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.

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

why layernorm so important? #145

Open
YilanWang opened this issue May 15, 2024 · 1 comment
Open

why layernorm so important? #145

YilanWang opened this issue May 15, 2024 · 1 comment

Comments

@YilanWang
Copy link

我尝试了巨量其他norm或者差不多的方式,比如bn,nfnet的结构,等等,发现只要替代ln网络全挂了. 但是其他的denoise/sr任务并没有这个现象,比如esrgan系列甚至都可以完全不要norm,太神奇了,不知道两年后作者能不能看到这个问题
@hzwer
Copy link

hzwer commented May 17, 2024 •
edited

特别深的 transformer 结构，layernorm 可能是最标准的（个人观点）

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@hzwer @YilanWang