好了，現在我們已經訓練好自己的model，如何用這個model去預測我們待測樣本的標籤，就成了一個需要解決的問題。

       這裡我們主要說的是Matlab程式呼叫訓練好的model來預測標籤。但是在說這個之前，有必要說說如何用caffe檔案中的classification.exe

       程式碼如下：

>>e:
>>cd E:\Python\Caffe\Build\x64\Release
>>compute_image_mean.exe ../../../examples/mnist/Deal_Data/mnist_train_lmdb ../../../examples/mnist/mean.binaryproto --backend=lmdb
>>classification.exe ../../../examples/mnist/lenet_deploy.prototxt ../../../examples/mnist/lenet_iter_10000.caffemodel ../../../examples/mnist/mean.binaryproto ../../../examples/mnist/MatlabCode/label.txt ../../../examples/mnist/MatlabCode/testimage/12.png
>>pause
 

Step1：準備階段

1、這裡我們需要將編譯好的“+caffe檔案”複製到你的matlab程式所在的資料夾下

2、將待測圖片也複製到該資料夾下

3、新建一個TXT檔案（名為label.txt），寫0,1,2,3,4,5,6,7,8,9（為了將輸出的值對映到標籤時用的）

4、根據lenet_train_test.prototxt，改寫所需要的lenet_deploy。

name: "LeNet"
layer {
  name: "data"
  type: "Input"
  top: "data"
  input_param { shape: { dim: 1 dim: 1 dim: 28 dim: 28 } }
}
 

layer {
  name: "conv1"
  type: "Convolution"
  bottom: "data"
  top: "conv1"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 20
    kernel_size: 5
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "pool1"
  type: "Pooling"
  bottom: "conv1"
  top: "pool1"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "conv2"
  type: "Convolution"
  bottom: "pool1"
  top: "conv2"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 50
    kernel_size: 5
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "pool2"
  type: "Pooling"
  bottom: "conv2"
  top: "pool2"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "ip1"
  type: "InnerProduct"
  bottom: "pool2"
  top: "ip1"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  inner_product_param {
    num_output: 500
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "relu1"
  type: "ReLU"
  bottom: "ip1"
  top: "ip1"
}
layer {
  name: "ip2"
  type: "InnerProduct"
  bottom: "ip1"
  top: "ip2"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  inner_product_param {
    num_output: 10
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "prob"
  type: "Softmax"
  bottom: "ip2"
  top: "prob"
}
 

Step2：核心函式（ClassificateFuction.m）

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

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 = '../';  
net_model = [model_dir 'lenet_deploy.prototxt'];  
net_weights = [model_dir 'lenet_iter_10000.caffemodel'];  
phase = 'test'; % run with phase test (so that dropout isn't applied)  
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);  
% prepare oversampled input  
% input_data is Height x Width x Channel x Num  
tic;  
    mean_data = caffe.io.read_mean('../mean.binaryproto');  
    scale=0.00390625;  
    im=double(im);  
    im=(im-mean_data)*scale;  
    input_data = {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);  
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(); 

Step3：主函式（mnist_test.m）

%該程式為使用caffe中mnist訓練出來的model，來預測待測圖片的標籤

% ---------------------------------------自寫程式--------------------------------------
clc;clear all;close all;

im=imread('/testimage/14.png');

figure;imshow(im);%輸入im要進行轉置[scores,maxlabel]=classification_demo(im',0); %獲取得分 第二個引數0：cpu 1:gpu
figure;plot(scores);  %畫出得分情況
axis([0,10,-0.1,1.5]);%座標軸範圍
grid on;              %有網格

fid=fopen('label.txt','r');
i=0;
while ~feof(fid)%test for end-of-file
    i=i+1;
    lin=fgetl(fid);%read line from file
    lin=strtrim(lin);%remove the leading and trailing white-space from string
    if(i==maxlabel)
        fprintf('the labelof %d in label txt is %c\n',i,lin);
        break;
    end
end

Step4:run起來（mnist_test.m）

bingo！結果出來了，效果還不錯，基本上預測正確了

這麼跑一通，可以呼叫caffemodel了，特別注意的是：大部分錯誤在於路徑問題，所以一定要頭腦清楚，寫對路徑。