:py:mod:`kosmos.ml.datasets.fashion_dataset`
============================================

.. py:module:: kosmos.ml.datasets.fashion_dataset







Classes
-------

.. py:class:: FashionDataset(*, min_max_scaler: bool = True)

   Bases: :py:class:`kosmos.ml.datasets.dataset.SLDataset`

   Fashion MNIST dataset for multiclass classification.

   .. admonition:: Notes

      - Number of instances: 70,000 (60,000 train + 10,000 test)
      - Number of features: 784 numeric (28x28 pixel images, flattened)
      - Classes: 10 (balanced; clothing categories: T-shirt/top, Trouser, Pullover,
          Dress, Coat, Sandal, Shirt, Sneaker, Bag, Ankle boot)

   .. admonition:: References

      - OpenML — Fashion-MNIST dataset: https://www.openml.org/d/40996

   Initialize the dataset.

   :param min_max_scaler: Whether to apply min-max scaling to the features.
   :type min_max_scaler: bool




   |

   .. rubric:: Properties

   .. py:property:: class_names

      Return human-readable class labels of clothing categories.

   .. py:property:: input_dimension

      Number of feature columns.

   .. py:property:: output_dim

      Number of distinct classes.