BriefGPT.xyz
Apr, 2015
PerforatedCNNs: 通过消除冗余卷积加速
PerforatedCNNs: Acceleration through Elimination of Redundant Convolutions
HTML
PDF
Michael Figurnov, Dmitry Vetrov, Pushmeet Kohli
TL;DR
通过循环穿孔技术，我们提出一种降低卷积神经网络在低功耗设备如手机上计算成本的新方法，可以将现代卷积网络的速度提高2倍至4倍，这种方法还可以补充最近由Zhang等人提出的加速方法。
Abstract
This paper proposes a novel approach to reduce the computational cost of evaluation of
convolutional neural networks
, a factor that has hindered their deployment in low-power devices such as mobile phones. Our method is inspired by the
→