private void DoWork(object sender, DoWorkEventArgs e)
{
BackgroundWorker worker = sender as BackgroundWorker;
e.Result = new double[0];
if (worker.CancellationPending)
{
e.Cancel = true;
return;
}
TrainingDialog obj = (TrainingDialog)e.Argument;
_Series++;
#region Prepare data to be trained. Involves copying.
int numTrainingSets = obj._DataSet.Training.Rows.Count;
ArrayList inputs = new ArrayList();
ArrayList outputs = new ArrayList();
for (int i = 0; i < numTrainingSets; i++)
{
// Input data
double[] inData = new double[_NumInputNeurons];
inData[0] = obj._DataSet.Training[i].LipCornerLeftX;
inData[1] = obj._DataSet.Training[i].LipCornerLeftY;
inData[2] = obj._DataSet.Training[i].LipCornerRightX;
inData[3] = obj._DataSet.Training[i].LipCornerRightY;
inData[4] = obj._DataSet.Training[i].LipUpLeftX;
inData[5] = obj._DataSet.Training[i].LipUpLeftY;
inData[6] = obj._DataSet.Training[i].LipUpCenterX;
inData[7] = obj._DataSet.Training[i].LipUpCenterY;
inData[8] = obj._DataSet.Training[i].LipUpRightX;
inData[9] = obj._DataSet.Training[i].LipUpRightY;
inData[10] = obj._DataSet.Training[i].LipBottomLeftX;
inData[11] = obj._DataSet.Training[i].LipBottomLeftY;
inData[12] = obj._DataSet.Training[i].LipBottomCenterX;
inData[13] = obj._DataSet.Training[i].LipBottomCenterY;
inData[14] = obj._DataSet.Training[i].LipBottomRightX;
inData[15] = obj._DataSet.Training[i].LipBottomRightY;
inData[16] = obj._DataSet.Training[i].LeftEyeCenterX;
inData[17] = obj._DataSet.Training[i].LeftEyeCenterY;
inData[18] = obj._DataSet.Training[i].LeftLidBottomX;
inData[19] = obj._DataSet.Training[i].LeftLidBottomY;
inData[20] = obj._DataSet.Training[i].LeftLidCornerLeftX;
inData[21] = obj._DataSet.Training[i].LeftLidCornerLeftY;
inData[22] = obj._DataSet.Training[i].LeftLidCornerRightX;
inData[23] = obj._DataSet.Training[i].LeftLidCornerRightY;
inData[24] = obj._DataSet.Training[i].LeftLidUpX;
inData[25] = obj._DataSet.Training[i].LeftLidUpY;
inData[26] = obj._DataSet.Training[i].MouthCenterX;
inData[27] = obj._DataSet.Training[i].MouthCenterY;
inData[28] = obj._DataSet.Training[i].RightEyeCenterX;
inData[29] = obj._DataSet.Training[i].RightEyeCenterY;
inData[30] = obj._DataSet.Training[i].RightLidBottomX;
inData[31] = obj._DataSet.Training[i].RightLidBottomY;
inData[32] = obj._DataSet.Training[i].RightLidCornerLeftX;
inData[33] = obj._DataSet.Training[i].RightLidCornerLeftY;
inData[34] = obj._DataSet.Training[i].RightLidCornerRightX;
inData[35] = obj._DataSet.Training[i].RightLidCornerRightY;
inData[36] = obj._DataSet.Training[i].RightLidUpX;
inData[37] = obj._DataSet.Training[i].RightLidUpY;
inputs.Add(inData);
// Output data
double[] outData = new double[_NumOutputNeurons];
int eid = obj._DataSet.Training[i].ExpressionOID;
string expression = obj._DataSet.Expression.FindByExpressionOID(eid).Expression.ToLower();
outData[0] = expression.Contains("anger") ? 1 : 0;
outData[1] = expression.Contains("disg") ? 1 : 0;
outData[2] = expression.Contains("fear") ? 1 : 0;
outData[3] = expression.Contains("happy") ? 1 : 0;
outData[4] = expression.Contains("neutr") ? 1 : 0;
outData[5] = expression.Contains("sad") ? 1 : 0;
outData[6] = expression.Contains("surp") ? 1 : 0;
outputs.Add(outData);
}
#endregion
#region Norm datasets per input neuron
for (int j = 0; j < _NumInputNeurons; j++)
{
double min = 100000000.0;
double max = -100000000.0;
for (int i = 0; i < numTrainingSets; i++)
{
double cur = ((double[])inputs[i])[j];
if (min > cur)
{
min = cur;
}
if (max < cur)
{
max = cur;
}
}
for (int i = 0; (max - min) != 0 && i < numTrainingSets; i++)
{
((double[])inputs[i])[j] = (((double[])inputs[i])[j] - min) / (max - min);
}
}
#endregion
#region Pick random train-, validate and test datasets
// Like Mr. Schneider ;)
int numTestDataSets = (int)Math.Floor((double)numTrainingSets * 0.1);
int numValidationDataSets = (int)Math.Floor((double)(numTrainingSets - numTestDataSets) * 0.2);
int numTrainDataSets = numTrainingSets - numTestDataSets - numValidationDataSets;
Random rand = new Random();
// Get random training data
double[][] trainingInputs = new double[numTrainDataSets][];
double[][] trainingOutputs = new double[numTrainDataSets][];
for (int i = 0; i < trainingInputs.GetLength(0); i++)
{
int idx = rand.Next(inputs.Count);
trainingInputs[i] = (double[])inputs[idx];
trainingOutputs[i] = (double[])outputs[idx];
inputs.Remove(idx);
outputs.Remove(idx);
}
// Get random validation data
double[][] validateInputs = new double[numValidationDataSets][];
double[][] validateOutputs = new double[numValidationDataSets][];
for (int i = 0; i < validateInputs.GetLength(0); i++)
{
int idx = rand.Next(numTrainDataSets);
validateInputs[i] = trainingInputs[idx];
validateOutputs[i] = trainingOutputs[idx];
}
// Get random test data
double[][] testInputs = new double[numTestDataSets][];
double[][] testOutputs = new double[numTestDataSets][];
for (int i = 0; i < testInputs.GetLength(0); i++)
{
int idx = rand.Next(inputs.Count);
testInputs[i] = (double[])inputs[idx];
testOutputs[i] = (double[])outputs[idx];
inputs.Remove(idx);
outputs.Remove(idx);
}
#endregion
#region
_Network.SetActivationFunction(new SigmoidFunction(_SigmoidAlpha));
BackPropagationLearning teacher = new BackPropagationLearning(_Network);
teacher.LearningRate = obj._LearningRate;
teacher.Momentum = obj._Momentum;
double error = 1;
double maxError = -10000.0;
int maxIterations = obj._MaxIterations;
double epsilon = obj._Epsilon;
// Prepare the error Chart
double[,] errorValues = new double[maxIterations, 2];
ProgressState state = new ProgressState();
double[] errors = new double[maxIterations];
for (int i = 0; i < maxIterations || error <= epsilon; i++)
{
if (maxIterations > 0)
{
if (i >= maxIterations)
{
break;
}
}
if (epsilon > 0.0)
{
if (error <= epsilon)
{
break;
}
}
// Abort if use requested it
if (worker.CancellationPending)
{
e.Cancel = true;
break;
}
// Train
error = teacher.RunEpoch(trainingInputs, trainingOutputs);
// Store error for result
errors[i] = error;
state.Error = error;
// Plot size
if (maxError < error)
{
maxError = error;
}
// Plot values
errorValues[i, 0] = i;
errorValues[i, 1] = error;
// Report progress
if (i % 10 == 0 || i == (maxIterations - 1))
{
state.Iteration = i + 1;
state.Error = error;
worker.ReportProgress((int)((float)(100 * (i + 1)) / (float)maxIterations), state);
}
}
e.Result = errors;
obj._Chart.RangeX = new DoubleRange(0.0, (double)maxIterations);
obj._Chart.RangeY = new DoubleRange(0.0, maxError);
// add new data series to the chart
obj._Chart.AddDataSeries("Error " + _Series, System.Drawing.Color.DarkGreen, Chart.SeriesType.ConnectedDots, 2);
// update the chart
obj._Chart.UpdateDataSeries("Error " + _Series, errorValues);
#endregion
}
/// <summary>
/// Callback which starts the training process.
/// </summary>
/// <param name="sender"></param>
/// <param name="e"></param>
private void TrainingStart_Executed(object sender, ExecutedRoutedEventArgs e)
{
TrainingDialog dlg = new TrainingDialog(ref _DataSet);
dlg.Owner = this;
dlg.ShowDialog();
return;
// OOOOOLLLLD!!!!
//Microsoft.Win32.OpenFileDialog dlg = new Microsoft.Win32.OpenFileDialog();
//dlg.DefaultExt = "."; // Default file extension
//dlg.Filter = "Neural network (*.xml)|*.xml|All files (*.*)|*.*"; // Filter files by extension
//dlg.Title = "Select the neural network you want to train?";
//dlg.Multiselect = false;
//// Show save file dialog box
//Nullable<bool> result = dlg.ShowDialog();
//if (result == true)
//{
// bool res = _KLU.LoadANN(dlg.FileName);
// Console.WriteLine("Load ANN success? " + res );
// if ( !res )
// {
// return;
// }
// statusText.Text = "ANN loaded: " + dlg.FileName;
// TerminationCriteria terminationCriteria = new TerminationCriteria();
// terminationCriteria.TerminationType = Convert.ToInt32(TrainingTermination.MaxIterationTermination);
// terminationCriteria.MaxIteration = 2000; // TODO: (Ko) after checking the saved ANN file I think, there is an error with this number
// TrainOptions options = new TrainOptions();
// options.Algorithm = TrainingAlgorithm.BackpropAlgorithm;
// options.Termination = terminationCriteria;
// statusText.Text = "Now training...";
// // Enable infinite progess indicator
// statusProgess.IsEnabled = true;
// statusProgess.Visibility = Visibility.Visible;
// #region Prepare data to be trained. Involves copying.
// int numTrainingSets = _DataSet.Training.Rows.Count;
// int numInputNeurons = 16;
// int numOutputNeurons = 1;
// float[] inputs = new float[numTrainingSets * numInputNeurons];
// float[] outputs = new float[numTrainingSets * numOutputNeurons];
// for (int i = 0; i < numTrainingSets; i++)
// {
// inputs[i * numInputNeurons + 0] = _DataSet.Training[i].LipCornerLeftX;
// inputs[i * numInputNeurons + 1] = _DataSet.Training[i].LipCornerLeftY;
// inputs[i * numInputNeurons + 2] = _DataSet.Training[i].LipCornerRightX;
// inputs[i * numInputNeurons + 3] = _DataSet.Training[i].LipCornerRightY;
// inputs[i * numInputNeurons + 4] = _DataSet.Training[i].LipUpLeftX;
// inputs[i * numInputNeurons + 5] = _DataSet.Training[i].LipUpLeftY;
// inputs[i * numInputNeurons + 6] = _DataSet.Training[i].LipUpCenterX;
// inputs[i * numInputNeurons + 7] = _DataSet.Training[i].LipUpCenterY;
// inputs[i * numInputNeurons + 8] = _DataSet.Training[i].LipUpRightX;
// inputs[i * numInputNeurons + 9] = _DataSet.Training[i].LipUpRightY;
// inputs[i * numInputNeurons + 10] = _DataSet.Training[i].LipBottomLeftX;
// inputs[i * numInputNeurons + 11] = _DataSet.Training[i].LipBottomLeftY;
// inputs[i * numInputNeurons + 12] = _DataSet.Training[i].LipBottomCenterX;
// inputs[i * numInputNeurons + 13] = _DataSet.Training[i].LipBottomCenterY;
// inputs[i * numInputNeurons + 14] = _DataSet.Training[i].LipBottomRightX;
// inputs[i * numInputNeurons + 15] = _DataSet.Training[i].LipBottomRightY;
// outputs[i] = _DataSet.Training[i].ExpressionOID;
// }
// #endregion
// _KLU.SaveANN(dlg.FileName + ".untrained.xml");
// int iters = -10;
// res = _KLU.TrainAnn(options, numTrainingSets, inputs, outputs, ref iters);
// Console.WriteLine("Training success? " + res);
// // Disable infinite progess indicator
// statusProgess.IsEnabled = false;
// statusProgess.Visibility = Visibility.Hidden;
// statusText.Text = "Training result: " + res;
// _KLU.SaveANN(dlg.FileName + ".trained.xml");
// // Let's see if the ANN is trained. (simple for now)
// // TODO: (Ko) Do 7 out of 10 validation etc.
// // Test the first dataset and compare the predicted output with the expected
// float[] results = new float[1];
// _KLU.PredictANN(inputs, 16, results, 1);
// Console.WriteLine("Expected output: " + _DataSet.Training[0].ExpressionOID + " Predicted output: " + results[0]);
//}
}
/// <summary>
/// Callback which starts the training process.
/// </summary>
/// <param name="sender"></param>
/// <param name="e"></param>
private void TrainingStart_Executed(object sender, ExecutedRoutedEventArgs e)
{
TrainingDialog dlg = new TrainingDialog(ref _DataSet);
dlg.Owner = this;
dlg.ShowDialog();
return;
// OOOOOLLLLD!!!!
//Microsoft.Win32.OpenFileDialog dlg = new Microsoft.Win32.OpenFileDialog();
//dlg.DefaultExt = "."; // Default file extension
//dlg.Filter = "Neural network (*.xml)|*.xml|All files (*.*)|*.*"; // Filter files by extension
//dlg.Title = "Select the neural network you want to train?";
//dlg.Multiselect = false;
//// Show save file dialog box
//Nullable<bool> result = dlg.ShowDialog();
//if (result == true)
//{
// bool res = _KLU.LoadANN(dlg.FileName);
// Console.WriteLine("Load ANN success? " + res );
// if ( !res )
// {
// return;
// }
// statusText.Text = "ANN loaded: " + dlg.FileName;
// TerminationCriteria terminationCriteria = new TerminationCriteria();
// terminationCriteria.TerminationType = Convert.ToInt32(TrainingTermination.MaxIterationTermination);
// terminationCriteria.MaxIteration = 2000; // TODO: (Ko) after checking the saved ANN file I think, there is an error with this number
// TrainOptions options = new TrainOptions();
// options.Algorithm = TrainingAlgorithm.BackpropAlgorithm;
// options.Termination = terminationCriteria;
// statusText.Text = "Now training...";
// // Enable infinite progess indicator
// statusProgess.IsEnabled = true;
// statusProgess.Visibility = Visibility.Visible;
// #region Prepare data to be trained. Involves copying.
// int numTrainingSets = _DataSet.Training.Rows.Count;
// int numInputNeurons = 16;
// int numOutputNeurons = 1;
// float[] inputs = new float[numTrainingSets * numInputNeurons];
// float[] outputs = new float[numTrainingSets * numOutputNeurons];
// for (int i = 0; i < numTrainingSets; i++)
// {
// inputs[i * numInputNeurons + 0] = _DataSet.Training[i].LipCornerLeftX;
// inputs[i * numInputNeurons + 1] = _DataSet.Training[i].LipCornerLeftY;
// inputs[i * numInputNeurons + 2] = _DataSet.Training[i].LipCornerRightX;
// inputs[i * numInputNeurons + 3] = _DataSet.Training[i].LipCornerRightY;
// inputs[i * numInputNeurons + 4] = _DataSet.Training[i].LipUpLeftX;
// inputs[i * numInputNeurons + 5] = _DataSet.Training[i].LipUpLeftY;
// inputs[i * numInputNeurons + 6] = _DataSet.Training[i].LipUpCenterX;
// inputs[i * numInputNeurons + 7] = _DataSet.Training[i].LipUpCenterY;
// inputs[i * numInputNeurons + 8] = _DataSet.Training[i].LipUpRightX;
// inputs[i * numInputNeurons + 9] = _DataSet.Training[i].LipUpRightY;
// inputs[i * numInputNeurons + 10] = _DataSet.Training[i].LipBottomLeftX;
// inputs[i * numInputNeurons + 11] = _DataSet.Training[i].LipBottomLeftY;
// inputs[i * numInputNeurons + 12] = _DataSet.Training[i].LipBottomCenterX;
// inputs[i * numInputNeurons + 13] = _DataSet.Training[i].LipBottomCenterY;
// inputs[i * numInputNeurons + 14] = _DataSet.Training[i].LipBottomRightX;
// inputs[i * numInputNeurons + 15] = _DataSet.Training[i].LipBottomRightY;
// outputs[i] = _DataSet.Training[i].ExpressionOID;
// }
// #endregion
// _KLU.SaveANN(dlg.FileName + ".untrained.xml");
// int iters = -10;
// res = _KLU.TrainAnn(options, numTrainingSets, inputs, outputs, ref iters);
// Console.WriteLine("Training success? " + res);
// // Disable infinite progess indicator
// statusProgess.IsEnabled = false;
// statusProgess.Visibility = Visibility.Hidden;
// statusText.Text = "Training result: " + res;
// _KLU.SaveANN(dlg.FileName + ".trained.xml");
// // Let's see if the ANN is trained. (simple for now)
// // TODO: (Ko) Do 7 out of 10 validation etc.
// // Test the first dataset and compare the predicted output with the expected
// float[] results = new float[1];
// _KLU.PredictANN(inputs, 16, results, 1);
// Console.WriteLine("Expected output: " + _DataSet.Training[0].ExpressionOID + " Predicted output: " + results[0]);
//}
}