Directory

Google's end-to-end open-source platform for machine learning, from research to production.

Meta's Python-first deep-learning framework with strong GPU acceleration and dynamic graphs.

Computer vision and image-processing library with C++, Python, and Java interfaces.

Optical character recognition engine that extracts text from images.

Python framework for YOLO models doing object detection, segmentation, classification, pose estimation, and tracking.

Meta's image segmentation model with inference code, pretrained checkpoints, and example notebooks.

Python library for programmatically creating precise mathematical animations and diagrams.

PyTorch library from Facebook AI Research for object detection, segmentation, and other visual recognition tasks.

Neural network from OpenAI that links images and text to predict the most relevant caption for an image.

OpenMMLab PyTorch toolbox and benchmark for object detection and instance segmentation models.

Gradient boosting library for Python, R, Java, Scala and more, running on single machines or distributed clusters.

Platform for managing the machine learning lifecycle including tracking, evaluation, deployment and model registry.

Library of models, datasets and tools for applying end-to-end machine learning to real-world robotics.

Library for forecasting time series data with multiple seasonality and linear or non-linear growth.

Library for training transformer language models with reinforcement learning, including SFT, PPO, and DPO.

Gradient boosting framework based on decision tree algorithms for ranking, classification, and other ML tasks.

Datasets, model architectures, and image transforms for computer vision built on PyTorch.

Web-based interactive development environment for notebooks, code, and data across many languages.

Free, cross-platform desktop GIS for creating, editing, analysing, and publishing geospatial data.

Library for building visual, block-based programming editors, used in Scratch-like coding tools.