EluGrad

Stay organized with collections Save and categorize content based on your preferences.
public final class EluGrad

Computes gradients for the exponential linear (Elu) operation.

Constants

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

Public Methods

Output<T>
asOutput()
Returns the symbolic handle of the tensor.
Output<T>
backprops()
The gradients: `gradients * (outputs + 1)` if outputs < 0, `gradients` otherwise.
static <T extends TNumber> EluGrad<T>
create(Scope scope, Operand<T> gradients, Operand<T> outputs)
Factory method to create a class wrapping a new EluGrad operation.

Inherited Methods

Constants

public static final String OP_NAME

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

Constant Value: "EluGrad"

Public Methods

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 Output<T> backprops ()

The gradients: `gradients * (outputs + 1)` if outputs < 0, `gradients` otherwise.

public static EluGrad<T> create (Scope scope, Operand<T> gradients, Operand<T> outputs)

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

Parameters
scope current scope
gradients The backpropagated gradients to the corresponding Elu operation.
outputs The outputs of the corresponding Elu operation.
Returns
  • a new instance of EluGrad