[Bug fix ]Update pixel_samplers.py, tensor on different device, unpredictable behavior at assignment #2257
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
maturk
reviewed
Jul 22, 2023
| @@ -105,6 +105,7 @@ def collate_image_dataset_batch(self, batch: Dict, num_rays_per_batch: int, keep | |||
| assert collated_batch["image"].shape[0] == num_rays_per_batch | |||
|
|
|||
| # Needed to correct the random indices to their actual camera idx locations. | |||
| indices = indices.to(batch["image_idx"].device) | |||
There was a problem hiding this comment.
Is this necessary since the line 109 below basically does the same thing?
There was a problem hiding this comment.
yes, because after 109 the contents of indices[:, 0] does not equal to batch["image_idx"][c] if they are not on the same device.
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Outdated suggestions cannot be applied.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.
"indices" and "batch["image_idx"]" can be on different devices. The assignment between them, though will allow the model to converge correctly, have unpredictable behaviors. Namely, indices[:, 0] - batch["image_idx"][c].cpu() != 0. Putting them on the same device to have correct behavior.
It is a mystery to me why nerfstudio can work correctly with this unpredictable behavior.