BriefGPT.xyz
Mar, 2021
NetAdaptV2: 带快速超级网络训练和架构优化的高效神经网络架构搜索
NetAdaptV2: Efficient Neural Architecture Search with Fast Super-Network Training and Architecture Optimization
HTML
PDF
Tien-Ju Yang, Yi-Lun Liao, Vivienne Sze
TL;DR
本文提出NetAdaptV2,通过三项创新工作平衡各个步骤的时间并支持非可微分搜索指标,进而加速神经结构搜索并提高神经网络性能。
Abstract
neural architecture search
(NAS) typically consists of three main steps: training a super-network, training and evaluating sampled
deep neural networks
(DNNs), and training the discovered DNN. Most of the existin
→