CollaborativeCoding.dataloaders.usps_0_6
========================================

.. py:module:: CollaborativeCoding.dataloaders.usps_0_6

.. autoapi-nested-parse::

   Dataset class for USPS dataset with labels 0-6.

   This module contains the Dataset class for the USPS dataset with labels 0-6.



Classes
-------

.. autoapisummary::

   CollaborativeCoding.dataloaders.usps_0_6.USPSDataset0_6


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

.. py:class:: USPSDataset0_6(data_path: pathlib.Path, sample_ids: list, train: bool = False, transform=None, nr_channels=1)

   Bases: :py:obj:`torch.utils.data.Dataset`


   Dataset class for USPS dataset with labels 0-6.

   Args
   ----
   data_path : pathlib.Path
       Path to the data directory.
   train : bool, optional
       Mode of the dataset.
   transform : callable, optional
       A function/transform that takes in a sample and returns a transformed version.
   download : bool, optional
       Whether to download the Dataset.

   Attributes
   ----------
   filepath : pathlib.Path
       Path to the USPS dataset file.
   mode : str
       Mode of the dataset, either train or test.
   transform : callable
       A function/transform that takes in a sample and returns a transformed version.
   idx : numpy.ndarray
       Indices of samples with labels 0-6.
   num_classes : int
       Number of classes in the dataset

   Methods
   -------
   _index()
       Get indices of samples with labels 0-6.
   _load_data(idx)
       Load data and target label from the dataset.
   __len__()
       Get the number of samples in the dataset.
   __getitem__(idx)
       Get a sample from the dataset.

   Examples
   --------
   >>> from torchvision import transforms
   >>> from src.datahandlers import USPSDataset0_6
   >>> transform = transforms.Compose([
   ...     transforms.Resize((16, 16)),
   ...     transforms.ToTensor()
   ... ])
   >>> dataset = USPSDataset0_6(
   ...     data_path="data",
   ...     transform=transform
   ...     download=True,
   ...     train=True,
   ... )
   >>> len(dataset)
   5460
   >>> data, target = dataset[0]
   >>> data.shape
   (1, 16, 16)
   >>> target
   tensor([1., 0., 0., 0., 0., 0., 0.])


   .. py:attribute:: filename
      :value: 'usps.h5'



   .. py:attribute:: num_classes
      :value: 7



   .. py:attribute:: filepath


   .. py:attribute:: transform
      :value: None



   .. py:attribute:: mode
      :value: 'test'



   .. py:attribute:: sample_ids


   .. py:attribute:: nr_channels
      :value: 1



   .. py:method:: __len__()


   .. py:method:: __getitem__(id)