ó
    qyüi¿#  ã                   óö   • S r SSKJr  SSKrSSKJr  SSKJr  SSK	J
r
  SSKJrJr  SS	KJrJrJrJrJrJr  SS
KJrJr  SSKJrJrJrJr  \R:                  " \5      r " S S\SS9r \ " S S\5      5       r!S/r"g)z$Image processor class for MobileViT.é    )ÚUnionN)Ú
functionalé   )ÚTorchvisionBackend)ÚBatchFeature)Úgroup_images_by_shapeÚreorder_images)ÚIMAGENET_STANDARD_MEANÚIMAGENET_STANDARD_STDÚChannelDimensionÚ
ImageInputÚPILImageResamplingÚSizeDict)ÚImagesKwargsÚUnpack)Ú
TensorTypeÚauto_docstringÚloggingÚrequires_backendsc                   ó.   • \ rS rSr% Sr\\S'   \\S'   Srg)ÚMobileVitImageProcessorKwargsé,   aó  
do_flip_channel_order (`bool`, *optional*, defaults to `self.do_flip_channel_order`):
    Whether to flip the color channels from RGB to BGR or vice versa.
do_reduce_labels (`bool`, *optional*, defaults to `self.do_reduce_labels`):
    Whether or not to reduce all label values of segmentation maps by 1. Usually used for datasets where 0
    is used for background, and background itself is not included in all classes of a dataset (e.g.
    ADE20k). The background label will be replaced by 255.
Údo_flip_channel_orderÚdo_reduce_labels© N)Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__Ú__doc__ÚboolÚ__annotations__Ú__static_attributes__r   ó    Úu/home/mande/repo/quber/.venv/lib/python3.13/site-packages/transformers/models/mobilevit/image_processing_mobilevit.pyr   r   ,   s   ‡ ñð  ÓØÖr$   r   F)Útotalc                   ó´  ^ • \ rS rSrSr\r\R                  r	\
r\rSS0rSrSSS.rSrSrSrS	rS	rSrSrS
\\   4U 4S jjr\ S)S\S\S	-  S
\\   S\4U 4S jjj5       r S)S\S\S	-  S\S\S\ \!-  S	-  S\"\ S4   S	-  S\4S jjr#S\$S   S\$S   4S jr%S*S jr&  S+S\$S   S\S\'SSS\S\'S \S!\(S"\S	-  S#\S$\S\$S   4S% jjr)S)S&\$\*   S	-  4S' jjr+S(r,U =r-$ ),ÚMobileViTImageProcessoré:   zSTorchvision backend for MobileViT with flip_channel_order and reduce_label support.Úshortest_edgeéà   Fé   )ÚheightÚwidthTNÚkwargsc                 ó&   >• [         TU ]  " S0 UD6  g )Nr   )ÚsuperÚ__init__)Úselfr/   Ú	__class__s     €r%   r2   Ú MobileViTImageProcessor.__init__N   s   ø€ Ü‰ÒÑ"˜6Ó"r$   ÚimagesÚsegmentation_mapsÚreturnc                 ó&   >• [         TU ]  " X40 UD6$ )zX
segmentation_maps (`ImageInput`, *optional*):
    The segmentation maps to preprocess.
)r1   Ú
preprocess)r3   r6   r7   r/   r4   s       €r%   r:   Ú"MobileViTImageProcessor.preprocessQ   s   ø€ ô ‰wÒ! &ÑF¸vÑFÐFr$   Údo_convert_rgbÚinput_data_formatÚreturn_tensorsÚdeviceztorch.devicec                 óð  • U R                  XXFS9nUR                  5       nSUS'   0 n	U R                  " U40 UD6U	S'   Ub©  U R                  USS[        R                  S9n
UR                  5       nUR                  SS[        R                  S.5        U R                  " SSU
0UD6n
U
 Vs/ s H1  nUR                  S	5      R                  [        R                  5      PM3     n
nX©S
'   [        X•S9$ s  snf )z"Handle extra inputs beyond images.)r6   r<   r=   r?   Fr   Úpixel_valuesé   )r6   Úexpected_ndimsr<   r=   )Ú
do_rescaler   Úresampler6   r   Úlabels)ÚdataÚtensor_typer   )Ú_prepare_image_like_inputsÚcopyÚ_preprocessr   ÚFIRSTÚupdater   ÚNEARESTÚsqueezeÚtoÚtorchÚint64r   )r3   r6   r7   r<   r=   r>   r?   r/   Úimages_kwargsrG   Úprocessed_segmentation_mapsÚsegmentation_maps_kwargsÚprocessed_segmentation_maps                r%   Ú_preprocess_image_like_inputsÚ5MobileViTImageProcessor._preprocess_image_like_inputs^   s/  € ð ×0Ñ0ØÐL]ð 1ð 
ˆð Ÿ™›ˆØ,1ˆÐ(Ñ)ØˆØ#×/Ò/°ÑH¸-ÑHˆˆ^ÑàÑ(Ø*.×*IÑ*IØ(Ø Ø$Ü"2×"8Ñ"8ð	 +Jð +Ð'ð (.§{¡{£}Ð$Ø$×+Ñ+à"'Ø-2ä 2× :Ñ :ñ	ôð +/×*:Ò*:ñ +Ø2ð+Ø6Nñ+Ð'ñ 3Nó+â2MÐ.ð +×2Ñ2°1Ó5×8Ñ8¼¿¹ÖEÙ2Mð (ð +ð 9�‰Nä ÑBÐBùò+s   Â,8C3rF   útorch.Tensorc           
      ób  • [        [        U5      5       H–  nX   n[        R                  " US:H  [        R                  " SUR
                  UR                  S9U5      nUS-
  n[        R                  " US:H  [        R                  " SUR
                  UR                  S9U5      nX1U'   M˜     U$ )z/Reduce label values by 1, replacing 0 with 255.r   éÿ   )Údtyper?   é   éþ   )ÚrangeÚlenrQ   ÚwhereÚtensorr\   r?   )r3   rF   ÚidxÚlabels       r%   Úreduce_labelÚ$MobileViTImageProcessor.reduce_label�   s‘   € äœ˜V›Ö%ˆCØ‘KˆEÜ—K’K ¨¡
¬E¯LªL¸ÀEÇKÁKÐX]×XdÑXdÑ,eÐglÓmˆEØ˜A‘IˆEÜ—K’K ¨¡¬e¯lªl¸3ÀeÇkÁkÐZ_×ZfÑZfÑ.gÐinÓoˆEØ�3‹Kñ &ð ˆr$   c                 óÊ   • UR                   S:X  a  UR                  5       nU/ SQ   USS& U$ UR                   S:X  a&  UR                  5       nUSS2/ SQ4   USS2SS24'   U$ U$ )zFlip RGB to BGR or vice versa.r   )rB   r]   r   r   é   N)ÚndimÚclone)r3   r6   Úflippeds      r%   Úflip_channel_orderÚ*MobileViTImageProcessor.flip_channel_order™   si   € à�;‰;˜!Óà—l‘l“nˆGØ!¢)Ñ,ˆG�A�aˆLØˆNØ�[‰[˜AÓà—l‘l“nˆGØ$¢Qª	 \Ñ2ˆG’A�q˜�s�F‰OØˆNØˆr$   Ú	do_resizeÚsizerE   z7PILImageResampling | tvF.InterpolationMode | int | NoneÚdo_center_cropÚ	crop_sizerD   Úrescale_factorÚdisable_groupingr   r   c                 óÜ  • U
(       a  U R                  U5      n[        XS9u  pÞ0 nUR                  5        H$  u  nnU(       a  U R                  UX45      nUUU'   M&     [	        Xþ5      n[        UU	S9u  pÞ0 nUR                  5        HU  u  nnU(       a  U R                  UU5      nU(       a  U R                  UU5      nU(       a  U R                  U5      nUUU'   MW     [	        UU5      nU$ )z#Custom preprocessing for MobileViT.)rs   )re   r   ÚitemsÚresizer	   Úcenter_cropÚrescalerl   )r3   r6   rn   ro   rE   rp   rq   rD   rr   rs   r   r   r/   Úgrouped_imagesÚgrouped_images_indexÚresized_images_groupedÚshapeÚstacked_imagesÚresized_imagesÚprocessed_images_groupedÚprocessed_imagess                        r%   rK   Ú#MobileViTImageProcessor._preprocess§   sø   € ö  Ø×&Ñ& vÓ.ˆFä/DÀVÑ/oÑ,ˆØ!#ÐØ%3×%9Ñ%9Ö%;Ñ!ˆE�>ÞØ!%§¡¨^¸TÓ!L�Ø,:Ð" 5Ó)ñ &<ô (Ð(>ÓUˆä/DÀ^ÐfvÑ/wÑ,ˆØ#%Ð Ø%3×%9Ñ%9Ö%;Ñ!ˆE�>ÞØ!%×!1Ñ!1°.À)Ó!L�ÞØ!%§¡¨n¸nÓ!M�Þ$Ø!%×!8Ñ!8¸Ó!H�Ø.<Ð$ UÓ+ñ &<ô *Ð*BÐDXÓYÐØÐr$   Útarget_sizesc                 óV  • [        U S5        UR                  nUbÏ  [        U5      [        U5      :w  a  [        S5      e[	        U[
        R                  5      (       a  UR                  5       n/ n[        [        U5      5       Ha  n[
        R                  R                  R                  X5   R                  SS9X%   SSS9nUS   R                  SS9nUR                  U5        Mc     U$ UR                  SS9n[        UR                  S   5       Vs/ s H  o„U   PM	     nnU$ s  snf )	z\Converts the output of [`MobileViTForSemanticSegmentation`] into semantic segmentation maps.rQ   zTMake sure that you pass in as many target sizes as the batch dimension of the logitsr   )ÚdimÚbilinearF)ro   ÚmodeÚalign_cornersr]   )r   Úlogitsr`   Ú
ValueErrorÚ
isinstancerQ   ÚTensorÚnumpyr_   Únnr   ÚinterpolateÚ	unsqueezeÚargmaxÚappendr|   )	r3   Úoutputsr‚   rˆ   Úsemantic_segmentationrc   Úresized_logitsÚsemantic_mapÚis	            r%   Ú"post_process_semantic_segmentationÚ:MobileViTImageProcessor.post_process_semantic_segmentationÏ   s.  € ä˜$ Ô(Ø—‘ˆØÑ#Ü�6‹{œc ,Ó/Ó/Ü Øjóð ô ˜,¬¯©×5Ñ5Ø+×1Ñ1Ó3�Ø$&Ð!ÜœS ›[Ö)�Ü!&§¡×!4Ñ!4×!@Ñ!@Ø‘K×)Ñ)¨aÐ)Ð0°|Ñ7HÈzÐinð "Að "�ð  .¨aÑ0×7Ñ7¸AÐ7Ð>�Ø%×,Ñ,¨\Ö:ñ *ð %Ð$ð %+§M¡M°a MÐ$8Ð!ÜGLÐMb×MhÑMhÐijÑMkÔGlÓ$mÒGlÀ!¸1Ô%=ÑGlÐ!Ð$mØ$Ð$ùò %ns   ÄD&r   )N)r6   rY   r8   rY   )FT).r   r   r   r   r    r   Úvalid_kwargsr   ÚBICUBICrE   r
   Ú
image_meanr   Ú	image_stdro   Údefault_to_squarerq   rn   rp   rD   Údo_normalizer<   r   r   r   r2   r   r   r   r:   r!   r   Ústrr   r   rW   Úlistre   rl   r   ÚfloatrK   Útupler—   r#   Ú__classcell__)r4   s   @r%   r(   r(   :   s  ø† á]à0€Là!×)Ñ)€HØ'€JØ%€IØ˜SÐ!€DØÐØ¨Ñ-€IØ€IØ€NØ€JØ€LØ€NØ ÐØÐð# Ð(EÑ!F÷ #ð ð 04ñ
Gàð
Gð &¨Ñ,ð
Gð Ð6Ñ7ð	
Gð
 
÷
Gó ð
Gð& 59ñ/Càð/Cð &¨Ñ,ð/Cð ð	/Cð
 ,ð/Cð ˜jÑ(¨4Ñ/ð/Cð �c˜>Ð)Ñ*¨TÑ1ð/Cð 
õ/Cðb 4¨Ñ#7ð ¸DÀÑ<Pô ôð2 "'Ø&*ñ& à�^Ñ$ð& ð ð& ð ð	& ð
 Lð& ð ð& ð ð& ð ð& ð ð& ð  ™+ð& ð ð& ð  $ð& ð 
ˆnÑ	õ& ñP%ÈÈUÉÐVZÑHZ÷ %ó %r$   r(   )#r    Útypingr   rQ   Útorchvision.transforms.v2r   ÚtvFÚimage_processing_backendsr   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   Ú
get_loggerr   Úloggerr   r(   Ú__all__r   r$   r%   Ú<module>r°      s   ðñ +å ã Ý 7å ;Ý 2ß E÷÷ ÷ 5÷ó ð 
×	Ò	˜HÓ	%€ô L¸ò ð ôi%Ð0ó i%ó ði%ðX %Ð
%�r$   