static void Main(string[] args)
{
var model = new Sequential();
var dense = new Dense(units: 5, input_dim: 5,
kernel_initializer: new Constant(Matrix.Identity(5)),
bias_initializer: new Constant(0));
model.Add(dense);
float[,] input = Vector.Range(25).Reshape(5, 5).ToSingle();
float[,] output = MatrixEx.To <float[, ]>(model.predict(input)[0]);
}
public void conv_bias(string backend)
{
KerasSharp.Backends.Current.Switch(backend);
var model = new Sequential();
var dense = new Dense(units: 5, input_dim: 5,
kernel_initializer: new Constant(Matrix.Identity(5)),
bias_initializer: new Constant(42));
model.Add(dense);
float[,] input = Vector.Range(25).Reshape(5, 5).ToSingle();
float[,] output = MatrixEx.To <float[, ]>(model.predict(input)[0]);
Assert.IsTrue(input.Add(42).IsEqual(output, 1e-8f));
}
private Constant _constant <T>(T value, int?[] shape, DataType?dtype, string name)
{
if (value is Array)
{
NDArrayView x = In((value as Array).Convert(dtype.ToType()));
if (name != null)
{
return(new Constant(x, name));
}
else
{
return(new Constant(x));
}
}
if (value is double)
{
return(Constant.Scalar <double>(MatrixEx.To <double>(value), device: DeviceDescriptor.CPUDevice));
}
if (value is float)
{
return(Constant.Scalar <double>(MatrixEx.To <float>(value), device: DeviceDescriptor.CPUDevice));
}
if (name == null)
{
return(new Constant(shape: InShape(shape),
dataType: In(dtype.Value),
initValue: (dynamic)value,
device: DeviceDescriptor.CPUDevice));
}
return(new Constant(shape: InShape(shape),
dataType: In(dtype.Value),
initValue: (dynamic)value,
device: DeviceDescriptor.CPUDevice,
name: name));
}
