IMPLEMT_INFERFUNC
Applicability
Product |
Supported or Not |
|---|---|
√ |
|
√ |
|
√ |
|
√ |
|
√ |
Header File
#include <graph/operator_reg.h>
Function Usage
Encapsulates the InferShape function of an operator.
The OpType argument passed to this function is a subclass derived from class Operator. An op object of this subclass is automatically generated. The member functions of this subclass can be used to obtain the input and output description methods to implement InferShape.
The member functions of the subclass op object derived from OpType are as follows:
- op.set_input_x(Operator &v, const string &srcName): sets output srcName of operator v to input x of the current operator.
- op.get_input_desc_x(): obtains the description of the input x of the operator and returns an object of the TensorDesc type.
op.update_input_desc_x(const TensorDesc& tensorDesc): updates the description of the input x, including the shape, data type, and format.
- op.get_output_desc_y(): obtains the description of the output y of the operator and returns an object of the TensorDesc type.
- op.update_output_desc_y(const TensorDesc& tensorDesc): updates the description of the output y, including the shape, data type, and format.
- op.get_attr_attr1(AscendString &val): obtains the value of the attribute attr1.
Prototype
1 | IMPLEMT_INFERFUNC(op_name, func_name) |
Parameters
Parameter |
Input/Output |
Description |
|---|---|---|
op_name |
Input |
Operator type. |
func_name |
Input |
User-defined name of the InferShape function. |
Returns
None
Constraints
None