caffe 17 win10 caffe 数据可视化

本练习代码源自《深度学习21天实战caffe》

01 mnist 数据可视化

*本练习上接 [caffe 04 win10 运行examples的mnist测试用例]
(http://blog.csdn.net/longji/article/details/61446478)*

一定要注意需要为matlab设置环境，在path环境变量中加入：D:\git\DeepLearning\caffe\build\x64\install\bin

01.01 编写matlab代码

代码文件:D:\git\DeepLearning\caffe\data\mnist\show_mnist_data.m

% D:\git\DeepLearning\caffe\data\mnist\show_mnist_data.mclear;clc;close all;% 在 D:\git\DeepLearning\caffe\data\mnist\ 目录下的数据文件image_file_name = 't10k-images.idx3-ubyte';index_file_name = 't10k-labels.idx1-ubyte';fid1 = fopen(image_file_name, 'rb');fid2 = fopen(index_file_name, 'rb');images_data = fread(fid1, 'uint8');indexs_data = fread(fid2, 'uint8');fclose(fid1);fclose(fid2);images_data = images_data(17:end);indexs_data = indexs_data(9:end);image_buffer = zeros(28, 28);for k = 1 : 100: length(images_data)/28/28  figure(100);  for t = 1 : 100    image_buffer = reshape(images_data((k + t - 2) * 28 * 28 + 1 : (k + t - 1) * 28 * 28), 28, 28);    subplot(10, 10, t);    imshow(uint8(image_buffer)');    title(num2str(indexs_data(k + t -1)));  end  pause;end

01.02在matlab中运行mnist可视化代码

02 cifar10数据可视化

02.01 写matlab可视化代码

matlab代码文件：D:\git\DeepLearning\caffe\data\cifar10\show_cifar10_data.m

% data/cifar10/show_cifar10_data.mclear;clc;close all;strings = {  'airplane'  'automobile'  'bird'  'cat'  'deer'  'dog'  'frog'  'horse'  'ship'  'truck'};image_file_name = 'cifar-10-batches-bin/data_batch_1.bin';fid1 = fopen(image_file_name, 'rb');images_data = fread(fid1, 'uint8');fclose(fid1);images_data = reshape(images_data, 3073, [])';image_idx = images_data(:, 1);for k = 1: 100 : size(images_data, 1)  figure(100);  for t = 1 : 100    image_r = reshape(images_data(k + t - 1, 2: 1025), 32, [])';    image_g = reshape(images_data(k + t - 1, 1026 : 2049), 32, [])';    image_b = reshape(images_data(k + t - 1, 2050 : 3073), 32, [])';    image_buffer = cat(3, image_r, image_g, image_b);    subplot(10, 10, t);    imshow(uint8(image_buffer));    title(strings{image_idx(k + t - 1) + 1});  end  input('Press Enter to next picture :');  pause;end

02.02 在matlab中运行结果

03 权值可视化

03.01 Caffenet Conv1 权值可视化

matlat代码：D:\git\DeepLearning\caffe\conv1_weights_vis.m

% 网络权值可视化，D:\git\DeepLearning\caffe\conv_weights_vis.mclear;clc;close all;addpath('matlab');caffe.set_mode_cpu();caffe.version();net = caffe.Net('models/bvlc_reference_caffenet/deploy.prototxt', 'models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel', 'test');net.layer_namesnet.blob_namesconv1_layer = net.layer_vec(2);blob1 = conv1_layer.params(1);w = blob1.get_data();size(w)W = zeros(11*3, 11*96);for u = 1: 3  for v = 1: 96    W(11 * ( u - 1) + (1 : 11), 11 * (v - 1) + (1: 11)) = w(:, :, u, v)';  endendW = W - min(min(W));W = W / (max(max(W))) * 255;W = uint8(W);W = [W, zeros(size(W, 1), 4 * 11)];WW = cat(3, W(1:11, :), W(12:22, :), W(23:33, :));W = zeros(10 * 12, 10 * 12, 3);for u = 1: 10  for v = 1: 10    W((u - 1)*12 + (1:11), (v - 1) * 12 + (1:11), :) = WW(:, (u - 1) * 11 * 10 + (v - 1) * 11 + (1: 11), :);  endendW = uint8(W);figure;imshow(W);

运行结果：

03.02 Conv2-Conv5权值可视化

代码文件：D:\git\DeepLearning\caffe\visualize_weights.m

% D:\git\DeepLearning\caffe\visualize_weights.mfunction [] = visualize_weights(w, s)h = max(size(w, 1), size(w, 2));  % Kernel sizeg = h + s; % Grid size, larger than Kernel size for better visual effects.% Normalization for gray scalew = w - min(min(min(min(w))));w = w / max(max(max(max(w)))) * 255;w = uint8(w);W = zeros(g * size(w, 3), g * size(w, 4));for u = 1:size(w, 3)  for v = 1: size(w, 4)    W(g * (u - 1) + (1: h), g * (v - 1) + (1:h)) = w(:, :, u, v)';  endendW = uint8(W);figure;imshow(W);

代码文件：D:\git\DeepLearning\caffe\caffenet_weights_vis.m

% 网络权值可视化，caffe根目录caffenet_weights_vis.mclear;clc;close all;addpath('matlab');caffe.set_mode_cpu();fprintf(['Caffe Version = ', caffe.version(), '\n']);net = caffe.Net('models/bvlc_reference_caffenet/deploy.prototxt', 'models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel', 'test');fprintf('Load net done. Net layers : ');net.layer_namesfprintf('Net blobs : ');net.blob_names% Conv1 Weight Visualizetionconv1_layer = net.layer_vec(2);blob1 = conv1_layer.params(1);w1 = blob1.get_data();fprintf('Conv1 Weight shape: ');size(w1)visualize_weights(w1, 1);%Conv2 Weight Visualizetionconv2_layer = net.layer_vec(6);blob2 = conv2_layer.params(1);w2 = blob2.get_data();fprintf('Conv2 Weight shape: ');size(w2)visualize_weights(w2, 1);%Conv3 Weight Visualizetionconv3_layer = net.layer_vec(10);blob3 = conv3_layer.params(1);w3 = blob3.get_data();fprintf('Conv3 Weight shape: ');size(w3)visualize_weights(w3, 1);%Conv3 Weight Visualizetionconv3_layer = net.layer_vec(10);blob3 = conv3_layer.params(1);w3 = blob3.get_data();fprintf('Conv3 Weight shape: ');size(w3)visualize_weights(w3, 1);%Conv4 Weight Visualizetionconv4_layer = net.layer_vec(10);blob4 = conv4_layer.params(1);w4 = blob4.get_data();fprintf('Conv4 Weight shape: ');size(w4)visualize_weights(w4, 1);%Conv5 Weight Visualizetionconv5_layer = net.layer_vec(14);blob5 = conv5_layer.params(1);w5 = blob5.get_data();fprintf('Conv5 Weight shape: ');size(w5)visualize_weights(w5, 1);

运行结果：

04 特征图可视化

04.01 matlab源码

D:\git\DeepLearning\caffe\visualize_feature_maps.m

% 特征图可视化 D:\git\DeepLearning\caffe\visualize_feature_maps.mfunction [] = visualize_feature_maps(w, s)h = max(size(w, 1), size(w, 2)); % Feature map sizeg = h + s;c = size(w, 3);cv = ceil(sqrt(c));W = zeros(g * cv, g * cv);for u = 1: cv  for v = 1: cv    tw = zeros(h, h);    if (((u - 1) * cv + v) <= c)      tw = w(:, :, (u - 1) * cv + v, 1)';      tw = tw - min(min(tw));      tw = tw / max(max(tw)) * 255;    end    W(g * (u - 1) + (1: h), g * (v -1) + (1:h)) = tw;  endendW = uint8(W);figure;imshow(W);

D:\git\DeepLearning\caffe\fm_visual.m

% 特征图可视化，放在caffe根目录下，D:\git\DeepLearning\caffe\fm_visual.mclear;clc;close all;% 设置接口路径(D:\git\DeepLearning\caffe\下面的matlab)mat_fullname = mfilename('fullpath');i = strfind(mat_fullname,'\');work_path=mat_fullname(1: i(end));userpath(work_path);cd(work_path);addpath('matlab');% 设置设备类型为cpucaffe.set_mode_cpu();% 打印caffe版本号fprintf(['Caffe Version = ', caffe.version(), '\n']);net = caffe.Net('models/bvlc_reference_caffenet/deploy.prototxt', 'models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel', 'test');fprintf('Load net done. Net layers : ');net.layer_namesfprintf('Net blobs : ');net.blob_namesfprintf('Now preparing data...\n');im = imread('examples/images/cat.jpg');figure;imshow(im);title('Original Image');d = load('matlab/+caffe/imagenet/ilsvrc_2012_mean.mat');mean_data = d.mean_data;IMAGE_DIM = 256;CROPPED_DIM = 227;% Convert an image returned by Matlab's imread to im_data in caffe's data% format: W X H X C with BGR channelsim_data = im(:, :, [3, 2, 1]); % permute channels from RGB to BGRim_data = permute(im_data, [2, 1, 3]); % flip width and heightim_data = single(im_data); % convert from uint8 to singleim_data = imresize(im_data, [IMAGE_DIM IMAGE_DIM], 'bilinear'); % resize im_dataim_data = im_data - mean_data; % subtract mean_data (already in W X H X C, BGR)im = imresize(im_data, [CROPPED_DIM CROPPED_DIM], 'bilinear'); % resize im_datakm = cat(4, im, im, im, im, im);pm = cat(4, km, km);input_data = {pm};scores = net.forward(input_data);scores = scores{1};scores = mean(scores, 2); % take average scores over 10 crops[~, maxlabel] = max(scores);maxlabelfigure;plot(scores);fm_data = net.blob_vec(1);dl = fm_data.get_data();fprintf('Data size = ');size(dl)visualize_feature_maps(dl, 1);fm_conv1 = net.blob_vec(2);f1 = fm_conv1.get_data();fprintf('Feature map conv1 size = ');size(f1)visualize_feature_maps(f1,1);fm_conv2 = net.blob_vec(5);f2 = fm_conv2.get_data();fprintf('Feature map conv2 size = ');size(f2)visualize_feature_maps(f2,1);fm_conv3 = net.blob_vec(8);f3 = fm_conv3.get_data();fprintf('Feature map conv3 size = ');size(f3)visualize_feature_maps(f3,1);fm_conv4 = net.blob_vec(9);f4 = fm_conv4.get_data();fprintf('Feature map conv4 size = ');size(f4)visualize_feature_maps(f4,1);fm_conv5 = net.blob_vec(10);f5 = fm_conv5.get_data();fprintf('Feature map conv5 size = ');size(f5)visualize_feature_maps(f5,1);