Skip to content

random_rain

RandomRain

Bases: ImageOnlyAlbumentation

Add rain to an image

Parameters:

Name Type Description Default
inputs Union[str, Iterable[str]]

Key(s) of images to be modified.

required
outputs Union[str, Iterable[str]]

Key(s) into which to write the modified images.

required
mode Union[None, str, Iterable[str]]

What mode(s) to execute this Op in. For example, "train", "eval", "test", or "infer". To execute regardless of mode, pass None. To execute in all modes except for a particular one, you can pass an argument like "!infer" or "!train".

None
ds_id Union[None, str, Iterable[str]]

What dataset id(s) to execute this Op in. To execute regardless of ds_id, pass None. To execute in all ds_ids except for a particular one, you can pass an argument like "!ds1".

None
slant_lower int

Should be in range [-20, 20].

-10
slant_upper int

Should be in range [-20, 20].

10
drop_length int

Should be in range [0, 100].

20
drop_width int

Should be in range [1, 5].

1
drop_color Tuple[int, int, int]

Rain lines color (r, g, b).

(200, 200, 200)
blur_value int

How blurry to make the rain.

7
brightness_coefficient float

Rainy days are usually shady. Should be in range [0, 1].

0.7
rain_type Optional[str]

One of [None, "drizzle", "heavy", "torrential"].

None
Image types

uint8, float32

Source code in fastestimator/fastestimator/op/numpyop/univariate/random_rain.py
@traceable()
class RandomRain(ImageOnlyAlbumentation):
    """Add rain to an image

    Args:
        inputs: Key(s) of images to be modified.
        outputs: Key(s) into which to write the modified images.
        mode: What mode(s) to execute this Op in. For example, "train", "eval", "test", or "infer". To execute
            regardless of mode, pass None. To execute in all modes except for a particular one, you can pass an argument
            like "!infer" or "!train".
        ds_id: What dataset id(s) to execute this Op in. To execute regardless of ds_id, pass None. To execute in all
            ds_ids except for a particular one, you can pass an argument like "!ds1".
        slant_lower: Should be in range [-20, 20].
        slant_upper: Should be in range [-20, 20].
        drop_length: Should be in range [0, 100].
        drop_width: Should be in range [1, 5].
        drop_color: Rain lines color (r, g, b).
        blur_value: How blurry to make the rain.
        brightness_coefficient: Rainy days are usually shady. Should be in range [0, 1].
        rain_type: One of [None, "drizzle", "heavy", "torrential"].

    Image types:
        uint8, float32
    """
    def __init__(self,
                 inputs: Union[str, Iterable[str]],
                 outputs: Union[str, Iterable[str]],
                 mode: Union[None, str, Iterable[str]] = None,
                 ds_id: Union[None, str, Iterable[str]] = None,
                 slant_lower: int = -10,
                 slant_upper: int = 10,
                 drop_length: int = 20,
                 drop_width: int = 1,
                 drop_color: Tuple[int, int, int] = (200, 200, 200),
                 blur_value: int = 7,
                 brightness_coefficient: float = 0.7,
                 rain_type: Optional[str] = None):
        super().__init__(
            RandomRainAlb(slant_lower=slant_lower,
                          slant_upper=slant_upper,
                          drop_length=drop_length,
                          drop_width=drop_width,
                          drop_color=drop_color,  # Their docstring type hint doesn't match the real code
                          blur_value=blur_value,
                          brightness_coefficient=brightness_coefficient,
                          rain_type=rain_type,
                          always_apply=True),
            inputs=inputs,
            outputs=outputs,
            mode=mode,
            ds_id=ds_id)