a  d@s`dZddlmZmZmZddlmZddlmZm Z m Z m Z m Z ddl mZGdddeZd S) z Processor class for LayoutXLM. )ListOptionalUnion)ProcessorMixin) BatchEncodingPaddingStrategyPreTokenizedInput TextInputTruncationStrategy) TensorTypec@seZdZdZdZdZdeeee ee efe eee efee e e e e e e fe ee e e e e fe ee e efee e efe e e e e e e e e e e e e e e ee efedd d Zd d Zd dZddZeddZdS)LayoutXLMProcessorab Constructs a LayoutXLM processor which combines a LayoutXLM feature extractor and a LayoutXLM tokenizer into a single processor. [`LayoutXLMProcessor`] offers all the functionalities you need to prepare data for the model. It first uses [`LayoutLMv2FeatureExtractor`] to resize document images to a fixed size, and optionally applies OCR to get words and normalized bounding boxes. These are then provided to [`LayoutXLMTokenizer`] or [`LayoutXLMTokenizerFast`], which turns the words and bounding boxes into token-level `input_ids`, `attention_mask`, `token_type_ids`, `bbox`. Optionally, one can provide integer `word_labels`, which are turned into token-level `labels` for token classification tasks (such as FUNSD, CORD). Args: feature_extractor (`LayoutLMv2FeatureExtractor`): An instance of [`LayoutLMv2FeatureExtractor`]. The feature extractor is a required input. tokenizer (`LayoutXLMTokenizer` or `LayoutXLMTokenizerFast`): An instance of [`LayoutXLMTokenizer`] or [`LayoutXLMTokenizerFast`]. The tokenizer is a required input. ZLayoutLMv2FeatureExtractor)ZLayoutXLMTokenizerZLayoutXLMTokenizerFastNTFr)text 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|durtd|jjr0|dur0td|durH|durHtd|j||d}|dur|jjr|durt|tr~|g}|d}|jf|dur|n|d|dur|nd|dur|n|d ||||| | | | | ||||||d |}|d }|dur |||d }||d <|S)a This method first forwards the `images` argument to [`~LayoutLMv2FeatureExtractor.__call__`]. In case [`LayoutLMv2FeatureExtractor`] was initialized with `apply_ocr` set to `True`, it passes the obtained words and bounding boxes along with the additional arguments to [`~LayoutXLMTokenizer.__call__`] and returns the output, together with resized `images`. In case [`LayoutLMv2FeatureExtractor`] was initialized with `apply_ocr` set to `False`, it passes the words (`text`/``text_pair`) and `boxes` specified by the user along with the additional arguments to [`~LayoutXLMTokenizer.__call__`] and returns the output, together with resized `images``. Please refer to the docstring of the above two methods for more information. NzfYou cannot provide bounding boxes if you initialized the feature extractor with apply_ocr set to True.zcYou cannot provide word labels if you initialized the feature extractor with apply_ocr set to True.TFzKYou cannot return overflowing tokens without returning the offsets mapping.)imagesrwordsr)rrrrrrrrrrrrrrrrrrZ pixel_valuesoverflow_to_sample_mappingimage)Zfeature_extractorZ apply_ocr ValueError isinstancestr tokenizerpopget_overflowing_images)selfr!rrrrrrrrrrrrrrrrrrkwargsfeaturesZencoded_inputsr.{/var/www/html/stable-diffusion-webui/venv/lib/python3.9/site-packages/transformers/models/layoutxlm/processing_layoutxlm.py__call__/sT"   zLayoutXLMProcessor.__call__cCsLg}|D]}|||qt|t|krHtdt|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#Zimages_with_overflowZ sample_idxr.r.r/r*sz)LayoutXLMProcessor.get_overflowing_imagescOs|jj|i|S)z This method forwards all its arguments to PreTrainedTokenizer's [`~PreTrainedTokenizer.batch_decode`]. Please refer to the docstring of this method for more information. )r( batch_decoder+argsr,r.r.r/r3szLayoutXLMProcessor.batch_decodecOs|jj|i|S)z This method forwards all its arguments to PreTrainedTokenizer's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of this method for more information. )r(decoder4r.r.r/r6szLayoutXLMProcessor.decodecCsgdS)N)Z input_idsZbboxZattention_maskr$r.)r+r.r.r/model_input_namessz$LayoutXLMProcessor.model_input_names)NNNNTFNNrNNNFFFFTN)__name__ __module__ __qualname____doc__Zfeature_extractor_classZtokenizer_classrr r rrintboolr'rr r rr0r*r3r6propertyr7r.r.r.r/r s^   Wr N)r;typingrrrZprocessing_utilsrZtokenization_utils_baserrr r r utilsr r r.r.r.r/s