:py:mod:`box_embeddings.modules.intersection.tf_gumbel_intersection`
====================================================================

.. py:module:: box_embeddings.modules.intersection.tf_gumbel_intersection


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

.. py:function:: tf_gumbel_intersection(left: box_embeddings.parameterizations.TFTBoxTensor, right: box_embeddings.parameterizations.TFTBoxTensor, gumbel_beta: float = 1.0, approximation_mode: Optional[str] = None) -> box_embeddings.parameterizations.TFTBoxTensor

   Hard Intersection operation as a function.

   .. note:: This function can give fipped boxes, i.e. where z[i] > Z[i]

   .. todo:: Add support for automatic broadcasting

   :param left: BoxTensor which is the left operand
   :param right: BoxTensor which is the right operand
   :param gumbel_beta: Beta parameter
   :param approximation_mode: Use hard clipping ('clipping') or hard clipping with separeate value
                              for forward and backward passes  ('clipping_forward') to satisfy the required inequalities.
                              Set `None` to not use any approximation. (default: `None`)

   :returns: The resulting BoxTensor obtained by interection.
             It has the same concrete type as the `self` (left operand).

   :raises ValueError: When approximation_mode is not in [None, 'clipping', 'clipping_forward']


.. py:class:: TFGumbelIntersection(beta: float = 1.0, approximation_mode: Optional[str] = None)

   Bases: :py:obj:`box_embeddings.modules.intersection._tf_intersection._TFIntersection`

   Gumbel intersection operation as a Layer/Module.

   Performs the intersection operation as described in `Improving Local Identifiability in Probabilistic Box Embeddings <https://arxiv.org/abs/2010.04831>`_ .