dmarx / dmarx/cka_pytorch

self attention distance

Open
#3 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Jupyter Notebook
Stars
17
Forks
3
PR merge metrics
No merged PRs in 30d

Description

Hello, thank you very much for your reproduction work. I am also studying this paper.

I would like to ask, do you know how self attention distance is obtained using code in this paper?

Looking forward to your answer.

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.