:py:mod:`anomalib.models.patchcore`
===================================

.. py:module:: anomalib.models.patchcore

.. autoapi-nested-parse::

   PatchCore model.



Submodules
----------
.. toctree::
   :titlesonly:
   :maxdepth: 1

   anomaly_map/index.rst
   lightning_model/index.rst
   torch_model/index.rst


Package Contents
----------------

Classes
~~~~~~~

.. autoapisummary::

   anomalib.models.patchcore.Patchcore
   anomalib.models.patchcore.PatchcoreLightning




.. py:class:: Patchcore(input_size: Tuple[int, int], backbone: str, layers: List[str], pre_trained: bool = True, coreset_sampling_ratio: float = 0.1, num_neighbors: int = 9)

   Bases: :py:obj:`anomalib.models.components.AnomalyModule`

   PatchcoreLightning Module to train PatchCore algorithm.

   :param input_size: Size of the model input.
   :type input_size: Tuple[int, int]
   :param backbone: Backbone CNN network
   :type backbone: str
   :param layers: Layers to extract features from the backbone CNN
   :type layers: List[str]
   :param pre_trained: Boolean to check whether to use a pre_trained backbone.
   :type pre_trained: bool, optional
   :param coreset_sampling_ratio: Coreset sampling ratio to subsample embedding.
                                  Defaults to 0.1.
   :type coreset_sampling_ratio: float, optional
   :param num_neighbors: Number of nearest neighbors. Defaults to 9.
   :type num_neighbors: int, optional

   .. py:method:: configure_optimizers() -> None

      Configure optimizers.

      :returns: Do not set optimizers by returning None.
      :rtype: None


   .. py:method:: training_step(batch, _batch_idx)

      Generate feature embedding of the batch.

      :param batch: Batch containing image filename, image, label and mask
      :type batch: Dict[str, Any]
      :param _batch_idx: Batch Index
      :type _batch_idx: int

      :returns: Embedding Vector
      :rtype: Dict[str, np.ndarray]


   .. py:method:: on_validation_start() -> None

      Apply subsampling to the embedding collected from the training set.


   .. py:method:: validation_step(batch, _)

      Get batch of anomaly maps from input image batch.

      :param batch: Batch containing image filename,
                    image, label and mask
      :type batch: Dict[str, Any]
      :param _: Batch Index
      :type _: int

      :returns: Image filenames, test images, GT and predicted label/masks
      :rtype: Dict[str, Any]



.. py:class:: PatchcoreLightning(hparams)

   Bases: :py:obj:`Patchcore`

   PatchcoreLightning Module to train PatchCore algorithm.

   :param hparams: Model params
   :type hparams: Union[DictConfig, ListConfig]