cCiH SrSSKJr SSKJrJr SSKrSSKJ r J r J r SSK J r JrJr SSKJrJrJrJrJrJrJrJrJrJrJr SS KJrJrJrJ r J!r!J"r" SS K#J$r$ \ "5(aSSK%r%\"5(aSSK&r&\!RN"\(5r)S r*SS \RVS \\,S\\,S\\\\,44Sjjr-\$"SS9"SS\ 55r.S/r/g)z%Image processor class for LayoutLMv3.)Iterable)OptionalUnionN)BaseImageProcessor BatchFeature get_size_dict)resizeto_channel_dimension_format to_pil_image) IMAGENET_STANDARD_MEANIMAGENET_STANDARD_STDChannelDimension ImageInputPILImageResamplinginfer_channel_dimension_formatis_scaled_imagemake_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/$)Nirr)int)boxwidthheights t/home/james-whalen/.local/lib/python3.13/site-packages/transformers/models/layoutlmv3/image_processing_layoutlmv3.py normalize_boxr':s` DCFUN #$ DCFVO $% DCFUN #$ DCFVO $%  imagelangtesseract_configinput_data_formatc[XS9nURupV[R"XASUS9nUSUSUSUSUS4uppn [ U5V Vs/sHupUR 5(aMU PM nn n[ U5V Vs/sHupX;dM UPM nn n[ U 5V Vs/sHun nX;dM UPM n n n[ U 5V Vs/sHun nX;dM UPM n n n[ U 5V Vs/sHun nX;dM UPM n n n[ U 5V Vs/sHun nX;dM UPM n n n/n[ XX5H%unnnnUUUU-UU-/nURU5 M' /nUHnUR[UXV55 M [U5[U5:XdS 5eUU4$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$r%z-Not as many words as there are bounding boxes) r size pytesseract image_to_data enumeratestripzipappendr'len)r)r*r+r, pil_image image_width image_heightdatawordsr3r4r$r%idxwordirrelevant_indicescoord actual_boxesxywh actual_boxnormalized_boxesr#s r&apply_tesseractrMCsUHI )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 YsHG5G GG2 G G  G)G GG' G7G)vision)backendsc!^\rSrSrSrS/rSS\RSSSSSSSS4 S\S \ \ \ \ 4S \S \S \ S \S\ \\ \\ 4S\ \\ \\ 4S\S\ \ S\ \ SS4U4Sjjjr\RSS4S\R$S \ \ \ 4S \S\ \\ \4S\ \\ \4S\R$4 Sjjr\"5SSSSSSSSSSSS\R,S4S\S\ \S \ \ \ \ 4S \ \S\ \ S \ \S\ \\ \\ 4S\ \\ \\ 4S\ \S\ \ S\ \ S\ \\ \4S\S\ \\ \4S\R4R44Sjj5rSrU=r$)LayoutLMv3ImageProcessoria! Constructs a LayoutLMv3 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 `PILImageResampling.BILINEAR`): Resampling filter to use if resizing the image. Can be overridden by `resample` in `preprocess`. do_rescale (`bool`, *optional*, defaults to `True`): Whether to rescale the image's pixel values by the specified `rescale_value`. Can be overridden by `do_rescale` in `preprocess`. rescale_factor (`float`, *optional*, defaults to 1 / 255): Value by which the image's pixel values are rescaled. Can be overridden by `rescale_factor` in `preprocess`. do_normalize (`bool`, *optional*, defaults to `True`): Whether to normalize the image. Can be overridden by the `do_normalize` parameter in the `preprocess` method. image_mean (`Iterable[float]` or `float`, *optional*, defaults to `IMAGENET_STANDARD_MEAN`): Mean to use if normalizing the image. This is a float or list of floats the length of the number of channels in the image. Can be overridden by the `image_mean` parameter in the `preprocess` method. image_std (`Iterable[float]` or `float`, *optional*, defaults to `IMAGENET_STANDARD_STD`): Standard deviation to use if normalizing the image. This is a float or list of floats the length of the number of channels in the image. Can be overridden by the `image_std` 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 the `apply_ocr` parameter in the `preprocess` method. 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 the `ocr_lang` parameter in the `preprocess` method. tesseract_config (`str`, *optional*): Any additional custom configuration flags that are forwarded to the `config` parameter when calling Tesseract. For example: '--psm 6'. Can be overridden by the `tesseract_config` parameter in the `preprocess` method. pixel_valuesTNgp? do_resizer5resample do_rescale rescale_value do_normalize image_mean image_std apply_ocrocr_langr+returnc  >[T U]"S0U D6 UbUOSSS.n[U5nXlX lX0lX@lXPlX`lUbUO[Ul UbUO[Ul Xl XlXlg)N)r%r$)super__init__r rUr5rVrWrescale_factorrYr rZrr[r\r]r+)selfrUr5rVrWrXrYrZr[r\r]r+kwargs __class__s r&rc!LayoutLMv3ImageProcessor.__init__s~ "6"'tc-JT""  $+((2(>*DZ&/&;AV" 0r(r) data_formatr,c [U5nSU;dSU;a[SUR535eUSUS4n[U4UUUUS.UD6$)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$zFThe `size` dictionary must contain the keys `height` and `width`. Got )r5rVrir,)r ValueErrorkeysr )rer)r5rVrir,rf output_sizes r&r LayoutLMv3ImageProcessor.resizesyFT" 4 7$#6efjfofofqerst tH~tG}5   #/     r(imagesrdreturn_tensorsc UbUO URnUbUO URn[U5nUbUO URnUbUO URnUbUO UR nUbUO UR nUbUO URnU bU O URn U bU O URn U bU O URn U bU O URn [U5n[U5(d [S5e[UUUUU UUUS9 UVs/sHn[!U5PM nnU(a([#US5(a[$R'S5 Uc[)US5nU (aI[+US5 /n/nUH3n[-UXUS9unnUR/U5 UR/U5 M5 U(a!UVs/sHnUR1UX4US9PM nnU(a UVs/sHnUR3UXoS9PM nnU(a!UVs/sHnUR5UXUS 9PM nnUVs/sH n[7UXS 9PM nn[9S U0U S 9nU (a WUS 'WUS'U$s snfs snfs snfs snfs snf)a Preprocess an image or batch of images. Args: images (`ImageInput`): Image to preprocess. Expects a single or batch of images with pixel values ranging from 0 to 255. If passing in images with pixel values between 0 and 1, set `do_rescale=False`. 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 applying `resize`. resample (`int`, *optional*, defaults to `self.resample`): Resampling filter to use if resizing the image. This can be one of the `PILImageResampling` filters. Only has an effect if `do_resize` is set to `True`. do_rescale (`bool`, *optional*, defaults to `self.do_rescale`): Whether to rescale the image pixel values between [0, 1]. rescale_factor (`float`, *optional*, defaults to `self.rescale_factor`): Rescale factor to apply to the image pixel values. Only has an effect if `do_rescale` is set to `True`. do_normalize (`bool`, *optional*, defaults to `self.do_normalize`): Whether to normalize the image. image_mean (`float` or `Iterable[float]`, *optional*, defaults to `self.image_mean`): Mean values to be used for normalization. Only has an effect if `do_normalize` is set to `True`. image_std (`float` or `Iterable[float]`, *optional*, defaults to `self.image_std`): Standard deviation values to be used for normalization. Only has an effect if `do_normalize` 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. 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. zkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.)rWrdrYrZr[rUr5rVrzIt looks like you are trying to rescale already rescaled images. If the input images have pixel values between 0 and 1, set `do_rescale=False` to avoid rescaling them again.r6r.)r)r5rVr,)r)scaler,)r)meanstdr,)input_channel_dimrS)r@ tensor_typerAboxes)rUr5r rVrWrdrYrZr[r\r]r+rrrkrrrlogger warning_oncerrrMr;r rescale normalizer r)rerorUr5rVrWrdrYrZr[r\r]r+rprir,r) words_batch boxes_batchrArwr@s r& preprocess#LayoutLMv3ImageProcessor.preprocesssL"+!6IDNN 'tTYYT"'38#-#9Zt +9+E4K^K^'3'?|TEVEV #-#9Zt !*!6IDNN !*!6IDNN '38/?/K+QUQfQf)&1F##:  &!)%! 6<vay I   dM 2KK.uhduv u""5)""5) $#E %dYj k#  $#E 5 d#  $#EU^op#  ou ntej '{ `nt  .&!9~V 'DM'DM c=.    sI3II"I'#I,) r\rYrWrUrZr[r]rVrdr5r+)__name__ __module__ __qualname____firstlineno____doc__model_input_namesrBILINEARboolrr/strr"floatrrrcnpndarrayrr rFIRSTrrPILImager~__static_attributes__ __classcell__)rgs@r&rQrQis$L(()-'9'B'B&!>B=A"&*,11tCH~&1% 1  1  11U5(5/#9:;1E%%"89:113-1#3-1 11H(:'B'B>BDH . zz. 38n. % . eC)9$9:; . $E#/?*?$@A .  . `%&%))-%)*.'+>B=A$("&*.;?(8(>(>DH!UUD>UtCH~& U TN U!UtnUU5(5/#9:;UE%%"89:UD>U3-U#3-U!sJ!78U&U $E#/?*?$@A!U" #U'Ur(rQ)N)0rcollections.abcrtypingrrnumpyrimage_processing_utilsrrr image_transformsr r r image_utilsr rrrrrrrrrrutilsrrrrrrutils.import_utilsrrr6 get_loggerrrxr'rrrMrQ__all__rar(r&rs,$"UUQQ    +   H %AE ## ::## 3-##sm## &6&; <= ##L ;O1O Od & &r(