Softmax¶

General¶

Softmax operation applies following formula on every element of $$\src$$ tensor (the variable names follow the standard Naming Conventions):

$dst_i = \frac{exp(src_i)}{\sum_{j=1}^{C} exp(src_j)}$

where $$C$$ is a size of tensor along axis dimension.

Operation attributes¶

Attribute Name

Descr

axis

Represents the axis of which the Softmax is calculated.

s64

Arbitrary s64 value ( 1 in 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

Outputs¶

Index

Argu

0

dst

Required

Supported data types¶

Softmax operation supports the following data type combinations.

Src

D

f32

f32

bf16

bf16

f16

f16