Firebase & ML Kit

15:30 - 16:00 Firebase & ML Kit - Erol Kaftanoğlu & Burcu Geneci
---
Google I/O, Google tarafından 2008 yılından beri düzenlenen bir geliştirici festivalidir.

Bu sene 8-10 Mayıs tarihlerinde San Francisco'da düzenlenen Google I/O 2018 etkinliğine Google Developer Groups (GDG) Istanbul'dan katılan arkadaşlarımızın; Mobil, Firebase, Kotlin, Google Asistan, Flutter gibi konularda paylaşılan yenilikleri ve orada edindikleri tecrübeleri bizimle paylaşacağı, After I/O 2018 Istanbul etkinliğinde bir araya geliyoruz.

Transcript

1. Firebase & ML Kit Erol Kaftanoglu & Burcu Geneci
2. Who
 is 
 using 
 Firebase?
3. Ofcourse,
 ML Kit
4. Improving 
 Performance 
 Monitoring
8. StreamView 
 and 
 DebugView 
 reports.
9. New
 Role
 Authentication
10. Expanding
 Firebase
 Test Lab
 to
 iOS
11. Firebase
 Cloud
 Store new rule Simulator
12. Firebase
 Cloud
 Store sort and filter
13. Firebase
 Cloud
 Store sort and filter
14. Firebase
 Cloud
 Store sort and filter
15. Firebase
 Cloud
 Store sort and filter
16. Crashlytics
17. Authentication
18. • MLKit Vision (On-device & Cloud base Api) • Custom Models (TensorFlow Lite) ML Kit Machine Learning for Mobile Developers Beta
19. https://firebase.google.com/docs/ml-kit/
20. Text Recognition Face Detection Barcode Scanning Image Labeling Landmark Recognition
21. • Recognize text in any Latin-based language on- Device. • Real-time processing • Free for first 1000 uses of this feature per month. Text Recognition on-Device & Cloud
22. Text Recognition on-Device & Cloud
23. Text Recognition on-Device & Cloud
24. Text Recognition on-Device & Cloud
25. Text Recognition on-Device & Cloud
26. Text Recognition on-Device & Cloud
27. • Detect faces in an image and identify key facial features. • Get the coordinates of the eyes, ears, cheeks, nose, and mouth of every face detected. • Recognize facial expressions. • Get an identifier for each individual person's face that is detected. • Real time on-Device. Face Detection ☺ on-Device.
28. • Reads most standard formats. • Works with any orientation. • Supported information types include URLs, contact information, calendar events, email addresses, phone numbers, SMS message prompts, ISBNs, WiFi connection information, geographic location, and AAMVA-standard driver information. Barcode Scanning on-Device.
29. • The device-based API supports 400+ labels. Cloud 10.000+ • Free for first 1000 uses of this feature per month. Image Labeling on-Device & Cloud Places Places Animals Activities People Things Foods Events Device Cloud Fictional Characters Materials Arts & entertainment & Much more
30. • you get the landmarks that were recognized in it, along with each landmark's geographic coordinates and the region of the image the landmark was found. Landmark Recognition Cloud Description Bounding Polygon Geographic Coordinates Confidence Score
31. • For experienced ML developers. • Host your TensorFlow Lite models using Firebase or package them with your app. • Use the ML Kit SDK to perform inference using the best-available version of your custom model. • Automatically updated models. Custom Models Inference on-Device & Cloud
32. Custom Models Inference on-Device & Cloud
33. https://codelabs.developers.google.com/io2018
34. THANK YOU!