如何在OpenCV 2.4.13中导入训练有素的SVM检测器 [英] How to import a trained SVM detector in OpenCV 2.4.13

问题描述

因此，我已经按照本指南培训了自己的行人HOG检测器. https://github.com/DaHoC/trainHOG/wiki/trainHOG-Tutorial

So I have followed this guide to train my own pedestrian HOG detector. https://github.com/DaHoC/trainHOG/wiki/trainHOG-Tutorial

成功生成了4个文件.

And it was successful with 4 files generated.

• cvHOGClassifier.yaml
• descriptorvector.dat
• features.dat
• svmlightmodel.dat

有人知道如何将描述符vector.dat文件作为矢量加载吗? 我已经尝试过了，但是失败了.

Does anyone know how to load the descriptorvector.dat file as a vector? I've tried this but failed.

    vector<float> detector;
    std::ifstream file;
    file.open("descriptorvector.dat");
    file >> detector;
    file.close();

这是我最终要使用的东西.

This is something I would like to use eventually.

    gpu::HOGDescriptor hog(Size(64, 128), Size(16, 16), Size(8, 8), Size(8, 8),9);
    hog.setSVMDetector(detector);

先谢谢您！

推荐答案

您可以读取文件并将每个值都推回float数组，因此首先声明它:

You can read the file and push every value back to an array of float, so first declare it:

vector<float> myDescriptorVector;

然后推送每个值:

ifstream infile ("yourFile.dat".c_str());

float number;

while (infile >> number)
    myDescriptorVector.push_back(number);


return myDescriptorVector;

最后，对HOG使用标准初始化，然后将向量传递到SVM检测器，就像您已经猜到的那样:

Finally use the standard initialization for the HOG and pass the vector to the SVM detector as you already guessed:

hog.setSVMDetector(myDescriptorVector);

这篇关于如何在OpenCV 2.4.13中导入训练有素的SVM检测器的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！