Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Ultralytics YOLO 🚀 for SOTA object detection, instance segmentation, semantic segmentation, depth estimation, classification, pose estimation, oriented object detection, and multi-object tracking.
Typed Python SDK for the Ultralytics Platform API
Low level implementations for computer vision in Rust
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.
A set of easy-to-use utils that will come in handy in any Computer Vision project
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.
RF-DETR
QUick and DIrty Domain Adaptation
Image augmentation library for deep neural networks
A toolkit for making real world machine learning and data analysis applications
A unified library for object tracking featuring clean room re-implementations of leading multi-object tracking algorithms
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 (volume data, volumetric masks, keypoints) data, with optimized performance and seamless integration into ML workflows. Available under AGPL-3.0-only or a commercial license with agreed coverage for your team, products, and deployments.
RF100-VL Dataset Interface
The unified multimodal backend agents build with. Database, orchestration, and serving in one Python file.
A toolkit for making real world machine learning and data analysis applications
HPSv3: Towards Wide-Spectrum Human Preference Score - A VLM-based preference model for image quality assessment
Torchreid-Pip: Deep learning person re-identification in PyTorch.
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.
Packaged version of the Yolov5 object detector
Ultralytics YOLO 🚀 for SOTA computer vision in server, container, and headless environments.
Image Acquisition Library for GenICam-based Machine Vision System
BoxMOT: pluggable SOTA tracking modules for segmentation, object detection and pose estimation models
Easily turn a set of image urls to an image dataset
Python SDK and CLI for Pictograph: real-time vision tools for agents and developers. SAM3 labeling, RF-DETR and YOLOX training, TensorRT GPU endpoints, and live video streams.
Computer vision models for PyTorch
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.
Versioned dataset-head contracts and extension validation for the Euler ecosystem
RF-DETR+ Extension Package
Fast async image downloader for Python: self-tuning, rate-limit aware, every file accounted for.
Ultralytics HUB Client SDK.
The realtime communication library for Python
Viewing and rendering of sequences of 3D data.
Find issues in image datasets
A lightweight, unified, cross-platform desktop application for AI-assisted annotation of text, image, video, and multimodal data.
Automatically built Ultralytics package with python-opencv-headless dependency instead of python-opencv
Vision and speech interfaces for human-machine interaction
A Python library for multi-object tracking data structures and algorithms
Sovereign, zero-heavy-dependency Machine Learning, Deep Learning, Computer Vision, NLP, Audio, Generative AI, GNN, Time Series, XAI, and AutoML toolkit built from first principles in pure NumPy and SciPy.
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.
Image augmentation library for deep neural networks
Defining the Future of 3D Machine Vision
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.
Professional YOLO training library with MLOps integration and TensorRT accelerated inference
Catalyst. Accelerated deep learning R&D with PyTorch.
🔥LIT: The Learning Interpretability Tool
Python SDK for B3OS beta: vision (web pages and browsers), render, infer, sandboxes, routines, actions and vault, on the machine that runs the model.
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.
Image processing as Polars expressions: decode, transform and analyse images in a DataFrame column, in Rust, on every core.