pytorch /vision

Datasets, Transforms and Models specific to Computer Vision

★ 18,010⑂ 7,295👁 436⑃ 6,090● 3,634▤ 59
PythonBSD-3-ClauseCreated 2016-11-09pytorch.org/vision
Download: TorchVision 0.29.2TorchVision-0.29.2 ↓0.29.22026-10-28
+3
Daily
18,010
stars
7,295
forks
436
watchers
6,090
prs
3,634
issues
59
releases

README

torchvision




The torchvision package consists of popular datasets, model architectures, and common image transformations for computer
vision.

 Installation

Please refer to the official
instructions to install the stable
versions of torch and torchvision on your system.

To build source, refer to our contributing
page.

The following is the corresponding torchvision versions and supported Python
versions.

| torch            | torchvision      | Python              |
| ------------------ | ------------------ | ------------------- |
| main / nightly | main / nightly | =3.11, =3.10, =3.10, =3.10, =3.10, 
    older versions

| torch | torchvision     | Python                    |
|---------|-------------------|---------------------------|
| 2.9              | 0.24             | =3.10, =3.9, =3.9, =3.9, =3.9, =3.8, =3.8, =3.8, =3.8, =3.8, =3.7.2, =3.7, =3.7, =3.6, =3.6, =3.6, =3.6, =3.6, =3.5, =3.5, =3.5, =3.5, =3.5, =3.5, 

 Image Backends

Torchvision currently supports the following image backends:

- torch tensors
- PIL images:
    - Pillow
    - Pillow-SIMD - a much faster drop-in replacement for Pillow with SIMD.

Read more in in our docs.

 Documentation

You can find the API documentation on the pytorch website: 

 Contributing

See the CONTRIBUTING file for how to help out.

 Disclaimer on Datasets

This is a utility library that downloads and prepares public datasets. We do not host or distribute these datasets,
vouch for their quality or fairness, or claim that you have license to use the dataset. It is your responsibility to
determine whether you have permission to use the dataset under the dataset's license.

If you're a dataset owner and wish to update any part of it (description, citation, etc.), or do not want your dataset
to be included in this library, please get in touch through a GitHub issue. Thanks for your contribution to the ML
community!

 Pre-trained Model License

The pre-trained models provided in this library may have their own licenses or terms and conditions derived from the
dataset used for training. It is your responsibility to determine whether you have permission to use the models for your
use case.

More specifically, SWAG models are released under the CC-BY-NC 4.0 license. See
SWAG LICENSE for additional details.

 Citing TorchVision

If you find TorchVision useful in your work, please consider citing the following BibTeX entry:

bibtex
@software{torchvision2016,
    title        = {TorchVision: PyTorch's Computer Vision library},
    author       = {TorchVision maintainers and contributors},
    year         = 2016,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/pytorch/vision}}
}

Top issues

Latest release

TorchVision 0.29.2 v0.29.2 2026-10-28
This is a minor release with no new feature. It's compatible with PyTorch 2.14 and later.

 Improvements

[packaging] Build a single py3-none wheel per platform, covering all supported CPython versions including free-threaded builds (9643)

 Bug Fixes

[datasets] Use filter='data' when extracting tar archives, to prevent path traversal outside the target directory (9694)
[ops] Add more input checks to the CPU roi_align, roi_pool, ps_roi_align and ps_roi_pool kernels. Out-of-range batch indices, bad rois/grad shapes and oversized sampling grids now raise an error instead of accessing m

Snapshot: 2026-11-16T09:23:14Z · Data license Apache-2.0 · JSON