Skip to content
This repository has been archived by the owner on Jul 24, 2024. It is now read-only.

Why use bn in projection head? #205

Open
shesung opened this issue Sep 6, 2022 · 0 comments
Open

Why use bn in projection head? #205

shesung opened this issue Sep 6, 2022 · 0 comments

Comments

@shesung
Copy link

shesung commented Sep 6, 2022

use_bn=True,

In this code, bn is used in every layer of projection head, which is not mentioned in the papers.
Moreover, there is no bias in middle layer, which is conflict with the comments.

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant