Update object detection with latest resize and pad strategies #30955
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
|
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. |
qubvel
changed the title
qubvel
changed the title
amyeroberts
approved these changes
May 22, 2024
itazap
pushed a commit
that referenced
this pull request
May 24, 2024
* Update with new resizing and pad strategy * Return pixel mask param * Update inference in guide * Fix empty compose * Update guide
zucchini-nlp
pushed a commit
to zucchini-nlp/transformers
that referenced
this pull request
Jun 11, 2024
…gface#30955) * Update with new resizing and pad strategy * Return pixel mask param * Update inference in guide * Fix empty compose * Update guide
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Outdated suggestions cannot be applied.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.
What does this PR do?
Updates object detection example and guide. It is now possible to use
image_processor's resize and pad (#30742) instead of manual padding with albumentations. Despite image_processor resize being slower than albumenations I did not observe any degradation in training speed. Of course, it depends on data and hardware environment, but probably not too critical for not-so-fast detection models where bottleneck is GPU computations.Before submitting
Pull Request section?
documentation guidelines, and
here are tips on formatting docstrings.
Who can review?
@amyeroberts