S^(hdZddlmZmZddlmZddlmZmZm Z ddl m Z m Z m Z ddlmZGdd ed ZGd d eZd gZy)z( Image/Text processor class for AltCLIP )ListUnion) ImageInput)ProcessingKwargsProcessorMixinUnpack) BatchEncodingPreTokenizedInput TextInput)deprecate_kwargceZdZiZy)AltClipProcessorKwargsN)__name__ __module__ __qualname__ _defaultsl/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/transformers/models/altclip/processing_altclip.pyrrsIrrF)totalc eZdZdZddgZdZdZeddddfd Z dd e d e e e e e e e fd eed efdZdZdZedZxZS)AltCLIPProcessoraD Constructs a AltCLIP processor which wraps a CLIP image processor and a XLM-Roberta tokenizer into a single processor. [`AltCLIPProcessor`] offers all the functionalities of [`CLIPImageProcessor`] and [`XLMRobertaTokenizerFast`]. See the [`~AltCLIPProcessor.__call__`] and [`~AltCLIPProcessor.decode`] for more information. Args: image_processor ([`CLIPImageProcessor`], *optional*): The image processor is a required input. tokenizer ([`XLMRobertaTokenizerFast`], *optional*): The tokenizer is a required input. image_processor tokenizer)CLIPImageProcessorCLIPImageProcessorFast)XLMRobertaTokenizerXLMRobertaTokenizerFastfeature_extractorz5.0.0)old_nameversionnew_namecZ| td| tdt| ||y)Nz)You need to specify an `image_processor`.z"You need to specify a `tokenizer`.) ValueErrorsuper__init__)selfrr __class__s rr'zAltCLIPProcessor.__init__2s6  "HI I  AB B )4rimagestextkwargsreturnc | | td| | td|jtfd|jji|}||j|fi|d}||j |fi|d}d|dvr|dj dd} ||jd<|S|Sttd i 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 XLMRobertaTokenizerFast's [`~XLMRobertaTokenizerFast.__call__`] if `text` is not `None` to encode the text. To prepare the image(s), this method forwards the `images` and `kwrags` arguments to CLIPImageProcessor's [`~CLIPImageProcessor.__call__`] if `images` is not `None`. Please refer to the docstring of the above two methods for more information. Args: images (`ImageInput`): 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 (`TextInput`, `PreTokenizedInput`, `List[TextInput]`, `List[PreTokenizedInput]`): 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_kwargs text_kwargs images_kwargsreturn_tensors common_kwargs pixel_values)data tensor_typer) r% _merge_kwargsrr init_kwargsrpopr4r dict) r(r*r+audiovideosr, output_kwargsencodingimage_featuresr2s r__call__zAltCLIPProcessor.__call__;s P rYsK%HHRR0-UrX~rXj  r