-
Notifications
You must be signed in to change notification settings - Fork 54
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
Comments
hi:
建议你可以参考ttfnet,它已经修改为上下左右回归,而且收敛比centernet快很多;
旋转的话得看你怎么设计成一种分布式表示了,我目前也没接触过旋转这类,可能还要再细想一下~
…------------------ 原始邮件 ------------------
发件人: "implus/GFocalV2" <[email protected]>;
发送时间: 2020年12月10日(星期四) 晚上8:47
收件人: "implus/GFocalV2"<[email protected]>;
抄送: "Subscribed"<[email protected]>;
主题: [implus/GFocalV2] 关于anchor free+GFocalV2的疑问? (#9)
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?
—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub, or unsubscribe.
|
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? |
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
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?
The text was updated successfully, but these errors were encountered: