public ConvolutionalChromosome(GeneticProgramm gp, Random random)
{
_gp = gp;
this.random = random;
nrp = gp._nrp;
crp = gp._crp;
drp = gp._drp;
convPart = new ConvStructure(crp, random);
densePart = new DenseStructure(nrp, drp, random);
if (nrp.notRandomSpeed)
{
trainConstSpeed = nrp.trainConstSpeedRange[0];
}
else
{
trainConstSpeed = Convert.ToSingle(random.Next((int)(nrp.trainConstSpeedRange[0] * 1000), (int)(nrp.trainConstSpeedRange[1] * 1000))) / 1000;
}
optimizer = nrp.optimizers[random.Next(nrp.optimizers.Count)];
loss_function = nrp.loss_functions[random.Next(nrp.loss_functions.Count)];
}
///////////////////////////////////////////////////////
// new Process
public void UpdateAssessmentParams(ConvolutionalChromosome chromosome, GeneticProgramm gp, int epoch)
{
instance.Invoke(new Action(() => {
if (!instance.errDontClearChB.Checked)
{
instance.ErrorTB.Clear();
}
if (!instance.chrDontClearChB.Checked)
{
instance.chrOutTB.Clear();
}
}));
ConvolutionalNetwork tempNet = new ConvolutionalNetwork(chromosome, epoch, gp._nrp.networkName);
ConvolutionalNetwork.CreateNetworkScript(tempNet, chromosome.crp.convActivations, chromosome.drp.denseActivations);
ConvolutionalNetwork.CreateConvBatFile("temp_convolution.py", @"C:\keras\Directory\scripts\convolutional\genetic", gp._nrp.datasetPath,
gp._nrp._modelPath, gp._nrp._labelPath, gp._nrp._plotPath, gp._nrp.networkName, epoch, chromosome.indexNumber, 0);
CreateConvBatProcess();
chromosome.accuracy = instance.tempAccuracy;
chromosome.paramsCount = instance.tempParameters;
}
public GeneticProgramm CollectConv_NN_Params()
{
List <String> convActivations = new List <string>();
if (reluConvChb.Checked)
{
convActivations.Add("relu");
}
if (softmaxConvChb.Checked)
{
convActivations.Add("softmax");
}
if (lReluConvChb.Checked)
{
convActivations.Add("Leaky ReLU");
}
if (softsignConvChb.Checked)
{
convActivations.Add("softsign");
}
if (sigmoidConvChb.Checked)
{
convActivations.Add("sigmoid");
}
if (eluConvChb.Checked)
{
convActivations.Add("elu");
}
if (seluConvChb.Checked)
{
convActivations.Add("selu");
}
if (softplusConvChb.Checked)
{
convActivations.Add("softplus");
}
if (tanhConvChb.Checked)
{
convActivations.Add("tang");
}
if (PReLUConvChB.Checked)
{
convActivations.Add("PReLu");
}
if (TReLUConvChB.Checked)
{
convActivations.Add("TReLU");
}
List <String> denseActivations = new List <string>();
if (reluDenseChb.Checked)
{
denseActivations.Add("relu");
}
if (softmaxDenseChb.Checked)
{
denseActivations.Add("softmax");
}
if (lReluDenseChb.Checked)
{
denseActivations.Add("Leaky ReLU");
}
if (softsignDenseChb.Checked)
{
denseActivations.Add("softsign");
}
if (sigmoidDenseChb.Checked)
{
denseActivations.Add("sigmoid");
}
if (eluDenseChb.Checked)
{
denseActivations.Add("elu");
}
if (seluDenseChb.Checked)
{
denseActivations.Add("selu");
}
if (softplusDenseChb.Checked)
{
denseActivations.Add("softplus");
}
if (tanhDenseChb.Checked)
{
denseActivations.Add("tang");
}
if (PReLUDenseChB.Checked)
{
denseActivations.Add("PReLU");
}
if (ThReLUDenseChB.Checked)
{
denseActivations.Add("TReLU");
}
List <String> optimazers = new List <string>();
if (SGD_OptChB.Checked)
{
optimazers.Add("SGD");
}
List <String> lossFunctions = new List <string>();
if (categorical_crossentropyChB.Checked)
{
lossFunctions.Add("categorical_crossentropy");
}
List <int> callbacks_indexes = new List <int>();
if (modelCPChB.Checked)
{
callbacks_indexes.Add(0);
}
var nrp = new NetworkRandomParams(constSpeedChB.Checked,
new[] { float.Parse(minConstSpeedTB.Text, System.Globalization.CultureInfo.InvariantCulture),
float.Parse(maxConstSpeedTB.Text, System.Globalization.CultureInfo.InvariantCulture) },
datasetPathTB.Text, modelsPathTB.Text, labelsPathTB.Text, plotsPathTB.Text,
networkNameTB.Text, optimazers, lossFunctions, (int)learningEpochsNUD.Value, (int)batchSizeNUD.Value);
var crp = new ConvRandomParams((int)ConvLayersNumbNUD.Value,
(int)ConvFiltersNUD.Value,
convActivations.Count,
convActivations,
new[] { (int)slidingWindow1NUD.Value, (int)slidingWindow2NUD.Value },
convDropoutChB.Checked,
(int)convDropoutNUD.Value);
var drp = new DenseRandomParams((int)DenseLayersNumbNUD.Value,
(int)DenseNeuronsNUD.Value,
nrp.networkOutputNumb, // Support.GetOutputNumb(datasetPath);
denseActivations.Count,
denseActivations,
denseDropoutChB.Checked,
(int)denseDropoutNUD.Value);
var gp = new GeneticProgramm(nrp, crp, drp, (int)geneticEpochsNUD.Value, new[] { (int)copySelNUD.Value, (int)crossSelNUD.Value, (int)mutateRateNUD.Value },
(int)popolationCountNUD.Value, (int)mutateRateNUD.Value, (float)accPriorityNUD.Value, (float)memPriorityNUD.Value,
EstimatorCB.SelectedIndex, (int)instance.percentNUD.Value);
return(gp);
}
// ReSharper disable once InconsistentNaming
public static void TrainConvolutionalNN()
{
Support.pointParamsList.Clear();
Support.pointAssesList.Clear();
instance.currentTask++;
instance.Invoke(new Action((() =>
{
instance.curTaskLabel.Text = instance.currentTask.ToString();
instance.AssesGenZedGraph.Invalidate();
instance.ParamsZedGraph.Invalidate();
instance.accZG.Invalidate();
instance.currentTaskPB.Minimum = 0;
instance.currentTaskPB.Maximum = (int)instance.geneticEpochsNUD.Value + 1;
instance.currentTaskPB.Value = 0;
instance.currentTaskPB.Step = 1;
})));
string dateDirectory = Support.CreateDateTimeDirectory(@"C:\keras\Directory\reports", 0);
string timeDirectory = Support.CreateDateTimeDirectory(dateDirectory, 1);
File.Create(timeDirectory + @"\report.txt").Close();
int maxParams = 0;
GeneticProgramm gp = instance.geneticProgramms.Dequeue();
if (!instance.genDontClearChB.Checked)
{
instance.Invoke(new Action(instance.textBox9.Clear));
}
instance.population = new List <ConvolutionalChromosome>(gp._populationSize);
while (instance.population.Count != instance.population.Capacity)
{
instance.population.Add(new ConvolutionalChromosome(gp, random));
instance.population[instance.population.Count - 1].name = "Chromosome " + instance.population.Count.ToString();
instance.population[instance.population.Count - 1].indexNumber = instance.population.Count;
}
for (int i = 0; i < instance.population.Count; i++)
{
instance.tempAccuracy = instance.tempParameters = 0;
instance.WriteAdds(0, i);
instance.UpdateAssessmentParams(instance.population[i], gp, 0);
File.AppendAllText(@"C:\keras\Directory\Assessment_Statistic.txt",
instance.population[i].accuracy.ToString() + "_" + instance.population[i].paramsCount + Environment.NewLine);
if (instance.population[i].paramsCount > maxParams)
{
maxParams = instance.population[i].paramsCount;
}
Support.DrawParamsGraph(instance.ParamsZedGraph, instance.population[i].accuracy, instance.population[i].paramsCount, maxParams);
Support.DrawAccGraph(instance.accZG, 0, instance.population[0]._gp._genEpochs, instance.population[i].accuracy);
}
Support.UpdateAssesment(instance.population);
for (int z = 0; z < instance.population.Count; z++)
{
Support.DrawAssesGraph(instance.AssesGenZedGraph, 0, instance.population[z]._gp._genEpochs, instance.population[z].assessment, z);
}
instance.SortChromosome(instance.population, gp._assessmentIndex, gp._percent);
//instance.population = SortChromosome(instance.population, gp._assessmentIndex, gp._percent);
//instance.population.Sort(new ChromosomeComparer4((int)instance.percentNUD.Value));
//instance.population.Sort(new ChromosomeComparer2());
//instance.eliteChromosomes.Add(new ConvolutionalNetwork(instance.population[0]));
instance.WriteConvGeneticOutput(0);
File.WriteAllLines(timeDirectory + @"\report.txt", instance.textBox9.Lines);
instance.Invoke(new Action(instance.currentTaskPB.PerformStep));
// Evolve
for (int i = 1; i <= gp._genEpochs; i++)
{
for (int m = 1; m < instance.population.Count; m++)
{
// ReSharper disable once CompareOfFloatsByEqualityOperator
if (instance.population[m].assessment == 0)
{
string buff = instance.population[m].name;
instance.population[m] = new ConvolutionalChromosome(gp, random)
{
name = buff
};
}
else
{
if (new Random().Next() < 5)
{
string buff = instance.population[m].name;
instance.population[m] = new ConvolutionalChromosome(gp, random)
{
name = buff
};
}
else
{
instance.population[m].MutateConvolutional(gp._crp, gp._mutateRate);
instance.population[m].MutateDense(gp._drp, gp._mutateRate);
}
}
}
for (int n = 1; n < instance.population.Count; n++)
{
instance.population[n].assessment = instance.population[n].accuracy = instance.population[n].paramsCount = 0;
instance.tempAccuracy = instance.tempParameters = 0;
instance.WriteAdds(i, n);
instance.UpdateAssessmentParams(instance.population[n], gp, i);
File.AppendAllText(@"C:\keras\Directory\Assessment_Statistic.txt",
instance.population[n].accuracy.ToString() + "_" + instance.population[n].paramsCount + Environment.NewLine);
if (instance.population[n].paramsCount > maxParams)
{
maxParams = instance.population[n].paramsCount;
}
Support.DrawParamsGraph(instance.ParamsZedGraph, instance.population[n].accuracy, instance.population[n].paramsCount, maxParams);
}
Support.UpdateAssesment(instance.population);
for (int z = 0; z < instance.population.Count; z++)
{
Support.DrawAssesGraph(instance.AssesGenZedGraph, i, instance.population[z]._gp._genEpochs, instance.population[z].assessment, z);
}
instance.SortChromosome(instance.population, gp._assessmentIndex, gp._percent);
//instance.population.Sort(new ChromosomeComparer4((int)instance.percentNUD.Value));
//population.Sort(new ChromosomeComparer((float)memPriorityNUD.Value, (float)accPriorityNUD.Value));
//instance.population.Sort(new ChromosomeComparer2());
//instance.eliteChromosomes.Add(new ConvolutionalNetwork(instance.population[0]));
instance.WriteConvGeneticOutput(i);
File.WriteAllLines(timeDirectory + @"\report.txt", instance.textBox9.Lines);
instance.Invoke(new Action(instance.currentTaskPB.PerformStep));
}
Image image = new Bitmap(instance.AssesGenZedGraph.GetImage());
image.Save(timeDirectory + @"\asses.png");
image = new Bitmap(instance.ParamsZedGraph.GetImage());
image.Save(timeDirectory + @"\params.png");
image = new Bitmap(instance.accZG.GetImage());
image.Save(timeDirectory + @"\acc.png");
}