afe.ir.transform
================

.. py:module:: afe.ir.transform


Submodules
----------

.. toctree::
   :maxdepth: 1

   /pages/api_reference/python-autoapi/afe/ir/transform/base_transform/index
   /pages/api_reference/python-autoapi/afe/ir/transform/calibration_transforms/index
   /pages/api_reference/python-autoapi/afe/ir/transform/channel_scaling/index
   /pages/api_reference/python-autoapi/afe/ir/transform/compression_transforms/index
   /pages/api_reference/python-autoapi/afe/ir/transform/quantization_transforms/index
   /pages/api_reference/python-autoapi/afe/ir/transform/requantization_fusion/index
   /pages/api_reference/python-autoapi/afe/ir/transform/requantization_hoisting/index


Classes
-------

.. autoapisummary::

   afe.ir.transform.Calibrate
   afe.ir.transform.InsertNodeObservers
   afe.ir.transform.RemoveNodeObservers
   afe.ir.transform.UpdateQuantizationConfigs
   afe.ir.transform.Quantize
   afe.ir.transform.Compress


Package Contents
----------------

.. py:class:: Calibrate(length_hint: Optional[int], dataset: Iterable[Dict[str, numpy.ndarray]])



   Calibrates an AwesomeNet.

   :param length_hint: If not None, gives the number of items in the data set.  This is
      used for progress reporting and it does not affect the number of items used for calibration.
   :param dataset: The input data set for calibration.



.. py:class:: InsertNodeObservers(calibration_method: afe.apis.defines.CalibrationMethod)



   Inserts NodeObservers into AwesomeNet's nodes.  NodeObservers will not be added
   to nodes that don't use information obtained from calibration pass, but obtain
   quantization parameters based on the quantization parameters of its inputs.

   :param calibration_method: CalibrationMethod used in calibration.  Determines
       the type of observers which shall be created.  See CalibrationMethod Enum
       class for supported values.
   :param percentile_value: If the Histogram percentile is being used, percentage of
       values to keep.


.. py:class:: RemoveNodeObservers



   Remove NodeObservers from AwesomeNet's nodes.  This is needed in order to remove
   PyTorch infrastructure which is no longer needed from AwesomeNet's nodes.


.. py:class:: UpdateQuantizationConfigs(quant_configs: afe.core.configs.QuantizationConfigs, custom_quantization_configs: Optional[Dict[afe.ir.defines.NodeName, Dict[str, Any]]] = None)



   Update quantization configs to each node in AwesomeNet

   :attribute asymmetry: bool. Set to True if users want to do asymmetry quantization for all layers
       or False for symmetric quantization unless some layers are specific configured in
       the custom_quantization_configs.
   :attribute per_channel: bool. Set to True if users want to do per-channel quantization for all layers
       or False for per-tensor quantization unless some layers are specific configured in
       the custom_quantization_configs.
   :attribute leaky_relu_uses_udf: Default is True. If Ture, AFE will use UDF for LeakyRelu operation. Else
       AFE will breakdown the LeakyRelu into multiple elementwise operationis unless some layers are specific
       configured in the custom_quantization_configs.
   :attribute custom_quantization_configs: Optional[Dict[NodeName, Dict[str, Any]]]. A dictionary using NodeName
       as keys. The value to each key is a dictionary of the AwesomeQuantAttr's field names and sets target
       configuration.

   Example
   -------
       The example shows how a custom_quantization_configs looks like to config the output_int32 field in a
       Conv2DQuantAttrs in a output conv2d_add node to True.

       custom_quantization_configs = {"MLA_1/conv2d_add_84": {"output_int32": True}}


.. py:class:: Quantize



   Quantizes an AwesomeNet


.. py:class:: Compress



   Compresses an AwesomeNet