ksuit.data.preprocessors.preprocessor
=====================================

.. py:module:: ksuit.data.preprocessors.preprocessor


Classes
-------

.. autoapisummary::

   ksuit.data.preprocessors.preprocessor.PreProcessor


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

.. py:class:: PreProcessor(normalization_key)

   Base class for all data preprocessors.
   .. rubric:: Example

   >>> class MyPreProcessor(PreProcessor):
   >>>     def __init__(self, normalization_key: "image"):
   >>>         super().__init__(normalization_key=normalization_key)
   >>>     def __call__(self, x):
   >>> # Example processing: normalize to [0, 1]
   >>>         return x / 255.0
   >>>     def denormalize(self, x):
   >>> # Example denormalization: scale back to [0, 255]
   >>>         return x * 255.0

   :param normalization_key: key to identify on which getitem_ in the dataset/tensor the preprocessor is applied.

   :raises TypeError: If normalization_key is not a string.


   .. py:attribute:: normalization_key


   .. py:method:: denormalize(x)
      :abstractmethod:


      Denormalizes the input data. This method should be overridden by subclasses if denormalization is supported.
      If denormalization is not supported, it raises NotImplementedError or decide to implement the identity function.

      :param x: The input tensor to denormalize.