o ei@sZdZddlmZddlmZmZmZmZmZddl m Z m Z e GdddeZ dgZ dS)z! Processor class for LayoutLMv2. )ProcessorMixin) BatchEncodingPaddingStrategyPreTokenizedInput TextInputTruncationStrategy) TensorTypeauto_docstringc(s*eZdZd fdd Ze                  d!deeBeeBeeBdeeeBdBd eeeeeeeBdBd eeeeeBdBd e d e e Be Bd e e Be BdedBdededBde dBde dBde de de de de de e BdBdef&ddZddZeddZZS)"LayoutLMv2ProcessorNc st||dS)N)super__init__)selfimage_processor tokenizerkwargs __class__r/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/layoutlmv2/processing_layoutlmv2.pyr szLayoutLMv2Processor.__init__TFtext text_pairboxes word_labelsadd_special_tokenspadding truncation max_lengthstridepad_to_multiple_ofreturn_token_type_idsreturn_attention_maskreturn_overflowing_tokensreturn_special_tokens_maskreturn_offsets_mapping return_lengthverbosereturn_tensorsreturncKs\|jjr |dur td|jjr|durtd|dur$|dur$td|j||d}|durC|jjrC|durCt|tr?|g}|d}|jdid|durN|n|dd |durY|ndd |durb|n|d d |d |d |d|d| d| d| d| d| d|d|d|d|d|d||}|d}|dur|||d}||d<|S)NzdYou cannot provide bounding boxes if you initialized the image processor with apply_ocr set to True.zaYou cannot provide word labels if you initialized the image processor with apply_ocr set to True.TFzKYou cannot return overflowing tokens without returning the offsets mapping.)imagesr'wordsrrrrrrrrrrr r!r"r#r$r%r&r' pixel_valuesoverflow_to_sample_mappingimager)r apply_ocr ValueError isinstancestrrpopget_overflowing_images)r r)rrrrrrrrrrr r!r"r#r$r%r&r'rfeaturesencoded_inputsrrr__call__sz        zLayoutLMv2Processor.__call__cCsLg}|D] }|||qt|t|kr$tdt|dt||S)Nz`Expected length of images to be the same as the length of `overflow_to_sample_mapping`, but got z and )appendlenr/)r r)r,images_with_overflow sample_idxrrrr3isz*LayoutLMv2Processor.get_overflowing_imagescCsgdS)N) input_idsbboxtoken_type_idsattention_maskr-r)r rrrmodel_input_nameswsz%LayoutLMv2Processor.model_input_names)NN)NNNNTFFNrNNNFFFFTN)__name__ __module__ __qualname__r r rrlistintboolr1rrrrr6r3propertyr? __classcell__rrrrr s~        Lr N)__doc__processing_utilsrtokenization_utils_baserrrrrutilsrr r __all__rrrrs  d