+ j^RIt^RIHuHt^RIHt^RIHt^RI H t H t ^RI H t Ht^RIHt^RIHt^RIHt]]!R R 7!R R ]444tR .tR#) N) BatchFeature)TorchvisionBackend)group_images_by_shapereorder_images)PILImageResamplingSizeDict)auto_docstring) TensorType)requires)backendscta]tRt^"toRtRtRRRR/t]Pt V3RlRlt R V3RlR llt R t Vt R #) UVDocImageProcessorTheightiwidthic<V^8dQhRS[R,RS[RS[RS[RS[RS[RS[S[S[,,R ,R S[S[S[,,R ,R S[R ,R S[S[,R ,R S[/ #)imagesz torch.Tensor do_resizesize do_rescalerescale_factor do_normalize image_meanN image_stddisable_groupingreturn_tensorsreturn)listboolrfloatstrr r)format __classdict__s"q/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/uvdoc/image_processing_uvdoc.py __annotate__ UVDocImageProcessor.__annotate__*s/ / ^$/ /  /  /  / / DK'$./ 4;&-/ +/ j(4//  / c \WR7wr/pV P4F-wppVPVWEWgV4pVR.RORR3,pVW&K/ \W4pVP 4p\VV R7wr/pV P4FCwppV'd1\ P !VVPVP3RRR7pVVV&KE \VV 4p\RVRV/V R.R7#) )r:NNNbilinearTrmode align_corners pixel_valuesoriginal_images)data tensor_typeskip_tensor_conversion)rr) ritemsrescale_and_normalizercopyF interpolaterrr)selfrrrrrrrrrrkwargsgrouped_imagesgrouped_images_indexprocessed_images_groupedshapestacked_imagesrescale_and_normalize_imagesr.interpolated_images_groupedr-s&&&&&&&&&&&, r$ _preprocessUVDocImageProcessor._preprocess*s 0EV/o,#% %3%9%9%; !E>!77 LV_N,Ay!Q,>?N.< $ + &<(66N'e$6;;=/D (;K0 ,')#%3%9%9%; !E>!""$++tzz)Bcg"2@ ' . &<&&ACWX  ,0A?S&$5#6  r'c <V^8dQhRS[PRS[S[P,RS[RS[S[S[S[P3,,/#)r predictionr.scaler)torchTensorrr dictr!)r"r#s"r$r%r&[sS55LL5ell+5 5 d3 $% & 5r'c \V4p\P!R \V4VPR7p.p\ V4EFwrgVP ^8XdVP^4pVPVP4pVPR,wr\P!WV^,W3RRR7p V P^^^^4p \P!W{RR7p V P^4P^^^4p W,p V PR .R7P\P RRR 7p VP#R V /4EK V#) aN Post-process document rectification predictions to convert them into rectified images. Args: prediction: Predicted 2D Bezier mesh coordinates, shape (B, 2, H, W) original_images: List of original input tensors, each of shape (C, H_i, W_i). Images may have different sizes. scale: Scaling factor for output images (default: 255.0) Returns: List of dictionaries containing rectified images. Each dictionary has: - "images": Rectified image tensor of shape (H, W, 3) with dtype torch.uint8 and BGR channel order (suitable for OpenCV visualization) )device:rNNr)Tr*)r,)dimsF)dtype non_blockingr5r)rrFfullr rJ enumeratendim unsqueezetor=r6r7permute grid_samplesqueezeflipuint8append)r8rDr.rE image_listresultsioriginal_imageoriginal_heightoriginal_widthupsampled_meshrearranged_mesh rectifiedimages&&&& r$#post_process_document_rectification7UVDocImageProcessor.post_process_document_rectification[sF&/*  2uU|J4E4EF!*:!6 A""a'!/!9!9!!<+..z/@/@AN.<.B.B2.F +O]]q1u%%6" N-44Q1a@O nUYZI%%a(00Aq9EMEJJRDJ),,5;;TX],^E NNHe, -9"7<r'rNN)go@)__name__ __module__ __qualname____firstlineno__rrrrBILINEARresamplerAre__static_attributes____classdictcell__)r#s@r$rr"sDJI c7C (D!**H/ / b555r'r)rF)rFtorch.nn.functionalnn functionalr6feature_extraction_utilsrimage_processing_backendsrimage_transformsrr image_utilsrrutilsr utils.genericr utils.import_utilsr r__all__rNr'r$rzs\, 4;E7#'* :l,ll^ ! !r'