dcnum.segm.segm_torch
=====================

.. py:module:: dcnum.segm.segm_torch


Submodules
----------

.. toctree::
   :maxdepth: 1

   /autoapi/dcnum/segm/segm_torch/segm_torch_base/index
   /autoapi/dcnum/segm/segm_torch/segm_torch_mpo/index
   /autoapi/dcnum/segm/segm_torch/segm_torch_sto/index
   /autoapi/dcnum/segm/segm_torch/torch_model/index
   /autoapi/dcnum/segm/segm_torch/torch_postproc/index
   /autoapi/dcnum/segm/segm_torch/torch_preproc/index
   /autoapi/dcnum/segm/segm_torch/torch_setup/index


Classes
-------

.. autoapisummary::

   dcnum.segm.segm_torch.SegmentTorchMPO
   dcnum.segm.segm_torch.SegmentTorchSTO


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

.. py:class:: SegmentTorchMPO(*, kwargs_mask: dict | None = None, debug: bool = False, **kwargs)

   Bases: :py:obj:`dcnum.segm.segm_torch.segm_torch_base.TorchSegmenterBase`, :py:obj:`dcnum.segm.segmenter_mpo.MPOSegmenter`


   Base segmenter class

   This is the base segmenter class for the multiprocessing operation
   segmenter :class:`.segmenter_mpo.MPOSegmenter` (multiple
   subprocesses are spawned and each of them works on a queue of images)
   and the single-threaded operation segmenter
   :class:`.segmenter_sto.STOSegmenter` (e.g. for batch segmentation on
   a GPU).

   :param kwargs_mask: Keyword arguments for mask post-processing (see `process_labels`)
   :type kwargs_mask: dict
   :param debug: Enable debugging mode (e.g. CPU segmenter runs in one thread)
   :type debug: bool
   :param kwargs: Additional, optional keyword arguments for `segment_batch`.


   .. py:method:: segment_algorithm(image, *, model_file: str | None = None)
      :staticmethod:


      :param image: event image
      :type image: 2d ndarray
      :param model_file: path to or name of a dcnum model file (.dcnm); if only a
                         name is provided, then the "torch_model_files" directory
                         paths are searched for the file name
      :type model_file: str

      :returns: **mask** -- mask or labeling image for the give index
      :rtype: 2d boolean or integer ndarray



.. py:class:: SegmentTorchSTO(*, kwargs_mask: dict | None = None, debug: bool = False, **kwargs)

   Bases: :py:obj:`dcnum.segm.segm_torch.segm_torch_base.TorchSegmenterBase`, :py:obj:`dcnum.segm.STOSegmenter`


   Base segmenter class

   This is the base segmenter class for the multiprocessing operation
   segmenter :class:`.segmenter_mpo.MPOSegmenter` (multiple
   subprocesses are spawned and each of them works on a queue of images)
   and the single-threaded operation segmenter
   :class:`.segmenter_sto.STOSegmenter` (e.g. for batch segmentation on
   a GPU).

   :param kwargs_mask: Keyword arguments for mask post-processing (see `process_labels`)
   :type kwargs_mask: dict
   :param debug: Enable debugging mode (e.g. CPU segmenter runs in one thread)
   :type debug: bool
   :param kwargs: Additional, optional keyword arguments for `segment_batch`.


   .. py:method:: log_info(logger, gpu_id=None)

      Allow segmenter to write informative log messages



   .. py:method:: is_available()
      :staticmethod:


      Subclasses may override this method e.g. if dependencies exist



   .. py:method:: _segment_in_batches(images, model, model_meta, device)
      :staticmethod:


      Segment image data in batches

      Return mask array with same shape as `images`.



   .. py:method:: segment_algorithm(images, gpu_id: str | None = None, *, model_file: str | None = None)
      :staticmethod:


      :param images: array of N event images of shape (N, H, W)
      :type images: 3d ndarray
      :param gpu_id: optional argument specifying the GPU to use
      :type gpu_id: str
      :param model_file: path to or name of a dcnum model file (.dcnm); if only a
                         name is provided, then the "torch_model_files" directory
                         paths are searched for the file name
      :type model_file: str

      :returns: **mask** -- mask images of shape (N, H, W)
      :rtype: 2d boolean or integer ndarray