kd.metrics.Ssim#

class kauldron.metrics.Ssim( *, pred: typing.Annotated[typing.Any, <object object at 0x7824c478ba80>] = '__KEY_REQUIRED__', target: typing.Annotated[typing.Any, <object object at 0x7824c478ba80>] = '__KEY_REQUIRED__', mask: typing.Annotated[typing.Any, <object object at 0x7824c478ba80>] | None = None, in_vrange: tuple[float, float] = (0.0, 1.0), filter_size: int = 11, filter_sigma: float = 1.5, k1: float = 0.01, k2: float = 0.03, )[source]

Bases: kauldron.metrics.base.Metric

Structural similarity (SSIM).

pred: Annotated[Any, <object object at 0x7824c478ba80>] = '__KEY_REQUIRED__'

target: Annotated[Any, <object object at 0x7824c478ba80>] = '__KEY_REQUIRED__'

mask: Annotated[Any, <object object at 0x7824c478ba80>] | None = None

in_vrange: tuple[float, float] = (0.0, 1.0)

filter_size: int = 11

filter_sigma: float = 1.5

k1: float = 0.01

k2: float = 0.03

class State( total: "Float['']", count: "Float['']", *, parent: '_MetricT' = <_EMPTY_TYPE.EMPTY: 1>, )[source]

Bases: kauldron.metrics.base_state.AverageState

merge( other: kauldron.metrics.base_state.AverageState, ) → kauldron.metrics.base_state.AverageState[source]

Returns a new state that is the accumulation of self and other.

Parameters:: other – A State whose intermediate values should be accumulated onto the values of self.
Returns:: A new State that accumulates the value from both self and other.

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

get_state( pred: jaxtyping.Float[Array, '*b h w c'] | jaxtyping.Float[ndarray, '*b h w c'], target: jaxtyping.Float[Array, '*b h w c'] | jaxtyping.Float[ndarray, '*b h w c'], mask: jaxtyping.Bool[Array, '*b 1'] | jaxtyping.Bool[ndarray, '*b 1'] | jaxtyping.Float[Array, '*b 1'] | jaxtyping.Float[ndarray, '*b 1'] | None = None, ) → kauldron.metrics.image.Ssim.State[source]

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