Deep Learning 十_深度学习UFLDL教程：Convolution and Pooling_exercise（斯坦福大学深度学习教程）

%% CS294A/CS294W Convolutional Neural Networks Exercise

%  Instructions
%  ------------
% 
%  This file contains code that helps you get started on the
%  convolutional neural networks exercise. In this exercise, you will only
%  need to modify cnnConvolve.m and cnnPool.m. You will not need to modify
%  this file.

%%======================================================================
%% STEP 0: Initialization
%  Here we initialize some parameters used for the exercise.

imageDim = 64;         % image dimension
imageChannels = 3;     % number of channels (rgb, so 3)

patchDim = 8;          % patch dimension
numPatches = 50000;    % number of patches

visibleSize = patchDim * patchDim * imageChannels;  % number of input units 
outputSize = visibleSize;   % number of output units
hiddenSize = 400;           % number of hidden units 

epsilon = 0.1;           % epsilon for ZCA whitening

poolDim = 19;          % dimension of pooling region

%%======================================================================
%% STEP 1: Train a sparse autoencoder (with a linear decoder) to learn 
%  features from color patches. If you have completed the linear decoder
%  execise, use the features that you have obtained from that exercise, 
%  loading them into optTheta. Recall that we have to keep around the 
%  parameters used in whitening (i.e., the ZCA whitening matrix and the
%  meanPatch)

% --------------------------- YOUR CODE HERE --------------------------
% Train the sparse autoencoder and fill the following variables with 
% the optimal parameters:

optTheta =  zeros(2*hiddenSize*visibleSize+hiddenSize+visibleSize, 1);
ZCAWhite =  zeros(visibleSize, visibleSize);
meanPatch = zeros(visibleSize, 1);
load STL10Features.mat;

% --------------------------------------------------------------------

% Display and check to see that the features look good
W = reshape(optTheta(1:visibleSize * hiddenSize), hiddenSize, visibleSize);
b = optTheta(2*hiddenSize*visibleSize+1:2*hiddenSize*visibleSize+hiddenSize);

displayColorNetwork( (W*ZCAWhite)‘);

%%======================================================================
%% STEP 2: Implement and test convolution and pooling
%  In this step, you will implement convolution and pooling, and test them
%  on a small part of the data set to ensure that you have implemented
%  these two functions correctly. In the next step, you will actually
%  convolve and pool the features with the STL10 images.

%% STEP 2a: Implement convolution
%  Implement convolution in the function cnnConvolve in cnnConvolve.m

% Note that we have to preprocess the images in the exact same way 
% we preprocessed the patches before we can obtain the feature activations.

load stlTrainSubset.mat % loads numTrainImages, trainImages, trainLabels

%% 只用8张图片来测试卷积和池化是否正确 Use only the first 8 images for testing
convImages = trainImages(:, :, :, 1:8);  % 格式：trainImages(r, c, channel, image number)

% NOTE: Implement cnnConvolve in cnnConvolve.m first!
convolvedFeatures = cnnConvolve(patchDim, hiddenSize, convImages, W, b, ZCAWhite, meanPatch);

%% STEP 2b: Checking your convolution
%  To ensure that you have convolved the features correctly, we have
%  provided some code to compare the results of your convolution with
%  activations from the sparse autoencoder

% For 1000 random points
for i = 1:1000    
    featureNum = randi([1, hiddenSize]);
    imageNum = randi([1, 8]);
    imageRow = randi([1, imageDim - patchDim + 1]);
    imageCol = randi([1, imageDim - patchDim + 1]);    
   
    patch = convImages(imageRow:imageRow + patchDim - 1, imageCol:imageCol + patchDim - 1, :, imageNum);
    patch = patch(:);  % 将patch矩阵从3维矩阵转换为一个列向量         
    patch = patch - meanPatch;
    patch = ZCAWhite * patch;  % 白化后的数据
    
    features = feedForwardAutoencoder(optTheta, hiddenSize, visibleSize, patch); 

    if abs(features(featureNum, 1) - convolvedFeatures(featureNum, imageNum, imageRow, imageCol)) > 1e-9
        fprintf(‘Convolved feature does not match activation from autoencoder\n‘);
        fprintf(‘Feature Number    : %d\n‘, featureNum);
        fprintf(‘Image Number      : %d\n‘, imageNum);
        fprintf(‘Image Row         : %d\n‘, imageRow);
        fprintf(‘Image Column      : %d\n‘, imageCol);
        fprintf(‘Convolved feature : %0.5f\n‘, convolvedFeatures(featureNum, imageNum, imageRow, imageCol));
        fprintf(‘Sparse AE feature : %0.5f\n‘, features(featureNum, 1));       
        error(‘Convolved feature does not match activation from autoencoder‘);
    end 
end

disp(‘Congratulations! Your convolution code passed the test.‘);

%% STEP 2c: Implement pooling
%  Implement pooling in the function cnnPool in cnnPool.m

% NOTE: Implement cnnPool in cnnPool.m first!
pooledFeatures = cnnPool(poolDim, convolvedFeatures);

%% STEP 2d: Checking your pooling
%  To ensure that you have implemented pooling, we will use your pooling
%  function to pool over a test matrix and check the results.

testMatrix = reshape(1:64, 8, 8);
expectedMatrix = [mean(mean(testMatrix(1:4, 1:4))) mean(mean(testMatrix(1:4, 5:8))); ...
                  mean(mean(testMatrix(5:8, 1:4))) mean(mean(testMatrix(5:8, 5:8))); ];
            
testMatrix = reshape(testMatrix, 1, 1, 8, 8);
        
pooledFeatures = squeeze(cnnPool(4, testMatrix));

if ~isequal(pooledFeatures, expectedMatrix)
    disp(‘Pooling incorrect‘);
    disp(‘Expected‘);
    disp(expectedMatrix);
    disp(‘Got‘);
    disp(pooledFeatures);
else
    disp(‘Congratulations! Your pooling code passed the test.‘);
end

%%======================================================================
%% STEP 3: Convolve and pool with the dataset
%  In this step, you will convolve each of the features you learned with
%  the full large images to obtain the convolved features. You will then
%  pool the convolved features to obtain the pooled features for
%  classification.
%
%  Because the convolved features matrix is very large, we will do the
%  convolution and pooling 50 features at a time to avoid running out of
%  memory. Reduce this number if necessary

stepSize = 50;
assert(mod(hiddenSize, stepSize) == 0, ‘stepSize should divide hiddenSize‘);

load stlTrainSubset.mat % loads numTrainImages, trainImages, trainLabels
load stlTestSubset.mat  % loads numTestImages,  testImages,  testLabels

pooledFeaturesTrain = zeros(hiddenSize, numTrainImages, ...
    floor((imageDim - patchDim + 1) / poolDim), ...
    floor((imageDim - patchDim + 1) / poolDim) );
pooledFeaturesTest = zeros(hiddenSize, numTestImages, ...
    floor((imageDim - patchDim + 1) / poolDim), ...
    floor((imageDim - patchDim + 1) / poolDim) );

tic();

for convPart = 1:(hiddenSize / stepSize)
    
    featureStart = (convPart - 1) * stepSize + 1;
    featureEnd = convPart * stepSize;
    
    fprintf(‘Step %d: features %d to %d\n‘, convPart, featureStart, featureEnd);  
    Wt = W(featureStart:featureEnd, :);
    bt = b(featureStart:featureEnd);    
    
    fprintf(‘Convolving and pooling train images\n‘);
    convolvedFeaturesThis = cnnConvolve(patchDim, stepSize, ...
        trainImages, Wt, bt, ZCAWhite, meanPatch);
    pooledFeaturesThis = cnnPool(poolDim, convolvedFeaturesThis);
    pooledFeaturesTrain(featureStart:featureEnd, :, :, :) = pooledFeaturesThis;   
    toc();
    clear convolvedFeaturesThis pooledFeaturesThis;
    
    fprintf(‘Convolving and pooling test images\n‘);
    convolvedFeaturesThis = cnnConvolve(patchDim, stepSize, ...
        testImages, Wt, bt, ZCAWhite, meanPatch);
    pooledFeaturesThis = cnnPool(poolDim, convolvedFeaturesThis);
    pooledFeaturesTest(featureStart:featureEnd, :, :, :) = pooledFeaturesThis;   
    toc();

    clear convolvedFeaturesThis pooledFeaturesThis;

end


% You might want to save the pooled features since convolution and pooling takes a long time
save(‘cnnPooledFeatures.mat‘, ‘pooledFeaturesTrain‘, ‘pooledFeaturesTest‘);
toc();

%%======================================================================
%% STEP 4: Use pooled features for classification
%  Now, you will use your pooled features to train a softmax classifier,
%  using softmaxTrain from the softmax exercise.
%  Training the softmax classifer for 1000 iterations should take less than
%  10 minutes.

% Add the path to your softmax solution, if necessary
% addpath /path/to/solution/

% Setup parameters for softmax
softmaxLambda = 1e-4;
numClasses = 4;
% Reshape the pooledFeatures to form an input vector for softmax
softmaxX = permute(pooledFeaturesTrain, [1 3 4 2]); % 把pooledFeaturesTrain的第2维移到最后
softmaxX = reshape(softmaxX, numel(pooledFeaturesTrain) / numTrainImages,...
    numTrainImages);
softmaxY = trainLabels;

options = struct;
options.maxIter = 200;
softmaxModel = softmaxTrain(numel(pooledFeaturesTrain) / numTrainImages,...
    numClasses, softmaxLambda, softmaxX, softmaxY, options);

%%======================================================================
%% STEP 5: Test classifer
%  Now you will test your trained classifer against the test images

softmaxX = permute(pooledFeaturesTest, [1 3 4 2]);
softmaxX = reshape(softmaxX, numel(pooledFeaturesTest) / numTestImages, numTestImages);
softmaxY = testLabels;

[pred] = softmaxPredict(softmaxModel, softmaxX);
acc = (pred(:) == softmaxY(:));
acc = sum(acc) / size(acc, 1);
fprintf(‘Accuracy: %2.3f%%\n‘, acc * 100);

% You should expect to get an accuracy of around 80% on the test images.

function convolvedFeatures = cnnConvolve(patchDim, numFeatures, images, W, b, ZCAWhite, meanPatch)
%卷积特征提取：把每一个特征都与每一张大尺寸图片images相卷积，并返回卷积结果
%cnnConvolve Returns the convolution of the features given by W and b with
%the given images
%
% Parameters:
%  patchDim - patch (feature) dimension
%  numFeatures - number of features
%  images - large images to convolve with, matrix in the form
%           images(r, c, channel, image number)
%  W, b - W, b for features from the sparse autoencoder
%  ZCAWhite, meanPatch - ZCAWhitening and meanPatch matrices used for
%                        preprocessing
%
% Returns:
%  convolvedFeatures - matrix of convolved features in the form
%                      convolvedFeatures(featureNum, imageNum, imageRow, imageCol)
%                      表示第个featureNum特征与第imageNum张图片相卷的结果保存在矩阵
%                      convolvedFeatures(featureNum, imageNum, ：, ：)的第imageRow行第imageCol列,
%                      而每行和列的大小都为imageDim - patchDim + 1

numImages = size(images, 4);     % 图片数量
imageDim = size(images, 1);      % 每幅图片行数
imageChannels = size(images, 3); % 每幅图片通道数

patchSize = patchDim*patchDim;
assert(numFeatures == size(W,1), ‘W should have numFeatures rows‘);
assert(patchSize*imageChannels == size(W,2), ‘W should have patchSize*imageChannels cols‘);


% Instructions:
%   Convolve every feature with every large image here to produce the 
%   numFeatures x numImages x (imageDim - patchDim + 1) x (imageDim - patchDim + 1) 
%   matrix convolvedFeatures, such that 
%   convolvedFeatures(featureNum, imageNum, imageRow, imageCol) is the
%   value of the convolved featureNum feature for the imageNum image over
%   the region (imageRow, imageCol) to (imageRow + patchDim - 1, imageCol + patchDim - 1)
%
% Expected running times: 
%   Convolving with 100 images should take less than 3 minutes 
%   Convolving with 5000 images should take around an hour
%   (So to save time when testing, you should convolve with less images, as
%   described earlier)

% -------------------- YOUR CODE HERE --------------------
% Precompute the matrices that will be used during the convolution. Recall
% that you need to take into account the whitening and mean subtraction
% steps

WT = W*ZCAWhite;           % 等效的网络权值
b_mean = b - WT*meanPatch; % 等效偏置项


% --------------------------------------------------------

convolvedFeatures = zeros(numFeatures, numImages, imageDim - patchDim + 1, imageDim - patchDim + 1);
for imageNum = 1:numImages
  for featureNum = 1:numFeatures

    % convolution of image with feature matrix for each channel
    convolvedImage = zeros(imageDim - patchDim + 1, imageDim - patchDim + 1);
    for channel = 1:3

      % Obtain the feature (patchDim x patchDim) needed during the convolution
      % ---- YOUR CODE HERE ----
      offset = (channel-1)*patchSize;
      feature = reshape(WT(featureNum,offset+1:offset+patchSize), patchDim, patchDim);%取一个权值图像块出来
      im  = images(:,:,channel,imageNum);
      
      
      % ------------------------

      % Flip the feature matrix because of the definition of convolution, as explained later
      feature = rot90(squeeze(feature),2);
      
      % Obtain the image
      im = squeeze(images(:, :, channel, imageNum));

      % Convolve "feature" with "im", adding the result to convolvedImage
      % be sure to do a ‘valid‘ convolution
      % ---- YOUR CODE HERE ----

      convolvedoneChannel = conv2(im, feature, ‘valid‘);    % 单个特征分别与所有图片相卷
      convolvedImage = convolvedImage + convolvedoneChannel;% 直接把3通道的值加起来，理由：3通道相当于有3个feature-map，类似于cnn第2层以后的输入。
            
      % ------------------------

    end
    
    % Subtract the bias unit (correcting for the mean subtraction as well)
    % Then, apply the sigmoid function to get the hidden activation
    % ---- YOUR CODE HERE ----

    convolvedImage = sigmoid(convolvedImage+b_mean(featureNum));
    
    
    % ------------------------
    
    % The convolved feature is the sum of the convolved values for all channels
    convolvedFeatures(featureNum, imageNum, :, :) = convolvedImage;
  end
end


end
function sigm = sigmoid(x)
    sigm = 1./(1+exp(-x));
end

function pooledFeatures = cnnPool(poolDim, convolvedFeatures)
%cnnPool Pools the given convolved features
%
% Parameters:
%  poolDim - dimension of pooling region
%  convolvedFeatures - convolved features to pool (as given by cnnConvolve)
%                      convolvedFeatures(featureNum, imageNum, imageRow, imageCol)
%
% Returns:
%  pooledFeatures - matrix of pooled features in the form
%                   pooledFeatures(featureNum, imageNum, poolRow, poolCol)
%                      表示第个featureNum特征与第imageNum张图片的卷积特征池化后的结果保存在矩阵
%                      pooledFeatures(featureNum, imageNum, ：, ：)的第poolRow行第poolCol列
%     

numImages = size(convolvedFeatures, 2);   % 图片数量
numFeatures = size(convolvedFeatures, 1); % 卷积特征数量
convolvedDim = size(convolvedFeatures, 3);% 卷积特征维数

pooledFeatures = zeros(numFeatures, numImages, floor(convolvedDim / poolDim), floor(convolvedDim / poolDim));

% -------------------- YOUR CODE HERE --------------------
% Instructions:
%   Now pool the convolved features in regions of poolDim x poolDim,
%   to obtain the 
%   numFeatures x numImages x (convolvedDim/poolDim) x (convolvedDim/poolDim) 
%   matrix pooledFeatures, such that
%   pooledFeatures(featureNum, imageNum, poolRow, poolCol) is the 
%   value of the featureNum feature for the imageNum image pooled over the
%   corresponding (poolRow, poolCol) pooling region 
%   (see http://ufldl/wiki/index.php/Pooling )
%   
%   Use mean pooling here.
% -------------------- YOUR CODE HERE --------------------

resultDim  = floor(convolvedDim / poolDim);
for imageNum = 1:numImages   % 第imageNum张图片
    for featureNum = 1:numFeatures  % 第featureNum个特征
        for poolRow = 1:resultDim
            offsetRow = 1+(poolRow-1)*poolDim;
            for poolCol = 1:resultDim
                offsetCol = 1+(poolCol-1)*poolDim;
                patch = convolvedFeatures(featureNum,imageNum,offsetRow:offsetRow+poolDim-1,...
                    offsetCol:offsetCol+poolDim-1);%取出一个patch
                pooledFeatures(featureNum,imageNum,poolRow,poolCol) = mean(patch(:));%使用均值pool
            end
        end
    end
end


end