helios.losses.utils
===================

.. py:module:: helios.losses.utils


Attributes
----------

.. autoapisummary::

   helios.losses.utils.LOSS_REGISTRY


Functions
---------

.. autoapisummary::

   helios.losses.utils.create_loss


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

.. py:data:: LOSS_REGISTRY

   Global instance of the registry for loss functions.

   By default, the registry contains the following losses:

   .. list-table:: Optimizers
       :header-rows: 1

       * - Loss
         - Name
       * - ``torch.nn.L1Loss``
         - L1Loss
       * - ``torch.nn.MSELoss``
         - MSELoss
       * - ``torch.nn.CrossEntropyLoss``
         - CrossEntropyLoss
       * - ``torch.nn.CTCLoss``
         - CTCLoss
       * - ``torch.nn.NLLLoss``
         - NLLLoss
       * - ``torch.nn.PoissonNLLLoss``
         - PoissonNLLLoss
       * - ``torch.nn.GaussianNLLLoss``
         - GaussianNLLLoss
       * - ``torch.nn.KLDivLoss``
         - KLDivLoss
       * - ``torch.nn.BCELoss``
         - BCELoss
       * - ``torch.nn.BCEWithLogitsLoss``
         - BCEWithLogitsLoss
       * - ``torch.nn.MarginRankingLoss``
         - MarginRankingLoss
       * - ``torch.nn.HingeEmbeddingLoss``
         - HingeEmbeddingLoss
       * - ``torch.nn.MultiLabelMarginLoss``
         - MultiLabelMarginLoss
       * - ``torch.nn.HuberLoss``
         - HuberLoss
       * - ``torch.nn.SmoothL1Loss``
         - SmoothL1Loss
       * - ``torch.nn.SoftMarginLoss``
         - SoftMarginLoss
       * - ``torch.nn.MultiLabelMarginLoss``
         - MultiLabelMarginLoss
       * - ``torch.nn.CosineEmbeddingLoss``
         - CosineEmbeddingLoss
       * - ``torch.nn.MultiMarginLoss``
         - MultiMarginLoss
       * - ``torch.nn.TripletMarginLoss``
         - TripletMarginLoss
       * - ``torch.nn.TripletMarginWithDistanceLoss``
         - TripletMarginWithDistanceLoss

   .. rubric:: Example

   .. code-block:: python

       import helios.losses as hll

       # This automatically registers your loss function.
       @hll.LOSS_REGISTRY.register
       class MyLoss:
           ...

       # Alternatively you can manually register a loss function like this:
       hll.LOSS_REGISTRY.register(MyLoss)

.. py:function:: create_loss(type_name: str, *args: Any, **kwargs: Any) -> torch.nn.Module

   Create the loss function for the given type.

   :param type_name: the type of the loss to create.
   :param args: positional arguments to pass into the loss.
   :param kwargs: keyword arguments to pass into the loss.

   :returns: The loss function.