Files
openvino/docs/IE_DG/nGraphTutorial.md
Alina Alborova 9ba4db7eae [Cherrypick] Remove the deprecation notice (#2408)
* cherry-pick 1/2

* Removed deprecation notice
2020-09-30 20:32:25 +03:00

1.6 KiB

Build a Model with nGraph Library

This section illustrates how to construct an nGraph function composed of operations from the opset3 namespace. 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.

Now that you can build graphs with anything from the opset3 definition, some parameters for shape-relevant (or shape-specific) inputs can be added. The following code prepares a graph for shape-relevant parameters.

Note

: validate_nodes_and_infer_types(ops) must be included for partial shape inference.

@snippet openvino/docs/snippets/nGraphTutorial.cpp part0

To wrap it into a CNNNetwork, use:

@snippet openvino/docs/snippets/nGraphTutorial.cpp part1

See Also