/// <summary>
/// Create, train and use a neural network for XOR.
/// </summary>
/// <param name="args">Not used</param>
static void Main(string[] args)
{
FeedforwardNetwork network = new FeedforwardNetwork();
network.AddLayer(new FeedforwardLayer(2));
network.AddLayer(new FeedforwardLayer(3));
network.AddLayer(new FeedforwardLayer(1));
network.Reset();
// train the neural network
Train train = new HeatonResearchNeural.Feedforward.Train.Backpropagation.Backpropagation(network, XOR_INPUT, XOR_IDEAL,
0.7, 0.9);
int epoch = 1;
do
{
train.Iteration();
Console.WriteLine("Epoch #" + epoch + " Error:" + train.Error);
epoch++;
} while ((epoch < 5000) && (train.Error > 0.001));
// test the neural network
Console.WriteLine("Neural Network Results:");
for (int i = 0; i < XOR_IDEAL.Length; i++)
{
double[] actual = network.ComputeOutputs(XOR_INPUT[i]);
Console.WriteLine(XOR_INPUT[i][0] + "," + XOR_INPUT[i][1]
+ ", actual=" + actual[0] + ",ideal=" + XOR_IDEAL[i][0]);
}
}
static void Main(string[] args) {
FeedforwardNetwork network = new FeedforwardNetwork();
network.AddLayer(new FeedforwardLayer(2));
network.AddLayer(new FeedforwardLayer(3));
network.AddLayer(new FeedforwardLayer(1));
network.Reset();
// train the neural network
TrainingSetNeuralGeneticAlgorithm train = new TrainingSetNeuralGeneticAlgorithm(
network, true, XOR_INPUT, XOR_IDEAL, 5000, 0.1, 0.25);
int epoch = 1;
do {
train.Iteration();
Console.WriteLine("Epoch #" + epoch + " Error:" + train.Error);
epoch++;
} while ((epoch < 5000) && (train.Error > 0.001));
network = train.Network;
// test the neural network
Console.WriteLine("Neural Network Results:");
for (int i = 0; i < XOR_IDEAL.Length; i++) {
double []actual = network.ComputeOutputs(XOR_INPUT[i]);
Console.WriteLine(XOR_INPUT[i][0] + "," + XOR_INPUT[i][1]
+ ", actual=" + actual[0] + ",ideal=" + XOR_IDEAL[i][0]);
}
}
public static BitmapImage GetEdges(BitmapImage binaryBitmapImage, FeedforwardNetwork network,
BackgroundWorker backgroundWorker)
{
Bitmap sourceBitmap = GetBitmap(binaryBitmapImage);
int width = sourceBitmap.Width;
int height = sourceBitmap.Height;
if (width < 2 || height < 2)
{
return null;
}
//todo:переделать
if (width % 2 != 0 || height % 2 != 0)
{
return null;
}
Bitmap edgeBitmap = new Bitmap(width, height);
for (int y = 0; y < height; y += 1)
{
for (int x = 0; x < width; x += 1)
{
edgeBitmap.SetPixel(x, y, Color.White);
}
}
/*using (StreamWriter file = new StreamWriter("debug.txt"))
{*/
for (int y = 0; y < height - 1; y += 1)
{
for (int x = 0; x < width - 1; x += 1)
{
double[] values =
{
(sourceBitmap.GetPixel(x, y).R) / 255,
(sourceBitmap.GetPixel(x + 1, y).R) / 255,
(sourceBitmap.GetPixel(x, y + 1).R) / 255,
(sourceBitmap.GetPixel(x + 1, y + 1).R) / 255
};
double[] output = network.ComputeOutputs(values);
backgroundWorker.ReportProgress(0, new[] {values, output});
//Thread.Sleep(300);
double[,] outputValues =
{
{
output[0], output[1]
},
{
output[2], output[3]
}
};
/*file.Write(x + "," + y + " " + (x + 1) + "," + y + " " + x + "," + (y + 1) + " " + (x + 1) + "," + (y + 1) + ": "
+ (sourceBitmap.GetPixel(x, y).R) + " " + (sourceBitmap.GetPixel(x + 1, y).R)
+ " " + (sourceBitmap.GetPixel(x, y + 1).R) + " " + (sourceBitmap.GetPixel(x + 1, y + 1).R) + " -> ");
for (int y1 = 0; y1 < 2; y1++)
{
for (int x1 = 0; x1 < 2; x1++)
{
file.Write((x + x1) + "," + (y + y1));
if (x1 == 1 && y1 == 1)
{
file.Write(": ");
}
else
{
file.Write(" ");
}
}
}*/
for (int y1 = 0; y1 < 2; y1++)
{
for (int x1 = 0; x1 < 2; x1++)
{
double value = outputValues[y1, x1];
int intValue = (int)value;
if (value - intValue == 0.5)
{
value += 0.01;
}
int pixelValue = (int)(Math.Round(value) * 255);
Color color = Color.FromArgb(pixelValue, pixelValue, pixelValue);
if (edgeBitmap.GetPixel(x + x1, y + y1).R == 255)
{
edgeBitmap.SetPixel(x + x1, y + y1, color);
}
/* file.Write(color.R);
if (x1 == 1 && y1 == 1)
{
file.Write("\r\n");
}
else
{
file.Write(" ");
}*/
}
}
}
}
// }
edgeBitmap.Save("edges.jpg");
BitmapImage resultBitmapImage = GetBitmapImage(edgeBitmap);
resultBitmapImage.Freeze();
return resultBitmapImage;
}
/// <summary>
/// Create, train and use a neural network for XOR.
/// </summary>
/// <param name="args">Not used</param>
static void Main(string[] args)
{
/*XOR_INPUT = new double[256][];
XOR_IDEAL = new double[256][];
String[] lines = File.ReadAllLines("input.txt");
for (int i = 0; i < lines.Length; i++)
{
String str = lines[i];
double[] input = new double[8];
for (int j = 0; j < 8; j++)
{
input[j] = Double.Parse(str[j].ToString());
}
XOR_INPUT[i] = input;
}
lines = File.ReadAllLines("output.txt");
for (int i = 0; i < lines.Length; i++)
{
String str = lines[i];
double[] output = new double[1];
output[0] = Double.Parse(str);
XOR_IDEAL[i] = output;
}
*/
FeedforwardNetwork network = new FeedforwardNetwork();
network.AddLayer(new FeedforwardLayer(4));
network.AddLayer(new FeedforwardLayer(12));
network.AddLayer(new FeedforwardLayer(4));
network.Reset();
// train the neural network
Train train = new Backpropagation(network, XOR_INPUT, XOR_IDEAL,
0.2, 0.95);
int epoch = 1;
Stopwatch watch = new Stopwatch();
watch.Start();
do
{
train.Iteration();
Console.WriteLine("Epoch #" + epoch + " Error:" + train.Error);
epoch++;
} while ((epoch < 40000) && (train.Error > 0.001));
watch.Stop();
Console.WriteLine(watch.ElapsedMilliseconds / 1000.0);
// test the neural network
#if DEBUG
Console.WriteLine("Neural Network Results:");
for (int i = 0; i < XOR_IDEAL.Length; i++)
{
double[] actual = network.ComputeOutputs(XOR_INPUT[i]);
Console.WriteLine(XOR_INPUT[i][0] + "," + XOR_INPUT[i][1] + "," + XOR_INPUT[i][2] + "," + XOR_INPUT[i][3]
+ ", actual=" + actual[0] + "," + actual[1] + "," + actual[2] + "," + actual[3] + ",ideal=" + XOR_IDEAL[i][0] + "," + XOR_IDEAL[i][1] + "," + XOR_IDEAL[i][2] + "," + XOR_IDEAL[i][3]);
}
#endif
FeedforwardLayer inputLayer = network.InputLayer;
Console.WriteLine("Input layer matrix:");
Matrix layerMatrix = inputLayer.LayerMatrix;
using (StreamWriter file = new StreamWriter("weights.txt"))
{
for (int i = 0; i < layerMatrix.Rows; i++)
{
for (int j = 0; j < layerMatrix.Cols; j++)
{
Console.Write(Math.Round(layerMatrix[i, j], 3) + " ");
file.Write(layerMatrix[i, j]);
if (j != layerMatrix.Cols - 1)
{
file.Write(" ");
}
}
Console.WriteLine();
file.WriteLine();
}
file.WriteLine();
FeedforwardLayer hiddenLayer = network.HiddenLayers.ToList()[0];
Console.WriteLine("Hidden layer matrix:");
layerMatrix = hiddenLayer.LayerMatrix;
for (int i = 0; i < layerMatrix.Rows; i++)
{
for (int j = 0; j < layerMatrix.Cols; j++)
{
Console.Write(Math.Round(layerMatrix[i, j], 3) + " ");
file.Write(layerMatrix[i, j]);
if (j != layerMatrix.Cols - 1)
{
file.Write(" ");
}
}
Console.WriteLine();
file.WriteLine();
}
}
#if SHOW_MATRIX
FeedforwardLayer outputLayer = network.OutputLayer;
Console.WriteLine("Output layer matrix:");
layerMatrix = outputLayer.LayerMatrix;
for (int i = 0; i < layerMatrix.Rows; i++)
{
for (int j = 0; j < layerMatrix.Cols; j++)
{
Console.Write(layerMatrix[i, j] + " ");
}
Console.WriteLine();
}
foreach (FeedforwardLayer feedforwardLayer in network.Layers)
{
Matrix layerMatrix = feedforwardLayer.LayerMatrix;
Console.WriteLine(feedforwardLayer.Next);
for (int i = 0; i < layerMatrix.Rows; i++)
{
for (int j = 0; j < layerMatrix.Cols; j++)
{
Console.Write(layerMatrix[i, j] + " ");
}
Console.WriteLine();
}
}
#endif
Console.ReadKey();
}
/// <summary>
/// Create, train and use a neural network for XOR.
/// </summary>
/// <param name="args">Not used</param>
static void Main(string[] args)
{
List<String> lines = File.ReadAllLines("weights.txt").ToList();
double[,] inputLayerWeights = new double[5, 12];
double[,] hiddenLayerWeights = new double[13, 4];
bool forInput = true;
int counter = 0;
foreach (string line in lines)
{
if (String.IsNullOrWhiteSpace(line))
{
forInput = false;
counter = 0;
}
else
{
if (forInput)
{
string[] strings = line.Split(' ');
for (int i = 0; i < strings.Count(); i++)
{
inputLayerWeights[counter, i] = double.Parse(strings[i]);
}
}
else
{
string[] strings = line.Split(' ');
for (int i = 0; i < strings.Count(); i++)
{
hiddenLayerWeights[counter, i] = double.Parse(strings[i]);
}
}
counter++;
}
}
Matrix inputLayerMatrix = new Matrix(inputLayerWeights);
Matrix hiddenLayermatrix = new Matrix(hiddenLayerWeights);
FeedforwardNetwork network = new FeedforwardNetwork();
network.AddLayer(new FeedforwardLayer(4));
network.AddLayer(new FeedforwardLayer(12));
network.AddLayer(new FeedforwardLayer(4));
network.Reset();
FeedforwardLayer inputLayer = network.InputLayer;
inputLayer.LayerMatrix = inputLayerMatrix;
FeedforwardLayer hiddenLayer = network.HiddenLayers.ToList()[0];
hiddenLayer.LayerMatrix = hiddenLayermatrix;
Console.WriteLine("Neural Network Results:");
for (int i = 0; i < XOR_IDEAL.Length; i++)
{
double[] actual = network.ComputeOutputs(XOR_INPUT[i]);
Console.WriteLine(XOR_INPUT[i][0] + "," + XOR_INPUT[i][1] + "," + XOR_INPUT[i][2] + "," + XOR_INPUT[i][3]
+ ", actual=" + actual[0] + "," + actual[1] + "," + actual[2] + "," + actual[3] + ",ideal=" + XOR_IDEAL[i][0] + "," + XOR_IDEAL[i][1] + "," + XOR_IDEAL[i][2] + "," + XOR_IDEAL[i][3]);
}
Console.ReadKey();
/*Console.WriteLine("Input layer matrix:");
Matrix layerMatrix = inputLayer.LayerMatrix;
for (int i = 0; i < layerMatrix.Rows; i++)
{
for (int j = 0; j < layerMatrix.Cols; j++)
{
Console.Write(Math.Round(layerMatrix[i, j], 3) + " ");
}
Console.WriteLine();
}
Console.WriteLine("Hidden layer matrix:");
layerMatrix = hiddenLayer.LayerMatrix;
for (int i = 0; i < layerMatrix.Rows; i++)
{
for (int j = 0; j < layerMatrix.Cols; j++)
{
Console.Write(Math.Round(layerMatrix[i, j], 3) + " ");
}
Console.WriteLine();
} */
}