torchvision 0.25.0

image and video datasets and models for torch deep learning

Stars: 17518, Watchers: 17518, Forks: 7206, Open Issues: 1189

The pytorch/vision repo was created 9 years ago and the last code push was 8 hours ago.
The project is extremely popular with a mindblowing 17518 github stars!

How to Install torchvision

You can install torchvision using pip

pip install torchvision

or add it to a project with poetry

poetry add torchvision

Package Details

Author

PyTorch Core Team

License

BSD

Homepage

https://github.com/pytorch/vision

PyPi:

https://pypi.org/project/torchvision/

GitHub Repo:

https://github.com/pytorch/vision

Related Packages

Errors

A list of common torchvision errors.

Code Examples

Here are some torchvision code examples and snippets.

GitHub Issues

The torchvision package has 1189 open issues on GitHub

• Refactor: extract shared affine helpers for keypoints and bbox
• Fix int64 bbox rounding in perspective and elastic transforms
• Clarify ImageFolder sample ordering and indexing
• Port io/image to stable ABI
• specify rotation direction in RandomRotation docs
• ElasticTransform docs: fix issue#8879
• The URL for the SUN397 dataset isn't working
• Fix masks_to_boxes for empty masks and vectorize for performance
• ops.masks_to_boxes , RuntimeError: min(): Expected reduction dim to be specified for input.numel() == 0. Specify the reduction dim with the 'dim' argument.
• Error on trying to run fasterrcnn_resnet50_fpn on Mac M2 with device set to "mps"
• Bundled libpng prior to 1.6.54 is vulnerable
• Add rocjpeg support for image decoding
• Remove video decoder build from setup.py
• add warning for CelebA bbox data
• [torchvision] Fixing typos

See more issues on GitHub