adding KID metric

[SkafteNicki]

Before submitting

• Was this discussed/approved 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?

What does this PR do?

Implements kernel inception distance (KID).
Should be merged after #299

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 🙃

[pep8speaks]

Hello @SkafteNicki! Thanks for updating this PR.

There are currently no PEP 8 issues detected in this Pull Request. Cheers! 🍻

Comment last updated at 2021-06-21 18:51:23 UTC

[codecov]

Codecov Report

Merging #301 (3f1e0e0) into master (7af6d13) will increase coverage by 0.03%.
The diff coverage is 95.78%.

@@            Coverage Diff             @@
##           master     #301      +/-   ##
==========================================
+ Coverage   96.37%   96.41%   +0.03%     
==========================================
  Files          97       98       +1     
  Lines        3259     3350      +91     
==========================================
+ Hits         3141     3230      +89     
- Misses        118      120       +2     

Flag	Coverage Δ
Linux	75.26% <21.05%> (-1.53%)	⬇️
Windows	75.26% <21.05%> (-1.53%)	⬇️
cpu	96.35% <95.78%> (-0.03%)	⬇️
gpu	96.38% <95.78%> (?)
macOS	96.35% <95.78%> (-0.03%)	⬇️
pytest	96.41% <95.78%> (+0.03%)	⬆️
python3.6	95.42% <95.78%> (+<0.01%)	⬆️
python3.8	95.52% <95.78%> (-0.86%)	⬇️
python3.9	96.26% <95.78%> (-0.02%)	⬇️
torch1.3.1	95.42% <95.78%> (+<0.01%)	⬆️
torch1.4.0	95.52% <95.78%> (+<0.01%)	⬆️
torch1.9.0	96.26% <95.78%> (-0.02%)	⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files	Coverage Δ
torchmetrics/utilities/data.py	94.73% <50.00%> (-1.63%)	⬇️
torchmetrics/image/kid.py	96.51% <96.51%> (ø)
torchmetrics/__init__.py	100.00% <100.00%> (ø)
torchmetrics/image/__init__.py	100.00% <100.00%> (ø)
torchmetrics/image/fid.py	82.55% <100.00%> (+0.20%)	⬆️
torchmetrics/image/inception.py	95.00% <100.00%> (+0.12%)	⬆️
torchmetrics/functional/regression/spearman.py	97.77% <0.00%> (+4.44%)	⬆️

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 7af6d13...3f1e0e0. Read the comment docs.

[justusschock]

Some minor comments. Looks good overall

[Borda]

@SkafteNicki there seems to some argument errors with Conda tests