§
    9²¸jÕH  ã                   ó  — d Z ddlZddlmZ ddlmZ ddlmZm	Z	m
Z
 ddlmZmZmZmZ ddlmZmZmZmZmZmZmZmZmZmZmZ dd	lmZmZ  e¦   «         rddlZ ej         e!¦  «        Z"d
e#e#e                  fd„Z$ G d„ de¦  «        Z%dgZ&dS )z Image processor class for Vivit.é    N)Úis_vision_available)Ú
TensorTypeé   )ÚBaseImageProcessorÚBatchFeatureÚget_size_dict)Úget_resize_output_image_sizeÚrescaleÚresizeÚto_channel_dimension_format)ÚIMAGENET_STANDARD_MEANÚIMAGENET_STANDARD_STDÚChannelDimensionÚ
ImageInputÚPILImageResamplingÚinfer_channel_dimension_formatÚis_scaled_imageÚis_valid_imageÚto_numpy_arrayÚvalid_imagesÚvalidate_preprocess_arguments)Úfilter_out_non_signature_kwargsÚloggingÚreturnc                 ój  — t          | t          t          f¦  «        r?t          | d         t          t          f¦  «        rt          | d         d         ¦  «        r| S t          | t          t          f¦  «        rt          | d         ¦  «        r| gS t          | ¦  «        r| ggS t	          d| › �¦  «        ‚)Nr   z"Could not make batched video from )Ú
isinstanceÚlistÚtupler   Ú
ValueError)Úvideoss    ú€/root/private/project/pallet_detection_v2/.venv/lib/python3.11/site-packages/transformers/models/vivit/image_processing_vivit.pyÚmake_batchedr"   2   s´   € Ý�&�4¥˜-Ñ(Ô(ð ­Z¸¸q¼	ÅDÍ%À=Ñ-QÔ-Qð ÕVdÐekÐlmÔenÐopÔeqÑVrÔVrð Øˆå	�F�T¥5˜MÑ	*Ô	*ð ­~¸fÀQ¼iÑ/HÔ/Hð Øˆxˆå	˜Ñ	Ô	ð Ø�ˆzÐå
ÐB¸&ÐBÐBÑ
CÔ
CÐCó    c            "       óæ  ‡ — e Zd ZdZdgZddej        ddddddddfdedee	e
f         dz  ded	ed
ee	e
f         dz  dede
ez  dededeee         z  dz  deee         z  dz  ddfˆ fd„Zej        ddfdej        dee	e
f         dede	ez  dz  de	ez  dz  dej        fd„Z	 	 	 ddej        de
ez  dede	ez  dz  de	ez  dz  f
d„Zdddddddddddej        dfdededz  dee	e
f         dz  dedz  d	edz  d
ee	e
f         dz  dedz  dedz  dedz  dedz  deee         z  dz  deee         z  dz  dedz  de	ez  dz  dej        fd„Z e¦   «         ddddddddddddej        dfdededz  dee	e
f         dz  dedz  d	edz  d
ee	e
f         dz  dedz  dedz  dedz  dedz  deee         z  dz  deee         z  dz  de	ez  dz  dede	ez  dz  dej        j        f d„¦   «         Zˆ xZS )ÚVivitImageProcessoraC  
    Constructs a Vivit image processor.

    Args:
        do_resize (`bool`, *optional*, defaults to `True`):
            Whether to resize the image's (height, width) dimensions to the specified `size`. Can be overridden by the
            `do_resize` parameter in the `preprocess` method.
        size (`dict[str, int]` *optional*, defaults to `{"shortest_edge": 256}`):
            Size of the output image after resizing. The shortest edge of the image will be resized to
            `size["shortest_edge"]` while maintaining the aspect ratio of the original image. Can be overridden by
            `size` in the `preprocess` method.
        resample (`PILImageResampling`, *optional*, defaults to `Resampling.BILINEAR`):
            Resampling filter to use if resizing the image. Can be overridden by the `resample` parameter in the
            `preprocess` method.
        do_center_crop (`bool`, *optional*, defaults to `True`):
            Whether to center crop the image to the specified `crop_size`. Can be overridden by the `do_center_crop`
            parameter in the `preprocess` method.
        crop_size (`dict[str, int]`, *optional*, defaults to `{"height": 224, "width": 224}`):
            Size of the image after applying the center crop. Can be overridden by the `crop_size` parameter in the
            `preprocess` method.
        do_rescale (`bool`, *optional*, defaults to `True`):
            Whether to rescale the image by the specified scale `rescale_factor`. Can be overridden by the `do_rescale`
            parameter in the `preprocess` method.
        rescale_factor (`int` or `float`, *optional*, defaults to `1/127.5`):
            Defines the scale factor to use if rescaling the image. Can be overridden by the `rescale_factor` parameter
            in the `preprocess` method.
        offset (`bool`, *optional*, defaults to `True`):
            Whether to scale the image in both negative and positive directions. Can be overridden by the `offset` in
            the `preprocess` method.
        do_normalize (`bool`, *optional*, defaults to `True`):
            Whether to normalize the image. Can be overridden by the `do_normalize` parameter in the `preprocess`
            method.
        image_mean (`float` or `list[float]`, *optional*, defaults to `IMAGENET_STANDARD_MEAN`):
            Mean to use if normalizing the image. This is a float or list of floats the length of the number of
            channels in the image. Can be overridden by the `image_mean` parameter in the `preprocess` method.
        image_std (`float` or `list[float]`, *optional*, defaults to `IMAGENET_STANDARD_STD`):
            Standard deviation to use if normalizing the image. This is a float or list of floats the length of the
            number of channels in the image. Can be overridden by the `image_std` parameter in the `preprocess` method.
    Úpixel_valuesTNg€?Ú	do_resizeÚsizeÚresampleÚdo_center_cropÚ	crop_sizeÚ
do_rescaleÚrescale_factorÚoffsetÚdo_normalizeÚ
image_meanÚ	image_stdr   c                 ó^  •—  t          ¦   «         j        d	i |¤Ž |�|nddi}t          |d¬¦  «        }|�|ndddœ}t          |d¬¦  «        }|| _        || _        || _        || _        || _        || _        || _	        || _
        |	| _        |
�|
nt          | _        |�|nt          | _        d S )
NÚshortest_edgeé   F©Údefault_to_squareéà   )ÚheightÚwidthr+   ©Ú
param_name© )ÚsuperÚ__init__r   r'   r(   r*   r+   r)   r,   r-   r.   r/   r   r0   r   r1   )Úselfr'   r(   r)   r*   r+   r,   r-   r.   r/   r0   r1   ÚkwargsÚ	__class__s                €r!   r>   zVivitImageProcessor.__init__j   sØ   ø€ ð 	�‰ŒÔÐ"Ð"˜6Ð"Ð"Ð"ØÐ'ˆtˆt¨o¸sÐ-CˆÝ˜T°UÐ;Ñ;Ô;ˆØ!*Ð!6�I�IÀsÐUXÐ<YÐ<Yˆ	Ý! )¸ÐDÑDÔDˆ	à"ˆŒØˆŒ	Ø,ˆÔØ"ˆŒØ ˆŒØ$ˆŒØ,ˆÔØˆŒØ(ˆÔØ(2Ð(>˜*˜*ÕDZˆŒØ&/Ð&;˜˜ÕAVˆŒˆˆr#   ÚimageÚdata_formatÚinput_data_formatc                 óþ   — t          |d¬¦  «        }d|v rt          ||d         d|¬¦  «        }n=d|v rd|v r|d         |d         f}n$t          d|                     ¦   «         › �¦  «        ‚t	          |f||||dœ|¤ŽS )	a÷  
        Resize an image.

        Args:
            image (`np.ndarray`):
                Image to resize.
            size (`dict[str, int]`):
                Size of the output image. If `size` is of the form `{"height": h, "width": w}`, the output image will
                have the size `(h, w)`. If `size` is of the form `{"shortest_edge": s}`, the output image will have its
                shortest edge of length `s` while keeping the aspect ratio of the original image.
            resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BILINEAR`):
                Resampling filter to use when resiizing the image.
            data_format (`str` or `ChannelDimension`, *optional*):
                The channel dimension format of the image. If not provided, it will be the same as the input image.
            input_data_format (`str` or `ChannelDimension`, *optional*):
                The channel dimension format of the input image. If not provided, it will be inferred.
        Fr5   r3   )r6   rD   r8   r9   zDSize must have 'height' and 'width' or 'shortest_edge' as keys. Got )r(   r)   rC   rD   )r   r	   r   Úkeysr   )r?   rB   r(   r)   rC   rD   r@   Úoutput_sizes           r!   r   zVivitImageProcessor.resize‹   sÈ   € õ4 ˜T°UÐ;Ñ;Ô;ˆØ˜dÐ"Ð"Ý6Ø�t˜OÔ,ÀÐYjðñ ô ˆKˆKð ˜ÐÐ '¨T / /Ø œ>¨4°¬=Ð9ˆKˆKåÐqÐdh×dmÒdmÑdoÔdoÐqÐqÑrÔrÐrÝØð
àØØ#Ø/ð
ð 
ð ð
ð 
ð 	
r#   Úscalec                 ó6   — t          |f|||dœ|¤Ž}|r|dz
  }|S )a  
        Rescale an image by a scale factor.

        If `offset` is `True`, the image has its values rescaled by `scale` and then offset by 1. If `scale` is
        1/127.5, the image is rescaled between [-1, 1].
            image = image * scale - 1

        If `offset` is `False`, and `scale` is 1/255, the image is rescaled between [0, 1].
            image = image * scale

        Args:
            image (`np.ndarray`):
                Image to rescale.
            scale (`int` or `float`):
                Scale to apply to the image.
            offset (`bool`, *optional*):
                Whether to scale the image in both negative and positive directions.
            data_format (`str` or `ChannelDimension`, *optional*):
                The channel dimension format of the image. If not provided, it will be the same as the input image.
            input_data_format (`ChannelDimension` or `str`, *optional*):
                The channel dimension format of the input image. If not provided, it will be inferred.
        )rH   rC   rD   é   )r
   )r?   rB   rH   r.   rC   rD   r@   Úrescaled_images           r!   r
   zVivitImageProcessor.rescale·   sJ   € õ> !Øð
Ø¨KÐK\ð
ð 
Ø`fð
ð 
ˆð ð 	0Ø+¨aÑ/ˆNàÐr#   c                 óî  — t          |||
|||||||¬¦
  «
         |	r|st          d¦  «        ‚t          |¦  «        }|r)t          |¦  «        rt                               d¦  «         |€t          |¦  «        }|r|                      ||||¬¦  «        }|r|                      |||¬¦  «        }|r|  	                    |||	|¬¦  «        }|
r|  
                    ||||¬¦  «        }t          |||¬	¦  «        }|S )
zPreprocesses a single image.)
r,   r-   r/   r0   r1   r*   r+   r'   r(   r)   z0For offset, do_rescale must also be set to True.z­It looks like you are trying to rescale already rescaled images. If the input images have pixel values between 0 and 1, set `do_rescale=False` to avoid rescaling them again.N)rB   r(   r)   rD   )r(   rD   )rB   rH   r.   rD   )rB   ÚmeanÚstdrD   )Úinput_channel_dim)r   r   r   r   ÚloggerÚwarning_oncer   r   Úcenter_cropr
   Ú	normalizer   )r?   rB   r'   r(   r)   r*   r+   r,   r-   r.   r/   r0   r1   rC   rD   s                  r!   Ú_preprocess_imagez%VivitImageProcessor._preprocess_imageß   s\  € õ& 	&Ø!Ø)Ø%Ø!ØØ)ØØØØð	
ñ 	
ô 	
ð 	
ð ð 	Q˜*ð 	QÝÐOÑPÔPÐPõ ˜uÑ%Ô%ˆàð 	�/¨%Ñ0Ô0ð 	Ý×Òðsñô ð ð
 Ð$Ý >¸uÑ EÔ EÐàð 	pØ—K’K e°$ÀÐ]n�KÑoÔoˆEàð 	aØ×$Ò$ U°ÐN_Ð$Ñ`Ô`ˆEàð 	xØ—L’L u°NÈ6Ðev�LÑwÔwˆEàð 	uØ—N’N¨°ZÀYÐbs�NÑtÔtˆEå+¨E°;ÐRcÐdÑdÔdˆØˆr#   r    Úreturn_tensorsc                 ó  ‡ ‡‡‡‡‡‡‡‡	‡
‡‡‡‡— ‰�‰n‰ j         Š‰�‰n‰ j        Š‰�‰n‰ j        Š‰�‰n‰ j        Š‰�‰n‰ j        Š‰	�‰	n‰ j        Š	‰
�‰
n‰ j        Š
‰�‰n‰ j        Š‰�‰n‰ j        Š‰�‰n‰ j	        Št          ‰d¬¦  «        Š‰�‰n‰ j        Št          ‰d¬¦  «        Št          |¦  «        st          d¦  «        ‚t          |¦  «        }ˆˆˆˆ
ˆˆˆˆˆˆ	ˆˆˆ ˆfd„|D ¦   «         }d|i}t          ||¬	¦  «        S )
a_  
        Preprocess an image or batch of images.

        Args:
            videos (`ImageInput`):
                Video frames to preprocess. Expects a single or batch of video frames with pixel values ranging from 0
                to 255. If passing in frames with pixel values between 0 and 1, set `do_rescale=False`.
            do_resize (`bool`, *optional*, defaults to `self.do_resize`):
                Whether to resize the image.
            size (`dict[str, int]`, *optional*, defaults to `self.size`):
                Size of the image after applying resize.
            resample (`PILImageResampling`, *optional*, defaults to `self.resample`):
                Resampling filter to use if resizing the image. This can be one of the enum `PILImageResampling`, Only
                has an effect if `do_resize` is set to `True`.
            do_center_crop (`bool`, *optional*, defaults to `self.do_centre_crop`):
                Whether to centre crop the image.
            crop_size (`dict[str, int]`, *optional*, defaults to `self.crop_size`):
                Size of the image after applying the centre crop.
            do_rescale (`bool`, *optional*, defaults to `self.do_rescale`):
                Whether to rescale the image values between `[-1 - 1]` if `offset` is `True`, `[0, 1]` otherwise.
            rescale_factor (`float`, *optional*, defaults to `self.rescale_factor`):
                Rescale factor to rescale the image by if `do_rescale` is set to `True`.
            offset (`bool`, *optional*, defaults to `self.offset`):
                Whether to scale the image in both negative and positive directions.
            do_normalize (`bool`, *optional*, defaults to `self.do_normalize`):
                Whether to normalize the image.
            image_mean (`float` or `list[float]`, *optional*, defaults to `self.image_mean`):
                Image mean.
            image_std (`float` or `list[float]`, *optional*, defaults to `self.image_std`):
                Image standard deviation.
            return_tensors (`str` or `TensorType`, *optional*):
                The type of tensors to return. Can be one of:
                    - Unset: Return a list of `np.ndarray`.
                    - `TensorType.PYTORCH` or `'pt'`: Return a batch of type `torch.Tensor`.
                    - `TensorType.NUMPY` or `'np'`: Return a batch of type `np.ndarray`.
            data_format (`ChannelDimension` or `str`, *optional*, defaults to `ChannelDimension.FIRST`):
                The channel dimension format for the output image. Can be one of:
                    - `ChannelDimension.FIRST`: image in (num_channels, height, width) format.
                    - `ChannelDimension.LAST`: image in (height, width, num_channels) format.
                    - Unset: Use the inferred channel dimension format of the input image.
            input_data_format (`ChannelDimension` or `str`, *optional*):
                The channel dimension format for the input image. If unset, the channel dimension format is inferred
                from the input image. Can be one of:
                - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format.
                - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format.
                - `"none"` or `ChannelDimension.NONE`: image in (height, width) format.
        NFr5   r+   r:   zSInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, or torch.Tensorc                 óF   •— g | ]}ˆˆˆˆˆˆˆˆ	ˆ
ˆˆˆˆˆfd „|D ¦   «         ‘ŒS )c                 óV   •— g | ]%}‰                      |‰‰‰‰‰‰‰‰‰‰‰	‰‰
¬ ¦  «        ‘Œ&S ))rB   r'   r(   r)   r*   r+   r,   r-   r.   r/   r0   r1   rC   rD   )rT   )Ú.0Úimgr+   rC   r*   r/   r,   r'   r0   r1   rD   r.   r)   r-   r?   r(   s     €€€€€€€€€€€€€€r!   ú
<listcomp>z=VivitImageProcessor.preprocess.<locals>.<listcomp>.<listcomp>t  sj   ø€ ð ð ð ð" ð! ×&Ò&ØØ'ØØ%Ø#1Ø'Ø)Ø#1Ø!Ø!-Ø)Ø'Ø +Ø&7ð 'ñ ô ðð ð r#   r<   )rY   Úvideor+   rC   r*   r/   r,   r'   r0   r1   rD   r.   r)   r-   r?   r(   s     €€€€€€€€€€€€€€r!   r[   z2VivitImageProcessor.preprocess.<locals>.<listcomp>s  s�   ø€ ð 
ð 
ð 
ð( ð'ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð" !ð#ñ ô ð
ð 
ð 
r#   r&   )ÚdataÚtensor_type)r'   r)   r*   r,   r-   r.   r/   r0   r1   r(   r   r+   r   r   r"   r   )r?   r    r'   r(   r)   r*   r+   r,   r-   r.   r/   r0   r1   rU   rC   rD   r]   s   ` ``````````` `` r!   Ú
preprocesszVivitImageProcessor.preprocess  s¡  øøøøøøøøøøøøøø€ ðD "+Ð!6�I�I¸D¼Nˆ	Ø'Ð3�8�8¸¼ˆØ+9Ð+E˜˜È4ÔK^ˆØ#-Ð#9�Z�Z¸t¼ˆ
Ø+9Ð+E˜˜È4ÔK^ˆØ!Ð-��°4´;ˆØ'3Ð'?�|�|ÀTÔEVˆØ#-Ð#9�Z�Z¸t¼ˆ
Ø!*Ð!6�I�I¸D¼Nˆ	àÐ'ˆtˆt¨T¬YˆÝ˜T°UÐ;Ñ;Ô;ˆØ!*Ð!6�I�I¸D¼Nˆ	Ý! )¸ÐDÑDÔDˆ	å˜FÑ#Ô#ð 	tÝÐrÑsÔsÐså˜fÑ%Ô%ˆð
ð 
ð 
ð 
ð 
ð 
ð 
ð 
ð 
ð 
ð 
ð 
ð 
ð 
ð 
ð 
ð 
ð(  ð)
ñ 
ô 
ˆð.  Ð'ˆÝ °>ÐBÑBÔBÐBr#   )TNN)Ú__name__Ú
__module__Ú__qualname__Ú__doc__Úmodel_input_namesr   ÚBILINEARÚboolÚdictÚstrÚintÚfloatr   r>   ÚnpÚndarrayr   r   r
   ÚFIRSTr   rT   r   r   ÚPILÚImager_   Ú__classcell__)rA   s   @r!   r%   r%   ?   s  ø€ € € € € ð&ð &ðP (Ð(Ðð Ø&*Ø'9Ô'BØ#Ø+/ØØ&/ØØ!Ø15Ø04ðWð WàðWð �3˜�8Œn˜tÑ#ðWð %ð	Wð
 ðWð ˜˜S˜”> DÑ(ðWð ðWð ˜e™ðWð ðWð ðWð ˜D œKÑ'¨$Ñ.ðWð ˜4 œ;Ñ&¨Ñ-ðWð 
ðWð Wð Wð Wð Wð WðJ (:Ô'BØ59Ø;?ð*
ð *
àŒzð*
ð �3˜�8Œnð*
ð %ð	*
ð
 Ð+Ñ+¨dÑ2ð*
ð Ð!1Ñ1°DÑ8ð*
ð 
Œð*
ð *
ð *
ð *
ð` Ø59Ø;?ð&ð &àŒzð&ð �U‰{ð&ð ð	&ð
 Ð+Ñ+¨dÑ2ð&ð Ð!1Ñ1°DÑ8ð&ð &ð &ð &ðV "&Ø&*Ø.2Ø&*Ø+/Ø"&Ø'+Ø"Ø$(Ø15Ø04Ø/?Ô/EØ;?ð<ð <àð<ð ˜$‘;ð<ð �3˜�8Œn˜tÑ#ð	<ð
 % tÑ+ð<ð ˜t™ð<ð ˜˜S˜”> DÑ(ð<ð ˜4‘Kð<ð  ™ð<ð �t‘ð<ð ˜T‘kð<ð ˜D œKÑ'¨$Ñ.ð<ð ˜4 œ;Ñ&¨Ñ-ð<ð &¨Ñ,ð<ð Ð!1Ñ1°DÑ8ð<ð  
Œð!<ð <ð <ð <ð| %Ð$Ñ&Ô&ð "&Ø&*Ø.2Ø&*Ø+/Ø"&Ø'+Ø"Ø$(Ø15Ø04Ø26Ø(8Ô(>Ø;?ð!mCð mCàðmCð ˜$‘;ðmCð �3˜�8Œn˜tÑ#ð	mCð
 % tÑ+ðmCð ˜t™ðmCð ˜˜S˜”> DÑ(ðmCð ˜4‘KðmCð  ™ðmCð �t‘ðmCð ˜T‘kðmCð ˜D œKÑ'¨$Ñ.ðmCð ˜4 œ;Ñ&¨Ñ-ðmCð ˜jÑ(¨4Ñ/ðmCð &ðmCð  Ð!1Ñ1°DÑ8ð!mCð" 
ŒŒð#mCð mCð mCñ 'Ô&ðmCð mCð mCð mCð mCr#   r%   )'rc   Únumpyrk   Útransformers.utilsr   Útransformers.utils.genericr   Úimage_processing_utilsr   r   r   Úimage_transformsr	   r
   r   r   Úimage_utilsr   r   r   r   r   r   r   r   r   r   r   Úutilsr   r   rn   Ú
get_loggerr`   rP   r   r"   r%   Ú__all__r<   r#   r!   ú<module>rz      sÕ  ðð 'Ð &à Ð Ð Ð à 2Ð 2Ð 2Ð 2Ð 2Ð 2Ø 1Ð 1Ð 1Ð 1Ð 1Ð 1à UÐ UÐ UÐ UÐ UÐ UÐ UÐ UÐ UÐ Uðð ð ð ð ð ð ð ð ð ð ð ðð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð >Ð =Ð =Ð =Ð =Ð =Ð =Ð =ð ÐÑÔð Ø€J€J€Jà	ˆÔ	˜HÑ	%Ô	%€ð
D˜D  jÔ!1Ô2ð 
Dð 
Dð 
Dð 
DðLCð LCð LCð LCð LCÐ,ñ LCô LCð LCð^
 !Ð
!€€€r#   