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 supported13 Subscribers
Add a CodeTriage badge to vision
Help out
- Issues
- The link of **Multi-view Stereo Correspondence** doesn't exist in the doc
- make processing of arbitrary inputs to transforms.v2 public and document it
- Wrong code in setup.py: it assumes that it is Windows if it's not linux or darwin
- I am using the torchvision-0.13.1+cu113 version, but it seems that it does not have the datapoints package. How can I solve this issue?
- `torchvision.ops.boxes.batched_nms` slow on large box numbers
- Phototour dataset URLs are broken
- Contribution Proposal: ScatterND Implementation for PyTorch
- [Feature Request] PadToSquare: Square Padding to Preserve Aspect Ratios When Resizing Images with Varied Shapes in torchvision.transforms.v2
- [Feature Request] PadToSquare: Square Padding to Preserve Aspect Ratios When Resizing Images with Varied Shapes in torchvision.transforms.v2
- torchvision is restricted to ffmpeg-4 on conda
- Docs
- Python not yet supported