kd.summaries.ShowSegmentations#

class kauldron.summaries.ShowSegmentations(*, segmentations: typing.Annotated[typing.Any, <object object at 0x7824c478ba80>], num_images: int = 5, entropy: bool = False, rearrange: str | None = None, rearrange_kwargs: typing.Mapping[str, typing.Any] | None = None)[source]

Bases: kauldron.metrics.base.Metric

Show a set of segmentations with optional reshaping.

segmentations

Key to the segmentations to display.

Type:: Any

num_images

Number of segmentations to collect and display. Default 5.

Type:: int

entropy

Whether to scale the lightness of the segments in proportion to the (normalized) per-pixel entropy of the soft-segmentation.

Type:: bool

rearrange

Optional einops string to reshape the images.

Type:: str | None

rearrange_kwargs

Optional keyword arguments for the einops reshape.

Type:: Mapping[str, Any] | None

segmentations: Annotated[Any, <object object at 0x7824c478ba80>]

num_images: int = 5

entropy: bool = False

rearrange: str | None = None

rearrange_kwargs: Mapping[str, Any] | None = None

class State( segmentations: Integer['*b h w 1'] | Float['*b h w k'], *, parent: _MetricT = _EMPTY_TYPE.EMPTY, )[source]

Bases: kauldron.metrics.auto_state.AutoState[ShowSegmentations]

Collects the first num_images segmentations.

segmentations: Integer['*b h w 1'] | Float['*b h w k']

compute() → jaxtyping.Float[Array, 'n h w #3'] | jaxtyping.Float[ndarray, 'n h w #3'][source]: Computes final metrics from intermediate values.

merge( other: kauldron.metrics.auto_state._SelfT, ) → kauldron.metrics.auto_state._SelfT[source]: Checks static fields for equality and merges data-fields.

replace(**updates): Returns a new object replacing the specified fields with new values.

get_state( segmentations: jaxtyping.Float[Array, '...'] | jaxtyping.Float[ndarray, '...'], ) → kauldron.summaries.images.ShowSegmentations.State[source]

empty() → kauldron.metrics.base.Metric.State[source]