Fix bug in macro average for a number of classification metrics

[SkafteNicki]

What does this PR do?

Fixes #1693
Fixes #1692
Fixes #1691
Fixes #1664

Before submitting

• Was this discussed/agreed via a Github issue? (no need for typos and docs improvements)
• Did you read the contributor guideline, Pull Request section?
• Did you make sure to update the docs?
• Did you write any new necessary tests?

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 🙃

[JohannesK14]

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.

[ioangatop]

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 :/

[SkafteNicki]

@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.