
     `i<>                         d Z ddl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 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%dS )zImage processor class for BiT.    )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_flat_list_of_imagesto_numpy_arrayvalid_imagesvalidate_preprocess_arguments)
TensorTypefilter_out_non_signature_kwargsis_vision_availableloggingc            #       V    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
ef                  ded	ed
e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 e            ddddddddddddej        dfdedee         dee	e
ef                  dee         d	ee         d
e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e
ef                  dee         deee
ef                  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                 `    t                      j        d	i | ||nddi}t          |d          }||nddd}t          |dd          }|| _        || _        || _        || _        || _        || _        || _	        || _
        |	|	nt          | _        |
|
nt          | _        || _        d S )
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                /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/bit/image_processing_bit.pyr4   zBitImageProcessor.__init__\   s     	""6"""'ttos-CTU;;;!*!6IIsUX<Y<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/   r0   zASize must contain either 'shortest_edge' or 'height' and 'width'.)r    r.   r<   )r    r!   r;   r<   )
ValueErrorr
   r   )	r5   r:   r    r!   r;   r<   r6   r.   output_sizes	            r8   r   zBitImageProcessor.resize~   s    2 !d""(D %'T//NDM2DD`aaa2//	
 
 
 
#/
 
 
 
 	
r9   imagesreturn_tensorsc                    ||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	 |D             }d
 |D             }|r/t!          |d                   rt"                              d           t'          |d                   g }|D ]}|r|                     |||          }|r|                     ||          }|r|                     ||          }|	r|                     ||
|          }|                    |           fd|D             }d|i}t3          ||          S )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.
        Nr    F)r1   r.   r#   TzkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.)
r$   r%   r&   r'   r(   r"   r#   r   r    r!   c                 ,    g | ]}t          |          S r2   )r	   .0r:   s     r8   
<listcomp>z0BitImageProcessor.preprocess.<locals>.<listcomp>  s     @@@nU++@@@r9   c                 ,    g | ]}t          |          S r2   )r   rD   s     r8   rF   z0BitImageProcessor.preprocess.<locals>.<listcomp>  s     <<<E.''<<<r9   r   zIt looks like you are trying to rescale already rescaled images. If the input images have pixel values between 0 and 1, set `do_rescale=False` to avoid rescaling them again.)r:   r    r!   r<   )r:   r    r<   )r:   scaler<   )r:   meanstdr<   c                 4    g | ]}t          |           S ))input_channel_dim)r   )rE   r:   r;   r<   s     r8   rF   z0BitImageProcessor.preprocess.<locals>.<listcomp>;  s9     
 
 
 ({N_```
 
 
r9   r   )datatensor_type)r   r    r   r!   r"   r#   r$   r%   r&   r'   r(   r)   r   r   r>   r   r   loggerwarning_oncer   r   center_croprescale	normalizeappendr   )r5   r@   r   r    r!   r"   r#   r$   r%   r&   r'   r(   r)   rA   r;   r<   
all_imagesr:   rM   s                 ``   r8   
preprocesszBitImageProcessor.preprocess   s   L "+!6IIDN	'ttTYTfNNN'388+9+E4K^!*!6IIDN	!)W[\\\	#-#9ZZt
+9+E4K^'3'?||TEV#-#9ZZt
!*!6IIDN	+9+E4K^)&11F## 	:  
 	&!)%!)	
 	
 	
 	
  	A@@@@@F =<V<<< 	/&)44 	s  
 $ >vay I I
 	% 	%E t%dXarss k((u9Xi(jj m5Zkll jiSd '   e$$$$
 
 
 
 
#
 
 

 '>BBBBr9   )__name__
__module____qualname____doc__model_input_namesr   BICUBICboolr   dictstrintr   floatlistr4   npndarrayr   r   r   FIRSTr   r   PILImagerV   __classcell__)r7   s   @r8   r   r   3   sw       $ $L (( )-'9'A#.2,3!:>9=#- -- tCH~&- %	-
 - DcN+- - c5j)- - U5$u+#567- E%e"456- - 
- - - - - -L (:'A>BDH/
 /
z/
 38n/
 %	/

 eC)9$9:;/
 $E#/?*?$@A/
 
/
 /
 /
 /
b %$&& %))-15)-#'%)*.'+:>9=)-;?2B2HDH!QC QCQC D>QC tCH~&	QC
 -.QC !QC C=QC TNQC !QC tnQC U5$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 QC QC '&QC QC QC QC QCr9   r   )&rZ   typingr   r   numpyrc   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_loggerrW   rO   rf   r   __all__r2   r9   r8   <module>rq      s   % $ " " " " " " " "     U U U U U U U U U U                                     _ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ 
	H	%	%  JJJNC NC NC NC NC* NC NC NCb 
r9   