Help Center/ Atlas 300 Application (Model 3000)/ GE API Reference/ Operator Registration APIs/ INPUT
Updated on 2022-03-13 GMT+08:00
View PDF
Share

INPUT

Function Prototype

INPUT (x, t)

Function Description

Registers the input information of an operator.

After the operator input information is successfully registered, APIs (for obtaining the operator input name and setting the operator input description) are generated automatically.

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

static const string name_in_x(); // Returns the input name, that is, x.
_THIS_TYPE& set_input_x(Operator& v, const string& srcName);// Specifies the link between input x and output srcName of the operator object v. The operator object itself is returned.
_THIS_TYPE& set_input_x(Operator& v); // Specifies the link between input x and output 0 of the operator object v. The operator object is returned.
TensorDesc get_input_desc_x(); // Returns the description of input x.
graphStatus update_input_desc_x(const TensorDesc& tensorDesc);// Sets the description of input x, including Shape, DataType, and Format. graphStatus indicates the uint32_t type. If a non-zero value is returned, an error occurs.

Parameter Description

Parameter

Input/Output

Type

Description

x

Input

-

Macro parameter, input name of the operator

t

Input

-

Data type supported by the operator input. 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}

For details about class TensorType, see Description of Class TensorType.

Return Value

None

Exception Handling

None

Restriction

For an operator, the registered input name must be unique.

Description of Class TensorType

Class TensorType defines the data types supported by the input or output. The following APIs are provided:

  • TensorType(DataType dt): Specifies that only one data type is supported.
  • TensorType(std::initializer_list<DataType> types): Specifies that multiple data types are supported.
  • static TensorType ALL(): Specifies that all data types are supported.
  • static TensorType FLOAT(): Specifies that the DT_FLOAT and DT_FLOAT16 data types are supported.