Computer Vision

Ultralytics YOLO 🚀 for SOTA object detection, multi-object tracking, instance segmentation, pose estimation and image classification.

Fast, flexible, and advanced image augmentation library for deep learning and computer vision. Albumentations offers a wide range of transformations for images, masks, bounding boxes, and keypoints, with optimized performance and seamless integration into ML workflows.

Open Source Differentiable Computer Vision Library for PyTorch

Low level implementations for computer vision in Rust

High-performance image processing functions for deep learning and computer vision.

A set of easy-to-use utils that will come in handy in any Computer Vision project

Basic face library

Collection of common code shared among different research projects in FAIR computer vision team

QUick and DIrty Domain Adaptation

Image augmentation library for deep neural networks

A series of convenience functions to make basic image processing functions such as translation, rotation, resizing, skeletonization, displaying Matplotlib images, sorting contours, detecting edges, and much more easier with OpenCV and both Python 2.7 and Python 3.

Video scene cut/shot detection program and Python library.

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration

Open Source Image and Video Super-Resolution Toolbox

Microsoft Azure Cognitive Services Computer Vision Client Library for Python

The Rerun Logging SDK

OpenMMLab Detection Toolbox and Benchmark

A toolkit for making real world machine learning and data analysis applications

With no prior knowledge of machine learning or device-specific deployment, you can deploy a computer vision model to a range of devices and environments using Roboflow Inference.

Real-ESRGAN aims at developing Practical Algorithms for General Image Restoration

Light Weight Toolkit for Bounding Boxes

OpenMMLab Computer Vision Foundation

With no prior knowledge of machine learning or device-specific deployment, you can deploy a computer vision model to a range of devices and environments using Roboflow Inference CLI.

Industry-strength computer Vision extensions for Keras.

Savant Rust core functions library

FiftyOne: the open-source tool for building high-quality datasets and computer vision models

Automation with Computer Vision for Python

With no prior knowledge of machine learning or device-specific deployment, you can deploy a computer vision model to a range of devices and environments using Roboflow Inference.

OpenMMLab Computer Vision Foundation

Document Text Recognition (docTR): deep Learning for high-performance OCR on documents.

Open MMLab Semantic Segmentation Toolbox and Benchmark

OpenMMLab Pose Estimation Toolbox and Benchmark.

SuperGradients

A toolkit for making real world machine learning and data analysis applications

Savant Rust core functions library

OpenMMLab Image Classification Toolbox and Benchmark

Catalyst. Accelerated deep learning R&D with PyTorch.

Skeletonize densely labeled image volumes.

With no prior knowledge of machine learning or device-specific deployment, you can deploy a computer vision model to a range of devices and environments using Roboflow Inference.

Ultralytics HUB Client SDK.

AI2-THOR: A Near Photo-Realistic Interactable Framework for Embodied AI Agents

This is the module for detecting and classifying text on rama pictures

A lightweight Computer Vision library for high-performance AI research - Modern Computer Vision on the Fly.

Computer Vision Helping Library

Mahotas: Computer Vision Library

OpenMMLab Model Pretraining Toolbox and Benchmark

Provides spatial maths capability for Python.

Industry-strength computer Vision extensions for Keras.

An open source framework for deep learning on satellite and aerial imagery

High-performance cross-platform Video Processing Python framework powerpacked with unique trailblazing features.