Clean, Robust, and Unified PyTorch implementation of popular Deep Reinforcement Learning (DRL) algorithms (Q-learning, Duel DDQN, PER, C51, Noisy DQN, PPO, DDPG, TD3, SAC, ASL)

C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

Automatic architecture search and hyperparameter optimization for PyTorch

Code for Neural Architecture Search without Training (ICML 2021)

[ICLR 2020] Once for All: Train One Network and Specialize it for Efficient Deployment

Mobile vision models and code

FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search

PaddlePaddle High Performance Deep Learning Inference Engine for Mobile and Edge (飞桨高性能深度学习端侧推理引擎）

ProxylessNAS-Pytorch

🔥 TensorFlow Code for technical report: "YOLOv3: An Incremental Improvement"

[ICLR 2019] ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware