bidZddlmZddlmZmZddlZddlm Z ddl m Z ddl m Z ddlmZmZd d lmZd gZd ZGd d eZy)aImplementation 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. ) annotations) AnnotatedAnyN)get_num_channels)AfterValidator)check_range_bounds)BaseTransformInitSchemaImageOnlyTransform)channel_dropoutChannelDropoutc\eZdZdZGddeZ d dfd Zd dZd dZxZ S) r a 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. Args: channel_drop_range (tuple[int, int]): 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): Probability of applying the transform. Must be in the range [0, 1]. Default: 0.5. Raises: NotImplementedError: If the input image has only one channel. ValueError: If the upper bound of channel_drop_range is greater than or equal to the number of channels in the input image. Targets: image, volume Image types: uint8, float32 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 Note: - 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. c"eZdZUded<ded<y)ChannelDropout.InitSchemazGAnnotated[tuple[int, int], AfterValidator(check_range_bounds(1, None))]channel_drop_rangefloatfillN)__name__ __module__ __qualname____annotations__o/home/cdr/jupyterlab/.venv/lib/python3.12/site-packages/albumentations/augmentations/dropout/channel_dropout.py InitSchemarRs cc rrcBt||||_||_y)N)p)super__init__rr)selfrrr __class__s rr zChannelDropout.__init__Vs$ 1"4 rc 0t|||jS)aBApply channel dropout to the image. Args: img (np.ndarray): Image to apply channel dropout to. channels_to_drop (list[int]): List of channel indices to drop. **params (Any): Additional parameters. Returns: np.ndarray: Image with dropped channels. )r r)r!imgchannels_to_dropparamss rapplyzChannelDropout.applyass$4dii@@rc6d|vr|dn|dd}t|}|dk(r d}t||jd|k\r d}t||jj |j}|jj t||}d|iS) zGet parameters that depend on input data. Args: params (dict[str, Any]): Parameters. data (dict[str, Any]): Input data. Returns: dict[str, list[int]]: Dictionary with channels to drop. imageimagesrr z6Images has one channel. ChannelDropout is not defined.z,Can not drop all channels in ChannelDropout.)kr%)rNotImplementedErrorr ValueError py_randomrandintsamplerange)r!r&datar) num_channelsmsgnum_drop_channelsr%s rget_params_dependent_on_dataz+ChannelDropout.get_params_dependent_on_dataos")DW d8nQ6G'. 1 JC%c* *  " "1 % 5@CS/ !2DNN22D4K4KL>>00|1DHY0Z"$455r))r r rg?)rztuple[int, int]rrrr)r$ np.ndarrayr%z list[int]r&rreturnr7)r&dict[str, Any]r2r9r8zdict[str, list[int]]) rrr__doc__r rr r'r6 __classcell__)r"s@rr r sM4l, /5 +     A6r)r: __future__rtypingrrnumpynpalbucorerpydanticralbumentations.core.pydanticr(albumentations.core.transforms_interfacer r functionalr __all__MIN_DROPOUT_CHANNEL_LIST_LENGTHr rrrrGsA#!%#;`'  "#k6'k6r