rh`ddlmZddlmZmZddlZddlmZm Z m Z m Z ddl m Z mZmZmZmZddlmZmZmZmZmZmZmZmZmZmZddlmZmZej@e!Z"d ejFd e$d e%ejFfd Z&Gd deZ'dgZ(y))Iterable)OptionalUnionN)BaseImageProcessor BatchFeatureget_patch_output_sizeselect_best_resolution) PaddingModeconvert_to_rgbpadresizeto_channel_dimension_format) ChannelDimension ImageInputPILImageResamplingget_image_sizeinfer_channel_dimension_formatis_scaled_imagemake_flat_list_of_imagesto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypeloggingimage patch_sizereturncg}t||\}}td||D]^}td||D]L}|tjk(r||||z|||zf}n|dd|||z|||zf}|j |N`|S)a Divides an image into patches of a specified size. Args: image (`np.array`): The input image. patch_size (`int`): The size of each patch. input_data_format (`ChannelDimension` or `str`): The channel dimension format of the input image. Returns: list: A list of np.array representing the patches.  channel_dimrN)rrangerLASTappend) rrinput_data_formatpatchesheightwidthijpatchs /var/www/html/ai-insurance-compliance-backend/venv/lib/python3.12/site-packages/transformers/models/aria/image_processing_aria.pydivide_to_patchesr-.sG"56GHMFE 1fj )"q%, "A $4$9$99a!j.0!a*n2DDEaQ^!3QZ5GGH NN5 !  "" Nc eZdZdZgdZddddddddddej f d eee d eee d e d e d eee e e fdee dee de de e e fdee deffd Zdddddddddddej df de eeefd ee e ee fd ee e ee fd ee d ee dee dee dee dee dee dedee eefdeedee eeffdZdej,de dedej,fdZde de fd Zdej,de dedej,fd!Zej6d"ddfdej8d#e e e e e fee e e ffd$ed%e e ee fdee eefdee eefdej8fd&Zdej,d'ee e e fd(e dedededeej,fd)Zd-d*e d+e fd,Z xZ!S).AriaImageProcessoraG A vision processor for the Aria model that handles image preprocessing. Initialize the AriaImageProcessor. Args: image_mean (`list`, *optional*, defaults to [0.5, 0.5, 0.5]): Mean values for normalization. image_std (`list`, *optional*, defaults to [0.5, 0.5, 0.5]): Standard deviation values for normalization. max_image_size (`int`, *optional*, defaults to 980): Maximum image size. min_image_size (`int`, *optional*, defaults to 336): Minimum image size. split_resolutions (`list`, *optional*, defaults to a list of optimal,resolutions as tuples): The optimal resolutions for splitting the image. split_image (`bool`, *optional*, defaults to `False`): Whether to split the image. do_convert_rgb (`bool`, *optional*, defaults to `True`): Whether to convert the image to RGB. do_rescale (`bool`, *optional*, defaults to `True`): Whether to rescale the image by the specified scale `rescale_factor`. Can be overridden by `do_rescale` 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 `rescale_factor` in the `preprocess` method. do_normalize (`bool`, *optional*, defaults to `True`): Whether to normalize the image. resample (PILImageResampling, *optional*, defaults to `BICUBIC`): The resampling filter to use if resizing the image.  pixel_values pixel_mask num_cropsNiPFTgp? image_mean image_stdmax_image_sizemin_image_sizesplit_resolutions split_imagedo_convert_rgb do_rescalerescale_factor do_normalizeresamplec  &t|di| |gd}|gd}||_||_||_||_||_|!gd}|D cgc]} | ddz| ddzf}} ||_||_||_ | |_ | |_ | |_ ycc} w)N)?rBrB)))rCr)rC)rC)rC)rC)rC)rDrE)rDr)rDrD)rDrC)rrC)rrD)rErC)rErD)rFrC)rGrC)rHrC)rIrCrrC) super__init__r8r9r6r7r;r:r<r=r>r?r@)selfr6r7r8r9r:r;r<r=r>r?r@kwargsel __class__s r,rMzAriaImageProcessor.__init__ls "6"  (J  'I,,$"&  $!y FW X"Q%#+r!us{!; X  X!2,$,(  !Ys Bptimagesreturn_tensors data_formatr%c .||n |j}||n |j}||n |j}||n |j}||n |j}||n |j }||n |j }| | n |j} | | n |j} | | n |j} |dvr tdt|}t|s tdt| ||| || |r|Dcgc] }t|}}|Dcgc] }t|}}|r#t!|drt"j%d|t'|d}g}g}d}|D]}}|r"|j)||j*|| ||}n|g}|t-||kDr t-|}|D]2}t/|\}}|t1||z }||k\rt1t3||z||f}n|t1t3||z|f}t5||| || }||dz ||d z }}t7|d|fd|ff||}t9j:||ft< }d |d|dd|d f<|j?||r|jA|| | }| r;|jC||j|j||}| tE|| |n|}|j?|5tGt9jH|d t9jH|d |d| Scc}wcc}w)aI Process a list of images. Args: images (ImageInput or list of ImageInput): The input image or a list of images. image_mean (`list`, *optional*, defaults to [0.5, 0.5, 0.5]): Mean values for normalization. image_std (`list`, *optional*, defaults to [0.5, 0.5, 0.5]): Standard deviation values for normalization. max_image_size (`int`, *optional*, defaults to `self.max_image_size` (980)): Maximum image size. min_image_size (`int`, *optional*, defaults to `self.min_image_size` (336)): Minimum image size. split_image (`bool`, *optional*, defaults to `self.split_image` (False)): Whether to split the image. do_convert_rgb (`bool`, *optional*, defaults to `self.do_convert_rgb` (True)): Whether to convert the image to RGB. do_rescale (`bool`, *optional*, defaults to `self.do_rescale`): Whether to rescale the image. rescale_factor (`float`, *optional*, defaults to `self.rescale_factor`): Rescale factor to rescale the image by if `do_rescale` is set to `True`. do_normalize (`bool`, *optional*, defaults to `self.do_normalize` (True)): Whether to normalize the image. resample (PILImageResampling, *optional*, defaults to `self.resample` (BICUBIC)): The resampling filter to use if resizing the image. return_tensors (`str` or `TensorType`, *optional*, defaults to "pt"): The type of tensor to return. data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format for the output 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. If unset, will use same as the input image. input_data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format for 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. If unset, will use the inferred format of the input image. Returns: BatchFeature: A BatchFeature object containing: - 'pixel_values': Tensor of processed image pixel values. - 'pixel_mask': Boolean pixel mask. This mask is a 2D tensor of shape (max_image_size, max_image_size) where: - True (1) values indicate pixels that belong to the original resized image. - False (0) values indicate pixels that are part of the padding. The mask helps distinguish between actual image content and padded areas in subsequent processing steps. - 'num_crops': The maximum number of crops across all images. N)rJr5z(max_image_size must be either 490 or 980zkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.)r?r6r7r@r=r>rzIt 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.)rUr%)r@rUr%rC)dtype)rscaler%)axisr1)data tensor_type)%r6r7r8r9r;r<r=r>r?r@ ValueErrorrrrr rrlogger warning_oncerget_image_patchesr:lenrmaxintrr npzerosboolr$rescale normalizerrstack)rNrSr6r7r8r9r;r<r=r>r?r@rTrUr%rr2 pixel_masksr4 crop_images crop_imagehwrXnew_sizecrop_image_resizedpadding_bottom padding_rightcrop_image_paddedr3s r, preprocesszAriaImageProcessor.preprocesssR$.#9Zt !*!6IDNN +9+E4K^K^+9+E4K^K^%0%vay I    @ 7E"44**" 1&7 5  %g  C $4y$@ , )1 7 %j11&Q26 #CE NN C^TH .CE NN0STH%+% 1&7 &"1?!0Ln_ghi_jNj $'&(1m*<= 1&7 %! XX~~&FdS ;< =Xa[=-HQK-78"":.(, /~Yj)5)% (,)$5*; )7)%'244E{Tef.& ##$56c1 7@ 7B "A > hh{;& '   iA=s (L Lrtarget_resolutionrcHt|||\}}t|||f||}|S)aC Resizes an image to a target resolution while maintaining aspect ratio. Args: image (np.array): The input image. target_resolution (tuple): The target resolution (height, width) of the image. resample (`PILImageResampling`): Resampling filter to use if resizing the image. input_data_format (`ChannelDimension` or `str`): The channel dimension format of the input image. Returns: np.array: The resized and padded image. r@r%)r r)rNrrtr@r% new_height new_width resized_images r,_resize_for_patchingz'AriaImageProcessor._resize_for_patchingVs7&!6e=NPa b Iuz9&=duv r.original_resolutioncz|\}}|\}}t||z d\}}t||z d\} } | | | zf|||zffS)NrD)divmod) rNr{rtoriginal_heightoriginal_width target_height target_widthpaste_xr_xpaste_yr_ys r,_get_padding_sizez$AriaImageProcessor._get_padding_sizeps]*='&7# |l^;Q? mo=qA 3''7S=)AAAr.cjt|||}|j||}|j||}|S)zU Pad an image to a target resolution while maintaining aspect ratio. )padding)r rr )rNrrtr%new_resolutionr padded_images r,_pad_for_patchingz$AriaImageProcessor._pad_for_patchingws? /u6GIZ[((9JKxxwx7 r.grmodeconstant_valuesc^t|tst|dk7rt||||||S| t |}t j dt jdt jdt jdi}tj|||||}|t|||}|S|}|S)a Pads the `image` with the specified `padding` and `mode`. Padding can be in the (`height`, `width`) dimension of in the (`num_patches`) dimension. In the second case an iterable if tuples is expected as input. Args: image (`np.ndarray`): The image to pad. padding (`int` or `tuple[int, int]` or `Iterable[tuple[int, int]]`): Padding to apply to the edges of the height, width axes. Can be one of three formats: - `((before_height, after_height), (before_width, after_width))` unique pad widths for each axis. - `((before, after),)` yields same before and after pad for height and width. - `(pad,)` or int is a shortcut for before = after = pad width for all axes. mode (`PaddingMode`): The padding mode to use. Can be one of: - `"constant"`: pads with a constant value. - `"reflect"`: pads with the reflection of the vector mirrored on the first and last values of the vector along each axis. - `"replicate"`: pads with the replication of the last value on the edge of the array along each axis. - `"symmetric"`: pads with the reflection of the vector mirrored along the edge of the array. constant_values (`float` or `Iterable[float]`, *optional*): The value to use for the padding if `mode` is `"constant"`. data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format for the output 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. If unset, will use same as the input image. input_data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format for 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. If unset, will use the inferred format of the input image. Returns: `np.ndarray`: The padded image. rEconstantreflectedge symmetric)rr) isinstancerbr`r rr CONSTANTREFLECT REPLICATE SYMMETRICrcr)rNrrrrrUr%padding_mode_mappings r,r zAriaImageProcessor.pads` gs #s7|q'8ugt_kK\] ]  $ >u E   *     ! !6  ! !;   ug,@,FXghR]Ri '{PTPfPf(g% *a 1?.0PS`0`dr0r r.)N)"__name__ __module__ __qualname____doc__model_input_namesrBICUBICrrfloatrbtuplererrMrFIRSTrstrrrsrcarrayrzrrr rndarrayrr r_r __classcell__)rQs@r,r0r0Js>D-1+/!!=A&+)-,3'+'9'A'A"!T%[)"!DK("! "!  "! $DsCx$9: "!d^"!!"!"!c5j)"!tn"!%"!N;?9=(,(,&*)-%)*.'+'+;?2B2H2HDHD j$z"223D U5$u+#567D E%e"456 D ! D ! D d^D !D TND !D tnD %D !sJ!78D ./D $E#/?*?$@AD LXX27Vf 4BUBuB XX 27 L\   "(009<>BDH@zz@sE#s(OXeCHo-FFG@ @ uhuo56 @ eC)9$9:; @$E#/?*?$@A@ @D0xx0U38_-0 0 % 0 & 0,0 bhh0d#cr.r0))collections.abcrtypingrrnumpyrcimage_processing_utilsrrr r image_transformsr r r rr image_utilsrrrrrrrrrrutilsrr get_loggerrr]rrbrr-r0__all__rKr.r,rs*%"uuee   )   H %RXX3dSUS[S[n8A+AH r.