Computer Vision Python Packages

datasets

🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools

torchvision

Datasets, Transforms and Models specific to Computer Vision

scikit-image

Image processing in Python

ultralytics

Ultralytics YOLO 🚀

ultralytics-thop

Profile PyTorch models for FLOPs and parameters, helping to evaluate computational efficiency and memory usage.

roboflow

The official Roboflow Python package. Manage your datasets, models, and deployments. Roboflow has everything you need to build a computer vision application.

pytorch-metric-learning

The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

kornia

🐍 Geometric Computer Vision Library for Spatial AI

kornia-rs

🦀 Low-level 3D Computer Vision library in Rust

mediapipe

Cross-platform, customizable ML solutions for live and streaming media.

open-clip-torch

An open source implementation of CLIP.

rerun-sdk

Visualize, query, and stream to train on multimodal robotics data.

openvino

OpenVINO™ is an open source toolkit for optimizing and deploying AI inference

autogluon-tabular

Fast and Accurate ML in 3 Lines of Code

supervision

We write your reusable computer vision tools. 💜

autogluon-core

Fast and Accurate ML in 3 Lines of Code

autogluon-features

Fast and Accurate ML in 3 Lines of Code

autogluon-common

Fast and Accurate ML in 3 Lines of Code

inference-gpu

Turn any computer or edge device into a command center for your computer vision projects.

inference-cli

Turn any computer or edge device into a command center for your computer vision projects.

segmentation-models-pytorch

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

mmengine

OpenMMLab Foundational Library for Training Deep Learning Models

faster-coco-eval

Continuation of an abandoned project fast-coco-eval

autogluon-timeseries

Fast and Accurate ML in 3 Lines of Code