-
Notifications
You must be signed in to change notification settings - Fork 251
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
why layernorm so important? #145
Comments
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
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
The text was updated successfully, but these errors were encountered: