Flutter + ML Kit: Building smart cross-platform apps
summary
Flutter compiles Dart ahead-of-time to ARM machine code for native performance, uses JIT for hot reload that updates UI in under a second (demo changed “Hello World” to “Hello droidcon SF” live), and models UI as nested widgets. ML Kit provides on-device and cloud APIs: image labeling, text recognition, face detection (bounding boxes, landmarks, smiling/eye-open probabilities, tracking), and barcode scanning; landmark detection and custom TensorFlow Lite models are available on Android/iOS but the Flutter ML Kit plugin is still being developed.
AI-written summary · about
chapters (14)
- 0:00Introduction to Flutter
- 4:27Setting up a Flutter project
- 7:16Understanding Flutter widgets
- 11:29Hot reload demo
- 12:13Why choose Flutter over others
- 15:05Introduction to ML Kit
- 17:12Image labeling with ML Kit
- 19:21Face detection in Flutter
- 23:16Text recognition with ML Kit
- 24:16Barcode scanning demo
- 25:19Landmark detection overview
- 26:03Custom models with TensorFlow Lite
- 27:06Summary and resources
- 28:30Q&A session
related talks
42mSmartly Smartest Apps with Cross-Platform Machine Learning (Using Flutter and ML Kit)
04mTop 5 reasons to add ML Kit to your Android or iOS app
24mML Kit: Machine learning for mobile developers
30mMachine Learning in Android Apps with ML Kit
12mML Kit: Turnkey APIs to use on-device ML in mobile apps
29mFirebase MLKit — AI in Android Town!!
34mIt’s an ML full world! MLKit for Android Devs
35mUnderstanding MLKit offerings on Android