:py:mod:`anomalib.models.fastflow.anomaly_map`
==============================================

.. py:module:: anomalib.models.fastflow.anomaly_map

.. autoapi-nested-parse::

   FastFlow Anomaly Map Generator Implementation.



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

Classes
~~~~~~~

.. autoapisummary::

   anomalib.models.fastflow.anomaly_map.AnomalyMapGenerator




.. py:class:: AnomalyMapGenerator(input_size: Union[omegaconf.ListConfig, Tuple])

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

   Generate Anomaly Heatmap.

   .. py:method:: forward(hidden_variables: List[torch.Tensor]) -> torch.Tensor

      Generate Anomaly Heatmap.

      This implementation generates the heatmap based on the flow maps
      computed from the normalizing flow (NF) FastFlow blocks. Each block
      yields a flow map, which overall is stacked and averaged to an anomaly
      map.

      :param hidden_variables: List of hidden variables from each NF FastFlow block.
      :type hidden_variables: List[Tensor]

      :returns: Anomaly Map.
      :rtype: Tensor