delta.utilities.getTrackingScores

delta.utilities.getTrackingScores(labels: ndarray[Any, dtype[uint16]], outputs: ndarray[Any, dtype[float32]], boxes: Optional[List[Tuple[CroppingBox, CroppingBox]]] = None) → Optional[ndarray[Any, dtype[float32]]]

Get overlap scores between input/target cells and tracking outputs

Parameters

inputs2D array of floats

Segmentation mask of input/target cells that the tracking U-Net is tracking against. (ie segmentation mask of the ‘current’/’new’ frame)

outputs4D array of floats

Tracking U-Net output.

boxeslist of dict, optional

Cropping box and fill box to re-place output prediction masks in the original coordinates to index the labels frame.

Returns

scores2D array of floats, or None

Overlap scores matrix between tracking predictions and current segmentation mask for each new-old cell.