o Zh#@sndZddlZddlmZmZmZddlmZddlm Z m Z m Z m Z m Z ddlmZGdd d eZd gZdS) z! Processor class for LayoutLMv3. N)ListOptionalUnion)ProcessorMixin) BatchEncodingPaddingStrategyPreTokenizedInput TextInputTruncationStrategy) TensorTypec(sveZdZdZddgZdZdZd-fdd Z          d.d ee e e e e e fd e ee e e fde ee e e e e e e fde ee e e e e fdedeeeefdeeeefde e de de e de ede edededededede eeefdef&dd Zd!d"Zd#d$Zd%d&Zed'd(Zed)d*Zed+d,ZZS)/LayoutLMv3Processorav Constructs a LayoutLMv3 processor which combines a LayoutLMv3 image processor and a LayoutLMv3 tokenizer into a single processor. [`LayoutLMv3Processor`] offers all the functionalities you need to prepare data for the model. It first uses [`LayoutLMv3ImageProcessor`] to resize and normalize document images, and optionally applies OCR to get words and normalized bounding boxes. These are then provided to [`LayoutLMv3Tokenizer`] or [`LayoutLMv3TokenizerFast`], 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 (`LayoutLMv3ImageProcessor`, *optional*): An instance of [`LayoutLMv3ImageProcessor`]. The image processor is a required input. tokenizer (`LayoutLMv3Tokenizer` or `LayoutLMv3TokenizerFast`, *optional*): An instance of [`LayoutLMv3Tokenizer`] or [`LayoutLMv3TokenizerFast`]. The tokenizer is a required input. image_processor tokenizerZLayoutLMv3ImageProcessor)ZLayoutLMv3TokenizerZLayoutLMv3TokenizerFastNc sdd}d|vrtdt|d}|dur|n|}|dur!td|dur)tdt||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__)selfrrkwargsr __class__c/var/www/auris/lib/python3.10/site-packages/transformers/models/layoutlmv3/processing_layoutlmv3.pyr3s zLayoutLMv3Processor.__init__TFrtext 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_tensorsreturncKsD|jjr |dur td|jjr|durtd|j||d}|dur7|jjr7|dur7t|tr3|g}|d}|jdid|durB|n|dd|durM|ndd|durV|n|dd |d |d |d |d | d| d| d| d| d|d|d|d|d|d||}|d}|dur|||d}||d<|S)aF This method first forwards the `images` argument to [`~LayoutLMv3ImageProcessor.__call__`]. In case [`LayoutLMv3ImageProcessor`] was initialized with `apply_ocr` set to `True`, it passes the obtained words and bounding boxes along with the additional arguments to [`~LayoutLMv3Tokenizer.__call__`] and returns the output, together with resized and normalized `pixel_values`. In case [`LayoutLMv3ImageProcessor`] 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 [`~LayoutLMv3Tokenizer.__call__`] and returns the output, together with resized and normalized `pixel_values`. 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.)imagesr/wordsrrr r!r"r#r$r%r&r'r(r)r*r+r,r-r.r/ pixel_valuesToverflow_to_sample_mappingr)rZ apply_ocrr isinstancestrrrget_overflowing_images)rr1rrr r!r"r#r$r%r&r'r(r)r*r+r,r-r.r/rfeaturesZencoded_inputsrrr__call__Esv#        zLayoutLMv3Processor.__call__cCsLg}|D] }|||qt|t|kr$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)rr1r4Zimages_with_overflowZ sample_idxrrrr7sz*LayoutLMv3Processor.get_overflowing_imagescO|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_decoderargsrrrrr=z LayoutLMv3Processor.batch_decodecOr<)z This method forwards all its arguments to PreTrainedTokenizer's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of this method for more information. )rdecoder>rrrrAr@zLayoutLMv3Processor.decodecCsgdS)N)Z input_idsZbboxZattention_maskr3rrrrrmodel_input_namessz%LayoutLMv3Processor.model_input_namescCtdt|jS)Nzg`feature_extractor_class` is deprecated and will be removed in v5. Use `image_processor_class` instead.)rrrimage_processor_classrBrrrfeature_extractor_class z+LayoutLMv3Processor.feature_extractor_classcCrD)Nz[`feature_extractor` is deprecated and will be removed in v5. Use `image_processor` instead.)rrrrrBrrrrrGz%LayoutLMv3Processor.feature_extractor)NN)NNNNTFNNrNNNFFFFTN)__name__ __module__ __qualname____doc__ attributesrEZtokenizer_classrrr r rrintboolr6rr r rr9r7r=rApropertyrCrFr __classcell__rrrrr s"       T  r )rKrtypingrrrZprocessing_utilsrZtokenization_utils_baserrr r r utilsr r __all__rrrrs   0