torchvision

image and video datasets and models for torch deep learning

torchvision Permissive license BSD Active ★ 17,861 v0.28.0 released 2026-07-08

Install

torchvision on PyPI

pip

pip install torchvision

uv

uv add torchvision

poetry

poetry add torchvision

Package facts

License	BSD (permissive)
Python support	supports the current Python release (!=3.14.1,>=3.10)
Install friction	medium — platform-specific wheel
Runtime dependencies	3 — numpy, torch, pillow
Maintenance	actively maintained — 36 days since the last release
Last repo commit	2026-08-13
First released	2017-01-18
Popularity	one of the top 1,000 most-downloaded packages on PyPI (30-day window, as of 2026-08-13)
Known vulnerabilities	none known (OSV.dev, checked 2026-08-13)

Evidence: torchvision-0.28.0-cp310-cp310-macosx_14_0_arm64.whl; torchvision-0.28.0-cp310-cp310-manylinux_2_28_aarch64.whl; torchvision-0.28.0-cp310-cp310-manylinux_2_28_x86_64.whl; torchvision-0.28.0-cp310-cp310-win_amd64.whl; torchvision-0.28.0-cp311-cp311-macosx_14_0_arm64.whl; torchvision-0.28.0-cp311-cp311-manylinux_2_28_aarch64.whl; torchvision-0.28.0-cp311-cp311-manylinux_2_28_x86_64.whl; torchvision-0.28.0-cp311-cp311-win_amd64.whl; torchvision-0.28.0-cp312-cp312-macosx_14_0_arm64.whl; torchvision-0.28.0-cp312-cp312-manylinux_2_28_aarch64.whl; torchvision-0.28.0-cp312-cp312-manylinux_2_28_x86_64.whl; torchvision-0.28.0-cp312-cp312-win_amd64.whl; torchvision-0.28.0-cp313-cp313-macosx_14_0_arm64.whl; torchvision-0.28.0-cp313-cp313-manylinux_2_28_aarch64.whl; torchvision-0.28.0-cp313-cp313-manylinux_2_28_x86_64.whl; torchvision-0.28.0-cp313-cp313-win_amd64.whl; torchvision-0.28.0-cp314-cp314-macosx_14_0_arm64.whl; torchvision-0.28.0-cp314-cp314-manylinux_2_28_aarch64.whl; torchvision-0.28.0-cp314-cp314-manylinux_2_28_x86_64.whl; torchvision-0.28.0-cp314-cp314t-macosx_14_0_arm64.whl

About torchvision

from the package's own PyPI description — quoted content, verbatim

torchvision

total torchvision downloads (image) documentation (image)

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`	`>=3.10`, `<=3.14`
`2.12`	`0.27`	`>=3.10`, `<=3.14`
`2.11`	`0.26`...

Read as markdown · JSON record · Source repository · Homepage

AI interpretation — verify before relying

AI-generated interpretation of the package facts above; every digit, version, license, or vulnerability id it cites is grounded in the facts already shown on this page

Provides popular datasets, model architectures, and image transformations for computer vision tasks with PyTorch.

Medium install friction due to compiled dependencies on torch and pillow; actively maintained with recent releases and broad platform coverage across Python 3.10–3.14 and multiple OS/architecture wheels.

BSD permissive license allows commercial and private use with minimal restrictions; you must retain copyright and license notices in distributions.

Usage

pip install torchvision torch pillow numpy
import torchvision
from torchvision import transforms

Requires torch to be installed first; torchvision 0.28.0 requires torch 2.12 or compatible version.

Verdict: Actively maintained top-1000 package with no known vulnerabilities and permissive BSD licensing. Medium install friction is typical for ML libraries with compiled dependencies. Suitable for production computer vision work when torch version alignment is respected.

Needs verification

Whether pre-trained model weights have additional license restrictions beyond BSD (SWAG models noted as CC-BY-NC 4.0 in description).
Performance characteristics of pillow vs. pillow-simd as the image backend in typical workflows.

pytorch computer vision modelsimage dataset loading pytorchpretrained vision modelsimage transformations deep learningvideo datasets pytorchcomputer vision pytorch