credit.postblock.wet_mask_samudra
=================================

.. py:module:: credit.postblock.wet_mask_samudra


Classes
-------

.. autoapisummary::

   credit.postblock.wet_mask_samudra.WetMaskBlock


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

.. py:class:: WetMaskBlock(conf, key: str = 'prediction')

   Bases: :py:obj:`torch.nn.Module`


   Post-processing layer that applies wet mask to ocean predictions.
   Zero trainable parameters, but mask influences gradients.

   Masks predictions so land points = 0, ocean points preserve values.
   This encourages the model to focus learning on ocean regions.


   .. py:attribute:: key
      :value: 'prediction'



   .. py:method:: forward(batch_dict: dict) -> dict

      Apply wet mask to ``batch_dict[self.key]`` (land=0, ocean preserved).