zensvi.cv.Segmenter
===================

.. py:class:: zensvi.cv.Segmenter(dataset='cityscapes', task='semantic', device=None, verbosity=1)

   A class for performing semantic and panoptic segmentation on images.

   The models used are from the Mask2Former (https://huggingface.co/docs/transformers/model_doc/mask2former).

   .. attribute:: device

      The device to run the model on (e.g., "cuda" or "cpu").

      :type: str

   .. attribute:: dataset

      The name of the dataset (e.g., "cityscapes" or "mapillary").

      :type: str

   .. attribute:: task

      The type of segmentation task (e.g., "semantic" or "panoptic").

      :type: str

   .. attribute:: model_name

      The name of the pre-trained model corresponding to the dataset and task.

      :type: str

   .. attribute:: model

      The segmentation model.

   .. attribute:: processor

      The image processor for the model.

   .. attribute:: color_map

      A mapping of class IDs to colors.

   .. attribute:: label_map

      A mapping of class IDs to labels.

   .. attribute:: id_to_name_map

      A mapping of label IDs to label names.

   .. attribute:: verbosity

      Level of verbosity for progress bars (0=no progress, 1=outer loops only, 2=all loops)

      :type: int

   :param dataset: The name of the dataset (default is "cityscapes").
   :type dataset: str
   :param task: The type of task (default is "semantic").
   :type task: str
   :param device: The device to run the model on (e.g., "cuda" or "cpu"). If None, the default device will be used.
   :type device: str, optional
   :param verbosity: Level of verbosity for progress bars (0=no progress, 1=outer loops only, 2=all loops). Default is 1.
   :type verbosity: int, optional

   :returns: None


   .. py:method:: segment(dir_input: Union[str, pathlib.Path], dir_image_output: Union[str, pathlib.Path, None] = None, dir_summary_output: Union[str, pathlib.Path, None] = None, batch_size=1, save_image_options='segmented_image blend_image', save_format='json csv', csv_format='long', max_workers: Union[int, None] = None)

      Processes a batch of images for segmentation, saves the segmented images and
      summary statistics.

      This method handles the processing of images for segmentation, managing input/output directories,
      saving options, and parallel processing settings. The method requires specifying an input directory
      or a path to a single image and supports optional saving of output images and segmentation summaries.

      :param dir_input: Input directory or path to a single image file
      :param dir_image_output: Output directory where segmented images are saved
      :param dir_summary_output: Output directory where segmentation summary files are saved
      :param batch_size: Batch size for processing images (Default: 1)
      :param save_image_options: Options for saving images ("segmented_image blend_image")
      :param save_format: Format for saving summary files ("json csv")
      :param csv_format: Format for CSV summary files ("long" or "wide")
      :param max_workers: Maximum number of workers for parallel processing

      :returns: The method does not return any value but saves the processed results to specified directories.
      :rtype: None

      :raises ValueError: If neither dir_image_output nor dir_summary_output is provided
      :raises ValueError: If the input path is neither a file nor a directory



   .. py:method:: calculate_pixel_ratio_post_process(dir_input, dir_output, save_format='json csv')

      Calculates the pixel ratio of different classes present in the segmented
      images and saves the results in either JSON or CSV format.

      :param dir_input: A string or Path object representing the input directory containing the segmented images.
      :param dir_output: A string or Path object representing the output directory where the pixel ratio results will be saved.
      :param save_format: A list containing the file formats in which the results will be saved. The allowed file formats are "json" and "csv". The default value is "json csv".

      :returns: None