ML Kit: Machine learning for mobile developers

on YouTube ↗24m

" summary

ML Kit shows concrete APIs and numbers: an on-device (400 labels) image labeler with no network, a cloud (10,000 labels) option with 1,000 free calls/month, and easy real‑time frame processing via FirebaseVisionImage and detector.detectInImage. Custom models upload as TensorFlow Lite to Firebase for serving and A/B via Remote Config. A compression demo claims shrinking an 80+ MB model to <1 MB with the model compression service. A flags classifier is retrained, deployed and correctly recognizes flags live.

AI-written summary · about

" chapters (10)

1. 0:00Intro
2. 2:27ML models
3. 4:29Code
4. 10:17Introduction
5. 13:08Tensorflow model
6. 14:04Getting started
7. 15:48Transfer learning
8. 17:11Model compression
9. 18:37Recap
10. 19:13Demo

" related talks

• 36mMachine Learning for Mobile DevelopersLaura Morinigo · Mobilization 8
• 30mMachine Learning in Android Apps with ML KitFelipe Pedroso · AndroidFest Campinas 2018
• 47mExploring Firebase MLKit on AndroidHiren Dave · GDG DevFest Ahmedabad 2018
• 29mPushing Machine Learning into your app When TensorFlow and MLKit rule the worldSandra Dupré · DevFest Nantes 2018
• 14mDo you want an easy way to add Machine Learning into your app?Sandra Dupré · Android Makers 2019
• 38mML Kit: Machine Learning for Mobile with FirebaseChristiaan Prins, Ann Zimmer, Shiyu Hu · Google I/O 2019
• 34mIt’s an ML full world! MLKit for Android DevsBritt Barak · DevFest Ukraine 2018
• 21mGetting the best of on-device ML with ML KitDong Chen · Android Dev Summit 2018