We are thrilled to announce official support for the Renesas RZ/V2L Evaluation Board Kit.
Designed for vision AI applications, the Renesas RZ/V2L is an industrial-grade, energy-efficient Linux MPU offering powerful hardware acceleration through its Dynamically Reconfigurable Processor (DRP) and multiply-accumulate unit (AI-MAC).
Featuring a dual-core Arm Cortex-A55 processor running at 1.2 GHZ and an Arm Mali-G31 graphic engine, in addition to the DRP-AI IP, the board can achieve high power efficiency without the need for a heat sink.
Renesas, through its powerful DRP-AI, provides a new ecosystem for neural network processing on the device. The official support from Edge Impulse allows a user to take this ecosystem to unprecedented levels, enabling the building of a machine learning model in less than five minutes, deploying this model to the RZ/V2L, and enjoying the full capacities of the DRP-AI.
Since the RZ/V2L is intended for vision AI, the EVK already comes with the Google Coral camera module. The kit also consists of a SMARC system-on-module and an I/O carrier board equipped with USB serial, two-channel Ethernet, HDMI, and other interfaces (Pmod, microphone, audio output, etc.).
The DRP-AI’s performance recently drew attention during Embedded World 2022 with a joint demo between Renesas and Edge Impulse. For the demo, we deployed our FOMO object detection algorithm and achieved a performance of 166 frames per second — the FOMO model was able to easily identify and track around 50 objects, consisting of various chips and printed Renesas logos, on a rotating turntable.
Getting Started
Here’s how to jump into the RZ/V2L:
- The RZ/V2L Evaluation Board Kit can be ordered through Renesas.
- Please consult our getting started guide for the RZ/V2L on our documentation page.
- Follow Renesas’ instructions on building the Yocto Linux Image and flashing the image to your SD card.
- Connect the board to Edge Impulse Studio and start sampling a dataset, or upload an existing dataset to the Studio if you have already one.
We have several tutorials for vision applications. Please have a look at the following for more detailed guidance:
Once you have trained your machine learning model using the Edge Impulse Studio, you can go to the Deployment tab of your project and download an EIM model that includes your binary. Or you can do it directly from the CLI.
You also have the option to download the C++ library that is customized for the Renesas DRP-AI.
Congratulations! You have now successfully built and deployed a low-power, industrial-grade embedded ML application for the Renesas RZ/V2L Evaluation Board Kit.
We are very excited to see what you come up with using the Renesas RZ/V2L and Edge Impulse. Please post your questions and any projects you create over on our forum or tag @EdgeImpulse and @RenesasGlobal on social media!