Inference Engine Extension API allows to register operation sets (opsets) with custom nGraph operations, it allows to support Networks with unknown operations.
To add your custom nGraph operation, create a new class that extends ngraph::Op
, which is in turn derived from ngraph::Node
, the base class for all graph operations in nGraph. Follow the steps below:
NodeTypeInfo
object that identifies the type of the operation to the graph users and helps with dynamic type resolution. The type info of an nGraph operation currently consists of a string identifier and a version number, but this may change in the future.validate_and_infer_types
. This method is called multiple times during graph manipulations to determine the shapes and element types of the outputs of the operations. You can access the input shapes through the get_input_partial_shape()
method and input element types through the get_input_element_type()
method of ngraph::Node
. Set the inferred shape and element type of the output using set_output_type
.copy_with_new_args
method, which allows graph manipulation routines to create copies of this operation and connect it to different nodes during optimization.visit_attributes
method, which allows serialization and deserialization of attributes. An AttributeVisitor
is passed to the method, and the implementation is expected to walk over all the attributes in the op using the type-aware on_attribute
helper. Helpers are already implemented for standard C++ types like int64_t
, float
, bool
, vector
and for existing nGraph defined types.Based on that, declaration of a operation class can look as follows:
The provided implementation has several fields:
add
of type int64_t
is an attribute of custom operationtype_info
of type ngraph::NodeTypeInfo
defines the type and version of operationnGraph operation contains two constructors: a default constructor, which allows to create operation without attributes and a constructor that creates and validates operation with specified inputs and attributes.
validate_and_infer_types()
ngraph::Node::validate_and_infer_types
method validates operation attributes and calculates output shapes using attributes of operation.
copy_with_new_args()
ngraph::Node::copy_with_new_args
method creates a copy of nGraph operation with new inputs.
visit_attributes()
ngraph::Node::visit_attributes
method allows to visit all operation attributes.
To add custom operations to the Extension class, create an operation set with custom operations and implement the InferenceEngine::IExtension::getOpSets
method:
This method returns a map of opsets that exist in the extension library.
nGraph provides opsets mechanism for operation versioning. Different opsets distinguish between different versions of one operation.
When specifying opset names, follow the rules below:
extension
, experimental
, opset1
, opest2
.version
attribute specifying the opset.opset1
is the name of default operations set. Operations from the default opset cannot be redefined.Use a custom opset to create a new operation or extend functionality of an existing operation from another opset.