search

PaddlePaddle / PaddleOCR

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)
https://paddlepaddle.github.io/PaddleOCR/
Apache License 2.0
42.74k stars 7.68k forks source link

SRN模型在自己数据集上微调报错 RecursionError: maximum recursion depth exceeded in comparison #5587

Closed Babysun-ljh closed 2 years ago

Babysun-ljh commented 2 years ago

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

Ginkle commented 2 years ago

你好，我也遇到这个问题，请问你是怎么解决的？

Ginkle commented 2 years ago

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：python 3.8
  • 版本号/Version：Paddle： 2.4 PaddleOCR： 问题相关组件/Related components：SRN模型微调
  • 运行指令/Command Code： python tools/train.py -c /Users/cynthia/git_version_paddle/PaddleOCR-release-2.4/configs/rec_pda/rec_r50_fpn_srn_finetune.yml
  • 完整报错/Complete Error Message： Exception in thread Thread-1: Traceback (most recent call last): File "/Users/cynthia/opt/anaconda3/lib/python3.8/threading.py", line 932, in _bootstrap_inner self.run() File "/Users/cynthia/opt/anaconda3/lib/python3.8/threading.py", line 870, in run self._target(*self._args, self._kwargs) File "/Users/cynthia/opt/anaconda3/lib/python3.8/site-packages/paddle/fluid/dataloader/dataloader_iter.py", line 212, in _thread_loop batch = self._dataset_fetcher.fetch(indices, File "/Users/cynthia/opt/anaconda3/lib/python3.8/site-packages/paddle/fluid/dataloader/fetcher.py", line 121, in fetch data.append(self.dataset[idx]) File "/Users/cynthia/git_version_paddle/PaddleOCR-release-2.4/ppocr/data/lmdb_dataset.py", line 111, in getitem return self.getitem(np.random.randint(self.len())) File "/Users/cynthia/git_version_paddle/PaddleOCR-release-2.4/ppocr/data/lmdb_dataset.py", line 111, in getitem return self.getitem(np.random.randint(self.len())) File "/Users/cynthia/git_version_paddle/PaddleOCR-release-2.4/ppocr/data/lmdb_dataset.py", line 111, in getitem return self.getitem(np.random.randint(self.len())) [Previous line repeated 986 more times] File "/Users/cynthia/git_version_paddle/PaddleOCR-release-2.4/ppocr/data/lmdb_dataset.py", line 109, in getitem outs = transform(data, self.ops) File "/Users/cynthia/git_version_paddle/PaddleOCR-release-2.4/ppocr/data/imaug/init.py", line 43, in transform data = op(data) File "/Users/cynthia/git_version_paddle/PaddleOCR-release-2.4/ppocr/data/imaug/operators.py", line 43, in call** img = np.frombuffer(img, dtype='uint8') RecursionError: maximum recursion depth exceeded in comparison

你好，我也遇到这个问题，请问你是怎么解决的？

HanMengdan6 commented 7 months ago

你好，我也是遇到同样的问题请问是如何解决的？