Exercise:Convolution and Pooling 代码示例
来源:互联网 发布:c语言中字符串数组 编辑:程序博客网 时间:2024/05/22 00:12
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
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 1WT = 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; endendendfunction 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); endend
0 0
- Exercise:Convolution and Pooling 代码示例
- UFLDL Exercise:Convolution and Pooling
- UFLDL Exercise: Convolution and Pooling
- Ufldl Exercise:Convolution and Pooling
- Stanford UFLDL教程 Exercise:Convolution and Pooling
- UFLDL教程:Exercise:Convolution and Pooling
- 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
- Convolution and Pooling
- Convolution and Pooling
- UFLDL——Exercise: Convolution and Pooling 卷积和池化
- 【UFLDL-exercise9-Convolution and Pooling】
- Convolution and Pooling --卷积和池化
- Exercise:PCA and Whitening 代码示例
- deep learning convolution and pooling(卷积和池化)
- Exercise:Vectorization 代码示例
- Exercise:Sparse Autoencoder 代码示例
- cocos2d-x在iOS/Android双平台上嵌入WebView
- 移动互联时代怎么利用搜索核心原则做SEO优化
- 定制Internet Explorer下载管理器
- android的SwipeRefreshLayout 扩展
- wordpress随机文章调用代码
- Exercise:Convolution and Pooling 代码示例
- 【Java笔记】Java形参长度可变方法
- mongodb的serverstatus
- 搭建sqoop的eclipse调试环境
- Spring学习2—Spring容器
- linux : VNC使用命令 以及 复制VNC里面的内容到windows本地
- Tomcat 系统架构与设计模式 第 1 部分: 工作原理
- 如何在MacBook Pro Retina上安装Linux
- Linux 安装mysql