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
ML Kit Introduction (for iOS)
Search
Sponsored
·
Ship Features Fearlessly
Turn features on and off without deploys. Used by thousands of Ruby developers.
→
Elvis Lin
July 19, 2018
Programming
190
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
ML Kit Introduction (for iOS)
Introduce the basic concept of ML Kit and how to use it in iOS development
Elvis Lin
July 19, 2018
More Decks by Elvis Lin
See All by Elvis Lin
Protect Users' Privacy in iOS 14
elvismetaphor
0
62
Dubugging Tips and Tricks for iOS development
elvismetaphor
0
75
Strategies of Facebook LightSpeed project
elvismetaphor
0
120
Background Execution And WorkManager
elvismetaphor
2
520
作為一個跨平台的 Mobile App 開發者,從入門到放棄!?
elvismetaphor
2
560
Dependency Injection for testability of iOS app
elvismetaphor
1
1.5k
Briefly Introduction of Kotlin coroutines
elvismetaphor
1
330
MotionLayout Brief Introduction
elvismetaphor
1
380
Chapter 10. Pattern Matching with Regular Expressions
elvismetaphor
0
80
Other Decks in Programming
See All in Programming
AIと壁打ちしながら進めるコスト管理
fufuhu
2
1.6k
実装をデザインガイドラインに追従させるための取り組み / 260731-dip-mosh-design-system
dachi023
0
7.7k
Loosening the Reins: Go Generics Get More Flexible
kuro_kurorrr
0
300
為什麼你並不需要ViewModel / No, you don't need a ViewModel
lovee
1
510
How I Won Prize Money at a Hackathon Using Codex and Symphony Alpha
yasei_no_otoko
0
120
Cloudflare is Agents
chimame
0
180
MySQLとPostgreSQLって何が違うの?
akagami
0
130
[PyCon KR 2026] More Variants, More Diversity for AI Accelerators
achimnol
0
110
関東Kaggler会_NVIDIA_Nemotron_コンペ_振り返り
rick_ds
0
710
30年振りにコンパイラの定数整数除算を改善した
herumi
9
4.1k
Claude CodeとAgentCore Gatewayを繋ぐ際の認証認可 / Authentication and authorization when connecting Claude Code with AgentCore Gateway
har1101
2
370
引き算の組織 ― アウトカムとAIに全振りするために辞めたこと ― / Organization by Subtraction
hirokiyamamoto14
PRO
0
290
Featured
See All Featured
[RailsConf 2023 Opening Keynote] The Magic of Rails
eileencodes
31
10k
YesSQL, Process and Tooling at Scale
rocio
174
15k
Accessibility Awareness
sabderemane
1
180
How To Speak Unicorn (iThemes Webinar)
marktimemedia
1
560
Lightning Talk: Beautiful Slides for Beginners
inesmontani
PRO
2
640
GitHub's CSS Performance
jonrohan
1033
470k
Test your architecture with Archunit
thirion
2
2.4k
More Than Pixels: Becoming A User Experience Designer
marktimemedia
3
500
Digital Projects Gone Horribly Wrong (And the UX Pros Who Still Save the Day) - Dean Schuster
uxyall
1
2.5k
The Web Performance Landscape in 2024 [PerfNow 2024]
tammyeverts
12
1.3k
State of Search Keynote: SEO is Dead Long Live SEO
ryanjones
0
250
Organizational Design Perspectives: An Ontology of Organizational Design Elements
kimpetersen
PRO
1
800
Transcript
ML Kit 使⽤用簡介 (iOS) Elvis Lin @Cocoahead Taipei 2018-07-19
關於我 • Elvis Lin • iOS 與 Android 永遠的初學者 •
Twitter: @elvismetaphor • Blog: https://blog.elvismetaphor.me
⼤大綱 • 什什麼是(我理理解的)機器學習 • 移動裝置上實作機器學習應⽤用的限制 • TensorFlow Lite 與 ML
Kit • 範例例
機器學習的應⽤用
機器學習 • 從資料中歸納出有⽤用的規則 • 訓練模型 • 使⽤用模型 • Mobile Application
Engineer 參參 與開發主要是在「使⽤用模型」 這個範圍
Data Result (Trained) Model
移動裝置上 實作機器學習應⽤用的限制 • 記憶體有限與儲存空間有限 • 計算能⼒力力不如⼤大型伺服器 • 電池容量量有限
移動裝置上 實作機器學習應⽤用的改良⽅方向 • 記憶體有限與儲存空間有限 —> 減少模型(Model)的體積 • 計算能⼒力力不如⼤大型伺服器 —> 降低演算法的複雜度
• 電池容量量有限 —> 降低演算法的複雜度
Google 推出的解決⽅方案 • TensorFlow Lite • ML Kit
Tensorflow Lite https://youtu.be/ByJnpbDd-zc
https://www.tensorflow.org/mobile/tflite/
轉換 Tensorflow 檔案的⼯工具 • Tensorflow converter • 轉成 Tensorflow Lite
格式 • Tensorflow-CoreML converter • 轉成 CoreML 格式 • https://github.com/tf-coreml/tf-coreml
ML Kit https://youtu.be/Z-dqGRSsaBs
Neural Networks API Metal
ML Kit • Cloud Vision API / Mobile Vision API
• Tensorflow Lite • 整合 Firebase,託管「客製化的模型」
ML Kit Base APIs • Image labeling • Text recognition
(OCR) • Face detection • Barcode scanning • Landmark detection • others……
託管客製化的模型 ⽬目前只⽀支援 Tensorflow Lite 格式
使⽤用 ML Kit
建立⼀一個 Firebase 專案
建立⼀一個 iOS app 然後下載設定檔 設定好 Bundle ID 下載 GoogleService-info.plist
新增 plist 檔案到專案 • 將 GoogleService-Info.plist 放到 <root>/<application_folder>/ 下
安裝 Firebase 函式庫 • 修改 Podfile,新增以下的內容 • cd <root> pod
install • 打改 <project_name>.xcworkspace pod 'Firebase/Core' pod 'Firebase/MLVision' pod 'Firebase/MLVisionTextModel' pod 'Firebase/MLVisionFaceModel' pod 'Firebase/MLVisionBarcodeModel' pod 'Firebase/MLVision' pod 'Firebase/MLVisionLabelModel'
掃描 Barcode (Local) let barcodeDetector: VisionBarcodeDetector = Vision.vision().barcodeDetector(options: options)
let visionImage = VisionImage(image: pickedImage) barcodeDetector.detect(in: visionImage) { (barcodes, error) in guard error == nil, let barcodes = barcodes, !barcodes.isEmpty else { self.dismiss(animated: true, completion: nil) self.resultView.text = "No Barcode Detected" return } for barcode in barcodes { // handle the detected barcode } }
第1步:初始化 Detector let barcodeDetector: VisionBarcodeDetector = Vision.vision().barcodeDetector(options: options) let
visionImage = VisionImage(image: pickedImage)
第2步:取得結果 barcodeDetector.detect(in: visionImage) { (barcodes, error) in guard error ==
nil, let barcodes = barcodes, !barcodes.isEmpty else { self.dismiss(animated: true, completion: nil) self.resultView.text = "No Barcode Detected" return } for barcode in barcodes { // handle the detected barcode } }
⽀支援的 Barcode 格式 • Code 128 (FORMAT_CODE_128) • Code 39
(FORMAT_CODE_39) • Code 93 (FORMAT_CODE_93) • Codabar (FORMAT_CODABAR) • EAN-13 (FORMAT_EAN_13) • EAN-8 (FORMAT_EAN_8) • ITF (FORMAT_ITF) • UPC-A (FORMAT_UPC_A) • UPC-E (FORMAT_UPC_E) •QR Code (FORMAT_QR_CODE) • PDF417 (FORMAT_PDF417) • Aztec (FORMAT_AZTEC) • Data Matrix (FORMAT_DATA_MATRIX)
辨識⽂文字 (Local) lazy var textDetector: VisionTextDetector = Vision.vision().textDetector() func
runTextRecognition(with image: UIImage) { let visionImage = VisionImage(image: image) textDetector.detect(in: visionImage) { (features, error) in if let error = error { print("Received error: \(error)") } self.processResult(from: features, error: error) } }
辨識⽂文字 (Cloud) Lazy var cloudTextDetector: VisionCloudTextDetector = Vision.vision().cloudTextDetector() func
runCloudTextRecognition(with image: UIImage) { let visionImage = VisionImage(image: image) cloudTextDetector.detect(in: visionImage) { (features, error) in if let error = error { print("Received error: \(error)") } self.processCloudResult(from: features, error: error) } }
補充資料 • ML Kit 簡介 (for Android) https://blog.elvismetaphor.me/ml-kit-fundamentals-for- android-6444e2db0fdb •
ML Kit 簡介 (for iOS) https://blog.elvismetaphor.me/ml-kit-fundamentals-for- ios-cb705044e69b
參參考資料 • https://youtu.be/Z-dqGRSsaBs • https://codelabs.developers.google.com/codelabs/mlkit-ios/ • https://github.com/firebase/quickstart-ios/tree/master/ mlvision • https://www.appcoda.com.tw/ml-kit/
None