UFLDL cnnPool.m

虽然pool也能通过比较naive的方法来实现，但是效率相对来说比较低，因此我通过conv2来实现，然后间隔取样，效率较高。

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(imageRow, imageCol, featureNum, imageNum)
%
% Returns:
%  pooledFeatures - matrix of pooled features in the form
%                   pooledFeatures(poolRow, poolCol, featureNum, imageNum)
%     

numImages = size(convolvedFeatures, 4);
numFilters = size(convolvedFeatures, 3);
convolvedDim = size(convolvedFeatures, 1);

pooledFeatures = zeros(convolvedDim / poolDim, ...
        convolvedDim / poolDim, numFilters, numImages);

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

%%% YOUR CODE HERE %%%
for imageNum = 1:numImages
    for filterNum = 1:numFilters
        pooledFeature = zeros(convolvedDim / poolDim , convolvedDim / poolDim);
        pooledFeature = conv2(convolvedFeatures(:,:,filterNum,imageNum),ones(poolDim,poolDim),'valid')/(poolDim*poolDim);
        pooledFeature = pooledFeature(1:poolDim:end,1:poolDim:end);
        pooledFeatures(:,:,filterNum,imageNum) = pooledFeature(:,:);
    end
end

end