albumentations.augmentations.dropout.guided_coarse_dropout

View Source on GitHub

Apply coarse dropout within a caller-supplied binary region while preserving selected bounding boxes and filtering annotations by the actual dropout mask.

Members

classGuidedCoarseDropout

GuidedCoarseDropoutclass

GuidedCoarseDropout(
    region_key: str = dropout_region,
    protected_bbox_labels: list[str | int | float] | None,
    protection_margin: float = 0.0,
    num_holes_range: tuple[int, int] = (1, 1),
    hole_height_range: tuple[float, float] = (0.05, 0.2),
    hole_width_range: tuple[float, float] = (0.05, 0.2),
    fill: float | tuple[float, ...] | random | random_uniform | inpaint_telea | inpaint_ns | grayscale = 0,
    fill_mask: tuple[float, ...] | float | None,
    p: float = 0.5
)

Apply coarse dropout within a caller-supplied binary region while preserving selected bounding boxes and filtering annotations by the actual dropout mask. The caller supplies a two-dimensional binary region as top-level metadata. A pixel value of True or 1 permits dropout; False or 0 leaves the pixel unchanged. Hole centers are sampled uniformly over the entire eligible region, after subtracting protected bounding boxes and their margins.

Parameters

Name	Type	Default	Description
region_key	str	dropout_region	Top-level key containing the binary (H, W) dropout region. Default: "dropout_region".
protected_bbox_labels	One of: list[str \| int \| float] None	-	Labels of boxes to protect. String labels use the configured bbox label encoder. Default: None.
protection_margin	float	0.0	Relative expansion applied to every protected box side. A margin m expands horizontally by m * box_width and vertically by m * box_height. Default: 0.0.
num_holes_range	tuple[int, int]	(1, 1)	Inclusive number of holes sampled per image. Default: (1, 1).
hole_height_range	tuple[float, float]	(0.05, 0.2)	Hole-height fraction of the full image height. Default: (0.05, 0.20).
hole_width_range	tuple[float, float]	(0.05, 0.2)	Hole-width fraction of the full image width. Default: (0.05, 0.20).
fill	One of: float tuple[float, ...] random random_uniform inpaint_telea inpaint_ns grayscale	0	Value used for dropped image pixels. Default: 0.
fill_mask	One of: tuple[float, ...] float None	-	Value used for dropped mask pixels. None leaves masks unchanged. Default: None.
p	float	0.5	Probability of applying the transform. Default: 0.5.

Examples

>>> import albumentations as A
>>> import numpy as np
>>> image = np.full((100, 100, 3), 255, dtype=np.uint8)
>>> dropout_region = np.zeros((100, 100), dtype=np.uint8)
>>> dropout_region[20:80, 20:80] = 1
>>> transform = A.Compose(
...     [A.GuidedCoarseDropout(fill=0, p=1.0)],
...     bbox_params=A.BboxParams(coord_format="pascal_voc", label_fields=["labels"]),
... )
>>> result = transform(
...     image=image,
...     dropout_region=dropout_region,
...     bboxes=[[40, 40, 60, 60]],
...     labels=["person"],
... )

Notes

- The region is aligned metadata and is returned unchanged. Place this transform before geometry changes unless the caller has already aligned the region to their coordinates. - If no eligible pixels remain, the transform is a no-op. - fill="random_uniform" samples one value per original hole, including holes whose rectangular footprint is clipped by the eligible region.