§
    9²¸j=  ã                   ó*  — d Z ddlmZ ddlZddlZddl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 ddlmZmZ ddlmZmZmZ de de!e"e e e f                  fd„Z# G d„ ded¬¦  «        Z$e G d„ de
¦  «        ¦   «         Z%dgZ&dS )z!Image processor class for SegGPT.é    )ÚUnionN)Ú
functionalé   )ÚTorchvisionBackend)Ú'SemanticSegmentationPostProcessorOutput)ÚBatchFeature)Úgroup_images_by_shapeÚreorder_images)ÚIMAGENET_DEFAULT_MEANÚIMAGENET_DEFAULT_STDÚChannelDimensionÚ
ImageInputÚPILImageResamplingÚSizeDict)ÚImagesKwargsÚUnpack)Ú
TensorTypeÚauto_docstringÚrequires_backendsÚ
num_labelsÚreturnc                 óô   — t          | dz  ¦  «        dz   }d|z  }dg}t          | ¦  «        D ]J}||dz  z  }||dz  z  |z  }||z  }d||z  z
  }d||z  z
  }	d||z  z
  }
|                     ||	|
f¦  «         ŒK|S )NgUUUUUUÕ?é   é   )r   r   r   é   éÿ   )ÚintÚrangeÚappend)r   ÚbaseÚmarginÚ
color_listÚlocationÚ	num_seq_rÚ	num_seq_gÚ	num_seq_bÚRÚGÚBs              ú‚/root/private/project/pallet_detection_v2/.venv/lib/python3.11/site-packages/transformers/models/seggpt/image_processing_seggpt.pyÚbuild_paletter+   (   s¼   € Ýˆz˜eÑ$Ñ%Ô%¨Ñ)€DØ�D‰[€Fð �€JÝ˜*Ñ%Ô%ð 	%ð 	%ˆØ  a¡Ñ'ˆ	Ø  a¡Ñ'¨DÑ0ˆ	Ø˜t‘Oˆ	à�)˜fÑ$Ñ$ˆØ�)˜fÑ$Ñ$ˆØ�)˜fÑ$Ñ$ˆà×Ò˜1˜a ˜)Ñ$Ô$Ð$Ð$àÐó    c                   ó   — e Zd ZU dZeed<   dS )ÚSegGptImageProcessorKwargsaµ  
    num_labels (`int`, *optional*):
        Number of classes in the segmentation task (excluding the background). If specified, a palette will be
        built, assuming that class_idx 0 is the background, to map the prompt mask from a plain segmentation map
        to a 3-channel RGB image. Not specifying this will result in the prompt mask being duplicated across the
        channel dimension when `do_convert_rgb` is `True`.
    r   N)Ú__name__Ú
__module__Ú__qualname__Ú__doc__r   Ú__annotations__© r,   r*   r.   r.   <   s%   € € € € € € ðð ð €O€O�O€O€Or,   r.   F)Útotalc                   ój  ‡ — e Zd ZeZej        ZeZ	e
ZdddœZdZdZdZdZdZdee         fˆ fd„Zdedeeeeef                  fd	„Zd(d
ej        deeeeef                  dz  dej        fd„Ze	 	 	 d)dedz  dedz  dedz  dee         def
ˆ fd„¦   «         Z	 	 d*dededz  dedz  dede de!e"z  dz  de#e!df         dz  dedz  defd„Z$ded         dede%dddede&dede&ee&         z  dz  d e&ee&         z  dz  d!edz  ded         fd"„Z'	 	 	 d+d$eeeef                  dz  dedz  d%edd&fd'„Z(ˆ xZ)S ),ÚSegGptImageProcessoriÀ  )ÚheightÚwidthTNÚkwargsc                 ó:   •—  t          ¦   «         j        di |¤Ž d S )Nr4   )ÚsuperÚ__init__)Úselfr:   Ú	__class__s     €r*   r=   zSegGptImageProcessor.__init__V   s&   ø€ Ø�‰ŒÔÐ"Ð"˜6Ð"Ð"Ð"Ð"Ð"r,   r   r   c                 ó    — t          |¦  «        S )aB  Build a palette to map the prompt mask from a single channel to a 3-channel RGB.

        Args:
            num_labels (`int`):
                Number of classes in the segmentation task (excluding the background).

        Returns:
            `list[tuple[int, int, int]]`: Palette to map the prompt mask to RGB.
        )r+   )r>   r   s     r*   Úget_palettez SegGptImageProcessor.get_paletteY   s   € õ ˜ZÑ(Ô(Ð(r,   ÚmaskÚpalettec                 óÂ  — |j         dk    r|                     d¦  «        }|j        \  }}|��t          j        d||ft          j        ¬¦  «        }t          j        |¦  «        }|D ]š}||         }||k                         t          j        ¦  «        }	t          j        |t          j        ¬¦  «         	                    ddd¦  «        }
|t          j
        |	d¦  «        |
z                       t          j        ¦  «        z  }Œ›t          j        |dd¦  «                             t          j        ¦  «        }n)t          j        |t          j        df         dd¬¦  «        }|S )	a,  Converts a segmentation map to RGB format.

        Args:
            mask (`np.ndarray`):
                Segmentation map with shape `(height, width)` or `(1, height, width)` where pixel values
                represent the class index.
            palette (`list[tuple[int, int, int]]`, *optional*):
                Palette to use to convert the mask to RGB format. If unset, the mask is duplicated across
                the channel dimension.

        Returns:
            `np.ndarray`: The mask in RGB format with shape `(3, height, width)`.
        r   r   N)Údtyper   r   .)Úaxis)ÚndimÚsqueezeÚshapeÚnpÚzerosÚuint8ÚuniqueÚastypeÚarrayÚreshapeÚexpand_dimsÚclipÚrepeatÚnewaxis)r>   rB   rC   r8   r9   Úrgb_maskÚclasses_in_maskÚ	class_idxÚ	rgb_valueÚ
class_maskÚ	class_rgbs              r*   Úmask_to_rgbz SegGptImageProcessor.mask_to_rgbe   s.  € ð Œ9˜Š>ˆ>Ø—<’< ‘?”?ˆDàœ
‰ˆ�àÑÝ”x  F¨EÐ 2½"¼(ÐCÑCÔCˆHÝ œi¨™oœoˆOØ,ð Yð Y�	Ø# IÔ.�	Ø" iÒ/×7Ò7½¼ÑAÔA�
ÝœH Yµb´hÐ?Ñ?Ô?×GÒGÈÈ1ÈaÑPÔP�	Ø�Rœ^¨J¸Ñ:Ô:¸YÑF×NÒNÍrÌxÑXÔXÑX��Ý”w˜x¨¨CÑ0Ô0×7Ò7½¼ÑAÔAˆHˆHå”y ¥b¤j°# oÔ!6¸ÀÐBÑBÔBˆHàˆr,   ÚimagesÚprompt_imagesÚprompt_masksc                 óž   •— t          d„ |||fD ¦   «         ¦  «        rt          d¦  «        ‚|�|ng } t          ¦   «         j        |||fi |¤ŽS )aÑ  
        prompt_images (`ImageInput`, *optional*):
            Prompt images to preprocess. Expects a single or batch of images with pixel values ranging from 0 to 255.
        prompt_masks (`ImageInput`, *optional*):
            Prompt masks to preprocess. Can be in the format of segmentation maps (no channels) or RGB images.
            If in the format of RGB images, `do_convert_rgb` should be set to `False`. If in the format of
            segmentation maps, specifying `num_labels` is recommended to build a palette to map the prompt mask
            from a single channel to a 3-channel RGB. If `num_labels` is not specified, the prompt mask will be
            duplicated across the channel dimension.
        c              3   ó   K  — | ]}|d u V — Œ	d S ©Nr4   )Ú.0Úvs     r*   ú	<genexpr>z2SegGptImageProcessor.preprocess.<locals>.<genexpr>˜   s&   è è € ÐHÐH˜Qˆq�DˆyÐHÐHÐHÐHÐHÐHr,   zFAt least one of images, prompt_images, prompt_masks must be specified.)ÚallÚ
ValueErrorr<   Ú
preprocess)r>   r\   r]   r^   r:   Ú_images_inputr?   s         €r*   rg   zSegGptImageProcessor.preprocess†   so   ø€ õ$ ÐHÐH 6¨=¸,Ð"GÐHÑHÔHÑHÔHð 	gÝÐeÑfÔfÐfð #)Ð"4˜˜¸"ˆØ!�u‰wŒwÔ! -°ÀÐWÐWÐPVÐWÐWÐWr,   Údo_convert_rgbÚinput_data_formatÚreturn_tensorsÚdeviceztorch.devicec	                 óX  — i }
t          |t          ¦  «        ot          |¦  «        dk     }|r*|                      |d||¬¦  «        } | j        |fi |	¤Ž|
d<   |�*|                      |d||¬¦  «        } | j        |fi |	¤Ž|
d<   |��|rÉ|                      |ddt
          j        |¬¦  «        }|�|                      |¦  «        nd }g }|D ]„}|                     d¦  «         	                    ¦   «         }|  
                    ||¬¦  «        }|                     t          j        |                     t          j        ¦  «        ¦  «        ¦  «         Œ…|}n|                      |d	d||¬¦  «        }t#          |	¦  «        }t$          j        |d
<    | j        |fi |¤Ž|
d<   t)          |
|¬¦  «        S )Nr   F)r\   ri   rj   rl   Úpixel_valuesÚprompt_pixel_valuesr   )r\   Úexpected_ndimsri   rj   rl   )rC   r   Úresampler^   )ÚdataÚtensor_type)Ú
isinstanceÚlistÚlenÚ_prepare_image_like_inputsÚ_preprocessr   ÚFIRSTrA   rH   Únumpyr[   r   ÚtorchÚ
from_numpyrN   rJ   Úfloat32Údictr   ÚNEARESTr   )r>   r\   r]   r^   ri   rj   rk   rl   r   r:   rr   Ú_images_providedÚprepared_imagesÚprepared_prompt_imagesÚprepared_masksrC   Ú	convertedÚmask_tensorÚmask_npÚrgb_npÚmasks_kwargss                        r*   Ú_preprocess_image_like_inputsz2SegGptImageProcessor._preprocess_image_like_inputsŸ   s*  € ð ˆõ !+¨6µ4Ñ 8Ô 8Ð M½SÀ¹[¼[ÈAÒ=MÐNÐØð 	OØ"×=Ò=Ø¨eÐGXÐagð >ñ ô ˆOð $4 4Ô#3°OÐ#NÐ#NÀvÐ#NÐ#NˆD�Ñ ð Ð$Ø%)×%DÒ%DØ$°UÐN_Ðhnð &Eñ &ô &Ð"ð +;¨$Ô*:Ð;QÐ*\Ð*\ÐU[Ð*\Ð*\ˆDÐ&Ñ'ð Ñ#Øð à!%×!@Ò!@Ø'Ø#$Ø#(Ý&6Ô&<Ø!ð "Añ "ô "�ð ;EÐ:P˜$×*Ò*¨:Ñ6Ô6Ð6ÐVZ�Ø�	Ø#1ð Rð R�KØ)×1Ò1°!Ñ4Ô4×:Ò:Ñ<Ô<�GØ!×-Ò-¨g¸wÐ-ÑGÔG�FØ×$Ò$¥UÔ%5°f·m²mÅBÄJÑ6OÔ6OÑ%PÔ%PÑQÔQÐQÐQØ!*��ð "&×!@Ò!@Ø'Ø#$Ø#(Ø&7Ø!ð "Añ "ô "�õ   ™<œ<ˆLÝ'9Ô'AˆL˜Ñ$Ø#3 4Ô#3°NÐ#SÐ#SÀlÐ#SÐ#SˆD�Ñ å °>ÐBÑBÔBÐBr,   ztorch.TensorÚ	do_resizeÚsizerq   z7PILImageResampling | tvF.InterpolationMode | int | NoneÚ
do_rescaleÚrescale_factorÚdo_normalizeÚ
image_meanÚ	image_stdÚdisable_groupingc           	      ó|  — t          ||
¬¦  «        \  }}i }|                     ¦   «         D ]#\  }}|r|                      |||¦  «        }|||<   Œ$t          ||¦  «        }t          ||
¬¦  «        \  }}i }|                     ¦   «         D ]$\  }}|                      ||||||	¦  «        }|||<   Œ%t          ||¦  «        S )N)r‘   )r	   ÚitemsÚresizer
   Úrescale_and_normalize)r>   r\   rŠ   r‹   rq   rŒ   r�   rŽ   r�   r�   r‘   r:   Úgrouped_imagesÚgrouped_images_indexÚresized_images_groupedrI   Ústacked_imagesÚresized_imagesÚprocessed_images_groupeds                      r*   rx   z SegGptImageProcessor._preprocessß   s  € õ 0EÀVÐ^nÐ/oÑ/oÔ/oÑ,ˆÐ,Ø!#ÐØ%3×%9Ò%9Ñ%;Ô%;ð 	;ð 	;Ñ!ˆE�>Øð MØ!%§¢¨^¸TÀ8Ñ!LÔ!L�Ø,:Ð" 5Ñ)Ð)Ý'Ð(>Ð@TÑUÔUˆå/DÀ^ÐfvÐ/wÑ/wÔ/wÑ,ˆÐ,Ø#%Ð Ø%3×%9Ò%9Ñ%;Ô%;ð 	=ð 	=Ñ!ˆE�>Ø!×7Ò7Ø 
¨N¸LÈ*ÐV_ñô ˆNð /=Ð$ UÑ+Ð+åÐ6Ð8LÑMÔMÐMr,   FÚtarget_sizesÚreturn_segmentation_scoreszBlist[torch.Tensor] | list[SemanticSegmentationPostProcessorOutput]c                 óæ  — t          | dg¦  «         |j        }|�/t          |¦  «        t          |¦  «        k    rt          d¦  «        ‚|dd…dd…|j        d         dz  d…dd…f         }t          j        | j        ¦  «                             |j	        ¦  «        }t          j        | j
        ¦  «                             |j	        ¦  «        }|                     dddd¦  «        |z  |z   }|                     dddd¦  «        }t          j        |dz  dd¦  «        }g }d}	|�|                      |¦  «        nd}
|
�_t          j        |
¦  «                             |j	        t
          j        ¬	¦  «        }	|j        \  }}}}|	                     dd|dz   |¦  «        }	t!          |¦  «        D �]7\  }}|�Ft
          j        j                             |                     d¦  «        ||         d
¬¦  «        d         }|�—|j        \  }}}|                     ddd¦  «                             ||d|¦  «        }||	z
  }t          j        |d¦  «        }t          j        |d¬¦  «        }|                     d¬¦  «        }|                     ddd¦  «         }n*|                     d¬¦  «                             ¦   «         }d}|                     t7          ||dœ¬¦  «        ¦  «         �Œ9|sd„ |D ¦   «         }|S )aÛ  
        Converts the output of [`SegGptImageSegmentationOutput`] into segmentation maps. Only supports PyTorch.

        Args:
            outputs ([`SegGptImageSegmentationOutput`]):
                Raw outputs of the model.
            target_sizes (`list[tuple[int, int]]`, *optional*):
                List of length `batch_size`, where each item corresponds to the requested final size `(height, width)`
                of each prediction. If left to `None`, predictions will not be resized.
            num_labels (`int`, *optional*):
                Number of classes in the segmentation task (excluding the background). If specified, a palette will be
                built to map prediction masks from RGB values back to class indices. Should match the value used during
                preprocessing.
            return_segmentation_scores (`bool`, *optional*, defaults to `False`):
                Whether to return segmentation scores alongside the segmentation map. When `True`, each element of
                the returned list is a [`SemanticSegmentationPostProcessorOutput`] with fields `segmentation`
                (class IDs, shape `(height, width)`) and `segmentation_scores` (shape `(num_labels+1, height, width)`
                of negative squared L2 distances to each palette color, or `None` when `num_labels` is not provided).

        Returns:
            `list[torch.Tensor]` or `list[SemanticSegmentationPostProcessorOutput]`: When
            `return_segmentation_scores=False` (default), a list of length `batch_size` where each item is a
            segmentation map of shape `(height, width)` with class IDs. When `return_segmentation_scores=True`,
            a list of [`SemanticSegmentationPostProcessorOutput`] with fields `segmentation` (class IDs, shape
            `(height, width)`) and `segmentation_scores` (shape `(num_labels+1, height, width)`). In both cases,
            `(height, width)` corresponds to the target size (if `target_sizes` is specified).
        r{   NzTMake sure that you pass in as many target sizes as the batch dimension of the logitsr   r   r   r   r   )rl   rE   Únearest)r‹   Úmodeéÿÿÿÿ)Údim)ÚsegmentationÚsegmentation_scores)rr   c                 ó   — g | ]	}|j         ‘Œ
S r4   )r£   )rb   Úitems     r*   ú
<listcomp>zKSegGptImageProcessor.post_process_semantic_segmentation.<locals>.<listcomp>Y  s   € Ð$YÐ$YÐ$Y¸4 TÔ%6Ð$YÐ$YÐ$Yr,   )r   Ú
pred_masksrv   rf   rI   r{   Útensorr�   Útorl   r�   ÚpermuterR   rA   ÚfloatÚviewÚ	enumerateÚnnr   ÚinterpolateÚ	unsqueezeÚpowÚsumÚargminÚmeanr   r   r   )r>   Úoutputsrœ   r   r�   ÚmasksÚstdrµ   Úsemantic_segmentationÚpalette_tensorrC   Ú_Únum_channelsÚidxrB   Úchannelsr8   r9   ÚdistÚpredr¤   s                        r*   Ú"post_process_semantic_segmentationz7SegGptImageProcessor.post_process_semantic_segmentationÿ   s  € õF 	˜$  	Ñ*Ô*Ð*ð Ô"ˆàÐ#­¨E©
¬
µc¸,Ñ6GÔ6GÒ(GÐ(GÝÐsÑtÔtÐtð �a�a�a˜˜˜˜EœK¨œN¨aÑ/Ð1Ð1°1°1°1Ð4Ô5ˆõ Œl˜4œ>Ñ*Ô*×-Ò-¨e¬lÑ;Ô;ˆÝŒ|˜DœOÑ,Ô,×/Ò/°´Ñ=Ô=ˆØ—’˜a  A qÑ)Ô)¨CÑ/°$Ñ6ˆØ—’˜a  A qÑ)Ô)ˆå”
˜5 3™;¨¨3Ñ/Ô/ˆà "ÐØˆØ2<Ð2H�$×"Ò" :Ñ.Ô.Ð.ÈdˆØÐÝ"œ\¨'Ñ2Ô2×5Ò5¸U¼\ÕQVÔQ\Ð5Ñ]Ô]ˆNØ$)¤KÑ!ˆAˆ|˜Q Ø+×0Ò0°°A°zÀA±~À|ÑTÔTˆNå" 5Ñ)Ô)ð 	ñ 	‰IˆC�ØÐ'Ý”xÔ*×6Ò6Ø—N’N 1Ñ%Ô%Ø% cÔ*Ø"ð 7ñ ô ð ô	�ð Ð%Ø*.¬*Ñ'�˜& %Ø—|’| A q¨!Ñ,Ô,×1Ò1°&¸%ÀÀHÑMÔM�Ø˜nÑ,�Ý”y  qÑ)Ô)�Ý”y ¨2Ð.Ñ.Ô.�Ø—{’{ r�{Ñ*Ô*�Ø'+§|¢|°A°q¸!Ñ'<Ô'<Ð&<Ð#Ð#à—y’y Q�yÑ'Ô'×+Ò+Ñ-Ô-�Ø&*Ð#à!×(Ò(Ý7Ø*.ÐGZÐ[Ð[ðñ ô ñô ð ñ ð *ð 	ZØ$YÐ$YÐCXÐ$YÑ$YÔ$YÐ!à$Ð$r,   ra   )NNN)NN)NNF)*r/   r0   r1   r.   Úvalid_kwargsr   ÚBICUBICrq   r   r�   r   r�   r‹   rŠ   rŒ   rŽ   ri   r   r   r=   r   ru   ÚtuplerA   rJ   Úndarrayr[   r   r   r   rg   Úboolr   Ústrr   r   r‰   r   r¬   rx   rÁ   Ú__classcell__)r?   s   @r*   r7   r7   H   sj  ø€ € € € € à-€Là!Ô)€HØ&€JØ$€IØ CÐ(Ð(€DØ€IØ€JØ€LØ€NØ€Jð# Ð(BÔ!Cð #ð #ð #ð #ð #ð #ð
) cð 
)¨d°5¸¸cÀ3¸Ô3GÔ.Hð 
)ð 
)ð 
)ð 
)ðð  ¤
ð °T¸%ÀÀSÈ#ÀÔ:NÔ5OÐRVÑ5Vð ÐbdÔblð ð ð ð ðB ð %)Ø+/Ø*.ð	Xð Xà˜TÑ!ðXð " DÑ(ðXð ! 4Ñ'ð	Xð
 Ð3Ô4ðXð 
ðXð Xð Xð Xð Xñ „^ðXð@ 59Ø!%ð>Cð >Càð>Cð " DÑ(ð>Cð ! 4Ñ'ð	>Cð
 ð>Cð ,ð>Cð ˜jÑ(¨4Ñ/ð>Cð �c˜>Ð)Ô*¨TÑ1ð>Cð ˜$‘Jð>Cð 
ð>Cð >Cð >Cð >Cð@Nà�^Ô$ðNð ðNð ð	Nð
 LðNð ðNð ðNð ðNð ˜D œKÑ'¨$Ñ.ðNð ˜4 œ;Ñ&¨Ñ-ðNð  ™+ðNð 
ˆnÔ	ðNð Nð Nð NðF 6:Ø!%Ø+0ð\%ð \%ð ˜5  c œ?Ô+¨dÑ2ð\%ð ˜$‘Jð	\%ð
 %)ð\%ð 
Nð\%ð \%ð \%ð \%ð \%ð \%ð \%ð \%r,   r7   )'r2   Útypingr   rz   rJ   r{   Útorchvision.transforms.v2r   ÚtvFÚimage_processing_backendsr   Úimage_processing_outputsr   Úimage_processing_utilsr   Úimage_transformsr	   r
   Úimage_utilsr   r   r   r   r   r   Úprocessing_utilsr   r   Úutilsr   r   r   r   ru   rÄ   r+   r.   r7   Ú__all__r4   r,   r*   ú<module>rÔ      sÍ  ðð (Ð 'à Ð Ð Ð Ð Ð à Ð Ð Ð Ø €€€Ø 7Ð 7Ð 7Ð 7Ð 7Ð 7à ;Ð ;Ð ;Ð ;Ð ;Ð ;Ø OÐ OÐ OÐ OÐ OÐ OØ 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 5Ð 4Ð 4Ð 4Ð 4Ð 4Ð 4Ð 4Ø BÐ BÐ BÐ BÐ BÐ BÐ BÐ BÐ BÐ Bð
˜cð  d¨5°°c¸3°Ô+?Ô&@ð ð ð ð ð(	ð 	ð 	ð 	ð 	 °Uð 	ñ 	ô 	ð 	ð ðR%ð R%ð R%ð R%ð R%Ð-ñ R%ô R%ñ „ðR%ðj "Ð
"€€€r,   