afe.load.importers.tflite

Functions

import_tflite_model(file_path)	Load a TFLite model from a tflite file
validate_input_parameters(→ None)	Validates the user supplied input.
import_tflite_to_tvm(→ afe._tvm._defines.TVMIRModule)	Use TVM frontend to import a tflite pb model into TVM Relay IR

Module Contents

afe.load.importers.tflite.import_tflite_model(file_path: str)

Load a TFLite model from a tflite file :param file_path: str. File path to the tensorflow .pb file :return: A TFLite model

afe.load.importers.tflite.validate_input_parameters(tflite_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 tflite_file_path: filepath to the tensorflow .pb 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.tflite.import_tflite_to_tvm(tflite_file_path: str, shape_dict: Dict[str, Tuple[int, Ellipsis]], dtype_dict: Dict[str, afe.ir.tensor_type.ScalarType]) → afe._tvm._defines.TVMIRModule

Use TVM frontend to import a tflite pb model into TVM Relay IR :param tflite_file_path: filepath to the tensorflow .pb 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) :return: Imported TVM IR module.