tesatory

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

pytorch-lightning

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

fastText

Library for fast text representation and classification.

Paddle

PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）

detr

End-to-End Object Detection with Transformers

ParlAI

A framework for training and evaluating AI models on a variety of openly available dialogue datasets.

visdom

A flexible tool for creating, organizing, and sharing visualizations of live, rich data. Supports Torch and Numpy.

deep-photo-styletransfer

Code and data for paper "Deep Photo Style Transfer": https://arxiv.org/abs/1703.07511

deep-learning-models

Keras code and weights files for popular deep learning models.

pytorch-a2c-ppo-acktr-gail

PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).

reinforcement-learning

Minimal and Clean Reinforcement Learning Examples

WassersteinGAN

noreward-rl

[ICML 2017] TensorFlow code for Curiosity-driven Exploration for Deep Reinforcement Learning

debugger.lua

A dependency free, embeddable debugger for Lua in a single file (.lua or .h)

modular_rl

Implementation of TRPO and related algorithms

adaptive-span

Transformer training code for sequential tasks

learning-to-communicate

Learning to Communicate with Deep Multi-Agent Reinforcement Learning

pytorch-trpo

PyTorch implementation of Trust Region Policy Optimization

unlikelihood_training

Neural Text Generation with Unlikelihood Training

nips2016

A list of resources for all invited talks, tutorials, workshops and presentations at NIPS 2016

CommNet

Neural network model, suitable for multi-agent learning. https://arxiv.org/abs/1605.07736

transformer-sequential

Trains Transformer model variants. Data isn't shuffled between batches.

RAM

A framework to study AI models in Reasoning, Alignment, and use of Memory (RAM).

psketch

Modular multitask reinforcement learning with policy sketches

gym-doom

Gym - Doom environments based on VizDoom.

ReinforcementLearning

gym-starcraft

StarCraft: BroodWars OpenAI Gym environment

Multiple-smi

Python bindings for pyNVML and psutil library over network

CommNet

PyTorch implementation of CommNet

gym

A toolkit for developing and comparing reinforcement learning algorithms.