#3838th of 56 in ML frameworks and libraries
vision
PyTorch library of vision datasets, model architectures and image transforms
- Stars
- 17.9k
- License
- BSD-3-Clause
- Last commit
- Oct 2026
- Last release
- Sep 2026
- Language
- Python
Missed the latest GitHub check; these facts may be older.
Overview
torchvision is the computer vision companion package to PyTorch. It provides dataset loaders, pre-trained model architectures and image transformations, working on torch tensors or PIL images (Pillow or Pillow-SIMD). Each release is paired with a specific torch version, for example torchvision 0.28 with torch 2.13 on Python 3.10 to 3.14.
Who it is for: PyTorch users building or training computer vision models
Strengths
- Maintained in the pytorch organization, with releases matched to each torch version
- Supports torch tensor and PIL image backends, with optional Pillow-SIMD
- Bundles datasets, model architectures and transforms in one package
- API reference published on pytorch.org
Weaknesses
- Each release only works with its matching torch version
- Requires PyTorch; not usable with other tensor frameworks
- Some pre-trained weights have separate licenses, e.g. SWAG is CC-BY-NC 4.0
- Dataset loaders only download public data; license checks are left to the user
What it needs
- Needs torch, Pillow (optional Pillow-SIMD)
- Models: PyTorch, torch tensors, PIL images
Also in ML frameworks and libraries
See all 56| Rank | Project | Score |
|---|---|---|
| 1 | transformersPython library defining open models for text, vision, audio and multimodal tasks | 95 out of 100 |
| 2 | pytorchPython tensor library with GPU support and tape-based autograd for deep learning | 94 out of 100 |
| 3 | ultralyticsPython library and CLI for training and running YOLO vision models | 92 out of 100 |
| #4 | supervisionPython toolkit for loading, annotating and counting computer vision detections | 89 out of 100 |
| #5 | pytorch-image-modelsPyTorch library of image models, pretrained weights and reference training scripts | 89 out of 100 |