public void Run()
{
var task = _trainer.Train(_cts.Token);
var running = true;
while (running)
{
var c = Console.ReadKey().Key;
switch (c)
{
case ConsoleKey.Q:
Console.WriteLine("Stopping training manually");
running = false;
break;
case ConsoleKey.R:
Console.WriteLine("Reseting optimizer cache!");
_trainer.Pause();
_network.ResetOptimizer();
_trainer.Resume();
break;
}
}
_cts.Cancel();
Task.WaitAll(task);
}
private static void RegressionUpdate(int n, double[] x, TrainerBase trainer, double[] y)
{
var netx = new Volume(1, 1, 1);
var avloss = 0.0;
for (var iters = 0; iters < 50; iters++)
{
for (var ix = 0; ix < n; ix++)
{
netx.Set(0, 0, 0, x[ix]);
trainer.Train(netx, y[ix]);
avloss += trainer.Loss;
}
}
avloss /= n * 50.0;
Console.WriteLine("Loss:" + avloss);
}
private static void Classify2DUpdate(int n, List <double[]> data, TrainerBase trainer, List <int> labels)
{
var netx = new Volume(1, 1, 2);
var avloss = 0.0;
for (var iters = 0; iters < 50; iters++)
{
for (var ix = 0; ix < n; ix++)
{
netx.Set(0, 0, 0, data[ix][0]);
netx.Set(0, 0, 1, data[ix][1]);
trainer.Train(netx, labels[ix]);
avloss += trainer.Loss;
}
}
avloss /= n * 50.0;
Console.WriteLine("Loss:" + avloss);
}
private static void RegressionUpdate(int n, double[] x, TrainerBase <double> trainer, double[] y)
{
var netx = BuilderInstance.Volume.SameAs(new Shape(1, 1, 1, n));
var nety = BuilderInstance.Volume.SameAs(new Shape(1, 1, 1, n));
var avloss = 0.0;
for (var ix = 0; ix < n; ix++)
{
netx.Set(0, 0, 0, ix, x[ix]);
nety.Set(0, 0, 0, ix, y[ix]);
}
for (var iters = 0; iters < 50; iters++)
{
trainer.Train(netx, nety);
avloss += trainer.Loss;
}
avloss /= n * 50.0;
Console.WriteLine("Loss:" + avloss);
}
private static void Classify2DUpdate(int n, List <double[]> data, TrainerBase <double> trainer, List <int> labels)
{
var avloss = 0.0;
//var netx = new Volume(new double[2], new Shape(1, 1, 2, 1));
//for (var iters = 0; iters < 50; iters++)
//{
// for (var ix = 0; ix < n; ix++)
// {
// var hotLabels = new Volume(new double[2], new Shape(1, 1, 2, 1));
// hotLabels.Set(0, 0, labels[ix], 0, 1.0);
// netx.Set(0, 0, 0, data[ix][0]);
// netx.Set(0, 0, 1, data[ix][1]);
// trainer.Train(netx, hotLabels);
// avloss += trainer.Loss;
// }
//}
var netx = new Volume(new double[2 * n], new Shape(1, 1, 2, n));
var hotLabels = new Volume(new double[2 * n], new Shape(1, 1, 2, n));
for (var ix = 0; ix < n; ix++)
{
hotLabels.Set(0, 0, labels[ix], ix, 1.0);
netx.Set(0, 0, 0, ix, data[ix][0]);
netx.Set(0, 0, 1, ix, data[ix][1]);
}
for (var iters = 0; iters < 50; iters++)
{
trainer.Train(netx, hotLabels);
avloss += trainer.Loss;
}
avloss /= 50.0;
Console.WriteLine("Loss:" + avloss);
}
public void BatchTrain(double[][] batchInputs, double[][] batchOutputs, int iterations, Action <double, int, string> progressCallback)
{
trainer.BatchSize = batchInputs.Length;
foreach (int currentIteration in Enumerable.Range(1, iterations))
{
Randomizer.Shuffle(batchInputs, batchOutputs);
(Volume <double> inputs, Volume <double> outputs) = GetVolumeDataSetsFromArrays(batchInputs, batchOutputs);
trainer.Train(inputs, outputs);
var error = network.GetCostLoss(inputs, outputs);
if (progressCallback != null)
{
progressCallback(error, currentIteration, "Supervised");
}
inputs.Dispose();
outputs.Dispose();
if (this.ShouldStopTraning)
{
this.ShouldStopTraning = false;
break;
}
}
}
private static void Classify2DUpdate(int n, List <double[]> data, TrainerBase <double> trainer, List <int> labels)
{
var avloss = 0.0;
var netx = BuilderInstance.Volume.SameAs(new Shape(1, 1, 2, n));
var hotLabels = BuilderInstance.Volume.SameAs(new Shape(1, 1, 2, n));
for (var ix = 0; ix < n; ix++)
{
hotLabels.Set(0, 0, labels[ix], ix, 1.0);
netx.Set(0, 0, 0, ix, data[ix][0]);
netx.Set(0, 0, 1, ix, data[ix][1]);
}
for (var iters = 0; iters < 50; iters++)
{
trainer.Train(netx, hotLabels);
avloss += trainer.Loss;
}
avloss /= 50.0;
Console.WriteLine(k++ + " Loss:" + avloss);
}