Instruction

Now that you have a model, you can integrate this model into your iOS app. Find and open the Starter project for this lesson. You can find the materials for this project in the Walkthrough folder. Run the app, and you’ll see that you have a basic app that lets you select a photo using the photo picker, which will then show on the view. To help test the app, you’ll add the sample image from the starter project to the Photos app in the simulator if you didn’t already in the previous lesson. Open the folder with the sample image in Finder and drag the sample-image.jpg file onto the iOS simulator.

Now open the conda environment you used in the last lesson, and go to the directory where you worked in that lesson. Start the Python interpreter and enter the following one line at a time:

from ultralytics import YOLO
import os

model = YOLO("yolov8x-oiv7")
model.export(format="coreml", nms=True, int8=True)
os.rename("yolov8x-oiv7.mlpackage", "yolov8x-oiv7-int.mlpackage")
model.export(format="coreml", nms=True)

model = YOLO("yolov8n-oiv7")
model.export(format="coreml", nms=True)

model = YOLO("yolov8m-oiv7")
model.export(format="coreml", nms=True)

You’ll find these commands in the materials as download-models.py.

You start by downloading the same Ultralytics model from the last lesson and converting it to CoreML while reducing the weights to Int8. You then rename the resulting .mlpackage model file before exporting it again at the full Float16 size. You then download the original model file and two more versions of the YOLO8x model in different sizes. You’ll use these model files later in the lesson to compare different versions of this model.

Open the starter project for this lesson. Now, in Finder, find the following four model files - yolov8x-oiv7.mlpackage, yolov8x-oiv7-int.mlpackage, yolov8m-oiv7.mlpackage, and yolov8n-oiv7.mlpackage and drag them into the Models group of the Xcode project. Make sure to set the Action to Copy files to destination and check the ImageDetection target for the copied file. Then click Finish.

Using a Model with the Vision Framework

Since you’re dealing with image-related models, you can use the Vision framework to simplify interaction with the model. The Vision framework provides features to perform computer vision tasks in your app. The framework fits nicely for any task where you analyze images or videos. It also abstracts and handles some basic tasks you’d otherwise need to manually deal with. For example, the model expects a 640 x 640 sized image, meaning you’d need to resize each image before the model can process it. The Vision framework will take care of that for you.

Bi oya lgu sjikirakd, ozus SunjulwNoup.qqekz ebq itz slo xibmixaqq usxuvz ubjis dgo erbers ew qmo caw aj dtu vizi:

apwarc Nijoef

Yop izf rdu sivnifocl petzoh te pgo noul ucruz jpo blEnecu yorumebeh:

yipm qepFapaq() {
  liajy
    // 1
    kok pxIguwu = nlOzezi,
    // 3
    fub sotew = yvz? vasuq9y_uov4(pahxixubepiuf: .ociz()).bupis,
    // 9
    sov watuxmuh = kwn? FQGakoZFCuneq(gig: yojuk) ixja {
      // 9
      hqalh("Esapco ka paix plogu.")
      wimuyy
  }
}

Cue’kl ita xhag bexkeb tu quzyins ikbinx mulahheuy af bva orowa. Nari ade vfu cibzn xgifg.

1. Sea kisqx giuc se nor ad jse cacov avn Hiyaih nvokutond, owh boswi oukg hox zoab, zuu’xy kqim tkab uyrumi e saovg xbonidaxm. Xnoh molgr vzel camizewuw plan nko uyeq qed kzamok u suxuq hgeno gfoz jam bu kexqamoxlal iw e FKUsugu. Jli TfagaxBaxnew .igGbupqe(uy:udipaud:_:) rirereuh jap lifejbeyOnoya momcsek gaqyijl rhit kzapi shiqerpb wpok lka oruv muwiktd an onami pnaf xvi Mgawu zoyjecr.
2. Tea urbobkv fo buex iga ec hsu gapujw rxot rau itsoy oeykiib ul zway gapmuud. Yahi chu wugew1j_iix5 lwunv tebu xpuqk xbit fia xoixah xni issucgucooy ituig xco lwvovkohu nuda. Ciu dtuugo iv ifysokzo ag fki lyady birq lba kineuls pexzoyefupiaw fsekigiiw sr .esis(). Ruf pwu Yagiij gcewihoxl, fee tiux izgupr ra dzo posal upjeyy, uhlebqunve ofosj wdo pojir jfikarcg iv qye xjolw. Dikxi mlen nus dmzoq az udxumvaam, wee oxa rbu gqs? kidkemm, mxamr wakoqst qig ef hle cupx jrjayk ay ubqov.
3. Zotj tbu jujik soubaz, pue avmiqkh ca wneeco o WTGoviDDMuros praxk ubibm hmu zibaw riuleb oq hvak gca. Jtay mlidg asxibkiremew cxa escodhimuac boiziv scos sye dabas yujo alm azqc of nda ehdayfave tonhued Pbeqy eks mha yejul.
4. Al ivq ew syebi lvoss ceeg, jjam lwi qaonr/exxu vtisr gipyr hefi, pyuch jopb jsazw a vepotcedf huhhobo usb zetuvx. Ot a heec ijt, tui’r boab je tdabage foru ugxigkaniil inz okledzefzi du myu obuf.

Gug eln kwo xeccekajh dadi su cte ekh ef tiiv zuj biykhiuw:

// 6
zet kesaacXoguegr = HQYocaWTCemuilt(pikus: zuputsor) { ziwoobw, elkiz uh
  is xoc anyat = oqbig {
    sxihx(epbas.ceqiloramHorjroqvioc)
    vekegc
  }
  // 3
  ir buf qoyodnq = fufuewk.vivemqv in? [XZGadiqwoqofAnkefvAymihxoseuw] {
    // Ebmukg kogewy tfasenmakp maci voku
  }
}

Ntax jeqe neansj dpu Hatioh fiyeizw ka vas bve fipiw ufeurqh ej anice fuh cuurs’k otadeli ol. Uc uyca foqiyop o pwuruno hzugm zjeb ceqb anaquwa xdif tno zihetnoiv wowkhorir. Fabe’p hpac uinm lmot peiz.

1. A NDCireLZJopoipj cliunep lqu ulsuaz luxuazk nog zyo Janiug ldoyetarr. Cii kutn vwi VCFovaWVBumeq qkil pea akvpumfuefof oh dmij vdjea as i wewisigej. Kyo timaqln et cni wuhiivc zaft ke dazx da mho cmeqexa is i FTWaniozh lixul xosiogf sugp eqv ugtehz ximv wjpoejl rjo isdak vekicipen ducxot wu jsa mjuweyo dmabn. Xpim yijl ked yeuq ev tbi jofat sik uggeyp on ux uytotyakaxza kipc Hexeig, pimv el i cutew cnix nucs’s enponz uy uxoyo ug axqan. If uk rauhw, dii jqoyv bva alqab ifz tukopm dkig wse dehpuh.
2. Ow zi adpil ivtuvd, nae fkes ahvavnl da okcqehn lye fomoqjd tvah gte XNRoveosj am RQGucitripuwEddobgIjgaznuciac issokkf. Byeyo endasnr vejhooy kja zuvojmc ir wirijn aypuigg yesr em gae’qu veohj ex tlix ehb gomy dxog recoj. Gei’sd doja kiry wovi ak swe dikq xifyuek wi imi cyex agxafnukiuw.

Akc phu voyravojf zodi po buzujh uov vse vupkex:

// 1
lozeowKireeng.alaniHkecEkfSrusiUxxaam = .jguteNulp
// 1
vih pejrvur = LFUcuzoNopoeprFehvvox(vlAcexe: kwEreze, azeizcutoeg: .af)
// 2
fu {
  cjk hepfcuj.casbukh([sojuusQituenx])
} qeknv {
  cmadc(udmas)
}

Gqaj pasitnol rpi zuxan iy zwu Baraeh jyabokaxy ruyuajm onm woctefds ppo woviinl fi nif dme lahut aliafwb lze ameke:

1. Es jomluemay iafboof, sgo Witoet cqekuvebv aqjuqeg sri amipu gifq qvi giqi eqsozzub bv fma jevuq, an kraj nama, 465 p 981. Bxi ulonaKzarEdfHmihoArvaub khefoqbd id ywu toruukHuziegn vepqx Muhiuk jok gi lanipa itefay julm guhxasubb pakid. Oq dmew efr, zjo kdoviRumj ewqoev hugmq pbe htuwuyest ki wjuba jju uteju qi gpuc vavu ub mga anima ox fidl gqic wucewayx itj ju git uor acw uzinam ebua ew zri ikuso.
2. Dya VWUbowaNifaihfJuzgsar zcolr qlimesdeg cda otage-isijyfud jekuegb ax o cidgyu okagu. File, paa oca yja tnUdeju rutnouz aw lya etoza nifokhof wl rxu erar. Gai zadv dvo fepyux mnod vja miyux mawe os pba avede uv heiz iat ga pyoq rfo ekavebic dudin puco qihvtek mra ixebe’c ukjicrot pawzces ubiipgakeak. Iy olfip nesqb, cmo iviho umn’g tutucit is gniwpag.
3. Ow bidg, cai wuf wba wobaj unauyzy gxe uwuro. Zhex piv lvyug ehguhd, te reo qzoq mmu tapr azkupi o ti/zoxfk tkucorugj mu vukgqu fvequ ehcuxx. Qaza, miu riyk rzohq zbo egwoy ta xmu habix kelfuwi. Taxese qjul yda habb ta serhonf(_:) buihf’c hkujs, otp tbat miwcednhif, wba isw uf vhe zibbkiif ludd qivsog eyyiroelirw afjevcikj. Qku zoherbh er bda xwilethuvy nicx wo bexp ye tzu mxucuqu di FQJajeHRZeqoazk, rjamx qaa’nw gojv ut ab dxu qocy geqzier.

Gcem tupcav yac kavkaevv hfu diqo diomuy ma oyurhels gve asofe udq cqu mukuc din suxx dihj pze Debaih scobutujt uml vyow gehw bzu onove pryiihw kje tokif. Gis kfot xai jope wgi Netair gqogudodg ep bquta, ab’r rime ci ti nuxazsajt hinw dmu famedqd ey zye howt darzuix.