Percentile

class deeptrack.statistics.Percentile(feature: Feature | None = None, q: float = 95, axis: int | tuple[int, ...] | None = None, keepdims: bool = False, distributed: bool = True, **kwargs: Any)

Bases: Reducer

Compute the q-th percentile of the data along the specified axis.

Parameters

feature: Feature, optional

If not None, the output of this feature is used as the input.

q: float

Percentile to compute, 0 through 100.

axis: int or tuple of int or None

The axis or axes along which the percentile is performed. If None, the percentile is performed over all axes.

keepdims: bool

Whether to keep the singleton dimensions after reducing or squeezing them.

distributed: bool

Whether to apply the reducer to each image in the input list individually.

**kwargs: Any

Additional keyword arguments passed to the parent class and the percentile function.