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

关于anchor free+GFocalV2的疑问? #9

Open
sunzhe09 opened this issue Dec 10, 2020 · 3 comments
Open

关于anchor free+GFocalV2的疑问? #9

sunzhe09 opened this issue Dec 10, 2020 · 3 comments

Comments

@sunzhe09
Copy link

你好,我想基于centernet这种网络加上GFlcalV2的loss来训练,但是发现centernet只有wh这个可以类比于gfocalhead这个部分,是不是distrib 这个分支可以改成2n的通道?
另外,如果是360度旋转的目标检测任务,GFocalV2还能wok吗?

@implus
Copy link
Owner

implus commented Dec 10, 2020 via email

@sunzhe09
Copy link
Author

谢谢翔哥,我看了下ttfnet,确实很适合,我们只需要把原来的回归WH,改成回归中心点到四个边的距离就行,然后把distrib loss 这个分支加在中间,这样就可以让它学习到box的分布了对吧?

@Originlightwkp
Copy link

你好sunzhe09,请问你成功了吗?centernet+gfl

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