An Open Source Machine Learning Framework for Everyone

🦜🔗 The platform for reliable agents.

Robust Speech Recognition via Large-Scale Weak Supervision

Models and examples built with TensorFlow

Scrapy, a fast high-level web crawling & scraping framework for Python.

🌐 Jekyll is a blog-aware static site generator in Ruby

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

A toolkit for developing and comparing reinforcement learning algorithms.

Caffe: a fast open framework for deep learning.

The official Python library for the OpenAI API

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

Deep learning library featuring a higher-level API for TensorFlow.

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

An adversarial example library for constructing attacks, building defenses, and benchmarking both

Numenta Platform for Intelligent Computing is an implementation of Hierarchical Temporal Memory (HTM), a theory of intelligence based strictly on the neuroscience of the neocortex.

A Python-embedded modeling language for convex optimization problems.

A TypeScript chess library for chess move generation/validation, piece placement/movement, and check/checkmate/draw detection

Drivers and libraries for the Xbox Kinect device on Windows, Linux, and OS X

Serverless Python

Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.

Code for reproducing results in "Glow: Generative Flow with Invertible 1x1 Convolutions"

MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.

Massively parallel rigidbody physics simulation on accelerator hardware.

Collection of reinforcement learning algorithms

Multi-layer Recurrent Neural Networks (LSTM, RNN) for character-level language models in Python using Tensorflow

Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning

A large-scale benchmark and learning environment.

Assignments for CS294-112.