Question

我尝试使用dlib训练具有默认数据集（/dlib-19.0/examples/faces/training_with_face_landmarks.xml）和默认训练样本（train_shape_predictor_ex.cpp）的形状预测器。

所以我想训练形状预测器，它与默认形状预测器（ shape_predictor_68_face_landmarks.dat ）完全一样，因为我使用了相同的数据集和相同的训练代码。但是我遇到了一些问题。

训练结束后，我获得了16.6mb的.dat文件（但默认的dlib预测器shape_predictor_68_face_landmarks.dat有99.7mb）。在测试了我的.dat文件（16.6mb）后，我的准确度很低，但在测试了默认的.dat文件（shape_predictor_68_face_landmarks.dat，16.6mb）后，我的准确度很高。

我的形状预测器： shape_predictor_68_face_landmarks.dat：

训练：

#include <QCoreApplication>

#include <dlib/image_processing.h>
#include <dlib/data_io.h>
#include <iostream>

using namespace dlib;
using namespace std;

std::vector<std::vector<double> > get_interocular_distances (
        const std::vector<std::vector<full_object_detection> >& objects
        );

int main(int argc, char *argv[])
{
    QCoreApplication a(argc, argv);

    try
    {

        const std::string faces_directory = "/home/user/Documents/dlib-19.0/examples/faces/";

        dlib::array<array2d<unsigned char> > images_train;
        std::vector<std::vector<full_object_detection> > faces_train;

        load_image_dataset(images_train, faces_train, faces_directory+"training_with_face_landmarks.xml");

        shape_predictor_trainer trainer;

        trainer.set_oversampling_amount(300);

        trainer.set_nu(0.05);
        trainer.set_tree_depth(2);

        trainer.be_verbose();

        shape_predictor sp = trainer.train(images_train, faces_train);
        cout << "mean training error: "<<
                test_shape_predictor(sp, images_train, faces_train, get_interocular_distances(faces_train)) << endl;

        serialize(faces_directory+"sp_default_settings.dat") << sp;
    }
    catch (exception& e)
    {
        cout << "\nexception thrown!" << endl;
        cout << e.what() << endl;
    }

    return a.exec();
}

double interocular_distance (
        const full_object_detection& det
        )
{
    dlib::vector<double,2> l, r;
    double cnt = 0;
    // Find the center of the left eye by averaging the points around
    // the eye.
    for (unsigned long i = 36; i <= 41; ++i)
    {
        l += det.part(i);
        ++cnt;
    }
    l /= cnt;

    // Find the center of the right eye by averaging the points around
    // the eye.
    cnt = 0;
    for (unsigned long i = 42; i <= 47; ++i)
    {
        r += det.part(i);
        ++cnt;
    }
    r /= cnt;

    // Now return the distance between the centers of the eyes
    return length(l-r);
}

std::vector<std::vector<double> > get_interocular_distances (
        const std::vector<std::vector<full_object_detection> >& objects
        )
{
    std::vector<std::vector<double> > temp(objects.size());
    for (unsigned long i = 0; i < objects.size(); ++i)
    {
        for (unsigned long j = 0; j < objects[i].size(); ++j)
        {
            temp[i].push_back(interocular_distance(objects[i][j]));
        }
    }
    return temp;
}

测试：

#include <QCoreApplication>
#include <dlib/image_processing/frontal_face_detector.h>
#include <dlib/image_processing/render_face_detections.h>
#include <dlib/image_processing.h>
#include <dlib/gui_widgets.h>
#include <dlib/image_io.h>
#include <dlib/data_io.h>
#include <iostream>

using namespace dlib;
using namespace std;

int main(int argc, char *argv[])
{
    QCoreApplication a(argc, argv);

    try
        {

            // We need a face detector.  We will use this to get bounding boxes for
            // each face in an image.
            frontal_face_detector detector = get_frontal_face_detector();
            // And we also need a shape_predictor.  This is the tool that will predict face
            // landmark positions given an image and face bounding box.  Here we are just
            // loading the model from the shape_predictor_68_face_landmarks.dat file you gave
            // as a command line argument.
            shape_predictor sp;
            deserialize("/home/user/Downloads/muct-master/samples/sp_default_settings.dat") >> sp;

            string srcDir = "/home/user/Downloads/muct-master/samples/selection/";
            string dstDir = "/home/user/Downloads/muct-master/samples/my_results_default/";

            std::vector<string> vecOfImg;

            vecOfImg.push_back("i001qa-mn.jpg");
            vecOfImg.push_back("i002ra-mn.jpg");
            vecOfImg.push_back("i003ra-fn.jpg");
            vecOfImg.push_back("i003sa-fn.jpg");
            vecOfImg.push_back("i004qa-mn.jpg");
            vecOfImg.push_back("i004ra-mn.jpg");
            vecOfImg.push_back("i005ra-fn.jpg");
            vecOfImg.push_back("i006ra-mn.jpg");
            vecOfImg.push_back("i007qa-fn.jpg");
            vecOfImg.push_back("i008ra-mn.jpg");
            vecOfImg.push_back("i009qa-mn.jpg");
            vecOfImg.push_back("i009ra-mn.jpg");
            vecOfImg.push_back("i009sa-mn.jpg");
            vecOfImg.push_back("i010qa-mn.jpg");
            vecOfImg.push_back("i010sa-mn.jpg");
            vecOfImg.push_back("i011qa-mn.jpg");
            vecOfImg.push_back("i011ra-mn.jpg");
            vecOfImg.push_back("i012ra-mn.jpg");
            vecOfImg.push_back("i012sa-mn.jpg");
            vecOfImg.push_back("i014qa-fn.jpg");

            for(int imgC = 0; imgC < vecOfImg.size(); imgC++){

                array2d<rgb_pixel> img;
                load_image(img, srcDir + vecOfImg.at(imgC));
                // Make the image larger so we can detect small faces.
                pyramid_up(img);

                // Now tell the face detector to give us a list of bounding boxes
                // around all the faces in the image.
                std::vector<rectangle> dets = detector(img);
                cout << "Number of faces detected: " << dets.size() << endl;

                // Now we will go ask the shape_predictor to tell us the pose of
                // each face we detected.
                std::vector<full_object_detection> shapes;
                for (unsigned long j = 0; j < dets.size(); ++j)
                {
                    full_object_detection shape = sp(img, dets[j]);
                    cout << "number of parts: "<< shape.num_parts() << endl;
                    cout << "pixel position of first part:  " << shape.part(0) << endl;
                    cout << "pixel position of second part: " << shape.part(1) << endl;

                    for(unsigned long i = 0; i < shape.num_parts(); i++){
                        draw_solid_circle(img, shape.part(i), 2, rgb_pixel(100,255,100));
                    }

                    save_jpeg(img, dstDir + vecOfImg.at(imgC));
                    // You get the idea, you can get all the face part locations if
                    // you want them.  Here we just store them in shapes so we can
                    // put them on the screen.
                    shapes.push_back(shape);
                }

            }

        }
        catch (exception& e)
        {
            cout << "\nexception thrown!" << endl;
            cout << e.what() << endl;
        }
    return a.exec();
}

如果我使用默认数据集和示例，默认与我的培训和测试之间有什么区别？我如何将形状预测器训练为shape_predictor_68_face_landmarks.dat？

Answer 1

它正在生成一个16.6MB的DAT文件，因为您要么使用一些图像进行训练，要么使用正确的设置。

根据this Github issue，您在列车过程中没有使用最佳/默认设置。

在您的设置上，训练师的过采样量非常高（300），默认值为20。您还通过增加正则化（使nu param更小）和使用更小深度的树来减少模型的容量。

你的nu param：0.05。默认值为0.1

您的树深度：2。默认值为4

通过反复试验改变参数和训练，你会发现文件较小的最佳准确度。

请记住，每个培训过程大约需要45分钟，而您至少需要一台16GB的RAM计算机。

Answer 2

示例数据集（/dlib-19.0/examples/faces/training_with_face_landmarks.xml）太小，无法训练高质量的模型。这不是dlib附带的模型所训练的。

这些示例使用一个小数据集来使示例快速运行。所有示例的要点是解释dlib API，而不是有用的程序。它们只是文档。您可以使用dlib API做一些有趣的事情。

具有默认数据集和训练的形状预测器的低精度

2 个答案: