PixelDropout

Description

Drops random pixels from the image.

    This transform randomly sets pixels in the image to a specified value, effectively "dropping out" those pixels.
    It can be applied to both the image and its corresponding mask.

    Args:
        dropout_prob (float): Probability of dropping out each pixel. Should be in the range [0, 1].
            Default: 0.01

        per_channel (bool): If True, the dropout mask will be generated independently for each channel.
            If False, the same dropout mask will be applied to all channels.
            Default: False

        drop_value (float | Sequence[float] | None): Value to assign to the dropped pixels.
            If None, the value will be randomly sampled for each application:
                - For uint8 images: Random integer in [0, 255]
                - For float32 images: Random float in [0, 1]
            If a single number, that value will be used for all dropped pixels.
            If a sequence, it should contain one value per channel.
            Default: 0

        mask_drop_value (float | Sequence[float] | None): Value to assign to dropped pixels in the mask.
            If None, the mask will remain unchanged.
            If a single number, that value will be used for all dropped pixels in the mask.
            If a sequence, it should contain one value per channel of the mask.
            Note: Only applicable when per_channel=False.
            Default: None

        always_apply (bool): If True, the transform will always be applied.
            Default: False

        p (float): Probability of applying the transform. Should be in the range [0, 1].
            Default: 0.5

    Targets:
        image, mask, bboxes, keypoints

    Image types:
        uint8, float32

    Note:
        - When applied to bounding boxes, this transform may cause some boxes to have zero area
          if all pixels within the box are dropped. Such boxes will be removed.
        - When applied to keypoints, keypoints that fall on dropped pixels will be removed if
          the keypoint processor is configured to remove invisible keypoints.
        - The 'per_channel' option is not supported for mask dropout. If you need to drop pixels
          in a multi-channel mask independently, consider applying this transform multiple times
          with per_channel=False.

    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)
        >>> transform = A.PixelDropout(dropout_prob=0.1, per_channel=True, p=1.0)
        >>> result = transform(image=image, mask=mask)
        >>> dropped_image, dropped_mask = result['image'], result['mask']
    

Parameters

• dropout_prob: float (default: 0.01)
• per_channel: bool (default: false)
• drop_value: float | tuple[float, float] | None (default: 0)
• mask_drop_value: float | tuple[float, float] | None (default: null)
• p: float (default: 0.5)

Targets

• Image
• Mask
• BBoxes
• Keypoints