T^(hdZddlmZmZmZddlmZddlmZddl m Z m Z m Z m Z ddlmZmZGdd e d ZGd d e d ZGdde ZdgZy)z) Image/Text processor class for SigLIP2. )ListOptionalUnion) BatchFeature) ImageInput) ImagesKwargsProcessingKwargsProcessorMixinUnpack)PreTokenizedInput TextInputc.eZdZUeeed<eeed<y)Siglip2ImagesKwargsmax_num_patches patch_sizeN)__name__ __module__ __qualname__rint__annotations__l/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/transformers/models/siglip2/processing_siglip2.pyrrsc]" rrF)totalc0eZdZUeed<dddddddd Zy ) Siglip2ProcessorKwargs images_kwargs max_lengthT@)padding truncationr)rr) text_kwargsrN)rrrrr _defaultsrrrrr s,&&$ # Irrc eZdZdZddgZdZdZfdZ ddee e e e e e e fdee e d e e e d fd e ed efd Zd ZdZedZxZS)Siglip2Processora! Constructs a Siglip2 processor which wraps a Siglip2 image processor and a Gemma tokenizer into a single processor. [`Siglip2Processor`] offers all the functionalities of [`Siglip2ImageProcessor`] and [`GemmaTokenizerFast`]. See the [`~Siglip2Processor.__call__`] and [`~Siglip2Processor.decode`] for more information. Args: image_processor ([`Siglip2ImageProcessor`]): The image processor is a required input. tokenizer ([`GemmaTokenizerFast`]): The tokenizer is a required input. image_processor tokenizerAutoImageProcessor AutoTokenizerc&t|||yN)super__init__)selfr)r* __class__s rr0zSiglip2Processor.__init__Cs )4rimagestextr kwargsreturnc L|jtfd|jji|}| | t d||j|fi|d}||j |fi|d}||j |S|S|dd} ttdi| 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 GemmaTokenizerFast's [`~GemmaTokenizerFast.__call__`] if `text` is not `None` to encode the text. To prepare the image(s), this method forwards the `images` argument to Siglip2ImageProcessor's [`~Siglip2ImageProcessor.__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]`, `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). padding (`bool`, `str` or [`~utils.PaddingStrategy`], *optional*, defaults to `max_length`): Select a strategy to pad the returned sequences (according to the model's padding side and padding index) among: - `'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. - `True` or `'longest'`: Pad to the longest sequence in the batch (or no padding if only a single sequence if provided). - `False` or `'do_not_pad'` (default): No padding (i.e., can output a batch with sequences of different lengths). max_length (`int`, *optional*, defaults to 64): Maximum length of the returned list and optionally padding length (see above). truncation (`bool`, *optional*, defaults to `True`): Activates truncation to cut input sequences longer than `max_length` to `max_length`. return_tensors (`str` or [`~utils.TensorType`], *optional*, defaults to `'pt'`): 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`. - **pixel_attention_mask** -- Attention mask for the pixel values. Returned when `images` is not `None`. - **spatial_shapes** -- The number of horizontal and vertical patches per image. Returned when `images` is not `None`. tokenizer_init_kwargsz?You have to specify either text or images. Both cannot be none.r%r common_kwargsreturn_tensors)data tensor_typer) _merge_kwargsrr* init_kwargs ValueErrorr)updaterdict) r1r3r4audiovideosr5 output_kwargsencodingimage_featuresr:s r__call__zSiglip2Processor.__call__Fsp+** " "&.."<"<  r`sY)(4%VVC,e -U  xX~xXv  r