a h@svdZddlmZmZddlmZddlmZmZm Z ddl m Z m Z m Z Gddded d ZGd d d eZd gZd S)z Processor class for Blip. )OptionalUnion) ImageInput)ProcessingKwargsProcessorMixinUnpack) BatchEncodingPreTokenizedInput TextInputc @s*eZdZdddddddddd idZdS)BlipProcessorKwargsTFr) Zadd_special_tokenspaddingZstrideZreturn_overflowing_tokensZreturn_special_tokens_maskZreturn_offsets_mappingreturn_token_type_idsZ return_lengthverbose) text_kwargs images_kwargsN)__name__ __module__ __qualname__ _defaultsrrd/var/www/html/assistant/venv/lib/python3.9/site-packages/transformers/models/blip/processing_blip.pyr s r F)totalcsjeZdZdZddgZdZdZfddZdee e e e e e efeeed d d Zed d ZZS) BlipProcessora] Constructs a BLIP processor which wraps a BERT tokenizer and BLIP image processor into a single processor. [`BlipProcessor`] offers all the functionalities of [`BlipImageProcessor`] and [`BertTokenizerFast`]. See the docstring of [`~BlipProcessor.__call__`] and [`~BlipProcessor.decode`] for more information. Args: image_processor (`BlipImageProcessor`): An instance of [`BlipImageProcessor`]. The image processor is a required input. tokenizer (`BertTokenizerFast`): An instance of ['BertTokenizerFast`]. The tokenizer is a required input. image_processor tokenizer)ZBlipImageProcessorZBlipImageProcessorFast)Z BertTokenizerZBertTokenizerFastc s d|_t|||j|_dS)NF)rsuper__init__rZcurrent_processor)selfrrkwargs __class__rrr=szBlipProcessor.__init__N)imagestextrreturnc Ks|dur|durtdd}|jtfd|jji|}|durT|j|fi|d}|dur|j|fi|d}|dur|||S|S)ae This method uses [`BlipImageProcessor.__call__`] method to prepare image(s) for the model, and [`BertTokenizerFast.__call__`] to prepare text for the model. 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. Nz*You have to specify either images or text.Ztokenizer_init_kwargsrr) ValueErrorZ _merge_kwargsr rZ init_kwargsrupdate) rr"r#ZaudioZvideosrZ text_encodingZ output_kwargsZencoding_image_processorrrr__call__Bs$ zBlipProcessor.__call__cCs&|jj}|jj}dd|D}||S)NcSsg|]}|dkr|qS)Ztoken_type_idsr).0namerrr yz3BlipProcessor.model_input_names..)rmodel_input_namesr)rZtokenizer_input_namesZimage_processor_input_namesrrrr,uszBlipProcessor.model_input_names)NNNN)rrr__doc__ attributesZimage_processor_classZtokenizer_classrrrrstrlistr r rr r r'propertyr, __classcell__rrr rr+s"   3rN)r-typingrrZ image_utilsrZprocessing_utilsrrrZtokenization_utils_baser r r r r__all__rrrrs R