Improve numerical stability of _torch_impl.project_cov3d_ewa #182
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Looks good to me. Have you tested the test_project_gaussians.py ? |
Yes. Still passing. (Just double checked after realizing the passing CI build does not apparently test CUDA things) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Fixes the a minimal set of numerical issues in
_torch_implso that it can be used in actual training and not just unit tests. This makes testing and optimizing various things a lot easier (example here). Similar to one of the goals in #172. However, #172 seems to be still a work-in-progress, so this PR still makes sense too and should not conflict with #172.The numerical issues were mostly related to: