static void Main(string[] args)
{
IActivationFunction activationFunction = new TanH();
for (float x = -2; x < 2; x += 0.1f)
{
Debug.Write($"{activationFunction.ActivationDerivative((float)Math.Tanh(x))},");
//Debug.Write($"{Math.Tanh(x)},");
}
// Create the random object.
Random random = new Random();
// Load the data set.
DigitDataSet digitDataSet = DigitDataSet.LoadFromFile("Files/labels.idx1-ubyte", "Files/images.idx3-ubyte");
DigitDataSet testSet = DigitDataSet.LoadFromFile("Files/t10k-labels.idx1-ubyte", "Files/t10k-images.idx3-ubyte");
// Take input.
Console.WriteLine("Choose the size of a batch.");
int batchSize = int.Parse(Console.ReadLine());
Console.WriteLine("Choose number of epochs.");
int epochs = int.Parse(Console.ReadLine());
// Create the neural network.
NeuralNetwork neuralNetwork = new NeuralNetwork(random, new int[] { digitDataSet.ImageWidth *digitDataSet.ImageHeight, 30, 10 }, 3.0f); //Network.NeuralNetwork.Load(new XmlNetworkLoader("DigitRecognition.xml"));
neuralNetwork.LearnOverData(random, digitDataSet, epochs, batchSize, new NetworkConsoleLogger(OutputOptions.All ^ OutputOptions.CurrentData), testSet);
//neuralNetwork.LearnOverData(random, digitDataSet, epochs, batchSize, new NetworkConsoleLogger(OutputOptions.None ^ OutputOptions.WhenFinished), testSet);
neuralNetwork.Save(new XmlNetworkSaver("DigitRecognition.xml", true));
Console.ReadKey();
}
public void CalculateTest(double firstValue, double expected)
{
var calculator = new TanH();
var actualResult = calculator.Calculate(firstValue);
Assert.AreEqual(expected, actualResult, 0.0001);
}
private void btn_createNetwork_Click(object sender, RoutedEventArgs e)
{
int[] layers = new int[this.wp_layers.Items.Count + 2];
layers[0] = Convert.ToInt32((this.ucInputLayer.Content as NetwokLayerSizeControl).GetLayerSize());
for (int i = 1; i < layers.Length - 1; i++)
{
layers[i] = Convert.ToInt32((this.wp_layers.Items[i - 1] as NetwokLayerSizeControl).GetLayerSize());
}
layers[layers.Length - 1] = Convert.ToInt32((this.ucOutputLayer.Content as NetwokLayerSizeControl).GetLayerSize());
ActivationStrategy acti = new Sigmoid();
if (this.cb_activationFunctions.SelectedIndex == 0)
{
acti = new Sigmoid();
}
else if (this.cb_activationFunctions.SelectedIndex == 1)
{
acti = new TanH();
}
else if (this.cb_activationFunctions.SelectedIndex == 2)
{
acti = new ReLU();
}
NetworkHelper.SaveNetToFile(new NeuralNetwork(layers, acti), "neuralNetwork.txt");
MessageBox.Show("Success!");
}
private List <IKernelDescriptor> ReadDescriptors(JObject model)
{
List <IKernelDescriptor> dscps = model.SelectToken("descriptors").Select(layer => {
IKernelDescriptor descriptor = null;
String layerName = (String)layer.SelectToken("layer");
switch (layerName)
{
case "AvgPooling1D":
descriptor = new AvgPooling1D(
(int)layer.SelectToken("padding"),
(int)layer.SelectToken("stride"),
(int)layer.SelectToken("kernel_size"));
break;
case "GlobalAveragePooling1D":
descriptor = new GlobalAvgPooling1D();
break;
case "AvgPooling2D":
descriptor = new AvgPooling2D((int)layer.SelectToken("padding_vl"), (int)layer.SelectToken("padding_hz"),
(int)layer.SelectToken("stride_vl"), (int)layer.SelectToken("stride_hz"),
(int)layer.SelectToken("kernel_height"), (int)layer.SelectToken("kernel_width"));
break;
case "GlobalAveragePooling2D":
descriptor = new GlobalAvgPooling2D();
break;
case "BatchNormalization":
descriptor = new BatchNormalization(
(int)layer.SelectToken("epsilon"));
break;
case "Cropping1D":
descriptor = new Cropping1D(
(int)layer.SelectToken("trimBegin"),
(int)layer.SelectToken("trimEnd"));
break;
case "Cropping2D":
descriptor = new Cropping2D(
(int)layer.SelectToken("topTrim"),
(int)layer.SelectToken("bottomTrim"),
(int)layer.SelectToken("leftTrim"),
(int)layer.SelectToken("rightTrim"));
break;
case "MaxPooling1D":
descriptor = new MaxPooling1D(
(int)layer.SelectToken("padding"),
(int)layer.SelectToken("stride"),
(int)layer.SelectToken("kernel_size"));
break;
case "GlobalMaxPooling1D":
descriptor = new GlobalMaxPooling1D();
break;
case "MaxPooling2D":
descriptor = new MaxPooling2D((int)layer.SelectToken("padding_vl"), (int)layer.SelectToken("padding_hz"),
(int)layer.SelectToken("stride_vl"), (int)layer.SelectToken("stride_hz"),
(int)layer.SelectToken("kernel_height"), (int)layer.SelectToken("kernel_width"));
break;
case "GlobalMaxPooling2D":
descriptor = new GlobalMaxPooling2D();
break;
case "Convolution1D":
descriptor = new Convolution1D(
(int)layer.SelectToken("padding"),
(int)layer.SelectToken("stride"),
(int)layer.SelectToken("kernel_size"),
(int)layer.SelectToken("kernel_num"));
break;
case "Convolution2D":
descriptor = new Convolution2D((int)layer.SelectToken("padding_vl"), (int)layer.SelectToken("padding_hz"),
(int)layer.SelectToken("stride_vl"), (int)layer.SelectToken("stride_hz"),
(int)layer.SelectToken("kernel_height"), (int)layer.SelectToken("kernel_width"),
(int)layer.SelectToken("kernel_num"));
break;
case "Dense2D":
descriptor = new Dense2D((int)layer.SelectToken("units"));
break;
case "Input2D":
descriptor = new Input2D((int)layer.SelectToken("height"), (int)layer.SelectToken("width"),
(int)layer.SelectToken("channel"), (int)layer.SelectToken("batch"));
break;
case "Bias2D":
descriptor = new Bias2D();
break;
case "Permute":
descriptor = new Permute(
(int)layer.SelectToken("dim1"),
(int)layer.SelectToken("dim2"),
(int)layer.SelectToken("dim3"));
break;
case "Reshape":
descriptor = new Reshape2D(
(int)layer.SelectToken("height"),
(int)layer.SelectToken("width"),
(int)layer.SelectToken("channel"),
1);
break;
case "RepeatVector":
descriptor = new RepeatVector(
(int)layer.SelectToken("num"));
break;
case "SimpleRNN":
descriptor = new SimpleRNN(
(int)layer.SelectToken("units"),
(int)layer.SelectToken("input_dim"),
ANR((string)layer.SelectToken("activation")));
break;
case "LSTM":
descriptor = new LSTM(
(int)layer.SelectToken("units"),
(int)layer.SelectToken("input_dim"),
ANR((string)layer.SelectToken("activation")),
ANR((string)layer.SelectToken("rec_act")));
break;
case "GRU":
descriptor = new GRU(
(int)layer.SelectToken("units"),
(int)layer.SelectToken("input_dim"),
ANR((string)layer.SelectToken("activation")),
ANR((string)layer.SelectToken("rec_act")));
break;
case "ELu":
descriptor = new ELu(1);
break;
case "HardSigmoid":
descriptor = new HardSigmoid();
break;
case "ReLu":
descriptor = new ReLu();
break;
case "Sigmoid":
descriptor = new Sigmoid();
break;
case "Flatten":
descriptor = new Flatten();
break;
case "Softmax":
descriptor = new Softmax();
break;
case "SoftPlus":
descriptor = new SoftPlus();
break;
case "SoftSign":
descriptor = new Softsign();
break;
case "TanH":
descriptor = new TanH();
break;
default:
throw new Exception("Unknown layer type!");
}
return(descriptor);
}).ToList();
return(dscps);
}
