卷积神经网络matlab.docxVIP

function test_example_CNNload mnist_uint8;train_x = double(reshape(train_x,28,28,60000))/255;test_x = double(reshape(test_x,28,28,10000))/255;train_y = double(train_y);test_y = double(test_y);%% ex1 Train a 6c-2s-12c-2s Convolutional neural network %will run 1 epoch in about 200 second and get around 11% error. %With 100 epochs youll get around 1.2% errorcnn.layers = { struct(type, i) %input layer struct(type, c, outputmaps, 6, kernelsize, 5) %convolution layer struct(type, s, scale, 2) %sub sampling layer struct(type, c, outputmaps, 12, kernelsize, 5) %convolution layer struct(type, s, scale, 2) %subsampling layer};cnn = cnnsetup(cnn, train_x, train_y);opts.alpha = 1;opts.batchsize = 50;opts.numepochs = 1;cnn = cnntrain(cnn, train_x, train_y, opts);[er, bad] = cnntest(cnn, test_x, test_y);%plot mean squared errorfigure; plot(cnn.rL);assert(er0.12, Too big error);function net = cnnsetup(net, x, y) inputmaps = 1; mapsize = size(squeeze(x(:, :, 1)));for l = 1 : numel(net.layers) % layerif strcmp(net.layers{l}.type, s) mapsize = mapsize / net.layers{l}.scale; assert(all(floor(mapsize)==mapsize), [Layer num2str(l) size must be integer. Actual: num2str(mapsize)]);for j = 1 : inputmaps net.layers{l}.b{j} = 0;endendif strcmp(net.layers{l}.type, c) mapsize = mapsize - net.layers{l}.kernelsize + 1; fan_out = net.layers{l}.outputmaps * net.layers{l}.kernelsize ^ 2;for j = 1 : net.layers{l}.outputmaps % output map fan_in = inputmaps * net.layers{l}.kernelsize ^ 2;for i = 1 : inputmaps % input map net.layers{l}.k{i}{j} = (rand(net.layers{l}.kernelsize) - 0.5) * 2 * sqrt(6 / (fan_in + fan_out));end net.layers{l}.b{j} = 0;end inputmaps = net.layers{l}.outputmaps;endend% onum is the number of labels, thats why it is calculated using size(y, 1). If you have 20 labels so the output of the network will be 20 neurons.% fvnum is the numbe