Skip to main navigation Skip to search Skip to main content

A convolutional neural network based on optimized structure and its lightweighting

  • Jinyong Deng*
  • , Zhiheng Zhao
  • , Yang Liu
  • , Yongzhe Chen
  • , Zhefan Zhang
  • , Yu Zhang
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In this paper, we design a convolutional neural network based on the ideas of depthwise separable convolution and inverted residual module. The scaling factor of BN layer is used as a measure for channel pruning of the network model to compress it. By analyzing the layer-by-layer pruning process of conventional convolution, the layer-by-layer pruning method with depthwise separable convolution and inverted residual structure is proposed to prune the channels of the network model, and finally, the channel pruning strategy of classification simplification network is developed. Tests on the selected dataset showed that the classification accuracy of the pruned and fine-tuned network model is 97.7% when the pruning rate is 0.7.

Original languageEnglish
Title of host publicationSecond International Conference on Advanced Algorithms and Signal Image Processing, AASIP 2022
EditorsKannimuthu Subramaniyam
PublisherSPIE
ISBN (Electronic)9781510660571
DOIs
StatePublished - 2022
Externally publishedYes
Event2nd International Conference on Advanced Algorithms and Signal Image Processing, AASIP 2022 - Hulun Buir, China
Duration: 19 Aug 202221 Aug 2022

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume12475
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

Conference2nd International Conference on Advanced Algorithms and Signal Image Processing, AASIP 2022
Country/TerritoryChina
CityHulun Buir
Period19/08/2221/08/22

Keywords

  • Convolutional neural network
  • channel pruning
  • depthwise separable convolution
  • inverted residual structure

Fingerprint

Dive into the research topics of 'A convolutional neural network based on optimized structure and its lightweighting'. Together they form a unique fingerprint.

Cite this