2022/12/15 01:35:38 - mmengine - INFO - ------------------------------------------------------------ System environment: sys.platform: linux Python: 3.7.11 (default, Jul 27 2021, 14:32:16) [GCC 7.5.0] CUDA available: True numpy_random_seed: 2123600807 GPU 0,1,2,3,4,5,6,7: NVIDIA A100-SXM4-80GB CUDA_HOME: /usr/local/cuda NVCC: Cuda compilation tools, release 11.3, V11.3.109 GCC: gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0 PyTorch: 1.10.0 PyTorch compiling details: PyTorch built with: - GCC 7.3 - C++ Version: 201402 - Intel(R) oneAPI Math Kernel Library Version 2021.3-Product Build 20210617 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v2.2.3 (Git Hash 7336ca9f055cf1bfa13efb658fe15dc9b41f0740) - OpenMP 201511 (a.k.a. OpenMP 4.5) - LAPACK is enabled (usually provided by MKL) - NNPACK is enabled - CPU capability usage: AVX512 - CUDA Runtime 11.3 - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_37,code=compute_37 - CuDNN 8.2 - Magma 2.5.2 - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.3, CUDNN_VERSION=8.2.0, CXX_COMPILER=/opt/rh/devtoolset-7/root/usr/bin/c++, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.10.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, TorchVision: 0.11.0 OpenCV: 4.6.0 MMEngine: 0.3.1 Runtime environment: cudnn_benchmark: True mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0} dist_cfg: {'backend': 'nccl'} seed: None Distributed launcher: pytorch Distributed training: True GPU number: 8 ------------------------------------------------------------ 2022/12/15 01:35:38 - mmengine - INFO - Config: model = dict( type='DBNet', backbone=dict( type='mmdet.ResNet', depth=50, num_stages=4, out_indices=(0, 1, 2, 3), frozen_stages=-1, norm_cfg=dict(type='BN', requires_grad=True), norm_eval=False, style='pytorch', dcn=dict(type='DCNv2', deform_groups=1, fallback_on_stride=False), init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50'), stage_with_dcn=(False, True, True, True)), neck=dict( type='FPNC', in_channels=[256, 512, 1024, 2048], lateral_channels=256, asf_cfg=dict(attention_type='ScaleChannelSpatial')), det_head=dict( type='DBHead', in_channels=256, module_loss=dict(type='DBModuleLoss'), postprocessor=dict( type='DBPostprocessor', text_repr_type='quad', epsilon_ratio=0.002)), data_preprocessor=dict( type='TextDetDataPreprocessor', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], bgr_to_rgb=True, pad_size_divisor=32)) train_pipeline = [ dict(type='LoadImageFromFile', color_type='color_ignore_orientation'), dict( type='LoadOCRAnnotations', with_bbox=True, with_polygon=True, with_label=True), dict(type='FixInvalidPolygon'), dict(type='RemoveIgnored'), dict( type='TorchVisionWrapper', op='ColorJitter', brightness=0.12549019607843137, saturation=0.5), dict( type='ImgAugWrapper', args=[['Fliplr', 0.5], { 'cls': 'Affine', 'rotate': [-10, 10] }, ['Resize', [0.5, 3.0]]]), dict(type='RandomCrop', min_side_ratio=0.1), dict(type='Resize', scale=(640, 640), keep_ratio=True), dict(type='Pad', size=(640, 640)), dict( type='PackTextDetInputs', meta_keys=('img_path', 'ori_shape', 'img_shape')) ] test_pipeline = [ dict(type='LoadImageFromFile', color_type='color_ignore_orientation'), dict(type='Resize', scale=(4068, 1024), keep_ratio=True), dict( type='LoadOCRAnnotations', with_polygon=True, with_bbox=True, with_label=True), dict( type='PackTextDetInputs', meta_keys=('img_path', 'ori_shape', 'img_shape', 'scale_factor', 'instances')) ] default_scope = 'mmocr' env_cfg = dict( cudnn_benchmark=True, mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0), dist_cfg=dict(backend='nccl')) randomness = dict(seed=None) default_hooks = dict( timer=dict(type='IterTimerHook'), logger=dict(type='LoggerHook', interval=1000), param_scheduler=dict(type='ParamSchedulerHook'), checkpoint=dict( type='CheckpointHook', interval=10000, by_epoch=False, max_keep_ckpts=1), sampler_seed=dict(type='DistSamplerSeedHook'), sync_buffer=dict(type='SyncBuffersHook'), visualization=dict( type='VisualizationHook', interval=1, enable=False, show=False, draw_gt=False, draw_pred=False)) log_level = 'INFO' log_processor = dict(type='LogProcessor', window_size=10, by_epoch=True) load_from = None resume = False val_evaluator = None test_evaluator = None vis_backends = [dict(type='LocalVisBackend')] visualizer = dict( type='TextDetLocalVisualizer', name='visualizer', vis_backends=[dict(type='LocalVisBackend')]) synthtext_textdet_data_root = 'data/synthtext' synthtext_textdet_train = dict( type='OCRDataset', data_root='data/synthtext', ann_file='textdet_train.json', filter_cfg=dict(filter_empty_gt=True, min_size=32), pipeline=[ dict(type='LoadImageFromFile', color_type='color_ignore_orientation'), dict( type='LoadOCRAnnotations', with_bbox=True, with_polygon=True, with_label=True), dict(type='FixInvalidPolygon'), dict(type='RemoveIgnored'), dict( type='TorchVisionWrapper', op='ColorJitter', brightness=0.12549019607843137, saturation=0.5), dict( type='ImgAugWrapper', args=[['Fliplr', 0.5], { 'cls': 'Affine', 'rotate': [-10, 10] }, ['Resize', [0.5, 3.0]]]), dict(type='RandomCrop', min_side_ratio=0.1), dict(type='Resize', scale=(640, 640), keep_ratio=True), dict(type='Pad', size=(640, 640)), dict( type='PackTextDetInputs', meta_keys=('img_path', 'ori_shape', 'img_shape')) ]) optim_wrapper = dict( type='OptimWrapper', optimizer=dict(type='SGD', lr=0.007, momentum=0.9, weight_decay=0.0001)) train_cfg = dict(type='IterBasedTrainLoop', max_iters=100000) test_cfg = None val_cfg = None param_scheduler = [ dict(type='PolyLR', power=0.9, eta_min=1e-07, by_epoch=False, end=100000) ] train_dataloader = dict( batch_size=2, num_workers=8, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=True), dataset=dict( type='OCRDataset', data_root='data/synthtext', ann_file='textdet_train.json', filter_cfg=dict(filter_empty_gt=True, min_size=32), pipeline=[ dict( type='LoadImageFromFile', color_type='color_ignore_orientation'), dict( type='LoadOCRAnnotations', with_bbox=True, with_polygon=True, with_label=True), dict(type='FixInvalidPolygon'), dict(type='RemoveIgnored'), dict( type='TorchVisionWrapper', op='ColorJitter', brightness=0.12549019607843137, saturation=0.5), dict( type='ImgAugWrapper', args=[['Fliplr', 0.5], { 'cls': 'Affine', 'rotate': [-10, 10] }, ['Resize', [0.5, 3.0]]]), dict(type='RandomCrop', min_side_ratio=0.1), dict(type='Resize', scale=(640, 640), keep_ratio=True), dict(type='Pad', size=(640, 640)), dict( type='PackTextDetInputs', meta_keys=('img_path', 'ori_shape', 'img_shape')) ])) auto_scale_lr = dict(base_batch_size=16) launcher = 'pytorch' work_dir = 'work_dirs/db++_r50-dcnv2_synthtext' 2022/12/15 01:35:38 - mmengine - INFO - Result has been saved to /mmocr/work_dirs/db++_r50-dcnv2_synthtext/modules_statistic_results.json 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.conv2.conv_offset.weight - torch.Size([27, 128, 3, 3]): The value is the same before and after calling `init_weights` of DBNet backbone.layer2.0.conv2.conv_offset.bias - torch.Size([27]): The value is the same before and after calling `init_weights` of DBNet 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.conv2.conv_offset.weight - torch.Size([27, 128, 3, 3]): The value is the same before and after calling `init_weights` of DBNet backbone.layer2.1.conv2.conv_offset.bias - torch.Size([27]): The value is the same before and after calling `init_weights` of DBNet 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.conv2.conv_offset.weight - torch.Size([27, 128, 3, 3]): The value is the same before and after calling `init_weights` of DBNet backbone.layer2.2.conv2.conv_offset.bias - torch.Size([27]): The value is the same before and after calling `init_weights` of DBNet 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.conv2.conv_offset.weight - torch.Size([27, 128, 3, 3]): The value is the same before and after calling `init_weights` of DBNet backbone.layer2.3.conv2.conv_offset.bias - torch.Size([27]): The value is the same before and after calling `init_weights` of DBNet 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.conv2.conv_offset.weight - torch.Size([27, 256, 3, 3]): The value is the same before and after calling `init_weights` of DBNet backbone.layer3.0.conv2.conv_offset.bias - torch.Size([27]): The value is the same before and after calling `init_weights` of DBNet 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.conv2.conv_offset.weight - torch.Size([27, 256, 3, 3]): The value is the same before and after calling `init_weights` of DBNet backbone.layer3.1.conv2.conv_offset.bias - torch.Size([27]): The value is the same before and after calling `init_weights` of DBNet 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.conv2.conv_offset.weight - torch.Size([27, 256, 3, 3]): The value is the same before and after calling `init_weights` of DBNet backbone.layer3.2.conv2.conv_offset.bias - torch.Size([27]): The value is the same before and after calling `init_weights` of DBNet 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.conv2.conv_offset.weight - torch.Size([27, 256, 3, 3]): The value is the same before and after calling `init_weights` of DBNet backbone.layer3.3.conv2.conv_offset.bias - torch.Size([27]): The value is the same before and after calling `init_weights` of DBNet 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.conv2.conv_offset.weight - torch.Size([27, 256, 3, 3]): The value is the same before and after calling `init_weights` of DBNet backbone.layer3.4.conv2.conv_offset.bias - torch.Size([27]): The value is the same before and after calling `init_weights` of DBNet 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.conv2.conv_offset.weight - torch.Size([27, 256, 3, 3]): The value is the same before and after calling `init_weights` of DBNet backbone.layer3.5.conv2.conv_offset.bias - torch.Size([27]): The value is the same before and after calling `init_weights` of DBNet 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.conv2.conv_offset.weight - torch.Size([27, 512, 3, 3]): The value is the same before and after calling `init_weights` of DBNet backbone.layer4.0.conv2.conv_offset.bias - torch.Size([27]): The value is the same before and after calling `init_weights` of DBNet 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.conv2.conv_offset.weight - torch.Size([27, 512, 3, 3]): The value is the same before and after calling `init_weights` of DBNet backbone.layer4.1.conv2.conv_offset.bias - torch.Size([27]): The value is the same before and after calling `init_weights` of DBNet 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.conv2.conv_offset.weight - torch.Size([27, 512, 3, 3]): The value is the same before and after calling `init_weights` of DBNet backbone.layer4.2.conv2.conv_offset.bias - torch.Size([27]): The value is the same before and after calling `init_weights` of DBNet 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 neck.lateral_convs.0.conv.weight - torch.Size([256, 256, 1, 1]): Initialized by user-defined `init_weights` in ConvModule neck.lateral_convs.1.conv.weight - torch.Size([256, 512, 1, 1]): Initialized by user-defined `init_weights` in ConvModule neck.lateral_convs.2.conv.weight - torch.Size([256, 1024, 1, 1]): Initialized by user-defined `init_weights` in ConvModule neck.lateral_convs.3.conv.weight - torch.Size([256, 2048, 1, 1]): Initialized by user-defined `init_weights` in ConvModule neck.smooth_convs.0.conv.weight - torch.Size([64, 256, 3, 3]): Initialized by user-defined `init_weights` in ConvModule neck.smooth_convs.1.conv.weight - torch.Size([64, 256, 3, 3]): Initialized by user-defined `init_weights` in ConvModule neck.smooth_convs.2.conv.weight - torch.Size([64, 256, 3, 3]): Initialized by user-defined `init_weights` in ConvModule neck.smooth_convs.3.conv.weight - torch.Size([64, 256, 3, 3]): Initialized by user-defined `init_weights` in ConvModule neck.asf_conv.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined `init_weights` in ConvModule neck.asf_conv.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of DBNet neck.asf_attn.channel_wise.0.conv.weight - torch.Size([64, 256, 1, 1]): Initialized by user-defined `init_weights` in ConvModule neck.asf_attn.channel_wise.1.conv.weight - torch.Size([256, 64, 1, 1]): Initialized by user-defined `init_weights` in ConvModule neck.asf_attn.spatial_wise.0.conv.weight - torch.Size([1, 1, 3, 3]): Initialized by user-defined `init_weights` in ConvModule neck.asf_attn.spatial_wise.1.conv.weight - torch.Size([1, 1, 1, 1]): Initialized by user-defined `init_weights` in ConvModule neck.asf_attn.attention_wise.conv.weight - torch.Size([4, 256, 1, 1]): Initialized by user-defined `init_weights` in ConvModule det_head.binarize.0.weight - torch.Size([64, 256, 3, 3]): The value is the same before and after calling `init_weights` of DBNet det_head.binarize.1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of DBNet det_head.binarize.1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of DBNet det_head.binarize.3.weight - torch.Size([64, 64, 2, 2]): The value is the same before and after calling `init_weights` of DBNet det_head.binarize.3.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of DBNet det_head.binarize.4.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of DBNet det_head.binarize.4.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of DBNet det_head.binarize.6.weight - torch.Size([64, 1, 2, 2]): The value is the same before and after calling `init_weights` of DBNet det_head.binarize.6.bias - torch.Size([1]): The value is the same before and after calling `init_weights` of DBNet det_head.threshold.0.weight - torch.Size([64, 256, 3, 3]): The value is the same before and after calling `init_weights` of DBNet det_head.threshold.1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of DBNet det_head.threshold.1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of DBNet det_head.threshold.3.weight - torch.Size([64, 64, 2, 2]): The value is the same before and after calling `init_weights` of DBNet det_head.threshold.3.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of DBNet det_head.threshold.4.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of DBNet det_head.threshold.4.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of DBNet det_head.threshold.6.weight - torch.Size([64, 1, 2, 2]): The value is the same before and after calling `init_weights` of DBNet det_head.threshold.6.bias - torch.Size([1]): The value is the same before and after calling `init_weights` of DBNet 2022/12/15 01:37:19 - mmengine - INFO - Checkpoints will be saved to /mmocr/work_dirs/db++_r50-dcnv2_synthtext. 2022/12/15 01:41:34 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 01:41:34 - mmengine - INFO - Epoch(train) [1][1000/53672] lr: 6.9370e-03 eta: 7:01:17 time: 0.2460 data_time: 0.0038 memory: 35104 loss: 2.8736 loss_prob: 1.8450 loss_thr: 0.6959 loss_db: 0.3328 2022/12/15 01:45:33 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 01:45:33 - mmengine - INFO - Epoch(train) [1][2000/53672] lr: 6.8739e-03 eta: 6:43:47 time: 0.2324 data_time: 0.0039 memory: 2393 loss: 3.0653 loss_prob: 1.9265 loss_thr: 0.7599 loss_db: 0.3789 2022/12/15 01:49:34 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 01:49:34 - mmengine - INFO - Epoch(train) [1][3000/53672] lr: 6.8108e-03 eta: 6:36:30 time: 0.2416 data_time: 0.0043 memory: 2393 loss: 2.4581 loss_prob: 1.5859 loss_thr: 0.6072 loss_db: 0.2650 2022/12/15 01:53:36 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 01:53:36 - mmengine - INFO - Epoch(train) [1][4000/53672] lr: 6.7476e-03 eta: 6:31:04 time: 0.2435 data_time: 0.0040 memory: 2393 loss: 1.8959 loss_prob: 1.1830 loss_thr: 0.5262 loss_db: 0.1867 2022/12/15 01:57:38 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 01:57:38 - mmengine - INFO - Epoch(train) [1][5000/53672] lr: 6.6843e-03 eta: 6:26:05 time: 0.2412 data_time: 0.0039 memory: 2393 loss: 2.0908 loss_prob: 1.2983 loss_thr: 0.5842 loss_db: 0.2082 2022/12/15 02:01:40 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 02:01:40 - mmengine - INFO - Epoch(train) [1][6000/53672] lr: 6.6209e-03 eta: 6:21:39 time: 0.2365 data_time: 0.0039 memory: 2393 loss: 2.7221 loss_prob: 1.7163 loss_thr: 0.7041 loss_db: 0.3017 2022/12/15 02:05:43 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 02:05:43 - mmengine - INFO - Epoch(train) [1][7000/53672] lr: 6.5575e-03 eta: 6:17:19 time: 0.2498 data_time: 0.0042 memory: 2393 loss: 2.2217 loss_prob: 1.4111 loss_thr: 0.5830 loss_db: 0.2276 2022/12/15 02:09:45 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 02:09:45 - mmengine - INFO - Epoch(train) [1][8000/53672] lr: 6.4940e-03 eta: 6:12:59 time: 0.2682 data_time: 0.0038 memory: 2393 loss: 2.4074 loss_prob: 1.6028 loss_thr: 0.5662 loss_db: 0.2384 2022/12/15 02:13:50 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 02:13:50 - mmengine - INFO - Epoch(train) [1][9000/53672] lr: 6.4304e-03 eta: 6:09:15 time: 0.2557 data_time: 0.0039 memory: 2393 loss: 1.9326 loss_prob: 1.1875 loss_thr: 0.5576 loss_db: 0.1875 2022/12/15 02:17:56 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 02:17:56 - mmengine - INFO - Epoch(train) [1][10000/53672] lr: 6.3668e-03 eta: 6:05:33 time: 0.2486 data_time: 0.0041 memory: 2393 loss: 2.1487 loss_prob: 1.3651 loss_thr: 0.5609 loss_db: 0.2226 2022/12/15 02:17:56 - mmengine - INFO - Saving checkpoint at 10000 iterations 2022/12/15 02:22:01 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 02:22:01 - mmengine - INFO - Epoch(train) [1][11000/53672] lr: 6.3031e-03 eta: 6:01:41 time: 0.2621 data_time: 0.0039 memory: 2393 loss: 2.1116 loss_prob: 1.3541 loss_thr: 0.5297 loss_db: 0.2278 2022/12/15 02:26:03 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 02:26:03 - mmengine - INFO - Epoch(train) [1][12000/53672] lr: 6.2393e-03 eta: 5:57:25 time: 0.3049 data_time: 0.0038 memory: 2393 loss: 1.8150 loss_prob: 1.1350 loss_thr: 0.5018 loss_db: 0.1782 2022/12/15 02:30:08 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 02:30:08 - mmengine - INFO - Epoch(train) [1][13000/53672] lr: 6.1755e-03 eta: 5:53:27 time: 0.2338 data_time: 0.0040 memory: 2393 loss: 2.4105 loss_prob: 1.4913 loss_thr: 0.6437 loss_db: 0.2756 2022/12/15 02:34:12 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 02:34:12 - mmengine - INFO - Epoch(train) [1][14000/53672] lr: 6.1116e-03 eta: 5:49:26 time: 0.2317 data_time: 0.0038 memory: 2393 loss: 2.0389 loss_prob: 1.2528 loss_thr: 0.5747 loss_db: 0.2115 2022/12/15 02:38:13 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 02:38:13 - mmengine - INFO - Epoch(train) [1][15000/53672] lr: 6.0476e-03 eta: 5:45:05 time: 0.2178 data_time: 0.0039 memory: 2393 loss: 1.8292 loss_prob: 1.1690 loss_thr: 0.4889 loss_db: 0.1712 2022/12/15 02:42:16 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 02:42:16 - mmengine - INFO - Epoch(train) [1][16000/53672] lr: 5.9835e-03 eta: 5:40:59 time: 0.2548 data_time: 0.0043 memory: 2393 loss: 1.5672 loss_prob: 0.9692 loss_thr: 0.4497 loss_db: 0.1483 2022/12/15 02:46:21 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 02:46:21 - mmengine - INFO - Epoch(train) [1][17000/53672] lr: 5.9193e-03 eta: 5:37:04 time: 0.2436 data_time: 0.0039 memory: 2393 loss: 1.8083 loss_prob: 1.1281 loss_thr: 0.4990 loss_db: 0.1812 2022/12/15 02:50:24 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 02:50:24 - mmengine - INFO - Epoch(train) [1][18000/53672] lr: 5.8551e-03 eta: 5:32:55 time: 0.2229 data_time: 0.0039 memory: 2393 loss: 1.8520 loss_prob: 1.1681 loss_thr: 0.5145 loss_db: 0.1694 2022/12/15 02:54:27 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 02:54:27 - mmengine - INFO - Epoch(train) [1][19000/53672] lr: 5.7908e-03 eta: 5:28:48 time: 0.2370 data_time: 0.0039 memory: 2393 loss: 2.0693 loss_prob: 1.3107 loss_thr: 0.5352 loss_db: 0.2233 2022/12/15 02:58:28 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 02:58:28 - mmengine - INFO - Epoch(train) [1][20000/53672] lr: 5.7264e-03 eta: 5:24:37 time: 0.2397 data_time: 0.0040 memory: 2393 loss: 1.6874 loss_prob: 1.0615 loss_thr: 0.4655 loss_db: 0.1604 2022/12/15 02:58:28 - mmengine - INFO - Saving checkpoint at 20000 iterations 2022/12/15 03:02:32 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 03:02:32 - mmengine - INFO - Epoch(train) [1][21000/53672] lr: 5.6620e-03 eta: 5:20:35 time: 0.2416 data_time: 0.0045 memory: 2393 loss: 1.7770 loss_prob: 1.0868 loss_thr: 0.5232 loss_db: 0.1670 2022/12/15 03:06:36 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 03:06:36 - mmengine - INFO - Epoch(train) [1][22000/53672] lr: 5.5974e-03 eta: 5:16:31 time: 0.2316 data_time: 0.0038 memory: 2393 loss: 2.1476 loss_prob: 1.3716 loss_thr: 0.5498 loss_db: 0.2262 2022/12/15 03:10:38 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 03:10:38 - mmengine - INFO - Epoch(train) [1][23000/53672] lr: 5.5328e-03 eta: 5:12:22 time: 0.2196 data_time: 0.0042 memory: 2393 loss: 2.0022 loss_prob: 1.2476 loss_thr: 0.5399 loss_db: 0.2147 2022/12/15 03:14:40 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 03:14:40 - mmengine - INFO - Epoch(train) [1][24000/53672] lr: 5.4681e-03 eta: 5:08:13 time: 0.2388 data_time: 0.0038 memory: 2393 loss: 2.5602 loss_prob: 1.7077 loss_thr: 0.5708 loss_db: 0.2817 2022/12/15 03:18:44 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 03:18:44 - mmengine - INFO - Epoch(train) [1][25000/53672] lr: 5.4033e-03 eta: 5:04:13 time: 0.2477 data_time: 0.0039 memory: 2393 loss: 1.8299 loss_prob: 1.1287 loss_thr: 0.5181 loss_db: 0.1831 2022/12/15 03:22:51 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 03:22:51 - mmengine - INFO - Epoch(train) [1][26000/53672] lr: 5.3384e-03 eta: 5:00:20 time: 0.2316 data_time: 0.0040 memory: 2393 loss: 2.1736 loss_prob: 1.3535 loss_thr: 0.5808 loss_db: 0.2393 2022/12/15 03:26:55 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 03:26:55 - mmengine - INFO - Epoch(train) [1][27000/53672] lr: 5.2734e-03 eta: 4:56:17 time: 0.2752 data_time: 0.0040 memory: 2393 loss: 2.3249 loss_prob: 1.5035 loss_thr: 0.5862 loss_db: 0.2353 2022/12/15 03:30:57 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 03:30:57 - mmengine - INFO - Epoch(train) [1][28000/53672] lr: 5.2084e-03 eta: 4:52:09 time: 0.2523 data_time: 0.0039 memory: 2393 loss: 1.3764 loss_prob: 0.8232 loss_thr: 0.4220 loss_db: 0.1312 2022/12/15 03:34:58 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 03:34:58 - mmengine - INFO - Epoch(train) [1][29000/53672] lr: 5.1432e-03 eta: 4:48:01 time: 0.2168 data_time: 0.0039 memory: 2393 loss: 1.3822 loss_prob: 0.8458 loss_thr: 0.4048 loss_db: 0.1316 2022/12/15 03:39:00 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 03:39:00 - mmengine - INFO - Epoch(train) [1][30000/53672] lr: 5.0780e-03 eta: 4:43:54 time: 0.2269 data_time: 0.0039 memory: 2393 loss: 1.3493 loss_prob: 0.7962 loss_thr: 0.4220 loss_db: 0.1310 2022/12/15 03:39:00 - mmengine - INFO - Saving checkpoint at 30000 iterations 2022/12/15 03:43:05 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 03:43:05 - mmengine - INFO - Epoch(train) [1][31000/53672] lr: 5.0127e-03 eta: 4:39:54 time: 0.2395 data_time: 0.0040 memory: 2393 loss: 1.8562 loss_prob: 1.1988 loss_thr: 0.4802 loss_db: 0.1772 2022/12/15 03:47:08 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 03:47:08 - mmengine - INFO - Epoch(train) [1][32000/53672] lr: 4.9472e-03 eta: 4:35:50 time: 0.2417 data_time: 0.0047 memory: 2393 loss: 1.4548 loss_prob: 0.8865 loss_thr: 0.4256 loss_db: 0.1427 2022/12/15 03:51:12 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 03:51:12 - mmengine - INFO - Epoch(train) [1][33000/53672] lr: 4.8817e-03 eta: 4:31:47 time: 0.2408 data_time: 0.0040 memory: 2393 loss: 1.4802 loss_prob: 0.9047 loss_thr: 0.4338 loss_db: 0.1416 2022/12/15 03:55:18 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 03:55:18 - mmengine - INFO - Epoch(train) [1][34000/53672] lr: 4.8161e-03 eta: 4:27:49 time: 0.2225 data_time: 0.0038 memory: 2393 loss: 1.8202 loss_prob: 1.1054 loss_thr: 0.4972 loss_db: 0.2175 2022/12/15 03:59:24 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 03:59:24 - mmengine - INFO - Epoch(train) [1][35000/53672] lr: 4.7504e-03 eta: 4:23:50 time: 0.2292 data_time: 0.0039 memory: 2393 loss: 1.5400 loss_prob: 0.9305 loss_thr: 0.4575 loss_db: 0.1519 2022/12/15 04:03:27 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 04:03:27 - mmengine - INFO - Epoch(train) [1][36000/53672] lr: 4.6845e-03 eta: 4:19:46 time: 0.2349 data_time: 0.0040 memory: 2393 loss: 1.1261 loss_prob: 0.6424 loss_thr: 0.3791 loss_db: 0.1046 2022/12/15 04:07:30 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 04:07:30 - mmengine - INFO - Epoch(train) [1][37000/53672] lr: 4.6186e-03 eta: 4:15:40 time: 0.2607 data_time: 0.0040 memory: 2393 loss: 1.7604 loss_prob: 1.1010 loss_thr: 0.4881 loss_db: 0.1713 2022/12/15 04:11:34 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 04:11:34 - mmengine - INFO - Epoch(train) [1][38000/53672] lr: 4.5526e-03 eta: 4:11:38 time: 0.2309 data_time: 0.0040 memory: 2393 loss: 2.3829 loss_prob: 1.5486 loss_thr: 0.5810 loss_db: 0.2533 2022/12/15 04:15:38 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 04:15:38 - mmengine - INFO - Epoch(train) [1][39000/53672] lr: 4.4864e-03 eta: 4:07:34 time: 0.2246 data_time: 0.0038 memory: 2393 loss: 1.3731 loss_prob: 0.8160 loss_thr: 0.4219 loss_db: 0.1353 2022/12/15 04:19:40 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 04:19:40 - mmengine - INFO - Epoch(train) [1][40000/53672] lr: 4.4202e-03 eta: 4:03:29 time: 0.2438 data_time: 0.0040 memory: 2393 loss: 1.9389 loss_prob: 1.2063 loss_thr: 0.5351 loss_db: 0.1975 2022/12/15 04:19:40 - mmengine - INFO - Saving checkpoint at 40000 iterations 2022/12/15 04:23:45 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 04:23:45 - mmengine - INFO - Epoch(train) [1][41000/53672] lr: 4.3538e-03 eta: 3:59:28 time: 0.2694 data_time: 0.0044 memory: 2393 loss: 1.2843 loss_prob: 0.7477 loss_thr: 0.4180 loss_db: 0.1186 2022/12/15 04:27:51 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 04:27:51 - mmengine - INFO - Epoch(train) [1][42000/53672] lr: 4.2874e-03 eta: 3:55:27 time: 0.2612 data_time: 0.0039 memory: 2393 loss: 1.8878 loss_prob: 1.2244 loss_thr: 0.4797 loss_db: 0.1837 2022/12/15 04:31:52 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 04:31:52 - mmengine - INFO - Epoch(train) [1][43000/53672] lr: 4.2208e-03 eta: 3:51:20 time: 0.2177 data_time: 0.0043 memory: 2393 loss: 1.4787 loss_prob: 0.8843 loss_thr: 0.4498 loss_db: 0.1446 2022/12/15 04:35:54 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 04:35:54 - mmengine - INFO - Epoch(train) [1][44000/53672] lr: 4.1541e-03 eta: 3:47:14 time: 0.2446 data_time: 0.0041 memory: 2393 loss: 1.8100 loss_prob: 1.1160 loss_thr: 0.5101 loss_db: 0.1839 2022/12/15 04:40:01 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 04:40:01 - mmengine - INFO - Epoch(train) [1][45000/53672] lr: 4.0873e-03 eta: 3:43:15 time: 0.2389 data_time: 0.0044 memory: 2393 loss: 1.1345 loss_prob: 0.6687 loss_thr: 0.3594 loss_db: 0.1064 2022/12/15 04:44:06 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 04:44:06 - mmengine - INFO - Epoch(train) [1][46000/53672] lr: 4.0203e-03 eta: 3:39:13 time: 0.2254 data_time: 0.0039 memory: 2393 loss: 1.5968 loss_prob: 0.9656 loss_thr: 0.4762 loss_db: 0.1550 2022/12/15 04:48:08 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 04:48:08 - mmengine - INFO - Epoch(train) [1][47000/53672] lr: 3.9533e-03 eta: 3:35:07 time: 0.2224 data_time: 0.0042 memory: 2393 loss: 2.1915 loss_prob: 1.6059 loss_thr: 0.3984 loss_db: 0.1871 2022/12/15 04:52:09 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 04:52:09 - mmengine - INFO - Epoch(train) [1][48000/53672] lr: 3.8861e-03 eta: 3:31:01 time: 0.2461 data_time: 0.0039 memory: 2393 loss: 1.8029 loss_prob: 1.1335 loss_thr: 0.4727 loss_db: 0.1966 2022/12/15 04:56:18 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 04:56:18 - mmengine - INFO - Epoch(train) [1][49000/53672] lr: 3.8187e-03 eta: 3:27:03 time: 0.2633 data_time: 0.0045 memory: 2393 loss: 1.4156 loss_prob: 0.8534 loss_thr: 0.4250 loss_db: 0.1373 2022/12/15 05:00:21 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 05:00:21 - mmengine - INFO - Epoch(train) [1][50000/53672] lr: 3.7513e-03 eta: 3:22:59 time: 0.2358 data_time: 0.0039 memory: 2393 loss: 1.3766 loss_prob: 0.8058 loss_thr: 0.4373 loss_db: 0.1335 2022/12/15 05:00:21 - mmengine - INFO - Saving checkpoint at 50000 iterations 2022/12/15 05:04:30 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 05:04:30 - mmengine - INFO - Epoch(train) [1][51000/53672] lr: 3.6837e-03 eta: 3:19:00 time: 0.2277 data_time: 0.0040 memory: 2393 loss: 1.7356 loss_prob: 1.0877 loss_thr: 0.4788 loss_db: 0.1691 2022/12/15 05:08:32 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 05:08:32 - mmengine - INFO - Epoch(train) [1][52000/53672] lr: 3.6160e-03 eta: 3:14:55 time: 0.2697 data_time: 0.0039 memory: 2393 loss: 1.5395 loss_prob: 0.9352 loss_thr: 0.4552 loss_db: 0.1492 2022/12/15 05:12:37 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 05:12:37 - mmengine - INFO - Epoch(train) [1][53000/53672] lr: 3.5481e-03 eta: 3:10:53 time: 0.2430 data_time: 0.0042 memory: 2393 loss: 1.2473 loss_prob: 0.7185 loss_thr: 0.4093 loss_db: 0.1195 2022/12/15 05:15:23 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 05:16:45 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 05:16:45 - mmengine - INFO - Epoch(train) [1][54000/53672] lr: 3.4801e-03 eta: 3:06:52 time: 0.2697 data_time: 0.0042 memory: 2393 loss: 1.4158 loss_prob: 0.8713 loss_thr: 0.4057 loss_db: 0.1387 2022/12/15 05:20:48 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 05:20:48 - mmengine - INFO - Epoch(train) [1][55000/53672] lr: 3.4119e-03 eta: 3:02:48 time: 0.2260 data_time: 0.0040 memory: 2393 loss: 1.6951 loss_prob: 1.1218 loss_thr: 0.4027 loss_db: 0.1706 2022/12/15 05:24:49 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 05:24:49 - mmengine - INFO - Epoch(train) [1][56000/53672] lr: 3.3436e-03 eta: 2:58:42 time: 0.2800 data_time: 0.0044 memory: 2393 loss: 1.4367 loss_prob: 0.8690 loss_thr: 0.4263 loss_db: 0.1415 2022/12/15 05:28:50 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 05:28:50 - mmengine - INFO - Epoch(train) [1][57000/53672] lr: 3.2751e-03 eta: 2:54:36 time: 0.2528 data_time: 0.0041 memory: 2393 loss: 1.6703 loss_prob: 1.0343 loss_thr: 0.4689 loss_db: 0.1671 2022/12/15 05:32:51 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 05:32:51 - mmengine - INFO - Epoch(train) [1][58000/53672] lr: 3.2065e-03 eta: 2:50:31 time: 0.2399 data_time: 0.0039 memory: 2393 loss: 1.7667 loss_prob: 1.1077 loss_thr: 0.4735 loss_db: 0.1855 2022/12/15 05:36:51 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 05:36:51 - mmengine - INFO - Epoch(train) [1][59000/53672] lr: 3.1377e-03 eta: 2:46:25 time: 0.2496 data_time: 0.0041 memory: 2393 loss: 1.2616 loss_prob: 0.7661 loss_thr: 0.3780 loss_db: 0.1175 2022/12/15 05:40:54 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 05:40:54 - mmengine - INFO - Epoch(train) [1][60000/53672] lr: 3.0688e-03 eta: 2:42:21 time: 0.2100 data_time: 0.0040 memory: 2393 loss: 1.0599 loss_prob: 0.6266 loss_thr: 0.3386 loss_db: 0.0947 2022/12/15 05:40:54 - mmengine - INFO - Saving checkpoint at 60000 iterations 2022/12/15 05:45:02 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 05:45:02 - mmengine - INFO - Epoch(train) [1][61000/53672] lr: 2.9996e-03 eta: 2:38:20 time: 0.2271 data_time: 0.0039 memory: 2393 loss: 1.8862 loss_prob: 1.1785 loss_thr: 0.5149 loss_db: 0.1928 2022/12/15 05:49:04 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 05:49:04 - mmengine - INFO - Epoch(train) [1][62000/53672] lr: 2.9303e-03 eta: 2:34:15 time: 0.2344 data_time: 0.0040 memory: 2393 loss: 1.0094 loss_prob: 0.5737 loss_thr: 0.3395 loss_db: 0.0961 2022/12/15 05:53:05 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 05:53:05 - mmengine - INFO - Epoch(train) [1][63000/53672] lr: 2.8608e-03 eta: 2:30:10 time: 0.2280 data_time: 0.0041 memory: 2393 loss: 1.4655 loss_prob: 0.8944 loss_thr: 0.4251 loss_db: 0.1461 2022/12/15 05:57:10 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 05:57:10 - mmengine - INFO - Epoch(train) [1][64000/53672] lr: 2.7912e-03 eta: 2:26:07 time: 0.2192 data_time: 0.0042 memory: 2393 loss: 1.8452 loss_prob: 1.2184 loss_thr: 0.4435 loss_db: 0.1833 2022/12/15 06:01:11 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 06:01:11 - mmengine - INFO - Epoch(train) [1][65000/53672] lr: 2.7213e-03 eta: 2:22:02 time: 0.2310 data_time: 0.0045 memory: 2393 loss: 1.5359 loss_prob: 0.9820 loss_thr: 0.4174 loss_db: 0.1365 2022/12/15 06:05:17 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 06:05:17 - mmengine - INFO - Epoch(train) [1][66000/53672] lr: 2.6512e-03 eta: 2:18:00 time: 0.2598 data_time: 0.0045 memory: 2393 loss: 1.2374 loss_prob: 0.7436 loss_thr: 0.3801 loss_db: 0.1136 2022/12/15 06:09:22 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 06:09:22 - mmengine - INFO - Epoch(train) [1][67000/53672] lr: 2.5809e-03 eta: 2:13:57 time: 0.2413 data_time: 0.0040 memory: 2393 loss: 1.2205 loss_prob: 0.7163 loss_thr: 0.3844 loss_db: 0.1198 2022/12/15 06:13:24 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 06:13:24 - mmengine - INFO - Epoch(train) [1][68000/53672] lr: 2.5104e-03 eta: 2:09:53 time: 0.2392 data_time: 0.0040 memory: 2393 loss: 1.7170 loss_prob: 1.0766 loss_thr: 0.4750 loss_db: 0.1654 2022/12/15 06:17:29 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 06:17:29 - mmengine - INFO - Epoch(train) [1][69000/53672] lr: 2.4397e-03 eta: 2:05:50 time: 0.2301 data_time: 0.0039 memory: 2393 loss: 1.6347 loss_prob: 1.0183 loss_thr: 0.4506 loss_db: 0.1658 2022/12/15 06:21:33 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 06:21:33 - mmengine - INFO - Epoch(train) [1][70000/53672] lr: 2.3688e-03 eta: 2:01:46 time: 0.2854 data_time: 0.0041 memory: 2393 loss: 1.2372 loss_prob: 0.7508 loss_thr: 0.3656 loss_db: 0.1208 2022/12/15 06:21:33 - mmengine - INFO - Saving checkpoint at 70000 iterations 2022/12/15 06:25:43 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 06:25:43 - mmengine - INFO - Epoch(train) [1][71000/53672] lr: 2.2976e-03 eta: 1:57:45 time: 0.2229 data_time: 0.0041 memory: 2393 loss: 1.5287 loss_prob: 0.9286 loss_thr: 0.4517 loss_db: 0.1485 2022/12/15 06:29:46 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 06:29:46 - mmengine - INFO - Epoch(train) [1][72000/53672] lr: 2.2262e-03 eta: 1:53:41 time: 0.2281 data_time: 0.0040 memory: 2393 loss: 1.1898 loss_prob: 0.7071 loss_thr: 0.3735 loss_db: 0.1092 2022/12/15 06:33:49 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 06:33:49 - mmengine - INFO - Epoch(train) [1][73000/53672] lr: 2.1545e-03 eta: 1:49:37 time: 0.2516 data_time: 0.0041 memory: 2393 loss: 1.6274 loss_prob: 1.0008 loss_thr: 0.4695 loss_db: 0.1571 2022/12/15 06:37:51 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 06:37:51 - mmengine - INFO - Epoch(train) [1][74000/53672] lr: 2.0825e-03 eta: 1:45:33 time: 0.2466 data_time: 0.0040 memory: 2393 loss: 1.3693 loss_prob: 0.8136 loss_thr: 0.4280 loss_db: 0.1277 2022/12/15 06:41:55 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 06:41:55 - mmengine - INFO - Epoch(train) [1][75000/53672] lr: 2.0103e-03 eta: 1:41:30 time: 0.2407 data_time: 0.0040 memory: 2393 loss: 1.2288 loss_prob: 0.7387 loss_thr: 0.3726 loss_db: 0.1176 2022/12/15 06:46:01 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 06:46:01 - mmengine - INFO - Epoch(train) [1][76000/53672] lr: 1.9378e-03 eta: 1:37:27 time: 0.2485 data_time: 0.0041 memory: 2393 loss: 1.1850 loss_prob: 0.6835 loss_thr: 0.3883 loss_db: 0.1132 2022/12/15 06:50:03 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 06:50:03 - mmengine - INFO - Epoch(train) [1][77000/53672] lr: 1.8650e-03 eta: 1:33:23 time: 0.2200 data_time: 0.0039 memory: 2393 loss: 1.1173 loss_prob: 0.6529 loss_thr: 0.3519 loss_db: 0.1126 2022/12/15 06:54:08 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 06:54:08 - mmengine - INFO - Epoch(train) [1][78000/53672] lr: 1.7918e-03 eta: 1:29:19 time: 0.2384 data_time: 0.0041 memory: 2393 loss: 1.1649 loss_prob: 0.6805 loss_thr: 0.3783 loss_db: 0.1061 2022/12/15 06:58:11 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 06:58:11 - mmengine - INFO - Epoch(train) [1][79000/53672] lr: 1.7184e-03 eta: 1:25:15 time: 0.2264 data_time: 0.0040 memory: 2393 loss: 1.2355 loss_prob: 0.7479 loss_thr: 0.3715 loss_db: 0.1161 2022/12/15 07:02:12 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 07:02:12 - mmengine - INFO - Epoch(train) [1][80000/53672] lr: 1.6446e-03 eta: 1:21:11 time: 0.2454 data_time: 0.0040 memory: 2393 loss: 1.4499 loss_prob: 0.9072 loss_thr: 0.4027 loss_db: 0.1400 2022/12/15 07:02:12 - mmengine - INFO - Saving checkpoint at 80000 iterations 2022/12/15 07:06:15 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 07:06:15 - mmengine - INFO - Epoch(train) [1][81000/53672] lr: 1.5704e-03 eta: 1:17:07 time: 0.2647 data_time: 0.0041 memory: 2393 loss: 1.2503 loss_prob: 0.7335 loss_thr: 0.3948 loss_db: 0.1220 2022/12/15 07:10:15 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 07:10:15 - mmengine - INFO - Epoch(train) [1][82000/53672] lr: 1.4958e-03 eta: 1:13:03 time: 0.2122 data_time: 0.0040 memory: 2393 loss: 1.6723 loss_prob: 1.0512 loss_thr: 0.4548 loss_db: 0.1663 2022/12/15 07:14:16 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 07:14:16 - mmengine - INFO - Epoch(train) [1][83000/53672] lr: 1.4208e-03 eta: 1:08:59 time: 0.2479 data_time: 0.0048 memory: 2393 loss: 1.0851 loss_prob: 0.6178 loss_thr: 0.3640 loss_db: 0.1033 2022/12/15 07:18:18 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 07:18:18 - mmengine - INFO - Epoch(train) [1][84000/53672] lr: 1.3454e-03 eta: 1:04:55 time: 0.2306 data_time: 0.0042 memory: 2393 loss: 1.3826 loss_prob: 0.8241 loss_thr: 0.4299 loss_db: 0.1286 2022/12/15 07:22:21 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 07:22:21 - mmengine - INFO - Epoch(train) [1][85000/53672] lr: 1.2694e-03 eta: 1:00:52 time: 0.2325 data_time: 0.0040 memory: 2393 loss: 1.2097 loss_prob: 0.7186 loss_thr: 0.3728 loss_db: 0.1184 2022/12/15 07:26:25 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 07:26:25 - mmengine - INFO - Epoch(train) [1][86000/53672] lr: 1.1930e-03 eta: 0:56:48 time: 0.2487 data_time: 0.0040 memory: 2393 loss: 1.2147 loss_prob: 0.7018 loss_thr: 0.3978 loss_db: 0.1150 2022/12/15 07:30:30 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 07:30:30 - mmengine - INFO - Epoch(train) [1][87000/53672] lr: 1.1161e-03 eta: 0:52:45 time: 0.2829 data_time: 0.0040 memory: 2393 loss: 1.0807 loss_prob: 0.6249 loss_thr: 0.3536 loss_db: 0.1021 2022/12/15 07:34:35 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 07:34:35 - mmengine - INFO - Epoch(train) [1][88000/53672] lr: 1.0385e-03 eta: 0:48:42 time: 0.2768 data_time: 0.0042 memory: 2393 loss: 1.3430 loss_prob: 0.8003 loss_thr: 0.4105 loss_db: 0.1321 2022/12/15 07:38:41 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 07:38:41 - mmengine - INFO - Epoch(train) [1][89000/53672] lr: 9.6027e-04 eta: 0:44:38 time: 0.2492 data_time: 0.0041 memory: 2393 loss: 1.1174 loss_prob: 0.6613 loss_thr: 0.3493 loss_db: 0.1068 2022/12/15 07:42:48 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 07:42:48 - mmengine - INFO - Epoch(train) [1][90000/53672] lr: 8.8134e-04 eta: 0:40:35 time: 0.2447 data_time: 0.0041 memory: 2393 loss: 1.3885 loss_prob: 0.8425 loss_thr: 0.4168 loss_db: 0.1293 2022/12/15 07:42:48 - mmengine - INFO - Saving checkpoint at 90000 iterations 2022/12/15 07:46:56 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 07:46:56 - mmengine - INFO - Epoch(train) [1][91000/53672] lr: 8.0162e-04 eta: 0:36:32 time: 0.2637 data_time: 0.0042 memory: 2393 loss: 1.2413 loss_prob: 0.7680 loss_thr: 0.3527 loss_db: 0.1206 2022/12/15 07:51:00 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 07:51:00 - mmengine - INFO - Epoch(train) [1][92000/53672] lr: 7.2100e-04 eta: 0:32:28 time: 0.2388 data_time: 0.0045 memory: 2393 loss: 1.3785 loss_prob: 0.8146 loss_thr: 0.4339 loss_db: 0.1300 2022/12/15 07:55:03 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 07:55:03 - mmengine - INFO - Epoch(train) [1][93000/53672] lr: 6.3937e-04 eta: 0:28:25 time: 0.2432 data_time: 0.0041 memory: 2393 loss: 1.3047 loss_prob: 0.7762 loss_thr: 0.3986 loss_db: 0.1299 2022/12/15 07:59:04 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 07:59:04 - mmengine - INFO - Epoch(train) [1][94000/53672] lr: 5.5656e-04 eta: 0:24:21 time: 0.2757 data_time: 0.0042 memory: 2393 loss: 1.3602 loss_prob: 0.8270 loss_thr: 0.4037 loss_db: 0.1294 2022/12/15 08:03:08 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 08:03:08 - mmengine - INFO - Epoch(train) [1][95000/53672] lr: 4.7235e-04 eta: 0:20:17 time: 0.2425 data_time: 0.0044 memory: 2393 loss: 1.2103 loss_prob: 0.7108 loss_thr: 0.3838 loss_db: 0.1157 2022/12/15 08:07:12 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 08:07:12 - mmengine - INFO - Epoch(train) [1][96000/53672] lr: 3.8642e-04 eta: 0:16:14 time: 0.2037 data_time: 0.0041 memory: 2393 loss: 1.1195 loss_prob: 0.6658 loss_thr: 0.3501 loss_db: 0.1036 2022/12/15 08:11:14 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 08:11:14 - mmengine - INFO - Epoch(train) [1][97000/53672] lr: 2.9830e-04 eta: 0:12:10 time: 0.2256 data_time: 0.0044 memory: 2393 loss: 1.7193 loss_prob: 1.0686 loss_thr: 0.4850 loss_db: 0.1657 2022/12/15 08:15:22 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 08:15:22 - mmengine - INFO - Epoch(train) [1][98000/53672] lr: 2.0712e-04 eta: 0:08:07 time: 0.2178 data_time: 0.0042 memory: 2393 loss: 1.1945 loss_prob: 0.6897 loss_thr: 0.3877 loss_db: 0.1171 2022/12/15 08:19:28 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 08:19:28 - mmengine - INFO - Epoch(train) [1][99000/53672] lr: 1.1104e-04 eta: 0:04:03 time: 0.2626 data_time: 0.0041 memory: 2393 loss: 1.2967 loss_prob: 0.7725 loss_thr: 0.4004 loss_db: 0.1238 2022/12/15 08:23:31 - mmengine - INFO - Exp name: dbnetpp_resnet50-dcnv2_fpnc_100k_synthtext_20221215_013531 2022/12/15 08:23:31 - mmengine - INFO - Epoch(train) [1][100000/53672] lr: 1.0000e-07 eta: 0:00:00 time: 0.2416 data_time: 0.0042 memory: 2393 loss: 1.2071 loss_prob: 0.7030 loss_thr: 0.3891 loss_db: 0.1150 2022/12/15 08:23:31 - mmengine - INFO - Saving checkpoint at 100000 iterations