S^(hKdZddlmZmZmZddlmZddlmZddl m Z m Z m Z m Z ddlmZmZddlmZGd d e d Zej(eZGd de ZdgZy)z$ Image/Text processor class for GIT )ListOptionalUnion) BatchFeature) ImageInput)ProcessingKwargsProcessorMixinUnpack!_validate_images_text_input_order)PreTokenizedInput TextInput)loggingceZdZiZy)GitProcessorKwargsN)__name__ __module__ __qualname__ _defaultsd/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/transformers/models/git/processing_git.pyrrsIrrF)totalc eZdZdZddgZdZdZfdZ ddee dee e e e e e e fd eed efd Zd Zd ZedZxZS) GitProcessora Constructs a GIT processor which wraps a CLIP image processor and a BERT tokenizer into a single processor. [`GitProcessor`] offers all the functionalities of [`CLIPImageProcessor`] and [`BertTokenizerFast`]. See the [`~GitProcessor.__call__`] and [`~GitProcessor.decode`] for more information. Args: image_processor ([`AutoImageProcessor`]): The image processor is a required input. tokenizer ([`AutoTokenizer`]): The tokenizer is a required input. image_processor tokenizerAutoImageProcessor AutoTokenizercHt||||j|_y)N)super__init__rcurrent_processor)selfrr __class__s rr"zGitProcessor.__init__5s  )4!%!5!5rimagestextkwargsreturnc ~| | tdt||\}}|jtfd|jj i|}i}|'|j|fi|d}|j ||'|j|fi|d} |j | t||djdS)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 BertTokenizerFast's [`~BertTokenizerFast.__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 (`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 (`TextInput`, `PreTokenizedInput`, `List[TextInput]`, `List[PreTokenizedInput]`, *optional*): 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: [`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.tokenizer_init_kwargs text_kwargs images_kwargs common_kwargsreturn_tensors)data tensor_type) ValueErrorr _merge_kwargsrr init_kwargsupdaterrget) r$r&r'audiovideosr( output_kwargsr0 text_featuresimage_featuress r__call__zGitProcessor.__call__9sR zGitProcessor.batch_decodexs +t~~**D;F;;rc:|jj|i|S)z This method forwards all its arguments to BertTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of this method for more information. )rdecoder?s rrBzGitProcessor.decodes %t~~$$d5f55rc gdS)N) input_idsattention_mask pixel_valuesr)r$s rmodel_input_nameszGitProcessor.model_input_namess>>r)NNNN)rrr__doc__ attributesimage_processor_classtokenizer_classr"rrrrr rr rrr<r>rBpropertyrG __classcell__)r%s@rrr#s $[1J0%O6 (,hl =i$=iuY(94 ?DQbLccde=i +, =i =i~<6??rrN)rHtypingrrrfeature_extraction_utilsr image_utilsrprocessing_utilsr r r r tokenization_utils_baser rutilsrr get_loggerrloggerr__all__rrrrWs`)(4%kkC)   H %e?>e?P  r