public double Evaluate(BasicNetwork network, IMLDataSet training)
{
var rprop = new ResilientPropagation(network, training);
double startingError = network.CalculateError(training);
for (int i = 0; i < ITERATIONS; i++)
{
rprop.Iteration();
}
double finalError = network.CalculateError(training);
return(startingError - finalError);
}
static void Main(string[] args)
{
IMLDataSet trainingSet = new BasicMLDataSet(XOR_INPUT, XOR_IDEAL);
BasicNetwork network = EncogUtility.SimpleFeedForward(2, 6, 0, 1, false);
EncogUtility.TrainToError(network, trainingSet, 0.01);
double error = network.CalculateError(trainingSet);
Console.WriteLine($"Error before save to EG: {error}");
EncogDirectoryPersistence.SaveObject(new FileInfo(FILENAME), network);
network = (BasicNetwork)EncogDirectoryPersistence.LoadObject(new FileInfo(FILENAME));
error = network.CalculateError(trainingSet);
Console.WriteLine($"Error after load from EG: {error}");
}
public void Execute(IExampleInterface app)
{
this.app = app;
IMLDataSet trainingSet = new BasicMLDataSet(XOR_INPUT, XOR_IDEAL);
BasicNetwork network = EncogUtility.SimpleFeedForward(2, 6, 0, 1, false);
EncogUtility.TrainToError(network, trainingSet, 0.01);
double error = network.CalculateError(trainingSet);
EncogDirectoryPersistence.SaveObject(new FileInfo(FILENAME), network);
double error2 = network.CalculateError(trainingSet);
app.WriteLine("Error before save to EG: " + Format.FormatPercent(error));
app.WriteLine("Error before after to EG: " + Format.FormatPercent(error2));
}
public void Execute(IExampleInterface app)
{
this.app = app;
this.app = app;
IMLDataSet trainingSet = new BasicMLDataSet(XOR_INPUT, XOR_IDEAL);
BasicNetwork network = EncogUtility.SimpleFeedForward(2, 6, 0, 1, false);
EncogUtility.TrainToError(network, trainingSet, 0.01);
double error = network.CalculateError(trainingSet);
SerializeObject.Save("encog.ser", network);
network = (BasicNetwork)SerializeObject.Load("encog.ser");
double error2 = network.CalculateError(trainingSet);
app.WriteLine("Error before save to ser: " + Format.FormatPercent(error));
app.WriteLine("Error before after to ser: " + Format.FormatPercent(error2));
}
public double[][] Train(double[][] trainingData, double[][] validationData)
{
var error = new List <double[]>();
PrepareNormalizerFor(trainingData, validationData);
var trainingSet = PrepareSet(trainingData);
var validationSet = PrepareSet(validationData);
var training = new Backpropagation(_network, trainingSet, _settings.LearningRate, _settings.Momentum)
{
BatchSize = 1
};
for (int epoch = 0; epoch < _settings.Iterations; epoch++)
{
training.Iteration();
double trainingError = -1;
double testingError = -1;
if (_settings.Type == ProblemType.Regression)
{
trainingError = _network.CalculateError(trainingSet);
if (validationSet != null)
{
testingError = _network.CalculateError(validationSet);
}
}
else
{
trainingError = CalculateClassificationError(trainingSet);
if (validationSet != null)
{
testingError = CalculateClassificationError(validationSet);
}
}
var errorIter = new[] { epoch, trainingError, testingError };
error.Add(errorIter);
Console.WriteLine($"Epoch #{epoch} [{training.Error}] TrainingError: {errorIter[1]} ValidationError: {errorIter[2]}");
}
training.FinishTraining();
return(error.ToArray());
}
private void BtnComprobar_Click(object sender, EventArgs e)
{
try
{
if (i0 != null)
{
this.conect.Open();
OleDbCommand comando = new OleDbCommand(string.Format("select ArchivoNeuronal,Tamano from tbl_firmas where Pnombre = '{0}' and PApellido = '{1}' ", txtNombre.Text, txtApellido.Text), this.conect);
OleDbDataReader lector = comando.ExecuteReader();
string dirArchivo = null;
if (lector.HasRows)
{
while (lector.Read())
{
dirArchivo = Application.StartupPath + "\\" + lector.GetString(0);
tam = lector.GetString(1);
}
BasicNetwork RedExtraida = (BasicNetwork)EncogDirectoryPersistence.LoadObject(new FileInfo(dirArchivo));
IMLDataSet par = new BasicMLDataSet(E, IDEAL);
double Respuesta = RedExtraida.CalculateError(par);
if (Respuesta <= .20)
{
MessageBox.Show("La firma Introducida Tiene un nivel de aceptacion del : " + Convert.ToString(100 - Math.Round(Respuesta, 3) * 100) + "%, la firma ha sido ACEPTADA");
}
else
{
MessageBox.Show("La firma Introducida Tiene un nivel de aceptacion del : " + Convert.ToString(100 - Math.Round(Respuesta, 3) * 100) + "%, la firma ha sido RECHAZADA");
}
}
else
{
MessageBox.Show("Nombre y apellido no existe");
}
}
else
{
MessageBox.Show("No hay imagen cargada");
}
}
catch (System.ArgumentException)
{
MessageBox.Show("Verifique que la imagen tenga un tamaño de " + tam);
}
this.conect.Close();
}
public double EvaluateMPROP(BasicNetwork network, IMLDataSet data)
{
var train = new ResilientPropagation(network, data);
long start = DateTime.Now.Ticks;
Console.WriteLine(@"Training 20 Iterations with MPROP");
for (int i = 1; i <= 20; i++)
{
train.Iteration();
Console.WriteLine("Iteration #" + i + " Error:" + train.Error);
}
//train.finishTraining();
long stop = DateTime.Now.Ticks;
double diff = new TimeSpan(stop - start).Seconds;
Console.WriteLine("MPROP Result:" + diff + " seconds.");
Console.WriteLine("Final MPROP error: " + network.CalculateError(data));
return(diff);
}
static void Main(string[] args)
{
string ruta_datos = "C:\\Users\\soyal\\Downloads\\Muestra2RGBC.csv";
StreamReader lector = new StreamReader(ruta_datos);
var lineas = new List <string[]>();
string[] Linea;
while (!lector.EndOfStream)
{
Linea = lector.ReadLine().Split(',');
lineas.Add(Linea);
}
double[][] Input = new double[lineas.Count][];
double[][] Output = new double[lineas.Count][];
for (int i = 0; i < lineas.Count; i++)
{
Input[i] = new double[4];
Output[i] = new double[6];
Input[i][0] = Convert.ToDouble(lineas[i][0]); //Canal R
Input[i][1] = Convert.ToDouble(lineas[i][1]); //Canal G
Input[i][2] = Convert.ToDouble(lineas[i][2]); //Canal B
Input[i][3] = Convert.ToDouble(lineas[i][3]); //Canal C
Output[i][0] = Convert.ToDouble(lineas[i][4]); //1 si es rojo
Output[i][1] = Convert.ToDouble(lineas[i][5]); //1 si es naranja
Output[i][2] = Convert.ToDouble(lineas[i][6]); //1 si es amarillo
Output[i][3] = Convert.ToDouble(lineas[i][7]); //1 si es verde
Output[i][4] = Convert.ToDouble(lineas[i][8]); //1 si es azul
Output[i][5] = Convert.ToDouble(lineas[i][9]); //1 si es cafe
Console.WriteLine("\t" + Input[i][0] + "\t" + Input[i][1] + "\t" + Input[i][2] + "\t" + Input[i][3] + "\t" + Output[i][0] + "\t" + Output[i][1] + "\t" + Output[i][2] + "\t" + Output[i][3] + "\t" + Output[i][4] + "\t" + Output[i][5] + "\t");
}
Console.ReadKey();
string ruta_red = "C:\\Users\\soyal\\Downloads\\TrainRGBC4to6.csv";
IMLDataSet trainingSet = new BasicMLDataSet(Input, Output); //Se dan entradas y salidas a la red
BasicNetwork network = EncogUtility.SimpleFeedForward(4, 200, 200, 6, false); //Diseño de red
EncogUtility.TrainToError(network, trainingSet, 0.0001); //Método de entrenamiento
double error = network.CalculateError(trainingSet);
EncogDirectoryPersistence.SaveObject(new FileInfo(ruta_red), network); //Guardar red entrenada
Console.WriteLine("Ready");
Console.ReadKey();
}
static void Main(string[] args)
{
//Datos excel
string ruta_datos = "C:\\Users\\soyal\\OneDrive - UNIVERSIDAD NACIONAL AUTÓNOMA DE MÉXICO\\Documentos\\2020-2\\InteligenciaArtificial\\Encog\\DatosEntrenamiento.csv";
StreamReader lector = new StreamReader(ruta_datos);
var lineas = new List <string[]>();
string[] Linea;
while (!lector.EndOfStream)
{
Linea = lector.ReadLine().Split(',');
lineas.Add(Linea);
}
double[][] Input = new double[lineas.Count][];
double[][] Output = new double[lineas.Count][];
for (int i = 0; i < lineas.Count; i++)
{
Input[i] = new double[2];
Output[i] = new double[1];
Input[i][0] = Convert.ToDouble(lineas[i][0]);;
Input[i][1] = Convert.ToDouble(lineas[i][1]);
Output[i][0] = Convert.ToDouble(lineas[i][2]);
Console.WriteLine("|" + Input[i][0] + "|" + Input[i][1] + "|" + Output[i][0] + "|");
}
Console.ReadKey();
string ruta_red = "C:\\Users\\soyal\\OneDrive - UNIVERSIDAD NACIONAL AUTÓNOMA DE MÉXICO\\Documentos\\2020-2\\InteligenciaArtificial\\Encog\\Train.txt";
IMLDataSet trainingSet = new BasicMLDataSet(Input, Output); //Se dan entradas y salidas a la red
BasicNetwork network = EncogUtility.SimpleFeedForward(2, 6, 0, 1, false); //Diseño de red
EncogUtility.TrainToError(network, trainingSet, 0.0001); //Método de entrenamiento
double error = network.CalculateError(trainingSet);
EncogDirectoryPersistence.SaveObject(new FileInfo(ruta_red), network); //Guardar red entrenada
Console.WriteLine("Ready");
Console.ReadKey();
}
void trainWorker_DoWork(object sender, DoWorkEventArgs e)
{
int epoch = 1;
do
{
if (trainWorker.CancellationPending == true)
{
e.Cancel = true;
return;
}
else
{
Wait(100);
train.Iteration();
var IterationResults = new KeyValuePair <int, double> [2];
IterationResults[0] = new KeyValuePair <int, double>(epoch, train.Error);;
IterationResults[1] = new KeyValuePair <int, double>(epoch, network.CalculateError(crossValidationSet));
trainWorker.ReportProgress(epoch, IterationResults);
epoch++;
}
} while (train.Error > 0.01);
}
/// <summary>
/// Calculate the error for the neural network with a given set of weights.
/// </summary>
/// <param name="weights">The weights to use.</param>
/// <returns>The current error.</returns>
public double Fn(double[] weights)
{
NetworkCODEC.ArrayToNetwork(weights, _network);
return(_network.CalculateError(Training));
}
/// <summary>
/// Calculate the score for the network.
/// </summary>
/// <param name="network">The network to calculate for.</param>
/// <returns>The score.</returns>
public double CalculateScore(BasicNetwork network)
{
return(network.CalculateError(this.training));
}
/// <summary>
/// Calculate the score for the network.
/// </summary>
/// <param name="network">The network to calculate for.</param>
/// <returns>The score.</returns>
public double CalculateScore(BasicNetwork network)
{
return network.CalculateError(this.training);
}