Skip to content

coarse_dropout

CoarseDropout

Bases: ImageOnlyAlbumentation

Drop rectangular regions from 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
max_holes int

Maximum number of regions to zero out.

 8
max_height int

Maximum height of the hole.

 8
max_width int

Maximum width of the hole.

 8
min_holes Optional[int]

Minimum number of regions to zero out. If None, min_holes is set to max_holes.

 None
min_height Optional[int]

Minimum height of the hole. If None, min_height is set to max_height.

 None
min_width Optional[int]

Minimum width of the hole. If None, min_height is set to max_width.

 None
fill_value Union[int, float, List[int], List[float]]

value for dropped pixels.

 0
Image types

uint8, float32

Source code in fastestimator/fastestimator/op/numpyop/univariate/coarse_dropout.py 
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
@traceable()
class CoarseDropout(ImageOnlyAlbumentation):
    """Drop rectangular regions from 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".
        max_holes: Maximum number of regions to zero out.
        max_height: Maximum height of the hole.
        max_width: Maximum width of the hole.
        min_holes: Minimum number of regions to zero out. If `None`, `min_holes` is set to `max_holes`.
        min_height: Minimum height of the hole. If `None`, `min_height` is set to `max_height`.
        min_width: Minimum width of the hole. If `None`, `min_height` is set to `max_width`.
        fill_value: value for dropped pixels.

    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,
                 max_holes: int = 8,
                 max_height: int = 8,
                 max_width: int = 8,
                 min_holes: Optional[int] = None,
                 min_height: Optional[int] = None,
                 min_width: Optional[int] = None,
                 fill_value: Union[int, float, List[int], List[float]] = 0):
        super().__init__(
            CoarseDropoutAlb(max_holes=max_holes,
                             max_height=max_height,
                             max_width=max_width,
                             min_holes=min_holes,
                             min_height=min_height,
                             min_width=min_width,
                             fill_value=fill_value,
                             always_apply=True),
            inputs=inputs,
            outputs=outputs,
            mode=mode,
            ds_id=ds_id)