albumentations.augmentations.dropout.channel_dropout

View Source on GitHub

Implementation of the Channel Dropout transform for multi-channel images. This module provides the ChannelDropout transform, which randomly drops (sets to a fill value) one or more channels in multi-channel images. This augmentation can help models become more robust to missing or corrupted channel information and encourage learning from all available channels rather than relying on a subset.

Members

classChannelDropout

ChannelDropoutclass

Try it on Explore Albumentations

ChannelDropout(
    channel_drop_range: tuple[int, int] = (1, 1),
    fill: float = 0,
    p: float = 0.5
)

Randomly drop channels in the input image. This transform randomly selects a number of channels to drop from the input image and replaces them with a specified fill value. This can improve model robustness to missing or corrupted channels. The technique is conceptually similar to: - Dropout layers in neural networks, which randomly set input units to 0 during training. - CoarseDropout augmentation, which drops out regions in the spatial dimensions of the image. However, ChannelDropout operates on the channel dimension, effectively "dropping out" entire color channels or feature maps.

Parameters

Name	Type	Default	Description
channel_drop_range	tuple[int, int]	(1, 1)	Range from which to choose the number of channels to drop. The actual number will be randomly selected from the inclusive range [min, max]. Default: (1, 1).
fill	float	0	Pixel value used to fill the dropped channels. Default: 0.
p	float	0.5	Probability of applying the transform. Must be in the range [0, 1]. Default: 0.5.

Example

>>> import numpy as np
>>> import albumentations as A
>>> image = np.random.randint(0, 256, (100, 100, 3), dtype=np.uint8)
>>> transform = A.ChannelDropout(channel_drop_range=(1, 2), fill=128, p=1.0)
>>> result = transform(image=image)
>>> dropped_image = result['image']
>>> assert dropped_image.shape == image.shape
>>> assert np.any(dropped_image != image)  # Some channels should be different

Notes

- The number of channels to drop is randomly chosen within the specified range. - Channels are randomly selected for dropping. - This transform is not applicable to single-channel (grayscale) images. - The transform will raise an error if it's not possible to drop the specified number of channels (e.g., trying to drop 3 channels from an RGB image). - This augmentation can be particularly useful for training models to be robust against missing or corrupted channel data in multi-spectral or hyperspectral imagery.

ChannelDropout