public override void UpdateSpeeds(double learningRate, double momentumCoefficient, double weightDecayCoefficient)
{
// Should include backpropagation to input in all member layers
convolutionalLayer2.UpdateSpeeds(learningRate, momentumCoefficient, weightDecayCoefficient);
convolutionalLayer2.BackPropagate();
if (nonlinearityType == "ReLU")
{
nonlinearityReLU.BackPropagate();
}
else if (nonlinearityType == "ELU")
{
nonlinearityELU.BackPropagate();
}
convolutionalLayer1.UpdateSpeeds(learningRate, momentumCoefficient, weightDecayCoefficient);
convolutionalLayer1.BackPropagate();
}
public void should_backpropagate_tensor_of_correct_size(int inputSize, int weightLength, int outputSize)
{
// Arrange
_sut = (ConvolutionalLayer) new Net(inputSize, inputSize)
.ConvolutionTranspose(new[] { weightLength, weightLength })
.Layers[0];
var trainingRun = new TrainingRun(1)
{
Input = new float[inputSize, inputSize].ToMatrix(),
Output = _sut.FeedForwards(new float[inputSize, inputSize].ToMatrix()),
OutputError = new float[outputSize, outputSize].ToMatrix()
};
// Act
_sut.BackPropagate(trainingRun);
// Assert
Assert.That(trainingRun.InputError.Size, Is.EqualTo(trainingRun.Input.Size));
}
public void should_backpropagate_tensor_of_correct_kernel_size(int kernelSize)
{
// Arrange
_sut = (ConvolutionalLayer) new Net(1, 1)
.ConvolutionTranspose(new[] { 5, 5 }, kernelSize)
.Layers[0];
var input = new float[, ] {
{ 0 }
}.ToMatrix();
var trainingRun = new TrainingRun(1)
{
Input = input,
Output = _sut.FeedForwards(input),
OutputError = new Tensor(new Size(5, 5, kernelSize), new float[5 * 5 * kernelSize])
};
// Act
_sut.BackPropagate(trainingRun);
// Assert
Assert.That(trainingRun.InputError.Size, Is.EqualTo(trainingRun.Input.Size));
}
