Created by: JawerZ

2020-08-03 12:21:39,396-INFO: {'Global': {'debug': False, 'algorithm': 'EAST', 'use_gpu': False, 'epoch_num': 100000, 'log_smooth_window': 20, 'print_batch_step': 5, 'save_model_dir': './output/det_east/', 'save_epoch_step': 10000, 'ev al_batch_step': [5000, 5000], 'train_batch_size_per_card': 8, 'test_batch_size_per_card': 116, 'image_shape': [3, 512, 512], 'reader_yml': './configs/det/det_east_icdar15_reader.yml', 'pretrain_weights': './pretrain_models/ResNet50_vd_ ssld_pretrained/', 'save_res_path': './output/det_east/predicts_east.txt', 'checkpoints': './output/det_EAST/best_accuracy', 'save_inference_dir': None, 'use_space_char': True}, 'Architecture': {'function': 'ppocr.modeling.architecture s.det_model,DetModel'}, 'Backbone': {'function': 'ppocr.modeling.backbones.det_resnet_vd,ResNet', 'layers': 50}, 'Head': {'function': 'ppocr.modeling.heads.det_east_head,EASTHead', 'model_name': 'large'}, 'Loss': {'function': 'ppocr.mo deling.losses.det_east_loss,EASTLoss'}, 'Optimizer': {'function': 'ppocr.optimizer,AdamDecay', 'base_lr': 0.0001, 'beta1': 0.9, 'beta2': 0.999}, 'PostProcess': {'function': 'ppocr.postprocess.east_postprocess,EASTPostPocess', 'score_th resh': 0.8, 'cover_thresh': 0.1, 'nms_thresh': 0.2}, 'TrainReader': {'reader_function': 'ppocr.data.det.dataset_traversal,TrainReader', 'process_function': 'ppocr.data.det.east_process,EASTProcessTrain', 'num_workers': 1, 'img_set_dir' : './train_data/train/', 'label_file_path': './train_data/train_det_label.txt', 'background_ratio': 0.125, 'min_crop_side_ratio': 0.1, 'min_text_size': 1}, 'EvalReader': {'reader_function': 'ppocr.data.det.dataset_traversal,EvalTestRea der', 'process_function': 'ppocr.data.det.east_process,EASTProcessTest', 'img_set_dir': './train_data/test/', 'label_file_path': './train_data/test_det_label.txt'}, 'TestReader': {'reader_function': 'ppocr.data.det.dataset_traversal,Ev alTestReader', 'process_function': 'ppocr.data.det.east_process,EASTProcessTest', 'infer_img': None, 'img_set_dir': './train_data/test/', 'label_file_path': './train_data/test_det_label.txt', 'do_eval': True}} 2020-08-03 12:21:41,645-INFO: places would be ommited when DataLoader is not iterable 2020-08-03 12:21:44,960-INFO: Finish initing model from ./output/det_EAST/best_accuracy 2020-08-03 12:21:44,960-INFO: During the training process, after the 5000th iteration, an evaluation is run every 5000 iterations W0803 12:21:45.811342 1876 build_strategy.cc:170] fusion_group is not enabled for Windows/MacOS now, and only effective when running with CUDA GPU. W0803 12:21:46.173436 1876 fuse_all_reduce_op_pass.cc:74] Find all_reduce operators: 198. To make the speed faster, some all_reduce ops are fused during training, after fusion, the number of all_reduce ops is 198. 2020-08-03 12:45:34,097-INFO: Already save model in ./output/det_east//iter_epoch_10000 2020-08-03 13:04:33,037-INFO: Already save model in ./output/det_east//iter_epoch_20000 2020-08-03 13:23:33,422-INFO: Already save model in ./output/det_east//iter_epoch_30000 2020-08-03 13:42:35,780-INFO: Already save model in ./output/det_east//iter_epoch_40000 2020-08-03 14:01:48,962-INFO: Already save model in ./output/det_east//iter_epoch_50000 只保存了model 但是model进行测试无法检测到文本