CoarseDropout

Targets:

image

mask

bboxes

keypoints

Image Types:uint8, float32

Randomly drop rectangular regions from image (and optionally mask). num_holes_range, hole_size_range, fill. For robustness and regularization.

This transformation is an evolution of CutOut and RandomErasing, offering more flexibility in the size, number of dropout regions, and fill values.

Arguments

num_holes_range

tuple[int, int]

[1,2]

Range (min, max) for the number of rectangular regions to drop out. Default: (1, 1)

hole_height_range

tuple[float, float] | tuple[int, int]

[0.1,0.2]

Range (min, max) for the height of dropout regions. If int, specifies absolute pixel values. If float, interpreted as a fraction of the image height. Default: (0.1, 0.2)

hole_width_range

tuple[float, float] | tuple[int, int]

[0.1,0.2]

Range (min, max) for the width of dropout regions. If int, specifies absolute pixel values. If float, interpreted as a fraction of the image width. Default: (0.1, 0.2)

fill

Value for the dropped pixels. Can be:

int or float: all channels are filled with this value
tuple: tuple of values for each channel
'random': each pixel is filled with random values
'random_uniform': each hole is filled with a single random color
'inpaint_telea': uses OpenCV Telea inpainting method
'inpaint_ns': uses OpenCV Navier-Stokes inpainting method Default: 0

fill_mask

tuple[float, ...] | float | None

Fill value for dropout regions in the mask. If None, mask regions corresponding to image dropouts are unchanged. Default: None

p

float

0.5

Probability of applying the transform. Default: 0.5

Examples

>>> import numpy as np
>>> import albumentations as A
>>> image = np.random.randint(0, 256, (100, 100, 3), dtype=np.uint8)
>>> mask = np.random.randint(0, 2, (100, 100), dtype=np.uint8)
>>> # Example with random uniform fill
>>> aug_random = A.CoarseDropout(
...     num_holes_range=(3, 6),
...     hole_height_range=(10, 20),
...     hole_width_range=(10, 20),
...     fill="random_uniform",
...     p=1.0
... )
>>> # Example with inpainting
>>> aug_inpaint = A.CoarseDropout(
...     num_holes_range=(3, 6),
...     hole_height_range=(10, 20),
...     hole_width_range=(10, 20),
...     fill="inpaint_ns",
...     p=1.0
... )
>>> transformed = aug_random(image=image, mask=mask)
>>> transformed_image, transformed_mask = transformed["image"], transformed["mask"]

Notes

The actual number and size of dropout regions are randomly chosen within the specified ranges for each application.
When using float values for hole_height_range and hole_width_range, ensure they are between 0 and 1.
This implementation includes deprecation warnings for older parameter names (min_holes, max_holes, etc.).
Inpainting methods ('inpaint_telea', 'inpaint_ns') work only with grayscale or RGB images.
For 'random_uniform' fill, each hole gets a single random color, unlike 'random' where each pixel gets its own random value.

References

CutOuthttps://arxiv.org/abs/1708.04552
Random Erasinghttps://arxiv.org/abs/1708.04896
OpenCV Inpainting methodshttps://docs.opencv.org/master/df/d3d/tutorial_py_inpainting.html

>>> import numpy as np >>> import albumentations as A >>> image = np.random.randint(0, 256, (100, 100, 3), dtype=np.uint8) >>> mask = np.random.randint(0, 2, (100, 100), dtype=np.uint8) >>> # Example with random uniform fill >>> aug_random = A.CoarseDropout( ... num_holes_range=(3, 6), ... hole_height_range=(10, 20), ... hole_width_range=(10, 20), ... fill="random_uniform", ... p=1.0 ... ) >>> # Example with inpainting >>> aug_inpaint = A.CoarseDropout( ... num_holes_range=(3, 6), ... hole_height_range=(10, 20), ... hole_width_range=(10, 20), ... fill="inpaint_ns", ... p=1.0 ... ) >>> transformed = aug_random(image=image, mask=mask) >>> transformed_image, transformed_mask = transformed["image"], transformed["mask"]