Value

class onnx_ir.Value(producer=None, *, index=None, name=None, shape=None, type=None, doc_string=None, const_value=None, metadata_props=None)

IR Value.

A value is a named entity that can be used to represent an input or output of a graph, a function, or a node. The information it stores generalizes over ValueInfoProto in the ONNX specification.

A Value is always not owned or owned by exactly one node. When the value is not owned, it must be an input of a graph or a function. producer and index are None.

When the value is owned by a node, it is an output of the node. The node that produces the value can be accessed with producer(). The index of the output of the node that produces the value can be accessed with index().

To find all the nodes that use this value as an input, call uses(). Consuming nodes can be obtained with consumers().

To check if the value is an is an input, output or initializer of a graph, use is_graph_input(), is_graph_output() or is_initializer().

Use graph to get the graph that owns the value.

Parameters:

• producer (Node | None)

• index (int | None)

• name (str | None)

• shape (Shape | None)

• type (_protocols.TypeProtocol | None)

• doc_string (str | None)

• const_value (_protocols.TensorProtocol | None)

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

doc_string

property const_value: TensorProtocol | None

The backing constant tensor for the value.

If the Value has a const_value and is part of a graph initializers dictionary, the value is an initialized value. Its const_value will appear as an initializer in the GraphProto when serialized.

If the Value is not part of a graph initializers dictionary, the const_value field will be ignored during serialization.

const_value can be backed by different raw data types, such as numpy arrays. The only guarantee is that it conforms TensorProtocol.

consumers()

Return the nodes (deduplicated) that consume this value.

Return type:

Sequence[Node]

display(*, page=False)

Pretty print the object.

Parameters:

page (bool) – Whether to page the output.

Return type:

None

property dtype: DataType | None

The data type of the tensor.

property graph: Graph | None

Return the graph that defines this value.

When the value is an input/output/initializer of a graph, the owning graph is that graph. When the value is an output of a node, the owning graph is the graph that the node belongs to. When the value is not owned by any graph, it returns None.

index()

The index of the output of the defining node.

Return type:

int | None

is_graph_input()

Whether the value is an input of a graph.

Return type:

bool

is_graph_output()

Whether the value is an output of a graph.

Return type:

bool

is_initializer()

Whether the value is an initializer of a graph.

Return type:

bool

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]

The metadata properties of the value.

The metadata properties are used to store additional information about the value. Unlike meta, this property is serialized to the ONNX proto.

property name: str | None

producer()

The node that produces this value.

When producer is None, the value does not belong to a node, and is typically a graph input or an initializer. You can use graph`() to find the graph that owns this value. Use is_graph_input(), is_graph_output() or is_initializer() to check if the value is an input, output or initializer of a graph.

Return type:

Node | None

replace_all_uses_with(replacement, /, replace_graph_outputs=False)

Replace all uses of this value with another value.

Tip

Handling graph outputs

To also replace graph outputs that reference the values being replaced, either set replace_graph_outputs to True, or manually update the graph outputs before calling this function to avoid an error being raised when replace_graph_outputs=False.

Be careful when a value appears multiple times in the graph outputs - this is invalid. An identity node will need to be added on each duplicated outputs to ensure a valid ONNX graph.

You may also want to assign the name of this value to the replacement value to maintain the name when it is a graph output.

To replace usage of a sequence of values with another sequence of values, consider using onnx_ir.convenience.replace_all_uses_with().

Added in version 0.1.12.

Parameters:

• replacement (Value) – The value to replace all uses with.

• replace_graph_outputs (bool) – If True, graph outputs that reference this value will also be updated to reference the replacement.

Raises:

ValueError – When replace_graph_outputs is False && when the value to replace is a graph output.

Return type:

None

property shape: Shape | None

property type: TypeProtocol | None

The type of the tensor.

Example types can be TensorType, SparseTensorType, SequenceType, OptionalType. To obtain the data type of the tensor, use type.dtype or conveniently dtype.

uses()

Return a set of uses of the value.

The set contains tuples of (Node, index) where the index is the index of the input of the node. For example, if node.inputs[1] == value, then the use is (node, 1).

Return type:

Collection[Usage]