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

.. py:module:: kosmos.ml.datasets.bloodmnist_dataset







Classes
-------

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

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

   BloodMNIST dataset for blood cell classification from biomedical images.

   .. admonition:: Notes

      - Number of instances: 17,092 (11,959 train + 1,712 val + 3,421 test)
      - Number of features: 2,352 numeric (28x28x3 RGB images, flattened)
      - Classes: 8 (different blood cell types)

   .. admonition:: References

      - MedMNIST: https://medmnist.com/

   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 for blood cell types.

   .. py:property:: input_dimension

      Number of feature columns.

   .. py:property:: output_dim

      Number of distinct classes.