-
Notifications
You must be signed in to change notification settings - Fork 394
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.
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
Fix bug in macro average for a number of classification metrics #1715
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Hi, I know I created #1693 (comment) and suggest a IoU of 1.0 if a class is neither present in target nor prediction, but I am not that sure anymore.
Doing so quietly might lead to overly optimistic values.
As I showed in #1693 (comment), the JaccardIndex internally updates a confusion matrix over all batches, which results in the correct values, if a final compute() is called after the validation/testing epoch.
Hi @SkafteNicki @Borda @JohannesK14 thank you for the fix and / or review! I wanted to ask the state of this PR, because I also experience the issue :/ |
@ioangatop I am currently working on it locally. Nearly done, but I have some unit tests that are still failing which I need to debug. Hopefully, get it done before the end of this week and I make sure that it is done before v1.0 release. |
What does this PR do?
Fixes #1693
Fixes #1692
Fixes #1691
Fixes #1664
Before submitting
PR review
Anyone in the community is free to review the PR once the tests have passed.
If we didn't discuss your PR in Github issues there's a high chance it will not be merged.
Did you have fun?
Make sure you had fun coding 🙃