BatchNormInference¶

General¶

The formula is the same as Batch Normalization primitive like below.

$\dst(n, c, h, w) = \gamma(c) \cdot \frac{\src(n, c, h, w) - \mu(c)} {\sqrt{\sigma^2(c) + \varepsilon}} + \beta(c),$

where

• $$\gamma(c), \beta(c)$$ are required scale and shift for a channel,

• $$\mu(c), \sigma^2(c)$$ are mean and variance for a channel, and

• $$\varepsilon$$ is a constant to improve numerical stability.

Operation attributes¶

Attribute Name

De

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 below index order when constructing an operation.

Inputs¶

Index

Argu

0

src

Required

1

gamma

Required

2

beta

Required

3

mean

Required

4

variance ( $$\sigma^2$$ )

Required

Outputs¶

Index

Argu

0

dst

Required

Supported data types¶

BatchNormInference operation supports the following data type combinations.

Src /

f32

f32

bf16

f32, bf16

f16

f32