h3 SSKJr SSKJrJrJrJrJrJrJ r SSK r SSK r SSK Js Jr SSK JrJrJr "SS5r"SS5rS \S \\S \S \S \ \\S44 Sjr"SS5r"SS5rg)) namedtuple)AnyDictNewTypeOptionalSequenceTupleTypeN) IR_VERSION ModelProto NodeProtoc`\rSrSr%Sr\"S\5r\"S5r\\ S'\"S5r \\ S'Sr g ) DeviceTypez Describes device type. _TyperCPUCUDAN) __name__ __module__ __qualname____firstlineno____doc__rintrr__annotations__r__static_attributes__rK/var/www/fran/franai/venv/lib/python3.13/site-packages/onnx/backend/base.pyrrs1 GS !EqC(D%rrc*\rSrSrSrS\SS4SjrSrg)Devicezn Describes device type and device id syntax: device_type:device_id(optional) example: 'CPU', 'CUDA', 'CUDA:1' devicereturnNcURS5n[[US5UlSUl[ U5S:a[ US5Ulgg)N:rr)splitgetattrrtype device_idlenr)selfr#optionss r__init__Device.__init__!sI,,s#J 3  w[U[5(aTUn[[U5U]U5$N) isinstancer0superr) __getitem__)r,r7field_names_maps rgetitemnamedtupledict..getitem1s0 c3  !#&CT$Z2377r) enumerate setdefaultrrr<) r1r2r3r4indatar>r=s @rnamedtupledictrE)su)2+(>?(>qt(>?O h% h =d =f =D8c888  K@sA%c8\rSrSrSrS\S\S\\S44SjrSrg ) BackendRep:z BackendRep 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. inputsr4r$.c g)zAbstract function.r9r)r,rIr4s rrunBackendRep.runAsrrN) rrrrrrr rKrrrrrGrG:s) #sCxrrGcH\rSrSrSr\SS\S\S\S\ 4Sjj5r \SS\S\S\S\ \ 4Sjj5r \SS\S \S\S\S\\S 44 S jj5r\SS \S \S\S\ \\\R&\\S 44S\\\4S\ \\S 44 Sjj5r\S\S\ 4Sj5rSrg )BackendFa Backend is the entity that will take an ONNX model with inputs, perform a computation, and then return the output. For one-off execution, users can use run_node and run_model to obtain results quickly. For repeated execution, users should use prepare, in which the Backend does all of the preparation work for executing the model repeatedly (e.g., loading initializers), and returns a BackendRep handle. modelr#r4r$c g)NTrclsrPr#r4s r is_compatibleBackend.is_compatibleRs rc B[RRU5 gr9)onnxchecker check_modelrRs rprepareBackend.prepareYs   'rrI.c TUR"X40UD6nUceURU5$r9)rZrK)rSrPrIr#r4backends r run_modelBackend.run_modelas2++e6v6"""{{6""rNnode outputs_infoc SU;aL[R"5n[UlSUS0Ul[ R RX5 g[ R RU5 g)aXSimple run one operator and return the results. Args: 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 opset_versionN) c_checkerCheckerContextr ir_version opset_importsrWrX check_node)rSr`rIr#rar4special_contexts rrun_nodeBackend.run_nodeisb" f $'668O)3O &-/1H,IO ) LL # #D : LL # #D )rcg)zv Checks whether the backend is compiled with particular device support. In particular it's used in the testing suite. Tr)rSr#s rsupports_deviceBackend.supports_devices rr)r)rN)rrrrr classmethodr r0rboolrTrrGrZr r^r rnumpydtyperrrkrnrrrrrNrNFsn .3(+?B  .3(+?B * ;@##(+#58#LO# sCx## PT   xekk5c?.J(KLM  sCx.  %S/ "4STrrN) collectionsrtypingrrrrrr r rr onnx.checkerrWonnx.onnx_cpp2py_export.checkeronnx_cpp2py_exportrXrer r r rr!r0rErGrNrrrrys #FFF 3322 - - ( 69EH %S/"  DDr