Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
20170829_iOSLT_機械学習とVision.framework
Search
shtnkgm
September 20, 2017
Programming
0
91
20170829_iOSLT_機械学習とVision.framework
機械学習の基礎的な内容を交えつつ、iOS11で追加されたVision.frameworkの説明とデモ
shtnkgm
September 20, 2017
Tweet
Share
More Decks by shtnkgm
See All by shtnkgm
Combine入門
shtnkgm
2
300
Property Wrappers
shtnkgm
0
360
Saliency Detection
shtnkgm
0
74
パフォーマンス改善とユニットテスト
shtnkgm
4
1.7k
iOSのコードベースレイアウト
shtnkgm
2
800
20190117_iOSLT_CBLinSwift.pdf
shtnkgm
0
110
SwiftとFunctional Reactive Programming
shtnkgm
0
190
20180710_iOSLT_iOSでDarkModeを実装する
shtnkgm
0
110
20180410_iOSLT_SwiftとProtocol-OrientedProgramming
shtnkgm
0
120
Other Decks in Programming
See All in Programming
AI Agent の開発と運用を支える Durable Execution #AgentsInProd
izumin5210
7
2.3k
Smart Handoff/Pickup ガイド - Claude Code セッション管理
yukiigarashi
0
150
疑似コードによるプロンプト記述、どのくらい正確に実行される?
kokuyouwind
0
390
AI & Enginnering
codelynx
0
120
AIエージェントのキホンから学ぶ「エージェンティックコーディング」実践入門
masahiro_nishimi
6
680
dchart: charts from deck markup
ajstarks
3
1k
Automatic Grammar Agreementと Markdown Extended Attributes について
kishikawakatsumi
0
200
AI時代のキャリアプラン「技術の引力」からの脱出と「問い」へのいざない / tech-gravity
minodriven
21
7.4k
CSC307 Lecture 01
javiergs
PRO
0
690
Package Management Learnings from Homebrew
mikemcquaid
0
230
20260127_試行錯誤の結晶を1冊に。著者が解説 先輩データサイエンティストからの指南書 / author's_commentary_ds_instructions_guide
nash_efp
1
990
IFSによる形状設計/デモシーンの魅力 @ 慶應大学SFC
gam0022
1
310
Featured
See All Featured
Reflections from 52 weeks, 52 projects
jeffersonlam
356
21k
How STYLIGHT went responsive
nonsquared
100
6k
The Pragmatic Product Professional
lauravandoore
37
7.1k
Documentation Writing (for coders)
carmenintech
77
5.3k
Code Review Best Practice
trishagee
74
20k
Beyond borders and beyond the search box: How to win the global "messy middle" with AI-driven SEO
davidcarrasco
1
58
My Coaching Mixtape
mlcsv
0
50
ピンチをチャンスに:未来をつくるプロダクトロードマップ #pmconf2020
aki_iinuma
128
55k
Facilitating Awesome Meetings
lara
57
6.8k
HDC tutorial
michielstock
1
390
The Art of Programming - Codeland 2020
erikaheidi
57
14k
Learning to Love Humans: Emotional Interface Design
aarron
275
41k
Transcript
ػցֶशͱVision.framework Shota Nakagami / @shtnkgm 2017/8/29
͢༰ — Vision.frameworkͷجຊతͳઆ໌ — ػցֶशͷ֓ཁ — VisionΛ༻͍ͨΧϝϥը૾Λผ͢ΔαϯϓϧΞϓϦ
Vision.frameworkͱ — iOS11͔ΒՃ͞Εͨը૾ೝࣝAPIΛఏڙ͢ΔϑϨʔϜϫʔ Ϋ — ಉ͘͡iOS11͔ΒՃ͞ΕͨػցֶशϑϨʔϜϫʔΫͷCore MLΛநԽ
ػցֶशελοΫ
χϡʔϥϧωοτϫʔΫͱ — ػցֶशख๏ͷҰछ — ਓؒͷͷਆܦճ࿏Λ ࣜϞσϧͰදͨ͠ͷ — NNͱུ͞ΕΔ ʢDNN1ɺRNN2ɺCNN3ͳͲʣ 3
Convolutional Neural NetworkʢΈࠐΈχϡʔϥϧωο τϫʔΫʣ 2 Recurrent Neural Networkʢ࠶ؼܕχϡʔϥϧωοτϫ ʔΫʣ 1 Deep Neural NetworkʢσΟʔϓχϡʔϥϧωοτϫʔ Ϋʣ
VisionͰೝࣝͰ͖Δͷ
VisionͰೝࣝͰ͖Δͷᶃ — إݕग़ / Face Detection and Recognition — όʔίʔυݕग़
/ Barcode Detection — ը૾ͷҐஔ߹Θͤ / Image Alignment Analysis — ςΩετݕग़ / Text Detection — ਫฏઢݕग़ / Horizon Detection
VisionͰೝࣝͰ͖Δͷᶄ ػցֶशϞσϧͷ༻ҙ͕ඞཁͳͷ — ΦϒδΣΫτݕग़ͱτϥοΩϯά / Object Detection and Tracking —
ػցֶशʹΑΔը૾ੳ / Machine Learning Image Analysis
Χϝϥը૾Λผ͢ΔαϯϓϧΞ ϓϦΛͭ͘Δ
αϯϓϧΞϓϦ֓ཁ — VisionͷʮػցֶशʹΑΔը૾ੳʯػೳΛར༻ — ΧϝϥͰөͨ͠ը૾Λผ͠ɺϞϊͷ໊લΛग़ྗ
ػցֶशʹΑΔը૾ೝࣝͷྲྀΕ 1. ֶशͷͨΊը૾σʔλΛऩूʢڭࡐΛूΊΔʣ 2. ֶश༻σʔλ͔ΒɺػցֶशΞϧΰϦζϜʹΑΓϞσϧΛ࡞ ※Ϟσϧɾɾɾ͑Λग़ͯ͘͠ΕΔϩδοΫ ྨɿ͜ͷը૾ݘʁೣʁ ճؼɿ༧ଌʢ໌ͷגՁʁʣ 3.
ֶशࡁΈϞσϧΛ༻͍ͯະͷը૾Λผʢ࣮ફʣ
Ϟσϧ࡞ׂѪ — ֶशσʔλͷऩूɾܗׂΓͱେม — ͦΕͳΓͷϚγϯεϖοΫɺܭࢉ͕࣌ؒඞཁ — ػցֶशʹؔ͢Δ͕ࣝඞཁ
Ϟσϧͷ༻ҙ ؆୯ͷͨΊɺֶशࡁΈϞσϧΛར༻ AppleͷαΠτͰ͞Ε͍ͯΔʢ.mlmodelܗࣜʣ https://developer.apple.com/machine-learning/
ϞσϧҰཡ ϞσϧʹΑͬͯಘҙͳը૾ͷछྨ༰ྔ͕ҟͳΔ ʢ5MBʙ553.5MBʣ — MobileNets — SqueezeNet — Places205-GoogLeNet —
ResNet50 — Inception v3 — VGG16
ࠓճResNet50Λར༻ — थɺಈɺ৯ɺΓɺਓͳͲͷ1000छྨͷΧςΰϦ — αΠζ102.6 MB — MITϥΠηϯε
ϞσϧΛϓϩδΣΫτʹࠐΉ
Xcodeʹυϥοά&υϩοϓ
ϞσϧΫϥε͕ࣗಈੜ͞ΕΔ ࣗಈͰϞσϧ໊.swiftͱ͍͏໊લͰϞσϧΫϥε͕࡞͞ΕΔ ྫ) Resnet50.swiftʢҰ෦ൈਮʣ
Χϝϥը૾ͷΩϟϓνϟॲཧ
private func startCapture() { let captureSession = AVCaptureSession() captureSession.sessionPreset =
AVCaptureSessionPresetPhoto // ೖྗͷࢦఆ let captureDevice = AVCaptureDevice.defaultDevice(withMediaType: AVMediaTypeVideo) guard let input = try? AVCaptureDeviceInput(device: captureDevice) else { return } guard captureSession.canAddInput(input) else { return } captureSession.addInput(input) // ग़ྗͷࢦఆ let output: AVCaptureVideoDataOutput = AVCaptureVideoDataOutput() output.setSampleBufferDelegate(self, queue: DispatchQueue(label: "VideoQueue")) guard captureSession.canAddOutput(output) else { return } captureSession.addOutput(output) // ϓϨϏϡʔͷࢦఆ guard let previewLayer = AVCaptureVideoPreviewLayer(session: captureSession) else { return } previewLayer.videoGravity = AVLayerVideoGravityResizeAspectFill previewLayer.frame = view.bounds view.layer.insertSublayer(previewLayer, at: 0) // Ωϟϓνϟ։࢝ captureSession.startRunning() }
ࡱӨϑϨʔϜຖʹݺΕΔDeleate extension ViewController: AVCaptureVideoDataOutputSampleBufferDelegate { func captureOutput(_ output: AVCaptureOutput!, didOutputSampleBuffer
sampleBuffer: CMSampleBuffer!, from connection: AVCaptureConnection!) { // CMSampleBufferΛCVPixelBufferʹม guard let pixelBuffer = CMSampleBufferGetImageBuffer(sampleBuffer) else { return } // ͜ͷதʹVision.frameworkͷॲཧΛॻ͍͍ͯ͘ʢը૾ೝࣝ෦ʣ } }
ը૾ೝࣝ෦ͷॲཧ
VisionͰར༻͢ΔओͳΫϥε — VNCoreMLModel — VNCoreMLRequest — VNImageRequestHandler — VNObservation
VNCoreMLModel — CoreMLͷϞσϧΛVisionͰѻ͏ͨΊͷίϯςφΫϥε
VNCoreMLRequest — CoreMLʹը૾ೝࣝΛཁٻ͢ΔͨΊͷΫϥε — ೝࣝ݁ՌϞσϧͷग़ྗܗࣜʹΑΓܾ·Δ — ը૾→Ϋϥεʢྨ݁Ռʣ — ը૾→ಛྔ —
ը૾→ը૾
VNImageRequestHandler — Ұͭͷը૾ʹର͠ɺҰͭҎ্ͷը૾ೝࣝॲཧ ʢVNCoreMLRequestʣΛ࣮ߦ͢ΔͨΊͷΫϥε — ॳظԽ࣌ʹೝࣝରͷը૾ܗࣜΛࢦఆ͢Δ — CVPixelBuffer — CIImage
— CGImage
VNObservation — ը૾ೝࣝ݁ՌͷநΫϥε — ݁Ռͱͯ͜͠ͷΫϥεͷαϒΫϥεͷ͍ͣΕ͔͕ฦ͞ΕΔ — ೝࣝͷ֬৴Λද͢confidenceϓϩύςΟΛ࣋ͭ ʢVNConfidence=FloatͷΤΠϦΞεʣ
VNObservationαϒΫϥε — VNClassificationObservation ྨ໊ͱͯ͠identifierϓϩύςΟΛ࣋ͭ — VNCoreMLFeatureValueObservation ಛྔσʔλͱͯ͠featureValueϓϩύςΟΛ࣋ͭ — VNPixelBufferObservation ը૾σʔλͱͯ͠pixelBufferϓϩύςΟΛ࣋ͭ
·ͱΊΔͱ… — VNCoreMLModelʢΈࠐΜͩϞσϧʣ — VNCoreMLRequestʢը૾ೝࣝͷϦΫΤετʣ — VNImageRequestHandlerʢϦΫΤετͷ࣮ߦʣ — VNObservationʢೝࣝ݁Ռʣ
۩ମతͳ࣮ίʔυ
ϞσϧΫϥεͷॳظԽ // CoreMLͷϞσϧΫϥεͷॳظԽ guard let model = try? VNCoreMLModel(for: Resnet50().model)
else { return }
ը૾ೝࣝϦΫΤετΛ࡞ // ը૾ೝࣝϦΫΤετΛ࡞ʢҾϞσϧͱϋϯυϥʣ let request = VNCoreMLRequest(model: model) { [weak
self] (request: VNRequest, error: Error?) in guard let results = request.results as? [VNClassificationObservation] else { return } // ผ݁Ռͱͦͷ֬৴Λ্Ґ3݅·Ͱදࣔ // identifierΧϯϚ۠ΓͰෳॻ͔Ε͍ͯΔ͜ͱ͕͋ΔͷͰɺ࠷ॳͷ୯ޠͷΈऔಘ͢Δ let displayText = results.prefix(3) .flatMap { "\(Int($0.confidence * 100))% \($0.identifier.components(separatedBy: ", ")[0])" } .joined(separator: "\n") DispatchQueue.main.async { self?.textView.text = displayText } }
ը૾ೝࣝϦΫΤετΛ࣮ߦ // CVPixelBufferʹର͠ɺը૾ೝࣝϦΫΤετΛ࣮ߦ try? VNImageRequestHandler(cvPixelBuffer: pixelBuffer, options: [:]).perform([request])
ը૾ೝࣝ෦ͷܗ guard let pixelBuffer = CMSampleBufferGetImageBuffer(sampleBuffer) else { return }
guard let model = try? VNCoreMLModel(for: Resnet50().model) else { return } let request = VNCoreMLRequest(model: model) { [weak self] (request: VNRequest, error: Error?) in guard let results = request.results as? [VNClassificationObservation] else { return } let displayText = results.prefix(3) .flatMap { "\(Int($0.confidence * 100))% \($0.identifier.components(separatedBy: ", ")[0])" } .joined(separator: "\n") DispatchQueue.main.async { self?.textView.text = displayText } } try? VNImageRequestHandler(cvPixelBuffer: pixelBuffer, options: [:]).perform([request])
σϞಈը
None
tabbyͬͯԿʁ
tabby = τϥωίʂ τϥωίͱɺτϥͷΑ͏ͳࣶ༷Λ࣋ͭωίͷ͜ͱͰ͋ΔɻλϏʔͱݺΕΔɻτϥೣ ετϥΠϓͷଞʹɺ్ࣶ༷͕Εͯɺൗ༷ɺᤳᤶ൝ɺࡉ͔ࣶ༷͘Λ్Εͤͯͨ͞ ͷ͕͋Γɺଟ༷Ͱ͋ΔɻʢҾ༻: ΟΩϖσΟΞʣ
·ͱΊ
— ֶशࡁΈϞσϧ͕͋Εɺ࣮ࣗମ؆୯! — ωίͷछྨڭ͑ͯ͘ΕΔ" — ͋ͱϞσϧࣗͰ࡞ΕΔΑ͏ʹͳΕͬͱ෯͕͕ Δ
ॳΓ͔ͨͬͨ͜ͱ — ΠϯελάϥϜ༻ͷࣗಈϋογϡλά͚ΞϓϦ — ϋογϡλάΛ͢ΩϟϓγϣϯAPIطʹഇࢭʘ(^o^)ʗ
αϯϓϧίʔυ ࠓճ͝հͨ͠αϯϓϧίʔυͪ͜Βʹஔ͍ͯ͋Γ·͢ɻ https://github.com/shtnkgm/VisionFrameworkSample ※εΫϦʔϯγϣοτͷެ։ʹNDAҙ
͓ΘΓ
ࢀߟࢿྉᶃ — Build more intelligent apps with machine learning. /
Apple — Vision / Apple Developer Documentation — ʲWWDC2017ʳVision.framework ͷςΩετݕग़Λࢼ͠ ͯΈ·ͨ͠ʲiOS11ʳ — Keras + iOS11 CoreML + Vision Framework ʹΑΔɺ ΫϩإࣝผΞϓϦͷ։ൃ — [Core ML] .mlmodel ϑΝΠϧΛ࡞͢Δ / ϑΣϯϦϧ
ࢀߟࢿྉᶄ — [iOS 11] CoreMLͰը૾ͷࣝผΛࢼͯ͠Έ·ͨ͠ ʢVision.FrameworkΛΘͳ͍ύλʔϯʣ #WWDC2017 — Places205-GoogLeNetͰॴͷఆ /
fabo.io — iOSDCͷϦδΣΫτίϯͰʰiOSͱσΟʔϓϥʔχϯάʱʹ ͍ͭͯ͠·ͨ͠Add Star — [iOS 10][χϡʔϥϧωοτϫʔΫ] OSSͰAccelerateʹՃ ͞ΕͨBNNSΛཧղ͢Δ ~XORฤ~