BatchNormInference#

The formula is the same as Batch Normalization primitive :ref:`batch_normalization-label like below.

dst(n,c,h,w)=γ(c)src(n,c,h,w)μ(c)σ2(c)+ε+β(c),

where

  • γ(c),β(c) are required scale and shift for a channel,

  • μ(c),σ2(c) are mean and variance for a channel, and

  • ε is a constant to improve numerical stability.

Operation Attributes#

Attribute

Name

Description

Value Type

Supported

Values

Required or

Optional

epsilon

A number to be added to the variance to avoid division by zero

f32

A positive float value

Required

data_format

Controls how to interpret the shape of src and dst.

string

NCX, NXC (default)

Optional

Execution Arguments#

The inputs and outputs must be provided according to the below index order when constructing an operation.

Inputs#

Index

Argument Name

Required or Optional

0

src

Required

1

gamma

Required

2

beta

Required

3

mean

Required

4

variance (σ2)

Required

Outputs#

Index

Argument Name

Required or Optional

0

dst

Required

Supported Data Types#

BatchNormInference operation supports the following data type combinations.

Src / Dst

Gamma / Beta / Mean / Variance

f32

f32

bf16

f32, bf16

f16

f32