介绍

在本教程中，您将学习如何使用OpenCv_dnn模块进行图像分类，方法是使用来自Caffe模型动物园的 GoogLeNet训练网络。

我们将在下面的图片中展示这个例子的结果。

布兰航天飞机

源代码

我们将使用示例应用程序的片段，可以在这里下载。

#include <opencv2/dnn.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/highgui.hpp>
#include <opencv2/core/utils/trace.hpp>
using namespace cv;
using namespace cv::dnn;
#include <fstream>
#include <iostream>
#include <cstdlib>
using namespace std;
/* Find best class for the blob (i. e. class with maximal probability) */
static void getMaxClass(const Mat &probBlob, int *classId, double *classProb)
{
    Mat probMat = probBlob.reshape(1, 1); //reshape the blob to 1x1000 matrix
    Point classNumber;
    minMaxLoc(probMat, NULL, classProb, NULL, &classNumber);
    *classId = classNumber.x;
}
static std::vector<String> readClassNames(const char *filename = "synset_words.txt")
{
    std::vector<String> classNames;
    std::ifstream fp(filename);
    if (!fp.is_open())
    {
        std::cerr << "File with classes labels not found: " << filename << std::endl;
        exit(-1);
    }
    std::string name;
    while (!fp.eof())
    {
        std::getline(fp, name);
        if (name.length())
            classNames.push_back( name.substr(name.find(' ')+1) );
    }
    fp.close();
    return classNames;
}
int main(int argc, char **argv)
{
    CV_TRACE_FUNCTION();
    String modelTxt = "bvlc_googlenet.prototxt";
    String modelBin = "bvlc_googlenet.caffemodel";
    String imageFile = (argc > 1) ? argv[1] : "space_shuttle.jpg";
    Net net;
    try {
        net = dnn::readNetFromCaffe(modelTxt, modelBin);
    }
    catch (cv::Exception& e) {
        std::cerr << "Exception: " << e.what() << std::endl;
        if (net.empty())
        {
            std::cerr << "Can't load network by using the following files: " << std::endl;
            std::cerr << "prototxt:   " << modelTxt << std::endl;
            std::cerr << "caffemodel: " << modelBin << std::endl;
            std::cerr << "bvlc_googlenet.caffemodel can be downloaded here:" << std::endl;
            std::cerr << "http://dl.caffe.berkeleyvision.org/bvlc_googlenet.caffemodel" << std::endl;
            exit(-1);
        }
    }
    Mat img = imread(imageFile);
    if (img.empty())
    {
        std::cerr << "Can't read image from the file: " << imageFile << std::endl;
        exit(-1);
    }
    //GoogLeNet accepts only 224x224 BGR-images
    Mat inputBlob = blobFromImage(img, 1.0f, Size(224, 224),
                                  Scalar(104, 117, 123), false);   //Convert Mat to batch of images
    Mat prob;
    cv::TickMeter t;
    for (int i = 0; i < 10; i++)
    {
        CV_TRACE_REGION("forward");
        net.setInput(inputBlob, "data");        //set the network input
        t.start();
        prob = net.forward("prob");                          //compute output
        t.stop();
    }
    int classId;
    double classProb;
    getMaxClass(prob, &classId, &classProb);//find the best class
    std::vector<String> classNames = readClassNames();
    std::cout << "Best class: #" << classId << " '" << classNames.at(classId) << "'" << std::endl;
    std::cout << "Probability: " << classProb * 100 << "%" << std::endl;
    std::cout << "Time: " << (double)t.getTimeMilli() / t.getCounter() << " ms (average from " << t.getCounter() << " iterations)" << std::endl;
    return 0;
} //main

说明

• 首先，下载GoogLeNet模型文件：bvlc_googlenet.prototxt和bvlc_googlenet.caffemodel还需要使用名称为ILSVRC2012类的文件：synset_words.txt。将这些文件放入此程序示例的工作目录中。
• 使用.prototxt和.caffemodel文件的路径读取并初始化网络

        net = dnn :: readNetFromCaffe（modelTxt，modelBin）;

• 检查网络是否已成功读取
  

        if (net.empty())
        {
            std::cerr << "Can't load network by using the following files: " << std::endl;
            std::cerr << "prototxt:   " << modelTxt << std::endl;
            std::cerr << "caffemodel: " << modelBin << std::endl;
            std::cerr << "bvlc_googlenet.caffemodel can be downloaded here:" << std::endl;
            std::cerr << "http://dl.caffe.berkeleyvision.org/bvlc_googlenet.caffemodel" << std::endl;
            exit(-1);
        }

• 读取输入图像并转换为Blob，可由GoogleNet接受
  

    Mat img = imread(imageFile);
    if (img.empty())
    {
        std::cerr << "Can't read image from the file: " << imageFile << std::endl;
        exit(-1);
    }
    //GoogLeNet accepts only 224x224 BGR-images
    Mat inputBlob = blobFromImage(img, 1.0f, Size(224, 224),
                                  Scalar(104, 117, 123), false);   //Convert Mat to batch of images

首先，我们调整图像的大小并改变其频道序列顺序。

现在图像实际上是一个具有224x224x3形状的三维数组。

接下来，我们通过使用特殊的cv :: dnn :: blobFromImages构造函数将图像转换为具有1x3x224x224形状的4维blob（所谓批处理）。

• 将blob传递到网络
  

        net.setInput(inputBlob, "data");        //set the network input

在bvlc_googlenet.prototxt中，网络输入blob命名为“data”，因此这个blob在opencv_dnn API中标记为“.data”。

其他标记为“name_of_layer.name_of_layer_output”的blob。

• Make forward pass
  

        prob = net.forward("prob");                          //compute output

在计算每个网络层的正向传输输出期间，但在本例中，我们仅需要“prob”层的输出。

• 确定最好的class

    int classId;
    double classProb;
    getMaxClass(prob, &classId, &classProb);//find the best class

我们把包含1000个ILSVRC2012图像类别的概率的“prob”层的输出放到probblob上。并在此找到具有最大值的元素的索引。该索引对应于图像的类。

• 打印结果

    std::vector<String> classNames = readClassNames();
    std::cout << "Best class: #" << classId << " '" << classNames.at(classId) << "'" << std::endl;
    std::cout << "Probability: " << classProb * 100 << "%" << std::endl;

对于我们的形象我们得到：

Best class: #812 'space shuttle'

Probability: 99.6378%