tensorflow::ops::LRN::Attrs

#include <nn_ops.h>

Optional attribute setters for LRN.

Summary

Public attributes

alpha_ = 1.0f
float
beta_ = 0.5f
float
bias_ = 1.0f
float
depth_radius_ = 5
int64

Public functions

Alpha(float x)
TF_MUST_USE_RESULT Attrs
A scale factor, usually positive.
Beta(float x)
TF_MUST_USE_RESULT Attrs
An exponent.
Bias(float x)
TF_MUST_USE_RESULT Attrs
An offset (usually positive to avoid dividing by 0).
DepthRadius(int64 x)
TF_MUST_USE_RESULT Attrs
0-D.

Public attributes

alpha_

float tensorflow::ops::LRN::Attrs::alpha_ = 1.0f

beta_

float tensorflow::ops::LRN::Attrs::beta_ = 0.5f

bias_

float tensorflow::ops::LRN::Attrs::bias_ = 1.0f

depth_radius_

int64 tensorflow::ops::LRN::Attrs::depth_radius_ = 5

Public functions

Alpha

TF_MUST_USE_RESULT Attrs tensorflow::ops::LRN::Attrs::Alpha(
  float x
)

A scale factor, usually positive.

Defaults to 1

Beta

TF_MUST_USE_RESULT Attrs tensorflow::ops::LRN::Attrs::Beta(
  float x
)

An exponent.

Defaults to 0.5

Bias

TF_MUST_USE_RESULT Attrs tensorflow::ops::LRN::Attrs::Bias(
  float x
)

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

Defaults to 1

DepthRadius

TF_MUST_USE_RESULT Attrs tensorflow::ops::LRN::Attrs::DepthRadius(
  int64 x
)

0-D.

Half-width of the 1-D normalization window.

Defaults to 5