Ng ddlmZddlmZmZmZmZmZmZm Z ddl Z ddl Z ddl mcmZddl mZmZmZGddZGddZd ed eed ed ed e eedff dZGddZGddZdS)) namedtuple)AnyDictNewTypeOptionalSequenceTupleTypeN) IR_VERSION ModelProto NodeProtocleZdZUdZedeZedZeed<edZ eed<dS) DeviceTypezDescribes device type._TyperCPUCUDAN) __name__ __module__ __qualname____doc__rintrr__annotations__rM/var/www/html/ai-engine/env/lib/python3.11/site-packages/onnx/backend/base.pyrrsY  GGS ! !EqC%((D%rrc"eZdZdZdeddfdZdS)DevicezyDescribes device type and device id syntax: device_type:device_id(optional) example: 'CPU', 'CUDA', 'CUDA:1' devicereturnNc|d}tt|d|_d|_t |dkrt |d|_dSdS)N:rr)splitgetattrrtype device_idlenr)selfroptionss r__init__zDevice.__init__s],,s##J 33  w<z"namedtupledict..)s???1q!???rrenameTr(keyr ct|tr|}tt|||SN) isinstancer+superr% __getitem__)r(r7field_names_maps rgetitemznamedtupledict..getitem.sC c3   '!#&CT$ZZ&&223777r) enumerate setdefaultrrr<)r,r-r.r/datar>r=s @rnamedtupledictrB&s@? +(>(>???O h%%% h =d = = =f = =D8c88888888 D Krc6eZdZdZdededeedffdZdS) BackendRepzBackendRep is the handle that a Backend returns after preparing to execute a model repeatedly. Users will then pass inputs to the run function of BackendRep to retrieve the corresponding results. inputsr/r .c dS)zAbstract function.r9r)r(rEr/s rrunzBackendRep.run=swrN)rrrrrr rGrrrrDrD7sO #sCxrrDczeZdZdZe ddedededefdZ e ddededede e fdZ e dded ededede ed ff d Ze dd ed edede ee eje ed ffdeeefde e ed ff dZededefdZd S)BackendaBackend is the entity that will take an ONNX model with inputs, perform a computation, and then return the output. For one-off execution, users can use run_node and run_model to obtain results quickly. For repeated execution, users should use prepare, in which the Backend does all of the preparation work for executing the model repeatedly (e.g., loading initializers), and returns a BackendRep handle. rmodelrr/r c dS)NTrclsrJrr/s r is_compatiblezBackend.is_compatibleM trc Dtj|dSr9)onnxchecker check_modelrLs rpreparezBackend.prepareTs   '''trrE.c R|j||fi|}|J||Sr9)rTrG)rMrJrErr/backends r run_modelzBackend.run_model\s=#+eV66v66"""{{6"""rNnode outputs_infoc d|vrOtj}t|_d|di|_t j||nt j|dS)a6Simple run one operator and return the results. Args: node: The node proto. inputs: Inputs to the node. device: The device to run on. outputs_info: a list of tuples, which contains the element type and shape of each output. First element of the tuple is the dtype, and the second element is the shape. More use case can be found in https://github.com/onnx/onnx/blob/main/onnx/backend/test/runner/__init__.py kwargs: Other keyword arguments. opset_versionN) c_checkerCheckerContextr ir_version opset_importsrQrR check_node)rMrXrErrYr/special_contexts rrun_nodezBackend.run_nodedsm, f $ $'688O)3O &-/1H,IO ) L # #D/ : : : : L # #D ) ) )trcdS)zChecks whether the backend is compiled with particular device support. In particular it's used in the testing suite. Tr)rMrs rsupports_devicezBackend.supports_devicerOr)r)rN)rrrr classmethodr r+rboolrNrrDrTr rWr rnumpydtyperrrcrerrrrIrIBs.3(+?B [ .3(+?B * [;@###(+#58#LO# sCx###[# PT   xek5c?.J(KLM  sCx.  %S/ "[>ST[rrI) collectionsrtypingrrrrrr r rh onnx.checkerrQonnx.onnx_cpp2py_export.checkeronnx_cpp2py_exportrRr]r r r rrr+rBrDrIrrrros #"""""FFFFFFFFFFFFFFFFFF 3333333332222222222 - - - - - - - - ( 69EH %S/"GGGGGGGGGGr