org.tensorflow.op.core

Class LRN<T extends Number>

java.lang.Object

org.tensorflow.op.PrimitiveOp

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

Type Parameters:

T - data type for output() output

All Implemented Interfaces:

Op, Operand<T>

@Operator
public final class LRN<T extends Number>
extends PrimitiveOp
implements Operand<T>

Local Response Normalization.

The 4-D `input` tensor is treated as a 3-D array of 1-D vectors (along the last dimension), and each vector is normalized independently. Within a given vector, each component is divided by the weighted, squared sum of inputs within `depth_radius`. In detail,

sqr_sum[a, b, c, d] = sum(input[a, b, c, d - depth_radius : d + depth_radius + 1] ** 2) output = input / (bias + alpha * sqr_sum) ** beta

For details, see [Krizhevsky et al., ImageNet classification with deep convolutional neural networks (NIPS 2012)](http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks).

Nested Class Summary

Nested Classes

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

Field Summary

Fields inherited from class org.tensorflow.op.PrimitiveOp

operation

Method Summary

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

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> LRN<T> create(Scope scope,
                                               Operand<T> input,
                                               LRN.Options... options)

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

Parameters:

scope - current graph scope

input - 4-D.

options - carries optional attributes values

Returns:

a new instance of LRN

depthRadius

public static LRN.Options depthRadius(Long depthRadius)

Parameters:

depthRadius - 0-D. Half-width of the 1-D normalization window.

bias

public static LRN.Options bias(Float bias)

Parameters:

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

alpha

public static LRN.Options alpha(Float alpha)

Parameters:

alpha - A scale factor, usually positive.

beta

public static LRN.Options beta(Float beta)

Parameters:

beta - An exponent.

output

public Output<T> output()

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)