afe.load.importers.onnx
=======================

.. py:module:: afe.load.importers.onnx


Functions
---------

.. autoapisummary::

   afe.load.importers.onnx.import_onnx_model
   afe.load.importers.onnx.validate_input_parameters
   afe.load.importers.onnx.import_onnx_to_tvm


Module Contents
---------------

.. py:function:: import_onnx_model(file_path: str)

   Load a ONNX model from a file
   :param file_path: str. File path to the onnx .onnx file
   :return: A ONNX model


.. py:function:: validate_input_parameters(onnx_file_path: str, shape_dict: Dict[str, Tuple[int, Ellipsis]], dtype_dict: Dict[str, afe.ir.tensor_type.ScalarType]) -> None

   Validates the user supplied input.
   :param onnx_file_path: filepath to the onnx .onnx file
   :param shape_dict: dictionary of input names to input shapes (eg. (1,224,224,3))
   :param dtype_dict: dictionary of input names to input types (eg. float32 or int64)


.. py:function:: import_onnx_to_tvm(onnx_file_path: str, shape_dict: Dict[str, Tuple[int, Ellipsis]], dtype_dict: Dict[str, afe.ir.tensor_type.ScalarType], custom_convert_map: Optional[Dict[str, Callable]] = None) -> Tuple[afe._tvm._defines.TVMIRModule, List[str]]

   Use TVM frontend to import a onnx model into TVM Relay IR
   :param onnx_file_path: filepath to the onnx .onnx file
   :param shape_dict: dictionary of input names to input shapes (eg. (1,224,224,3))
   :param dtype_dict: dictionary of input names to input types (eg. float32 or int64)
   :param custom_convert_map: A custom op conversion map that maps operation names to functions. Whenever an operator
                              with a name found in the custom_convert_map is found in TVM, the function is called with
                              3 arguments
                                  inputs = a tvm onnx_input object which contains a dictionary of tvm function inputs
                                  attr = a dictionary of operation attributes
                                  params = a dictionary of all the constants in the onnx network
                              The function then returns the tvm relay IR expression that is inserted into the model
                              wherever the operation occurs.
   :return: Imported TVM IR module and names of the ONNX model's outputs.