Eta Compute ECM3532 AI Vision


End of Life

ETA compute ECM3532 boards (AI Vision + AI Sensor) being no longer distributed 1, we are consequently also stopping the support. If you already have an existing model working on these boards, you can still deploy it on the other supported targets.

The Eta Compute ECM3532 AI Vision board is a tiny development board featuring the ECM3532 TENSAI SoC with a Cortex-M3 microcontroller and a separate CoolFlux DSP to speed up machine learning operations. The board includes a camera, a microphone and a one 6-axis accelerometer/gyroscope. The ECM3532 SoC on the development board supports Continuous Voltage Frequency Scaling, which allows the clock rate and voltage to be scaled at runtime to maximize energy efficiency, to run ultra-low power machine learning algorithms. This board is fully supported by Edge Impulse and you'll be able to sample raw data, build models, and deploy trained machine learning models directly from the studio. The AI Sensor is available for $65 from Digikey.

The Edge Impulse firmware for this development board is open source and hosted on GitHub: edgeimpulse/firmware-eta-compute-ecm3532.

Eta Compute ECM3532 AI VisionEta Compute ECM3532 AI Vision

Eta Compute ECM3532 AI Vision

Installing dependencies

To set this device up in Edge Impulse, you will need to install the following software:

  1. Edge Impulse CLI.
  2. Python 3 to flash new firmware.
  3. On Linux:
    • GNU Screen: install for example via sudo apt install screen.


Problems installing the CLI?

See the Installation and troubleshooting guide.

Connecting to Edge Impulse

With all the software in place it's time to connect the development board to Edge Impulse.

If you haven't created your free Edge Impulse account yet, head to Edge Impulse Studio to sign up.

1. Connect the development board to your computer

The Eta Compute EC3532 AI Vision comes with a SparkFun FTDI Basic Breakout - 3.3V board in the box. This breakout board is used to program the AI Sensor and to relay serial messages back to your computer. You can also use a different FTDI cable, but make sure that it outputs 3.3V as the AI Sensor is not 5V tolerant.

Connect the SparkFun FTDI Basic Breakout board to the AI Vision using connector J6. The most top pin on this connector (as seen below) is GND, so make sure you connect the breakout board correctly. Then connect the breakout board to your computer. The LEDs on the on the AI Vision should blink rapidly to indicate that the bootloader is running.

Connecting the Eta Compute ECM3532 AI Vision to your computer using the SparkFun FTDI Basic Breakout board.Connecting the Eta Compute ECM3532 AI Vision to your computer using the SparkFun FTDI Basic Breakout board.

Connecting the Eta Compute ECM3532 AI Vision to your computer using the SparkFun FTDI Basic Breakout board.

2. Update the firmware

The development board does not come with the right firmware yet. To update the firmware:

  1. Download the latest Edge Impulse firmware, and unzip the file.
  2. Open the flash script for your operating system (flash_windows.bat, flash_mac.command or to flash the firmware.
  3. Wait until flashing is complete. The on-board LEDs should stop blinking to indicate that the new firmware is running.

3. Setting keys

From a command prompt or terminal, run:


This will start a wizard which will ask you to log in, and choose an Edge Impulse project. If you want to switch projects run the command with --clean.

Alternatively, recent versions of Google Chrome and Microsoft Edge can collect data directly from your development board, without the need for the Edge Impulse CLI. See this blog post for more information.

4. Verifying that the device is connected

That's all! Your device is now connected to Edge Impulse. To verify this, go to your Edge Impulse project, and click Devices. The device will be listed here.

AI Vision connected to Edge ImpulseAI Vision connected to Edge Impulse

AI Vision connected to Edge Impulse

Next steps: building a machine learning model

With everything set up you can now build your first machine learning model with these tutorials:

Looking to connect different sensors? The Data forwarder lets you easily send data from any sensor into Edge Impulse.

Did this page help you?