Function main

examples/dnn_introduction2_ex.cpp:130–387

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

int main(int argc, char** argv) try
{
    if (argc != 2)
    {
        cout << "This example needs the MNIST dataset to run!" << endl;
        cout << "You can get MNIST from http://yann.lecun.com/exdb/mnist/" << endl;
        cout << "Download the 4 files that comprise the dataset, decompress them, and" << endl;
        cout << "put them in a folder.  Then give that folder as input to this program." << endl;
        return 1;
    }

    std::vector<matrix<unsigned char>> training_images;
    std::vector<unsigned long> training_labels;
    std::vector<matrix<unsigned char>> testing_images;
    std::vector<unsigned long> testing_labels;
    load_mnist_dataset(argv[1], training_images, training_labels, testing_images, testing_labels);


    // dlib uses cuDNN under the covers.  One of the features of cuDNN is the
    // option to use slower methods that use less RAM or faster methods that use
    // a lot of RAM.  If you find that you run out of RAM on your graphics card
    // then you can call this function and we will request the slower but more
    // RAM frugal cuDNN algorithms.
    set_dnn_prefer_smallest_algorithms();


    // Create a network as defined above.  This network will produce 10 outputs
    // because that's how we defined net_type.  However, fc layers can have the
    // number of outputs they produce changed at runtime.  
    net_type net;
    // So if you wanted to use the same network but override the number of
    // outputs at runtime you can do so like this:
    net_type net2(num_fc_outputs(15));

    // Now, let's imagine we wanted to replace some of the relu layers with
    // prelu layers.  We might do it like this:
    using net_type2 = loss_multiclass_log<fc<number_of_classes,
                                avg_pool_everything<
                                pres<res<res<res_down< // 2 prelu layers here
                                tag4<repeat<9,pres,    // 9 groups, each containing 2 prelu layers  
                                res_down<
                                res<
                                input<matrix<unsigned char>>
                                >>>>>>>>>>>;

    // prelu layers have a floating point parameter.  If you want to set it to
    // something other than its default value you can do so like this:
    net_type2 pnet(prelu_(0.2),  
                   prelu_(0.25),
                   repeat_group(prelu_(0.3),prelu_(0.4)) // Initialize all the prelu instances in the repeat 
                                                         // layer.  repeat_group() is needed to group the 
                                                         // things that are part of repeat's block.
                   );
    // As you can see, a network will greedily assign things given to its
    // constructor to the layers inside itself.  The assignment is done in the
    // order the layers are defined, but it will skip layers where the
    // assignment doesn't make sense.