org.tensorflow.op.data

Class LeakyReluGrad<T extends Number>

java.lang.Object

org.tensorflow.op.PrimitiveOp

org.tensorflow.op.data.LeakyReluGrad<T>

Type Parameters:

T - data type for backprops() output

All Implemented Interfaces:

Op, Operand<T>

public final class LeakyReluGrad<T extends Number>
extends PrimitiveOp
implements Operand<T>

Computes rectified linear gradients for a LeakyRelu operation.

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	LeakyReluGrad.Options Optional attributes for LeakyReluGrad

Field Summary

Fields inherited from class org.tensorflow.op.PrimitiveOp

operation

Method Summary

Modifier and Type	Method and Description
static LeakyReluGrad.Options	alpha(Float alpha)
Output<T>	asOutput() Returns the symbolic handle of a tensor.
Output<T>	backprops() `gradients * (features > 0) + alpha * gradients * (features <= 0)`.
static <T extends Number> LeakyReluGrad<T>	create(Scope scope, Operand<T> gradients, Operand<T> features, LeakyReluGrad.Options... options) Factory method to create a class wrapping a new LeakyReluGrad operation.

Methods inherited from class org.tensorflow.op.PrimitiveOp

equals, hashCode, op, toString

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Method Detail

create

public static <T extends Number> LeakyReluGrad<T> create(Scope scope,
                                                         Operand<T> gradients,
                                                         Operand<T> features,
                                                         LeakyReluGrad.Options... options)

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

Parameters:

scope - current scope

gradients - The backpropagated gradients to the corresponding LeakyRelu operation.

features - The features passed as input to the corresponding LeakyRelu operation, OR the outputs of that operation (both work equivalently).

options - carries optional attributes values

Returns:

a new instance of LeakyReluGrad

alpha

public static LeakyReluGrad.Options alpha(Float alpha)

Parameters:

alpha -

backprops

public Output<T> backprops()

`gradients * (features > 0) + alpha * gradients * (features <= 0)`.

asOutput

public Output<T> asOutput()

Description copied from interface: Operand

Returns the symbolic handle of a 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.

Specified by:

asOutput in interface Operand<T extends Number>

See Also:

OperationBuilder.addInput(Output)