o hH@s0dZddlmZddlmZGdddeZdS)z& Image/Text processor class for ALIGN )ProcessorMixin) BatchEncodingcsVeZdZdZddgZdZdZfddZdd d Zd dZ ddZ e ddZ Z S)AlignProcessora( 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. Args: image_processor ([`EfficientNetImageProcessor`]): The image processor is a required input. tokenizer ([`BertTokenizer`, `BertTokenizerFast`]): The tokenizer is a required input. image_processor tokenizerEfficientNetImageProcessor) BertTokenizerBertTokenizerFastcst||dSN)super__init__)selfrr __class__`/var/www/html/ai/venv/lib/python3.10/site-packages/transformers/models/align/processing_align.pyr *szAlignProcessor.__init__N max_length@c Ks|dur |dur td|dur|j|f|||d|}|dur,|j|fd|i|}|dur;|dur;|j|d<|S|durA|Sttdi||dS)a Main method to prepare text(s) and image(s) to be fed as input to the model. This method forwards the `text` and `kwargs` 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` and `kwargs` 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: 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). 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. In case of a NumPy array/PyTorch tensor, each image should be of shape (C, H, W), where C is a number of channels, H and W are image height and width. padding (`bool`, `str` or [`~utils.PaddingStrategy`], *optional*, defaults to `max_length`): Activates and controls padding for tokenization of input text. Choose between [`True` or `'longest'`, `'max_length'`, `False` or `'do_not_pad'`] max_length (`int`, *optional*, defaults to `max_length`): Maximum padding value to use to pad the input text during tokenization. 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 have to specify either text or images. Both cannot be none.)paddingrreturn_tensorsr pixel_values)data tensor_typer) ValueErrorrrrrdict) r textimagesrrrkwargsencodingimage_featuresrrr__call__-s$( zAlignProcessor.__call__cO|jj|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_decoder argsrrrrr"hzAlignProcessor.batch_decodecOr!)z This method forwards all its arguments to BertTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of this method for more information. )rdecoder#rrrr&or%zAlignProcessor.decodecCs"|jj}|jj}tt||Sr )rmodel_input_namesrlistrfromkeys)r tokenizer_input_namesimage_processor_input_namesrrrr'vsz AlignProcessor.model_input_names)NNrrN)__name__ __module__ __qualname____doc__ attributesimage_processor_classtokenizer_classr r r"r&propertyr' __classcell__rrrrrs   ;rN)r/processing_utilsrtokenization_utils_baserrrrrrs