:py:mod:`neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_layer_norm`
===================================================================================

.. py:module:: neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_layer_norm

.. autoapi-nested-parse::

   Fuse small ops to LayerNorm Graph Rewriter.



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

Classes
~~~~~~~

.. autoapisummary::

   neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_layer_norm.FuseLayerNormOptimizer



Functions
~~~~~~~~~

.. autoapisummary::

   neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_layer_norm.node_name_from_input
   neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_layer_norm.node_from_map
   neural_compressor.adaptor.tf_utils.graph_rewriter.generic.fuse_layer_norm.values_from_const



.. py:class:: FuseLayerNormOptimizer(input_graph_def)


   Remap smaller ops into fused LayerNorm.

   Current fusion is only for the case, when LayerNormalization uses FusedBatcNormV3.
   And further restrict it to only 2D or 3D tensor inputs to keras LayerNormalization api.


.. py:function:: node_name_from_input(node_name)

   Strips off ports and other decorations to get the underlying node name.


.. py:function:: node_from_map(node_map, name)

   Pulls a node def from a dictionary for a given name.

   :param node_map: Dictionary containing an entry indexed by name for every node.
   :param name: Identifies the node we want to find.

   :returns: NodeDef of the node with the given name.

   :raises ValueError: If the node isn't present in the dictionary.


.. py:function:: values_from_const(node_def)

   Extracts the values from a const NodeDef as a numpy ndarray.

   :param node_def: Const NodeDef that has the values we want to access.

   :returns: Numpy ndarray containing the values.

   :raises ValueError: If the node isn't a Const.