Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

单元格识别模型RT-DETR-L_wireless_table_cell_det只输出300个结果 #3591

Open
DFxiaotu opened this issue Mar 13, 2025 · 1 comment
Assignees

Comments

@DFxiaotu
Copy link

描述问题

在使用RT-DETR-L_wireless_table_cell_det模型对表格结构进行识别时,发现只输出300个矩形框结果,请问这是在模型训练中就已经限制好了吗?是否有什么办法生成更多结果?

环境

  1. 请提供您使用的PaddlePaddle和PaddleX的版本号
    3.0rc
  2. 请提供您使用的操作系统信息,如Linux/Windows/MacOS
    linux
  3. 请问您使用的Python版本是?
    3.9.21
  4. 请问您使用的CUDA/cuDNN的版本号是?
    12.4
@liu-jiaxuan
Copy link
Collaborator

Hi,RT-DETR-L_wireless_table_cell_det 模型确实最多只能输出300个单元格,这是因为当单元格过多(也即表格过于复杂)时,表格结构识别的准确率已经不能达到预期了,因此设定了一个上限,如果需要生成更多结果,建议可以将表格进行拆分,这样也有助于提高结构识别的准确率。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants