Repository navigation
Preserve empty shapes when extracting image patches - #145
Open
satiricalguru wants to merge 1 commit into
Open
satiricalguru wants to merge 1 commit into
satiricalguru wants to merge 1 commit into
Conversation
Use explicit reshape dimensions so empty image batches and empty spatial outputs match TensorFlow patch extraction. Assisted-by: Codex <noreply@openai.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
extract_patchesraisesZeroDivisionErrorfor an empty image batch or aVALIDconvolution with no patch positions. Both reshapes infer a dimension using-1, which is ambiguous when a known dimension is zero.Use explicit dimensions for the channel reorder and reuse the convolution output shape. The regression compares both empty cases against
tf.image.extract_patches, including under JIT.Verified with
pytest -q dm_pix/_src/patch_test.py(108 passed, 27 skipped) and the completedm_pix/_srcsuite (1,959 passed, 152 skipped).Codex assisted with implementation, tests, and review.