cCi95 SrSSKJrJr SSKrSSKJrJrJ r SSK J r J r J r Jr SSKJrJrJrJrJrJrJrJr SSKJrJrJrJrJrJr SS KJ r \"5(aSSK!r!\"5(aSSK"r"\RF"\$5r%S r&SS \RNS \\(S \\(S\\\(\44Sjjr)\ "SS9"SS\55r*S/r+g)z%Image processor class for LayoutLMv2.)OptionalUnionN)BaseImageProcessor BatchFeature get_size_dict)flip_channel_orderresizeto_channel_dimension_format to_pil_image)ChannelDimension ImageInputPILImageResamplinginfer_channel_dimension_formatmake_flat_list_of_imagesto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargsis_pytesseract_availableis_vision_availableloggingrequires_backends)requiresc[SUSU- -5[SUSU- -5[SUSU- -5[SUSU- -5/$)Nirr)int)boxwidthheights t/home/james-whalen/.local/lib/python3.13/site-packages/transformers/models/layoutlmv2/image_processing_layoutlmv2.py normalize_boxr$6s` DCFUN #$ DCFVO $% DCFUN #$ DCFVO $%  imagelangtesseract_configinput_data_formatcUbUOSn[XS9nURupV[R"XASUS9nUSUSUSUSUS 4uppn [ U5V Vs/sHupUR 5(aMU PM nn n[ U5V Vs/sHupX;dM UPM nn n[ U 5V Vs/sHun nX;dM UPM n n n[ U 5V Vs/sHun nX;dM UPM n n n[ U 5V Vs/sHun nX;dM UPM n n n[ U 5V Vs/sHun nX;dM UPM n n n/n[ XX5H%unnnnUUUU-UU-/nURU5 M' /nUHnUR[UXV55 M [U5[U5:XdS 5eUU4$s snn fs snn fs snn fs snn fs snn fs snn f) zdApplies Tesseract OCR on a document image, and returns recognized words + normalized bounding boxes.r)dict)r' output_typeconfigtextlefttopr!r"z-Not as many words as there are bounding boxes) r size pytesseract image_to_data enumeratestripzipappendr$len)r&r'r(r) pil_image image_width image_heightdatawordsr1r2r!r"idxwordirrelevant_indicescoord actual_boxesxywh actual_boxnormalized_boxesr s r#apply_tesseractrK?s,<+G'RUHI )K  $ $YvVf gD&*6lDL$u+tT[}^bck^l&l#EV09/?T/?)#tzz|#/?T#,U#3 U#3ics7TT#3E U$-dO UOjc5s7TEOD U#,S> S>ZS%S5R5>C S%.u%5 W%5zsE9VU%5E W&/&7 Y&7 U3;Xe&7F YL$U3 1aAE1q5) J'4  c; MN u:-. ._0__ . " "")U U U S W YsHG<G G "G 9 G G G0G GG. G%>G%)vision)backendsc^\rSrSrSrS/rSS\RSSS4S\S\ \ \ \ 4S \S \S \ \ S \ \ S S4U4Sjjjr \RSS4S\RS\ \ \ 4S \S\ \\ \4S\ \\ \4S \R4 Sjjr\"5SSSSSSS\R(S4 S\S\ \S\ \ \ \ 4S \ \S \ \S \ \ S \ \ S\ \\ \4S\S\ \\ \4S \R0R04Sjj5rSrU=r$)LayoutLMv2ImageProcessorfa? Constructs a LayoutLMv2 image processor. Args: do_resize (`bool`, *optional*, defaults to `True`): Whether to resize the image's (height, width) dimensions to `(size["height"], size["width"])`. Can be overridden by `do_resize` in `preprocess`. size (`dict[str, int]` *optional*, defaults to `{"height": 224, "width": 224}`): Size of the image after resizing. Can be overridden by `size` in `preprocess`. resample (`PILImageResampling`, *optional*, defaults to `Resampling.BILINEAR`): Resampling filter to use if resizing the image. Can be overridden by the `resample` parameter in the `preprocess` method. apply_ocr (`bool`, *optional*, defaults to `True`): Whether to apply the Tesseract OCR engine to get words + normalized bounding boxes. Can be overridden by `apply_ocr` in `preprocess`. ocr_lang (`str`, *optional*): The language, specified by its ISO code, to be used by the Tesseract OCR engine. By default, English is used. Can be overridden by `ocr_lang` in `preprocess`. tesseract_config (`str`, *optional*, defaults to `""`): Any additional custom configuration flags that are forwarded to the `config` parameter when calling Tesseract. For example: '--psm 6'. Can be overridden by `tesseract_config` in `preprocess`. pixel_valuesTNr+ do_resizer3resample apply_ocrocr_langr(returnc >[TU]"S0UD6 UbUOSSS.n[U5nXlX lX0lX@lXPlX`lg)N)r"r!) super__init__rrRr3rSrTrUr() selfrRr3rSrTrUr(kwargs __class__s r#r[!LayoutLMv2ImageProcessor.__init__sO "6"'tc-JT""  " 0r%r& data_formatr)c [U5nSU;dSU;a[SUR535eUSUS4n[U4UUUUS.UD6$)a Resize an image to `(size["height"], size["width"])`. Args: image (`np.ndarray`): Image to resize. size (`dict[str, int]`): Dictionary in the format `{"height": int, "width": int}` specifying the size of the output image. resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BILINEAR`): `PILImageResampling` filter to use when resizing the image e.g. `PILImageResampling.BILINEAR`. data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format for the output image. If unset, the channel dimension format of the input image is used. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format. - `"none"` or `ChannelDimension.NONE`: image in (height, width) format. input_data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format for the input image. If unset, the channel dimension format is inferred from the input image. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format. - `"none"` or `ChannelDimension.NONE`: image in (height, width) format. Returns: `np.ndarray`: The resized image. r"r!zFThe `size` dictionary must contain the keys `height` and `width`. Got )r3rSr`r))r ValueErrorkeysr )r\r&r3rSr`r)r] output_sizes r#r LayoutLMv2ImageProcessor.resizesyFT" 4 7$#6efjfofofqerst tH~tG}5   #/     r%imagesreturn_tensorsc TUbUO URnUbUO URn[U5nUbUO URnUbUO URnUbUO UR nUbUO UR n[U5n[U5(d [S5e[UUUS9 UV s/sHn [U 5PM nn U c[US5n U(aG[US5 /n /n UH1n [XXzS9upU RU5 U RU5 M3 U(a UV s/sHn UR!XXJS9PM nn UV s/sH n [#XS9PM nn UV s/sH n [%XU S9PM nn ['SU0US 9nU(a W US 'W US 'U$s sn fs sn fs sn fs sn f) a Preprocess an image or batch of images. Args: images (`ImageInput`): Image to preprocess. do_resize (`bool`, *optional*, defaults to `self.do_resize`): Whether to resize the image. size (`dict[str, int]`, *optional*, defaults to `self.size`): Desired size of the output image after resizing. resample (`PILImageResampling`, *optional*, defaults to `self.resample`): Resampling filter to use if resizing the image. This can be one of the enum `PIL.Image` resampling filter. Only has an effect if `do_resize` is set to `True`. apply_ocr (`bool`, *optional*, defaults to `self.apply_ocr`): Whether to apply the Tesseract OCR engine to get words + normalized bounding boxes. ocr_lang (`str`, *optional*, defaults to `self.ocr_lang`): The language, specified by its ISO code, to be used by the Tesseract OCR engine. By default, English is used. tesseract_config (`str`, *optional*, defaults to `self.tesseract_config`): Any additional custom configuration flags that are forwarded to the `config` parameter when calling Tesseract. return_tensors (`str` or `TensorType`, *optional*): The type of tensors to return. Can be one of: - Unset: Return a list of `np.ndarray`. - `TensorType.TENSORFLOW` or `'tf'`: Return a batch of type `tf.Tensor`. - `TensorType.PYTORCH` or `'pt'`: Return a batch of type `torch.Tensor`. - `TensorType.NUMPY` or `'np'`: Return a batch of type `np.ndarray`. - `TensorType.JAX` or `'jax'`: Return a batch of type `jax.numpy.ndarray`. data_format (`ChannelDimension` or `str`, *optional*, defaults to `ChannelDimension.FIRST`): The channel dimension format for the output image. Can be one of: - `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `ChannelDimension.LAST`: image in (height, width, num_channels) format. zkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.)rRr3rSrr4r,)r&r3rSr))input_channel_dimrQ)r> tensor_typer?boxes)rRr3rrSrTrUr(rrrbrrrrrKr9r r r r)r\rfrRr3rSrTrUr(rgr`r)r& words_batch boxes_batchr?rkr>s r# preprocess#LayoutLMv2ImageProcessor.preprocesss^"+!6IDNN 'tTYYT"'38!*!6IDNN '38/?/K+QUQfQf)&1F##:  & 6<vay I   dM 2KK.u@Pv ""5)""5) $#E %X k#  _ee^dUZ$UP^dent ntej 'N_ `nt  .&!9~V 'DM'DM A=  f s'F(FF !F%)rTrRrUrSr3r()__name__ __module__ __qualname____firstlineno____doc__model_input_namesrBILINEARboolrr-strrr[npndarrayrr r rFIRSTrrPILImagern__static_attributes__ __classcell__)r^s@r#rOrOfs .(()-'9'B'B"&*,11tCH~&1% 1  1 3- 1#3-1 114(:'B'B>BDH . zz. 38n. % . eC)9$9:; . $E#/?*?$@A .  . `%&%))-15$("&*.;?(8(>(>DHddD>dtCH~& d -. d D> d3-d#3-d!sJ!78d&d$E#/?*?$@Ad d'dr%rO)NN),rttypingrrnumpyryimage_processing_utilsrrrimage_transformsr r r r image_utilsr rrrrrrrutilsrrrrrrutils.import_utilsrr|r4 get_loggerrploggerr$rzrxrKrO__all__rYr%r#rs,"UUee   +   H %'+@D $# ::$# 3-$#sm$# c+;&; <= $#N ;E1E EP & &r%