
    sg                         d Z ddlmZmZ ddlmZ ddlmZmZm	Z	m
Z
 ddlmZmZmZ  G d ded	
      Z G d de      ZdgZy)z&
Image/Text processor class for ALIGN
    )ListUnion   )
ImageInput)ProcessingKwargsProcessorMixinUnpack!_validate_images_text_input_order)BatchEncodingPreTokenizedInput	TextInputc                       e Zd ZddddiZy)AlignProcessorKwargstext_kwargs
max_length@   )paddingr   N)__name__
__module____qualname__	_defaults     ]/var/www/html/venv/lib/python3.12/site-packages/transformers/models/align/processing_align.pyr   r      s     	#
Ir   r   F)totalc            
            e Zd ZdZddgZdZdZ fdZ	 	 	 	 ddede	e
eee
   ee   f   d	ee   d
efdZd Zd Zed        Z xZS )AlignProcessoray  
    Constructs an ALIGN processor which wraps [`EfficientNetImageProcessor`] and
    [`BertTokenizer`]/[`BertTokenizerFast`] into a single processor that interits both the image processor and
    tokenizer functionalities. See the [`~AlignProcessor.__call__`] and [`~OwlViTProcessor.decode`] for more
    information.
    The preferred way of passing kwargs is as a dictionary per modality, see usage example below.
        ```python
        from transformers import AlignProcessor
        from PIL import Image
        model_id = "kakaobrain/align-base"
        processor = AlignProcessor.from_pretrained(model_id)

        processor(
            images=your_pil_image,
            text=["What is that?"],
            images_kwargs = {"crop_size": {"height": 224, "width": 224}},
            text_kwargs = {"padding": "do_not_pad"},
            common_kwargs = {"return_tensors": "pt"},
        )
        ```

    Args:
        image_processor ([`EfficientNetImageProcessor`]):
            The image processor is a required input.
        tokenizer ([`BertTokenizer`, `BertTokenizerFast`]):
            The tokenizer is a required input.

    image_processor	tokenizerEfficientNetImageProcessor)BertTokenizerBertTokenizerFastc                 &    t         |   ||       y N)super__init__)selfr   r   	__class__s      r   r&   zAlignProcessor.__init__F   s    )4r   imagestextkwargsreturnc                    ||t        d      t        ||      \  }} | j                  t        fd| j                  j
                  i|}| | j                  |fi |d   }| | j                  |fi |d   }d|d   v r|d   j                  dd      }	||j                  d<   |S |S t        t        d
i 		      S )a  
        Main method to prepare text(s) and image(s) to be fed as input to the model. This method forwards the `text`
        arguments to BertTokenizerFast's [`~BertTokenizerFast.__call__`] if `text` is not `None` to encode
        the text. To prepare the image(s), this method forwards the `images` arguments to
        EfficientNetImageProcessor's [`~EfficientNetImageProcessor.__call__`] if `images` is not `None`. Please refer
        to the doctsring of the above two methods for more information.

        Args:
            images (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`, `List[PIL.Image.Image]`, `List[np.ndarray]`, `List[torch.Tensor]`):
                The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch
                tensor. Both channels-first and channels-last formats are supported.
            text (`str`, `List[str]`):
                The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings
                (pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set
                `is_split_into_words=True` (to lift the ambiguity with a batch of sequences).
            return_tensors (`str` or [`~utils.TensorType`], *optional*):
                If set, will return tensors of a particular framework. Acceptable values are:
                    - `'tf'`: Return TensorFlow `tf.constant` objects.
                    - `'pt'`: Return PyTorch `torch.Tensor` objects.
                    - `'np'`: Return NumPy `np.ndarray` objects.
                    - `'jax'`: Return JAX `jnp.ndarray` objects.
        Returns:
            [`BatchEncoding`]: A [`BatchEncoding`] with the following fields:

            - **input_ids** -- List of token ids to be fed to a model. Returned when `text` is not `None`.
            - **attention_mask** -- List of indices specifying which tokens should be attended to by the model (when
              `return_attention_mask=True` or if *"attention_mask"* is in `self.model_input_names` and if `text` is not
              `None`).
            - **pixel_values** -- Pixel values to be fed to a model. Returned when `images` is not `None`.
        Nz'You must specify either text or images.tokenizer_init_kwargsr   images_kwargsreturn_tensorscommon_kwargspixel_values)datatensor_typer   )
ValueErrorr
   _merge_kwargsr   r   init_kwargsr   popr2   r   dict)
r'   r)   r*   audiovideosr+   output_kwargsencodingimage_featuresr0   s
             r   __call__zAlignProcessor.__call__I   s   L <FNFGG8F*** 
"&.."<"<
 
 %t~~dKmM.JKH1T11&[M/<Z[N }_==*?;??@PRVWN 2'5'B'BH^$OO d&<^&<.YYr   c                 :     | j                   j                  |i |S )z
        This method forwards all its arguments to BertTokenizerFast's [`~PreTrainedTokenizer.batch_decode`]. Please
        refer to the docstring of this method for more information.
        )r   batch_decoder'   argsr+   s      r   rA   zAlignProcessor.batch_decode   s     
 +t~~**D;F;;r   c                 :     | j                   j                  |i |S )z
        This method forwards all its arguments to BertTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to
        the docstring of this method for more information.
        )r   decoderB   s      r   rE   zAlignProcessor.decode   s     
 %t~~$$d5f55r   c                     | j                   j                  }| j                  j                  }t        t        j                  ||z               S r$   )r   model_input_namesr   listr9   fromkeys)r'   tokenizer_input_namesimage_processor_input_namess      r   rG   z AlignProcessor.model_input_names   s?     $ @ @&*&:&:&L&L#DMM"7:U"UVWWr   )NNNN)r   r   r   __doc__
attributesimage_processor_classtokenizer_classr&   r   r   r   r   r   r	   r   r   r?   rA   rE   propertyrG   __classcell__)r(   s   @r   r   r   $   s    : $[1J8<O5
 "^bAZAZ I0$y/4HYCZZ[AZ -.AZ 
AZF<6 X Xr   r   N)rL   typingr   r   image_utilsr   processing_utilsr   r   r	   r
   tokenization_utils_baser   r   r   r   r   __all__r   r   r   <module>rW      sH     % k k R R+5 zX^ zXz 
r   