PaddleOCR icon indicating copy to clipboard operation
PaddleOCR copied to clipboard

文本识别训练过程中出现list index out of range问题

Open phb-shiyige-fw opened this issue 1 year ago • 3 comments

请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem

  • 系统环境/System Environment:win10
  • 版本号/Version:Paddle:2.3.2 PaddleOCR:2.6 问题相关组件/Related components:rec-PPOCRv3
  • 运行指令/Command Code:train.py
  • 完整报错/Complete Error Message: [2023/12/09 20:45:37] ppocr ERROR: When parsing line crop_img/table246_crop_11.jpg 6.车辆识别代号/车架号LHGCV1676P9038532 , error happened with msg: Traceback (most recent call last): File "D:\PaddleOCR-release-2.7\ppocr\data\simple_dataset.py", line 158, in getitem data['ext_data'] = self.get_ext_data() File "D:\PaddleOCR-release-2.7\ppocr\data\simple_dataset.py", line 124, in get_ext_data label = substr[1] IndexError: list index out of range 进行模型微调的训练过程中,总是会出现如上述所示的错误,好像是显示训练数据有问题,但是不知道问题在哪里?不知道如何解决。 求各位大佬帮忙分析一下是什么原因导致。感激不尽!!!!@haobibo @WenmuZhou @ZeyuChen @bingooo

phb-shiyige-fw avatar Dec 09 '23 12:12 phb-shiyige-fw