Build nGraph Function

This section illustrates how to construct an nGraph function composed of operations from an available opset. Once created, it can wrap into a CNNNetwork, creating utility for data scientists or app developers to define a deep-learning model in a neutral way that does not depend on existing Deep Learning (DL) frameworks.

Operation Set  opsetX integrates a list of nGraph pre-compiled operations that work for this purpose. In other words, opsetX defines a set of operations for building a graph.

For a complete list of operation sets supported by Inference Engine, see Available Operations Sets.

To add custom nGraph operations to an existing CNNNetwork, see the Add Custom nGraph Operations document.

Below you can find examples on to how build ngraph::Function from the opset3 operations:

#include <ngraph/ngraph.hpp>
#include <ngraph/opsets/opset3.hpp>
std::shared_ptr<ngraph::Function> create_simple_function() {
    // This example shows how to create ngraph::Function
    // Parameter--->Multiply--->Add--->Result
    //    Constant---'          /
    //              Constant---'

    // Create opset3::Parameter operation with static shape
    auto data = std::make_shared<ngraph::opset3::Parameter>(ngraph::element::f32, ngraph::Shape{3, 1, 2});

    auto mul_constant = ngraph::opset3::Constant::create(ngraph::element::f32, ngraph::Shape{1}, {1.5});
    auto mul = std::make_shared<ngraph::opset3::Multiply>(data, mul_constant);

    auto add_constant = ngraph::opset3::Constant::create(ngraph::element::f32, ngraph::Shape{1}, {0.5});
    auto add = std::make_shared<ngraph::opset3::Add>(mul, add_constant);

    // Create opset3::Result operation
    auto res = std::make_shared<ngraph::opset3::Result>(mul);

    // Create nGraph function
    return std::make_shared<ngraph::Function>(ngraph::ResultVector{res}, ngraph::ParameterVector{data});
std::shared_ptr<ngraph::Function> create_advanced_function() {
    // Advanced example with multi output operation
    // Parameter->Split---0-->Result
    //               | `--1-->Relu-->Result
    //               `----2-->Result

    auto data = std::make_shared<ngraph::opset3::Parameter>(ngraph::element::f32, ngraph::Shape{1, 3, 64, 64});

    // Create Constant for axis value
    auto axis_const = ngraph::opset3::Constant::create(ngraph::element::i64, ngraph::Shape{}/*scalar shape*/, {1});

    // Create opset3::Split operation that splits input to three slices across 1st dimension
    auto split = std::make_shared<ngraph::opset3::Split>(data, axis_const, 3);

    // Create opset3::Relu operation that takes 1st Split output as input
    auto relu = std::make_shared<ngraph::opset3::Relu>(split->output(1)/*specify explicit output*/);

    // Results operations will be created automatically based on provided OutputVector
    return std::make_shared<ngraph::Function>(ngraph::OutputVector{split->output(0), relu, split->output(2)}, ngraph::ParameterVector{data});

To wrap it into a CNNNetwork, use:

CNNNetwork net (ng_function);

See Also

  • Available Operation Sets

  • Operation Set `opset1 Specification <doxid-openvino_docs_ops_opset1>`

  • Operation Set `opset2 Specification <doxid-openvino_docs_ops_opset2>`

  • Operation Set `opset3 Specification <doxid-openvino_docs_ops_opset3>`

  • Operation Set `opset4 Specification <doxid-openvino_docs_ops_opset4>`

  • Inference Engine Extensibility Developer Guide