Spatter

Description

Apply spatter transform. It simulates corruption which can occlude a lens in the form of rain or mud.

    Args:
        mean (float, or tuple of floats): Mean value of normal distribution for generating liquid layer.
            If single float mean will be sampled from `(0, mean)`
            If tuple of float mean will be sampled from range `(mean[0], mean[1])`.
            If you want constant value use (mean, mean).
            Default (0.65, 0.65)
        std (float, or tuple of floats): Standard deviation value of normal distribution for generating liquid layer.
            If single float the number will be sampled from `(0, std)`.
            If tuple of float std will be sampled from range `(std[0], std[1])`.
            If you want constant value use (std, std).
            Default: (0.3, 0.3).
        gauss_sigma (float, or tuple of floats): Sigma value for gaussian filtering of liquid layer.
            If single float the number will be sampled from `(0, gauss_sigma)`.
            If tuple of float gauss_sigma will be sampled from range `(gauss_sigma[0], gauss_sigma[1])`.
            If you want constant value use (gauss_sigma, gauss_sigma).
            Default: (2, 3).
        cutout_threshold (float, or tuple of floats): Threshold for filtering liqued layer
            (determines number of drops). If single float it will used as cutout_threshold.
            If single float the number will be sampled from `(0, cutout_threshold)`.
            If tuple of float cutout_threshold will be sampled from range `(cutout_threshold[0], cutout_threshold[1])`.
            If you want constant value use `(cutout_threshold, cutout_threshold)`.
            Default: (0.68, 0.68).
        intensity (float, or tuple of floats): Intensity of corruption.
            If single float the number will be sampled from `(0, intensity)`.
            If tuple of float intensity will be sampled from range `(intensity[0], intensity[1])`.
            If you want constant value use `(intensity, intensity)`.
            Default: (0.6, 0.6).
        mode (string, or list of strings): Type of corruption. Currently, supported options are 'rain' and 'mud'.
             If list is provided type of corruption will be sampled list. Default: ("rain").
        color (list of (r, g, b) or dict or None): Corruption elements color.
            If list uses provided list as color for specified mode.
            If dict uses provided color for specified mode. Color for each specified mode should be provided in dict.
            If None uses default colors (rain: (238, 238, 175), mud: (20, 42, 63)).
        p (float): probability of applying the transform. Default: 0.5.

    Targets:
        image

    Image types:
        uint8, float32

    Reference:
        https://arxiv.org/abs/1903.12261
        https://github.com/hendrycks/robustness/blob/master/ImageNet-C/create_c/make_imagenet_c.py

    

Parameters

• p: float (default: 0.5)
• mean: int | tuple[int, int] | float | tuple[float, float] (default: (0.65, 0.65))
• std: int | tuple[int, int] | float | tuple[float, float] (default: (0.3, 0.3))
• gauss_sigma: int | tuple[int, int] | float | tuple[float, float] (default: (2, 2))
• cutout_threshold: int | tuple[int, int] | float | tuple[float, float] (default: (0.68, 0.68))
• intensity: int | tuple[int, int] | float | tuple[float, float] (default: (0.6, 0.6))
• mode: Literal['rain', 'mud'] | Sequence[Literal['rain', 'mud']] (default: 'rain')
• color: Sequence[int] | dict[str, Sequence[int]] | None (default: null)

Targets

• Image

Try it out