:py:mod:`utils`
===============

.. py:module:: utils


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


Functions
~~~~~~~~~

.. autoapisummary::

   utils.compute_pad_size
   utils.compute_pad_size_padded
   utils.pad_object
   utils.unpad_object
   utils.get_kernel_meshgrid



.. py:function:: compute_pad_size(width)

   Computes the pad size required for rotation / inverse rotation so that pad + rotate + inverse rotate + unpad = original object

   :param width: Width of input tensor (assumed to be square)
   :type width: int

   :returns: How much to pad each side by
   :rtype: int


.. py:function:: compute_pad_size_padded(width)

   Given a padded tensor, computes how much padding it has had

   :param width: Width of input padded tensor (assumed square)
   :type width: int

   :returns: How much padding was applied to the input tensor
   :rtype: int


.. py:function:: pad_object(object, mode='constant')

   Pads an input tensor so that pad + rotate + inverse rotate + unpad = original object. This is useful for rotating objects without losing information at the edges.

   :param object: Object to be padded
   :type object: torch.Tensor
   :param mode: Mode for extrapolation beyonf out of bounds. Defaults to 'constant'.
   :type mode: str, optional

   :returns: Padded object
   :rtype: torch.Tensor


.. py:function:: unpad_object(object)

   Given a padded object, removes the padding to return the original object

   :param object: Padded object
   :type object: torch.Tensor

   :returns: Unpadded, original object
   :rtype: torch.Tensor


.. py:function:: get_kernel_meshgrid(xv_input, yv_input, k_width)

   Obtains a kernel meshgrid of given spatial width k_width (in same units as meshgrid). Enforces the kernel size is odd

   :param xv_input: Meshgrid x-coordinates corresponding to the input of some operator
   :type xv_input: torch.Tensor
   :param yv_input: Meshgrid y-coordinates corresponding to the input of some operator
   :type yv_input: torch.Tensor
   :param k_width: Width of kernel in same units as meshgrid
   :type k_width: float

   :returns: Meshgrid of kernel
   :rtype: tuple[torch.Tensor, torch.Tensor]