o ZhK@sdZddlmZmZmZddlmZddlmZddl m Z m Z m Z m Z ddlmZmZddlmZGd d d e d d ZeeZGd dde ZdgZdS)z$ Image/Text processor class for GIT )ListOptionalUnion) BatchFeature) ImageInput)ProcessingKwargsProcessorMixinUnpack!_validate_images_text_input_order)PreTokenizedInput TextInput)loggingc@seZdZiZdS)GitProcessorKwargsN)__name__ __module__ __qualname__ _defaultsrrU/var/www/auris/lib/python3.10/site-packages/transformers/models/git/processing_git.pyrsrF)totalc seZdZdZddgZdZdZfddZ    dd ee d ee e e e e e e fd eed efd dZddZddZeddZZS) 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 tokenizerZAutoImageProcessorZ AutoTokenizercst|||j|_dS)N)super__init__rZcurrent_processor)selfrr __class__rrr5s zGitProcessor.__init__Nimagestextkwargsreturnc Ks|dur |dur tdt||\}}|jtfd|jji|}i}|dur6|j|fi|d}|||durJ|j|fi|d} || t||d ddS) 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`. Nz?You have to specify either text or images. Both cannot be none.Ztokenizer_init_kwargsZ text_kwargsZ images_kwargsZ common_kwargsZreturn_tensors)dataZ tensor_type) ValueErrorr Z _merge_kwargsrrZ init_kwargsupdaterrget) rrr ZaudioZvideosr!Z output_kwargsr#Z text_featuresZimage_featuresrrr__call__9s$)  zGitProcessor.__call__cO|jj|i|S)z This method forwards all its arguments to BertTokenizerFast's [`~PreTrainedTokenizer.batch_decode`]. Please refer to the docstring of this method for more information. )r batch_decoderargsr!rrrr)xzGitProcessor.batch_decodecOr()z This method forwards all its arguments to BertTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of this method for more information. )rdecoder*rrrr-r,zGitProcessor.decodecCsgdS)N)Z input_idsZattention_maskZ pixel_valuesr)rrrrmodel_input_namesszGitProcessor.model_input_names)NNNN)rrr__doc__ attributesZimage_processor_classZtokenizer_classrrrrr r rr rrr'r)r-propertyr. __classcell__rrrrr#s.   ?rN)r/typingrrrZfeature_extraction_utilsrZ image_utilsrZprocessing_utilsrr r r Ztokenization_utils_baser r utilsrrZ get_loggerrloggerr__all__rrrrs     h