
    <h                     x    S r SSKJr  SSKJr  SSKJrJrJr  SSK	J
r
JrJr   " S S\S	S
9r " S S\5      rS/rg)z&
Image/Text processor class for ALIGN
    )Union   )
ImageInput)ProcessingKwargsProcessorMixinUnpack)BatchEncodingPreTokenizedInput	TextInputc                   "    \ rS rSrSSSS.0rSrg)AlignProcessorKwargs   text_kwargs
max_length@   )paddingr    N)__name__
__module____qualname____firstlineno__	_defaults__static_attributes__r       b/var/www/html/shao/venv/lib/python3.13/site-packages/transformers/models/align/processing_align.pyr   r      s     	#
Ir   r   F)totalc            
          ^  \ rS rSrSrSS/rSrSrU 4S jr    SS\	S	\
\\\\   \\   4   S
\\   S\4S jjrS rS r\S 5       rSrU =r$ )AlignProcessor$   a  
Constructs an ALIGN processor which wraps [`EfficientNetImageProcessor`] and
[`BertTokenizer`]/[`BertTokenizerFast`] into a single processor that inherits 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                 $   > [         TU ]  X5        g N)super__init__)selfr    r!   	__class__s      r   r(   AlignProcessor.__init__F   s    4r   imagestextkwargsreturnc                 |   Uc  Uc  [        S5      eU R                  " [        4SU R                  R                  0UD6nUb  U R                  " U40 US   D6nUb  U R
                  " U40 US   D6nSUS   ;   a  US   R                  SS5      n	Ub  Ub  WR                  WS'   U$ Ub  W$ [        [        S
0 WD6W	S	9$ )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 docstring 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   )

ValueError_merge_kwargsr   r!   init_kwargsr    popr5   r	   dict)
r)   r,   r-   audiovideosr.   output_kwargsencodingimage_featuresr3   s
             r   __call__AlignProcessor.__call__I   s    L <FNFGG** 
"&.."<"<
 
 ~~dKmM.JKH!11&[M/<Z[N }_==*?;??@PRVWN 2'5'B'BH^$OO d&<^&<.YYr   c                 :    U R                   R                  " U0 UD6$ )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   rE   AlignProcessor.batch_decode   s    
 ~~**D;F;;r   c                 :    U R                   R                  " U0 UD6$ )z
This method forwards all its arguments to BertTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to
the docstring of this method for more information.
)r!   decoderF   s      r   rJ   AlignProcessor.decode   s    
 ~~$$d5f55r   c                     U R                   R                  nU R                  R                  n[        [        R                  X-   5      5      $ r&   )r!   model_input_namesr    listr<   fromkeys)r)   tokenizer_input_namesimage_processor_input_namess      r   rM    AlignProcessor.model_input_names   s<     $ @ @&*&:&:&L&L#DMM"7"UVWWr   r   )NNNN)r   r   r   r   __doc__
attributesimage_processor_classtokenizer_classr(   r   r   r   r
   rN   r   r   r	   rB   rE   rJ   propertyrM   r   __classcell__)r*   s   @r   r   r   $   s    : $[1J8<O5
 "^b?Z?Z I0$y/4HYCZZ[?Z -.?Z 
?ZB<6 X Xr   r   N)rS   typingr   image_utilsr   processing_utilsr   r   r   tokenization_utils_baser	   r
   r   r   r   __all__r   r   r   <module>r^      sH     % H H R R+5 xX^ xXv 
r   