使用默认模型识别图片没问题，修改训练模型后报错如下：

[root@nwpuWeiXin PaddleOCR-develop]# export PYTHONPATH=. && python3 tools/train.py -c configs/det/det_mv3_db.yml
2021-01-26 11:07:50,231-INFO: {'Optimizer': {'base_lr': 0.001, 'beta2': 0.999, 'function': 'ppocr.optimizer,AdamDecay', 'beta1': 0.9}, 'PostProcess': {'max_candidates': 1000, 'box_thresh': 0.6, 'thresh': 0.3, 'unclip_ratio': 1.5, 'function': 'ppocr.postprocess.db_postprocess,DBPostProcess'}, 'Global': {'save_epoch_step': 200, 'save_model_dir': './output/det_db/', 'debug': False, 'save_res_path': './output/det_db/predicts_db.txt', 'pretrain_weights': './pretrain_models/MobileNetV3_large_x0_5_pretrained/', 'infer_img': None, 'log_smooth_window': 20, 'test_batch_size_per_card': 16, 'train_batch_size_per_card': 16, 'image_shape': [3, 640, 640], 'use_gpu': False, 'algorithm': 'DB', 'reader_yml': './configs/det/det_db_icdar15_reader.yml', 'epoch_num': 1200, 'save_inference_dir': None, 'print_batch_step': 2, 'eval_batch_step': [4000, 5000], 'checkpoints': None}, 'Loss': {'ohem_ratio': 3, 'alpha': 5, 'function': 'ppocr.modeling.losses.det_db_loss,DBLoss', 'main_loss_type': 'DiceLoss', 'beta': 10, 'balance_loss': True}, 'TrainReader': {'process_function': 'ppocr.data.det.db_process,DBProcessTrain', 'num_workers': 8, 'reader_function': 'ppocr.data.det.dataset_traversal,TrainReader', 'label_file_path': './train_data/icdar2015/text_localization/train_icdar2015_label.txt', 'img_set_dir': './train_data/icdar2015/text_localization/'}, 'Architecture': {'function': 'ppocr.modeling.architectures.det_model,DetModel'}, 'Head': {'out_channels': 2, 'inner_channels': 96, 'k': 50, 'function': 'ppocr.modeling.heads.det_db_head,DBHead', 'model_name': 'large'}, 'TestReader': {'process_function': 'ppocr.data.det.db_process,DBProcessTest', 'reader_function': 'ppocr.data.det.dataset_traversal,EvalTestReader', 'do_eval': True, 'label_file_path': './train_data/icdar2015/text_localization/test_icdar2015_label.txt', 'img_set_dir': './train_data/icdar2015/text_localization/'}, 'Backbone': {'scale': 0.5, 'function': 'ppocr.modeling.backbones.det_mobilenet_v3,MobileNetV3', 'model_name': 'large'}, 'EvalReader': {'process_function': 'ppocr.data.det.db_process,DBProcessTest', 'reader_function': 'ppocr.data.det.dataset_traversal,EvalTestReader', 'test_image_shape': [736, 1280], 'label_file_path': './train_data/icdar2015/text_localization/test_icdar2015_label.txt', 'img_set_dir': './train_data/icdar2015/text_localization/'}}
3 640 640
2021-01-26 11:07:51,319-INFO: If regularizer of a Parameter has been set by 'fluid.ParamAttr' or 'fluid.WeightNormParamAttr' already. The Regularization[L2Decay, regularization_coeff=0.000000] in Optimizer will not take effect, and it will only be applied to other Parameters!
3 640 640
./train_data/icdar2015/text_localization/train_icdar2015_label.txt
2021-01-26 11:07:54,596-INFO: places would be ommited when DataLoader is not iterable
Traceback (most recent call last):
File "tools/train.py", line 135, in
main()
File "tools/train.py", line 72, in main
eval_reader = reader_main(config=config, mode="eval")
File "/home/paddle/PaddleOCR-develop/ppocr/data/reader_main.py", line 77, in reader_main
return function(mode)
File "/home/paddle/PaddleOCR-develop/ppocr/data/det/dataset_traversal.py", line 139, in __call__
with open(img_name_list_path, "rb") as fin:
FileNotFoundError: [Errno 2] No such file or directory: './train_data/icdar2015/text_localization/test_icdar2015_label.txt'