public void Init()
{
INeuralNetwork network = NetworkManager.NewSequential(TensorInfo.Image <Alpha8>(20, 20),
CuDnnNetworkLayers.Convolutional((5, 5), 20, ActivationType.Identity),
CuDnnNetworkLayers.Pooling(ActivationType.LeakyReLU),
CuDnnNetworkLayers.Convolutional((3, 3), 40, ActivationType.LeakyReLU),
CuDnnNetworkLayers.Pooling(ActivationType.LeakyReLU),
CuDnnNetworkLayers.FullyConnected(125, ActivationType.LeakyReLU),
CuDnnNetworkLayers.FullyConnected(64, ActivationType.LeakyReLU),
CuDnnNetworkLayers.Softmax(10));
}
public static async Task Main()
{
// Create the network
INeuralNetwork network = NetworkManager.NewSequential(TensorInfo.Image <Alpha8>(28, 28),
CuDnnNetworkLayers.Convolutional((5, 5), 20, ActivationType.Identity),
CuDnnNetworkLayers.Pooling(ActivationType.LeakyReLU),
CuDnnNetworkLayers.Convolutional((3, 3), 40, ActivationType.Identity),
CuDnnNetworkLayers.Pooling(ActivationType.LeakyReLU),
CuDnnNetworkLayers.FullyConnected(125, ActivationType.LeCunTanh),
CuDnnNetworkLayers.Softmax(10));
// Prepare the dataset
ITrainingDataset trainingData = await Mnist.GetTrainingDatasetAsync(400); // Batches of 400 samples
ITestDataset testData = await Mnist.GetTestDatasetAsync(p => Printf($"Epoch {p.Iteration}, cost: {p.Result.Cost}, accuracy: {p.Result.Accuracy}"));
if (trainingData == null || testData == null)
{
Printf("Error downloading the datasets");
Console.ReadKey();
return;
}
// Setup and network training
CancellationTokenSource cts = new CancellationTokenSource();
Console.CancelKeyPress += (s, e) => cts.Cancel();
TrainingSessionResult result = await NetworkManager.TrainNetworkAsync(network,
trainingData,
TrainingAlgorithms.AdaDelta(),
20, 0.5f,
TrackBatchProgress,
testDataset : testData, token : cts.Token);
// Save the training reports
string
timestamp = DateTime.Now.ToString("yy-MM-dd-hh-mm-ss"),
path = Path.GetDirectoryName(Path.GetFullPath(Assembly.GetExecutingAssembly().Location)),
dir = Path.Combine(path ?? throw new InvalidOperationException("The dll path can't be null"), "TrainingResults", timestamp);
Directory.CreateDirectory(dir);
File.WriteAllText(Path.Combine(dir, $"{timestamp}_cost.py"), result.TestReports.AsPythonMatplotlibChart(TrainingReportType.Cost));
File.WriteAllText(Path.Combine(dir, $"{timestamp}_accuracy.py"), result.TestReports.AsPythonMatplotlibChart(TrainingReportType.Accuracy));
network.Save(new FileInfo(Path.Combine(dir, $"{timestamp}{NetworkLoader.NetworkFileExtension}")));
File.WriteAllText(Path.Combine(dir, $"{timestamp}.json"), network.SerializeMetadataAsJson());
File.WriteAllText(Path.Combine(dir, $"{timestamp}_report.json"), result.SerializeAsJson());
Printf($"Stop reason: {result.StopReason}, elapsed time: {result.TrainingTime}");
Console.ReadKey();
}
public void NetworkSerialization()
{
INeuralNetwork network = NetworkManager.NewSequential(TensorInfo.Image <Rgb24>(120, 120),
CuDnnNetworkLayers.Convolutional(ConvolutionInfo.New(ConvolutionMode.CrossCorrelation), (10, 10), 20, ActivationType.AbsoluteReLU),
CuDnnNetworkLayers.Convolutional(ConvolutionInfo.New(ConvolutionMode.Convolution, 2, 2), (5, 5), 20, ActivationType.ELU),
CuDnnNetworkLayers.Convolutional(ConvolutionInfo.Default, (10, 10), 20, ActivationType.Identity),
CuDnnNetworkLayers.Pooling(PoolingInfo.New(PoolingMode.AverageIncludingPadding, 2, 2, 1, 1), ActivationType.ReLU),
CuDnnNetworkLayers.Convolutional(ConvolutionInfo.Default, (10, 10), 20, ActivationType.Identity),
CuDnnNetworkLayers.Pooling(PoolingInfo.Default, ActivationType.ReLU),
CuDnnNetworkLayers.FullyConnected(125, ActivationType.Tanh),
CuDnnNetworkLayers.FullyConnected(27, ActivationType.Tanh),
CuDnnNetworkLayers.Softmax(133));
using (MemoryStream stream = new MemoryStream())
{
network.Save(stream);
stream.Seek(0, SeekOrigin.Begin);
INeuralNetwork copy = NetworkLoader.TryLoad(stream, ExecutionModePreference.Cuda);
Assert.IsTrue(network.Equals(copy));
}
}
public void ForwardTest2()
{
INeuralNetwork cpu = NetworkManager.NewSequential(TensorInfo.Image <Alpha8>(28, 28),
CuDnnNetworkLayers.Convolutional(ConvolutionInfo.Default, (5, 5), 20, ActivationType.Identity),
CuDnnNetworkLayers.Pooling(PoolingInfo.Default, ActivationType.ReLU),
CuDnnNetworkLayers.Convolutional(ConvolutionInfo.Default, (3, 3), 20, ActivationType.Identity),
CuDnnNetworkLayers.Pooling(PoolingInfo.Default, ActivationType.ReLU),
CuDnnNetworkLayers.FullyConnected(100, ActivationType.LeCunTanh),
CuDnnNetworkLayers.FullyConnected(50, ActivationType.LeCunTanh),
CuDnnNetworkLayers.Softmax(10));
INeuralNetwork gpu = NetworkManager.NewGraph(TensorInfo.Image <Alpha8>(28, 28), root =>
{
var conv1 = root.Layer(_ => cpu.Layers[0].Clone());
var pool1 = conv1.Layer(_ => cpu.Layers[1].Clone());
var conv2 = pool1.Layer(_ => cpu.Layers[2].Clone());
var pool2 = conv2.Layer(_ => cpu.Layers[3].Clone());
var fc1 = pool2.Layer(_ => cpu.Layers[4].Clone());
var fc2 = fc1.Layer(_ => cpu.Layers[5].Clone());
fc2.Layer(_ => cpu.Layers[6].Clone());
});
ForwardTest(cpu, gpu);
}