public void BatchBackPropogate(DataSet[] dataSet, int iterations, double leanrnignRate, double momentum = 0, BackgroundWorker worker = null)
{
int y =0;
for (int i = 0; i < iterations; i++)
{
foreach (DataSet data in dataSet)
{
BackPropogate(data, leanrnignRate, momentum);
y++;
if (worker != null)
{
worker.ReportProgress((int)(((double)y / (double)(iterations * dataSet.Count())) *100));
}
}
}
}
public List<List<List<double>>> BackPropogate(DataSet datain, double learninnRate, double momentum = 0)
{
if (PrevDW == null)
{
PrevDW = new List<List<List<double>>>();
deltaArr = new List<List<double>>();
for (int i = 0; i < NumLayers; i++)
{
deltaArr.Add(new List<double>());
PrevDW.Add(new List<List<double>>());
for (int n = 0; n < Layers[i].NumNeurons; n++)
{
deltaArr[i].Add(0);
PrevDW[i].Add(new List<double>());
IEnumerable<Connection> outConn = Layers[i].Neurons[n].Connections.Where(r => r.toNeuron == Layers[i].Neurons[n]);
int d = 0;
foreach (Connection c in outConn)
{
PrevDW[i][n].Add(0);
d++;
}
}
}
}
ApplyInput(datain.Inputs);
CalculateOutput();
Layer currentLayer = Layers[OutputIndex];
while (currentLayer != Layers[InputIndex])
{
Parallel.ForEach(currentLayer.Neurons, new Action<Neuron>((n) =>
{
double error = 0;
if (currentLayer == Layers[OutputIndex])
{
error = datain.Outputs[n.Index] - n.Value;
}
else
{
foreach (Connection c in n.Connections.Where(r => r.fromNeuron == n))
{
error += c.Weight * deltaArr[c.toNeuron.SelfLayer.Index][c.toNeuron.Index];
}
}
error = error * n.Value * (1 - n.Value);
deltaArr[currentLayer.Index][n.Index] = error;
}));
currentLayer = Layers[currentLayer.Index - 1];
}
currentLayer = Layers[OutputIndex];
while (currentLayer != Layers[InputIndex])
{
for (int i = 0; i < currentLayer.NumNeurons; i++)
{
Neuron n = currentLayer.Neurons[i];
foreach (Connection c in n.Connections.Where(r => r.toNeuron == n))
{
double dw = (deltaArr[c.toNeuron.SelfLayer.Index][c.toNeuron.Index] * learninnRate * c.fromNeuron.Value) + (momentum * PrevDW[currentLayer.Index][i][n.Connections.IndexOf(c)]);
c.Weight += dw;
PrevDW[currentLayer.Index][i][n.Connections.IndexOf(c)] = dw;
}
n.Bias += deltaArr[currentLayer.Index][i] * learninnRate;
}
currentLayer = Layers[currentLayer.Index - 1];
}
return PrevDW;
}
public void think()
{
ClosestFriend = get_friends_informaion();
ClosestFoe = get_foe_informaion();
Enviroment = get_evironment_information();
ClosestFriend2 = sort_distance(ClosestFriend);
#if DebugA
GD.Print("Network input Objects");
GD.Print(ClosestFriend);
GD.Print(ClosestFoe);
GD.Print(Enviroment);
GD.Print(ClosestFriend2);
GD.Print(ClosestFoe[0].Position);
GD.Print(ClosestFoe[0].Position.x);
GD.Print(ClosestFoe[0].Position.y);
#endif
#if DebugB
GD.Print("+++ClosestFrient+++");
GD.Print(ClosestFriend);
GD.Print("---ClosestFrient2---");
GD.Print(ClosestFriend2);
#endif
data_in[0] = ClosestFoe[0].Position.x;
data_in[1] = ClosestFoe[0].Position.y;
data_in[2] = ClosestFoe[1].Position.x;
data_in[3] = ClosestFoe[1].Position.y;
data_in[4] = ClosestFoe[2].Position.x;
data_in[5] = ClosestFoe[2].Position.y;
data_in[6] = ClosestFriend[0].Position.x;
data_in[7] = ClosestFriend[0].Position.y;
data_in[8] = ClosestFriend[1].Position.x;
data_in[9] = ClosestFriend[1].Position.y;
//data_in[10] = ClosestFriend[2].Position.x;
//data_in[11] = ClosestFriend[2].Position.y;
data_in[12] = Enviroment[0].Position.x;
data_in[13] = Enviroment[0].Position.y;
data_in[14] = Enviroment[1].Position.x;
data_in[15] = Enviroment[1].Position.y;
data_in[16] = Enviroment[2].Position.x;
data_in[17] = Enviroment[2].Position.y;
FirstData.Inputs[0] = ClosestFoe[0].Position.x;
#if (DebugA)
MyString = "";
foreach (double Anumber in data_in)
{
MyString += Anumber.ToString() + ",";
}
GD.Print("Objects Position Data");
GD.Print(MyString);
#endif
normalize(data_in);
MoveShootNet.ApplyInput(data_in);
MoveShootNet.CalculateOutput();
data_out2 = MoveShootNet.ReadOutput();
data_out2 = denormalize(data_out2);
data_out = new double[] { data_in[0], data_in[1], data_in[0], data_in[1] };
//normalize(data_out);
Training = new NeuralNetworks.DataSet {
Outputs = data_out, Inputs = data_in
};
//Training = new NeuralNetworks.DataSet() {(double[]) data_out2, Inputs = data_in };
TrainingData.Add(Training);
#if DebugA
MyString = "";
foreach (double Anumber in data_out2)
{
MyString += Anumber.ToString() + ",";
}
GD.Print("Output of Network");
GD.Print(MyString);
//data_out = (double[]) data_out2;
GD.Print("Has Current Move ", Parent.Get("CurrentMove"));
GD.Print("Has Side ", Parent.Get("Side"));
#endif
Acount = 0;
foreach (double Anumber in data_out2)
{
data_out3[Acount] = (float)Anumber;
Acount++;
}
Parent.Set("CurrentMove", Parent.ToLocal(new Godot.Vector2(data_out3[2], data_out3[3])));
Parent.Set("CurrentTarget", new Godot.Vector2(data_out3[0], data_out3[1]));
}