Relu6Grad

Stay organized with collections Save and categorize content based on your preferences.
public final class Relu6Grad

Computes rectified linear 6 gradients for a Relu6 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 * (features > 0) * (features < 6)`.
static <T extends TNumber> Relu6Grad<T>
create(Scope scope, Operand<T> gradients, Operand<T> features)
Factory method to create a class wrapping a new Relu6Grad operation.

Inherited Methods

Constants

public static final String OP_NAME

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

Constant Value: "Relu6Grad"

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 * (features > 0) * (features < 6)`.

public static Relu6Grad<T> create (Scope scope, Operand<T> gradients, Operand<T> features)

Factory method to create a class wrapping a new Relu6Grad operation.

Parameters
scope current scope
gradients The backpropagated gradients to the corresponding Relu6 operation.
features The features passed as input to the corresponding Relu6 operation, or its output; using either one produces the same result.
Returns
  • a new instance of Relu6Grad