
    sgS                     
   d Z ddlmZ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 ddlmZmZmZm Z m!Z!m"Z"  e!       rddl#Z# e       rddl$Z$ e"jJ                  e&      Z' G d	 d
e
      Z(y)z$Image processor class for MobileViT.    )DictListOptionalTupleUnionN   )BaseImageProcessorBatchFeatureget_size_dict)flip_channel_orderget_resize_output_image_sizeresizeto_channel_dimension_format)	ChannelDimension
ImageInputPILImageResamplinginfer_channel_dimension_formatis_scaled_imagemake_list_of_imagesto_numpy_arrayvalid_imagesvalidate_preprocess_arguments)
TensorTypefilter_out_non_signature_kwargsis_torch_availableis_torch_tensoris_vision_availableloggingc                       e Zd ZdZdgZddej                  dddddfdedee	e
f   ded	ed
ee
ef   dedee	e
f   deddf fdZej                  ddfdej                  dee	e
f   dedeee	ef      deee	ef      dej                  fdZ	 	 d dej                  deee	ef      deee	ef      dej                  fdZd! fd	Z	 	 	 	 	 d"deded	edededeee	e
f      ded
ee   deee	e
f      deee	ef      fdZ	 	 	 	 	 	 	 	 	 	 d#dededee	e
f   ded	ed
ededee	e
f   dedeee	ef      deee	ef      dej                  fdZ	 	 	 	 	 d"dededee	e
f   dedee	e
f   deee	ef      dej                  fdZ e       ddddddddddej4                  dfdedee   dedee	e
f   ded	ed
ededee	e
f   dedeee	ef      dedeee	ef      dej:                  j:                  fd       Zd!dee    fdZ! xZ"S )$MobileViTImageProcessora$  
    Constructs a MobileViT 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 the
            `do_resize` parameter in the `preprocess` method.
        size (`Dict[str, int]` *optional*, defaults to `{"shortest_edge": 224}`):
            Controls the 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`):
            Defines the 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_center_crop (`bool`, *optional*, defaults to `True`):
            Whether to crop the input at the center. If the input size is smaller than `crop_size` along any edge, the
            image is padded with 0's and then center cropped. Can be overridden by the `do_center_crop` parameter in
            the `preprocess` method.
        crop_size (`Dict[str, int]`, *optional*, defaults to `{"height": 256, "width": 256}`):
            Desired output size `(size["height"], size["width"])` when applying center-cropping. Can be overridden by
            the `crop_size` parameter in the `preprocess` method.
        do_flip_channel_order (`bool`, *optional*, defaults to `True`):
            Whether to flip the color channels from RGB to BGR. Can be overridden by the `do_flip_channel_order`
            parameter in the `preprocess` method.
    pixel_valuesTNgp?	do_resizesizeresample
do_rescalerescale_factordo_center_crop	crop_sizedo_flip_channel_orderreturnc	                     t        
|   d	i |	 ||nddi}t        |d      }||nddd}t        |d      }|| _        || _        || _        || _        || _        || _        || _	        || _
        y )
Nshortest_edge   Fdefault_to_square   )heightwidthr(   
param_name )super__init__r   r"   r#   r$   r%   r&   r'   r(   r)   )selfr"   r#   r$   r%   r&   r'   r(   r)   kwargs	__class__s             k/var/www/html/venv/lib/python3.12/site-packages/transformers/models/mobilevit/image_processing_mobilevit.pyr7   z MobileViTImageProcessor.__init__X   s     	"6"'tos-CTU;!*!6IsUX<Y	!)D	"	 $,,"%:"    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 )	a[  
        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.BILINEAR`):
                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,   Fr1   r2   zASize must contain either 'shortest_edge' or 'height' and 'width'.)r#   r/   r?   )r#   r$   r>   r?   )
ValueErrorr   r   )	r8   r=   r#   r$   r>   r?   r9   r/   output_sizes	            r;   r   zMobileViTImageProcessor.resizet   s    2 !d"(D %'T/NDM2D`aa2//	
 
#/
 
 	
r<   c                     t        |||      S )a  
        Flip the color channels from RGB to BGR or vice versa.

        Args:
            image (`np.ndarray`):
                The image, represented as a numpy array.
            data_format (`ChannelDimension` or `str`, *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.
        )r>   r?   )r   )r8   r=   r>   r?   s       r;   r   z*MobileViTImageProcessor.flip_channel_order   s    " "%[Teffr<   c                 (    t        |   |fd|i|S )z
        Preprocesses a batch of images and optionally segmentation maps.

        Overrides the `__call__` method of the `Preprocessor` class so that both images and segmentation maps can be
        passed in as positional arguments.
        segmentation_maps)r6   __call__)r8   imagesrE   r9   r:   s       r;   rF   z MobileViTImageProcessor.__call__   s      wV:KVvVVr<   c                     |r| j                  ||||
      }|r| j                  |||
      }|r| j                  ||	|
      }|r| j                  ||
      }|S )N)r=   r#   r$   r?   )r=   scaler?   )r=   r#   r?   )r?   )r   rescalecenter_cropr   )r8   r=   r"   r%   r'   r)   r#   r$   r&   r(   r?   s              r;   _preprocessz#MobileViTImageProcessor._preprocess   so     KKe$]nKoELLuNVgLhE$$5yTe$fE ++EEV+WEr<   c                     t        |      }t        |      r|rt        j                  d       |t	        |      }| j                  |||||||||	|
      }t        ||
|      }|S )zPreprocesses a single image.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$   r%   r&   r'   r(   r)   r?   )input_channel_dim)r   r   loggerwarning_oncer   rL   r   )r8   r=   r"   r#   r$   r%   r&   r'   r(   r)   r>   r?   s               r;   _preprocess_imagez)MobileViTImageProcessor._preprocess_image   s      u%5!js $ >u E  !))"7/ ! 
 ,E;Rcdr<   segmentation_mapc                 @   t        |      }|j                  dk(  rd}|d   }t        j                  }nd}|t	        |d      }| j                  |||t        j                  d||d|	      }|r|j                  d      }|j                  t        j                        }|S )	zPreprocesses a single mask.   T)N.F   )num_channels)	r=   r"   r#   r$   r%   r'   r(   r)   r?   r   )r   ndimr   FIRSTr   rL   r   NEARESTsqueezeastypenpint64)r8   rR   r"   r#   r'   r(   r?   added_channel_dims           r;   _preprocess_maskz(MobileViTImageProcessor._preprocess_mask  s     **:;  A% $/	: 0 6 6 % ($BCSbc$d!++"'//)"'/ , 

 /77:+22288<r<   rG   rE   return_tensorsc                    ||n| j                   }||n| j                  }||n| j                  }||n| j                  }||n| j                  }|
|
n| j
                  }
||n| j                  }t        |d      }|	|	n| j                  }	t        |	d      }	t        |      }|t        |d      }t        |      }t        |      st        d      |t        |      st        d      t        ||||	|||	       |D cg c]  }| j                  ||||||||	|
||
        }}d|i}|)|D cg c]  }| j                  |||||	|       }}||d<   t        ||      S c c}w c c}w )aj  
        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`.
            segmentation_maps (`ImageInput`, *optional*):
                Segmentation map to preprocess.
            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.
            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_rescale (`bool`, *optional*, defaults to `self.do_rescale`):
                Whether to rescale the image by rescale factor.
            rescale_factor (`float`, *optional*, defaults to `self.rescale_factor`):
                Rescale factor to rescale the image by if `do_rescale` 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 if `do_center_crop` is set to `True`.
            do_flip_channel_order (`bool`, *optional*, defaults to `self.do_flip_channel_order`):
                Whether to flip the channel order of the image.
            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:
                    - `ChannelDimension.FIRST`: image in (num_channels, height, width) format.
                    - `ChannelDimension.LAST`: image in (height, width, num_channels) 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.
        Fr.   r(   r3   rT   )expected_ndimszkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.zvInvalid segmentation map type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.)r%   r&   r'   r(   r"   r#   r$   )r=   r"   r#   r$   r%   r&   r'   r(   r)   r>   r?   r!   )rR   r"   r#   r'   r(   r?   labels)datatensor_type)r"   r$   r%   r&   r'   r)   r#   r   r(   r   r   rA   r   rQ   r_   r
   )r8   rG   rE   r"   r#   r$   r%   r&   r'   r(   r)   r`   r>   r?   imgrd   rR   s                    r;   
preprocessz"MobileViTImageProcessor.preprocess,  s   z "+!6IDNN	'38#-#9Zt
+9+E4K^K^+9+E4K^K^%:%F!DLfLf 	 'tTYYTU;!*!6IDNN	!)D	$V,( 34EVW X$V,F#: 
 (>O1P: 
 	&!))	
0 
  ""#!%--#&;'"3 # 
 
" '( ):
! % %%%5'#1'&7 & 
! 
! /DN>BBE
(
!s   #E%3E*target_sizesc                 &   |j                   }|t        |      t        |      k7  rt        d      t        |      r|j	                         }g }t        t        |            D ]k  }t        j                  j                  j                  ||   j                  d      ||   dd      }|d   j                  d      }|j                  |       m |S |j                  d      }t        |j                  d         D cg c]  }||   	 }}|S c c}w )a@  
        Converts the output of [`MobileViTForSemanticSegmentation`] into semantic segmentation maps. Only supports PyTorch.

        Args:
            outputs ([`MobileViTForSemanticSegmentation`]):
                Raw outputs of the model.
            target_sizes (`List[Tuple]` of length `batch_size`, *optional*):
                List of tuples corresponding to the requested final size (height, width) of each prediction. If unset,
                predictions will not be resized.

        Returns:
            semantic_segmentation: `List[torch.Tensor]` of length `batch_size`, where each item is a semantic
            segmentation map of shape (height, width) corresponding to the target_sizes entry (if `target_sizes` is
            specified). Each entry of each `torch.Tensor` correspond to a semantic class id.
        zTMake sure that you pass in as many target sizes as the batch dimension of the logitsr   )dimbilinearF)r#   modealign_cornersrU   )logitslenrA   r   numpyrangetorchnn
functionalinterpolate	unsqueezeargmaxappendshape)	r8   outputsrh   rn   semantic_segmentationidxresized_logitssemantic_mapis	            r;   "post_process_semantic_segmentationz:MobileViTImageProcessor.post_process_semantic_segmentation  s(   "  #6{c,// j  |,+113$&!S[) ;!&!4!4!@!@3K))a)0|C7Hzin "A "  .a077A7>%,,\:; %$ %+MMaM$8!GLMbMhMhijMkGl$m!%:1%=$m!$m$$ %ns   >D)NN)N)NNNNN)
NNNNNNNNNN)#__name__
__module____qualname____doc__model_input_namesr   BILINEARboolr   strintr   floatr7   r\   ndarrayr   r   r   r   rF   r   rL   rQ   r_   r   rX   r   PILImagerg   r   r   r   __classcell__)r:   s   @r;   r    r    6   s   > (( #'9'B'B,3#$(&*;; 38n; %	;
 ; c5j); ; S>;  $; 
;@ (:'B'B>BDH/
zz/
 38n/
 %	/

 eC)9$9:;/
 $E#/?*?$@A/
 
/
h ?CDH	gzzg eC)9$9:;g $E#/?*?$@A	g
 
g&W  *.'+*..2DH  	
   $ tCH~& % ! DcN+ $E#/?*?$@A< #'+ $#$(&*>BDH(( ( 38n	(
 %( ( ( ( S>(  $( eC)9$9:;( $E#/?*?$@A( 
(Z ##$(DH$ $$  $  38n	$ 
 $  S>$  $E#/?*?$@A$  
$ L %& 37#'+ $#$(&*;?(8(>(>DHICIC $J/IC 	IC
 38nIC %IC IC IC IC S>IC  $IC !sJ!78IC &IC $E#/?*?$@AIC 
IC 'ICX)%U )%r<   r    ))r   typingr   r   r   r   r   rp   r\   image_processing_utilsr	   r
   r   image_transformsr   r   r   r   image_utilsr   r   r   r   r   r   r   r   r   utilsr   r   r   r   r   r   r   rr   
get_loggerr   rO   r    r5   r<   r;   <module>r      so    + 5 5  U U u u
 
 
   
		H	%l%0 l%r<   