ChannelDropout

Targets:

image

Image Types:uint8, float32

Randomly drop channels. channel_drop_range, fill. Replaces selected channels with fill; improves robustness to missing channels. Image-only.

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.

Arguments

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

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.

Examples

>>> 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.

>>> 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