bi]dZddlmZddlmZmZmZddlmZm Z ddl m cm cm ZddlmZddlmZmZdgZGd deZy) aImplementation of grid-based dropout augmentation. This module provides GridDropout, which creates a regular grid over the image and drops out rectangular regions according to the specified grid pattern. Unlike random dropout methods, grid dropout enforces a structured pattern of occlusions that can help models learn spatial relationships and context across the entire image space. ) annotations) AnnotatedAnyLiteral)AfterValidatorFieldN) BaseDropout)check_range_bounds nondecreasing GridDropoutceZdZdZGddej Z d dfd ZddZxZS) r aApply GridDropout augmentation to images, masks, bounding boxes, and keypoints. GridDropout drops out rectangular regions of an image and the corresponding mask in a grid fashion. This technique can help improve model robustness by forcing the network to rely on a broader context rather than specific local features. Args: ratio (float): The ratio of the mask holes to the unit size (same for horizontal and vertical directions). Must be between 0 and 1. Default: 0.5. unit_size_range (tuple[int, int] | None): Range from which to sample grid size. Default: None. Must be between 2 and the image's shorter edge. If None, grid size is calculated based on image size. holes_number_xy (tuple[int, int] | None): The number of grid units in x and y directions. First value should be between 1 and image width//2, Second value should be between 1 and image height//2. Default: None. If provided, overrides unit_size_range. random_offset (bool): Whether to offset the grid randomly between 0 and (grid unit size - hole size). If True, entered shift_xy is ignored and set randomly. Default: True. fill (tuple[float, float] | float | Literal["random", "random_uniform", "inpaint_telea", "inpaint_ns"]): 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] | float | None): Value for the dropped pixels in mask. If None, the mask is not modified. Default: None. shift_xy (tuple[int, int]): Offsets of the grid start in x and y directions from (0,0) coordinate. Only used when random_offset is False. Default: (0, 0). p (float): Probability of applying the transform. Default: 0.5. Targets: image, mask, bboxes, keypoints, volume, mask3d Image types: uint8, float32 Note: - If both unit_size_range and holes_number_xy are None, the grid size is calculated based on the image size. - The actual number of dropped regions may differ slightly from holes_number_xy due to rounding. - Inpainting methods ('inpaint_telea', 'inpaint_ns') work only with grayscale or RGB images. - For 'random_uniform' fill, each grid cell gets a single random color, unlike 'random' where each pixel gets its own random value. Example: >>> 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 standard fill value >>> aug_basic = A.GridDropout( ... ratio=0.3, ... unit_size_range=(10, 20), ... random_offset=True, ... p=1.0 ... ) >>> # Example with random uniform fill >>> aug_random = A.GridDropout( ... ratio=0.3, ... unit_size_range=(10, 20), ... fill="random_uniform", ... p=1.0 ... ) >>> # Example with inpainting >>> aug_inpaint = A.GridDropout( ... ratio=0.3, ... unit_size_range=(10, 20), ... fill="inpaint_ns", ... p=1.0 ... ) >>> transformed = aug_random(image=image, mask=mask) >>> transformed_image, transformed_mask = transformed["image"], transformed["mask"] Reference: - Paper: https://arxiv.org/abs/2001.04086 - OpenCV Inpainting methods: https://docs.opencv.org/master/df/d3d/tutorial_py_inpainting.html cTeZdZUeddZded<ded<ded <d ed <d ed <y)GridDropout.InitSchemar)gtlefloatratiobool random_offsetzmAnnotated[tuple[int, int], AfterValidator(check_range_bounds(2, None)), AfterValidator(nondecreasing)] | Noneunit_size_rangezGAnnotated[tuple[int, int], AfterValidator(check_range_bounds(0, None))]shift_xyzNAnnotated[tuple[int, int], AfterValidator(check_range_bounds(1, None))] | Noneholes_number_xyN)__name__ __module__ __qualname__rr__annotations__l/home/cdr/jupyterlab/.venv/lib/python3.12/site-packages/albumentations/augmentations/dropout/grid_dropout.py InitSchemargs2a(u(  ZYggrr!c pt ||||||_||_||_||_||_y)N)fill fill_maskp)super__init__rrrrr) selfrrrrrr#r$r% __class__s r r'zGridDropout.__init__ts? di1= ..*  rc|d}|jr |j}nItj||j|j|j\}}|d|z|d|zf}tj |||j |j|j|j}||jjdddS)a!Get parameters dependent on the data. Args: params (dict[str, Any]): Dictionary containing parameters. data (dict[str, Any]): Dictionary containing data. Returns: dict[str, Any]: Dictionary with parameters for transformation. shaperrl)holesseed) rfdropoutcalculate_grid_dimensionsrrandom_generatorgenerate_grid_holesrrrintegers)r(paramsdata image_shapegrid unit_height unit_widthr,s r get_params_dependent_on_dataz(GridDropout.get_params_dependent_on_datasWo   ''D'/&H&H$$$$%% ' #K  Nk1;q>Z3OPD,,   JJ    MM  ! !  (=(=(F(Fq)(TUUr)?TNN)rrrNr:)rrrrrtuple[int, int] | Nonerr;rztuple[int, int]r#z^tuple[float, ...] | float | Literal['random', 'random_uniform', 'inpaint_telea', 'inpaint_ns']r$z tuple[float, ...] | float | Noner%r)r3dict[str, Any]r4r<returnr<) rrr__doc__r r!r'r9 __classcell__)r)s@r r r sN` h[++ h"2626$*op6:!!!0 ! 0 ! " !m!4! !$ Vr)r> __future__rtypingrrrpydanticrr/albumentations.augmentations.dropout.functional augmentationsdropout functionalr./albumentations.augmentations.dropout.transformsr albumentations.core.pydanticr r __all__r rrr rJs;#***BBGJ /PV+PVr