minerva.losses.batchwise_barlowtwins_loss
=========================================

.. py:module:: minerva.losses.batchwise_barlowtwins_loss


Classes
-------

.. autoapisummary::

   minerva.losses.batchwise_barlowtwins_loss.BatchWiseBarlowTwinLoss


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

.. py:class:: BatchWiseBarlowTwinLoss(diag_lambda = 0.01, normalize = False)

   Bases: :py:obj:`torch.nn.modules.loss._Loss`


   Implementation of the Batch-wise Barlow Twins loss function (https://arxiv.org/abs/2310.07756).

   Initialize the BatchWiseBarlowtwinsLoss class.

   Parameters
   ----------
   diag_lambda: float
       The value of the diagonal lambda parameter. By default, 0.01.
   normalize: bool
       Whether to normalize the loss or not. By default, False.


   .. py:method:: bt_loss_bs(p, z, lambd=0.01, normalize=False)


   .. py:attribute:: diag_lambda
      :value: 0.01



   .. py:method:: forward(prediction_data, projection_data)

      Calculate the loss between the prediction and projection data. This implementation uses a batch-wise
      version of the Barlow Twins loss function.

      Parameters
      ----------
      prediction_data : torch.Tensor
          The prediction data.
      projection_data : torch.Tensor
          The projection data.



   .. py:attribute:: normalize
      :value: False



   .. py:method:: off_diagonal(x)