
    sgz4                         d Z ddlmZmZmZ ddlZddlmZm	Z	 ddl
mZmZ ddlmZmZmZmZmZmZmZmZmZmZmZ ddlmZmZmZ  ej:                  e      Z G d	 d
e      Z y)z#Image processor class for ViTMatte.    )ListOptionalUnionN   )BaseImageProcessorBatchFeature)padto_channel_dimension_format)IMAGENET_STANDARD_MEANIMAGENET_STANDARD_STDChannelDimension
ImageInputget_image_sizeinfer_channel_dimension_formatis_scaled_imagemake_list_of_imagesto_numpy_arrayvalid_imagesvalidate_preprocess_arguments)
TensorTypefilter_out_non_signature_kwargsloggingc                       e Zd ZdZdgZ	 	 	 	 	 	 	 ddedeeef   dede	eee
e   f      de	eee
e   f      d	ed
eddf fdZ	 	 	 ddej                  d
ede	eeef      de	eeef      dej                  f
dZ e       ddddddddej$                  df
dedede	e   de	e   de	e   de	eee
e   f      de	eee
e   f      d	e	e   d
e	e   de	eeef      deeef   de	eeef      fd       Z xZS )VitMatteImageProcessora  
    Constructs a ViTMatte image processor.

    Args:
        do_rescale (`bool`, *optional*, defaults to `True`):
            Whether to rescale the image by the specified scale `rescale_factor`. Can be overridden by the `do_rescale`
            parameter in the `preprocess` method.
        rescale_factor (`int` or `float`, *optional*, defaults to `1/255`):
            Scale factor to use if rescaling the image. Can be overridden by the `rescale_factor` parameter in the
            `preprocess` method.
        do_normalize (`bool`, *optional*, defaults to `True`):
            Whether to normalize the image. Can be overridden by the `do_normalize` parameter in the `preprocess`
            method.
        image_mean (`float` or `List[float]`, *optional*, defaults to `IMAGENET_STANDARD_MEAN`):
            Mean to use if normalizing the image. This is a float or list of floats the length of the number of
            channels in the image. Can be overridden by the `image_mean` parameter in the `preprocess` method.
        image_std (`float` or `List[float]`, *optional*, defaults to `IMAGENET_STANDARD_STD`):
            Standard deviation to use if normalizing the image. This is a float or list of floats the length of the
            number of channels in the image. Can be overridden by the `image_std` parameter in the `preprocess` method.
        do_pad (`bool`, *optional*, defaults to `True`):
            Whether to pad the image to make the width and height divisible by `size_divisibility`. Can be overridden
            by the `do_pad` parameter in the `preprocess` method.
        size_divisibility (`int`, *optional*, defaults to 32):
            The width and height of the image will be padded to be divisible by this number.
    pixel_valuesN
do_rescalerescale_factordo_normalize
image_mean	image_stddo_padsize_divisibilityreturnc                     t        	|   di | || _        || _        || _        || _        ||nt        | _        ||nt        | _	        || _
        y )N )super__init__r   r   r!   r   r   r   r   r    r"   )
selfr   r   r   r   r    r!   r"   kwargs	__class__s
            i/var/www/html/venv/lib/python3.12/site-packages/transformers/models/vitmatte/image_processing_vitmatte.pyr'   zVitMatteImageProcessor.__init__G   sY     	"6"$(,(2(>*DZ&/&;AV!2    imagedata_formatinput_data_formatc                     |t        |      }t        ||      \  }}||z  dk(  rdn|||z  z
  }||z  dk(  rdn|||z  z
  }||z   dkD  rd|fd|ff}	t        ||	||      }|t        |||      }|S )a  
        Args:
            image (`np.ndarray`):
                Image to pad.
            size_divisibility (`int`, *optional*, defaults to 32):
                The width and height of the image will be padded to be divisible by this number.
            data_format (`ChannelDimension` or `str`, *optional*, defaults to `ChannelDimension.FIRST`):
                The channel dimension format for the output image. Can be one of:
                - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format.
                - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format.
                - Unset: Use the channel dimension format of the input image.
            input_data_format (`ChannelDimension` or `str`, *optional*):
                The channel dimension format for the input image. If unset, the channel dimension format is inferred
                from the input image. Can be one of:
                - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format.
                - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format.
                - `"none"` or `ChannelDimension.NONE`: image in (height, width) format.
        r   )paddingr.   r/   )r   r   r	   r
   )
r(   r-   r"   r.   r/   heightwidth
pad_height	pad_widthr1   s
             r+   	pad_imagez VitMatteImageProcessor.pad_image[   s    2 $ >u E&u.?@ #449Q?PSY\mSm?m
!22a7A=NQVYjQj=j	z!A%:I7GwK[lmE"/{DUVEr,   imagestrimapsreturn_tensorsc                    ||n| j                   }||n| j                  }||n| j                  }||n| j                  }||n| j                  }||n| j
                  }|	|	n| j                  }	t        |      }t        |d      }t        |      st        d      t        |      st        d      t        |||||||	       |D cg c]  }t        |       }}|D cg c]  }t        |       }}t        |d         r|rt        j                  d       |t        |d         }|rB|D cg c]  }| j!                  |||       }}|D cg c]  }| j!                  |||       }}|r"|D cg c]  }| j#                  ||||	       }}t%        ||      D cg c]3  \  }}t'        j(                  |t'        j*                  |d
      gd
      5 }}}|r!|D cg c]  }| j-                  ||	|       }}|D cg c]  }t/        |||       }}d|i}t1        ||
      S c c}w c c}w c c}w c c}w c c}w c c}}w c c}w c c}w )a  
        Preprocess an image or batch of images.

        Args:
            images (`ImageInput`):
                Image to preprocess. Expects a single or batch of images with pixel values ranging from 0 to 255. If
                passing in images with pixel values between 0 and 1, set `do_rescale=False`.
            trimaps (`ImageInput`):
                Trimap to preprocess.
            do_rescale (`bool`, *optional*, defaults to `self.do_rescale`):
                Whether to rescale the image values between [0 - 1].
            rescale_factor (`float`, *optional*, defaults to `self.rescale_factor`):
                Rescale factor to rescale the image by if `do_rescale` is set to `True`.
            do_normalize (`bool`, *optional*, defaults to `self.do_normalize`):
                Whether to normalize the image.
            image_mean (`float` or `List[float]`, *optional*, defaults to `self.image_mean`):
                Image mean to use if `do_normalize` is set to `True`.
            image_std (`float` or `List[float]`, *optional*, defaults to `self.image_std`):
                Image standard deviation to use if `do_normalize` is set to `True`.
            do_pad (`bool`, *optional*, defaults to `self.do_pad`):
                Whether to pad the image.
            size_divisibility (`int`, *optional*, defaults to `self.size_divisibility`):
                The size divisibility to pad the image to if `do_pad` is set to `True`.
            return_tensors (`str` or `TensorType`, *optional*):
                The type of tensors to return. Can be one of:
                - Unset: Return a list of `np.ndarray`.
                - `TensorType.TENSORFLOW` or `'tf'`: Return a batch of type `tf.Tensor`.
                - `TensorType.PYTORCH` or `'pt'`: Return a batch of type `torch.Tensor`.
                - `TensorType.NUMPY` or `'np'`: Return a batch of type `np.ndarray`.
                - `TensorType.JAX` or `'jax'`: Return a batch of type `jax.numpy.ndarray`.
            data_format (`ChannelDimension` or `str`, *optional*, defaults to `ChannelDimension.FIRST`):
                The channel dimension format for the output image. Can be one of:
                - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format.
                - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format.
                - Unset: Use the channel dimension format of the input image.
            input_data_format (`ChannelDimension` or `str`, *optional*):
                The channel dimension format for the input image. If unset, the channel dimension format is inferred
                from the input image. Can be one of:
                - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format.
                - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format.
                - `"none"` or `ChannelDimension.NONE`: image in (height, width) format.
           )expected_ndimszlInvalid trimap type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.zkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.)r   r   r   r   r    r!   r"   r   zIt looks like you are trying to rescale already rescaled images. If the input images have pixel values between 0 and 1, set `do_rescale=False` to avoid rescaling them again.)r-   scaler/   )r-   meanstdr/   )axis)r"   r/   )r-   channel_diminput_channel_dimr   )datatensor_type)r   r   r!   r   r   r    r"   r   r   
ValueErrorr   r   r   loggerwarning_oncer   rescale	normalizezipnpconcatenateexpand_dimsr6   r
   r   )r(   r7   r8   r   r   r   r   r    r!   r"   r9   r.   r/   r-   trimaprD   s                   r+   
preprocessz!VitMatteImageProcessor.preprocess   s   t $.#9Zt
'3'?|TEVEV!-4;;+9+E4K^K^#-#9Zt
!*!6IDNN	1B1N-TXTjTj$V,%ga@G$: 
 F#:  	&!)%!/	
 6<<E.'<<8?@f>&)@@6!9%*s
 $ >vay I $ 5RcdF  & 6SdeG 
  $ U^opF  dggmovcw
R_RWY_BNNE2>>&r#BC"M
 
  $ u8I]noF   
 (e`qr
 

 '>BB] =@



s0   H-#H22H7H<6I#8I$II)Tgp?TNNT    )rQ   NN)__name__
__module____qualname____doc__model_input_namesboolr   intfloatr   r   r'   rL   ndarraystrr   r6   r   FIRSTr   r   rP   __classcell__)r*   s   @r+   r   r   *   sG   4 ((  ,3!:>9=!#33 c5j)3 	3
 U5$u+#5673 E%e"4563 3 3 
3. "$>BDH'zz' ' eC)9$9:;	'
 $E#/?*?$@A' 
'R %&
 &**.'+:>9=!%+/;?4D4J4JDHHCHC HC TN	HC
 !HC tnHC U5$u+#567HC E%e"456HC HC $C=HC !sJ!78HC 3 001HC $E#/?*?$@AHC 'HCr,   r   )!rU   typingr   r   r   numpyrL   image_processing_utilsr   r   image_transformsr	   r
   image_utilsr   r   r   r   r   r   r   r   r   r   r   utilsr   r   r   
get_loggerrR   rG   r   r%   r,   r+   <module>re      s[    * ( (  F @    J I 
		H	%cC/ cCr,   