org.tensorflow.op.nn

Class LocalResponseNormalization<T extends TNumber>

java.lang.Object

org.tensorflow.op.RawOp

org.tensorflow.op.nn.LocalResponseNormalization<T>

Type Parameters:

T - data type for output output

All Implemented Interfaces:

org.tensorflow.ndarray.Shaped, Op, Operand<T>

@Operator(group="nn")
public final class LocalResponseNormalization<T extends TNumber>
extends RawOp
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) .

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	LocalResponseNormalization.Inputs<T extends TNumber>
static class	LocalResponseNormalization.Options Optional attributes for LocalResponseNormalization

Field Summary

Fields

Modifier and Type	Field and Description
static String	OP_NAME The name of this op, as known by TensorFlow core engine

Fields inherited from class org.tensorflow.op.RawOp

operation

Constructor Summary

Constructors

Constructor and Description
LocalResponseNormalization(Operation operation)

Method Summary

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

Methods inherited from class org.tensorflow.op.RawOp

equals, hashCode, op, toString

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.tensorflow.Operand

asTensor, shape, type

Methods inherited from interface org.tensorflow.op.Op

env, op

Methods inherited from interface org.tensorflow.ndarray.Shaped

rank, size

Field Detail

OP_NAME

public static final String OP_NAME

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

See Also:

Constant Field Values

Constructor Detail

LocalResponseNormalization

public LocalResponseNormalization(Operation operation)

Method Detail

create

@Endpoint(describeByClass=true)
public static <T extends TNumber> LocalResponseNormalization<T> create(Scope scope,
                                                                                                       Operand<T> input,
                                                                                                       LocalResponseNormalization.Options... options)

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

Type Parameters:

T - data type for LRN output and operands

Parameters:

scope - current scope

input - 4-D.

options - carries optional attribute values

Returns:

a new instance of LocalResponseNormalization

depthRadius

public static LocalResponseNormalization.Options depthRadius(Long depthRadius)

Sets the depthRadius option.

Parameters:

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

Returns:

this Options instance.

bias

public static LocalResponseNormalization.Options bias(Float bias)

Sets the bias option.

Parameters:

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

Returns:

this Options instance.

alpha

public static LocalResponseNormalization.Options alpha(Float alpha)

Sets the alpha option.

Parameters:

alpha - A scale factor, usually positive.

Returns:

this Options instance.

beta

public static LocalResponseNormalization.Options beta(Float beta)

Sets the beta option.

Parameters:

beta - An exponent.

Returns:

this Options instance.

output

public Output<T> output()

Gets output.

Returns:

output.

asOutput

public Output<T> asOutput()

Description copied from interface: Operand

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.

Specified by:

asOutput in interface Operand<T extends TNumber>

See Also:

OperationBuilder.addInput(Output)