
    qi<                         d 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 ddlmZmZmZmZ  ej:                  e      Z e       rddl Z  G d d	e      Z!d	gZ"y)
zImage processor class for BiT.    N   )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_flat_list_of_imagesto_numpy_arrayvalid_imagesvalidate_preprocess_arguments)
TensorTypefilter_out_non_signature_kwargs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z  ded	ed
ee	e
f   dz  dede
ez  dedeee   z  dz  deee   z  dz  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z  dz  de	ez  dz  dej                  fdZ e       ddddddddddddej&                  dfdededz  dee	e
f   dz  dedz  d	edz  d
e
dz  dedz  dedz  dedz  deee   z  dz  deee   z  dz  dedz  de	ez  dz  dedz  de	ez  dz  dej.                  j.                  f d       Z xZS )BitImageProcessora`
  
    Constructs a BiT 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 `PILImageResampling.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:
            Whether to normalize the image. Can be overridden by `do_normalize` in the `preprocess` method.
        image_mean (`float` or `list[float]`, *optional*, defaults to `OPENAI_CLIP_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 `OPENAI_CLIP_MEAN`):
            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                 6   t        |   d	i | ||nddi}t        |d      }||nddd}t        |dd      }|| _        || _        || _        || _        || _        || _        || _	        || _
        |	|	nt        | _        |
|
nt        | _        || _        y )
Nshortest_edge   F)default_to_square)heightwidthTr!   )r,   
param_name )super__init__r   r   r   r   r    r!   r"   r#   r$   r   r%   r   r&   r'   )selfr   r   r   r    r!   r"   r#   r$   r%   r&   r'   kwargs	__class__s                ^/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/bit/image_processing_bit.pyr2   zBitImageProcessor.__init__Y   s     	"6"'tos-CTU;!*!6IsUX<Y	!)tP[\	"	 ,"$,((2(>*DT&/&;,    imagedata_formatinput_data_formatc                     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*   Fr-   r.   zASize must contain either 'shortest_edge' or 'height' and 'width'.)r   r,   r:   )r   r   r9   r:   )
ValueErrorr   r	   )	r3   r8   r   r   r9   r:   r4   r,   output_sizes	            r6   r	   zBitImageProcessor.resize{   s    2 !d"(D %'T/NDM2D`aa2//	
 
#/
 
 	
r7   imagesreturn_tensorsc                 2   ||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        |      }t        |      st        d      t        |||	|
||||||
       |r|D cg c]  }t!        |       }}|D cg c]  }t#        |       }}|r#t%        |d         rt&        j)                  d	       |t+        |d         }g }|D ]m  }|r| j-                  ||||
      }|r| j/                  |||      }|r| j1                  |||      }|	r| j3                  ||
||      }|j5                  |       o |D cg c]  }t7        |||       }}d|i}t9        ||      S c c}w c c}w c c}w )aP  
        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.PYTORCH` or `'pt'`: Return a batch of type `torch.Tensor`.
                - `TensorType.NUMPY` or `'np'`: Return a batch of type `np.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)r/   r,   r!   TzSInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, or torch.Tensor)
r"   r#   r$   r%   r&   r    r!   r   r   r   r   zIt looks like you are trying to rescale already rescaled images. If the input images have pixel values between 0 and 1, set `do_rescale=False` to avoid rescaling them again.)r8   r   r   r:   )r8   r   r:   )r8   scaler:   )r8   meanstdr:   )input_channel_dimr   )datatensor_type)r   r   r   r   r    r!   r"   r#   r$   r%   r&   r'   r   r   r<   r   r   r   r   loggerwarning_oncer   r	   center_croprescale	normalizeappendr
   r   )r3   r>   r   r   r   r    r!   r"   r#   r$   r%   r&   r'   r?   r9   r:   r8   
all_imagesrE   s                      r6   
preprocesszBitImageProcessor.preprocess   sr   H "+!6IDNN	'tTYYTfN'38+9+E4K^K^!*!6IDNN	!)W[\	#-#9Zt
+9+E4K^K^'3'?|TEVEV#-#9Zt
!*!6IDNN	+9+E4K^K^)&1F#rss%!)%!)	
 9?@nU+@F@ 6<<E.'<</&)4s
 $ >vay I
 	%E%dXars((u9Xi(j5ZkljiSd '  e$	%& $
 ({N_`
 

 '>BBO A =<
s   	H
!H"H)__name__
__module____qualname____doc__model_input_namesr   BICUBICbooldictstrintfloatlistr2   npndarrayr   r	   r   FIRSTr   r   PILImagerN   __classcell__)r5   s   @r6   r   r   0   s   $L (( &*'9'A'A#+/&-!1504#-- 38nt#- %	-
 - S>D(- - e- - DK'$.- 4;&-- - 
-L (:'A'A59;?/
zz/
 38n/
 %	/

 ++d2/
 !11D8/
 
/
b %& "&&*.2&* $"&'+$(1504&*26/?/E/E;?!LCLC $;LC 38nt#	LC
 %t+LC tLC :LC 4KLC LC TkLC DK'$.LC 4;&-LC tLC j(4/LC &,LC  !11D8!LC" 
#LC 'LCr7   r   )#rR   numpyr[   image_processing_utilsr   r   r   image_transformsr   r   r	   r
   image_utilsr   r   r   r   r   r   r   r   r   r   r   utilsr   r   r   r   
get_loggerrO   rG   r^   r   __all__r0   r7   r6   <module>rh      su    %  U U     _ ^ 
		H	% IC* ICX 
r7   