Add LW-DETR object detection models#334
Merged
Merged
Conversation
cregouby
reviewed
Jun 26, 2026
cregouby
requested changes
Jun 28, 2026
cregouby
left a comment
cregouby
left a comment
Collaborator
There was a problem hiding this comment.
praise again an impressive contribution
todo see inline
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Closes #328
Implements LW-DETR (https://arxiv.org/abs/2406.03459), a real-time detection transformer
Adds model_lw_detr_tiny(), model_lw_detr_small(), model_lw_detr_medium(), and model_lw_detr_large() with COCO-pretrained weights. The architecture comprises a ViT backbone, a C2f multi-scale projector, and a two-stage deformable-attention decoder. All four variants load the official weights with exact key/shape match and reproduce reference detections; pixel_mask is supported for letterboxed (non-square) inputs.