org.tensorflow.op.core

Class LRNGrad<T extends Number>

java.lang.Object

org.tensorflow.op.PrimitiveOp

org.tensorflow.op.core.LRNGrad<T>

Type Parameters:

T - data type for output() output

All Implemented Interfaces:

Op, Operand<T>

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

Gradients for Local Response Normalization.

Nested Class Summary

Nested Classes

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

Field Summary

Fields inherited from class org.tensorflow.op.PrimitiveOp

operation

Method Summary

Modifier and Type	Method and Description
static LRNGrad.Options	alpha(Float alpha)
Output<T>	asOutput() Returns the symbolic handle of a tensor.
static LRNGrad.Options	beta(Float beta)
static LRNGrad.Options	bias(Float bias)
static <T extends Number> LRNGrad<T>	create(Scope scope, Operand<T> inputGrads, Operand<T> inputImage, Operand<T> outputImage, LRNGrad.Options... options) Factory method to create a class to wrap a new LRNGrad operation to the graph.
static LRNGrad.Options	depthRadius(Long depthRadius)
Output<T>	output() The gradients for LRN.

Methods inherited from class org.tensorflow.op.PrimitiveOp

equals, hashCode, toString

Methods inherited from class java.lang.Object

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

Method Detail

create

public static <T extends Number> LRNGrad<T> create(Scope scope,
                                                   Operand<T> inputGrads,
                                                   Operand<T> inputImage,
                                                   Operand<T> outputImage,
                                                   LRNGrad.Options... options)

Factory method to create a class to wrap a new LRNGrad operation to the graph.

Parameters:

scope - current graph scope

inputGrads - 4-D with shape `[batch, height, width, channels]`.

inputImage - 4-D with shape `[batch, height, width, channels]`.

outputImage - 4-D with shape `[batch, height, width, channels]`.

options - carries optional attributes values

Returns:

a new instance of LRNGrad

depthRadius

public static LRNGrad.Options depthRadius(Long depthRadius)

Parameters:

depthRadius - A depth radius.

bias

public static LRNGrad.Options bias(Float bias)

Parameters:

bias - An offset (usually > 0 to avoid dividing by 0).

alpha

public static LRNGrad.Options alpha(Float alpha)

Parameters:

alpha - A scale factor, usually positive.

beta

public static LRNGrad.Options beta(Float beta)

Parameters:

beta - An exponent.

output

public Output<T> output()

The gradients for LRN.

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)