Machine Vision

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

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.

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

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

Light Weight Toolkit for Bounding Boxes

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.

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.

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.

Ultralytics HUB Client SDK.

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

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

Image Acquisition Library for GenICam-based Machine Vision System

Catalyst. Accelerated deep learning R&D with PyTorch.

RF-DETR

The realtime communication library for Python

RF100-VL Dataset Interface

TorchSeg: Semantic Segmentation models for PyTorch

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

Easily turn a set of image urls to an image dataset

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

Computer vision models for PyTorch

A rastervision plugin that adds geospatial machine learning pipelines

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

HuggingFace utilities for Ultralytics/YOLOv8.

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

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

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

Defining the Future of 3D Machine Vision

🔥LIT: The Learning Interpretability Tool

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.

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

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.

AI Data Infrastructure: Declarative, Multimodal, and Incremental

Find issues in image datasets

Agnostic Computer Vision Framework

Image dataset analyzer using image embedding models and clustering methods.

Python Tools for Visual Dataset Transformation

Viewing and rendering of sequences of 3D data.

Training utility library and config manager for Granular Machine Vision research

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

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

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

Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models

:warning: The `yolov8` package is a placeholder, not the official Ultralytics version. Please install the official `ultralytics` package via `pip install ultralytics` instead.