Add LlavaImageProcessor #33191
Merged
Add LlavaImageProcessor #33191
+667
−4
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. |
NielsRogge
commented
Aug 30, 2024
zucchini-nlp
approved these changes
Sep 2, 2024
amyeroberts
reviewed
Sep 2, 2024
| self.assertEqual(image_processor.crop_size, {"height": 84, "width": 84}) | ||
|
|
||
| # Ignore copy | ||
| def test_padding(self): |
There was a problem hiding this comment.
This needs to be more thoroughly tested namely - it needs to test:
- background colour is properly set when
background_coloris a non-default int, or a non-default tuple - the method works as expected for both channels first and channels last inputs
There was a problem hiding this comment.
Hi @zucchini-nlp could you take this up?
There was a problem hiding this comment.
oke, no prob, I will come back on this tomorrow
|
Is there any update for this feature? It seems very important for aligning implementations between Hugging Face and the official ones. |
qubvel
reviewed
Jan 21, 2025
Co-authored-by: Pavel Iakubovskii <qubvel@gmail.com>
Co-authored-by: Pavel Iakubovskii <qubvel@gmail.com>
qubvel
approved these changes
Jan 21, 2025
bursteratom
pushed a commit
to bursteratom/transformers
that referenced
this pull request
Jan 31, 2025
* First draft * Add equivalence test * Update docstrings * Add tests * Use numpy * Fix tests * Improve variable names * Improve docstring * Add link * Remove script * Add copied from * Address comment * Add note in docs * Add docstring, data format * Improve test * Add test * update * Update src/transformers/models/llava/image_processing_llava.py Co-authored-by: Pavel Iakubovskii <qubvel@gmail.com> * Update src/transformers/models/llava/image_processing_llava.py Co-authored-by: Pavel Iakubovskii <qubvel@gmail.com> * loop once only --------- Co-authored-by: raushan <raushan@huggingface.co> Co-authored-by: Raushan Turganbay <raushan.turganbay@alumni.nu.edu.kz> Co-authored-by: Pavel Iakubovskii <qubvel@gmail.com>
elvircrn
pushed a commit
to elvircrn/transformers
that referenced
this pull request
Feb 13, 2025
* First draft * Add equivalence test * Update docstrings * Add tests * Use numpy * Fix tests * Improve variable names * Improve docstring * Add link * Remove script * Add copied from * Address comment * Add note in docs * Add docstring, data format * Improve test * Add test * update * Update src/transformers/models/llava/image_processing_llava.py Co-authored-by: Pavel Iakubovskii <qubvel@gmail.com> * Update src/transformers/models/llava/image_processing_llava.py Co-authored-by: Pavel Iakubovskii <qubvel@gmail.com> * loop once only --------- Co-authored-by: raushan <raushan@huggingface.co> Co-authored-by: Raushan Turganbay <raushan.turganbay@alumni.nu.edu.kz> Co-authored-by: Pavel Iakubovskii <qubvel@gmail.com>
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?
Fixes #33175. It adds the option to pad an image before applying the same preprocessing as
CLIPImageProcessorbased on the original implementation. This allows people to match the logits with the original implementation.For now I decided to set
do_padtoFalseby default as otherwise it would be a breaking change.To do: