Have a question? Connect with the community at the TensorFlow Forum Visit Forum

LocalResponseNormalization

public final class LocalResponseNormalization

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 Classes

class LocalResponseNormalization.Options Optional attributes for LocalResponseNormalization

Constants

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

Public Methods

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

Inherited Methods

Constants

public static final String OP_NAME

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

Constant Value: "LRN"

Public Methods

public static LocalResponseNormalization.Options alpha (Float alpha)

Parameters
alpha A scale factor, usually positive.

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 static LocalResponseNormalization.Options beta (Float beta)

Parameters
beta An exponent.

public static LocalResponseNormalization.Options bias (Float bias)

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

public static LocalResponseNormalization <T> create ( Scope scope, Operand <T> input, Options... options)

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

Parameters
scope current scope
input 4-D.
options carries optional attributes values
Returns
  • a new instance of LocalResponseNormalization

public static LocalResponseNormalization.Options depthRadius (Long depthRadius)

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

public Output <T> output ()