Fix inaccuracy in PerspectiveTransformation #585
Merged
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
Fix an inaccuracy in `PerspectiveTransform` that can lead to slightly misaligned transformations between images and coordinate-based augmentables (e.g. bounding boxes). The problem is more significant the smaller the images and larger the `scale` values. It is also worsened by using `fit_output`. The inaccuracy is caused by using H-1 and W-1 instead of H and W.
Codecov Report
@@ Coverage Diff @@
## master #585 +/- ##
=======================================
Coverage 96.48% 96.48%
=======================================
Files 40 40
Lines 14548 14548
=======================================
Hits 14036 14036
Misses 512 512 |
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Outdated suggestions cannot be applied.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.
Fix an inaccuracy in
PerspectiveTransformthat can lead toslightly misaligned transformations between images and
coordinate-based augmentables (e.g. bounding boxes). The problem
is more significant the smaller the images and larger the
scalevalues. It is also worsened by usingfit_output.The inaccuracy is caused by using H-1 and W-1 instead of
H and W.