public static Image <Rgba32> GenerateImage(List <List <Node> > network, Dictionary <string, bool> state, int size)
{
var img2 = new Image <Rgba32>(size, size);
for (int x = 0; x < size; x++)
{
for (int y = 0; y < size; y++)
{
double outx = x / (double)size * 2.0 - 1.0;
double outy = y / (double)size * 2.0 - 1.0;
var input = MLHelper.ConstructInput(state, outx, outy);
var lastNode = NetworkBuilder.ForwardProp(network, input);
//byte r = (byte)(255 * (1 - lastNode));
//byte g = 0;
//byte b = 0;
//=MAX((1-((A2+1)/2) / 2 * 3) *255; 0)
byte r = (byte)Math.Max((1 - ((lastNode + 1) / 2.0) / 2.0 * 3.0) * 255.0, 0);
//=MAX((1-((A2+1)/2) / 2 * 6) *128; 0)
byte g = (byte)Math.Max((1 - ((lastNode + 1) / 2.0) / 2.0 * 6.0) * 128.0, 0);
//=MIN(MAX((((A2+1 - 0,6666)/2 / 2 *3) ) *255; 0); 255)
byte b = (byte)Math.Min(Math.Max((((lastNode + 1 - (2.0 / 3.0)) / 2.0 / 2.0 * 3.0)) * 255.0, 0), 255);
img2[x, y] = new Rgba32(r, g, b);
//var pntX = ((pnt.X + 1.0) / 2.0) * size;
//var pntY = ((pnt.Y + 1.0) / 2.0) * size;
}
}
return(img2);
}
public static double GetLoss(List <List <Node> > network, Dictionary <string, bool> state, List <Puntje> dataPoints)
{
double loss = 0;
for (var i = 0; i < dataPoints.Count; i++)
{
var dataPoint = dataPoints[i];
var input = MLHelper.ConstructInput(state, dataPoint.X, dataPoint.Y);
var output = NetworkBuilder.ForwardProp(network, input);
loss += Errors.SQUARE.Error(output, dataPoint.Label);
}
return(loss / dataPoints.Count);
}
private void Go()
{
var lijstje = DataSetGenerator.Generate();
int size = 500;
var img = new Image <Rgba32>(size, size);
MLImager.AddPointsToImage(img, lijstje);
using (var fs = new FileStream("output.png", FileMode.Create, FileAccess.Write, FileShare.Read))
{
img.SaveAsPng(fs);
}
lijstje.Shuffle();
var testData = lijstje.Take(lijstje.Count / 2).ToList();
var trainData = lijstje.Skip(lijstje.Count / 2).ToList();
foreach (var inp in INPUTS.INPUTSDICT)
{
state[inp.Key] = false;
}
state["x"] = true;
state["y"] = true;
//state["xTimesY"] = true;
//var networkShape = new List<int>() { 2, 1, 1 };
var networkShape = new List <int>()
{
2, 8, 8, 8, 8, 8, 8, 1
};
var inputIds = new List <string>()
{
"x", "y"
};
var network = NetworkBuilder.BuildNetwork(networkShape, Activations.TANH, Activations.TANH, null, inputIds, false);
var w = Stopwatch.StartNew();
for (int i = 0; i < 100000; i++)
{
foreach (var trainPoint in trainData)
{
var input = MLHelper.ConstructInput(state, trainPoint.X, trainPoint.Y);
NetworkBuilder.ForwardProp(network, input);
NetworkBuilder.BackProp(network, trainPoint.Label, Errors.SQUARE);
if ((i + 1) % batchSize == 0)
{
NetworkBuilder.UpdateWeights(network, learningrate, regularizationRate);
}
}
lossTrain = MLHelper.GetLoss(network, state, trainData);
lossTest = MLHelper.GetLoss(network, state, testData);
Console.WriteLine($"{i}: LossTrain: {lossTrain} LossTest: {lossTest}");
if (w.Elapsed.TotalSeconds > 1)
{
var img2 = MLImager.GenerateImage(network, state, size);
MLImager.AddPointsToImage(img2, lijstje);
try
{
using (var fs = new FileStream("output2.png", FileMode.Create, FileAccess.Write, FileShare.Read))
{
img2.SaveAsPng(fs);
}
}
catch (Exception ex)
{
}
w.Restart();
}
//for (int y = 1; y < network.Count; y++)
//{
// var layer = network[y];
// Console.WriteLine(y);
// foreach (var node in layer)
// {
// var sb = new StringBuilder();
// foreach (var link in node.InputLinks)
// {
// sb.Append($"Lnk: {link.Weight} ");
// }
// Console.WriteLine($" {sb.ToString()}");
// }
// Console.WriteLine();
//}
//double cccc = 0;
//foreach (var testPoint in testData)
//{
// var input = ConstructInput(testPoint.X, testPoint.Y);
// var result = NetworkBuilder.ForwardProp(network, input);
// var res = Math.Abs(result - testPoint.Label);
// cccc += res;
//}
//Console.WriteLine($"Res: {cccc}");
}
}