//Constructor
/// <summary>
/// Creates an initialized instance.
/// </summary>
/// <param name="preprocessingResults">The preprocessing overview.</param>
/// <param name="regressionResults">The regression overview.</param>
public TrainingResults(NeuralPreprocessor.PreprocessingOverview preprocessingResults,
ReadoutLayer.RegressionOverview regressionResults
)
{
PreprocessingResults = preprocessingResults;
RegressionResults = regressionResults;
return;
}
/// <summary>
/// Displays information about the preprocessing progress and at the end displays important NeuralPreprocessor's statistics.
/// </summary>
/// <param name="totalNumOfInputs">Total number of inputs to be processed</param>
/// <param name="numOfProcessedInputs">Number of processed inputs</param>
/// <param name="finalPreprocessingOverview">Final overview of the preprocessing phase</param>
protected void OnPreprocessingProgressChanged(int totalNumOfInputs,
int numOfProcessedInputs,
NeuralPreprocessor.PreprocessingOverview finalPreprocessingOverview
)
{
if (finalPreprocessingOverview == null)
{
//Display progress
if (numOfProcessedInputs % 10 == 0 || numOfProcessedInputs == totalNumOfInputs || totalNumOfInputs == 1)
{
_log.Write($" Neural preprocessing and collection of State Machine predictors {totalNumOfInputs}/{numOfProcessedInputs}", true);
}
}
else
{
//Display preprocessing final information
_log.Write(string.Empty);
_log.Write(finalPreprocessingOverview.CreateReport(4));
_log.Write(string.Empty);
}
return;
}
/// <summary>
/// Performs the training of the state machine.
/// </summary>
/// <param name="trainingData">The training data bundle.</param>
/// <param name="controller">The build process controller (optional).</param>
/// <returns>The training results.</returns>
public TrainingResults Train(VectorBundle trainingData, TNRNetBuilder.BuildControllerDelegate controller = null)
{
//StateMachine reset
Reset();
VectorBundle readoutTrainingData;
NeuralPreprocessor.PreprocessingOverview preprocessingOverview = null;
if (NP == null)
{
//Neural preprocessor is bypassed
readoutTrainingData = trainingData;
}
else
{
//Neural preprocessing
readoutTrainingData = NP.InitializeAndPreprocessBundle(trainingData, out preprocessingOverview);
}
//Training of the readout layer
ReadoutLayer.RegressionOverview regressionOverview = RL.Build(readoutTrainingData, BuildPredictorsMapper(), controller, Config.RandomizerSeek);
//Return the training results
return(new TrainingResults(preprocessingOverview, regressionOverview));
}
/// <summary>
/// Performs training of the StateMachine
/// </summary>
/// <param name="vectorBundle">Training data bundle (input vectors and desired output vectors)</param>
/// <param name="regressionController">Optional regression controller.</param>
/// <returns>Output of the regression stage</returns>
public TrainingResults Train(VectorBundle vectorBundle, TrainedNetworkBuilder.RegressionControllerDelegate regressionController = null)
{
//StateMachine reset
Reset();
VectorBundle readoutInput;
NeuralPreprocessor.PreprocessingOverview preprocessingOverview = null;
if (NP == null)
{
//Neural preprocessor is bypassed
readoutInput = vectorBundle;
}
else
{
//Neural preprocessing
readoutInput = NP.InitializeAndPreprocessBundle(vectorBundle, out preprocessingOverview);
}
//Training of the readout layer
ReadoutLayer.RegressionOverview regressionOverview = RL.Build(readoutInput, BuildPredictorsMapper(), regressionController);
//Return compact results
return(new TrainingResults(preprocessingOverview, regressionOverview));
}