private List <Data> GenerateTrainingData(int samples, Shape inShape, Tensor expectedParams, TrainDataFunc f)
{
List <Data> trainingData = new List <Data>();
for (int i = 0; i < samples; ++i)
{
var input = new Tensor(inShape);
input.FillWithRand(3 * i);
trainingData.Add(new Data(input, f(input, expectedParams)));
}
return(trainingData);
}
private void TestConvolutionLayer(Shape inputShape, int kernelSize, int kernelsNum, int stride, int samples, int batchSize, int epochs, TrainDataFunc convFunc)
{
var net = new NeuralNetwork("convolution_test", 7);
var model = new Sequential();
model.AddLayer(new Convolution(inputShape, kernelSize, kernelsNum, stride, Activation.Linear)
{
KernelInitializer = new Initializers.Constant(1)
});
net.Model = model;
var expectedKernels = new Tensor(new Shape(kernelSize, kernelSize, inputShape.Depth, kernelsNum));
expectedKernels.FillWithRand(17);
var tData = GenerateTrainingData(samples, model.LastLayer.InputShape, expectedKernels, convFunc);
net.Optimize(new SGD(0.02f), Loss.MeanSquareError);
net.Fit(tData, batchSize, epochs, null, 0, Track.Nothing);
var paramsAndGrads = model.LastLayer.GetParametersAndGradients();
for (int i = 0; i < expectedKernels.Length; ++i)
{
Assert.AreEqual(paramsAndGrads[0].Parameters.GetFlat(i), expectedKernels.GetFlat(i), 1e-2);
}
}
