§
    l¬¸j×4  ã                  ó    — d dl mZ d dlmZ d dlmZ d dlZd dlZd dl	m
c mZ d dlmZ d dlmZmZ d dlmZ d dlmZmZ  G d	„ d
e¦  «        ZdS )é    )Úannotations)ÚPath)ÚAnyN)ÚDetectionValidator)ÚLOGGERÚops)Úcheck_requirements)ÚSegmentMetricsÚmask_iouc                  ó®   ‡ — e Zd ZdZd*d+ˆ fd„Zd,ˆ fd
„Zd-ˆ fd„Zd.d„Zd/ˆ fd„Zd0ˆ fd„Z	d1ˆ fd„Z
d2ˆ fd„Zd3ˆ fd„Zd4d$„Zd5ˆ fd&„Zd6ˆ fd'„Zd7ˆ fd)„Zˆ xZS )8ÚSegmentationValidatoraY  A class extending the DetectionValidator class for validation based on a segmentation model.

    This validator handles the evaluation of segmentation models, processing both bounding box and mask predictions to
    compute metrics such as mAP for both detection and segmentation tasks.

    Attributes:
        process (callable): Function to process masks based on save_json and save_txt flags.
        args (SimpleNamespace): Arguments for the validator.
        metrics (SegmentMetrics): Metrics calculator for segmentation tasks.
        stats (dict): Dictionary to store statistics during validation.

    Examples:
        >>> from ultralytics.models.yolo.segment import SegmentationValidator
        >>> args = dict(model="yolo26n-seg.pt", data="coco8-seg.yaml")
        >>> validator = SegmentationValidator(args=args)
        >>> validator()
    NÚ
_callbacksúdict | NoneÚreturnÚNonec                óœ   •— t          ¦   «                              ||||¦  «         d| _        d| j        _        t          ¦   «         | _        dS )a�  Initialize SegmentationValidator and set task to 'segment', metrics to SegmentMetrics.

        Args:
            dataloader (torch.utils.data.DataLoader, optional): DataLoader to use for validation.
            save_dir (Path, optional): Directory to save results.
            args (dict, optional): Arguments for the validator.
            _callbacks (dict, optional): Dictionary of callback functions.
        NÚsegment)ÚsuperÚ__init__ÚprocessÚargsÚtaskr
   Úmetrics)ÚselfÚ
dataloaderÚsave_dirr   r   Ú	__class__s        €ús/root/private/project/pallet_detection_v2/.venv/lib/python3.11/site-packages/ultralytics/models/yolo/segment/val.pyr   zSegmentationValidator.__init__%   sD   ø€ õ 	‰Œ×Ò˜ X¨t°ZÑ@Ô@Ð@ØˆŒØ"ˆŒ	ŒÝ%Ñ'Ô'ˆŒˆˆó    Úbatchúdict[str, Any]c                ó„   •— t          ¦   «                              |¦  «        }|d                              ¦   «         |d<   |S )zåPreprocess batch of images for YOLO segmentation validation.

        Args:
            batch (dict[str, Any]): Batch containing images and annotations.

        Returns:
            (dict[str, Any]): Preprocessed batch.
        Úmasks)r   Ú
preprocessÚfloat)r   r    r   s     €r   r$   z SegmentationValidator.preprocess3   s:   ø€ õ ‘”×"Ò" 5Ñ)Ô)ˆØ˜wœ×-Ò-Ñ/Ô/ˆˆg‰Øˆr   Úmodelútorch.nn.Modulec                óê   •— t          ¦   «                              |¦  «         | j        j        rt	          d¦  «         | j        j        s| j        j        rt          j        nt          j        | _	        dS )zŸInitialize metrics and select mask processing function based on save_json flag.

        Args:
            model (torch.nn.Module): Model to validate.
        zfaster-coco-eval>=1.6.7N)
r   Úinit_metricsr   Ú	save_jsonr	   Úsave_txtr   Úprocess_mask_nativeÚprocess_maskr   )r   r&   r   s     €r   r)   z"SegmentationValidator.init_metrics@   sd   ø€ õ 	‰Œ×Ò˜UÑ#Ô#Ð#ØŒ9Ôð 	:ÝÐ8Ñ9Ô9Ð9à26´)Ô2EÐqÈÌÔI[Ðq•sÔ.Ð.ÕadÔaqˆŒˆˆr   Ústrc                ó   — ddz  S )z5Return a formatted description of evaluation metrics.z,%22s%11s%11s%11s%11s%11s%11s%11s%11s%11s%11s)ÚClassÚImagesÚ	InstanceszBox(PÚRÚmAP50ú	mAP50-95)zMask(Pr3   r4   r5   © )r   s    r   Úget_desczSegmentationValidator.get_descL   s   € à$ð )
ñ 
ð 	
r   Úpredsúlist[torch.Tensor]úlist[dict[str, torch.Tensor]]c                óŽ  •— t          |d         t          ¦  «        r|d         d         n|d         }t          ¦   «                              |d         ¦  «        }d„ |j        dd…         D ¦   «         }t          |¦  «        D ]B\  }}|                     d¦  «        }|                      ||         ||d         |¬¦  «        |d	<   ŒC|S )
a  Post-process YOLO predictions and return output detections with proto.

        Args:
            preds (list[torch.Tensor]): Raw predictions from the model.

        Returns:
            (list[dict[str, torch.Tensor]]): Processed detection predictions with masks.
        r   é   c                ó   — g | ]}d |z  ‘ŒS ©é   r6   )Ú.0Úxs     r   ú
<listcomp>z5SegmentationValidator.postprocess.<locals>.<listcomp>g   s   € Ð0Ð0Ð0˜1��Q‘Ð0Ð0Ð0r   é   NÚextraÚbboxes)Úshaper#   )Ú
isinstanceÚtupler   ÚpostprocessrF   Ú	enumerateÚpopr   )r   r8   ÚprotoÚimgszÚiÚpredÚcoefficientr   s          €r   rI   z!SegmentationValidator.postprocess\   sÀ   ø€ õ  *¨%°¬(µEÑ:Ô:ÐH��a”˜”�ÀÀaÄˆÝ‘”×#Ò# E¨!¤HÑ-Ô-ˆØ0Ð0 ¤¨A¨B¨B¤Ð0Ñ0Ô0ˆÝ  Ñ'Ô'ð 	]ð 	]‰GˆAˆtØŸ(š( 7Ñ+Ô+ˆKØ ŸLšL¨¨q¬°;ÀÀXÄÐV[˜LÑ\Ô\ˆD�‰MˆMØˆr   ÚsiÚintc                ó@  •‡ — t          ¦   «                              ||¦  «        }|d         j        d         }‰ j        j        r[|d         |         }t          j        d|dz   |j        ¬¦  «                             |dd¦  «        }||k     	                    ¦   «         }n|d         |d         |k             }|r`ˆ fd„|d         D ¦   «         }|j        dd	…         |k    r9t          j        |d	         |d
d¬¦  «        d         }|                     d¦  «        }||d<   |S )a:  Prepare a batch for validation by processing images and targets.

        Args:
            si (int): Sample index within the batch.
            batch (dict[str, Any]): Batch data containing images and annotations.

        Returns:
            (dict[str, Any]): Prepared batch with processed annotations.
        Úclsr   r#   r<   )ÚdeviceÚ	batch_idxc                óD   •— g | ]}‰j         t          j        u r|n|d z  ‘ŒS r>   )r   r   r,   )r@   Úsr   s     €r   rB   z8SegmentationValidator._prepare_batch.<locals>.<listcomp>€   s2   ø€ ÐsÐsÐsÐVW˜dœl­cÔ.EÐEÐE˜˜È1ÐPQÉ6ÐsÐsÐsr   rM   NÚbilinearF)ÚmodeÚalign_cornersg      à?)r   Ú_prepare_batchrF   r   Úoverlap_maskÚtorchÚarangerU   Úviewr%   ÚFÚinterpolateÚgt_)	r   rQ   r    Úprepared_batchÚnlr#   ÚindexÚ	mask_sizer   s	   `       €r   r\   z$SegmentationValidator._prepare_batchm   s(  øø€ õ ™œ×/Ò/°°EÑ:Ô:ˆØ˜EÔ"Ô(¨Ô+ˆØŒ9Ô!ð 	=Ø˜'”N 2Ô&ˆEÝ”L  B¨¡F°5´<Ð@Ñ@Ô@×EÒEÀbÈ!ÈQÑOÔOˆEØ˜e’^×*Ò*Ñ,Ô,ˆEˆEà˜'”N 5¨Ô#5¸Ò#;Ô<ˆEØð 	'ØsÐsÐsÐsÐ[iÐjqÔ[rÐsÑsÔsˆIØŒ{˜1˜2˜2Œ )Ò+Ð+Ýœ e¨D¤k°9À:Ð]bÐcÑcÔcÐdeÔf�ØŸ	š	 #™œ�Ø"'ˆ�wÑØÐr   c                ó†   •— t          ¦   «                              ¦   «          |                      | j        j        ¦  «         dS )zGather stats from all GPUs.N)r   Úgather_statsÚ_gather_image_metricsr   Úseg)r   r   s    €r   ri   z"SegmentationValidator.gather_stats‡   s8   ø€ å‰Œ×ÒÑÔÐØ×"Ò" 4¤<Ô#3Ñ4Ô4Ð4Ð4Ð4r   údict[str, torch.Tensor]údict[str, np.ndarray]c                ól  •— t          ¦   «                              ||¦  «        }|d         }|j        d         dk    s|d         j        d         dk    r4t          j        |d         j        d         | j        ft          ¬¦  «        }n•t          |d                              d¦  «        |d                              d¦  «         	                    ¦   «         ¦  «        }|  
                    |d         ||¦  «                             ¦   «                              ¦   «         }|                     d|i¦  «         |S )aÎ  Compute correct prediction matrix for a batch based on bounding boxes and optional masks.

        Args:
            preds (dict[str, torch.Tensor]): Dictionary containing predictions with keys like 'cls' and 'masks'.
            batch (dict[str, Any]): Dictionary containing batch data with keys like 'cls' and 'masks'.

        Returns:
            (dict[str, np.ndarray]): A dictionary containing correct prediction matrices including 'tp_m' for mask IoU.

        Examples:
            >>> preds = {"cls": torch.tensor([1, 0]), "masks": torch.rand(2, 640, 640), "bboxes": torch.rand(2, 4)}
            >>> batch = {"cls": torch.tensor([1, 0]), "masks": torch.rand(2, 640, 640), "bboxes": torch.rand(2, 4)}
            >>> correct_preds = validator._process_batch(preds, batch)

        Notes:
            - This method computes IoU between predicted and ground truth masks.
            - Overlapping masks are handled based on the overlap_mask argument setting.
        rT   r   ©Údtyper#   r<   Útp_m)r   Ú_process_batchrF   ÚnpÚzerosÚniouÚboolr   Úflattenr%   Úmatch_predictionsÚcpuÚnumpyÚupdate)r   r8   r    ÚtpÚgt_clsrq   Úiour   s          €r   rr   z$SegmentationValidator._process_batchŒ   s  ø€ õ& ‰WŒW×#Ò# E¨5Ñ1Ô1ˆØ�u”ˆØŒ<˜Œ?˜aÒÐ 5¨¤<Ô#5°aÔ#8¸AÒ#=Ð#=Ý”8˜U 5œ\Ô/°Ô2°D´IÐ>ÅdÐKÑKÔKˆDˆDå˜5 œ>×1Ò1°!Ñ4Ô4°e¸G´n×6LÒ6LÈQÑ6OÔ6O×6UÒ6UÑ6WÔ6WÑXÔXˆCØ×)Ò)¨%°¬,¸ÀÑDÔD×HÒHÑJÔJ×PÒPÑRÔRˆDØ
�	Š	�6˜4�.Ñ!Ô!Ð!Øˆ	r   Únic                óˆ  •— |D ]Ž}|d         }|j         d         | j        j        k    r"t          j        d| j        j        › d�¦  «         t          j        |d| j        j        …         t
          j        ¬¦  «                             ¦   «         |d<   Œ�t          ¦   «          
                    |||| j        j        ¬¦  «         dS )a  Plot batch predictions with masks and bounding boxes.

        Args:
            batch (dict[str, Any]): Batch containing images and annotations.
            preds (list[dict[str, torch.Tensor]]): List of predictions from the model.
            ni (int): Batch index.
        r#   r   z&Limiting validation plots to 'max_det=z' items.Nro   )Úmax_det)rF   r   r�   r   Úwarningr^   Ú	as_tensorÚuint8ry   r   Úplot_predictions)r   r    r8   r   Úpr#   r   s         €r   r…   z&SegmentationValidator.plot_predictions©   sº   ø€ ð ð 	^ð 	^ˆAØ�g”JˆEØŒ{˜1Œ~ ¤	Ô 1Ò1Ð1Ý”ÐcÈÌ	ÔHYÐcÐcÐcÑdÔdÐdÝœ¨Ð/B°´Ô1BÐ/BÔ)CÍ5Ì;ÐWÑWÔW×[Ò[Ñ]Ô]ˆAˆg‰JˆJÝ‰Œ× Ò  ¨¨r¸4¼9Ô;LÐ ÑMÔMÐMÐMÐMr   ÚprednÚ	save_confrv   rF   útuple[int, int]Úfiler   c                ó¤  — ddl m}  |t          j        |d         |d         ft          j        ¬¦  «        d| j        t          j        |d         |d                              d¦  «        |d	                              d¦  «        gd¬
¦  «        t          j	        |d         t          j        ¬¦  «        ¬¦  «         
                    ||¬¦  «         dS )a¡  Save YOLO detections to a txt file in normalized coordinates in a specific format.

        Args:
            predn (dict[str, torch.Tensor]): Prediction dictionary containing 'bboxes', 'conf', 'cls', and 'masks' keys.
            save_conf (bool): Whether to save confidence scores.
            shape (tuple[int, int]): Shape of the original image.
            file (Path): File path to save the detections.
        r   )ÚResultsr<   ro   NrE   ÚconféÿÿÿÿrT   )Údimr#   )ÚpathÚnamesÚboxesr#   )rˆ   )Úultralytics.engine.resultsrŒ   rs   rt   r„   r‘   r^   ÚcatÚ	unsqueezerƒ   r+   )r   r‡   rˆ   rF   rŠ   rŒ   s         r   Úsave_one_txtz"SegmentationValidator.save_one_txt¸   sË   € ð 	7Ð6Ð6Ð6Ð6Ð6àˆÝŒH�e˜A”h  a¤Ð)µ´Ð:Ñ:Ô:ØØ”*Ý”)˜U 8œ_¨e°F¬m×.EÒ.EÀbÑ.IÔ.IÈ5ÐQVÌ<×KaÒKaÐbdÑKeÔKeÐfÐlmÐnÑnÔnÝ”/ %¨¤.½¼ÐDÑDÔDð	
ñ 	
ô 	
÷ Š(�4 9ˆ(Ñ
-Ô
-Ð
-Ð
-Ð
-r   Úpbatchc                ó  •— dd„}dd„}|d	                               d
d¦  «                             ¦   «                              t          |d	         ¦  «        d¦  «        }|d	         j        dd…         \  }} ||¦  «        }g }	|D ]%}
|	                     ||g ||
¦  «        dœ¦  «         Œ&t          ¦   «                              ||¦  «         t          |	¦  «        D ]&\  }}|| j	        t          |	¦  «         |z            d<   Œ'dS )a'  Save one JSON result for COCO evaluation.

        Args:
            predn (dict[str, torch.Tensor]): Predictions containing bboxes, masks, confidence scores, and classes.
            pbatch (dict[str, Any]): Batch dictionary containing 'imgsz', 'ori_shape', 'ratio_pad', and 'im_file'.
        Úcountsú	list[int]r   r.   c                óv  — g }t          t          | ¦  «        ¦  «        D ]†}t          | |         ¦  «        }|dk    r|t          | |dz
           ¦  «        z  }	 |dz  }|dz  }|dz  r|dk    n|dk    }|r|dz  }|d	z  }|                     t	          |¦  «        ¦  «         |snŒMŒ‡d
                     |¦  «        S )zæConverts the RLE object into a compact string representation. Each count is delta-encoded and
            variable-length encoded as a string.

            Args:
                counts (list[int]): List of RLE counts.
            rC   Té   é   é   rŽ   r   é    é0   Ú )ÚrangeÚlenrR   ÚappendÚchrÚjoin)r™   ÚresultrN   rA   ÚcÚmores         r   Ú	to_stringz5SegmentationValidator.pred_to_json.<locals>.to_stringÓ   sä   € ð ˆFå�3˜v™;œ;Ñ'Ô'ð ð �Ý˜˜qœ	‘N”N�ð �q’5�5Ø�˜V A¨¡Eœ]Ñ+Ô+Ñ+�AðØ˜D™�AØ˜!‘G�Að *+¨T©Ð@˜A šG˜G¸¸aº�DØð "Ø˜T™	˜Ø˜‘G�AØ—M’M¥# a¡&¤&Ñ)Ô)Ð)Øð Øðð à—7’7˜6‘?”?Ð"r   Úpixelsútorch.Tensorc                óæ  — | j         \  }}| dd…dd…f         | dd…dd…f         k    }t          j        |¦  «        \  }}t          |¦  «        }|                     |¦  «                             |¦  «                             d¦  «         ~t          j        || dd…df                              |j        ¦  «        f¦  «         	                    ¦   «          
                    ¦   «         }t          j        ||f¦  «        \  }}	t          j        |t          j        |dz   ¦  «        |z  ¦  «        }
g }t          |¦  «        D ]²}||
|         |
|dz            …         ||z  z
  }|j        rat          j        |¦  «                             ¦   «         }|                     d|d         ¦  «         |                     ||d         z
  ¦  «         n|g}|	|         dk    rdg|¢}|                     |¦  «         Œ³|S )aI  Convert multiple binary masks using Run-Length Encoding (RLE).

            Args:
                pixels (torch.Tensor): A 2D tensor where each row represents a flattened binary mask with shape [N,
                    H*W].

            Returns:
                (list[list[int]]): A list of RLE counts for each mask.
            Nr<   rŽ   r   )rF   r^   Úwherer£   Úmul_Úadd_r”   Útorp   ry   rz   rs   ÚsplitÚsearchsortedr_   r¢   ÚsizeÚdiffÚtolistÚinsertr¤   )r«   Ú	num_masksÚwidthÚtransitionsÚrow_idxÚcol_idxÚnÚpackedÚ	positionsÚstartsÚ
boundariesr™   rN   Úmask_positionsÚcounts                  r   Úmulti_encodez8SegmentationValidator.pred_to_json.<locals>.multi_encodeô   së  € ð  &œ|ÑˆI�uØ     A B B œ-¨6°!°!°!°S°b°S°&¬>Ò9ˆKÝ$œ{¨;Ñ7Ô7ÑˆG�WÝ�G‘”ˆAà�LŠL˜ÑÔ×$Ò$ WÑ-Ô-×2Ò2°1Ñ5Ô5Ð5ØÝ”Y ¨°°°°1°¬¯ª¸¼Ñ)GÔ)GÐHÑIÔI×MÒMÑOÔO×UÒUÑWÔWˆFÝ "¤¨°!°Ñ 6Ô 6ÑˆI�vÝœ¨µB´I¸iÈ!¹mÑ4LÔ4LÈuÑ4TÑUÔUˆJð ˆFÝ˜9Ñ%Ô%ð %ð %�Ø!*¨:°a¬=¸:ÀaÈ!ÁeÔ;LÐ+LÔ!MÐPQÐTYÑPYÑ!Y�Ø!Ô&ð $ÝœG NÑ3Ô3×:Ò:Ñ<Ô<�EØ—L’L  N°1Ô$5Ñ6Ô6Ð6Ø—L’L ¨¸Ô);Ñ!;Ñ<Ô<Ð<Ð<à"˜G�Eð ˜!”9 ’>�>Ø˜K ˜K�EØ—’˜eÑ$Ô$Ð$Ð$àˆMr   r#   rC   r<   rŽ   é   )r´   r™   ÚsegmentationN)r™   rš   r   r.   )r«   r¬   r   rš   )
Ú	transposeÚ
contiguousr`   r£   rF   r¤   r   Úpred_to_jsonrJ   Újdict)r   r‡   r—   rª   rÄ   Ú
pred_masksÚhÚwr™   Úrlesr¨   rN   Úrr   s                €r   rÉ   z"SegmentationValidator.pred_to_jsonË   s6  ø€ ð	#ð 	#ð 	#ð 	#ðB%	ð %	ð %	ð %	ðN ˜7”^×-Ò-¨a°Ñ3Ô3×>Ò>Ñ@Ô@×EÒEÅcÈ%ÐPWÌ.ÑFYÔFYÐ[]Ñ^Ô^ˆ
Ø�WŒ~Ô# A a CÔ(‰ˆˆ1Ø�˜jÑ)Ô)ˆØˆØð 	Bð 	BˆAØ�KŠK ! Q °9°9¸Q±<´<Ð@Ð@ÑAÔAÐAÐAÝ‰Œ×Ò˜U FÑ+Ô+Ð+Ý˜d‘O”Oð 	;ð 	;‰DˆAˆqØ9:ˆDŒJ�˜D™	œ	�z A‘~Ô& ~Ñ6Ð6ð	;ð 	;r   c                óÞ   •— i t          ¦   «                              ||¦  «        ¥dt          j        |d         d         |d         |d         ¬¦  «        d                              ¦   «         i¥S )z.Scales predictions to the original image size.r#   NÚ	ori_shapeÚ	ratio_pad)rÒ   r   )r   Úscale_predsr   Úscale_masksÚbyte)r   r‡   r—   r   s      €r   rÓ   z!SegmentationValidator.scale_preds%  so   ø€ ð
Ý‰gŒg×!Ò! %¨Ñ0Ô0ð
à•S”_ U¨7¤^°DÔ%9¸6À+Ô;NÐZ`ÐalÔZmÐnÑnÔnØôçŠd‰fŒfð	
ð 
ð 	
r   Ústatsc                óÀ   •— | j         dz  }| j        d         dz  | j        rdnd| j        j        › d�z  }t          ¦   «                              |||ddgd	d
g¬¦  «        S )z;Return COCO-style instance segmentation evaluation metrics.zpredictions.jsonr�   r   zinstances_val2017.jsonÚlvis_v1_z.jsonÚbboxÚsegmÚBoxÚMask)Úsuffix)r   ÚdataÚis_cocor   r²   r   Úcoco_evaluate)r   rÖ   Ú	pred_jsonÚ	anno_jsonr   s       €r   Ú	eval_jsonzSegmentationValidator.eval_json.  s~   ø€ à”MÐ$6Ñ6ˆ	àŒI�fÔØñà+/¬<Ð^Ð'Ð'Ð=^ÈÌ	ÌÐ=^Ð=^Ð=^ñ`ð 	õ
 ‰wŒw×$Ò$ U¨I°yÀ6È6ÐBRÐ\aÐciÐ[jÐ$ÑkÔkÐkr   )NNNN)r   r   r   r   )r    r!   r   r!   )r&   r'   r   r   )r   r.   )r8   r9   r   r:   )rQ   rR   r    r!   r   r!   )r   r   )r8   rl   r    r!   r   rm   )r    r!   r8   r:   r   rR   r   r   )
r‡   rl   rˆ   rv   rF   r‰   rŠ   r   r   r   )r‡   rl   r—   r!   r   r   )r‡   rl   r—   r!   r   rl   )rÖ   r!   r   r!   )Ú__name__Ú
__module__Ú__qualname__Ú__doc__r   r$   r)   r7   rI   r\   ri   rr   r…   r–   rÉ   rÓ   rã   Ú__classcell__)r   s   @r   r   r      s½  ø€ € € € € ðð ð$(ð (ð (ð (ð (ð (ð (ðð ð ð ð ð ð
rð 
rð 
rð 
rð 
rð 
rð
ð 
ð 
ð 
ð ð ð ð ð ð ð"ð ð ð ð ð ð45ð 5ð 5ð 5ð 5ð 5ð
ð ð ð ð ð ð:Nð Nð Nð Nð Nð Nð.ð .ð .ð .ð&X;ð X;ð X;ð X;ð X;ð X;ðt
ð 
ð 
ð 
ð 
ð 
ðlð lð lð lð lð lð lð lð lð lr   r   )Ú
__future__r   Úpathlibr   Útypingr   rz   rs   r^   Útorch.nn.functionalÚnnÚ
functionalra   Úultralytics.models.yolo.detectr   Úultralytics.utilsr   r   Úultralytics.utils.checksr	   Úultralytics.utils.metricsr
   r   r   r6   r   r   ú<module>ró      s
  ðð #Ð "Ð "Ð "Ð "Ð "à Ð Ð Ð Ð Ð Ø Ð Ð Ð Ð Ð à Ð Ð Ð Ø €€€Ø Ð Ð Ð Ð Ð Ð Ð Ð à =Ð =Ð =Ð =Ð =Ð =Ø )Ð )Ð )Ð )Ð )Ð )Ð )Ð )Ø 7Ð 7Ð 7Ð 7Ð 7Ð 7Ø >Ð >Ð >Ð >Ð >Ð >Ð >Ð >ðdlð dlð dlð dlð dlÐ.ñ dlô dlð dlð dlð dlr   