Change RT-Detr docs to reflect fixed 640x640 input size #41364
+2
−1
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
added 2 commits
October 6, 2025 12:44
The authors of RT-Detr mention that the model was trained on 640x640 images and was meant to be used for inference on 640x640 images. Also, the current implementation has certain quirks that make training/inferring on images of different sizes problematic. For example, the pixel masks used for batches of varying image sizes are discarded. I've added a few lines in the docs to notify the user about these issues.
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Outdated suggestions cannot be applied.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?
The authors of RT-Detr mention that the model was trained on 640x640 images and was meant to be used for inference on 640x640 images. Also, the current implementation has certain quirks that make training/inferring on images of different sizes problematic. For example, the pixel masks used for batching images of varying sizes are discarded. I've added a few lines in the docs to notify the user about these issues.
proj_feats = [self.encoder_input_proj[level](source) for level, (source, mask) in enumerate(features)]Fixes # (issue)
#41363
Before submitting
Who can review?
Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.
Models: