o
    oia                     @   sh   d dl mZmZmZmZ d dlmZ d dlm	Z	 d dl
mZ d dlmZ d dlmZ G dd de	Zd	S )
    )AnyDictOptionalTuple)random_generator)IntensityAugmentationBase2D)_range_bound)Tensor)adjust_saturationc                       s~   e Zd ZdZ				ddeeef dededed	d
f
 fddZ	
ddede	e
ef de	e
ef dee d	ef
ddZ  ZS )RandomSaturationa  Apply a random transformation to the saturation of a tensor image.

    This implementation aligns PIL. Hence, the output is close to TorchVision.

    .. image:: _static/img/RandomSaturation.png

    Args:
        p: probability of applying the transformation.
        saturation: the saturation factor to apply.
        same_on_batch: apply the same transformation across the batch.
        keepdim: whether to keep the output shape the same as input (True) or broadcast it
                 to the batch form (False).
    Shape:
        - Input: :math:`(C, H, W)` or :math:`(B, C, H, W)`, Optional: :math:`(B, 3, 3)`
        - Output: :math:`(B, C, H, W)`

    .. note::
        This function internally uses :func:`kornia.enhance.adjust_saturation`

    Examples:
        >>> rng = torch.manual_seed(0)
        >>> inputs = torch.rand(1, 3, 3, 3)
        >>> aug = RandomSaturation(saturation = (0.5,2.),p=1.)
        >>> aug(inputs)
        tensor([[[[0.5569, 0.7682, 0.3529],
                  [0.4811, 0.3474, 0.7411],
                  [0.5028, 0.8964, 0.6772]],
        <BLANKLINE>
                 [[0.6323, 0.5358, 0.5265],
                  [0.4203, 0.2706, 0.5525],
                  [0.5185, 0.7863, 0.8681]],
        <BLANKLINE>
                 [[0.3711, 0.4989, 0.6816],
                  [0.9152, 0.3971, 0.8742],
                  [0.4636, 0.7060, 0.9527]]]])

    To apply the exact augmenation again, you may take the advantage of the previous parameter state:

        >>> input = torch.rand(1, 3, 32, 32)
        >>> aug = RandomSaturation((0.8,1.2), p=1.)
        >>> (aug(input) == aug(input, params=aug._params)).all()
        tensor(True)

          ?r   Fr   
saturationsame_on_batchpkeepdimreturnNc                    s<   t  j|||d t|ddd| _t| jdd d f| _d S )N)r   r   r   r   r   )centersaturation_factor)super__init__r   r   rgPlainUniformGenerator_param_generator)selfr   r   r   r   	__class__ `/home/ubuntu/.local/lib/python3.10/site-packages/kornia/augmentation/_2d/intensity/saturation.pyr   I   s   zRandomSaturation.__init__inputparamsflags	transformc                 C   s   |d  |}t||S )Nr   )tor
   )r   r   r    r!   r"   r   r   r   r   apply_transformT   s   
z RandomSaturation.apply_transform)r   Fr   F)N)__name__
__module____qualname____doc__r   floatboolr   r	   r   strr   r   r$   __classcell__r   r   r   r   r      s:    /


r   N)typingr   r   r   r   kornia.augmentationr   r   &kornia.augmentation._2d.intensity.baser   kornia.augmentation.utilsr   kornia.corer	   kornia.enhance.adjustr
   r   r   r   r   r   <module>   s   