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

RMSLE metric appears to be incorrect #3162

Closed
Sordie opened this issue Aug 25, 2020 · 2 comments · Fixed by #3188
Closed

RMSLE metric appears to be incorrect #3162

Sordie opened this issue Aug 25, 2020 · 2 comments · Fixed by #3188
Labels
bug Something isn't working help wanted Open to be worked on priority: 0 High priority task

Comments

@Sordie
Copy link
Contributor

Sordie commented Aug 25, 2020

🐛 Bug

The usage of mse in the rmsle function looks wrong to me. It looks like this function currently computes mean squared log error instead of root mean squared log error.

Expected behavior

I would expect that rmsle looks like this:

rmsle = rmse(torch.log(pred + 1), torch.log(target + 1), reduction=reduction)
@Sordie Sordie added bug Something isn't working help wanted Open to be worked on labels Aug 25, 2020
@github-actions
Copy link
Contributor

Hi! thanks for your contribution!, great first issue!

@rohitgr7
Copy link
Contributor

yep it's a bug. mind send a PR :)

@Borda Borda added the priority: 0 High priority task label Aug 25, 2020
@Sordie Sordie mentioned this issue Aug 26, 2020
Merged
7 tasks
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
bug Something isn't working help wanted Open to be worked on priority: 0 High priority task
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Fix RMSLE metric Sordie/pytorch-lightning
3 participants
@Borda @rohitgr7 @Sordie