Model

class onnx_ir.Model(graph, *, ir_version, producer_name=None, producer_version=None, domain=None, model_version=None, doc_string=None, functions=(), metadata_props=None)

Parameters:

• graph (Graph)

• ir_version (int)

• producer_name (str | None)

• producer_version (str | None)

• domain (str | None)

• model_version (int | None)

• doc_string (str | None)

• functions (Sequence[Function])

• metadata_props (dict[str, str] | None)

doc_string

domain

graph

ir_version

model_version

producer_name

producer_version

display(*, page=False)

Pretty print the object.

Parameters:

page (bool) – Whether to page the output.

Return type:

None

property functions: dict[tuple[str, str, str], Function]

graphs()

Get all graphs and subgraphs in the model.

This is a convenience method to traverse the model. Consider using onnx_ir.traversal.RecursiveGraphIterator for more advanced traversals on nodes.

Return type:

Iterable[Graph]

property meta: MetadataStore

The metadata store for intermediate analysis.

Write to the metadata_props if you would like the metadata to be serialized to the ONNX proto.

property metadata_props: dict[str, str]

property opset_imports: dict[str, int]