PONAS: Progressive One-shot Neural Architecture Search for Very Efficient Deployment

11 Mar 2020Sian-Yao HuangWei-Ta Chu

We achieve very efficient deep learning model deployment that designs neural network architectures to fit different hardware constraints. Given a constraint, most neural architecture search (NAS) methods either sample a set of sub-networks according to a pre-trained accuracy predictor, or adopt the evolutionary algorithm to evolve specialized networks from the supernet... (read more)

PDF Abstract

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods used in the Paper