§
    9²¸j–1  ã                   óN  — d dl mZ d dlmZmZ d dlmZ ddlm	Z	 ddl
mZ ddlmZmZ ddlmZmZmZmZmZmZmZmZ dd	lmZmZ dd
lmZmZmZ  e¦   «         rd dlZerddl m!Z!  G d„ ded¬¦  «        Z"d„ Z#defd„Z$	 	 dd„Z%	 	 	 	 dd„Z&e G d„ de	¦  «        ¦   «         Z'dgZ(dS )é    )ÚTYPE_CHECKING)ÚImageÚ	ImageDraw)Ú
functionalé   )ÚTorchvisionBackend)ÚBatchFeature)Úgroup_images_by_shapeÚreorder_images)Ú
ImageInputÚ	ImageTypeÚPILImageResamplingÚSizeDictÚget_image_typeÚis_pil_imageÚis_valid_imageÚto_numpy_array)ÚImagesKwargsÚUnpack)Ú
TensorTypeÚauto_docstringÚis_torch_availableNé   )Ú$EfficientLoFTRKeypointMatchingOutputc                   ó   — e Zd ZU dZeed<   dS )Ú"EfficientLoFTRImageProcessorKwargszÀ
    do_grayscale (`bool`, *optional*, defaults to `self.do_grayscale`):
        Whether to convert the image to grayscale. Can be overridden by `do_grayscale` in the `preprocess` method.
    Údo_grayscaleN)Ú__name__Ú
__module__Ú__qualname__Ú__doc__ÚboolÚ__annotations__© ó    ú’/root/private/project/pallet_detection_v2/.venv/lib/python3.11/site-packages/transformers/models/efficientloftr/image_processing_efficientloftr.pyr   r   $   s*   € € € € € € ðð ð
 ÐÐÑÐÐr%   r   F)Útotalc                 ó¨   — t          | ¦  «        pCt          | ¦  «        o4t          | ¦  «        t          j        k    ot          | j        ¦  «        dk    S )Nr   ©r   r   r   r   ÚPILÚlenÚshape©Úimages    r&   Ú_is_valid_imager/   -   sM   € Ý˜ÑÔð Ý�uÑÔÐb¥.°Ñ"7Ô"7½9¼=Ò"HÐbÍSÐQVÔQ\ÑM]ÔM]ÐabÒMbðr%   Úimagesc                 ó  ‡— d}d„ Št          | t          ¦  «        rWt          | ¦  «        dk    rt          ˆfd„| D ¦   «         ¦  «        r| S t          ˆfd„| D ¦   «         ¦  «        rd„ | D ¦   «         S t	          |¦  «        ‚)N)z-Input images must be a one of the following :z - A pair of PIL images.z - A pair of 3D arrays.z! - A list of pairs of PIL images.z  - A list of pairs of 3D arrays.c                 ó¨   — t          | ¦  «        pCt          | ¦  «        o4t          | ¦  «        t          j        k    ot          | j        ¦  «        dk    S )z$images is a PIL Image or a 3D array.r   r)   r-   s    r&   r/   z8validate_and_format_image_pairs.<locals>._is_valid_image<   sN   € å˜EÑ"Ô"ð 
Ý˜5Ñ!Ô!Ðf¥n°UÑ&;Ô&;½y¼}Ò&LÐfÕQTÐUZÔU`ÑQaÔQaÐefÒQfð	
r%   é   c              3   ó.   •K  — | ]} ‰|¦  «        V — Œd S ©Nr$   ©Ú.0r.   r/   s     €r&   ú	<genexpr>z2validate_and_format_image_pairs.<locals>.<genexpr>C   s-   øè è € Ð#QÐ#QÀ _ _°UÑ%;Ô%;Ð#QÐ#QÐ#QÐ#QÐ#QÐ#Qr%   c              3   óž   •K  — | ]G}t          |t          ¦  «        o-t          |¦  «        d k    ot          ˆfd„|D ¦   «         ¦  «        V — ŒHdS )r3   c              3   ó.   •K  — | ]} ‰|¦  «        V — Œd S r5   r$   r6   s     €r&   r8   z<validate_and_format_image_pairs.<locals>.<genexpr>.<genexpr>H   s-   øè è € ÐCÐC¨u�O�O EÑ*Ô*ÐCÐCÐCÐCÐCÐCr%   N)Ú
isinstanceÚlistr+   Úall)r7   Ú
image_pairr/   s     €r&   r8   z2validate_and_format_image_pairs.<locals>.<genexpr>E   s}   øè è € ð 
ð 
ð õ �z¥4Ñ(Ô(ð DÝ�J‘” 1Ò$ðDåÐCÐCÐCÐC¸
ÐCÑCÔCÑCÔCð
ð 
ð 
ð 
ð 
ð 
r%   c                 ó   — g | ]	}|D ]}|‘ŒŒ
S r$   r$   )r7   r>   r.   s      r&   ú
<listcomp>z3validate_and_format_image_pairs.<locals>.<listcomp>K   s%   € ÐKÐKÐK˜jÀ
ÐKÐK°u�EÐKÐKÐKÐKr%   )r;   r<   r+   r=   Ú
ValueError)r0   Úerror_messager/   s     @r&   Úvalidate_and_format_image_pairsrC   3   sÆ   ø€ ð€Mð
ð 
ð 
õ �&�$ÑÔð 	LÝˆv‰;Œ;˜!ÒÐ¥Ð#QÐ#QÐ#QÐ#QÈ&Ð#QÑ#QÔ#QÑ QÔ QÐØˆMÝð 
ð 
ð 
ð 
ð %ð	
ñ 
ô 
ñ 
ô 
ð 	Lð LÐK¨FÐKÑKÔKÐKÝ
�]Ñ
#Ô
#Ð#r%   r.   útorch.Tensorc           	      ó(  — | j         dk     s| j        | j         dk    rdnd         dk    rdS t          j        | dddd…dd…f         | dddd…dd…f         k    ¦  «        o3t          j        | dddd…dd…f         | dddd…dd…f         k    ¦  «        S )zAChecks if an image is grayscale (all RGB channels are identical).r   r   r   T.Nr3   )Úndimr,   Útorchr=   r-   s    r&   Úis_grayscalerH   O   s»   € ð „z�A‚~€~˜œ¨%¬*¸ª/¨/ Q Q¸qÔAÀQÒFÐFØˆtÝŒ9�U˜3  1 1 1 a a a˜<Ô(¨E°#°q¸!¸!¸!¸Q¸Q¸Q°,Ô,?Ò?Ñ@Ô@ð ÅUÄYØˆc�1�a�a�a˜˜˜ˆlÔ˜u S¨!¨Q¨Q¨Q°°° \Ô2Ò2ñFô Fð r%   Úreturnc                 óP   — t          | ¦  «        r| S t          j        | d¬¦  «        S )a±  
    Converts an image to grayscale format using the NTSC formula. Only support torch.Tensor.

    This function is supposed to return a 1-channel image, but it returns a 3-channel image with the same value in each
    channel, because of an issue that is discussed in :
    https://github.com/huggingface/transformers/pull/25786#issuecomment-1730176446

    Args:
        image (torch.Tensor):
            The image to convert.
    r   )Únum_output_channels)rH   ÚtvFÚrgb_to_grayscaler-   s    r&   Úconvert_to_grayscalerN   Z   s/   € õ �EÑÔð ØˆÝÔ ¸1Ð=Ñ=Ô=Ð=r%   c                   ó–  ‡ — e Zd ZeZej        ZdddœZdZ	dZ
dZdZdZdZdee         fˆ fd	„Zed
edee         defˆ fd„¦   «         Zd
edefd„Z	 d#d
ed         dededddedededz  deez  dz  dedefd„Z	 d$dddeee         z  dedeeeej         f                  fd„Z!deeeej         f                  ded          fd!„Z"d"„ Z#ˆ xZ$S )%ÚEfficientLoFTRImageProcessorià  i€  )ÚheightÚwidthFTgp?NÚkwargsc                 ó:   •—  t          ¦   «         j        di |¤Ž d S )Nr$   )ÚsuperÚ__init__)ÚselfrS   Ú	__class__s     €r&   rV   z%EfficientLoFTRImageProcessor.__init__y   s&   ø€ Ø�‰ŒÔÐ"Ð"˜6Ð"Ð"Ð"Ð"Ð"r%   r0   rI   c                 ó8   •—  t          ¦   «         j        |fi |¤ŽS r5   )rU   Ú
preprocess)rW   r0   rS   rX   s      €r&   rZ   z'EfficientLoFTRImageProcessor.preprocess|   s"   ø€ à!�u‰wŒwÔ! &Ð3Ð3¨FÐ3Ð3Ð3r%   c                 óJ   — |                       |¦  «        }t          |¦  «        S r5   )Úfetch_imagesrC   )rW   r0   rS   s      r&   Ú_prepare_images_structurez6EfficientLoFTRImageProcessor._prepare_images_structure€   s%   € ð ×"Ò" 6Ñ*Ô*ˆÝ.¨vÑ6Ô6Ð6r%   rD   Ú	do_resizeÚsizeÚresamplez7PILImageResampling | tvF.InterpolationMode | int | NoneÚ
do_rescaleÚrescale_factorÚdisable_groupingÚreturn_tensorsr   c
                 ó0  ‡— t          ||¬¦  «        \  }}i }|                     ¦   «         D ]$\  }}|r|                      |||¬¦  «        }|||<   Œ%t          ||¦  «        }t          ||¬¦  «        \  }}i }|                     ¦   «         D ]3\  }}|r|                      ||¦  «        }|	rt          |¦  «        }|||<   Œ4t          ||¦  «        Šˆfd„t          dt          ‰¦  «        d¦  «        D ¦   «         }d„ |D ¦   «         }t          d|i|¬¦  «        S )	N)rc   )r_   r`   c                 ó*   •— g | ]}‰||d z   …         ‘ŒS ©r3   r$   )r7   ÚiÚprocessed_imagess     €r&   r@   z<EfficientLoFTRImageProcessor._preprocess.<locals>.<listcomp>«   s'   ø€ Ð_Ð_Ð_°qÐ'¨¨A°©E¨	Ô2Ð_Ð_Ð_r%   r   r3   c                 ó:   — g | ]}t          j        |d ¬¦  «        ‘ŒS )r   )Údim)rG   Ústack)r7   Úpairs     r&   r@   z<EfficientLoFTRImageProcessor._preprocess.<locals>.<listcomp>®   s'   € ÐJÐJÐJ°d�œ T¨qÐ1Ñ1Ô1ÐJÐJÐJr%   Úpixel_values)ÚdataÚtensor_type)	r
   ÚitemsÚresizer   ÚrescalerN   Úranger+   r	   )rW   r0   r^   r_   r`   ra   rb   rc   rd   r   rS   Úgrouped_imagesÚgrouped_images_indexÚprocessed_images_groupedr,   Ústacked_imagesÚresized_imagesÚimage_pairsÚstacked_pairsri   s                      @r&   Ú_preprocessz(EfficientLoFTRImageProcessor._preprocess‰   sx  ø€ õ 0EÀVÐ^nÐ/oÑ/oÔ/oÑ,ˆÐ,Ø#%Ð à%3×%9Ò%9Ñ%;Ô%;ð 	=ð 	=Ñ!ˆE�>Øð [Ø!%§¢¨^À$ÐQY Ñ!ZÔ!Z�Ø.<Ð$ UÑ+Ð+Ý'Ð(@ÐBVÑWÔWˆå/DÀ^ÐfvÐ/wÑ/wÔ/wÑ,ˆÐ,Ø#%Ð Ø%3×%9Ò%9Ñ%;Ô%;ð 	=ð 	=Ñ!ˆE�>Øð NØ!%§¢¨n¸nÑ!MÔ!M�Øð FÝ!5°nÑ!EÔ!E�Ø.<Ð$ UÑ+Ð+å)Ð*BÐDXÑYÔYÐð `Ð_Ð_Ð_½EÀ!ÅSÐIYÑEZÔEZÐ\]Ñ<^Ô<^Ð_Ñ_Ô_ˆð KÐJ¸kÐJÑJÔJˆõ  .°-Ð!@ÈnÐ]Ñ]Ô]Ð]r%   ç        Úoutputsr   Útarget_sizesÚ	thresholdc                 ó„  — |j         j        d         t          |¦  «        k    rt          d¦  «        ‚t	          d„ |D ¦   «         ¦  «        st          d¦  «        ‚t          |t          ¦  «        r!t          j        ||j         j	        ¬¦  «        }n3|j        d         dk    s|j        d         dk    rt          d¦  «        ‚|}|j
                             ¦   «         }||                     d¦  «                             dddd¦  «        z  }|                     t          j        ¦  «        }g }t!          ||j         |j        ¦  «        D ]x\  }}}	t          j        |	|k    |dk    ¦  «        }
|d         |
d                  }|d         |
d                  }|	d         |
d                  }|                     |||d	œ¦  «         Œy|S )
aõ  
        Converts the raw output of [`EfficientLoFTRKeypointMatchingOutput`] into lists of keypoints, scores and descriptors
        with coordinates absolute to the original image sizes.
        Args:
            outputs ([`EfficientLoFTRKeypointMatchingOutput`]):
                Raw outputs of the model.
            target_sizes (`torch.Tensor` or `List[Tuple[Tuple[int, int]]]`, *optional*):
                Tensor of shape `(batch_size, 2, 2)` or list of tuples of tuples (`Tuple[int, int]`) containing the
                target size `(height, width)` of each image in the batch. This must be the original image size (before
                any processing).
            threshold (`float`, *optional*, defaults to 0.0):
                Threshold to filter out the matches with low scores.
        Returns:
            `List[Dict]`: A list of dictionaries, each dictionary containing the keypoints in the first and second image
            of the pair, the matching scores and the matching indices.
        r   zRMake sure that you pass in as many target sizes as the batch dimension of the maskc              3   ó<   K  — | ]}t          |¦  «        d k    V — ŒdS )r3   N)r+   )r7   Útarget_sizes     r&   r8   zNEfficientLoFTRImageProcessor.post_process_keypoint_matching.<locals>.<genexpr>Ì   s/   è è € ÐIÐI¨[•3�{Ñ#Ô# qÒ(ÐIÐIÐIÐIÐIÐIr%   zTEach element of target_sizes must contain the size (h, w) of each image of the batch)Údevicer   r3   éÿÿÿÿ)Ú
keypoints0Ú
keypoints1Úmatching_scores)Úmatchesr,   r+   rA   r=   r;   r<   rG   Útensorr„   Ú	keypointsÚcloneÚflipÚreshapeÚtoÚint32Úziprˆ   Úlogical_andÚappend)rW   r~   r   r€   Úimage_pair_sizesr‹   ÚresultsÚkeypoints_pairr‰   ÚscoresÚvalid_matchesÚmatched_keypoints0Úmatched_keypoints1rˆ   s                 r&   Úpost_process_keypoint_matchingz;EfficientLoFTRImageProcessor.post_process_keypoint_matching´   sÝ  € ð, Œ?Ô  Ô#¥s¨<Ñ'8Ô'8Ò8Ð8ÝÐqÑrÔrÐrÝÐIÐI¸LÐIÑIÔIÑIÔIð 	uÝÐsÑtÔtÐtå�l¥DÑ)Ô)ð 	,Ý$œ|¨LÀÄÔAWÐXÑXÔXÐÐàÔ! !Ô$¨Ò)Ð)¨\Ô-?ÀÔ-BÀaÒ-GÐ-GÝ Øjñô ð ð  ,ÐàÔ%×+Ò+Ñ-Ô-ˆ	ØÐ 0× 5Ò 5°bÑ 9Ô 9× AÒ AÀ"ÀaÈÈAÑ NÔ NÑNˆ	Ø—L’L¥¤Ñ-Ô-ˆ	àˆÝ/2°9¸g¼oÈwÔOfÑ/gÔ/gð 	ð 	Ñ+ˆN˜G Vå!Ô-¨f°yÒ.@À'ÈBÂ,ÑOÔOˆMà!/°Ô!2°=ÀÔ3CÔ!DÐØ!/°Ô!2°=ÀÔ3CÔ!DÐØ$ Qœi¨°aÔ(8Ô9ˆOà�NŠNà"4Ø"4Ø'6ðð ñô ð ð ð ˆr%   Úkeypoint_matching_outputzImage.Imagec           	      ó„  ‡— t          ‰¦  «        Šd„ ‰D ¦   «         Šˆfd„t          dt          ‰¦  «        d¦  «        D ¦   «         }g }t          ||¦  «        D �]å\  }}|d         j        dd…         \  }}|d         j        dd…         \  }	}
t          j        t          ||	¦  «        ||
z   dft
          j        ¬¦  «        }t          j	        |d         ¦  «        |d|…d|…f<   t          j	        |d         ¦  «        |d|	…|d…f<   t          j        |                     ¦   «         ¦  «        }t          j        |¦  «        }|d	                              d¦  «        \  }}|d
                              d¦  «        \  }}t          |||||d         ¦  «        D ]�\  }}}}}|                      |¦  «        }|                     ||||z   |f|d¬¦  «         |                     |dz
  |dz
  |dz   |dz   fd¬¦  «         |                     ||z   dz
  |dz
  ||z   dz   |dz   fd¬¦  «         Œ‘|                     |¦  «         �Œç|S )a¸  
        Plots the image pairs side by side with the detected keypoints as well as the matching between them.

        Args:
            images:
                Image pairs to plot. Same as `EfficientLoFTRImageProcessor.preprocess`. Expects either a list of 2
                images or a list of list of 2 images list with pixel values ranging from 0 to 255.
            keypoint_matching_output (List[Dict[str, torch.Tensor]]]):
                A post processed keypoint matching output

        Returns:
            `List[PIL.Image.Image]`: A list of PIL images, each containing the image pairs side by side with the detected
            keypoints as well as the matching between them.
        c                 ó,   — g | ]}t          |¦  «        ‘ŒS r$   )r   )r7   r.   s     r&   r@   zLEfficientLoFTRImageProcessor.visualize_keypoint_matching.<locals>.<listcomp>  s    € Ð<Ð<Ð<¨E•. Ñ'Ô'Ð<Ð<Ð<r%   c                 ó*   •— g | ]}‰||d z   …         ‘ŒS rg   r$   )r7   rh   r0   s     €r&   r@   zLEfficientLoFTRImageProcessor.visualize_keypoint_matching.<locals>.<listcomp>  s&   ø€ ÐKÐKÐK¨Q�v˜a ! a¡%˜iÔ(ÐKÐKÐKr%   r   r3   Nr   r   )Údtyper†   r‡   rˆ   )ÚfillrR   Úblack)r¡   )rC   rt   r+   r‘   r,   rG   ÚzerosÚmaxÚuint8Ú
from_numpyr   Ú	fromarrayÚnumpyr   ÚDrawÚunbindÚ
_get_colorÚlineÚellipser“   )rW   r0   rœ   rz   r•   r>   Úpair_outputÚheight0Úwidth0Úheight1Úwidth1Ú
plot_imageÚplot_image_pilÚdrawÚkeypoints0_xÚkeypoints0_yÚkeypoints1_xÚkeypoints1_yÚkeypoint0_xÚkeypoint0_yÚkeypoint1_xÚkeypoint1_yÚmatching_scoreÚcolors    `                      r&   Úvisualize_keypoint_matchingz8EfficientLoFTRImageProcessor.visualize_keypoint_matchingï   sŸ  ø€ õ( 1°Ñ8Ô8ˆØ<Ð<°VÐ<Ñ<Ô<ˆØKÐKÐKÐKµ%¸½3¸v¹;¼;ÈÑ2JÔ2JÐKÑKÔKˆàˆÝ'*¨;Ð8PÑ'QÔ'Qð 	+ñ 	+Ñ#ˆJ˜Ø(¨œmÔ1°"°1°"Ô5‰OˆG�VØ(¨œmÔ1°"°1°"Ô5‰OˆG�VÝœ¥c¨'°7Ñ&;Ô&;¸VÀf¹_ÈaÐ%PÕX]ÔXcÐdÑdÔdˆJÝ,1Ô,<¸ZÈ¼]Ñ,KÔ,KˆJ�x˜�x  & Ð(Ñ)Ý,1Ô,<¸ZÈ¼]Ñ,KÔ,KˆJ�x˜�x   Ð(Ñ)å"œ_¨Z×-=Ò-=Ñ-?Ô-?Ñ@Ô@ˆNÝ”> .Ñ1Ô1ˆDà)4°\Ô)B×)IÒ)IÈ!Ñ)LÔ)LÑ&ˆL˜,Ø)4°\Ô)B×)IÒ)IÈ!Ñ)LÔ)LÑ&ˆL˜,ÝVYØ˜l¨L¸,ÈÐTeÔHfñWô Wð ð ÑR�˜[¨+°{ÀNð Ÿš¨Ñ7Ô7�Ø—	’	Ø  +¨{¸VÑ/CÀ[ÐQØØð ñ ô ð ð
 —’˜k¨A™o¨{¸Q©ÀÈaÁÐQ\Ð_`ÑQ`ÐaÐho�ÑpÔpÐpØ—’Ø  6Ñ)¨AÑ-¨{¸Q©ÀÈfÑ@TÐWXÑ@XÐZeÐhiÑZiÐjØ ð ñ ô ð ð ð
 �NŠN˜>Ñ*Ô*Ð*Ñ*Øˆr%   c                 ó^   — t          dd|z
  z  ¦  «        }t          d|z  ¦  «        }d}|||fS )zMaps a score to a color.éÿ   r   r   )Úint)rW   ÚscoreÚrÚgÚbs        r&   r«   z'EfficientLoFTRImageProcessor._get_color&  s9   € å��q˜5‘yÑ!Ñ"Ô"ˆÝ��e‘ÑÔˆØˆØ�!�Qˆwˆr%   )T)r}   )%r   r   r    r   Úvalid_kwargsr   ÚBILINEARr`   r_   Údefault_to_squarer^   ra   rb   Údo_normalizer   r   rV   r   r   r	   rZ   r]   r<   r"   r   ÚfloatÚstrr   r|   ÚtupleÚdictrG   ÚTensorr›   rÀ   r«   Ú__classcell__)rX   s   @r&   rP   rP   m   s@  ø€ € € € € à5€LØ!Ô*€HØ CÐ(Ð(€DØÐØ€IØ€JØ€NØ€LØ€Lð# Ð(JÔ!Kð #ð #ð #ð #ð #ð #ð ð4 ð 4°vÐ>`Ô7að 4Ðfrð 4ð 4ð 4ð 4ð 4ñ „^ð4ð7àð7ð 
ð	7ð 7ð 7ð 7ð& "ð)^ð )^à�^Ô$ð)^ð ð)^ð ð	)^ð
 Lð)^ð ð)^ð ð)^ð  ™+ð)^ð ˜jÑ(¨4Ñ/ð)^ð ð)^ð 
ð)^ð )^ð )^ð )^ð^ ð	9ð 9à7ð9ð ! 4¨¤;Ñ.ð9ð ð	9ð
 
ˆd�3˜œÐ$Ô%Ô	&ð9ð 9ð 9ð 9ðv5ð #' t¨C°´Ð,=Ô'>Ô"?ð5ð 
ˆmÔ	ð	5ð 5ð 5ð 5ðnð ð ð ð ð ð r%   rP   )r.   rD   )r.   rD   rI   rD   ))Útypingr   r*   r   r   Útorchvision.transforms.v2r   rL   Úimage_processing_backendsr   Úimage_processing_utilsr	   Úimage_transformsr
   r   Úimage_utilsr   r   r   r   r   r   r   r   Úprocessing_utilsr   r   Úutilsr   r   r   rG   Úmodeling_efficientloftrr   r   r/   rC   rH   rN   rP   Ú__all__r$   r%   r&   ú<module>rÜ      s;  ðð !Ð  Ð  Ð  Ð  Ð  à  Ð  Ð  Ð  Ð  Ð  Ð  Ð  Ø 7Ð 7Ð 7Ð 7Ð 7Ð 7à ;Ð ;Ð ;Ð ;Ð ;Ð ;Ø 2Ð 2Ð 2Ð 2Ð 2Ð 2Ø EÐ EÐ EÐ EÐ EÐ EÐ EÐ Eð	ð 	ð 	ð 	ð 	ð 	ð 	ð 	ð 	ð 	ð 	ð 	ð 	ð 	ð 	ð 	ð 	ð 	ð 	ð 	ð 5Ð 4Ð 4Ð 4Ð 4Ð 4Ð 4Ð 4Ø CÐ CÐ CÐ CÐ CÐ CÐ CÐ CÐ CÐ Cð ÐÑÔð Ø€L€L€Làð NØMÐMÐMÐMÐMÐMðð ð ð ð ¨¸Uð ñ ô ð ðð ð ð$¨Jð $ð $ð $ð $ð8Øðð ð ð ð>Øð>àð>ð >ð >ð >ð& ð}ð }ð }ð }ð }Ð#5ñ }ô }ñ „ð}ð@ *Ð
*€€€r%   