计算机工程与应用2019，Vol.55Issue(16)：25-35,11.DOI:10.3778/j.issn.1002-8331.1903-0340
轻量化卷积神经网络技术研究
Research on Lightweight Convolutional Neural Network Technology
毕鹏程 1罗健欣 1陈卫卫1
作者信息
- 1. 中国人民解放军陆军工程大学 指挥控制工程学院,南京 210007
- 折叠
摘要
Abstract
In order to better apply the convolutional neural network model to mobile and embedded devices, it is neces-sary to reduce the amount of model parameters and reduce computational complexity. Firstly, several popular solutions are briefly introduced. Next, six lightweight convolutional neural network models are elaborated, showing the computa-tional complexity and parameter quantities of different network computing methods. The core building blocks of the model, the overall network structure and innovations are discussed. The classification accuracy of each network and conventional convolutional network on the ImageNet dataset is analyzed. Furthermore, comparing the techniques of lightening the weight of each network, the conclusion is drawn that the direct index is used instead of the indirect index when designing the model. At the same time, the importance of the residual structure to ensure the accuracy of the lightweight model is found. Finally, the development prospect of lightweight convolutional neural network is prospected.关键词
卷积神经网络(CNN)/轻量化/卷积方式Key words
Convolutional Neural Network(CNN)/ lightweight/ convolution method分类
信息技术与安全科学引用本文复制引用
毕鹏程,罗健欣,陈卫卫..轻量化卷积神经网络技术研究[J].计算机工程与应用,2019,55(16):25-35,11.
