
    cCi:6                         S r SSKJrJr  SSKrSSKJrJrJ	r	  SSK
JrJr  SSKJrJrJrJrJrJrJrJrJrJrJr  SSKJrJrJr  \R:                  " \5      r " S	 S
\5      r S
/r!g)zImage processor class for Pvt.    )OptionalUnionN   )BaseImageProcessorBatchFeatureget_size_dict)resizeto_channel_dimension_format)IMAGENET_DEFAULT_MEANIMAGENET_DEFAULT_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loggingc                   Z  ^  \ rS rSrSrS/rSS\R                  SSSSS4S\S\	\
\\4      S	\S
\S\\\4   S\S\	\\\\   4      S\	\\\\   4      SS4U 4S jjjr\R                  SS4S\R$                  S\
\\4   S	\S\	\\\4      S\	\\\4      S\R$                  4S jjr\" 5       SSSSSSSSS\R,                  S4S\S\	\   S\	\
\\4      S	\	\   S
\	\   S\	\   S\	\   S\	\\\\   4      S\	\\\\   4      S\	\\\4      S\\\4   S\	\\\4      4S jj5       rSrU =r$ )PvtImageProcessor*   a  
Constructs a PVT image processor.

Args:
    do_resize (`bool`, *optional*, defaults to `True`):
        Whether to resize the image's (height, width) dimensions to the specified `(size["height"],
        size["width"])`. Can be overridden by the `do_resize` parameter in the `preprocess` method.
    size (`dict`, *optional*, defaults to `{"height": 224, "width": 224}`):
        Size of the output image after resizing. Can be overridden by the `size` parameter in the `preprocess`
        method.
    resample (`PILImageResampling`, *optional*, defaults to `Resampling.BILINEAR`):
        Resampling filter to use if resizing the image. Can be overridden by the `resample` parameter 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 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_DEFAULT_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_DEFAULT_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.
pixel_valuesTNgp?	do_resizesizeresample
do_rescalerescale_factordo_normalize
image_mean	image_stdreturnc	                    > [         T
U ]  " S0 U	D6  Ub  UOSSS.n[        U5      nXl        X@l        X`l        X l        X0l        XPl        Ub  UO[        U l
        Ub  Xl        g [        U l        g )N   )heightwidth )super__init__r   r   r    r"   r   r   r!   r   r#   r   r$   )selfr   r   r   r    r!   r"   r#   r$   kwargs	__class__s             f/home/james-whalen/.local/lib/python3.13/site-packages/transformers/models/pvt/image_processing_pvt.pyr,   PvtImageProcessor.__init__K   sp     	"6"'tc-JT""$(	 ,(2(>*DY&/&;AU    imagedata_formatinput_data_formatc                     [        U5      nSU;  d  SU;  a  [        SUR                  5        35      eUS   US   4n[        U4UUUUS.UD6$ )a  
Resize an image to `(size["height"], size["width"])`.

Args:
    image (`np.ndarray`):
        Image to resize.
    size (`dict[str, int]`):
        Dictionary in the format `{"height": int, "width": int}` specifying the size of the output image.
    resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BILINEAR`):
        `PILImageResampling` filter to use when resizing the image e.g. `PILImageResampling.BILINEAR`.
    data_format (`ChannelDimension` or `str`, *optional*):
        The channel dimension format for the output image. If unset, the channel dimension format of the input
        image is used. 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.
    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.

Returns:
    `np.ndarray`: The resized image.
r(   r)   zFThe `size` dictionary must contain the keys `height` and `width`. Got )r   r   r4   r5   )r   
ValueErrorkeysr	   )r-   r3   r   r   r4   r5   r.   output_sizes           r0   r	   PvtImageProcessor.resized   sy    F T"47$#6efjfofofqersttH~tG}5
#/
 
 	
r2   imagesreturn_tensorsc                    Ub  UOU R                   nUb  UOU R                  nUb  UOU R                  nUb  UOU R                  nUb  UOU R                  nUb  UOU R
                  nU	b  U	OU R                  n	Ub  UOU R                  n[        U5      n[        U5      n[        U5      (       d  [        S5      e[        UUUUU	UUUS9  U Vs/ s H  n[        U5      PM     nnU(       a(  [        US   5      (       a  [        R!                  S5        Uc  [#        US   5      nU(       a   U Vs/ s H  nU R%                  XXLS9PM     nnU(       a   U Vs/ s H  nU R'                  XUS9PM     nnU(       a   U Vs/ s H  nU R)                  XXS9PM     nnU Vs/ s H  n[+        XUS9PM     nnS	U0n[-        XS
9$ s  snf s  snf s  snf s  snf s  snf )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`):
        Dictionary in the format `{"height": h, "width": w}` specifying the size of the output image after
        resizing.
    resample (`PILImageResampling` filter, *optional*, defaults to `self.resample`):
        `PILImageResampling` filter to use if resizing the image e.g. `PILImageResampling.BILINEAR`. Only has
        an effect if `do_resize` is set to `True`.
    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`.
    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.
zkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.)r    r!   r"   r#   r$   r   r   r   r   zIt looks like you are trying to rescale already rescaled images. If the input images have pixel values between 0 and 1, set `do_rescale=False` to avoid rescaling them again.)r3   r   r   r5   )r3   scaler5   )r3   meanstdr5   )input_channel_dimr   )datatensor_type)r   r    r"   r   r!   r#   r$   r   r   r   r   r7   r   r   r   loggerwarning_oncer   r	   rescale	normalizer
   r   )r-   r;   r   r   r   r    r!   r"   r#   r$   r<   r4   r5   	size_dictr3   rB   s                   r0   
preprocessPvtImageProcessor.preprocess   s*   x "+!6IDNN	#-#9Zt
'3'?|TEVEV'38+9+E4K^K^#-#9Zt
!*!6IDNN	'tTYY!$'	)&1F##:  	&!)%!		
 6<<VE.'V</&)44s
 $ >vay I $#E %(p#  
  $#E 5Rcd#  
  $#E Up#   ou
ntej'N_`nt 	 
 'BBG =

s   G0GG>GG)r"   r    r   r#   r$   r   r!   r   )__name__
__module____qualname____firstlineno____doc__model_input_namesr   BILINEARboolr   dictstrintr   floatlistr,   npndarrayr   r	   r   FIRSTr   r   rI   __static_attributes____classcell__)r/   s   @r0   r   r   *   s   < (( )-'9'B'B,3!:>9=VV tCH~&V %	V
 V c5j)V V U5$u+#567V E%e"456V 
V V: (:'B'B>BDH.
zz.
 38n.
 %	.

 eC)9$9:;.
 $E#/?*?$@A.
 
.
` %& %))-15%)*.'+:>9=;?4D4J4JDH|C|C D>|C tCH~&	|C
 -.|C TN|C !|C tn|C U5$u+#567|C E%e"456|C !sJ!78|C 3 001|C $E#/?*?$@A|C '|Cr2   r   )"rO   typingr   r   numpyrX   image_processing_utilsr   r   r   image_transformsr	   r
   image_utilsr   r   r   r   r   r   r   r   r   r   r   utilsr   r   r   
get_loggerrK   rD   r   __all__r*   r2   r0   <module>re      sd    % "  U U C    J I 
		H	%gC* gCT 
r2   