U h@sddlmZddlZddlmZmZddlZddlm Z ddl m Z m Z ddl mZddlmZddlmZmZd d lmZd gZd ZGd d d eZdS)) annotationsN)AnyMapping)get_num_channels)AfterValidatorField) Annotated) check_1plus)BaseTransformInitSchemaImageOnlyTransform)channel_dropoutChannelDropoutcsreZdZdZGdddeZddd d d d fd d ZdddddddZddddddZddddZ Z S)ra 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_value (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 Image types: uint8, float32 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_value=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@seZdZUded<ded<dS)zChannelDropout.InitSchemaz7Annotated[tuple[int, int], AfterValidator(check_1plus)]channel_drop_rangezKAnnotated[float, Field(description='Pixel value for the dropped channel.')] fill_valueN)__name__ __module__ __qualname____annotations__rrX/tmp/pip-unpacked-wheel-e8onvpoz/albumentations/augmentations/dropout/channel_dropout.py InitSchemaLs rr r rN?ztuple[int, int]floatz bool | None)rr always_applypcs tj||d||_||_dS)N)rr)super__init__rr)selfrrrr __class__rrrPszChannelDropout.__init__z np.ndarrayztuple[int, ...]r)imgchannels_to_dropparamsreturncKst|||jS)N)r r)r r#r$r%rrrapply\szChannelDropout.applyzMapping[str, Any]zdict[str, Any])r%datar&cCsxd|kr|dn |dd}t|}|dkr8d}t||jd|krRd}t|tj|j}tjt||d}d|iS) NimageZimagesrr z6Images has one channel. ChannelDropout is not defined.z,Can not drop all channels in ChannelDropout.)kr$)rNotImplementedErrorr ValueErrorrandomrandintsamplerange)r r%r(r)Z num_channelsmsgZnum_drop_channelsr$rrrget_params_dependent_on_data_s z+ChannelDropout.get_params_dependent_on_dataztuple[str, ...])r&cCsdS)N)rrr)r rrrget_transform_init_args_namesqsz,ChannelDropout.get_transform_init_args_names)rrNr) rrr__doc__r rrr'r2r3 __classcell__rrr!rrs6 ) __future__rr-typingrrZnumpynpZalbucorerZpydanticrrZtyping_extensionsrZalbumentations.core.pydanticr Z(albumentations.core.transforms_interfacer r Z functionalr __all__ZMIN_DROPOUT_CHANNEL_LIST_LENGTHrrrrrs