private void Conv()
{
Random random = new Random();
Vector dat = GetSigXY(random).Item1;
Vector nnwOut = networkMeneger.Forward(dat);
GraphCPU graph = new GraphCPU(false);
// Нейросеть для формирования эмбедингов
NNW net = new NNW();
net.Layers.Add(nnw.Layers[0]);
net.Layers.Add(nnw.Layers[1]);
net.Layers.Add(nnw.Layers[2]);
net.Layers.Add(nnw.Layers[3]);
net.Layers.Add(nnw.Layers[4]);
net.Layers.Add(nnw.Layers[5]);
net.Layers.Add(nnw.Layers[6]);
net.Layers.Add(nnw.Layers[7]);
Vector hl = net.Activate(new NNValue(dat), graph).ToVector();
sigChart.PlotBlack(t, dat);
hChart.BarBlack(hl);
outChart.PlotBlack(t, nnwOut);
}
// Линейный энкодер
private void creatLin_Click(object sender, EventArgs e)
{
lin = true;
nnw = new NNW();
nnw.AddNewLayer(new Shape(n), new FeedForwardLayer(h));
nnw.AddNewLayer(new FeedForwardLayer(n));
CreateMeneger();
}
public Agent(NNW model, int degreesOfFreedom, Random random)
{
lifes = new List <Life>();
graphForward = new GraphCPU(false);
graphBackward = new GraphCPU(true);
this.degreesOfFreedom = degreesOfFreedom;
this.model = model;
this.random = random;
}
public ComplexNet()
{
InitializeComponent();
t = new Vector(n);
double dt = 1.0 / n;
for (int i = 1; i < n; i++)
{
t[i] = t[i - 1] + dt;
}
NNW.AddNewLayer(new Shape(n), new ComplexFeedForwardLayer(20, new CSigmoidUnit()));
NNW.AddNewLayer(new ComplexFeedForwardLayer(outp, new CLinearUnit()));
}
/// <summary>
/// Конструктор
/// </summary>
/// <param name="model">Модель нейронной сети</param>
/// <param name="degreesOfFreedom">Количество возможных действий</param>
/// <param name="random">Генератор рандома</param>
public MLAgent(NNW model, int degreesOfFreedom, Random random, IOptimizer optimizer = null)
{
Generations = new List <Generation>();
graphForward = new GraphCPU(false);
graphBackward = new GraphCPU(true);
this.degreesOfFreedom = degreesOfFreedom;
this.model = model;
this.random = random;
if (optimizer == null)
{
optimizer = new Adam();
}
this.optimizer = optimizer;
trainer = new Trainer(graphBackward, TrainType.Online, optimizer);
}
public ImitComplex()
{
InitializeComponent();
t = new Vector(n);
double dt = 1.0 / n;
for (int i = 1; i < n; i++)
{
t[i] = t[i - 1] + dt;
}
NNW.AddNewLayer(new Shape(n), new FeedForwardLayer(100, new ReLU(0.1)));
NNW.AddNewLayer(new ReShape(new Shape(10, 1, 2))); // Разделение на реальную и мнимую часть
NNW.AddNewLayer(new BatchReNormalization());
NNW.AddNewLayer(new FeedComplexLayer(1000, new EliotSigUnit())); // Комплексный слой
NNW.AddNewLayer(new DropOut(0.85));
NNW.AddNewLayer(new Flatten()); // Соединение реальной и мнимой части
NNW.AddNewLayer(new FeedForwardLayer(outp, new SigmoidWithBCE()));
Console.WriteLine(NNW);
}
//Сверточный энкодер
private void creatConv_Click(object sender, EventArgs e)
{
lin = false;
nnw = new NNW();
nnw.AddNewLayer(new Shape(n), new Conv1D(3, 8, new ReLU(0.1)));
nnw.AddNewLayer(new MaxPool1D());
nnw.AddNewLayer(new Conv1D(3, 16, new ReLU(0.1)));
nnw.AddNewLayer(new MaxPool1D());
nnw.AddNewLayer(new Conv1D(3, 16, new ReLU(0.1)));
nnw.AddNewLayer(new MaxPool1D());
nnw.AddNewLayer(new Flatten());
nnw.AddNewLayer(new FeedForwardLayer(h));
nnw.AddNewLayer(new FeedForwardLayer(64, new ReLU(0.1)));
nnw.AddNewLayer(new UpSampling1D());
nnw.AddNewLayer(new Conv1D(3, 32, new ReLU(0.1))
{
IsSame = true
});
nnw.AddNewLayer(new UpSampling1D());
nnw.AddNewLayer(new Conv1D(3, 16, new ReLU(0.1))
{
IsSame = true
});
nnw.AddNewLayer(new UpSampling1D());
nnw.AddNewLayer(new Conv1D(3, 1, new LinearUnit())
{
IsSame = true
});
CreateMeneger();
}
/// <summary>
/// Загрузить модель обученной нейронной сети
/// </summary>
/// <param name="path">путь до модели</param>
public void LoadModel(string path)
{
model = NNW.Load(path);
}
