tensorflow::ops::LRN

#include <nn_ops.h>

Local Response Normalization.

Summary

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).

Arguments:

  • scope: A Scope object
  • input: 4-D.

Optional attributes (see Attrs):

  • depth_radius: 0-D. Half-width of the 1-D normalization window.
  • bias: An offset (usually positive to avoid dividing by 0).
  • alpha: A scale factor, usually positive.
  • beta: An exponent.

Returns:

Constructors and Destructors

LRN(const ::tensorflow::Scope & scope, ::tensorflow::Input input)
LRN(const ::tensorflow::Scope & scope, ::tensorflow::Input input, const LRN::Attrs & attrs)

Public attributes

output

Public functions

node() const
::tensorflow::Node *
operator::tensorflow::Input() const
operator::tensorflow::Output() const

Public static functions

Alpha(float x)
Beta(float x)
Bias(float x)
DepthRadius(int64 x)

Structs

tensorflow::ops::LRN::Attrs

Optional attribute setters for LRN.

Public attributes

output

::tensorflow::Output output

Public functions

LRN

 LRN(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input input
)

LRN

 LRN(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input input,
  const LRN::Attrs & attrs
)

node

::tensorflow::Node * node() const 

operator::tensorflow::Input

 operator::tensorflow::Input() const 

operator::tensorflow::Output

 operator::tensorflow::Output() const 

Public static functions

Alpha

Attrs Alpha(
  float x
)

Beta

Attrs Beta(
  float x
)

Bias

Attrs Bias(
  float x
)

DepthRadius

Attrs DepthRadius(
  int64 x
)