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

关于论文中图6的问题 #12

Open
w-z-hub opened this issue Dec 8, 2022 · 2 comments
Open

关于论文中图6的问题 #12

w-z-hub opened this issue Dec 8, 2022 · 2 comments

Comments

@w-z-hub
Copy link

w-z-hub commented Dec 8, 2022

您好,在看完您的文章后,我有一些不清楚的地方想向您请教一下,图六中关于两个分支的权重值,在网络训练时该如何呈现出来?或者在网络训练完毕后,如何得知每个块中对应的两个分支的权重值?希望您有空的话,可以解决一下我的疑惑。谢谢您的指教!!!

@haoyuc
Copy link
Owner

haoyuc commented Dec 9, 2022

x = attention * ax[:,0].view(a,1,1,1) + non_attention * ax[:,1].view(a,1,1,1)
您好,可以通过直接看 ax 的值得到

@w-z-hub
Copy link
Author

w-z-hub commented Dec 9, 2022

谢谢您的回答,由于我的代码水平很薄弱,如果只有一个AAB时,我能懂您的意思,但是当在整体网络中运用self.AAB_trunk = make_layer(AAB_block_f, nb)时,我并不清楚该如何写出相应代码,来输出每个AAB中的ax值,不知道您是否可以再帮忙解答一下,万分感谢!!

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