - Epoch(train) [21][20/79] lr: 1.0000e-06 eta: 1:54:14 time: 0.4449 data_time: 0.0014 memory: 29468 loss: 0.1302 loss_ce: 0.1302 2023/03/03 10:52:05 - mmengine - INFO - Epoch(train) [21][30/79] lr: 1.0000e-06 eta: 1:54:07 time: 0.4604 data_time: 0.0014 memory: 36447 loss: 0.1204 loss_ce: 0.1204 2023/03/03 10:52:10 - mmengine - INFO - Epoch(train) [21][40/79] lr: 1.0000e-06 eta: 1:54:00 time: 0.4537 data_time: 0.0014 memory: 40816 loss: 0.1414 loss_ce: 0.1414 2023/03/03 10:52:14 - mmengine - INFO - Epoch(train) [21][50/79] lr: 1.0000e-06 eta: 1:53:53 time: 0.4546 data_time: 0.0014 memory: 33903 loss: 0.1447 loss_ce: 0.1447 2023/03/03 10:52:19 - mmengine - INFO - Epoch(train) [21][60/79] lr: 1.0000e-06 eta: 1:53:46 time: 0.4666 data_time: 0.0016 memory: 31659 loss: 0.1368 loss_ce: 0.1368 2023/03/03 10:52:23 - mmengine - INFO - Epoch(train) [21][70/79] lr: 1.0000e-06 eta: 1:53:39 time: 0.4579 data_time: 0.0014 memory: 28298 loss: 0.1099 loss_ce: 0.1099 2023/03/03 10:52:27 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 10:52:32 - mmengine - INFO - Epoch(train) [22][10/79] lr: 1.0000e-06 eta: 1:53:28 time: 0.4783 data_time: 0.0585 memory: 39119 loss: 0.1506 loss_ce: 0.1506 2023/03/03 10:52:37 - mmengine - INFO - Epoch(train) [22][20/79] lr: 1.0000e-06 eta: 1:53:18 time: 0.4278 data_time: 0.0015 memory: 34065 loss: 0.1136 loss_ce: 0.1136 2023/03/03 10:52:41 - mmengine - INFO - Epoch(train) [22][30/79] lr: 1.0000e-06 eta: 1:53:14 time: 0.4905 data_time: 0.0014 memory: 38570 loss: 0.1293 loss_ce: 0.1293 2023/03/03 10:52:46 - mmengine - INFO - Epoch(train) [22][40/79] lr: 1.0000e-06 eta: 1:53:09 time: 0.4755 data_time: 0.0014 memory: 36227 loss: 0.1278 loss_ce: 0.1278 2023/03/03 10:52:51 - mmengine - INFO - Epoch(train) [22][50/79] lr: 1.0000e-06 eta: 1:53:03 time: 0.4722 data_time: 0.0014 memory: 25739 loss: 0.1414 loss_ce: 0.1414 2023/03/03 10:52:55 - mmengine - INFO - Epoch(train) [22][60/79] lr: 1.0000e-06 eta: 1:52:56 time: 0.4552 data_time: 0.0014 memory: 38408 loss: 0.1288 loss_ce: 0.1288 2023/03/03 10:53:00 - mmengine - INFO - Epoch(train) [22][70/79] lr: 1.0000e-06 eta: 1:52:52 time: 0.4920 data_time: 0.0016 memory: 38091 loss: 0.1338 loss_ce: 0.1338 2023/03/03 10:53:04 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 10:53:10 - mmengine - INFO - Epoch(train) [23][10/79] lr: 1.0000e-06 eta: 1:52:46 time: 0.5372 data_time: 0.0451 memory: 44272 loss: 0.1135 loss_ce: 0.1135 2023/03/03 10:53:15 - mmengine - INFO - Epoch(train) [23][20/79] lr: 1.0000e-06 eta: 1:52:41 time: 0.4910 data_time: 0.0014 memory: 40522 loss: 0.1136 loss_ce: 0.1136 2023/03/03 10:53:19 - mmengine - INFO - Epoch(train) [23][30/79] lr: 1.0000e-06 eta: 1:52:33 time: 0.4348 data_time: 0.0014 memory: 39389 loss: 0.1183 loss_ce: 0.1183 2023/03/03 10:53:24 - mmengine - INFO - Epoch(train) [23][40/79] lr: 1.0000e-06 eta: 1:52:31 time: 0.5201 data_time: 0.0015 memory: 31427 loss: 0.1374 loss_ce: 0.1374 2023/03/03 10:53:29 - mmengine - INFO - Epoch(train) [23][50/79] lr: 1.0000e-06 eta: 1:52:24 time: 0.4456 data_time: 0.0016 memory: 37922 loss: 0.1419 loss_ce: 0.1419 2023/03/03 10:53:34 - mmengine - INFO - Epoch(train) [23][60/79] lr: 1.0000e-06 eta: 1:52:19 time: 0.4833 data_time: 0.0016 memory: 39880 loss: 0.1446 loss_ce: 0.1446 2023/03/03 10:53:38 - mmengine - INFO - Epoch(train) [23][70/79] lr: 1.0000e-06 eta: 1:52:11 time: 0.4420 data_time: 0.0014 memory: 41273 loss: 0.1322 loss_ce: 0.1322 2023/03/03 10:53:42 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 10:53:46 - mmengine - INFO - Epoch(train) [24][10/79] lr: 1.0000e-06 eta: 1:51:56 time: 0.4832 data_time: 0.0475 memory: 39955 loss: 0.1172 loss_ce: 0.1172 2023/03/03 10:53:52 - mmengine - INFO - Epoch(train) [24][20/79] lr: 1.0000e-06 eta: 1:51:55 time: 0.5192 data_time: 0.0014 memory: 36139 loss: 0.1316 loss_ce: 0.1316 2023/03/03 10:53:57 - mmengine - INFO - Epoch(train) [24][30/79] lr: 1.0000e-06 eta: 1:51:53 time: 0.5222 data_time: 0.0015 memory: 29007 loss: 0.1436 loss_ce: 0.1436 2023/03/03 10:54:02 - mmengine - INFO - Epoch(train) [24][40/79] lr: 1.0000e-06 eta: 1:51:50 time: 0.5077 data_time: 0.0015 memory: 44776 loss: 0.1450 loss_ce: 0.1450 2023/03/03 10:54:06 - mmengine - INFO - Epoch(train) [24][50/79] lr: 1.0000e-06 eta: 1:51:44 time: 0.4590 data_time: 0.0015 memory: 35536 loss: 0.1322 loss_ce: 0.1322 2023/03/03 10:54:12 - mmengine - INFO - Epoch(train) [24][60/79] lr: 1.0000e-06 eta: 1:51:42 time: 0.5184 data_time: 0.0014 memory: 37933 loss: 0.1383 loss_ce: 0.1383 2023/03/03 10:54:16 - mmengine - INFO - Epoch(train) [24][70/79] lr: 1.0000e-06 eta: 1:51:36 time: 0.4665 data_time: 0.0014 memory: 37933 loss: 0.1200 loss_ce: 0.1200 2023/03/03 10:54:20 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 10:54:26 - mmengine - INFO - Epoch(train) [25][10/79] lr: 1.0000e-06 eta: 1:51:30 time: 0.5794 data_time: 0.0606 memory: 38332 loss: 0.1362 loss_ce: 0.1362 2023/03/03 10:54:31 - mmengine - INFO - Epoch(train) [25][20/79] lr: 1.0000e-06 eta: 1:51:26 time: 0.4899 data_time: 0.0015 memory: 34195 loss: 0.1357 loss_ce: 0.1357 2023/03/03 10:54:36 - mmengine - INFO - Epoch(train) [25][30/79] lr: 1.0000e-06 eta: 1:51:21 time: 0.4847 data_time: 0.0015 memory: 41714 loss: 0.1438 loss_ce: 0.1438 2023/03/03 10:54:40 - mmengine - INFO - Epoch(train) [25][40/79] lr: 1.0000e-06 eta: 1:51:16 time: 0.4764 data_time: 0.0015 memory: 34489 loss: 0.1440 loss_ce: 0.1440 2023/03/03 10:54:45 - mmengine - INFO - Epoch(train) [25][50/79] lr: 1.0000e-06 eta: 1:51:12 time: 0.5007 data_time: 0.0016 memory: 33996 loss: 0.1263 loss_ce: 0.1263 2023/03/03 10:54:50 - mmengine - INFO - Epoch(train) [25][60/79] lr: 1.0000e-06 eta: 1:51:04 time: 0.4349 data_time: 0.0016 memory: 33776 loss: 0.1296 loss_ce: 0.1296 2023/03/03 10:54:55 - mmengine - INFO - Epoch(train) [25][70/79] lr: 1.0000e-06 eta: 1:51:00 time: 0.4935 data_time: 0.0014 memory: 37933 loss: 0.1211 loss_ce: 0.1211 2023/03/03 10:54:59 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 10:55:04 - mmengine - INFO - Epoch(train) [26][10/79] lr: 1.0000e-06 eta: 1:50:52 time: 0.5384 data_time: 0.0645 memory: 38587 loss: 0.1323 loss_ce: 0.1323 2023/03/03 10:55:08 - mmengine - INFO - Epoch(train) [26][20/79] lr: 1.0000e-06 eta: 1:50:43 time: 0.4181 data_time: 0.0015 memory: 38845 loss: 0.1346 loss_ce: 0.1346 2023/03/03 10:55:11 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 10:55:13 - mmengine - INFO - Epoch(train) [26][30/79] lr: 1.0000e-06 eta: 1:50:36 time: 0.4613 data_time: 0.0015 memory: 39955 loss: 0.1279 loss_ce: 0.1279 2023/03/03 10:55:17 - mmengine - INFO - Epoch(train) [26][40/79] lr: 1.0000e-06 eta: 1:50:29 time: 0.4368 data_time: 0.0016 memory: 36006 loss: 0.1477 loss_ce: 0.1477 2023/03/03 10:55:22 - mmengine - INFO - Epoch(train) [26][50/79] lr: 1.0000e-06 eta: 1:50:27 time: 0.5246 data_time: 0.0014 memory: 38764 loss: 0.1175 loss_ce: 0.1175 2023/03/03 10:55:27 - mmengine - INFO - Epoch(train) [26][60/79] lr: 1.0000e-06 eta: 1:50:22 time: 0.4745 data_time: 0.0015 memory: 38845 loss: 0.1388 loss_ce: 0.1388 2023/03/03 10:55:31 - mmengine - INFO - Epoch(train) [26][70/79] lr: 1.0000e-06 eta: 1:50:13 time: 0.4304 data_time: 0.0013 memory: 39389 loss: 0.1320 loss_ce: 0.1320 2023/03/03 10:55:36 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 10:55:41 - mmengine - INFO - Epoch(train) [27][10/79] lr: 1.0000e-06 eta: 1:50:07 time: 0.5131 data_time: 0.0611 memory: 42236 loss: 0.1466 loss_ce: 0.1466 2023/03/03 10:55:46 - mmengine - INFO - Epoch(train) [27][20/79] lr: 1.0000e-06 eta: 1:50:05 time: 0.5232 data_time: 0.0014 memory: 37189 loss: 0.1327 loss_ce: 0.1327 2023/03/03 10:55:51 - mmengine - INFO - Epoch(train) [27][30/79] lr: 1.0000e-06 eta: 1:49:59 time: 0.4654 data_time: 0.0014 memory: 29822 loss: 0.1356 loss_ce: 0.1356 2023/03/03 10:55:55 - mmengine - INFO - Epoch(train) [27][40/79] lr: 1.0000e-06 eta: 1:49:51 time: 0.4323 data_time: 0.0014 memory: 38587 loss: 0.1196 loss_ce: 0.1196 2023/03/03 10:56:00 - mmengine - INFO - Epoch(train) [27][50/79] lr: 1.0000e-06 eta: 1:49:43 time: 0.4351 data_time: 0.0014 memory: 27076 loss: 0.1251 loss_ce: 0.1251 2023/03/03 10:56:05 - mmengine - INFO - Epoch(train) [27][60/79] lr: 1.0000e-06 eta: 1:49:40 time: 0.5088 data_time: 0.0015 memory: 38336 loss: 0.1334 loss_ce: 0.1334 2023/03/03 10:56:09 - mmengine - INFO - Epoch(train) [27][70/79] lr: 1.0000e-06 eta: 1:49:33 time: 0.4393 data_time: 0.0014 memory: 34693 loss: 0.1312 loss_ce: 0.1312 2023/03/03 10:56:13 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 10:56:19 - mmengine - INFO - Epoch(train) [28][10/79] lr: 1.0000e-06 eta: 1:49:30 time: 0.5978 data_time: 0.0808 memory: 42020 loss: 0.1360 loss_ce: 0.1360 2023/03/03 10:56:24 - mmengine - INFO - Epoch(train) [28][20/79] lr: 1.0000e-06 eta: 1:49:23 time: 0.4538 data_time: 0.0015 memory: 41411 loss: 0.1337 loss_ce: 0.1337 2023/03/03 10:56:28 - mmengine - INFO - Epoch(train) [28][30/79] lr: 1.0000e-06 eta: 1:49:17 time: 0.4539 data_time: 0.0015 memory: 31244 loss: 0.1052 loss_ce: 0.1052 2023/03/03 10:56:33 - mmengine - INFO - Epoch(train) [28][40/79] lr: 1.0000e-06 eta: 1:49:14 time: 0.5167 data_time: 0.0014 memory: 31738 loss: 0.1273 loss_ce: 0.1273 2023/03/03 10:56:38 - mmengine - INFO - Epoch(train) [28][50/79] lr: 1.0000e-06 eta: 1:49:10 time: 0.4908 data_time: 0.0015 memory: 28296 loss: 0.1228 loss_ce: 0.1228 2023/03/03 10:56:43 - mmengine - INFO - Epoch(train) [28][60/79] lr: 1.0000e-06 eta: 1:49:05 time: 0.4720 data_time: 0.0014 memory: 38587 loss: 0.1337 loss_ce: 0.1337 2023/03/03 10:56:47 - mmengine - INFO - Epoch(train) [28][70/79] lr: 1.0000e-06 eta: 1:48:57 time: 0.4396 data_time: 0.0013 memory: 36959 loss: 0.1513 loss_ce: 0.1513 2023/03/03 10:56:51 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 10:56:57 - mmengine - INFO - Epoch(train) [29][10/79] lr: 1.0000e-06 eta: 1:48:50 time: 0.5822 data_time: 0.0801 memory: 37283 loss: 0.1279 loss_ce: 0.1279 2023/03/03 10:57:02 - mmengine - INFO - Epoch(train) [29][20/79] lr: 1.0000e-06 eta: 1:48:45 time: 0.4701 data_time: 0.0015 memory: 31184 loss: 0.1127 loss_ce: 0.1127 2023/03/03 10:57:06 - mmengine - INFO - Epoch(train) [29][30/79] lr: 1.0000e-06 eta: 1:48:38 time: 0.4521 data_time: 0.0015 memory: 35980 loss: 0.1424 loss_ce: 0.1424 2023/03/03 10:57:11 - mmengine - INFO - Epoch(train) [29][40/79] lr: 1.0000e-06 eta: 1:48:32 time: 0.4589 data_time: 0.0014 memory: 39119 loss: 0.1249 loss_ce: 0.1249 2023/03/03 10:57:16 - mmengine - INFO - Epoch(train) [29][50/79] lr: 1.0000e-06 eta: 1:48:30 time: 0.5343 data_time: 0.0014 memory: 38587 loss: 0.1206 loss_ce: 0.1206 2023/03/03 10:57:21 - mmengine - INFO - Epoch(train) [29][60/79] lr: 1.0000e-06 eta: 1:48:24 time: 0.4529 data_time: 0.0015 memory: 38080 loss: 0.1490 loss_ce: 0.1490 2023/03/03 10:57:25 - mmengine - INFO - Epoch(train) [29][70/79] lr: 1.0000e-06 eta: 1:48:17 time: 0.4458 data_time: 0.0014 memory: 38332 loss: 0.1304 loss_ce: 0.1304 2023/03/03 10:57:29 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 10:57:34 - mmengine - INFO - Epoch(train) [30][10/79] lr: 1.0000e-06 eta: 1:48:10 time: 0.5200 data_time: 0.0730 memory: 39119 loss: 0.1464 loss_ce: 0.1464 2023/03/03 10:57:39 - mmengine - INFO - Epoch(train) [30][20/79] lr: 1.0000e-06 eta: 1:48:05 time: 0.4762 data_time: 0.0015 memory: 40280 loss: 0.1271 loss_ce: 0.1271 2023/03/03 10:57:44 - mmengine - INFO - Epoch(train) [30][30/79] lr: 1.0000e-06 eta: 1:48:01 time: 0.5090 data_time: 0.0015 memory: 37685 loss: 0.1227 loss_ce: 0.1227 2023/03/03 10:57:49 - mmengine - INFO - Epoch(train) [30][40/79] lr: 1.0000e-06 eta: 1:47:57 time: 0.4877 data_time: 0.0014 memory: 38080 loss: 0.1360 loss_ce: 0.1360 2023/03/03 10:57:53 - mmengine - INFO - Epoch(train) [30][50/79] lr: 1.0000e-06 eta: 1:47:49 time: 0.4223 data_time: 0.0015 memory: 26682 loss: 0.1368 loss_ce: 0.1368 2023/03/03 10:57:58 - mmengine - INFO - Epoch(train) [30][60/79] lr: 1.0000e-06 eta: 1:47:45 time: 0.4908 data_time: 0.0015 memory: 38332 loss: 0.1333 loss_ce: 0.1333 2023/03/03 10:58:03 - mmengine - INFO - Epoch(train) [30][70/79] lr: 1.0000e-06 eta: 1:47:39 time: 0.4646 data_time: 0.0014 memory: 36562 loss: 0.1352 loss_ce: 0.1352 2023/03/03 10:58:07 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 10:58:20 - mmengine - INFO - Epoch(val) [30][10/75] eta: 0:01:22 time: 1.2683 data_time: 0.0034 memory: 37931 2023/03/03 10:59:20 - mmengine - INFO - Epoch(val) [30][20/75] eta: 0:03:20 time: 6.0115 data_time: 0.0003 memory: 1077 2023/03/03 10:59:42 - mmengine - INFO - Epoch(val) [30][30/75] eta: 0:02:22 time: 2.2142 data_time: 0.0004 memory: 1020 2023/03/03 10:59:58 - mmengine - INFO - Epoch(val) [30][40/75] eta: 0:01:37 time: 1.5993 data_time: 0.0003 memory: 1019 2023/03/03 11:00:13 - mmengine - INFO - Epoch(val) [30][50/75] eta: 0:01:02 time: 1.4704 data_time: 0.0003 memory: 1077 2023/03/03 11:01:19 - mmengine - INFO - Epoch(val) [30][60/75] eta: 0:00:47 time: 6.6235 data_time: 0.0004 memory: 1045 2023/03/03 11:01:51 - mmengine - INFO - Epoch(val) [30][70/75] eta: 0:00:16 time: 3.2444 data_time: 0.0005 memory: 1077 2023/03/03 11:02:05 - mmengine - INFO - text score threshold: 0.80, recall: 0.6817, precision: 0.7615, hmean: 0.7194 2023/03/03 11:02:05 - mmengine - INFO - text score threshold: 0.81, recall: 0.6811, precision: 0.7665, hmean: 0.7213 2023/03/03 11:02:05 - mmengine - INFO - text score threshold: 0.82, recall: 0.6806, precision: 0.7711, hmean: 0.7230 2023/03/03 11:02:05 - mmengine - INFO - text score threshold: 0.83, recall: 0.6806, precision: 0.7769, hmean: 0.7256 2023/03/03 11:02:05 - mmengine - INFO - text score threshold: 0.84, recall: 0.6795, precision: 0.7840, hmean: 0.7280 2023/03/03 11:02:05 - mmengine - INFO - text score threshold: 0.85, recall: 0.6773, precision: 0.7885, hmean: 0.7287 2023/03/03 11:02:05 - mmengine - INFO - text score threshold: 0.86, recall: 0.6734, precision: 0.7968, hmean: 0.7299 2023/03/03 11:02:05 - mmengine - INFO - text score threshold: 0.87, recall: 0.6690, precision: 0.8046, hmean: 0.7306 2023/03/03 11:02:05 - mmengine - INFO - text score threshold: 0.88, recall: 0.6668, precision: 0.8089, hmean: 0.7310 2023/03/03 11:02:05 - mmengine - INFO - text score threshold: 0.89, recall: 0.6652, precision: 0.8151, hmean: 0.7325 2023/03/03 11:02:05 - mmengine - INFO - text score threshold: 0.90, recall: 0.6625, precision: 0.8216, hmean: 0.7335 2023/03/03 11:02:05 - mmengine - INFO - text score threshold: 0.91, recall: 0.6564, precision: 0.8248, hmean: 0.7311 2023/03/03 11:02:05 - mmengine - INFO - text score threshold: 0.92, recall: 0.6520, precision: 0.8308, hmean: 0.7306 2023/03/03 11:02:05 - mmengine - INFO - text score threshold: 0.93, recall: 0.6438, precision: 0.8379, hmean: 0.7281 2023/03/03 11:02:05 - mmengine - INFO - text score threshold: 0.94, recall: 0.6312, precision: 0.8468, hmean: 0.7233 2023/03/03 11:02:05 - mmengine - INFO - text score threshold: 0.95, recall: 0.6196, precision: 0.8547, hmean: 0.7184 2023/03/03 11:02:05 - mmengine - INFO - text score threshold: 0.96, recall: 0.6059, precision: 0.8652, hmean: 0.7127 2023/03/03 11:02:05 - mmengine - INFO - text score threshold: 0.97, recall: 0.5950, precision: 0.8742, hmean: 0.7080 2023/03/03 11:02:05 - mmengine - INFO - text score threshold: 0.98, recall: 0.5724, precision: 0.8884, hmean: 0.6963 2023/03/03 11:02:05 - mmengine - INFO - text score threshold: 0.99, recall: 0.5247, precision: 0.9027, hmean: 0.6637 2023/03/03 11:02:14 - mmengine - INFO - text score threshold: 0.80, recall: 0.7629, precision: 0.8831, hmean: 0.8186 2023/03/03 11:02:14 - mmengine - INFO - text score threshold: 0.81, recall: 0.7607, precision: 0.8856, hmean: 0.8184 2023/03/03 11:02:14 - mmengine - INFO - text score threshold: 0.82, recall: 0.7591, precision: 0.8900, hmean: 0.8193 2023/03/03 11:02:14 - mmengine - INFO - text score threshold: 0.83, recall: 0.7558, precision: 0.8913, hmean: 0.8179 2023/03/03 11:02:14 - mmengine - INFO - text score threshold: 0.84, recall: 0.7536, precision: 0.8945, hmean: 0.8180 2023/03/03 11:02:14 - mmengine - INFO - text score threshold: 0.85, recall: 0.7497, precision: 0.8975, hmean: 0.8170 2023/03/03 11:02:14 - mmengine - INFO - text score threshold: 0.86, recall: 0.7409, precision: 0.9000, hmean: 0.8128 2023/03/03 11:02:14 - mmengine - INFO - text score threshold: 0.87, recall: 0.7327, precision: 0.9032, hmean: 0.8091 2023/03/03 11:02:14 - mmengine - INFO - text score threshold: 0.88, recall: 0.7283, precision: 0.9052, hmean: 0.8072 2023/03/03 11:02:14 - mmengine - INFO - text score threshold: 0.89, recall: 0.7250, precision: 0.9092, hmean: 0.8067 2023/03/03 11:02:14 - mmengine - INFO - text score threshold: 0.90, recall: 0.7190, precision: 0.9129, hmean: 0.8044 2023/03/03 11:02:14 - mmengine - INFO - text score threshold: 0.91, recall: 0.7119, precision: 0.9160, hmean: 0.8011 2023/03/03 11:02:14 - mmengine - INFO - text score threshold: 0.92, recall: 0.7042, precision: 0.9177, hmean: 0.7969 2023/03/03 11:02:14 - mmengine - INFO - text score threshold: 0.93, recall: 0.6915, precision: 0.9204, hmean: 0.7897 2023/03/03 11:02:14 - mmengine - INFO - text score threshold: 0.94, recall: 0.6729, precision: 0.9225, hmean: 0.7782 2023/03/03 11:02:14 - mmengine - INFO - text score threshold: 0.95, recall: 0.6570, precision: 0.9258, hmean: 0.7685 2023/03/03 11:02:14 - mmengine - INFO - text score threshold: 0.96, recall: 0.6361, precision: 0.9279, hmean: 0.7548 2023/03/03 11:02:14 - mmengine - INFO - text score threshold: 0.97, recall: 0.6213, precision: 0.9325, hmean: 0.7457 2023/03/03 11:02:14 - mmengine - INFO - text score threshold: 0.98, recall: 0.5928, precision: 0.9383, hmean: 0.7265 2023/03/03 11:02:14 - mmengine - INFO - text score threshold: 0.99, recall: 0.5401, precision: 0.9489, hmean: 0.6884 2023/03/03 11:02:14 - mmengine - INFO - Epoch(val) [30][75/75] none/precision: 0.8216 none/recall: 0.6625 none/hmean: 0.7335 full/precision: 0.8900 full/recall: 0.7591 full/hmean: 0.8193 2023/03/03 11:02:14 - mmengine - INFO - The previous best checkpoint mmocr/projects/SPTS/work_dirs/spts_resnet50_350e_totaltext/best_none/hmean_epoch_10.pth is removed 2023/03/03 11:02:16 - mmengine - INFO - The best checkpoint with 0.7335 none/hmean at 30 epoch is saved to best_none/hmean_epoch_30.pth. 2023/03/03 11:02:22 - mmengine - INFO - Epoch(train) [31][10/79] lr: 1.0000e-06 eta: 1:47:30 time: 0.5198 data_time: 0.0390 memory: 41411 loss: 0.1263 loss_ce: 0.1263 2023/03/03 11:02:26 - mmengine - INFO - Epoch(train) [31][20/79] lr: 1.0000e-06 eta: 1:47:23 time: 0.4330 data_time: 0.0014 memory: 37933 loss: 0.1385 loss_ce: 0.1385 2023/03/03 11:02:30 - mmengine - INFO - Epoch(train) [31][30/79] lr: 1.0000e-06 eta: 1:47:15 time: 0.4326 data_time: 0.0015 memory: 38080 loss: 0.1121 loss_ce: 0.1121 2023/03/03 11:02:35 - mmengine - INFO - Epoch(train) [31][40/79] lr: 1.0000e-06 eta: 1:47:08 time: 0.4368 data_time: 0.0015 memory: 39119 loss: 0.1391 loss_ce: 0.1391 2023/03/03 11:02:40 - mmengine - INFO - Epoch(train) [31][50/79] lr: 1.0000e-06 eta: 1:47:04 time: 0.5030 data_time: 0.0014 memory: 43280 loss: 0.1341 loss_ce: 0.1341 2023/03/03 11:02:45 - mmengine - INFO - Epoch(train) [31][60/79] lr: 1.0000e-06 eta: 1:47:01 time: 0.5038 data_time: 0.0016 memory: 37933 loss: 0.1211 loss_ce: 0.1211 2023/03/03 11:02:49 - mmengine - INFO - Epoch(train) [31][70/79] lr: 1.0000e-06 eta: 1:46:54 time: 0.4458 data_time: 0.0014 memory: 30873 loss: 0.1141 loss_ce: 0.1141 2023/03/03 11:02:53 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:02:58 - mmengine - INFO - Epoch(train) [32][10/79] lr: 1.0000e-06 eta: 1:46:45 time: 0.5225 data_time: 0.0605 memory: 32186 loss: 0.1288 loss_ce: 0.1288 2023/03/03 11:03:03 - mmengine - INFO - Epoch(train) [32][20/79] lr: 1.0000e-06 eta: 1:46:37 time: 0.4365 data_time: 0.0015 memory: 40218 loss: 0.1311 loss_ce: 0.1311 2023/03/03 11:03:07 - mmengine - INFO - Epoch(train) [32][30/79] lr: 1.0000e-06 eta: 1:46:33 time: 0.4860 data_time: 0.0015 memory: 45994 loss: 0.1255 loss_ce: 0.1255 2023/03/03 11:03:13 - mmengine - INFO - Epoch(train) [32][40/79] lr: 1.0000e-06 eta: 1:46:30 time: 0.5169 data_time: 0.0014 memory: 37933 loss: 0.1192 loss_ce: 0.1192 2023/03/03 11:03:17 - mmengine - INFO - Epoch(train) [32][50/79] lr: 1.0000e-06 eta: 1:46:22 time: 0.4112 data_time: 0.0015 memory: 37933 loss: 0.1280 loss_ce: 0.1280 2023/03/03 11:03:22 - mmengine - INFO - Epoch(train) [32][60/79] lr: 1.0000e-06 eta: 1:46:20 time: 0.5305 data_time: 0.0015 memory: 44612 loss: 0.1257 loss_ce: 0.1257 2023/03/03 11:03:27 - mmengine - INFO - Epoch(train) [32][70/79] lr: 1.0000e-06 eta: 1:46:13 time: 0.4512 data_time: 0.0014 memory: 28594 loss: 0.1243 loss_ce: 0.1243 2023/03/03 11:03:31 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:03:37 - mmengine - INFO - Epoch(train) [33][10/79] lr: 1.0000e-06 eta: 1:46:10 time: 0.5663 data_time: 0.0648 memory: 40168 loss: 0.1273 loss_ce: 0.1273 2023/03/03 11:03:42 - mmengine - INFO - Epoch(train) [33][20/79] lr: 1.0000e-06 eta: 1:46:05 time: 0.4708 data_time: 0.0015 memory: 35586 loss: 0.1471 loss_ce: 0.1471 2023/03/03 11:03:46 - mmengine - INFO - Epoch(train) [33][30/79] lr: 1.0000e-06 eta: 1:45:59 time: 0.4580 data_time: 0.0015 memory: 38845 loss: 0.1173 loss_ce: 0.1173 2023/03/03 11:03:51 - mmengine - INFO - Epoch(train) [33][40/79] lr: 1.0000e-06 eta: 1:45:54 time: 0.4653 data_time: 0.0014 memory: 44610 loss: 0.1215 loss_ce: 0.1215 2023/03/03 11:03:56 - mmengine - INFO - Epoch(train) [33][50/79] lr: 1.0000e-06 eta: 1:45:49 time: 0.4883 data_time: 0.0015 memory: 41411 loss: 0.1303 loss_ce: 0.1303 2023/03/03 11:04:01 - mmengine - INFO - Epoch(train) [33][60/79] lr: 1.0000e-06 eta: 1:45:46 time: 0.5047 data_time: 0.0014 memory: 36351 loss: 0.1423 loss_ce: 0.1423 2023/03/03 11:04:05 - mmengine - INFO - Epoch(train) [33][70/79] lr: 1.0000e-06 eta: 1:45:40 time: 0.4712 data_time: 0.0013 memory: 42639 loss: 0.1129 loss_ce: 0.1129 2023/03/03 11:04:09 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:04:14 - mmengine - INFO - Epoch(train) [34][10/79] lr: 1.0000e-06 eta: 1:45:30 time: 0.5474 data_time: 0.0692 memory: 32920 loss: 0.1265 loss_ce: 0.1265 2023/03/03 11:04:19 - mmengine - INFO - Epoch(train) [34][20/79] lr: 1.0000e-06 eta: 1:45:24 time: 0.4580 data_time: 0.0015 memory: 35041 loss: 0.1193 loss_ce: 0.1193 2023/03/03 11:04:24 - mmengine - INFO - Epoch(train) [34][30/79] lr: 1.0000e-06 eta: 1:45:20 time: 0.4992 data_time: 0.0015 memory: 49115 loss: 0.1253 loss_ce: 0.1253 2023/03/03 11:04:28 - mmengine - INFO - Epoch(train) [34][40/79] lr: 1.0000e-06 eta: 1:45:11 time: 0.3887 data_time: 0.0015 memory: 31941 loss: 0.1234 loss_ce: 0.1234 2023/03/03 11:04:33 - mmengine - INFO - Epoch(train) [34][50/79] lr: 1.0000e-06 eta: 1:45:06 time: 0.4792 data_time: 0.0015 memory: 33422 loss: 0.1442 loss_ce: 0.1442 2023/03/03 11:04:38 - mmengine - INFO - Epoch(train) [34][60/79] lr: 1.0000e-06 eta: 1:45:02 time: 0.5028 data_time: 0.0015 memory: 37933 loss: 0.1521 loss_ce: 0.1521 2023/03/03 11:04:42 - mmengine - INFO - Epoch(train) [34][70/79] lr: 1.0000e-06 eta: 1:44:55 time: 0.4262 data_time: 0.0013 memory: 34412 loss: 0.1181 loss_ce: 0.1181 2023/03/03 11:04:46 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:04:51 - mmengine - INFO - Epoch(train) [35][10/79] lr: 1.0000e-06 eta: 1:44:44 time: 0.4475 data_time: 0.0382 memory: 35617 loss: 0.1513 loss_ce: 0.1513 2023/03/03 11:04:55 - mmengine - INFO - Epoch(train) [35][20/79] lr: 1.0000e-06 eta: 1:44:39 time: 0.4764 data_time: 0.0015 memory: 34431 loss: 0.1340 loss_ce: 0.1340 2023/03/03 11:05:00 - mmengine - INFO - Epoch(train) [35][30/79] lr: 1.0000e-06 eta: 1:44:35 time: 0.4929 data_time: 0.0015 memory: 30373 loss: 0.1478 loss_ce: 0.1478 2023/03/03 11:05:05 - mmengine - INFO - Epoch(train) [35][40/79] lr: 1.0000e-06 eta: 1:44:27 time: 0.4287 data_time: 0.0015 memory: 33577 loss: 0.1290 loss_ce: 0.1290 2023/03/03 11:05:09 - mmengine - INFO - Epoch(train) [35][50/79] lr: 1.0000e-06 eta: 1:44:21 time: 0.4433 data_time: 0.0016 memory: 29169 loss: 0.1290 loss_ce: 0.1290 2023/03/03 11:05:14 - mmengine - INFO - Epoch(train) [35][60/79] lr: 1.0000e-06 eta: 1:44:16 time: 0.4764 data_time: 0.0016 memory: 39669 loss: 0.1140 loss_ce: 0.1140 2023/03/03 11:05:19 - mmengine - INFO - Epoch(train) [35][70/79] lr: 1.0000e-06 eta: 1:44:12 time: 0.5082 data_time: 0.0015 memory: 38845 loss: 0.1276 loss_ce: 0.1276 2023/03/03 11:05:23 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:05:29 - mmengine - INFO - Epoch(train) [36][10/79] lr: 1.0000e-06 eta: 1:44:07 time: 0.5744 data_time: 0.0364 memory: 38033 loss: 0.1430 loss_ce: 0.1430 2023/03/03 11:05:34 - mmengine - INFO - Epoch(train) [36][20/79] lr: 1.0000e-06 eta: 1:44:03 time: 0.4940 data_time: 0.0017 memory: 34630 loss: 0.1217 loss_ce: 0.1217 2023/03/03 11:05:39 - mmengine - INFO - Epoch(train) [36][30/79] lr: 1.0000e-06 eta: 1:44:00 time: 0.5196 data_time: 0.0016 memory: 45922 loss: 0.1225 loss_ce: 0.1225 2023/03/03 11:05:44 - mmengine - INFO - Epoch(train) [36][40/79] lr: 1.0000e-06 eta: 1:43:55 time: 0.4611 data_time: 0.0015 memory: 26186 loss: 0.1166 loss_ce: 0.1166 2023/03/03 11:05:48 - mmengine - INFO - Epoch(train) [36][50/79] lr: 1.0000e-06 eta: 1:43:49 time: 0.4645 data_time: 0.0016 memory: 37709 loss: 0.1194 loss_ce: 0.1194 2023/03/03 11:05:53 - mmengine - INFO - Epoch(train) [36][60/79] lr: 1.0000e-06 eta: 1:43:45 time: 0.4826 data_time: 0.0015 memory: 34243 loss: 0.1468 loss_ce: 0.1468 2023/03/03 11:05:57 - mmengine - INFO - Epoch(train) [36][70/79] lr: 1.0000e-06 eta: 1:43:38 time: 0.4375 data_time: 0.0014 memory: 34564 loss: 0.1340 loss_ce: 0.1340 2023/03/03 11:06:01 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:06:06 - mmengine - INFO - Epoch(train) [37][10/79] lr: 1.0000e-06 eta: 1:43:27 time: 0.4885 data_time: 0.0468 memory: 35745 loss: 0.1279 loss_ce: 0.1279 2023/03/03 11:06:11 - mmengine - INFO - Epoch(train) [37][20/79] lr: 1.0000e-06 eta: 1:43:22 time: 0.4675 data_time: 0.0017 memory: 38080 loss: 0.1442 loss_ce: 0.1442 2023/03/03 11:06:16 - mmengine - INFO - Epoch(train) [37][30/79] lr: 1.0000e-06 eta: 1:43:18 time: 0.4995 data_time: 0.0016 memory: 35427 loss: 0.1361 loss_ce: 0.1361 2023/03/03 11:06:21 - mmengine - INFO - Epoch(train) [37][40/79] lr: 1.0000e-06 eta: 1:43:14 time: 0.4965 data_time: 0.0015 memory: 34671 loss: 0.1184 loss_ce: 0.1184 2023/03/03 11:06:25 - mmengine - INFO - Epoch(train) [37][50/79] lr: 1.0000e-06 eta: 1:43:08 time: 0.4566 data_time: 0.0015 memory: 38628 loss: 0.1251 loss_ce: 0.1251 2023/03/03 11:06:30 - mmengine - INFO - Epoch(train) [37][60/79] lr: 1.0000e-06 eta: 1:43:04 time: 0.4848 data_time: 0.0016 memory: 38870 loss: 0.1124 loss_ce: 0.1124 2023/03/03 11:06:36 - mmengine - INFO - Epoch(train) [37][70/79] lr: 1.0000e-06 eta: 1:43:01 time: 0.5296 data_time: 0.0014 memory: 30306 loss: 0.1257 loss_ce: 0.1257 2023/03/03 11:06:40 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:06:45 - mmengine - INFO - Epoch(train) [38][10/79] lr: 1.0000e-06 eta: 1:42:53 time: 0.5335 data_time: 0.0664 memory: 39669 loss: 0.1193 loss_ce: 0.1193 2023/03/03 11:06:49 - mmengine - INFO - Epoch(train) [38][20/79] lr: 1.0000e-06 eta: 1:42:47 time: 0.4376 data_time: 0.0015 memory: 38959 loss: 0.1396 loss_ce: 0.1396 2023/03/03 11:06:54 - mmengine - INFO - Epoch(train) [38][30/79] lr: 1.0000e-06 eta: 1:42:42 time: 0.4794 data_time: 0.0015 memory: 37046 loss: 0.1235 loss_ce: 0.1235 2023/03/03 11:06:58 - mmengine - INFO - Epoch(train) [38][40/79] lr: 1.0000e-06 eta: 1:42:34 time: 0.4214 data_time: 0.0015 memory: 36805 loss: 0.1247 loss_ce: 0.1247 2023/03/03 11:07:03 - mmengine - INFO - Epoch(train) [38][50/79] lr: 1.0000e-06 eta: 1:42:31 time: 0.5013 data_time: 0.0015 memory: 38634 loss: 0.1207 loss_ce: 0.1207 2023/03/03 11:07:08 - mmengine - INFO - Epoch(train) [38][60/79] lr: 1.0000e-06 eta: 1:42:24 time: 0.4257 data_time: 0.0016 memory: 32022 loss: 0.1356 loss_ce: 0.1356 2023/03/03 11:07:14 - mmengine - INFO - Epoch(train) [38][70/79] lr: 1.0000e-06 eta: 1:42:25 time: 0.6257 data_time: 0.0014 memory: 51354 loss: 0.1290 loss_ce: 0.1290 2023/03/03 11:07:17 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:07:18 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:07:24 - mmengine - INFO - Epoch(train) [39][10/79] lr: 1.0000e-06 eta: 1:42:19 time: 0.5459 data_time: 0.0557 memory: 36634 loss: 0.1283 loss_ce: 0.1283 2023/03/03 11:07:29 - mmengine - INFO - Epoch(train) [39][20/79] lr: 1.0000e-06 eta: 1:42:15 time: 0.4893 data_time: 0.0017 memory: 33945 loss: 0.1409 loss_ce: 0.1409 2023/03/03 11:07:33 - mmengine - INFO - Epoch(train) [39][30/79] lr: 1.0000e-06 eta: 1:42:10 time: 0.4877 data_time: 0.0017 memory: 39770 loss: 0.1271 loss_ce: 0.1271 2023/03/03 11:07:38 - mmengine - INFO - Epoch(train) [39][40/79] lr: 1.0000e-06 eta: 1:42:05 time: 0.4745 data_time: 0.0016 memory: 37876 loss: 0.1361 loss_ce: 0.1361 2023/03/03 11:07:43 - mmengine - INFO - Epoch(train) [39][50/79] lr: 1.0000e-06 eta: 1:41:59 time: 0.4558 data_time: 0.0017 memory: 37933 loss: 0.1383 loss_ce: 0.1383 2023/03/03 11:07:47 - mmengine - INFO - Epoch(train) [39][60/79] lr: 1.0000e-06 eta: 1:41:53 time: 0.4408 data_time: 0.0017 memory: 39670 loss: 0.1378 loss_ce: 0.1378 2023/03/03 11:07:53 - mmengine - INFO - Epoch(train) [39][70/79] lr: 1.0000e-06 eta: 1:41:51 time: 0.5429 data_time: 0.0015 memory: 42157 loss: 0.1357 loss_ce: 0.1357 2023/03/03 11:07:56 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:08:01 - mmengine - INFO - Epoch(train) [40][10/79] lr: 1.0000e-06 eta: 1:41:38 time: 0.4673 data_time: 0.0546 memory: 36494 loss: 0.1402 loss_ce: 0.1402 2023/03/03 11:08:05 - mmengine - INFO - Epoch(train) [40][20/79] lr: 1.0000e-06 eta: 1:41:32 time: 0.4495 data_time: 0.0017 memory: 32587 loss: 0.1197 loss_ce: 0.1197 2023/03/03 11:08:10 - mmengine - INFO - Epoch(train) [40][30/79] lr: 1.0000e-06 eta: 1:41:28 time: 0.4940 data_time: 0.0016 memory: 39670 loss: 0.1240 loss_ce: 0.1240 2023/03/03 11:08:15 - mmengine - INFO - Epoch(train) [40][40/79] lr: 1.0000e-06 eta: 1:41:23 time: 0.4803 data_time: 0.0015 memory: 38675 loss: 0.1257 loss_ce: 0.1257 2023/03/03 11:08:20 - mmengine - INFO - Epoch(train) [40][50/79] lr: 1.0000e-06 eta: 1:41:17 time: 0.4594 data_time: 0.0018 memory: 28181 loss: 0.1360 loss_ce: 0.1360 2023/03/03 11:08:24 - mmengine - INFO - Epoch(train) [40][60/79] lr: 1.0000e-06 eta: 1:41:12 time: 0.4582 data_time: 0.0015 memory: 27522 loss: 0.1310 loss_ce: 0.1310 2023/03/03 11:08:29 - mmengine - INFO - Epoch(train) [40][70/79] lr: 1.0000e-06 eta: 1:41:07 time: 0.4867 data_time: 0.0016 memory: 35638 loss: 0.1323 loss_ce: 0.1323 2023/03/03 11:08:33 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:08:46 - mmengine - INFO - Epoch(val) [40][10/75] eta: 0:01:22 time: 1.2755 data_time: 0.0040 memory: 41714 2023/03/03 11:09:27 - mmengine - INFO - Epoch(val) [40][20/75] eta: 0:02:26 time: 4.0652 data_time: 0.0005 memory: 1077 2023/03/03 11:09:51 - mmengine - INFO - Epoch(val) [40][30/75] eta: 0:01:55 time: 2.3708 data_time: 0.0005 memory: 1020 2023/03/03 11:10:07 - mmengine - INFO - Epoch(val) [40][40/75] eta: 0:01:21 time: 1.6476 data_time: 0.0007 memory: 1019 2023/03/03 11:10:22 - mmengine - INFO - Epoch(val) [40][50/75] eta: 0:00:54 time: 1.4563 data_time: 0.0006 memory: 1077 2023/03/03 11:11:06 - mmengine - INFO - Epoch(val) [40][60/75] eta: 0:00:38 time: 4.3931 data_time: 0.0005 memory: 1045 2023/03/03 11:11:40 - mmengine - INFO - Epoch(val) [40][70/75] eta: 0:00:13 time: 3.4014 data_time: 0.0007 memory: 1077 2023/03/03 11:11:53 - mmengine - INFO - text score threshold: 0.80, recall: 0.6855, precision: 0.7597, hmean: 0.7207 2023/03/03 11:11:53 - mmengine - INFO - text score threshold: 0.81, recall: 0.6844, precision: 0.7646, hmean: 0.7223 2023/03/03 11:11:53 - mmengine - INFO - text score threshold: 0.82, recall: 0.6828, precision: 0.7684, hmean: 0.7230 2023/03/03 11:11:53 - mmengine - INFO - text score threshold: 0.83, recall: 0.6806, precision: 0.7726, hmean: 0.7237 2023/03/03 11:11:53 - mmengine - INFO - text score threshold: 0.84, recall: 0.6778, precision: 0.7802, hmean: 0.7254 2023/03/03 11:11:53 - mmengine - INFO - text score threshold: 0.85, recall: 0.6762, precision: 0.7852, hmean: 0.7266 2023/03/03 11:11:53 - mmengine - INFO - text score threshold: 0.86, recall: 0.6729, precision: 0.7899, hmean: 0.7267 2023/03/03 11:11:53 - mmengine - INFO - text score threshold: 0.87, recall: 0.6696, precision: 0.7974, hmean: 0.7279 2023/03/03 11:11:53 - mmengine - INFO - text score threshold: 0.88, recall: 0.6668, precision: 0.8020, hmean: 0.7282 2023/03/03 11:11:53 - mmengine - INFO - text score threshold: 0.89, recall: 0.6652, precision: 0.8102, hmean: 0.7306 2023/03/03 11:11:53 - mmengine - INFO - text score threshold: 0.90, recall: 0.6592, precision: 0.8165, hmean: 0.7294 2023/03/03 11:11:53 - mmengine - INFO - text score threshold: 0.91, recall: 0.6537, precision: 0.8237, hmean: 0.7289 2023/03/03 11:11:53 - mmengine - INFO - text score threshold: 0.92, recall: 0.6487, precision: 0.8295, hmean: 0.7281 2023/03/03 11:11:53 - mmengine - INFO - text score threshold: 0.93, recall: 0.6416, precision: 0.8386, hmean: 0.7270 2023/03/03 11:11:53 - mmengine - INFO - text score threshold: 0.94, recall: 0.6350, precision: 0.8458, hmean: 0.7254 2023/03/03 11:11:53 - mmengine - INFO - text score threshold: 0.95, recall: 0.6224, precision: 0.8526, hmean: 0.7195 2023/03/03 11:11:53 - mmengine - INFO - text score threshold: 0.96, recall: 0.6081, precision: 0.8670, hmean: 0.7148 2023/03/03 11:11:53 - mmengine - INFO - text score threshold: 0.97, recall: 0.5928, precision: 0.8788, hmean: 0.7080 2023/03/03 11:11:53 - mmengine - INFO - text score threshold: 0.98, recall: 0.5730, precision: 0.8908, hmean: 0.6974 2023/03/03 11:11:53 - mmengine - INFO - text score threshold: 0.99, recall: 0.5324, precision: 0.9057, hmean: 0.6706 2023/03/03 11:12:03 - mmengine - INFO - text score threshold: 0.80, recall: 0.7667, precision: 0.8831, hmean: 0.8208 2023/03/03 11:12:03 - mmengine - INFO - text score threshold: 0.81, recall: 0.7645, precision: 0.8844, hmean: 0.8201 2023/03/03 11:12:03 - mmengine - INFO - text score threshold: 0.82, recall: 0.7623, precision: 0.8875, hmean: 0.8202 2023/03/03 11:12:03 - mmengine - INFO - text score threshold: 0.83, recall: 0.7580, precision: 0.8881, hmean: 0.8179 2023/03/03 11:12:03 - mmengine - INFO - text score threshold: 0.84, recall: 0.7519, precision: 0.8919, hmean: 0.8160 2023/03/03 11:12:03 - mmengine - INFO - text score threshold: 0.85, recall: 0.7481, precision: 0.8944, hmean: 0.8147 2023/03/03 11:12:03 - mmengine - INFO - text score threshold: 0.86, recall: 0.7426, precision: 0.8960, hmean: 0.8121 2023/03/03 11:12:03 - mmengine - INFO - text score threshold: 0.87, recall: 0.7371, precision: 0.8989, hmean: 0.8100 2023/03/03 11:12:03 - mmengine - INFO - text score threshold: 0.88, recall: 0.7327, precision: 0.9026, hmean: 0.8088 2023/03/03 11:12:03 - mmengine - INFO - text score threshold: 0.89, recall: 0.7283, precision: 0.9064, hmean: 0.8077 2023/03/03 11:12:03 - mmengine - INFO - text score threshold: 0.90, recall: 0.7173, precision: 0.9076, hmean: 0.8013 2023/03/03 11:12:03 - mmengine - INFO - text score threshold: 0.91, recall: 0.7097, precision: 0.9131, hmean: 0.7986 2023/03/03 11:12:03 - mmengine - INFO - text score threshold: 0.92, recall: 0.7031, precision: 0.9170, hmean: 0.7959 2023/03/03 11:12:03 - mmengine - INFO - text score threshold: 0.93, recall: 0.6899, precision: 0.9182, hmean: 0.7878 2023/03/03 11:12:03 - mmengine - INFO - text score threshold: 0.94, recall: 0.6811, precision: 0.9241, hmean: 0.7842 2023/03/03 11:12:03 - mmengine - INFO - text score threshold: 0.95, recall: 0.6630, precision: 0.9250, hmean: 0.7724 2023/03/03 11:12:03 - mmengine - INFO - text score threshold: 0.96, recall: 0.6422, precision: 0.9315, hmean: 0.7602 2023/03/03 11:12:03 - mmengine - INFO - text score threshold: 0.97, recall: 0.6202, precision: 0.9354, hmean: 0.7459 2023/03/03 11:12:03 - mmengine - INFO - text score threshold: 0.98, recall: 0.5944, precision: 0.9393, hmean: 0.7281 2023/03/03 11:12:03 - mmengine - INFO - text score threshold: 0.99, recall: 0.5483, precision: 0.9469, hmean: 0.6945 2023/03/03 11:12:03 - mmengine - INFO - Epoch(val) [40][75/75] none/precision: 0.8102 none/recall: 0.6652 none/hmean: 0.7306 full/precision: 0.8831 full/recall: 0.7667 full/hmean: 0.8208 2023/03/03 11:12:08 - mmengine - INFO - Epoch(train) [41][10/79] lr: 1.0000e-06 eta: 1:41:01 time: 0.5476 data_time: 0.0771 memory: 38335 loss: 0.1343 loss_ce: 0.1343 2023/03/03 11:12:13 - mmengine - INFO - Epoch(train) [41][20/79] lr: 1.0000e-06 eta: 1:40:55 time: 0.4566 data_time: 0.0017 memory: 31408 loss: 0.1259 loss_ce: 0.1259 2023/03/03 11:12:17 - mmengine - INFO - Epoch(train) [41][30/79] lr: 1.0000e-06 eta: 1:40:49 time: 0.4430 data_time: 0.0015 memory: 26127 loss: 0.1126 loss_ce: 0.1126 2023/03/03 11:12:22 - mmengine - INFO - Epoch(train) [41][40/79] lr: 1.0000e-06 eta: 1:40:43 time: 0.4533 data_time: 0.0015 memory: 39121 loss: 0.1324 loss_ce: 0.1324 2023/03/03 11:12:26 - mmengine - INFO - Epoch(train) [41][50/79] lr: 1.0000e-06 eta: 1:40:36 time: 0.4185 data_time: 0.0015 memory: 38080 loss: 0.1395 loss_ce: 0.1395 2023/03/03 11:12:31 - mmengine - INFO - Epoch(train) [41][60/79] lr: 1.0000e-06 eta: 1:40:31 time: 0.4895 data_time: 0.0015 memory: 36502 loss: 0.1373 loss_ce: 0.1373 2023/03/03 11:12:35 - mmengine - INFO - Epoch(train) [41][70/79] lr: 1.0000e-06 eta: 1:40:26 time: 0.4572 data_time: 0.0013 memory: 39482 loss: 0.1194 loss_ce: 0.1194 2023/03/03 11:12:39 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:12:45 - mmengine - INFO - Epoch(train) [42][10/79] lr: 1.0000e-06 eta: 1:40:18 time: 0.5537 data_time: 0.0573 memory: 31026 loss: 0.1493 loss_ce: 0.1493 2023/03/03 11:12:50 - mmengine - INFO - Epoch(train) [42][20/79] lr: 1.0000e-06 eta: 1:40:13 time: 0.4930 data_time: 0.0016 memory: 32270 loss: 0.1291 loss_ce: 0.1291 2023/03/03 11:12:54 - mmengine - INFO - Epoch(train) [42][30/79] lr: 1.0000e-06 eta: 1:40:07 time: 0.4368 data_time: 0.0016 memory: 37933 loss: 0.1368 loss_ce: 0.1368 2023/03/03 11:12:58 - mmengine - INFO - Epoch(train) [42][40/79] lr: 1.0000e-06 eta: 1:40:00 time: 0.4212 data_time: 0.0016 memory: 40816 loss: 0.1129 loss_ce: 0.1129 2023/03/03 11:13:03 - mmengine - INFO - Epoch(train) [42][50/79] lr: 1.0000e-06 eta: 1:39:54 time: 0.4440 data_time: 0.0016 memory: 33886 loss: 0.1240 loss_ce: 0.1240 2023/03/03 11:13:07 - mmengine - INFO - Epoch(train) [42][60/79] lr: 1.0000e-06 eta: 1:39:48 time: 0.4432 data_time: 0.0015 memory: 37933 loss: 0.1188 loss_ce: 0.1188 2023/03/03 11:13:12 - mmengine - INFO - Epoch(train) [42][70/79] lr: 1.0000e-06 eta: 1:39:41 time: 0.4330 data_time: 0.0016 memory: 29409 loss: 0.1299 loss_ce: 0.1299 2023/03/03 11:13:16 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:13:21 - mmengine - INFO - Epoch(train) [43][10/79] lr: 1.0000e-06 eta: 1:39:35 time: 0.5329 data_time: 0.0566 memory: 48940 loss: 0.1302 loss_ce: 0.1302 2023/03/03 11:13:26 - mmengine - INFO - Epoch(train) [43][20/79] lr: 1.0000e-06 eta: 1:39:29 time: 0.4573 data_time: 0.0016 memory: 33850 loss: 0.1199 loss_ce: 0.1199 2023/03/03 11:13:31 - mmengine - INFO - Epoch(train) [43][30/79] lr: 1.0000e-06 eta: 1:39:23 time: 0.4499 data_time: 0.0015 memory: 32402 loss: 0.1318 loss_ce: 0.1318 2023/03/03 11:13:35 - mmengine - INFO - Epoch(train) [43][40/79] lr: 1.0000e-06 eta: 1:39:17 time: 0.4318 data_time: 0.0015 memory: 39670 loss: 0.1243 loss_ce: 0.1243 2023/03/03 11:13:39 - mmengine - INFO - Epoch(train) [43][50/79] lr: 1.0000e-06 eta: 1:39:11 time: 0.4543 data_time: 0.0017 memory: 33244 loss: 0.1242 loss_ce: 0.1242 2023/03/03 11:13:44 - mmengine - INFO - Epoch(train) [43][60/79] lr: 1.0000e-06 eta: 1:39:04 time: 0.4259 data_time: 0.0015 memory: 33886 loss: 0.1263 loss_ce: 0.1263 2023/03/03 11:13:48 - mmengine - INFO - Epoch(train) [43][70/79] lr: 1.0000e-06 eta: 1:38:59 time: 0.4657 data_time: 0.0012 memory: 38763 loss: 0.1387 loss_ce: 0.1387 2023/03/03 11:13:53 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:13:58 - mmengine - INFO - Epoch(train) [44][10/79] lr: 1.0000e-06 eta: 1:38:54 time: 0.5669 data_time: 0.0691 memory: 42637 loss: 0.1240 loss_ce: 0.1240 2023/03/03 11:14:03 - mmengine - INFO - Epoch(train) [44][20/79] lr: 1.0000e-06 eta: 1:38:49 time: 0.4846 data_time: 0.0015 memory: 35494 loss: 0.1186 loss_ce: 0.1186 2023/03/03 11:14:08 - mmengine - INFO - Epoch(train) [44][30/79] lr: 1.0000e-06 eta: 1:38:45 time: 0.4944 data_time: 0.0015 memory: 40173 loss: 0.1266 loss_ce: 0.1266 2023/03/03 11:14:13 - mmengine - INFO - Epoch(train) [44][40/79] lr: 1.0000e-06 eta: 1:38:39 time: 0.4330 data_time: 0.0015 memory: 45646 loss: 0.1098 loss_ce: 0.1098 2023/03/03 11:14:17 - mmengine - INFO - Epoch(train) [44][50/79] lr: 1.0000e-06 eta: 1:38:34 time: 0.4675 data_time: 0.0016 memory: 35929 loss: 0.1159 loss_ce: 0.1159 2023/03/03 11:14:22 - mmengine - INFO - Epoch(train) [44][60/79] lr: 1.0000e-06 eta: 1:38:28 time: 0.4617 data_time: 0.0016 memory: 40522 loss: 0.1315 loss_ce: 0.1315 2023/03/03 11:14:26 - mmengine - INFO - Epoch(train) [44][70/79] lr: 1.0000e-06 eta: 1:38:22 time: 0.4390 data_time: 0.0015 memory: 37933 loss: 0.1143 loss_ce: 0.1143 2023/03/03 11:14:30 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:14:36 - mmengine - INFO - Epoch(train) [45][10/79] lr: 1.0000e-06 eta: 1:38:15 time: 0.5959 data_time: 0.0411 memory: 44428 loss: 0.1069 loss_ce: 0.1069 2023/03/03 11:14:41 - mmengine - INFO - Epoch(train) [45][20/79] lr: 1.0000e-06 eta: 1:38:10 time: 0.4628 data_time: 0.0015 memory: 45994 loss: 0.1276 loss_ce: 0.1276 2023/03/03 11:14:45 - mmengine - INFO - Epoch(train) [45][30/79] lr: 1.0000e-06 eta: 1:38:04 time: 0.4601 data_time: 0.0015 memory: 38080 loss: 0.1278 loss_ce: 0.1278 2023/03/03 11:14:50 - mmengine - INFO - Epoch(train) [45][40/79] lr: 1.0000e-06 eta: 1:37:59 time: 0.4605 data_time: 0.0015 memory: 38846 loss: 0.1267 loss_ce: 0.1267 2023/03/03 11:14:54 - mmengine - INFO - Epoch(train) [45][50/79] lr: 1.0000e-06 eta: 1:37:53 time: 0.4536 data_time: 0.0015 memory: 30080 loss: 0.1280 loss_ce: 0.1280 2023/03/03 11:14:59 - mmengine - INFO - Epoch(train) [45][60/79] lr: 1.0000e-06 eta: 1:37:48 time: 0.4784 data_time: 0.0014 memory: 46502 loss: 0.1117 loss_ce: 0.1117 2023/03/03 11:15:03 - mmengine - INFO - Epoch(train) [45][70/79] lr: 1.0000e-06 eta: 1:37:41 time: 0.4188 data_time: 0.0013 memory: 38846 loss: 0.1438 loss_ce: 0.1438 2023/03/03 11:15:07 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:15:13 - mmengine - INFO - Epoch(train) [46][10/79] lr: 1.0000e-06 eta: 1:37:33 time: 0.5486 data_time: 0.0661 memory: 36661 loss: 0.1347 loss_ce: 0.1347 2023/03/03 11:15:18 - mmengine - INFO - Epoch(train) [46][20/79] lr: 1.0000e-06 eta: 1:37:30 time: 0.5236 data_time: 0.0014 memory: 37933 loss: 0.1321 loss_ce: 0.1321 2023/03/03 11:15:23 - mmengine - INFO - Epoch(train) [46][30/79] lr: 1.0000e-06 eta: 1:37:26 time: 0.4929 data_time: 0.0015 memory: 39148 loss: 0.1339 loss_ce: 0.1339 2023/03/03 11:15:27 - mmengine - INFO - Epoch(train) [46][40/79] lr: 1.0000e-06 eta: 1:37:20 time: 0.4442 data_time: 0.0017 memory: 27710 loss: 0.1300 loss_ce: 0.1300 2023/03/03 11:15:32 - mmengine - INFO - Epoch(train) [46][50/79] lr: 1.0000e-06 eta: 1:37:16 time: 0.5092 data_time: 0.0015 memory: 38080 loss: 0.1426 loss_ce: 0.1426 2023/03/03 11:15:37 - mmengine - INFO - Epoch(train) [46][60/79] lr: 1.0000e-06 eta: 1:37:11 time: 0.4621 data_time: 0.0016 memory: 38587 loss: 0.1284 loss_ce: 0.1284 2023/03/03 11:15:42 - mmengine - INFO - Epoch(train) [46][70/79] lr: 1.0000e-06 eta: 1:37:06 time: 0.4612 data_time: 0.0013 memory: 37933 loss: 0.1405 loss_ce: 0.1405 2023/03/03 11:15:45 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:15:51 - mmengine - INFO - Epoch(train) [47][10/79] lr: 1.0000e-06 eta: 1:36:57 time: 0.5736 data_time: 0.0417 memory: 38080 loss: 0.1151 loss_ce: 0.1151 2023/03/03 11:15:56 - mmengine - INFO - Epoch(train) [47][20/79] lr: 1.0000e-06 eta: 1:36:52 time: 0.4968 data_time: 0.0016 memory: 33521 loss: 0.1384 loss_ce: 0.1384 2023/03/03 11:16:00 - mmengine - INFO - Epoch(train) [47][30/79] lr: 1.0000e-06 eta: 1:36:45 time: 0.3900 data_time: 0.0015 memory: 28419 loss: 0.1308 loss_ce: 0.1308 2023/03/03 11:16:04 - mmengine - INFO - Epoch(train) [47][40/79] lr: 1.0000e-06 eta: 1:36:40 time: 0.4667 data_time: 0.0015 memory: 36483 loss: 0.1257 loss_ce: 0.1257 2023/03/03 11:16:09 - mmengine - INFO - Epoch(train) [47][50/79] lr: 1.0000e-06 eta: 1:36:35 time: 0.4923 data_time: 0.0015 memory: 39392 loss: 0.1290 loss_ce: 0.1290 2023/03/03 11:16:14 - mmengine - INFO - Epoch(train) [47][60/79] lr: 1.0000e-06 eta: 1:36:29 time: 0.4300 data_time: 0.0015 memory: 29466 loss: 0.1192 loss_ce: 0.1192 2023/03/03 11:16:19 - mmengine - INFO - Epoch(train) [47][70/79] lr: 1.0000e-06 eta: 1:36:28 time: 0.5831 data_time: 0.0013 memory: 38332 loss: 0.1168 loss_ce: 0.1168 2023/03/03 11:16:23 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:16:28 - mmengine - INFO - Epoch(train) [48][10/79] lr: 1.0000e-06 eta: 1:36:18 time: 0.5175 data_time: 0.0301 memory: 39148 loss: 0.1227 loss_ce: 0.1227 2023/03/03 11:16:33 - mmengine - INFO - Epoch(train) [48][20/79] lr: 1.0000e-06 eta: 1:36:11 time: 0.4284 data_time: 0.0014 memory: 38587 loss: 0.1286 loss_ce: 0.1286 2023/03/03 11:16:37 - mmengine - INFO - Epoch(train) [48][30/79] lr: 1.0000e-06 eta: 1:36:06 time: 0.4632 data_time: 0.0015 memory: 42017 loss: 0.1198 loss_ce: 0.1198 2023/03/03 11:16:42 - mmengine - INFO - Epoch(train) [48][40/79] lr: 1.0000e-06 eta: 1:36:02 time: 0.4915 data_time: 0.0015 memory: 32402 loss: 0.1227 loss_ce: 0.1227 2023/03/03 11:16:47 - mmengine - INFO - Epoch(train) [48][50/79] lr: 1.0000e-06 eta: 1:35:58 time: 0.5036 data_time: 0.0015 memory: 26417 loss: 0.1378 loss_ce: 0.1378 2023/03/03 11:16:52 - mmengine - INFO - Epoch(train) [48][60/79] lr: 1.0000e-06 eta: 1:35:52 time: 0.4409 data_time: 0.0015 memory: 38787 loss: 0.1124 loss_ce: 0.1124 2023/03/03 11:16:56 - mmengine - INFO - Epoch(train) [48][70/79] lr: 1.0000e-06 eta: 1:35:47 time: 0.4602 data_time: 0.0013 memory: 34635 loss: 0.1330 loss_ce: 0.1330 2023/03/03 11:17:01 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:17:06 - mmengine - INFO - Epoch(train) [49][10/79] lr: 1.0000e-06 eta: 1:35:40 time: 0.5147 data_time: 0.0512 memory: 36526 loss: 0.1265 loss_ce: 0.1265 2023/03/03 11:17:11 - mmengine - INFO - Epoch(train) [49][20/79] lr: 1.0000e-06 eta: 1:35:34 time: 0.4572 data_time: 0.0014 memory: 25913 loss: 0.1232 loss_ce: 0.1232 2023/03/03 11:17:15 - mmengine - INFO - Epoch(train) [49][30/79] lr: 1.0000e-06 eta: 1:35:27 time: 0.3970 data_time: 0.0015 memory: 32525 loss: 0.1183 loss_ce: 0.1183 2023/03/03 11:17:19 - mmengine - INFO - Epoch(train) [49][40/79] lr: 1.0000e-06 eta: 1:35:22 time: 0.4827 data_time: 0.0015 memory: 37933 loss: 0.1359 loss_ce: 0.1359 2023/03/03 11:17:24 - mmengine - INFO - Epoch(train) [49][50/79] lr: 1.0000e-06 eta: 1:35:17 time: 0.4544 data_time: 0.0015 memory: 30770 loss: 0.1306 loss_ce: 0.1306 2023/03/03 11:17:29 - mmengine - INFO - Epoch(train) [49][60/79] lr: 1.0000e-06 eta: 1:35:12 time: 0.4971 data_time: 0.0015 memory: 33925 loss: 0.1359 loss_ce: 0.1359 2023/03/03 11:17:34 - mmengine - INFO - Epoch(train) [49][70/79] lr: 1.0000e-06 eta: 1:35:09 time: 0.5056 data_time: 0.0013 memory: 40578 loss: 0.1197 loss_ce: 0.1197 2023/03/03 11:17:38 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:17:43 - mmengine - INFO - Epoch(train) [50][10/79] lr: 1.0000e-06 eta: 1:35:01 time: 0.5782 data_time: 0.0485 memory: 34960 loss: 0.1308 loss_ce: 0.1308 2023/03/03 11:17:48 - mmengine - INFO - Epoch(train) [50][20/79] lr: 1.0000e-06 eta: 1:34:54 time: 0.4229 data_time: 0.0015 memory: 32918 loss: 0.1369 loss_ce: 0.1369 2023/03/03 11:17:52 - mmengine - INFO - Epoch(train) [50][30/79] lr: 1.0000e-06 eta: 1:34:48 time: 0.4314 data_time: 0.0015 memory: 38080 loss: 0.1259 loss_ce: 0.1259 2023/03/03 11:17:57 - mmengine - INFO - Epoch(train) [50][40/79] lr: 1.0000e-06 eta: 1:34:44 time: 0.5163 data_time: 0.0016 memory: 37343 loss: 0.1225 loss_ce: 0.1225 2023/03/03 11:18:02 - mmengine - INFO - Epoch(train) [50][50/79] lr: 1.0000e-06 eta: 1:34:40 time: 0.5056 data_time: 0.0019 memory: 34742 loss: 0.1324 loss_ce: 0.1324 2023/03/03 11:18:07 - mmengine - INFO - Epoch(train) [50][60/79] lr: 1.0000e-06 eta: 1:34:35 time: 0.4782 data_time: 0.0021 memory: 38498 loss: 0.1170 loss_ce: 0.1170 2023/03/03 11:18:12 - mmengine - INFO - Epoch(train) [50][70/79] lr: 1.0000e-06 eta: 1:34:32 time: 0.5066 data_time: 0.0013 memory: 36795 loss: 0.1200 loss_ce: 0.1200 2023/03/03 11:18:16 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:18:28 - mmengine - INFO - Epoch(val) [50][10/75] eta: 0:01:19 time: 1.2220 data_time: 0.0035 memory: 28901 2023/03/03 11:19:29 - mmengine - INFO - Epoch(val) [50][20/75] eta: 0:03:22 time: 6.1254 data_time: 0.0005 memory: 1077 2023/03/03 11:19:51 - mmengine - INFO - Epoch(val) [50][30/75] eta: 0:02:22 time: 2.1494 data_time: 0.0003 memory: 1020 2023/03/03 11:20:08 - mmengine - INFO - Epoch(val) [50][40/75] eta: 0:01:37 time: 1.6976 data_time: 0.0003 memory: 1019 2023/03/03 11:20:22 - mmengine - INFO - Epoch(val) [50][50/75] eta: 0:01:03 time: 1.4076 data_time: 0.0003 memory: 1077 2023/03/03 11:21:07 - mmengine - INFO - Epoch(val) [50][60/75] eta: 0:00:42 time: 4.5090 data_time: 0.0007 memory: 1045 2023/03/03 11:21:38 - mmengine - INFO - Epoch(val) [50][70/75] eta: 0:00:14 time: 3.1209 data_time: 0.0005 memory: 1077 2023/03/03 11:21:52 - mmengine - INFO - text score threshold: 0.80, recall: 0.6877, precision: 0.7622, hmean: 0.7230 2023/03/03 11:21:52 - mmengine - INFO - text score threshold: 0.81, recall: 0.6872, precision: 0.7672, hmean: 0.7250 2023/03/03 11:21:52 - mmengine - INFO - text score threshold: 0.82, recall: 0.6855, precision: 0.7700, hmean: 0.7253 2023/03/03 11:21:52 - mmengine - INFO - text score threshold: 0.83, recall: 0.6855, precision: 0.7772, hmean: 0.7285 2023/03/03 11:21:52 - mmengine - INFO - text score threshold: 0.84, recall: 0.6822, precision: 0.7837, hmean: 0.7295 2023/03/03 11:21:52 - mmengine - INFO - text score threshold: 0.85, recall: 0.6800, precision: 0.7887, hmean: 0.7303 2023/03/03 11:21:52 - mmengine - INFO - text score threshold: 0.86, recall: 0.6778, precision: 0.7968, hmean: 0.7325 2023/03/03 11:21:52 - mmengine - INFO - text score threshold: 0.87, recall: 0.6751, precision: 0.8013, hmean: 0.7328 2023/03/03 11:21:52 - mmengine - INFO - text score threshold: 0.88, recall: 0.6729, precision: 0.8066, hmean: 0.7337 2023/03/03 11:21:52 - mmengine - INFO - text score threshold: 0.89, recall: 0.6674, precision: 0.8134, hmean: 0.7332 2023/03/03 11:21:52 - mmengine - INFO - text score threshold: 0.90, recall: 0.6658, precision: 0.8201, hmean: 0.7349 2023/03/03 11:21:52 - mmengine - INFO - text score threshold: 0.91, recall: 0.6603, precision: 0.8262, hmean: 0.7340 2023/03/03 11:21:52 - mmengine - INFO - text score threshold: 0.92, recall: 0.6515, precision: 0.8307, hmean: 0.7302 2023/03/03 11:21:52 - mmengine - INFO - text score threshold: 0.93, recall: 0.6438, precision: 0.8397, hmean: 0.7288 2023/03/03 11:21:52 - mmengine - INFO - text score threshold: 0.94, recall: 0.6334, precision: 0.8454, hmean: 0.7242 2023/03/03 11:21:52 - mmengine - INFO - text score threshold: 0.95, recall: 0.6240, precision: 0.8575, hmean: 0.7224 2023/03/03 11:21:52 - mmengine - INFO - text score threshold: 0.96, recall: 0.6092, precision: 0.8658, hmean: 0.7152 2023/03/03 11:21:52 - mmengine - INFO - text score threshold: 0.97, recall: 0.5982, precision: 0.8790, hmean: 0.7120 2023/03/03 11:21:52 - mmengine - INFO - text score threshold: 0.98, recall: 0.5757, precision: 0.8912, hmean: 0.6996 2023/03/03 11:21:52 - mmengine - INFO - text score threshold: 0.99, recall: 0.5379, precision: 0.9024, hmean: 0.6740 2023/03/03 11:22:01 - mmengine - INFO - text score threshold: 0.80, recall: 0.7689, precision: 0.8817, hmean: 0.8215 2023/03/03 11:22:01 - mmengine - INFO - text score threshold: 0.81, recall: 0.7678, precision: 0.8843, hmean: 0.8220 2023/03/03 11:22:01 - mmengine - INFO - text score threshold: 0.82, recall: 0.7645, precision: 0.8856, hmean: 0.8206 2023/03/03 11:22:01 - mmengine - INFO - text score threshold: 0.83, recall: 0.7613, precision: 0.8885, hmean: 0.8200 2023/03/03 11:22:01 - mmengine - INFO - text score threshold: 0.84, recall: 0.7558, precision: 0.8918, hmean: 0.8182 2023/03/03 11:22:01 - mmengine - INFO - text score threshold: 0.85, recall: 0.7519, precision: 0.8931, hmean: 0.8164 2023/03/03 11:22:01 - mmengine - INFO - text score threshold: 0.86, recall: 0.7464, precision: 0.8965, hmean: 0.8146 2023/03/03 11:22:01 - mmengine - INFO - text score threshold: 0.87, recall: 0.7404, precision: 0.8975, hmean: 0.8114 2023/03/03 11:22:01 - mmengine - INFO - text score threshold: 0.88, recall: 0.7366, precision: 0.9019, hmean: 0.8109 2023/03/03 11:22:01 - mmengine - INFO - text score threshold: 0.89, recall: 0.7272, precision: 0.9051, hmean: 0.8065 2023/03/03 11:22:01 - mmengine - INFO - text score threshold: 0.90, recall: 0.7212, precision: 0.9068, hmean: 0.8034 2023/03/03 11:22:01 - mmengine - INFO - text score threshold: 0.91, recall: 0.7151, precision: 0.9112, hmean: 0.8014 2023/03/03 11:22:01 - mmengine - INFO - text score threshold: 0.92, recall: 0.7053, precision: 0.9159, hmean: 0.7969 2023/03/03 11:22:01 - mmengine - INFO - text score threshold: 0.93, recall: 0.6910, precision: 0.9183, hmean: 0.7886 2023/03/03 11:22:01 - mmengine - INFO - text score threshold: 0.94, recall: 0.6773, precision: 0.9209, hmean: 0.7805 2023/03/03 11:22:01 - mmengine - INFO - text score threshold: 0.95, recall: 0.6619, precision: 0.9263, hmean: 0.7721 2023/03/03 11:22:01 - mmengine - INFO - text score threshold: 0.96, recall: 0.6443, precision: 0.9317, hmean: 0.7618 2023/03/03 11:22:01 - mmengine - INFO - text score threshold: 0.97, recall: 0.6268, precision: 0.9376, hmean: 0.7513 2023/03/03 11:22:01 - mmengine - INFO - text score threshold: 0.98, recall: 0.5988, precision: 0.9421, hmean: 0.7322 2023/03/03 11:22:01 - mmengine - INFO - text score threshold: 0.99, recall: 0.5538, precision: 0.9439, hmean: 0.6980 2023/03/03 11:22:01 - mmengine - INFO - Epoch(val) [50][75/75] none/precision: 0.8201 none/recall: 0.6658 none/hmean: 0.7349 full/precision: 0.8843 full/recall: 0.7678 full/hmean: 0.8220 2023/03/03 11:22:01 - mmengine - INFO - The previous best checkpoint mmocr/projects/SPTS/work_dirs/spts_resnet50_350e_totaltext/best_none/hmean_epoch_30.pth is removed 2023/03/03 11:22:04 - mmengine - INFO - The best checkpoint with 0.7349 none/hmean at 50 epoch is saved to best_none/hmean_epoch_50.pth. 2023/03/03 11:22:09 - mmengine - INFO - Epoch(train) [51][10/79] lr: 1.0000e-06 eta: 1:34:23 time: 0.5166 data_time: 0.0615 memory: 40234 loss: 0.1214 loss_ce: 0.1214 2023/03/03 11:22:13 - mmengine - INFO - Epoch(train) [51][20/79] lr: 1.0000e-06 eta: 1:34:16 time: 0.4297 data_time: 0.0022 memory: 38587 loss: 0.1364 loss_ce: 0.1364 2023/03/03 11:22:18 - mmengine - INFO - Epoch(train) [51][30/79] lr: 1.0000e-06 eta: 1:34:11 time: 0.4540 data_time: 0.0026 memory: 38587 loss: 0.1429 loss_ce: 0.1429 2023/03/03 11:22:23 - mmengine - INFO - Epoch(train) [51][40/79] lr: 1.0000e-06 eta: 1:34:06 time: 0.4885 data_time: 0.0018 memory: 46820 loss: 0.1166 loss_ce: 0.1166 2023/03/03 11:22:27 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:22:27 - mmengine - INFO - Epoch(train) [51][50/79] lr: 1.0000e-06 eta: 1:34:01 time: 0.4635 data_time: 0.0019 memory: 33487 loss: 0.1433 loss_ce: 0.1433 2023/03/03 11:22:33 - mmengine - INFO - Epoch(train) [51][60/79] lr: 1.0000e-06 eta: 1:33:58 time: 0.5200 data_time: 0.0016 memory: 43937 loss: 0.1266 loss_ce: 0.1266 2023/03/03 11:22:37 - mmengine - INFO - Epoch(train) [51][70/79] lr: 1.0000e-06 eta: 1:33:52 time: 0.4516 data_time: 0.0013 memory: 48940 loss: 0.1312 loss_ce: 0.1312 2023/03/03 11:22:41 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:22:46 - mmengine - INFO - Epoch(train) [52][10/79] lr: 1.0000e-06 eta: 1:33:42 time: 0.4760 data_time: 0.0282 memory: 35738 loss: 0.1252 loss_ce: 0.1252 2023/03/03 11:22:51 - mmengine - INFO - Epoch(train) [52][20/79] lr: 1.0000e-06 eta: 1:33:37 time: 0.4622 data_time: 0.0015 memory: 39670 loss: 0.1144 loss_ce: 0.1144 2023/03/03 11:22:55 - mmengine - INFO - Epoch(train) [52][30/79] lr: 1.0000e-06 eta: 1:33:32 time: 0.4911 data_time: 0.0016 memory: 31612 loss: 0.1386 loss_ce: 0.1386 2023/03/03 11:23:00 - mmengine - INFO - Epoch(train) [52][40/79] lr: 1.0000e-06 eta: 1:33:27 time: 0.4621 data_time: 0.0016 memory: 37933 loss: 0.1211 loss_ce: 0.1211 2023/03/03 11:23:05 - mmengine - INFO - Epoch(train) [52][50/79] lr: 1.0000e-06 eta: 1:33:23 time: 0.5046 data_time: 0.0015 memory: 31328 loss: 0.1366 loss_ce: 0.1366 2023/03/03 11:23:10 - mmengine - INFO - Epoch(train) [52][60/79] lr: 1.0000e-06 eta: 1:33:20 time: 0.5217 data_time: 0.0015 memory: 34496 loss: 0.1248 loss_ce: 0.1248 2023/03/03 11:23:15 - mmengine - INFO - Epoch(train) [52][70/79] lr: 1.0000e-06 eta: 1:33:13 time: 0.4184 data_time: 0.0013 memory: 34942 loss: 0.1210 loss_ce: 0.1210 2023/03/03 11:23:18 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:23:23 - mmengine - INFO - Epoch(train) [53][10/79] lr: 1.0000e-06 eta: 1:33:02 time: 0.4595 data_time: 0.0483 memory: 42017 loss: 0.1322 loss_ce: 0.1322 2023/03/03 11:23:27 - mmengine - INFO - Epoch(train) [53][20/79] lr: 1.0000e-06 eta: 1:32:56 time: 0.4549 data_time: 0.0015 memory: 28709 loss: 0.1286 loss_ce: 0.1286 2023/03/03 11:23:32 - mmengine - INFO - Epoch(train) [53][30/79] lr: 1.0000e-06 eta: 1:32:52 time: 0.5050 data_time: 0.0015 memory: 34548 loss: 0.1318 loss_ce: 0.1318 2023/03/03 11:23:37 - mmengine - INFO - Epoch(train) [53][40/79] lr: 1.0000e-06 eta: 1:32:48 time: 0.4807 data_time: 0.0015 memory: 39777 loss: 0.1097 loss_ce: 0.1097 2023/03/03 11:23:42 - mmengine - INFO - Epoch(train) [53][50/79] lr: 1.0000e-06 eta: 1:32:42 time: 0.4545 data_time: 0.0015 memory: 38696 loss: 0.1329 loss_ce: 0.1329 2023/03/03 11:23:46 - mmengine - INFO - Epoch(train) [53][60/79] lr: 1.0000e-06 eta: 1:32:36 time: 0.4444 data_time: 0.0015 memory: 26609 loss: 0.1285 loss_ce: 0.1285 2023/03/03 11:23:51 - mmengine - INFO - Epoch(train) [53][70/79] lr: 1.0000e-06 eta: 1:32:31 time: 0.4350 data_time: 0.0012 memory: 34490 loss: 0.1308 loss_ce: 0.1308 2023/03/03 11:23:55 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:23:59 - mmengine - INFO - Epoch(train) [54][10/79] lr: 1.0000e-06 eta: 1:32:20 time: 0.4605 data_time: 0.0542 memory: 36660 loss: 0.1336 loss_ce: 0.1336 2023/03/03 11:24:04 - mmengine - INFO - Epoch(train) [54][20/79] lr: 1.0000e-06 eta: 1:32:15 time: 0.4624 data_time: 0.0016 memory: 38774 loss: 0.1398 loss_ce: 0.1398 2023/03/03 11:24:09 - mmengine - INFO - Epoch(train) [54][30/79] lr: 1.0000e-06 eta: 1:32:10 time: 0.4588 data_time: 0.0016 memory: 39121 loss: 0.1234 loss_ce: 0.1234 2023/03/03 11:24:14 - mmengine - INFO - Epoch(train) [54][40/79] lr: 1.0000e-06 eta: 1:32:07 time: 0.5364 data_time: 0.0018 memory: 35364 loss: 0.1146 loss_ce: 0.1146 2023/03/03 11:24:18 - mmengine - INFO - Epoch(train) [54][50/79] lr: 1.0000e-06 eta: 1:32:00 time: 0.4133 data_time: 0.0015 memory: 39036 loss: 0.1060 loss_ce: 0.1060 2023/03/03 11:24:23 - mmengine - INFO - Epoch(train) [54][60/79] lr: 1.0000e-06 eta: 1:31:56 time: 0.5095 data_time: 0.0015 memory: 46345 loss: 0.1159 loss_ce: 0.1159 2023/03/03 11:24:28 - mmengine - INFO - Epoch(train) [54][70/79] lr: 1.0000e-06 eta: 1:31:53 time: 0.5391 data_time: 0.0014 memory: 38846 loss: 0.1185 loss_ce: 0.1185 2023/03/03 11:24:33 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:24:38 - mmengine - INFO - Epoch(train) [55][10/79] lr: 1.0000e-06 eta: 1:31:45 time: 0.5295 data_time: 0.0499 memory: 40816 loss: 0.1110 loss_ce: 0.1110 2023/03/03 11:24:43 - mmengine - INFO - Epoch(train) [55][20/79] lr: 1.0000e-06 eta: 1:31:41 time: 0.5010 data_time: 0.0015 memory: 43937 loss: 0.1287 loss_ce: 0.1287 2023/03/03 11:24:48 - mmengine - INFO - Epoch(train) [55][30/79] lr: 1.0000e-06 eta: 1:31:36 time: 0.4772 data_time: 0.0016 memory: 40234 loss: 0.1155 loss_ce: 0.1155 2023/03/03 11:24:52 - mmengine - INFO - Epoch(train) [55][40/79] lr: 1.0000e-06 eta: 1:31:31 time: 0.4525 data_time: 0.0016 memory: 43956 loss: 0.1238 loss_ce: 0.1238 2023/03/03 11:24:57 - mmengine - INFO - Epoch(train) [55][50/79] lr: 1.0000e-06 eta: 1:31:25 time: 0.4349 data_time: 0.0016 memory: 39955 loss: 0.1389 loss_ce: 0.1389 2023/03/03 11:25:01 - mmengine - INFO - Epoch(train) [55][60/79] lr: 1.0000e-06 eta: 1:31:19 time: 0.4361 data_time: 0.0020 memory: 29411 loss: 0.1276 loss_ce: 0.1276 2023/03/03 11:25:06 - mmengine - INFO - Epoch(train) [55][70/79] lr: 1.0000e-06 eta: 1:31:15 time: 0.4839 data_time: 0.0013 memory: 36051 loss: 0.1286 loss_ce: 0.1286 2023/03/03 11:25:10 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:25:15 - mmengine - INFO - Epoch(train) [56][10/79] lr: 1.0000e-06 eta: 1:31:06 time: 0.5209 data_time: 0.0843 memory: 35999 loss: 0.1199 loss_ce: 0.1199 2023/03/03 11:25:20 - mmengine - INFO - Epoch(train) [56][20/79] lr: 1.0000e-06 eta: 1:31:01 time: 0.4795 data_time: 0.0016 memory: 38117 loss: 0.1127 loss_ce: 0.1127 2023/03/03 11:25:24 - mmengine - INFO - Epoch(train) [56][30/79] lr: 1.0000e-06 eta: 1:30:56 time: 0.4678 data_time: 0.0015 memory: 39169 loss: 0.1329 loss_ce: 0.1329 2023/03/03 11:25:30 - mmengine - INFO - Epoch(train) [56][40/79] lr: 1.0000e-06 eta: 1:30:52 time: 0.5125 data_time: 0.0016 memory: 35448 loss: 0.1260 loss_ce: 0.1260 2023/03/03 11:25:34 - mmengine - INFO - Epoch(train) [56][50/79] lr: 1.0000e-06 eta: 1:30:46 time: 0.4295 data_time: 0.0015 memory: 39006 loss: 0.1246 loss_ce: 0.1246 2023/03/03 11:25:38 - mmengine - INFO - Epoch(train) [56][60/79] lr: 1.0000e-06 eta: 1:30:40 time: 0.4406 data_time: 0.0016 memory: 29634 loss: 0.1264 loss_ce: 0.1264 2023/03/03 11:25:42 - mmengine - INFO - Epoch(train) [56][70/79] lr: 1.0000e-06 eta: 1:30:34 time: 0.4168 data_time: 0.0014 memory: 33344 loss: 0.1137 loss_ce: 0.1137 2023/03/03 11:25:46 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:25:51 - mmengine - INFO - Epoch(train) [57][10/79] lr: 1.0000e-06 eta: 1:30:24 time: 0.5127 data_time: 0.0353 memory: 37933 loss: 0.1343 loss_ce: 0.1343 2023/03/03 11:25:56 - mmengine - INFO - Epoch(train) [57][20/79] lr: 1.0000e-06 eta: 1:30:18 time: 0.4178 data_time: 0.0015 memory: 33979 loss: 0.1221 loss_ce: 0.1221 2023/03/03 11:26:01 - mmengine - INFO - Epoch(train) [57][30/79] lr: 1.0000e-06 eta: 1:30:15 time: 0.5256 data_time: 0.0015 memory: 39670 loss: 0.1427 loss_ce: 0.1427 2023/03/03 11:26:05 - mmengine - INFO - Epoch(train) [57][40/79] lr: 1.0000e-06 eta: 1:30:09 time: 0.4499 data_time: 0.0015 memory: 38846 loss: 0.1061 loss_ce: 0.1061 2023/03/03 11:26:10 - mmengine - INFO - Epoch(train) [57][50/79] lr: 1.0000e-06 eta: 1:30:04 time: 0.4501 data_time: 0.0015 memory: 41837 loss: 0.1354 loss_ce: 0.1354 2023/03/03 11:26:15 - mmengine - INFO - Epoch(train) [57][60/79] lr: 1.0000e-06 eta: 1:29:59 time: 0.4791 data_time: 0.0014 memory: 42325 loss: 0.1361 loss_ce: 0.1361 2023/03/03 11:26:19 - mmengine - INFO - Epoch(train) [57][70/79] lr: 1.0000e-06 eta: 1:29:54 time: 0.4519 data_time: 0.0013 memory: 39766 loss: 0.1453 loss_ce: 0.1453 2023/03/03 11:26:23 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:26:28 - mmengine - INFO - Epoch(train) [58][10/79] lr: 1.0000e-06 eta: 1:29:45 time: 0.5429 data_time: 0.0383 memory: 39670 loss: 0.1354 loss_ce: 0.1354 2023/03/03 11:26:34 - mmengine - INFO - Epoch(train) [58][20/79] lr: 1.0000e-06 eta: 1:29:42 time: 0.5317 data_time: 0.0015 memory: 29655 loss: 0.1317 loss_ce: 0.1317 2023/03/03 11:26:38 - mmengine - INFO - Epoch(train) [58][30/79] lr: 1.0000e-06 eta: 1:29:36 time: 0.4312 data_time: 0.0015 memory: 41110 loss: 0.1066 loss_ce: 0.1066 2023/03/03 11:26:42 - mmengine - INFO - Epoch(train) [58][40/79] lr: 1.0000e-06 eta: 1:29:30 time: 0.4332 data_time: 0.0015 memory: 25538 loss: 0.1214 loss_ce: 0.1214 2023/03/03 11:26:47 - mmengine - INFO - Epoch(train) [58][50/79] lr: 1.0000e-06 eta: 1:29:24 time: 0.4432 data_time: 0.0016 memory: 31486 loss: 0.1330 loss_ce: 0.1330 2023/03/03 11:26:52 - mmengine - INFO - Epoch(train) [58][60/79] lr: 1.0000e-06 eta: 1:29:19 time: 0.4700 data_time: 0.0015 memory: 33747 loss: 0.1363 loss_ce: 0.1363 2023/03/03 11:26:56 - mmengine - INFO - Epoch(train) [58][70/79] lr: 1.0000e-06 eta: 1:29:14 time: 0.4528 data_time: 0.0013 memory: 32446 loss: 0.1260 loss_ce: 0.1260 2023/03/03 11:27:00 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:27:05 - mmengine - INFO - Epoch(train) [59][10/79] lr: 1.0000e-06 eta: 1:29:05 time: 0.5333 data_time: 0.0230 memory: 37995 loss: 0.1134 loss_ce: 0.1134 2023/03/03 11:27:10 - mmengine - INFO - Epoch(train) [59][20/79] lr: 1.0000e-06 eta: 1:29:00 time: 0.4631 data_time: 0.0015 memory: 31115 loss: 0.1045 loss_ce: 0.1045 2023/03/03 11:27:15 - mmengine - INFO - Epoch(train) [59][30/79] lr: 1.0000e-06 eta: 1:28:56 time: 0.5073 data_time: 0.0015 memory: 33434 loss: 0.1307 loss_ce: 0.1307 2023/03/03 11:27:19 - mmengine - INFO - Epoch(train) [59][40/79] lr: 1.0000e-06 eta: 1:28:51 time: 0.4555 data_time: 0.0015 memory: 39161 loss: 0.1260 loss_ce: 0.1260 2023/03/03 11:27:24 - mmengine - INFO - Epoch(train) [59][50/79] lr: 1.0000e-06 eta: 1:28:45 time: 0.4419 data_time: 0.0015 memory: 37255 loss: 0.1179 loss_ce: 0.1179 2023/03/03 11:27:28 - mmengine - INFO - Epoch(train) [59][60/79] lr: 1.0000e-06 eta: 1:28:40 time: 0.4491 data_time: 0.0015 memory: 38846 loss: 0.1170 loss_ce: 0.1170 2023/03/03 11:27:33 - mmengine - INFO - Epoch(train) [59][70/79] lr: 1.0000e-06 eta: 1:28:34 time: 0.4305 data_time: 0.0015 memory: 29409 loss: 0.1345 loss_ce: 0.1345 2023/03/03 11:27:36 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:27:42 - mmengine - INFO - Epoch(train) [60][10/79] lr: 1.0000e-06 eta: 1:28:24 time: 0.5059 data_time: 0.0590 memory: 44609 loss: 0.1191 loss_ce: 0.1191 2023/03/03 11:27:46 - mmengine - INFO - Epoch(train) [60][20/79] lr: 1.0000e-06 eta: 1:28:20 time: 0.4886 data_time: 0.0016 memory: 39485 loss: 0.1367 loss_ce: 0.1367 2023/03/03 11:27:51 - mmengine - INFO - Epoch(train) [60][30/79] lr: 1.0000e-06 eta: 1:28:15 time: 0.4756 data_time: 0.0016 memory: 38332 loss: 0.1210 loss_ce: 0.1210 2023/03/03 11:27:56 - mmengine - INFO - Epoch(train) [60][40/79] lr: 1.0000e-06 eta: 1:28:11 time: 0.4994 data_time: 0.0016 memory: 31416 loss: 0.1095 loss_ce: 0.1095 2023/03/03 11:28:00 - mmengine - INFO - Epoch(train) [60][50/79] lr: 1.0000e-06 eta: 1:28:04 time: 0.4074 data_time: 0.0016 memory: 30976 loss: 0.1164 loss_ce: 0.1164 2023/03/03 11:28:05 - mmengine - INFO - Epoch(train) [60][60/79] lr: 1.0000e-06 eta: 1:28:00 time: 0.5017 data_time: 0.0015 memory: 37548 loss: 0.1308 loss_ce: 0.1308 2023/03/03 11:28:10 - mmengine - INFO - Epoch(train) [60][70/79] lr: 1.0000e-06 eta: 1:27:55 time: 0.4547 data_time: 0.0016 memory: 38587 loss: 0.1428 loss_ce: 0.1428 2023/03/03 11:28:14 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:28:26 - mmengine - INFO - Epoch(val) [60][10/75] eta: 0:01:17 time: 1.1954 data_time: 0.0034 memory: 38846 2023/03/03 11:29:08 - mmengine - INFO - Epoch(val) [60][20/75] eta: 0:02:27 time: 4.1862 data_time: 0.0005 memory: 1077 2023/03/03 11:29:28 - mmengine - INFO - Epoch(val) [60][30/75] eta: 0:01:51 time: 2.0500 data_time: 0.0004 memory: 1020 2023/03/03 11:29:42 - mmengine - INFO - Epoch(val) [60][40/75] eta: 0:01:17 time: 1.4284 data_time: 0.0004 memory: 1019 2023/03/03 11:29:57 - mmengine - INFO - Epoch(val) [60][50/75] eta: 0:00:51 time: 1.4178 data_time: 0.0003 memory: 1077 2023/03/03 11:30:38 - mmengine - INFO - Epoch(val) [60][60/75] eta: 0:00:35 time: 4.1195 data_time: 0.0004 memory: 1045 2023/03/03 11:31:41 - mmengine - INFO - Epoch(val) [60][70/75] eta: 0:00:14 time: 6.3665 data_time: 0.0006 memory: 1077 2023/03/03 11:31:55 - mmengine - INFO - text score threshold: 0.80, recall: 0.6926, precision: 0.7630, hmean: 0.7261 2023/03/03 11:31:55 - mmengine - INFO - text score threshold: 0.81, recall: 0.6926, precision: 0.7667, hmean: 0.7278 2023/03/03 11:31:55 - mmengine - INFO - text score threshold: 0.82, recall: 0.6915, precision: 0.7711, hmean: 0.7292 2023/03/03 11:31:55 - mmengine - INFO - text score threshold: 0.83, recall: 0.6910, precision: 0.7810, hmean: 0.7333 2023/03/03 11:31:55 - mmengine - INFO - text score threshold: 0.84, recall: 0.6899, precision: 0.7871, hmean: 0.7353 2023/03/03 11:31:55 - mmengine - INFO - text score threshold: 0.85, recall: 0.6888, precision: 0.7923, hmean: 0.7369 2023/03/03 11:31:55 - mmengine - INFO - text score threshold: 0.86, recall: 0.6872, precision: 0.8000, hmean: 0.7393 2023/03/03 11:31:55 - mmengine - INFO - text score threshold: 0.87, recall: 0.6817, precision: 0.8091, hmean: 0.7399 2023/03/03 11:31:55 - mmengine - INFO - text score threshold: 0.88, recall: 0.6767, precision: 0.8133, hmean: 0.7388 2023/03/03 11:31:55 - mmengine - INFO - text score threshold: 0.89, recall: 0.6718, precision: 0.8165, hmean: 0.7371 2023/03/03 11:31:55 - mmengine - INFO - text score threshold: 0.90, recall: 0.6663, precision: 0.8214, hmean: 0.7358 2023/03/03 11:31:55 - mmengine - INFO - text score threshold: 0.91, recall: 0.6630, precision: 0.8263, hmean: 0.7357 2023/03/03 11:31:55 - mmengine - INFO - text score threshold: 0.92, recall: 0.6586, precision: 0.8299, hmean: 0.7344 2023/03/03 11:31:55 - mmengine - INFO - text score threshold: 0.93, recall: 0.6509, precision: 0.8382, hmean: 0.7328 2023/03/03 11:31:55 - mmengine - INFO - text score threshold: 0.94, recall: 0.6400, precision: 0.8437, hmean: 0.7278 2023/03/03 11:31:55 - mmengine - INFO - text score threshold: 0.95, recall: 0.6295, precision: 0.8534, hmean: 0.7246 2023/03/03 11:31:55 - mmengine - INFO - text score threshold: 0.96, recall: 0.6186, precision: 0.8629, hmean: 0.7206 2023/03/03 11:31:55 - mmengine - INFO - text score threshold: 0.97, recall: 0.6059, precision: 0.8707, hmean: 0.7146 2023/03/03 11:31:55 - mmengine - INFO - text score threshold: 0.98, recall: 0.5851, precision: 0.8943, hmean: 0.7074 2023/03/03 11:31:55 - mmengine - INFO - text score threshold: 0.99, recall: 0.5488, precision: 0.9050, hmean: 0.6833 2023/03/03 11:32:05 - mmengine - INFO - text score threshold: 0.80, recall: 0.7711, precision: 0.8820, hmean: 0.8228 2023/03/03 11:32:05 - mmengine - INFO - text score threshold: 0.81, recall: 0.7706, precision: 0.8836, hmean: 0.8232 2023/03/03 11:32:05 - mmengine - INFO - text score threshold: 0.82, recall: 0.7684, precision: 0.8850, hmean: 0.8226 2023/03/03 11:32:05 - mmengine - INFO - text score threshold: 0.83, recall: 0.7634, precision: 0.8905, hmean: 0.8221 2023/03/03 11:32:05 - mmengine - INFO - text score threshold: 0.84, recall: 0.7618, precision: 0.8943, hmean: 0.8228 2023/03/03 11:32:05 - mmengine - INFO - text score threshold: 0.85, recall: 0.7602, precision: 0.8982, hmean: 0.8234 2023/03/03 11:32:05 - mmengine - INFO - text score threshold: 0.86, recall: 0.7536, precision: 0.9009, hmean: 0.8207 2023/03/03 11:32:05 - mmengine - INFO - text score threshold: 0.87, recall: 0.7459, precision: 0.9048, hmean: 0.8177 2023/03/03 11:32:05 - mmengine - INFO - text score threshold: 0.88, recall: 0.7404, precision: 0.9096, hmean: 0.8163 2023/03/03 11:32:05 - mmengine - INFO - text score threshold: 0.89, recall: 0.7349, precision: 0.9115, hmean: 0.8137 2023/03/03 11:32:05 - mmengine - INFO - text score threshold: 0.90, recall: 0.7261, precision: 0.9124, hmean: 0.8087 2023/03/03 11:32:05 - mmengine - INFO - text score threshold: 0.91, recall: 0.7206, precision: 0.9156, hmean: 0.8065 2023/03/03 11:32:05 - mmengine - INFO - text score threshold: 0.92, recall: 0.7130, precision: 0.9154, hmean: 0.8016 2023/03/03 11:32:05 - mmengine - INFO - text score threshold: 0.93, recall: 0.7014, precision: 0.9188, hmean: 0.7955 2023/03/03 11:32:05 - mmengine - INFO - text score threshold: 0.94, recall: 0.6861, precision: 0.9205, hmean: 0.7862 2023/03/03 11:32:05 - mmengine - INFO - text score threshold: 0.95, recall: 0.6701, precision: 0.9236, hmean: 0.7767 2023/03/03 11:32:05 - mmengine - INFO - text score threshold: 0.96, recall: 0.6570, precision: 0.9315, hmean: 0.7705 2023/03/03 11:32:05 - mmengine - INFO - text score threshold: 0.97, recall: 0.6411, precision: 0.9366, hmean: 0.7612 2023/03/03 11:32:05 - mmengine - INFO - text score threshold: 0.98, recall: 0.6087, precision: 0.9422, hmean: 0.7396 2023/03/03 11:32:05 - mmengine - INFO - text score threshold: 0.99, recall: 0.5664, precision: 0.9459, hmean: 0.7085 2023/03/03 11:32:05 - mmengine - INFO - Epoch(val) [60][75/75] none/precision: 0.8091 none/recall: 0.6817 none/hmean: 0.7399 full/precision: 0.8982 full/recall: 0.7602 full/hmean: 0.8234 2023/03/03 11:32:05 - mmengine - INFO - The previous best checkpoint mmocr/projects/SPTS/work_dirs/spts_resnet50_350e_totaltext/best_none/hmean_epoch_50.pth is removed 2023/03/03 11:32:07 - mmengine - INFO - The best checkpoint with 0.7399 none/hmean at 60 epoch is saved to best_none/hmean_epoch_60.pth. 2023/03/03 11:32:12 - mmengine - INFO - Epoch(train) [61][10/79] lr: 1.0000e-06 eta: 1:27:46 time: 0.4919 data_time: 0.0595 memory: 30676 loss: 0.1179 loss_ce: 0.1179 2023/03/03 11:32:16 - mmengine - INFO - Epoch(train) [61][20/79] lr: 1.0000e-06 eta: 1:27:39 time: 0.4153 data_time: 0.0020 memory: 38321 loss: 0.1559 loss_ce: 0.1559 2023/03/03 11:32:21 - mmengine - INFO - Epoch(train) [61][30/79] lr: 1.0000e-06 eta: 1:27:35 time: 0.4929 data_time: 0.0017 memory: 32678 loss: 0.1149 loss_ce: 0.1149 2023/03/03 11:32:26 - mmengine - INFO - Epoch(train) [61][40/79] lr: 1.0000e-06 eta: 1:27:30 time: 0.4704 data_time: 0.0016 memory: 30913 loss: 0.1318 loss_ce: 0.1318 2023/03/03 11:32:31 - mmengine - INFO - Epoch(train) [61][50/79] lr: 1.0000e-06 eta: 1:27:25 time: 0.4786 data_time: 0.0016 memory: 40522 loss: 0.1235 loss_ce: 0.1235 2023/03/03 11:32:35 - mmengine - INFO - Epoch(train) [61][60/79] lr: 1.0000e-06 eta: 1:27:20 time: 0.4455 data_time: 0.0015 memory: 38020 loss: 0.1254 loss_ce: 0.1254 2023/03/03 11:32:40 - mmengine - INFO - Epoch(train) [61][70/79] lr: 1.0000e-06 eta: 1:27:16 time: 0.5010 data_time: 0.0014 memory: 25061 loss: 0.1285 loss_ce: 0.1285 2023/03/03 11:32:44 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:32:48 - mmengine - INFO - Epoch(train) [62][10/79] lr: 1.0000e-06 eta: 1:27:05 time: 0.4608 data_time: 0.0368 memory: 39028 loss: 0.1228 loss_ce: 0.1228 2023/03/03 11:32:53 - mmengine - INFO - Epoch(train) [62][20/79] lr: 1.0000e-06 eta: 1:27:00 time: 0.4782 data_time: 0.0017 memory: 38639 loss: 0.1130 loss_ce: 0.1130 2023/03/03 11:32:58 - mmengine - INFO - Epoch(train) [62][30/79] lr: 1.0000e-06 eta: 1:26:55 time: 0.4758 data_time: 0.0017 memory: 36169 loss: 0.1182 loss_ce: 0.1182 2023/03/03 11:33:02 - mmengine - INFO - Epoch(train) [62][40/79] lr: 1.0000e-06 eta: 1:26:49 time: 0.4103 data_time: 0.0016 memory: 35738 loss: 0.1339 loss_ce: 0.1339 2023/03/03 11:33:07 - mmengine - INFO - Epoch(train) [62][50/79] lr: 1.0000e-06 eta: 1:26:45 time: 0.5269 data_time: 0.0016 memory: 37084 loss: 0.1130 loss_ce: 0.1130 2023/03/03 11:33:12 - mmengine - INFO - Epoch(train) [62][60/79] lr: 1.0000e-06 eta: 1:26:40 time: 0.4487 data_time: 0.0016 memory: 46345 loss: 0.1209 loss_ce: 0.1209 2023/03/03 11:33:16 - mmengine - INFO - Epoch(train) [62][70/79] lr: 1.0000e-06 eta: 1:26:34 time: 0.4461 data_time: 0.0014 memory: 37874 loss: 0.1108 loss_ce: 0.1108 2023/03/03 11:33:21 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:33:26 - mmengine - INFO - Epoch(train) [63][10/79] lr: 1.0000e-06 eta: 1:26:28 time: 0.5352 data_time: 0.0586 memory: 41714 loss: 0.1433 loss_ce: 0.1433 2023/03/03 11:33:31 - mmengine - INFO - Epoch(train) [63][20/79] lr: 1.0000e-06 eta: 1:26:22 time: 0.4568 data_time: 0.0018 memory: 32544 loss: 0.1252 loss_ce: 0.1252 2023/03/03 11:33:35 - mmengine - INFO - Epoch(train) [63][30/79] lr: 1.0000e-06 eta: 1:26:17 time: 0.4329 data_time: 0.0020 memory: 38080 loss: 0.1322 loss_ce: 0.1322 2023/03/03 11:33:40 - mmengine - INFO - Epoch(train) [63][40/79] lr: 1.0000e-06 eta: 1:26:12 time: 0.4916 data_time: 0.0021 memory: 37933 loss: 0.1317 loss_ce: 0.1317 2023/03/03 11:33:45 - mmengine - INFO - Epoch(train) [63][50/79] lr: 1.0000e-06 eta: 1:26:08 time: 0.4866 data_time: 0.0027 memory: 42017 loss: 0.1117 loss_ce: 0.1117 2023/03/03 11:33:49 - mmengine - INFO - Epoch(train) [63][60/79] lr: 1.0000e-06 eta: 1:26:02 time: 0.4098 data_time: 0.0024 memory: 31546 loss: 0.1131 loss_ce: 0.1131 2023/03/03 11:33:53 - mmengine - INFO - Epoch(train) [63][70/79] lr: 1.0000e-06 eta: 1:25:56 time: 0.4350 data_time: 0.0018 memory: 35124 loss: 0.1016 loss_ce: 0.1016 2023/03/03 11:33:57 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:34:03 - mmengine - INFO - Epoch(train) [64][10/79] lr: 1.0000e-06 eta: 1:25:47 time: 0.5671 data_time: 0.0322 memory: 39671 loss: 0.1074 loss_ce: 0.1074 2023/03/03 11:34:08 - mmengine - INFO - Epoch(train) [64][20/79] lr: 1.0000e-06 eta: 1:25:43 time: 0.5097 data_time: 0.0017 memory: 55549 loss: 0.1090 loss_ce: 0.1090 2023/03/03 11:34:09 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:34:12 - mmengine - INFO - Epoch(train) [64][30/79] lr: 1.0000e-06 eta: 1:25:37 time: 0.4211 data_time: 0.0017 memory: 34973 loss: 0.1270 loss_ce: 0.1270 2023/03/03 11:34:17 - mmengine - INFO - Epoch(train) [64][40/79] lr: 1.0000e-06 eta: 1:25:33 time: 0.4974 data_time: 0.0015 memory: 41294 loss: 0.1246 loss_ce: 0.1246 2023/03/03 11:34:21 - mmengine - INFO - Epoch(train) [64][50/79] lr: 1.0000e-06 eta: 1:25:27 time: 0.4248 data_time: 0.0015 memory: 45747 loss: 0.1378 loss_ce: 0.1378 2023/03/03 11:34:26 - mmengine - INFO - Epoch(train) [64][60/79] lr: 1.0000e-06 eta: 1:25:22 time: 0.4665 data_time: 0.0016 memory: 38296 loss: 0.1365 loss_ce: 0.1365 2023/03/03 11:34:31 - mmengine - INFO - Epoch(train) [64][70/79] lr: 1.0000e-06 eta: 1:25:18 time: 0.4853 data_time: 0.0016 memory: 38116 loss: 0.1192 loss_ce: 0.1192 2023/03/03 11:34:35 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:34:40 - mmengine - INFO - Epoch(train) [65][10/79] lr: 1.0000e-06 eta: 1:25:10 time: 0.5178 data_time: 0.0518 memory: 38928 loss: 0.1289 loss_ce: 0.1289 2023/03/03 11:34:45 - mmengine - INFO - Epoch(train) [65][20/79] lr: 1.0000e-06 eta: 1:25:05 time: 0.4957 data_time: 0.0017 memory: 40236 loss: 0.1197 loss_ce: 0.1197 2023/03/03 11:34:50 - mmengine - INFO - Epoch(train) [65][30/79] lr: 1.0000e-06 eta: 1:25:01 time: 0.4966 data_time: 0.0016 memory: 38828 loss: 0.1144 loss_ce: 0.1144 2023/03/03 11:34:55 - mmengine - INFO - Epoch(train) [65][40/79] lr: 1.0000e-06 eta: 1:24:56 time: 0.4645 data_time: 0.0018 memory: 35263 loss: 0.1325 loss_ce: 0.1325 2023/03/03 11:35:00 - mmengine - INFO - Epoch(train) [65][50/79] lr: 1.0000e-06 eta: 1:24:51 time: 0.4876 data_time: 0.0017 memory: 31165 loss: 0.1186 loss_ce: 0.1186 2023/03/03 11:35:05 - mmengine - INFO - Epoch(train) [65][60/79] lr: 1.0000e-06 eta: 1:24:47 time: 0.4932 data_time: 0.0016 memory: 31271 loss: 0.1399 loss_ce: 0.1399 2023/03/03 11:35:09 - mmengine - INFO - Epoch(train) [65][70/79] lr: 1.0000e-06 eta: 1:24:42 time: 0.4717 data_time: 0.0013 memory: 41108 loss: 0.1316 loss_ce: 0.1316 2023/03/03 11:35:14 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:35:19 - mmengine - INFO - Epoch(train) [66][10/79] lr: 1.0000e-06 eta: 1:24:35 time: 0.5361 data_time: 0.0613 memory: 36931 loss: 0.1192 loss_ce: 0.1192 2023/03/03 11:35:24 - mmengine - INFO - Epoch(train) [66][20/79] lr: 1.0000e-06 eta: 1:24:29 time: 0.4489 data_time: 0.0017 memory: 34242 loss: 0.1154 loss_ce: 0.1154 2023/03/03 11:35:28 - mmengine - INFO - Epoch(train) [66][30/79] lr: 1.0000e-06 eta: 1:24:24 time: 0.4746 data_time: 0.0016 memory: 39390 loss: 0.1363 loss_ce: 0.1363 2023/03/03 11:35:33 - mmengine - INFO - Epoch(train) [66][40/79] lr: 1.0000e-06 eta: 1:24:19 time: 0.4645 data_time: 0.0016 memory: 40236 loss: 0.1355 loss_ce: 0.1355 2023/03/03 11:35:38 - mmengine - INFO - Epoch(train) [66][50/79] lr: 1.0000e-06 eta: 1:24:15 time: 0.5145 data_time: 0.0016 memory: 34852 loss: 0.1267 loss_ce: 0.1267 2023/03/03 11:35:43 - mmengine - INFO - Epoch(train) [66][60/79] lr: 1.0000e-06 eta: 1:24:10 time: 0.4645 data_time: 0.0016 memory: 39669 loss: 0.1259 loss_ce: 0.1259 2023/03/03 11:35:47 - mmengine - INFO - Epoch(train) [66][70/79] lr: 1.0000e-06 eta: 1:24:05 time: 0.4674 data_time: 0.0013 memory: 40959 loss: 0.1100 loss_ce: 0.1100 2023/03/03 11:35:52 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:35:58 - mmengine - INFO - Epoch(train) [67][10/79] lr: 1.0000e-06 eta: 1:23:59 time: 0.5528 data_time: 0.0636 memory: 38708 loss: 0.1128 loss_ce: 0.1128 2023/03/03 11:36:02 - mmengine - INFO - Epoch(train) [67][20/79] lr: 1.0000e-06 eta: 1:23:54 time: 0.4875 data_time: 0.0016 memory: 41160 loss: 0.1108 loss_ce: 0.1108 2023/03/03 11:36:07 - mmengine - INFO - Epoch(train) [67][30/79] lr: 1.0000e-06 eta: 1:23:50 time: 0.4975 data_time: 0.0016 memory: 36379 loss: 0.1193 loss_ce: 0.1193 2023/03/03 11:36:12 - mmengine - INFO - Epoch(train) [67][40/79] lr: 1.0000e-06 eta: 1:23:45 time: 0.4583 data_time: 0.0015 memory: 32531 loss: 0.1472 loss_ce: 0.1472 2023/03/03 11:36:17 - mmengine - INFO - Epoch(train) [67][50/79] lr: 1.0000e-06 eta: 1:23:39 time: 0.4491 data_time: 0.0015 memory: 30962 loss: 0.1329 loss_ce: 0.1329 2023/03/03 11:36:21 - mmengine - INFO - Epoch(train) [67][60/79] lr: 1.0000e-06 eta: 1:23:35 time: 0.4962 data_time: 0.0016 memory: 39060 loss: 0.1048 loss_ce: 0.1048 2023/03/03 11:36:26 - mmengine - INFO - Epoch(train) [67][70/79] lr: 1.0000e-06 eta: 1:23:30 time: 0.4786 data_time: 0.0015 memory: 40236 loss: 0.1243 loss_ce: 0.1243 2023/03/03 11:36:30 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:36:36 - mmengine - INFO - Epoch(train) [68][10/79] lr: 1.0000e-06 eta: 1:23:22 time: 0.5451 data_time: 0.0511 memory: 38082 loss: 0.1127 loss_ce: 0.1127 2023/03/03 11:36:40 - mmengine - INFO - Epoch(train) [68][20/79] lr: 1.0000e-06 eta: 1:23:17 time: 0.4629 data_time: 0.0022 memory: 36582 loss: 0.1169 loss_ce: 0.1169 2023/03/03 11:36:45 - mmengine - INFO - Epoch(train) [68][30/79] lr: 1.0000e-06 eta: 1:23:13 time: 0.4909 data_time: 0.0022 memory: 43666 loss: 0.1008 loss_ce: 0.1008 2023/03/03 11:36:50 - mmengine - INFO - Epoch(train) [68][40/79] lr: 1.0000e-06 eta: 1:23:07 time: 0.4256 data_time: 0.0022 memory: 36232 loss: 0.1111 loss_ce: 0.1111 2023/03/03 11:36:54 - mmengine - INFO - Epoch(train) [68][50/79] lr: 1.0000e-06 eta: 1:23:01 time: 0.4317 data_time: 0.0022 memory: 32220 loss: 0.1359 loss_ce: 0.1359 2023/03/03 11:36:58 - mmengine - INFO - Epoch(train) [68][60/79] lr: 1.0000e-06 eta: 1:22:55 time: 0.4073 data_time: 0.0019 memory: 38334 loss: 0.1346 loss_ce: 0.1346 2023/03/03 11:37:03 - mmengine - INFO - Epoch(train) [68][70/79] lr: 1.0000e-06 eta: 1:22:50 time: 0.4795 data_time: 0.0017 memory: 39390 loss: 0.1089 loss_ce: 0.1089 2023/03/03 11:37:07 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:37:12 - mmengine - INFO - Epoch(train) [69][10/79] lr: 1.0000e-06 eta: 1:22:41 time: 0.5163 data_time: 0.0415 memory: 38851 loss: 0.1189 loss_ce: 0.1189 2023/03/03 11:37:16 - mmengine - INFO - Epoch(train) [69][20/79] lr: 1.0000e-06 eta: 1:22:36 time: 0.4410 data_time: 0.0018 memory: 33439 loss: 0.1369 loss_ce: 0.1369 2023/03/03 11:37:21 - mmengine - INFO - Epoch(train) [69][30/79] lr: 1.0000e-06 eta: 1:22:31 time: 0.4826 data_time: 0.0024 memory: 37934 loss: 0.1128 loss_ce: 0.1128 2023/03/03 11:37:26 - mmengine - INFO - Epoch(train) [69][40/79] lr: 1.0000e-06 eta: 1:22:26 time: 0.4519 data_time: 0.0017 memory: 35974 loss: 0.1417 loss_ce: 0.1417 2023/03/03 11:37:30 - mmengine - INFO - Epoch(train) [69][50/79] lr: 1.0000e-06 eta: 1:22:21 time: 0.4682 data_time: 0.0017 memory: 42016 loss: 0.1308 loss_ce: 0.1308 2023/03/03 11:37:35 - mmengine - INFO - Epoch(train) [69][60/79] lr: 1.0000e-06 eta: 1:22:16 time: 0.4443 data_time: 0.0016 memory: 31110 loss: 0.1165 loss_ce: 0.1165 2023/03/03 11:37:40 - mmengine - INFO - Epoch(train) [69][70/79] lr: 1.0000e-06 eta: 1:22:12 time: 0.5207 data_time: 0.0024 memory: 43579 loss: 0.1196 loss_ce: 0.1196 2023/03/03 11:37:44 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:37:49 - mmengine - INFO - Epoch(train) [70][10/79] lr: 1.0000e-06 eta: 1:22:03 time: 0.5449 data_time: 0.0475 memory: 34412 loss: 0.1370 loss_ce: 0.1370 2023/03/03 11:37:54 - mmengine - INFO - Epoch(train) [70][20/79] lr: 1.0000e-06 eta: 1:21:58 time: 0.4742 data_time: 0.0020 memory: 30796 loss: 0.1388 loss_ce: 0.1388 2023/03/03 11:37:58 - mmengine - INFO - Epoch(train) [70][30/79] lr: 1.0000e-06 eta: 1:21:53 time: 0.4588 data_time: 0.0020 memory: 32667 loss: 0.1192 loss_ce: 0.1192 2023/03/03 11:38:03 - mmengine - INFO - Epoch(train) [70][40/79] lr: 1.0000e-06 eta: 1:21:48 time: 0.4841 data_time: 0.0018 memory: 38180 loss: 0.1073 loss_ce: 0.1073 2023/03/03 11:38:07 - mmengine - INFO - Epoch(train) [70][50/79] lr: 1.0000e-06 eta: 1:21:43 time: 0.4343 data_time: 0.0018 memory: 25604 loss: 0.1239 loss_ce: 0.1239 2023/03/03 11:38:12 - mmengine - INFO - Epoch(train) [70][60/79] lr: 1.0000e-06 eta: 1:21:38 time: 0.4855 data_time: 0.0018 memory: 37795 loss: 0.1189 loss_ce: 0.1189 2023/03/03 11:38:17 - mmengine - INFO - Epoch(train) [70][70/79] lr: 1.0000e-06 eta: 1:21:33 time: 0.4711 data_time: 0.0017 memory: 34627 loss: 0.1243 loss_ce: 0.1243 2023/03/03 11:38:21 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:38:33 - mmengine - INFO - Epoch(val) [70][10/75] eta: 0:01:16 time: 1.1775 data_time: 0.0032 memory: 36818 2023/03/03 11:39:33 - mmengine - INFO - Epoch(val) [70][20/75] eta: 0:03:17 time: 5.9953 data_time: 0.0005 memory: 1077 2023/03/03 11:39:55 - mmengine - INFO - Epoch(val) [70][30/75] eta: 0:02:20 time: 2.1898 data_time: 0.0004 memory: 1020 2023/03/03 11:40:10 - mmengine - INFO - Epoch(val) [70][40/75] eta: 0:01:35 time: 1.5170 data_time: 0.0006 memory: 1019 2023/03/03 11:40:25 - mmengine - INFO - Epoch(val) [70][50/75] eta: 0:01:01 time: 1.4723 data_time: 0.0006 memory: 1077 2023/03/03 11:41:08 - mmengine - INFO - Epoch(val) [70][60/75] eta: 0:00:41 time: 4.3335 data_time: 0.0004 memory: 1045 2023/03/03 11:42:02 - mmengine - INFO - Epoch(val) [70][70/75] eta: 0:00:15 time: 5.3410 data_time: 0.0004 memory: 1077 2023/03/03 11:42:16 - mmengine - INFO - text score threshold: 0.80, recall: 0.6987, precision: 0.7646, hmean: 0.7301 2023/03/03 11:42:16 - mmengine - INFO - text score threshold: 0.81, recall: 0.6976, precision: 0.7675, hmean: 0.7309 2023/03/03 11:42:16 - mmengine - INFO - text score threshold: 0.82, recall: 0.6965, precision: 0.7700, hmean: 0.7314 2023/03/03 11:42:16 - mmengine - INFO - text score threshold: 0.83, recall: 0.6937, precision: 0.7783, hmean: 0.7336 2023/03/03 11:42:16 - mmengine - INFO - text score threshold: 0.84, recall: 0.6921, precision: 0.7857, hmean: 0.7359 2023/03/03 11:42:16 - mmengine - INFO - text score threshold: 0.85, recall: 0.6910, precision: 0.7918, hmean: 0.7380 2023/03/03 11:42:16 - mmengine - INFO - text score threshold: 0.86, recall: 0.6883, precision: 0.7967, hmean: 0.7385 2023/03/03 11:42:16 - mmengine - INFO - text score threshold: 0.87, recall: 0.6855, precision: 0.8001, hmean: 0.7384 2023/03/03 11:42:16 - mmengine - INFO - text score threshold: 0.88, recall: 0.6839, precision: 0.8049, hmean: 0.7395 2023/03/03 11:42:16 - mmengine - INFO - text score threshold: 0.89, recall: 0.6767, precision: 0.8107, hmean: 0.7377 2023/03/03 11:42:16 - mmengine - INFO - text score threshold: 0.90, recall: 0.6729, precision: 0.8162, hmean: 0.7377 2023/03/03 11:42:16 - mmengine - INFO - text score threshold: 0.91, recall: 0.6679, precision: 0.8229, hmean: 0.7374 2023/03/03 11:42:16 - mmengine - INFO - text score threshold: 0.92, recall: 0.6625, precision: 0.8290, hmean: 0.7364 2023/03/03 11:42:16 - mmengine - INFO - text score threshold: 0.93, recall: 0.6542, precision: 0.8365, hmean: 0.7342 2023/03/03 11:42:16 - mmengine - INFO - text score threshold: 0.94, recall: 0.6432, precision: 0.8444, hmean: 0.7302 2023/03/03 11:42:16 - mmengine - INFO - text score threshold: 0.95, recall: 0.6301, precision: 0.8523, hmean: 0.7245 2023/03/03 11:42:16 - mmengine - INFO - text score threshold: 0.96, recall: 0.6202, precision: 0.8613, hmean: 0.7211 2023/03/03 11:42:16 - mmengine - INFO - text score threshold: 0.97, recall: 0.6059, precision: 0.8734, hmean: 0.7155 2023/03/03 11:42:16 - mmengine - INFO - text score threshold: 0.98, recall: 0.5895, precision: 0.8891, hmean: 0.7089 2023/03/03 11:42:16 - mmengine - INFO - text score threshold: 0.99, recall: 0.5538, precision: 0.9025, hmean: 0.6864 2023/03/03 11:42:25 - mmengine - INFO - text score threshold: 0.80, recall: 0.7777, precision: 0.8785, hmean: 0.8250 2023/03/03 11:42:25 - mmengine - INFO - text score threshold: 0.81, recall: 0.7755, precision: 0.8793, hmean: 0.8241 2023/03/03 11:42:25 - mmengine - INFO - text score threshold: 0.82, recall: 0.7739, precision: 0.8807, hmean: 0.8238 2023/03/03 11:42:25 - mmengine - INFO - text score threshold: 0.83, recall: 0.7678, precision: 0.8843, hmean: 0.8220 2023/03/03 11:42:25 - mmengine - INFO - text score threshold: 0.84, recall: 0.7629, precision: 0.8876, hmean: 0.8205 2023/03/03 11:42:25 - mmengine - INFO - text score threshold: 0.85, recall: 0.7613, precision: 0.8937, hmean: 0.8222 2023/03/03 11:42:25 - mmengine - INFO - text score threshold: 0.86, recall: 0.7569, precision: 0.8966, hmean: 0.8208 2023/03/03 11:42:25 - mmengine - INFO - text score threshold: 0.87, recall: 0.7530, precision: 0.8991, hmean: 0.8196 2023/03/03 11:42:25 - mmengine - INFO - text score threshold: 0.88, recall: 0.7492, precision: 0.9022, hmean: 0.8186 2023/03/03 11:42:25 - mmengine - INFO - text score threshold: 0.89, recall: 0.7371, precision: 0.9038, hmean: 0.8120 2023/03/03 11:42:25 - mmengine - INFO - text score threshold: 0.90, recall: 0.7300, precision: 0.9054, hmean: 0.8083 2023/03/03 11:42:25 - mmengine - INFO - text score threshold: 0.91, recall: 0.7223, precision: 0.9095, hmean: 0.8051 2023/03/03 11:42:25 - mmengine - INFO - text score threshold: 0.92, recall: 0.7151, precision: 0.9131, hmean: 0.8021 2023/03/03 11:42:25 - mmengine - INFO - text score threshold: 0.93, recall: 0.7025, precision: 0.9162, hmean: 0.7953 2023/03/03 11:42:25 - mmengine - INFO - text score threshold: 0.94, recall: 0.6899, precision: 0.9216, hmean: 0.7891 2023/03/03 11:42:25 - mmengine - INFO - text score threshold: 0.95, recall: 0.6718, precision: 0.9252, hmean: 0.7784 2023/03/03 11:42:25 - mmengine - INFO - text score threshold: 0.96, recall: 0.6581, precision: 0.9287, hmean: 0.7703 2023/03/03 11:42:25 - mmengine - INFO - text score threshold: 0.97, recall: 0.6383, precision: 0.9349, hmean: 0.7586 2023/03/03 11:42:25 - mmengine - INFO - text score threshold: 0.98, recall: 0.6131, precision: 0.9394, hmean: 0.7419 2023/03/03 11:42:25 - mmengine - INFO - text score threshold: 0.99, recall: 0.5714, precision: 0.9455, hmean: 0.7123 2023/03/03 11:42:25 - mmengine - INFO - Epoch(val) [70][75/75] none/precision: 0.8049 none/recall: 0.6839 none/hmean: 0.7395 full/precision: 0.8785 full/recall: 0.7777 full/hmean: 0.8250 2023/03/03 11:42:30 - mmengine - INFO - Epoch(train) [71][10/79] lr: 1.0000e-06 eta: 1:21:25 time: 0.5193 data_time: 0.0326 memory: 40524 loss: 0.1297 loss_ce: 0.1297 2023/03/03 11:42:35 - mmengine - INFO - Epoch(train) [71][20/79] lr: 1.0000e-06 eta: 1:21:20 time: 0.4801 data_time: 0.0017 memory: 39123 loss: 0.1153 loss_ce: 0.1153 2023/03/03 11:42:40 - mmengine - INFO - Epoch(train) [71][30/79] lr: 1.0000e-06 eta: 1:21:14 time: 0.4270 data_time: 0.0017 memory: 37934 loss: 0.1400 loss_ce: 0.1400 2023/03/03 11:42:44 - mmengine - INFO - Epoch(train) [71][40/79] lr: 1.0000e-06 eta: 1:21:09 time: 0.4515 data_time: 0.0017 memory: 35718 loss: 0.1298 loss_ce: 0.1298 2023/03/03 11:42:49 - mmengine - INFO - Epoch(train) [71][50/79] lr: 1.0000e-06 eta: 1:21:05 time: 0.4902 data_time: 0.0016 memory: 38136 loss: 0.1163 loss_ce: 0.1163 2023/03/03 11:42:54 - mmengine - INFO - Epoch(train) [71][60/79] lr: 1.0000e-06 eta: 1:21:00 time: 0.4974 data_time: 0.0017 memory: 29941 loss: 0.1213 loss_ce: 0.1213 2023/03/03 11:42:59 - mmengine - INFO - Epoch(train) [71][70/79] lr: 1.0000e-06 eta: 1:20:56 time: 0.5167 data_time: 0.0014 memory: 50589 loss: 0.1347 loss_ce: 0.1347 2023/03/03 11:43:03 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:43:08 - mmengine - INFO - Epoch(train) [72][10/79] lr: 1.0000e-06 eta: 1:20:47 time: 0.5118 data_time: 0.0602 memory: 36046 loss: 0.1241 loss_ce: 0.1241 2023/03/03 11:43:13 - mmengine - INFO - Epoch(train) [72][20/79] lr: 1.0000e-06 eta: 1:20:42 time: 0.4601 data_time: 0.0017 memory: 39955 loss: 0.1322 loss_ce: 0.1322 2023/03/03 11:43:18 - mmengine - INFO - Epoch(train) [72][30/79] lr: 1.0000e-06 eta: 1:20:38 time: 0.5184 data_time: 0.0015 memory: 38136 loss: 0.1040 loss_ce: 0.1040 2023/03/03 11:43:22 - mmengine - INFO - Epoch(train) [72][40/79] lr: 1.0000e-06 eta: 1:20:32 time: 0.4111 data_time: 0.0016 memory: 30693 loss: 0.1221 loss_ce: 0.1221 2023/03/03 11:43:27 - mmengine - INFO - Epoch(train) [72][50/79] lr: 1.0000e-06 eta: 1:20:27 time: 0.4552 data_time: 0.0016 memory: 34589 loss: 0.1334 loss_ce: 0.1334 2023/03/03 11:43:31 - mmengine - INFO - Epoch(train) [72][60/79] lr: 1.0000e-06 eta: 1:20:22 time: 0.4405 data_time: 0.0015 memory: 41277 loss: 0.1172 loss_ce: 0.1172 2023/03/03 11:43:36 - mmengine - INFO - Epoch(train) [72][70/79] lr: 1.0000e-06 eta: 1:20:17 time: 0.4479 data_time: 0.0014 memory: 34921 loss: 0.1323 loss_ce: 0.1323 2023/03/03 11:43:40 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:43:45 - mmengine - INFO - Epoch(train) [73][10/79] lr: 1.0000e-06 eta: 1:20:08 time: 0.5074 data_time: 0.0635 memory: 39669 loss: 0.1298 loss_ce: 0.1298 2023/03/03 11:43:49 - mmengine - INFO - Epoch(train) [73][20/79] lr: 1.0000e-06 eta: 1:20:03 time: 0.4630 data_time: 0.0016 memory: 34120 loss: 0.1073 loss_ce: 0.1073 2023/03/03 11:43:55 - mmengine - INFO - Epoch(train) [73][30/79] lr: 1.0000e-06 eta: 1:19:59 time: 0.5108 data_time: 0.0016 memory: 28821 loss: 0.1302 loss_ce: 0.1302 2023/03/03 11:43:59 - mmengine - INFO - Epoch(train) [73][40/79] lr: 1.0000e-06 eta: 1:19:53 time: 0.4443 data_time: 0.0016 memory: 38082 loss: 0.1216 loss_ce: 0.1216 2023/03/03 11:44:04 - mmengine - INFO - Epoch(train) [73][50/79] lr: 1.0000e-06 eta: 1:19:49 time: 0.5119 data_time: 0.0017 memory: 38678 loss: 0.1188 loss_ce: 0.1188 2023/03/03 11:44:09 - mmengine - INFO - Epoch(train) [73][60/79] lr: 1.0000e-06 eta: 1:19:45 time: 0.5082 data_time: 0.0015 memory: 37535 loss: 0.1342 loss_ce: 0.1342 2023/03/03 11:44:14 - mmengine - INFO - Epoch(train) [73][70/79] lr: 1.0000e-06 eta: 1:19:40 time: 0.4551 data_time: 0.0014 memory: 32080 loss: 0.1059 loss_ce: 0.1059 2023/03/03 11:44:18 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:44:23 - mmengine - INFO - Epoch(train) [74][10/79] lr: 1.0000e-06 eta: 1:19:32 time: 0.5781 data_time: 0.0620 memory: 43206 loss: 0.1251 loss_ce: 0.1251 2023/03/03 11:44:28 - mmengine - INFO - Epoch(train) [74][20/79] lr: 1.0000e-06 eta: 1:19:27 time: 0.4765 data_time: 0.0016 memory: 40729 loss: 0.1160 loss_ce: 0.1160 2023/03/03 11:44:33 - mmengine - INFO - Epoch(train) [74][30/79] lr: 1.0000e-06 eta: 1:19:23 time: 0.5027 data_time: 0.0015 memory: 40524 loss: 0.1344 loss_ce: 0.1344 2023/03/03 11:44:38 - mmengine - INFO - Epoch(train) [74][40/79] lr: 1.0000e-06 eta: 1:19:17 time: 0.4375 data_time: 0.0015 memory: 25673 loss: 0.1278 loss_ce: 0.1278 2023/03/03 11:44:42 - mmengine - INFO - Epoch(train) [74][50/79] lr: 1.0000e-06 eta: 1:19:12 time: 0.4619 data_time: 0.0015 memory: 36647 loss: 0.1295 loss_ce: 0.1295 2023/03/03 11:44:48 - mmengine - INFO - Epoch(train) [74][60/79] lr: 1.0000e-06 eta: 1:19:09 time: 0.5506 data_time: 0.0016 memory: 39444 loss: 0.1186 loss_ce: 0.1186 2023/03/03 11:44:53 - mmengine - INFO - Epoch(train) [74][70/79] lr: 1.0000e-06 eta: 1:19:04 time: 0.4856 data_time: 0.0014 memory: 42016 loss: 0.1148 loss_ce: 0.1148 2023/03/03 11:44:57 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:45:02 - mmengine - INFO - Epoch(train) [75][10/79] lr: 1.0000e-06 eta: 1:18:57 time: 0.5681 data_time: 0.0831 memory: 40818 loss: 0.1076 loss_ce: 0.1076 2023/03/03 11:45:07 - mmengine - INFO - Epoch(train) [75][20/79] lr: 1.0000e-06 eta: 1:18:51 time: 0.4393 data_time: 0.0017 memory: 38082 loss: 0.1213 loss_ce: 0.1213 2023/03/03 11:45:11 - mmengine - INFO - Epoch(train) [75][30/79] lr: 1.0000e-06 eta: 1:18:46 time: 0.4589 data_time: 0.0018 memory: 33489 loss: 0.1457 loss_ce: 0.1457 2023/03/03 11:45:16 - mmengine - INFO - Epoch(train) [75][40/79] lr: 1.0000e-06 eta: 1:18:42 time: 0.4931 data_time: 0.0016 memory: 39955 loss: 0.1210 loss_ce: 0.1210 2023/03/03 11:45:21 - mmengine - INFO - Epoch(train) [75][50/79] lr: 1.0000e-06 eta: 1:18:37 time: 0.4785 data_time: 0.0015 memory: 39179 loss: 0.1193 loss_ce: 0.1193 2023/03/03 11:45:26 - mmengine - INFO - Epoch(train) [75][60/79] lr: 1.0000e-06 eta: 1:18:32 time: 0.4876 data_time: 0.0015 memory: 37934 loss: 0.1170 loss_ce: 0.1170 2023/03/03 11:45:30 - mmengine - INFO - Epoch(train) [75][70/79] lr: 1.0000e-06 eta: 1:18:27 time: 0.4544 data_time: 0.0013 memory: 36205 loss: 0.1347 loss_ce: 0.1347 2023/03/03 11:45:34 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:45:39 - mmengine - INFO - Epoch(train) [76][10/79] lr: 1.0000e-06 eta: 1:18:18 time: 0.5136 data_time: 0.0475 memory: 40524 loss: 0.1208 loss_ce: 0.1208 2023/03/03 11:45:44 - mmengine - INFO - Epoch(train) [76][20/79] lr: 1.0000e-06 eta: 1:18:14 time: 0.4883 data_time: 0.0015 memory: 49048 loss: 0.1173 loss_ce: 0.1173 2023/03/03 11:45:49 - mmengine - INFO - Epoch(train) [76][30/79] lr: 1.0000e-06 eta: 1:18:09 time: 0.4632 data_time: 0.0019 memory: 41928 loss: 0.1213 loss_ce: 0.1213 2023/03/03 11:45:53 - mmengine - INFO - Epoch(train) [76][40/79] lr: 1.0000e-06 eta: 1:18:03 time: 0.4504 data_time: 0.0019 memory: 36767 loss: 0.1301 loss_ce: 0.1301 2023/03/03 11:45:58 - mmengine - INFO - Epoch(train) [76][50/79] lr: 1.0000e-06 eta: 1:17:59 time: 0.4772 data_time: 0.0019 memory: 40524 loss: 0.1166 loss_ce: 0.1166 2023/03/03 11:46:03 - mmengine - INFO - Epoch(train) [76][60/79] lr: 1.0000e-06 eta: 1:17:54 time: 0.4827 data_time: 0.0016 memory: 37934 loss: 0.1151 loss_ce: 0.1151 2023/03/03 11:46:08 - mmengine - INFO - Epoch(train) [76][70/79] lr: 1.0000e-06 eta: 1:17:50 time: 0.5057 data_time: 0.0015 memory: 37911 loss: 0.1381 loss_ce: 0.1381 2023/03/03 11:46:11 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:46:13 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:46:18 - mmengine - INFO - Epoch(train) [77][10/79] lr: 1.0000e-06 eta: 1:17:42 time: 0.5235 data_time: 0.0560 memory: 40948 loss: 0.1076 loss_ce: 0.1076 2023/03/03 11:46:23 - mmengine - INFO - Epoch(train) [77][20/79] lr: 1.0000e-06 eta: 1:17:37 time: 0.4699 data_time: 0.0016 memory: 35662 loss: 0.1420 loss_ce: 0.1420 2023/03/03 11:46:27 - mmengine - INFO - Epoch(train) [77][30/79] lr: 1.0000e-06 eta: 1:17:32 time: 0.4519 data_time: 0.0018 memory: 39301 loss: 0.1189 loss_ce: 0.1189 2023/03/03 11:46:32 - mmengine - INFO - Epoch(train) [77][40/79] lr: 1.0000e-06 eta: 1:17:27 time: 0.5059 data_time: 0.0016 memory: 32701 loss: 0.1244 loss_ce: 0.1244 2023/03/03 11:46:37 - mmengine - INFO - Epoch(train) [77][50/79] lr: 1.0000e-06 eta: 1:17:23 time: 0.4904 data_time: 0.0016 memory: 34625 loss: 0.1173 loss_ce: 0.1173 2023/03/03 11:46:42 - mmengine - INFO - Epoch(train) [77][60/79] lr: 1.0000e-06 eta: 1:17:18 time: 0.4505 data_time: 0.0016 memory: 48557 loss: 0.1169 loss_ce: 0.1169 2023/03/03 11:46:46 - mmengine - INFO - Epoch(train) [77][70/79] lr: 1.0000e-06 eta: 1:17:12 time: 0.4311 data_time: 0.0014 memory: 38588 loss: 0.1350 loss_ce: 0.1350 2023/03/03 11:46:50 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:46:55 - mmengine - INFO - Epoch(train) [78][10/79] lr: 1.0000e-06 eta: 1:17:03 time: 0.5263 data_time: 0.0457 memory: 40433 loss: 0.1293 loss_ce: 0.1293 2023/03/03 11:46:59 - mmengine - INFO - Epoch(train) [78][20/79] lr: 1.0000e-06 eta: 1:16:58 time: 0.4250 data_time: 0.0015 memory: 29068 loss: 0.1272 loss_ce: 0.1272 2023/03/03 11:47:04 - mmengine - INFO - Epoch(train) [78][30/79] lr: 1.0000e-06 eta: 1:16:53 time: 0.4764 data_time: 0.0015 memory: 23576 loss: 0.1297 loss_ce: 0.1297 2023/03/03 11:47:08 - mmengine - INFO - Epoch(train) [78][40/79] lr: 1.0000e-06 eta: 1:16:47 time: 0.4246 data_time: 0.0015 memory: 38851 loss: 0.1272 loss_ce: 0.1272 2023/03/03 11:47:13 - mmengine - INFO - Epoch(train) [78][50/79] lr: 1.0000e-06 eta: 1:16:43 time: 0.4810 data_time: 0.0016 memory: 33084 loss: 0.1201 loss_ce: 0.1201 2023/03/03 11:47:18 - mmengine - INFO - Epoch(train) [78][60/79] lr: 1.0000e-06 eta: 1:16:38 time: 0.4634 data_time: 0.0016 memory: 39123 loss: 0.1132 loss_ce: 0.1132 2023/03/03 11:47:23 - mmengine - INFO - Epoch(train) [78][70/79] lr: 1.0000e-06 eta: 1:16:33 time: 0.4774 data_time: 0.0016 memory: 40848 loss: 0.1260 loss_ce: 0.1260 2023/03/03 11:47:26 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:47:32 - mmengine - INFO - Epoch(train) [79][10/79] lr: 1.0000e-06 eta: 1:16:24 time: 0.5536 data_time: 0.0489 memory: 39059 loss: 0.1290 loss_ce: 0.1290 2023/03/03 11:47:36 - mmengine - INFO - Epoch(train) [79][20/79] lr: 1.0000e-06 eta: 1:16:19 time: 0.4672 data_time: 0.0016 memory: 30448 loss: 0.1325 loss_ce: 0.1325 2023/03/03 11:47:41 - mmengine - INFO - Epoch(train) [79][30/79] lr: 1.0000e-06 eta: 1:16:14 time: 0.4687 data_time: 0.0019 memory: 43393 loss: 0.1215 loss_ce: 0.1215 2023/03/03 11:47:46 - mmengine - INFO - Epoch(train) [79][40/79] lr: 1.0000e-06 eta: 1:16:09 time: 0.4513 data_time: 0.0018 memory: 38082 loss: 0.1233 loss_ce: 0.1233 2023/03/03 11:47:50 - mmengine - INFO - Epoch(train) [79][50/79] lr: 1.0000e-06 eta: 1:16:04 time: 0.4533 data_time: 0.0015 memory: 31777 loss: 0.1103 loss_ce: 0.1103 2023/03/03 11:47:55 - mmengine - INFO - Epoch(train) [79][60/79] lr: 1.0000e-06 eta: 1:15:59 time: 0.4664 data_time: 0.0018 memory: 33237 loss: 0.1290 loss_ce: 0.1290 2023/03/03 11:47:59 - mmengine - INFO - Epoch(train) [79][70/79] lr: 1.0000e-06 eta: 1:15:53 time: 0.4051 data_time: 0.0017 memory: 31618 loss: 0.1384 loss_ce: 0.1384 2023/03/03 11:48:03 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:48:08 - mmengine - INFO - Epoch(train) [80][10/79] lr: 1.0000e-06 eta: 1:15:44 time: 0.4804 data_time: 0.0597 memory: 42327 loss: 0.1132 loss_ce: 0.1132 2023/03/03 11:48:12 - mmengine - INFO - Epoch(train) [80][20/79] lr: 1.0000e-06 eta: 1:15:39 time: 0.4547 data_time: 0.0016 memory: 38082 loss: 0.1367 loss_ce: 0.1367 2023/03/03 11:48:17 - mmengine - INFO - Epoch(train) [80][30/79] lr: 1.0000e-06 eta: 1:15:35 time: 0.4895 data_time: 0.0020 memory: 40215 loss: 0.1223 loss_ce: 0.1223 2023/03/03 11:48:22 - mmengine - INFO - Epoch(train) [80][40/79] lr: 1.0000e-06 eta: 1:15:30 time: 0.5042 data_time: 0.0019 memory: 42963 loss: 0.1221 loss_ce: 0.1221 2023/03/03 11:48:27 - mmengine - INFO - Epoch(train) [80][50/79] lr: 1.0000e-06 eta: 1:15:25 time: 0.4247 data_time: 0.0016 memory: 30725 loss: 0.1175 loss_ce: 0.1175 2023/03/03 11:48:32 - mmengine - INFO - Epoch(train) [80][60/79] lr: 1.0000e-06 eta: 1:15:21 time: 0.5079 data_time: 0.0016 memory: 39245 loss: 0.1034 loss_ce: 0.1034 2023/03/03 11:48:37 - mmengine - INFO - Epoch(train) [80][70/79] lr: 1.0000e-06 eta: 1:15:16 time: 0.4987 data_time: 0.0014 memory: 52955 loss: 0.1130 loss_ce: 0.1130 2023/03/03 11:48:41 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:48:52 - mmengine - INFO - Epoch(val) [80][10/75] eta: 0:01:15 time: 1.1597 data_time: 0.0035 memory: 25847 2023/03/03 11:49:33 - mmengine - INFO - Epoch(val) [80][20/75] eta: 0:02:24 time: 4.0776 data_time: 0.0004 memory: 1077 2023/03/03 11:49:54 - mmengine - INFO - Epoch(val) [80][30/75] eta: 0:01:50 time: 2.1027 data_time: 0.0003 memory: 1020 2023/03/03 11:50:09 - mmengine - INFO - Epoch(val) [80][40/75] eta: 0:01:17 time: 1.4627 data_time: 0.0004 memory: 1019 2023/03/03 11:50:23 - mmengine - INFO - Epoch(val) [80][50/75] eta: 0:00:50 time: 1.3860 data_time: 0.0003 memory: 1077 2023/03/03 11:51:28 - mmengine - INFO - Epoch(val) [80][60/75] eta: 0:00:41 time: 6.4932 data_time: 0.0005 memory: 1045 2023/03/03 11:52:22 - mmengine - INFO - Epoch(val) [80][70/75] eta: 0:00:15 time: 5.4233 data_time: 0.0005 memory: 1077 2023/03/03 11:52:35 - mmengine - INFO - text score threshold: 0.80, recall: 0.6899, precision: 0.7600, hmean: 0.7232 2023/03/03 11:52:35 - mmengine - INFO - text score threshold: 0.81, recall: 0.6899, precision: 0.7674, hmean: 0.7266 2023/03/03 11:52:35 - mmengine - INFO - text score threshold: 0.82, recall: 0.6866, precision: 0.7717, hmean: 0.7267 2023/03/03 11:52:35 - mmengine - INFO - text score threshold: 0.83, recall: 0.6850, precision: 0.7776, hmean: 0.7283 2023/03/03 11:52:35 - mmengine - INFO - text score threshold: 0.84, recall: 0.6839, precision: 0.7841, hmean: 0.7306 2023/03/03 11:52:35 - mmengine - INFO - text score threshold: 0.85, recall: 0.6822, precision: 0.7887, hmean: 0.7316 2023/03/03 11:52:35 - mmengine - INFO - text score threshold: 0.86, recall: 0.6795, precision: 0.7931, hmean: 0.7319 2023/03/03 11:52:35 - mmengine - INFO - text score threshold: 0.87, recall: 0.6773, precision: 0.8013, hmean: 0.7341 2023/03/03 11:52:35 - mmengine - INFO - text score threshold: 0.88, recall: 0.6740, precision: 0.8058, hmean: 0.7340 2023/03/03 11:52:35 - mmengine - INFO - text score threshold: 0.89, recall: 0.6696, precision: 0.8133, hmean: 0.7345 2023/03/03 11:52:35 - mmengine - INFO - text score threshold: 0.90, recall: 0.6652, precision: 0.8189, hmean: 0.7341 2023/03/03 11:52:35 - mmengine - INFO - text score threshold: 0.91, recall: 0.6608, precision: 0.8258, hmean: 0.7341 2023/03/03 11:52:35 - mmengine - INFO - text score threshold: 0.92, recall: 0.6553, precision: 0.8309, hmean: 0.7327 2023/03/03 11:52:35 - mmengine - INFO - text score threshold: 0.93, recall: 0.6476, precision: 0.8369, hmean: 0.7302 2023/03/03 11:52:35 - mmengine - INFO - text score threshold: 0.94, recall: 0.6350, precision: 0.8445, hmean: 0.7249 2023/03/03 11:52:35 - mmengine - INFO - text score threshold: 0.95, recall: 0.6284, precision: 0.8507, hmean: 0.7229 2023/03/03 11:52:35 - mmengine - INFO - text score threshold: 0.96, recall: 0.6169, precision: 0.8626, hmean: 0.7194 2023/03/03 11:52:35 - mmengine - INFO - text score threshold: 0.97, recall: 0.6037, precision: 0.8716, hmean: 0.7134 2023/03/03 11:52:35 - mmengine - INFO - text score threshold: 0.98, recall: 0.5851, precision: 0.8906, hmean: 0.7062 2023/03/03 11:52:35 - mmengine - INFO - text score threshold: 0.99, recall: 0.5516, precision: 0.9079, hmean: 0.6862 2023/03/03 11:52:45 - mmengine - INFO - text score threshold: 0.80, recall: 0.7728, precision: 0.8817, hmean: 0.8236 2023/03/03 11:52:45 - mmengine - INFO - text score threshold: 0.81, recall: 0.7711, precision: 0.8864, hmean: 0.8248 2023/03/03 11:52:45 - mmengine - INFO - text score threshold: 0.82, recall: 0.7667, precision: 0.8875, hmean: 0.8227 2023/03/03 11:52:45 - mmengine - INFO - text score threshold: 0.83, recall: 0.7618, precision: 0.8892, hmean: 0.8206 2023/03/03 11:52:45 - mmengine - INFO - text score threshold: 0.84, recall: 0.7580, precision: 0.8933, hmean: 0.8201 2023/03/03 11:52:45 - mmengine - INFO - text score threshold: 0.85, recall: 0.7552, precision: 0.8958, hmean: 0.8195 2023/03/03 11:52:45 - mmengine - INFO - text score threshold: 0.86, recall: 0.7508, precision: 0.8976, hmean: 0.8177 2023/03/03 11:52:45 - mmengine - INFO - text score threshold: 0.87, recall: 0.7448, precision: 0.9017, hmean: 0.8157 2023/03/03 11:52:45 - mmengine - INFO - text score threshold: 0.88, recall: 0.7393, precision: 0.9034, hmean: 0.8132 2023/03/03 11:52:45 - mmengine - INFO - text score threshold: 0.89, recall: 0.7305, precision: 0.9054, hmean: 0.8086 2023/03/03 11:52:45 - mmengine - INFO - text score threshold: 0.90, recall: 0.7228, precision: 0.9070, hmean: 0.8045 2023/03/03 11:52:45 - mmengine - INFO - text score threshold: 0.91, recall: 0.7162, precision: 0.9113, hmean: 0.8021 2023/03/03 11:52:45 - mmengine - INFO - text score threshold: 0.92, recall: 0.7075, precision: 0.9135, hmean: 0.7974 2023/03/03 11:52:45 - mmengine - INFO - text score threshold: 0.93, recall: 0.6959, precision: 0.9155, hmean: 0.7908 2023/03/03 11:52:45 - mmengine - INFO - text score threshold: 0.94, recall: 0.6800, precision: 0.9191, hmean: 0.7817 2023/03/03 11:52:45 - mmengine - INFO - text score threshold: 0.95, recall: 0.6701, precision: 0.9222, hmean: 0.7762 2023/03/03 11:52:45 - mmengine - INFO - text score threshold: 0.96, recall: 0.6537, precision: 0.9283, hmean: 0.7671 2023/03/03 11:52:45 - mmengine - INFO - text score threshold: 0.97, recall: 0.6356, precision: 0.9324, hmean: 0.7559 2023/03/03 11:52:45 - mmengine - INFO - text score threshold: 0.98, recall: 0.6081, precision: 0.9374, hmean: 0.7377 2023/03/03 11:52:45 - mmengine - INFO - text score threshold: 0.99, recall: 0.5681, precision: 0.9469, hmean: 0.7101 2023/03/03 11:52:45 - mmengine - INFO - Epoch(val) [80][75/75] none/precision: 0.8133 none/recall: 0.6696 none/hmean: 0.7345 full/precision: 0.8864 full/recall: 0.7711 full/hmean: 0.8248 2023/03/03 11:52:50 - mmengine - INFO - Epoch(train) [81][10/79] lr: 1.0000e-06 eta: 1:15:08 time: 0.5254 data_time: 0.0450 memory: 31316 loss: 0.1149 loss_ce: 0.1149 2023/03/03 11:52:55 - mmengine - INFO - Epoch(train) [81][20/79] lr: 1.0000e-06 eta: 1:15:03 time: 0.4753 data_time: 0.0014 memory: 38334 loss: 0.1118 loss_ce: 0.1118 2023/03/03 11:52:59 - mmengine - INFO - Epoch(train) [81][30/79] lr: 1.0000e-06 eta: 1:14:58 time: 0.4481 data_time: 0.0014 memory: 32714 loss: 0.1201 loss_ce: 0.1201 2023/03/03 11:53:04 - mmengine - INFO - Epoch(train) [81][40/79] lr: 1.0000e-06 eta: 1:14:53 time: 0.5007 data_time: 0.0016 memory: 38851 loss: 0.1254 loss_ce: 0.1254 2023/03/03 11:53:09 - mmengine - INFO - Epoch(train) [81][50/79] lr: 1.0000e-06 eta: 1:14:49 time: 0.4934 data_time: 0.0019 memory: 46903 loss: 0.1244 loss_ce: 0.1244 2023/03/03 11:53:14 - mmengine - INFO - Epoch(train) [81][60/79] lr: 1.0000e-06 eta: 1:14:44 time: 0.4789 data_time: 0.0017 memory: 39786 loss: 0.1124 loss_ce: 0.1124 2023/03/03 11:53:18 - mmengine - INFO - Epoch(train) [81][70/79] lr: 1.0000e-06 eta: 1:14:38 time: 0.4206 data_time: 0.0014 memory: 40524 loss: 0.1126 loss_ce: 0.1126 2023/03/03 11:53:22 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:53:26 - mmengine - INFO - Epoch(train) [82][10/79] lr: 1.0000e-06 eta: 1:14:28 time: 0.4814 data_time: 0.0379 memory: 38082 loss: 0.1327 loss_ce: 0.1327 2023/03/03 11:53:31 - mmengine - INFO - Epoch(train) [82][20/79] lr: 1.0000e-06 eta: 1:14:24 time: 0.4690 data_time: 0.0015 memory: 29242 loss: 0.1196 loss_ce: 0.1196 2023/03/03 11:53:36 - mmengine - INFO - Epoch(train) [82][30/79] lr: 1.0000e-06 eta: 1:14:18 time: 0.4355 data_time: 0.0016 memory: 38334 loss: 0.1196 loss_ce: 0.1196 2023/03/03 11:53:41 - mmengine - INFO - Epoch(train) [82][40/79] lr: 1.0000e-06 eta: 1:14:14 time: 0.5051 data_time: 0.0015 memory: 34718 loss: 0.1162 loss_ce: 0.1162 2023/03/03 11:53:45 - mmengine - INFO - Epoch(train) [82][50/79] lr: 1.0000e-06 eta: 1:14:09 time: 0.4511 data_time: 0.0015 memory: 36310 loss: 0.1317 loss_ce: 0.1317 2023/03/03 11:53:50 - mmengine - INFO - Epoch(train) [82][60/79] lr: 1.0000e-06 eta: 1:14:04 time: 0.5014 data_time: 0.0016 memory: 39339 loss: 0.1208 loss_ce: 0.1208 2023/03/03 11:53:56 - mmengine - INFO - Epoch(train) [82][70/79] lr: 1.0000e-06 eta: 1:14:01 time: 0.5453 data_time: 0.0013 memory: 39123 loss: 0.1123 loss_ce: 0.1123 2023/03/03 11:53:59 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:54:04 - mmengine - INFO - Epoch(train) [83][10/79] lr: 1.0000e-06 eta: 1:13:51 time: 0.5087 data_time: 0.0474 memory: 42016 loss: 0.1046 loss_ce: 0.1046 2023/03/03 11:54:09 - mmengine - INFO - Epoch(train) [83][20/79] lr: 1.0000e-06 eta: 1:13:46 time: 0.4631 data_time: 0.0016 memory: 31438 loss: 0.1155 loss_ce: 0.1155 2023/03/03 11:54:13 - mmengine - INFO - Epoch(train) [83][30/79] lr: 1.0000e-06 eta: 1:13:41 time: 0.4398 data_time: 0.0019 memory: 40553 loss: 0.1168 loss_ce: 0.1168 2023/03/03 11:54:18 - mmengine - INFO - Epoch(train) [83][40/79] lr: 1.0000e-06 eta: 1:13:36 time: 0.4692 data_time: 0.0019 memory: 38793 loss: 0.1090 loss_ce: 0.1090 2023/03/03 11:54:23 - mmengine - INFO - Epoch(train) [83][50/79] lr: 1.0000e-06 eta: 1:13:31 time: 0.4371 data_time: 0.0019 memory: 39123 loss: 0.1147 loss_ce: 0.1147 2023/03/03 11:54:27 - mmengine - INFO - Epoch(train) [83][60/79] lr: 1.0000e-06 eta: 1:13:26 time: 0.4491 data_time: 0.0020 memory: 34693 loss: 0.1167 loss_ce: 0.1167 2023/03/03 11:54:32 - mmengine - INFO - Epoch(train) [83][70/79] lr: 1.0000e-06 eta: 1:13:21 time: 0.4602 data_time: 0.0019 memory: 38588 loss: 0.1241 loss_ce: 0.1241 2023/03/03 11:54:36 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:54:41 - mmengine - INFO - Epoch(train) [84][10/79] lr: 1.0000e-06 eta: 1:13:12 time: 0.5127 data_time: 0.0674 memory: 37934 loss: 0.1310 loss_ce: 0.1310 2023/03/03 11:54:46 - mmengine - INFO - Epoch(train) [84][20/79] lr: 1.0000e-06 eta: 1:13:08 time: 0.4819 data_time: 0.0019 memory: 37934 loss: 0.1244 loss_ce: 0.1244 2023/03/03 11:54:51 - mmengine - INFO - Epoch(train) [84][30/79] lr: 1.0000e-06 eta: 1:13:03 time: 0.4753 data_time: 0.0019 memory: 39490 loss: 0.1183 loss_ce: 0.1183 2023/03/03 11:54:56 - mmengine - INFO - Epoch(train) [84][40/79] lr: 1.0000e-06 eta: 1:12:59 time: 0.5006 data_time: 0.0018 memory: 52955 loss: 0.1124 loss_ce: 0.1124 2023/03/03 11:55:00 - mmengine - INFO - Epoch(train) [84][50/79] lr: 1.0000e-06 eta: 1:12:54 time: 0.4758 data_time: 0.0017 memory: 28762 loss: 0.0924 loss_ce: 0.0924 2023/03/03 11:55:05 - mmengine - INFO - Epoch(train) [84][60/79] lr: 1.0000e-06 eta: 1:12:49 time: 0.4885 data_time: 0.0016 memory: 44609 loss: 0.1392 loss_ce: 0.1392 2023/03/03 11:55:10 - mmengine - INFO - Epoch(train) [84][70/79] lr: 1.0000e-06 eta: 1:12:45 time: 0.5201 data_time: 0.0014 memory: 27896 loss: 0.1086 loss_ce: 0.1086 2023/03/03 11:55:14 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:55:20 - mmengine - INFO - Epoch(train) [85][10/79] lr: 1.0000e-06 eta: 1:12:36 time: 0.5271 data_time: 0.0298 memory: 37934 loss: 0.1388 loss_ce: 0.1388 2023/03/03 11:55:24 - mmengine - INFO - Epoch(train) [85][20/79] lr: 1.0000e-06 eta: 1:12:31 time: 0.4670 data_time: 0.0015 memory: 31452 loss: 0.1051 loss_ce: 0.1051 2023/03/03 11:55:29 - mmengine - INFO - Epoch(train) [85][30/79] lr: 1.0000e-06 eta: 1:12:26 time: 0.4269 data_time: 0.0017 memory: 34113 loss: 0.1175 loss_ce: 0.1175 2023/03/03 11:55:34 - mmengine - INFO - Epoch(train) [85][40/79] lr: 1.0000e-06 eta: 1:12:22 time: 0.5011 data_time: 0.0016 memory: 39045 loss: 0.1313 loss_ce: 0.1313 2023/03/03 11:55:38 - mmengine - INFO - Epoch(train) [85][50/79] lr: 1.0000e-06 eta: 1:12:16 time: 0.4405 data_time: 0.0015 memory: 29249 loss: 0.1165 loss_ce: 0.1165 2023/03/03 11:55:42 - mmengine - INFO - Epoch(train) [85][60/79] lr: 1.0000e-06 eta: 1:12:11 time: 0.4356 data_time: 0.0019 memory: 40524 loss: 0.1294 loss_ce: 0.1294 2023/03/03 11:55:48 - mmengine - INFO - Epoch(train) [85][70/79] lr: 1.0000e-06 eta: 1:12:07 time: 0.5132 data_time: 0.0017 memory: 38588 loss: 0.1234 loss_ce: 0.1234 2023/03/03 11:55:52 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:55:57 - mmengine - INFO - Epoch(train) [86][10/79] lr: 1.0000e-06 eta: 1:11:58 time: 0.4876 data_time: 0.0434 memory: 42016 loss: 0.1089 loss_ce: 0.1089 2023/03/03 11:56:02 - mmengine - INFO - Epoch(train) [86][20/79] lr: 1.0000e-06 eta: 1:11:53 time: 0.4940 data_time: 0.0015 memory: 39955 loss: 0.1163 loss_ce: 0.1163 2023/03/03 11:56:06 - mmengine - INFO - Epoch(train) [86][30/79] lr: 1.0000e-06 eta: 1:11:48 time: 0.4377 data_time: 0.0016 memory: 32641 loss: 0.1235 loss_ce: 0.1235 2023/03/03 11:56:11 - mmengine - INFO - Epoch(train) [86][40/79] lr: 1.0000e-06 eta: 1:11:43 time: 0.4929 data_time: 0.0016 memory: 30207 loss: 0.1132 loss_ce: 0.1132 2023/03/03 11:56:15 - mmengine - INFO - Epoch(train) [86][50/79] lr: 1.0000e-06 eta: 1:11:38 time: 0.4643 data_time: 0.0016 memory: 30153 loss: 0.1128 loss_ce: 0.1128 2023/03/03 11:56:20 - mmengine - INFO - Epoch(train) [86][60/79] lr: 1.0000e-06 eta: 1:11:33 time: 0.4334 data_time: 0.0018 memory: 37934 loss: 0.1329 loss_ce: 0.1329 2023/03/03 11:56:25 - mmengine - INFO - Epoch(train) [86][70/79] lr: 1.0000e-06 eta: 1:11:29 time: 0.5009 data_time: 0.0015 memory: 39640 loss: 0.1226 loss_ce: 0.1226 2023/03/03 11:56:29 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:56:34 - mmengine - INFO - Epoch(train) [87][10/79] lr: 1.0000e-06 eta: 1:11:20 time: 0.5538 data_time: 0.0767 memory: 39123 loss: 0.1202 loss_ce: 0.1202 2023/03/03 11:56:39 - mmengine - INFO - Epoch(train) [87][20/79] lr: 1.0000e-06 eta: 1:11:15 time: 0.4580 data_time: 0.0016 memory: 28822 loss: 0.1129 loss_ce: 0.1129 2023/03/03 11:56:43 - mmengine - INFO - Epoch(train) [87][30/79] lr: 1.0000e-06 eta: 1:11:10 time: 0.4672 data_time: 0.0016 memory: 30373 loss: 0.1218 loss_ce: 0.1218 2023/03/03 11:56:48 - mmengine - INFO - Epoch(train) [87][40/79] lr: 1.0000e-06 eta: 1:11:06 time: 0.5000 data_time: 0.0015 memory: 42963 loss: 0.1412 loss_ce: 0.1412 2023/03/03 11:56:53 - mmengine - INFO - Epoch(train) [87][50/79] lr: 1.0000e-06 eta: 1:11:01 time: 0.4539 data_time: 0.0017 memory: 36592 loss: 0.1197 loss_ce: 0.1197 2023/03/03 11:56:58 - mmengine - INFO - Epoch(train) [87][60/79] lr: 1.0000e-06 eta: 1:10:56 time: 0.5062 data_time: 0.0019 memory: 37934 loss: 0.1159 loss_ce: 0.1159 2023/03/03 11:57:03 - mmengine - INFO - Epoch(train) [87][70/79] lr: 1.0000e-06 eta: 1:10:51 time: 0.4465 data_time: 0.0014 memory: 36604 loss: 0.1064 loss_ce: 0.1064 2023/03/03 11:57:06 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:57:12 - mmengine - INFO - Epoch(train) [88][10/79] lr: 1.0000e-06 eta: 1:10:43 time: 0.6007 data_time: 0.0405 memory: 48938 loss: 0.1034 loss_ce: 0.1034 2023/03/03 11:57:17 - mmengine - INFO - Epoch(train) [88][20/79] lr: 1.0000e-06 eta: 1:10:39 time: 0.4895 data_time: 0.0016 memory: 40236 loss: 0.1098 loss_ce: 0.1098 2023/03/03 11:57:22 - mmengine - INFO - Epoch(train) [88][30/79] lr: 1.0000e-06 eta: 1:10:34 time: 0.4615 data_time: 0.0015 memory: 40818 loss: 0.1236 loss_ce: 0.1236 2023/03/03 11:57:27 - mmengine - INFO - Epoch(train) [88][40/79] lr: 1.0000e-06 eta: 1:10:29 time: 0.4652 data_time: 0.0016 memory: 37934 loss: 0.1367 loss_ce: 0.1367 2023/03/03 11:57:32 - mmengine - INFO - Epoch(train) [88][50/79] lr: 1.0000e-06 eta: 1:10:25 time: 0.5103 data_time: 0.0017 memory: 38851 loss: 0.1132 loss_ce: 0.1132 2023/03/03 11:57:36 - mmengine - INFO - Epoch(train) [88][60/79] lr: 1.0000e-06 eta: 1:10:20 time: 0.4589 data_time: 0.0015 memory: 33155 loss: 0.1115 loss_ce: 0.1115 2023/03/03 11:57:41 - mmengine - INFO - Epoch(train) [88][70/79] lr: 1.0000e-06 eta: 1:10:15 time: 0.4819 data_time: 0.0016 memory: 32642 loss: 0.1122 loss_ce: 0.1122 2023/03/03 11:57:45 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:57:51 - mmengine - INFO - Epoch(train) [89][10/79] lr: 1.0000e-06 eta: 1:10:07 time: 0.5905 data_time: 0.0494 memory: 41445 loss: 0.1143 loss_ce: 0.1143 2023/03/03 11:57:56 - mmengine - INFO - Epoch(train) [89][20/79] lr: 1.0000e-06 eta: 1:10:03 time: 0.4873 data_time: 0.0015 memory: 31572 loss: 0.1075 loss_ce: 0.1075 2023/03/03 11:58:01 - mmengine - INFO - Epoch(train) [89][30/79] lr: 1.0000e-06 eta: 1:09:58 time: 0.4654 data_time: 0.0016 memory: 37053 loss: 0.1032 loss_ce: 0.1032 2023/03/03 11:58:05 - mmengine - INFO - Epoch(train) [89][40/79] lr: 1.0000e-06 eta: 1:09:53 time: 0.4444 data_time: 0.0015 memory: 32762 loss: 0.1358 loss_ce: 0.1358 2023/03/03 11:58:09 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:58:10 - mmengine - INFO - Epoch(train) [89][50/79] lr: 1.0000e-06 eta: 1:09:48 time: 0.5128 data_time: 0.0015 memory: 36004 loss: 0.1248 loss_ce: 0.1248 2023/03/03 11:58:15 - mmengine - INFO - Epoch(train) [89][60/79] lr: 1.0000e-06 eta: 1:09:43 time: 0.4371 data_time: 0.0016 memory: 37728 loss: 0.1193 loss_ce: 0.1193 2023/03/03 11:58:19 - mmengine - INFO - Epoch(train) [89][70/79] lr: 1.0000e-06 eta: 1:09:38 time: 0.4793 data_time: 0.0013 memory: 38588 loss: 0.1207 loss_ce: 0.1207 2023/03/03 11:58:23 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:58:28 - mmengine - INFO - Epoch(train) [90][10/79] lr: 1.0000e-06 eta: 1:09:28 time: 0.4678 data_time: 0.0478 memory: 32658 loss: 0.1134 loss_ce: 0.1134 2023/03/03 11:58:33 - mmengine - INFO - Epoch(train) [90][20/79] lr: 1.0000e-06 eta: 1:09:24 time: 0.4985 data_time: 0.0019 memory: 38136 loss: 0.1326 loss_ce: 0.1326 2023/03/03 11:58:37 - mmengine - INFO - Epoch(train) [90][30/79] lr: 1.0000e-06 eta: 1:09:19 time: 0.4555 data_time: 0.0017 memory: 35447 loss: 0.1257 loss_ce: 0.1257 2023/03/03 11:58:42 - mmengine - INFO - Epoch(train) [90][40/79] lr: 1.0000e-06 eta: 1:09:14 time: 0.4993 data_time: 0.0017 memory: 42647 loss: 0.1033 loss_ce: 0.1033 2023/03/03 11:58:47 - mmengine - INFO - Epoch(train) [90][50/79] lr: 1.0000e-06 eta: 1:09:09 time: 0.4447 data_time: 0.0016 memory: 38334 loss: 0.1420 loss_ce: 0.1420 2023/03/03 11:58:51 - mmengine - INFO - Epoch(train) [90][60/79] lr: 1.0000e-06 eta: 1:09:04 time: 0.4394 data_time: 0.0015 memory: 36467 loss: 0.1268 loss_ce: 0.1268 2023/03/03 11:58:56 - mmengine - INFO - Epoch(train) [90][70/79] lr: 1.0000e-06 eta: 1:08:59 time: 0.4699 data_time: 0.0014 memory: 26876 loss: 0.1332 loss_ce: 0.1332 2023/03/03 11:59:00 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 11:59:12 - mmengine - INFO - Epoch(val) [90][10/75] eta: 0:01:16 time: 1.1807 data_time: 0.0032 memory: 34704 2023/03/03 12:00:13 - mmengine - INFO - Epoch(val) [90][20/75] eta: 0:03:18 time: 6.0538 data_time: 0.0004 memory: 1077 2023/03/03 12:00:32 - mmengine - INFO - Epoch(val) [90][30/75] eta: 0:02:18 time: 1.9859 data_time: 0.0003 memory: 1020 2023/03/03 12:00:47 - mmengine - INFO - Epoch(val) [90][40/75] eta: 0:01:33 time: 1.4977 data_time: 0.0004 memory: 1019 2023/03/03 12:01:02 - mmengine - INFO - Epoch(val) [90][50/75] eta: 0:01:00 time: 1.4287 data_time: 0.0004 memory: 1077 2023/03/03 12:01:46 - mmengine - INFO - Epoch(val) [90][60/75] eta: 0:00:41 time: 4.3828 data_time: 0.0005 memory: 1045 2023/03/03 12:02:15 - mmengine - INFO - Epoch(val) [90][70/75] eta: 0:00:13 time: 2.9796 data_time: 0.0005 memory: 1077 2023/03/03 12:02:29 - mmengine - INFO - text score threshold: 0.80, recall: 0.6910, precision: 0.7589, hmean: 0.7234 2023/03/03 12:02:29 - mmengine - INFO - text score threshold: 0.81, recall: 0.6899, precision: 0.7614, hmean: 0.7239 2023/03/03 12:02:29 - mmengine - INFO - text score threshold: 0.82, recall: 0.6888, precision: 0.7671, hmean: 0.7259 2023/03/03 12:02:29 - mmengine - INFO - text score threshold: 0.83, recall: 0.6877, precision: 0.7725, hmean: 0.7276 2023/03/03 12:02:29 - mmengine - INFO - text score threshold: 0.84, recall: 0.6866, precision: 0.7775, hmean: 0.7292 2023/03/03 12:02:29 - mmengine - INFO - text score threshold: 0.85, recall: 0.6839, precision: 0.7841, hmean: 0.7306 2023/03/03 12:02:29 - mmengine - INFO - text score threshold: 0.86, recall: 0.6822, precision: 0.7922, hmean: 0.7331 2023/03/03 12:02:29 - mmengine - INFO - text score threshold: 0.87, recall: 0.6817, precision: 0.7962, hmean: 0.7345 2023/03/03 12:02:29 - mmengine - INFO - text score threshold: 0.88, recall: 0.6773, precision: 0.8013, hmean: 0.7341 2023/03/03 12:02:29 - mmengine - INFO - text score threshold: 0.89, recall: 0.6745, precision: 0.8091, hmean: 0.7357 2023/03/03 12:02:29 - mmengine - INFO - text score threshold: 0.90, recall: 0.6701, precision: 0.8156, hmean: 0.7358 2023/03/03 12:02:29 - mmengine - INFO - text score threshold: 0.91, recall: 0.6679, precision: 0.8201, hmean: 0.7362 2023/03/03 12:02:29 - mmengine - INFO - text score threshold: 0.92, recall: 0.6630, precision: 0.8268, hmean: 0.7359 2023/03/03 12:02:29 - mmengine - INFO - text score threshold: 0.93, recall: 0.6542, precision: 0.8347, hmean: 0.7335 2023/03/03 12:02:29 - mmengine - INFO - text score threshold: 0.94, recall: 0.6460, precision: 0.8395, hmean: 0.7301 2023/03/03 12:02:29 - mmengine - INFO - text score threshold: 0.95, recall: 0.6312, precision: 0.8468, hmean: 0.7233 2023/03/03 12:02:29 - mmengine - INFO - text score threshold: 0.96, recall: 0.6207, precision: 0.8594, hmean: 0.7208 2023/03/03 12:02:29 - mmengine - INFO - text score threshold: 0.97, recall: 0.6037, precision: 0.8709, hmean: 0.7131 2023/03/03 12:02:29 - mmengine - INFO - text score threshold: 0.98, recall: 0.5856, precision: 0.8936, hmean: 0.7076 2023/03/03 12:02:29 - mmengine - INFO - text score threshold: 0.99, recall: 0.5549, precision: 0.9075, hmean: 0.6887 2023/03/03 12:02:39 - mmengine - INFO - text score threshold: 0.80, recall: 0.7744, precision: 0.8830, hmean: 0.8251 2023/03/03 12:02:39 - mmengine - INFO - text score threshold: 0.81, recall: 0.7728, precision: 0.8844, hmean: 0.8248 2023/03/03 12:02:39 - mmengine - INFO - text score threshold: 0.82, recall: 0.7700, precision: 0.8885, hmean: 0.8251 2023/03/03 12:02:39 - mmengine - INFO - text score threshold: 0.83, recall: 0.7667, precision: 0.8915, hmean: 0.8244 2023/03/03 12:02:39 - mmengine - INFO - text score threshold: 0.84, recall: 0.7629, precision: 0.8922, hmean: 0.8225 2023/03/03 12:02:39 - mmengine - INFO - text score threshold: 0.85, recall: 0.7591, precision: 0.8975, hmean: 0.8225 2023/03/03 12:02:39 - mmengine - INFO - text score threshold: 0.86, recall: 0.7541, precision: 0.9004, hmean: 0.8208 2023/03/03 12:02:39 - mmengine - INFO - text score threshold: 0.87, recall: 0.7519, precision: 0.9025, hmean: 0.8204 2023/03/03 12:02:39 - mmengine - INFO - text score threshold: 0.88, recall: 0.7448, precision: 0.9041, hmean: 0.8167 2023/03/03 12:02:39 - mmengine - INFO - text score threshold: 0.89, recall: 0.7404, precision: 0.9090, hmean: 0.8161 2023/03/03 12:02:39 - mmengine - INFO - text score threshold: 0.90, recall: 0.7327, precision: 0.9106, hmean: 0.8120 2023/03/03 12:02:39 - mmengine - INFO - text score threshold: 0.91, recall: 0.7289, precision: 0.9133, hmean: 0.8107 2023/03/03 12:02:39 - mmengine - INFO - text score threshold: 0.92, recall: 0.7201, precision: 0.9156, hmean: 0.8061 2023/03/03 12:02:39 - mmengine - INFO - text score threshold: 0.93, recall: 0.7064, precision: 0.9186, hmean: 0.7986 2023/03/03 12:02:39 - mmengine - INFO - text score threshold: 0.94, recall: 0.6937, precision: 0.9193, hmean: 0.7907 2023/03/03 12:02:39 - mmengine - INFO - text score threshold: 0.95, recall: 0.6734, precision: 0.9205, hmean: 0.7778 2023/03/03 12:02:39 - mmengine - INFO - text score threshold: 0.96, recall: 0.6586, precision: 0.9281, hmean: 0.7705 2023/03/03 12:02:39 - mmengine - INFO - text score threshold: 0.97, recall: 0.6350, precision: 0.9323, hmean: 0.7555 2023/03/03 12:02:39 - mmengine - INFO - text score threshold: 0.98, recall: 0.6081, precision: 0.9406, hmean: 0.7387 2023/03/03 12:02:39 - mmengine - INFO - text score threshold: 0.99, recall: 0.5719, precision: 0.9490, hmean: 0.7137 2023/03/03 12:02:39 - mmengine - INFO - Epoch(val) [90][75/75] none/precision: 0.8201 none/recall: 0.6679 none/hmean: 0.7362 full/precision: 0.8830 full/recall: 0.7744 full/hmean: 0.8251 2023/03/03 12:02:44 - mmengine - INFO - Epoch(train) [91][10/79] lr: 1.0000e-06 eta: 1:08:51 time: 0.5381 data_time: 0.0334 memory: 38334 loss: 0.1378 loss_ce: 0.1378 2023/03/03 12:02:49 - mmengine - INFO - Epoch(train) [91][20/79] lr: 1.0000e-06 eta: 1:08:47 time: 0.5103 data_time: 0.0015 memory: 38886 loss: 0.1086 loss_ce: 0.1086 2023/03/03 12:02:54 - mmengine - INFO - Epoch(train) [91][30/79] lr: 1.0000e-06 eta: 1:08:42 time: 0.4462 data_time: 0.0016 memory: 38588 loss: 0.1417 loss_ce: 0.1417 2023/03/03 12:02:58 - mmengine - INFO - Epoch(train) [91][40/79] lr: 1.0000e-06 eta: 1:08:37 time: 0.4542 data_time: 0.0015 memory: 30626 loss: 0.1206 loss_ce: 0.1206 2023/03/03 12:03:03 - mmengine - INFO - Epoch(train) [91][50/79] lr: 1.0000e-06 eta: 1:08:32 time: 0.4797 data_time: 0.0015 memory: 40524 loss: 0.1333 loss_ce: 0.1333 2023/03/03 12:03:08 - mmengine - INFO - Epoch(train) [91][60/79] lr: 1.0000e-06 eta: 1:08:27 time: 0.4920 data_time: 0.0015 memory: 39123 loss: 0.1260 loss_ce: 0.1260 2023/03/03 12:03:12 - mmengine - INFO - Epoch(train) [91][70/79] lr: 1.0000e-06 eta: 1:08:22 time: 0.4663 data_time: 0.0013 memory: 36164 loss: 0.1279 loss_ce: 0.1279 2023/03/03 12:03:16 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:03:21 - mmengine - INFO - Epoch(train) [92][10/79] lr: 1.0000e-06 eta: 1:08:13 time: 0.5122 data_time: 0.0457 memory: 39390 loss: 0.1270 loss_ce: 0.1270 2023/03/03 12:03:26 - mmengine - INFO - Epoch(train) [92][20/79] lr: 1.0000e-06 eta: 1:08:08 time: 0.4734 data_time: 0.0016 memory: 35216 loss: 0.1110 loss_ce: 0.1110 2023/03/03 12:03:30 - mmengine - INFO - Epoch(train) [92][30/79] lr: 1.0000e-06 eta: 1:08:03 time: 0.4506 data_time: 0.0016 memory: 32691 loss: 0.1289 loss_ce: 0.1289 2023/03/03 12:03:35 - mmengine - INFO - Epoch(train) [92][40/79] lr: 1.0000e-06 eta: 1:07:58 time: 0.4782 data_time: 0.0015 memory: 38082 loss: 0.1278 loss_ce: 0.1278 2023/03/03 12:03:41 - mmengine - INFO - Epoch(train) [92][50/79] lr: 1.0000e-06 eta: 1:07:54 time: 0.5337 data_time: 0.0015 memory: 31271 loss: 0.1067 loss_ce: 0.1067 2023/03/03 12:03:45 - mmengine - INFO - Epoch(train) [92][60/79] lr: 1.0000e-06 eta: 1:07:49 time: 0.4547 data_time: 0.0015 memory: 28740 loss: 0.1344 loss_ce: 0.1344 2023/03/03 12:03:50 - mmengine - INFO - Epoch(train) [92][70/79] lr: 1.0000e-06 eta: 1:07:45 time: 0.4641 data_time: 0.0013 memory: 28629 loss: 0.1226 loss_ce: 0.1226 2023/03/03 12:03:54 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:03:59 - mmengine - INFO - Epoch(train) [93][10/79] lr: 1.0000e-06 eta: 1:07:36 time: 0.4960 data_time: 0.0730 memory: 45998 loss: 0.1143 loss_ce: 0.1143 2023/03/03 12:04:05 - mmengine - INFO - Epoch(train) [93][20/79] lr: 1.0000e-06 eta: 1:07:32 time: 0.5270 data_time: 0.0018 memory: 40299 loss: 0.1005 loss_ce: 0.1005 2023/03/03 12:04:09 - mmengine - INFO - Epoch(train) [93][30/79] lr: 1.0000e-06 eta: 1:07:27 time: 0.4507 data_time: 0.0015 memory: 31994 loss: 0.1404 loss_ce: 0.1404 2023/03/03 12:04:13 - mmengine - INFO - Epoch(train) [93][40/79] lr: 1.0000e-06 eta: 1:07:22 time: 0.4229 data_time: 0.0015 memory: 32885 loss: 0.1132 loss_ce: 0.1132 2023/03/03 12:04:18 - mmengine - INFO - Epoch(train) [93][50/79] lr: 1.0000e-06 eta: 1:07:17 time: 0.4784 data_time: 0.0015 memory: 38082 loss: 0.1130 loss_ce: 0.1130 2023/03/03 12:04:23 - mmengine - INFO - Epoch(train) [93][60/79] lr: 1.0000e-06 eta: 1:07:12 time: 0.4920 data_time: 0.0015 memory: 39390 loss: 0.1300 loss_ce: 0.1300 2023/03/03 12:04:28 - mmengine - INFO - Epoch(train) [93][70/79] lr: 1.0000e-06 eta: 1:07:07 time: 0.4501 data_time: 0.0013 memory: 34096 loss: 0.1224 loss_ce: 0.1224 2023/03/03 12:04:32 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:04:36 - mmengine - INFO - Epoch(train) [94][10/79] lr: 1.0000e-06 eta: 1:06:58 time: 0.4560 data_time: 0.0384 memory: 41506 loss: 0.1366 loss_ce: 0.1366 2023/03/03 12:04:41 - mmengine - INFO - Epoch(train) [94][20/79] lr: 1.0000e-06 eta: 1:06:53 time: 0.5085 data_time: 0.0018 memory: 39123 loss: 0.1199 loss_ce: 0.1199 2023/03/03 12:04:46 - mmengine - INFO - Epoch(train) [94][30/79] lr: 1.0000e-06 eta: 1:06:49 time: 0.5080 data_time: 0.0016 memory: 42327 loss: 0.1291 loss_ce: 0.1291 2023/03/03 12:04:51 - mmengine - INFO - Epoch(train) [94][40/79] lr: 1.0000e-06 eta: 1:06:44 time: 0.4589 data_time: 0.0016 memory: 38018 loss: 0.1207 loss_ce: 0.1207 2023/03/03 12:04:56 - mmengine - INFO - Epoch(train) [94][50/79] lr: 1.0000e-06 eta: 1:06:39 time: 0.4875 data_time: 0.0016 memory: 37423 loss: 0.1301 loss_ce: 0.1301 2023/03/03 12:05:00 - mmengine - INFO - Epoch(train) [94][60/79] lr: 1.0000e-06 eta: 1:06:34 time: 0.4123 data_time: 0.0018 memory: 30799 loss: 0.1209 loss_ce: 0.1209 2023/03/03 12:05:05 - mmengine - INFO - Epoch(train) [94][70/79] lr: 1.0000e-06 eta: 1:06:29 time: 0.4920 data_time: 0.0015 memory: 31810 loss: 0.1136 loss_ce: 0.1136 2023/03/03 12:05:09 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:05:14 - mmengine - INFO - Epoch(train) [95][10/79] lr: 1.0000e-06 eta: 1:06:20 time: 0.5037 data_time: 0.0625 memory: 35801 loss: 0.1121 loss_ce: 0.1121 2023/03/03 12:05:19 - mmengine - INFO - Epoch(train) [95][20/79] lr: 1.0000e-06 eta: 1:06:15 time: 0.4881 data_time: 0.0017 memory: 36297 loss: 0.1162 loss_ce: 0.1162 2023/03/03 12:05:23 - mmengine - INFO - Epoch(train) [95][30/79] lr: 1.0000e-06 eta: 1:06:11 time: 0.4798 data_time: 0.0018 memory: 38082 loss: 0.1071 loss_ce: 0.1071 2023/03/03 12:05:28 - mmengine - INFO - Epoch(train) [95][40/79] lr: 1.0000e-06 eta: 1:06:06 time: 0.4656 data_time: 0.0018 memory: 36767 loss: 0.1327 loss_ce: 0.1327 2023/03/03 12:05:33 - mmengine - INFO - Epoch(train) [95][50/79] lr: 1.0000e-06 eta: 1:06:01 time: 0.4715 data_time: 0.0017 memory: 38247 loss: 0.1094 loss_ce: 0.1094 2023/03/03 12:05:38 - mmengine - INFO - Epoch(train) [95][60/79] lr: 1.0000e-06 eta: 1:05:56 time: 0.4974 data_time: 0.0016 memory: 35069 loss: 0.1347 loss_ce: 0.1347 2023/03/03 12:05:43 - mmengine - INFO - Epoch(train) [95][70/79] lr: 1.0000e-06 eta: 1:05:52 time: 0.4768 data_time: 0.0014 memory: 35565 loss: 0.1336 loss_ce: 0.1336 2023/03/03 12:05:46 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:05:51 - mmengine - INFO - Epoch(train) [96][10/79] lr: 1.0000e-06 eta: 1:05:42 time: 0.4975 data_time: 0.0605 memory: 38588 loss: 0.1010 loss_ce: 0.1010 2023/03/03 12:05:56 - mmengine - INFO - Epoch(train) [96][20/79] lr: 1.0000e-06 eta: 1:05:38 time: 0.4712 data_time: 0.0019 memory: 39300 loss: 0.1093 loss_ce: 0.1093 2023/03/03 12:06:01 - mmengine - INFO - Epoch(train) [96][30/79] lr: 1.0000e-06 eta: 1:05:33 time: 0.5046 data_time: 0.0020 memory: 35268 loss: 0.1247 loss_ce: 0.1247 2023/03/03 12:06:06 - mmengine - INFO - Epoch(train) [96][40/79] lr: 1.0000e-06 eta: 1:05:29 time: 0.5107 data_time: 0.0018 memory: 36555 loss: 0.1206 loss_ce: 0.1206 2023/03/03 12:06:11 - mmengine - INFO - Epoch(train) [96][50/79] lr: 1.0000e-06 eta: 1:05:24 time: 0.4532 data_time: 0.0016 memory: 26489 loss: 0.1099 loss_ce: 0.1099 2023/03/03 12:06:15 - mmengine - INFO - Epoch(train) [96][60/79] lr: 1.0000e-06 eta: 1:05:19 time: 0.4539 data_time: 0.0015 memory: 36505 loss: 0.1137 loss_ce: 0.1137 2023/03/03 12:06:20 - mmengine - INFO - Epoch(train) [96][70/79] lr: 1.0000e-06 eta: 1:05:14 time: 0.4884 data_time: 0.0015 memory: 35200 loss: 0.1384 loss_ce: 0.1384 2023/03/03 12:06:24 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:06:29 - mmengine - INFO - Epoch(train) [97][10/79] lr: 1.0000e-06 eta: 1:05:05 time: 0.5080 data_time: 0.0613 memory: 48557 loss: 0.1104 loss_ce: 0.1104 2023/03/03 12:06:34 - mmengine - INFO - Epoch(train) [97][20/79] lr: 1.0000e-06 eta: 1:05:01 time: 0.5113 data_time: 0.0016 memory: 40236 loss: 0.1143 loss_ce: 0.1143 2023/03/03 12:06:40 - mmengine - INFO - Epoch(train) [97][30/79] lr: 1.0000e-06 eta: 1:04:56 time: 0.5346 data_time: 0.0016 memory: 39955 loss: 0.1251 loss_ce: 0.1251 2023/03/03 12:06:44 - mmengine - INFO - Epoch(train) [97][40/79] lr: 1.0000e-06 eta: 1:04:51 time: 0.4106 data_time: 0.0015 memory: 27190 loss: 0.1329 loss_ce: 0.1329 2023/03/03 12:06:48 - mmengine - INFO - Epoch(train) [97][50/79] lr: 1.0000e-06 eta: 1:04:46 time: 0.4632 data_time: 0.0017 memory: 34658 loss: 0.1065 loss_ce: 0.1065 2023/03/03 12:06:53 - mmengine - INFO - Epoch(train) [97][60/79] lr: 1.0000e-06 eta: 1:04:41 time: 0.4760 data_time: 0.0020 memory: 40524 loss: 0.1147 loss_ce: 0.1147 2023/03/03 12:06:58 - mmengine - INFO - Epoch(train) [97][70/79] lr: 1.0000e-06 eta: 1:04:36 time: 0.4527 data_time: 0.0015 memory: 44269 loss: 0.1141 loss_ce: 0.1141 2023/03/03 12:07:02 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:07:08 - mmengine - INFO - Epoch(train) [98][10/79] lr: 1.0000e-06 eta: 1:04:28 time: 0.5711 data_time: 0.0338 memory: 39390 loss: 0.1157 loss_ce: 0.1157 2023/03/03 12:07:13 - mmengine - INFO - Epoch(train) [98][20/79] lr: 1.0000e-06 eta: 1:04:24 time: 0.5465 data_time: 0.0016 memory: 40987 loss: 0.1330 loss_ce: 0.1330 2023/03/03 12:07:18 - mmengine - INFO - Epoch(train) [98][30/79] lr: 1.0000e-06 eta: 1:04:19 time: 0.4781 data_time: 0.0016 memory: 37840 loss: 0.1083 loss_ce: 0.1083 2023/03/03 12:07:22 - mmengine - INFO - Epoch(train) [98][40/79] lr: 1.0000e-06 eta: 1:04:14 time: 0.4422 data_time: 0.0015 memory: 37869 loss: 0.1153 loss_ce: 0.1153 2023/03/03 12:07:26 - mmengine - INFO - Epoch(train) [98][50/79] lr: 1.0000e-06 eta: 1:04:09 time: 0.4193 data_time: 0.0017 memory: 37934 loss: 0.1236 loss_ce: 0.1236 2023/03/03 12:07:31 - mmengine - INFO - Epoch(train) [98][60/79] lr: 1.0000e-06 eta: 1:04:04 time: 0.4497 data_time: 0.0017 memory: 40524 loss: 0.1272 loss_ce: 0.1272 2023/03/03 12:07:36 - mmengine - INFO - Epoch(train) [98][70/79] lr: 1.0000e-06 eta: 1:03:59 time: 0.4742 data_time: 0.0014 memory: 41714 loss: 0.1150 loss_ce: 0.1150 2023/03/03 12:07:39 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:07:45 - mmengine - INFO - Epoch(train) [99][10/79] lr: 1.0000e-06 eta: 1:03:50 time: 0.5439 data_time: 0.0439 memory: 41690 loss: 0.1316 loss_ce: 0.1316 2023/03/03 12:07:49 - mmengine - INFO - Epoch(train) [99][20/79] lr: 1.0000e-06 eta: 1:03:45 time: 0.4458 data_time: 0.0017 memory: 38851 loss: 0.1273 loss_ce: 0.1273 2023/03/03 12:07:54 - mmengine - INFO - Epoch(train) [99][30/79] lr: 1.0000e-06 eta: 1:03:40 time: 0.4683 data_time: 0.0016 memory: 35429 loss: 0.1263 loss_ce: 0.1263 2023/03/03 12:07:59 - mmengine - INFO - Epoch(train) [99][40/79] lr: 1.0000e-06 eta: 1:03:35 time: 0.4606 data_time: 0.0015 memory: 33421 loss: 0.1036 loss_ce: 0.1036 2023/03/03 12:08:03 - mmengine - INFO - Epoch(train) [99][50/79] lr: 1.0000e-06 eta: 1:03:31 time: 0.4697 data_time: 0.0016 memory: 28082 loss: 0.1197 loss_ce: 0.1197 2023/03/03 12:08:08 - mmengine - INFO - Epoch(train) [99][60/79] lr: 1.0000e-06 eta: 1:03:26 time: 0.4469 data_time: 0.0015 memory: 40236 loss: 0.1176 loss_ce: 0.1176 2023/03/03 12:08:13 - mmengine - INFO - Epoch(train) [99][70/79] lr: 1.0000e-06 eta: 1:03:21 time: 0.4947 data_time: 0.0013 memory: 29281 loss: 0.1175 loss_ce: 0.1175 2023/03/03 12:08:17 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:08:22 - mmengine - INFO - Epoch(train) [100][10/79] lr: 1.0000e-06 eta: 1:03:12 time: 0.4815 data_time: 0.0685 memory: 34909 loss: 0.1250 loss_ce: 0.1250 2023/03/03 12:08:26 - mmengine - INFO - Epoch(train) [100][20/79] lr: 1.0000e-06 eta: 1:03:07 time: 0.4656 data_time: 0.0018 memory: 46321 loss: 0.1293 loss_ce: 0.1293 2023/03/03 12:08:31 - mmengine - INFO - Epoch(train) [100][30/79] lr: 1.0000e-06 eta: 1:03:02 time: 0.4834 data_time: 0.0016 memory: 46346 loss: 0.1230 loss_ce: 0.1230 2023/03/03 12:08:36 - mmengine - INFO - Epoch(train) [100][40/79] lr: 1.0000e-06 eta: 1:02:58 time: 0.4881 data_time: 0.0016 memory: 36608 loss: 0.1048 loss_ce: 0.1048 2023/03/03 12:08:41 - mmengine - INFO - Epoch(train) [100][50/79] lr: 1.0000e-06 eta: 1:02:53 time: 0.4898 data_time: 0.0016 memory: 36749 loss: 0.1149 loss_ce: 0.1149 2023/03/03 12:08:46 - mmengine - INFO - Epoch(train) [100][60/79] lr: 1.0000e-06 eta: 1:02:48 time: 0.4704 data_time: 0.0017 memory: 34998 loss: 0.1249 loss_ce: 0.1249 2023/03/03 12:08:51 - mmengine - INFO - Epoch(train) [100][70/79] lr: 1.0000e-06 eta: 1:02:44 time: 0.5120 data_time: 0.0016 memory: 39669 loss: 0.1150 loss_ce: 0.1150 2023/03/03 12:08:55 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:09:07 - mmengine - INFO - Epoch(val) [100][10/75] eta: 0:01:18 time: 1.2143 data_time: 0.0033 memory: 27859 2023/03/03 12:10:03 - mmengine - INFO - Epoch(val) [100][20/75] eta: 0:03:08 time: 5.6251 data_time: 0.0004 memory: 1077 2023/03/03 12:10:22 - mmengine - INFO - Epoch(val) [100][30/75] eta: 0:02:11 time: 1.9110 data_time: 0.0004 memory: 1020 2023/03/03 12:10:36 - mmengine - INFO - Epoch(val) [100][40/75] eta: 0:01:28 time: 1.4185 data_time: 0.0004 memory: 1019 2023/03/03 12:10:50 - mmengine - INFO - Epoch(val) [100][50/75] eta: 0:00:57 time: 1.3611 data_time: 0.0003 memory: 1077 2023/03/03 12:11:55 - mmengine - INFO - Epoch(val) [100][60/75] eta: 0:00:45 time: 6.4798 data_time: 0.0004 memory: 1045 2023/03/03 12:12:24 - mmengine - INFO - Epoch(val) [100][70/75] eta: 0:00:14 time: 2.9082 data_time: 0.0005 memory: 1077 2023/03/03 12:12:38 - mmengine - INFO - text score threshold: 0.80, recall: 0.6915, precision: 0.7482, hmean: 0.7188 2023/03/03 12:12:38 - mmengine - INFO - text score threshold: 0.81, recall: 0.6910, precision: 0.7534, hmean: 0.7209 2023/03/03 12:12:38 - mmengine - INFO - text score threshold: 0.82, recall: 0.6910, precision: 0.7580, hmean: 0.7229 2023/03/03 12:12:38 - mmengine - INFO - text score threshold: 0.83, recall: 0.6894, precision: 0.7631, hmean: 0.7243 2023/03/03 12:12:38 - mmengine - INFO - text score threshold: 0.84, recall: 0.6877, precision: 0.7687, hmean: 0.7260 2023/03/03 12:12:38 - mmengine - INFO - text score threshold: 0.85, recall: 0.6861, precision: 0.7754, hmean: 0.7280 2023/03/03 12:12:38 - mmengine - INFO - text score threshold: 0.86, recall: 0.6844, precision: 0.7823, hmean: 0.7301 2023/03/03 12:12:38 - mmengine - INFO - text score threshold: 0.87, recall: 0.6817, precision: 0.7901, hmean: 0.7319 2023/03/03 12:12:38 - mmengine - INFO - text score threshold: 0.88, recall: 0.6789, precision: 0.7955, hmean: 0.7326 2023/03/03 12:12:38 - mmengine - INFO - text score threshold: 0.89, recall: 0.6740, precision: 0.8010, hmean: 0.7320 2023/03/03 12:12:38 - mmengine - INFO - text score threshold: 0.90, recall: 0.6690, precision: 0.8116, hmean: 0.7335 2023/03/03 12:12:38 - mmengine - INFO - text score threshold: 0.91, recall: 0.6641, precision: 0.8170, hmean: 0.7327 2023/03/03 12:12:38 - mmengine - INFO - text score threshold: 0.92, recall: 0.6592, precision: 0.8209, hmean: 0.7312 2023/03/03 12:12:38 - mmengine - INFO - text score threshold: 0.93, recall: 0.6526, precision: 0.8280, hmean: 0.7299 2023/03/03 12:12:38 - mmengine - INFO - text score threshold: 0.94, recall: 0.6454, precision: 0.8311, hmean: 0.7266 2023/03/03 12:12:38 - mmengine - INFO - text score threshold: 0.95, recall: 0.6361, precision: 0.8417, hmean: 0.7246 2023/03/03 12:12:38 - mmengine - INFO - text score threshold: 0.96, recall: 0.6229, precision: 0.8515, hmean: 0.7195 2023/03/03 12:12:38 - mmengine - INFO - text score threshold: 0.97, recall: 0.6037, precision: 0.8621, hmean: 0.7101 2023/03/03 12:12:38 - mmengine - INFO - text score threshold: 0.98, recall: 0.5884, precision: 0.8845, hmean: 0.7067 2023/03/03 12:12:38 - mmengine - INFO - text score threshold: 0.99, recall: 0.5593, precision: 0.8994, hmean: 0.6897 2023/03/03 12:12:47 - mmengine - INFO - text score threshold: 0.80, recall: 0.7755, precision: 0.8744, hmean: 0.8220 2023/03/03 12:12:47 - mmengine - INFO - text score threshold: 0.81, recall: 0.7733, precision: 0.8768, hmean: 0.8218 2023/03/03 12:12:47 - mmengine - INFO - text score threshold: 0.82, recall: 0.7722, precision: 0.8794, hmean: 0.8223 2023/03/03 12:12:47 - mmengine - INFO - text score threshold: 0.83, recall: 0.7689, precision: 0.8828, hmean: 0.8219 2023/03/03 12:12:47 - mmengine - INFO - text score threshold: 0.84, recall: 0.7656, precision: 0.8863, hmean: 0.8216 2023/03/03 12:12:47 - mmengine - INFO - text score threshold: 0.85, recall: 0.7613, precision: 0.8897, hmean: 0.8205 2023/03/03 12:12:47 - mmengine - INFO - text score threshold: 0.86, recall: 0.7585, precision: 0.8945, hmean: 0.8209 2023/03/03 12:12:47 - mmengine - INFO - text score threshold: 0.87, recall: 0.7525, precision: 0.8990, hmean: 0.8192 2023/03/03 12:12:47 - mmengine - INFO - text score threshold: 0.88, recall: 0.7475, precision: 0.9020, hmean: 0.8175 2023/03/03 12:12:47 - mmengine - INFO - text score threshold: 0.89, recall: 0.7393, precision: 0.9028, hmean: 0.8129 2023/03/03 12:12:47 - mmengine - INFO - text score threshold: 0.90, recall: 0.7283, precision: 0.9077, hmean: 0.8082 2023/03/03 12:12:47 - mmengine - INFO - text score threshold: 0.91, recall: 0.7212, precision: 0.9106, hmean: 0.8049 2023/03/03 12:12:47 - mmengine - INFO - text score threshold: 0.92, recall: 0.7151, precision: 0.9118, hmean: 0.8016 2023/03/03 12:12:47 - mmengine - INFO - text score threshold: 0.93, recall: 0.7053, precision: 0.9146, hmean: 0.7964 2023/03/03 12:12:47 - mmengine - INFO - text score threshold: 0.94, recall: 0.6970, precision: 0.9163, hmean: 0.7918 2023/03/03 12:12:47 - mmengine - INFO - text score threshold: 0.95, recall: 0.6789, precision: 0.9177, hmean: 0.7804 2023/03/03 12:12:47 - mmengine - INFO - text score threshold: 0.96, recall: 0.6608, precision: 0.9219, hmean: 0.7698 2023/03/03 12:12:47 - mmengine - INFO - text score threshold: 0.97, recall: 0.6345, precision: 0.9248, hmean: 0.7526 2023/03/03 12:12:47 - mmengine - INFO - text score threshold: 0.98, recall: 0.6109, precision: 0.9345, hmean: 0.7388 2023/03/03 12:12:47 - mmengine - INFO - text score threshold: 0.99, recall: 0.5774, precision: 0.9443, hmean: 0.7166 2023/03/03 12:12:47 - mmengine - INFO - Epoch(val) [100][75/75] none/precision: 0.8116 none/recall: 0.6690 none/hmean: 0.7335 full/precision: 0.8794 full/recall: 0.7722 full/hmean: 0.8223 2023/03/03 12:12:53 - mmengine - INFO - Epoch(train) [101][10/79] lr: 1.0000e-06 eta: 1:02:35 time: 0.5399 data_time: 0.0717 memory: 30700 loss: 0.1153 loss_ce: 0.1153 2023/03/03 12:12:58 - mmengine - INFO - Epoch(train) [101][20/79] lr: 1.0000e-06 eta: 1:02:30 time: 0.4602 data_time: 0.0017 memory: 24496 loss: 0.1076 loss_ce: 0.1076 2023/03/03 12:13:02 - mmengine - INFO - Epoch(train) [101][30/79] lr: 1.0000e-06 eta: 1:02:25 time: 0.4600 data_time: 0.0020 memory: 37891 loss: 0.1200 loss_ce: 0.1200 2023/03/03 12:13:07 - mmengine - INFO - Epoch(train) [101][40/79] lr: 1.0000e-06 eta: 1:02:21 time: 0.4899 data_time: 0.0020 memory: 40236 loss: 0.1186 loss_ce: 0.1186 2023/03/03 12:13:12 - mmengine - INFO - Epoch(train) [101][50/79] lr: 1.0000e-06 eta: 1:02:16 time: 0.4573 data_time: 0.0017 memory: 31411 loss: 0.1165 loss_ce: 0.1165 2023/03/03 12:13:17 - mmengine - INFO - Epoch(train) [101][60/79] lr: 1.0000e-06 eta: 1:02:11 time: 0.5098 data_time: 0.0016 memory: 38329 loss: 0.1279 loss_ce: 0.1279 2023/03/03 12:13:22 - mmengine - INFO - Epoch(train) [101][70/79] lr: 1.0000e-06 eta: 1:02:07 time: 0.4923 data_time: 0.0016 memory: 41355 loss: 0.1191 loss_ce: 0.1191 2023/03/03 12:13:26 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:13:31 - mmengine - INFO - Epoch(train) [102][10/79] lr: 1.0000e-06 eta: 1:01:58 time: 0.4765 data_time: 0.0572 memory: 40236 loss: 0.1367 loss_ce: 0.1367 2023/03/03 12:13:36 - mmengine - INFO - Epoch(train) [102][20/79] lr: 1.0000e-06 eta: 1:01:53 time: 0.4671 data_time: 0.0020 memory: 31484 loss: 0.1216 loss_ce: 0.1216 2023/03/03 12:13:37 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:13:41 - mmengine - INFO - Epoch(train) [102][30/79] lr: 1.0000e-06 eta: 1:01:49 time: 0.4954 data_time: 0.0019 memory: 32910 loss: 0.1192 loss_ce: 0.1192 2023/03/03 12:13:46 - mmengine - INFO - Epoch(train) [102][40/79] lr: 1.0000e-06 eta: 1:01:44 time: 0.5149 data_time: 0.0018 memory: 45998 loss: 0.1120 loss_ce: 0.1120 2023/03/03 12:13:50 - mmengine - INFO - Epoch(train) [102][50/79] lr: 1.0000e-06 eta: 1:01:39 time: 0.4487 data_time: 0.0019 memory: 39306 loss: 0.1291 loss_ce: 0.1291 2023/03/03 12:13:55 - mmengine - INFO - Epoch(train) [102][60/79] lr: 1.0000e-06 eta: 1:01:35 time: 0.5042 data_time: 0.0017 memory: 38322 loss: 0.1158 loss_ce: 0.1158 2023/03/03 12:14:00 - mmengine - INFO - Epoch(train) [102][70/79] lr: 1.0000e-06 eta: 1:01:30 time: 0.4789 data_time: 0.0014 memory: 50103 loss: 0.1190 loss_ce: 0.1190 2023/03/03 12:14:04 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:14:10 - mmengine - INFO - Epoch(train) [103][10/79] lr: 1.0000e-06 eta: 1:01:21 time: 0.5191 data_time: 0.0339 memory: 39955 loss: 0.1080 loss_ce: 0.1080 2023/03/03 12:14:14 - mmengine - INFO - Epoch(train) [103][20/79] lr: 1.0000e-06 eta: 1:01:16 time: 0.4484 data_time: 0.0016 memory: 33018 loss: 0.1231 loss_ce: 0.1231 2023/03/03 12:14:19 - mmengine - INFO - Epoch(train) [103][30/79] lr: 1.0000e-06 eta: 1:01:12 time: 0.4864 data_time: 0.0016 memory: 39123 loss: 0.1247 loss_ce: 0.1247 2023/03/03 12:14:23 - mmengine - INFO - Epoch(train) [103][40/79] lr: 1.0000e-06 eta: 1:01:06 time: 0.4380 data_time: 0.0017 memory: 40422 loss: 0.1278 loss_ce: 0.1278 2023/03/03 12:14:27 - mmengine - INFO - Epoch(train) [103][50/79] lr: 1.0000e-06 eta: 1:01:01 time: 0.4137 data_time: 0.0017 memory: 29665 loss: 0.1208 loss_ce: 0.1208 2023/03/03 12:14:32 - mmengine - INFO - Epoch(train) [103][60/79] lr: 1.0000e-06 eta: 1:00:56 time: 0.4504 data_time: 0.0016 memory: 41714 loss: 0.1347 loss_ce: 0.1347 2023/03/03 12:14:37 - mmengine - INFO - Epoch(train) [103][70/79] lr: 1.0000e-06 eta: 1:00:52 time: 0.5016 data_time: 0.0017 memory: 37338 loss: 0.1317 loss_ce: 0.1317 2023/03/03 12:14:41 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:14:46 - mmengine - INFO - Epoch(train) [104][10/79] lr: 1.0000e-06 eta: 1:00:43 time: 0.5070 data_time: 0.0408 memory: 40053 loss: 0.1302 loss_ce: 0.1302 2023/03/03 12:14:51 - mmengine - INFO - Epoch(train) [104][20/79] lr: 1.0000e-06 eta: 1:00:39 time: 0.5075 data_time: 0.0016 memory: 37255 loss: 0.1245 loss_ce: 0.1245 2023/03/03 12:14:56 - mmengine - INFO - Epoch(train) [104][30/79] lr: 1.0000e-06 eta: 1:00:33 time: 0.4363 data_time: 0.0015 memory: 38082 loss: 0.1186 loss_ce: 0.1186 2023/03/03 12:15:01 - mmengine - INFO - Epoch(train) [104][40/79] lr: 1.0000e-06 eta: 1:00:29 time: 0.4858 data_time: 0.0018 memory: 39955 loss: 0.1101 loss_ce: 0.1101 2023/03/03 12:15:05 - mmengine - INFO - Epoch(train) [104][50/79] lr: 1.0000e-06 eta: 1:00:24 time: 0.4511 data_time: 0.0016 memory: 29884 loss: 0.1102 loss_ce: 0.1102 2023/03/03 12:15:10 - mmengine - INFO - Epoch(train) [104][60/79] lr: 1.0000e-06 eta: 1:00:19 time: 0.4644 data_time: 0.0015 memory: 38334 loss: 0.1346 loss_ce: 0.1346 2023/03/03 12:15:15 - mmengine - INFO - Epoch(train) [104][70/79] lr: 1.0000e-06 eta: 1:00:14 time: 0.4974 data_time: 0.0016 memory: 40340 loss: 0.1188 loss_ce: 0.1188 2023/03/03 12:15:19 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:15:24 - mmengine - INFO - Epoch(train) [105][10/79] lr: 1.0000e-06 eta: 1:00:05 time: 0.5171 data_time: 0.0348 memory: 29940 loss: 0.1148 loss_ce: 0.1148 2023/03/03 12:15:29 - mmengine - INFO - Epoch(train) [105][20/79] lr: 1.0000e-06 eta: 1:00:01 time: 0.4943 data_time: 0.0020 memory: 42327 loss: 0.1175 loss_ce: 0.1175 2023/03/03 12:15:33 - mmengine - INFO - Epoch(train) [105][30/79] lr: 1.0000e-06 eta: 0:59:56 time: 0.4547 data_time: 0.0017 memory: 29834 loss: 0.1164 loss_ce: 0.1164 2023/03/03 12:15:38 - mmengine - INFO - Epoch(train) [105][40/79] lr: 1.0000e-06 eta: 0:59:51 time: 0.4647 data_time: 0.0016 memory: 45060 loss: 0.1058 loss_ce: 0.1058 2023/03/03 12:15:42 - mmengine - INFO - Epoch(train) [105][50/79] lr: 1.0000e-06 eta: 0:59:46 time: 0.4400 data_time: 0.0015 memory: 31513 loss: 0.1287 loss_ce: 0.1287 2023/03/03 12:15:47 - mmengine - INFO - Epoch(train) [105][60/79] lr: 1.0000e-06 eta: 0:59:41 time: 0.4667 data_time: 0.0018 memory: 40144 loss: 0.1045 loss_ce: 0.1045 2023/03/03 12:15:52 - mmengine - INFO - Epoch(train) [105][70/79] lr: 1.0000e-06 eta: 0:59:36 time: 0.4526 data_time: 0.0015 memory: 27887 loss: 0.1034 loss_ce: 0.1034 2023/03/03 12:15:56 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:16:01 - mmengine - INFO - Epoch(train) [106][10/79] lr: 1.0000e-06 eta: 0:59:27 time: 0.5200 data_time: 0.0599 memory: 37467 loss: 0.1100 loss_ce: 0.1100 2023/03/03 12:16:06 - mmengine - INFO - Epoch(train) [106][20/79] lr: 1.0000e-06 eta: 0:59:22 time: 0.4774 data_time: 0.0016 memory: 42963 loss: 0.1240 loss_ce: 0.1240 2023/03/03 12:16:10 - mmengine - INFO - Epoch(train) [106][30/79] lr: 1.0000e-06 eta: 0:59:17 time: 0.4815 data_time: 0.0016 memory: 33886 loss: 0.1160 loss_ce: 0.1160 2023/03/03 12:16:15 - mmengine - INFO - Epoch(train) [106][40/79] lr: 1.0000e-06 eta: 0:59:12 time: 0.4448 data_time: 0.0016 memory: 37934 loss: 0.1154 loss_ce: 0.1154 2023/03/03 12:16:19 - mmengine - INFO - Epoch(train) [106][50/79] lr: 1.0000e-06 eta: 0:59:07 time: 0.4100 data_time: 0.0016 memory: 31436 loss: 0.1347 loss_ce: 0.1347 2023/03/03 12:16:23 - mmengine - INFO - Epoch(train) [106][60/79] lr: 1.0000e-06 eta: 0:59:02 time: 0.4451 data_time: 0.0015 memory: 37084 loss: 0.1058 loss_ce: 0.1058 2023/03/03 12:16:28 - mmengine - INFO - Epoch(train) [106][70/79] lr: 1.0000e-06 eta: 0:58:57 time: 0.4899 data_time: 0.0014 memory: 34446 loss: 0.1220 loss_ce: 0.1220 2023/03/03 12:16:32 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:16:38 - mmengine - INFO - Epoch(train) [107][10/79] lr: 1.0000e-06 eta: 0:58:49 time: 0.5407 data_time: 0.0585 memory: 42096 loss: 0.1164 loss_ce: 0.1164 2023/03/03 12:16:42 - mmengine - INFO - Epoch(train) [107][20/79] lr: 1.0000e-06 eta: 0:58:44 time: 0.4906 data_time: 0.0018 memory: 36962 loss: 0.1015 loss_ce: 0.1015 2023/03/03 12:16:47 - mmengine - INFO - Epoch(train) [107][30/79] lr: 1.0000e-06 eta: 0:58:39 time: 0.4753 data_time: 0.0016 memory: 35815 loss: 0.1164 loss_ce: 0.1164 2023/03/03 12:16:53 - mmengine - INFO - Epoch(train) [107][40/79] lr: 1.0000e-06 eta: 0:58:35 time: 0.5357 data_time: 0.0016 memory: 45829 loss: 0.1083 loss_ce: 0.1083 2023/03/03 12:16:57 - mmengine - INFO - Epoch(train) [107][50/79] lr: 1.0000e-06 eta: 0:58:30 time: 0.4399 data_time: 0.0015 memory: 40236 loss: 0.1004 loss_ce: 0.1004 2023/03/03 12:17:02 - mmengine - INFO - Epoch(train) [107][60/79] lr: 1.0000e-06 eta: 0:58:25 time: 0.4793 data_time: 0.0014 memory: 37934 loss: 0.1306 loss_ce: 0.1306 2023/03/03 12:17:07 - mmengine - INFO - Epoch(train) [107][70/79] lr: 1.0000e-06 eta: 0:58:21 time: 0.5050 data_time: 0.0013 memory: 39571 loss: 0.1189 loss_ce: 0.1189 2023/03/03 12:17:11 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:17:16 - mmengine - INFO - Epoch(train) [108][10/79] lr: 1.0000e-06 eta: 0:58:12 time: 0.4861 data_time: 0.0574 memory: 39955 loss: 0.1239 loss_ce: 0.1239 2023/03/03 12:17:21 - mmengine - INFO - Epoch(train) [108][20/79] lr: 1.0000e-06 eta: 0:58:07 time: 0.4953 data_time: 0.0016 memory: 48398 loss: 0.1192 loss_ce: 0.1192 2023/03/03 12:17:26 - mmengine - INFO - Epoch(train) [108][30/79] lr: 1.0000e-06 eta: 0:58:02 time: 0.4536 data_time: 0.0016 memory: 38851 loss: 0.1214 loss_ce: 0.1214 2023/03/03 12:17:30 - mmengine - INFO - Epoch(train) [108][40/79] lr: 1.0000e-06 eta: 0:57:57 time: 0.4457 data_time: 0.0015 memory: 32128 loss: 0.1125 loss_ce: 0.1125 2023/03/03 12:17:35 - mmengine - INFO - Epoch(train) [108][50/79] lr: 1.0000e-06 eta: 0:57:53 time: 0.4949 data_time: 0.0015 memory: 42671 loss: 0.1044 loss_ce: 0.1044 2023/03/03 12:17:40 - mmengine - INFO - Epoch(train) [108][60/79] lr: 1.0000e-06 eta: 0:57:48 time: 0.5073 data_time: 0.0016 memory: 31508 loss: 0.1093 loss_ce: 0.1093 2023/03/03 12:17:45 - mmengine - INFO - Epoch(train) [108][70/79] lr: 1.0000e-06 eta: 0:57:43 time: 0.4710 data_time: 0.0014 memory: 38588 loss: 0.1187 loss_ce: 0.1187 2023/03/03 12:17:49 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:17:54 - mmengine - INFO - Epoch(train) [109][10/79] lr: 1.0000e-06 eta: 0:57:35 time: 0.5768 data_time: 0.0580 memory: 38586 loss: 0.1146 loss_ce: 0.1146 2023/03/03 12:17:59 - mmengine - INFO - Epoch(train) [109][20/79] lr: 1.0000e-06 eta: 0:57:30 time: 0.4299 data_time: 0.0018 memory: 38082 loss: 0.1292 loss_ce: 0.1292 2023/03/03 12:18:03 - mmengine - INFO - Epoch(train) [109][30/79] lr: 1.0000e-06 eta: 0:57:24 time: 0.4085 data_time: 0.0016 memory: 26614 loss: 0.1076 loss_ce: 0.1076 2023/03/03 12:18:08 - mmengine - INFO - Epoch(train) [109][40/79] lr: 1.0000e-06 eta: 0:57:20 time: 0.5133 data_time: 0.0018 memory: 38088 loss: 0.1011 loss_ce: 0.1011 2023/03/03 12:18:13 - mmengine - INFO - Epoch(train) [109][50/79] lr: 1.0000e-06 eta: 0:57:15 time: 0.4945 data_time: 0.0017 memory: 37468 loss: 0.0994 loss_ce: 0.0994 2023/03/03 12:18:17 - mmengine - INFO - Epoch(train) [109][60/79] lr: 1.0000e-06 eta: 0:57:10 time: 0.4418 data_time: 0.0015 memory: 31323 loss: 0.1088 loss_ce: 0.1088 2023/03/03 12:18:22 - mmengine - INFO - Epoch(train) [109][70/79] lr: 1.0000e-06 eta: 0:57:05 time: 0.4501 data_time: 0.0015 memory: 29549 loss: 0.1199 loss_ce: 0.1199 2023/03/03 12:18:26 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:18:30 - mmengine - INFO - Epoch(train) [110][10/79] lr: 1.0000e-06 eta: 0:56:56 time: 0.4515 data_time: 0.0448 memory: 39669 loss: 0.1142 loss_ce: 0.1142 2023/03/03 12:18:35 - mmengine - INFO - Epoch(train) [110][20/79] lr: 1.0000e-06 eta: 0:56:51 time: 0.4693 data_time: 0.0018 memory: 38358 loss: 0.1247 loss_ce: 0.1247 2023/03/03 12:18:39 - mmengine - INFO - Epoch(train) [110][30/79] lr: 1.0000e-06 eta: 0:56:46 time: 0.4198 data_time: 0.0015 memory: 28296 loss: 0.1136 loss_ce: 0.1136 2023/03/03 12:18:44 - mmengine - INFO - Epoch(train) [110][40/79] lr: 1.0000e-06 eta: 0:56:41 time: 0.4381 data_time: 0.0015 memory: 35734 loss: 0.1127 loss_ce: 0.1127 2023/03/03 12:18:49 - mmengine - INFO - Epoch(train) [110][50/79] lr: 1.0000e-06 eta: 0:56:36 time: 0.5001 data_time: 0.0016 memory: 31886 loss: 0.1088 loss_ce: 0.1088 2023/03/03 12:18:53 - mmengine - INFO - Epoch(train) [110][60/79] lr: 1.0000e-06 eta: 0:56:31 time: 0.4310 data_time: 0.0015 memory: 33319 loss: 0.1270 loss_ce: 0.1270 2023/03/03 12:18:58 - mmengine - INFO - Epoch(train) [110][70/79] lr: 1.0000e-06 eta: 0:56:26 time: 0.4807 data_time: 0.0015 memory: 31854 loss: 0.1136 loss_ce: 0.1136 2023/03/03 12:19:02 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:19:14 - mmengine - INFO - Epoch(val) [110][10/75] eta: 0:01:15 time: 1.1594 data_time: 0.0033 memory: 41521 2023/03/03 12:20:11 - mmengine - INFO - Epoch(val) [110][20/75] eta: 0:03:10 time: 5.7604 data_time: 0.0004 memory: 1077 2023/03/03 12:20:32 - mmengine - INFO - Epoch(val) [110][30/75] eta: 0:02:15 time: 2.1103 data_time: 0.0004 memory: 1020 2023/03/03 12:20:47 - mmengine - INFO - Epoch(val) [110][40/75] eta: 0:01:32 time: 1.4886 data_time: 0.0005 memory: 1019 2023/03/03 12:21:02 - mmengine - INFO - Epoch(val) [110][50/75] eta: 0:00:59 time: 1.4406 data_time: 0.0005 memory: 1077 2023/03/03 12:21:45 - mmengine - INFO - Epoch(val) [110][60/75] eta: 0:00:40 time: 4.3286 data_time: 0.0004 memory: 1045 2023/03/03 12:22:15 - mmengine - INFO - Epoch(val) [110][70/75] eta: 0:00:13 time: 3.0549 data_time: 0.0005 memory: 1077 2023/03/03 12:22:29 - mmengine - INFO - text score threshold: 0.80, recall: 0.6926, precision: 0.7490, hmean: 0.7197 2023/03/03 12:22:29 - mmengine - INFO - text score threshold: 0.81, recall: 0.6926, precision: 0.7521, hmean: 0.7211 2023/03/03 12:22:29 - mmengine - INFO - text score threshold: 0.82, recall: 0.6915, precision: 0.7563, hmean: 0.7225 2023/03/03 12:22:29 - mmengine - INFO - text score threshold: 0.83, recall: 0.6899, precision: 0.7595, hmean: 0.7230 2023/03/03 12:22:29 - mmengine - INFO - text score threshold: 0.84, recall: 0.6888, precision: 0.7643, hmean: 0.7246 2023/03/03 12:22:29 - mmengine - INFO - text score threshold: 0.85, recall: 0.6877, precision: 0.7735, hmean: 0.7281 2023/03/03 12:22:29 - mmengine - INFO - text score threshold: 0.86, recall: 0.6855, precision: 0.7811, hmean: 0.7302 2023/03/03 12:22:29 - mmengine - INFO - text score threshold: 0.87, recall: 0.6833, precision: 0.7860, hmean: 0.7311 2023/03/03 12:22:29 - mmengine - INFO - text score threshold: 0.88, recall: 0.6784, precision: 0.7913, hmean: 0.7305 2023/03/03 12:22:29 - mmengine - INFO - text score threshold: 0.89, recall: 0.6756, precision: 0.7983, hmean: 0.7319 2023/03/03 12:22:29 - mmengine - INFO - text score threshold: 0.90, recall: 0.6723, precision: 0.8070, hmean: 0.7335 2023/03/03 12:22:29 - mmengine - INFO - text score threshold: 0.91, recall: 0.6679, precision: 0.8157, hmean: 0.7345 2023/03/03 12:22:29 - mmengine - INFO - text score threshold: 0.92, recall: 0.6619, precision: 0.8187, hmean: 0.7320 2023/03/03 12:22:29 - mmengine - INFO - text score threshold: 0.93, recall: 0.6548, precision: 0.8290, hmean: 0.7317 2023/03/03 12:22:29 - mmengine - INFO - text score threshold: 0.94, recall: 0.6471, precision: 0.8374, hmean: 0.7300 2023/03/03 12:22:29 - mmengine - INFO - text score threshold: 0.95, recall: 0.6383, precision: 0.8428, hmean: 0.7264 2023/03/03 12:22:29 - mmengine - INFO - text score threshold: 0.96, recall: 0.6235, precision: 0.8529, hmean: 0.7204 2023/03/03 12:22:29 - mmengine - INFO - text score threshold: 0.97, recall: 0.6109, precision: 0.8682, hmean: 0.7171 2023/03/03 12:22:29 - mmengine - INFO - text score threshold: 0.98, recall: 0.5900, precision: 0.8804, hmean: 0.7065 2023/03/03 12:22:29 - mmengine - INFO - text score threshold: 0.99, recall: 0.5593, precision: 0.8986, hmean: 0.6894 2023/03/03 12:22:39 - mmengine - INFO - text score threshold: 0.80, recall: 0.7750, precision: 0.8743, hmean: 0.8216 2023/03/03 12:22:39 - mmengine - INFO - text score threshold: 0.81, recall: 0.7750, precision: 0.8765, hmean: 0.8226 2023/03/03 12:22:39 - mmengine - INFO - text score threshold: 0.82, recall: 0.7739, precision: 0.8801, hmean: 0.8236 2023/03/03 12:22:39 - mmengine - INFO - text score threshold: 0.83, recall: 0.7717, precision: 0.8826, hmean: 0.8234 2023/03/03 12:22:39 - mmengine - INFO - text score threshold: 0.84, recall: 0.7689, precision: 0.8850, hmean: 0.8229 2023/03/03 12:22:39 - mmengine - INFO - text score threshold: 0.85, recall: 0.7645, precision: 0.8890, hmean: 0.8221 2023/03/03 12:22:39 - mmengine - INFO - text score threshold: 0.86, recall: 0.7591, precision: 0.8923, hmean: 0.8203 2023/03/03 12:22:39 - mmengine - INFO - text score threshold: 0.87, recall: 0.7547, precision: 0.8940, hmean: 0.8185 2023/03/03 12:22:39 - mmengine - INFO - text score threshold: 0.88, recall: 0.7486, precision: 0.8980, hmean: 0.8165 2023/03/03 12:22:39 - mmengine - INFO - text score threshold: 0.89, recall: 0.7442, precision: 0.9010, hmean: 0.8151 2023/03/03 12:22:39 - mmengine - INFO - text score threshold: 0.90, recall: 0.7377, precision: 0.9063, hmean: 0.8133 2023/03/03 12:22:39 - mmengine - INFO - text score threshold: 0.91, recall: 0.7289, precision: 0.9108, hmean: 0.8098 2023/03/03 12:22:39 - mmengine - INFO - text score threshold: 0.92, recall: 0.7201, precision: 0.9105, hmean: 0.8042 2023/03/03 12:22:39 - mmengine - INFO - text score threshold: 0.93, recall: 0.7064, precision: 0.9128, hmean: 0.7964 2023/03/03 12:22:39 - mmengine - INFO - text score threshold: 0.94, recall: 0.6943, precision: 0.9153, hmean: 0.7896 2023/03/03 12:22:39 - mmengine - INFO - text score threshold: 0.95, recall: 0.6828, precision: 0.9181, hmean: 0.7831 2023/03/03 12:22:39 - mmengine - INFO - text score threshold: 0.96, recall: 0.6619, precision: 0.9227, hmean: 0.7709 2023/03/03 12:22:39 - mmengine - INFO - text score threshold: 0.97, recall: 0.6443, precision: 0.9317, hmean: 0.7618 2023/03/03 12:22:39 - mmengine - INFO - text score threshold: 0.98, recall: 0.6164, precision: 0.9351, hmean: 0.7430 2023/03/03 12:22:39 - mmengine - INFO - text score threshold: 0.99, recall: 0.5779, precision: 0.9444, hmean: 0.7171 2023/03/03 12:22:39 - mmengine - INFO - Epoch(val) [110][75/75] none/precision: 0.8157 none/recall: 0.6679 none/hmean: 0.7345 full/precision: 0.8801 full/recall: 0.7739 full/hmean: 0.8236 2023/03/03 12:22:44 - mmengine - INFO - Epoch(train) [111][10/79] lr: 1.0000e-06 eta: 0:56:17 time: 0.4907 data_time: 0.0667 memory: 37934 loss: 0.1232 loss_ce: 0.1232 2023/03/03 12:22:49 - mmengine - INFO - Epoch(train) [111][20/79] lr: 1.0000e-06 eta: 0:56:13 time: 0.4963 data_time: 0.0014 memory: 37934 loss: 0.1271 loss_ce: 0.1271 2023/03/03 12:22:53 - mmengine - INFO - Epoch(train) [111][30/79] lr: 1.0000e-06 eta: 0:56:08 time: 0.4361 data_time: 0.0016 memory: 30573 loss: 0.1284 loss_ce: 0.1284 2023/03/03 12:22:58 - mmengine - INFO - Epoch(train) [111][40/79] lr: 1.0000e-06 eta: 0:56:03 time: 0.5017 data_time: 0.0015 memory: 37934 loss: 0.1023 loss_ce: 0.1023 2023/03/03 12:23:03 - mmengine - INFO - Epoch(train) [111][50/79] lr: 1.0000e-06 eta: 0:55:59 time: 0.4928 data_time: 0.0021 memory: 39955 loss: 0.1160 loss_ce: 0.1160 2023/03/03 12:23:08 - mmengine - INFO - Epoch(train) [111][60/79] lr: 1.0000e-06 eta: 0:55:53 time: 0.4397 data_time: 0.0015 memory: 36405 loss: 0.1146 loss_ce: 0.1146 2023/03/03 12:23:12 - mmengine - INFO - Epoch(train) [111][70/79] lr: 1.0000e-06 eta: 0:55:48 time: 0.4376 data_time: 0.0013 memory: 43855 loss: 0.1095 loss_ce: 0.1095 2023/03/03 12:23:16 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:23:21 - mmengine - INFO - Epoch(train) [112][10/79] lr: 1.0000e-06 eta: 0:55:39 time: 0.5036 data_time: 0.0260 memory: 49218 loss: 0.1092 loss_ce: 0.1092 2023/03/03 12:23:26 - mmengine - INFO - Epoch(train) [112][20/79] lr: 1.0000e-06 eta: 0:55:35 time: 0.4969 data_time: 0.0016 memory: 40818 loss: 0.1232 loss_ce: 0.1232 2023/03/03 12:23:31 - mmengine - INFO - Epoch(train) [112][30/79] lr: 1.0000e-06 eta: 0:55:30 time: 0.4899 data_time: 0.0016 memory: 32677 loss: 0.1099 loss_ce: 0.1099 2023/03/03 12:23:36 - mmengine - INFO - Epoch(train) [112][40/79] lr: 1.0000e-06 eta: 0:55:25 time: 0.5025 data_time: 0.0017 memory: 39123 loss: 0.1061 loss_ce: 0.1061 2023/03/03 12:23:41 - mmengine - INFO - Epoch(train) [112][50/79] lr: 1.0000e-06 eta: 0:55:21 time: 0.5122 data_time: 0.0016 memory: 31567 loss: 0.1321 loss_ce: 0.1321 2023/03/03 12:23:45 - mmengine - INFO - Epoch(train) [112][60/79] lr: 1.0000e-06 eta: 0:55:16 time: 0.4195 data_time: 0.0017 memory: 34757 loss: 0.1302 loss_ce: 0.1302 2023/03/03 12:23:49 - mmengine - INFO - Epoch(train) [112][70/79] lr: 1.0000e-06 eta: 0:55:11 time: 0.4551 data_time: 0.0020 memory: 34589 loss: 0.1298 loss_ce: 0.1298 2023/03/03 12:23:54 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:23:59 - mmengine - INFO - Epoch(train) [113][10/79] lr: 1.0000e-06 eta: 0:55:02 time: 0.5389 data_time: 0.0610 memory: 37934 loss: 0.1183 loss_ce: 0.1183 2023/03/03 12:24:04 - mmengine - INFO - Epoch(train) [113][20/79] lr: 1.0000e-06 eta: 0:54:58 time: 0.4722 data_time: 0.0016 memory: 38082 loss: 0.1148 loss_ce: 0.1148 2023/03/03 12:24:08 - mmengine - INFO - Epoch(train) [113][30/79] lr: 1.0000e-06 eta: 0:54:53 time: 0.4510 data_time: 0.0016 memory: 37934 loss: 0.1215 loss_ce: 0.1215 2023/03/03 12:24:13 - mmengine - INFO - Epoch(train) [113][40/79] lr: 1.0000e-06 eta: 0:54:48 time: 0.4683 data_time: 0.0017 memory: 40419 loss: 0.1040 loss_ce: 0.1040 2023/03/03 12:24:18 - mmengine - INFO - Epoch(train) [113][50/79] lr: 1.0000e-06 eta: 0:54:43 time: 0.5277 data_time: 0.0017 memory: 41714 loss: 0.1212 loss_ce: 0.1212 2023/03/03 12:24:24 - mmengine - INFO - Epoch(train) [113][60/79] lr: 1.0000e-06 eta: 0:54:39 time: 0.5070 data_time: 0.0022 memory: 38240 loss: 0.1162 loss_ce: 0.1162 2023/03/03 12:24:29 - mmengine - INFO - Epoch(train) [113][70/79] lr: 1.0000e-06 eta: 0:54:34 time: 0.5077 data_time: 0.0018 memory: 34188 loss: 0.1190 loss_ce: 0.1190 2023/03/03 12:24:32 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:24:37 - mmengine - INFO - Epoch(train) [114][10/79] lr: 1.0000e-06 eta: 0:54:25 time: 0.5117 data_time: 0.0520 memory: 38082 loss: 0.1193 loss_ce: 0.1193 2023/03/03 12:24:42 - mmengine - INFO - Epoch(train) [114][20/79] lr: 1.0000e-06 eta: 0:54:21 time: 0.4924 data_time: 0.0018 memory: 37283 loss: 0.1166 loss_ce: 0.1166 2023/03/03 12:24:47 - mmengine - INFO - Epoch(train) [114][30/79] lr: 1.0000e-06 eta: 0:54:16 time: 0.4990 data_time: 0.0016 memory: 37730 loss: 0.1316 loss_ce: 0.1316 2023/03/03 12:24:52 - mmengine - INFO - Epoch(train) [114][40/79] lr: 1.0000e-06 eta: 0:54:11 time: 0.5030 data_time: 0.0015 memory: 37754 loss: 0.1129 loss_ce: 0.1129 2023/03/03 12:24:57 - mmengine - INFO - Epoch(train) [114][50/79] lr: 1.0000e-06 eta: 0:54:06 time: 0.4499 data_time: 0.0015 memory: 40104 loss: 0.1217 loss_ce: 0.1217 2023/03/03 12:25:02 - mmengine - INFO - Epoch(train) [114][60/79] lr: 1.0000e-06 eta: 0:54:02 time: 0.4950 data_time: 0.0016 memory: 32492 loss: 0.1204 loss_ce: 0.1204 2023/03/03 12:25:07 - mmengine - INFO - Epoch(train) [114][70/79] lr: 1.0000e-06 eta: 0:53:57 time: 0.4820 data_time: 0.0014 memory: 32697 loss: 0.1152 loss_ce: 0.1152 2023/03/03 12:25:08 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:25:11 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:25:17 - mmengine - INFO - Epoch(train) [115][10/79] lr: 1.0000e-06 eta: 0:53:49 time: 0.5871 data_time: 0.0613 memory: 46346 loss: 0.1240 loss_ce: 0.1240 2023/03/03 12:25:21 - mmengine - INFO - Epoch(train) [115][20/79] lr: 1.0000e-06 eta: 0:53:44 time: 0.4481 data_time: 0.0014 memory: 35706 loss: 0.1034 loss_ce: 0.1034 2023/03/03 12:25:26 - mmengine - INFO - Epoch(train) [115][30/79] lr: 1.0000e-06 eta: 0:53:39 time: 0.4634 data_time: 0.0015 memory: 38082 loss: 0.1291 loss_ce: 0.1291 2023/03/03 12:25:31 - mmengine - INFO - Epoch(train) [115][40/79] lr: 1.0000e-06 eta: 0:53:34 time: 0.4870 data_time: 0.0015 memory: 44021 loss: 0.0908 loss_ce: 0.0908 2023/03/03 12:25:35 - mmengine - INFO - Epoch(train) [115][50/79] lr: 1.0000e-06 eta: 0:53:30 time: 0.4768 data_time: 0.0015 memory: 34778 loss: 0.1120 loss_ce: 0.1120 2023/03/03 12:25:40 - mmengine - INFO - Epoch(train) [115][60/79] lr: 1.0000e-06 eta: 0:53:25 time: 0.4858 data_time: 0.0015 memory: 36310 loss: 0.1324 loss_ce: 0.1324 2023/03/03 12:25:45 - mmengine - INFO - Epoch(train) [115][70/79] lr: 1.0000e-06 eta: 0:53:20 time: 0.4571 data_time: 0.0012 memory: 36637 loss: 0.1278 loss_ce: 0.1278 2023/03/03 12:25:49 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:25:54 - mmengine - INFO - Epoch(train) [116][10/79] lr: 1.0000e-06 eta: 0:53:11 time: 0.4794 data_time: 0.0368 memory: 39955 loss: 0.1226 loss_ce: 0.1226 2023/03/03 12:25:58 - mmengine - INFO - Epoch(train) [116][20/79] lr: 1.0000e-06 eta: 0:53:06 time: 0.4520 data_time: 0.0015 memory: 31316 loss: 0.1358 loss_ce: 0.1358 2023/03/03 12:26:03 - mmengine - INFO - Epoch(train) [116][30/79] lr: 1.0000e-06 eta: 0:53:01 time: 0.4582 data_time: 0.0015 memory: 44271 loss: 0.1180 loss_ce: 0.1180 2023/03/03 12:26:07 - mmengine - INFO - Epoch(train) [116][40/79] lr: 1.0000e-06 eta: 0:52:56 time: 0.4597 data_time: 0.0016 memory: 39306 loss: 0.1056 loss_ce: 0.1056 2023/03/03 12:26:12 - mmengine - INFO - Epoch(train) [116][50/79] lr: 1.0000e-06 eta: 0:52:52 time: 0.5192 data_time: 0.0015 memory: 33419 loss: 0.1275 loss_ce: 0.1275 2023/03/03 12:26:17 - mmengine - INFO - Epoch(train) [116][60/79] lr: 1.0000e-06 eta: 0:52:47 time: 0.4402 data_time: 0.0015 memory: 38889 loss: 0.1206 loss_ce: 0.1206 2023/03/03 12:26:22 - mmengine - INFO - Epoch(train) [116][70/79] lr: 1.0000e-06 eta: 0:52:42 time: 0.4954 data_time: 0.0013 memory: 39199 loss: 0.1199 loss_ce: 0.1199 2023/03/03 12:26:25 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:26:31 - mmengine - INFO - Epoch(train) [117][10/79] lr: 1.0000e-06 eta: 0:52:33 time: 0.5126 data_time: 0.0607 memory: 36389 loss: 0.1179 loss_ce: 0.1179 2023/03/03 12:26:35 - mmengine - INFO - Epoch(train) [117][20/79] lr: 1.0000e-06 eta: 0:52:28 time: 0.4643 data_time: 0.0018 memory: 33472 loss: 0.1095 loss_ce: 0.1095 2023/03/03 12:26:40 - mmengine - INFO - Epoch(train) [117][30/79] lr: 1.0000e-06 eta: 0:52:23 time: 0.4960 data_time: 0.0016 memory: 32227 loss: 0.1156 loss_ce: 0.1156 2023/03/03 12:26:44 - mmengine - INFO - Epoch(train) [117][40/79] lr: 1.0000e-06 eta: 0:52:18 time: 0.3972 data_time: 0.0017 memory: 43606 loss: 0.1248 loss_ce: 0.1248 2023/03/03 12:26:49 - mmengine - INFO - Epoch(train) [117][50/79] lr: 1.0000e-06 eta: 0:52:13 time: 0.4638 data_time: 0.0015 memory: 36000 loss: 0.1164 loss_ce: 0.1164 2023/03/03 12:26:54 - mmengine - INFO - Epoch(train) [117][60/79] lr: 1.0000e-06 eta: 0:52:09 time: 0.5111 data_time: 0.0017 memory: 36928 loss: 0.1150 loss_ce: 0.1150 2023/03/03 12:26:59 - mmengine - INFO - Epoch(train) [117][70/79] lr: 1.0000e-06 eta: 0:52:04 time: 0.4814 data_time: 0.0013 memory: 35599 loss: 0.1264 loss_ce: 0.1264 2023/03/03 12:27:03 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:27:08 - mmengine - INFO - Epoch(train) [118][10/79] lr: 1.0000e-06 eta: 0:51:55 time: 0.5326 data_time: 0.0683 memory: 45998 loss: 0.1171 loss_ce: 0.1171 2023/03/03 12:27:12 - mmengine - INFO - Epoch(train) [118][20/79] lr: 1.0000e-06 eta: 0:51:50 time: 0.4229 data_time: 0.0015 memory: 34945 loss: 0.1283 loss_ce: 0.1283 2023/03/03 12:27:17 - mmengine - INFO - Epoch(train) [118][30/79] lr: 1.0000e-06 eta: 0:51:45 time: 0.4768 data_time: 0.0017 memory: 38334 loss: 0.1217 loss_ce: 0.1217 2023/03/03 12:27:22 - mmengine - INFO - Epoch(train) [118][40/79] lr: 1.0000e-06 eta: 0:51:40 time: 0.4352 data_time: 0.0016 memory: 35869 loss: 0.1153 loss_ce: 0.1153 2023/03/03 12:27:26 - mmengine - INFO - Epoch(train) [118][50/79] lr: 1.0000e-06 eta: 0:51:35 time: 0.4739 data_time: 0.0020 memory: 42963 loss: 0.0985 loss_ce: 0.0985 2023/03/03 12:27:31 - mmengine - INFO - Epoch(train) [118][60/79] lr: 1.0000e-06 eta: 0:51:31 time: 0.4586 data_time: 0.0015 memory: 36866 loss: 0.1191 loss_ce: 0.1191 2023/03/03 12:27:36 - mmengine - INFO - Epoch(train) [118][70/79] lr: 1.0000e-06 eta: 0:51:26 time: 0.4656 data_time: 0.0013 memory: 42115 loss: 0.1219 loss_ce: 0.1219 2023/03/03 12:27:40 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:27:45 - mmengine - INFO - Epoch(train) [119][10/79] lr: 1.0000e-06 eta: 0:51:17 time: 0.5924 data_time: 0.0646 memory: 38588 loss: 0.1199 loss_ce: 0.1199 2023/03/03 12:27:50 - mmengine - INFO - Epoch(train) [119][20/79] lr: 1.0000e-06 eta: 0:51:12 time: 0.4652 data_time: 0.0019 memory: 38334 loss: 0.1051 loss_ce: 0.1051 2023/03/03 12:27:54 - mmengine - INFO - Epoch(train) [119][30/79] lr: 1.0000e-06 eta: 0:51:07 time: 0.4167 data_time: 0.0019 memory: 32405 loss: 0.1224 loss_ce: 0.1224 2023/03/03 12:27:59 - mmengine - INFO - Epoch(train) [119][40/79] lr: 1.0000e-06 eta: 0:51:03 time: 0.5039 data_time: 0.0018 memory: 38334 loss: 0.1216 loss_ce: 0.1216 2023/03/03 12:28:04 - mmengine - INFO - Epoch(train) [119][50/79] lr: 1.0000e-06 eta: 0:50:58 time: 0.4641 data_time: 0.0016 memory: 37000 loss: 0.1229 loss_ce: 0.1229 2023/03/03 12:28:09 - mmengine - INFO - Epoch(train) [119][60/79] lr: 1.0000e-06 eta: 0:50:53 time: 0.4917 data_time: 0.0016 memory: 38571 loss: 0.1126 loss_ce: 0.1126 2023/03/03 12:28:13 - mmengine - INFO - Epoch(train) [119][70/79] lr: 1.0000e-06 eta: 0:50:48 time: 0.4600 data_time: 0.0014 memory: 40053 loss: 0.1008 loss_ce: 0.1008 2023/03/03 12:28:18 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:28:23 - mmengine - INFO - Epoch(train) [120][10/79] lr: 1.0000e-06 eta: 0:50:40 time: 0.5212 data_time: 0.0520 memory: 33834 loss: 0.1223 loss_ce: 0.1223 2023/03/03 12:28:27 - mmengine - INFO - Epoch(train) [120][20/79] lr: 1.0000e-06 eta: 0:50:34 time: 0.4178 data_time: 0.0017 memory: 28289 loss: 0.1131 loss_ce: 0.1131 2023/03/03 12:28:31 - mmengine - INFO - Epoch(train) [120][30/79] lr: 1.0000e-06 eta: 0:50:29 time: 0.4201 data_time: 0.0021 memory: 34696 loss: 0.1155 loss_ce: 0.1155 2023/03/03 12:28:35 - mmengine - INFO - Epoch(train) [120][40/79] lr: 1.0000e-06 eta: 0:50:24 time: 0.4224 data_time: 0.0018 memory: 36282 loss: 0.1165 loss_ce: 0.1165 2023/03/03 12:28:41 - mmengine - INFO - Epoch(train) [120][50/79] lr: 1.0000e-06 eta: 0:50:20 time: 0.5183 data_time: 0.0021 memory: 48557 loss: 0.1161 loss_ce: 0.1161 2023/03/03 12:28:45 - mmengine - INFO - Epoch(train) [120][60/79] lr: 1.0000e-06 eta: 0:50:15 time: 0.4277 data_time: 0.0019 memory: 31734 loss: 0.1193 loss_ce: 0.1193 2023/03/03 12:28:50 - mmengine - INFO - Epoch(train) [120][70/79] lr: 1.0000e-06 eta: 0:50:10 time: 0.4741 data_time: 0.0021 memory: 32533 loss: 0.1249 loss_ce: 0.1249 2023/03/03 12:28:54 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:29:05 - mmengine - INFO - Epoch(val) [120][10/75] eta: 0:01:15 time: 1.1557 data_time: 0.0035 memory: 35523 2023/03/03 12:29:46 - mmengine - INFO - Epoch(val) [120][20/75] eta: 0:02:24 time: 4.1155 data_time: 0.0005 memory: 1077 2023/03/03 12:30:06 - mmengine - INFO - Epoch(val) [120][30/75] eta: 0:01:48 time: 1.9374 data_time: 0.0004 memory: 1020 2023/03/03 12:30:21 - mmengine - INFO - Epoch(val) [120][40/75] eta: 0:01:16 time: 1.5036 data_time: 0.0004 memory: 1019 2023/03/03 12:30:35 - mmengine - INFO - Epoch(val) [120][50/75] eta: 0:00:50 time: 1.4681 data_time: 0.0005 memory: 1077 2023/03/03 12:31:40 - mmengine - INFO - Epoch(val) [120][60/75] eta: 0:00:41 time: 6.4752 data_time: 0.0005 memory: 1045 2023/03/03 12:32:09 - mmengine - INFO - Epoch(val) [120][70/75] eta: 0:00:13 time: 2.8809 data_time: 0.0004 memory: 1077 2023/03/03 12:32:23 - mmengine - INFO - text score threshold: 0.80, recall: 0.6910, precision: 0.7419, hmean: 0.7155 2023/03/03 12:32:23 - mmengine - INFO - text score threshold: 0.81, recall: 0.6905, precision: 0.7466, hmean: 0.7174 2023/03/03 12:32:23 - mmengine - INFO - text score threshold: 0.82, recall: 0.6894, precision: 0.7503, hmean: 0.7185 2023/03/03 12:32:23 - mmengine - INFO - text score threshold: 0.83, recall: 0.6894, precision: 0.7571, hmean: 0.7216 2023/03/03 12:32:23 - mmengine - INFO - text score threshold: 0.84, recall: 0.6894, precision: 0.7621, hmean: 0.7239 2023/03/03 12:32:23 - mmengine - INFO - text score threshold: 0.85, recall: 0.6883, precision: 0.7698, hmean: 0.7267 2023/03/03 12:32:23 - mmengine - INFO - text score threshold: 0.86, recall: 0.6855, precision: 0.7772, hmean: 0.7285 2023/03/03 12:32:23 - mmengine - INFO - text score threshold: 0.87, recall: 0.6833, precision: 0.7860, hmean: 0.7311 2023/03/03 12:32:23 - mmengine - INFO - text score threshold: 0.88, recall: 0.6795, precision: 0.7951, hmean: 0.7328 2023/03/03 12:32:23 - mmengine - INFO - text score threshold: 0.89, recall: 0.6762, precision: 0.8010, hmean: 0.7333 2023/03/03 12:32:23 - mmengine - INFO - text score threshold: 0.90, recall: 0.6734, precision: 0.8067, hmean: 0.7341 2023/03/03 12:32:23 - mmengine - INFO - text score threshold: 0.91, recall: 0.6668, precision: 0.8193, hmean: 0.7352 2023/03/03 12:32:23 - mmengine - INFO - text score threshold: 0.92, recall: 0.6603, precision: 0.8234, hmean: 0.7329 2023/03/03 12:32:23 - mmengine - INFO - text score threshold: 0.93, recall: 0.6548, precision: 0.8314, hmean: 0.7326 2023/03/03 12:32:23 - mmengine - INFO - text score threshold: 0.94, recall: 0.6509, precision: 0.8417, hmean: 0.7341 2023/03/03 12:32:23 - mmengine - INFO - text score threshold: 0.95, recall: 0.6400, precision: 0.8492, hmean: 0.7299 2023/03/03 12:32:23 - mmengine - INFO - text score threshold: 0.96, recall: 0.6257, precision: 0.8584, hmean: 0.7238 2023/03/03 12:32:23 - mmengine - INFO - text score threshold: 0.97, recall: 0.6092, precision: 0.8665, hmean: 0.7154 2023/03/03 12:32:23 - mmengine - INFO - text score threshold: 0.98, recall: 0.5922, precision: 0.8881, hmean: 0.7106 2023/03/03 12:32:23 - mmengine - INFO - text score threshold: 0.99, recall: 0.5626, precision: 0.8991, hmean: 0.6921 2023/03/03 12:32:32 - mmengine - INFO - text score threshold: 0.80, recall: 0.7772, precision: 0.8682, hmean: 0.8202 2023/03/03 12:32:32 - mmengine - INFO - text score threshold: 0.81, recall: 0.7761, precision: 0.8718, hmean: 0.8211 2023/03/03 12:32:32 - mmengine - INFO - text score threshold: 0.82, recall: 0.7744, precision: 0.8748, hmean: 0.8215 2023/03/03 12:32:32 - mmengine - INFO - text score threshold: 0.83, recall: 0.7717, precision: 0.8793, hmean: 0.8220 2023/03/03 12:32:32 - mmengine - INFO - text score threshold: 0.84, recall: 0.7711, precision: 0.8820, hmean: 0.8228 2023/03/03 12:32:32 - mmengine - INFO - text score threshold: 0.85, recall: 0.7673, precision: 0.8865, hmean: 0.8226 2023/03/03 12:32:32 - mmengine - INFO - text score threshold: 0.86, recall: 0.7618, precision: 0.8897, hmean: 0.8208 2023/03/03 12:32:32 - mmengine - INFO - text score threshold: 0.87, recall: 0.7569, precision: 0.8955, hmean: 0.8203 2023/03/03 12:32:32 - mmengine - INFO - text score threshold: 0.88, recall: 0.7497, precision: 0.8993, hmean: 0.8177 2023/03/03 12:32:32 - mmengine - INFO - text score threshold: 0.89, recall: 0.7442, precision: 0.9028, hmean: 0.8159 2023/03/03 12:32:32 - mmengine - INFO - text score threshold: 0.90, recall: 0.7393, precision: 0.9065, hmean: 0.8144 2023/03/03 12:32:32 - mmengine - INFO - text score threshold: 0.91, recall: 0.7256, precision: 0.9111, hmean: 0.8078 2023/03/03 12:32:32 - mmengine - INFO - text score threshold: 0.92, recall: 0.7179, precision: 0.9147, hmean: 0.8044 2023/03/03 12:32:32 - mmengine - INFO - text score threshold: 0.93, recall: 0.7075, precision: 0.9174, hmean: 0.7989 2023/03/03 12:32:32 - mmengine - INFO - text score threshold: 0.94, recall: 0.6992, precision: 0.9225, hmean: 0.7955 2023/03/03 12:32:32 - mmengine - INFO - text score threshold: 0.95, recall: 0.6833, precision: 0.9243, hmean: 0.7857 2023/03/03 12:32:32 - mmengine - INFO - text score threshold: 0.96, recall: 0.6630, precision: 0.9264, hmean: 0.7729 2023/03/03 12:32:32 - mmengine - INFO - text score threshold: 0.97, recall: 0.6427, precision: 0.9316, hmean: 0.7606 2023/03/03 12:32:32 - mmengine - INFO - text score threshold: 0.98, recall: 0.6164, precision: 0.9397, hmean: 0.7444 2023/03/03 12:32:32 - mmengine - INFO - text score threshold: 0.99, recall: 0.5812, precision: 0.9447, hmean: 0.7197 2023/03/03 12:32:32 - mmengine - INFO - Epoch(val) [120][75/75] none/precision: 0.8193 none/recall: 0.6668 none/hmean: 0.7352 full/precision: 0.8820 full/recall: 0.7711 full/hmean: 0.8228 2023/03/03 12:32:38 - mmengine - INFO - Epoch(train) [121][10/79] lr: 1.0000e-06 eta: 0:50:01 time: 0.5040 data_time: 0.0416 memory: 31759 loss: 0.1194 loss_ce: 0.1194 2023/03/03 12:32:43 - mmengine - INFO - Epoch(train) [121][20/79] lr: 1.0000e-06 eta: 0:49:56 time: 0.5032 data_time: 0.0015 memory: 36871 loss: 0.1050 loss_ce: 0.1050 2023/03/03 12:32:47 - mmengine - INFO - Epoch(train) [121][30/79] lr: 1.0000e-06 eta: 0:49:51 time: 0.4854 data_time: 0.0017 memory: 43865 loss: 0.1045 loss_ce: 0.1045 2023/03/03 12:32:52 - mmengine - INFO - Epoch(train) [121][40/79] lr: 1.0000e-06 eta: 0:49:47 time: 0.4757 data_time: 0.0015 memory: 32018 loss: 0.1195 loss_ce: 0.1195 2023/03/03 12:32:57 - mmengine - INFO - Epoch(train) [121][50/79] lr: 1.0000e-06 eta: 0:49:42 time: 0.4539 data_time: 0.0016 memory: 40236 loss: 0.1092 loss_ce: 0.1092 2023/03/03 12:33:01 - mmengine - INFO - Epoch(train) [121][60/79] lr: 1.0000e-06 eta: 0:49:37 time: 0.4048 data_time: 0.0017 memory: 28805 loss: 0.1077 loss_ce: 0.1077 2023/03/03 12:33:05 - mmengine - INFO - Epoch(train) [121][70/79] lr: 1.0000e-06 eta: 0:49:32 time: 0.4455 data_time: 0.0021 memory: 29822 loss: 0.1207 loss_ce: 0.1207 2023/03/03 12:33:09 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:33:14 - mmengine - INFO - Epoch(train) [122][10/79] lr: 1.0000e-06 eta: 0:49:22 time: 0.5055 data_time: 0.0630 memory: 40059 loss: 0.1145 loss_ce: 0.1145 2023/03/03 12:33:18 - mmengine - INFO - Epoch(train) [122][20/79] lr: 1.0000e-06 eta: 0:49:17 time: 0.3989 data_time: 0.0019 memory: 40524 loss: 0.1350 loss_ce: 0.1350 2023/03/03 12:33:23 - mmengine - INFO - Epoch(train) [122][30/79] lr: 1.0000e-06 eta: 0:49:12 time: 0.4669 data_time: 0.0024 memory: 35684 loss: 0.1250 loss_ce: 0.1250 2023/03/03 12:33:27 - mmengine - INFO - Epoch(train) [122][40/79] lr: 1.0000e-06 eta: 0:49:08 time: 0.4625 data_time: 0.0021 memory: 29125 loss: 0.0913 loss_ce: 0.0913 2023/03/03 12:33:32 - mmengine - INFO - Epoch(train) [122][50/79] lr: 1.0000e-06 eta: 0:49:03 time: 0.4580 data_time: 0.0016 memory: 36046 loss: 0.1204 loss_ce: 0.1204 2023/03/03 12:33:37 - mmengine - INFO - Epoch(train) [122][60/79] lr: 1.0000e-06 eta: 0:48:58 time: 0.4617 data_time: 0.0017 memory: 38914 loss: 0.1026 loss_ce: 0.1026 2023/03/03 12:33:41 - mmengine - INFO - Epoch(train) [122][70/79] lr: 1.0000e-06 eta: 0:48:53 time: 0.4771 data_time: 0.0014 memory: 46155 loss: 0.1072 loss_ce: 0.1072 2023/03/03 12:33:46 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:33:51 - mmengine - INFO - Epoch(train) [123][10/79] lr: 1.0000e-06 eta: 0:48:45 time: 0.5520 data_time: 0.0668 memory: 38911 loss: 0.1121 loss_ce: 0.1121 2023/03/03 12:33:56 - mmengine - INFO - Epoch(train) [123][20/79] lr: 1.0000e-06 eta: 0:48:40 time: 0.4963 data_time: 0.0016 memory: 36592 loss: 0.1227 loss_ce: 0.1227 2023/03/03 12:34:01 - mmengine - INFO - Epoch(train) [123][30/79] lr: 1.0000e-06 eta: 0:48:35 time: 0.4673 data_time: 0.0016 memory: 38334 loss: 0.1327 loss_ce: 0.1327 2023/03/03 12:34:06 - mmengine - INFO - Epoch(train) [123][40/79] lr: 1.0000e-06 eta: 0:48:30 time: 0.4817 data_time: 0.0017 memory: 37708 loss: 0.1147 loss_ce: 0.1147 2023/03/03 12:34:10 - mmengine - INFO - Epoch(train) [123][50/79] lr: 1.0000e-06 eta: 0:48:26 time: 0.4618 data_time: 0.0019 memory: 39223 loss: 0.1078 loss_ce: 0.1078 2023/03/03 12:34:15 - mmengine - INFO - Epoch(train) [123][60/79] lr: 1.0000e-06 eta: 0:48:21 time: 0.4858 data_time: 0.0016 memory: 32612 loss: 0.1092 loss_ce: 0.1092 2023/03/03 12:34:20 - mmengine - INFO - Epoch(train) [123][70/79] lr: 1.0000e-06 eta: 0:48:16 time: 0.4846 data_time: 0.0020 memory: 38851 loss: 0.1172 loss_ce: 0.1172 2023/03/03 12:34:24 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:34:29 - mmengine - INFO - Epoch(train) [124][10/79] lr: 1.0000e-06 eta: 0:48:07 time: 0.4915 data_time: 0.0429 memory: 39123 loss: 0.1081 loss_ce: 0.1081 2023/03/03 12:34:34 - mmengine - INFO - Epoch(train) [124][20/79] lr: 1.0000e-06 eta: 0:48:03 time: 0.5286 data_time: 0.0019 memory: 33935 loss: 0.1150 loss_ce: 0.1150 2023/03/03 12:34:39 - mmengine - INFO - Epoch(train) [124][30/79] lr: 1.0000e-06 eta: 0:47:58 time: 0.4536 data_time: 0.0016 memory: 41408 loss: 0.1175 loss_ce: 0.1175 2023/03/03 12:34:43 - mmengine - INFO - Epoch(train) [124][40/79] lr: 1.0000e-06 eta: 0:47:53 time: 0.4580 data_time: 0.0017 memory: 40279 loss: 0.1173 loss_ce: 0.1173 2023/03/03 12:34:48 - mmengine - INFO - Epoch(train) [124][50/79] lr: 1.0000e-06 eta: 0:47:48 time: 0.4547 data_time: 0.0016 memory: 32357 loss: 0.1249 loss_ce: 0.1249 2023/03/03 12:34:52 - mmengine - INFO - Epoch(train) [124][60/79] lr: 1.0000e-06 eta: 0:47:43 time: 0.4626 data_time: 0.0016 memory: 39955 loss: 0.1178 loss_ce: 0.1178 2023/03/03 12:34:57 - mmengine - INFO - Epoch(train) [124][70/79] lr: 1.0000e-06 eta: 0:47:38 time: 0.4072 data_time: 0.0013 memory: 38082 loss: 0.1225 loss_ce: 0.1225 2023/03/03 12:35:01 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:35:06 - mmengine - INFO - Epoch(train) [125][10/79] lr: 1.0000e-06 eta: 0:47:29 time: 0.4701 data_time: 0.0486 memory: 37934 loss: 0.1246 loss_ce: 0.1246 2023/03/03 12:35:10 - mmengine - INFO - Epoch(train) [125][20/79] lr: 1.0000e-06 eta: 0:47:24 time: 0.4665 data_time: 0.0015 memory: 37934 loss: 0.1121 loss_ce: 0.1121 2023/03/03 12:35:15 - mmengine - INFO - Epoch(train) [125][30/79] lr: 1.0000e-06 eta: 0:47:19 time: 0.4815 data_time: 0.0015 memory: 50407 loss: 0.1156 loss_ce: 0.1156 2023/03/03 12:35:20 - mmengine - INFO - Epoch(train) [125][40/79] lr: 1.0000e-06 eta: 0:47:15 time: 0.4631 data_time: 0.0019 memory: 33963 loss: 0.1125 loss_ce: 0.1125 2023/03/03 12:35:24 - mmengine - INFO - Epoch(train) [125][50/79] lr: 1.0000e-06 eta: 0:47:10 time: 0.4713 data_time: 0.0016 memory: 29782 loss: 0.1344 loss_ce: 0.1344 2023/03/03 12:35:29 - mmengine - INFO - Epoch(train) [125][60/79] lr: 1.0000e-06 eta: 0:47:05 time: 0.4884 data_time: 0.0015 memory: 32791 loss: 0.1245 loss_ce: 0.1245 2023/03/03 12:35:34 - mmengine - INFO - Epoch(train) [125][70/79] lr: 1.0000e-06 eta: 0:47:00 time: 0.4601 data_time: 0.0013 memory: 40236 loss: 0.1354 loss_ce: 0.1354 2023/03/03 12:35:38 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:35:43 - mmengine - INFO - Epoch(train) [126][10/79] lr: 1.0000e-06 eta: 0:46:51 time: 0.4755 data_time: 0.0509 memory: 38136 loss: 0.1224 loss_ce: 0.1224 2023/03/03 12:35:48 - mmengine - INFO - Epoch(train) [126][20/79] lr: 1.0000e-06 eta: 0:46:47 time: 0.5190 data_time: 0.0017 memory: 30366 loss: 0.1370 loss_ce: 0.1370 2023/03/03 12:35:53 - mmengine - INFO - Epoch(train) [126][30/79] lr: 1.0000e-06 eta: 0:46:42 time: 0.5038 data_time: 0.0016 memory: 40524 loss: 0.1257 loss_ce: 0.1257 2023/03/03 12:35:58 - mmengine - INFO - Epoch(train) [126][40/79] lr: 1.0000e-06 eta: 0:46:38 time: 0.4850 data_time: 0.0015 memory: 33937 loss: 0.1192 loss_ce: 0.1192 2023/03/03 12:36:03 - mmengine - INFO - Epoch(train) [126][50/79] lr: 1.0000e-06 eta: 0:46:33 time: 0.4993 data_time: 0.0017 memory: 36552 loss: 0.1236 loss_ce: 0.1236 2023/03/03 12:36:08 - mmengine - INFO - Epoch(train) [126][60/79] lr: 1.0000e-06 eta: 0:46:28 time: 0.4928 data_time: 0.0017 memory: 42016 loss: 0.1073 loss_ce: 0.1073 2023/03/03 12:36:12 - mmengine - INFO - Epoch(train) [126][70/79] lr: 1.0000e-06 eta: 0:46:23 time: 0.4332 data_time: 0.0016 memory: 36711 loss: 0.1033 loss_ce: 0.1033 2023/03/03 12:36:16 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:36:21 - mmengine - INFO - Epoch(train) [127][10/79] lr: 1.0000e-06 eta: 0:46:14 time: 0.5285 data_time: 0.0471 memory: 42916 loss: 0.1083 loss_ce: 0.1083 2023/03/03 12:36:26 - mmengine - INFO - Epoch(train) [127][20/79] lr: 1.0000e-06 eta: 0:46:10 time: 0.4618 data_time: 0.0016 memory: 37119 loss: 0.1227 loss_ce: 0.1227 2023/03/03 12:36:31 - mmengine - INFO - Epoch(train) [127][30/79] lr: 1.0000e-06 eta: 0:46:05 time: 0.4809 data_time: 0.0016 memory: 41108 loss: 0.1193 loss_ce: 0.1193 2023/03/03 12:36:36 - mmengine - INFO - Epoch(train) [127][40/79] lr: 1.0000e-06 eta: 0:46:00 time: 0.5046 data_time: 0.0016 memory: 37456 loss: 0.1212 loss_ce: 0.1212 2023/03/03 12:36:38 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:36:40 - mmengine - INFO - Epoch(train) [127][50/79] lr: 1.0000e-06 eta: 0:45:55 time: 0.4602 data_time: 0.0016 memory: 39035 loss: 0.1183 loss_ce: 0.1183 2023/03/03 12:36:46 - mmengine - INFO - Epoch(train) [127][60/79] lr: 1.0000e-06 eta: 0:45:51 time: 0.5398 data_time: 0.0015 memory: 42963 loss: 0.1081 loss_ce: 0.1081 2023/03/03 12:36:50 - mmengine - INFO - Epoch(train) [127][70/79] lr: 1.0000e-06 eta: 0:45:46 time: 0.4349 data_time: 0.0013 memory: 31257 loss: 0.1119 loss_ce: 0.1119 2023/03/03 12:36:55 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:37:00 - mmengine - INFO - Epoch(train) [128][10/79] lr: 1.0000e-06 eta: 0:45:37 time: 0.5139 data_time: 0.0372 memory: 37968 loss: 0.1317 loss_ce: 0.1317 2023/03/03 12:37:05 - mmengine - INFO - Epoch(train) [128][20/79] lr: 1.0000e-06 eta: 0:45:33 time: 0.4979 data_time: 0.0018 memory: 28269 loss: 0.1192 loss_ce: 0.1192 2023/03/03 12:37:09 - mmengine - INFO - Epoch(train) [128][30/79] lr: 1.0000e-06 eta: 0:45:28 time: 0.4681 data_time: 0.0017 memory: 31062 loss: 0.1040 loss_ce: 0.1040 2023/03/03 12:37:14 - mmengine - INFO - Epoch(train) [128][40/79] lr: 1.0000e-06 eta: 0:45:23 time: 0.4406 data_time: 0.0019 memory: 39881 loss: 0.1103 loss_ce: 0.1103 2023/03/03 12:37:19 - mmengine - INFO - Epoch(train) [128][50/79] lr: 1.0000e-06 eta: 0:45:18 time: 0.4890 data_time: 0.0020 memory: 44578 loss: 0.0990 loss_ce: 0.0990 2023/03/03 12:37:23 - mmengine - INFO - Epoch(train) [128][60/79] lr: 1.0000e-06 eta: 0:45:13 time: 0.4546 data_time: 0.0020 memory: 32622 loss: 0.1142 loss_ce: 0.1142 2023/03/03 12:37:28 - mmengine - INFO - Epoch(train) [128][70/79] lr: 1.0000e-06 eta: 0:45:08 time: 0.4547 data_time: 0.0024 memory: 36825 loss: 0.1090 loss_ce: 0.1090 2023/03/03 12:37:32 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:37:36 - mmengine - INFO - Epoch(train) [129][10/79] lr: 1.0000e-06 eta: 0:44:59 time: 0.4698 data_time: 0.0595 memory: 48115 loss: 0.1034 loss_ce: 0.1034 2023/03/03 12:37:41 - mmengine - INFO - Epoch(train) [129][20/79] lr: 1.0000e-06 eta: 0:44:54 time: 0.4800 data_time: 0.0022 memory: 34647 loss: 0.1292 loss_ce: 0.1292 2023/03/03 12:37:46 - mmengine - INFO - Epoch(train) [129][30/79] lr: 1.0000e-06 eta: 0:44:50 time: 0.4812 data_time: 0.0017 memory: 44584 loss: 0.1116 loss_ce: 0.1116 2023/03/03 12:37:51 - mmengine - INFO - Epoch(train) [129][40/79] lr: 1.0000e-06 eta: 0:44:45 time: 0.5356 data_time: 0.0020 memory: 36384 loss: 0.1298 loss_ce: 0.1298 2023/03/03 12:37:56 - mmengine - INFO - Epoch(train) [129][50/79] lr: 1.0000e-06 eta: 0:44:40 time: 0.4782 data_time: 0.0015 memory: 41105 loss: 0.1053 loss_ce: 0.1053 2023/03/03 12:38:01 - mmengine - INFO - Epoch(train) [129][60/79] lr: 1.0000e-06 eta: 0:44:36 time: 0.4738 data_time: 0.0020 memory: 38175 loss: 0.1008 loss_ce: 0.1008 2023/03/03 12:38:06 - mmengine - INFO - Epoch(train) [129][70/79] lr: 1.0000e-06 eta: 0:44:31 time: 0.5048 data_time: 0.0018 memory: 36825 loss: 0.1112 loss_ce: 0.1112 2023/03/03 12:38:09 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:38:14 - mmengine - INFO - Epoch(train) [130][10/79] lr: 1.0000e-06 eta: 0:44:22 time: 0.4756 data_time: 0.0304 memory: 38367 loss: 0.1150 loss_ce: 0.1150 2023/03/03 12:38:18 - mmengine - INFO - Epoch(train) [130][20/79] lr: 1.0000e-06 eta: 0:44:16 time: 0.4139 data_time: 0.0015 memory: 36470 loss: 0.1186 loss_ce: 0.1186 2023/03/03 12:38:23 - mmengine - INFO - Epoch(train) [130][30/79] lr: 1.0000e-06 eta: 0:44:12 time: 0.4798 data_time: 0.0016 memory: 38588 loss: 0.1176 loss_ce: 0.1176 2023/03/03 12:38:27 - mmengine - INFO - Epoch(train) [130][40/79] lr: 1.0000e-06 eta: 0:44:07 time: 0.4526 data_time: 0.0016 memory: 37934 loss: 0.1252 loss_ce: 0.1252 2023/03/03 12:38:33 - mmengine - INFO - Epoch(train) [130][50/79] lr: 1.0000e-06 eta: 0:44:02 time: 0.5169 data_time: 0.0015 memory: 41714 loss: 0.1247 loss_ce: 0.1247 2023/03/03 12:38:37 - mmengine - INFO - Epoch(train) [130][60/79] lr: 1.0000e-06 eta: 0:43:58 time: 0.4690 data_time: 0.0016 memory: 40125 loss: 0.1152 loss_ce: 0.1152 2023/03/03 12:38:42 - mmengine - INFO - Epoch(train) [130][70/79] lr: 1.0000e-06 eta: 0:43:53 time: 0.4962 data_time: 0.0014 memory: 43636 loss: 0.1184 loss_ce: 0.1184 2023/03/03 12:38:46 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:38:58 - mmengine - INFO - Epoch(val) [130][10/75] eta: 0:01:16 time: 1.1803 data_time: 0.0031 memory: 39390 2023/03/03 12:39:38 - mmengine - INFO - Epoch(val) [130][20/75] eta: 0:02:22 time: 4.0179 data_time: 0.0004 memory: 1077 2023/03/03 12:39:57 - mmengine - INFO - Epoch(val) [130][30/75] eta: 0:01:46 time: 1.8744 data_time: 0.0003 memory: 1020 2023/03/03 12:40:12 - mmengine - INFO - Epoch(val) [130][40/75] eta: 0:01:15 time: 1.5088 data_time: 0.0004 memory: 1019 2023/03/03 12:40:27 - mmengine - INFO - Epoch(val) [130][50/75] eta: 0:00:50 time: 1.4402 data_time: 0.0004 memory: 1077 2023/03/03 12:41:09 - mmengine - INFO - Epoch(val) [130][60/75] eta: 0:00:35 time: 4.2610 data_time: 0.0005 memory: 1045 2023/03/03 12:42:00 - mmengine - INFO - Epoch(val) [130][70/75] eta: 0:00:13 time: 5.0986 data_time: 0.0005 memory: 1077 2023/03/03 12:42:14 - mmengine - INFO - text score threshold: 0.80, recall: 0.6910, precision: 0.7494, hmean: 0.7190 2023/03/03 12:42:14 - mmengine - INFO - text score threshold: 0.81, recall: 0.6899, precision: 0.7536, hmean: 0.7203 2023/03/03 12:42:14 - mmengine - INFO - text score threshold: 0.82, recall: 0.6899, precision: 0.7554, hmean: 0.7212 2023/03/03 12:42:14 - mmengine - INFO - text score threshold: 0.83, recall: 0.6894, precision: 0.7589, hmean: 0.7225 2023/03/03 12:42:14 - mmengine - INFO - text score threshold: 0.84, recall: 0.6872, precision: 0.7639, hmean: 0.7235 2023/03/03 12:42:14 - mmengine - INFO - text score threshold: 0.85, recall: 0.6861, precision: 0.7697, hmean: 0.7255 2023/03/03 12:42:14 - mmengine - INFO - text score threshold: 0.86, recall: 0.6839, precision: 0.7773, hmean: 0.7276 2023/03/03 12:42:14 - mmengine - INFO - text score threshold: 0.87, recall: 0.6811, precision: 0.7825, hmean: 0.7283 2023/03/03 12:42:14 - mmengine - INFO - text score threshold: 0.88, recall: 0.6795, precision: 0.7931, hmean: 0.7319 2023/03/03 12:42:14 - mmengine - INFO - text score threshold: 0.89, recall: 0.6756, precision: 0.7962, hmean: 0.7310 2023/03/03 12:42:14 - mmengine - INFO - text score threshold: 0.90, recall: 0.6723, precision: 0.8043, hmean: 0.7324 2023/03/03 12:42:14 - mmengine - INFO - text score threshold: 0.91, recall: 0.6658, precision: 0.8125, hmean: 0.7318 2023/03/03 12:42:14 - mmengine - INFO - text score threshold: 0.92, recall: 0.6597, precision: 0.8171, hmean: 0.7300 2023/03/03 12:42:14 - mmengine - INFO - text score threshold: 0.93, recall: 0.6520, precision: 0.8250, hmean: 0.7284 2023/03/03 12:42:14 - mmengine - INFO - text score threshold: 0.94, recall: 0.6460, precision: 0.8383, hmean: 0.7297 2023/03/03 12:42:14 - mmengine - INFO - text score threshold: 0.95, recall: 0.6339, precision: 0.8462, hmean: 0.7248 2023/03/03 12:42:14 - mmengine - INFO - text score threshold: 0.96, recall: 0.6224, precision: 0.8610, hmean: 0.7225 2023/03/03 12:42:14 - mmengine - INFO - text score threshold: 0.97, recall: 0.6087, precision: 0.8691, hmean: 0.7159 2023/03/03 12:42:14 - mmengine - INFO - text score threshold: 0.98, recall: 0.5911, precision: 0.8828, hmean: 0.7081 2023/03/03 12:42:14 - mmengine - INFO - text score threshold: 0.99, recall: 0.5653, precision: 0.8980, hmean: 0.6938 2023/03/03 12:42:23 - mmengine - INFO - text score threshold: 0.80, recall: 0.7739, precision: 0.8720, hmean: 0.8200 2023/03/03 12:42:23 - mmengine - INFO - text score threshold: 0.81, recall: 0.7728, precision: 0.8756, hmean: 0.8210 2023/03/03 12:42:23 - mmengine - INFO - text score threshold: 0.82, recall: 0.7722, precision: 0.8766, hmean: 0.8211 2023/03/03 12:42:23 - mmengine - INFO - text score threshold: 0.83, recall: 0.7700, precision: 0.8785, hmean: 0.8207 2023/03/03 12:42:23 - mmengine - INFO - text score threshold: 0.84, recall: 0.7667, precision: 0.8819, hmean: 0.8203 2023/03/03 12:42:23 - mmengine - INFO - text score threshold: 0.85, recall: 0.7640, precision: 0.8861, hmean: 0.8205 2023/03/03 12:42:23 - mmengine - INFO - text score threshold: 0.86, recall: 0.7580, precision: 0.8875, hmean: 0.8176 2023/03/03 12:42:23 - mmengine - INFO - text score threshold: 0.87, recall: 0.7530, precision: 0.8892, hmean: 0.8155 2023/03/03 12:42:23 - mmengine - INFO - text score threshold: 0.88, recall: 0.7481, precision: 0.8961, hmean: 0.8154 2023/03/03 12:42:23 - mmengine - INFO - text score threshold: 0.89, recall: 0.7420, precision: 0.8971, hmean: 0.8123 2023/03/03 12:42:23 - mmengine - INFO - text score threshold: 0.90, recall: 0.7371, precision: 0.9032, hmean: 0.8117 2023/03/03 12:42:23 - mmengine - INFO - text score threshold: 0.91, recall: 0.7267, precision: 0.9081, hmean: 0.8073 2023/03/03 12:42:23 - mmengine - INFO - text score threshold: 0.92, recall: 0.7179, precision: 0.9102, hmean: 0.8027 2023/03/03 12:42:23 - mmengine - INFO - text score threshold: 0.93, recall: 0.7064, precision: 0.9121, hmean: 0.7962 2023/03/03 12:42:23 - mmengine - INFO - text score threshold: 0.94, recall: 0.6915, precision: 0.9164, hmean: 0.7882 2023/03/03 12:42:23 - mmengine - INFO - text score threshold: 0.95, recall: 0.6751, precision: 0.9186, hmean: 0.7782 2023/03/03 12:42:23 - mmengine - INFO - text score threshold: 0.96, recall: 0.6592, precision: 0.9281, hmean: 0.7709 2023/03/03 12:42:23 - mmengine - INFO - text score threshold: 0.97, recall: 0.6405, precision: 0.9306, hmean: 0.7588 2023/03/03 12:42:23 - mmengine - INFO - text score threshold: 0.98, recall: 0.6175, precision: 0.9375, hmean: 0.7445 2023/03/03 12:42:23 - mmengine - INFO - text score threshold: 0.99, recall: 0.5834, precision: 0.9424, hmean: 0.7207 2023/03/03 12:42:23 - mmengine - INFO - Epoch(val) [130][75/75] none/precision: 0.8043 none/recall: 0.6723 none/hmean: 0.7324 full/precision: 0.8766 full/recall: 0.7722 full/hmean: 0.8211 2023/03/03 12:42:28 - mmengine - INFO - Epoch(train) [131][10/79] lr: 1.0000e-06 eta: 0:43:44 time: 0.5005 data_time: 0.0359 memory: 35734 loss: 0.1237 loss_ce: 0.1237 2023/03/03 12:42:33 - mmengine - INFO - Epoch(train) [131][20/79] lr: 1.0000e-06 eta: 0:43:39 time: 0.4528 data_time: 0.0015 memory: 36556 loss: 0.1173 loss_ce: 0.1173 2023/03/03 12:42:37 - mmengine - INFO - Epoch(train) [131][30/79] lr: 1.0000e-06 eta: 0:43:34 time: 0.4520 data_time: 0.0016 memory: 22485 loss: 0.1345 loss_ce: 0.1345 2023/03/03 12:42:42 - mmengine - INFO - Epoch(train) [131][40/79] lr: 1.0000e-06 eta: 0:43:29 time: 0.4425 data_time: 0.0020 memory: 32737 loss: 0.1070 loss_ce: 0.1070 2023/03/03 12:42:47 - mmengine - INFO - Epoch(train) [131][50/79] lr: 1.0000e-06 eta: 0:43:24 time: 0.4628 data_time: 0.0015 memory: 37934 loss: 0.1384 loss_ce: 0.1384 2023/03/03 12:42:51 - mmengine - INFO - Epoch(train) [131][60/79] lr: 1.0000e-06 eta: 0:43:20 time: 0.4894 data_time: 0.0015 memory: 35546 loss: 0.1078 loss_ce: 0.1078 2023/03/03 12:42:56 - mmengine - INFO - Epoch(train) [131][70/79] lr: 1.0000e-06 eta: 0:43:15 time: 0.4790 data_time: 0.0013 memory: 49713 loss: 0.1046 loss_ce: 0.1046 2023/03/03 12:43:00 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:43:05 - mmengine - INFO - Epoch(train) [132][10/79] lr: 1.0000e-06 eta: 0:43:06 time: 0.4933 data_time: 0.0377 memory: 42327 loss: 0.1223 loss_ce: 0.1223 2023/03/03 12:43:10 - mmengine - INFO - Epoch(train) [132][20/79] lr: 1.0000e-06 eta: 0:43:01 time: 0.4863 data_time: 0.0016 memory: 37700 loss: 0.1220 loss_ce: 0.1220 2023/03/03 12:43:15 - mmengine - INFO - Epoch(train) [132][30/79] lr: 1.0000e-06 eta: 0:42:56 time: 0.4724 data_time: 0.0015 memory: 32893 loss: 0.1150 loss_ce: 0.1150 2023/03/03 12:43:19 - mmengine - INFO - Epoch(train) [132][40/79] lr: 1.0000e-06 eta: 0:42:52 time: 0.4831 data_time: 0.0015 memory: 35013 loss: 0.1112 loss_ce: 0.1112 2023/03/03 12:43:24 - mmengine - INFO - Epoch(train) [132][50/79] lr: 1.0000e-06 eta: 0:42:47 time: 0.4314 data_time: 0.0015 memory: 37934 loss: 0.1016 loss_ce: 0.1016 2023/03/03 12:43:29 - mmengine - INFO - Epoch(train) [132][60/79] lr: 1.0000e-06 eta: 0:42:42 time: 0.4844 data_time: 0.0015 memory: 26939 loss: 0.0990 loss_ce: 0.0990 2023/03/03 12:43:34 - mmengine - INFO - Epoch(train) [132][70/79] lr: 1.0000e-06 eta: 0:42:37 time: 0.5004 data_time: 0.0013 memory: 36603 loss: 0.1304 loss_ce: 0.1304 2023/03/03 12:43:38 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:43:43 - mmengine - INFO - Epoch(train) [133][10/79] lr: 1.0000e-06 eta: 0:42:28 time: 0.5400 data_time: 0.0713 memory: 37271 loss: 0.1242 loss_ce: 0.1242 2023/03/03 12:43:47 - mmengine - INFO - Epoch(train) [133][20/79] lr: 1.0000e-06 eta: 0:42:23 time: 0.4287 data_time: 0.0015 memory: 32002 loss: 0.1121 loss_ce: 0.1121 2023/03/03 12:43:52 - mmengine - INFO - Epoch(train) [133][30/79] lr: 1.0000e-06 eta: 0:42:19 time: 0.4419 data_time: 0.0017 memory: 44834 loss: 0.1167 loss_ce: 0.1167 2023/03/03 12:43:56 - mmengine - INFO - Epoch(train) [133][40/79] lr: 1.0000e-06 eta: 0:42:14 time: 0.4161 data_time: 0.0017 memory: 38394 loss: 0.1006 loss_ce: 0.1006 2023/03/03 12:44:01 - mmengine - INFO - Epoch(train) [133][50/79] lr: 1.0000e-06 eta: 0:42:09 time: 0.5298 data_time: 0.0020 memory: 47491 loss: 0.1202 loss_ce: 0.1202 2023/03/03 12:44:06 - mmengine - INFO - Epoch(train) [133][60/79] lr: 1.0000e-06 eta: 0:42:04 time: 0.4980 data_time: 0.0017 memory: 24890 loss: 0.1134 loss_ce: 0.1134 2023/03/03 12:44:11 - mmengine - INFO - Epoch(train) [133][70/79] lr: 1.0000e-06 eta: 0:42:00 time: 0.4534 data_time: 0.0014 memory: 39123 loss: 0.1146 loss_ce: 0.1146 2023/03/03 12:44:15 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:44:19 - mmengine - INFO - Epoch(train) [134][10/79] lr: 1.0000e-06 eta: 0:41:50 time: 0.4936 data_time: 0.0214 memory: 39123 loss: 0.1159 loss_ce: 0.1159 2023/03/03 12:44:25 - mmengine - INFO - Epoch(train) [134][20/79] lr: 1.0000e-06 eta: 0:41:46 time: 0.5451 data_time: 0.0015 memory: 39713 loss: 0.1055 loss_ce: 0.1055 2023/03/03 12:44:30 - mmengine - INFO - Epoch(train) [134][30/79] lr: 1.0000e-06 eta: 0:41:41 time: 0.4584 data_time: 0.0015 memory: 31027 loss: 0.1160 loss_ce: 0.1160 2023/03/03 12:44:34 - mmengine - INFO - Epoch(train) [134][40/79] lr: 1.0000e-06 eta: 0:41:36 time: 0.4254 data_time: 0.0015 memory: 25611 loss: 0.1189 loss_ce: 0.1189 2023/03/03 12:44:39 - mmengine - INFO - Epoch(train) [134][50/79] lr: 1.0000e-06 eta: 0:41:32 time: 0.4920 data_time: 0.0015 memory: 37934 loss: 0.1274 loss_ce: 0.1274 2023/03/03 12:44:44 - mmengine - INFO - Epoch(train) [134][60/79] lr: 1.0000e-06 eta: 0:41:27 time: 0.5106 data_time: 0.0015 memory: 33886 loss: 0.1208 loss_ce: 0.1208 2023/03/03 12:44:48 - mmengine - INFO - Epoch(train) [134][70/79] lr: 1.0000e-06 eta: 0:41:22 time: 0.4405 data_time: 0.0015 memory: 38626 loss: 0.1228 loss_ce: 0.1228 2023/03/03 12:44:53 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:44:58 - mmengine - INFO - Epoch(train) [135][10/79] lr: 1.0000e-06 eta: 0:41:13 time: 0.5127 data_time: 0.0688 memory: 39422 loss: 0.1145 loss_ce: 0.1145 2023/03/03 12:45:03 - mmengine - INFO - Epoch(train) [135][20/79] lr: 1.0000e-06 eta: 0:41:09 time: 0.5439 data_time: 0.0017 memory: 39930 loss: 0.1046 loss_ce: 0.1046 2023/03/03 12:45:08 - mmengine - INFO - Epoch(train) [135][30/79] lr: 1.0000e-06 eta: 0:41:04 time: 0.4344 data_time: 0.0015 memory: 44569 loss: 0.1172 loss_ce: 0.1172 2023/03/03 12:45:12 - mmengine - INFO - Epoch(train) [135][40/79] lr: 1.0000e-06 eta: 0:40:59 time: 0.4492 data_time: 0.0014 memory: 35970 loss: 0.1199 loss_ce: 0.1199 2023/03/03 12:45:17 - mmengine - INFO - Epoch(train) [135][50/79] lr: 1.0000e-06 eta: 0:40:54 time: 0.5102 data_time: 0.0015 memory: 42642 loss: 0.1117 loss_ce: 0.1117 2023/03/03 12:45:22 - mmengine - INFO - Epoch(train) [135][60/79] lr: 1.0000e-06 eta: 0:40:50 time: 0.4581 data_time: 0.0016 memory: 38334 loss: 0.1108 loss_ce: 0.1108 2023/03/03 12:45:27 - mmengine - INFO - Epoch(train) [135][70/79] lr: 1.0000e-06 eta: 0:40:45 time: 0.4853 data_time: 0.0014 memory: 35440 loss: 0.1176 loss_ce: 0.1176 2023/03/03 12:45:31 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:45:36 - mmengine - INFO - Epoch(train) [136][10/79] lr: 1.0000e-06 eta: 0:40:36 time: 0.5252 data_time: 0.0647 memory: 38334 loss: 0.1181 loss_ce: 0.1181 2023/03/03 12:45:41 - mmengine - INFO - Epoch(train) [136][20/79] lr: 1.0000e-06 eta: 0:40:31 time: 0.4894 data_time: 0.0017 memory: 30876 loss: 0.1023 loss_ce: 0.1023 2023/03/03 12:45:46 - mmengine - INFO - Epoch(train) [136][30/79] lr: 1.0000e-06 eta: 0:40:27 time: 0.4749 data_time: 0.0016 memory: 30418 loss: 0.1009 loss_ce: 0.1009 2023/03/03 12:45:50 - mmengine - INFO - Epoch(train) [136][40/79] lr: 1.0000e-06 eta: 0:40:22 time: 0.4663 data_time: 0.0017 memory: 30096 loss: 0.1092 loss_ce: 0.1092 2023/03/03 12:45:55 - mmengine - INFO - Epoch(train) [136][50/79] lr: 1.0000e-06 eta: 0:40:17 time: 0.4547 data_time: 0.0018 memory: 26910 loss: 0.1363 loss_ce: 0.1363 2023/03/03 12:45:59 - mmengine - INFO - Epoch(train) [136][60/79] lr: 1.0000e-06 eta: 0:40:12 time: 0.4238 data_time: 0.0016 memory: 31830 loss: 0.1156 loss_ce: 0.1156 2023/03/03 12:46:04 - mmengine - INFO - Epoch(train) [136][70/79] lr: 1.0000e-06 eta: 0:40:07 time: 0.4798 data_time: 0.0014 memory: 35035 loss: 0.1139 loss_ce: 0.1139 2023/03/03 12:46:08 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:46:14 - mmengine - INFO - Epoch(train) [137][10/79] lr: 1.0000e-06 eta: 0:39:59 time: 0.5404 data_time: 0.0501 memory: 37934 loss: 0.1109 loss_ce: 0.1109 2023/03/03 12:46:18 - mmengine - INFO - Epoch(train) [137][20/79] lr: 1.0000e-06 eta: 0:39:54 time: 0.4468 data_time: 0.0016 memory: 32227 loss: 0.1067 loss_ce: 0.1067 2023/03/03 12:46:23 - mmengine - INFO - Epoch(train) [137][30/79] lr: 1.0000e-06 eta: 0:39:49 time: 0.4963 data_time: 0.0016 memory: 40524 loss: 0.1146 loss_ce: 0.1146 2023/03/03 12:46:28 - mmengine - INFO - Epoch(train) [137][40/79] lr: 1.0000e-06 eta: 0:39:44 time: 0.4431 data_time: 0.0016 memory: 25785 loss: 0.1140 loss_ce: 0.1140 2023/03/03 12:46:32 - mmengine - INFO - Epoch(train) [137][50/79] lr: 1.0000e-06 eta: 0:39:39 time: 0.4731 data_time: 0.0015 memory: 41108 loss: 0.1166 loss_ce: 0.1166 2023/03/03 12:46:37 - mmengine - INFO - Epoch(train) [137][60/79] lr: 1.0000e-06 eta: 0:39:34 time: 0.4595 data_time: 0.0016 memory: 37934 loss: 0.1397 loss_ce: 0.1397 2023/03/03 12:46:42 - mmengine - INFO - Epoch(train) [137][70/79] lr: 1.0000e-06 eta: 0:39:30 time: 0.4745 data_time: 0.0013 memory: 43939 loss: 0.0974 loss_ce: 0.0974 2023/03/03 12:46:46 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:46:51 - mmengine - INFO - Epoch(train) [138][10/79] lr: 1.0000e-06 eta: 0:39:21 time: 0.5055 data_time: 0.0588 memory: 38851 loss: 0.1253 loss_ce: 0.1253 2023/03/03 12:46:56 - mmengine - INFO - Epoch(train) [138][20/79] lr: 1.0000e-06 eta: 0:39:16 time: 0.4602 data_time: 0.0017 memory: 27666 loss: 0.1201 loss_ce: 0.1201 2023/03/03 12:47:00 - mmengine - INFO - Epoch(train) [138][30/79] lr: 1.0000e-06 eta: 0:39:11 time: 0.4859 data_time: 0.0018 memory: 38082 loss: 0.1237 loss_ce: 0.1237 2023/03/03 12:47:05 - mmengine - INFO - Epoch(train) [138][40/79] lr: 1.0000e-06 eta: 0:39:07 time: 0.4772 data_time: 0.0017 memory: 38588 loss: 0.1268 loss_ce: 0.1268 2023/03/03 12:47:10 - mmengine - INFO - Epoch(train) [138][50/79] lr: 1.0000e-06 eta: 0:39:02 time: 0.4723 data_time: 0.0019 memory: 39555 loss: 0.1174 loss_ce: 0.1174 2023/03/03 12:47:15 - mmengine - INFO - Epoch(train) [138][60/79] lr: 1.0000e-06 eta: 0:38:57 time: 0.4630 data_time: 0.0018 memory: 38082 loss: 0.1125 loss_ce: 0.1125 2023/03/03 12:47:19 - mmengine - INFO - Epoch(train) [138][70/79] lr: 1.0000e-06 eta: 0:38:52 time: 0.4633 data_time: 0.0020 memory: 35644 loss: 0.1167 loss_ce: 0.1167 2023/03/03 12:47:24 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:47:29 - mmengine - INFO - Epoch(train) [139][10/79] lr: 1.0000e-06 eta: 0:38:43 time: 0.5224 data_time: 0.0349 memory: 38082 loss: 0.1183 loss_ce: 0.1183 2023/03/03 12:47:33 - mmengine - INFO - Epoch(train) [139][20/79] lr: 1.0000e-06 eta: 0:38:38 time: 0.4470 data_time: 0.0021 memory: 34636 loss: 0.1195 loss_ce: 0.1195 2023/03/03 12:47:38 - mmengine - INFO - Epoch(train) [139][30/79] lr: 1.0000e-06 eta: 0:38:34 time: 0.4474 data_time: 0.0019 memory: 32447 loss: 0.1050 loss_ce: 0.1050 2023/03/03 12:47:42 - mmengine - INFO - Epoch(train) [139][40/79] lr: 1.0000e-06 eta: 0:38:29 time: 0.4650 data_time: 0.0018 memory: 34610 loss: 0.1106 loss_ce: 0.1106 2023/03/03 12:47:47 - mmengine - INFO - Epoch(train) [139][50/79] lr: 1.0000e-06 eta: 0:38:24 time: 0.4947 data_time: 0.0017 memory: 42618 loss: 0.1242 loss_ce: 0.1242 2023/03/03 12:47:52 - mmengine - INFO - Epoch(train) [139][60/79] lr: 1.0000e-06 eta: 0:38:20 time: 0.5092 data_time: 0.0016 memory: 28750 loss: 0.1075 loss_ce: 0.1075 2023/03/03 12:47:57 - mmengine - INFO - Epoch(train) [139][70/79] lr: 1.0000e-06 eta: 0:38:15 time: 0.4628 data_time: 0.0013 memory: 39556 loss: 0.0998 loss_ce: 0.0998 2023/03/03 12:48:01 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:48:06 - mmengine - INFO - Epoch(train) [140][10/79] lr: 1.0000e-06 eta: 0:38:06 time: 0.5155 data_time: 0.0468 memory: 36831 loss: 0.1198 loss_ce: 0.1198 2023/03/03 12:48:10 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:48:10 - mmengine - INFO - Epoch(train) [140][20/79] lr: 1.0000e-06 eta: 0:38:01 time: 0.4695 data_time: 0.0019 memory: 39123 loss: 0.1129 loss_ce: 0.1129 2023/03/03 12:48:15 - mmengine - INFO - Epoch(train) [140][30/79] lr: 1.0000e-06 eta: 0:37:56 time: 0.4928 data_time: 0.0016 memory: 38510 loss: 0.1077 loss_ce: 0.1077 2023/03/03 12:48:20 - mmengine - INFO - Epoch(train) [140][40/79] lr: 1.0000e-06 eta: 0:37:51 time: 0.4951 data_time: 0.0020 memory: 39955 loss: 0.1040 loss_ce: 0.1040 2023/03/03 12:48:25 - mmengine - INFO - Epoch(train) [140][50/79] lr: 1.0000e-06 eta: 0:37:46 time: 0.4299 data_time: 0.0016 memory: 33512 loss: 0.1074 loss_ce: 0.1074 2023/03/03 12:48:29 - mmengine - INFO - Epoch(train) [140][60/79] lr: 1.0000e-06 eta: 0:37:41 time: 0.4049 data_time: 0.0016 memory: 33794 loss: 0.1221 loss_ce: 0.1221 2023/03/03 12:48:33 - mmengine - INFO - Epoch(train) [140][70/79] lr: 1.0000e-06 eta: 0:37:37 time: 0.4644 data_time: 0.0013 memory: 31266 loss: 0.1206 loss_ce: 0.1206 2023/03/03 12:48:37 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:48:49 - mmengine - INFO - Epoch(val) [140][10/75] eta: 0:01:18 time: 1.2042 data_time: 0.0032 memory: 40822 2023/03/03 12:49:30 - mmengine - INFO - Epoch(val) [140][20/75] eta: 0:02:24 time: 4.0451 data_time: 0.0004 memory: 1077 2023/03/03 12:49:49 - mmengine - INFO - Epoch(val) [140][30/75] eta: 0:01:48 time: 1.9548 data_time: 0.0003 memory: 1020 2023/03/03 12:50:05 - mmengine - INFO - Epoch(val) [140][40/75] eta: 0:01:16 time: 1.5041 data_time: 0.0003 memory: 1019 2023/03/03 12:50:19 - mmengine - INFO - Epoch(val) [140][50/75] eta: 0:00:50 time: 1.4022 data_time: 0.0003 memory: 1077 2023/03/03 12:51:01 - mmengine - INFO - Epoch(val) [140][60/75] eta: 0:00:35 time: 4.2428 data_time: 0.0004 memory: 1045 2023/03/03 12:51:29 - mmengine - INFO - Epoch(val) [140][70/75] eta: 0:00:12 time: 2.8490 data_time: 0.0004 memory: 1077 2023/03/03 12:51:43 - mmengine - INFO - text score threshold: 0.80, recall: 0.6883, precision: 0.7390, hmean: 0.7127 2023/03/03 12:51:43 - mmengine - INFO - text score threshold: 0.81, recall: 0.6877, precision: 0.7423, hmean: 0.7140 2023/03/03 12:51:43 - mmengine - INFO - text score threshold: 0.82, recall: 0.6877, precision: 0.7485, hmean: 0.7168 2023/03/03 12:51:43 - mmengine - INFO - text score threshold: 0.83, recall: 0.6872, precision: 0.7524, hmean: 0.7183 2023/03/03 12:51:43 - mmengine - INFO - text score threshold: 0.84, recall: 0.6872, precision: 0.7574, hmean: 0.7206 2023/03/03 12:51:43 - mmengine - INFO - text score threshold: 0.85, recall: 0.6833, precision: 0.7643, hmean: 0.7215 2023/03/03 12:51:43 - mmengine - INFO - text score threshold: 0.86, recall: 0.6811, precision: 0.7718, hmean: 0.7236 2023/03/03 12:51:43 - mmengine - INFO - text score threshold: 0.87, recall: 0.6789, precision: 0.7809, hmean: 0.7264 2023/03/03 12:51:43 - mmengine - INFO - text score threshold: 0.88, recall: 0.6762, precision: 0.7872, hmean: 0.7275 2023/03/03 12:51:43 - mmengine - INFO - text score threshold: 0.89, recall: 0.6723, precision: 0.7934, hmean: 0.7279 2023/03/03 12:51:43 - mmengine - INFO - text score threshold: 0.90, recall: 0.6690, precision: 0.7983, hmean: 0.7280 2023/03/03 12:51:43 - mmengine - INFO - text score threshold: 0.91, recall: 0.6641, precision: 0.8077, hmean: 0.7289 2023/03/03 12:51:43 - mmengine - INFO - text score threshold: 0.92, recall: 0.6570, precision: 0.8137, hmean: 0.7270 2023/03/03 12:51:43 - mmengine - INFO - text score threshold: 0.93, recall: 0.6515, precision: 0.8203, hmean: 0.7262 2023/03/03 12:51:43 - mmengine - INFO - text score threshold: 0.94, recall: 0.6454, precision: 0.8288, hmean: 0.7257 2023/03/03 12:51:43 - mmengine - INFO - text score threshold: 0.95, recall: 0.6350, precision: 0.8415, hmean: 0.7238 2023/03/03 12:51:43 - mmengine - INFO - text score threshold: 0.96, recall: 0.6246, precision: 0.8505, hmean: 0.7203 2023/03/03 12:51:43 - mmengine - INFO - text score threshold: 0.97, recall: 0.6087, precision: 0.8630, hmean: 0.7139 2023/03/03 12:51:43 - mmengine - INFO - text score threshold: 0.98, recall: 0.5939, precision: 0.8804, hmean: 0.7093 2023/03/03 12:51:43 - mmengine - INFO - text score threshold: 0.99, recall: 0.5631, precision: 0.8899, hmean: 0.6897 2023/03/03 12:51:53 - mmengine - INFO - text score threshold: 0.80, recall: 0.7739, precision: 0.8629, hmean: 0.8160 2023/03/03 12:51:53 - mmengine - INFO - text score threshold: 0.81, recall: 0.7728, precision: 0.8654, hmean: 0.8165 2023/03/03 12:51:53 - mmengine - INFO - text score threshold: 0.82, recall: 0.7711, precision: 0.8700, hmean: 0.8176 2023/03/03 12:51:53 - mmengine - INFO - text score threshold: 0.83, recall: 0.7695, precision: 0.8724, hmean: 0.8177 2023/03/03 12:51:53 - mmengine - INFO - text score threshold: 0.84, recall: 0.7684, precision: 0.8761, hmean: 0.8187 2023/03/03 12:51:53 - mmengine - INFO - text score threshold: 0.85, recall: 0.7629, precision: 0.8820, hmean: 0.8181 2023/03/03 12:51:53 - mmengine - INFO - text score threshold: 0.86, recall: 0.7591, precision: 0.8854, hmean: 0.8174 2023/03/03 12:51:53 - mmengine - INFO - text score threshold: 0.87, recall: 0.7519, precision: 0.8902, hmean: 0.8152 2023/03/03 12:51:53 - mmengine - INFO - text score threshold: 0.88, recall: 0.7475, precision: 0.8943, hmean: 0.8143 2023/03/03 12:51:53 - mmengine - INFO - text score threshold: 0.89, recall: 0.7415, precision: 0.8983, hmean: 0.8124 2023/03/03 12:51:53 - mmengine - INFO - text score threshold: 0.90, recall: 0.7366, precision: 0.9001, hmean: 0.8101 2023/03/03 12:51:53 - mmengine - INFO - text score threshold: 0.91, recall: 0.7261, precision: 0.9043, hmean: 0.8055 2023/03/03 12:51:53 - mmengine - INFO - text score threshold: 0.92, recall: 0.7157, precision: 0.9062, hmean: 0.7998 2023/03/03 12:51:53 - mmengine - INFO - text score threshold: 0.93, recall: 0.7053, precision: 0.9075, hmean: 0.7937 2023/03/03 12:51:53 - mmengine - INFO - text score threshold: 0.94, recall: 0.6937, precision: 0.9094, hmean: 0.7870 2023/03/03 12:51:53 - mmengine - INFO - text score threshold: 0.95, recall: 0.6745, precision: 0.9124, hmean: 0.7756 2023/03/03 12:51:53 - mmengine - INFO - text score threshold: 0.96, recall: 0.6592, precision: 0.9147, hmean: 0.7662 2023/03/03 12:51:53 - mmengine - INFO - text score threshold: 0.97, recall: 0.6389, precision: 0.9223, hmean: 0.7549 2023/03/03 12:51:53 - mmengine - INFO - text score threshold: 0.98, recall: 0.6175, precision: 0.9305, hmean: 0.7423 2023/03/03 12:51:53 - mmengine - INFO - text score threshold: 0.99, recall: 0.5818, precision: 0.9339, hmean: 0.7169 2023/03/03 12:51:53 - mmengine - INFO - Epoch(val) [140][75/75] none/precision: 0.8077 none/recall: 0.6641 none/hmean: 0.7289 full/precision: 0.8761 full/recall: 0.7684 full/hmean: 0.8187 2023/03/03 12:51:59 - mmengine - INFO - Epoch(train) [141][10/79] lr: 1.0000e-06 eta: 0:37:28 time: 0.5460 data_time: 0.0544 memory: 45171 loss: 0.1150 loss_ce: 0.1150 2023/03/03 12:52:03 - mmengine - INFO - Epoch(train) [141][20/79] lr: 1.0000e-06 eta: 0:37:23 time: 0.4445 data_time: 0.0015 memory: 39932 loss: 0.1150 loss_ce: 0.1150 2023/03/03 12:52:08 - mmengine - INFO - Epoch(train) [141][30/79] lr: 1.0000e-06 eta: 0:37:18 time: 0.4297 data_time: 0.0015 memory: 35734 loss: 0.1300 loss_ce: 0.1300 2023/03/03 12:52:12 - mmengine - INFO - Epoch(train) [141][40/79] lr: 1.0000e-06 eta: 0:37:13 time: 0.4939 data_time: 0.0017 memory: 40079 loss: 0.1249 loss_ce: 0.1249 2023/03/03 12:52:17 - mmengine - INFO - Epoch(train) [141][50/79] lr: 1.0000e-06 eta: 0:37:08 time: 0.4208 data_time: 0.0016 memory: 31650 loss: 0.1092 loss_ce: 0.1092 2023/03/03 12:52:21 - mmengine - INFO - Epoch(train) [141][60/79] lr: 1.0000e-06 eta: 0:37:03 time: 0.4452 data_time: 0.0016 memory: 29940 loss: 0.1037 loss_ce: 0.1037 2023/03/03 12:52:26 - mmengine - INFO - Epoch(train) [141][70/79] lr: 1.0000e-06 eta: 0:36:59 time: 0.4614 data_time: 0.0013 memory: 33581 loss: 0.1129 loss_ce: 0.1129 2023/03/03 12:52:30 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:52:35 - mmengine - INFO - Epoch(train) [142][10/79] lr: 1.0000e-06 eta: 0:36:50 time: 0.4994 data_time: 0.0613 memory: 37934 loss: 0.1248 loss_ce: 0.1248 2023/03/03 12:52:40 - mmengine - INFO - Epoch(train) [142][20/79] lr: 1.0000e-06 eta: 0:36:45 time: 0.5080 data_time: 0.0015 memory: 40524 loss: 0.1170 loss_ce: 0.1170 2023/03/03 12:52:45 - mmengine - INFO - Epoch(train) [142][30/79] lr: 1.0000e-06 eta: 0:36:40 time: 0.4757 data_time: 0.0019 memory: 41086 loss: 0.1272 loss_ce: 0.1272 2023/03/03 12:52:49 - mmengine - INFO - Epoch(train) [142][40/79] lr: 1.0000e-06 eta: 0:36:35 time: 0.4523 data_time: 0.0015 memory: 39669 loss: 0.1196 loss_ce: 0.1196 2023/03/03 12:52:54 - mmengine - INFO - Epoch(train) [142][50/79] lr: 1.0000e-06 eta: 0:36:31 time: 0.4881 data_time: 0.0015 memory: 37934 loss: 0.1310 loss_ce: 0.1310 2023/03/03 12:52:59 - mmengine - INFO - Epoch(train) [142][60/79] lr: 1.0000e-06 eta: 0:36:26 time: 0.5062 data_time: 0.0015 memory: 37934 loss: 0.1135 loss_ce: 0.1135 2023/03/03 12:53:04 - mmengine - INFO - Epoch(train) [142][70/79] lr: 1.0000e-06 eta: 0:36:21 time: 0.4494 data_time: 0.0016 memory: 35486 loss: 0.1204 loss_ce: 0.1204 2023/03/03 12:53:08 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:53:13 - mmengine - INFO - Epoch(train) [143][10/79] lr: 1.0000e-06 eta: 0:36:12 time: 0.5518 data_time: 0.0478 memory: 44609 loss: 0.1147 loss_ce: 0.1147 2023/03/03 12:53:18 - mmengine - INFO - Epoch(train) [143][20/79] lr: 1.0000e-06 eta: 0:36:08 time: 0.5000 data_time: 0.0016 memory: 41597 loss: 0.1300 loss_ce: 0.1300 2023/03/03 12:53:23 - mmengine - INFO - Epoch(train) [143][30/79] lr: 1.0000e-06 eta: 0:36:03 time: 0.4972 data_time: 0.0015 memory: 37036 loss: 0.1149 loss_ce: 0.1149 2023/03/03 12:53:28 - mmengine - INFO - Epoch(train) [143][40/79] lr: 1.0000e-06 eta: 0:35:58 time: 0.4496 data_time: 0.0016 memory: 39955 loss: 0.1141 loss_ce: 0.1141 2023/03/03 12:53:32 - mmengine - INFO - Epoch(train) [143][50/79] lr: 1.0000e-06 eta: 0:35:53 time: 0.4568 data_time: 0.0015 memory: 38588 loss: 0.1075 loss_ce: 0.1075 2023/03/03 12:53:37 - mmengine - INFO - Epoch(train) [143][60/79] lr: 1.0000e-06 eta: 0:35:49 time: 0.4810 data_time: 0.0019 memory: 38418 loss: 0.1174 loss_ce: 0.1174 2023/03/03 12:53:42 - mmengine - INFO - Epoch(train) [143][70/79] lr: 1.0000e-06 eta: 0:35:44 time: 0.4477 data_time: 0.0014 memory: 40640 loss: 0.1104 loss_ce: 0.1104 2023/03/03 12:53:45 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:53:50 - mmengine - INFO - Epoch(train) [144][10/79] lr: 1.0000e-06 eta: 0:35:34 time: 0.4419 data_time: 0.0497 memory: 37285 loss: 0.1102 loss_ce: 0.1102 2023/03/03 12:53:55 - mmengine - INFO - Epoch(train) [144][20/79] lr: 1.0000e-06 eta: 0:35:30 time: 0.5105 data_time: 0.0020 memory: 37892 loss: 0.1156 loss_ce: 0.1156 2023/03/03 12:54:00 - mmengine - INFO - Epoch(train) [144][30/79] lr: 1.0000e-06 eta: 0:35:25 time: 0.4818 data_time: 0.0022 memory: 31987 loss: 0.1106 loss_ce: 0.1106 2023/03/03 12:54:04 - mmengine - INFO - Epoch(train) [144][40/79] lr: 1.0000e-06 eta: 0:35:20 time: 0.4243 data_time: 0.0022 memory: 24250 loss: 0.1262 loss_ce: 0.1262 2023/03/03 12:54:09 - mmengine - INFO - Epoch(train) [144][50/79] lr: 1.0000e-06 eta: 0:35:15 time: 0.4797 data_time: 0.0021 memory: 37934 loss: 0.1138 loss_ce: 0.1138 2023/03/03 12:54:13 - mmengine - INFO - Epoch(train) [144][60/79] lr: 1.0000e-06 eta: 0:35:10 time: 0.4025 data_time: 0.0018 memory: 36483 loss: 0.1148 loss_ce: 0.1148 2023/03/03 12:54:18 - mmengine - INFO - Epoch(train) [144][70/79] lr: 1.0000e-06 eta: 0:35:06 time: 0.4925 data_time: 0.0014 memory: 37919 loss: 0.1192 loss_ce: 0.1192 2023/03/03 12:54:22 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:54:27 - mmengine - INFO - Epoch(train) [145][10/79] lr: 1.0000e-06 eta: 0:34:57 time: 0.5812 data_time: 0.0468 memory: 40004 loss: 0.1199 loss_ce: 0.1199 2023/03/03 12:54:32 - mmengine - INFO - Epoch(train) [145][20/79] lr: 1.0000e-06 eta: 0:34:52 time: 0.4558 data_time: 0.0019 memory: 37934 loss: 0.1313 loss_ce: 0.1313 2023/03/03 12:54:36 - mmengine - INFO - Epoch(train) [145][30/79] lr: 1.0000e-06 eta: 0:34:47 time: 0.4226 data_time: 0.0018 memory: 33444 loss: 0.1210 loss_ce: 0.1210 2023/03/03 12:54:41 - mmengine - INFO - Epoch(train) [145][40/79] lr: 1.0000e-06 eta: 0:34:42 time: 0.4523 data_time: 0.0020 memory: 37934 loss: 0.1143 loss_ce: 0.1143 2023/03/03 12:54:45 - mmengine - INFO - Epoch(train) [145][50/79] lr: 1.0000e-06 eta: 0:34:37 time: 0.4425 data_time: 0.0019 memory: 34189 loss: 0.1226 loss_ce: 0.1226 2023/03/03 12:54:50 - mmengine - INFO - Epoch(train) [145][60/79] lr: 1.0000e-06 eta: 0:34:33 time: 0.4928 data_time: 0.0016 memory: 34390 loss: 0.1140 loss_ce: 0.1140 2023/03/03 12:54:55 - mmengine - INFO - Epoch(train) [145][70/79] lr: 1.0000e-06 eta: 0:34:28 time: 0.4911 data_time: 0.0016 memory: 28461 loss: 0.1076 loss_ce: 0.1076 2023/03/03 12:54:59 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:55:04 - mmengine - INFO - Epoch(train) [146][10/79] lr: 1.0000e-06 eta: 0:34:19 time: 0.5111 data_time: 0.0573 memory: 35704 loss: 0.1152 loss_ce: 0.1152 2023/03/03 12:55:09 - mmengine - INFO - Epoch(train) [146][20/79] lr: 1.0000e-06 eta: 0:34:14 time: 0.4294 data_time: 0.0016 memory: 29454 loss: 0.1463 loss_ce: 0.1463 2023/03/03 12:55:14 - mmengine - INFO - Epoch(train) [146][30/79] lr: 1.0000e-06 eta: 0:34:10 time: 0.5064 data_time: 0.0016 memory: 26261 loss: 0.1201 loss_ce: 0.1201 2023/03/03 12:55:19 - mmengine - INFO - Epoch(train) [146][40/79] lr: 1.0000e-06 eta: 0:34:05 time: 0.4945 data_time: 0.0015 memory: 38679 loss: 0.1089 loss_ce: 0.1089 2023/03/03 12:55:23 - mmengine - INFO - Epoch(train) [146][50/79] lr: 1.0000e-06 eta: 0:34:00 time: 0.4789 data_time: 0.0015 memory: 34693 loss: 0.1192 loss_ce: 0.1192 2023/03/03 12:55:28 - mmengine - INFO - Epoch(train) [146][60/79] lr: 1.0000e-06 eta: 0:33:55 time: 0.4817 data_time: 0.0017 memory: 33026 loss: 0.1075 loss_ce: 0.1075 2023/03/03 12:55:33 - mmengine - INFO - Epoch(train) [146][70/79] lr: 1.0000e-06 eta: 0:33:51 time: 0.4448 data_time: 0.0015 memory: 42016 loss: 0.1122 loss_ce: 0.1122 2023/03/03 12:55:37 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:55:42 - mmengine - INFO - Epoch(train) [147][10/79] lr: 1.0000e-06 eta: 0:33:42 time: 0.4944 data_time: 0.0470 memory: 46636 loss: 0.1216 loss_ce: 0.1216 2023/03/03 12:55:47 - mmengine - INFO - Epoch(train) [147][20/79] lr: 1.0000e-06 eta: 0:33:37 time: 0.4812 data_time: 0.0015 memory: 37888 loss: 0.1122 loss_ce: 0.1122 2023/03/03 12:55:52 - mmengine - INFO - Epoch(train) [147][30/79] lr: 1.0000e-06 eta: 0:33:32 time: 0.4904 data_time: 0.0017 memory: 40861 loss: 0.0988 loss_ce: 0.0988 2023/03/03 12:55:56 - mmengine - INFO - Epoch(train) [147][40/79] lr: 1.0000e-06 eta: 0:33:27 time: 0.4218 data_time: 0.0016 memory: 38082 loss: 0.1300 loss_ce: 0.1300 2023/03/03 12:56:01 - mmengine - INFO - Epoch(train) [147][50/79] lr: 1.0000e-06 eta: 0:33:23 time: 0.4773 data_time: 0.0017 memory: 38334 loss: 0.1092 loss_ce: 0.1092 2023/03/03 12:56:05 - mmengine - INFO - Epoch(train) [147][60/79] lr: 1.0000e-06 eta: 0:33:18 time: 0.4043 data_time: 0.0018 memory: 41327 loss: 0.1084 loss_ce: 0.1084 2023/03/03 12:56:09 - mmengine - INFO - Epoch(train) [147][70/79] lr: 1.0000e-06 eta: 0:33:13 time: 0.4451 data_time: 0.0014 memory: 39123 loss: 0.1200 loss_ce: 0.1200 2023/03/03 12:56:13 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:56:18 - mmengine - INFO - Epoch(train) [148][10/79] lr: 1.0000e-06 eta: 0:33:04 time: 0.5002 data_time: 0.0284 memory: 37876 loss: 0.0996 loss_ce: 0.0996 2023/03/03 12:56:24 - mmengine - INFO - Epoch(train) [148][20/79] lr: 1.0000e-06 eta: 0:32:59 time: 0.5076 data_time: 0.0017 memory: 35662 loss: 0.1179 loss_ce: 0.1179 2023/03/03 12:56:28 - mmengine - INFO - Epoch(train) [148][30/79] lr: 1.0000e-06 eta: 0:32:54 time: 0.4496 data_time: 0.0016 memory: 40524 loss: 0.1004 loss_ce: 0.1004 2023/03/03 12:56:33 - mmengine - INFO - Epoch(train) [148][40/79] lr: 1.0000e-06 eta: 0:32:50 time: 0.5208 data_time: 0.0015 memory: 36209 loss: 0.1225 loss_ce: 0.1225 2023/03/03 12:56:38 - mmengine - INFO - Epoch(train) [148][50/79] lr: 1.0000e-06 eta: 0:32:45 time: 0.5150 data_time: 0.0016 memory: 40458 loss: 0.1183 loss_ce: 0.1183 2023/03/03 12:56:43 - mmengine - INFO - Epoch(train) [148][60/79] lr: 1.0000e-06 eta: 0:32:40 time: 0.4208 data_time: 0.0015 memory: 24624 loss: 0.1245 loss_ce: 0.1245 2023/03/03 12:56:48 - mmengine - INFO - Epoch(train) [148][70/79] lr: 1.0000e-06 eta: 0:32:36 time: 0.5255 data_time: 0.0018 memory: 48695 loss: 0.1129 loss_ce: 0.1129 2023/03/03 12:56:52 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:56:58 - mmengine - INFO - Epoch(train) [149][10/79] lr: 1.0000e-06 eta: 0:32:27 time: 0.5962 data_time: 0.0478 memory: 39390 loss: 0.1146 loss_ce: 0.1146 2023/03/03 12:57:03 - mmengine - INFO - Epoch(train) [149][20/79] lr: 1.0000e-06 eta: 0:32:22 time: 0.4472 data_time: 0.0019 memory: 30274 loss: 0.1246 loss_ce: 0.1246 2023/03/03 12:57:08 - mmengine - INFO - Epoch(train) [149][30/79] lr: 1.0000e-06 eta: 0:32:18 time: 0.5161 data_time: 0.0018 memory: 39955 loss: 0.1277 loss_ce: 0.1277 2023/03/03 12:57:13 - mmengine - INFO - Epoch(train) [149][40/79] lr: 1.0000e-06 eta: 0:32:13 time: 0.4586 data_time: 0.0020 memory: 36797 loss: 0.1095 loss_ce: 0.1095 2023/03/03 12:57:17 - mmengine - INFO - Epoch(train) [149][50/79] lr: 1.0000e-06 eta: 0:32:08 time: 0.4758 data_time: 0.0022 memory: 33976 loss: 0.1081 loss_ce: 0.1081 2023/03/03 12:57:22 - mmengine - INFO - Epoch(train) [149][60/79] lr: 1.0000e-06 eta: 0:32:03 time: 0.4752 data_time: 0.0021 memory: 39444 loss: 0.1189 loss_ce: 0.1189 2023/03/03 12:57:27 - mmengine - INFO - Epoch(train) [149][70/79] lr: 1.0000e-06 eta: 0:31:59 time: 0.4633 data_time: 0.0019 memory: 27256 loss: 0.1139 loss_ce: 0.1139 2023/03/03 12:57:31 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:57:36 - mmengine - INFO - Epoch(train) [150][10/79] lr: 1.0000e-06 eta: 0:31:50 time: 0.5473 data_time: 0.0441 memory: 39955 loss: 0.1085 loss_ce: 0.1085 2023/03/03 12:57:41 - mmengine - INFO - Epoch(train) [150][20/79] lr: 1.0000e-06 eta: 0:31:45 time: 0.4745 data_time: 0.0017 memory: 38588 loss: 0.1121 loss_ce: 0.1121 2023/03/03 12:57:45 - mmengine - INFO - Epoch(train) [150][30/79] lr: 1.0000e-06 eta: 0:31:40 time: 0.4187 data_time: 0.0017 memory: 38334 loss: 0.1024 loss_ce: 0.1024 2023/03/03 12:57:50 - mmengine - INFO - Epoch(train) [150][40/79] lr: 1.0000e-06 eta: 0:31:35 time: 0.4677 data_time: 0.0018 memory: 33583 loss: 0.1147 loss_ce: 0.1147 2023/03/03 12:57:54 - mmengine - INFO - Epoch(train) [150][50/79] lr: 1.0000e-06 eta: 0:31:30 time: 0.4460 data_time: 0.0016 memory: 34872 loss: 0.1209 loss_ce: 0.1209 2023/03/03 12:57:59 - mmengine - INFO - Epoch(train) [150][60/79] lr: 1.0000e-06 eta: 0:31:25 time: 0.4533 data_time: 0.0015 memory: 25277 loss: 0.1233 loss_ce: 0.1233 2023/03/03 12:58:04 - mmengine - INFO - Epoch(train) [150][70/79] lr: 1.0000e-06 eta: 0:31:21 time: 0.4918 data_time: 0.0014 memory: 39955 loss: 0.1363 loss_ce: 0.1363 2023/03/03 12:58:07 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 12:58:19 - mmengine - INFO - Epoch(val) [150][10/75] eta: 0:01:18 time: 1.2067 data_time: 0.0032 memory: 26063 2023/03/03 12:58:59 - mmengine - INFO - Epoch(val) [150][20/75] eta: 0:02:23 time: 4.0106 data_time: 0.0004 memory: 1077 2023/03/03 12:59:18 - mmengine - INFO - Epoch(val) [150][30/75] eta: 0:01:46 time: 1.8645 data_time: 0.0004 memory: 1020 2023/03/03 12:59:34 - mmengine - INFO - Epoch(val) [150][40/75] eta: 0:01:15 time: 1.5586 data_time: 0.0004 memory: 1019 2023/03/03 12:59:48 - mmengine - INFO - Epoch(val) [150][50/75] eta: 0:00:50 time: 1.4517 data_time: 0.0004 memory: 1077 2023/03/03 13:00:32 - mmengine - INFO - Epoch(val) [150][60/75] eta: 0:00:36 time: 4.4256 data_time: 0.0007 memory: 1045 2023/03/03 13:01:02 - mmengine - INFO - Epoch(val) [150][70/75] eta: 0:00:12 time: 2.9069 data_time: 0.0005 memory: 1077 2023/03/03 13:01:16 - mmengine - INFO - text score threshold: 0.80, recall: 0.6883, precision: 0.7372, hmean: 0.7119 2023/03/03 13:01:16 - mmengine - INFO - text score threshold: 0.81, recall: 0.6877, precision: 0.7423, hmean: 0.7140 2023/03/03 13:01:16 - mmengine - INFO - text score threshold: 0.82, recall: 0.6877, precision: 0.7472, hmean: 0.7162 2023/03/03 13:01:16 - mmengine - INFO - text score threshold: 0.83, recall: 0.6866, precision: 0.7523, hmean: 0.7179 2023/03/03 13:01:16 - mmengine - INFO - text score threshold: 0.84, recall: 0.6855, precision: 0.7579, hmean: 0.7199 2023/03/03 13:01:16 - mmengine - INFO - text score threshold: 0.85, recall: 0.6844, precision: 0.7655, hmean: 0.7227 2023/03/03 13:01:16 - mmengine - INFO - text score threshold: 0.86, recall: 0.6828, precision: 0.7712, hmean: 0.7243 2023/03/03 13:01:16 - mmengine - INFO - text score threshold: 0.87, recall: 0.6817, precision: 0.7792, hmean: 0.7272 2023/03/03 13:01:16 - mmengine - INFO - text score threshold: 0.88, recall: 0.6778, precision: 0.7876, hmean: 0.7286 2023/03/03 13:01:16 - mmengine - INFO - text score threshold: 0.89, recall: 0.6723, precision: 0.7929, hmean: 0.7277 2023/03/03 13:01:16 - mmengine - INFO - text score threshold: 0.90, recall: 0.6685, precision: 0.7976, hmean: 0.7274 2023/03/03 13:01:16 - mmengine - INFO - text score threshold: 0.91, recall: 0.6647, precision: 0.8063, hmean: 0.7286 2023/03/03 13:01:16 - mmengine - INFO - text score threshold: 0.92, recall: 0.6586, precision: 0.8147, hmean: 0.7284 2023/03/03 13:01:16 - mmengine - INFO - text score threshold: 0.93, recall: 0.6537, precision: 0.8225, hmean: 0.7284 2023/03/03 13:01:16 - mmengine - INFO - text score threshold: 0.94, recall: 0.6482, precision: 0.8311, hmean: 0.7283 2023/03/03 13:01:16 - mmengine - INFO - text score threshold: 0.95, recall: 0.6394, precision: 0.8424, hmean: 0.7270 2023/03/03 13:01:16 - mmengine - INFO - text score threshold: 0.96, recall: 0.6284, precision: 0.8545, hmean: 0.7242 2023/03/03 13:01:16 - mmengine - INFO - text score threshold: 0.97, recall: 0.6131, precision: 0.8639, hmean: 0.7172 2023/03/03 13:01:16 - mmengine - INFO - text score threshold: 0.98, recall: 0.5971, precision: 0.8774, hmean: 0.7106 2023/03/03 13:01:16 - mmengine - INFO - text score threshold: 0.99, recall: 0.5659, precision: 0.8919, hmean: 0.6924 2023/03/03 13:01:26 - mmengine - INFO - text score threshold: 0.80, recall: 0.7755, precision: 0.8621, hmean: 0.8165 2023/03/03 13:01:26 - mmengine - INFO - text score threshold: 0.81, recall: 0.7744, precision: 0.8656, hmean: 0.8175 2023/03/03 13:01:26 - mmengine - INFO - text score threshold: 0.82, recall: 0.7733, precision: 0.8692, hmean: 0.8185 2023/03/03 13:01:26 - mmengine - INFO - text score threshold: 0.83, recall: 0.7711, precision: 0.8732, hmean: 0.8190 2023/03/03 13:01:26 - mmengine - INFO - text score threshold: 0.84, recall: 0.7684, precision: 0.8766, hmean: 0.8190 2023/03/03 13:01:26 - mmengine - INFO - text score threshold: 0.85, recall: 0.7640, precision: 0.8821, hmean: 0.8188 2023/03/03 13:01:26 - mmengine - INFO - text score threshold: 0.86, recall: 0.7596, precision: 0.8838, hmean: 0.8170 2023/03/03 13:01:26 - mmengine - INFO - text score threshold: 0.87, recall: 0.7558, precision: 0.8884, hmean: 0.8167 2023/03/03 13:01:26 - mmengine - INFO - text score threshold: 0.88, recall: 0.7492, precision: 0.8927, hmean: 0.8147 2023/03/03 13:01:26 - mmengine - INFO - text score threshold: 0.89, recall: 0.7409, precision: 0.8958, hmean: 0.8111 2023/03/03 13:01:26 - mmengine - INFO - text score threshold: 0.90, recall: 0.7344, precision: 0.8980, hmean: 0.8080 2023/03/03 13:01:26 - mmengine - INFO - text score threshold: 0.91, recall: 0.7272, precision: 0.9032, hmean: 0.8057 2023/03/03 13:01:26 - mmengine - INFO - text score threshold: 0.92, recall: 0.7179, precision: 0.9071, hmean: 0.8015 2023/03/03 13:01:26 - mmengine - INFO - text score threshold: 0.93, recall: 0.7086, precision: 0.9098, hmean: 0.7967 2023/03/03 13:01:26 - mmengine - INFO - text score threshold: 0.94, recall: 0.6976, precision: 0.9131, hmean: 0.7909 2023/03/03 13:01:26 - mmengine - INFO - text score threshold: 0.95, recall: 0.6817, precision: 0.9166, hmean: 0.7819 2023/03/03 13:01:26 - mmengine - INFO - text score threshold: 0.96, recall: 0.6641, precision: 0.9195, hmean: 0.7712 2023/03/03 13:01:26 - mmengine - INFO - text score threshold: 0.97, recall: 0.6454, precision: 0.9260, hmean: 0.7607 2023/03/03 13:01:26 - mmengine - INFO - text score threshold: 0.98, recall: 0.6240, precision: 0.9320, hmean: 0.7475 2023/03/03 13:01:26 - mmengine - INFO - text score threshold: 0.99, recall: 0.5834, precision: 0.9357, hmean: 0.7187 2023/03/03 13:01:26 - mmengine - INFO - Epoch(val) [150][75/75] none/precision: 0.8063 none/recall: 0.6647 none/hmean: 0.7286 full/precision: 0.8732 full/recall: 0.7711 full/hmean: 0.8190 2023/03/03 13:01:31 - mmengine - INFO - Epoch(train) [151][10/79] lr: 1.0000e-06 eta: 0:31:12 time: 0.5443 data_time: 0.0541 memory: 41108 loss: 0.1093 loss_ce: 0.1093 2023/03/03 13:01:35 - mmengine - INFO - Epoch(train) [151][20/79] lr: 1.0000e-06 eta: 0:31:07 time: 0.4394 data_time: 0.0020 memory: 38082 loss: 0.1228 loss_ce: 0.1228 2023/03/03 13:01:40 - mmengine - INFO - Epoch(train) [151][30/79] lr: 1.0000e-06 eta: 0:31:02 time: 0.4627 data_time: 0.0019 memory: 34644 loss: 0.1172 loss_ce: 0.1172 2023/03/03 13:01:45 - mmengine - INFO - Epoch(train) [151][40/79] lr: 1.0000e-06 eta: 0:30:57 time: 0.4533 data_time: 0.0019 memory: 43881 loss: 0.1059 loss_ce: 0.1059 2023/03/03 13:01:49 - mmengine - INFO - Epoch(train) [151][50/79] lr: 1.0000e-06 eta: 0:30:52 time: 0.4586 data_time: 0.0018 memory: 30869 loss: 0.1206 loss_ce: 0.1206 2023/03/03 13:01:54 - mmengine - INFO - Epoch(train) [151][60/79] lr: 1.0000e-06 eta: 0:30:48 time: 0.5039 data_time: 0.0017 memory: 41643 loss: 0.1091 loss_ce: 0.1091 2023/03/03 13:01:59 - mmengine - INFO - Epoch(train) [151][70/79] lr: 1.0000e-06 eta: 0:30:43 time: 0.4508 data_time: 0.0018 memory: 35500 loss: 0.1032 loss_ce: 0.1032 2023/03/03 13:02:03 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:02:08 - mmengine - INFO - Epoch(train) [152][10/79] lr: 1.0000e-06 eta: 0:30:34 time: 0.5156 data_time: 0.0494 memory: 39251 loss: 0.1182 loss_ce: 0.1182 2023/03/03 13:02:13 - mmengine - INFO - Epoch(train) [152][20/79] lr: 1.0000e-06 eta: 0:30:29 time: 0.4704 data_time: 0.0022 memory: 26528 loss: 0.1198 loss_ce: 0.1198 2023/03/03 13:02:17 - mmengine - INFO - Epoch(train) [152][30/79] lr: 1.0000e-06 eta: 0:30:24 time: 0.4559 data_time: 0.0019 memory: 35178 loss: 0.1197 loss_ce: 0.1197 2023/03/03 13:02:22 - mmengine - INFO - Epoch(train) [152][40/79] lr: 1.0000e-06 eta: 0:30:20 time: 0.4557 data_time: 0.0018 memory: 36745 loss: 0.1178 loss_ce: 0.1178 2023/03/03 13:02:27 - mmengine - INFO - Epoch(train) [152][50/79] lr: 1.0000e-06 eta: 0:30:15 time: 0.4883 data_time: 0.0017 memory: 28461 loss: 0.1195 loss_ce: 0.1195 2023/03/03 13:02:31 - mmengine - INFO - Epoch(train) [152][60/79] lr: 1.0000e-06 eta: 0:30:10 time: 0.4861 data_time: 0.0017 memory: 37100 loss: 0.1148 loss_ce: 0.1148 2023/03/03 13:02:36 - mmengine - INFO - Epoch(train) [152][70/79] lr: 1.0000e-06 eta: 0:30:05 time: 0.4529 data_time: 0.0016 memory: 39407 loss: 0.1141 loss_ce: 0.1141 2023/03/03 13:02:37 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:02:40 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:02:45 - mmengine - INFO - Epoch(train) [153][10/79] lr: 1.0000e-06 eta: 0:29:56 time: 0.4913 data_time: 0.0555 memory: 39123 loss: 0.1035 loss_ce: 0.1035 2023/03/03 13:02:50 - mmengine - INFO - Epoch(train) [153][20/79] lr: 1.0000e-06 eta: 0:29:52 time: 0.4935 data_time: 0.0018 memory: 38051 loss: 0.1127 loss_ce: 0.1127 2023/03/03 13:02:55 - mmengine - INFO - Epoch(train) [153][30/79] lr: 1.0000e-06 eta: 0:29:47 time: 0.4566 data_time: 0.0017 memory: 35825 loss: 0.1270 loss_ce: 0.1270 2023/03/03 13:02:59 - mmengine - INFO - Epoch(train) [153][40/79] lr: 1.0000e-06 eta: 0:29:42 time: 0.4218 data_time: 0.0018 memory: 33954 loss: 0.1273 loss_ce: 0.1273 2023/03/03 13:03:04 - mmengine - INFO - Epoch(train) [153][50/79] lr: 1.0000e-06 eta: 0:29:37 time: 0.4917 data_time: 0.0016 memory: 36752 loss: 0.1032 loss_ce: 0.1032 2023/03/03 13:03:09 - mmengine - INFO - Epoch(train) [153][60/79] lr: 1.0000e-06 eta: 0:29:33 time: 0.5178 data_time: 0.0016 memory: 42642 loss: 0.1049 loss_ce: 0.1049 2023/03/03 13:03:14 - mmengine - INFO - Epoch(train) [153][70/79] lr: 1.0000e-06 eta: 0:29:28 time: 0.5293 data_time: 0.0014 memory: 31678 loss: 0.1075 loss_ce: 0.1075 2023/03/03 13:03:19 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:03:24 - mmengine - INFO - Epoch(train) [154][10/79] lr: 1.0000e-06 eta: 0:29:19 time: 0.5032 data_time: 0.0665 memory: 41313 loss: 0.1100 loss_ce: 0.1100 2023/03/03 13:03:28 - mmengine - INFO - Epoch(train) [154][20/79] lr: 1.0000e-06 eta: 0:29:14 time: 0.4696 data_time: 0.0018 memory: 36237 loss: 0.1206 loss_ce: 0.1206 2023/03/03 13:03:33 - mmengine - INFO - Epoch(train) [154][30/79] lr: 1.0000e-06 eta: 0:29:10 time: 0.4376 data_time: 0.0017 memory: 40965 loss: 0.1059 loss_ce: 0.1059 2023/03/03 13:03:37 - mmengine - INFO - Epoch(train) [154][40/79] lr: 1.0000e-06 eta: 0:29:05 time: 0.4316 data_time: 0.0018 memory: 27004 loss: 0.1225 loss_ce: 0.1225 2023/03/03 13:03:42 - mmengine - INFO - Epoch(train) [154][50/79] lr: 1.0000e-06 eta: 0:29:00 time: 0.4886 data_time: 0.0018 memory: 41273 loss: 0.1172 loss_ce: 0.1172 2023/03/03 13:03:47 - mmengine - INFO - Epoch(train) [154][60/79] lr: 1.0000e-06 eta: 0:28:55 time: 0.4492 data_time: 0.0022 memory: 31812 loss: 0.1192 loss_ce: 0.1192 2023/03/03 13:03:51 - mmengine - INFO - Epoch(train) [154][70/79] lr: 1.0000e-06 eta: 0:28:50 time: 0.4940 data_time: 0.0017 memory: 35229 loss: 0.1265 loss_ce: 0.1265 2023/03/03 13:03:55 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:04:00 - mmengine - INFO - Epoch(train) [155][10/79] lr: 1.0000e-06 eta: 0:28:41 time: 0.4879 data_time: 0.0448 memory: 28753 loss: 0.1071 loss_ce: 0.1071 2023/03/03 13:04:05 - mmengine - INFO - Epoch(train) [155][20/79] lr: 1.0000e-06 eta: 0:28:36 time: 0.4627 data_time: 0.0019 memory: 38533 loss: 0.1101 loss_ce: 0.1101 2023/03/03 13:04:09 - mmengine - INFO - Epoch(train) [155][30/79] lr: 1.0000e-06 eta: 0:28:32 time: 0.4232 data_time: 0.0017 memory: 37934 loss: 0.1111 loss_ce: 0.1111 2023/03/03 13:04:14 - mmengine - INFO - Epoch(train) [155][40/79] lr: 1.0000e-06 eta: 0:28:27 time: 0.4641 data_time: 0.0016 memory: 42016 loss: 0.1128 loss_ce: 0.1128 2023/03/03 13:04:19 - mmengine - INFO - Epoch(train) [155][50/79] lr: 1.0000e-06 eta: 0:28:22 time: 0.5220 data_time: 0.0015 memory: 37934 loss: 0.1252 loss_ce: 0.1252 2023/03/03 13:04:24 - mmengine - INFO - Epoch(train) [155][60/79] lr: 1.0000e-06 eta: 0:28:17 time: 0.4682 data_time: 0.0015 memory: 37097 loss: 0.1148 loss_ce: 0.1148 2023/03/03 13:04:28 - mmengine - INFO - Epoch(train) [155][70/79] lr: 1.0000e-06 eta: 0:28:12 time: 0.4145 data_time: 0.0016 memory: 37934 loss: 0.1133 loss_ce: 0.1133 2023/03/03 13:04:32 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:04:37 - mmengine - INFO - Epoch(train) [156][10/79] lr: 1.0000e-06 eta: 0:28:04 time: 0.5460 data_time: 0.0570 memory: 46540 loss: 0.1190 loss_ce: 0.1190 2023/03/03 13:04:42 - mmengine - INFO - Epoch(train) [156][20/79] lr: 1.0000e-06 eta: 0:27:59 time: 0.4933 data_time: 0.0020 memory: 33715 loss: 0.1086 loss_ce: 0.1086 2023/03/03 13:04:47 - mmengine - INFO - Epoch(train) [156][30/79] lr: 1.0000e-06 eta: 0:27:54 time: 0.4684 data_time: 0.0016 memory: 37934 loss: 0.1173 loss_ce: 0.1173 2023/03/03 13:04:51 - mmengine - INFO - Epoch(train) [156][40/79] lr: 1.0000e-06 eta: 0:27:49 time: 0.4841 data_time: 0.0015 memory: 34258 loss: 0.1275 loss_ce: 0.1275 2023/03/03 13:04:56 - mmengine - INFO - Epoch(train) [156][50/79] lr: 1.0000e-06 eta: 0:27:45 time: 0.4616 data_time: 0.0016 memory: 39669 loss: 0.1340 loss_ce: 0.1340 2023/03/03 13:05:01 - mmengine - INFO - Epoch(train) [156][60/79] lr: 1.0000e-06 eta: 0:27:40 time: 0.5250 data_time: 0.0016 memory: 35680 loss: 0.0997 loss_ce: 0.0997 2023/03/03 13:05:06 - mmengine - INFO - Epoch(train) [156][70/79] lr: 1.0000e-06 eta: 0:27:35 time: 0.4568 data_time: 0.0015 memory: 26656 loss: 0.1165 loss_ce: 0.1165 2023/03/03 13:05:10 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:05:15 - mmengine - INFO - Epoch(train) [157][10/79] lr: 1.0000e-06 eta: 0:27:26 time: 0.5081 data_time: 0.0369 memory: 37009 loss: 0.1362 loss_ce: 0.1362 2023/03/03 13:05:20 - mmengine - INFO - Epoch(train) [157][20/79] lr: 1.0000e-06 eta: 0:27:21 time: 0.4629 data_time: 0.0018 memory: 42351 loss: 0.0939 loss_ce: 0.0939 2023/03/03 13:05:24 - mmengine - INFO - Epoch(train) [157][30/79] lr: 1.0000e-06 eta: 0:27:17 time: 0.4637 data_time: 0.0019 memory: 34484 loss: 0.1167 loss_ce: 0.1167 2023/03/03 13:05:29 - mmengine - INFO - Epoch(train) [157][40/79] lr: 1.0000e-06 eta: 0:27:12 time: 0.4806 data_time: 0.0020 memory: 35147 loss: 0.1173 loss_ce: 0.1173 2023/03/03 13:05:34 - mmengine - INFO - Epoch(train) [157][50/79] lr: 1.0000e-06 eta: 0:27:07 time: 0.4556 data_time: 0.0018 memory: 30984 loss: 0.1121 loss_ce: 0.1121 2023/03/03 13:05:38 - mmengine - INFO - Epoch(train) [157][60/79] lr: 1.0000e-06 eta: 0:27:02 time: 0.4384 data_time: 0.0017 memory: 39123 loss: 0.1105 loss_ce: 0.1105 2023/03/03 13:05:42 - mmengine - INFO - Epoch(train) [157][70/79] lr: 1.0000e-06 eta: 0:26:57 time: 0.4528 data_time: 0.0018 memory: 38465 loss: 0.1264 loss_ce: 0.1264 2023/03/03 13:05:46 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:05:52 - mmengine - INFO - Epoch(train) [158][10/79] lr: 1.0000e-06 eta: 0:26:48 time: 0.5771 data_time: 0.0948 memory: 31332 loss: 0.1066 loss_ce: 0.1066 2023/03/03 13:05:57 - mmengine - INFO - Epoch(train) [158][20/79] lr: 1.0000e-06 eta: 0:26:44 time: 0.4375 data_time: 0.0019 memory: 38082 loss: 0.1144 loss_ce: 0.1144 2023/03/03 13:06:01 - mmengine - INFO - Epoch(train) [158][30/79] lr: 1.0000e-06 eta: 0:26:39 time: 0.4743 data_time: 0.0020 memory: 35561 loss: 0.1119 loss_ce: 0.1119 2023/03/03 13:06:06 - mmengine - INFO - Epoch(train) [158][40/79] lr: 1.0000e-06 eta: 0:26:34 time: 0.4695 data_time: 0.0026 memory: 36521 loss: 0.1101 loss_ce: 0.1101 2023/03/03 13:06:11 - mmengine - INFO - Epoch(train) [158][50/79] lr: 1.0000e-06 eta: 0:26:29 time: 0.5052 data_time: 0.0018 memory: 40229 loss: 0.1023 loss_ce: 0.1023 2023/03/03 13:06:16 - mmengine - INFO - Epoch(train) [158][60/79] lr: 1.0000e-06 eta: 0:26:25 time: 0.4832 data_time: 0.0017 memory: 35035 loss: 0.1128 loss_ce: 0.1128 2023/03/03 13:06:21 - mmengine - INFO - Epoch(train) [158][70/79] lr: 1.0000e-06 eta: 0:26:20 time: 0.5055 data_time: 0.0016 memory: 37934 loss: 0.1264 loss_ce: 0.1264 2023/03/03 13:06:25 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:06:31 - mmengine - INFO - Epoch(train) [159][10/79] lr: 1.0000e-06 eta: 0:26:11 time: 0.5755 data_time: 0.1316 memory: 44271 loss: 0.1039 loss_ce: 0.1039 2023/03/03 13:06:36 - mmengine - INFO - Epoch(train) [159][20/79] lr: 1.0000e-06 eta: 0:26:07 time: 0.5116 data_time: 0.0024 memory: 34184 loss: 0.1367 loss_ce: 0.1367 2023/03/03 13:06:41 - mmengine - INFO - Epoch(train) [159][30/79] lr: 1.0000e-06 eta: 0:26:02 time: 0.4931 data_time: 0.0028 memory: 48193 loss: 0.1111 loss_ce: 0.1111 2023/03/03 13:06:46 - mmengine - INFO - Epoch(train) [159][40/79] lr: 1.0000e-06 eta: 0:25:57 time: 0.4505 data_time: 0.0024 memory: 38233 loss: 0.1162 loss_ce: 0.1162 2023/03/03 13:06:50 - mmengine - INFO - Epoch(train) [159][50/79] lr: 1.0000e-06 eta: 0:25:52 time: 0.4263 data_time: 0.0024 memory: 24036 loss: 0.1081 loss_ce: 0.1081 2023/03/03 13:06:55 - mmengine - INFO - Epoch(train) [159][60/79] lr: 1.0000e-06 eta: 0:25:48 time: 0.5278 data_time: 0.0022 memory: 33650 loss: 0.1089 loss_ce: 0.1089 2023/03/03 13:06:59 - mmengine - INFO - Epoch(train) [159][70/79] lr: 1.0000e-06 eta: 0:25:43 time: 0.4191 data_time: 0.0017 memory: 37934 loss: 0.1018 loss_ce: 0.1018 2023/03/03 13:07:03 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:07:08 - mmengine - INFO - Epoch(train) [160][10/79] lr: 1.0000e-06 eta: 0:25:34 time: 0.5115 data_time: 0.0747 memory: 37934 loss: 0.1137 loss_ce: 0.1137 2023/03/03 13:07:14 - mmengine - INFO - Epoch(train) [160][20/79] lr: 1.0000e-06 eta: 0:25:29 time: 0.5315 data_time: 0.0017 memory: 48178 loss: 0.1134 loss_ce: 0.1134 2023/03/03 13:07:18 - mmengine - INFO - Epoch(train) [160][30/79] lr: 1.0000e-06 eta: 0:25:24 time: 0.4525 data_time: 0.0017 memory: 37556 loss: 0.0987 loss_ce: 0.0987 2023/03/03 13:07:24 - mmengine - INFO - Epoch(train) [160][40/79] lr: 1.0000e-06 eta: 0:25:20 time: 0.5846 data_time: 0.0016 memory: 40918 loss: 0.1028 loss_ce: 0.1028 2023/03/03 13:07:28 - mmengine - INFO - Epoch(train) [160][50/79] lr: 1.0000e-06 eta: 0:25:15 time: 0.3816 data_time: 0.0018 memory: 38334 loss: 0.1240 loss_ce: 0.1240 2023/03/03 13:07:32 - mmengine - INFO - Epoch(train) [160][60/79] lr: 1.0000e-06 eta: 0:25:10 time: 0.4394 data_time: 0.0016 memory: 41469 loss: 0.1140 loss_ce: 0.1140 2023/03/03 13:07:36 - mmengine - INFO - Epoch(train) [160][70/79] lr: 1.0000e-06 eta: 0:25:05 time: 0.3823 data_time: 0.0014 memory: 28556 loss: 0.1215 loss_ce: 0.1215 2023/03/03 13:07:40 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:07:53 - mmengine - INFO - Epoch(val) [160][10/75] eta: 0:01:25 time: 1.3202 data_time: 0.0048 memory: 35852 2023/03/03 13:08:39 - mmengine - INFO - Epoch(val) [160][20/75] eta: 0:02:40 time: 4.5169 data_time: 0.0004 memory: 1077 2023/03/03 13:08:59 - mmengine - INFO - Epoch(val) [160][30/75] eta: 0:01:57 time: 2.0269 data_time: 0.0003 memory: 1020 2023/03/03 13:09:15 - mmengine - INFO - Epoch(val) [160][40/75] eta: 0:01:22 time: 1.5755 data_time: 0.0004 memory: 1019 2023/03/03 13:09:30 - mmengine - INFO - Epoch(val) [160][50/75] eta: 0:00:54 time: 1.5376 data_time: 0.0004 memory: 1077 2023/03/03 13:09:53 - mmengine - INFO - Epoch(val) [160][60/75] eta: 0:00:33 time: 2.2963 data_time: 0.0004 memory: 1045 2023/03/03 13:10:46 - mmengine - INFO - Epoch(val) [160][70/75] eta: 0:00:13 time: 5.2950 data_time: 0.0004 memory: 1077 2023/03/03 13:10:59 - mmengine - INFO - text score threshold: 0.80, recall: 0.6844, precision: 0.7383, hmean: 0.7103 2023/03/03 13:10:59 - mmengine - INFO - text score threshold: 0.81, recall: 0.6839, precision: 0.7426, hmean: 0.7120 2023/03/03 13:10:59 - mmengine - INFO - text score threshold: 0.82, recall: 0.6839, precision: 0.7457, hmean: 0.7134 2023/03/03 13:10:59 - mmengine - INFO - text score threshold: 0.83, recall: 0.6833, precision: 0.7477, hmean: 0.7141 2023/03/03 13:10:59 - mmengine - INFO - text score threshold: 0.84, recall: 0.6795, precision: 0.7521, hmean: 0.7140 2023/03/03 13:10:59 - mmengine - INFO - text score threshold: 0.85, recall: 0.6784, precision: 0.7587, hmean: 0.7163 2023/03/03 13:10:59 - mmengine - INFO - text score threshold: 0.86, recall: 0.6767, precision: 0.7630, hmean: 0.7173 2023/03/03 13:10:59 - mmengine - INFO - text score threshold: 0.87, recall: 0.6762, precision: 0.7705, hmean: 0.7203 2023/03/03 13:10:59 - mmengine - INFO - text score threshold: 0.88, recall: 0.6740, precision: 0.7797, hmean: 0.7230 2023/03/03 13:10:59 - mmengine - INFO - text score threshold: 0.89, recall: 0.6718, precision: 0.7866, hmean: 0.7247 2023/03/03 13:10:59 - mmengine - INFO - text score threshold: 0.90, recall: 0.6674, precision: 0.7963, hmean: 0.7262 2023/03/03 13:10:59 - mmengine - INFO - text score threshold: 0.91, recall: 0.6592, precision: 0.8039, hmean: 0.7244 2023/03/03 13:10:59 - mmengine - INFO - text score threshold: 0.92, recall: 0.6537, precision: 0.8108, hmean: 0.7238 2023/03/03 13:10:59 - mmengine - INFO - text score threshold: 0.93, recall: 0.6487, precision: 0.8186, hmean: 0.7238 2023/03/03 13:10:59 - mmengine - INFO - text score threshold: 0.94, recall: 0.6416, precision: 0.8279, hmean: 0.7229 2023/03/03 13:10:59 - mmengine - INFO - text score threshold: 0.95, recall: 0.6350, precision: 0.8390, hmean: 0.7229 2023/03/03 13:10:59 - mmengine - INFO - text score threshold: 0.96, recall: 0.6251, precision: 0.8519, hmean: 0.7211 2023/03/03 13:10:59 - mmengine - INFO - text score threshold: 0.97, recall: 0.6142, precision: 0.8608, hmean: 0.7168 2023/03/03 13:10:59 - mmengine - INFO - text score threshold: 0.98, recall: 0.5960, precision: 0.8744, hmean: 0.7089 2023/03/03 13:10:59 - mmengine - INFO - text score threshold: 0.99, recall: 0.5648, precision: 0.8925, hmean: 0.6918 2023/03/03 13:11:09 - mmengine - INFO - text score threshold: 0.80, recall: 0.7722, precision: 0.8653, hmean: 0.8161 2023/03/03 13:11:09 - mmengine - INFO - text score threshold: 0.81, recall: 0.7706, precision: 0.8677, hmean: 0.8163 2023/03/03 13:11:09 - mmengine - INFO - text score threshold: 0.82, recall: 0.7700, precision: 0.8687, hmean: 0.8164 2023/03/03 13:11:09 - mmengine - INFO - text score threshold: 0.83, recall: 0.7695, precision: 0.8708, hmean: 0.8170 2023/03/03 13:11:09 - mmengine - INFO - text score threshold: 0.84, recall: 0.7651, precision: 0.8745, hmean: 0.8162 2023/03/03 13:11:09 - mmengine - INFO - text score threshold: 0.85, recall: 0.7602, precision: 0.8777, hmean: 0.8147 2023/03/03 13:11:09 - mmengine - INFO - text score threshold: 0.86, recall: 0.7569, precision: 0.8806, hmean: 0.8140 2023/03/03 13:11:09 - mmengine - INFO - text score threshold: 0.87, recall: 0.7530, precision: 0.8829, hmean: 0.8128 2023/03/03 13:11:09 - mmengine - INFO - text score threshold: 0.88, recall: 0.7481, precision: 0.8891, hmean: 0.8125 2023/03/03 13:11:09 - mmengine - INFO - text score threshold: 0.89, recall: 0.7437, precision: 0.8938, hmean: 0.8119 2023/03/03 13:11:09 - mmengine - INFO - text score threshold: 0.90, recall: 0.7355, precision: 0.8987, hmean: 0.8089 2023/03/03 13:11:09 - mmengine - INFO - text score threshold: 0.91, recall: 0.7250, precision: 0.9036, hmean: 0.8045 2023/03/03 13:11:09 - mmengine - INFO - text score threshold: 0.92, recall: 0.7151, precision: 0.9061, hmean: 0.7994 2023/03/03 13:11:09 - mmengine - INFO - text score threshold: 0.93, recall: 0.7058, precision: 0.9088, hmean: 0.7946 2023/03/03 13:11:09 - mmengine - INFO - text score threshold: 0.94, recall: 0.6932, precision: 0.9126, hmean: 0.7879 2023/03/03 13:11:09 - mmengine - INFO - text score threshold: 0.95, recall: 0.6784, precision: 0.9142, hmean: 0.7788 2023/03/03 13:11:09 - mmengine - INFO - text score threshold: 0.96, recall: 0.6597, precision: 0.9169, hmean: 0.7673 2023/03/03 13:11:09 - mmengine - INFO - text score threshold: 0.97, recall: 0.6443, precision: 0.9201, hmean: 0.7579 2023/03/03 13:11:09 - mmengine - INFO - text score threshold: 0.98, recall: 0.6213, precision: 0.9271, hmean: 0.7440 2023/03/03 13:11:09 - mmengine - INFO - text score threshold: 0.99, recall: 0.5845, precision: 0.9375, hmean: 0.7201 2023/03/03 13:11:09 - mmengine - INFO - Epoch(val) [160][75/75] none/precision: 0.7963 none/recall: 0.6674 none/hmean: 0.7262 full/precision: 0.8708 full/recall: 0.7695 full/hmean: 0.8170 2023/03/03 13:11:14 - mmengine - INFO - Epoch(train) [161][10/79] lr: 1.0000e-06 eta: 0:24:56 time: 0.5266 data_time: 0.0481 memory: 39123 loss: 0.1339 loss_ce: 0.1339 2023/03/03 13:11:19 - mmengine - INFO - Epoch(train) [161][20/79] lr: 1.0000e-06 eta: 0:24:51 time: 0.4546 data_time: 0.0015 memory: 37934 loss: 0.1254 loss_ce: 0.1254 2023/03/03 13:11:23 - mmengine - INFO - Epoch(train) [161][30/79] lr: 1.0000e-06 eta: 0:24:46 time: 0.4499 data_time: 0.0015 memory: 23778 loss: 0.1192 loss_ce: 0.1192 2023/03/03 13:11:29 - mmengine - INFO - Epoch(train) [161][40/79] lr: 1.0000e-06 eta: 0:24:42 time: 0.5093 data_time: 0.0015 memory: 32450 loss: 0.1085 loss_ce: 0.1085 2023/03/03 13:11:33 - mmengine - INFO - Epoch(train) [161][50/79] lr: 1.0000e-06 eta: 0:24:37 time: 0.4530 data_time: 0.0014 memory: 27605 loss: 0.1182 loss_ce: 0.1182 2023/03/03 13:11:38 - mmengine - INFO - Epoch(train) [161][60/79] lr: 1.0000e-06 eta: 0:24:32 time: 0.4836 data_time: 0.0014 memory: 36416 loss: 0.1045 loss_ce: 0.1045 2023/03/03 13:11:42 - mmengine - INFO - Epoch(train) [161][70/79] lr: 1.0000e-06 eta: 0:24:27 time: 0.4390 data_time: 0.0013 memory: 38116 loss: 0.1082 loss_ce: 0.1082 2023/03/03 13:11:46 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:11:51 - mmengine - INFO - Epoch(train) [162][10/79] lr: 1.0000e-06 eta: 0:24:18 time: 0.5153 data_time: 0.0478 memory: 40818 loss: 0.1110 loss_ce: 0.1110 2023/03/03 13:11:56 - mmengine - INFO - Epoch(train) [162][20/79] lr: 1.0000e-06 eta: 0:24:14 time: 0.4565 data_time: 0.0014 memory: 32330 loss: 0.1103 loss_ce: 0.1103 2023/03/03 13:12:00 - mmengine - INFO - Epoch(train) [162][30/79] lr: 1.0000e-06 eta: 0:24:09 time: 0.4259 data_time: 0.0014 memory: 39718 loss: 0.1063 loss_ce: 0.1063 2023/03/03 13:12:05 - mmengine - INFO - Epoch(train) [162][40/79] lr: 1.0000e-06 eta: 0:24:04 time: 0.4594 data_time: 0.0014 memory: 27972 loss: 0.1033 loss_ce: 0.1033 2023/03/03 13:12:10 - mmengine - INFO - Epoch(train) [162][50/79] lr: 1.0000e-06 eta: 0:23:59 time: 0.4820 data_time: 0.0016 memory: 37934 loss: 0.1251 loss_ce: 0.1251 2023/03/03 13:12:15 - mmengine - INFO - Epoch(train) [162][60/79] lr: 1.0000e-06 eta: 0:23:55 time: 0.5623 data_time: 0.0014 memory: 42159 loss: 0.1190 loss_ce: 0.1190 2023/03/03 13:12:20 - mmengine - INFO - Epoch(train) [162][70/79] lr: 1.0000e-06 eta: 0:23:50 time: 0.5129 data_time: 0.0013 memory: 38334 loss: 0.1126 loss_ce: 0.1126 2023/03/03 13:12:24 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:12:29 - mmengine - INFO - Epoch(train) [163][10/79] lr: 1.0000e-06 eta: 0:23:41 time: 0.4859 data_time: 0.0560 memory: 37934 loss: 0.1122 loss_ce: 0.1122 2023/03/03 13:12:33 - mmengine - INFO - Epoch(train) [163][20/79] lr: 1.0000e-06 eta: 0:23:36 time: 0.4542 data_time: 0.0016 memory: 34593 loss: 0.1053 loss_ce: 0.1053 2023/03/03 13:12:38 - mmengine - INFO - Epoch(train) [163][30/79] lr: 1.0000e-06 eta: 0:23:31 time: 0.4754 data_time: 0.0014 memory: 40505 loss: 0.1208 loss_ce: 0.1208 2023/03/03 13:12:42 - mmengine - INFO - Epoch(train) [163][40/79] lr: 1.0000e-06 eta: 0:23:26 time: 0.4344 data_time: 0.0022 memory: 27662 loss: 0.1060 loss_ce: 0.1060 2023/03/03 13:12:47 - mmengine - INFO - Epoch(train) [163][50/79] lr: 1.0000e-06 eta: 0:23:22 time: 0.4606 data_time: 0.0017 memory: 38082 loss: 0.1049 loss_ce: 0.1049 2023/03/03 13:12:52 - mmengine - INFO - Epoch(train) [163][60/79] lr: 1.0000e-06 eta: 0:23:17 time: 0.5030 data_time: 0.0015 memory: 39123 loss: 0.1302 loss_ce: 0.1302 2023/03/03 13:12:57 - mmengine - INFO - Epoch(train) [163][70/79] lr: 1.0000e-06 eta: 0:23:12 time: 0.4994 data_time: 0.0013 memory: 38588 loss: 0.1179 loss_ce: 0.1179 2023/03/03 13:13:01 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:13:06 - mmengine - INFO - Epoch(train) [164][10/79] lr: 1.0000e-06 eta: 0:23:03 time: 0.5412 data_time: 0.0433 memory: 37934 loss: 0.1188 loss_ce: 0.1188 2023/03/03 13:13:11 - mmengine - INFO - Epoch(train) [164][20/79] lr: 1.0000e-06 eta: 0:22:59 time: 0.4507 data_time: 0.0015 memory: 35262 loss: 0.1029 loss_ce: 0.1029 2023/03/03 13:13:16 - mmengine - INFO - Epoch(train) [164][30/79] lr: 1.0000e-06 eta: 0:22:54 time: 0.5410 data_time: 0.0017 memory: 34959 loss: 0.1122 loss_ce: 0.1122 2023/03/03 13:13:21 - mmengine - INFO - Epoch(train) [164][40/79] lr: 1.0000e-06 eta: 0:22:49 time: 0.4434 data_time: 0.0016 memory: 31756 loss: 0.1184 loss_ce: 0.1184 2023/03/03 13:13:27 - mmengine - INFO - Epoch(train) [164][50/79] lr: 1.0000e-06 eta: 0:22:45 time: 0.5889 data_time: 0.0018 memory: 39123 loss: 0.0999 loss_ce: 0.0999 2023/03/03 13:13:32 - mmengine - INFO - Epoch(train) [164][60/79] lr: 1.0000e-06 eta: 0:22:40 time: 0.5142 data_time: 0.0016 memory: 47581 loss: 0.1300 loss_ce: 0.1300 2023/03/03 13:13:36 - mmengine - INFO - Epoch(train) [164][70/79] lr: 1.0000e-06 eta: 0:22:35 time: 0.4617 data_time: 0.0014 memory: 31204 loss: 0.1205 loss_ce: 0.1205 2023/03/03 13:13:40 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:13:46 - mmengine - INFO - Epoch(train) [165][10/79] lr: 1.0000e-06 eta: 0:22:26 time: 0.5560 data_time: 0.0447 memory: 39390 loss: 0.1185 loss_ce: 0.1185 2023/03/03 13:13:51 - mmengine - INFO - Epoch(train) [165][20/79] lr: 1.0000e-06 eta: 0:22:22 time: 0.5429 data_time: 0.0015 memory: 43939 loss: 0.1013 loss_ce: 0.1013 2023/03/03 13:13:56 - mmengine - INFO - Epoch(train) [165][30/79] lr: 1.0000e-06 eta: 0:22:17 time: 0.5060 data_time: 0.0016 memory: 40757 loss: 0.1175 loss_ce: 0.1175 2023/03/03 13:14:01 - mmengine - INFO - Epoch(train) [165][40/79] lr: 1.0000e-06 eta: 0:22:12 time: 0.4791 data_time: 0.0015 memory: 40236 loss: 0.1163 loss_ce: 0.1163 2023/03/03 13:14:03 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:14:05 - mmengine - INFO - Epoch(train) [165][50/79] lr: 1.0000e-06 eta: 0:22:07 time: 0.4199 data_time: 0.0015 memory: 36467 loss: 0.1051 loss_ce: 0.1051 2023/03/03 13:14:10 - mmengine - INFO - Epoch(train) [165][60/79] lr: 1.0000e-06 eta: 0:22:03 time: 0.4692 data_time: 0.0015 memory: 33299 loss: 0.1279 loss_ce: 0.1279 2023/03/03 13:14:14 - mmengine - INFO - Epoch(train) [165][70/79] lr: 1.0000e-06 eta: 0:21:58 time: 0.4530 data_time: 0.0013 memory: 35965 loss: 0.1076 loss_ce: 0.1076 2023/03/03 13:14:18 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:14:24 - mmengine - INFO - Epoch(train) [166][10/79] lr: 1.0000e-06 eta: 0:21:49 time: 0.5412 data_time: 0.0572 memory: 48938 loss: 0.1224 loss_ce: 0.1224 2023/03/03 13:14:29 - mmengine - INFO - Epoch(train) [166][20/79] lr: 1.0000e-06 eta: 0:21:44 time: 0.4879 data_time: 0.0016 memory: 38082 loss: 0.1016 loss_ce: 0.1016 2023/03/03 13:14:33 - mmengine - INFO - Epoch(train) [166][30/79] lr: 1.0000e-06 eta: 0:21:39 time: 0.4816 data_time: 0.0016 memory: 31949 loss: 0.1211 loss_ce: 0.1211 2023/03/03 13:14:39 - mmengine - INFO - Epoch(train) [166][40/79] lr: 1.0000e-06 eta: 0:21:35 time: 0.5230 data_time: 0.0018 memory: 36411 loss: 0.1244 loss_ce: 0.1244 2023/03/03 13:14:43 - mmengine - INFO - Epoch(train) [166][50/79] lr: 1.0000e-06 eta: 0:21:30 time: 0.4329 data_time: 0.0015 memory: 29939 loss: 0.1236 loss_ce: 0.1236 2023/03/03 13:14:47 - mmengine - INFO - Epoch(train) [166][60/79] lr: 1.0000e-06 eta: 0:21:25 time: 0.4472 data_time: 0.0015 memory: 32601 loss: 0.0978 loss_ce: 0.0978 2023/03/03 13:14:52 - mmengine - INFO - Epoch(train) [166][70/79] lr: 1.0000e-06 eta: 0:21:20 time: 0.4705 data_time: 0.0013 memory: 37872 loss: 0.1278 loss_ce: 0.1278 2023/03/03 13:14:56 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:15:01 - mmengine - INFO - Epoch(train) [167][10/79] lr: 1.0000e-06 eta: 0:21:11 time: 0.5375 data_time: 0.0675 memory: 43333 loss: 0.1106 loss_ce: 0.1106 2023/03/03 13:15:06 - mmengine - INFO - Epoch(train) [167][20/79] lr: 1.0000e-06 eta: 0:21:06 time: 0.4604 data_time: 0.0016 memory: 26391 loss: 0.1029 loss_ce: 0.1029 2023/03/03 13:15:11 - mmengine - INFO - Epoch(train) [167][30/79] lr: 1.0000e-06 eta: 0:21:02 time: 0.4880 data_time: 0.0015 memory: 38686 loss: 0.1288 loss_ce: 0.1288 2023/03/03 13:15:15 - mmengine - INFO - Epoch(train) [167][40/79] lr: 1.0000e-06 eta: 0:20:57 time: 0.4473 data_time: 0.0015 memory: 24742 loss: 0.1155 loss_ce: 0.1155 2023/03/03 13:15:20 - mmengine - INFO - Epoch(train) [167][50/79] lr: 1.0000e-06 eta: 0:20:52 time: 0.4637 data_time: 0.0017 memory: 34189 loss: 0.1175 loss_ce: 0.1175 2023/03/03 13:15:24 - mmengine - INFO - Epoch(train) [167][60/79] lr: 1.0000e-06 eta: 0:20:47 time: 0.4442 data_time: 0.0015 memory: 51713 loss: 0.1117 loss_ce: 0.1117 2023/03/03 13:15:29 - mmengine - INFO - Epoch(train) [167][70/79] lr: 1.0000e-06 eta: 0:20:42 time: 0.4687 data_time: 0.0014 memory: 45577 loss: 0.1113 loss_ce: 0.1113 2023/03/03 13:15:32 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:15:37 - mmengine - INFO - Epoch(train) [168][10/79] lr: 1.0000e-06 eta: 0:20:33 time: 0.4922 data_time: 0.0494 memory: 38296 loss: 0.0989 loss_ce: 0.0989 2023/03/03 13:15:42 - mmengine - INFO - Epoch(train) [168][20/79] lr: 1.0000e-06 eta: 0:20:29 time: 0.5039 data_time: 0.0017 memory: 32251 loss: 0.1226 loss_ce: 0.1226 2023/03/03 13:15:47 - mmengine - INFO - Epoch(train) [168][30/79] lr: 1.0000e-06 eta: 0:20:24 time: 0.4722 data_time: 0.0015 memory: 37934 loss: 0.1095 loss_ce: 0.1095 2023/03/03 13:15:52 - mmengine - INFO - Epoch(train) [168][40/79] lr: 1.0000e-06 eta: 0:20:19 time: 0.5157 data_time: 0.0016 memory: 37920 loss: 0.1147 loss_ce: 0.1147 2023/03/03 13:15:57 - mmengine - INFO - Epoch(train) [168][50/79] lr: 1.0000e-06 eta: 0:20:14 time: 0.4853 data_time: 0.0016 memory: 29104 loss: 0.1200 loss_ce: 0.1200 2023/03/03 13:16:02 - mmengine - INFO - Epoch(train) [168][60/79] lr: 1.0000e-06 eta: 0:20:10 time: 0.4682 data_time: 0.0016 memory: 40444 loss: 0.1066 loss_ce: 0.1066 2023/03/03 13:16:06 - mmengine - INFO - Epoch(train) [168][70/79] lr: 1.0000e-06 eta: 0:20:05 time: 0.4456 data_time: 0.0016 memory: 25030 loss: 0.1145 loss_ce: 0.1145 2023/03/03 13:16:10 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:16:16 - mmengine - INFO - Epoch(train) [169][10/79] lr: 1.0000e-06 eta: 0:19:56 time: 0.5554 data_time: 0.0308 memory: 40550 loss: 0.1028 loss_ce: 0.1028 2023/03/03 13:16:20 - mmengine - INFO - Epoch(train) [169][20/79] lr: 1.0000e-06 eta: 0:19:51 time: 0.4437 data_time: 0.0018 memory: 36938 loss: 0.1143 loss_ce: 0.1143 2023/03/03 13:16:25 - mmengine - INFO - Epoch(train) [169][30/79] lr: 1.0000e-06 eta: 0:19:46 time: 0.4557 data_time: 0.0017 memory: 38828 loss: 0.0936 loss_ce: 0.0936 2023/03/03 13:16:30 - mmengine - INFO - Epoch(train) [169][40/79] lr: 1.0000e-06 eta: 0:19:42 time: 0.4745 data_time: 0.0016 memory: 39884 loss: 0.1029 loss_ce: 0.1029 2023/03/03 13:16:34 - mmengine - INFO - Epoch(train) [169][50/79] lr: 1.0000e-06 eta: 0:19:37 time: 0.4687 data_time: 0.0015 memory: 43939 loss: 0.1124 loss_ce: 0.1124 2023/03/03 13:16:39 - mmengine - INFO - Epoch(train) [169][60/79] lr: 1.0000e-06 eta: 0:19:32 time: 0.4747 data_time: 0.0015 memory: 40236 loss: 0.1173 loss_ce: 0.1173 2023/03/03 13:16:44 - mmengine - INFO - Epoch(train) [169][70/79] lr: 1.0000e-06 eta: 0:19:27 time: 0.4927 data_time: 0.0013 memory: 42642 loss: 0.1055 loss_ce: 0.1055 2023/03/03 13:16:48 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:16:53 - mmengine - INFO - Epoch(train) [170][10/79] lr: 1.0000e-06 eta: 0:19:18 time: 0.5366 data_time: 0.0405 memory: 38082 loss: 0.1159 loss_ce: 0.1159 2023/03/03 13:16:58 - mmengine - INFO - Epoch(train) [170][20/79] lr: 1.0000e-06 eta: 0:19:14 time: 0.5115 data_time: 0.0014 memory: 35283 loss: 0.1119 loss_ce: 0.1119 2023/03/03 13:17:03 - mmengine - INFO - Epoch(train) [170][30/79] lr: 1.0000e-06 eta: 0:19:09 time: 0.4911 data_time: 0.0015 memory: 29440 loss: 0.1219 loss_ce: 0.1219 2023/03/03 13:17:08 - mmengine - INFO - Epoch(train) [170][40/79] lr: 1.0000e-06 eta: 0:19:04 time: 0.4972 data_time: 0.0014 memory: 38588 loss: 0.1002 loss_ce: 0.1002 2023/03/03 13:17:12 - mmengine - INFO - Epoch(train) [170][50/79] lr: 1.0000e-06 eta: 0:18:59 time: 0.4336 data_time: 0.0014 memory: 37934 loss: 0.0985 loss_ce: 0.0985 2023/03/03 13:17:17 - mmengine - INFO - Epoch(train) [170][60/79] lr: 1.0000e-06 eta: 0:18:55 time: 0.4414 data_time: 0.0014 memory: 31963 loss: 0.1217 loss_ce: 0.1217 2023/03/03 13:17:22 - mmengine - INFO - Epoch(train) [170][70/79] lr: 1.0000e-06 eta: 0:18:50 time: 0.4831 data_time: 0.0013 memory: 38334 loss: 0.0989 loss_ce: 0.0989 2023/03/03 13:17:26 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:17:39 - mmengine - INFO - Epoch(val) [170][10/75] eta: 0:01:24 time: 1.2949 data_time: 0.0033 memory: 37934 2023/03/03 13:18:21 - mmengine - INFO - Epoch(val) [170][20/75] eta: 0:02:30 time: 4.1910 data_time: 0.0004 memory: 1077 2023/03/03 13:18:41 - mmengine - INFO - Epoch(val) [170][30/75] eta: 0:01:52 time: 1.9958 data_time: 0.0003 memory: 1020 2023/03/03 13:18:56 - mmengine - INFO - Epoch(val) [170][40/75] eta: 0:01:18 time: 1.5314 data_time: 0.0005 memory: 1019 2023/03/03 13:19:11 - mmengine - INFO - Epoch(val) [170][50/75] eta: 0:00:52 time: 1.5010 data_time: 0.0004 memory: 1077 2023/03/03 13:19:54 - mmengine - INFO - Epoch(val) [170][60/75] eta: 0:00:37 time: 4.3148 data_time: 0.0007 memory: 1045 2023/03/03 13:20:23 - mmengine - INFO - Epoch(val) [170][70/75] eta: 0:00:12 time: 2.8941 data_time: 0.0005 memory: 1077 2023/03/03 13:20:37 - mmengine - INFO - text score threshold: 0.80, recall: 0.6883, precision: 0.7346, hmean: 0.7107 2023/03/03 13:20:37 - mmengine - INFO - text score threshold: 0.81, recall: 0.6883, precision: 0.7398, hmean: 0.7131 2023/03/03 13:20:37 - mmengine - INFO - text score threshold: 0.82, recall: 0.6877, precision: 0.7454, hmean: 0.7154 2023/03/03 13:20:37 - mmengine - INFO - text score threshold: 0.83, recall: 0.6877, precision: 0.7503, hmean: 0.7176 2023/03/03 13:20:37 - mmengine - INFO - text score threshold: 0.84, recall: 0.6866, precision: 0.7541, hmean: 0.7188 2023/03/03 13:20:37 - mmengine - INFO - text score threshold: 0.85, recall: 0.6855, precision: 0.7616, hmean: 0.7215 2023/03/03 13:20:37 - mmengine - INFO - text score threshold: 0.86, recall: 0.6844, precision: 0.7702, hmean: 0.7248 2023/03/03 13:20:37 - mmengine - INFO - text score threshold: 0.87, recall: 0.6822, precision: 0.7754, hmean: 0.7258 2023/03/03 13:20:37 - mmengine - INFO - text score threshold: 0.88, recall: 0.6795, precision: 0.7840, hmean: 0.7280 2023/03/03 13:20:37 - mmengine - INFO - text score threshold: 0.89, recall: 0.6756, precision: 0.7881, hmean: 0.7275 2023/03/03 13:20:37 - mmengine - INFO - text score threshold: 0.90, recall: 0.6696, precision: 0.7922, hmean: 0.7258 2023/03/03 13:20:37 - mmengine - INFO - text score threshold: 0.91, recall: 0.6647, precision: 0.8025, hmean: 0.7271 2023/03/03 13:20:37 - mmengine - INFO - text score threshold: 0.92, recall: 0.6597, precision: 0.8111, hmean: 0.7276 2023/03/03 13:20:37 - mmengine - INFO - text score threshold: 0.93, recall: 0.6553, precision: 0.8229, hmean: 0.7296 2023/03/03 13:20:37 - mmengine - INFO - text score threshold: 0.94, recall: 0.6487, precision: 0.8336, hmean: 0.7296 2023/03/03 13:20:37 - mmengine - INFO - text score threshold: 0.95, recall: 0.6405, precision: 0.8438, hmean: 0.7282 2023/03/03 13:20:37 - mmengine - INFO - text score threshold: 0.96, recall: 0.6317, precision: 0.8532, hmean: 0.7260 2023/03/03 13:20:37 - mmengine - INFO - text score threshold: 0.97, recall: 0.6191, precision: 0.8650, hmean: 0.7217 2023/03/03 13:20:37 - mmengine - INFO - text score threshold: 0.98, recall: 0.5993, precision: 0.8764, hmean: 0.7119 2023/03/03 13:20:37 - mmengine - INFO - text score threshold: 0.99, recall: 0.5752, precision: 0.8927, hmean: 0.6996 2023/03/03 13:20:47 - mmengine - INFO - text score threshold: 0.80, recall: 0.7761, precision: 0.8632, hmean: 0.8173 2023/03/03 13:20:47 - mmengine - INFO - text score threshold: 0.81, recall: 0.7755, precision: 0.8658, hmean: 0.8182 2023/03/03 13:20:47 - mmengine - INFO - text score threshold: 0.82, recall: 0.7744, precision: 0.8710, hmean: 0.8199 2023/03/03 13:20:47 - mmengine - INFO - text score threshold: 0.83, recall: 0.7739, precision: 0.8747, hmean: 0.8212 2023/03/03 13:20:47 - mmengine - INFO - text score threshold: 0.84, recall: 0.7717, precision: 0.8782, hmean: 0.8215 2023/03/03 13:20:47 - mmengine - INFO - text score threshold: 0.85, recall: 0.7684, precision: 0.8827, hmean: 0.8216 2023/03/03 13:20:47 - mmengine - INFO - text score threshold: 0.86, recall: 0.7634, precision: 0.8877, hmean: 0.8209 2023/03/03 13:20:47 - mmengine - INFO - text score threshold: 0.87, recall: 0.7596, precision: 0.8912, hmean: 0.8201 2023/03/03 13:20:47 - mmengine - INFO - text score threshold: 0.88, recall: 0.7552, precision: 0.8953, hmean: 0.8193 2023/03/03 13:20:47 - mmengine - INFO - text score threshold: 0.89, recall: 0.7497, precision: 0.8987, hmean: 0.8175 2023/03/03 13:20:47 - mmengine - INFO - text score threshold: 0.90, recall: 0.7415, precision: 0.9013, hmean: 0.8136 2023/03/03 13:20:47 - mmengine - INFO - text score threshold: 0.91, recall: 0.7338, precision: 0.9071, hmean: 0.8113 2023/03/03 13:20:47 - mmengine - INFO - text score threshold: 0.92, recall: 0.7228, precision: 0.9089, hmean: 0.8053 2023/03/03 13:20:47 - mmengine - INFO - text score threshold: 0.93, recall: 0.7102, precision: 0.9106, hmean: 0.7980 2023/03/03 13:20:47 - mmengine - INFO - text score threshold: 0.94, recall: 0.6970, precision: 0.9143, hmean: 0.7910 2023/03/03 13:20:47 - mmengine - INFO - text score threshold: 0.95, recall: 0.6833, precision: 0.9188, hmean: 0.7838 2023/03/03 13:20:47 - mmengine - INFO - text score threshold: 0.96, recall: 0.6696, precision: 0.9215, hmean: 0.7756 2023/03/03 13:20:47 - mmengine - INFO - text score threshold: 0.97, recall: 0.6526, precision: 0.9282, hmean: 0.7664 2023/03/03 13:20:47 - mmengine - INFO - text score threshold: 0.98, recall: 0.6257, precision: 0.9306, hmean: 0.7483 2023/03/03 13:20:47 - mmengine - INFO - text score threshold: 0.99, recall: 0.5950, precision: 0.9385, hmean: 0.7282 2023/03/03 13:20:47 - mmengine - INFO - Epoch(val) [170][75/75] none/precision: 0.8336 none/recall: 0.6487 none/hmean: 0.7296 full/precision: 0.8827 full/recall: 0.7684 full/hmean: 0.8216 2023/03/03 13:20:52 - mmengine - INFO - Epoch(train) [171][10/79] lr: 1.0000e-06 eta: 0:18:41 time: 0.5089 data_time: 0.0555 memory: 38338 loss: 0.1111 loss_ce: 0.1111 2023/03/03 13:20:57 - mmengine - INFO - Epoch(train) [171][20/79] lr: 1.0000e-06 eta: 0:18:36 time: 0.4732 data_time: 0.0015 memory: 32944 loss: 0.1031 loss_ce: 0.1031 2023/03/03 13:21:02 - mmengine - INFO - Epoch(train) [171][30/79] lr: 1.0000e-06 eta: 0:18:31 time: 0.4958 data_time: 0.0014 memory: 31869 loss: 0.1091 loss_ce: 0.1091 2023/03/03 13:21:07 - mmengine - INFO - Epoch(train) [171][40/79] lr: 1.0000e-06 eta: 0:18:27 time: 0.5123 data_time: 0.0014 memory: 36351 loss: 0.1085 loss_ce: 0.1085 2023/03/03 13:21:12 - mmengine - INFO - Epoch(train) [171][50/79] lr: 1.0000e-06 eta: 0:18:22 time: 0.4694 data_time: 0.0016 memory: 30756 loss: 0.1070 loss_ce: 0.1070 2023/03/03 13:21:17 - mmengine - INFO - Epoch(train) [171][60/79] lr: 1.0000e-06 eta: 0:18:17 time: 0.5114 data_time: 0.0014 memory: 38588 loss: 0.1206 loss_ce: 0.1206 2023/03/03 13:21:21 - mmengine - INFO - Epoch(train) [171][70/79] lr: 1.0000e-06 eta: 0:18:12 time: 0.4260 data_time: 0.0014 memory: 27665 loss: 0.1220 loss_ce: 0.1220 2023/03/03 13:21:25 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:21:30 - mmengine - INFO - Epoch(train) [172][10/79] lr: 1.0000e-06 eta: 0:18:03 time: 0.5433 data_time: 0.0477 memory: 42274 loss: 0.1178 loss_ce: 0.1178 2023/03/03 13:21:35 - mmengine - INFO - Epoch(train) [172][20/79] lr: 1.0000e-06 eta: 0:17:59 time: 0.4535 data_time: 0.0016 memory: 32974 loss: 0.0884 loss_ce: 0.0884 2023/03/03 13:21:40 - mmengine - INFO - Epoch(train) [172][30/79] lr: 1.0000e-06 eta: 0:17:54 time: 0.4939 data_time: 0.0015 memory: 37486 loss: 0.1209 loss_ce: 0.1209 2023/03/03 13:21:45 - mmengine - INFO - Epoch(train) [172][40/79] lr: 1.0000e-06 eta: 0:17:49 time: 0.5290 data_time: 0.0015 memory: 43454 loss: 0.0992 loss_ce: 0.0992 2023/03/03 13:21:49 - mmengine - INFO - Epoch(train) [172][50/79] lr: 1.0000e-06 eta: 0:17:44 time: 0.4205 data_time: 0.0016 memory: 33442 loss: 0.1340 loss_ce: 0.1340 2023/03/03 13:21:54 - mmengine - INFO - Epoch(train) [172][60/79] lr: 1.0000e-06 eta: 0:17:40 time: 0.4520 data_time: 0.0015 memory: 39123 loss: 0.1024 loss_ce: 0.1024 2023/03/03 13:21:59 - mmengine - INFO - Epoch(train) [172][70/79] lr: 1.0000e-06 eta: 0:17:35 time: 0.5048 data_time: 0.0013 memory: 37934 loss: 0.1194 loss_ce: 0.1194 2023/03/03 13:22:03 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:22:08 - mmengine - INFO - Epoch(train) [173][10/79] lr: 1.0000e-06 eta: 0:17:26 time: 0.5481 data_time: 0.0383 memory: 42473 loss: 0.1042 loss_ce: 0.1042 2023/03/03 13:22:12 - mmengine - INFO - Epoch(train) [173][20/79] lr: 1.0000e-06 eta: 0:17:21 time: 0.4127 data_time: 0.0018 memory: 43939 loss: 0.0957 loss_ce: 0.0957 2023/03/03 13:22:17 - mmengine - INFO - Epoch(train) [173][30/79] lr: 1.0000e-06 eta: 0:17:16 time: 0.4637 data_time: 0.0015 memory: 33749 loss: 0.1191 loss_ce: 0.1191 2023/03/03 13:22:22 - mmengine - INFO - Epoch(train) [173][40/79] lr: 1.0000e-06 eta: 0:17:12 time: 0.4951 data_time: 0.0015 memory: 32426 loss: 0.1273 loss_ce: 0.1273 2023/03/03 13:22:27 - mmengine - INFO - Epoch(train) [173][50/79] lr: 1.0000e-06 eta: 0:17:07 time: 0.4769 data_time: 0.0015 memory: 27860 loss: 0.1140 loss_ce: 0.1140 2023/03/03 13:22:31 - mmengine - INFO - Epoch(train) [173][60/79] lr: 1.0000e-06 eta: 0:17:02 time: 0.4575 data_time: 0.0015 memory: 31735 loss: 0.1130 loss_ce: 0.1130 2023/03/03 13:22:36 - mmengine - INFO - Epoch(train) [173][70/79] lr: 1.0000e-06 eta: 0:16:57 time: 0.4920 data_time: 0.0014 memory: 40524 loss: 0.1198 loss_ce: 0.1198 2023/03/03 13:22:40 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:22:46 - mmengine - INFO - Epoch(train) [174][10/79] lr: 1.0000e-06 eta: 0:16:48 time: 0.5635 data_time: 0.0728 memory: 43337 loss: 0.1101 loss_ce: 0.1101 2023/03/03 13:22:51 - mmengine - INFO - Epoch(train) [174][20/79] lr: 1.0000e-06 eta: 0:16:44 time: 0.4906 data_time: 0.0014 memory: 39123 loss: 0.1026 loss_ce: 0.1026 2023/03/03 13:22:55 - mmengine - INFO - Epoch(train) [174][30/79] lr: 1.0000e-06 eta: 0:16:39 time: 0.4319 data_time: 0.0015 memory: 34764 loss: 0.1063 loss_ce: 0.1063 2023/03/03 13:23:00 - mmengine - INFO - Epoch(train) [174][40/79] lr: 1.0000e-06 eta: 0:16:34 time: 0.4607 data_time: 0.0014 memory: 38588 loss: 0.1089 loss_ce: 0.1089 2023/03/03 13:23:04 - mmengine - INFO - Epoch(train) [174][50/79] lr: 1.0000e-06 eta: 0:16:29 time: 0.4305 data_time: 0.0014 memory: 31874 loss: 0.1229 loss_ce: 0.1229 2023/03/03 13:23:08 - mmengine - INFO - Epoch(train) [174][60/79] lr: 1.0000e-06 eta: 0:16:25 time: 0.4656 data_time: 0.0015 memory: 39390 loss: 0.1043 loss_ce: 0.1043 2023/03/03 13:23:13 - mmengine - INFO - Epoch(train) [174][70/79] lr: 1.0000e-06 eta: 0:16:20 time: 0.4772 data_time: 0.0013 memory: 45301 loss: 0.1203 loss_ce: 0.1203 2023/03/03 13:23:17 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:23:22 - mmengine - INFO - Epoch(train) [175][10/79] lr: 1.0000e-06 eta: 0:16:11 time: 0.5078 data_time: 0.0635 memory: 35619 loss: 0.1035 loss_ce: 0.1035 2023/03/03 13:23:27 - mmengine - INFO - Epoch(train) [175][20/79] lr: 1.0000e-06 eta: 0:16:06 time: 0.4490 data_time: 0.0015 memory: 40409 loss: 0.1090 loss_ce: 0.1090 2023/03/03 13:23:32 - mmengine - INFO - Epoch(train) [175][30/79] lr: 1.0000e-06 eta: 0:16:01 time: 0.5050 data_time: 0.0014 memory: 36229 loss: 0.1321 loss_ce: 0.1321 2023/03/03 13:23:37 - mmengine - INFO - Epoch(train) [175][40/79] lr: 1.0000e-06 eta: 0:15:57 time: 0.4898 data_time: 0.0014 memory: 38588 loss: 0.1033 loss_ce: 0.1033 2023/03/03 13:23:41 - mmengine - INFO - Epoch(train) [175][50/79] lr: 1.0000e-06 eta: 0:15:52 time: 0.4504 data_time: 0.0014 memory: 34627 loss: 0.1207 loss_ce: 0.1207 2023/03/03 13:23:46 - mmengine - INFO - Epoch(train) [175][60/79] lr: 1.0000e-06 eta: 0:15:47 time: 0.4735 data_time: 0.0014 memory: 37934 loss: 0.1237 loss_ce: 0.1237 2023/03/03 13:23:50 - mmengine - INFO - Epoch(train) [175][70/79] lr: 1.0000e-06 eta: 0:15:42 time: 0.4356 data_time: 0.0013 memory: 33836 loss: 0.1273 loss_ce: 0.1273 2023/03/03 13:23:54 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:24:00 - mmengine - INFO - Epoch(train) [176][10/79] lr: 1.0000e-06 eta: 0:15:33 time: 0.5483 data_time: 0.0584 memory: 39390 loss: 0.1105 loss_ce: 0.1105 2023/03/03 13:24:05 - mmengine - INFO - Epoch(train) [176][20/79] lr: 1.0000e-06 eta: 0:15:29 time: 0.5337 data_time: 0.0015 memory: 33697 loss: 0.1004 loss_ce: 0.1004 2023/03/03 13:24:10 - mmengine - INFO - Epoch(train) [176][30/79] lr: 1.0000e-06 eta: 0:15:24 time: 0.4727 data_time: 0.0017 memory: 41350 loss: 0.0999 loss_ce: 0.0999 2023/03/03 13:24:14 - mmengine - INFO - Epoch(train) [176][40/79] lr: 1.0000e-06 eta: 0:15:19 time: 0.3798 data_time: 0.0015 memory: 25812 loss: 0.1031 loss_ce: 0.1031 2023/03/03 13:24:19 - mmengine - INFO - Epoch(train) [176][50/79] lr: 1.0000e-06 eta: 0:15:14 time: 0.4752 data_time: 0.0016 memory: 32665 loss: 0.1121 loss_ce: 0.1121 2023/03/03 13:24:24 - mmengine - INFO - Epoch(train) [176][60/79] lr: 1.0000e-06 eta: 0:15:09 time: 0.5258 data_time: 0.0019 memory: 36746 loss: 0.1123 loss_ce: 0.1123 2023/03/03 13:24:29 - mmengine - INFO - Epoch(train) [176][70/79] lr: 1.0000e-06 eta: 0:15:05 time: 0.5022 data_time: 0.0021 memory: 51733 loss: 0.1020 loss_ce: 0.1020 2023/03/03 13:24:33 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:24:37 - mmengine - INFO - Epoch(train) [177][10/79] lr: 1.0000e-06 eta: 0:14:56 time: 0.4868 data_time: 0.0435 memory: 36007 loss: 0.1291 loss_ce: 0.1291 2023/03/03 13:24:42 - mmengine - INFO - Epoch(train) [177][20/79] lr: 1.0000e-06 eta: 0:14:51 time: 0.4753 data_time: 0.0016 memory: 26443 loss: 0.1186 loss_ce: 0.1186 2023/03/03 13:24:48 - mmengine - INFO - Epoch(train) [177][30/79] lr: 1.0000e-06 eta: 0:14:46 time: 0.5350 data_time: 0.0015 memory: 35478 loss: 0.1149 loss_ce: 0.1149 2023/03/03 13:24:53 - mmengine - INFO - Epoch(train) [177][40/79] lr: 1.0000e-06 eta: 0:14:42 time: 0.5269 data_time: 0.0017 memory: 39669 loss: 0.1294 loss_ce: 0.1294 2023/03/03 13:24:57 - mmengine - INFO - Epoch(train) [177][50/79] lr: 1.0000e-06 eta: 0:14:37 time: 0.4312 data_time: 0.0016 memory: 40818 loss: 0.1078 loss_ce: 0.1078 2023/03/03 13:25:02 - mmengine - INFO - Epoch(train) [177][60/79] lr: 1.0000e-06 eta: 0:14:32 time: 0.5106 data_time: 0.0016 memory: 37909 loss: 0.1088 loss_ce: 0.1088 2023/03/03 13:25:08 - mmengine - INFO - Epoch(train) [177][70/79] lr: 1.0000e-06 eta: 0:14:27 time: 0.5356 data_time: 0.0015 memory: 37934 loss: 0.1069 loss_ce: 0.1069 2023/03/03 13:25:12 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:25:17 - mmengine - INFO - Epoch(train) [178][10/79] lr: 1.0000e-06 eta: 0:14:18 time: 0.5352 data_time: 0.0534 memory: 39123 loss: 0.1048 loss_ce: 0.1048 2023/03/03 13:25:20 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:25:21 - mmengine - INFO - Epoch(train) [178][20/79] lr: 1.0000e-06 eta: 0:14:14 time: 0.4125 data_time: 0.0016 memory: 26437 loss: 0.1146 loss_ce: 0.1146 2023/03/03 13:25:26 - mmengine - INFO - Epoch(train) [178][30/79] lr: 1.0000e-06 eta: 0:14:09 time: 0.4688 data_time: 0.0015 memory: 38588 loss: 0.1322 loss_ce: 0.1322 2023/03/03 13:25:30 - mmengine - INFO - Epoch(train) [178][40/79] lr: 1.0000e-06 eta: 0:14:04 time: 0.4052 data_time: 0.0016 memory: 34390 loss: 0.1118 loss_ce: 0.1118 2023/03/03 13:25:35 - mmengine - INFO - Epoch(train) [178][50/79] lr: 1.0000e-06 eta: 0:13:59 time: 0.4574 data_time: 0.0015 memory: 36797 loss: 0.1134 loss_ce: 0.1134 2023/03/03 13:25:39 - mmengine - INFO - Epoch(train) [178][60/79] lr: 1.0000e-06 eta: 0:13:54 time: 0.4250 data_time: 0.0016 memory: 39669 loss: 0.1240 loss_ce: 0.1240 2023/03/03 13:25:44 - mmengine - INFO - Epoch(train) [178][70/79] lr: 1.0000e-06 eta: 0:13:50 time: 0.5148 data_time: 0.0014 memory: 30381 loss: 0.1176 loss_ce: 0.1176 2023/03/03 13:25:48 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:25:53 - mmengine - INFO - Epoch(train) [179][10/79] lr: 1.0000e-06 eta: 0:13:41 time: 0.5254 data_time: 0.0661 memory: 37958 loss: 0.0977 loss_ce: 0.0977 2023/03/03 13:25:58 - mmengine - INFO - Epoch(train) [179][20/79] lr: 1.0000e-06 eta: 0:13:36 time: 0.4855 data_time: 0.0015 memory: 40236 loss: 0.1085 loss_ce: 0.1085 2023/03/03 13:26:03 - mmengine - INFO - Epoch(train) [179][30/79] lr: 1.0000e-06 eta: 0:13:31 time: 0.4852 data_time: 0.0015 memory: 38082 loss: 0.1238 loss_ce: 0.1238 2023/03/03 13:26:08 - mmengine - INFO - Epoch(train) [179][40/79] lr: 1.0000e-06 eta: 0:13:27 time: 0.5384 data_time: 0.0019 memory: 51559 loss: 0.0995 loss_ce: 0.0995 2023/03/03 13:26:14 - mmengine - INFO - Epoch(train) [179][50/79] lr: 1.0000e-06 eta: 0:13:22 time: 0.5189 data_time: 0.0015 memory: 42051 loss: 0.1002 loss_ce: 0.1002 2023/03/03 13:26:18 - mmengine - INFO - Epoch(train) [179][60/79] lr: 1.0000e-06 eta: 0:13:17 time: 0.4592 data_time: 0.0015 memory: 25539 loss: 0.1076 loss_ce: 0.1076 2023/03/03 13:26:23 - mmengine - INFO - Epoch(train) [179][70/79] lr: 1.0000e-06 eta: 0:13:12 time: 0.5276 data_time: 0.0014 memory: 37536 loss: 0.1129 loss_ce: 0.1129 2023/03/03 13:26:27 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:26:33 - mmengine - INFO - Epoch(train) [180][10/79] lr: 1.0000e-06 eta: 0:13:03 time: 0.5521 data_time: 0.0476 memory: 41408 loss: 0.1112 loss_ce: 0.1112 2023/03/03 13:26:37 - mmengine - INFO - Epoch(train) [180][20/79] lr: 1.0000e-06 eta: 0:12:59 time: 0.4499 data_time: 0.0014 memory: 37902 loss: 0.1128 loss_ce: 0.1128 2023/03/03 13:26:42 - mmengine - INFO - Epoch(train) [180][30/79] lr: 1.0000e-06 eta: 0:12:54 time: 0.4447 data_time: 0.0015 memory: 27726 loss: 0.1284 loss_ce: 0.1284 2023/03/03 13:26:46 - mmengine - INFO - Epoch(train) [180][40/79] lr: 1.0000e-06 eta: 0:12:49 time: 0.4586 data_time: 0.0014 memory: 35845 loss: 0.1054 loss_ce: 0.1054 2023/03/03 13:26:51 - mmengine - INFO - Epoch(train) [180][50/79] lr: 1.0000e-06 eta: 0:12:44 time: 0.4616 data_time: 0.0014 memory: 32791 loss: 0.1181 loss_ce: 0.1181 2023/03/03 13:26:56 - mmengine - INFO - Epoch(train) [180][60/79] lr: 1.0000e-06 eta: 0:12:40 time: 0.4550 data_time: 0.0015 memory: 32527 loss: 0.1041 loss_ce: 0.1041 2023/03/03 13:27:00 - mmengine - INFO - Epoch(train) [180][70/79] lr: 1.0000e-06 eta: 0:12:35 time: 0.4796 data_time: 0.0013 memory: 37934 loss: 0.1076 loss_ce: 0.1076 2023/03/03 13:27:04 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:27:17 - mmengine - INFO - Epoch(val) [180][10/75] eta: 0:01:22 time: 1.2762 data_time: 0.0034 memory: 35702 2023/03/03 13:27:58 - mmengine - INFO - Epoch(val) [180][20/75] eta: 0:02:28 time: 4.1189 data_time: 0.0004 memory: 1077 2023/03/03 13:28:12 - mmengine - INFO - Epoch(val) [180][30/75] eta: 0:01:41 time: 1.3894 data_time: 0.0004 memory: 1020 2023/03/03 13:28:28 - mmengine - INFO - Epoch(val) [180][40/75] eta: 0:01:13 time: 1.5646 data_time: 0.0004 memory: 1019 2023/03/03 13:28:43 - mmengine - INFO - Epoch(val) [180][50/75] eta: 0:00:49 time: 1.4793 data_time: 0.0004 memory: 1077 2023/03/03 13:29:39 - mmengine - INFO - Epoch(val) [180][60/75] eta: 0:00:38 time: 5.6009 data_time: 0.0005 memory: 1045 2023/03/03 13:30:07 - mmengine - INFO - Epoch(val) [180][70/75] eta: 0:00:13 time: 2.7957 data_time: 0.0004 memory: 1077 2023/03/03 13:30:21 - mmengine - INFO - text score threshold: 0.80, recall: 0.6844, precision: 0.7314, hmean: 0.7071 2023/03/03 13:30:21 - mmengine - INFO - text score threshold: 0.81, recall: 0.6839, precision: 0.7373, hmean: 0.7096 2023/03/03 13:30:21 - mmengine - INFO - text score threshold: 0.82, recall: 0.6828, precision: 0.7422, hmean: 0.7113 2023/03/03 13:30:21 - mmengine - INFO - text score threshold: 0.83, recall: 0.6822, precision: 0.7465, hmean: 0.7129 2023/03/03 13:30:21 - mmengine - INFO - text score threshold: 0.84, recall: 0.6822, precision: 0.7520, hmean: 0.7154 2023/03/03 13:30:21 - mmengine - INFO - text score threshold: 0.85, recall: 0.6817, precision: 0.7573, hmean: 0.7175 2023/03/03 13:30:21 - mmengine - INFO - text score threshold: 0.86, recall: 0.6789, precision: 0.7622, hmean: 0.7181 2023/03/03 13:30:21 - mmengine - INFO - text score threshold: 0.87, recall: 0.6773, precision: 0.7688, hmean: 0.7202 2023/03/03 13:30:21 - mmengine - INFO - text score threshold: 0.88, recall: 0.6745, precision: 0.7754, hmean: 0.7215 2023/03/03 13:30:21 - mmengine - INFO - text score threshold: 0.89, recall: 0.6685, precision: 0.7808, hmean: 0.7203 2023/03/03 13:30:21 - mmengine - INFO - text score threshold: 0.90, recall: 0.6641, precision: 0.7857, hmean: 0.7198 2023/03/03 13:30:21 - mmengine - INFO - text score threshold: 0.91, recall: 0.6592, precision: 0.7948, hmean: 0.7207 2023/03/03 13:30:21 - mmengine - INFO - text score threshold: 0.92, recall: 0.6537, precision: 0.8042, hmean: 0.7212 2023/03/03 13:30:21 - mmengine - INFO - text score threshold: 0.93, recall: 0.6504, precision: 0.8144, hmean: 0.7232 2023/03/03 13:30:21 - mmengine - INFO - text score threshold: 0.94, recall: 0.6443, precision: 0.8250, hmean: 0.7236 2023/03/03 13:30:21 - mmengine - INFO - text score threshold: 0.95, recall: 0.6367, precision: 0.8339, hmean: 0.7221 2023/03/03 13:30:21 - mmengine - INFO - text score threshold: 0.96, recall: 0.6273, precision: 0.8454, hmean: 0.7202 2023/03/03 13:30:21 - mmengine - INFO - text score threshold: 0.97, recall: 0.6153, precision: 0.8603, hmean: 0.7174 2023/03/03 13:30:21 - mmengine - INFO - text score threshold: 0.98, recall: 0.5999, precision: 0.8751, hmean: 0.7118 2023/03/03 13:30:21 - mmengine - INFO - text score threshold: 0.99, recall: 0.5757, precision: 0.8867, hmean: 0.6982 2023/03/03 13:30:31 - mmengine - INFO - text score threshold: 0.80, recall: 0.7711, precision: 0.8588, hmean: 0.8126 2023/03/03 13:30:31 - mmengine - INFO - text score threshold: 0.81, recall: 0.7695, precision: 0.8633, hmean: 0.8137 2023/03/03 13:30:31 - mmengine - INFO - text score threshold: 0.82, recall: 0.7684, precision: 0.8679, hmean: 0.8151 2023/03/03 13:30:31 - mmengine - INFO - text score threshold: 0.83, recall: 0.7678, precision: 0.8727, hmean: 0.8169 2023/03/03 13:30:31 - mmengine - INFO - text score threshold: 0.84, recall: 0.7673, precision: 0.8770, hmean: 0.8185 2023/03/03 13:30:31 - mmengine - INFO - text score threshold: 0.85, recall: 0.7656, precision: 0.8796, hmean: 0.8187 2023/03/03 13:30:31 - mmengine - INFO - text score threshold: 0.86, recall: 0.7596, precision: 0.8815, hmean: 0.8160 2023/03/03 13:30:31 - mmengine - INFO - text score threshold: 0.87, recall: 0.7558, precision: 0.8844, hmean: 0.8150 2023/03/03 13:30:31 - mmengine - INFO - text score threshold: 0.88, recall: 0.7508, precision: 0.8872, hmean: 0.8133 2023/03/03 13:30:31 - mmengine - INFO - text score threshold: 0.89, recall: 0.7431, precision: 0.8908, hmean: 0.8103 2023/03/03 13:30:31 - mmengine - INFO - text score threshold: 0.90, recall: 0.7377, precision: 0.8930, hmean: 0.8079 2023/03/03 13:30:31 - mmengine - INFO - text score threshold: 0.91, recall: 0.7283, precision: 0.8978, hmean: 0.8042 2023/03/03 13:30:31 - mmengine - INFO - text score threshold: 0.92, recall: 0.7190, precision: 0.9028, hmean: 0.8005 2023/03/03 13:30:31 - mmengine - INFO - text score threshold: 0.93, recall: 0.7086, precision: 0.9060, hmean: 0.7952 2023/03/03 13:30:31 - mmengine - INFO - text score threshold: 0.94, recall: 0.6943, precision: 0.9081, hmean: 0.7869 2023/03/03 13:30:31 - mmengine - INFO - text score threshold: 0.95, recall: 0.6795, precision: 0.9096, hmean: 0.7779 2023/03/03 13:30:31 - mmengine - INFO - text score threshold: 0.96, recall: 0.6658, precision: 0.9148, hmean: 0.7706 2023/03/03 13:30:31 - mmengine - INFO - text score threshold: 0.97, recall: 0.6487, precision: 0.9234, hmean: 0.7621 2023/03/03 13:30:31 - mmengine - INFO - text score threshold: 0.98, recall: 0.6262, precision: 0.9284, hmean: 0.7480 2023/03/03 13:30:31 - mmengine - INFO - text score threshold: 0.99, recall: 0.5977, precision: 0.9356, hmean: 0.7294 2023/03/03 13:30:31 - mmengine - INFO - Epoch(val) [180][75/75] none/precision: 0.8250 none/recall: 0.6443 none/hmean: 0.7236 full/precision: 0.8796 full/recall: 0.7656 full/hmean: 0.8187 2023/03/03 13:30:36 - mmengine - INFO - Epoch(train) [181][10/79] lr: 1.0000e-06 eta: 0:12:26 time: 0.5356 data_time: 0.0399 memory: 38334 loss: 0.1091 loss_ce: 0.1091 2023/03/03 13:30:41 - mmengine - INFO - Epoch(train) [181][20/79] lr: 1.0000e-06 eta: 0:12:21 time: 0.4601 data_time: 0.0019 memory: 38238 loss: 0.1053 loss_ce: 0.1053 2023/03/03 13:30:45 - mmengine - INFO - Epoch(train) [181][30/79] lr: 1.0000e-06 eta: 0:12:16 time: 0.4692 data_time: 0.0018 memory: 32762 loss: 0.1104 loss_ce: 0.1104 2023/03/03 13:30:50 - mmengine - INFO - Epoch(train) [181][40/79] lr: 1.0000e-06 eta: 0:12:11 time: 0.4589 data_time: 0.0016 memory: 37216 loss: 0.1004 loss_ce: 0.1004 2023/03/03 13:30:55 - mmengine - INFO - Epoch(train) [181][50/79] lr: 1.0000e-06 eta: 0:12:07 time: 0.4614 data_time: 0.0016 memory: 45998 loss: 0.1109 loss_ce: 0.1109 2023/03/03 13:31:00 - mmengine - INFO - Epoch(train) [181][60/79] lr: 1.0000e-06 eta: 0:12:02 time: 0.4867 data_time: 0.0016 memory: 37934 loss: 0.1227 loss_ce: 0.1227 2023/03/03 13:31:04 - mmengine - INFO - Epoch(train) [181][70/79] lr: 1.0000e-06 eta: 0:11:57 time: 0.4448 data_time: 0.0014 memory: 40818 loss: 0.1051 loss_ce: 0.1051 2023/03/03 13:31:08 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:31:12 - mmengine - INFO - Epoch(train) [182][10/79] lr: 1.0000e-06 eta: 0:11:48 time: 0.4808 data_time: 0.0590 memory: 32591 loss: 0.1147 loss_ce: 0.1147 2023/03/03 13:31:18 - mmengine - INFO - Epoch(train) [182][20/79] lr: 1.0000e-06 eta: 0:11:43 time: 0.5147 data_time: 0.0015 memory: 42726 loss: 0.1062 loss_ce: 0.1062 2023/03/03 13:31:22 - mmengine - INFO - Epoch(train) [182][30/79] lr: 1.0000e-06 eta: 0:11:39 time: 0.4351 data_time: 0.0015 memory: 28768 loss: 0.0968 loss_ce: 0.0968 2023/03/03 13:31:27 - mmengine - INFO - Epoch(train) [182][40/79] lr: 1.0000e-06 eta: 0:11:34 time: 0.4605 data_time: 0.0015 memory: 30386 loss: 0.1197 loss_ce: 0.1197 2023/03/03 13:31:31 - mmengine - INFO - Epoch(train) [182][50/79] lr: 1.0000e-06 eta: 0:11:29 time: 0.4891 data_time: 0.0015 memory: 35937 loss: 0.1064 loss_ce: 0.1064 2023/03/03 13:31:36 - mmengine - INFO - Epoch(train) [182][60/79] lr: 1.0000e-06 eta: 0:11:24 time: 0.4577 data_time: 0.0016 memory: 33581 loss: 0.1153 loss_ce: 0.1153 2023/03/03 13:31:41 - mmengine - INFO - Epoch(train) [182][70/79] lr: 1.0000e-06 eta: 0:11:20 time: 0.4905 data_time: 0.0015 memory: 33150 loss: 0.1090 loss_ce: 0.1090 2023/03/03 13:31:45 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:31:50 - mmengine - INFO - Epoch(train) [183][10/79] lr: 1.0000e-06 eta: 0:11:11 time: 0.4996 data_time: 0.0616 memory: 37872 loss: 0.1065 loss_ce: 0.1065 2023/03/03 13:31:55 - mmengine - INFO - Epoch(train) [183][20/79] lr: 1.0000e-06 eta: 0:11:06 time: 0.4592 data_time: 0.0015 memory: 28352 loss: 0.1189 loss_ce: 0.1189 2023/03/03 13:31:59 - mmengine - INFO - Epoch(train) [183][30/79] lr: 1.0000e-06 eta: 0:11:01 time: 0.4784 data_time: 0.0015 memory: 38082 loss: 0.1269 loss_ce: 0.1269 2023/03/03 13:32:04 - mmengine - INFO - Epoch(train) [183][40/79] lr: 1.0000e-06 eta: 0:10:56 time: 0.4816 data_time: 0.0015 memory: 37254 loss: 0.1184 loss_ce: 0.1184 2023/03/03 13:32:09 - mmengine - INFO - Epoch(train) [183][50/79] lr: 1.0000e-06 eta: 0:10:51 time: 0.4648 data_time: 0.0016 memory: 28842 loss: 0.1223 loss_ce: 0.1223 2023/03/03 13:32:14 - mmengine - INFO - Epoch(train) [183][60/79] lr: 1.0000e-06 eta: 0:10:47 time: 0.4716 data_time: 0.0017 memory: 42327 loss: 0.1156 loss_ce: 0.1156 2023/03/03 13:32:18 - mmengine - INFO - Epoch(train) [183][70/79] lr: 1.0000e-06 eta: 0:10:42 time: 0.4339 data_time: 0.0014 memory: 25886 loss: 0.0956 loss_ce: 0.0956 2023/03/03 13:32:22 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:32:27 - mmengine - INFO - Epoch(train) [184][10/79] lr: 1.0000e-06 eta: 0:10:33 time: 0.5389 data_time: 0.0520 memory: 47556 loss: 0.1105 loss_ce: 0.1105 2023/03/03 13:32:32 - mmengine - INFO - Epoch(train) [184][20/79] lr: 1.0000e-06 eta: 0:10:28 time: 0.4685 data_time: 0.0017 memory: 37705 loss: 0.1259 loss_ce: 0.1259 2023/03/03 13:32:36 - mmengine - INFO - Epoch(train) [184][30/79] lr: 1.0000e-06 eta: 0:10:23 time: 0.4382 data_time: 0.0015 memory: 37729 loss: 0.1054 loss_ce: 0.1054 2023/03/03 13:32:41 - mmengine - INFO - Epoch(train) [184][40/79] lr: 1.0000e-06 eta: 0:10:19 time: 0.4310 data_time: 0.0015 memory: 35612 loss: 0.1205 loss_ce: 0.1205 2023/03/03 13:32:46 - mmengine - INFO - Epoch(train) [184][50/79] lr: 1.0000e-06 eta: 0:10:14 time: 0.5268 data_time: 0.0015 memory: 30382 loss: 0.1289 loss_ce: 0.1289 2023/03/03 13:32:50 - mmengine - INFO - Epoch(train) [184][60/79] lr: 1.0000e-06 eta: 0:10:09 time: 0.4300 data_time: 0.0015 memory: 32656 loss: 0.1122 loss_ce: 0.1122 2023/03/03 13:32:55 - mmengine - INFO - Epoch(train) [184][70/79] lr: 1.0000e-06 eta: 0:10:04 time: 0.4514 data_time: 0.0014 memory: 48500 loss: 0.0957 loss_ce: 0.0957 2023/03/03 13:32:59 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:33:04 - mmengine - INFO - Epoch(train) [185][10/79] lr: 1.0000e-06 eta: 0:09:55 time: 0.4635 data_time: 0.0472 memory: 33884 loss: 0.1146 loss_ce: 0.1146 2023/03/03 13:33:08 - mmengine - INFO - Epoch(train) [185][20/79] lr: 1.0000e-06 eta: 0:09:51 time: 0.4647 data_time: 0.0014 memory: 39123 loss: 0.1240 loss_ce: 0.1240 2023/03/03 13:33:14 - mmengine - INFO - Epoch(train) [185][30/79] lr: 1.0000e-06 eta: 0:09:46 time: 0.5233 data_time: 0.0016 memory: 24936 loss: 0.1093 loss_ce: 0.1093 2023/03/03 13:33:19 - mmengine - INFO - Epoch(train) [185][40/79] lr: 1.0000e-06 eta: 0:09:41 time: 0.4891 data_time: 0.0016 memory: 36077 loss: 0.1263 loss_ce: 0.1263 2023/03/03 13:33:23 - mmengine - INFO - Epoch(train) [185][50/79] lr: 1.0000e-06 eta: 0:09:36 time: 0.4555 data_time: 0.0015 memory: 26519 loss: 0.1087 loss_ce: 0.1087 2023/03/03 13:33:28 - mmengine - INFO - Epoch(train) [185][60/79] lr: 1.0000e-06 eta: 0:09:32 time: 0.4721 data_time: 0.0015 memory: 41714 loss: 0.1163 loss_ce: 0.1163 2023/03/03 13:33:33 - mmengine - INFO - Epoch(train) [185][70/79] lr: 1.0000e-06 eta: 0:09:27 time: 0.4943 data_time: 0.0013 memory: 38059 loss: 0.1058 loss_ce: 0.1058 2023/03/03 13:33:37 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:33:42 - mmengine - INFO - Epoch(train) [186][10/79] lr: 1.0000e-06 eta: 0:09:18 time: 0.4908 data_time: 0.0675 memory: 33322 loss: 0.1107 loss_ce: 0.1107 2023/03/03 13:33:46 - mmengine - INFO - Epoch(train) [186][20/79] lr: 1.0000e-06 eta: 0:09:13 time: 0.4584 data_time: 0.0015 memory: 35804 loss: 0.1123 loss_ce: 0.1123 2023/03/03 13:33:51 - mmengine - INFO - Epoch(train) [186][30/79] lr: 1.0000e-06 eta: 0:09:08 time: 0.5306 data_time: 0.0015 memory: 45998 loss: 0.1109 loss_ce: 0.1109 2023/03/03 13:33:56 - mmengine - INFO - Epoch(train) [186][40/79] lr: 1.0000e-06 eta: 0:09:04 time: 0.4957 data_time: 0.0015 memory: 40236 loss: 0.1170 loss_ce: 0.1170 2023/03/03 13:34:01 - mmengine - INFO - Epoch(train) [186][50/79] lr: 1.0000e-06 eta: 0:08:59 time: 0.4632 data_time: 0.0015 memory: 28789 loss: 0.1050 loss_ce: 0.1050 2023/03/03 13:34:05 - mmengine - INFO - Epoch(train) [186][60/79] lr: 1.0000e-06 eta: 0:08:54 time: 0.4341 data_time: 0.0018 memory: 34863 loss: 0.1207 loss_ce: 0.1207 2023/03/03 13:34:10 - mmengine - INFO - Epoch(train) [186][70/79] lr: 1.0000e-06 eta: 0:08:49 time: 0.4949 data_time: 0.0013 memory: 26268 loss: 0.1048 loss_ce: 0.1048 2023/03/03 13:34:14 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:34:19 - mmengine - INFO - Epoch(train) [187][10/79] lr: 1.0000e-06 eta: 0:08:40 time: 0.5073 data_time: 0.0257 memory: 32405 loss: 0.0960 loss_ce: 0.0960 2023/03/03 13:34:23 - mmengine - INFO - Epoch(train) [187][20/79] lr: 1.0000e-06 eta: 0:08:35 time: 0.4293 data_time: 0.0018 memory: 29956 loss: 0.1235 loss_ce: 0.1235 2023/03/03 13:34:28 - mmengine - INFO - Epoch(train) [187][30/79] lr: 1.0000e-06 eta: 0:08:31 time: 0.4677 data_time: 0.0015 memory: 38588 loss: 0.1157 loss_ce: 0.1157 2023/03/03 13:34:33 - mmengine - INFO - Epoch(train) [187][40/79] lr: 1.0000e-06 eta: 0:08:26 time: 0.4562 data_time: 0.0014 memory: 45016 loss: 0.0995 loss_ce: 0.0995 2023/03/03 13:34:37 - mmengine - INFO - Epoch(train) [187][50/79] lr: 1.0000e-06 eta: 0:08:21 time: 0.4779 data_time: 0.0015 memory: 39669 loss: 0.0902 loss_ce: 0.0902 2023/03/03 13:34:42 - mmengine - INFO - Epoch(train) [187][60/79] lr: 1.0000e-06 eta: 0:08:16 time: 0.4831 data_time: 0.0015 memory: 39150 loss: 0.1262 loss_ce: 0.1262 2023/03/03 13:34:47 - mmengine - INFO - Epoch(train) [187][70/79] lr: 1.0000e-06 eta: 0:08:12 time: 0.4774 data_time: 0.0013 memory: 33324 loss: 0.1071 loss_ce: 0.1071 2023/03/03 13:34:51 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:34:56 - mmengine - INFO - Epoch(train) [188][10/79] lr: 1.0000e-06 eta: 0:08:03 time: 0.5842 data_time: 0.0446 memory: 34480 loss: 0.0970 loss_ce: 0.0970 2023/03/03 13:35:02 - mmengine - INFO - Epoch(train) [188][20/79] lr: 1.0000e-06 eta: 0:07:58 time: 0.5232 data_time: 0.0014 memory: 37934 loss: 0.1238 loss_ce: 0.1238 2023/03/03 13:35:06 - mmengine - INFO - Epoch(train) [188][30/79] lr: 1.0000e-06 eta: 0:07:53 time: 0.4649 data_time: 0.0014 memory: 36564 loss: 0.1210 loss_ce: 0.1210 2023/03/03 13:35:11 - mmengine - INFO - Epoch(train) [188][40/79] lr: 1.0000e-06 eta: 0:07:48 time: 0.4477 data_time: 0.0014 memory: 33701 loss: 0.1153 loss_ce: 0.1153 2023/03/03 13:35:16 - mmengine - INFO - Epoch(train) [188][50/79] lr: 1.0000e-06 eta: 0:07:44 time: 0.5105 data_time: 0.0014 memory: 27572 loss: 0.0929 loss_ce: 0.0929 2023/03/03 13:35:20 - mmengine - INFO - Epoch(train) [188][60/79] lr: 1.0000e-06 eta: 0:07:39 time: 0.4552 data_time: 0.0016 memory: 44047 loss: 0.1025 loss_ce: 0.1025 2023/03/03 13:35:25 - mmengine - INFO - Epoch(train) [188][70/79] lr: 1.0000e-06 eta: 0:07:34 time: 0.4723 data_time: 0.0015 memory: 38851 loss: 0.1191 loss_ce: 0.1191 2023/03/03 13:35:29 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:35:35 - mmengine - INFO - Epoch(train) [189][10/79] lr: 1.0000e-06 eta: 0:07:25 time: 0.5392 data_time: 0.0496 memory: 42642 loss: 0.0992 loss_ce: 0.0992 2023/03/03 13:35:39 - mmengine - INFO - Epoch(train) [189][20/79] lr: 1.0000e-06 eta: 0:07:20 time: 0.4509 data_time: 0.0015 memory: 32533 loss: 0.1173 loss_ce: 0.1173 2023/03/03 13:35:44 - mmengine - INFO - Epoch(train) [189][30/79] lr: 1.0000e-06 eta: 0:07:16 time: 0.4618 data_time: 0.0016 memory: 38023 loss: 0.1022 loss_ce: 0.1022 2023/03/03 13:35:49 - mmengine - INFO - Epoch(train) [189][40/79] lr: 1.0000e-06 eta: 0:07:11 time: 0.4967 data_time: 0.0017 memory: 37934 loss: 0.1174 loss_ce: 0.1174 2023/03/03 13:35:54 - mmengine - INFO - Epoch(train) [189][50/79] lr: 1.0000e-06 eta: 0:07:06 time: 0.4890 data_time: 0.0016 memory: 45998 loss: 0.1114 loss_ce: 0.1114 2023/03/03 13:35:58 - mmengine - INFO - Epoch(train) [189][60/79] lr: 1.0000e-06 eta: 0:07:01 time: 0.4341 data_time: 0.0015 memory: 36233 loss: 0.1272 loss_ce: 0.1272 2023/03/03 13:36:03 - mmengine - INFO - Epoch(train) [189][70/79] lr: 1.0000e-06 eta: 0:06:57 time: 0.5175 data_time: 0.0014 memory: 30571 loss: 0.1041 loss_ce: 0.1041 2023/03/03 13:36:07 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:36:13 - mmengine - INFO - Epoch(train) [190][10/79] lr: 1.0000e-06 eta: 0:06:48 time: 0.5281 data_time: 0.0551 memory: 43282 loss: 0.1007 loss_ce: 0.1007 2023/03/03 13:36:17 - mmengine - INFO - Epoch(train) [190][20/79] lr: 1.0000e-06 eta: 0:06:43 time: 0.4621 data_time: 0.0016 memory: 40236 loss: 0.1011 loss_ce: 0.1011 2023/03/03 13:36:22 - mmengine - INFO - Epoch(train) [190][30/79] lr: 1.0000e-06 eta: 0:06:38 time: 0.4620 data_time: 0.0015 memory: 31319 loss: 0.1228 loss_ce: 0.1228 2023/03/03 13:36:27 - mmengine - INFO - Epoch(train) [190][40/79] lr: 1.0000e-06 eta: 0:06:33 time: 0.4741 data_time: 0.0015 memory: 46200 loss: 0.1170 loss_ce: 0.1170 2023/03/03 13:36:31 - mmengine - INFO - Epoch(train) [190][50/79] lr: 1.0000e-06 eta: 0:06:29 time: 0.4426 data_time: 0.0015 memory: 36209 loss: 0.1082 loss_ce: 0.1082 2023/03/03 13:36:36 - mmengine - INFO - Epoch(train) [190][60/79] lr: 1.0000e-06 eta: 0:06:24 time: 0.4576 data_time: 0.0015 memory: 38306 loss: 0.1097 loss_ce: 0.1097 2023/03/03 13:36:40 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:36:40 - mmengine - INFO - Epoch(train) [190][70/79] lr: 1.0000e-06 eta: 0:06:19 time: 0.4529 data_time: 0.0015 memory: 25151 loss: 0.1031 loss_ce: 0.1031 2023/03/03 13:36:45 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:36:58 - mmengine - INFO - Epoch(val) [190][10/75] eta: 0:01:26 time: 1.3237 data_time: 0.0031 memory: 38801 2023/03/03 13:37:41 - mmengine - INFO - Epoch(val) [190][20/75] eta: 0:02:33 time: 4.2630 data_time: 0.0004 memory: 1077 2023/03/03 13:38:01 - mmengine - INFO - Epoch(val) [190][30/75] eta: 0:01:53 time: 2.0015 data_time: 0.0005 memory: 1020 2023/03/03 13:38:16 - mmengine - INFO - Epoch(val) [190][40/75] eta: 0:01:19 time: 1.5231 data_time: 0.0005 memory: 1019 2023/03/03 13:38:30 - mmengine - INFO - Epoch(val) [190][50/75] eta: 0:00:52 time: 1.4532 data_time: 0.0005 memory: 1077 2023/03/03 13:39:35 - mmengine - INFO - Epoch(val) [190][60/75] eta: 0:00:42 time: 6.4734 data_time: 0.0005 memory: 1045 2023/03/03 13:40:15 - mmengine - INFO - Epoch(val) [190][70/75] eta: 0:00:15 time: 3.9875 data_time: 0.0004 memory: 1077 2023/03/03 13:40:29 - mmengine - INFO - text score threshold: 0.80, recall: 0.6872, precision: 0.7216, hmean: 0.7040 2023/03/03 13:40:29 - mmengine - INFO - text score threshold: 0.81, recall: 0.6866, precision: 0.7282, hmean: 0.7068 2023/03/03 13:40:29 - mmengine - INFO - text score threshold: 0.82, recall: 0.6861, precision: 0.7323, hmean: 0.7084 2023/03/03 13:40:29 - mmengine - INFO - text score threshold: 0.83, recall: 0.6855, precision: 0.7417, hmean: 0.7125 2023/03/03 13:40:29 - mmengine - INFO - text score threshold: 0.84, recall: 0.6850, precision: 0.7460, hmean: 0.7142 2023/03/03 13:40:29 - mmengine - INFO - text score threshold: 0.85, recall: 0.6839, precision: 0.7520, hmean: 0.7163 2023/03/03 13:40:29 - mmengine - INFO - text score threshold: 0.86, recall: 0.6811, precision: 0.7576, hmean: 0.7173 2023/03/03 13:40:29 - mmengine - INFO - text score threshold: 0.87, recall: 0.6784, precision: 0.7667, hmean: 0.7199 2023/03/03 13:40:29 - mmengine - INFO - text score threshold: 0.88, recall: 0.6762, precision: 0.7758, hmean: 0.7226 2023/03/03 13:40:29 - mmengine - INFO - text score threshold: 0.89, recall: 0.6745, precision: 0.7838, hmean: 0.7251 2023/03/03 13:40:29 - mmengine - INFO - text score threshold: 0.90, recall: 0.6712, precision: 0.7906, hmean: 0.7260 2023/03/03 13:40:29 - mmengine - INFO - text score threshold: 0.91, recall: 0.6674, precision: 0.7995, hmean: 0.7275 2023/03/03 13:40:29 - mmengine - INFO - text score threshold: 0.92, recall: 0.6625, precision: 0.8084, hmean: 0.7282 2023/03/03 13:40:29 - mmengine - INFO - text score threshold: 0.93, recall: 0.6542, precision: 0.8142, hmean: 0.7255 2023/03/03 13:40:29 - mmengine - INFO - text score threshold: 0.94, recall: 0.6482, precision: 0.8259, hmean: 0.7263 2023/03/03 13:40:29 - mmengine - INFO - text score threshold: 0.95, recall: 0.6378, precision: 0.8372, hmean: 0.7240 2023/03/03 13:40:29 - mmengine - INFO - text score threshold: 0.96, recall: 0.6290, precision: 0.8489, hmean: 0.7226 2023/03/03 13:40:29 - mmengine - INFO - text score threshold: 0.97, recall: 0.6196, precision: 0.8592, hmean: 0.7200 2023/03/03 13:40:29 - mmengine - INFO - text score threshold: 0.98, recall: 0.6015, precision: 0.8740, hmean: 0.7126 2023/03/03 13:40:29 - mmengine - INFO - text score threshold: 0.99, recall: 0.5730, precision: 0.8862, hmean: 0.6960 2023/03/03 13:40:39 - mmengine - INFO - text score threshold: 0.80, recall: 0.7816, precision: 0.8547, hmean: 0.8165 2023/03/03 13:40:39 - mmengine - INFO - text score threshold: 0.81, recall: 0.7783, precision: 0.8578, hmean: 0.8161 2023/03/03 13:40:39 - mmengine - INFO - text score threshold: 0.82, recall: 0.7772, precision: 0.8624, hmean: 0.8176 2023/03/03 13:40:39 - mmengine - INFO - text score threshold: 0.83, recall: 0.7744, precision: 0.8683, hmean: 0.8187 2023/03/03 13:40:39 - mmengine - INFO - text score threshold: 0.84, recall: 0.7739, precision: 0.8725, hmean: 0.8202 2023/03/03 13:40:39 - mmengine - INFO - text score threshold: 0.85, recall: 0.7717, precision: 0.8777, hmean: 0.8213 2023/03/03 13:40:39 - mmengine - INFO - text score threshold: 0.86, recall: 0.7673, precision: 0.8815, hmean: 0.8204 2023/03/03 13:40:39 - mmengine - INFO - text score threshold: 0.87, recall: 0.7613, precision: 0.8868, hmean: 0.8193 2023/03/03 13:40:39 - mmengine - INFO - text score threshold: 0.88, recall: 0.7574, precision: 0.8926, hmean: 0.8195 2023/03/03 13:40:39 - mmengine - INFO - text score threshold: 0.89, recall: 0.7536, precision: 0.8968, hmean: 0.8190 2023/03/03 13:40:39 - mmengine - INFO - text score threshold: 0.90, recall: 0.7459, precision: 0.8994, hmean: 0.8155 2023/03/03 13:40:39 - mmengine - INFO - text score threshold: 0.91, recall: 0.7393, precision: 0.9046, hmean: 0.8137 2023/03/03 13:40:39 - mmengine - INFO - text score threshold: 0.92, recall: 0.7294, precision: 0.9084, hmean: 0.8091 2023/03/03 13:40:39 - mmengine - INFO - text score threshold: 0.93, recall: 0.7162, precision: 0.9100, hmean: 0.8016 2023/03/03 13:40:39 - mmengine - INFO - text score threshold: 0.94, recall: 0.7020, precision: 0.9123, hmean: 0.7934 2023/03/03 13:40:39 - mmengine - INFO - text score threshold: 0.95, recall: 0.6817, precision: 0.9132, hmean: 0.7806 2023/03/03 13:40:39 - mmengine - INFO - text score threshold: 0.96, recall: 0.6668, precision: 0.9177, hmean: 0.7724 2023/03/03 13:40:39 - mmengine - INFO - text score threshold: 0.97, recall: 0.6531, precision: 0.9225, hmean: 0.7648 2023/03/03 13:40:39 - mmengine - INFO - text score threshold: 0.98, recall: 0.6268, precision: 0.9254, hmean: 0.7474 2023/03/03 13:40:39 - mmengine - INFO - text score threshold: 0.99, recall: 0.5950, precision: 0.9337, hmean: 0.7268 2023/03/03 13:40:39 - mmengine - INFO - Epoch(val) [190][75/75] none/precision: 0.8084 none/recall: 0.6625 none/hmean: 0.7282 full/precision: 0.8777 full/recall: 0.7717 full/hmean: 0.8213 2023/03/03 13:40:44 - mmengine - INFO - Epoch(train) [191][10/79] lr: 1.0000e-06 eta: 0:06:10 time: 0.4793 data_time: 0.0612 memory: 35032 loss: 0.1088 loss_ce: 0.1088 2023/03/03 13:40:49 - mmengine - INFO - Epoch(train) [191][20/79] lr: 1.0000e-06 eta: 0:06:05 time: 0.5427 data_time: 0.0015 memory: 36637 loss: 0.1301 loss_ce: 0.1301 2023/03/03 13:40:54 - mmengine - INFO - Epoch(train) [191][30/79] lr: 1.0000e-06 eta: 0:06:01 time: 0.4734 data_time: 0.0016 memory: 36224 loss: 0.1251 loss_ce: 0.1251 2023/03/03 13:40:59 - mmengine - INFO - Epoch(train) [191][40/79] lr: 1.0000e-06 eta: 0:05:56 time: 0.4513 data_time: 0.0015 memory: 30007 loss: 0.1240 loss_ce: 0.1240 2023/03/03 13:41:03 - mmengine - INFO - Epoch(train) [191][50/79] lr: 1.0000e-06 eta: 0:05:51 time: 0.4835 data_time: 0.0015 memory: 37870 loss: 0.1066 loss_ce: 0.1066 2023/03/03 13:41:08 - mmengine - INFO - Epoch(train) [191][60/79] lr: 1.0000e-06 eta: 0:05:46 time: 0.4296 data_time: 0.0014 memory: 35547 loss: 0.1066 loss_ce: 0.1066 2023/03/03 13:41:13 - mmengine - INFO - Epoch(train) [191][70/79] lr: 1.0000e-06 eta: 0:05:42 time: 0.5088 data_time: 0.0013 memory: 31171 loss: 0.1135 loss_ce: 0.1135 2023/03/03 13:41:17 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:41:22 - mmengine - INFO - Epoch(train) [192][10/79] lr: 1.0000e-06 eta: 0:05:33 time: 0.5111 data_time: 0.0315 memory: 41028 loss: 0.1137 loss_ce: 0.1137 2023/03/03 13:41:27 - mmengine - INFO - Epoch(train) [192][20/79] lr: 1.0000e-06 eta: 0:05:28 time: 0.5029 data_time: 0.0016 memory: 36658 loss: 0.1184 loss_ce: 0.1184 2023/03/03 13:41:32 - mmengine - INFO - Epoch(train) [192][30/79] lr: 1.0000e-06 eta: 0:05:23 time: 0.5248 data_time: 0.0015 memory: 41714 loss: 0.0958 loss_ce: 0.0958 2023/03/03 13:41:37 - mmengine - INFO - Epoch(train) [192][40/79] lr: 1.0000e-06 eta: 0:05:18 time: 0.4568 data_time: 0.0014 memory: 40524 loss: 0.1033 loss_ce: 0.1033 2023/03/03 13:41:42 - mmengine - INFO - Epoch(train) [192][50/79] lr: 1.0000e-06 eta: 0:05:14 time: 0.4807 data_time: 0.0015 memory: 41108 loss: 0.1038 loss_ce: 0.1038 2023/03/03 13:41:46 - mmengine - INFO - Epoch(train) [192][60/79] lr: 1.0000e-06 eta: 0:05:09 time: 0.4556 data_time: 0.0015 memory: 36385 loss: 0.1156 loss_ce: 0.1156 2023/03/03 13:41:51 - mmengine - INFO - Epoch(train) [192][70/79] lr: 1.0000e-06 eta: 0:05:04 time: 0.5089 data_time: 0.0015 memory: 42015 loss: 0.0981 loss_ce: 0.0981 2023/03/03 13:41:55 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:42:01 - mmengine - INFO - Epoch(train) [193][10/79] lr: 1.0000e-06 eta: 0:04:55 time: 0.5468 data_time: 0.0376 memory: 40243 loss: 0.1199 loss_ce: 0.1199 2023/03/03 13:42:06 - mmengine - INFO - Epoch(train) [193][20/79] lr: 1.0000e-06 eta: 0:04:50 time: 0.4777 data_time: 0.0015 memory: 42327 loss: 0.1114 loss_ce: 0.1114 2023/03/03 13:42:11 - mmengine - INFO - Epoch(train) [193][30/79] lr: 1.0000e-06 eta: 0:04:46 time: 0.5298 data_time: 0.0015 memory: 43402 loss: 0.1151 loss_ce: 0.1151 2023/03/03 13:42:16 - mmengine - INFO - Epoch(train) [193][40/79] lr: 1.0000e-06 eta: 0:04:41 time: 0.5048 data_time: 0.0015 memory: 29100 loss: 0.1028 loss_ce: 0.1028 2023/03/03 13:42:20 - mmengine - INFO - Epoch(train) [193][50/79] lr: 1.0000e-06 eta: 0:04:36 time: 0.4345 data_time: 0.0015 memory: 31143 loss: 0.1204 loss_ce: 0.1204 2023/03/03 13:42:25 - mmengine - INFO - Epoch(train) [193][60/79] lr: 1.0000e-06 eta: 0:04:31 time: 0.4642 data_time: 0.0014 memory: 35826 loss: 0.1054 loss_ce: 0.1054 2023/03/03 13:42:30 - mmengine - INFO - Epoch(train) [193][70/79] lr: 1.0000e-06 eta: 0:04:27 time: 0.4837 data_time: 0.0013 memory: 36575 loss: 0.1178 loss_ce: 0.1178 2023/03/03 13:42:34 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:42:39 - mmengine - INFO - Epoch(train) [194][10/79] lr: 1.0000e-06 eta: 0:04:18 time: 0.5224 data_time: 0.0522 memory: 43433 loss: 0.1124 loss_ce: 0.1124 2023/03/03 13:42:44 - mmengine - INFO - Epoch(train) [194][20/79] lr: 1.0000e-06 eta: 0:04:13 time: 0.5001 data_time: 0.0018 memory: 34909 loss: 0.1066 loss_ce: 0.1066 2023/03/03 13:42:49 - mmengine - INFO - Epoch(train) [194][30/79] lr: 1.0000e-06 eta: 0:04:08 time: 0.4711 data_time: 0.0015 memory: 38169 loss: 0.1248 loss_ce: 0.1248 2023/03/03 13:42:53 - mmengine - INFO - Epoch(train) [194][40/79] lr: 1.0000e-06 eta: 0:04:03 time: 0.4741 data_time: 0.0015 memory: 38588 loss: 0.1329 loss_ce: 0.1329 2023/03/03 13:42:59 - mmengine - INFO - Epoch(train) [194][50/79] lr: 1.0000e-06 eta: 0:03:59 time: 0.5114 data_time: 0.0016 memory: 39012 loss: 0.1168 loss_ce: 0.1168 2023/03/03 13:43:03 - mmengine - INFO - Epoch(train) [194][60/79] lr: 1.0000e-06 eta: 0:03:54 time: 0.4141 data_time: 0.0015 memory: 27948 loss: 0.1033 loss_ce: 0.1033 2023/03/03 13:43:08 - mmengine - INFO - Epoch(train) [194][70/79] lr: 1.0000e-06 eta: 0:03:49 time: 0.4899 data_time: 0.0013 memory: 34356 loss: 0.1100 loss_ce: 0.1100 2023/03/03 13:43:12 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:43:17 - mmengine - INFO - Epoch(train) [195][10/79] lr: 1.0000e-06 eta: 0:03:40 time: 0.5086 data_time: 0.0368 memory: 44609 loss: 0.1063 loss_ce: 0.1063 2023/03/03 13:43:21 - mmengine - INFO - Epoch(train) [195][20/79] lr: 1.0000e-06 eta: 0:03:35 time: 0.4214 data_time: 0.0014 memory: 38849 loss: 0.1124 loss_ce: 0.1124 2023/03/03 13:43:25 - mmengine - INFO - Epoch(train) [195][30/79] lr: 1.0000e-06 eta: 0:03:31 time: 0.4483 data_time: 0.0014 memory: 49116 loss: 0.1071 loss_ce: 0.1071 2023/03/03 13:43:30 - mmengine - INFO - Epoch(train) [195][40/79] lr: 1.0000e-06 eta: 0:03:26 time: 0.4676 data_time: 0.0015 memory: 29981 loss: 0.0974 loss_ce: 0.0974 2023/03/03 13:43:35 - mmengine - INFO - Epoch(train) [195][50/79] lr: 1.0000e-06 eta: 0:03:21 time: 0.5280 data_time: 0.0015 memory: 39057 loss: 0.1188 loss_ce: 0.1188 2023/03/03 13:43:40 - mmengine - INFO - Epoch(train) [195][60/79] lr: 1.0000e-06 eta: 0:03:16 time: 0.4469 data_time: 0.0015 memory: 29862 loss: 0.1143 loss_ce: 0.1143 2023/03/03 13:43:44 - mmengine - INFO - Epoch(train) [195][70/79] lr: 1.0000e-06 eta: 0:03:12 time: 0.4211 data_time: 0.0013 memory: 26219 loss: 0.1074 loss_ce: 0.1074 2023/03/03 13:43:48 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:43:53 - mmengine - INFO - Epoch(train) [196][10/79] lr: 1.0000e-06 eta: 0:03:02 time: 0.5052 data_time: 0.0414 memory: 37511 loss: 0.1093 loss_ce: 0.1093 2023/03/03 13:43:58 - mmengine - INFO - Epoch(train) [196][20/79] lr: 1.0000e-06 eta: 0:02:58 time: 0.4803 data_time: 0.0015 memory: 33401 loss: 0.0958 loss_ce: 0.0958 2023/03/03 13:44:03 - mmengine - INFO - Epoch(train) [196][30/79] lr: 1.0000e-06 eta: 0:02:53 time: 0.4523 data_time: 0.0015 memory: 36889 loss: 0.1068 loss_ce: 0.1068 2023/03/03 13:44:07 - mmengine - INFO - Epoch(train) [196][40/79] lr: 1.0000e-06 eta: 0:02:48 time: 0.4327 data_time: 0.0015 memory: 32765 loss: 0.1058 loss_ce: 0.1058 2023/03/03 13:44:12 - mmengine - INFO - Epoch(train) [196][50/79] lr: 1.0000e-06 eta: 0:02:43 time: 0.4848 data_time: 0.0015 memory: 32648 loss: 0.1082 loss_ce: 0.1082 2023/03/03 13:44:16 - mmengine - INFO - Epoch(train) [196][60/79] lr: 1.0000e-06 eta: 0:02:39 time: 0.4537 data_time: 0.0015 memory: 31245 loss: 0.1248 loss_ce: 0.1248 2023/03/03 13:44:21 - mmengine - INFO - Epoch(train) [196][70/79] lr: 1.0000e-06 eta: 0:02:34 time: 0.4809 data_time: 0.0013 memory: 30735 loss: 0.0968 loss_ce: 0.0968 2023/03/03 13:44:25 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:44:31 - mmengine - INFO - Epoch(train) [197][10/79] lr: 1.0000e-06 eta: 0:02:25 time: 0.5112 data_time: 0.0266 memory: 38082 loss: 0.1028 loss_ce: 0.1028 2023/03/03 13:44:35 - mmengine - INFO - Epoch(train) [197][20/79] lr: 1.0000e-06 eta: 0:02:20 time: 0.4977 data_time: 0.0016 memory: 44080 loss: 0.1032 loss_ce: 0.1032 2023/03/03 13:44:41 - mmengine - INFO - Epoch(train) [197][30/79] lr: 1.0000e-06 eta: 0:02:15 time: 0.5104 data_time: 0.0015 memory: 29172 loss: 0.1080 loss_ce: 0.1080 2023/03/03 13:44:45 - mmengine - INFO - Epoch(train) [197][40/79] lr: 1.0000e-06 eta: 0:02:11 time: 0.4752 data_time: 0.0015 memory: 24602 loss: 0.1278 loss_ce: 0.1278 2023/03/03 13:44:50 - mmengine - INFO - Epoch(train) [197][50/79] lr: 1.0000e-06 eta: 0:02:06 time: 0.5058 data_time: 0.0015 memory: 35177 loss: 0.1096 loss_ce: 0.1096 2023/03/03 13:44:55 - mmengine - INFO - Epoch(train) [197][60/79] lr: 1.0000e-06 eta: 0:02:01 time: 0.4760 data_time: 0.0018 memory: 37934 loss: 0.0972 loss_ce: 0.0972 2023/03/03 13:45:00 - mmengine - INFO - Epoch(train) [197][70/79] lr: 1.0000e-06 eta: 0:01:56 time: 0.5123 data_time: 0.0013 memory: 34644 loss: 0.1000 loss_ce: 0.1000 2023/03/03 13:45:05 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:45:10 - mmengine - INFO - Epoch(train) [198][10/79] lr: 1.0000e-06 eta: 0:01:47 time: 0.5069 data_time: 0.0522 memory: 38628 loss: 0.1009 loss_ce: 0.1009 2023/03/03 13:45:14 - mmengine - INFO - Epoch(train) [198][20/79] lr: 1.0000e-06 eta: 0:01:43 time: 0.4434 data_time: 0.0015 memory: 29775 loss: 0.1084 loss_ce: 0.1084 2023/03/03 13:45:19 - mmengine - INFO - Epoch(train) [198][30/79] lr: 1.0000e-06 eta: 0:01:38 time: 0.4557 data_time: 0.0018 memory: 38588 loss: 0.1254 loss_ce: 0.1254 2023/03/03 13:45:24 - mmengine - INFO - Epoch(train) [198][40/79] lr: 1.0000e-06 eta: 0:01:33 time: 0.5162 data_time: 0.0017 memory: 38265 loss: 0.1092 loss_ce: 0.1092 2023/03/03 13:45:28 - mmengine - INFO - Epoch(train) [198][50/79] lr: 1.0000e-06 eta: 0:01:28 time: 0.4645 data_time: 0.0015 memory: 39955 loss: 0.1027 loss_ce: 0.1027 2023/03/03 13:45:33 - mmengine - INFO - Epoch(train) [198][60/79] lr: 1.0000e-06 eta: 0:01:24 time: 0.4950 data_time: 0.0015 memory: 32761 loss: 0.0949 loss_ce: 0.0949 2023/03/03 13:45:38 - mmengine - INFO - Epoch(train) [198][70/79] lr: 1.0000e-06 eta: 0:01:19 time: 0.5061 data_time: 0.0013 memory: 41461 loss: 0.1200 loss_ce: 0.1200 2023/03/03 13:45:42 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:45:47 - mmengine - INFO - Epoch(train) [199][10/79] lr: 1.0000e-06 eta: 0:01:10 time: 0.4946 data_time: 0.0497 memory: 40471 loss: 0.1099 loss_ce: 0.1099 2023/03/03 13:45:52 - mmengine - INFO - Epoch(train) [199][20/79] lr: 1.0000e-06 eta: 0:01:05 time: 0.4888 data_time: 0.0014 memory: 34729 loss: 0.1056 loss_ce: 0.1056 2023/03/03 13:45:57 - mmengine - INFO - Epoch(train) [199][30/79] lr: 1.0000e-06 eta: 0:01:00 time: 0.4401 data_time: 0.0014 memory: 33155 loss: 0.1114 loss_ce: 0.1114 2023/03/03 13:46:02 - mmengine - INFO - Epoch(train) [199][40/79] lr: 1.0000e-06 eta: 0:00:56 time: 0.4979 data_time: 0.0016 memory: 42016 loss: 0.0980 loss_ce: 0.0980 2023/03/03 13:46:07 - mmengine - INFO - Epoch(train) [199][50/79] lr: 1.0000e-06 eta: 0:00:51 time: 0.4960 data_time: 0.0015 memory: 38588 loss: 0.1098 loss_ce: 0.1098 2023/03/03 13:46:11 - mmengine - INFO - Epoch(train) [199][60/79] lr: 1.0000e-06 eta: 0:00:46 time: 0.4689 data_time: 0.0020 memory: 36954 loss: 0.1084 loss_ce: 0.1084 2023/03/03 13:46:16 - mmengine - INFO - Epoch(train) [199][70/79] lr: 1.0000e-06 eta: 0:00:41 time: 0.4551 data_time: 0.0014 memory: 33681 loss: 0.1189 loss_ce: 0.1189 2023/03/03 13:46:20 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:46:25 - mmengine - INFO - Epoch(train) [200][10/79] lr: 1.0000e-06 eta: 0:00:32 time: 0.5289 data_time: 0.0569 memory: 40236 loss: 0.1030 loss_ce: 0.1030 2023/03/03 13:46:29 - mmengine - INFO - Epoch(train) [200][20/79] lr: 1.0000e-06 eta: 0:00:28 time: 0.4480 data_time: 0.0014 memory: 37844 loss: 0.1154 loss_ce: 0.1154 2023/03/03 13:46:34 - mmengine - INFO - Epoch(train) [200][30/79] lr: 1.0000e-06 eta: 0:00:23 time: 0.4217 data_time: 0.0015 memory: 30691 loss: 0.1091 loss_ce: 0.1091 2023/03/03 13:46:38 - mmengine - INFO - Epoch(train) [200][40/79] lr: 1.0000e-06 eta: 0:00:18 time: 0.4646 data_time: 0.0014 memory: 26207 loss: 0.1165 loss_ce: 0.1165 2023/03/03 13:46:43 - mmengine - INFO - Epoch(train) [200][50/79] lr: 1.0000e-06 eta: 0:00:13 time: 0.4533 data_time: 0.0014 memory: 37920 loss: 0.1091 loss_ce: 0.1091 2023/03/03 13:46:48 - mmengine - INFO - Epoch(train) [200][60/79] lr: 1.0000e-06 eta: 0:00:09 time: 0.4956 data_time: 0.0015 memory: 28277 loss: 0.1139 loss_ce: 0.1139 2023/03/03 13:46:53 - mmengine - INFO - Epoch(train) [200][70/79] lr: 1.0000e-06 eta: 0:00:04 time: 0.5465 data_time: 0.0015 memory: 28416 loss: 0.1219 loss_ce: 0.1219 2023/03/03 13:46:57 - mmengine - INFO - Exp name: spts_resnet50_350e_totaltext_20230303_103040 2023/03/03 13:46:57 - mmengine - INFO - Saving checkpoint at 200 epochs 2023/03/03 13:46:59 - mmengine - WARNING - `save_param_scheduler` is True but `self.param_schedulers` is None, so skip saving parameter schedulers 2023/03/03 13:47:13 - mmengine - INFO - Epoch(val) [200][10/75] eta: 0:01:22 time: 1.2621 data_time: 0.0031 memory: 36164 2023/03/03 13:47:55 - mmengine - INFO - Epoch(val) [200][20/75] eta: 0:02:30 time: 4.2273 data_time: 0.0004 memory: 1077 2023/03/03 13:48:14 - mmengine - INFO - Epoch(val) [200][30/75] eta: 0:01:51 time: 1.9237 data_time: 0.0004 memory: 1020 2023/03/03 13:48:30 - mmengine - INFO - Epoch(val) [200][40/75] eta: 0:01:18 time: 1.5527 data_time: 0.0004 memory: 1019 2023/03/03 13:48:44 - mmengine - INFO - Epoch(val) [200][50/75] eta: 0:00:52 time: 1.4776 data_time: 0.0005 memory: 1077 2023/03/03 13:49:28 - mmengine - INFO - Epoch(val) [200][60/75] eta: 0:00:36 time: 4.3495 data_time: 0.0004 memory: 1045 2023/03/03 13:49:57 - mmengine - INFO - Epoch(val) [200][70/75] eta: 0:00:12 time: 2.9312 data_time: 0.0004 memory: 1077 2023/03/03 13:50:11 - mmengine - INFO - text score threshold: 0.80, recall: 0.6855, precision: 0.7317, hmean: 0.7078 2023/03/03 13:50:11 - mmengine - INFO - text score threshold: 0.81, recall: 0.6844, precision: 0.7370, hmean: 0.7097 2023/03/03 13:50:11 - mmengine - INFO - text score threshold: 0.82, recall: 0.6839, precision: 0.7426, hmean: 0.7120 2023/03/03 13:50:11 - mmengine - INFO - text score threshold: 0.83, recall: 0.6833, precision: 0.7477, hmean: 0.7141 2023/03/03 13:50:11 - mmengine - INFO - text score threshold: 0.84, recall: 0.6828, precision: 0.7521, hmean: 0.7158 2023/03/03 13:50:11 - mmengine - INFO - text score threshold: 0.85, recall: 0.6828, precision: 0.7581, hmean: 0.7185 2023/03/03 13:50:11 - mmengine - INFO - text score threshold: 0.86, recall: 0.6811, precision: 0.7637, hmean: 0.7200 2023/03/03 13:50:11 - mmengine - INFO - text score threshold: 0.87, recall: 0.6784, precision: 0.7682, hmean: 0.7205 2023/03/03 13:50:11 - mmengine - INFO - text score threshold: 0.88, recall: 0.6762, precision: 0.7748, hmean: 0.7222 2023/03/03 13:50:11 - mmengine - INFO - text score threshold: 0.89, recall: 0.6729, precision: 0.7834, hmean: 0.7239 2023/03/03 13:50:11 - mmengine - INFO - text score threshold: 0.90, recall: 0.6707, precision: 0.7884, hmean: 0.7248 2023/03/03 13:50:11 - mmengine - INFO - text score threshold: 0.91, recall: 0.6658, precision: 0.7959, hmean: 0.7250 2023/03/03 13:50:11 - mmengine - INFO - text score threshold: 0.92, recall: 0.6592, precision: 0.8044, hmean: 0.7246 2023/03/03 13:50:11 - mmengine - INFO - text score threshold: 0.93, recall: 0.6531, precision: 0.8117, hmean: 0.7238 2023/03/03 13:50:11 - mmengine - INFO - text score threshold: 0.94, recall: 0.6460, precision: 0.8225, hmean: 0.7236 2023/03/03 13:50:11 - mmengine - INFO - text score threshold: 0.95, recall: 0.6411, precision: 0.8367, hmean: 0.7259 2023/03/03 13:50:11 - mmengine - INFO - text score threshold: 0.96, recall: 0.6306, precision: 0.8492, hmean: 0.7238 2023/03/03 13:50:11 - mmengine - INFO - text score threshold: 0.97, recall: 0.6191, precision: 0.8591, hmean: 0.7196 2023/03/03 13:50:11 - mmengine - INFO - text score threshold: 0.98, recall: 0.5999, precision: 0.8744, hmean: 0.7116 2023/03/03 13:50:11 - mmengine - INFO - text score threshold: 0.99, recall: 0.5757, precision: 0.8897, hmean: 0.6991 2023/03/03 13:50:21 - mmengine - INFO - text score threshold: 0.80, recall: 0.7794, precision: 0.8648, hmean: 0.8199 2023/03/03 13:50:21 - mmengine - INFO - text score threshold: 0.81, recall: 0.7766, precision: 0.8686, hmean: 0.8201 2023/03/03 13:50:21 - mmengine - INFO - text score threshold: 0.82, recall: 0.7739, precision: 0.8704, hmean: 0.8193 2023/03/03 13:50:21 - mmengine - INFO - text score threshold: 0.83, recall: 0.7717, precision: 0.8722, hmean: 0.8189 2023/03/03 13:50:21 - mmengine - INFO - text score threshold: 0.84, recall: 0.7700, precision: 0.8763, hmean: 0.8197 2023/03/03 13:50:21 - mmengine - INFO - text score threshold: 0.85, recall: 0.7689, precision: 0.8800, hmean: 0.8207 2023/03/03 13:50:21 - mmengine - INFO - text score threshold: 0.86, recall: 0.7656, precision: 0.8835, hmean: 0.8203 2023/03/03 13:50:21 - mmengine - INFO - text score threshold: 0.87, recall: 0.7623, precision: 0.8870, hmean: 0.8200 2023/03/03 13:50:21 - mmengine - INFO - text score threshold: 0.88, recall: 0.7558, precision: 0.8895, hmean: 0.8172 2023/03/03 13:50:21 - mmengine - INFO - text score threshold: 0.89, recall: 0.7503, precision: 0.8952, hmean: 0.8164 2023/03/03 13:50:21 - mmengine - INFO - text score threshold: 0.90, recall: 0.7442, precision: 0.8956, hmean: 0.8129 2023/03/03 13:50:21 - mmengine - INFO - text score threshold: 0.91, recall: 0.7366, precision: 0.9001, hmean: 0.8101 2023/03/03 13:50:21 - mmengine - INFO - text score threshold: 0.92, recall: 0.7256, precision: 0.9042, hmean: 0.8051 2023/03/03 13:50:21 - mmengine - INFO - text score threshold: 0.93, recall: 0.7151, precision: 0.9074, hmean: 0.7999 2023/03/03 13:50:21 - mmengine - INFO - text score threshold: 0.94, recall: 0.7003, precision: 0.9101, hmean: 0.7916 2023/03/03 13:50:21 - mmengine - INFO - text score threshold: 0.95, recall: 0.6861, precision: 0.9131, hmean: 0.7835 2023/03/03 13:50:21 - mmengine - INFO - text score threshold: 0.96, recall: 0.6690, precision: 0.9186, hmean: 0.7742 2023/03/03 13:50:21 - mmengine - INFO - text score threshold: 0.97, recall: 0.6542, precision: 0.9240, hmean: 0.7661 2023/03/03 13:50:21 - mmengine - INFO - text score threshold: 0.98, recall: 0.6279, precision: 0.9308, hmean: 0.7499 2023/03/03 13:50:21 - mmengine - INFO - text score threshold: 0.99, recall: 0.5971, precision: 0.9379, hmean: 0.7297 2023/03/03 13:50:22 - mmengine - INFO - Epoch(val) [200][75/75] none/precision: 0.8367 none/recall: 0.6411 none/hmean: 0.7259 full/precision: 0.8800 full/recall: 0.7689 full/hmean: 0.8207