:py:mod:`anomalib.models.dfm.lightning_model`
=============================================

.. py:module:: anomalib.models.dfm.lightning_model

.. autoapi-nested-parse::

   DFM: Deep Feature Kernel Density Estimation.



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

Classes
~~~~~~~

.. autoapisummary::

   anomalib.models.dfm.lightning_model.Dfm
   anomalib.models.dfm.lightning_model.DfmLightning




Attributes
~~~~~~~~~~

.. autoapisummary::

   anomalib.models.dfm.lightning_model.logger


.. py:data:: logger
   

   

.. py:class:: Dfm(backbone: str, layer: str, pre_trained: bool = True, pooling_kernel_size: int = 4, pca_level: float = 0.97, score_type: str = 'fre')

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

   DFM: Deep Featured Kernel Density Estimation.

   :param backbone: Backbone CNN network
   :type backbone: str
   :param layer: Layer to extract features from the backbone CNN
   :type layer: str
   :param pre_trained: Boolean to check whether to use a pre_trained backbone.
   :type pre_trained: bool, optional
   :param pooling_kernel_size: Kernel size to pool features extracted from the CNN.
                               Defaults to 4.
   :type pooling_kernel_size: int, optional
   :param pca_level: Ratio from which number of components for PCA are calculated.
                     Defaults to 0.97.
   :type pca_level: float, optional
   :param score_type: Scoring type. Options are `fre` and `nll`. Defaults to "fre".
   :type score_type: str, optional
   :param nll: for Gaussian modeling, fre: pca feature reconstruction error

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

      DFM doesn't require optimization, therefore returns no optimizers.


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

      Training Step of DFM.

      For each batch, features are extracted from the CNN.

      :param batch: Input batch
      :type batch: Dict[str, Tensor]
      :param _: Index of the batch.

      :returns: Deep CNN features.


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

      Fit a PCA transformation and a Gaussian model to dataset.


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

      Validation Step of DFM.

      Similar to the training step, features are extracted from the CNN for each batch.

      :param batch: Input batch
      :type batch: List[Dict[str, Any]]

      :returns: Dictionary containing FRE anomaly scores and ground-truth.



.. py:class:: DfmLightning(hparams: Union[omegaconf.DictConfig, omegaconf.ListConfig])

   Bases: :py:obj:`Dfm`

   DFM: Deep Featured Kernel Density Estimation.

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