
    bCi>                        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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Jr  SS	K J!r!  \" 5       (       a  SSK"r"\RF                  " \$5      r%\!" S
S9 " S S\5      5       r&S/r'g)z#Image processor class for ConvNeXT.    )OptionalUnionN   )BaseImageProcessorBatchFeatureget_size_dict)center_cropget_resize_output_image_sizeresizeto_channel_dimension_format)IMAGENET_STANDARD_MEANIMAGENET_STANDARD_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logging)requires)vision)backendsc                     ^  \ rS rSrSrS/rSSS\R                  SSSSS4	S\S\	\
\\4      S	\	\   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
\S\	\\\4      S\	\\\4      S\R&                  4S jjr\" 5       SSSSSSSSSS\R.                  S4S\S\	\   S\	\
\\4      S	\	\   S
\	\   S\	\   S\	\   S\	\   S\	\\\\   4      S\	\\\\   4      S\	\\\4      S\S\	\\\4      S\R6                  R6                  4S jj5       rSrU =r$ )ConvNextImageProcessor4   a	  
Constructs a ConvNeXT image processor.

Args:
    do_resize (`bool`, *optional*, defaults to `True`):
        Controls 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": 384}`):
        Resolution of the output image after `resize` is applied. If `size["shortest_edge"]` >= 384, the image is
        resized to `(size["shortest_edge"], size["shortest_edge"])`. Otherwise, the smaller edge of the image will
        be matched to `int(size["shortest_edge"]/crop_pct)`, after which the image is cropped to
        `(size["shortest_edge"], size["shortest_edge"])`. Only has an effect if `do_resize` is set to `True`. Can
        be overridden by `size` in the `preprocess` method.
    crop_pct (`float` *optional*, defaults to 224 / 256):
        Percentage of the image to crop. Only has an effect if `do_resize` is `True` and size < 384. Can be
        overridden by `crop_pct` in the `preprocess` method.
    resample (`PILImageResampling`, *optional*, defaults to `Resampling.BILINEAR`):
        Resampling filter to use if resizing the image. Can be overridden by `resample` 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 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.
pixel_valuesTNgp?	do_resizesizecrop_pct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0n[        USS9nXl        X l        Ub  UOSU l        X@l        XPl        X`l        Xpl	        Ub  UO[        U l        U	b  Xl        g [        U l        g )Nshortest_edge  Fdefault_to_squareg      ? )super__init__r   r#   r$   r%   r&   r'   r(   r)   r   r*   r   r+   )selfr#   r$   r%   r&   r'   r(   r)   r*   r+   kwargs	__class__s              p/home/james-whalen/.local/lib/python3.13/site-packages/transformers/models/convnext/image_processing_convnext.pyr4   ConvNextImageProcessor.__init__[   s     	"6"'tos-CTU;"	$,$8i $,((2(>*DZ&/&;AV    imagedata_formatinput_data_formatc           	         [        USS9nSU;  a  [        SUR                  5        35      eUS   nUS:  a:  [        X-  5      n	[	        XSUS9n
[        S
UU
UUUS.UD6n[        S
UX4UUS.UD6$ [        U4X4UUUS	.UD6$ )ab  
Resize an image.

Args:
    image (`np.ndarray`):
        Image to resize.
    size (`dict[str, int]`):
        Dictionary of the form `{"shortest_edge": int}`, specifying the size of the output image. If
        `size["shortest_edge"]` >= 384 image is resized to `(size["shortest_edge"], size["shortest_edge"])`.
        Otherwise, the smaller edge of the image will be matched to `int(size["shortest_edge"] / crop_pct)`,
        after which the image is cropped to `(size["shortest_edge"], size["shortest_edge"])`.
    crop_pct (`float`):
        Percentage of the image to crop. Only has an effect if size < 384.
    resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BICUBIC`):
        Resampling filter to use when resizing 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 from the input
        image.
Fr0   r.   z6Size dictionary must contain 'shortest_edge' key. Got r/   )r$   r1   r=   )r;   r$   r&   r<   r=   )r;   r$   r<   r=   )r$   r&   r<   r=   r2   )r   
ValueErrorkeysintr
   r   r	   )r5   r;   r$   r%   r&   r<   r=   r6   r.   resize_shortest_edgeresize_sizes              r8   r   ConvNextImageProcessor.resizew   s    > TU;$&UVZV_V_VaUbcdd_-3#&}'?#@ 6E]nK   !'"3 E  #3'"3	
   #3!'"3  r:   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b  UOU R                  n[        USS9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'                  XXEUS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`):
        Size of the output image after `resize` has been applied. If `size["shortest_edge"]` >= 384, the image
        is resized to `(size["shortest_edge"], size["shortest_edge"])`. Otherwise, the smaller edge of the
        image will be matched to `int(size["shortest_edge"]/ crop_pct)`, after which the image is cropped to
        `(size["shortest_edge"], size["shortest_edge"])`. Only has an effect if `do_resize` is set to `True`.
    crop_pct (`float`, *optional*, defaults to `self.crop_pct`):
        Percentage of the image to crop if size < 384.
    resample (`int`, *optional*, defaults to `self.resample`):
        Resampling filter to use if resizing the image. This can be one of `PILImageResampling`, filters. 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.
    image_std (`float` or `list[float]`, *optional*, defaults to `self.image_std`):
        Image standard deviation.
    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.
Fr0   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$   r&   r   zIt looks like you are trying to rescale already rescaled images. If the input images have pixel values between 0 and 1, set `do_rescale=False` to avoid rescaling them again.)r;   r$   r%   r&   r=   )r;   scaler=   )r;   meanstdr=   )input_channel_dimr"   )datatensor_type)r#   r%   r&   r'   r(   r)   r*   r+   r$   r   r   r   r?   r   r   r   loggerwarning_oncer   r   rescale	normalizer   r   )r5   rE   r#   r$   r%   r&   r'   r(   r)   r*   r+   rF   r<   r=   r;   rL   s                   r8   
preprocess!ConvNextImageProcessor.preprocess   sI   B "+!6IDNN	'38'38#-#9Zt
+9+E4K^K^'3'?|TEVEV#-#9Zt
!*!6IDNN	'tTYYTU;)&1F##: 
 	&!)%!		
 6<<VE.'V</&)44s
 $ >vay I
 $	 $E Xdu   $	    $#E 5Rcd#  
  $#E Up#   ou
ntej'N_`nt 	 
 'BBK =

s   G G(GG!/G&)	r%   r)   r'   r#   r*   r+   r&   r(   r$   )__name__
__module____qualname____firstlineno____doc__model_input_namesr   BILINEARboolr   dictstrrA   floatr   listr4   BICUBICnpndarrayr   r   r   FIRSTr   r   PILImagerR   __static_attributes____classcell__)r7   s   @r8   r    r    4   s   !F (( )-$('9'B'B,3!:>9=WW tCH~&W 5/	W
 %W W c5j)W W U5$u+#567W E%e"456W 
W WB (:'A'A>BDHCzzC 38nC 	C
 %C eC)9$9:;C $E#/?*?$@AC 
CJ %& %))-$(15%)*.'+:>9=;?(8(>(>DHECEC D>EC tCH~&	EC
 5/EC -.EC TNEC !EC tnEC U5$u+#567EC E%e"456EC !sJ!78EC &EC $E#/?*?$@AEC 
EC 'ECr:   r    )(rX   typingr   r   numpyra   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   utils.import_utilsr   rd   
get_loggerrT   rN   r    __all__r2   r:   r8   <module>rq      s    * "  U U     _ ^ *  
		H	% 
;MC/ MC  MC` $
$r:   