Correction for non-integral image resolutions with quantizations other than float32 #7356
Conversation
This file contains hidden or 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
DN6
reviewed
Mar 18, 2024
| x = torch.nn.functional.interpolate( | ||
| x.float(), skip.shape[-2:], mode="bilinear", align_corners=True | ||
| ) | ||
| x = x.type(orig_type) |
Collaborator
There was a problem hiding this comment.
Could we use x = x.to(orig_dtype) just to be consistent with how casting in done in other parts of the library.
DN6
reviewed
Mar 18, 2024
Collaborator
DN6
left a comment
DN6
left a comment
There was a problem hiding this comment.
Thanks for catching! Could we add a similar casting operation to the training section as well.
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
Contributor
Author
|
Thanks for the suggestions, I've changed the casting call and added the same code in the corresponding training location. |
Member
|
@DN6 good to merge? |
kashif
approved these changes
Mar 19, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 participants
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Outdated suggestions cannot be applied.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.
What does this PR do?
For Stable Cascade:
Adds support for non-integral image resolutions (I.e. not divisible by 32) when the model quantization choice is other than float32 (I.e. using bfloat16 et al.)
Fixes #7355
Before submitting
documentation guidelines, and
here are tips on formatting docstrings.
Who can review?
@sayakpaul @yiyixuxu @DN6