1、在GitHub下载deep Learning toolbox：https://github.com/rasmusbergpalm/DeepLearnToolbox
2、将解压后的deep Learning toolbox文件夹（自动命名为DeepLearnToolbox-master）放到matlab安装根目录的toobox文件夹里。
3、添加路径，在命令行输入addpath(genpath(‘D:\MATLAB\toolbox\DeepLearnToolbox-master’)),这个路径要根据自己的安装位置修改。然后点击主页，点击设置路径，点击保存，每次开机就可以直接调用这个工具箱的函数了。
4、改写nntrain
工具箱中的原始文件如下：
function [nn, L] = nntrain(nn, train_x, train_y, opts, val_x, val_y)
%NNTRAIN trains a neural net
% [nn, L] = nnff(nn, x, y, opts) trains the neural network nn with input x and
% output y for opts.numepochs epochs, with minibatches of size
% opts.batchsize。Returns a neural network nn with updated activations,
% errors, weights and biases, (nn.a, nn.e, nn.W, nn.b) and L, the sum
% squared error for each training minibatch.
assert(isfloat(train_x), ‘train_x must be a float’);
assert(nargin == 4 || nargin == 6,’number ofinput arguments must be 4 or 6′)
loss.train.e = [];
loss.train.e_frac = [];
loss.val.e = [];
loss.val.e_frac = [];
opts.validation = 0;
if nargin == 6
opts.validation = 1;
end
fhandle = [];
if isfield(opts,’plot’) && opts.plot == 1
fhandle = figure();
end
m = size(train_x, 1);
batchsize = opts.batchsize;
numepochs = opts.numepochs;
numbatches = m / batchsize;
assert(rem(numbatches, 1) == 0, ‘numbatches must be a integer’);
L = zeros(numepochs*numbatches,1);
n = 1;
for i = 1 : numepochs
tic;
kk = randperm(m);
for l = 1 : numbatches
batch_x = train_x(kk((l – 1) * batchsize + 1 : l * batchsize), :);
%Add noise to input (for use in denoising autoencoder)
if(nn.inputZeroMaskedFraction ~= 0)
batch_x = batch_x.*(rand(size(batch_x))>nn.inputZeroMaskedFraction);
end
batch_y = train_y(kk((l – 1) * batchsize + 1 : l * batchsize), :);
nn = nnff(nn, batch_x, batch_y);
nn = nnbp(nn);
nn = nnapplygrads(nn);
L(n) = nn.L;
n = n + 1;
end
t = toc;
if opts.validation == 1
loss = nneval(nn, loss, train_x, train_y, val_x, val_y);
str_perf = sprintf(‘; Full-batch train mse = %f, val mse = %f’, loss.train.e(end), loss.val.e(end));
else
loss = nneval(nn, loss, train_x, train_y);
str_perf = sprintf(‘; Full-batch train err = %f’, loss.train.e(end));
end
if ishandle(fhandle)
nnupdatefigures(nn, fhandle, loss, opts, i);
end
disp([‘epoch ‘ num2str(i) ‘/’ num2str(opts.numepochs) ‘。Took ‘ num2str(t) ‘ seconds’ ‘。Mini-batch mean squared error on training set is ‘ num2str(mean(L((n-numbatches):(n-1)))) str_perf]);
nn.learningRate = nn.learningRate * nn.scaling_learningRate;
end
end
上面文件中，L是训练过程中的损失，每次迭代（epoch），计算每个批样本（batch）的损失值，这里对其进行改写，使其输出每次迭代后所有训练样本的损失值，以及预测测试集的准确率。
首先我们改变函数参数的数量。
function [nn,Loss,accuracy, L] = nntrain(nn, train_x, train_y, opts,test_x,test_y,val_x, val_y)
assert(nargin == 4 || nargin == 6|| nargin == 8,’number ofinput arguments must be 4 or 6 or 8′)
参数中加入了测试集的input和labels，
if nargin == 8
opts.validation = 1;
end
这里修改成输入参数为8个时，opts.validation=1;
if nargin == 6
opts.test = 1;
end
增加一个opts.test参数；
为损失和准确性分配空间。
Loss=zeros(numepochs,1);
accuracy=zeros(numepochs,1);
loss_batch(l)=nn.L;%计算一次迭代过程中，每个batch的损失
Loss(i)=sum(loss_batch)/numbatches;计算所有训练集的损失
接下来，我们判断测试集的输入参数是否为[ ]，如果不是[ ]，则计算预测精度。
if opts.test==1
if isempty(test_x)||isempty(test_y)
opts.test=0;
else
[er, bad] = nntest(nn, test_x, test_y);
accuracy(i)=1-er;
end
end
以下是修改后的nntrain函数。
function [nn,Loss,accuracy, L] = nntrain(nn, train_x, train_y, opts,test_x,test_y,val_x, val_y)
%NNTRAIN trains a neural net
% [nn, L] = nnff(nn, x, y, opts) trains the neural network nn with input x and
% output y for opts.numepochs epochs, with minibatches of size
% opts.batchsize。Returns a neural network nn with updated activations,
% errors, weights and biases, (nn.a, nn.e, nn.W, nn.b) and L, the sum
% squared error for each training minibatch.
assert(isfloat(train_x), ‘train_x must be a float’);
assert(nargin == 4 || nargin == 6|| nargin == 8,’number ofinput arguments must be 4 or 6 or 8′)
loss.train.e = [];
loss.train.e_frac = [];
loss.val.e = [];
loss.val.e_frac = [];
opts.validation = 0;
opts.test = 0;
if nargin == 8
opts.validation = 1;
end
if nargin == 6
opts.test = 1;
end
fhandle = [];
if isfield(opts,’plot’) && opts.plot == 1
fhandle = figure();
end
m = size(train_x, 1);
batchsize = opts.batchsize;
numepochs = opts.numepochs;
numbatches = m / batchsize;
assert(rem(numbatches, 1) == 0, ‘numbatches must be a integer’);
L = zeros(numepochs*numbatches,1);
n = 1;
Loss=zeros(numepochs,1);
accuracy=zeros(numepochs,1);
for i = 1 : numepochs
tic;
loss_batch=zeros(numbatches,1);
kk = randperm(m);
for l = 1 : numbatches
batch_x = train_x(kk((l – 1) * batchsize + 1 : l * batchsize), :);
%Add noise to input (for use in denoising autoencoder)
if(nn.inputZeroMaskedFraction ~= 0)
batch_x = batch_x.*(rand(size(batch_x))>nn.inputZeroMaskedFraction);
end
batch_y = train_y(kk((l – 1) * batchsize + 1 : l * batchsize), :);
nn = nnff(nn, batch_x, batch_y);
nn = nnbp(nn);
nn = nnapplygrads(nn);
L(n) = nn.L;
n = n + 1;
loss_batch(l)=nn.L;
end
t = toc;
Loss(i)=sum(loss_batch)/numbatches;
if opts.test==1
if isempty(test_x)||isempty(test_y)
opts.test=0;
else
[er, bad] = nntest(nn, test_x, test_y);
accuracy(i)=1-er;
end
end
if opts.validation == 1
loss = nneval(nn, loss, train_x, train_y, val_x, val_y);
str_perf = sprintf(‘; Full-batch train mse = %f, val mse = %f’, loss.train.e(end), loss.val.e(end));
else
loss = nneval(nn, loss, train_x, train_y);
str_perf = sprintf(‘; Full-batch train err = %f’, loss.train.e(end));
end
if ishandle(fhandle)
nnupdatefigures(nn, fhandle, loss, opts, i);
end
disp([‘epoch ‘ num2str(i) ‘/’ num2str(opts.numepochs) ‘。Took ‘ num2str(t) ‘ seconds’ ‘。Mini-batch mean squared error on training set is ‘ num2str(mean(L((n-numbatches):(n-1)))) str_perf]);
nn.learningRate = nn.learningRate * nn.scaling_learningRate;
end
end
文章出处登录后可见！
