public void ForwardBackwardTest()
{
Shape shape = new Shape(new int[] { 2 });
SigmoidLayer layer = new SigmoidLayer(shape);
Session session = new Session();
Tensor source = new Tensor(null, shape);
source.Set(new float[] { 2, -3 });
Tensor x = source.Clone() as Tensor;
Tensor y = layer.Forward(session, new[] { x })[0];
float[] expected = source.Weights.Take(source.Length).Select(w => SigmoidLayerTest.activation(w)).ToArray();
Helpers.AreArraysEqual(x.Length, expected, y.Weights);
// unroll the graph
float[] dy = Enumerable.Range(1, x.Length).Select(w => (float)w).ToArray();
y.SetGradient(dy);
session.Unroll();
Helpers.AreArraysEqual(
expected.Length,
expected.Zip(dy, (w, dw) => SigmoidLayerTest.derivative(w) * dw).ToArray(),
x.Gradient);
}
public void CloneTest()
{
SigmoidLayer layer1 = new SigmoidLayer(new Shape(new int[] { 2 }));
SigmoidLayer layer2 = layer1.Clone() as SigmoidLayer;
Assert.AreEqual(JsonConvert.SerializeObject(layer1), JsonConvert.SerializeObject(layer2));
}
public void SerializationTest()
{
// Create a SigmoidLayer
var layer = new SigmoidLayer();
layer.Init(10, 10, 3);
SigmoidLayer deserialized;
using (var ms = new MemoryStream())
{
// Serialize
IFormatter formatter = new BinaryFormatter();
formatter.Serialize(ms, layer);
// Deserialize
ms.Position = 0;
deserialized = formatter.Deserialize(ms) as SigmoidLayer;
}
Assert.AreEqual(layer.InputDepth, deserialized.InputDepth);
Assert.AreEqual(layer.InputHeight, deserialized.InputHeight);
Assert.AreEqual(layer.InputWidth, deserialized.InputWidth);
Assert.AreEqual(layer.OutputDepth, deserialized.OutputDepth);
Assert.AreEqual(layer.OutputHeight, deserialized.OutputHeight);
Assert.AreEqual(layer.OutputWidth, deserialized.OutputWidth);
}
public void SigmoidLayer_BackwardGradient()
{
var layer = new SigmoidLayer();
var checker = new GradientChecker(1e-2f, 1e-3f, 1701, 0.0d, 0.01f);
checker.CheckEltwise(layer, bottom, top);
}
public void CanUseBigSigmoidLayer()
{
double[,] weights = new double[2000, 1000];
double[] input = new double[1000];
for (int i = 0; i < 1000; i++)
{
weights[i, i] = 1.0;
input[i] = (double)i;
}
NetworkVector inputvector = new NetworkVector(input);
Layer layer = new SigmoidLayer(weights);
layer.Run(inputvector);
double[] result = layer.Output.ToArray();
double sig0 = sigmoid(0.0);
for (int i = 0, j = 1000; i < 1000; i++, j++)
{
Assert.AreEqual(sigmoid((double)i), result[i], "Failed for i = " + i);
Assert.AreEqual(sig0, result[j], "Failed for j = " + j);
}
}
public void CopyConstructorTest1()
{
SigmoidLayer layer1 = new SigmoidLayer(new Shape(new int[] { 2 }));
SigmoidLayer layer2 = new SigmoidLayer(layer1);
Assert.AreEqual(JsonConvert.SerializeObject(layer1), JsonConvert.SerializeObject(layer2));
}
private Network CreateNetwork(string PBaseNetName)
{
if (PBaseNetName == null)
{
throw new Exception("AAARGGHH!");
}
Network tempacnet = Network.Load(PBaseNetName);
int numlayersnew = tempacnet.NumLayers / 2 + 1;
ILayer[] layers = new ILayer[numlayersnew];
double[][][] weights = new double[numlayersnew][][];
double[] learnrates = new double[numlayersnew];
for (int i = 0; i < numlayersnew; i++)
{
layers[i] = tempacnet.Layers[i];
weights[i] = tempacnet.Weights[i];
learnrates[i] = tempacnet.Learnrates[i];
}
layers[numlayersnew - 1] = new SigmoidLayer(10, 0.001);
weights[numlayersnew - 1] = new double[10][];
for (int i = 0; i < 10; i++)
{
int numneurons = layers[numlayersnew - 2].NumNeurons;
weights[numlayersnew - 1][i] = new double[numneurons];
for (int j = 0; j < numneurons; j++)
{
weights[numlayersnew - 1][i][j] = 0;
}
}
learnrates[numlayersnew - 1] = 0.001;
return(new Network(tempacnet.InputLayer, layers, weights, null, learnrates));
}
public override void Train(IForecastingDataSets datasets)
{
OnStartRunning(new ComponentRunEventArgs(datasets));
AnnModelParameter para = mParameter as AnnModelParameter;
LinearLayer inputLayer = new LinearLayer(datasets.InputData[0].Length);
SigmoidLayer hiddenLayer = new SigmoidLayer(para.HiddenNeuronsCount[0]);
SigmoidLayer outputLayer = new SigmoidLayer(1);
new BackpropagationConnector(inputLayer, hiddenLayer).Initializer = new RandomFunction(0d, 0.3d);
new BackpropagationConnector(hiddenLayer, outputLayer).Initializer = new RandomFunction(0d, 0.3d);
network = new BackpropagationNetwork(inputLayer, outputLayer);
network.SetLearningRate(para.LearningRate);
network.JitterEpoch = para.JitterEpoch;
network.JitterNoiseLimit = para.JitterNoiseLimit;
network.EndEpochEvent += new TrainingEpochEventHandler(
delegate(object senderNetwork, TrainingEpochEventArgs args)
{
// TODO: trainning error needs to be calculated
OnRunningEpoch(new AnnModelRunEpochEventArgs(args.TrainingIteration + 1, 0));
});
network.Learn(ForecastingDataSets.ConvertToTrainingSet(datasets), para.Iterations);
datasets.ForecastedData = new double[datasets.InputData.Length][];
for (int i = 0; i < datasets.InputData.Length; i++)
{
datasets.ForecastedData[i] = new double[1];
datasets.ForecastedData[i][0] = Forecast(datasets.InputData[i]);
}
OnFinishRunning(new ComponentRunEventArgs(datasets));
}
public void ComputeTwiceGradientShouldYieldTheSameResult()
{
const int inputWidth = 20;
const int inputHeight = 20;
const int inputDepth = 2;
var layer = new SigmoidLayer <double>();
layer.Init(inputWidth, inputHeight, inputDepth);
// Forward pass
var input = BuilderInstance <double> .Volume.Random(new Shape(inputWidth, inputHeight, inputDepth));
var output = layer.DoForward(input, true);
// Set output gradients to 1
var outputGradient = BuilderInstance <double> .Volume.SameAs(new double[output.Shape.TotalLength].Populate(1.0), output.Shape);
// Backward pass to retrieve gradients
layer.Backward(outputGradient);
var step1 = ((Volume <double>)layer.InputActivationGradients.Clone()).ToArray();
layer.Backward(outputGradient);
var step2 = ((Volume <double>)layer.InputActivationGradients.Clone()).ToArray();
Assert.IsTrue(step1.SequenceEqual(step2));
}
public void Test_Sigmoid_Execute()
{
sigmoid = new SigmoidLayer();
Data2D data = new Data2D(2, 3, 1, 1);
data[0, 0, 0, 0] = 4;
data[0, 1, 0, 0] = 2;
data[0, 2, 0, 0] = -2;
data[1, 0, 0, 0] = 3;
data[1, 1, 0, 0] = -1;
data[1, 2, 0, 0] = -3;
sigmoid.SetInput(data);
sigmoid.Execute();
Data2D output = sigmoid.GetOutput() as Data2D;
Assert.AreEqual(output[0, 0, 0, 0], SigmoidFunc(4.0), 0.00000001);
Assert.AreEqual(output[0, 1, 0, 0], SigmoidFunc(2.0), 0.00000001);
Assert.AreEqual(output[0, 2, 0, 0], SigmoidFunc(-2.0), 0.00000001);
Assert.AreEqual(output[1, 0, 0, 0], SigmoidFunc(3.0), 0.00000001);
Assert.AreEqual(output[1, 1, 0, 0], SigmoidFunc(-1.0), 0.00000001);
Assert.AreEqual(output[1, 2, 0, 0], SigmoidFunc(-3.0), 0.00000001);
}
public static SigmoidLayer<T> Sigmoid<T>(this LayerBase<T> layer) where T : struct, IEquatable<T>, IFormattable
{
var sigmoid = new SigmoidLayer<T>();
sigmoid.AcceptParent(sigmoid);
return sigmoid;
}
//Get neural network
public virtual NeuronDotNet.Core.Network getNeural()
{
LinearLayer inputLayer = new LinearLayer(23);
SigmoidLayer outputLayer = new SigmoidLayer(100);
return(new BackpropagationNetwork(inputLayer, outputLayer));
}
void CreateNewNetwork()
{
LinearLayer inputLayer = new LinearLayer(neurons);
SigmoidLayer hiddenLayer = new SigmoidLayer(hidden1Neurons);
SigmoidLayer hiddenLayer2 = new SigmoidLayer(hidden2Neurons);
LinearLayer outputLayer = new LinearLayer(outputNum);
BackpropagationConnector conn1 = new BackpropagationConnector(inputLayer, hiddenLayer);
conn1.Initializer = new RandomFunction(0d, 0.001d);
BackpropagationConnector conn3 = new BackpropagationConnector(hiddenLayer, hiddenLayer2);
conn3.Initializer = new RandomFunction(0d, 0.001d);
BackpropagationConnector conn2 = new BackpropagationConnector(hiddenLayer2, outputLayer);
conn2.Initializer = new RandomFunction(0d, 0.001d);
conn1.Initialize();
conn2.Initialize();
conn3.Initialize();
neuralNetwork = new BackpropagationNetwork(inputLayer, outputLayer);
neuralNetwork.SetLearningRate(learningRate);
neuralNetwork.Initialize();
}
public BackpropagationNetwork network(int trainInVectorDimension, int trainOutVectorDimension)
{
this.hiddenLayerList = HiddenLayerList();
ActivationLayer inputLayer = new LinearLayer(trainInVectorDimension);
ActivationLayer outputLayer = new SigmoidLayer(trainOutVectorDimension);
BackpropagationConnector bpc0 = new BackpropagationConnector(inputLayer, this.hiddenLayerList[0]);
for (int i = 1; i < this.hiddenLayerList.Count; i++)
{
bpc0 = new BackpropagationConnector(this.hiddenLayerList[i - 1], this.hiddenLayerList[i]);
}
bpc0 = new BackpropagationConnector(this.hiddenLayerList[this.hiddenLayerList.Count - 1], outputLayer);
BackpropagationNetwork network = new BackpropagationNetwork(inputLayer, outputLayer);
/*ActivationLayer inputLayer = hiddenLayerList[0];
* ActivationLayer outputLayer = hiddenLayerList[hiddenLayerList.Count - 1];
*
* if(hiddenLayerList.Count != 2)
* {
* BackpropagationConnector bpc0 = new BackpropagationConnector(inputLayer, this.hiddenLayerList[1]);
* for (int i = 2; i < this.hiddenLayerList.Count - 1; i++)
* {
* bpc0 = new BackpropagationConnector(this.hiddenLayerList[i - 1], this.hiddenLayerList[i]);
* }
* bpc0 = new BackpropagationConnector(this.hiddenLayerList[this.hiddenLayerList.Count - 2], outputLayer);
* }
*
* BackpropagationNetwork network = new BackpropagationNetwork(inputLayer, outputLayer);*/
network.SetLearningRate(this.learningRate);
return(network);
}
public static SigmoidLayer <T> Sigmoid <T>(this LayerBase <T> layer) where T : struct, IEquatable <T>, IFormattable
{
var sigmoid = new SigmoidLayer <T>();
layer.ConnectTo(sigmoid);
return(sigmoid);
}
public static SigmoidLayer Sigmoid(this LayerBase layer)
{
var sigmoid = new SigmoidLayer();
layer.ConnectTo(sigmoid);
return(sigmoid);
}
public void ArchitectureConstructorTest1()
{
Shape shape = new Shape(new int[] { 2 });
SigmoidLayer layer = new SigmoidLayer(shape, "SIG", null);
CollectionAssert.AreEqual(shape.Axes, layer.OutputShape.Axes);
Assert.AreEqual("SIG", layer.Architecture);
}
public void SigmoidLayer_BackwardGradient()
{
var layer = new SigmoidLayer();
var checker = new GradientChecker(1e-2f, 1e-3f, 1701, 0.0d, 0.01f);
checker.CheckEltwise(layer, bottom, top);
}
public void SerializeTest()
{
SigmoidLayer layer1 = new SigmoidLayer(new Shape(new int[] { 2 }));
string s1 = JsonConvert.SerializeObject(layer1);
SigmoidLayer layer2 = JsonConvert.DeserializeObject <SigmoidLayer>(s1);
string s2 = JsonConvert.SerializeObject(layer2);
Assert.AreEqual(s1, s2);
}
public void CanMakeSigmoidLayer()
{
double[,] weights = new double[, ] {
{ 1, 2 }, { 3, 4 }
};
Layer layer = new SigmoidLayer(weights);
Assert.IsNotNull(layer);
}
private void Form1_OnLoad(object sender, EventArgs e)
{
inputTier = new LinearLayer(35);
hiddenTier = new SigmoidLayer(3);
outputTier = new SigmoidLayer(5);
_ = new BackpropagationConnector(inputTier, hiddenTier);
_ = new BackpropagationConnector(hiddenTier, outputTier);
neuralNetwork = new BackpropagationNetwork(inputTier, outputTier);
neuralNetwork.Initialize();
}
private Network CreateNetwork()
{
ILayer[] layers = new ILayer[2];
layers[0] = new SigmoidLayer(300, 0.001);
layers[1] = new SigmoidLayer(10, 0.001);
double[] learnrates = new double[2];
learnrates[0] = 0.001;
learnrates[1] = 0.001;
return(new Network(new SigmoidLayer(784, 0.001), layers, learnrates));
}
private Network CreateNetwork()
{
ILayer[] layers = new ILayer[2];
layers[0] = new SigmoidLayer(300, 0.005);
layers[1] = new SigmoidLayer(10, 0.005);
double[] learnrates = new double[2];
learnrates[0] = 0.005;
learnrates[1] = 0.005;
return(new Network(new SigmoidLayer(autoencoderoutputs, 0.005), layers, learnrates));
}
public void SigmoidLayer_Setup()
{
var layer = new SigmoidLayer();
layer.Setup(bottom, top);
Assert.Equal(bottom.Num, top.Num);
Assert.Equal(bottom.Channels, top.Channels);
Assert.Equal(bottom.Height, top.Height);
Assert.Equal(bottom.Width, top.Width);
}
public void GradientWrtInputCheck()
{
const int inputWidth = 20;
const int inputHeight = 20;
const int inputDepth = 2;
// Create layer
var layer = new SigmoidLayer();
GradientCheckTools.GradientCheck(layer, inputWidth, inputHeight, inputDepth);
}
public void GradientWrtInputCheck()
{
const int inputWidth = 20;
const int inputHeight = 20;
const int inputDepth = 2;
// Create layer
var layer = new SigmoidLayer();
GradientCheckTools.GradientCheck(layer, inputWidth, inputHeight, inputDepth);
}
public void SigmoidLayer_Setup()
{
var layer = new SigmoidLayer();
layer.Setup(bottom, top);
Assert.Equal(bottom.Num, top.Num);
Assert.Equal(bottom.Channels, top.Channels);
Assert.Equal(bottom.Height, top.Height);
Assert.Equal(bottom.Width, top.Width);
}
private void WFAnnRecognition_Load(object sender, EventArgs e)
{
lstLog.Items.Insert(0, "Initialize ANN model");
inputLayer = new LinearLayer(35);
hiddenLayer = new SigmoidLayer(3);
outputLayer = new SigmoidLayer(5);
BackpropagationConnector connector = new BackpropagationConnector(inputLayer, hiddenLayer);
BackpropagationConnector connector2 = new BackpropagationConnector(hiddenLayer, outputLayer);
network = new BackpropagationNetwork(inputLayer, outputLayer);
network.Initialize();
}
public Imagine(int w, int h)
{
W = w;
H = h;
Inputs = W * H * 3;
iLay = new LinearLayer(Inputs);
hLay = new SigmoidLayer(neuronCount);
oLay = new SigmoidLayer(w * h * 3);
c1 = new BackpropagationConnector(iLay, hLay, ConnectionMode.Complete);
c2 = new BackpropagationConnector(hLay, oLay, ConnectionMode.Complete);
net = new BackpropagationNetwork(iLay, oLay);
net.SetLearningRate(learningRate);
}
public void GradientWrtInputCheck()
{
const int inputWidth = 20;
const int inputHeight = 20;
const int inputDepth = 2;
const int batchSize = 3;
// Create layer
var layer = new SigmoidLayer <double>();
GradientCheckTools.GradientCheck(layer, inputWidth, inputHeight, inputDepth, batchSize, 1e-6);
}
private void Form1_Load(object sender, EventArgs e)
{
int gizlikatmansayisi = Convert.ToInt32(Microsoft.VisualBasic.Interaction.InputBox("Gizli Katman Sayısını Giriniz", "Bilgi Girişi", "Örn: 3", 0, 0));
giriskatmanı = new LinearLayer(35);
gizlikatman = new SigmoidLayer(gizlikatmansayisi);
cikiskatmani = new SigmoidLayer(5);
BackpropagationConnector giris_gizli_baglanti = new BackpropagationConnector(giriskatmanı, gizlikatman);
BackpropagationConnector gizli_cikis_baglanti = new BackpropagationConnector(gizlikatman, cikiskatmani);
ag = new BackpropagationNetwork(giriskatmanı, cikiskatmani);
ag.Initialize();
}
private Network InitPreTrainedNet()
{
int numlayers = layersizes.GetLength(0);
ILayer[] layers = new ILayer[numlayers];
double[] learnrates = new double[4];
for (int i = 0; i < numlayers; i++)
{
layers[i] = new SigmoidLayer(layersizes[i], 0.01);
learnrates[i] = 0.01;
}
return(new Network(new SigmoidLayer(784, 0.01), layers, learnrates));
}
private Network InitPreTrainedNet()
{
ILayer[] layers = new ILayer[1];
layers[0] = new SigmoidLayer(100, 0.001);
//layers[1] = new SigmoidLayer(numoutputs, 0.05);
//layers[2] = new SigmoidLayer(100, 0.01);
//layers[3] = new SigmoidLayer(numoutputs, 0.01);
double[] learnrates = new double[1];
learnrates[0] = 0.001;
//learnrates[1] = 0.05;
//learnrates[2] = 0.01;
//learnrates[3] = 0.01;
return(new Network(new SigmoidLayer(625, 0.001), layers, learnrates));
}
public void SigmoidLayer_Forward()
{
var layer = new SigmoidLayer();
layer.Setup(bottom, top);
layer.Forward(bottom, top);
Assert.Equal(bottom.Count, top.Count);
using (var topCpu = top.OnCpu())
using (var bottomCpu = bottom.OnCpu())
{
int count = bottom.Count;
for (int i = 0; i < count; i++)
{
Assert.True(MathHelpers.Equality(topCpu.DataAt(i), 1.0d / (1.0d + Math.Exp(-bottomCpu.DataAt(i)))));
// check that we squashed the value between 0 and 1
Assert.True(topCpu.DataAt(i) >= 0.0d);
Assert.True(topCpu.DataAt(i) <= 1.0d);
};
}
}