private static void LastTrain(DataSet testDS, INeuralTrainerParams passedParams, IOptimizer trainer, string prefix, int seed)
{
string path = prefix + passedParams.NumberOfHiddenUnits + "_lr" + passedParams.learningRate + "_reg" + passedParams.regularizationRate;
//building the architecture
Network n = new Network(new List <Layer>()
{
new Layer(new ActivationIdentity(), true, 10),
new Layer(new ActivationTanh(), true, passedParams.NumberOfHiddenUnits),
// new Layer(new ActivationLeakyRelu(),true,40),
new Layer(new ActivationIdentity(), false, 2),
}, false, AA1_MLP.Enums.WeightsInitialization.Xavier, seed);
passedParams.network = n;
var watch = System.Diagnostics.Stopwatch.StartNew();
List <double[]> learningCurve = trainer.Train(passedParams);
watch.Stop();
var elapsedMs = watch.ElapsedMilliseconds;
Console.WriteLine("elapsed Time:{0} ms", elapsedMs);
double MEE = 0;
double MSE = 0;
var log = ModelManager.TesterCUPRegression(testDS, n, out MEE, out MSE);
File.WriteAllText(path + ".txt", string.Join("\n", learningCurve.Select(s => string.Join(",", s))));
File.AppendAllText(path + ".txt", "\nMEE:" + MEE + "MSE:" + MSE);
File.WriteAllText(path + "predVsActual.txt", string.Join("\n", log.Select(s => string.Join(",", s))));
ModelManager.SaveNetowrk(n, path + ".n");
}
public List <double[]> RunExperiment(IOptimizer optimizer, INeuralTrainerParams passedParams, out double MEE, out double MSE)
{
//building the architecture
Network n = new Network(new List <Layer>()
{
new Layer(new ActivationIdentity(), true, 10),
new Layer(new ActivationTanh(), true, passedParams.NumberOfHiddenUnits),
// new Layer(new ActivationLeakyRelu(),true,40),
new Layer(new ActivationIdentity(), false, 2),
}, false, AA1_MLP.Enums.WeightsInitialization.Xavier);
passedParams.network = n;
List <double[]> learningCurve = optimizer.Train(passedParams);
MEE = 0;
MSE = 0;
var log = ModelManager.TesterCUPRegression(passedParams.validationSet, n, out MEE, out MSE);
return(learningCurve);
}
internal void Train(Predictor predictor, double[] weightArray, DataSetObject dataSet)
{
_optimizer.Train(predictor, weightArray, dataSet, _learningRate);
}