学习笔记之 初试Caffe,Matlab接口提取feature

Caffe 提供了matlab接口,可以用于提取图像的feature.





















首先,打开终端,进入
caffe的主目录下,然后打开Matlab ...
默认的文件是:classification_demo.m,
里面有两个函数。把路径设置完了之后,就可以试试运行了。我把它改成了我比较习惯的方式,即:xiao.m 

clc;

close all;

clear all;


num1=1000; % 提取多少张图像的feature

use_gpu=1; % 运行的模式,gpu or cpu ?


if exist('../+caffe', 'dir')

addpath('..');

else

error('Please run this demo from caffe/matlab/demo');

end


if exist('use_gpu', 'var') && use_gpu

caffe.set_mode_gpu();

gpu_id = 0; % we will use the first gpu in this demo

caffe.set_device(gpu_id);

else

caffe.set_mode_cpu();

end


model_dir = '../../models/bvlc_reference_caffenet/';

net_model = [model_dir 'deploy.prototxt'];

net_weights = [model_dir 'bvlc_reference_caffenet.caffemodel'];


phase = 'train';


if ~exist(net_weights, 'file')

error('Please download CaffeNet from Model Zoo before you run this demo');

end


% Initialize a network

net = caffe.Net(net_model, net_weights, phase);


fprintf('Read PETA-dataset images and Extract features ...\n');



dataPath = '../../Link to PETA dataset/3DPeS/archive/';

images = dir([dataPath,'*.bmp']);

 

for num=1:num1

 

% disp('read the', num2str(num) ,'th', '/', num2str(num1) ,'image, please waiting ...');

im = imread([dataPath, images(num).name]);

fid1 = fopen('train_feature_id.txt', 'a');

fprintf(fid1, '%s \n', images(num).name );

fclose(fid1);

 

 

% prepare oversampled input

% input_data is Height x Width x Channel x Num

% tic;

input_data = {prepare_image(im)};

% toc;


% do forward pass to get scores ­

% scores are now Channels x Num, where Channels == 1000

% tic;

% The net forward function. It takes in a cell array of N-D arrays

% (where N == 4 here) containing data of input blob(s) and outputs a cell

% array containing data from output blob(s)

scores = net.forward(input_data);

Score = scores{1,1};

fid = fopen('train_feature.txt', 'a');

fprintf(fid, '%f \n', Score);

fclose(fid);

 


% toc;


% scores = scores{1};

% scores = mean(scores, 2); % take average scores over 10 crops

% [~, maxlabel] = max(scores);

% call caffe.reset_all() to reset caffe

% caffe.reset_all();

 

end


这个函数调用了 prepare_image.m,因为caffe对图像的处理方式和常规的方式不同,需要对读取的图像做一个转换工作,而这个过程是由 prepare_image.m来完成的。


运行之后,就会生成两个txt文件,一个是读取图像的图像名字,另一个是对应所提取的feature

 

 

 

 

 


















        (a) train_feature_id          (b)  train_feature




由于这个网络的输入是255×255的图像,会对其做一个crop,生成10227×227的图像,所以最后的feature4096×10
的矩阵,而不是4096的向量。。。










posted @ 2015-10-16 12:20  AHU-WangXiao  阅读(1870)  评论(0编辑  收藏  举报