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 supported15 Subscribers
Add a CodeTriage badge to vision
Help out
- Issues
- https://github.com/pytorch/vision/blob/b818d320a14a2e6d9d9f28853e9e7beae703e52e/torchvision/io/video.py#L274
- Follow-up on Pillow's mode argument in Image.fromarray()
- fix: fix lsun dataset error message.
- CocoDetection wrapped with wrap_dataset_for_transforms_v2 returns image_id even if not in target_keys
- `error: 'Python.h' file not found` building on Windows with Python installed to `C:\Program Files\Python312`
- InterpolationMode.NEAREST_EXACT and InterpolationMode.NEAREST are the same for tv_tensors.Mask
- DataLoader multiprocessing fails when dataset stores a module object (TypeError: cannot pickle 'module' object)
- Request: Provide +cpu wheels for ARM64 (aarch64) in official TorchVision releases
- torchvision.ops.nms doesn't work with cuda12.9
- `PILToTensor` input shape description is wrong/confusing
- Docs
- Python not yet supported