sgzdZddlmZmZmZddlmZddlmZddl m Z ddl m Z m Z mZmZddlmZGd d e Zy ) z( Image/Text processor class for SigLIP. )ListOptionalUnion) BatchFeature) ImageInput)ProcessorMixin)PaddingStrategyPreTokenizedInput TextInputTruncationStrategy) TensorTypeceZdZdZddgZdZdZfdZdddddejfd e e e e e e e fd ed e eeefd e eeefd edee eefdefdZdZdZedZxZS)SiglipProcessora Constructs a Siglip processor which wraps a Siglip image processor and a Siglip tokenizer into a single processor. [`SiglipProcessor`] offers all the functionalities of [`SiglipImageProcessor`] and [`SiglipTokenizer`]. See the [`~SiglipProcessor.__call__`] and [`~SiglipProcessor.decode`] for more information. Args: image_processor ([`SiglipImageProcessor`]): The image processor is a required input. tokenizer ([`SiglipTokenizer`]): The tokenizer is a required input. image_processor tokenizerSiglipImageProcessorSiglipTokenizerc&t|||yN)super__init__)selfrr __class__s _/var/www/html/venv/lib/python3.12/site-packages/transformers/models/siglip/processing_siglip.pyrzSiglipProcessor.__init__.s )4NFtextimagespadding truncation max_lengthreturn_tensorsreturnc| | td||j|||||}||j||}||jd<|S|St t di|S)a Main method to prepare for the model one or several sequences(s) and image(s). This method forwards the `text` and `kwargs` arguments to SiglipTokenizer's [`~SiglipTokenizer.__call__`] if `text` is not `None` to encode the text. To prepare the image(s), this method forwards the `images` argument to SiglipImageProcessor's [`~SiglipImageProcessor.__call__`] if `images` is not `None`. Please refer to the doctsring of the above two methods for more information. Args: text (`str`, `List[str]`, `List[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. Both channels-first and channels-last formats are supported. padding (`bool`, `str` or [`~utils.PaddingStrategy`], *optional*, defaults to `False`): Select a strategy to pad the returned sequences (according to the model's padding side and padding index) among: - `True` or `'longest'`: Pad to the longest sequence in the batch (or no padding if only a single sequence if provided). - `'max_length'`: Pad to a maximum length specified with the argument `max_length` or to the maximum acceptable input length for the model if that argument is not provided. - `False` or `'do_not_pad'` (default): No padding (i.e., can output a batch with sequences of different lengths). max_length (`int`, *optional*): Maximum length of the returned list and optionally padding length (see above). truncation (`bool`, *optional*): Activates truncation to cut input sequences longer than `max_length` to `max_length`. 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: [`BatchFeature`]: A [`BatchFeature`] 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`. z?You have to specify either text or images. Both cannot be none.)r"rr r!)r" pixel_values)data tensor_type) ValueErrorrrr%rdict) rrrrr r!r"encodingimage_featuress r__call__zSiglipProcessor.__call__1sn typingrrrfeature_extraction_utilsr image_utilsrprocessing_utilsr tokenization_utils_baser r r r utilsrrr(rrrNs4)(4%.hhrXnrXr