cCi?!pSrSSKrSSKJrJr SSKJr SSKJrJ r J r J r J r SSK Jr "SS \5rS /rg) z! Processor class for LayoutLMv2. N)OptionalUnion)ProcessorMixin) BatchEncodingPaddingStrategyPreTokenizedInput TextInputTruncationStrategy) TensorTypec(^\rSrSrSrSS/rSrSrS!U4SjjrS"S\ \ \ \ \ \ \ 4S \ \ \ \ \ 4S \ \ \ \ \\ \ \ \4S \ \ \ \\ \ \4S \S \ \\\4S\ \\\4S\ \S\S\ \S\ \S\ \S\S\S\S\S\S\ \ \\4S\4&SjjrSr\S5r\S5r\S5rS rU=r$)#LayoutLMv2Processora@ Constructs a LayoutLMv2 processor which combines a LayoutLMv2 image processor and a LayoutLMv2 tokenizer into a single processor. [`LayoutLMv2Processor`] 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 [`LayoutLMv2Tokenizer`] or [`LayoutLMv2TokenizerFast`], 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 (`LayoutLMv2Tokenizer` or `LayoutLMv2TokenizerFast`, *optional*): An instance of [`LayoutLMv2Tokenizer`] or [`LayoutLMv2TokenizerFast`]. The tokenizer is a required input. image_processor tokenizerLayoutLMv2ImageProcessor)LayoutLMv2TokenizerLayoutLMv2TokenizerFastc >SnSU;a,[R"S[5 URS5nUbUOUn[TU]X5 g)Nfeature_extractorzhThe `feature_extractor` argument is deprecated and will be removed in v5, use `image_processor` instead.)warningswarn FutureWarningpopsuper__init__)selfrrkwargsr __class__s n/home/james-whalen/.local/lib/python3.13/site-packages/transformers/models/layoutlmv2/processing_layoutlmv2.pyrLayoutLMv2Processor.__init__3sQ  & ( MM  !' +> ? -<-H/N_ 4text 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_tensorsreturnc URR(aUb [S5eURR(aUb [S5eUSLaUSLa [S5eURUUS9nUb;URR(a Uc[U[5(aU/nUSnUR "S0S UbUOUS_S UbUOS_S UbUOUS _S U_S U_SU_SU_SU _SU _SU _SU _SU _SU_SU_SU_SU_SU_SU_UD6nUR S5nUSLaURUUS5nUUS'U$)a This method first forwards the `images` argument to [`~LayoutLMv2ImageProcessor.__call__`]. In case [`LayoutLMv2ImageProcessor`] was initialized with `apply_ocr` set to `True`, it passes the obtained words and bounding boxes along with the additional arguments to [`~LayoutLMv2Tokenizer.__call__`] and returns the output, together with resized `images`. In case [`LayoutLMv2ImageProcessor`] 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 [`~LayoutLMv2Tokenizer.__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.)imagesr4wordsr#r$r%r&r'r(r)r*r+r,r-r.r/r0r1r2r3r4 pixel_valuesoverflow_to_sample_mappingimage)r apply_ocr ValueError isinstancestrrrget_overflowing_images)rr7r#r$r%r&r'r(r)r*r+r,r-r.r/r0r1r2r3r4rfeaturesencoded_inputss r __call__LayoutLMv2Processor.__call__AsD    ) )u/@v     ) ){/Fs  % ,1G51Pjk k''vn'U   4 4 > >9CT$$$v )I )x/@ #,#8id !,%(72C $  2    " "   2 #8 #8 '@ (B $: (! "# $*' .n- $ ,00Hd9efF"(wr"c/nUHnURX5 M [U5[U5:wa#[S[U5S[U535eU$)Nz`Expected length of images to be the same as the length of `overflow_to_sample_mapping`, but got z and )appendlenr>)rr7r:images_with_overflow sample_idxs r rA*LayoutLMv2Processor.get_overflowing_imagessr!4J ' '(: ;5 # $,F(G G,-.eC8R4S3TV  $#r"c /SQ$)N) input_idsbboxtoken_type_idsattention_maskr;r<rs r model_input_names%LayoutLMv2Processor.model_input_namessQQr"cP[R"S[5 UR$)Nzg`feature_extractor_class` is deprecated and will be removed in v5. Use `image_processor_class` instead.)rrrimage_processor_classrQs r feature_extractor_class+LayoutLMv2Processor.feature_extractor_classs" u  )))r"cP[R"S[5 UR$)Nz[`feature_extractor` is deprecated and will be removed in v5. Use `image_processor` instead.)rrrrrQs r r%LayoutLMv2Processor.feature_extractors" i  ###r"r<)NN)NNNNTFFNrNNNFFFFTN)__name__ __module__ __qualname____firstlineno____doc__ attributesrUtokenizer_classrrr r listrintboolr@rr r rrDrApropertyrRrVr__static_attributes__ __classcell__)rs@r rrs&$[1J6HO 5"_cQUIMCG#'5:;@$(,00404*/+0',#;?)TI0$y/4HYCZZ[TE"3T:K5L"LMN T d49otDcO/DDEF T eDItDI$>?@ T!TtS/12T$%778TSMTT%SMT (~T (~T$(T %)!T"!%#T$%T&'T(!sJ!78)T, -Tl $RR**$$r"r)r^rtypingrrprocessing_utilsrtokenization_utils_baserrr r r utilsr r__all__r<r"r rls7".ww\$.\$~ ! !r"