clc;
clear all;
I=imread('lv.jpg');
I=rgb2gray(I);
I=imresize(I,[128,128]);
figure;
imshow(I);
p=[];
for i=1:32 %预处理取4*4的字块,最后生成16*1024的矩阵
for j=1:32
I2=I((i-1)*4+1:i*4,(j-1)*4+1:j*4);
i3=reshape(I2,16,1);
II=double(i3);
p_1=II/255;
p=[p,p_1];
end
end
t=p;
net=newff(minmax(p),[2,16],{'tansig','logsig'},'trainlm'); %构建网络第一层8第二层16
net.trainParam.goal=0.001; %均方差为0.001;输出和目标值的差的平方再求平均值
net.trainParam.epochs=500; %训练次数为500次,什么迭代次数
tic %开始计时
net=train(net,p,t); %用该网络进行训练
toc %结束计时,在最后的时候回输出运行的时间
Y_chonggou=sim(net,p); %仿真相当于windows中的run命令,运行net网络
Ychonggou_ceshi=[];
for k=1:1024
Ychonggou_ceshi1=reshape(Y_chonggou(:,k),4,4);
Ychonggou_ceshi=[Ychonggou_ceshi,Ychonggou_ceshi1];
end
YYchonggou_ceshi=[];
for k=1:32
YYchonggou_ceshi1=Ychonggou_ceshi(:,(k-1)*128+1:k*128);
YYchonggou_ceshi=[YYchonggou_ceshi;YYchonggou_ceshi1];
end
Ychonggou_ce=uint8(YYchonggou_ceshi*255);
figure;
imshow(Ychonggou_ce);
clear all;
I=imread('lv.jpg');
I=rgb2gray(I);
I=imresize(I,[128,128]);
figure;
imshow(I);
p=[];
for i=1:32 %预处理取4*4的字块,最后生成16*1024的矩阵
for j=1:32
I2=I((i-1)*4+1:i*4,(j-1)*4+1:j*4);
i3=reshape(I2,16,1);
II=double(i3);
p_1=II/255;
p=[p,p_1];
end
end
t=p;
net=newff(minmax(p),[2,16],{'tansig','logsig'},'trainlm'); %构建网络第一层8第二层16
net.trainParam.goal=0.001; %均方差为0.001;输出和目标值的差的平方再求平均值
net.trainParam.epochs=500; %训练次数为500次,什么迭代次数
tic %开始计时
net=train(net,p,t); %用该网络进行训练
toc %结束计时,在最后的时候回输出运行的时间
Y_chonggou=sim(net,p); %仿真相当于windows中的run命令,运行net网络
Ychonggou_ceshi=[];
for k=1:1024
Ychonggou_ceshi1=reshape(Y_chonggou(:,k),4,4);
Ychonggou_ceshi=[Ychonggou_ceshi,Ychonggou_ceshi1];
end
YYchonggou_ceshi=[];
for k=1:32
YYchonggou_ceshi1=Ychonggou_ceshi(:,(k-1)*128+1:k*128);
YYchonggou_ceshi=[YYchonggou_ceshi;YYchonggou_ceshi1];
end
Ychonggou_ce=uint8(YYchonggou_ceshi*255);
figure;
imshow(Ychonggou_ce);