neuro_morpho.model.transforms
=============================

.. py:module:: neuro_morpho.model.transforms

.. autoapi-nested-parse::

   Image transformations for data augmentation and preprocessing.



Classes
-------

.. autoapisummary::

   neuro_morpho.model.transforms.Standardize
   neuro_morpho.model.transforms.Norm2One
   neuro_morpho.model.transforms.DownSample


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

.. py:class:: Standardize(eps: float = 1e-08)

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


   Standardize an image.

   This transform subtracts the mean and divides by the standard deviation.


   .. py:attribute:: eps
      :value: 1e-08



   .. py:method:: forward(x: torch.Tensor) -> torch.Tensor

      Apply the standardization.



.. py:class:: Norm2One(eps: float = 1e-08)

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


   Normalize an image to the range [0, 1].


   .. py:attribute:: eps
      :value: 1e-08



   .. py:method:: forward(x: torch.Tensor) -> torch.Tensor

      Apply the normalization.



.. py:class:: DownSample(in_size: tuple[int, int], factors: int | float | tuple[float, Ellipsis] | list[float])

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


   Downsample an image by a given factor.

   This transform can downsample an image by a single factor or multiple factors.


   .. py:attribute:: _single_factor


   .. py:method:: forward(x: torch.Tensor) -> torch.Tensor | tuple[torch.Tensor, Ellipsis]

      Apply the downsampling.

      :param x: The input tensor.
      :type x: torch.Tensor

      :returns: The downsampled tensor(s).
      :rtype: torch.Tensor | tuple[torch.Tensor, ...]