public override void ComputeOutput()
{
FilteredImageChannel[] channels = new FilteredImageChannel[FilterNumber];
FilteredImage img = (FilteredImage)PreviousLayer.GetData();
bool samePadding = (Padding == "same") ? true : false;
Task[] tasks = new Task[FilterNumber];
for (int i = 0; i < FilterNumber; i++)
{
int taski = 0 + i;
tasks[taski] = Task.Run(() =>
{
channels[taski] = Filters[taski].Convolve(img, samePadding);
});
}
Task.WaitAll(tasks);
//for (int i = 0; i < FilterNumber; i++)
//{
// channels[i] = Filters[i].Convolve(img, samePadding);
//}
OutputBeforeActivation = new FilteredImage(FilterNumber, channels);
OutputImage = ActivationFunction.Activate(OutputBeforeActivation);
}
public Array3D FormOutput(Array3D input)
{
var output = new Array3D(Neurals.Count);
for (var i = 0; i < output.Count; i++)
{
var summ = Neurals[i].FormOutput(input);
output[i] = ActivationFunction.Activate(summ);
}
return(output);
}
private void Convolution(Array3D input, Array3D ouput)
{
foreach (var filter in Neurals)
{
var result = new Array2D(ouput.Height, ouput.Width);
for (var i = 0; i <= input.Height - filter.Weights.Height; i += Stride)
{
for (var j = 0; j <= input.Width - filter.Weights.Width; j += Stride)
{
var output = Array3D.Merge(input, filter.Weights, i, j) + filter.Bias;
result[i / Stride, j / Stride] = ActivationFunction.Activate(output);
}
}
ouput.Insert(result);
}
}
public override void ComputeOutput()
{
FlattenedImage previous = (FlattenedImage)PreviousLayer.GetData();
Task[] tasks = new Task[NumberOfUnits];
for (int i = 0; i < NumberOfUnits; i++)
{
int taski = 0 + i;
tasks[taski] = Task.Run(() =>
{
Output.Values[taski] = Units[taski].ComputeOutput(previous);
});
}
Task.WaitAll(tasks);
Output = ActivationFunction.Activate(Output);
}
public MatrixFloat Activate()
{
return((Neurons + _bias).Apply((x) => ActivationFunction.Activate(x)));
}
public Array3D FormOutput(Array3D input)
{
var output = ActivationFunction.Activate(input);
return(output);
}