DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

An Open Source Machine Learning Framework for Everyone

Cross-platform, customizable ML solutions for live and streaming media.

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

Convolutional Neural Networks

Suite of tools for deploying and training deep learning models using the JVM. Highlights include model import for keras, tensorflow, and onnx/pytorch, a modular and tiny c++ library for running mat…

Open standard for machine learning interoperability

A C++ standalone library for machine learning

Relax! Flux is the ML library that doesn't make you tensor

TensorFlow for macOS 11.0+ accelerated using Apple's ML Compute framework.

Core ML tools contain supporting tools for Core ML model conversion, editing, and validation.

A WebGL accelerated JavaScript library for training and deploying ML models.

Code for the paper "Jukebox: A Generative Model for Music"

Generates video game music using neural networks.

A clean implementation based on AlphaZero for any game in any framework + tutorial + Othello/Gobang/TicTacToe/Connect4 and more

Go engine with no human-provided knowledge, modeled after the AlphaGo Zero paper.

Code for Motion Representations for Articulated Animation paper

This repository contains the source code for the paper First Order Motion Model for Image Animation

Theano was a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It is being continued as PyTensor: www.github.…

Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.

Datasets, Transforms and Models specific to Computer Vision

The Shark Machine Leaning Library. See more:

Deep Learning for humans

A toolkit for developing and comparing reinforcement learning algorithms.

Retro Games in Gym

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

Code samples for my book "Neural Networks and Deep Learning"

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

High-efficiency floating-point neural network inference operators for mobile, server, and Web