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 supported14 Subscribers
Add a CodeTriage badge to vision
Help out
- Issues
- Optional random number generation for get_params methods in image transforms
- How to load indexed images (color maps) using dataset loader
- Feature proposal: Cutout
- standardize dataset naming conventions
- Relocate image and video_reader extensions' dependencies on conda
- Create reset_parameters method for ResNet blocks and models + move existing parameters init code there
- Fix reading audio from a video file with pts_unit='sec'
- return identity when blocks less than 1 in resnet
- TorchVision support for pre-trained, quantised, ResNet50 using QNNpack backend
- torchvision.transforms.functional.adjust_hue does not respect alpha channel
- Docs
- Python not yet supported