You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
In comfy_extras/nodes_sdpose.py the SDPose preprocessing was corrected: model_w is now taken from head.heatmap_size[0] and model_h from head.heatmap_size[1]. _resize_to_model was changed to stretch images to (model_h, model_w) and return separate horizontal/vertical scales (sx, sy). _remap_keypoints was updated to use scale_x/scale_y with x/y-only remapping. Call sites were adjusted for the new return values and signature. In CropByBBoxes, common_upscale was switched from bilinear to area for both resize paths.
🚥 Pre-merge checks | ✅ 4 | ❌ 1
❌ Failed checks (1 warning)
Check name
Status
Explanation
Resolution
Docstring Coverage
⚠️ Warning
Docstring coverage is 50.00% which is insufficient. The required threshold is 80.00%.
Write docstrings for the functions missing them to satisfy the coverage threshold.
✅ Passed checks (4 passed)
Check name
Status
Explanation
Title check
✅ Passed
The title 'SDPose: resize fix' directly corresponds to the main changes: fixing SDPose keypoint extraction and switching from bilinear to area resizing.
Linked Issues check
✅ Passed
Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check
✅ Passed
Check skipped because no linked issues were found for this pull request.
Description check
✅ Passed
The pull request description directly addresses the changes made: fixing model input orientation (W, H vs H, W convention), switching from bilinear to area resize, and changing from aspect-ratio preserving pad to stretch resize.
✏️ Tip: You can configure your own custom pre-merge checks in the settings.
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.
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
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.
Fix model input orientation. head.heatmap_size follows MMPose's (W, H) convention, which was matched wrong for pytorch (H, W)
Switch resize from bilinear to area
Stretch resize instead of aspect ratio preserving pad, as the model is trained like that, gives expected accuracy on harder images.