TiyT%SrSSKJr SSKrSSKJr SSKJrJrJ r J r J r J r J r SSKJrJrJr SSKJr \R&(a SSKrSSKJr \\\\4rS \S '\R8"S S \55r\R8"S S\55r\R8"SS\\\55r\R8"SS\55r \R8"SS\55r!\R8"SS\55r"\R8"SS\55r#\R8"SS\55r$\R8"SS\55r%\R8"SS\55r&\R8"SS \55r'\R8"S!S"\55r(\R8"S#S$\55r)\R8"S%S&\55r*\R8"S'S(\55r+\R8"S)S*\55r,g)+aProtocols for the ONNX IR. This file defines the interfaces for tools to interact with the IR. The interfaces are designed such that tools leveraging the IR can be decoupled from the IR implementation. This allows for the implementation to evolve independently of the tools. ) annotationsN) OrderedDict) CollectionIterableIteratorMappingMutableMappingMutableSequenceSequence)AnyLiteralProtocol)_enums) TypeAliasrOperatorIdentifierc"\rSrSrSrSSjrSrg)ArrayCompatible<zProtocol for array-like objects. An example of an array-like object is a numpy ndarray or a PyTorch Tensor. Read more at https://numpy.org/devdocs/user/basics.interoperability.html cgNselfdtypes Q/var/www/html/ai-image-ml/venv/lib/python3.13/site-packages/onnx_ir/_protocols.py __array__ArrayCompatible.__array__Ds3rNrr return np.ndarray)__name__ __module__ __qualname____firstlineno____doc__r__static_attributes__rrrrr<s  7rrc4\rSrSrSrSS.S SjjrS SjrSrg) DLPackCompatibleGzProtocol for objects that can support dlpack. Computation backends can call __dlpack__ to obtain the underlying data in a tensor without copying the data. This allows use to use tensorflow tensors etc. without copying the data. .streamcgzReturn PyCapsule.Nrrr,s r __dlpack__DLPackCompatible.__dlpack__P rcgzReturn the device.Nrrs r__dlpack_device__"DLPackCompatible.__dlpack_device__Tr2rrNr,r r r r r )r"r#r$r%r&r0r6r'rrrr)r)Gs+.  rr)c\rSrSr%SrS\S'S\S'S\S'S\S 'S \S 'S \S 'S\S'\SSj5r\SSj5rSSjr SSSjjr SS.SSjjr S Sjr S!Sjr Srg)"TensorProtocolYaConcrete tensor backed by data. The protocol does not specify how the data is stored. That data is exposed through the :attr:`raw` attribute for examination, but accessing :attr:`raw` is typically not needed. To use the tensor as a numpy array, call :meth:`numpy`. To convert the tensor to a byte string for serialization, call :meth:`tobytes`. It is recommended to check the size of the tensor first before accessing the underlying data, because accessing the data may be expensive and incur IO overhead. Attributes: name: The name of the tensor. shape: The shape of the tensor. dtype: The data type of the elements of the tensor. It is an :class:`ir.DataType` enum. doc_string: Documentation string. raw: The raw data behind this tensor. It can be anything. size: The number of elements in the tensor. nbytes: The number of bytes in the tensor. metadata_props: Metadata that will be serialized to the ONNX file. meta: Metadata store for graph transform passes. str | Nonename ShapeProtocolshape_enums.DataTyper doc_stringr rawMutableMapping[str, str]metadata_propsMutableMapping[str, Any]metacgrrr5s rsizeTensorProtocol.size|srcgrrr5s rnbytesTensorProtocol.nbytess rcg)z#Return the tensor as a numpy array.Nrr5s rnumpyTensorProtocol.numpyr2rNcg)z=Return the tensor as a numpy array, compatible with np.array.Nrrs rrTensorProtocol.__array__r2r.r+cgr.rr/s rr0TensorProtocol.__dlpack__r2rcgr4rr5s rr6 TensorProtocol.__dlpack_device__r2rcg)zYReturn the tensor as a byte string conformed to the ONNX specification, in little endian.Nrr5s rtobytesTensorProtocol.tobytesr2rrr int)r r!rrr8r9)r bytes)r"r#r$r%r&__annotations__propertyrIrLrOrr0r6rXr'rrrr;r;Ysl2    H,, ""      +.   rr;c\rSrSr%SrS\S'S\S'S\S'S \S 'S \S 'S \S'S\S'SSjrSSjrSSjrSSjr SSSjjr Sr g) ValueProtocolaProtocol for values. 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 :class:`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 :meth:`producer`. The index of the output of the node that produces the value can be accessed with :meth:`index`. To find all the nodes that use this value as an input, call :meth:`uses`. To check if the value is an output of a graph, call :meth:`is_graph_output`. Attributes: name: The name of the value. A value is always named when it is part of a graph. shape: The shape of the value. type: The type of the value. metadata_props: Metadata that will be serialized to the ONNX file. meta: Metadata store for graph transform passes. doc_string: Documentation string. const_value: The constant tensor is the value constant. strr>zShapeProtocol | Noner@zTypeProtocol | NonetyperDrErFrGr=rBzTensorProtocol | None const_valuecg)z"The node that produces this value.Nrr5s rproducerValueProtocol.producerr2rcg)z=The index of the output of the node that produces this value.Nrr5s rindexValueProtocol.indexr2rcg)zUThe set of (node, input_index) with node being those that use this value as an input.Nrr5s rusesValueProtocol.usesr2rcg)z+Whether this value is an output of a graph.Nrr5s ris_graph_outputValueProtocol.is_graph_outputr2rcg)zReplace all uses of this value with the given new value. Args: new_value: The new value to replace this value with. replace_graph_outputs: Whether to replace graph outputs that use this value. Nr)r new_valuereplace_graph_outputss rreplace_all_uses_with#ValueProtocol.replace_all_uses_withs rrN)r zNodeProtocol | None)r int | None)r z$Collection[tuple[NodeProtocol, int]])r bool)F)rrValueProtocol | Nonersrwr None) r"r#r$r%r&r]rfrirlrortr'rrrr`r`so: I  ,, ""&&    NS  -  FJ     rr`c\rSrSr%SrS\S'S\S'S\S'S\S'S \S 'S \S 'S \S 'S\S'S\S'S\S'S\S'SSjrSrg) NodeProtocolaProtocol for nodes. A node represents an invocation of an operation on the :class:`Value` s in the computational graph. A node can be optionally named. A name should typically be assigned when the node is added to a graph. :attr:`domain`, :attr:`op_type`, and :attr:`overload` together uniquely identify the operator, and are always strings. For ONNX operators, :attr:`domain` and :attr:`overload` are both empty strings. :attr:`inputs` and :attr:`outputs` are the input and output values of the node. :attr:`attributes` are the attributes of the node. The attributes are stored in an ordered dictionary to preserve the order of the attributes. This is a deviation from the current ONNX spec where attributes are unordered, but it is helpful for tools that rely on the order of the attributes, e.g. those converting to and from Python function keyword arguments. :attr:`version` is unique to the IR and is not specified in the ONNX spec. This allows the IR to represent a graph with mixed opset versions. Deserializers should decide how to reconcile the different versions within the graph. A typical graph will have a single version, declared in the :class:`Graph` object and the nodes will have ``None`` as the version. Attributes: domain: The domain of the operator. E.g. ``""`` for ONNX operators. op_type: The operator name. overload: The overload name when the node is invoking a function. inputs: Input values. outputs: Output values. attributes: The attributes of the operator. version: The version of the operator. doc_string: Documentation string. metadata_props: Metadata that will be serialized to the ONNX file. meta: Metadata store for graph transform passes. r=r>rbdomainop_typeoverloadSequence[ValueProtocol]inputsoutputsz@OrderedDict[str, AttributeProtocol | ReferenceAttributeProtocol] attributesrvversionrBrDrErFrGcg)zRSet the input at the given index to the given value, replacing the original value.Nrrrivalues rreplace_input_withNodeProtocol.replace_input_withr2rrN)rir[rrxr ry)r"r#r$r%r&r]rr'rrrr{r{sN%N  K LM ## $$PP ,, "" rr{c\rSrSr%SrS\S'S\S'S\S'S\S 'S \S 'S \S 'S\S'S\S'SSjrSSjrS SjrS Sjr S!Sjr S"Sjr S!Sjr S#Sjr S#SjrS$SjrSrg)% GraphProtocoliaCProtocol for graphs. Graph represents a computation graph. In addition to the ONNX specification specified fields, it also contains a mapping of :attr:`opset_imports`. This allows different subgraphs to import different opsets. It is the responsibility of the deserializer to reconcile the different opsets. The nodes are not guaranteed to be topologically sorted. But the iteration order should be deterministic across different runs. It is the responsibility of the user to maintain a topological order of the nodes. Note that there is not a ``node`` attribute in the Graph. The Graph can be seen as a Sequence of nodes and should be used as such. For example, to obtain all nodes as a list, call ``list(graph)``. .. :note:: ``quantization_annotation`` is deserialized into the Value's ``meta`` field under the ``quant_parameter_tensor_names`` key. Values that are stored under this key will be serialized as quantization annotations. Attributes: name: The name of the graph. inputs: The input values of the graph. outputs: The output values of the graph. initializers: The initializers in the graph. doc_string: Documentation string. opset_imports: Opsets imported by the graph. metadata_props: Metadata that will be serialized to the ONNX file. meta: Metadata store for graph transform passes. r=r>zMutableSequence[ValueProtocol]rrz"MutableMapping[str, ValueProtocol] initializersrbrBMutableMapping[str, int] opset_importsrDrErFrGcgrrrris r __getitem__GraphProtocol.__getitem__>srcgrrr5s r__len__GraphProtocol.__len__?crcgrrr5s r__iter__GraphProtocol.__iter__@#rcgrrr5s r __reversed__GraphProtocol.__reversed__Acrcg)zAppend a node to the graph.Nrrnodes rappendGraphProtocol.appendDr2rcg)z&Extend the graph with the given nodes.Nrrnodess rextendGraphProtocol.extendHr2rcg)zRemove a node from the graph.Nrrs rremoveGraphProtocol.removeLr2rcgz&Insert new nodes after the given node.Nrrr new_nodess r insert_afterGraphProtocol.insert_afterP rcgz'Insert new nodes before the given node.Nrrs r insert_beforeGraphProtocol.insert_beforeVrrcg)z*Topologically sort the nodes in the graph.Nrr5s rsortGraphProtocol.sort\r2rrNrir[r r{rZr zIterator[NodeProtocol]rr{r ryrzIterable[NodeProtocol]r ryrr{rz%Iterator[NodeProtocol] | NodeProtocolr ryr ry)r"r#r$r%r&r]rrrrrrrrrrr'rrrrrs>  ** ++44O++,, "":!59      -R     -R   rrc\rSrSr%SrS\S'S\S'S\S'S\S 'S \S 'S \S 'S\S'S\S'SSjrSSjrSSjrSSjr Sr g)GraphViewProtocoliaaProtocol for a read-only view on a graph. The GraphView is useful for analysis of a subgraph. It can be initialized with a subset of nodes from a :class:`Graph`. Creating GraphView does not change the ownership of the nodes, and so it is possible to create multiple GraphViews that contain the same nodes. Attributes: name: The name of the graph. inputs: The input values of the graph. outputs: The output values of the graph. initializers: The initializers in the graph. doc_string: Documentation string. opset_imports: Opsets imported by the graph. metadata_props: Metadata that will be serialized to the ONNX file. meta: Metadata store for graph transform passes. r=r>rrrzMapping[str, ValueProtocol]rrbrBzMapping[str, int]rrDrErFrGcgrrrs rrGraphViewProtocol.__getitem__~rrcgrrr5s rrGraphViewProtocol.__len__rrcgrrr5s rrGraphViewProtocol.__iter__rrcgrrr5s rrGraphViewProtocol.__reversed__rrrNrrZr) r"r#r$r%r&r]rrrrr'rrrrrasD$  ## $$--O$$,, "":!59rrc\rSrSr%SrS\S'S\S'S\S'S\S 'S\S 'S \S 'S\S 'S\S'S\S'S\S'S\S'Srg) ModelProtocolia_Protocol for models. A model is a container for a graph and metadata. It is the top-level object that represents an ONNX model. Attributes: graph: The graph of the model. ir_version: The version of the IR. producer_name: The name of the producer. producer_version: The version of the producer. domain: The domain of the model. model_version: The version of the model. doc_string: Documentation string. functions: The functions defined in the model. metadata_props: Metadata that will be serialized to the ONNX file. meta: Metadata store for graph transform passes. rgraphr[ ir_versionr= producer_nameproducer_versionr}rv model_versionrBz%MutableMapping[str, FunctionProtocol] functionsrrrDrErFrGrNr"r#r$r%r&r]r'rrrrrsJ$ O  44++,, ""rrcL\rSrSr%SrS\S'S\S'S\S'S \S 'SS jrS rg )AttributeProtocolizProtocol for ONNX attributes. Attributes: name: The name of the attribute. type: The type of the attribute. value: The value of the attribute. doc_string: Documentation string. rbr>_enums.AttributeTypercr rr=rBcgrrr5s ris_refAttributeProtocol.is_refsrrN)r zLiteral[False]r"r#r$r%r&r]rr'rrrrrs" I  J+rrcL\rSrSr%SrS\S'S\S'S\S'S\S 'S S jrS rg )ReferenceAttributeProtocoliaDProtocol for a reference attribute. A reference attribute can only appear inside the definition body of a function. Attributes: name: The name of the attribute. ref_attr_name: The name of the attribute definition this attribute refers to. type: The type of the attribute. doc_string: Documentation string. rbr> ref_attr_namerrcr=rBcgrrr5s rr!ReferenceAttributeProtocol.is_refssrrN)r z Literal[True]rrrrrrs#  I *rrc4\rSrSr%S\S'S\S'S\S'Srg) SparseTensorProtocolir;valuesindices Sequence[int]dimsrN)r"r#r$r%r]r'rrrrrs   rrc$\rSrSr%SrS\S'Srg)SymbolicDimProtocolizmValue of a single symbolic/dynamic dimension in a shape. Attributes: value: The value of the dimension. r=rrNrrrrrrs rrc\rSrSr%SrS\S'SSjrSSjr\RSSj5r \RSSj5r SS jr SS jr SS jr SS jrSS jrSSjrSSjrSrg)r?iztProtocol for ONNX shapes. A shape is a sequence of dimensions. Attributes: dims: The dimensions of the shape. z#Sequence[int | SymbolicDimProtocol]rcgrrr5s rrShapeProtocol.__len__rrcgrrr5s rrShapeProtocol.__iter__ssrcgrrrs rrShapeProtocol.__getitem__sDGrcgrrrs rrrsRUrcgrrrs r __setitem__ShapeProtocol.__setitem__srcgrr)rothers r__eq__ShapeProtocol.__eq__Srcgrrrrs r__ne__ShapeProtocol.__ne__rrcgrrrs rget_denotationShapeProtocol.get_denotationsrcgrr)rri denotations rset_denotationShapeProtocol.set_denotations#rcgrrr5s rrOShapeProtocol.numpyscrcgrrr5s rrankShapeProtocol.ranks3rrNrZ)r z#Iterator[int | SymbolicDimProtocol])rir[r zint | SymbolicDimProtocol)rislicer z%tuple[int | SymbolicDimProtocol, ...])rir[rz&int | SymbolicDimProtocol | str | Noner ry)robjectr rwrr r rw)rir[r r=)rir[rr=r ry)r r)r"r#r$r%r&r]rrtypingrrrrrrrrOrr'rrrr?r?sj .-!B __GG __UU!G 10;M)rr?cB\rSrSr%SrS\S'S\S'S\S'S S jrS rg ) TypeProtocolia5Protocol for ONNX tensors, Sequence tensors, Optional tensors and Sparse tensors. These three types of tensors share the same attribute "elem_type" so they are merged in the same interface. Unlike the ONNX TensorProto, shapes are not included in the type and should be stored in the :class:`Value`. Attributes: denotation: An optional denotation can be used to denote the whole type with a standard semantic description as to what is stored inside. Refer to https://github.com/onnx/onnx/blob/main/docs/TypeDenotation.md#type-denotation-definition for pre-defined type denotations. elem_type: The type of its elements for nested types like Sequence[Optional] tensors. Or the DataType if the type is not nested. dtype: The data type of the tensor or the nested tensor. r=rzTypeProtocol | _enums.DataType elem_typerArcgrrrs rrTypeProtocol.__eq__srrNr )r"r#r$r%r&r]rr'rrrr r s"-- 3rr c.\rSrSr%SrS\S'S\S'Srg) MapTypeProtocolizYProtocol for ONNX map types. TODO: This protocol is not yet implemented in the ONNX IR. ztyping.Literal[_enums.DataType.STRING, _enums.DataType.INT64, _enums.DataType.INT32, _enums.DataType.INT16, _enums.DataType.INT8, _enums.DataType.UINT64, _enums.DataType.UINT32, _enums.DataType.UINT16, _enums.DataType.UINT8]key_typerA value_typerNrrrrrrs   rrc\rSrSr%SrS\S'S\S'S\S'S\S'S \S 'S\S 'S\S 'S \S'S\S'S\S'S SjrS!SjrS"SjrS"Sjr S#Sjr S$Sjr S%Sjr S$Sjr S&SjrS&SjrS'SjrSrg)(FunctionProtocoli,aProtocol for ONNX functions. Like a graph, a function can have nodes that are not topologically sorted. It is the responsibility of the user to maintain a topological order of the nodes. Note that there is not a ``node`` attribute in the Function. The Function can be seen as a Sequence of nodes and should be used as such. For example, to obtain all nodes as a list, call ``list(function)``. Attributes: name: The function name. domain: The domain this function is defined in. overload: The overload name when the function is overloaded. inputs: The input values of the function. attributes: The attributes this function defines. outputs: The output values of the function. opset_imports: Opsets imported by the function. doc_string: Documentation string. metadata_props: Metadata that will be serialized to the ONNX file. meta: Metadata store for graph transform passes. rbr>r}rrrz#OrderedDict[str, AttributeProtocol]rrrBrrrDrErFrGcgrrrs rrFunctionProtocol.__getitem__Orrcgrrr5s rrFunctionProtocol.__len__Prrcgrrr5s rrFunctionProtocol.__iter__Qrrcgrrr5s rrFunctionProtocol.__reversed__Rrrcg)z-Return the unique identifier of the function.Nrr5s r identifierFunctionProtocol.identifierSr2rcg)zAppend a node to the function.Nrrs rrFunctionProtocol.appendYr2rcg)z)Extend the function with the given nodes.Nrrs rrFunctionProtocol.extend]r2rcg)z Remove a node from the function.Nrrs rrFunctionProtocol.removear2rcgrrrs rrFunctionProtocol.insert_aftererrcgrrrs rrFunctionProtocol.insert_beforekrrcg)z-Topologically sort the nodes in the function.Nrr5s rrFunctionProtocol.sortqr2rrNrrZr)r rrrrr)r"r#r$r%r&r]rrrrr rrrrrrr'rrrrr,s, I KM ##33 $$O++,, "":!59       -R     -R   rr)-r& __future__rr  collectionsrcollections.abcrrrrr r r r r ronnx_irr TYPE_CHECKINGrOnptyping_extensionsrtuplerbrr]runtime_checkablerr)r;r`r{rrrrrrrr?r rrrrrr7s{8# #  +!&c3m 4I47h77 x  ": _&6: : z? H? ? D6 86 6 rI HI I X:::D#H##B,,,$+++(8 (H848442 h  (F xF F r