Monodepth Regularization #2284
Merged
Monodepth Regularization #2284
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
AdamRashid96
approved these changes
Aug 1, 2023
ethanweber
commented
Aug 1, 2023
|
LGTM! |
selitvin
reviewed
Aug 2, 2023
| mask: Optional[Tensor] = None, | ||
| device: Union[torch.device, str] = "cpu", | ||
| ) -> Int[Tensor, "batch_size 3"]: | ||
| if mask: |
There was a problem hiding this comment.
I think this should be: if mask is None. My transforms.json contains masks and as a result the code fails when maks tensor does not evaluate as a boolean expression.
Maybe it would be possible to add instructions to the NotImplementedError message on what needs to be adjusted in the configuration for the code to work with mask images (my case)? Naybe automatically fall back to the PixelSampler, if that's the solution?
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Outdated suggestions cannot be applied.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.
I created this PR to resolve the GitHub actions issues from PRs #2252 and #2066, which were duplicates. See PR #2066 for a detailed discussion and the contributions from @AdamRashid96.
This line change is particularly important because we call setup() with kwargs elsewhere. We rely on being able to change the default
num_rays_per_batchin thetest_train.pyscript, and the small value of 4 for testing was never actually passed through. I believe this lead to an out of memory issue and therefore GitHub actions failing with the non-descriptive error ofError: The operation was canceled.