Deep learning (DL) systems are complex and often have a few of dependencies. It is often painful to port a DL library into different platforms, especially for smart devices. There is one fun way to solve this problem: provide a light interface and put all required codes into a single file with minimal dependencies. In this tutorial we will give details on how to do the amalgamation. In addition, we will show a demo to run image object recognition on mobile devices.

Source: Deep Learning in a Single File for Smart Devices — mxnet 0.5.0 documentation