Let LinearTransformation return datapoints instead of tensors #7244
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
pmeier
approved these changes
Feb 14, 2023
facebook-github-bot
pushed a commit
that referenced
this pull request
Mar 28, 2023
#7244) Reviewed By: vmoens Differential Revision: D44416585 fbshipit-source-id: 8f61172e676563ad7eefbdb294eb76dab6dee2eb
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Outdated suggestions cannot be applied.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.
For the same reason as for Normalize or RandomPhotometricDistort done in #7113: the assumption about the range of the values is embedded in the
dtypeof the underlying tensor, not in its [sub]class. On top of that, Tensors are treated the same as Images, so returning a Tensor doesn't add any "security layer".I'm not adding tests because the relevant test is in #7238, which properly passes with this PR (checked locally).
cc @vfdev-5 @bjuncek @pmeier