+ j)Rt^RIHt^RIt^RIHuHt^RIHt ^RI H t ^RI H t ^RIHt^RIHtHt^RIHtHtHtHtHtHt^R IHtHt^R IHtHtH t !R R ]R R7t!]!RR] 44t"R.t#R#)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_availablec0a]tRt^&toRtV3RltRtVtR#)BeitImageProcessorKwargsaW 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. c&<V^8dQh/S[;R&#)do_reduce_labels)bool)format __classdict__s"o/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/beit/image_processing_beit.py __annotate__%BeitImageProcessorKwargs.__annotate__&sN)__name__ __module__ __qualname____firstlineno____doc____annotate_func____static_attributes____classdictcell__)rs@rrr&srrF)totalcaa]tRt^1toRt]t]Pt ] t ] t R^R^/tRtR^R^/tRtRtRtRtRtV3RlV3Rllt]RV3RlV3R lll4tRV3R lR lltV3R lR ltRV3RlRlltRV3RlRlltRtVtV;t#)BeitImageProcessorz/PIL backend for BEiT with reduce_label support.heightwidthTFc0<V^8dQhRS[S[,/#)rkwargs)rr)rrs"rrBeitImageProcessor.__annotate__Cs##(@!A#rc (<\SV`!R/VBR#)Nr )super__init__)selfr/ __class__s&,rr3BeitImageProcessor.__init__Cs "6"rcP<V^8dQhRS[RS[R,RS[S[,RS[/#)rimagessegmentation_mapsNr/return)r rrr)rrs"rrr0GsD G G G&, G12 G  Grc &<\SV`!W3/VB#)zX segmentation_maps (`ImageInput`, *optional*): The segmentation maps to preprocess. )r2 preprocess)r4r8r9r/r5s&&&,rr<BeitImageProcessor.preprocessFsw!&FvFFrc<V^8dQhRS[RS[R,RS[RS[RS[S[,R,RS[S[R3,R,R S[/#) rr8r9Ndo_convert_rgbinput_data_formatreturn_tensorsdevicez torch.devicer:)r rr strrrr)rrs"rrr0Ssx*C*C*C&,*C *C , *C j(4/ *Cc>)*T1*C *Crc VPWWFR7pVP4pRVR&/p VP!V3/VBV R&VeVPV^R\PR7p VP4p V P RRRR/4VP!R RV /V Bp V U u.uF1p V P ^4P\P4NK3 p p WR &\WR 7#uup i) z"Handle extra inputs beyond images.)r8r?r@rBFr pixel_values)r8expected_ndimsr?r@ do_normalize do_rescaler8labels)data tensor_typer ) _prepare_image_like_inputscopy _preprocessr FIRSTupdatesqueezetotorchint64r) r4r8r9r?r@rArBr/ images_kwargsrJprocessed_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+ '(.{{} $ $ + +^ULRW,X Y*.*:*:+2+6N+ '3N+2M.+221588E2M (+9NBB +s%7C.cB<V^8dQhRS[R,RS[R,/#)rrI torch.Tensorr:)list)rrs"rrr0s%4#7D!%^T!L,: "5 )&<((>@TU0E^fv/w,,#% %3%9%9%; !E>!%!1!1.)!L!77 LV_N/= $U +&<**BDXYrcH<V^8dQhRS[S[,R,RS[RR/#)r target_sizesNreturn_segmentation_scoresr:zBlist[torch.Tensor] | list[SemanticSegmentationPostProcessorOutput])r]tupler)rrs"rrr0s3@%@%%)%[4%7@%\`@% M@%rc  0\4'g \R4hVPpVe\V4\V48wd \ R4h\ V\ P4'dVP4p.p\\V44Fxp\P!WF,P^R7W&,RRR7pV^,P^R7pVP\RVRV^,/R 74Kz MWVP^R7p \VP ^,4U u.uFp \RW,RWJ,/R 7NK! pp V'gVU u.uFqP"NK pp V#uup iuup i) 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 logits)dimbilinearF)rjmode align_corners segmentationsegmentation_scores)rJ)r ImportErrorlogitsra ValueError isinstancerSTensornumpyr`F interpolate unsqueezeargmaxappendrr{r) r4outputsrrrsemantic_segmentationrdresized_logits semantic_mapseg_mapsiitems &&&& r"post_process_semantic_segmentation5BeitImageProcessor.post_process_semantic_segmentations2"##Z[ [  #6{c,// j, 55+113 $& !S[)!"K))a)0|7Hzin" .a077A7> %,,;,lrsr& 7;O2E5CC|5E%+E%E%P r