rh dZddlmZmZddlmZddlmZmZm Z ddl m Z m Z m Z Gdded ZGd d eZd gZy )z Processor class for Blip. )OptionalUnion) ImageInput)ProcessingKwargsProcessorMixinUnpack) BatchEncodingPreTokenizedInput TextInputc *eZdZdddddddddd idZy)BlipProcessorKwargsTFr) add_special_tokenspaddingstridereturn_overflowing_tokensreturn_special_tokens_maskreturn_offsets_mappingreturn_token_type_ids return_lengthverbose) text_kwargs images_kwargsN)__name__ __module__ __qualname__ _defaults{/var/www/html/ai-insurance-compliance-backend/venv/lib/python3.12/site-packages/transformers/models/blip/processing_blip.pyrrs0#').*/&+%*"   IrrF)totalc eZdZdZddgZdZdZfdZ ddede e e e e e efd eed efd Zd Zd ZedZxZS) 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)BlipImageProcessorBlipImageProcessorFast) BertTokenizerBertTokenizerFastc Vd|_t| |||j|_y)NF)rsuper__init__r$current_processor)selfr$r%kwargs __class__s r r,zBlipProcessor.__init__=s(*/ ' )4!%!5!5rimagestextr/returnc | | tdd}|jtfd|jji|}||j|fi|d}|+|j |fi|d}||j ||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.tokenizer_init_kwargsrr) ValueError _merge_kwargsrr% init_kwargsr$update) r.r1r2audiovideosr/ text_encoding output_kwargsencoding_image_processors r __call__zBlipProcessor.__call__Bs8 >dlIJ J +**  "&.."<"<   *DNN4P=3OPM  ';t';';F'emTcFd'e $((// >+ +rc:|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_decoder.argsr/s r rAzBlipProcessor.batch_decodeus +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. )r%decoderBs r rEzBlipProcessor.decode|s %t~~$$d5f55rc|jj}|jj}ttj ||zS)N)r%model_input_namesr$listdictfromkeys)r.tokenizer_input_namesimage_processor_input_namess r rGzBlipProcessor.model_input_namess? $ @ @&*&:&:&L&L#DMM"7:U"UVWWr)NNNN)rrr__doc__ attributesimage_processor_classtokenizer_classr,rrrstrrHr r r rr r?rArEpropertyrG __classcell__)r0s@r r#r#+s $[1JLrYsH#%HHRR*%"\XN\X~  r