EiAvSrSSKrSSKJr SSKJrJr SSKrSSKJr SSK J r "SS \R5r g) z, Implements the Generalized R-CNN framework N) OrderedDict)OptionalUnion)nn)_log_api_usage_oncec ^\rSrSrSrS\R S\R S\R S\R SS4 U4S jjr\RRS \ \ \R4S \\ \ \R4S\\ \ \R4\\ \ \R444S j5rSS \\RS\\\ \ \R4S\\ \ \R4\\ \ \R444SjjrSrU=r$)GeneralizedRCNNa@ Main class for Generalized R-CNN. Args: backbone (nn.Module): rpn (nn.Module): roi_heads (nn.Module): takes the features + the proposals from the RPN and computes detections / masks from it. transform (nn.Module): performs the data transformation from the inputs to feed into the model backbonerpn roi_heads transformreturnNcv>[TU]5 [U5 X@lXlX lX0lSUlg)NF)super__init__rrr r r _has_warned)selfr r rr __class__s j/home/mande/repo/quber/.venv/lib/python3.13/site-packages/torchvision/models/detection/generalized_rcnn.pyrGeneralizedRCNN.__init__s4 D!" " losses detectionsc,UR(aU$U$N)training)rrrs r eager_outputsGeneralizedRCNN.eager_outputs,s ==Mrimagestargetsc :UR(aUc[R"SS5 OUHnUSn[U[R5(aV[R"[ UR 5S:H=(a UR SS:HSUR S 35 M}[R"SS [U5S 35 M /nUH^nUR S Sn[R"[ U5S:HS UR S S35 URUS US45 M` URX5upUb[U5HupUSnUSS2SS24USS2SS24:*n U R5(dM8[R"U RSS95S S n XJR5n [R"SSU SUS 35 M URUR5n [U [R5(a[!SU 4/5n UR#XU5upUR%XUR&U5unnURR)XR&U5n0nUR+U5 UR+U5 [R,R/5(a2UR0(d[2R4"S5 SUlUU4$UR7UU5$)a Args: images (list[Tensor]): images to be processed targets (list[dict[str, tensor]]): ground-truth boxes present in the image (optional) Returns: result (list[BoxList] or dict[Tensor]): the output from the model. During training, it returns a dict[Tensor] which contains the losses. During testing, it returns list[BoxList] contains additional fields like `scores`, `labels` and `mask` (for Mask R-CNN models). NFz0targets should not be none when in training modeboxesz:Expected target boxes to be a tensor of shape [N, 4], got .z0Expected target boxes to be of type Tensor, got zJexpecting the last two dimensions of the Tensor to be H and W instead got r)dimzLAll bounding boxes should have positive height and width. Found invalid box z for target at index 0z=RCNN always returns a (Losses, Detections) tuple in scriptingT)rtorch_assert isinstanceTensorlenshapetypeappendr enumerateanywheretolistr tensorsrr r image_sizes postprocessupdatejit is_scriptingrwarningswarnr)rr!r"targetr$original_image_sizesimgval target_idxdegenerate_boxesbb_idxdegen_bbfeatures proposalsproposal_lossesrdetector_lossesrs rforwardGeneralizedRCNN.forward5s" == e%WX%F"7OE!%66  ,1Jekk"o6JXY^YdYdXeefg  !NtTY{m[\]&79C))BC.C MMCA \]`]f]fgigj]k\lm  ! ' 'QQ(8 9 ..9  &/&8" w#(AB<5BQB<#? #''))"[[)9)=)=!)=)DEaHKF,1M,@,@,BHMM..6Z7LZLXY['9==0 h - -"S(O#45H%)XXf%H" &*nnX&J\J\^e&f# O^^// **,@  o& o& 99 ! ! # ### ]^#' :% %%%fj9 9r)rr rr rr)__name__ __module__ __qualname____firstlineno____doc__rModulerr-r=unuseddictstrr0listrrrtuplerM__static_attributes__ __classcell__)rs@rr r sL !))!YY!99 ! 99 !  !  YY3 ,-;?S%,,EV@W;X tC%&T#u||2C-D(EE F<@P:U\\"P:$tC$5678P: tC%&T#u||2C-D(EE F P:P:rr ) rSr? collectionsrtypingrrr-rutilsrrTr rrr`s0#" (v:biiv:r