Add 'crop' option to RandomRotation#9458
Open
sg3-141-592 wants to merge 1 commit intopytorch:mainfrom
Open
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/vision/9458
Note: Links to docs will display an error until the docs builds have been completed. ❌ 3 New FailuresAs of commit 87ef6ab with merge base 6676c01 ( NEW FAILURES - The following jobs have failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
dc34375 to
db55653
Compare
…ve any padding regions introduced by the rotation
db55653 to
87ef6ab
Compare
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Add 'crop' option to
RandomRotationthat centre crops the rotated image to remove any padding regions introduced by the rotation #9147cropandexpandare mutually exlusive.This is based off the approach in albumentations - rotate.py. Which in turn is taken from here https://stackoverflow.com/questions/16702966/rotate-image-and-crop-out-black-borders. Slight difference is we use int() (floor) for the final crop dimensions rather than Albumentations' coordinate-based rounding, to guarantee no fill pixels appear in the output.
I've added a
RandomRotation._extract_params_for_v1_transformoverride to strip the crop parameter fortorch.jit.script()compatibility, and to raise aValueErrorifcrop=Truesince the v1 transform has no equivalent.