SER 本地使用预训练模型预测 TypeError: _infer() got an unexpected keyword argument 'attention_masks'

[Harryoung]

我们提供了issue bot来帮助你解答问题，你是否想要它来解答(请填写yes/no)?/We provide issue bot to solve issues, do you want it? (Please write yes/no):yes

请注意：issue bot基于大语言模型实现，其回答仅供参考。目前issue bot尚不能解析issue中的图片。/Please note: The issue bot is implemented based on large language models, and its answers are for reference only. Currently the issue bot cannot parse images in issues.

请在这里描述你的问题/Please describe your issue here:

Traceback (most recent call last):
File "E:\home\aistudio\PaddleOCR\tools\infer_vqa_token_ser.py", line 132, in
result, _ = ser_engine(img_path)
File "E:\home\aistudio\PaddleOCR\tools\infer_vqa_token_ser.py", line 105, in call
post_result = self.post_process_class(
File "E:\home\aistudio\PaddleOCR\ppocr\postprocess\vqa_token_ser_layoutlm_postprocess.py", line 52, in call
return self._infer(preds, **kwargs)
TypeError: _infer() got an unexpected keyword argument 'attention_masks'

[llm-issue-bot]

Issue Response

• ✨ Introduction: Thanks for opening this issue, I am the issue bot that will help you with your questoins!
• 🎯 First round response: The answer to your question is:

The error message "TypeError: _infer() got an unexpected keyword argument 'attention_masks'" indicates that there is an unexpected keyword argument 'attention_masks' in the '_infer()' function. This error occurred in the file 'vqa_token_ser_layoutlm_postprocess.py' at line 52. To resolve this issue, the code in the file 'infer_vqa_token_ser.py' should be checked to ensure that the 'attention_masks' argument is being passed correctly to the '_infer()' function.

Relevant Sources

• https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.7/applications/多模态表单识别.md
• https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.7/doc/doc_ch/kie.md

How to use

My answer may not be accurate. I suggest you refer to relevant sources to make a comprehensive judgment.
To invoke me for more questions, add a comment using following command:
@llm-issue-bot <QUESTION>

[fightfat]

@llm-issue-bot #34