aw_nas: A Modularized and Extensible NAS framework
This framework provides a flexible tool for researchers and practitioners in machine learning to explore and apply NAS algorithms more easily.
This paper introduces aw_nas, an open-source Python framework designed to implement and reproduce various Neural Architecture Search (NAS) algorithms. It allows users to experiment with different NAS algorithms across diverse applications such as classification, detection, and text modeling.
Neural Architecture Search (NAS) has received extensive attention due to its capability to discover neural network architectures in an automated manner. aw_nas is an open-source Python framework implementing various NAS algorithms in a modularized manner. Currently, aw_nas can be used to reproduce the results of mainstream NAS algorithms of various types. Also, due to the modularized design, one can simply experiment with different NAS algorithms for various applications with awnas (e.g., classification, detection, text modeling, fault tolerance, adversarial robustness, hardware efficiency, and etc.). Codes and documentation are available at https://github.com/walkerning/aw_nas.