DYNAMIC_OUTPUT

Function Prototype

DYNAMIC_OUTPUT (x, t)

Function Description

Registers the dynamic output information of an operator.

After the dynamic output information is successfully registered, APIs (for creating dynamic output and setting the output description) are generated automatically.

For example, if the dynamic output is d and the data type supported by the operator output is TensorType{DT_FLOAT}, call the DYNAMIC_OUTPUT (d, TensorType{DT_FLOAT}) API. After the dynamic output is successfully registered, the following APIs are automatically generated:

_THIS_TYPE& create_dynamic_output_d(unsigned int num); // Creates dynamic output d, including a number of num inputs.
TensorDesc get_dynamic_output_desc_d(unsigned int index);// Returns description indexth of dynamic output d, including Shape, DataType, and Format.
graphStatus update_dynamic_output_desc_d(unsigned int index, const TensorDesc& tensorDesc);// Updates description indexth of dynamic output d.

Parameter Description

Parameter	Input/Output	Type	Description
x	Input	-	Macro parameter, output name of the operator
t	Input	-	Data type supported by the operator output. One or more data types defined by TensorType are supported. Separate data types with commas (,). For example: TensorType{DT_FLOAT} TensorType({DT_FLOAT, DT_INT8}

Parameter

Input/Output

Type

Description

Input

Macro parameter, output name of the operator

Input

Data type supported by the operator output. One or more data types defined by TensorType are supported. Separate data types with commas (,). For example:

TensorType{DT_FLOAT}

TensorType({DT_FLOAT, DT_INT8}