MCPcopy Create free account
hub / github.com/davisking/dlib / main

Function main

examples/dnn_dcgan_train_ex.cpp:106–256  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

104}
105
106int main(int argc, char** argv) try
107{
108 // This example is going to run on the MNIST dataset.
109 if (argc != 2)
110 {
111 cout << "This example needs the MNIST dataset to run!" << endl;
112 cout << "You can get MNIST from http://yann.lecun.com/exdb/mnist/" << endl;
113 cout << "Download the 4 files that comprise the dataset, decompress them, and" << endl;
114 cout << "put them in a folder. Then give that folder as input to this program." << endl;
115 return EXIT_FAILURE;
116 }
117
118 // MNIST is broken into two parts, a training set of 60000 images and a test set of 10000
119 // images. Each image is labeled so that we know what hand written digit is depicted.
120 // These next statements load the dataset into memory.
121 std::vector<matrix<unsigned char>> training_images;
122 std::vector<unsigned long> training_labels;
123 std::vector<matrix<unsigned char>> testing_images;
124 std::vector<unsigned long> testing_labels;
125 load_mnist_dataset(argv[1], training_images, training_labels, testing_images, testing_labels);
126
127 // Fix the random generator seeds for network initialization and noise
128 srand(1234);
129 dlib::rand rnd(std::rand());
130
131 // Instantiate both generator and discriminator
132 generator_type generator;
133 discriminator_type discriminator;
134 // setup all leaky_relu_ layers in the discriminator to have alpha = 0.2
135 visit_computational_layers(discriminator, [](leaky_relu_& l){ l = leaky_relu_(0.2); });
136 // Remove the bias learning from all bn_ inputs in both networks
137 disable_duplicative_biases(generator);
138 disable_duplicative_biases(discriminator);
139 // Forward random noise so that we see the tensor size at each layer
140 discriminator(generate_image(generator, make_noise(rnd)));
141 cout << "generator (" << count_parameters(generator) << " parameters)" << endl;
142 cout << generator << endl;
143 cout << "discriminator (" << count_parameters(discriminator) << " parameters)" << endl;
144 cout << discriminator << endl;
145
146 // The solvers for the generator and discriminator networks. In this example, we are going to
147 // train the networks manually, so we don't need to use a dnn_trainer. Note that the
148 // discriminator could be trained using a dnn_trainer, but not the generator, since its
149 // training process is a bit particular.
150 std::vector<adam> g_solvers(generator.num_computational_layers, adam(0, 0.5, 0.999));
151 std::vector<adam> d_solvers(discriminator.num_computational_layers, adam(0, 0.5, 0.999));
152 double learning_rate = 2e-4;
153
154 // Resume training from last sync file
155 size_t iteration = 0;
156 if (file_exists("dcgan_sync"))
157 {
158 deserialize("dcgan_sync") >> generator >> discriminator >> iteration;
159 }
160
161 const size_t minibatch_size = 64;
162 const std::vector<float> real_labels(minibatch_size, 1);
163 const std::vector<float> fake_labels(minibatch_size, -1);

Callers

nothing calls this directly

Calls 15

load_mnist_datasetFunction · 0.85
generate_imageFunction · 0.85
make_noiseFunction · 0.85
count_parametersFunction · 0.85
file_existsFunction · 0.85
get_generated_imagesFunction · 0.85
tile_imagesFunction · 0.85
compute_lossMethod · 0.80
deserializeFunction · 0.70

Tested by

no test coverage detected