Replies: 1 comment
-
这种需要后处理拼接,或者送入模型前就拼一下。现在逻辑是送入模型的是PDF的一页一页的。 |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
🔎 Search before asking
🐛 Bug (问题描述)
如题,
pdf中表格的某一行,因为分页被分成了两行,识别错误
我的这个bad case中,
每一行都有序号索引,当前索引3的行,因为单行过长被截断分页到新的一页的关系,被识别为索引4的行了
这种情况可以通过调整参数,或者更换模型解决吗?还是现阶段的模型无法解决这种case
如果可以通过参数调整,麻烦给个示例,感谢
🏃♂️ Environment (运行环境)
paddle==3.0
cuda==12.1
python==3.10
🌰 Minimal Reproducible Example (最小可复现问题的Demo)
Beta Was this translation helpful? Give feedback.
All reactions