gdZddlmZmZmZddlmZddlmZddl m Z m Z m Z m Z ddlmZmZGdd e d ZGd d e ZdS)z$ Image/Text processor class for GIT )ListOptionalUnion) BatchFeature) ImageInput)ProcessingKwargsProcessorMixinUnpack!_validate_images_text_input_order)PreTokenizedInput TextInputceZdZiZdS)GitProcessorKwargsN)__name__ __module__ __qualname__ _defaultsb/var/www/html/ai-engine/env/lib/python3.11/site-packages/transformers/models/git/processing_git.pyrrsIIIrrF)totalc eZdZdZddgZdZdZfdZ ddee d ee e e e e e e fd eed efd Zd ZdZedZxZS) 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 AutoTokenizercdt|||j|_dS)N)super__init__rcurrent_processor)selfrr __class__s rr!zGitProcessor.__init__1s. )444!%!5rNimagestextkwargsreturnc ||tdt||\}}|jtfd|jji|}i}|)|j|fi|d}|||)|j|fi|d} || t||d dS) 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 doctsring 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`. Nz?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_kwargsr/ text_featuresimage_featuress r__call__zGitProcessor.__call__5sR s rrAzGitProcessor.decodezs %t~$d5f555rc gdS)N) input_idsattention_mask pixel_valuesr)r#s rmodel_input_nameszGitProcessor.model_input_namess>>>>r)NNNN)rrr__doc__ attributesimage_processor_classtokenizer_classr!rrrrr rr rrr;r=rApropertyrF __classcell__)r$s@rrrs  $[1J0%O66666 (,hl <i<i$<iuY(94 ?DQbLccde<i +, <i <i<i<i<i|<<<666??X?????rrN)rGtypingrrrfeature_extraction_utilsr image_utilsrprocessing_utilsr r r r tokenization_utils_baser rrrrrrrRs)(((((((((444444%%%%%%kkkkkkkkkkkkCCCCCCCC)d?d?d?d?d?>d?d?d?d?d?r