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

Use quantized weight for optimizing rotation matrices? #23

Open
SShock92 opened this issue Jan 7, 2025 · 0 comments
Open

Use quantized weight for optimizing rotation matrices? #23

SShock92 opened this issue Jan 7, 2025 · 0 comments

Comments

@SShock92
Copy link

SShock92 commented Jan 7, 2025

Thanks for the nice work!

One question for the setting of the rotation matrix optimization.
In the example of the README file (step 1), rotation matrices are optimized for the weight-activation quantized network.
Whereas, in Section 4.1 of the arXiv paper, it seems that weights remain full-precision when optimizing rotation matrices.

Which one is correct?
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
1 participant
@SShock92