`idZddlmZmZddlmZddlmZmZm Z ddl m Z m Z m Z Gdded ZGd d eZd gZd S)z Processor class for Blip. )OptionalUnion) ImageInput)ProcessingKwargsProcessorMixinUnpack) BatchEncodingPreTokenizedInput TextInputc ,eZdZdddddddddd idZdS)BlipProcessorKwargsTFr) add_special_tokenspaddingstridereturn_overflowing_tokensreturn_special_tokens_maskreturn_offsets_mappingreturn_token_type_ids return_lengthverbose) text_kwargs images_kwargsN)__name__ __module__ __qualname__ _defaults|/home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/blip/processing_blip.pyrrsF#').*/&+%*"     IIIrrF)totalc eZdZdZddgZdZdZfdZ ddee d ee e e e e efd eed efd Zed ZxZS) 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 rd|_t|||j|_dS)NF)rsuper__init__r$current_processor)selfr$r%kwargs __class__s r r,zBlipProcessor.__init__=s6*/ ' )444!%!5rNimagestextr/returnc ||tdd}|jtfd|jji|}||j|fi|d}|-|j|fi|d}||||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 >dlIJJ J +*   "&."<    *DN4PP=3OPPM  ';t';F'e'emTcFd'e'e $((// >>>+ +rcT|jj}|jj}d|D}||zS)Ncg|] }|dk| S)token_type_idsr).0names r z3BlipProcessor.model_input_names..ys# d d d$4ScKcKcKcKcKcr)r%model_input_namesr$)r.tokenizer_input_namesimage_processor_input_namess r rFzBlipProcessor.model_input_namesus: $ @&*&:&L# d d2G d d d$'BBBr)NNNN)rrr__doc__ attributesimage_processor_classtokenizer_classr,rrrstrlistr r r rr r?propertyrF __classcell__)r0s@r r#r#+s  $[1JLrVs#"""""""%%%%%%HHHHHHHHHHRRRRRRRRRR*%"OCOCOCOCOCNOCOCOCd  r