VisualStatsOutput

class dataeval.metrics.stats.VisualStatsOutput(source_index: list[SourceIndex], box_count: NDArray[np.uint16], brightness: NDArray[np.float16], sharpness: NDArray[np.float16], contrast: NDArray[np.float16], darkness: NDArray[np.float16], missing: NDArray[np.float16], zeros: NDArray[np.float16], percentiles: NDArray[np.float16])

Output class for visualstats() stats metric

brightness

Brightness of the images

Type:

NDArray[np.float16]

sharpness

Blurriness of the images

Type:

NDArray[np.float16]

contrast

Image contrast ratio

Type:

NDArray[np.float16]

darkness

Darkness of the images

Type:

NDArray[np.float16]

missing

Percentage of the images with missing pixels

Type:

NDArray[np.float16]

zeros

Percentage of the images with zero value pixels

Type:

NDArray[np.float16]

percentiles

Percentiles of the pixel values of the images with quartiles of (0, 25, 50, 75, 100)

Type:

NDArray[np.float16]

get_channel_mask(channel_index: int | Iterable[int] | None, channel_count: int | Iterable[int] | None = None) → list[bool]

Boolean mask for results filtered to specified channel index and optionally the count of the channels per image.

Parameters:

• channel_index (int | Iterable[int] | None) – Index or indices of channel(s) to filter for

• channel_count (int | Iterable[int] | None) – Optional count(s) of channels to filter for