§
    9²¸ja  ã                   ó  — d 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 ddlmZmZ dd	lmZmZmZmZ erdd
lmZ ddlZddlmZ  ej        e¦  «        Z G d„ ded¬¦  «        Ze G d„ de¦  «        ¦   «         Z dgZ!dS )zImage processor class for GLPN.é    )ÚTYPE_CHECKINGé   )ÚTorchvisionBackend)ÚBatchFeature)Úgroup_images_by_shapeÚreorder_images)Ú
ImageInputÚPILImageResamplingÚSizeDict)ÚImagesKwargsÚUnpack)Ú
TensorTypeÚauto_docstringÚloggingÚrequires_backends)ÚDepthEstimatorOutputN)Ú
functionalc                   ó   — e Zd ZU dZeed<   dS )ÚGLPNImageProcessorKwargszÐ
    size_divisor (`int`, *optional*, defaults to 32):
        When `do_resize` is `True`, images are resized so their height and width are rounded down to the closest
        multiple of `size_divisor`.
    Úsize_divisorN)Ú__name__Ú
__module__Ú__qualname__Ú__doc__ÚintÚ__annotations__© ó    ú~/root/private/project/pallet_detection_v2/.venv/lib/python3.11/site-packages/transformers/models/glpn/image_processing_glpn.pyr   r   (   s*   € € € € € € ðð ð ÐÐÑÐÐr   r   F)Útotalc            #       ó¾  ‡ — e Zd ZdZeZdZdZdZe	j
        ZdZdee         fˆ fd„Zˆ fd„Zededee         d	efˆ fd
„¦   «         Z	 d$dddeddded	df
ˆ fd„Z	 d$ded         dededddede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z  dedz  deez  dz  ded	ef"d„Z	 d%d d!d"eeeeef                  z  dz  d	eeeef                  fd#„Zˆ xZ S )&ÚGLPNImageProcessorz6Torchvision backend for GLPN with size_divisor resize.Tgp?é    Úkwargsc                 ó:   •—  t          ¦   «         j        di |¤Ž d S )Nr   )ÚsuperÚ__init__©Úselfr$   Ú	__class__s     €r   r'   zGLPNImageProcessor.__init__>   s&   ø€ Ø�‰ŒÔÐ"Ð"˜6Ð"Ð"Ð"Ð"Ð"r   c                 ób   •— |                      dd ¦  «          t          ¦   «         j        di |¤ŽS )NÚ	do_resizer   )Úpopr&   Ú_validate_preprocess_kwargsr(   s     €r   r.   z.GLPNImageProcessor._validate_preprocess_kwargsA   s4   ø€ à�
Š
�; Ñ%Ô%Ð%Ø2�u‰wŒwÔ2Ð<Ð<°VÐ<Ð<Ð<r   ÚimagesÚreturnc                 ó8   •—  t          ¦   «         j        |fi |¤ŽS ©N)r&   Ú
preprocess)r)   r/   r$   r*   s      €r   r3   zGLPNImageProcessor.preprocessF   s"   ø€ à!�u‰wŒwÔ! &Ð3Ð3¨FÐ3Ð3Ð3r   Úimageztorch.TensorÚsizeÚresamplez7PILImageResampling | tvF.InterpolationMode | int | Noner   c                 ó    •— |j         dd…         \  }}||z  |z  }||z  |z  }	 t          ¦   «         j        |t          ||	¬¦  «        fd|i|¤ŽS )zTResize so height and width are rounded down to the closest multiple of size_divisor.éþÿÿÿN)ÚheightÚwidthr6   )Úshaper&   Úresizer   )r)   r4   r5   r6   r   r$   r9   r:   Únew_hÚnew_wr*   s             €r   r<   zGLPNImageProcessor.resizeJ   s}   ø€ ð œ B C CÔ(‰ˆ�Ø˜,Ñ&¨Ñ5ˆØ˜Ñ%¨Ñ4ˆØ�u‰wŒwŒ~ØÝ˜E¨Ð/Ñ/Ô/ð
ð 
ð ð
ð ð	
ð 
ð 	
r   r,   Údo_center_cropÚ	crop_sizeÚ
do_rescaleÚrescale_factorÚdo_normalizeÚ
image_meanNÚ	image_stdÚdo_padÚpad_sizeÚdisable_groupingÚreturn_tensorsc           	      ó  — t          ||¬¦  «        \  }}i }|                     ¦   «         D ]?\  }}|r|                      ||||¬¦  «        }|                      ||||	|
|¦  «        }|||<   Œ@t	          ||¦  «        }t          d|i|¬¦  «        S )zCustom preprocessing for GLPN.)rH   )r   Úpixel_values)ÚdataÚtensor_type)r   Úitemsr<   Úrescale_and_normalizer   r   )r)   r/   r,   r5   r6   r?   r@   rA   rB   rC   rD   rE   rF   rG   rH   rI   r   r$   Úgrouped_imagesÚgrouped_images_indexÚprocessed_images_groupedr;   Ústacked_imagesÚprocessed_imagess                           r   Ú_preprocesszGLPNImageProcessor._preprocess]   sÆ   € õ* 0EÀVÐ^nÐ/oÑ/oÔ/oÑ,ˆÐ,Ø#%Ð Ø%3×%9Ò%9Ñ%;Ô%;ð 	=ð 	=Ñ!ˆE�>Øð hØ!%§¢¨^¸TÀ8ÐZf Ñ!gÔ!g�Ø!×7Ò7Ø 
¨N¸LÈ*ÐV_ñô ˆNð /=Ð$ UÑ+Ð+Ý)Ð*BÐDXÑYÔYÐÝ .Ð2BÐ!CÐQ_Ð`Ñ`Ô`Ð`r   Úoutputsr   Útarget_sizesc                 óÖ  — t          | d¦  «         |j        }|�/t          |¦  «        t          |¦  «        k    rt          d¦  «        ‚g }|€dgt          |¦  «        z  n|}t	          ||¦  «        D ]v\  }}|�X|d         }t
          j        j                             ||dd¬¦  «        }| 	                    d¦  «         	                    d¦  «        }| 
                    d	|i¦  «         Œw|S )
zf
        Convert raw model outputs to final depth predictions.
        Only supports PyTorch.
        ÚtorchNz]Make sure that you pass in as many target sizes as the batch dimension of the predicted depth)NN.ÚbicubicF)r5   ÚmodeÚalign_cornersr   Úpredicted_depth)r   r]   ÚlenÚ
ValueErrorÚziprY   Únnr   ÚinterpolateÚsqueezeÚappend)r)   rV   rW   r]   ÚresultsÚdepthÚtarget_sizes          r   Úpost_process_depth_estimationz0GLPNImageProcessor.post_process_depth_estimation~   s  € õ 	˜$ Ñ(Ô(Ð(Ø!Ô1ˆØÐ#­¨OÑ(<Ô(<ÅÀLÑ@QÔ@QÒ(QÐ(QÝØoñô ð ð ˆØ8DÐ8L˜�v¥ OÑ 4Ô 4Ñ4Ð4ÐR^ˆÝ"% o°|Ñ"DÔ"Dð 	7ð 	7ÑˆE�;ØÐ&Ø˜oÔ.�ÝœÔ+×7Ò7¸ÀKÐV_ÐotÐ7ÑuÔu�ØŸš aÑ(Ô(×0Ò0°Ñ3Ô3�Ø�NŠNÐ-¨uÐ5Ñ6Ô6Ð6Ð6Øˆr   )r#   r2   )!r   r   r   r   r   Úvalid_kwargsr,   rA   rB   r
   ÚBILINEARr6   r   r   r'   r.   r   r	   r   r3   r   r   r<   ÚlistÚboolÚfloatÚstrr   rU   ÚtupleÚdictrh   Ú__classcell__)r*   s   @r   r"   r"   2   s   ø€ € € € € à@Ð@à+€Là€IØ€JØ€NØ!Ô*€HØ€Lð# Ð(@Ô!Að #ð #ð #ð #ð #ð #ð=ð =ð =ð =ð =ð
 ð4 ð 4°vÐ>VÔ7Wð 4Ð\hð 4ð 4ð 4ð 4ð 4ñ „^ð4ð ð
ð 
àð
ð ð
ð Lð	
ð
 ð
ð 
ð
ð 
ð 
ð 
ð 
ð 
ðH ð#að aà�^Ô$ðað ðað ð	að
 Lðað ðað ðað ðað ðað ðað ˜D œKÑ'¨$Ñ.ðað ˜4 œ;Ñ&¨Ñ-ðað �t‘ðað ˜T‘/ðað  ™+ðað  ˜jÑ(¨4Ñ/ð!að" ð#að& 
ð'að að að aðH CGðð à'ðð ! 4¨¨c°3¨h¬Ô#8Ñ8¸4Ñ?ðð 
ˆd�3˜
�?Ô#Ô	$ð	ð ð ð ð ð ð ð r   r"   )"r   Útypingr   Úimage_processing_backendsr   Úimage_processing_utilsr   Úimage_transformsr   r   Úimage_utilsr	   r
   r   Úprocessing_utilsr   r   Úutilsr   r   r   r   Úmodeling_outputsr   rY   Útorchvision.transforms.v2r   ÚtvFÚ
get_loggerr   Úloggerr   r"   Ú__all__r   r   r   ú<module>r      s•  ðð &Ð %à  Ð  Ð  Ð  Ð  Ð  à ;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
 5Ð 4Ð 4Ð 4Ð 4Ð 4Ð 4Ð 4Ø KÐ KÐ KÐ KÐ KÐ KÐ KÐ KÐ KÐ KÐ KÐ Kð ð 9Ø8Ð8Ð8Ð8Ð8Ð8à €€€Ø 7Ð 7Ð 7Ð 7Ð 7Ð 7ð 
ˆÔ	˜HÑ	%Ô	%€ðð ð ð ð ˜|°5ð ñ ô ð ð ðbð bð bð bð bÐ+ñ bô bñ „ðbðJ  Ð
 €€€r   