Skip to content

This issue was moved to a discussion.

You can continue the conversation there. Go to discussion →

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.

Sign up for GitHub

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

Jump to bottom

ch_PP-OCRv4_rec文本识别，模型训练前40epoch时，验证精度可以达到90%以上，现在验证精度接近0. #12084

Closed
banhongjun opened this issue May 9, 2024 · 3 comments
Closed

ch_PP-OCRv4_rec文本识别，模型训练前40epoch时，验证精度可以达到90%以上，现在验证精度接近0. #12084

banhongjun opened this issue May 9, 2024 · 3 comments
Assignees
@cuicheng01

Comments

@banhongjun
Copy link

image
请问这种问题咋回事？
@gengyanlei
Copy link

@banhongjun
你好，请问你能直接训练ch_PP-OCRv4么，我按照官网上的config、预训练模型参数 执行出错。请问你是如何微调v4的det的呢

@banhongjun
Copy link
Author

这是识别模型，检测问题有人提出过，自己搜索下。

@gengyanlei
Copy link

@banhongjun 嗯嗯，检测的配置参数修改设置这些搜到了。就是训练精度 loss都为0的问题

@PaddlePaddle PaddlePaddle locked and limited conversation to collaborators May 25, 2024
@SWHL SWHL converted this issue into discussion #12265 May 25, 2024

This issue was moved to a discussion.

You can continue the conversation there. Go to discussion →

Assignees

@cuicheng01 cuicheng01

Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@gengyanlei @cuicheng01 @banhongjun