北京大学学报自然科学版 ›› 2021, Vol. 57 ›› Issue (4): 790-794.DOI: 10.13209/j.0479-8023.2021.053

上一篇    

基于全局信息的卷积神经网络模型剪枝微调优化方法

孙文宇, 曹健,  李普, 刘瑞   

  1. 北京大学软件与微电子学院, 北京 102600
  • 收稿日期:2020-06-02 修回日期:2020-07-08 出版日期:2021-07-20 发布日期:2021-07-20
  • 通讯作者: 曹健, E-mail: caojian(at)ss.pku.edu.cn
  • 基金资助:
    国家自然科学基金(U20A20204)资助

Pruning and Fine-tuning Optimization Method of Convolutional Neural Network Based on Global Information

SUN Wenyu, CAO Jian, LI Pu, LIU Rui   

  1. School of Software and Microelectronics, Peking University, Beijing 102600
  • Received:2020-06-02 Revised:2020-07-08 Online:2021-07-20 Published:2021-07-20
  • Contact: CAO Jian, E-mail: caojian(at)ss.pku.edu.cn

摘要:

为解决因卷积神经网络模型规模大, 模型剪枝方法引起的精度下降问题, 提出一种模型剪枝微调优化方法。该方法引入原卷积神经网络模型权重全局信息至剪枝后模型, 使原模型信息体现在剪枝后模型的权重上, 提升剪枝后模型的精度。在图像分类任务和目标检测任务中的实验结果表明, 所提出的微调优化方法可获得更大的压缩率和更小的模型精度损失。

关键词: 卷积神经网络, 模型剪枝微调, 全局信息, 图像分类, 目标检测

Abstract:

In order to solve the problem that convolutional neural network is large and the accuracy loss of the model pruning method is relatively serious, a fine-tuning optimization method for model pruning is proposed. The global information of the original convolutional neural network model is introduced to the post-prune model to make it store the original model information which improves the accuracy of the model after pruning. Experimental results show that for the image classification tasks and target detection tasks, proposed fine-tuning optimization method can obtain greater compression ratio and smaller model accuracy loss. 

Key words: convolutional neural network, model pruning and fine-tuning, global information, image classification, object detection