vision
https://github.com/pytorch/vision
Python
Datasets, Transforms and Models specific to Computer Vision
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported17 Subscribers
Add a CodeTriage badge to vision
Help out
- Issues
- Fix canvas_size of boxes and keypoints after rotate with expand=True
- RandomResizedCrop can produce a zero-size fallback crop on one-pixel-wide or one-pixel-high images
- Ensure non-empty center crop fallback in RandomResizedCrop (#9754)
- box_iou with rotated boxes is wrong when edges of the two boxes lie on the same line
- Fix rotated box IoU for boxes with edges on the same lines
- Use removesuffix instead of rstrip for the inaturalist archive name
- Fix DropBlock on inputs smaller than the block size
- docs: model guide gives an obsolete removal version for pretrained
- docs: correct pretrained deprecation timeline
- Use rot90 for right-angle tensor rotations in transforms.functional.rotate
- Docs
- Python not yet supported