MLonMCU: TinyML Benchmarking with Fast Retargeting
This addresses the problem of efficient TinyML deployment for developers, but it is incremental as it builds on existing frameworks.
The paper tackles the challenge of selecting optimal frameworks and targets for deploying machine learning models on microcontrollers by proposing MLonMCU, a tool that automates end-to-end benchmarking, demonstrated by benchmarking TFLite for Microcontrollers and TVM with many configurations quickly.
While there exist many ways to deploy machine learning models on microcontrollers, it is non-trivial to choose the optimal combination of frameworks and targets for a given application. Thus, automating the end-to-end benchmarking flow is of high relevance nowadays. A tool called MLonMCU is proposed in this paper and demonstrated by benchmarking the state-of-the-art TinyML frameworks TFLite for Microcontrollers and TVM effortlessly with a large number of configurations in a low amount of time.