[Object Detection] Add DETR Backbone, Object Detector, Preprocessor and Weight Conversion #2043
Conversation
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
|
Getting there :) 
|
sachinprasadhs
added
the
WIP
|
@DavidLandup0 , Any update on this PR? |
Picking it up now that a couple of other things are out the way - should have a more concrete update soon :) |
DavidLandup0
changed the title
DavidLandup0
commented
Oct 23, 2025
| return self.converter.convert_tokenizer(cls, self.preset, **kwargs) | ||
|
|
||
| def load_image_converter(self, cls, **kwargs): | ||
| # Check if the converter has an image converter conversion function |
There was a problem hiding this comment.
Adding this for backwards compatability - looks like we just didn't have a way to return the image converter so far, unless I missed it from another model.
This way, any convert_x.py that has convert_image_converter() method can return that image converter too.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
Adds DETR backbone, object detector and preprocessor.
DETR Elements
Preset Loader
To enable the
from_preset()convention, we also convert theDETRImageConverterparameters, but it looks like the method so far has just returnedNonewith a TODO for PaliGemma. In this PR, I've added aconvert_image_converter()method toconvert_detr.pyand updated the general preset loader to check if a specific implementation has the method and returns the class if it does for backwards compatability.