pytorch/vision
Datasets, Transforms and Models specific to Computer Vision
Provides pre-trained model architectures (ResNet, Vision Transformers, etc.) alongside modular image transformations and popular benchmark datasets (CIFAR, ImageNet, COCO) that integrate seamlessly with PyTorch's tensor operations. Supports multiple image backends including Pillow and Pillow-SIMD for efficient data loading, with strict version alignment to PyTorch releases ensuring API stability.
17,563 stars and 30,251,303 monthly downloads. Used by 356 other packages. Actively maintained with 18 commits in the last 30 days. Available on PyPI.
Stars
17,563
Forks
7,226
Language
Python
License
BSD-3-Clause
Category
Last pushed
Mar 13, 2026
Monthly downloads
30,251,303
Commits (30d)
18
Dependencies
3
Reverse dependents
356
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/pytorch/vision"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
opencv/opencv
Open Source Computer Vision Library
kornia/kornia
🐍 Geometric Computer Vision Library for Spatial AI
supervisely/supervisely
Supervisely SDK for Python - convenient way to automate, customize and extend Supervisely...
open-edge-platform/training_extensions
Train, Evaluate, Optimize, Deploy Computer Vision Models via OpenVINO™
ermig1979/Simd
C++ image processing and machine learning library with using of SIMD: SSE, AVX, AVX-512, AMX ...