public double CalcRMSE(PragmaLearn.Learner.BackpropNeuralNetwork net, Dataset data, int count)
{
var error = 0.0;
var c = 0;
for (int i = 0; i < count; ++i)
{
var x = Tools.rnd.Index(data.input.Count);
var p = net.Predict(data.input[x]);
var y = data.output[x];
var se = 0.0;
for (int j = 0; j < p.Length; ++j)
{
if (y[j] != -1)
{
se += (p[j] - y[j]) * (p[j] - y[j]);
c++;
}
}
error += se;
}
error /= c;
return(Math.Sqrt(error));
}
private void bLoadData_Click(object sender, EventArgs e)
{
resultData = KeypointData.LoadResultData();
var data = KeypointData.LoadTrainData();
data.RandomSplit(0.9f, out trainData, out testData);
var hidden = trainData.GetInputDimension();
initNet();
clonedNet = network.Clone();
}
//async void test(int iter)
//{
// var idx = pos % resultData.input.Count;
// var net = network.Clone();
// net.learningRate = network.learningRate;
// await Task.Run(() =>
// {
// try
// {
// var rmseTrain = CalcRMSE(net, trainData, 250) * KeypointData.origImgSize;
// var rmseTest = CalcRMSE(net, testData, 250) * KeypointData.origImgSize;
// zedTrain.Add(iter, rmseTrain);
// zedTrain.Sort((a, b) => a.X.CompareTo(b.X));
// zedTest.Add(iter, rmseTest);
// zedTest.Sort((a, b) => a.X.CompareTo(b.X));
// Console.WriteLine();
// Console.WriteLine("iteration: " + idx);
// Console.WriteLine("learning rate: " + net.learningRate);
// Console.WriteLine("train: " + rmseTrain);
// Console.WriteLine("test: " + rmseTest);
// Console.WriteLine();
// }
// catch (Exception e)
// {
// Console.WriteLine();
// Console.WriteLine(e);
// Console.WriteLine();
// }
// });
// // net.Save("network_" + iter + ".dat");
// clonedNet = net;
// zedGraphControl1.AxisChange();
// pos++;
// Refresh();
//}
void test(int iter)
{
var idx = pos % resultData.input.Count;
var net = network.Clone();
net.learningRate = network.learningRate;
try
{
var rmseTrain = CalcRMSE(net, trainData, 250) * KeypointData.origImgSize;
var rmseTest = CalcRMSE(net, testData, 250) * KeypointData.origImgSize;
zedTrain.Add(iter, rmseTrain);
zedTrain.Sort((a, b) => a.X.CompareTo(b.X));
zedTest.Add(iter, rmseTest);
zedTest.Sort((a, b) => a.X.CompareTo(b.X));
Console.WriteLine();
Console.WriteLine("iteration: " + idx);
Console.WriteLine("learning rate: " + net.learningRate);
Console.WriteLine("train: " + rmseTrain);
Console.WriteLine("test: " + rmseTest);
Console.WriteLine();
}
catch (Exception e)
{
Console.WriteLine();
Console.WriteLine(e);
Console.WriteLine();
}
// net.Save("network_" + iter + ".dat");
clonedNet = net;
zedGraphControl1.AxisChange();
pos++;
Refresh();
}
private void bLoad_Click(object sender, EventArgs e)
{
network.Open("network.dat");
clonedNet = network.Clone();
}
private void bLoad_Click(object sender, EventArgs e)
{
network.Open("network.dat");
clonedNet = network.Clone();
}
private void bLoadData_Click(object sender, EventArgs e)
{
resultData = KeypointData.LoadResultData();
var data = KeypointData.LoadTrainData();
data.RandomSplit(0.9f, out trainData, out testData);
var hidden = trainData.GetInputDimension();
initNet();
clonedNet = network.Clone();
}
//async void test(int iter)
//{
// var idx = pos % resultData.input.Count;
// var net = network.Clone();
// net.learningRate = network.learningRate;
// await Task.Run(() =>
// {
// try
// {
// var rmseTrain = CalcRMSE(net, trainData, 250) * KeypointData.origImgSize;
// var rmseTest = CalcRMSE(net, testData, 250) * KeypointData.origImgSize;
// zedTrain.Add(iter, rmseTrain);
// zedTrain.Sort((a, b) => a.X.CompareTo(b.X));
// zedTest.Add(iter, rmseTest);
// zedTest.Sort((a, b) => a.X.CompareTo(b.X));
// Console.WriteLine();
// Console.WriteLine("iteration: " + idx);
// Console.WriteLine("learning rate: " + net.learningRate);
// Console.WriteLine("train: " + rmseTrain);
// Console.WriteLine("test: " + rmseTest);
// Console.WriteLine();
// }
// catch (Exception e)
// {
// Console.WriteLine();
// Console.WriteLine(e);
// Console.WriteLine();
// }
// });
// // net.Save("network_" + iter + ".dat");
// clonedNet = net;
// zedGraphControl1.AxisChange();
// pos++;
// Refresh();
//}
void test(int iter)
{
var idx = pos % resultData.input.Count;
var net = network.Clone();
net.learningRate = network.learningRate;
try
{
var rmseTrain = CalcRMSE(net, trainData, 250) * KeypointData.origImgSize;
var rmseTest = CalcRMSE(net, testData, 250) * KeypointData.origImgSize;
zedTrain.Add(iter, rmseTrain);
zedTrain.Sort((a, b) => a.X.CompareTo(b.X));
zedTest.Add(iter, rmseTest);
zedTest.Sort((a, b) => a.X.CompareTo(b.X));
Console.WriteLine();
Console.WriteLine("iteration: " + idx);
Console.WriteLine("learning rate: " + net.learningRate);
Console.WriteLine("train: " + rmseTrain);
Console.WriteLine("test: " + rmseTest);
Console.WriteLine();
}
catch (Exception e)
{
Console.WriteLine();
Console.WriteLine(e);
Console.WriteLine();
}
// net.Save("network_" + iter + ".dat");
clonedNet = net;
zedGraphControl1.AxisChange();
pos++;
Refresh();
}
