j)SrSSKJr SSKrSSKJs Jr SSKJr SSK J r SSK J r SSKJr SS KJrJr SS KJrJrJrJrJrJr SS KJrJr SS KJrJrJ r "S S\SS9r!\"SS\ 55r"S/r#g)zImage processor class for BEiT.)UnionN) functional)TorchvisionBackend)'SemanticSegmentationPostProcessorOutput) BatchFeature)group_images_by_shapereorder_images)IMAGENET_STANDARD_MEANIMAGENET_STANDARD_STDChannelDimension ImageInputPILImageResamplingSizeDict) ImagesKwargsUnpack) TensorTypeauto_docstringis_torch_availablec$\rSrSr%Sr\\S'Srg)BeitImageProcessorKwargs&aW do_reduce_labels (`bool`, *optional*, defaults to `self.do_reduce_labels`): Whether or not to reduce all label values of segmentation maps by 1. Usually used for datasets where 0 is used for background, and background itself is not included in all classes of a dataset (e.g. ADE20k). The background label will be replaced by 255. do_reduce_labelsN)__name__ __module__ __qualname____firstlineno____doc__bool__annotations____static_attributes__rڼC:\Users\johnn\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.13_qbz5n2kfra8p0\LocalCache\local-packages\Python313\site-packages\transformers/models/beit/image_processing_beit.pyrr&sr#rF)totalc^\rSrSrSr\r\Rr \ r \ r SSS.rSrSSS.rSrSrSrSrSrS\\4U4Sjjr\S*S \S \S -S\\S \4U4S jjj5rS*S \S \S -S\S\S\\-S -S\ \S4S -S \4Sjjr!S\"SS \"S4Sjr#S+S \"SS\S\$SSS\S\$S\S\%S\S \%\"\%-S -S!\%\"\%-S -S"\S -S#\S \"S4S$jjr&S,S%\"\'S -S&\S S'4S(jjr(S)r)U=r*$)-BeitImageProcessor1z/PIL backend for BEiT with reduce_label support.)heightwidthTFkwargsc &>[TU]"S0UD6 g)Nr)super__init__)selfr, __class__s r$r/BeitImageProcessor.__init__Cs "6"r#Nimagessegmentation_mapsreturnc &>[TU]"X40UD6$)zX segmentation_maps (`ImageInput`, *optional*): The segmentation maps to preprocess. )r. preprocess)r0r3r4r,r1s r$r7BeitImageProcessor.preprocessFsw!&FvFFr#do_convert_rgbinput_data_formatreturn_tensorsdevicez torch.devicec URXXFS9nUR5nSUS'0n UR"U40UD6U S'UbURUSS[RS9n UR5n U R SSS.5 UR"S SU 0U D6n U V s/sH1n U R S 5R[R5PM3 n n XS '[XS 9$s sn f) z"Handle extra inputs beyond images.)r3r9r:r<Fr pixel_values)r3expected_ndimsr9r:) do_normalize do_rescaler3rlabels)data tensor_typer) _prepare_image_like_inputscopy _preprocessr FIRSTupdatesqueezetotorchint64r) r0r3r4r9r:r;r<r, images_kwargsrDprocessed_segmentation_mapssegmentation_maps_kwargsprocessed_segmentation_maps r$_preprocess_image_like_inputs0BeitImageProcessor._preprocess_image_like_inputsSs!00L]1  ,1 ()#//H-H^  (*.*I*I( $"2"8"8 +J+ '(.{{} $ $ + +URW,X Y*.*:*:+2+6N+ '3N+2M.+221588E2M (+9NBB +s8C$rCz torch.Tensorc b[[U55HnXn[R"US:H[R"SUR UR S9U5nUS- n[R"US:H[R"SUR UR S9U5nX1U'M U$)z/Reduce label values by 1, replacing 0 with 255.r)dtyper<)rangelenrMwheretensorrWr<)r0rCidxlabels r$ reduce_labelBeitImageProcessor.reduce_labelsV%CKEKK ELLEKKX]XdXd,eglmEAIEKK ell3ekkZ_ZfZf.ginoE3K &  r# do_resizesizeresamplez7PILImageResampling | tvF.InterpolationMode | int | Nonedo_center_crop crop_sizerBrescale_factorrA image_mean image_stddisable_groupingrc U (aURU5n[XS9unn0nUR5H$unnU(aURUX45nUUU'M& [ UU5n[UU S9unn0nUR5H8unnU(aUR UU5nUR UXxXU 5nUUU'M: [ UU5nU$)zCustom preprocessing for BEiT.)rj)r`r itemsresizer center_croprescale_and_normalize)r0r3rbrcrdrerfrBrgrArhrirjrr,grouped_imagesgrouped_images_indexresized_images_groupedshapestacked_imagesresized_imagesprocessed_images_groupedprocessed_imagess r$rHBeitImageProcessor._preprocesss$ &&v.F0EV/o,,!#%3%9%9%; !E>!%^T!L,: "5 )&<((>@TU0E^fv/w,,#% %3%9%9%; !E>!%!1!1.)!L!77 LV_N/= $U +&<**BDXYr# target_sizesreturn_segmentation_scoreszBlist[torch.Tensor] | list[SemanticSegmentationPostProcessorOutput]c[5(d [S5eURnUb[U5[U5:wa [ S5e[ U[ R5(aUR5n/n[[U55HZn[R"XFRSS9X&SSS9nUSRSS9nUR[XSS.S 95 M\ OEURS S9n [UR S5V s/sHn [XXJS.S 9PM nn U(dUV s/sHoR"PM nn U$s sn fs sn f) ag Converts the output of [`BeitForSemanticSegmentation`] into semantic segmentation maps. Args: outputs ([`BeitForSemanticSegmentation`]): Raw outputs of the model. target_sizes (`list[Tuple]` of length `batch_size`, *optional*): List of tuples corresponding to the requested final size (height, width) of each prediction. If unset, predictions will not be resized. return_segmentation_scores (`bool`, *optional*, defaults to `False`): Whether to return segmentation scores alongside the segmentation map. When `True`, each element of the returned list is a [`SemanticSegmentationPostProcessorOutput`] with fields `segmentation` (class IDs, shape `(height, width)`) and `segmentation_scores` (shape `(num_classes, height, width)`). Returns: `list[torch.Tensor]` or `list[SemanticSegmentationPostProcessorOutput]`: When `return_segmentation_scores=False` (default), a list of length `batch_size` where each item is a segmentation map of shape `(height, width)` with class IDs. When `return_segmentation_scores=True`, a list of [`SemanticSegmentationPostProcessorOutput`] with fields `segmentation` (class IDs, shape `(height, width)`) and `segmentation_scores` (shape `(num_classes, height, width)`). In both cases, `(height, width)` corresponds to the target size (if `target_sizes` is specified). z:PyTorch is required for post_process_semantic_segmentationzTMake sure that you pass in as many target sizes as the batch dimension of the logitsr)dimbilinearF)rcmode align_corners) segmentationsegmentation_scores)rDrX)r ImportErrorlogitsr[ ValueError isinstancerMTensornumpyrZF interpolate unsqueezeargmaxappendrrsr) r0outputsryrzrsemantic_segmentationr^resized_logits semantic_mapseg_mapsiitems r$"post_process_semantic_segmentation5BeitImageProcessor.post_process_semantic_segmentationss2"##Z[ [  #6{c,// j, 55+113 $& !S[)!"K))a)0|7Hzin" .a077A7> %,,;.:bcSde *}}}+H v||A/ %0A8*2+fiX0 "%*CX$YCX4%6%6CX !$Y$$%%Zs EEr)N)F)NF)+rrrrrr valid_kwargsrBICUBICrdr rhr rircdefault_to_squarerfrbrerBrArrr/rrrr7r r strrrrSlistr`rfloatrHtuplerr" __classcell__)r1s@r$r'r'1s?9+L!))H'J%IC (D-IINJL#(@!A#04 G G&, G12 G  G G&59*C*C&,*C *C , *C j(4/ *Cc>)*T1*C *CX4#7Drsr& 7;O2E5CC|5E%+E%E%P r#