This docker is designed to enable portability to leverage i.MX 8 series GPU/NPU. It enables flexibility on top of the Yocto image and allows the use of libraries available in Ubuntu for machine learning, which is otherwise difficult. Using docker, a user can develop and prototype GPU/NPU applications and then ship and run it anywhere using the container. This App note describes how to enable this Docker. The docker is a wrapper that provides an application with the necessary dependencies to execute code on the GPU/NPU. This is a significant achievement and has the potential to greatly simplify many customer developments for Linux. We keep the Yocto BSP intact, but customers can develop applications using the widely available neural network frameworks and libraries at the same time leveraging the GPU/NPU without compromising on performance. Not quite as straightforward as full up Debian but still should be an easy sell.
