helper¶

class onnx_extended.onnx2.helper.TensorDtypeMap(np_dtype, storage_dtype, name)[source]¶

name: str¶: Alias for field number 2

np_dtype: dtype¶: Alias for field number 0

storage_dtype: int¶: Alias for field number 1

onnx_extended.onnx2.helper.get_attribute_value(attr: AttributeProto) → Any[source]¶: Returns the attribute value whatever the type is.

onnx_extended.onnx2.helper.make_attribute(key: str, value: Any, doc_string: str | None = None, attr_type: int | None = None) → AttributeProto[source]¶: Makes an AttributeProto based on the value type.

onnx_extended.onnx2.helper.make_attribute_ref(name: str, attr_type: AttributeType, doc_string: str | None = None) → AttributeProto[source]¶: Makes an AttributeProto holding a reference to the parent ” function’s attribute of given name and type.

onnx_extended.onnx2.helper.make_empty_tensor_value_info(name: str) → ValueInfoProto[source]¶: Creates an empty tensor value info.

onnx_extended.onnx2.helper.make_function(domain: str, fname: str, inputs: Sequence[str], outputs: Sequence[str], nodes: Sequence[NodeProto], opset_imports: Sequence[OperatorSetIdProto], attributes: Sequence[str] | None = None, attribute_protos: Sequence[AttributeProto] | None = None, doc_string: str | None = None, overload: str | None = None, value_info: Sequence[ValueInfoProto] | None = None) → FunctionProto[source]¶

Constructs a FunctionProto.

Parameters:

domain – domain name
fname – function name
inputs – input names
outputs – output names
nodes – sequence of NodeProto
opset_imports – required domains (opset_import)
attributes – attribute names
attribute_protos – typed attributes
doc_string – documentation
overload – overload
value_info – information about type and shape for results

Returns:

a FunctionProto

onnx_extended.onnx2.helper.make_graph(nodes: Sequence[NodeProto], name: str, inputs: Sequence[ValueInfoProto], outputs: Sequence[ValueInfoProto], initializer: Sequence[TensorProto] | None = None, doc_string: str | None = None, value_info: Sequence[ValueInfoProto] | None = None, sparse_initializer: Sequence[SparseTensorProto] | None = None) → GraphProto[source]¶

Constructs a GraphProto

Args:: nodes: list of NodeProto name (string): graph name inputs: list of ValueInfoProto outputs: list of ValueInfoProto initializer: list of TensorProto doc_string (string): graph documentation value_info: list of ValueInfoProto sparse_initializer: list of SparseTensorProto
Returns:: GraphProto

onnx_extended.onnx2.helper.make_map_type_proto(key_type: int, value_type: TypeProto) → TypeProto[source]¶: Makes a map TypeProto.

onnx_extended.onnx2.helper.make_model(graph: GraphProto, ir_version: int = 11, opset_imports: Sequence[OperatorSetIdProto] | None = None, functions: Sequence[FunctionProto] | None = None, metadata_props: Sequence[StringStringEntryProto] | None = None, doc_string: str | None = None, producer_name: str | None = None, producer_version: str | None = None) → ModelProto[source]¶

Constructs a ModelProto

Parameters:

graph – GraphProto
ir_version – ir version, use the default one if missing
opset_imports – required domains, use the default one if missing
functions – list of functions
metadata_props – additional information
producer_name – producer name
producer_version – producer version
doc_string – documentation

Returns:

model

onnx_extended.onnx2.helper.make_node(op_type: str, inputs: Sequence[str], outputs: Sequence[str], name: str | None = None, doc_string: str | None = None, domain: str | None = None, overload: str | None = None, **kwargs: Any) → NodeProto[source]¶

Constructs a NodeProto.

Parameters:

op_type – (string): The name of the operator to construct
inputs – (list of string): list of input names
outputs – (list of string): list of output names
name – (string, default None): optional unique identifier for NodeProto
doc_string – (string, default None): optional documentation string for NodeProto
domain – (string, default None): optional domain for NodeProto. If it’s None, we will just use default domain (which is empty)
overload – (string, default None): optional field, used to resolve calls to model-local functions
kwargs – (dict): the attributes of the node. The acceptable values are documented in make_attribute().

Returns:

NodeProto

onnx_extended.onnx2.helper.make_operatorsetid(domain: str, version: int) → OperatorSetIdProto[source]¶

Construct an OperatorSetIdProto.

Args:: domain (string): The domain of the operator set id version (integer): Version of operator set id
Returns:: OperatorSetIdProto

onnx_extended.onnx2.helper.make_opsetid(domain: str, version: int) → OperatorSetIdProto[source]¶

Constructs an OperatorSetIdProto.

Args:: domain (string): The domain of the operator set id version (integer): Version of operator set id
Returns:: OperatorSetIdProto

onnx_extended.onnx2.helper.make_optional_type_proto(inner_type_proto: TypeProto) → TypeProto[source]¶: Makes an optional TypeProto.

onnx_extended.onnx2.helper.make_sequence_type_proto(inner_type_proto: TypeProto) → TypeProto[source]¶: Makes a sequence TypeProto.

onnx_extended.onnx2.helper.make_sparse_tensor(values: TensorProto, indices: TensorProto, dims: Sequence[int]) → SparseTensorProto[source]¶

Construct a SparseTensorProto

Args:: values (TensorProto): the values indices (TensorProto): the indices dims: the shape
Returns:: SparseTensorProto

onnx_extended.onnx2.helper.make_sparse_tensor_type_proto(elem_type: int, shape: Sequence[str | int | None] | None, shape_denotation: list[str] | None = None) → TypeProto[source]¶: Makes a SparseTensor TypeProto based on the data type and shape.

onnx_extended.onnx2.helper.make_sparse_tensor_value_info(name: str, elem_type: int, shape: Sequence[str | int | None] | None, doc_string: str = '', shape_denotation: list[str] | None = None) → ValueInfoProto[source]¶: Makes a SparseTensor ValueInfoProto based on the data type and shape.

onnx_extended.onnx2.helper.make_tensor(name: str, data_type: int, dims: Sequence[int], vals: Sequence[int | float] | bytes | ndarray, raw: bool = False) → TensorProto[source]¶

Makes a TensorProto with specified arguments. If raw is False, this function will choose the corresponding proto field to store the values based on data_type. If raw is True, use “raw_data” proto field to store the values, and values should be of type bytes in this case.

Parameters:

name – tensor name
data_type – a value such as TensorProto.FLOAT
dims – shape
vals – values
raw – if True, vals contains the serialized content of the tensor, otherwise, vals should be a list of values of the type defined by data_type.

Returns:

TensorProto

onnx_extended.onnx2.helper.make_tensor_sequence_value_info(name: str, elem_type: int, shape: Sequence[str | int | None] | None, doc_string: str = '', elem_shape_denotation: list[str] | None = None) → ValueInfoProto[source]¶: Makes a Sequence[Tensors] ValueInfoProto based on the data type and shape.

onnx_extended.onnx2.helper.make_tensor_type_proto(elem_type: int, shape: Sequence[str | int | None] | None, shape_denotation: list[str] | None = None) → TypeProto[source]¶: Makes a Tensor TypeProto based on the data type and shape.

onnx_extended.onnx2.helper.make_tensor_value_info(name: str, elem_type: int, shape: Sequence[str | int | None] | None, doc_string: str = '', shape_denotation: list[str] | None = None) → ValueInfoProto[source]¶: Makes a ValueInfoProto based on the data type and shape.

onnx_extended.onnx2.helper.make_value_info(name: str, type_proto: TypeProto, doc_string: str = '') → ValueInfoProto[source]¶: Makes a ValueInfoProto with the given type_proto.

onnx_extended.onnx2.helper.set_metadata_props(proto: ModelProto | GraphProto | FunctionProto | NodeProto | TensorProto | ValueInfoProto, dict_value: dict[str, str]) → None[source]¶: Sets metadata_props.

onnx_extended.onnx2.helper.set_model_props(model: ModelProto, dict_value: dict[str, str]) → None[source]¶: Sets metadata_props.

onnx_extended.onnx2.helper.tensor_dtype_to_field(tensor_dtype: int) → str[source]¶

Converts a TensorProto’s data_type to corresponding field name for storage. It can be used while making tensors.

Args:: tensor_dtype: TensorProto’s data_type
Returns:: field name

onnx_extended.onnx2.helper.tensor_dtype_to_np_dtype(tensor_dtype: int) → dtype[source]¶

Converts a TensorProto’s data_type to corresponding numpy dtype. It can be used while making tensor.

Args:: tensor_dtype: TensorProto’s data_type
Returns:: numpy’s data_type