ChannelDropout augmentation (augmentations.dropout.channel_dropout)¶
class ChannelDropout
(channel_drop_range=(1, 1), fill_value=0, always_apply=None, p=0.5)
[view source on GitHub] ΒΆ
Randomly Drop Channels in the input Image.
Parameters:
Name | Type | Description |
---|---|---|
channel_drop_range | int, int | range from which we choose the number of channels to drop. |
fill_value | int, float | pixel value for the dropped channel. |
p | float | probability of applying the transform. Default: 0.5. |
Targets
image
Image types: uint8, uint16, unit32, float32
Interactive Tool Available!
Explore this transform visually and adjust parameters interactively using this tool:
Source code in albumentations/augmentations/dropout/channel_dropout.py
Python
class ChannelDropout(ImageOnlyTransform):
"""Randomly Drop Channels in the input Image.
Args:
channel_drop_range (int, int): range from which we choose the number of channels to drop.
fill_value (int, float): pixel value for the dropped channel.
p (float): probability of applying the transform. Default: 0.5.
Targets:
image
Image types:
uint8, uint16, unit32, float32
"""
class InitSchema(BaseTransformInitSchema):
channel_drop_range: OnePlusIntRangeType = (1, 1)
fill_value: Annotated[ColorType, Field(description="Pixel value for the dropped channel.")]
def __init__(
self,
channel_drop_range: tuple[int, int] = (1, 1),
fill_value: float = 0,
always_apply: bool | None = None,
p: float = 0.5,
):
super().__init__(p=p, always_apply=always_apply)
self.channel_drop_range = channel_drop_range
self.fill_value = fill_value
def apply(self, img: np.ndarray, channels_to_drop: tuple[int, ...], **params: Any) -> np.ndarray:
return channel_dropout(img, channels_to_drop, self.fill_value)
def get_params_dependent_on_data(self, params: Mapping[str, Any], data: Mapping[str, Any]) -> dict[str, Any]:
image = data["image"] if "image" in data else data["images"][0]
num_channels = get_num_channels(image)
if num_channels == 1:
msg = "Images has one channel. ChannelDropout is not defined."
raise NotImplementedError(msg)
if self.channel_drop_range[1] >= num_channels:
msg = "Can not drop all channels in ChannelDropout."
raise ValueError(msg)
num_drop_channels = random.randint(self.channel_drop_range[0], self.channel_drop_range[1])
channels_to_drop = random.sample(range(num_channels), k=num_drop_channels)
return {"channels_to_drop": channels_to_drop}
def get_transform_init_args_names(self) -> tuple[str, ...]:
return "channel_drop_range", "fill_value"
apply (self, img, channels_to_drop, **params)
¶
get_params_dependent_on_data (self, params, data)
¶
Returns parameters dependent on input.
Source code in albumentations/augmentations/dropout/channel_dropout.py
Python
def get_params_dependent_on_data(self, params: Mapping[str, Any], data: Mapping[str, Any]) -> dict[str, Any]:
image = data["image"] if "image" in data else data["images"][0]
num_channels = get_num_channels(image)
if num_channels == 1:
msg = "Images has one channel. ChannelDropout is not defined."
raise NotImplementedError(msg)
if self.channel_drop_range[1] >= num_channels:
msg = "Can not drop all channels in ChannelDropout."
raise ValueError(msg)
num_drop_channels = random.randint(self.channel_drop_range[0], self.channel_drop_range[1])
channels_to_drop = random.sample(range(num_channels), k=num_drop_channels)
return {"channels_to_drop": channels_to_drop}