the cat is on the matlab,在MATLAB下调试Caffe

Caffe本身是C++、CUDA语言编写的。在调试模型、参数时，根据运行log、snapshot很难实时反馈当前训练的权值情况，也难以捕捉算法存在的bug。

MATLAB则是非常适合算法设计、快速迭代的利器，只需要做少量工作就能编写出复杂的算法，调试非常方便，位于workspace中的变量随时都能打印，无论是一维、二维还是三维数据，都能直观显示，从而有利于定位算法设计问题，减少调试时间。

Caffe中有两种Wrapper：Python和MATLAB。Python是开源工具，用户无需付费即可使用，缺点是语法不够灵活，尤其算法描述，与商业软件不能比。MATLAB支持几乎你所知道的所有矩阵变换、数值计算、随机过程、概率论、最优化、自适应滤波、图像处理、神经网络等算法。

下面介绍如何用MATLAB调试Caffe。本文假设操作系统为Ubuntu 14.04.1  64bit .

1. 安装MATLAB R2014A

可以到这里下载(http://yunpan.taobao.com/s/ZFLGQjNABU，提取码：dxBxMJ)

安装步骤类似Windows，不表。安装到~/MATLAB/，~/.bashrc中添加 export PATH=~/MATLAB/bin:$PATH

2.  安装Caffe

参考步骤：http://caffe.berkeleyvision.org/install_apt.html。其他OS请参考http://caffe.berkeleyvision.org/installation.html。

如果你希望自己编译依赖，可以到这里下载Caffe所有依赖包(http://yunpan.taobao.com/s/1I1TXcPYsk3，提取码：yuqZm1)

3. 编译 MatCaffe

修改Makefile.config，加上这一句：

MATLAB_DIR := ～/MATLAB

之后

make matcaffe

生成了 matlab/+caffe/private/caffe_.mex64，可以直接被MATLAB调用。

4. 运行MATLAB例子

在命令行中，配置好Caffe运行所需要的环境变量后(否则matcaffe会运行失败)，输入matlab&，这样就启动了MATLAB窗口。

在MATLAB命令窗口中进行以下步骤。

>> cd Caffe_root_directory/

切换到了Caffe根目录。

>> addpath('./matlab/+caffe/private');

添加matcaffe模块所在路径到MATLAB搜索路径，便于加载。

>> cd matlab/demo/

切到demo目录。

>> im = imread('../../examples/images/cat.jpg');

读取一张测试图片。

>> figure;imshow(im);

弹出一个窗口，显示猫的测试图片如下：

>> [scores, maxlabel] = classification_demo(im, 1);

Elapsed time is 0.533388 seconds.

Elapsed time is 0.511420 seconds.

Cleared 0 solvers and 1 stand-alone nets

运行分类demo程序。分类的结果返回到scores，maxlabel两个工作空间变量中。

>> maxlabel

maxlabel =

282

说明最大分类概率的标签号为282，查找ImageNet标签，对应的是n02123045 tabby, tabby cat(data/ilsvrc2012/synset_words.txt)

>> figure;plot(scores);

>> axis([0, 999, -0.1, 0.5]);

>> grid on

打印scores，一维图像如下：

说明这张图片被分到第282类的概率为0.2985。

到这里我们只是运行了简单的demo，接下来分析classification_demo.m这个文件内容。

function [scores, maxlabel] = classification_demo(im, use_gpu)

% [scores, maxlabel] = classification_demo(im, use_gpu)

% 使用BVLC CaffeNet进行图像分类的示例

% 重要：运行前，应首先从Model Zoo(http://caffe.berkeleyvision.org/model_zoo.html) 下载BVLC CaffeNet训练好的权值

%

% ****************************************************************************

% For detailed documentation and usage on Caffe's Matlab interface, please

% refer to Caffe Interface Tutorial at

% http://caffe.berkeleyvision.org/tutorial/interfaces.html#matlab

% ****************************************************************************

%

% input

% im color image as uint8 HxWx3

% use_gpu 1 to use the GPU, 0 to use the CPU

%

% output

% scores 1000-dimensional ILSVRC score vector

% maxlabel the label of the highest score

%

% You may need to do the following before you start matlab:

% $ export LD_LIBRARY_PATH=/opt/intel/mkl/lib/intel64:/usr/local/cuda-5.5/lib64

% $ export LD_PRELOAD=/usr/lib/x86_64-linux-gnu/libstdc++.so.6

% Or the equivalent based on where things are installed on your system

%

% Usage:

% im = imread('../../examples/images/cat.jpg');

% scores = classification_demo(im, 1);

% [score, class] = max(scores);

% Five things to be aware of:

% caffe uses row-major order

% matlab uses column-major order

% caffe uses BGR color channel order

% matlab uses RGB color channel order

% images need to have the data mean subtracted

% Data coming in from matlab needs to be in the order

% [width, height, channels, images]

% where width is the fastest dimension.

% Here is the rough matlab for putting image data into the correct

% format in W x H x C with BGR channels:

% % permute channels from RGB to BGR

% im_data = im(:, :, [3, 2, 1]);

% % flip width and height to make width the fastest dimension

% im_data = permute(im_data, [2, 1, 3]);

% % convert from uint8 to single

% im_data = single(im_data);

% % reshape to a fixed size (e.g., 227x227).

% im_data = imresize(im_data, [IMAGE_DIM IMAGE_DIM], 'bilinear');

% % subtract mean_data (already in W x H x C with BGR channels)

% im_data = im_data - mean_data;

% If you have multiple images, cat them with cat(4, ...)

% Add caffe/matlab to you Matlab search PATH to use matcaffe

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

addpath('..');

else

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

end

% Set caffe mode

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

% Initialize the network using BVLC CaffeNet for image classification

% Weights (parameter) file needs to be downloaded from Model Zoo.

model_dir = '../../models/bvlc_reference_caffenet/'; % 模型所在目录

net_model = [model_dir 'deploy.prototxt']; % 模型描述文件，注意是deploy.prototxt，不包含data layers

net_weights = [model_dir 'bvlc_reference_caffenet.caffemodel']; % 模型权值文件，需要预先下载到这里

phase = 'test'; % run with phase test (so that dropout isn't applied) % 只进行分类，不做训练

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); % 初始化网络

if nargin < 1

% For demo purposes we will use the cat image

fprintf('using caffe/examples/images/cat.jpg as input image\n');

im = imread('../../examples/images/cat.jpg'); % 获取输入图像

end

% prepare oversampled input

% input_data is Height x Width x Channel x Num

tic;

input_data = {prepare_image(im)}; % 图像冗余处理

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); % 分类，得到scores

toc;

scores = scores{1};

scores = mean(scores, 2); % 取所有分类结果的平均值

[~, maxlabel] = max(scores); % 找到最大概率对应的标签号

% call caffe.reset_all() to reset caffe

caffe.reset_all();

% ------------------------------------------------------------------------

function crops_data = prepare_image(im)

% ------------------------------------------------------------------------

% caffe/matlab/+caffe/imagenet/ilsvrc_2012_mean.mat contains mean_data that

% is already in W x H x C with BGR channels

d = load('../+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 channels

im_data = im(:, :, [3, 2, 1]); % permute channels from RGB to BGR

im_data = permute(im_data, [2, 1, 3]); % flip width and height

im_data = single(im_data); % convert from uint8 to single

im_data = imresize(im_data, [IMAGE_DIM IMAGE_DIM], 'bilinear'); % resize im_data

im_data = im_data - mean_data; % subtract mean_data (already in W x H x C, BGR)

% oversample (4 corners, center, and their x-axis flips)

crops_data = zeros(CROPPED_DIM, CROPPED_DIM, 3, 10, 'single');

indices = [0 IMAGE_DIM-CROPPED_DIM] + 1;

n = 1;

for i = indices

for j = indices

crops_data(:, :, :, n) = im_data(i:i+CROPPED_DIM-1, j:j+CROPPED_DIM-1, :);

crops_data(:, :, :, n+5) = crops_data(end:-1:1, :, :, n);

n = n + 1;

end

end

center = floor(indices(2) / 2) + 1;

crops_data(:,:,:,5) = ...

im_data(center:center+CROPPED_DIM-1,center:center+CROPPED_DIM-1,:);

crops_data(:,:,:,10) = crops_data(end:-1:1, :, :, 5);