Returns an instance ofEagerOnnx.

Converts a function into an executable functionbased on a backend. The new function is convertedto onnx on the first call.

Parameters:

• f – function to convert

• tensor_class – wrapper around a class defining the backend,if None, it defaults toonnx.reference.ReferenceEvaluator

• target_opsets – dictionary{opset: version}

• output_types – shape and type inference cannot be run beforethe onnx graph is created and type is needed to do such,if not specified, the class assumes there is only one outputof the same type as the input

• bypass_eager – this parameter must be true if the functionhas not annotation and is not decorated byxapi_inline orxapi_function

• ir_version – defines the IR version to use

Converts a function into an executable functionbased on a backend. The new function is convertedto onnx on the first call.

Parameters:

• f – function to convert

• tensor_class – wrapper around a class defining the backend,if None, it defaults toonnx.reference.ReferenceEvaluator

• target_opsets – dictionary{opset: version}

• output_types – shape and type inference cannot be run beforethe onnx graph is created and type is needed to do such,if not specified, the class assumes there is only one outputof the same type as the input

• ir_version – defines the IR version to use

propertyavailable_versions¶

Returns the key used to distinguish between every jitted version.

cast_from_tensor_class(results:List[EagerTensor])→Any|Tuple[Any][source]¶

Wraps input fromself.tensor_class to python types.

Parameters:

results – python inputs (including numpy)

Returns:

wrapped inputs

cast_to_tensor_class(inputs:List[Any])→List[EagerTensor][source]¶

Wraps input intoself.tensor_class.

Parameters:

inputs – python inputs (including numpy)

Returns:

wrapped inputs

get_onnx(key:int|None=None)[source]¶

Returns the jitted function associated to one key.If key is None, the assumes there is only one available jitted functionand it returns it.

info(prefix:str|None=None,method_name:str|None=None,already_eager:bool|None=None,args:List[Any]|None=None,kwargs:Dict[str,Any]|None=None,key:Tuple[Any,...]|None=None,onx:ModelProto|None=None,output:Any|None=None)[source]¶

Logs a status.

jit_call(*values,**kwargs)[source]¶

The method builds a key which identifies the signature(input types + parameters value).It then checks if the function was already converted into ONNXfrom a previous. If not, it converts it and caches the resultsindexed by the previous key. Finally, it executes the onnx graphand returns the result or the results in a tuple if there are several.

make_key(*values:List[Any],**kwargs:Dict[str,Any])→Tuple[Any,...][source]¶

Builds a key based on the input types and parameters.Every set of inputs or parameters producing the samekey (or signature) must use the same compiled ONNX.

Parameters:

• values – values given to the function

• kwargs – parameters

Returns:

tuple of mutable keys

move_input_to_kwargs(values:List[Any],kwargs:Dict[str,Any])→Tuple[List[Any],Dict[str,Any]][source]¶

Mandatory parameters not usually not named. Some inputs mustbe moved to the parameter list before calling ONNX.

Parameters:

• values – list of inputs

• kwargs – dictionary of arguments

Returns:

new values, new arguments

propertyn_versions¶

Returns the number of jitted functions.There is one per type and number of dimensions.

status(me:str)→str[source]¶

Returns a short string indicating the status.

to_jit(*values,**kwargs)[source]¶

Converts the function into ONNX based on the provided inputsand parameters. It then wraps it by callingself.tensor_class.create_function.The onnx graph built by the function defines the inputtypes and the expected number of dimensions.

Returns an instance ofJitOnnx.

Converts a function into an executable functionbased on a backend. The new function is convertedto onnx on the first call.

Parameters:

• f – function to convert

• tensor_class – wrapper around a class defining the backend,if None, it defaults toonnx.reference.ReferenceEvaluator

• target_opsets – dictionary{opset: version}

• output_types – shape and type inference cannot be run beforethe onnx graph is created and type is needed to do such,if not specified, the class assumes there is only one outputof the same type as the input

• ir_version – defines the IR version to use