ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware

international conference on learning representations, 2019.

Cited by: 303|Bibtex|Views14|Links
EI

Abstract:

Neural architecture search (NAS) has a great impact by automatically designing effective neural network architectures. However, the prohibitive computational demand of conventional NAS algorithms (e.g. $10^4$ GPU hours) makes it difficult to emph{directly} search the architectures on large-scale tasks (e.g. ImageNet). Differentiable NAS c...More

Code:

Data:

Your rating :
0

 

Tags
Comments