
    sgC                        d Z ddlmZmZmZmZ ddlZddlm	Z	m
Z
mZ ddl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mZ ddlmZmZm Z m!Z!  e        rddl"Z" e!jF                  e$      Z%d	ee   fd
Z& G d de	      Z'y)z{
Image processor class for InstructBLIPVideo. Largely copy of Blip2Processor with addition of a video processing abilities
    )DictListOptionalUnionN   )BaseImageProcessorBatchFeatureget_size_dict)convert_to_rgbresizeto_channel_dimension_format)OPENAI_CLIP_MEANOPENAI_CLIP_STDChannelDimension
ImageInputPILImageResampling
VideoInputinfer_channel_dimension_formatis_scaled_imageis_valid_imageto_numpy_arrayvalid_imagesvalidate_preprocess_arguments)
TensorTypefilter_out_non_signature_kwargsis_vision_availableloggingreturnc                 ^   t        | t        t        f      r,t        | d   t        t        f      rt        | d   d         r| S t        | t        t        f      rlt        | d         r^t        | d   t        j
                  j
                        r| gS t        | d   j                        dk(  rp| D cg c]  }t        |       c}S t        |       rLt        | t        j
                  j
                        r| ggS t        | j                        dk(  rt        |       gS t        d|        c c}w )Nr      z"Could not make batched video from )	
isinstancelisttupler   PILImagelenshape
ValueError)videosvideos     {/var/www/html/venv/lib/python3.12/site-packages/transformers/models/instructblipvideo/image_processing_instructblipvideo.pymake_batched_videosr,   2   s    &4-(Zq	D%=-QVdeklmenopeqVr	FT5M	*~fQi/HfQi18O!Q&-34EDK44		fciioo.H:!#L>!
9&B
CC 5s   0D*c                   J    e Zd ZdZdgZddej                  ddddddf	dedee	e
f   ded	ed
ee
ef   dedeeeee   f      deeeee   f      deddf fdZej                  ddfdej"                  dee	e
f   dedeee	ef      deee	ef      dej"                  fdZ e       dddddddddddej*                  dfdedee   deee	e
f      ded	ee   d
ee   dee   deeeee   f      deeeee   f      deee	ef      dededeee	ef      dej2                  j2                  fd       Zddddddddddej*                  dfdedee   deee	e
f      ded	ee   d
ee   dee   deeeee   f      deeeee   f      dededeee	ef      dej"                  fdZ xZS )InstructBlipVideoImageProcessora	  
    Constructs a InstructBLIPVideo 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`, *optional*, defaults to `{"height": 384, "width": 384}`):
            Size of the output image after resizing. Can be overridden by the `size` parameter in the `preprocess`
            method.
        resample (`PILImageResampling`, *optional*, defaults to `Resampling.BICUBIC`):
            Resampling filter to use if resizing the image. Only has an effect if `do_resize` is set to `True`. Can be
            overridden by the `resample` 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 `1/255`):
            Scale factor to use if rescaling the image. Only has an effect if `do_rescale` is set to `True`. Can be
            overridden by the `rescale_factor` parameter 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. 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. 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.
            Can be overridden by the `image_std` parameter in the `preprocess` method.
        do_convert_rgb (`bool`, *optional*, defaults to `True`):
            Whether to convert the image to RGB.
    pixel_valuesTNgp?	do_resizesizeresample
do_rescalerescale_factordo_normalize
image_mean	image_stddo_convert_rgbr   c
                     t        |   di |
 ||nddd}t        |d      }|| _        || _        || _        || _        || _        || _        ||nt        | _
        ||nt        | _        |	| _        y )Ni  )heightwidthTdefault_to_square )super__init__r
   r0   r1   r2   r3   r4   r5   r   r6   r   r7   r8   )selfr0   r1   r2   r3   r4   r5   r6   r7   r8   kwargs	__class__s              r+   r@   z(InstructBlipVideoImageProcessor.__init__k   s     	"6"'tc-JTT:"	 $,((2(>*DT&/&;,    imagedata_formatinput_data_formatc                     t        |      }d|vsd|vrt        d|j                                |d   |d   f}t        |f||||d|S )a  
        Resize an image to `(size["height"], size["width"])`.

        Args:
            image (`np.ndarray`):
                Image to resize.
            size (`Dict[str, int]`):
                Dictionary in the format `{"height": int, "width": int}` specifying the size of the output image.
            resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BICUBIC`):
                `PILImageResampling` filter to use when resizing the image e.g. `PILImageResampling.BICUBIC`.
            data_format (`ChannelDimension` or `str`, *optional*):
                The channel dimension format for the output image. If unset, the channel dimension format of the input
                image is used. 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.
            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.

        Returns:
            `np.ndarray`: The resized image.
        r:   r;   zFThe `size` dictionary must contain the keys `height` and `width`. Got )r1   r2   rF   rG   )r
   r(   keysr   )rA   rE   r1   r2   rF   rG   rB   output_sizes           r+   r   z&InstructBlipVideoImageProcessor.resize   sy    F T"47$#6efjfofofqersttH~tG}5
#/
 
 	
rD   imagesreturn_tensorsc                 P   ||n| j                   }||n| j                  }||n| j                  }||n| j                  }||n| j                  }||n| j
                  }|	|	n| j                  }	||n| j                  }||n| j                  }t        |d      }t        |      }t        |||||	|||       t        |      st        d      |D cg c]-  }|D cg c]  }| j                  |||||||||	|||      ! c}/ }}}t        d|i|
      }|S c c}w c c}}w )a  
        Preprocess a video or batch of images/videos.

        Args:
            videos (`VideoInput`):
                Video frames to preprocess. Expects a single or batch of videos as a list of frames with pixel values
                ranging from 0 to 255. If passing in video with pixel values between 0 and 1, set `do_rescale=False`.
            do_resize (`bool`, *optional*, defaults to `self.do_resize`):
                Whether to resize the video.
            size (`Dict[str, int]`, *optional*, defaults to `self.size`):
                Controls the size of the video after `resize`. The shortest edge of the image is resized to
                `size["shortest_edge"]` whilst preserving the aspect ratio. If the longest edge of this resized image
                is > `int(size["shortest_edge"] * (1333 / 800))`, then the image is resized again to make the longest
                edge equal to `int(size["shortest_edge"] * (1333 / 800))`.
            resample (`PILImageResampling`, *optional*, defaults to `self.resample`):
                Resampling filter to use if resizing the video. Only has an effect if `do_resize` is set to `True`.
            do_rescale (`bool`, *optional*, defaults to `self.do_rescale`):
                Whether to rescale the video values between [0 - 1].
            rescale_factor (`float`, *optional*, defaults to `self.rescale_factor`):
                Rescale factor to rescale the video by if `do_rescale` is set to `True`.
            do_normalize (`bool`, *optional*, defaults to `self.do_normalize`):
                Whether to normalize the video.
            image_mean (`float` or `List[float]`, *optional*, defaults to `self.image_mean`):
                Image mean to normalize the video by if `do_normalize` is set to `True`.
            image_std (`float` or `List[float]`, *optional*, defaults to `self.image_std`):
                Image standard deviation to normalize the video by if `do_normalize` is set to `True`.
            do_convert_rgb (`bool`, *optional*, defaults to `self.do_convert_rgb`):
                Whether to convert the image to RGB.
            return_tensors (`str` or `TensorType`, *optional*):
                The type of tensors to return. Can be one of:
                    - Unset: Return a list of `np.ndarray`.
                    - `TensorType.TENSORFLOW` or `'tf'`: Return a batch of type `tf.Tensor`.
                    - `TensorType.PYTORCH` or `'pt'`: Return a batch of type `torch.Tensor`.
                    - `TensorType.NUMPY` or `'np'`: Return a batch of type `np.ndarray`.
                    - `TensorType.JAX` or `'jax'`: Return a batch of type `jax.numpy.ndarray`.
            data_format (`ChannelDimension` or `str`, *optional*, defaults to `ChannelDimension.FIRST`):
                The channel dimension format for the output 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.
                - Unset: Use the 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.
        Fr<   )r3   r4   r5   r6   r7   r0   r1   r2   zkInvalid input type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.)rE   r0   r1   r2   r3   r4   r5   r6   r7   r8   rF   rG   r/   )datatensor_type)r0   r2   r3   r4   r5   r6   r7   r8   r1   r
   r,   r   r   r(   _preprocess_imager	   )rA   rK   r0   r1   r2   r3   r4   r5   r6   r7   rL   r8   rF   rG   r)   r*   framer/   encoded_outputss                      r+   
preprocessz*InstructBlipVideoImageProcessor.preprocess   s{   @ "+!6IDNN	'38#-#9Zt
+9+E4K^K^'3'?|TEVEV#-#9Zt
!*!6IDNN	+9+E4K^K^'tTYYTU;$V,%!)%!		
 F#: .  %
$  #  &&'%)#1!-)'#1 +&7 ' 
 
* '^\,JXfg+
s   	D" $DD"D"c                 8   |
rt        |      }t        |      }t        |      r|rt        j	                  d       |t        |      }|r| j                  ||||      }|r| j                  |||      }|r| j                  |||	|      }t        |||      }|S )NzIt looks like you are trying to rescale already rescaled video frames. If the input images have pixel values between 0 and 1, set `do_rescale=False` to avoid rescaling them again.)rE   r1   r2   rG   )rE   scalerG   )rE   meanstdrG   )input_channel_dim)
r   r   r   loggerwarning_oncer   r   rescale	normalizer   )rA   rE   r0   r1   r2   r3   r4   r5   r6   r7   r8   rF   rG   s                r+   rP   z1InstructBlipVideoImageProcessor._preprocess_image1  s      "5)E u%5!js
 $ >u EKKe$]nKoELLuNVgLhENNZYbsNtE+E;RcdrD   )__name__
__module____qualname____doc__model_input_namesr   BICUBICboolr   strintr   floatr   r   r@   npndarrayr   r   r   FIRSTr   r   r$   r%   rS   r   rP   __classcell__)rC   s   @r+   r.   r.   F   s    D (( #'9'A'A,3!:>9=#-- 38n- %	-
 - c5j)- - U5$u+#567- E%e"456- - 
-@ (:'A'A>BDH/
zz/
 38n/
 %	/

 eC)9$9:;/
 $E#/?*?$@A/
 
/
d %& "$()-'+%)*.'+:>9=;?#(8(>(>DHtt D>t tCH~&	t
 %t TNt !t tnt U5$u+#567t E%e"456t !sJ!78t t &t $E#/?*?$@At 
t 'tr !$()-'+%)*.'+:>9=#(8(>(>DH++ D>+ tCH~&	+
 %+ TN+ !+ tn+ U5$u+#567+ E%e"456+ + &+ $E#/?*?$@A+ 
+rD   r.   )(r`   typingr   r   r   r   numpyrg   image_processing_utilsr   r	   r
   image_transformsr   r   r   image_utilsr   r   r   r   r   r   r   r   r   r   r   r   utilsr   r   r   r   r$   
get_loggerr]   rY   r,   r.   r>   rD   r+   <module>rr      s     / .  U U S S    _ ^  
		H	%D4
#3 D(V&8 VrD   