¯wg MddlmZgdZddlmZmZmZmZmZm Z ddl Z ddl m Z ddl m ZddlmZmZmZdd lmZdd lmZmZmZmZdd lmZdd lm Z dd l!m"Z"m#Z#m$Z$m%Z%m&Z&m'Z'm(Z(m)Z)ddl*mZm+Z+m,Z,m-Z-m.Z.m/Z/m0Z0m1Z1m2Z2m3Z3m4Z4m5Z5m6Z6m7Z7m8Z8m9Z9m:Z:m!Z!ddl;mZ>m?Z?m@Z@mAZAe rddlBZBde<_Cde=_Cde_Cde_Cde>_Cde?_Cde _Cde@_Cde_Cde_Cde_CdeA_Cde_CdZDejZF ddddddddddddddddddej$jej jddddd ddZIdd ddZJe jZLddZMddZN e jZP e jZRy)) annotations)(symbolic_helperutilserrorssymbolic_caffe2symbolic_opset7symbolic_opset8symbolic_opset9symbolic_opset10symbolic_opset11symbolic_opset12symbolic_opset13symbolic_opset14symbolic_opset15symbolic_opset16symbolic_opset17symbolic_opset18symbolic_opset19symbolic_opset20 ExportTypesOperatorExportTypes TrainingModeTensorProtoDataType JitScalarTypeexportexport_to_pretty_stringis_in_onnx_exportselect_model_mode_for_exportregister_custom_op_symbolicunregister_custom_op_symbolic disable_log enable_logOnnxExporterErrorDiagnosticOptions ExportOptions ONNXProgramONNXRuntimeOptions OnnxRegistry dynamo_exportenable_fake_modeis_onnxrt_backend_supported)AnyCallable CollectionMappingSequence TYPE_CHECKINGN)_C)_onnx)rrr)r)r+ OrtBackendOrtBackendOptionsOrtExecutionProvider)r)r#)_optimize_graph_run_symbolic_function_run_symbolic_methodrrrrr )rrrrr r r r r rrrrrrrrr)r$r%r&r'r(r*z torch.onnxpytorchTF.)kwargs export_paramsverbose input_names output_names opset_version dynamic_axeskeep_initializers_as_inputsdynamo external_datadynamic_shapesreportverifyprofiledump_exported_program artifacts_dirfallbacktrainingoperator_export_typedo_constant_folding custom_opsetsexport_modules_as_functionsautograd_inliningc <| dus$t|tjjrGddlm}t|tj r|f}|j|||||||||| | | | ||||||Sddlm}| r td||||f|||du|||| | ||||||dy) a}Exports a model into ONNX format. Args: model: The model to be exported. args: Example positional inputs. Any non-Tensor arguments will be hard-coded into the exported model; any Tensor arguments will become inputs of the exported model, in the order they occur in the tuple. f: Path to the output ONNX model file. E.g. "model.onnx". kwargs: Optional example keyword inputs. export_params: If false, parameters (weights) will not be exported. verbose: Whether to enable verbose logging. input_names: names to assign to the input nodes of the graph, in order. output_names: names to assign to the output nodes of the graph, in order. opset_version: The version of the `default (ai.onnx) opset `_ to target. Must be >= 7. dynamic_axes: By default the exported model will have the shapes of all input and output tensors set to exactly match those given in ``args``. To specify axes of tensors as dynamic (i.e. known only at run-time), set ``dynamic_axes`` to a dict with schema: * KEY (str): an input or output name. Each name must also be provided in ``input_names`` or ``output_names``. * VALUE (dict or list): If a dict, keys are axis indices and values are axis names. If a list, each element is an axis index. For example:: class SumModule(torch.nn.Module): def forward(self, x): return torch.sum(x, dim=1) torch.onnx.export( SumModule(), (torch.ones(2, 2),), "onnx.pb", input_names=["x"], output_names=["sum"], ) Produces:: input { name: "x" ... shape { dim { dim_value: 2 # axis 0 } dim { dim_value: 2 # axis 1 ... output { name: "sum" ... shape { dim { dim_value: 2 # axis 0 ... While:: torch.onnx.export( SumModule(), (torch.ones(2, 2),), "onnx.pb", input_names=["x"], output_names=["sum"], dynamic_axes={ # dict value: manually named axes "x": {0: "my_custom_axis_name"}, # list value: automatic names "sum": [0], }, ) Produces:: input { name: "x" ... shape { dim { dim_param: "my_custom_axis_name" # axis 0 } dim { dim_value: 2 # axis 1 ... output { name: "sum" ... shape { dim { dim_param: "sum_dynamic_axes_1" # axis 0 ... keep_initializers_as_inputs: If True, all the initializers (typically corresponding to model weights) in the exported graph will also be added as inputs to the graph. If False, then initializers are not added as inputs to the graph, and only the user inputs are added as inputs. Set this to True if you intend to supply model weights at runtime. Set it to False if the weights are static to allow for better optimizations (e.g. constant folding) by backends/runtimes. dynamo: Whether to export the model with ``torch.export`` ExportedProgram instead of TorchScript. external_data: Whether to save the model weights as an external data file. This is required for models with large weights that exceed the ONNX file size limit (2GB). When False, the weights are saved in the ONNX file with the model architecture. dynamic_shapes: A dictionary of dynamic shapes for the model inputs. Refer to :func:`torch.export.export` for more details. This is only used (and preferred) when dynamo is True. Only one parameter `dynamic_axes` or `dynamic_shapes` should be set at the same time. report: Whether to generate a markdown report for the export process. verify: Whether to verify the exported model using ONNX Runtime. profile: Whether to profile the export process. dump_exported_program: Whether to dump the :class:`torch.export.ExportedProgram` to a file. This is useful for debugging the exporter. artifacts_dir: The directory to save the debugging artifacts like the report and the serialized exported program. fallback: Whether to fallback to the TorchScript exporter if the dynamo exporter fails. training: Deprecated option. Instead, set the training mode of the model before exporting. operator_export_type: Deprecated option. Only ONNX is supported. do_constant_folding: Deprecated option. The exported graph is always optimized. custom_opsets: Deprecated. A dictionary: * KEY (str): opset domain name * VALUE (int): opset version If a custom opset is referenced by ``model`` but not mentioned in this dictionary, the opset version is set to 1. Only custom opset domain name and version should be indicated through this argument. export_modules_as_functions: Deprecated option. Flag to enable exporting all ``nn.Module`` forward calls as local functions in ONNX. Or a set to indicate the particular types of modules to export as local functions in ONNX. This feature requires ``opset_version`` >= 15, otherwise the export will fail. This is because ``opset_version`` < 15 implies IR version < 8, which means no local function support. Module variables will be exported as function attributes. There are two categories of function attributes. 1. Annotated attributes: class variables that have type annotations via `PEP 526-style `_ will be exported as attributes. Annotated attributes are not used inside the subgraph of ONNX local function because they are not created by PyTorch JIT tracing, but they may be used by consumers to determine whether or not to replace the function with a particular fused kernel. 2. Inferred attributes: variables that are used by operators inside the module. Attribute names will have prefix "inferred::". This is to differentiate from predefined attributes retrieved from python module annotations. Inferred attributes are used inside the subgraph of ONNX local function. * ``False`` (default): export ``nn.Module`` forward calls as fine grained nodes. * ``True``: export all ``nn.Module`` forward calls as local function nodes. * Set of type of nn.Module: export ``nn.Module`` forward calls as local function nodes, only if the type of the ``nn.Module`` is found in the set. autograd_inlining: Deprecated. Flag used to control whether to inline autograd functions. Refer to https://github.com/pytorch/pytorch/pull/74765 for more details. Trexporter)r=r>r?r@rArBrCrDrFrGrHrIrJrKrLrM)rz[The exporter only supports dynamic shapes through parameter dynamic_axes when dynamo=False.)r=r>r?r@rArBrCrDrNrOrPrQrRrSN) isinstancetorchrExportedProgramtorch.onnx._internalrVTensor export_compattorch.onnx.utils ValueError)modelargsfr=r>r?r@rArBrCrDrErFrGrHrIrJrKrLrMrNrOrPrQrRrS_rVrs X/home/mcse/projects/flask/flask-venv/lib/python3.12/site-packages/torch/onnx/__init__.pyrrsV~E5<<+G+GH1 dELL )7D%%   '#%'%(C')"7''&  , , D      'tO#%'%(C!5 3'(C/# &)export_optionsc ddl}ddlm}ddlm}ddlm}t|tjjr|j||d|ddddS|jr^||jd t |'|jrd }|j!||} nd} |j||d|| dddd Sdd lm} | |g|d|i|S)aExport a torch.nn.Module to an ONNX graph. Args: model: The PyTorch model to be exported to ONNX. model_args: Positional inputs to ``model``. model_kwargs: Keyword inputs to ``model``. export_options: Options to influence the export to ONNX. Returns: An in-memory representation of the exported ONNX model. **Example 1 - Simplest export** :: class MyModel(torch.nn.Module): def __init__(self) -> None: super().__init__() self.linear = torch.nn.Linear(2, 2) def forward(self, x, bias=None): out = self.linear(x) out = out + bias return out model = MyModel() kwargs = {"bias": 3.0} args = (torch.randn(2, 2, 2),) onnx_program = torch.onnx.dynamo_export(model, *args, **kwargs).save( "my_simple_model.onnx" ) **Example 2 - Exporting with dynamic shapes** :: # The previous model can be exported with dynamic shapes export_options = torch.onnx.ExportOptions(dynamic_shapes=True) onnx_program = torch.onnx.dynamo_export( model, *args, **kwargs, export_options=export_options ) onnx_program.save("my_dynamic_model.onnx") rN)_flagsrU)_pytreeT)rar=rBrFr>rMzYou are using an experimental ONNX export logic, which currently only supports dynamic shapes. For a more comprehensive set of export options, including advanced features, please consider using `torch.onnx.export(..., dynamo=True)`. )categorycdfd}|S)Nrct|tjrVt|j}i}t |D]*}tj jdd|||<,dz |Sy)Narg__dim_r4)rWrXr[lenshaperangerDim)xrank dynamic_shapei arg_orders rc_to_dynamic_shapezKdynamo_export.._to_dynamic_shapes_mapper.._to_dynamic_shapess!!U\\2"177|(* !&tA/4||/?/?"&ykqc :0M!,"Q ,,#rd)rxrws @rc_to_dynamic_shapes_mapperz0dynamo_export.._to_dynamic_shapes_mappers  $)(rd)rar=rGrBrFr>rM)r)re)warnings torch.onnxrgrZrV torch.utilsrhrWrXrrYr\USE_EXPERIMENTAL_LOGICwarn FutureWarningrGtree_map%torch.onnx._internal._exporter_legacyr)) r_re model_args model_kwargsr{rgrVrhrzrGr)s rcr)r)sf!-#%556%%  &    & &  % MM:'    %.*G*G )(%--)+N "N%%  )&   H   /= AM  rdc.tjdy)zEnables ONNX logging.TNr2_jit_set_onnx_log_enabledryrdrcr"r"s  &rdc.tjdy)zDisables ONNX logging.FNrryrdrcr!r!s  'rd)ryN)8r_zbtorch.nn.Module | torch.export.ExportedProgram | torch.jit.ScriptModule | torch.jit.ScriptFunctionr`ztuple[Any, ...]razstr | os.PathLike | Noner=zdict[str, Any] | Noner>boolr?z bool | Noner@Sequence[str] | NonerArrBz int | NonerCzDMapping[str, Mapping[int, str]] | Mapping[str, Sequence[int]] | NonerDrrErrFrrGz3dict[str, Any] | tuple[Any, ...] | list[Any] | NonerHrrIrrJrrKrrLzstr | os.PathLikerMrrNz_C_onnx.TrainingModerOz_C_onnx.OperatorExportTypesrPrrQzMapping[str, int] | NonerRz(bool | Collection[type[torch.nn.Module]]rSrrbr,returnz Any | None)r_z9torch.nn.Module | Callable | torch.export.ExportedProgramrezExportOptions | NonerzONNXProgram | Any)rNone)S __future__r__all__typingr,r-r.r/r0r1rXr2torch._Cr3_C_onnxtorch._C._onnxrrr_exporter_statesr_internal.onnxruntimer+r5 _OrtBackendr6_OrtBackendOptionsr7_OrtExecutionProvider _type_utilsrrr#rr8r9r:rrrrr rrrr r r r r rrrrrrrr_internal._exporter_legacyr$r%r&r'r(r*os __module__ producer_namePRODUCER_VERSIONproducer_versionEVALONNXrr)_jit_is_onnx_log_enabledis_onnx_log_enabledr"r!_jit_set_onnx_log_output_streamset_log_stream _jit_onnx_loglogryrdrcrs"0 dON %QQ) '%   ,  ,' % ' %  ,+& %  ,#/ *)5& ++"& A%)(,)- $(-JN"''*%,%9%9%>%>8?8S8S8X8X $.2LQ"EA A  A  A "AAA&A'AA A""&#A$ %A()A*H+A, -A. /A01A2 3A4%5A67A:#;A<6=A>?A@,AAB"JCADEAF GAHIAP,0 z Dz ) z  z @11' (  33  rd