Guidance on Deploying TinyML on RISC-V and Integrating Board with Edge Impulse

Feature requests
#1

Hi, everyone! This is sreenivas. I have a question regarding the deployment of a TinyML algorithm on an RISC-V-based processor. I’d like to integrate my board into Edge Impulse, similar to how the Arduino BLE Sense is added. Could you please guide me through the procedure? I’ve attached information about my board for reference.

SRAM : 256 KB
• Flash : 2MB
• PWM Pins : 8 nos
• Analog Input Pins : 4 nos
• SPI : 3 nos
• UART : 3 nos
• I2C : 2 nos
• GPIOs : 25
• Input Voltage : 7-12V
• DC Current per I/O Pin : 12 mA
• IO Voltage : 3.3 V
• Clock Speed : 100 MHz

Data sheet link

#2

Hi @sreenivas123

Interesting, why are you going the firmware route here, you may simply be better to use a generic ardunio library →

It seems like the device is supported by Arduino IDE →
" Communication

VEGA_WiFiNINA

V1.0.1

CDAC

VEGA-Processor

Enables network connection (local and Internet) with VEGA ARIES IoT, ARIES v2, ARIES v3, ARIES MICRO

With this library you can instantiate Servers, Clients and send/receive UDP packets through WiFi. The board can connect either to open or encrypted networks (WEP, WPA). The IP address can be assigned statically or through a DHCP. The library can also manage DNS."
https://docs.arduino.cc/libraries/vega_wifinina/

While I can’t give step by step but this guide is a great place to start, and all of our firmware is open source - Espressif ESP-EYE | Edge Impulse Documentation

Arducam is pico based and community supported for example so we can publish if firmware is the goal here -

You can ask questions as you make progress and I will try to get some help, if you manage to get it working that would be fantastic.

Best

Eoin