:py:mod:`anomalib.models.draem.utils.augmenter`
===============================================

.. py:module:: anomalib.models.draem.utils.augmenter

.. autoapi-nested-parse::

   Augmenter module to generates out-of-distribution samples for the DRAEM implementation.



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

Classes
~~~~~~~

.. autoapisummary::

   anomalib.models.draem.utils.augmenter.Augmenter




.. py:class:: Augmenter(anomaly_source_path: Optional[str] = None)

   Class that generates noisy augmentations of input images.

   :param anomaly_source_path: Path to a folder of images that will be used as source of the anomalous
   :type anomaly_source_path: Optional[str]
   :param noise. If not specified:
   :param random noise will be used instead.:

   .. py:method:: rand_augmenter(self) -> imgaug.augmenters.Sequential

      Selects 3 random transforms that will be applied to the anomaly source images.

      :returns: A selection of 3 transforms.


   .. py:method:: generate_perturbation(self, height: int, width: int, anomaly_source_path: Optional[str]) -> Tuple[numpy.ndarray, numpy.ndarray]

      Generate an image containing a random anomalous perturbation using a source image.

      :param height: height of the generated image.
      :type height: int
      :param width: (int): width of the generated image.
      :param anomaly_source_path: Path to an image file. If not provided, random noise will be used
      :type anomaly_source_path: Optional[str]
      :param instead.:

      :returns: Image containing a random anomalous perturbation, and the corresponding ground truth anomaly mask.


   .. py:method:: augment_batch(self, batch: torch.Tensor) -> Tuple[torch.Tensor, torch.Tensor]

      Generate anomalous augmentations for a batch of input images.

      :param batch: Batch of input images
      :type batch: Tensor

      :returns:

                - Augmented image to which anomalous perturbations have been added.
                - Ground truth masks corresponding to the anomalous perturbations.