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

iclr18_estimate_bits_z entropy model does not match paper #4

Open
zzzzz314314 opened this issue May 14, 2024 · 0 comments
Open

iclr18_estimate_bits_z entropy model does not match paper #4

zzzzz314314 opened this issue May 14, 2024 · 0 comments

Comments

@zzzzz314314
Copy link

Hi, thanks to your hardwork and the opensourcing.
As said in title, the BitEstimator module (

iclr_17_compression/models/bitEstimator.py

Line 22 in bce72bc

return torch.sigmoid(x * F.softplus(self.h) + self.b)
) used in iclr18_estimate_bits_z does not match the paper, where h should be matrices multiplication to each channel instead of scaling factors applied to each channel. I was wondering if you have experimented this and found there is little difference. Thanks!
@zzzzz314314 zzzzz314314 changed the title iclr18_estimate_bits_z entropy model does might not match paper iclr18_estimate_bits_z entropy model does not match paper May 14, 2024
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
@zzzzz314314