-
Notifications
You must be signed in to change notification settings - Fork 411
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
Enhance Panoptic Quality implementation #1527
Enhance Panoptic Quality implementation #1527
Conversation
raise TypeError(f"Expected argument `target` to be of type `torch.Tensor`, but got {type(target)}") | ||
if preds.shape != target.shape: | ||
raise ValueError( | ||
f"Expected argument `preds` and `target` to have the same shape, but got {preds.shape} and {target.shape}" | ||
) | ||
if preds.dim() != 3 or preds.shape[-1] != 2: | ||
raise ValueError(f"Expected argument `preds` to have shape [height, width, 2], but got {preds.shape}") | ||
if preds.dim() < 3: |
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.
Question: what's the best way to deal with an unknown number of spatial dimensions? Here I just say "anything > 0 is fine", but maybe we want to restrict to just point clouds and images (but why no voxels..., and so on)?
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.
That is veru good question, so lets play with it in follow-up PR :)
cc: @Lightning-AI/core-metrics
f476b21
to
2c36e0b
Compare
Codecov Report
Additional details and impacted files@@ Coverage Diff @@
## master #1527 +/- ##
========================================
- Coverage 88% 37% -51%
========================================
Files 219 219
Lines 11473 11497 +24
========================================
- Hits 10069 4277 -5792
- Misses 1404 7220 +5816 |
2709853
to
178e715
Compare
Co-authored-by: Nicki Skafte Detlefsen <[email protected]>
for more information, see https://pre-commit.ci
What does this PR do?
Fixes #1511:
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 🙃
sure ✅