Using Deeplearning4J in Android Applications
This tutorial demonstrates how the Java-based deep learning library Deeplearning4J can use a trained neural network in Android Applications. The application loads a neural network trained on the Mnist data set and uses it to identify user drawn numbers as input. The key features of this demo include storing and accessing a trained model stored in the application’s Raw folder, internally saving an user-generated image, and accessing and converting that image for testing against the network. A tutorial for the application can be found here.
For more information on Deeplearning4J, please visit http://deeplearning4j.org/