SetInputValues(Var InputValues: Array);
SetInputValues(Var InputValues: System.Array);
InputValues. Real array of network input values.
The SetInputValues method assigns network input values.
Input values should be assigned before network calculation.
The number of the elements of the InputValues array must correspond to the number of network inputs. If the number of elements and the number of inputs do not correspond to each other, exception is thrown while the SetInputValues method is executed.
As an example, a function is given, which input has neural network fed into (the Net parameter). To execute the example, add a link to the NN system assembly.
Function n_SetInputValues(Net: NeuralNetwork): NeuralNetwork;
Var
InputVal: Array Of Double;
i: Integer;
Begin
InputVal := Net.GetInputValues;
For i := 0 To InputVal.Length - 1 Do
InputVal[i] := InputVal[i] + 0.02 * (i + 1);
End For;
Net.SetInputValues(InputVal);
net.ApplyConvexCombinationFactor(0.5);
Return Net;
End Function n_SetInputValues;
After executing the example the network input values are enlarged. Convex combinatorial transformation is also applied to them.
As an example, a function is given, which input has neural network fed into (the Net parameter).
Imports Prognoz.Platform.Interop.NN;
…
Public Shared Function n_SetInputValues(Net: NeuralNetwork): NeuralNetwork;
Var
InputVal: System.Array;
i: Integer;
Begin
InputVal := Net.GetInputValues();
For i := 0 To InputVal.Length - 1 Do
InputVal[i] := (InputVal[i] As Double) + 0.02 * (i + 1);
End For;
Net.SetInputValues(Var InputVal);
net.ApplyConvexCombinationFactor(0.5);
Return Net;
End Function n_SetInputValues;
After executing the example the network input values are enlarged. Convex combinatorial transformation is also applied to them.
See also: