This can be seen as a softplus applied to the scaled input, with the output
appropriately scaled. As alpha tends to 0, scaled_softplus(x, alpha) tends
to relu(x). The clipping is optional. As alpha->0, scaled_softplus(x, alpha)
tends to relu(x), and scaled_softplus(x, alpha, clip=6) tends to relu6(x).
A Tensor of inputs.
A Tensor, indicating the amount of smoothness. The caller
must ensure that alpha > 0.
(optional) A Tensor, the upper bound to clip the values.
A name for the scope of the operations (optional).
A tensor of the size and type determined by broadcasting of the inputs.