private void Conv()
{
Random random = new Random();
Vector dat = GetSigXY(random).Item1;
Vector nnwOut = networkMeneger.Forward(dat);
GraphCPU graph = new GraphCPU(false);
// Нейросеть для формирования эмбедингов
NNW net = new NNW();
net.Layers.Add(nnw.Layers[0]);
net.Layers.Add(nnw.Layers[1]);
net.Layers.Add(nnw.Layers[2]);
net.Layers.Add(nnw.Layers[3]);
net.Layers.Add(nnw.Layers[4]);
net.Layers.Add(nnw.Layers[5]);
net.Layers.Add(nnw.Layers[6]);
net.Layers.Add(nnw.Layers[7]);
Vector hl = net.Activate(new NNValue(dat), graph).ToVector();
sigChart.PlotBlack(t, dat);
hChart.BarBlack(hl);
outChart.PlotBlack(t, nnwOut);
}
private void ShDat()
{
Vector dat = random.NextDouble() > 0.5 ? GetSig(2) : GetSig(4);
GraphCPU graph = new GraphCPU(false);
Vector nnwOut = NNW.Activate(new NNValue(dat), graph).ToVector();
chartVisual1.PlotBlack(t, dat);
chartVisual2.BarBlack(nnwOut);
}
public Agent(NNW model, int degreesOfFreedom, Random random)
{
lifes = new List <Life>();
graphForward = new GraphCPU(false);
graphBackward = new GraphCPU(true);
this.degreesOfFreedom = degreesOfFreedom;
this.model = model;
this.random = random;
}
static void Main(string[] args)
{
Random random = new Random(13);
NeuralNetwork cNN = new NeuralNetwork(random, 0.2);
var conv = new ConvolutionLayer(new RectifiedLinearUnit(0.01), 8, 3, 3);
conv.IsSame = true;
cNN.AddNewLayer(new Shape(28, 28), conv);
cNN.AddNewLayer(new MaxPooling(2, 2));
cNN.AddNewLayer(new ConvolutionLayer(new RectifiedLinearUnit(0.01), 16, 3, 3));
cNN.AddNewLayer(new MaxPooling(2, 2));
cNN.AddNewLayer(new ConvolutionLayer(new RectifiedLinearUnit(0.01), 32, 3, 3));
cNN.AddNewLayer(new UnPooling(2, 2));
cNN.AddNewLayer(new ConvolutionLayer(new RectifiedLinearUnit(0.01), 16, 3, 3));
cNN.AddNewLayer(new MaxPooling(2, 2));
cNN.AddNewLayer(new Flatten());
cNN.AddNewLayer(new FeedForwardLayer(20, new RectifiedLinearUnit(0.01)));
cNN.AddNewLayer(new FeedForwardLayer(2, new SoftmaxUnit()));
Console.WriteLine(cNN);
GraphCPU graph = new GraphCPU(false);
NNValue nValue = NNValue.Random(28, 28, 2, random);
NNValue nValue1 = NNValue.Random(28, 28, 2, random);
NNValue outp = new NNValue(new double[] { 0, 1 });
NNValue outp1 = new NNValue(new double[] { 1, 0 });
DataSetNoReccurent data = new DataSetNoReccurent(new NNValue[] { nValue, nValue1 }, new NNValue[] { outp, outp1 }, new CrossEntropyWithSoftmax());
TrainerCPU trainer = new TrainerCPU(TrainType.MiniBatch, new Adam());
trainer.BatchSize = 2;
trainer.Train(10000, 0.001, cNN, data, 2, 0.0001);
double[] dbs = cNN.Activate(nValue, graph).DataInTensor;
double[] dbs1 = cNN.Activate(nValue1, graph).DataInTensor;
}
private void Lin()
{
Random random = new Random();
Vector dat = GetSigXY(random).Item1;
Vector nnwOut = networkMeneger.Forward(dat);
GraphCPU graph = new GraphCPU(false);
Vector hl = nnw.Layers[0].Activate(new NNValue(dat), graph).ToVector();
sigChart.PlotBlack(t, dat);
hChart.BarBlack(hl);
outChart.PlotBlack(t, nnwOut);
}
/// <summary>
/// Один проход для минипакетного обучения
/// </summary>
/// <param name="learningRate">Скорость обучения</param>
/// <param name="network">Нейросеть</param>
/// <param name="sequences">Датасет</param>
/// <param name="isTraining">Производится ли обучение</param>
/// <param name="lossFunction">Функция ошибки</param>
/// <returns></returns>
public double PassBatch(double learningRate, INetwork network, List <DataSequence> sequences,
bool isTraining, ILoss lossFunction)
{
double numerLoss = 0;
double denomLoss = 0;
int index, passes = (sequences.Count % BatchSize == 0) ? sequences.Count / BatchSize : sequences.Count / BatchSize + 1;
for (int j = 0; j < passes; j++)
{
GraphCPU g = new GraphCPU(isTraining);
for (int i = 0; i < BatchSize; i++)
{
index = random.Next(sequences.Count);
var seq = sequences[index];
network.ResetState();
foreach (DataStep step in seq.Steps)
{
NNValue output = network.Activate(step.Input, g);
if (step.TargetOutput != null)
{
double loss = lossFunction.Measure(output, step.TargetOutput);
if (Double.IsNaN(loss) || Double.IsInfinity(loss))
{
return(loss);
}
numerLoss += loss;
denomLoss++;
if (isTraining)
{
lossFunction.Backward(output, step.TargetOutput);
}
}
}
}
if (isTraining)
{
g.Backward(); //backprop dw values
UpdateModelParams(network, learningRate); //update params
}
}
return(numerLoss / denomLoss);
}
/// <summary>
/// Конструктор
/// </summary>
/// <param name="model">Модель нейронной сети</param>
/// <param name="degreesOfFreedom">Количество возможных действий</param>
/// <param name="random">Генератор рандома</param>
public MLAgent(NNW model, int degreesOfFreedom, Random random, IOptimizer optimizer = null)
{
Generations = new List <Generation>();
graphForward = new GraphCPU(false);
graphBackward = new GraphCPU(true);
this.degreesOfFreedom = degreesOfFreedom;
this.model = model;
this.random = random;
if (optimizer == null)
{
optimizer = new Adam();
}
this.optimizer = optimizer;
trainer = new Trainer(graphBackward, TrainType.Online, optimizer);
}
/// <summary>
/// Онлайн обучение
/// </summary>
/// <param name="learningRate"></param>
/// <param name="network"></param>
/// <param name="sequences"></param>
/// <param name="applyTraining"></param>
/// <param name="lossTraining"></param>
/// <returns></returns>
public double Pass(double learningRate, INetwork network, List <DataSequence> sequences,
bool applyTraining, ILoss lossTraining)
{
double numerLoss = 0;
double denomLoss = 0;
foreach (DataSequence seq in sequences)
{
GraphCPU g = new GraphCPU(applyTraining);
network.ResetState();
foreach (DataStep step in seq.Steps)
{
NNValue output = network.Activate(step.Input, g);
if (step.TargetOutput != null)
{
double loss = lossTraining.Measure(output, step.TargetOutput);
if (Double.IsNaN(loss) || Double.IsInfinity(loss))
{
return(loss);
}
numerLoss += loss;
denomLoss++;
if (applyTraining)
{
lossTraining.Backward(output, step.TargetOutput);
}
}
}
if (applyTraining)
{
g.Backward(); //backprop dw values
UpdateModelParams(network, learningRate); //update params
}
}
return(numerLoss / denomLoss);
}
public void Forward(int[] inp)
{
GraphCPU graph = new GraphCPU(false);
int indOld = 10;
network.ResetState();
for (int i = 0; i < inp.Length; i++)
{
NNValue valueMatrix = new NNValue(DataSetSeq2Seq.GetValue(inp[i], 11));
network.Activate(valueMatrix, graph);
}
for (int i = 0; i < inp.Length; i++)
{
NNValue valueMatrix = new NNValue(DataSetSeq2Seq.GetValue(indOld, 11));
indOld = GetInd(network.Activate(valueMatrix, graph));
Console.Write(indOld);
}
Console.WriteLine();
}
