Deep Learning with a DNN Compiler

Source: Deep Learning on Medium

How to run?

DNNC accepts model formats like onnx and converts them into executable that can run on a platform of your choice.

Inexpensive microcontrollers and mini computers

DNNC is designed to work on small form factor devices like micro-controllers, cpus and other embedded devices like raspberry-pi, odroid, arduino, SparkFun Edge, risc-V, mobile phones, x86 and arm laptops among others. It supports many compute architectures including x86, x86_64, arm, arm64, armv7, amd64, ppc64le and others. It can run on hardware without OS, it supports may OS distributions Ubuntu, CentOS, ArchLinux, Manjaro, Sierra (macOS) and windows.