MATLAB中的卷积神经网络。再增加一层

我想做的是证明一个事实，如果我在CNN中增加一层，准确度会更高

代码在下面

此代码来自

我正处于CNN的初级阶段，试图扩展更多的层面，包括 卷积和池化阶段。我试过几种方法，但似乎都不管用。有人能告诉我如何再扩展一层吗

谢谢。下面是代码

主要功能代码：

clear all; close all; clc;

maxtrain = 10000;
iter = 10;
eta = 0.01;

%% Data Load

trlblid = fopen('train-labels-idx1-ubyte');
trimgid = fopen('train-images-idx3-ubyte');
tslblid = fopen('t10k-labels-idx1-ubyte');
tsimgid = fopen('t10k-images-idx3-ubyte');

% read train labels
fread(trlblid, 4);
numtrlbls = toint(fread(trlblid, 4));
trainlabels = fread(trlblid, numtrlbls);

% read train data
fread(trimgid, 4);
numtrimg = toint(fread(trimgid, 4));
trimgh = toint(fread(trimgid, 4));
trimgw = toint(fread(trimgid, 4));
trainimages = permute(reshape(fread(trimgid,trimgh*trimgw*numtrimg),trimgh,trimgw,numtrimg), [2 1 3]);

% read test labels
fread(tslblid, 4);
numtslbls = toint(fread(tslblid, 4));
testlabels = fread(tslblid, numtslbls);

% read test data
fread(tsimgid, 4);
numtsimg = toint(fread(tsimgid, 4));
tsimgh = toint(fread(tsimgid, 4));
tsimgw = toint(fread(tsimgid, 4));
testimages = permute(reshape(fread(tsimgid, tsimgh*tsimgw*numtsimg),tsimgh,tsimgw,numtsimg), [2 1 3]);

%% CNN Training

[missimages, misslabels] = cnntrain(trainlabels,trainimages,testlabels,testimages,maxtrain,iter,eta);

%% CNN Testing

showmiss(missimages,misslabels,testimages,testlabels,25,2);

培训代码： 功能[missimages，misslabels]=cnntrain（列车标签，列车图像，测试标签，测试图像，maxtrain，iter，eta）

显示准确性的代码

function [] = showmiss(missim,misslab,testimages,testlabels,numshow,numpages)
    nummiss = nnz(missim);

    page = 1;
    showsize = floor(sqrt(numshow));
    for f=1:numshow:nummiss
        figure(floor(f/numshow) + 1);
        for m=f:min(nummiss,f+numshow-1)
            subplot(showsize,showsize,m-f+1);
            imshow(testimages(:,:,missim(m)));
            title(strcat(num2str(testlabels(missim(m))), ':', num2str(misslab(m))));
        end
        page = page + 1;
        if page > numpages
            break;
        end
    end

end

函数toint

function [x] = toint(b)
    x = b(1)*16777216 + b(2)*65536 + b(3)*256 + b(4);
end

function [x] = toint(b)
    x = b(1)*16777216 + b(2)*65536 + b(3)*256 + b(4);
end