CoverageOutput

class dataeval.metrics.bias.CoverageOutput(indices: ndarray[Any, dtype[int64]], radii: ndarray[Any, dtype[float64]], critical_value: float)

Output class for coverage() bias metric

indices

Array of uncovered indices

Type:

NDArray[np.intp]

radii

Array of critical value radii

Type:

NDArray[np.float64]

critical_value

Radius for coverage

Type:

float

plot(images: ArrayLike, top_k: int = 6) → Figure

Plot the top k images together for visualization

Parameters:

• images (ArrayLike) – Original images (not embeddings) in (N, C, H, W) or (N, H, W) format

• top_k (int, default 6) – Number of images to plot (plotting assumes groups of 3)

Return type:

matplotlib.figure.Figure