One key feature of TensorFlow includes the possibility to compile the trained model to run efficiently on mobile phones. This enables a wide range of opportunities for researchers and developers. In this tutorial, we teach attendees two basic steps to run neural networks on a mobile phone: Firstly, we will teach how to develop neural network architectures and train them in TensorFlow. Secondly, we show the process to run the trained models on a mobile phone.
The compiled Android app to test the model trained in Step 1 is available in the Android Store.
This tutorial will be held at:
- MobileHCI'17, 4th September 2017, 11:15-13:15, Vienna
- Mensch und Computer 2017, 10th September 2017, 11:00-15:30, Regensburg
As a first step, we presented a classification example. Beyond that, we want to provide a regression example which also is a plug and play example: https://github.com/interactionlab/Capacitive-Finger-Orientation-Estimation