:py:mod:`anomalib.utils.callbacks.export`
=========================================

.. py:module:: anomalib.utils.callbacks.export

.. autoapi-nested-parse::

   Callback that compresses a trained model by first exporting to .onnx format, and then converting to OpenVINO IR.



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

Classes
~~~~~~~

.. autoapisummary::

   anomalib.utils.callbacks.export.ExportCallback




Attributes
~~~~~~~~~~

.. autoapisummary::

   anomalib.utils.callbacks.export.logger


.. py:data:: logger
   

   

.. py:class:: ExportCallback(input_size: Tuple[int, int], dirpath: str, filename: str, export_mode: str)

   Bases: :py:obj:`pytorch_lightning.Callback`

   Callback to compresses a trained model.

   Model is first exported to ``.onnx`` format, and then converted to OpenVINO IR.

   :param input_size: Tuple of image height, width
   :type input_size: Tuple[int, int]
   :param dirpath: Path for model output
   :type dirpath: str
   :param filename: Name of output model
   :type filename: str

   .. py:method:: on_train_end(trainer, pl_module: anomalib.models.components.AnomalyModule) -> None

      Call when the train ends.

      Converts the model to ``onnx`` format and then calls OpenVINO's model optimizer to get the
      ``.xml`` and ``.bin`` IR files.