Portability is one of the main benefits of TensorFlow — you can easily move a neural network model to Android and run predictions on mobile phones, for all kinds of AI tricks from image recognition to motion recognition. But models are often large (tens of megabytes) and prediction can consume lots of CPU power. In this session, we’ll share tips and tricks on overcoming these challenges so you can bring the latest AI technologies to your Android app.
See all the talks from Google I/O ’17 here: https://goo.gl/D0D4VE
Watch more Android talks at I/O ’17 here: https://goo.gl/c0LWYl
Watch more Chrome talks at I/O ’17 here: https://goo.gl/Q1bFGY
Watch more Firebase talks at I/O ’17 here: https://goo.gl/pmO4Dr
Subscribe to the Google Developers channel: http://goo.gl/mQyv5L
#io17 #GoogleIO #GoogleIO2017 event: Google I/O 2017; re_ty: Publish;