| 基于字典学习的卷积神经网络压缩方法 |
| |
| 引用本文： | 耿旭,张永辉,张健.基于字典学习的卷积神经网络压缩方法[J].计算机工程与设计,2020,41(4):1024-1028. |
| |
| 作者姓名： | 耿旭 张永辉 张健 |
| |
| 作者单位： | 海南大学信息与通信工程学院,海南海口570228;海南大学信息与通信工程学院,海南海口570228;海南大学信息与通信工程学院,海南海口570228 |
| |
| 基金项目： | 海南省自然科学基金;海南省科技厅项目 |
| |
| 摘 要： | 为解决深度卷积神经网络模型占用存储空间较大的问题,提出一种基于K-SVD字典学习的卷积神经网络压缩方法。用字典中少数原子的线性组合来近似表示单个卷积核的参数,对原子的系数进行量化,存储卷积核参数时,只须存储原子的索引及其量化后的系数,达到模型压缩的目的。在MNIST数据集上对LeNet-C5和CIFAR-10数据集上对DenseNet的压缩实验结果表明,在准确率波动不足0.1%的情况下,将网络模型占用的存储空间降低至12%左右。
|
| 关 键 词： | 卷积神经网络 字典学习 压缩 量化 稀疏矩阵 |
Convolutional neural network compression method based on dictionary learning |
| |
| GENG Xu,ZHANG Yong-hui,ZHANG Jian.Convolutional neural network compression method based on dictionary learning[J].Computer Engineering and Design,2020,41(4):1024-1028. |
| |
| Authors: | GENG Xu ZHANG Yong-hui ZHANG Jian |
| |
| Affiliation: | (School of Information and Communication Engineering,Hainan University,Haikou 570228,China) |
| |
| Abstract: | To solve the problem that the deep convolutional neural network model occupies a large storage space,a convolutional neural network compression method based on K-SVD dictionary learning was proposed.The main idea was to approximate the parameters of a single convolution kernel by linear combination of a few atoms in the dictionary to achieve the purpose of model compression.The compression experiments of LeNet-C5 on the MNIST datasets and DenseNet on CIFAR-10 datasets show that the space occupied by the storage network model is reduced to about 12%when the accuracy fluctuation is less than 0.1%. |
| |
| Keywords: | convolutional neural network dictionary learning compression quantization sparse matrix |
| 本文献已被 维普 万方数据 等数据库收录！ |
|
