An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.

AutoML library for deep learning

Differentiable architecture search for convolutional and recurrent networks

PyTorch implementation of "Efficient Neural Architecture Search via Parameters Sharing"

Automated Deep Learning: Neural Architecture Search Is Not the End (a curated list of AutoDL resources and an in-depth analysis)

Automated deep learning algorithms implemented in PyTorch.

Automated Machine Learning on Kubernetes

An autoML framework & toolkit for machine learning on graphs.

Fast & Simple Resource-Constrained Learning of Deep Network Structure

Genetic neural architecture search with Keras

Slimmable Networks, AutoSlim, and Beyond, ICLR 2019, and ICCV 2019

Implementation of: "Exploring Randomly Wired Neural Networks for Image Recognition"

a distributed Hyperband implementation on Steroids

[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning

NASLib is a Neural Architecture Search (NAS) library for facilitating NAS research for the community by providing interfaces to several state-of-the-art NAS search spaces and optimizers.

[ICLR 2020] "FasterSeg: Searching for Faster Real-time Semantic Segmentation" by Wuyang Chen, Xinyu Gong, Xianming Liu, Qian Zhang, Yuan Li, Zhangyang Wang

An optimization and data collection toolbox for convenient and fast prototyping of computationally expensive models.

Accelerate your Neural Architecture Search (NAS) through fast, reproducible and modular research.

[ICCV 2019] "AutoGAN: Neural Architecture Search for Generative Adversarial Networks" by Xinyu Gong, Shiyu Chang, Yifan Jiang and Zhangyang Wang

Basic implementation of [Neural Architecture Search with Reinforcement Learning](https://arxiv.org/abs/1611.01578).