OrsGridBasedSAM_9fabead7dc3411f08046c85ea97229ba

OrsGridBasedSAM - A plugin that provides a simple button interface for grid-based SAM functionality. This plugin is embedded within OrsAISegmentationTools and should not create its own dock widget.

Class Code

class OrsPythonPlugins.OrsGridBasedSAM_9fabead7dc3411f08046c85ea97229ba.OrsGridBasedSAM_9fabead7dc3411f08046c85ea97229ba.OrsGridBasedSAM_9fabead7dc3411f08046c85ea97229ba(*args, **kwargs)
class AutoMaskGeneratorParameters(points_per_side: int | None = 32, pred_iou_thresh: float = 0.88, stability_score_thresh: float = 0.95, box_nms_thresh: float = 0.7, point_grids: list[numpy.ndarray] | None = None, min_mask_region_area: int = 10)
class AutoPointMethod(*values)
interfacemethod applyGridBasedSAM(sliceChannels: Annotated[list[Channel], MinLen(min_length=1)], timeStep: int, autoPointMethod: str, pointsNb: int, predIoUThreshold: float, stabilityScoreThreshold: float, boxNMSThreshold: float) → str

Compute slice channels segmentation

Parameters:

  • sliceChannels (ORSModel.ors.Channel) [count=[1, 3]] – The slice channels on which to perform the segmentation

  • timeStep (int) – The time step of the segmentation

  • autoPointMethod (str) – The method used to get the sampling points grid

  • pointsNb (int) – The total number of sampling points

  • predIoUThreshold (float) – A quality threshold for the output masks

  • stabilityScoreThreshold (float) – A stability score threshold based on how much the output mask varies with changes in its binarization threshold

  • boxNMSThreshold (float) – The box IoU cutoff used by non-maximal suppression to filter duplicate masks

Returns:

errMsg (str) – The error message

cleanup()

Deletes the variables managed by the plugin. It is the place to remove callbacks and other references to Python objects that would prevent them to be garbage collected. This method is called during the process of deletion of the plugin. It calls for the cleanup and deletion of the forms.

interfacemethod computeCurrentSlices(inputChannels: Annotated[list[Channel], MinLen(min_length=1)], viewBoundedPlane: Rectangle) → Annotated[list[Channel], MinLen(min_length=0)]

Compute slice channels

Parameters:
Returns:

sliceChannels (ORSModel.ors.Channel) [count=[0, 3]] – The slice channels

classmethod getMainFormClass()

Gets the class of the main form

Returns:

output –