afe.load.importers.onnx

Functions

import_onnx_model(file_path)	Load a ONNX model from a file
validate_input_parameters(→ None)	Validates the user supplied input.
import_onnx_to_tvm(...)	Use TVM frontend to import a onnx model into TVM Relay IR

Module Contents

afe.load.importers.onnx.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

afe.load.importers.onnx.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)

afe.load.importers.onnx.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: Dict[str, Callable] | None = 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.

Returns:

Imported TVM IR module and names of the ONNX model’s outputs.