public void Train(List <List <double> > inputs, List <List <double> > outputs,
double LearningRate, int epochs, int batchSize, bool writeNet = true)
{
DateTime startTime = DateTime.Now;
DateTime prevTime = DateTime.Now;
int procents = 0;
Console.ForegroundColor = ConsoleColor.Green;
for (int i = 0; i < epochs; ++i)
{
for (int j = 0; j < inputs.Count; ++j)
{
Collect(inputs[j], outputs[j], LearningRate);
if (i != 0 && j != 0 && (i * j + j) % batchSize == 0)
{
ApplyBatch();
}
}
if (i / (epochs / 100) != procents)
{
procents = i / (epochs / 100);
int tms = (int)((DateTime.Now - prevTime).TotalMinutes * (100 - procents));
if (tms != 0)
{
Console.Write("\rЗавершено на " + procents + "% Осталось " + tms + " минут SSE=" + SSE(inputs, outputs));
}
else
{
tms = (int)((DateTime.Now - prevTime).TotalSeconds * (100 - procents));
Console.Write("\rЗавершено на " + procents + "% Осталось " + tms + " секунд SSE=" + SSE(inputs, outputs));
}
prevTime = DateTime.Now;
}
}
ApplyBatch();
Console.Clear();
Console.WriteLine("\rDone!");
DateTime endTime = DateTime.Now;
Console.WriteLine("Время обучения: " + (endTime - startTime));
if (writeNet)
{
ANNSerializer.WriteNet(this, "first_net", "1");
}
}
static void Main(string[] args)
{
List <List <double> > inputs = ReadNetIO(@"input4.txt");
List <List <double> > outputs = ReadNetIO(@"output3.txt");
Shuffle(inputs);
Shuffle(outputs);
List <List <double> > testin = new List <List <double> >();
List <List <double> > testout = new List <List <double> >();
for (int i = 1; i < 11; ++i)
{
testin.Add(inputs[inputs.Count - i]);
testout.Add(outputs[outputs.Count - i]);
inputs.RemoveAt(inputs.Count - i);
outputs.RemoveAt(outputs.Count - i);
}
const bool newNet = true;
FeedForwardNet net;
if (newNet)
{
const double LearningRate = 0.1;
const int epochs = 10000;
const int batchSize = 1;
const int type = 1;
net = new FeedForwardNet();
if (type == 1)
{
net.AddSigmoidLayer(10, 4);
net.AddSigmoidLayer(5, 10);
net.AddSigmoidLayer(3, 5);
}
else if (type == 2)
{
net.AddTangentialLayer(10, 4);
net.AddTangentialLayer(5, 10);
net.AddTangentialLayer(3, 5);
}
else if (type == 3)
{
net.AddGaussianLayer(10, 4);
net.AddGaussianLayer(5, 10);
net.AddGaussianLayer(3, 5);
}
else if (type == 4)
{
net.AddGaussianLayer(10, 4);
net.AddSigmoidLayer(5, 10);
net.AddTangentialLayer(3, 5);
}
net.Train(inputs, outputs, LearningRate, epochs, batchSize);
}
else
{
net = ANNSerializer.ReadNet(@"first_net/1.ann");
}
for (int i = 0; i < outputs.Count; ++i)
{
List <double> result = net.Calculate(inputs[i]);
Console.ForegroundColor = ConsoleColor.White;
for (int j = 0; j < inputs[i].Count; ++j)
{
Console.Write(inputs[i][j] + " ");
}
Console.WriteLine();
Console.ForegroundColor = ConsoleColor.Yellow;
Console.Write(i + " " + ConvertToIris(result) + " ");
Console.ForegroundColor = ConsoleColor.Green;
Console.WriteLine(ConvertToIris(outputs[i]) + "\n");
}
Console.WriteLine("Tests:");
for (int i = 0; i < testin.Count; ++i)
{
List <double> result = net.Calculate(testin[i]);
Console.ForegroundColor = ConsoleColor.White;
for (int j = 0; j < testin[i].Count; ++j)
{
Console.Write(testin[i][j] + " ");
}
Console.WriteLine();
Console.ForegroundColor = ConsoleColor.Yellow;
Console.Write(i + " " + ConvertToIris(result) + " ");
Console.ForegroundColor = ConsoleColor.Green;
Console.WriteLine(ConvertToIris(testout[i]) + "\n");
}
}
