Elu

public final class Elu

Computes exponential linear: `exp(features) - 1` if < 0, `features` otherwise.

See [Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) ](http://arxiv.org/abs/1511.07289)

Constants

String OP_NAME The name of this op, as known by TensorFlow core engine

Public Methods

Output<T>
activations()
Output<T>
asOutput()
Returns the symbolic handle of the tensor.
static <T extends TNumber> Elu<T>
create(Scope scope, Operand<T> features)
Factory method to create a class wrapping a new Elu operation.

Inherited Methods

Constants

public static final String OP_NAME

The name of this op, as known by TensorFlow core engine

Constant Value: "Elu"

Public Methods

public Output<T> activations ()

public Output<T> asOutput ()

Returns the symbolic handle of the tensor.

Inputs to TensorFlow operations are outputs of another TensorFlow operation. This method is used to obtain a symbolic handle that represents the computation of the input.

public static Elu<T> create (Scope scope, Operand<T> features)

Factory method to create a class wrapping a new Elu operation.

Parameters
scope current scope
Returns
  • a new instance of Elu