public CommunicationVisualizer(SharpNeatLib.CPPNs.SubstrateDescription _sd, ModularNetwork _net)
{
InitializeComponent();
//zlevel = _zlevel;
drawFont = new System.Drawing.Font("Arial", 8);
drawBrush = new System.Drawing.SolidBrush(System.Drawing.Color.Black);
drawFormat = new System.Drawing.StringFormat();
sd = _sd;
net = _net;
_net.UpdateNetworkEvent += networkUpdated;
activation = new activationLevels[200];
// outgoingActivation = new List<float>[200];
for (int i = 0; i < activation.Length; i++)
{
activation[i] = new activationLevels();
//outgoingActivation[i] = new List<float>();
}
penConnection = new Pen(Color.Black);
penRed = new Pen(Color.Red);
this.SetStyle(
ControlStyles.AllPaintingInWmPaint |
ControlStyles.UserPaint |
ControlStyles.DoubleBuffer, true);
}
public NetworkDifferencesForm(ModularNetwork _net, List <Robot> _robots)
{
InitializeComponent();
net = _net;
robots = _robots;
saveAsEPS = false;
this.Text = "Network Difference Viewer";
SetBounds(1, 1, 640, 480);
brush = new SolidBrush(Color.Red);
penConnection = new Pen(Color.Black);
panel1.Width = (int)(_robots.Count * incX) + 100;
panel1.Height = (int)(_robots.Count * incY) + 100;
}
public ModuleUsageVisualizerForm(Robot _selectedRobot, ModularNetwork _net, int _evaluationTime)
{
evaluationTime = _evaluationTime;
_net.UpdateNetworkEvent += networkUpdated;
InitializeComponent();
net = _net;
selectedRobot = _selectedRobot;
this.Text = "Module Usage Visualizer [z=" + selectedRobot.zstack + "]";
SetBounds(1, 1, 320, 90); // Schrum: Need to tweak?
//set up double buffering
this.SetStyle(
ControlStyles.AllPaintingInWmPaint |
ControlStyles.UserPaint |
ControlStyles.DoubleBuffer, true);
}
public NetworkVisualizerForm(Robot _selectedRobot, ModularNetwork _net)
{
_net.UpdateNetworkEvent += networkUpdated;
InitializeComponent();
net = _net;
selectedRobot = _selectedRobot;
this.Text = "Network Visualizer [z=" + selectedRobot.zstack + "]";
SetBounds(1, 1, 320, 320);
brush = new SolidBrush(Color.Red);
penConnection = new Pen(Color.Black);
startX = 1.1f * dtx;
startY = 1.1f * dty;
//set up double buffering
this.SetStyle(
ControlStyles.AllPaintingInWmPaint |
ControlStyles.UserPaint |
ControlStyles.DoubleBuffer, true);
}
public Rect(float fixedx, float fixedy, bool from, Rect _parent, byte recPos, float _x1, float _y1, float _x2, float _y2, INetwork genome)
{
coordinates = new float[4];
this.genome = (ModularNetwork)genome;
this.fixedx = fixedx;
this.fixedy = fixedy;
this.recPos = recPos;
this.from = from;
activationLevel = float.NaN;
visited = false;
childs = new List <Rect>();
parent = _parent;
if (parent != null)
{
parent.childs.Add(this);
}
if (_x1 < _x2)
{
x1 = _x1;
x2 = _x2;
}
else
{
x2 = _x1;
x1 = _x2;
}
if (_y1 < _y2)
{
y1 = _y1;
y2 = _y2;
}
else
{
y2 = _y1;
y1 = _y2;
}
}
//TODO not really clean
public void clearANNSignals(float zstack)
{
int index = 0;
ModularNetwork net = ((ModularNetwork)brain);
foreach (ConnectionGene gene in net.genome.ConnectionGeneList)
{
if (gene.coordinates.Length > 4 && !gene.coordinates[4].Equals(float.NaN))
{
if (gene.coordinates[4] != zstack) //Only valid if robot has z-values
{
index++;
continue;
}
}
((ModularNetwork)brain).neuronSignals[net.connections[index].targetNeuronIdx] = 0.0f;
((ModularNetwork)brain).neuronSignals[net.connections[index].sourceNeuronIdx] = 0.0f;
}
}
public TeamVisualizerForm(ModularNetwork _net, int numAgents)
{
_net.UpdateNetworkEvent += networkUpdated;
InitializeComponent();
net = _net;
this.Text = "Team";
SetBounds(1, 1, 700, 400);
brush = new SolidBrush(Color.Red);
penConnection = new Pen(Color.Black);
penConnection.StartCap = System.Drawing.Drawing2D.LineCap.Flat;
penConnection.EndCap = System.Drawing.Drawing2D.LineCap.ArrowAnchor;
startX = 700;
startY = 150;
zdelta = 1.0f / (numAgents - 1);
//set up double buffering
this.SetStyle(
ControlStyles.AllPaintingInWmPaint |
ControlStyles.UserPaint |
ControlStyles.DoubleBuffer, true);
}
// Schrum: Just added the brainCounter to the old constructor
public NetworkVisualizerForm(Robot _selectedRobot, ModularNetwork _net, int brainCounter, bool checkZ)
{
this.checkZ = checkZ; // Schrum: added
//Console.WriteLine("Draw:" + brainCounter);
_net.UpdateNetworkEvent += networkUpdated;
InitializeComponent();
net = _net;
selectedRobot = _selectedRobot;
// Schrum: Modified this to identify the brain being accessed
this.Text = "Network Visualizer [z=" + selectedRobot.zstack + (brainCounter != -1 ? ",s=" + brainCounter : "") + "]";
SetBounds(1, 1, 320, 320);
brush = new SolidBrush(Color.Red);
penConnection = new Pen(Color.Black);
startX = 1.1f * dtx;
startY = 1.1f * dty;
//set up double buffering
this.SetStyle(
ControlStyles.AllPaintingInWmPaint |
ControlStyles.UserPaint |
ControlStyles.DoubleBuffer, true);
}
/// <summary>
/// Resets ANN signals to zero. Only valid if robot has z-values.
/// </summary>
public void clearANNSignals(float ZStack)
{
if (NeatBrain)
{
return;
}
int index = 0;
ModularNetwork net = ((ModularNetwork)Brain);
foreach (ConnectionGene gene in net.genome.ConnectionGeneList)
{
if (gene.coordinates.Length > 4 && !gene.coordinates[4].Equals(float.NaN))
{
if (gene.coordinates[4] != ZStack)
{
index++;
continue;
}
}
((ModularNetwork)Brain).neuronSignals[net.connections[index].targetNeuronIdx] = 0.0f;
((ModularNetwork)Brain).neuronSignals[net.connections[index].sourceNeuronIdx] = 0.0f;
}
}
float[] queryCPPNOutputs(ModularNetwork genome, float x1, float y1, float x2, float y2, float maxXDist, float minYDist)
{
float[] coordinates = new float[genome.InputNeuronCount];
coordinates[0] = x1;
coordinates[1] = y1;
coordinates[2] = x2;
coordinates[3] = y2;
//coordinates[4] = maxXDist;
//coordinates[5] = minYDist;
//Console.WriteLine("Coordinates: ({0}, {1} : {2}, {3})", x1, y1, x2, y2);
genome.ClearSignals();
genome.SetInputSignals(coordinates);
genome.RecursiveActivation();
float[] outs = new float[genome.OutputNeuronCount];
for (int i = 0; i < genome.OutputNeuronCount; i++)
{
outs[i] = genome.GetOutputSignal(i);
}
return(outs);
}
public void networkUpdated(ModularNetwork _net)
{
//net = _net;
Refresh();
}
//This function gets called when the current simulated network sends an update event
public void networkUpdated(ModularNetwork _net)
{
Refresh();
}
static public ModularNetwork DecodeToModularNetwork(NeatGenome.NeatGenome g)
{
int inputCount = g.InputNeuronCount;
int outputCount = g.OutputNeuronCount;
int neuronCount = g.NeuronGeneList.Count;
IActivationFunction[] activationFunctions = new IActivationFunction[neuronCount];
float[] biasList = new float[neuronCount];
Dictionary <long, int> neuronLookup = new Dictionary <long, int>(neuronCount);
// Create an array of the activation functions for each non-module node node in the genome.
// Start with a bias node if there is one in the genome.
// The genome's neuron list is assumed to be ordered by type, with the bias node appearing first.
int neuronGeneIndex = 0;
for (; neuronGeneIndex < neuronCount; neuronGeneIndex++)
{
if (g.NeuronGeneList[neuronGeneIndex].NeuronType != NeuronType.Bias)
{
break;
}
activationFunctions[neuronGeneIndex] = g.NeuronGeneList[neuronGeneIndex].ActivationFunction;
neuronLookup.Add(g.NeuronGeneList[neuronGeneIndex].InnovationId, neuronGeneIndex);
}
int biasCount = neuronGeneIndex;
for (; neuronGeneIndex < neuronCount; neuronGeneIndex++)
{
activationFunctions[neuronGeneIndex] = g.NeuronGeneList[neuronGeneIndex].ActivationFunction;
neuronLookup.Add(g.NeuronGeneList[neuronGeneIndex].InnovationId, neuronGeneIndex);
biasList[neuronGeneIndex] = g.NeuronGeneList[neuronGeneIndex].Bias;
}
// Create an array of the activation functions, inputs, and outputs for each module in the genome.
ModulePacket[] modules = new ModulePacket[g.ModuleGeneList.Count];
for (int i = g.ModuleGeneList.Count - 1; i >= 0; i--)
{
modules[i].function = g.ModuleGeneList[i].Function;
// Must translate input and output IDs to array locations.
modules[i].inputLocations = new int[g.ModuleGeneList[i].InputIds.Count];
for (int j = g.ModuleGeneList[i].InputIds.Count - 1; j >= 0; j--)
{
modules[i].inputLocations[j] = neuronLookup[g.ModuleGeneList[i].InputIds[j]];
}
modules[i].outputLocations = new int[g.ModuleGeneList[i].OutputIds.Count];
for (int j = g.ModuleGeneList[i].OutputIds.Count - 1; j >= 0; j--)
{
modules[i].outputLocations[j] = neuronLookup[g.ModuleGeneList[i].OutputIds[j]];
}
}
// ConnectionGenes point to a neuron's innovation ID. Translate this ID to the neuron's index in the neuron array.
FloatFastConnection[] connections = new FloatFastConnection[g.ConnectionGeneList.Count];
for (int connectionGeneIndex = g.ConnectionGeneList.Count - 1; connectionGeneIndex >= 0; connectionGeneIndex--)
{
ConnectionGene connectionGene = g.ConnectionGeneList[connectionGeneIndex];
connections[connectionGeneIndex].sourceNeuronIdx = neuronLookup[connectionGene.SourceNeuronId];
connections[connectionGeneIndex].targetNeuronIdx = neuronLookup[connectionGene.TargetNeuronId];
connections[connectionGeneIndex].weight = (float)connectionGene.Weight;
connections[connectionGeneIndex].learningRate = connectionGene.learningRate;
connections[connectionGeneIndex].A = connectionGene.A;
connections[connectionGeneIndex].B = connectionGene.B;
connections[connectionGeneIndex].C = connectionGene.C;
connections[connectionGeneIndex].D = connectionGene.D;
connections[connectionGeneIndex].modConnection = connectionGene.modConnection;
}
ModularNetwork mn = new ModularNetwork(biasCount, inputCount, outputCount, neuronCount, connections, biasList, activationFunctions, modules);
if (g.networkAdaptable)
{
mn.adaptable = true;
}
if (g.networkModulatory)
{
mn.modulatory = true;
}
mn.genome = g;
return(mn);
}
//This function gets called when the current simulated network sends an update event
public void networkUpdated(ModularNetwork _net)
{
//Console.WriteLine("networkUpdated");
//net = _net;
Refresh();
}
// Schrum: Old constructor, without a brain counter, simply calls new one with extra argument
public NetworkVisualizerForm(Robot _selectedRobot, ModularNetwork _net) : this(_selectedRobot, _net, -1, false)
{
}
static public ModularNetwork DecodeToModularNetwork(NeatGenome.NeatGenome g)
{
int inputCount = g.InputNeuronCount;
int outputCount = g.OutputNeuronCount;
int neuronCount = g.NeuronGeneList.Count;
IActivationFunction[] activationFunctions = new IActivationFunction[neuronCount];
float[] biasList = new float[neuronCount];
Dictionary <uint, int> neuronLookup = new Dictionary <uint, int>(neuronCount);
// Schrum: In case there are output neurons out of order
g.NeuronGeneList.NeuronSortCheck();
// Create an array of the activation functions for each non-module node node in the genome.
// Start with a bias node if there is one in the genome.
// The genome's neuron list is assumed to be ordered by type, with the bias node appearing first.
int neuronGeneIndex = 0;
for (; neuronGeneIndex < neuronCount; neuronGeneIndex++)
{
if (g.NeuronGeneList[neuronGeneIndex].NeuronType != NeuronType.Bias)
{
break;
}
activationFunctions[neuronGeneIndex] = g.NeuronGeneList[neuronGeneIndex].ActivationFunction;
neuronLookup.Add(g.NeuronGeneList[neuronGeneIndex].InnovationId, neuronGeneIndex);
}
int biasCount = neuronGeneIndex;
// Schrum: debug
//Console.WriteLine("start (after bias): " + g.GenomeId);
// Schrum: Debugging
//NeuronType expectedType = NeuronType.Input;
for (; neuronGeneIndex < neuronCount; neuronGeneIndex++)
{
activationFunctions[neuronGeneIndex] = g.NeuronGeneList[neuronGeneIndex].ActivationFunction;
// Schrum: Debug
/*
* if (expectedType != g.NeuronGeneList[neuronGeneIndex].NeuronType)
* {
* if (expectedType == NeuronType.Input && g.NeuronGeneList[neuronGeneIndex].NeuronType == NeuronType.Output)
* {
* expectedType = NeuronType.Output;
* }
* else if (expectedType == NeuronType.Output && g.NeuronGeneList[neuronGeneIndex].NeuronType == NeuronType.Hidden)
* {
* expectedType = NeuronType.Hidden;
* }
* else
* {
* // Error condition:
* Console.WriteLine("Error with genome: " + g.GenomeId);
*
* XmlDocument doc = new XmlDocument();
* XmlGenomeWriterStatic.Write(doc, (SharpNeatLib.NeatGenome.NeatGenome)g);
* FileInfo oFileInfo = new FileInfo("ProblemGenome.xml");
* doc.Save(oFileInfo.FullName);
*
* Environment.Exit(1);
* }
* }
*/
neuronLookup.Add(g.NeuronGeneList[neuronGeneIndex].InnovationId, neuronGeneIndex);
biasList[neuronGeneIndex] = g.NeuronGeneList[neuronGeneIndex].Bias;
}
// Create an array of the activation functions, inputs, and outputs for each module in the genome.
ModulePacket[] modules = new ModulePacket[g.ModuleGeneList.Count];
for (int i = g.ModuleGeneList.Count - 1; i >= 0; i--)
{
modules[i].function = g.ModuleGeneList[i].Function;
// Must translate input and output IDs to array locations.
modules[i].inputLocations = new int[g.ModuleGeneList[i].InputIds.Count];
for (int j = g.ModuleGeneList[i].InputIds.Count - 1; j >= 0; j--)
{
modules[i].inputLocations[j] = neuronLookup[g.ModuleGeneList[i].InputIds[j]];
}
modules[i].outputLocations = new int[g.ModuleGeneList[i].OutputIds.Count];
for (int j = g.ModuleGeneList[i].OutputIds.Count - 1; j >= 0; j--)
{
modules[i].outputLocations[j] = neuronLookup[g.ModuleGeneList[i].OutputIds[j]];
}
}
// ConnectionGenes point to a neuron's innovation ID. Translate this ID to the neuron's index in the neuron array.
FloatFastConnection[] connections = new FloatFastConnection[g.ConnectionGeneList.Count];
for (int connectionGeneIndex = g.ConnectionGeneList.Count - 1; connectionGeneIndex >= 0; connectionGeneIndex--)
{
ConnectionGene connectionGene = g.ConnectionGeneList[connectionGeneIndex];
connections[connectionGeneIndex].sourceNeuronIdx = neuronLookup[connectionGene.SourceNeuronId];
connections[connectionGeneIndex].targetNeuronIdx = neuronLookup[connectionGene.TargetNeuronId];
connections[connectionGeneIndex].weight = (float)connectionGene.Weight;
connections[connectionGeneIndex].learningRate = connectionGene.learningRate;
connections[connectionGeneIndex].A = connectionGene.A;
connections[connectionGeneIndex].B = connectionGene.B;
connections[connectionGeneIndex].C = connectionGene.C;
connections[connectionGeneIndex].D = connectionGene.D;
connections[connectionGeneIndex].modConnection = connectionGene.modConnection;
}
ModularNetwork mn = new ModularNetwork(biasCount, inputCount, outputCount, g.OutputsPerPolicy, neuronCount, connections, biasList, activationFunctions, modules);
if (g.networkAdaptable)
{
mn.adaptable = true;
}
if (g.networkModulatory)
{
mn.modulatory = true;
}
mn.genome = g;
return(mn);
}
/*
* The main method that generations a list of ANN connections based on the information in the
* underlying hypercube.
* Input : CPPN, InputPositions, OutputPositions, ES-HyperNEAT parameters
* Output: Connections, HiddenNodes
*/
public void generateSubstrate(List <PointF> inputNeuronPositions, List <PointF> outputNeuronPositions,
INetwork genome, int initialDepth, float varianceThreshold, float bandThreshold, int ESIterations,
float divsionThreshold, int maxDepth,
uint inputCount, uint outputCount,
ref ConnectionGeneList connections, ref List <PointF> hiddenNeurons, bool useLeo = false)
{
List <TempConnection> tempConnections = new List <TempConnection>();
int sourceIndex, targetIndex = 0;
uint counter = 0;
this.genome = (ModularNetwork)genome;
this.initialDepth = initialDepth;
this.maxDepth = maxDepth;
this.varianceThreshold = varianceThreshold;
this.bandThrehold = bandThreshold;
this.divisionThreshold = divsionThreshold;
//CONNECTIONS DIRECTLY FROM INPUT NODES
sourceIndex = 0;
foreach (PointF input in inputNeuronPositions)
{
// Analyze outgoing connectivity pattern from this input
QuadPoint root = QuadTreeInitialisation(input.X, input.Y, true, (int)initialDepth, (int)maxDepth);
tempConnections.Clear();
// Traverse quadtree and add connections to list
PruneAndExpress(input.X, input.Y, ref tempConnections, root, true, maxDepth);
foreach (TempConnection p in tempConnections)
{
PointF newp = new PointF(p.x2, p.y2);
targetIndex = hiddenNeurons.IndexOf(newp);
if (targetIndex == -1)
{
targetIndex = hiddenNeurons.Count;
hiddenNeurons.Add(newp);
}
connections.Add(new ConnectionGene(counter++, (sourceIndex), (targetIndex + inputCount + outputCount), p.weight * HyperNEATParameters.weightRange, new float[] { p.x1, p.y1, p.x2, p.y2 }, p.Outputs));
}
sourceIndex++;
}
tempConnections.Clear();
List <PointF> unexploredHiddenNodes = new List <PointF>();
unexploredHiddenNodes.AddRange(hiddenNeurons);
for (int step = 0; step < ESIterations; step++)
{
foreach (PointF hiddenP in unexploredHiddenNodes)
{
tempConnections.Clear();
QuadPoint root = QuadTreeInitialisation(hiddenP.X, hiddenP.Y, true, (int)initialDepth, (int)maxDepth);
PruneAndExpress(hiddenP.X, hiddenP.Y, ref tempConnections, root, true, maxDepth);
sourceIndex = hiddenNeurons.IndexOf(hiddenP); //TODO there might a computationally less expensive way
foreach (TempConnection p in tempConnections)
{
PointF newp = new PointF(p.x2, p.y2);
targetIndex = hiddenNeurons.IndexOf(newp);
if (targetIndex == -1)
{
targetIndex = hiddenNeurons.Count;
hiddenNeurons.Add(newp);
}
connections.Add(new ConnectionGene(counter++, (sourceIndex + inputCount + outputCount), (targetIndex + inputCount + outputCount), p.weight * HyperNEATParameters.weightRange, new float[] { p.x1, p.y1, p.x2, p.y2 }, p.Outputs));
}
}
// Remove the just explored nodes
List <PointF> temp = new List <PointF>();
temp.AddRange(hiddenNeurons);
foreach (PointF f in unexploredHiddenNodes)
{
temp.Remove(f);
}
unexploredHiddenNodes = temp;
}
tempConnections.Clear();
//CONNECT TO OUTPUT
targetIndex = 0;
foreach (PointF outputPos in outputNeuronPositions)
{
// Analyze incoming connectivity pattern to this output
QuadPoint root = QuadTreeInitialisation(outputPos.X, outputPos.Y, false, (int)initialDepth, (int)maxDepth);
tempConnections.Clear();
PruneAndExpress(outputPos.X, outputPos.Y, ref tempConnections, root, false, maxDepth);
PointF target = new PointF(outputPos.X, outputPos.Y);
foreach (TempConnection t in tempConnections)
{
PointF source = new PointF(t.x1, t.y1);
sourceIndex = hiddenNeurons.IndexOf(source);
/* New nodes not created here because all the hidden nodes that are
* connected to an input/hidden node are already expressed. */
if (sourceIndex != -1) //only connect if hidden neuron already exists
{
connections.Add(new ConnectionGene(counter++, (sourceIndex + inputCount + outputCount), (targetIndex + inputCount), t.weight * HyperNEATParameters.weightRange, new float[] { t.x1, t.y1, t.x2, t.y2 }, t.Outputs));
}
}
targetIndex++;
}
}