
    sg=                         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 ddlmZmZm Z m!Z!  e        rddl"Z" e!jF                  e$      Z% G d	 d
e	      Z&y)z#Image processor class for ConvNeXT.    )DictListOptionalUnionN   )BaseImageProcessorBatchFeatureget_size_dict)center_cropget_resize_output_image_sizeresizeto_channel_dimension_format)IMAGENET_STANDARD_MEANIMAGENET_STANDARD_STDChannelDimension
ImageInputPILImageResamplinginfer_channel_dimension_formatis_scaled_imagemake_list_of_imagesto_numpy_arrayvalid_imagesvalidate_preprocess_arguments)
TensorTypefilter_out_non_signature_kwargsis_vision_availableloggingc                   L    e Zd ZdZdgZdddej                  dddddf	dedee	e
f   ded	ed
edee
ef   dedeeeee   f      deeeee   f      ddf fdZej                   ddfdej$                  dee	e
f   de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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eeee   f      deeeee   f      deee	ef      dedeee	ef      dej4                  j4                  fd       Z xZS )ConvNextImageProcessora5
  
    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 overriden
            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 overriden 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
            overriden by `crop_pct` in the `preprocess` method.
        resample (`PILImageResampling`, *optional*, defaults to `Resampling.BILINEAR`):
            Resampling filter to use if resizing the image. Can be overriden 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 overriden 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 overriden 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        |   di |
 ||nddi}t        |d      }|| _        || _        ||nd| _        || _        || _        || _        || _	        ||nt        | _        |	|	| _        y t        | _        y )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              i/var/www/html/venv/lib/python3.12/site-packages/transformers/models/convnext/image_processing_convnext.pyr2   zConvNextImageProcessor.__init__Y   s     	"6"'tos-CTU;"	$,$8i $,((2(>*DZ&/&;AV    imagedata_formatinput_data_formatc           	         t        |d      }d|vrt        d|j                                |d   }|dk  r@t        ||z        }	t	        ||	d|      }
t        d
||
|||d|}t        d
|||f||d|S t        |f||f|||d	|S )a  
        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.
        Fr.   r,   z6Size dictionary must contain 'shortest_edge' key. Got r-   )r"   r/   r:   )r8   r"   r$   r9   r:   )r8   r"   r9   r:   )r"   r$   r9   r:   r0   )r
   
ValueErrorkeysintr   r   r   )r3   r8   r"   r#   r$   r9   r:   r4   r,   resize_shortest_edgeresize_sizes              r6   r   zConvNextImageProcessor.resizeu   s    > TU;$&UVZV_V_VaUbcdd_-3#&}x'?#@ 60E]nK   !'"3 E  #]3'"3	
   #]3!'"3  r7   imagesreturn_tensorsc           
         ||n| j                   }||n| j                  }||n| j                  }||n| j                  }||n| j                  }||n| j
                  }|	|	n| j                  }	|
|
n| j                  }
||n| j                  }t        |d      }t        |      }t        |      st        d      t        ||||	|
|||       |D cg c]  }t        |       }}t        |d         r|rt         j#                  d       |t%        |d         }|r#|D cg c]  }| j'                  |||||       }}|r!|D cg c]  }| j)                  |||       }}|r"|D cg c]  }| j+                  ||	|
|	       }}|D cg c]  }t-        |||
       }}d|i}t/        ||      S c c}w c c}w c c}w c c}w c c}w )aW  
        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.
        Fr.   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$   r   zIt looks like you are trying to rescale already rescaled images. If the input images have pixel values between 0 and 1, set `do_rescale=False` to avoid rescaling them again.)r8   r"   r#   r$   r:   )r8   scaler:   )r8   meanstdr:   )input_channel_dimr    )datatensor_type)r!   r#   r$   r%   r&   r'   r(   r)   r"   r
   r   r   r<   r   r   r   loggerwarning_oncer   r   rescale	normalizer   r	   )r3   rA   r!   r"   r#   r$   r%   r&   r'   r(   r)   rB   r9   r:   r8   rH   s                   r6   
preprocessz!ConvNextImageProcessor.preprocess   sB   B "+!6IDNN	'38'38#-#9Zt
+9+E4K^K^'3'?|TEVEV#-#9Zt
!*!6IDNN	'tTYYTU;$V,F#: 
 	&!)%!		
 6<<E.'<<6!9%*s
 $ >vay I
 $	  dXdu  F   $ 5RcdF 
  $ U^opF  ou
ej'{N_`
 
 '>BBK =

s   F7%F<
G-GG)__name__
__module____qualname____doc__model_input_namesr   BILINEARboolr   strr>   floatr   r   r   r2   BICUBICnpndarrayr   r   r   FIRSTr   r   PILImagerN   __classcell__)r5   s   @r6   r   r   3   s   !F (( #'9'B'B,3!:>9=WW 38nW 	W
 %W W c5j)W W U5$u+#567W E%e"456W 
WB (:'A'A>BDHCzzC 38nC 	C
 %C eC)9$9:;C $E#/?*?$@AC 
CJ %& #'+ $!:>9=;?(8(>(>DHECEC EC 38n	EC
 EC %EC EC EC 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r7   r   )'rR   typingr   r   r   r   numpyrY   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   r\   
get_loggerrO   rJ   r   r0   r7   r6   <module>rf      sp    * . .  U U     _ ^  
		H	%MC/ MCr7   