Function main

examples/train_shape_predictor_ex.cpp:41–149

// ----------------------------------------------------------------------------------------

int main(int argc, char** argv)
{
    try
    {
        // In this example we are going to train a shape_predictor based on the
        // small faces dataset in the examples/faces directory.  So the first
        // thing we do is load that dataset.  This means you need to supply the
        // path to this faces folder as a command line argument so we will know
        // where it is.
        if (argc != 2)
        {
            cout << "Give the path to the examples/faces directory as the argument to this" << endl;
            cout << "program.  For example, if you are in the examples folder then execute " << endl;
            cout << "this program by running: " << endl;
            cout << "   ./train_shape_predictor_ex faces" << endl;
            cout << endl;
            return 0;
        }
        const std::string faces_directory = argv[1];
        // The faces directory contains a training dataset and a separate
        // testing dataset.  The training data consists of 4 images, each
        // annotated with rectangles that bound each human face along with 68
        // face landmarks on each face.  The idea is to use this training data
        // to learn to identify the position of landmarks on human faces in new
        // images. 
        // 
        // Once you have trained a shape_predictor it is always important to
        // test it on data it wasn't trained on.  Therefore, we will also load
        // a separate testing set of 5 images.  Once we have a shape_predictor 
        // created from the training data we will see how well it works by
        // running it on the testing images. 
        // 
        // So here we create the variables that will hold our dataset.
        // images_train will hold the 4 training images and faces_train holds
        // the locations and poses of each face in the training images.  So for
        // example, the image images_train[0] has the faces given by the
        // full_object_detections in faces_train[0].
        dlib::array<array2d<unsigned char> > images_train, images_test;
        std::vector<std::vector<full_object_detection> > faces_train, faces_test;

        // Now we load the data.  These XML files list the images in each
        // dataset and also contain the positions of the face boxes and
        // landmarks (called parts in the XML file).  Obviously you can use any
        // kind of input format you like so long as you store the data into
        // images_train and faces_train.  But for convenience dlib comes with
        // tools for creating and loading XML image dataset files.  Here you see
        // how to load the data.  To create the XML files you can use the imglab
        // tool which can be found in the tools/imglab folder.  It is a simple
        // graphical tool for labeling objects in images.  To see how to use it
        // read the tools/imglab/README.txt file.
        load_image_dataset(images_train, faces_train, faces_directory+"/training_with_face_landmarks.xml");
        load_image_dataset(images_test, faces_test, faces_directory+"/testing_with_face_landmarks.xml");

        // Now make the object responsible for training the model.  
        shape_predictor_trainer trainer;
        // This algorithm has a bunch of parameters you can mess with.  The
        // documentation for the shape_predictor_trainer explains all of them.
        // You should also read Kazemi's paper which explains all the parameters