dataeval.metrics.bias.CoverageOutput ==================================== .. py:class:: dataeval.metrics.bias.CoverageOutput Output class for :func:`coverage` :term:`bias` metric .. attribute:: indices Array of uncovered indices :type: NDArray[np.intp] .. attribute:: radii Array of critical value radii :type: NDArray[np.float64] .. attribute:: critical_value Radius for :term:`coverage` :type: float .. py:method:: plot(images, top_k = 6) Plot the top k images together for visualization :param images: Original images (not embeddings) in (N, C, H, W) or (N, H, W) format :type images: ArrayLike :param top_k: Number of images to plot (plotting assumes groups of 3) :type top_k: int, default 6 :rtype: matplotlib.figure.Figure