Function main

examples/dnn_mmod_ex.cpp:71–226

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

int main(int argc, char** argv) try
{
    // In this example we are going to train a face detector 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 << "   ./dnn_mmod_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.  The idea is 
    // to use this training data to learn to identify human faces in new
    // images.  
    // 
    // Once you have trained an object detector 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 face detector
    // 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 face_boxes_train
    // holds the locations of the faces in the training images.  So for
    // example, the image images_train[0] has the faces given by the
    // rectangles in face_boxes_train[0].
    std::vector<matrix<rgb_pixel>> images_train, images_test;
    std::vector<std::vector<mmod_rect>> face_boxes_train, face_boxes_test;

    // Now we load the data.  These XML files list the images in each dataset
    // and also contain the positions of the face boxes.  Obviously you can use
    // any kind of input format you like so long as you store the data into
    // images_train and face_boxes_train.  But for convenience dlib comes with
    // tools for creating and loading XML image datasets.  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 with boxes.  To see how to use it read the
    // tools/imglab/README.txt file.
    load_image_dataset(images_train, face_boxes_train, faces_directory+"/training.xml");
    load_image_dataset(images_test, face_boxes_test, faces_directory+"/testing.xml");


    cout << "num training images: " << images_train.size() << endl;
    cout << "num testing images:  " << images_test.size() << endl;


    // The MMOD algorithm has some options you can set to control its behavior.  However,
    // you can also call the constructor with your training annotations and a "target
    // object size" and it will automatically configure itself in a reasonable way for your
    // problem.  Here we are saying that faces are still recognizably faces when they are