hSSKJr SSKJr SSKrSSKJrJr SSKJ r SSK J r SSK J r \ \ S .rSS \S \S S4S jjrSS \S \S S4SjjrS\S \S S4Sjrg))partial)PathN)YAMLIterableSimpleNamespace) check_yaml)BOTSORT) BYTETracker) bytetrackbotsort predictorpersistreturnc^TRRS:Xa [S5e[TS5(aU(ag[ TRR 5n[ S0[R"U5D6nURS;a[SURS35eSTl [TS5(aTRR5 URS :XGa UR(aURS :XaS S KJn [%TRR[&R(R*5(ad[%TRRRS U5(a2TRRRS R,(aSUlO=U4SjnTRRRS R/U5Tl /n[1TR2R45HHn[6UR"USS9nUR9U5 TR2R:S:wdMH O UTlS/TR2R4-Tlg)a Initialize trackers for object tracking during prediction. Args: predictor (ultralytics.engine.predictor.BasePredictor): The predictor object to initialize trackers for. persist (bool, optional): Whether to persist the trackers if they already exist. Examples: Initialize trackers for a predictor object >>> predictor = SomePredictorClass() >>> on_predict_start(predictor, persist=True) classifyu/❌ Classification doesn't support 'mode=track'trackersN>r r z?Only 'bytetrack' and 'botsort' are supported for now, but got ''_hookr autor)Detectzyolo11n-cls.ptc,>[US5Tlg)Nr)list_feats)moduleinputr s T/home/james-whalen/.local/lib/python3.13/site-packages/ultralytics/trackers/track.pypre_hook"on_predict_start..pre_hook9s#'a>  )args frame_ratestream) r"task ValueErrorhasattrrtrackerrrload tracker_typeAssertionErrorrrremove with_reidmodelultralytics.nn.modules.headr isinstancetorchnnModuleend2endregister_forward_pre_hookrangedatasetbs TRACKER_MAPappendmodervid_path)r rr)cfgrrr_s` ron_predict_startr@s~~j(JKKy*%%'//0G ! 7DIIg$6 7C 77^_b_o_o^ppqrssIy'""  9$399;N6 y,,ehhoo > >9??0066r:FCCOO))//3;;(CI 2(oo3399"=WWX`aIOH 9$$'' (c../SRH    ! !X -  ) "I)"3"3"6"66Ir c URRS:HnURRS:Hn[ UR 5GH~upEUR U(aUOSnUR[UR5R- nU(dCURU(aUOSU:wa'UR5 XpRU(aUOS'U(a URO URR5R!5nUR#XR$['USS55n [)U 5S:XaGMU SS2S4R+[,5n XZUR U'U(aSOS[.R0"U SS2SS2450n UR UR""S0U D6 GM g) a Postprocess detected boxes and update with object tracking. Args: predictor (object): The predictor object containing the predictions. persist (bool, optional): Whether to persist the trackers if they already exist. Examples: Postprocess predictions and update with tracking >>> predictor = YourPredictorClass() >>> on_predict_postprocess_end(predictor, persist=True) obbr$rfeatsNrboxesr%)r"r&r8r< enumerateresultsrsave_dirrpathnamer=resetrBrDcpunumpyupdateorig_imggetattrlenastypeintr2 as_tensor) r ris_obb is_streamiresultr)r=dettracksidx update_argss ron_predict_postprocess_endr\Hse^^ E )F!!&&(2Iy001 $$)Q;%%V[[(9(>(>>9--9a!DP MMO8@  Iq1 5#vzz::<BBD__gfgt6TU v;!  QUm""3'%{ ! &uGU__VAsPRsF^5TU !##2k22r r/c|URS[[US95 URS[[US95 g)aq Register tracking callbacks to the model for object tracking during prediction. Args: model (object): The model object to register tracking callbacks for. persist (bool): Whether to persist the trackers if they already exist. Examples: Register tracking callbacks to a YOLO model >>> model = YOLOModel() >>> register_tracker(model, persist=True) r@)rr\N) add_callbackrr@r\)r/rs rregister_trackerr_is7 )73CW+UV 3W=Wah5ijr )F) functoolsrpathlibrr2ultralytics.utilsrrultralytics.utils.checksrbot_sortr byte_trackerr r:objectboolr@r\r_r%r rrhs| ;/%(G< 373737$37l3&343D3BkFkTkdkr