BriefGPT.xyz
Apr, 2014
利用卷积网络内的线性结构进行高效评估
Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
HTML
PDF
Remi Denton, Wojciech Zaremba, Joan Bruna, Yann LeCun, Rob Fergus
TL;DR
本文介绍了一种可以加速大型卷积神经网络测试时间评估的技术，通过利用卷积滤波器中的线性结构进行逼近计算，可以在保持模型准确率的同时，将CPU和GPU上的卷积层速度提高了2倍。
Abstract
We present techniques for speeding up the test-time evaluation of large
convolutional networks
, designed for
object recognition
tasks. These models deliver impressive accuracy but each image evaluation requires m
→