sg\dZddlmZmZmZmZddlZddlm Z m Z m Z ddl m Z mZmZmZmZddlmZmZmZmZmZmZmZmZmZmZmZmZddlm Z m!Z!m"Z"dd l#m$Z$m%Z%e"jLe'Z(e$r e%rddl)Z)Gd d e Z*y) z!Image processor class for Nougat.)DictListOptionalUnionN)BaseImageProcessor BatchFeature get_size_dict)get_resize_output_image_sizepadresizeto_channel_dimension_format to_pil_image) IMAGENET_DEFAULT_MEANIMAGENET_DEFAULT_STDChannelDimension ImageInputPILImageResamplingget_image_sizeinfer_channel_dimension_formatis_scaled_imagemake_list_of_imagesto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargslogging)is_cv2_availableis_vision_availablec%zeZdZdZdgZdddej ddddddddf deded ee e fd ed ed ed edede e e fdede e e ee fde e e ee fddffd Zdej"fdZdZ d#dej"de de ede e e efdej"f dZ d$dej,d ee e fde e e efde e e efdej,f dZ d$dej,d ee e fde e e efde e e efdej,f dZej2ddfdej,d ee e fd ede e e efde e e efdej,f dZej2ddfdej,d ee e fd ede e e efde e e efdej,f dZedddddddddddddej:dfd ededed ee e fd ed ed ed edede e e fdede e e ee fde e e ee fd!e e e efde ede e e efde jBjBf"d"Z"xZ#S)%NougatImageProcessora Constructs a Nougat image processor. Args: do_crop_margin (`bool`, *optional*, defaults to `True`): Whether to crop the image margins. do_resize (`bool`, *optional*, defaults to `True`): Whether to resize the image's (height, width) dimensions to the specified `size`. Can be overridden by `do_resize` in the `preprocess` method. size (`Dict[str, int]` *optional*, defaults to `{"height": 896, "width": 672}`): Size of the image after resizing. Can be overridden by `size` in the `preprocess` method. resample (`PILImageResampling`, *optional*, defaults to `Resampling.BILINEAR`): Resampling filter to use if resizing the image. Can be overridden by `resample` in the `preprocess` method. do_thumbnail (`bool`, *optional*, defaults to `True`): Whether to resize the image using thumbnail method. do_align_long_axis (`bool`, *optional*, defaults to `False`): Whether to align the long axis of the image with the long axis of `size` by rotating by 90 degrees. do_pad (`bool`, *optional*, defaults to `True`): Whether to pad the images to the largest image size in the batch. do_rescale (`bool`, *optional*, defaults to `True`): Whether to rescale the image by the specified scale `rescale_factor`. Can be overridden by the `do_rescale` parameter in the `preprocess` method. rescale_factor (`int` or `float`, *optional*, defaults to `1/255`): Scale factor to use if rescaling the image. Can be overridden by the `rescale_factor` parameter in the `preprocess` method. do_normalize (`bool`, *optional*, defaults to `True`): Whether to normalize the image. Can be overridden by `do_normalize` in the `preprocess` method. image_mean (`float` or `List[float]`, *optional*, defaults to `IMAGENET_DEFAULT_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 (`float` or `List[float]`, *optional*, defaults to `IMAGENET_DEFAULT_STD`): Image standard deviation. pixel_valuesTNFgp?do_crop_margin do_resizesizeresample do_thumbnaildo_align_long_axisdo_pad do_rescalerescale_factor do_normalize image_mean image_stdreturnc  t|di| ||nddd}t|}||_||_||_||_||_||_||_ ||_ | |_ | |_ | | nt|_| | |_yt|_y)Nii)heightwidth)super__init__r r$r%r&r'r(r)r*r+r,r-rr.rr/)selfr$r%r&r'r(r)r*r+r,r-r.r/kwargs __class__s e/var/www/html/venv/lib/python3.12/site-packages/transformers/models/nougat/image_processing_nougat.pyr6zNougatImageProcessor.__init___s "6"'tc-JT","   ("4 $,((2(>*DY&/&;AUimagectjtj|}|ddddgf}|jddd}|S)zGThis is a reimplementation of a findNonZero function equivalent to cv2.Nr)np column_stacknonzeroreshape)r7r<non_zero_indicesidxvecs r:python_find_non_zeroz)NougatImageProcessor.python_find_non_zerosC??2::e+<=!!aV),Aq) r;ctj|djt}tj|djt}|d|d}}|d|z dz}|d|z dz}||||fS)zHThis is a reimplementation of a BoundingRect function equivalent to cv2.)rr>)axisrr>)rAminastypeintmax)r7 coordinates min_values max_valuesx_miny_minr3r2s r:python_bounding_rectz)NougatImageProcessor.python_bounding_rects~VVKf5<u E U6GHxx c*+22288<((*((* g HHUOE*,E;@QR  L  Lw7W#45;n$**40&*&?&?&G#ueV E5%%-HI&&rxx0+E3DFVF[F[\S^Ri '{vay I  `fgW\d&&u@Q&RgFg ouvfkd**5tO`*avFv $ %dXYj kF ouvfkdnn5tO`navFv ouvfkdnn5tO`navFv $ 5Rc dF $U^opF ou ej '{N_ `  '>BB_=hw ww   s6;I& I+,I0I53I:I?9JJ >J)NN)NN)$__name__ __module__ __qualname____doc__model_input_namesrBILINEARboolrstrrLrfloatrrr6rAr[rGrSrrendarrayrpryBICUBICr|r rFIRSTrrPILImager __classcell__)r9s@r:r"r":s D(( $#'9'B'B!#(,3!:>9= V V V38n V % V  V! V V Vc5j) V VU5$u+#567 VE%e"456 V  VD"((+"26DH 1xx11./ 1 $E#/?*?$@A 1  1p?CDH "zz"38n"eC)9$9:; " $E#/?*?$@A "  "P?CDH !azz!a38n!aeC)9$9:; !a $E#/?*?$@A !a  !aP(:'A'A>BDH 0 zz0 38n0 % 0 eC)9$9:; 0 $E#/?*?$@A 0  0 n(:'A'A>BDH %zz%38n%% % eC)9$9:; % $E#/?*?$@A % %N%& $#'+!#',0!:>9=;?2B2H2HDH#WCWCWC WC 38n WC % WCWC!WCWCWCc5j)WCWCU5$u+#567WCE%e"456WC!sJ!78WC ./!WC"$E#/?*?$@A#WC$ %WC'WCr;r")+rtypingrrrrnumpyrAimage_processing_utilsrr r image_transformsr r r rr image_utilsrrrrrrrrrrrrutilsrrrutils.import_utilsrr get_loggerrrrr"r4r;r:rs~(..UU    JIG   H %EC-ECr;