afe.load.importers.tensorflow
=============================

.. py:module:: afe.load.importers.tensorflow


Functions
---------

.. autoapisummary::

   afe.load.importers.tensorflow.convert_to_list
   afe.load.importers.tensorflow.import_tensorflow_model
   afe.load.importers.tensorflow.import_tensorflow2_model
   afe.load.importers.tensorflow.validate_input_parameters
   afe.load.importers.tensorflow.import_tensorflow_pb_to_tvm
   afe.load.importers.tensorflow.import_tensorflow2_pb_to_tvm


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

.. py:function:: convert_to_list(x)

   Taken from: https://github.com/apache/tvm/blob/main/python/tvm/relay/testing/tf.py#L72


.. py:function:: import_tensorflow_model(file_path: str, output_names: List[str])

   Load a Tensorflow model from a pb filepath and a list of output names
   :param file_path: str. File path to the tensorflow .pb file
   :param output_names: List[str]. List of output tensor names (really only applies to tensorflow imports.)
   :return: A Tensorflow graph


.. py:function:: import_tensorflow2_model(file_path: str)

   Load a Tensorflow model from a pb filepath and a list of output names
   :param file_path: str. File path to the tensorflow SavedModel dir.
   :return: A Tensorflow graph


.. py:function:: validate_input_parameters(pb_file_path: str, shape_dict: Dict[str, Tuple[int, Ellipsis]], output_names: List[str], layout: str) -> None

   Validates the user supplied input. Given a .pb file we should be able to discern the shape_dict and dtype_dict
   automatically and we can validate the user supplied output_names. The layout of the network must be given by
   the user. If the user has supplied their own input, this function will validate the input.
   If data cannot be discerned and the user has not supplied input this function will raise errors.
   :param pb_file_path: filepath to the tensorflow .pb file
   :param shape_dict: dictionary of input names to input shapes (eg. (1,224,224,3))
   :param output_names: list of output tensor names (really only applies to tensorflow imports.)
   :param layout: any variation of the characters NHWC representing Batch Size, Height, Width, and Channels


.. py:function:: import_tensorflow_pb_to_tvm(pb_file_path: str, shape_dict: Dict[str, Tuple[int, Ellipsis]], output_names: List[str], layout: str, custom_convert_map: Optional[Dict[str, Callable]] = None) -> afe._tvm._defines.TVMIRModule

   Use TVM frontend to import a tensorflow pb model into TVM Relay IR
   :param pb_file_path: filepath to the tensorflow .pb file
   :param shape_dict: dictionary of input names to input shapes (eg. (1,224,224,3))
   :param output_names: list of output tensor names (really only applies to tensorflow imports.)
   :param layout: any variation of the characters NHWC representing Batch Size, Height, Wdith, and Channels
   :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
                              4 arguments:
                                  inputs = tvm relay expression inputs to operator.
                                  attr = list of strings to operation attributes.
                                  params = list of strings to tvm runtime arrays that are constants in the network.
                                  mod = The tvm irmodule containing subgraphs it uses to help construct the main graph
                                        from tensorflow.
                              The function then returns the tvm relay IR expression that is inserted into the model
                              wherever the operation occurs.
   :return: TVM IR module.


.. py:function:: import_tensorflow2_pb_to_tvm(saved_model_path: str, shape_dict: Dict[str, Tuple[int, Ellipsis]], output_names: List[str], layout: str, custom_convert_map: Optional[Dict[str, Callable]] = None) -> afe._tvm._defines.TVMIRModule

   Use TVM frontend to import a tensorflow pb model into TVM Relay IR
   :param saved_model_path: path to the tensorflow SavedModel directory.
   :param shape_dict: dictionary of input names to input shapes (eg. (1,224,224,3))
   :param output_names: list of output tensor names (really only applies to tensorflow imports.)
   :param layout: any variation of the characters NHWC representing Batch Size, Height, Wdith, and Channels
   :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
                              4 arguments:
                                  inputs = tvm relay expression inputs to operator.
                                  attr = list of strings to operation attributes.
                                  params = list of strings to tvm runtime arrays that are constants in the network.
                                  mod = The tvm irmodule containing subgraphs it uses to help construct the main graph
                                        from tensorflow.
                              The function then returns the tvm relay IR expression that is inserted into the model
                              wherever the operation occurs.
   :return: TVM IR module.