# pytorch/vision

Datasets, Transforms and Models specific to Computer Vision

Repository: https://github.com/pytorch/vision
Canonical: https://ross.abutalabs.com/products/vision
Homepage: https://pytorch.org/vision
Language: Python
License: BSD-3-Clause
License Family: permissive
Topics: computer-vision, machine-learning
Last push: 2026-08-26T14:37:48+00:00

## Health v2 (maintenance only)
Score: 93/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 80, longevity 100
- inputs: {"age_days": 3584, "days_push": 7, "days_rel": 56, "gap_med": 55.5, "n_releases_24m": 13}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 17885, forks 7250 (observed 2026-08-28T04:11:20.511457+00:00)

## What it is
torchvision is the official PyTorch companion library providing datasets, model architectures, and image/video transformations for computer vision. It includes pretrained models and utilities that integrate tightly with PyTorch.

## Use cases
- load standard vision datasets like CIFAR and ImageNet
- apply image transforms and augmentations for training
- use pretrained models like ResNet for image classification
- run object detection and segmentation models
- read and decode images and videos into tensors

## When to choose
- you are training or evaluating computer vision models in PyTorch
- you need pretrained vision model architectures with weights
- you want standard dataset loaders and augmentation pipelines

## When to avoid
- you use TensorFlow, JAX, or another non-PyTorch framework
- you need general-purpose image editing rather than ML pipelines

## Facets
- artifact type: library
- maturity: stable
- function: machine-learning, image-processing, computer-vision, data-science
- domain: computer-vision, machine-learning, deep-learning, image-processing
- platform: python, cross-platform
- tags: torchvision, pytorch, datasets, transforms, pretrained-models, image-classification, object-detection, video, gpu

## Member repositories
- pytorch/vision (main) score 93

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:20.511457+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:02:17.730114+00:00, confidence not recorded.
  - readme: https://github.com/pytorch/vision (fetched 2026-08-28T04:11:20.511457+00:00, sha ec68b4fccd92)
  - homepage: https://pytorch.org/vision (fetched 2026-08-29T08:00:24.695497+00:00, sha 5404dfba40c9)
- Data as of 2026-08-30T08:39:29.467469+00:00.