U ,-e/@s`dZddlmZmZmZddlmZddlmZm Z m Z m Z m Z ddl mZGdddeZd S) z! Processor class for Pix2Struct. )ListOptionalUnion)ProcessorMixin) BatchEncodingPaddingStrategyPreTokenizedInput TextInputTruncationStrategy) TensorTypecseZdZdZddgZdZdZfddZdee e e e e e fe ee e efee e efeeeeeeeee e e e e e e eee efed ddZddZddZeddZZS)Pix2StructProcessora Constructs a PIX2STRUCT processor which wraps a BERT tokenizer and PIX2STRUCT image processor into a single processor. [`Pix2StructProcessor`] offers all the functionalities of [`Pix2StructImageProcessor`] and [`T5TokenizerFast`]. See the docstring of [`~Pix2StructProcessor.__call__`] and [`~Pix2StructProcessor.decode`] for more information. Args: image_processor (`Pix2StructImageProcessor`): An instance of [`Pix2StructImageProcessor`]. The image processor is a required input. tokenizer (Union[`T5TokenizerFast`, `T5Tokenizer`]): An instance of ['T5TokenizerFast`] or ['T5Tokenizer`]. The tokenizer is a required input. image_processor tokenizerZPix2StructImageProcessor)Z T5TokenizerZT5TokenizerFastcsd|_t||dS)NF)return_token_type_idssuper__init__)selfrr __class__u/var/www/html/Darija-Ai-Train/env/lib/python3.8/site-packages/transformers/models/pix2struct/processing_pix2struct.pyr,szPix2StructProcessor.__init__NTFr)textadd_special_tokenspadding truncation max_length max_patchesstridepad_to_multiple_ofreturn_attention_maskreturn_overflowing_tokensreturn_special_tokens_maskreturn_offsets_mappingr return_lengthverbosereturn_tensorsreturncKs0|dkr|dkrtd|dkrd|jjsd|j|_|jf||||||| | | | | ||||d|}|S|jjs|j|f||d|}n|j|f|||d|}|dk r|jjs|jf||||||| | | | | ||||d|}d|kr|d|d<d|kr|d|d <nd}|dk r,|||S) a This method uses [`Pix2StructImageProcessor.preprocess`] method to prepare image(s) for the model, and [`T5TokenizerFast.__call__`] to prepare text for the model. Please refer to the docstring of the above two methods for more information. Nz*You have to specify either images or text.)rrrrrrr r!r"r#r$rr%r&r')r'r)r'rZ header_textZattention_maskZdecoder_attention_maskZ input_idsZdecoder_input_ids) ValueErrorrZis_vqarZcurrent_processorpopupdate)rZimagesrrrrrrrr r!r"r#r$rr%r&r'kwargsZ text_encodingZencoding_image_processorrrr__call__0s   zPix2StructProcessor.__call__cOs|jj||S)z This method forwards all its arguments to Pix2StructTokenizerFast's [`~PreTrainedTokenizer.batch_decode`]. Please refer to the docstring of this method for more information. )r batch_decoderargsr,rrrr.sz Pix2StructProcessor.batch_decodecOs|jj||S)z This method forwards all its arguments to Pix2StructTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of this method for more information. )rdecoder/rrrr1szPix2StructProcessor.decodecCs"|jj}|jj}tt||S)N)rmodel_input_namesrlistdictfromkeys)rZtokenizer_input_namesZimage_processor_input_namesrrrr2sz%Pix2StructProcessor.model_input_names)NNTFNNrrNNFFFFFTN)__name__ __module__ __qualname____doc__ attributesZimage_processor_classZtokenizer_classrrr r rboolstrrr rintr rr-r.r1propertyr2 __classcell__rrrrr sZ     `r N)r9typingrrrZprocessing_utilsrZtokenization_utils_baserrr r r utilsr r rrrrs