synthval.metrics.KernelDistance
===============================

.. py:class:: synthval.metrics.KernelDistance(max_samples = 1000000, num_subsets = 100, max_subset_size = 1000)

   Bases: :py:obj:`SimilarityMetric`


   Similarity Metric that computes the Kernel distance between two distributions using provided samples.

   If the features extracted are from the last average pooling layer of the Inception model (e.g., from
   synthval.features_extraction.InceptionExtractor), this metric corresponds to the standard Kernel Inception
   Distance (KID).

   .. attribute:: max_samples

      Max number of samples to consider in the computation. To use in the case of limited time or hardware
      capabilities (default: 1000000).

      :type: int, Optional

   .. attribute:: num_subsets

      Number of subset to use for calculating the Kernel distance (default: 100).

      :type: int, Optional

   .. attribute:: max_subset_size

      Maximum size of each subset (default: 1000).

      :type: int, Optional

   .. rubric:: References

   Mikolaj Binkowski, Danica J. Sutherland, Michael Arbel, Arthur Gretton - Demystifying MMD GANs - 6th International
   Conference on Learning Representations, 2018.


   .. py:method:: calculate(real_dist_df, synth_dist_df)

      Compute the Kernel distance between two distributions using the samples
      provided.

      :param real_dist_df: Set of samples representing distribution real_dist.
      :type real_dist_df: pandas.DataFrame
      :param synth_dist_df: Set of samples representing distribution synth_dist.
      :type synth_dist_df: pandas.DataFrame

      :returns: A numpy array containing the Kernel Distance.
      :rtype: numpy.ndarray