public OutputLayer(double[,] InputDims, int ThisLayersNeurons, int _MiniBatchSize, ActivationFunction _ActivationFunction, WeightInitialization _WeightInitialization, TrainAlgorithm _TrainAlgorithm, double _LearnRate, double _L2_Regularization, double _gradient) : base(InputDims, ThisLayersNeurons, _MiniBatchSize, _ActivationFunction, _WeightInitialization, _TrainAlgorithm, _LearnRate, _L2_Regularization, _gradient)
{
}
public Layer(double[,,] InputDims_ZofPreviousLayer, int _FilterSize, int _Stride, int _Depth, int _MiniBatchSize, ActivationFunction _ActivationFunction, WeightInitialization _WeightInitialization, TrainAlgorithm _TrainAlgorithm, double _LearnRate, double _L2_Regularization, double _gradient)//Constructor For ConvolutionalLayer
{
TrainAlgorithm = _TrainAlgorithm;
MiniBatchSize = _MiniBatchSize;
gradient = _gradient;
L2_Regularization = _L2_Regularization;
Stride = _Stride;
//InputDims_ZofPreviousLayer.GetLength(0) = Height(i-1)
//InputDims_ZofPreviousLayer.GetLength(1) =Width(i-1)
//InputDims_ZofPreviousLayer.GetLength(2) = Depth(i-1)*MiniBacthSize = DepthOfInputLayer*MiniBatchSize
double dHeight = (InputDims_ZofPreviousLayer.GetLength(0) - 1.0) / Stride + 1.0; //when changing something here, also change in ANNMAth.Im2Mat
double dWidth = (InputDims_ZofPreviousLayer.GetLength(1) - 1.0) / Stride + 1.0; //when changing something here, also change in ANNMAth.Im2Mat
if (dHeight % 1 == 0 && dWidth % 1 == 0)
{
Height = (int)dHeight;
Width = (int)dWidth;
}
else
{
throw new Exception("xxxx");
}
Depth = _Depth;
FilterSize = _FilterSize;
if (FilterSize % 2 == 0)//Filtersize must be an uneaven number
{
throw new Exception("xxxx");
}
Stride = _Stride;
LearnRate = _LearnRate;
ActivationFunction = _ActivationFunction;
//PreInput is the Matrix that holds the zeropadded, Bias-added and arranged Input for the Computation of S
PreInput = new double[Height * Width * MiniBatchSize, FilterSize *FilterSize *InputDims_ZofPreviousLayer.GetLength(2) / MiniBatchSize + Bias];
//S is the matrix that holds the inputs to this layer
S = new double[Height * Width * MiniBatchSize, Depth];
//W is the ingoing rotated weight matrix for this layer inclusive a Bias for each Kernel
W = new double[FilterSize * FilterSize * InputDims_ZofPreviousLayer.GetLength(2) / MiniBatchSize + Bias, Depth];//Have a look at page 11 in Theory, rotated WeightMatrix for ForewardPass
if (_WeightInitialization == WeightInitialization.NormalizedGaussianRandom)
{
double mean = 0;
double stdDev = 1;
for (int i = 0; i < W.GetLength(0); i++)
{
for (int j = 0; j < W.GetLength(1); j++)
{
//W[i, j] = rnd.NextDouble() * 2 - 1; //Old initialization of weights
double u1 = 1.0 - rnd.NextDouble(); //uniform(0,1] random doubles
double u2 = 1.0 - rnd.NextDouble();
double randStdNormal = Math.Sqrt(-2.0 * Math.Log(u1)) * Math.Sin(2.0 * Math.PI * u2); //random normal(0,1)
W[i, j] = mean + stdDev * randStdNormal; //random normal(mean,stdDev^2)
}
}
}
else if (_WeightInitialization == WeightInitialization.Random)
{
for (int i = 0; i < W.GetLength(0); i++)
{
for (int j = 0; j < W.GetLength(1); j++)
{
W[i, j] = rnd.NextDouble() * 2 - 1;
}
}
}
//safe previous gradient for adaptive learnrate
dW_t_minus_1 = new double[W.GetLength(0), W.GetLength(1)];
//initialize dW_t_minus_1 as zeros-Matrix
for (int i = 0; i < dW_t_minus_1.GetLength(0); i++)
{
for (int j = 0; j < dW_t_minus_1.GetLength(1); j++)
{
dW_t_minus_1[i, j] = 0;
}
}
//initialaze the AdaptiveLearnRateGain
AdaptiveLearnRateGain = new double[W.GetLength(0), W.GetLength(1)];
//initialize AdaptiveLearnRateGain as ones-Matrix
for (int i = 0; i < AdaptiveLearnRateGain.GetLength(0); i++)
{
for (int j = 0; j < AdaptiveLearnRateGain.GetLength(1); j++)
{
AdaptiveLearnRateGain[i, j] = 1;
}
}
if (TrainAlgorithm == TrainAlgorithm.Adam)
{
//initialize Velocity_Adam as zeros-Matrix
Velocity_Adam = new double[W.GetLength(0), W.GetLength(1)];
//initialize Momentum_Adam as zeros-Matrix
Momentum_Adam = new double[W.GetLength(0), W.GetLength(1)];
}
//Z is the matrix that holds output values
Z = new double[MiniBatchSize, Height *Width *Depth + Bias]; //[Row = MiniBatchSize, Column=NeuronsperChannel*NumberOfChannels+Bias]
//Setting Bias of Z to 1
for (int i = 0; i < Z.GetLength(0); i++) //Z.GetLenght(0) = BatchSize
{
Z[i, Z.GetLength(1) - Bias] = 1;
}
Z_3D = new double[Height, Width, Depth *MiniBatchSize];
//D is the matrix that holds the deltas for this layer
D = new double[Height * Width * MiniBatchSize, Depth];
D_3D = new double[Height, Width, Depth *MiniBatchSize];
//dF is the matrix that holds the derivatives of the activation function
dF = new double[Height * Width * Depth, MiniBatchSize];
}
public Layer(double[,] InputDims_ZofPreviousLayer, int ThisLayersNeurons, int _MiniBatchSize, ActivationFunction _ActivationFunction, WeightInitialization _WeightInitialization, TrainAlgorithm _TrainAlgorithm, double _LearnRate, double _L2_Regularization, double _gradient)//Constructor For HiddenLayer and OutputLayer
{
TrainAlgorithm = _TrainAlgorithm;
MiniBatchSize = _MiniBatchSize;
gradient = _gradient;
L2_Regularization = _L2_Regularization;
LearnRate = _LearnRate;
ActivationFunction = _ActivationFunction;
//S is the matrix that holds the inputs to this layer
S = new double[InputDims_ZofPreviousLayer.GetLength(0), ThisLayersNeurons]; //[Rows=BatchSize,Columns]
//W is the ingoing weight matrix for this layer
W = new double[InputDims_ZofPreviousLayer.GetLength(1), ThisLayersNeurons]; //[Rows=PreviousLayersNeurons + Bias,Columns=ThisLayersNeurons]
if (_WeightInitialization == WeightInitialization.NormalizedGaussianRandom)
{
double mean = 0;
double stdDev = 1;
for (int i = 0; i < W.GetLength(0); i++)
{
for (int j = 0; j < W.GetLength(1); j++)
{
double u1 = 1.0 - rnd.NextDouble(); //uniform(0,1] random doubles
double u2 = 1.0 - rnd.NextDouble();
double randStdNormal = Math.Sqrt(-2.0 * Math.Log(u1)) * Math.Sin(2.0 * Math.PI * u2); //random normal(0,1)
W[i, j] = mean + stdDev * randStdNormal; //random normal(mean,stdDev^2)
}
}
}
else if (_WeightInitialization == WeightInitialization.Random)
{
for (int i = 0; i < W.GetLength(0); i++)
{
for (int j = 0; j < W.GetLength(1); j++)
{
W[i, j] = rnd.NextDouble() * 2 - 1;
}
}
}
//safe previous gradient for adaptive learnrate
dW_t_minus_1 = new double[W.GetLength(0), W.GetLength(1)];
//initialize dW_t_minus_1 as zeros-Matrix
for (int i = 0; i < dW_t_minus_1.GetLength(0); i++)
{
for (int j = 0; j < dW_t_minus_1.GetLength(1); j++)
{
dW_t_minus_1[i, j] = 0;
}
}
//initialaze the AdaptiveLearnRateGain
AdaptiveLearnRateGain = new double[W.GetLength(0), W.GetLength(1)];
//initialize AdaptiveLearnRateGain as ones-Matrix
for (int i = 0; i < AdaptiveLearnRateGain.GetLength(0); i++)
{
for (int j = 0; j < AdaptiveLearnRateGain.GetLength(1); j++)
{
AdaptiveLearnRateGain[i, j] = 1;
}
}
if (TrainAlgorithm == TrainAlgorithm.Adam)
{
//initialize Velocity_Adam as zeros-Matrix
Velocity_Adam = new double[W.GetLength(0), W.GetLength(1)];
//initialize Momentum_Adam as zeros-Matrix
Momentum_Adam = new double[W.GetLength(0), W.GetLength(1)];
}
//Z is the matrix that holds output values
if (GetType() == typeof(HiddenLayer))
{
Z = new double[S.GetLength(0), S.GetLength(1) + Bias]; //[Rows=BatchSize,Columns=ThisLayersNeurons + Bias]
//Setting Bias-Column (= Last Column) of Z to 1
for (int i = 0; i < Z.GetLength(0); i++) //Z.GetLenght(0) = BatchSize
{
Z[i, Z.GetLength(1) - Bias] = 1;
}
}
else//if OutputLayer, there's no Bias on Z
{
this.Z = new double[this.S.GetLength(0), this.S.GetLength(1)];
}
//D is the matrix that holds the deltas for this layer
this.D = new double[this.S.GetLength(1), this.S.GetLength(0)]; //[Rows=ThisLayersNeurons,Columns=BatchSize]
//dF is the matrix that holds the derivatives of the activation function. Bias doesent have a derevative
this.dF = new double[this.S.GetLength(1), this.S.GetLength(0)]; //[Rows=ThisLayersNeurons,Columns=BatchSize]
}
public ConvolutionalLayer(double[,,] InputDims_ZofPreviousLayer, int FilterSize, int Stride, int Depth, int _MiniBatchSize, ActivationFunction _ActivationFunction, WeightInitialization _WeightInitialization, TrainAlgorithm _TrainAlgorithm, double _LearnRate, double _L2_Regularization, double _gradient) : base(InputDims_ZofPreviousLayer, FilterSize, Stride, Depth, _MiniBatchSize, _ActivationFunction, _WeightInitialization, _TrainAlgorithm, _LearnRate, _L2_Regularization, _gradient)
{
}
