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

当运行文字识别的时候,经过det会得出boxes,然后能不能多线程进行rec处理,把boxes分为x个部分然后创建x个线程来跑,来提高rec的识别效率,有没有可行性 #10613

Open
manongxiaobaigbc opened this issue Dec 11, 2024 · 3 comments
Assignees

Comments

@manongxiaobaigbc
Copy link

No description provided.

@manongxiaobaigbc
Copy link
Author

我在调用rec处理文字识别的时候创建线程,但调用predictor_crnn->Run();就会报Segmentation fault,无论是多少个线程,只要是子线程就会报错,在主线程中运行就不会

@manongxiaobaigbc
Copy link
Author

进程的话是一直不运行,top命令查看到的是cpu占用0%,进程也是跑到predictor_crnn->Run()就停止了

@ddchenhao66
Copy link
Collaborator

ddchenhao66 commented Dec 12, 2024

你好,可以提供下详细的报错日志。可以开调高GLOG_v等级,比如export GLOG_v=5查看更详细的日志。另外Paddle Lite本身提供了多线程加速,可以在算子层面加速:
infoflow 2024-12-12 11-23-30

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

2 participants