:py:mod:`box_embeddings.modules.regularization.regularizer`
===========================================================

.. py:module:: box_embeddings.modules.regularization.regularizer


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

.. py:class:: BoxRegularizer(weight: float, log_scale: bool = True, reduction: str = 'sum', **kwargs: Any)

   Bases: :py:obj:`torch.nn.Module`, :py:obj:`box_embeddings.common.registrable.Registrable`

   Base box-regularizer class

   .. py:method:: forward(self, box_tensor: box_embeddings.parameterizations.box_tensor.BoxTensor) -> Union[float, torch.Tensor]

      Calls the _forward and multiplies the weight

      :param box_tensor: Input box tensor

      :returns: scalar regularization loss