
    sgA                         d Z ddlmZmZmZmZ ddlZddlm	Z	m
Z
mZ ddlmZmZ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mZ ddlmZm Z m!Z!  e!jD                  e#      Z$ e        rddl%Z% G d	 d
e	      Z&y)zImage processor class for CLIP.    )DictListOptionalUnionN   )BaseImageProcessorBatchFeatureget_size_dict)convert_to_rgbget_resize_output_image_sizeresizeto_channel_dimension_format)OPENAI_CLIP_MEANOPENAI_CLIP_STDChannelDimension
ImageInputPILImageResamplinginfer_channel_dimension_formatis_scaled_imagemake_list_of_imagesto_numpy_arrayvalid_imagesvalidate_kwargsvalidate_preprocess_arguments)
TensorTypeis_vision_availableloggingc            "       \    e Zd ZdZdgZddej                  ddddddddfdedee	e
f   ded	ed
ee	e
f   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df fdZej                  ddfdej"                  dee	e
f   dedeee	ef      deee	ef      dej"                  fdZddddddddddddej(                  dfdededee	e
f   ded	ed
e
dedededeeeee   f      deeeee   f      dedeee	ef      dee   deee	ef      dej0                  j0                  f dZ xZS )CLIPImageProcessora
  
    Constructs a CLIP image processor.

    Args:
        do_resize (`bool`, *optional*, defaults to `True`):
            Whether to resize the image's (height, width) dimensions to the specified `size`. Can be overridden by
            `do_resize` in the `preprocess` method.
        size (`Dict[str, int]` *optional*, defaults to `{"shortest_edge": 224}`):
            Size of the image after resizing. The shortest edge of the image is resized to size["shortest_edge"], with
            the longest edge resized to keep the input aspect ratio. Can be overridden by `size` in the `preprocess`
            method.
        resample (`PILImageResampling`, *optional*, defaults to `Resampling.BICUBIC`):
            Resampling filter to use if resizing the image. Can be overridden by `resample` in the `preprocess` method.
        do_center_crop (`bool`, *optional*, defaults to `True`):
            Whether to center crop the image to the specified `crop_size`. Can be overridden by `do_center_crop` in the
            `preprocess` method.
        crop_size (`Dict[str, int]` *optional*, defaults to 224):
            Size of the output image after applying `center_crop`. Can be overridden by `crop_size` in the `preprocess`
            method.
        do_rescale (`bool`, *optional*, defaults to `True`):
            Whether to rescale the image by the specified scale `rescale_factor`. Can be overridden by `do_rescale` 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 `rescale_factor` in the `preprocess`
            method.
        do_normalize (`bool`, *optional*, defaults to `True`):
            Whether to normalize the image. Can be overridden by `do_normalize` in the `preprocess` method.
        image_mean (`float` or `List[float]`, *optional*, defaults to `[0.48145466, 0.4578275, 0.40821073]`):
            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 `[0.26862954, 0.26130258, 0.27577711]`):
            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.
            Can be overridden by the `image_std` parameter in the `preprocess` method.
        do_convert_rgb (`bool`, *optional*, defaults to `True`):
            Whether to convert the image to RGB.
    pixel_valuesTNgp?	do_resizesizeresampledo_center_crop	crop_size
do_rescalerescale_factordo_normalize
image_mean	image_stddo_convert_rgbreturnc                    t        |   di | ||nddi}t        |d      }||nddd}t        |dd      }|| _        || _        || _        || _        || _        || _        || _	        || _
        |	|	nt        | _        |
|
nt        | _        || _        g d	| _        d
|v r#|d
   r|d   |d   d| _        t#        | d
       y y y )Nshortest_edge   F)default_to_square)heightwidthTr%   )r0   
param_name)imagesr!   r"   r#   r$   r%   r&   r'   r(   r)   r*   r+   return_tensorsdata_formatinput_data_formatuse_square_size )super__init__r
   r!   r"   r#   r$   r%   r&   r'   r(   r   r)   r   r*   r+   _valid_processor_keysdelattr)selfr!   r"   r#   r$   r%   r&   r'   r(   r)   r*   r+   kwargs	__class__s                a/var/www/html/venv/lib/python3.12/site-packages/transformers/models/clip/image_processing_clip.pyr;   zCLIPImageProcessor.__init__]   s     	"6"'tos-CTU;!*!6IsUX<Y	!)tP[\	"	 ,"$,((2(>*DT&/&;,&
"& &62C+D#'#84CXYDI D+, ,E&    imager6   r7   c                     d}d|v r|d   }d}nd|v rd|v r|d   |d   f}nt        d      t        ||||      }t        |f||||d|S )	aZ  
        Resize an image. The shortest edge of the image is resized to size["shortest_edge"], with the longest edge
        resized to keep the input aspect ratio.

        Args:
            image (`np.ndarray`):
                Image to resize.
            size (`Dict[str, int]`):
                Size of the output image.
            resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BICUBIC`):
                Resampling filter to use when resiizing the image.
            data_format (`str` or `ChannelDimension`, *optional*):
                The channel dimension format of the image. If not provided, it will be the same as the input image.
            input_data_format (`ChannelDimension` or `str`, *optional*):
                The channel dimension format of the input image. If not provided, it will be inferred.
        Tr.   Fr1   r2   zASize must contain either 'shortest_edge' or 'height' and 'width'.)r"   r0   r7   )r"   r#   r6   r7   )
ValueErrorr   r   )	r>   rC   r"   r#   r6   r7   r?   r0   output_sizes	            rA   r   zCLIPImageProcessor.resize   s    2 !d"(D %'T/NDM2D`aa2//	
 
#/
 
 	
rB   r4   r5   c                 |   ||n| j                   }||n| j                  }t        |dd      }||n| j                  }||n| j                  }||n| j
                  }t        |dd      }||n| j                  }||n| j                  }|	|	n| j                  }	|
|
n| j                  }
||n| j                  }||n| j                  }t        |j                         | j                         t        |      }t!        |      st#        d      t%        |||	|
||||||
       |r|D cg c]  }t'        |       }}|D cg c]  }t)        |       }}t+        |d	         r|rt,        j/                  d
       |t1        |d	         }g }|D ]m  }|r| j3                  ||||      }|r| j5                  |||      }|r| j7                  |||      }|	r| j9                  ||
||      }|j;                  |       o |D cg c]  }t=        |||       }}d|i}t?        ||      S 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`.
            do_resize (`bool`, *optional*, defaults to `self.do_resize`):
                Whether to resize the image.
            size (`Dict[str, int]`, *optional*, defaults to `self.size`):
                Size of the image after resizing. Shortest edge of the image is resized to size["shortest_edge"], with
                the longest edge resized to keep the input aspect ratio.
            resample (`int`, *optional*, defaults to `self.resample`):
                Resampling filter to use if resizing the image. This can be one of the enum `PILImageResampling`. Only
                has an effect if `do_resize` is set to `True`.
            do_center_crop (`bool`, *optional*, defaults to `self.do_center_crop`):
                Whether to center crop the image.
            crop_size (`Dict[str, int]`, *optional*, defaults to `self.crop_size`):
                Size of the center crop. Only has an effect if `do_center_crop` is set to `True`.
            do_rescale (`bool`, *optional*, defaults to `self.do_rescale`):
                Whether to rescale the image.
            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 for normalization. Only has an effect if `do_normalize` is set to `True`.
            image_std (`float` or `List[float]`, *optional*, defaults to `self.image_std`):
                Image standard deviation to use for normalization. Only has an effect if `do_normalize` is set to
                `True`.
            do_convert_rgb (`bool`, *optional*, defaults to `self.do_convert_rgb`):
                Whether to convert the image to RGB.
            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.
        r"   F)r3   r0   r%   T)captured_kwargsvalid_processor_keyszkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.)
r&   r'   r(   r)   r*   r$   r%   r!   r"   r#   r   zIt looks like you are trying to rescale already rescaled images. If the input images have pixel values between 0 and 1, set `do_rescale=False` to avoid rescaling them again.)rC   r"   r#   r7   )rC   r"   r7   )rC   scaler7   )rC   meanstdr7   )input_channel_dimr    )datatensor_type) r!   r"   r
   r#   r$   r%   r&   r'   r(   r)   r*   r+   r   keysr<   r   r   rE   r   r   r   r   loggerwarning_oncer   r   center_croprescale	normalizeappendr   r	   )r>   r4   r!   r"   r#   r$   r%   r&   r'   r(   r)   r*   r+   r5   r6   r7   r?   rC   
all_imagesrN   s                       rA   
preprocesszCLIPImageProcessor.preprocess   s   L "+!6IDNN	'tTYYTfN'38+9+E4K^K^!*!6IDNN	!)W[\	#-#9Zt
+9+E4K^K^'3'?|TEVEV#-#9Zt
!*!6IDNN	+9+E4K^K^DLfLfg$V,F#:  	&!)%!)	
 9?@nU+@F@ 6<<E.'<<6!9%*s
 $ >vay I
 	%E%dXars((u9Xi(j5ZkljiSd '  e$	%$ $
 ({N_`
 

 '>BBM A =:
s   .H/H4H9)__name__
__module____qualname____doc__model_input_namesr   BICUBICboolr   strintr   floatr   r   r;   npndarrayr   r   FIRSTr   r   PILImagerX   __classcell__)r@   s   @rA   r   r   4   s   $L (( #'9'A'A#$(,3!:>9=#8-8- 38n8- %	8-
 8- S>8- 8- c5j)8- 8- U5$u+#5678- E%e"4568- 8- 
8-| (:'A'A>BDH/
zz/
 38n/
 %	/

 eC)9$9:;/
 $E#/?*?$@A/
 
/
h #'+# $!:>9=#;?2B2H2HDH!QCQC QC 38n	QC
 %QC QC QC QC QC QC U5$u+#567QC E%e"456QC QC !sJ!78QC ./QC  $E#/?*?$@A!QC$ 
%QCrB   r   )'r\   typingr   r   r   r   numpyrc   image_processing_utilsr   r	   r
   image_transformsr   r   r   r   image_utilsr   r   r   r   r   r   r   r   r   r   r   r   utilsr   r   r   
get_loggerrY   rQ   rf   r   r9   rB   rA   <module>rp      so    & . .  U U     > = 
		H	% eC+ eCrB   