Piunora

by Diodes Delight

A tiny-but-mighty open-source carrier board for the Raspberry Pi CM4

View all updates Apr 28, 2021

Machine-Learning Demo

by Timon

In this update I want to show you how easy it is to create custom machine learning models for your Piunora using tools like Edge Impulse. Edge Impulse recently added support for the Raspberry Pi 4 and, along with it, the Compute Module 4. In fact, you don’t need anything but your Piunora for the entire workflow covered in this update! I used the Raspberry Pi HQ Camera connected via the camera port to gather data using Edge Impulse Studio. Everything is running in the browser and connected to the edge-impulse-runner software running locally on Piunora to stream the camera feed to your browser.

Edge Impulse Studio will automatically detect the running instance and allow you to create a dataset by capturing photos and labeling them, all of which is done in the browser without downloading any extra software. Next, all you need to do is tell it what sort of model you want to use with your dataset and train it on the Edge Impulse servers, so there’s no need for expensive GPUs. You can do this from any device, even your Piunora. Once the training is done, you can deploy the model to Piunora and execute it locally, using the same camera you used to capture your data set. It works at an impressive 60 FPS and it does so completely offline.

You can do the same thing with arbitrary sensor data from an I²C sensor attached to Piunora’s Qwiic connector. The Edge Impulse Python SDK is well suited for that, as it integrates seamlessly with a huge number of Adafruit CircuitPython drivers! I will explore this in a future update.

In the meantime, checkout the video below for a run down of the process.

About the Author

Timon

timonsku  ·  timonsku


$18,042 raised

of $15,000 goal

120% Funded! Order Below

Product Choices

$39

Piunora Pro

A compact, feature-rich CM4 carrier board


$30

Piunora Lite

Perfect if you need the slimmest possible form factor. Includes all features of Piunora Pro except for the camera connector and the PCI-e M.2 port.


$14

M.2 B-Key 2280 Extender

Expands Piunora's M.2 port to accommodate full-length 2280 peripherals. Keep in mind that such devices are quite a bit longer than Piunora itself, so they might look a little awkward hanging off the end there. But, if you have a cool idea that depends on a 2280 M.2 accessory...this is the product for you.


$37

Raspberry Pi CM4 (Lite, Wireless, 1 GB RAM)

From the Crowd Supply Basics project.

Something for your Piunora to carry.

This CM4101000 variant of the Raspberry Pi Compute Module 4 is a System on Module (SoM) containing an ARM quad-core Cortex-A72 processor, 1 GB RAM, 2.4 and 5 GHz 802.11b/g/n/ac Wi-Fi and Bluetooth 5.0, and supporting power circuitry. Does not include eMMC flash.


$49

Raspberry Pi CM4 (8 GB eMMC, Wireless, 2 GB RAM)

From the Crowd Supply Basics project.

Something for your Piunora to carry.

This CM4102008 variant of the Raspberry Pi Compute Module 4 is a System on Module (SoM) containing an ARM quad-core Cortex-A72 processor, 2 GB RAM, 2.4 and 5 GHz 802.11b/g/n/ac Wi-Fi and Bluetooth 5.0, 8 GB eMMC flash, and supporting power circuitry. With this eMMC variant of the CM4, the SD Card interface is not usable.


$15

Heatsink for CM4

You can operate the CM4 without a heatsink just fine, but if you have some extra-heavy computation to do, then a heatsink can help prevent thermal throttling of the SoC. Includes a mounting footprint for a 30 mm fan (not included) should you want to integrate it into an enclosure or take your CM4 to even greater extremes of computation. Also includes a set of stacking pin headers to accommodate expansion boards.


$10

microSD Card

From the Crowd Supply Basics project.

Boot media for the "Lite" (CM4101000) variant of the CM4. We recommend 64 GB or smaller.

An industrial-grade memory card with extended endurance.


$7

RPi CM4 Wi-Fi Antenna Kit

From the Crowd Supply Basics project.

An omnidirectional 2 dBi gain 2.4/5 GHz Wi-Fi antenna with panel-mounting hardware and an approximately 7.5" (19 cm) cable to connect the antenna's SMA connector to the CM4's U.FL connector. It is "certified for use with the Raspberry Pi Compute Module 4".

Credits

Diodes Delight

An open source hardware company and consultancy


Timon Skerutsch


Makerfabs

Recommended

PCB Fabrication & PCB Assembly

See Also

Subscribe to the Crowd Supply newsletter, highlighting the latest creators and projects: