Skip to content

channel_dropout

ChannelDropout

Bases: ImageOnlyAlbumentation

Randomly drop channels from the image.

Parameters:

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

Key(s) of images to be modified.

 required
outputs Union[str, Sequence[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
channel_drop_range Tuple[int, int]

Range from which we choose the number of channels to drop.

 (1, 1)
fill_value Union[int, float]

Pixel values for the dropped channel.

 0
Image types

int8, uint16, unit32, float32

Source code in fastestimator/fastestimator/op/numpyop/univariate/channel_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
@traceable()
class ChannelDropout(ImageOnlyAlbumentation):
    """Randomly drop channels from the 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".
        channel_drop_range: Range from which we choose the number of channels to drop.
        fill_value: Pixel values for the dropped channel.

    Image types:
        int8, uint16, unit32, float32
    """
    def __init__(self,
                 inputs: Union[str, Sequence[str]],
                 outputs: Union[str, Sequence[str]],
                 mode: Union[None, str, Iterable[str]] = None,
                 ds_id: Union[None, str, Iterable[str]] = None,
                 channel_drop_range: Tuple[int, int] = (1, 1),
                 fill_value: Union[int, float] = 0):
        super().__init__(
            ChannelDropoutAlb(channel_drop_range=channel_drop_range, fill_value=fill_value, always_apply=True),
            inputs=inputs,
            outputs=outputs,
            mode=mode,
            ds_id=ds_id)