Exercise:Convolution and Pooling 代码示例
2014-12-25 16:56
459 查看
练习参考Convolution and Pooling
这个练习用于处理大型图像,需要编写代码实现卷积特征提取和池化(采样)两个过程。在上一个练习中,通过小尺寸图像样本训练线性编码器得到的权重矩阵W、偏差向量b以及预处理的ZCA白化矩阵ZCAWhite、均值向量meanPatch存为文件STL10Features.mat。此练习利用STL10Features.mat中的特征与大图作卷积生成卷积特征矩阵。
卷积计算在cnnConvolve.m中实现。对每张图像的每个特征(隐藏单元)的每个RGB分量(三层循环),从W中提取对应的卷积核,将其与大图做卷积。这里计算大图与卷积核的卷积与数学中的矩阵卷积不同,是两矩阵的对应项直接相乘再求和,具体过程如下图:
每个RGB分量计算的卷积累加起来,其结果加上特征的偏置后取sigmoid就得到了一张图像的一个特征的卷积矩阵。三层循环结束后就得到了全部图像的卷积特征矩阵族。
cnnConvolve.m
池化采用平均采样。对每个卷积特征矩阵划分为若干个池化区域,每个区域取特征均值作为一个采样特征。在采样特征上做Softmax分类及测试。
cnnPool.m
这个练习用于处理大型图像,需要编写代码实现卷积特征提取和池化(采样)两个过程。在上一个练习中,通过小尺寸图像样本训练线性编码器得到的权重矩阵W、偏差向量b以及预处理的ZCA白化矩阵ZCAWhite、均值向量meanPatch存为文件STL10Features.mat。此练习利用STL10Features.mat中的特征与大图作卷积生成卷积特征矩阵。
卷积计算在cnnConvolve.m中实现。对每张图像的每个特征(隐藏单元)的每个RGB分量(三层循环),从W中提取对应的卷积核,将其与大图做卷积。这里计算大图与卷积核的卷积与数学中的矩阵卷积不同,是两矩阵的对应项直接相乘再求和,具体过程如下图:
每个RGB分量计算的卷积累加起来,其结果加上特征的偏置后取sigmoid就得到了一张图像的一个特征的卷积矩阵。三层循环结束后就得到了全部图像的卷积特征矩阵族。
cnnConvolve.m
function convolvedFeatures = cnnConvolve(patchDim, numFeatures, images, W, b, ZCAWhite, meanPatch) %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) numImages = size(images, 4); imageDim = size(images, 1); imageChannels = size(images, 3); % 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 % patchDim 8 % numFeatures 400; is hiddenSize % images images(r, c, channel, image number) % W hiddenSize X visibleSize % b hiddenSize X 1 % ZCAWhite visibleSize X visibleSize % meanPatch visibleSize X 1 WT = W * ZCAWhite; bias = b - WT * meanPatch; patchSize = patchDim * patchDim; % -------------------------------------------------------- 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:imageChannels % Obtain the feature (patchDim x patchDim) needed during the convolution % ---- YOUR CODE HERE ---- feature = reshape(WT(featureNum,(channel-1)*patchSize+1:channel*patchSize), patchDim, patchDim); % ------------------------ % 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 ---- convolvedImage = convolvedImage + conv2(im, feature, 'valid'); % ------------------------ 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 + bias(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
池化采用平均采样。对每个卷积特征矩阵划分为若干个池化区域,每个区域取特征均值作为一个采样特征。在采样特征上做Softmax分类及测试。
cnnPool.m
for imageNum = 1:numImages for featureNum = 1:numFeatures temp = conv2(squeeze(convolvedFeatures(featureNum,imageNum,:,:)),ones(poolDim)/poolDim/poolDim,'valid'); pooledFeatures(featureNum,imageNum,:,:) = temp(1:poolDim:end,1:poolDim:end); end end
相关文章推荐
- UFLDL教程答案(8):Exercise:Convolution and Pooling
- Convolutional neural networks(CNN) (十一) Convolution and Pooling Exercise
- UFLDL教程Exercise答案(8):Convolution and Pooling
- Stanford UFLDL教程 Exercise:Convolution and Pooling
- Ufldl Exercise:Convolution and Pooling
- 【DeepLearning】Exercise:Convolution and Pooling
- 【ufldl tutorial】Convolution and Pooling
- Convolution and Pooling
- Exercise:Sparse Autoencoder 代码示例
- Exercise:Vectorization 代码示例
- Convolution and Pooling
- UFLDL Exercise: Convolution and Pooling
- Exercise:Sparse Autoencoder 代码示例
- Java中的Drag and Drop详解与代码示例
- 学习笔记4 Supervised Convolutional Neural Network 之 Convolution and Pooling
- Unsupervised Feature Learning and Deep Learning(UFLDL) Exercise 代码实现
- UFLDL Exercise:Convolution and Pooling
- Exercise:Self-Taught Learning 代码示例
- Content type and column用法示例代码来自SharePoint会议
- drawable之scale and rotate代码示例