Superpower your Android apps with ML: Android 11
summary
Shows how to import a TFLite model into Android Studio, instantiate the generated class, and run inferences with three lines of code using the Model Binding Plugin plus an easy checkbox to add GPU deps; demonstrates a rock paper scissors model RPSModel.tflite that reports ~80% on a live demo and a food classifier built on top of ML Kit object detection, mentions Android 11 NNAPI support for asymmetric integer weights to shrink models and speed edge inference.
AI-written summary · about
chapters (7)
- 0:00Introduction
- 1:53Why on-device ML
- 8:12ML model binding plugin
- 22:43New ML Kit updates
- 32:36Creating TFLite models
- 34:01Demo rock paper scissors
- 36:28Q&A
related talks
36mMaking intelligent Android apps
43mWhat’s new in Android machine learning
13mWhat's new in Android machine learning
36mKeynote! The opportunity for Android devs with AI and ML
39mMachine Learning on Android Demystified
47mMyths and Reality of Android Machine Learning
10mWhat's new in Android Machine Learning
29mFrom TensorFlow to ML Kit: power your Android application with ML