《Tab.1 Test set accuracy rate for MNIST of various methods》
本系列图表出处文件名:随高清版一同展现
《Convolutional Neural Network Based on Spatial Pyramid for Image Classification》
%
The MNIST handwritten digital data consists of 28×28 pixel gray images,and each contains a digit 0-9(10 classes).There are 60 000 training images and 10 000 test images in total.Without extra pre-processing,the image pixels are only divided by255 so that they are in the range[0 1].Tab.1 shows CNN has the result of 98.15%,and LeNet-5 has the result of 99%.However,our method achieves the result of 99.08%.The learning rate of all methods are set 1.We beat others methods in our experiment.All the methods we test are original networks.We don't use some effective optimization way,such as RELU,dropout.So,the method will get a higher accuracy in the future.
图表编号 | XD003876100 严禁用于非法目的 |
---|---|
绘制时间 | 2018.12.01 |
作者 | Gaihua Wang、Meng Lü、Tao Li、Guoliang Yuan、Wenzhou Liu |
绘制单位 | Hubei Collaborative Innovation Centre for High-Efficiency Utilization of Solar Energy,Hubei University of Technology、School of Electrical and Electronic Engineering,Hubei University of Technology、School of Electrical and Electronic Engineering,Hubei Unive |
更多格式 | 高清、无水印(增值服务) |