/// <summary>
/// The main program entry point.
/// </summary>
/// <param name="args"></param>
static void Main(string[] args)
{
// unpack archive
if (!File.Exists("x_channels_first_8_5.bin"))
{
Console.WriteLine("Unpacking archive...");
ZipFile.ExtractToDirectory("frog_pictures.zip", ".");
}
// load training and test data
Console.WriteLine("Loading data files...");
var trainingData = DataUtil.LoadBinary <float>("x_channels_first_8_5.bin", 5000, channels * imageWidth * imageHeight);
// create the generator input variable
var generatorVar = CNTK.Variable.InputVariable(new int[] { latentDimensions }, CNTK.DataType.Float, name: "generator_input");
// create the generator
Console.WriteLine("Creating generator...");
var generator = generatorVar
.Dense(128 * 16 * 16, v => CNTK.CNTKLib.LeakyReLU(v, 0.1))
.Reshape(new int[] { 16, 16, 128 })
.Convolution2D(256, new int[] { 5, 5 }, padding: true, activation: v => CNTK.CNTKLib.LeakyReLU(v, 0.1))
.ConvolutionTranspose(
filterShape: new int[] { 4, 4 },
numberOfFilters: 256,
strides: new int[] { 2, 2 },
outputShape: new int[] { 32, 32 },
padding: true,
activation: v => CNTK.CNTKLib.LeakyReLU(v, 0.1)
)
.Convolution2D(256, new int[] { 5, 5 }, padding: true, activation: v => CNTK.CNTKLib.LeakyReLU(v, 0.1))
.Convolution2D(256, new int[] { 5, 5 }, padding: true, activation: v => CNTK.CNTKLib.LeakyReLU(v, 0.1))
.Convolution2D(channels, new int[] { 7, 7 }, padding: true, activation: CNTK.CNTKLib.Tanh)
.ToNetwork();
Console.WriteLine(generator.ToSummary());
// create the discriminator input variable
var discriminatorVar = CNTK.Variable.InputVariable(new int[] { imageWidth, imageHeight, channels }, CNTK.DataType.Float, name: "discriminator_input");
// create the discriminator
Console.WriteLine("Creating discriminator...");
var discriminator = discriminatorVar
.Convolution2D(128, new int[] { 3, 3 }, activation: v => CNTK.CNTKLib.LeakyReLU(v, 0.1))
.Convolution2D(128, new int[] { 4, 4 }, strides: new int[] { 2, 2 }, activation: v => CNTK.CNTKLib.LeakyReLU(v, 0.1))
.Convolution2D(128, new int[] { 4, 4 }, strides: new int[] { 2, 2 }, activation: v => CNTK.CNTKLib.LeakyReLU(v, 0.1))
.Convolution2D(128, new int[] { 4, 4 }, strides: new int[] { 2, 2 }, activation: v => CNTK.CNTKLib.LeakyReLU(v, 0.1))
.Dropout(0.4)
.Dense(1, CNTK.CNTKLib.Sigmoid)
.ToNetwork();
Console.WriteLine(discriminator.ToSummary());
// create the Gan
Console.WriteLine("Creating Gan...");
var gan = Gan.CreateGan(generator, discriminator);
// create the label variable
var labelVar = CNTK.Variable.InputVariable(shape: new CNTK.NDShape(0), dataType: CNTK.DataType.Float, name: "label_var");
// set up the loss functions
var discriminatorLoss = CNTK.CNTKLib.BinaryCrossEntropy(discriminator, labelVar);
var ganLoss = CNTK.CNTKLib.BinaryCrossEntropy(gan, labelVar);
// set up the learners
var discriminatorLearner = discriminator.GetAdaDeltaLearner(1);
var ganLearner = gan.GetAdaDeltaLearner(1);
// set up the trainers
var discriminatorTrainer = discriminator.GetTrainer(discriminatorLearner, discriminatorLoss, discriminatorLoss);
var ganTrainer = gan.GetTrainer(ganLearner, ganLoss, ganLoss);
// make sure we have an images folder to write to
var outputFolder = "images";
if (!Directory.Exists(outputFolder))
{
Directory.CreateDirectory(outputFolder);
}
// train the gan during multiple epochs
Console.WriteLine("Training Gan...");
var numEpochs = 100000;
var batchSize = 12;
var start = 0;
for (var epoch = 0; epoch < numEpochs; epoch++)
{
// run the generator and create a set of fake frog images
var generatedImages = Gan.GenerateImages(generator, batchSize, latentDimensions);
// get a training batch: a mix of fake and real images labelled correctly
start = Math.Min(start, trainingData.Length - batchSize);
var batch = Gan.GetTrainingBatch(discriminatorVar, generatedImages, trainingData, batchSize, start);
start += batchSize;
if (start >= trainingData.Length)
{
start = 0;
}
// train the discriminator
var discriminatorResult = discriminatorTrainer.TrainBatch(
new[] {
static void Main(string[] args)
{
foreach (var item in CNTK.DeviceDescriptor.AllDevices())
{
Console.WriteLine($"{item.Id}: {item.Type.ToString()}");
}
/// Data loading
if (!File.Exists("./x_channels_first_8_5.bin"))
{
Console.WriteLine("Unpacking archive...");
ZipFile.ExtractToDirectory("../../../../Resources/frog_pictures.zip", "./");
}
Console.WriteLine("Loading data files..");
float[][] trainingData = DataUtil.LoadBinary <float>("./x_channels_first_8_5.bin", 5000, channels * imageHeight * imageWidth);
/// Generator Input Variable
Variable generatorVar = CNTK.Variable.InputVariable(new int[] { latentDimensions }, DataType.Float, "generator_input");
// Generator Architecture
Function generator = generatorVar.Dense(128 * 16 * 16, v => CNTK.CNTKLib.LeakyReLU(v, 0.1))
.Reshape(new int[] { 16, 16, 128 })
.Convolution2D(256, new int[] { 5, 5 }, padding: true, activation: v => CNTK.CNTKLib.LeakyReLU(v, 0.1))
.ConvolutionTranspose(
filterShape: new int[] { 4, 4 },
numberOfFilters: 128,
strides: new int[] { 2, 2 },
outputShape: new int[] { 32, 32 },
padding: true,
activation: v => CNTK.CNTKLib.LeakyReLU(v, 0.1)
)
.Convolution2D(256, new int[] { 3, 3 }, padding: true, activation: v => CNTK.CNTKLib.LeakyReLU(v, 0.1))
.Convolution2D(256, new int[] { 5, 5 }, padding: true, activation: v => CNTK.CNTKLib.LeakyReLU(v, 0.1))
.Convolution2D(256, new int[] { 7, 7 }, padding: true, activation: v => CNTK.CNTKLib.Tanh(v))
.Convolution2D(channels, new int[] { 7, 7 }, padding: true, activation: CNTK.CNTKLib.Tanh)
.ToNetwork();
// .Dense(128 * 16 * 16, var => CNTK.CNTKLib.LeakyReLU(var, 0.1))
// .Reshape(new int[] { 16, 16, 128 })
// .Convolution2D(256, new int[] { 5, 5 }, padding: true, activation: var => CNTK.CNTKLib.LeakyReLU(var, 0.1))
// .ConvolutionTranspose(
// filterShape: new int[] { 4, 4 },
// numberOfFilters: 256,
// strides: new int[] { 2, 2 },
// outputShape: new int[] { 32, 32 },
// padding: true,
// activation: var => CNTK.CNTKLib.LeakyReLU(var, 0.1))
// .Convolution2D(256, new int[] { 5, 5 }, padding: true, activation: var => CNTK.CNTKLib.LeakyReLU(var, 0.1))
// .Convolution2D(256, new int[] { 5, 5 }, padding: true, activation: var => CNTK.CNTKLib.LeakyReLU(var, 0.1))
// .Convolution2D(channels, new int[] { 7, 7 }, padding: true, activation: CNTK.CNTKLib.Tanh)
// .ToNetwork();
// Discriminator Input Variable
Variable discriminatorVar = CNTK.Variable.InputVariable(new int[] { imageWidth, imageHeight, channels }, DataType.Float, name: "discriminator_input");
// Discriminator Architecture
Function discriminator = discriminatorVar.Convolution2D(32, new int[] { 7, 7 }, padding: true, activation: v => CNTK.CNTKLib.LeakyReLU(v, 0.1))
.Convolution2D(32, new int[] { 5, 5 }, padding: true, activation: v => CNTK.CNTKLib.LeakyReLU(v, 0.1))
.Pooling(PoolingType.Max, new int[] { 5, 5 }, new int[] { 1, 1 })
.Convolution2D(64, new int[] { 5, 5 }, padding: true, activation: v => CNTK.CNTKLib.LeakyReLU(v, 0.1))
.Convolution2D(64, new int[] { 5, 5 }, padding: true, activation: v => CNTK.CNTKLib.LeakyReLU(v, 0.1))
.Pooling(PoolingType.Max, new int[] { 5, 5 }, new int[] { 1, 1 })
.Convolution2D(128, new int[] { 4, 4 }, padding: true, strides: new int[] { 2, 2 }, activation: v => CNTK.CNTKLib.LeakyReLU(v, 0.1))
.Convolution2D(256, new int[] { 4, 4 }, padding: true, strides: new int[] { 2, 2 }, activation: v => CNTK.CNTKLib.LeakyReLU(v, 0.1))
.Pooling(PoolingType.Max, new int[] { 4, 4 }, new int[] { 1, 1 })
.Convolution2D(512, new int[] { 3, 3 }, strides: new int[] { 2, 2 }, activation: v => CNTK.CNTKLib.Tanh(v))
.Dropout(0.2)
.Dense(1, CNTK.CNTKLib.Sigmoid)
.ToNetwork();
// +++ Create GAN +++
Function gan = Gan.CreateGan(generator, discriminator);
// Output of GAN
Variable labelVar = CNTK.Variable.InputVariable(new NDShape(0), DataType.Float, "label_var");
// Loss Function
Function discriminatorLoss = CNTK.CNTKLib.BinaryCrossEntropy(discriminator, labelVar);
Function ganLoss = CNTK.CNTKLib.BinaryCrossEntropy(gan, labelVar);
// Set up the algorithms for traning discriminator and the GAN (learners)
Learner discriminatorLearner = discriminator.GetAdaDeltaLearner(1);
Learner ganLearner = gan.GetAdaDeltaLearner(0.25);
// Set up the trainers for calculating [_ the discriminator and gan loss _] during each training epoch
Trainer discriminatorTrainer = discriminator.GetTrainer(discriminatorLearner, discriminatorLoss, discriminatorLoss);
Trainer ganTrainer = gan.GetTrainer(ganLearner, ganLoss, ganLoss);
/// START Training!
string outputFolder = "./images";
if (!Directory.Exists(outputFolder))
{
Directory.CreateDirectory(outputFolder);
}
Console.WriteLine("Training GAN...");
int numEpoches = 100_000;
int batchSize = 15;
int start = 0;
for (int epoch = 0; epoch < numEpoches; epoch++)
{
// create a set of fake images..
var generatedImages = Gan.GenerateImages(generator, batchSize, latentDimensions);
start = Math.Min(start, trainingData.Length - batchSize);
///////////////////////COPIED
var batch = Gan.GetTrainingBatch(discriminatorVar, generatedImages, trainingData, batchSize, start);
start += batchSize;
if (start >= trainingData.Length)
{
start = 0;
}
// train the discriminator
//var discriminatorResult = discriminatorTrainer.TrainMinibatch(
// new Dictionary<Variable, Value> { { discriminatorVar, batch.featureBatch }, { labelVar, batch.labelBatch } }, false, CNTK.DeviceDescriptor.GPUDevice(0)
// );
var discriminatorResult = discriminatorTrainer.TrainBatch(
new[] {
