a h!@sjdZddlZddlmZmZddlmZddlmZm Z m Z m Z m Z ddl mZGdd d eZd gZdS) z Processor class for LayoutXLM. N)OptionalUnion)ProcessorMixin) BatchEncodingPaddingStrategyPreTokenizedInput TextInputTruncationStrategy) TensorTypecseZdZdZddgZdZdZdfdd Zdee e e e e e fe ee e e fe ee e e e e e e fe ee e e e e feeeeefeeeefe e e e e e ee eeeeeee eeefed d dZddZeddZeddZeddZZS)LayoutXLMProcessoran Constructs a LayoutXLM processor which combines a LayoutXLM image processor and a LayoutXLM tokenizer into a single processor. [`LayoutXLMProcessor`] offers all the functionalities you need to prepare data for the model. It first uses [`LayoutLMv2ImageProcessor`] 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: image_processor (`LayoutLMv2ImageProcessor`, *optional*): An instance of [`LayoutLMv2ImageProcessor`]. The image processor is a required input. tokenizer (`LayoutXLMTokenizer` or `LayoutXLMTokenizerFast`, *optional*): An instance of [`LayoutXLMTokenizer`] or [`LayoutXLMTokenizerFast`]. The tokenizer is a required input. image_processor tokenizerZLayoutLMv2ImageProcessor)ZLayoutXLMTokenizerZLayoutXLMTokenizerFastNc s`d|vrtdt|d}|dur*|n|}|dur>td|durNtdt||dS)Nfeature_extractorzhThe `feature_extractor` argument is deprecated and will be removed in v5, use `image_processor` instead.z)You need to specify an `image_processor`.z"You need to specify a `tokenizer`.)warningswarn FutureWarningpop ValueErrorsuper__init__)selfr rkwargsr __class__n/var/www/html/assistant/venv/lib/python3.9/site-packages/transformers/models/layoutxlm/processing_layoutxlm.pyr3s zLayoutXLMProcessor.__init__TFr)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 [`~LayoutLMv2ImagePrpcessor.__call__`]. In case [`LayoutLMv2ImagePrpcessor`] 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 [`LayoutLMv2ImagePrpcessor`] 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. 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.wordsr)rrrr r!r"r#r$r%r&r'r(r)r*r+r,r-r.Z pixel_valuesoverflow_to_sample_mappingimage)r Z apply_ocrr isinstancestrrrget_overflowing_images)rr0rrrr r!r"r#r$r%r&r'r(r)r*r+r,r-r.rfeaturesZencoded_inputsrrr__call__DsT"   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)rr0r2Zimages_with_overflowZ sample_idxrrrr6sz)LayoutXLMProcessor.get_overflowing_imagescCsgdS)N)Z input_idsZbboxZattention_maskr3rrrrrmodel_input_namessz$LayoutXLMProcessor.model_input_namescCstdt|jS)Nzg`feature_extractor_class` is deprecated and will be removed in v5. Use `image_processor_class` instead.)rrrimage_processor_classr;rrrfeature_extractor_classs z*LayoutXLMProcessor.feature_extractor_classcCstdt|jS)Nz[`feature_extractor` is deprecated and will be removed in v5. Use `image_processor` instead.)rrrr r;rrrrs z$LayoutXLMProcessor.feature_extractor)NN)NNNNTFNNrNNNFFFFTN)__name__ __module__ __qualname____doc__ attributesr=Ztokenizer_classrrr rlistrintboolr5rr r rr8r6propertyr<r>r __classcell__rrrrr sf"   V  r )rBrtypingrrZprocessing_utilsrZtokenization_utils_baserrrr r utilsr r __all__rrrrs  #