Machine Vision

State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow

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

Fast, flexible, and advanced augmentation library for deep learning, computer vision, and medical imaging. Albumentations offers a wide range of transformations for both 2D (images, masks, bboxes, keypoints) and 3D (volumes, volumetric masks, keypoints) data, with optimized performance and seamless integration into ML workflows.

John Snow Labs Spark NLP is a natural language processing library built on top of Apache Spark ML. It provides simple, performant & accurate NLP annotations for machine learning pipelines, that scale easily in a distributed environment.

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

QUick and DIrty Domain Adaptation

Image augmentation library for deep neural networks

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.

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.

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.

Light Weight Toolkit for Bounding Boxes

Packaged version of the Yolov5 object detector

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.

The realtime communication library for Python

BoxMOT: pluggable SOTA tracking modules for segmentation, object detection and pose estimation models

Catalyst. Accelerated deep learning R&D with PyTorch.

Image Acquisition Library for GenICam-based Machine Vision System

Pymba is a Python wrapper for Allied Vision's Vimba C API.

TorchSeg: Semantic Segmentation models for PyTorch

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

RF100-VL Dataset Interface

RF-DETR

[DEPRECATED] An inference runtime offering GPU-class performance on CPUs and APIs to integrate ML into your application

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

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

Easily turn a set of image urls to an image dataset

Computer vision models for PyTorch

HuggingFace utilities for Ultralytics/YOLOv8.

🔥LIT: The Learning Interpretability Tool

A rastervision plugin that adds geospatial machine learning pipelines

Viewing and rendering of sequences of 3D data.

Easily computing clip embeddings and building a clip retrieval system with them

A research and production integrated edge-cloud library for federated/distributed machine learning at anywhere at any scale.

Automatically built Ultralytics package with python-opencv-headless dependency instead of python-opencv

PythonAIBrain is a versatile, plug-and-play Python package designed to help you build offline intelligent AI assistants and applications effortlessly. With modules covering speech recognition, text-to-speech, image generation, natural language understanding, and more, PythonAIBrain lets you create powerful AI solutions without deep expertise or complex setup. Whether you’re a beginner or an experienced developer, get ready to bring your AI ideas to life quickly and efficiently.

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.

Video streaming inference framework, integrating image algorithms and models for real-time/offline video structuring

Declarative machine learning: End-to-end machine learning pipelines using data-driven configurations.

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.

[DEPRECATED] Neural network model repository for highly sparse and sparse-quantized models with matching sparsification recipes

Defining the Future of 3D Machine Vision

Find issues in image datasets

Torchreid-Pip: Deep learning person re-identification in PyTorch.

AI Data Infrastructure: Declarative, Multimodal, and Incremental

Deploy inference models served for Artificial Intelligence solutions including but not limited to Pixano.

A computer vision pipeline for the semantic exploration of maps/images at scale

doc2text drastically improves the extraction of text from images by fixing resolution, text area (crop), and skew.

Agnostic Computer Vision Framework