ZjH, "SSKrSSKJr SSKJr SSKrSSKJr SSKJ r SSK J r J r SSK JrJrJrJr SS KJr SS KJrJrJr S S KJr \(aSS KJr SSKJr SSS\\\-S\ S\S\4 Sjr!"SS\SS9r"\"SS\55r#S/r$g)N)Iterable) TYPE_CHECKING)TorchvisionBackend) BatchFeature)group_images_by_shapereorder_images)IMAGENET_STANDARD_MEANIMAGENET_STANDARD_STDPILImageResamplingSizeDict) ImagesKwargs) TensorTypeauto_docstringrequires_backends)BeitImageProcessor)DepthEstimatorOutput) functional input_image torch.Tensor output_sizekeep_aspect_ratiomultiplereturncSSjnURSSupVUupxXu- n X- n U(a#[SU - 5[SU - 5:aU n OU n U"X-US9n U"X-US9n [XS9$)Nc[X- 5U-nUb XC:a[R"X- 5U-nXB:a[R"X- 5U-nU$N)roundmathfloorceil)valrmin_valmax_valxs t/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/dpt/modular_dpt.pyconstrain_to_multiple_of>get_resize_output_image_size..constrain_to_multiple_of0sQ #. !H ,  1; 3>*X5A ; #.)H4A)rheightwidth)rN)shapeabsr ) rrrrr( input_height input_width output_height output_width scale_height scale_width new_height new_widths r'get_resize_output_image_sizer:*s !, 1 1"# 6L"-M!/L,K q; #a,&6"7 7&L'K),*EPXYJ()BXVI : 77r*cB\rSrSr%Sr\\S'\\S'\\S'\\S'Srg) DPTImageProcessorKwargsQa ensure_multiple_of (`int`, *optional*, defaults to 1): If `do_resize` is `True`, the image is resized to a size that is a multiple of this value. Can be overridden by `ensure_multiple_of` in `preprocess`. keep_aspect_ratio (`bool`, *optional*, defaults to `False`): If `True`, the image is resized to the largest possible size such that the aspect ratio is preserved. Can be overridden by `keep_aspect_ratio` in `preprocess`. do_reduce_labels (`bool`, *optional*, defaults to `self.do_reduce_labels`): Whether or not to reduce all label values of segmentation maps by 1. Usually used for datasets where 0 is used for background, and background itself is not included in all classes of a dataset (e.g. ADE20k). The background label will be replaced by 255. ensure_multiple_of size_divisorrdo_reduce_labelsN) __name__ __module__ __qualname____firstlineno____doc__int__annotations__bool__static_attributes__rAr*r'r<r<Qs! r*r<F)totalc$\rSrSr\R r\r\ r SSS.r Sr Sr SrSrSrSrSrSrSrSr\rS'S S S \S S S\S\S-S\SS 4SjjrS(S S S\SS 4SjjrS\S S\S\S \S S S\S\S\S\S\S\\\-S-S\\\-S-S\S\S-S\S\S-S \S-S\4$S!jr S)S"S#S$\!\\"\\4-S-S-S\\#\$\!44S%jjr%S&r&g)*DPTImageProcessoreir-TFgp?r,Nimagersizeresamplez7PILImageResampling | tvF.InterpolationMode | int | None antialiasr>rrcUR(aUR(d[SUR535e[ UURUR4UUS9n[ R "XXsUS9$)a Resize an image to `(size["height"], size["width"])`. Args: image (`torch.Tensor`): Image to resize. size (`SizeDict`): Dictionary in the format `{"height": int, "width": int}` specifying the size of the output image. interpolation (`InterpolationMode`, *optional*, defaults to `InterpolationMode.BILINEAR`): `InterpolationMode` filter to use when resizing the image e.g. `InterpolationMode.BICUBIC`. antialias (`bool`, *optional*, defaults to `True`): Whether to use antialiasing when resizing the image ensure_multiple_of (`int`, *optional*): If `do_resize` is `True`, the image is resized to a size that is a multiple of this value keep_aspect_ratio (`bool`, *optional*, defaults to `False`): If `True`, and `do_resize` is `True`, the image is resized to the largest possible size such that the aspect ratio is preserved. Returns: `torch.Tensor`: The resized image. zDThe size dictionary must contain the keys 'height' and 'width'. Got )rrr)rQrR)r.r/ ValueErrorkeysr:rresize)selfrOrPrQrRr>rrs r'rVDPTImageProcessor.resizezsj:{{$**cdhdmdmdocpqr r2 djj1/'  "((k`ijjr*r?cURSSup4SnU"X25upgU"XB5upXX4n [R"X5$)aL Center pad a batch of images to be a multiple of `size_divisor`. Args: image (`torch.Tensor`): Image to pad. Can be a batch of images of dimensions (N, C, H, W) or a single image of dimensions (C, H, W). size_divisor (`int`): The width and height of the image will be padded to a multiple of this number. r+NcX[R"X- 5U-nX - nUS-nX4- nXE4$)Nr)r r")rPr?new_sizepad_size pad_size_leftpad_size_rights r'_get_pad-DPTImageProcessor.pad_image.._get_pads9yy!45 DHH$MM%5N 0 0r*)r0tvFpad) rWrOr?r.r/r_pad_top pad_bottompad_left pad_rightpaddings r' pad_imageDPTImageProcessor.pad_imagesP BC(  1'v<&u;i<wwu&&r*imagesr@ do_resizedo_center_crop crop_size do_rescalerescale_factor do_normalize image_mean image_stddo_paddisable_groupingc U(aURU5n[UUS9unn0nUR5H%unnU(aURUUUUU S9nUUU'M' [ UU5n[UUS9unn0nUR5HQunnU(aUR UU5nUR UXXU 5nU(aURUU5nUUU'MS [ UU5nU$)N)rt)rOrPrQr>r) reduce_labelritemsrVr center_croprescale_and_normalizerh)rWrjr@rkrPrQrlrmrnrorprqrrrr>rsr?rtkwargsgrouped_imagesgrouped_images_indexresized_images_groupedr0stacked_imagesresized_imagesprocessed_images_groupedprocessed_imagess r' _preprocessDPTImageProcessor._preprocesss'* &&v.F0EV^n/o,,!#%3%9%9%; !E>!%(%'9&7 "-"-; "5 )&<((>@TU0E^fv/w,,#% %3%9%9%; !E>!%!1!1.)!L!77 LV_N!% !M.< $U +&<**BDXYr*outputsr target_sizesc[US5 URnUb#[U5[U5:wa [S5e/nUcS/[U5-OUn[ X25HqupVUbV[ R RRURS5RS5USSS9R5nURS U05 Ms U$) aj Converts the raw output of [`DepthEstimatorOutput`] into final depth predictions and depth PIL images. Only supports PyTorch. Args: outputs ([`DepthEstimatorOutput`]): Raw outputs of the model. target_sizes (`TensorType` or `List[Tuple[int, int]]`, *optional*): Tensor of shape `(batch_size, 2)` or list of tuples (`Tuple[int, int]`) containing the target size (height, width) of each image in the batch. If left to None, predictions will not be resized. Returns: `List[Dict[str, TensorType]]`: A list of dictionaries of tensors representing the processed depth predictions. torchNz]Make sure that you pass in as many target sizes as the batch dimension of the predicted depthrr,bicubicF)rPmode align_cornerspredicted_depth) rrlenrTziprnnr interpolate unsqueezesqueezeappend)rWrrrresultsdepth target_sizes r'post_process_depth_estimation/DPTImageProcessor.post_process_depth_estimations( $(!11  $3+?3|CT+To 8D8LvO 44R^ "%o"D E&++77OOA&003+Iej8') NN-u5 6 #Er*rA)Tr,F)r,r)'rBrCrDrEr BICUBICrQr rqr rrrPrkrnrprsror>rrmrlr@r< valid_kwargsr rIrGrVrhlistfloatrrrtupledictstrrrJrAr*r'rMrMes"!))H'J%IC (DIJL FNIN*L)*"'&k&k&kL &k  &k  $J &k &k &kV'''  '88 ^$8 8  8  8 L 8 8 8 8 8 8 DK'$.8 4;&-8  8  $J8 !8 "Dj#8 $+%8 ( )8 zJN'''!4c3h#884?$F' d3 ?# $ ''r*rM)%r collections.abcrtypingrrimage_processing_backendsrimage_processing_baserimage_transformsrr image_utilsr r r r processing_utilsrutilsrrrbeit.image_processing_beitrmodeling_outputsrtorchvision.transforms.v2rrarGrIr:r<rM__all__rAr*r'rs  $ ;1E -BB;87$8$8x}$$8$8 $8  $8Nl%(y*yyx  r*