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

Total Variation Loss #972

Closed
ragavvenkatesan opened this issue Apr 20, 2022 · 2 comments · Fixed by #978
Closed

Total Variation Loss #972

ragavvenkatesan opened this issue Apr 20, 2022 · 2 comments · Fixed by #978
Labels
enhancement New feature or request New metric topic: Image

Comments

@ragavvenkatesan
Copy link
Contributor

🚀 Feature

Hi, in the image package, we are missing the total variation loss.

Motivation

Total variation loss is a useful loss in reconstruction models such as in auto-encoders. Traditionally used in denoising, it is now being used in several other types of hi-res reconstruction.

Pitch

Alternatives

Additional context
@ragavvenkatesan ragavvenkatesan added the enhancement New feature or request label Apr 20, 2022
@stancld
Copy link
Contributor

stancld commented Apr 21, 2022

Hi @ragavvenkatesan, looks like a good addition. Do you wanna try to tackle this one and send a PR? :]

@ragavvenkatesan
Copy link
Contributor Author

ragavvenkatesan commented Apr 22, 2022 •
edited
Loading

Hi @ragavvenkatesan, looks like a good addition. Do you wanna try to tackle this one and send a PR? :]

Sure, what are the perks of being a contributor :)?

Here is a PR with some basic code for a quick review. I will formalize this and add tests over the weekend.

@Borda Borda mentioned this issue Apr 22, 2022
Merged
4 tasks
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
enhancement New feature or request New metric topic: Image
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Total Variation Loss ragavvenkatesan/metrics
3 participants
@Borda @ragavvenkatesan @stancld