DBN (深度信念网络) MATLAB DeepLearnToolbox 源码学习

来源：互联网发布：win10正在准备windows 编辑：程序博客网时间：2024/05/17 01:46

DeepLearnToolbox 源码下载地址 https://github.com/rasmusbergpalm/DeepLearnToolbox

解压后可得到

data里面有数据集，tests里面有测试代码例子。如下

% function test_example_DBNload mnist_uint8;  % 该数据集为集为手写数字数据集该数据集为集为手写数字数据集数据集改mnist   28*28 的图片。放在data文件夹中。train_x = double(train_x) / 255;   % train_x为784个像素值， 这里是在做数据归一化，（0-1）test_x  = double(test_x) / 255;train_y = double(train_y);test_y  = double(test_y);%%  ex1 train a 100 hidden unit RBM and visualize its weights% rng(0);dbn.sizes = [  100  ];  %设置网络隐藏单元数为100opts.numepochs =   1;       %设置训练迭代次数。opts.batchsize = 100;     %批次大小opts.momentum  =   0;    %动量opts.alpha     =   1;     % 学习率dbn = dbnsetup(dbn, train_x, opts);  %初始化RBM的参数dbn = dbntrain(dbn, train_x, opts);   %开始训练figure; visualize(dbn.rbm{1}.W');   %  Visualize the RBM weights%%  ex2 train a 100-100 hidden unit DBN and use its weights to initialize a NN% rng(0);%train dbndbn.sizes = [100 100];opts.numepochs =   10;opts.batchsize = 100;opts.momentum  =   0;opts.alpha     =   1;dbn = dbnsetup(dbn, train_x, opts);dbn = dbntrain(dbn, train_x, opts);%unfold dbn to nn nn = dbnunfoldtonn(dbn, 10);           %设计一个有十个输出单元的NN，并用已经训练好的DBN的权值参数去初始化相应结构的NN网络nn.activation_function = 'sigm';        %设置激活函数为 sigm%train nnopts.numepochs =  1;                   % 设置训练参数opts.batchsize = 10;                           nn = nntrain(nn, train_x, train_y, opts);   %训练网络[er, bad] = nntest(nn, test_x, test_y);     %测试网络错误率assert(er < 0.10, 'Too big error');

阅读全文

0 0