:py:mod:`data`
==============

.. py:module:: data

.. autoapi-nested-parse::

   Loading images and other data from the file-system.



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

Classes
~~~~~~~

.. autoapisummary::

   data.ImageLoader
   data.LoadImagesModule




.. py:class:: ImageLoader

   Loads images from the file-system.

   .. py:attribute:: image_directory
      :annotation: :str

      The image directory to load images recursively from.


   .. py:attribute:: image_size
      :annotation: :Tuple[int, int]

      The size (height, width) to resize all images to.


   .. py:attribute:: extension
      :annotation: :str = jpg

      The extension (without a leading period) that all image files must match.


   .. py:attribute:: rgb
      :annotation: :bool = True

      When true, images are always loaded as RGB. when false, they are loaded as grayscale.


   .. py:attribute:: batch_size
      :annotation: :int = 16

      How many images should be in a batch.


   .. py:attribute:: num_workers
      :annotation: :int = 1

      The number of workers for the data-loader.


   .. py:method:: load_images(self) -> torch.utils.data.DataLoader

      Load all images recursively from a directory.

      :returns: a data-loader with all the images that match the extension recursively in a directory.


   .. py:method:: load_images_split_two(self, ratio_validation: float = 0.3) -> Tuple[torch.utils.data.DataLoader, torch.utils.data.DataLoader]

      Load all images recursively from a directory, and split into *training and validation batches*.

      :param ratio_validation: a number between 0 and 1 determining linearly how many elements belong in the
                               validation set e.g. 0.4 would try and place 40% approximately of elements into the
                               second partition.
      :returns: the loaded images, split into training and validation data respectively.


   .. py:method:: load_images_split_three(self, ratio_validation: float = 0.3, ratio_test: float = 0.2) -> Tuple[torch.utils.data.DataLoader, torch.utils.data.DataLoader, torch.utils.data.DataLoader]

      Load all images recursively from a directory, and split into *training, validation and test batches*.

      :param ratio_validation: a number between 0 and 1 determining linearly how many elements belong in the
                               validation set e.g. 0.4 would try and place 40% approximately of elements into the
                               second batch.
      :param ratio_test: a number between 0 and 1 determining linearly how many elements belong in the validation
                               set e.g. 0.2 would try and place 20% approximately of elements into the third batch.
      :returns: the loaded images, split into training and validation data and test data respectively.



.. py:class:: LoadImagesModule(image_directory: str, image_size: int, extension: str = 'jpg', rgb: bool = True, batch_size: int = 16, num_workers: int = 1, ratio_validation: float = 0.3, ratio_test: float = 0.2)

   Bases: :py:obj:`pytorch_lightning.LightningDataModule`

   A Lightning data-module for loading images recursively from a file-system directory.

   .. py:method:: prepare_data(self) -> None

      Overrides :class:`pl.LightningDataModule`.


   .. py:method:: setup(self, stage: Optional[pytorch_lightning.trainer.states.TrainerFn] = None)

      Overrides :class:`pl.LightningDataModule`.


   .. py:method:: train_dataloader(self)

      Overrides :class:`pl.LightningDataModule`.


   .. py:method:: val_dataloader(self)

      Overrides :class:`pl.LightningDataModule`.


   .. py:method:: test_dataloader(self)

      Overrides :class:`pl.LightningDataModule`.


   .. py:method:: predict_dataloader(self)

      Overrides :class:`pl.LightningDataModule`.