计算机应用与软件2018，Vol.35Issue(3)：177-181,5.DOI:10.3969/j.issn.1000-386x.2018.03.034
基于CIFAR-10的图像分类模型优化
THE OPTIMIZATION OF IMAGE CATEGORIZATION MODEL BASED ON CIFAR-10
摘要
Abstract
With the research and application of convolutional neural network in image processing, the accuracy of image classification has been greatly improved, but the problem of over-fitting has always existed and has become an important factor affecting the classification accuracy.In this paper,starting from the source of over-fitting,we increased the amount of data and reduced the number of parameters in order to reduce the over-fitting purposes.Based on the classical model LeNet-5, this paper made input data enhancement and split the convolution layer to reduce the parameters.At the same time,it used L1 and L2 mixed constraints and adjusted the proportion of the two to achieve the best effect.Experimental results showed that the optimized network achieved 91.2%accuracy on the CIFAR-10 dataset. Compared with the original LeNet-5 model,it was increased by 23%.It greatly reduced the over-fitting,and improved the classification accuracy of the model.关键词
过拟合/数据增强/正则约束/卷积拆分/准确率Key words
Over-fitting/Data enhancement/Regular constraints/Convolutional split/Accuracy分类
信息技术与安全科学引用本文复制引用
张占军,彭艳兵,程光..基于CIFAR-10的图像分类模型优化[J].计算机应用与软件,2018,35(3):177-181,5.基金项目
国家自然科学基金项目(61602114) （61602114）
国家高技术研究发展计划(2015AA015603). （2015AA015603）
