CropToMultiplesOf

class deeptrack.optical.augmentations.CropToMultiplesOf(multiple: int | tuple[int | None, ...] | Callable[[...], int | tuple[int | None, ...]] = 1, corner: str | Callable[[...], str] = 'random', **kwargs)

Bases: Crop

Crop images so their dimensions are multiples of a given value.

The image is cropped along each axis until its size becomes a multiple of the specified value.

Parameters

multiple: PropertyLike[int | tuple[int | None, …]]

Target multiples for each axis. If a single integer is provided, the same multiple is applied to all axes. If a tuple is provided, each value corresponds to an axis. A value of None or -1 indicates that the axis should not be constrained.

corner: PropertyLike[str], optional

Top-left corner of the cropped region. - “random” selects a random valid corner. (default) - A tuple specifies the corner explicitly. - A callable receives the input array and returns a corner.

Examples

>>> import deeptrack as dt

>>> particle = dt.PointParticle(position=(32, 32))
>>> optics = dt.Fluorescence()
>>> crop_mult = dt.CropToMultiplesOf(multiple=5, corner=(0,0))
>>> image = optics(particle) >> crop_mult
>>> print(image.resolve().shape)