SmoothDistTransform

Bases: OnlyInstMapTransform

available_keys `property` ¶

available_keys: set[str]

Returns set of available keys.

__init__(deduplicate: bool = True)

Generate FIM distance transforms from a label mask.

Parameters:

Name	Type	Description	Default
`deduplicate`	`bool, default=True`	Whether to fix duplicate values in the mask before transforming. This adds overhead, so use only if you know that the mask has duplicates.	`True`

__call__(inst: ndarray, **kwargs) -> np.ndarray

Generate smooth distance transforms.

Parameters inst (np.ndarray): Instance labelled mask. Shape (H, W).

Returns:

Type	Description
`ndarray`	np.ndarray: Smooth distance transforms of objects. Shape: (H, W). Dtype: float64.