BriefGPT.xyz
Feb, 2019
AutoQ: 自动化的基于内核的神经网络量化
AutoQB: AutoML for Network Quantization and Binarization on Mobile Devices
HTML
PDF
Qian Lou, Lantao Liu, Minje Kim, Lei Jiang
TL;DR
本论文提出了一种基于分层深度强化学习的自动量化技术 AutoQ,可以自动搜索每个权重核的量化位宽,以及每个激活层的另一个量化位宽,并极大地提高了卷积神经网络的推断性能,同时保持了推断精度。
Abstract
In this paper, we propose a hierarchical
deep reinforcement learning
(DRL)-based AutoML framework, AutoQB, to automatically explore the design space of channel-level
network quantization
and binarization for hard
→