pytorch/vision
Datasets, Transforms and Models specific to Computer Vision
Build and train computer vision models efficiently by providing popular datasets, pre-trained model architectures, and common image manipulation tools. You input raw images or image datasets, apply transformations, and get trained models or processed image data for tasks like object recognition or image classification. This is for machine learning engineers, data scientists, or researchers working on visual intelligence applications.
17,563 stars. Used by 357 other packages. Actively maintained with 13 commits in the last 30 days. Available on PyPI.
Use this if you are developing computer vision systems and need standardized ways to handle image data, apply transformations, and leverage established model architectures.
Not ideal if your primary focus is on natural language processing, tabular data analysis, or general-purpose deep learning without a strong computer vision component.
Stars
17,563
Forks
7,226
Language
Python
License
BSD-3-Clause
Category
Last pushed
Mar 13, 2026
Commits (30d)
13
Dependencies
3
Reverse dependents
357
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.
Community Discussion
Recent Releases
Related frameworks
opencv/opencv
Open Source Computer Vision Library
kornia/kornia
🐍 Geometric Computer Vision Library for Spatial AI
ermig1979/Simd
C++ image processing and machine learning library with using of SIMD: SSE, AVX, AVX-512, AMX ...
open-edge-platform/training_extensions
Train, Evaluate, Optimize, Deploy Computer Vision Models via OpenVINO™
supervisely/supervisely
Supervisely SDK for Python - convenient way to automate, customize and extend Supervisely...