The Arducam Pico4ML TinyML Dev Kit is a development board from Arducam with a RP2040 microcontroller, QVGA camera, bluetooth module (depending on your version), LCD screen, onboard microphone, accelerometer, gyroscope, and compass. Arducam has created in depth tutorials on how to get started using the Pico4ML Dev Kit with Edge Impulse, including how to collect new data and how to train and deploy your Edge Impulse models to the Pico4ML. The Arducam Pico4ML TinyML Dev Kit has two versions, the version with BLE and the version without BLE.

Setting up your development board

To set up your Arducam Pico4ML TinyML Dev Kit, follow this guide: Arducam: How to use Edge Impulse to train machine learning models for Raspberry Pico.

Next steps: building a machine learning model

With everything set up you can now build your first machine learning model with the Edge Impulse continuous motion recognition tutorial.

Or you can follow Arducam's tutorial on How to build a Magic Wand with Edge Impulse for Arducam Pico4ML-BLE.

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

Deploying back to device

With the impulse designed, trained and verified you can deploy this model back to your Arducam Pico4ML TinyML Dev Kit. This makes the model run without an internet connection, minimizes latency, and runs with minimum power consumption. Edge Impulse can package the complete impulse - including the signal processing code, neural network weights, and classification code - up into a single library that you can run on your development board. See the end of the Arducam's How to use Edge Impulse to train machine learning models for Raspberry Pico tutorial for more information on deploying your model onto the device.

Ambiq®, the leader in low-power System-on-Chip (SoC) solutions, has once again raised the bar with the Apollo4 Family of SoCs. With the lowest dynamic and sleep mode power on the market, the Apollo4 allows designers of next-generation edge AI devices to take their innovative products to the next level. Built upon Ambiq’s proprietary Subthreshold Power-Optimized Technology (SPOT®) platform, the Apollo4 Family of SoCs is a complete hardware and software solution that enables the battery-powered endpoint devices of tomorrow to achieve a higher level of intelligence without sacrificing battery life. Edge Impulse support is available on the Apollo4 Plus, Apollo4 Blue Plus, Apollo4 Lite, and Apollo4 Blue Lite. See below for how to get started on the Apollo4 Plus and Apollo4 Blue Plus SoCs.

The Apollo4 Plus is built on the 32-bit Arm® Cortex®-M4 core with Floating Point Unit (FPU). With up to 2 MB of NVM and 2.75 MB of SRAM, the Apollo4 Plus has more than enough compute and storage to handle complex algorithms and neural networks while displaying vibrant, crystal clear, and smooth graphics. If additional memory is required, an external memory is supported through Ambiq’s multi-bit SPI and eMMC interfaces. The Apollo4 Plus is purpose-built to serve as both an application processor and a co-processor for battery-powered endpoint devices, including predictive health and maintenance sensors, smart home devices, livestock trackers, wrist-based wearables, smart rings, smart voice devices, and more. The Apollo4 Plus is available now in BGA packaging. The Apollo4 Blue Plus incorporates an optional BLE 5.4 radio.

Installing dependencies

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

1. Edge Impulse CLI

2. Segger JLink

Connecting the Apollo4 Audio Add-on Board (Models with Audio Input Only)

This step is only needed when using models requiring microphone input, such as the example below. Skip this section if you are testing other models that do not need audio input.

Remove the pin header protectors on the Apollo4 Plus EVB (AMAP4PEVB) or Apollo4 Blue Plus KXR EVB (AMAP4BPXEVB), and carefully plug the Apollo4 Audio Add-onBoard (AMA4AUD) into the development board. Pay special attention to the highspeed connector with film tape, which must be removed before connecting the boards. Place the digital and analog microphone modules onto the shield, as shown in the image below, and connect cables to both type-C connectors on the evaluation board.

Connecting an ArduCam Mega 5MP SPI

This step is only needed when using models requiring camera input. Skip this section if you are testing other models that do not need camera input.

The ArduCam Mega 5MP SPI connects to the Apollo4 Plus EVB and Apollo4 Blue Plus KXR EVB pins as shown in the table below:

Flashing

Pre-built image with only audio support and "Hello World" detector example here

Pre-built image with full video and audio data collection and FOMO Face detector example here

Get started by extracting the archive and choose the appropriate script for your system architecture to flash the firmware:

Connecting to Edge Impulse

Using the daemon

From a command prompt or terminal, run:

edge-impulse-daemon

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, you can access the project API Key as shown below by navigating to the Dashboard section on the left pane of your Studio project and select the Keys tab, then click the copy/paste icon next to the API Key to copy the entire text to your clipboard, then run:

edge-impulse-daemon --api-key [paste your key here]

Connecting to Studio

Run the edge-impulse-daemon and connect to your project, you will be prompted to name your device:

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.

Collecting data

Audio

With the device connected to Studio, you can use it to collect audio data up to 5 seconds in length for training and testing your model. Navigate to the Data acquisition tab and start collecting samples:

Daemon output during sampling:

Video

Sampling images:

Three supported sizes 96x96, 128x128, 160x160:

Building a machine learning model

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

• Recognizing sounds from audio

• Responding to your voice

• Detecting objects with FOMO

If you flashed the pre-built binary with FOMO Face Detection example from above then just connect your board and run edge-impulse-run-impulse to see an output similar to this:

Example Impulse

Start by going to your Studio projects then create a new project and navigate to the Create impulse section of Impulse design, at which point you will be prompted to select your target, choose the Apollo4 Plus:

Then add the DSP block:

Then the keyword spotting learn block:

And finally save the impulse:

DSP

Now select the DSP block:

And go to Generate features:

Click the button and wait for the job to finish, when it does you'll see something like this:

Training

Select the learning block:

Then click Save & train and you'll eventually see an output like this:

Testing

Go to the Model testing section and enable int8 testing:

And run the test:

Deploying

Navigate to the Deployment section and choose the Apollo4 Blue Plus:

Now click Build and wait for the job to finish, when it does a zip archive will be downloaded to your computer:

Flashing

See the previous section on flashing the board.

Running the impulse

You can run your impulse by using edge-impulse-run-impulse:

Troubleshooting

If you have problems with the flashing script make sure you are using USB cables with data and not just power-only cables.

Reach out to us on the forum and have fun making machine learning models on the Apollo4 Family of SoCs from Ambiq!

The Portenta H7 is a powerful development board from Arduino with both a Cortex-M7 microcontroller and a Cortex-M4 microcontroller, a BLE/WiFi radio, and an extension slot to connect the Portenta vision shield - which adds a camera and dual microphones. The Portenta H7 and the vision shield are available directly from for ~$150 in total.

There are two versions of the vision shield: one that has an Ethernet connection and one with a LoRa radio. Both of these can be used with Edge Impulse.

The Edge Impulse firmware for this development board is open source and hosted on GitHub: .

Installing dependencies

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

3. On Linux:

   • GNU Screen: install for example via sudo apt install screen.

Connecting to Edge Impulse

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

1. Connect the vision shield

Using the vision shield using two edge connectors on the back Portenta H7.

2. Connect the development board to your computer

Use a USB-C cable to connect the development board to your computer. Then, double-tap the RESET button to put the device into bootloader mode. You should see the green LED on the front pulsating.

3. Update the firmware

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

2. Double press on the RESET button on your board to put it in the bootloader mode.

3. Open the flash script for your operating system (flash_windows.bat, flash_mac.command or flash_linux.sh) to flash the firmware.

4. Wait until flashing is complete, and press the RESET button once to launch the new firmware.

4. 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.

5. Verifying that the device is connected

Next steps: building a machine learning model

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

Deploying back to device

• Download your custom firmware from the Deployment tab in the Studio and install the firmware with the same method as in the "Update the firmware" section and run the edge-impulse-run-impulse command:

Note that it may take up to 10 minutes to compile the firmware for the Arduino Portenta H7

Troubleshooting

If you come across this issue:

You probably forgot to double press the RESET button before running the flash script.

The Arduino Nano 33 BLE Sense is a tiny development board with a Cortex-M4 microcontroller, motion sensors, a microphone and BLE - and it's fully supported by Edge Impulse. You'll be able to sample raw data, build models, and deploy trained machine learning models directly from the studio.

You can also use the Arduino Tiny Machine Learning Kit to run image classification models on the edge with the Arduino Nano and attached OV7675 camera module (or connect the hardware together via jumper wire and a breadboard if purchased separately).

You can tell which version of the Arduino Nano 33 BLE Sense you have by looking at the underside of the board. The first version will simply have NANO 33 BLE SENSE written in the silkscreen. The second version will have NANO 33 BLE SENSE REV2.

The Edge Impulse firmware for this development board is open source and hosted on GitHub: edgeimpulse/firmware-arduino-nano-33-ble-sense.

Installing dependencies

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

1. Edge Impulse CLI.

2. Arduino CLI.

   • Here's an instruction video for Windows.

   • The Arduino website has instructions for macOS and Linux.

3. On Linux:

   • GNU Screen: install for example via sudo apt install screen.

Connecting to Edge Impulse

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

1. Connect the development board to your computer

Use a micro-USB cable to connect the development board to your computer. Then press RESET twice to launch into the bootloader. The on-board LED should start pulsating to indicate this.

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 flash_linux.sh) to flash the firmware.

3. Wait until flashing is complete, and press the RESET button once to launch the new firmware.

3. Setting keys

From a command prompt or terminal, run:

edge-impulse-daemon

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.

Next steps: building a machine learning model

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

• Responding to your voice

• Recognize sounds from audio

• Adding sight to your sensors

• Object detection

• Counting objects using FOMO

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

Use a model in the Arduino IDE

One option to deploy your model is to use the Arduino library option on the Deployment page in your Edge Impulse Studio project. This will combine your model with your chosen processing block and automatically download an Arduino in a .zip file. In the Arduino IDE, select Sketch > Include Library > Add .ZIP Library... and select your downloaded .zip file.

Once the library finishes installing, you can select File > Examples > <name_of_your_project>_inferencing to see a list of available Arduino examples for the various supported boards. Notice that you have both Nano 33 Sense and Nano 33 Sense Rev2 options available.

The examples for camera, microphone, and microphone_fusion under nano_ble33_sense will work for both boards. You must choose the correct board revision (nano_ble33_sense or nano_ble33_sense_rev2) for the accelerometer, accelerometer_continuous, or fusion examples, as the accelerometer and environmental sensors are different between the board revisions.

These examples should give you a good starting place for developing your own edge ML applications on the Arduino. For example, if you train a keyword spotting model to identify the words "yes" and "no," you would deploy the model as an Arduino library and upload the nano_ble3_sense_microphone_continuous example to your Nano 33 BLE. Once uploaded, open the Serial Monitor to see the inference results printed out.

Troubleshooting

Bad CPU type in executable (Macbook M1)

It probably means you don't have Rosetta 2 installed yet (which allows Intel-based apps to run on M1 chips).

The error looks like the following:

Flashing board...
Failed uploading: cannot execute upload tool: fork/exec /Users/brianmcfadden/Library/Arduino15/packages/arduino/tools/bossac/1.9.1-arduino2/bossac: bad CPU type in executable

Saving session...
...copying shared history...
...saving history...truncating history files...
...completed.

[Process completed]

To install Rosetta 2 you can run this command:

softwareupdate --install-rosetta --agree-to-license

Connecting an off-the-shelf OV7675 camera module

You will need the following hardware:

• Arduino Nano 33 BLE Sense board with headers.

• OV7675 camera module.

• Micro-USB cable.

• Solderless breadboard and female-to-male jumper wires.

First, slot the Arduino Nano 33 BLE Sense board into a solderless breadboard:

With female-to-male jumper wire, use the following wiring diagram, pinout diagrams, and connection table to link the OV7675 camera module to the microcontroller board via the solderless breadboard:

Download the full pinout diagram of the Arduino Nano 33 BLE Sense here.

Finally, use a micro-USB cable to connect the Arduino Nano 33 BLE Sense development board to your computer.

Now build & train your own image classification model and deploy to the Arduino Nano 33 BLE Sense with Edge Impulse!

The Nicla Sense ME is a tiny, low-power tool that sets a new standard for intelligent sensing solutions. With the simplicity of integration and scalability of the Arduino ecosystem, the board combines four state-of-the-art sensors from Bosch Sensortec:

• BHI260AP motion sensor system with integrated AI.

• BMM150 magnetometer.

• BMP390 pressure sensor.

• BME688 4-in-1 gas sensor with AI and integrated high-linearity, as well as high-accuracy pressure, humidity and temperature sensors.

Designed to easily analyze motion and the surrounding environment – hence the “M” and “E” in the name – it measures rotation, acceleration, pressure, humidity, temperature, air quality and CO2 levels by introducing completely new Bosch Sensortec sensors on the market.

Its tiny size and robust design make it suitable for projects that need to combine sensor fusion and AI capabilities on the edge, thanks to a strong computational power and low-consumption combination that can even lead to standalone applications when battery-operated.

The Arduino Nicla Sense ME is available on the Arduino Store.

Installing dependencies

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

1. Edge Impulse CLI.

2. Arduino CLI.

   • Here's an instruction video for Windows.

   • The Arduino website has instructions for macOS and Linux.

3. On Linux:

   • GNU Screen: install for example via sudo apt install screen.

Connecting to Edge Impulse

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

1. Connect the development board to your computer

Use a micro-USB cable to connect the development board to your computer.

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 ingestion sketch.

2. Open the nicla_sense_ingestion.ino sketch in a text editor or the Arduino IDE.

3. For data ingestion into your Edge Impulse project, at the top of the file, select 1 or multiple sensors by un-commenting the defines and select a desired sample frequency (in Hz). For example, for the Environmental sensors:

   Copy

   /**
    * @brief   Sample & upload data to Edge Impulse Studio.
    * @details Select 1 or multiple sensors by un-commenting the defines and select
    * a desired sample frequency. When this sketch runs, you can see raw sample
    * values outputted over the serial line. Now connect to the studio using the
    * `edge-impulse-data-forwarder` and start capturing data
    */
   // #define SAMPLE_ACCELEROMETER
   // #define SAMPLE_GYROSCOPE
   // #define SAMPLE_ORIENTATION
   #define SAMPLE_ENVIRONMENTAL
   // #define SAMPLE_ROTATION_VECTOR
   
   /**
    * Configure the sample frequency. This is the frequency used to send the data
    * to the studio regardless of the frequency used to sample the data from the
    * sensor. This differs per sensors, and can be modified in the API of the sensor
    */
   #define FREQUENCY_HZ        10

4. Then, from your sketch's directory, run the Arduino CLI to compile:

   Copy

   arduino-cli compile --fqbn arduino:mbed_nicla:nicla_sense --output-dir . --verbose

5. Then flash to your Nicla Sense using the Arduino CLI:

   Copy

   arduino-cli upload --fqbn arduino:mbed_nicla:nicla_sense --input-dir . --verbose

6. Wait until flashing is complete, and press the RESET button once to launch the new firmware.

3. Data forwarder

From a command prompt or terminal, run:

edge-impulse-data-forwarder

This will start a wizard which will ask you to log in, and choose an Edge Impulse project. You will also name your sensor's axes (depending on which sensor you selected in your compiled nicla_sense_ingestion.ino sketch). If you want to switch projects/sensors run the command with --clean. Please refer to the table below for the names used for each axis corresponding to the type of sensor:

Note: These exact axis names are required to run the Edge Impulse Arduino library deployment example applications for the Nicla Sense without any changes.

Else, when deploying the model, you will see an error like the following:

Starting inferencing in 2 seconds...
ERR: Nicla sensors don't match the sensors required in the model
Following sensors are required: accel.x + accel.y + accel.z + gyro.x + gyro.y + gyro.z + ori.heading + ori.pitch + ori.roll + rotation.x ...

If your axis names are different, when using the generated Arduino Library for the inference, you can modify the eiSensors nicla_sensors[] (near line 70) in the sketch example to add your custom names. e.g.:

eiSensors nicla_sensors[] =
{
“accel.x”, &get_accX,
“accel.y”, &get_accY,
“accel.z”, &get_accZ,
“gyro.x”, &get_gyrX,
“gyro.y”, &get_gyrY,
“gyro.z”, &get_gyrZ,
“ori.heading”, &get_oriHeading,
“ori.pitch”, &get_oriPitch,
“ori.roll”, &get_oriRoll,
“rotation.x”, &get_rotX,
“rotation.y”, &get_rotY,
“rotation.z”, &get_rotZ,
“rotation.w”, &get_rotW,
“temperature”, &get_temperature,
“barometer”, &get_barrometric_pressure,
“humidity”, &get_humidity,
“gas”, &get_gas,
};

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.

Next steps: building a machine learning model

With everything set up you can now build your first machine learning model with the Edge Impulse continuous motion recognition tutorial.

Looking to connect different sensors? Use the nicla_sense_ingestion sketch and the Edge Impulse Data forwarder to easily send data from any sensor on the Nicla Sense into your Edge Impulse project.

Deploying back to device

With the impulse designed, trained and verified you can deploy this model back to your Arduino Nicla Sense ME. This makes the model run without an internet connection, minimizes latency, and runs with minimum power consumption. Edge Impulse can package the complete impulse - including the signal processing code, neural network weights, and classification code - up into a single library that you can run on your development board.

Use the Running your impulse locally: On your Arduino tutorial and select one of the Nicla Sense examples.

The Nicla Vision is a ready-to-use, standalone camera for analyzing and processing images on the Edge. Thanks to its 2MP color camera, smart 6-axis motion sensor, integrated microphone, and distance sensor, it is suitable for asset tracking, object recognition, and predictive maintenance. Some of its key features include:

• Powerful microcontroller equipped with a 2MP color camera

• Tiny form factor of 22.86 x 22.86 mm

• Integrated microphone, distance sensor, and intelligent 6-axis motion sensor

• Onboard Wi-Fi and Bluetooth® Low Energy connectivity

• Standalone when battery-powered

• Expand existing projects with sensing capabilities

• Enable fast Machine Vision prototyping

• Compatible with Nicla, Portenta, and MKR products

Its exceptional capabilities are supported by a powerful STMicroelectronics STM32H747AII6 Dual ARM® Cortex® processor, combining an M7 core up to 480 Mhz and an M4 core up to 240 Mhz. Despite its industrial strength, it keeps energy consumption low for battery-powered standalone applications.

The Arduino Nicla Vision is available for around 95 EUR from the Arduino Store.

Installing dependencies

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

1. Edge Impulse CLI.

2. Arduino CLI.

   • Here's an instruction video for Windows.

   • The Arduino website has instructions for macOS and Linux.

3. On Linux:

   • GNU Screen: install for example via sudo apt install screen.

Connecting to Edge Impulse

There are two ways to connect the Nicla Vision to Edge Impulse:

• Using the official Edge Impulse firmware - it supports all onboard sensors, including camera.

• Using an ingestion script. This supports analog, IMU, proximity sensors and microphone (limited to 8 kHz), but not the camera. It is only recommended if you want to modify the ingestion flow for third-party sensors.

Edge Impulse firmware

1. Connect the development board to your computer

Use a micro-USB cable to connect the development board to your computer. Under normal circumstances, flash process should work without entering the bootloader manually. However if run into difficulties flashing the board, you can enter the bootloader by pressing RESET twice. The onboard LED should start pulsating to indicate this.

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 flash_linux.sh) to flash the firmware.

3. Wait until flashing is complete, and press the RESET button once to launch the new firmware.

3. Setting keys

From a command prompt or terminal, run:

edge-impulse-daemon

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.

Edge Impulse ingestion scripts

1. Connect the development board to your computer

Use a micro-USB cable to connect the development board to your computer.

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 ingestion sketches and unzip the file.

2. Open the nicla_vision_ingestion.ino (for IMU/proximity sensor) or nicla_vision_ingestion_mic.ino(for microphone) sketch in a text editor or the Arduino IDE.

3. For IMU/proximity sensor data ingestion into your Edge Impulse project, at the top of the file, select 1 or multiple sensors by un-commenting the defines and select the desired sample frequency (in Hz). For example, for the accelerometer sensor:

/**
 * @brief   Sample & upload data to Edge Impulse Studio.
 * @details Select 1 or multiple sensors by un-commenting the defines and select
 * a desired sample frequency. When this sketch runs, you can see raw sample
 * values outputted over the serial line. Now connect to the studio using the
 * `edge-impulse-data-forwarder` and start capturing data
 */
#define SAMPLE_ACCELEROMETER
//#define SAMPLE_GYROSCOPE
//#define SAMPLE_PROXIMITY

/**
 * Configure the sample frequency. This is the frequency used to send the data
 * to the studio regardless of the frequency used to sample the data from the
 * sensor. This differs per sensors, and can be modified in the API of the sensor
 */
#define FREQUENCY_HZ        10

For microphone data ingestion, you do not need to change the default parameters in the nicla_vision_ingestion_mic.ino sketch.

1. Then, from your sketch's directory, run the Arduino CLI to compile:

   Copy

   arduino-cli compile --fqbn arduino:mbed_nicla:nicla_vision --output-dir .

2. Then flash to your Nicla Vision using the Arduino CLI:

   Copy

   arduino-cli upload --fqbn arduino:mbed_nicla:nicla_vision

1. Wait until flashing is complete, and press the RESET button once to launch the new firmware.

3a. Data forwarder (Fusion sensors)

From a command prompt or terminal, run:

edge-impulse-data-forwarder

This will start a wizard which will ask you to log in, and choose an Edge Impulse project. You will also name your sensor's axes (depending on which sensor you selected in your compiled nicla_vision_ingestion.ino sketch). If you want to switch projects/sensors run the command with --clean. Please refer to the table below for the names used for each axis corresponding to the type of sensor:

Note: These exact axis names are required for the Edge Impulse Arduino library deployment example applications for the Nicla Vision.

3b. Data forwarder (Microphone)

From a command prompt or terminal, run:

edge-impulse-data-forwarder --baud 1000000 --frequency 8000

This will start a wizard which will ask you to log in and choose an Edge Impulse project. You will also name your sensor axes - in the case of the microphone, you need to enter audio. If you want to switch projects/sensors run the command with --clean.

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.

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

• Building a continuous motion recognition system.

• Recognizing sounds from audio.

• Responding to your voice

• Adding sight to your sensors

• Counting objects using FOMO

Looking to connect different sensors? Use the nicla_vision_ingestion.ino sketch and the Edge Impulse data forwarder to easily send data from any sensor on the Nicla Vision into your Edge Impulse project.

Deploying back to device

With the impulse designed, trained and verified you can deploy this model back to your Arduino Nicla Vision. This makes the model run without an internet connection, minimizes latency, and runs with minimum power consumption. Edge Impulse can package the complete impulse - including the signal processing code, neural network weights, and classification code - up into a single library that you can run on your development board.

Use the Running your impulse locally: On your Arduino tutorial and select one of the Nicla Vision examples.

The Infineon Semiconductor enables the evaluation and development of applications using the PSoC 62 Series MCU. This low-cost hardware platform enables the design and debug of the PSoC 62 MCU and the Murata 1LV Module (CYW43012 Wi-Fi + Bluetooth Combo Chip). The PSoC 6 MCU is Infineon' latest, ultra-low-power PSoC specifically designed for wearables and IoT products. The board features a PSoC 6 MCU, and a CYW43012 Wi-Fi/Bluetooth combo module. Infineon CYW43012 is a 28nm, ultra-low-power device that supports single-stream, dual-band IEEE 802.11n-compliant Wi-Fi MAC/baseband/radio and Bluetooth 5.0 BR/EDR/LE. When paired with the , the PSoC® 62S2 Wi-Fi® BLUETOOTH® Pioneer Kit can be used to easily interface a variety of sensors with the PSoC™ 6 MCU platform, specifically targeted for audio and machine learning applications which are fully supported by Edge Impulse! You'll be able to sample raw data as well as build and deploy trained machine learning models to your PSoC® 62S2 Wi-Fi® BLUETOOTH® Pioneer Kit, directly from the Edge Impulse Studio.

The Edge Impulse firmware for this development board is open source and hosted on GitHub: .

Installing dependencies

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

Updating the firmware

1. Download the base firmware image

2. Connect the CY8CKIT-062S2 Pioneer Kit to your computer

3. Load the base firmware image with Infineon CyProgrammer

Then select the base firmware image file you downloaded in the first step above (i.e., the file named firmware-infineon-cy8ckit-062s2.hex). You can now press the Connect button to connect to the board, and finally the Program button to load the base firmware image onto the CY8CKIT-062S2 Pioneer Kit.

Connecting to Edge Impulse

With all the software in place, it's time to connect the CY8CKIT-062S2 Pioneer Kit to Edge Impulse.

1. Connect the development board to your computer

Use a micro-USB cable to connect the development board to your computer.

2. 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.

3. Verifying that the device is connected

Next steps: Build a machine learning model

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

The is a hardware platform that enables the evaluation and development of applications using the PSoC™ 63 MCU with AIROC™ Bluetooth® LE. The PSoC 6 BLE Pioneer Kit when paired along with the E-ink display shield board, , forms a powerful combination with its onboard sensors. The kit come with an onboard thermistor, 6-axis motion sensor, and a digital microphone. The PSoC 6 BLE Pioneer Kit baseboard also comes with 2 buttons, a 5-segment slider, and a proximity sensor based on CAPSENSE™ technology.

The Edge Impulse firmware for this development board is open source and hosted on GitHub: .

Installing dependencies

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

Updating the firmware

1. Download the base firmware image

2. Connect the CY8CKIT-062-BLEPioneer Kit to your computer

3. Load the base firmware image with Infineon CyProgrammer

Then select the base firmware image file you downloaded in the first step above (i.e., the file named firmware-infineon-cy8ckit-062-ble.hex). You can now press the Connect button to connect to the board, and finally the Program button to load the base firmware image onto the CY8CKIT-062S2 Pioneer Kit.

Connecting to Edge Impulse

With all the software in place, it's time to connect the CY8CKIT-062S2 Pioneer Kit to Edge Impulse.

1. Connect the development board to your computer

Use a micro-USB cable to connect the development board to your computer.

2. 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.

3. Verifying that the device is connected

ModusToolBox Examples

To create an example project you must first open a new ModusToolBox application from the File menu

Then, you must choose which board support package (BSP) you wish to run your application on. Boards that are officially supported will have Edge Impulse examples.

Lastly, in the Project Creator window, you may select any Edge Impulse listings available for that product and click on Create. Please refer to the ModusToolBox help and tutorials for more information on running applications on your device.

Inferencing with BLE

Next steps: Build a machine learning model

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

Espressif ESP-EYE (ESP32) is a compact development board based on Espressif's ESP32 chip, equipped with a 2-Megapixel camera and a microphone. ESP-EYE also offers plenty of storage, with 8 MB PSRAM and 4 MB SPI flash - and it's fully supported by Edge Impulse. You'll be able to sample raw data, build models, and deploy trained machine learning models directly from the studio.

There are plenty of other boards built with ESP32 chip - and of course there are custom designs utilizing ESP32 SoM. Edge Impulse firmware was tested with ESP-EYE and ESP FireBeetle boards, but there is a possibility to modify the firmware to use it with other ESP32 designs. Read more on that in section of this documentation.

The Edge Impulse firmware for this development board is open source and hosted on GitHub: .

Installing dependencies

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

2. Python 3.

4. On Linux:

   • GNU Screen: install for example via sudo apt install screen.

Connecting to Edge Impulse

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

1. Connect the development board to your computer

Use a micro-USB cable to connect the development board to your computer.

2. Update the firmware

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

2. Open the flash script for your operating system (flash_windows.bat, flash_mac.command or flash_linux.sh) to flash the firmware.

3. Wait until flashing is complete.

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.

4. Verifying that the device is connected

Next steps: building a machine learning model

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

Sensors available

The standard firmware supports the following sensors:

• Camera: OV2640, OV3660, OV5640 modules from Omnivision

• Microphone: I2S microphone on ESP-EYE (MIC8-4X3-1P0)

• LIS3DHTR module connected to I2C (SCL pin 22, SDA pin 21)

• Any analog sensor, connected to A0

Using with other ESP32 boards

ESP32 is a very popular chip both in a community projects and in industry, due to its high performance, low price and large amount of documentation/support available. There are other camera enabled development boards based on ESP32, which can use Edge Impulse firmware after applying certain changes, e.g.

• AI-Thinker ESP-CAM

• M5STACK ESP32 PSRAM Timer Camera X (OV3660)

• M5STACK ESP32 Camera Module Development Board (OV2640)

Additionally, since Edge Impulse firmware is open-source and available to public, if you have made modifications/added new sensors capabilities, we encourage you to make a PR in firmware repository!

Deploy your impulse

To deploy your impulse on your ESP32 board, please see:

The Himax WE-I Plus is a tiny development board with a camera, a microphone, an accelerometer and a very fast DSP - and it's fully supported by Edge Impulse. You'll be able to sample raw data, build models, and deploy trained machine learning models directly from the studio. It's available on .

The Edge Impulse firmware for this development board is open source and hosted on GitHub: .

Installing dependencies

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

2. On Linux:

   • GNU Screen: install for example via sudo apt install screen.

Connecting to Edge Impulse

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

1. Connect the development board to your computer

Use a micro-USB cable to connect the development board to your computer.

2. Update the firmware

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

2. Open the flash script for your operating system (flash_windows.bat, flash_mac.command or flash_linux.sh) to flash the firmware.

3. Wait until flashing is complete, and press the RESET button once to launch the new firmware.

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.

4. Verifying that the device is connected

Next steps: building a machine learning model

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

Troubleshooting

All licenses are in use by other developers.

COM port not detected

The Blues Wireless Swan is a development board featuring a 120MHz ARM Cortex-M4 from STMicroelectronics with 2MB of flash and 640KB of RAM. Blues Wireless has created an on how to get started using the Swan with Edge Impulse, including how to collect new data from a triple axis accelerometer and how to train and deploy your Edge Impulse models to the Swan. For more details and ordering information, visit the Blues Wireless Swan .

Setting up your development board

Next steps: building a machine learning model

1. Idle (no motion)

2. Circle

3. Slash

4. An up-and-down motion in the shape of the letter "W"

Deploying back to device

With the impulse designed, trained and verified you can deploy this model back to your Blues Wireless Swan. This makes the model run without an internet connection, minimizes latency, and runs with minimum power consumption. Edge Impulse can package the complete impulse - including the signal processing code, neural network weights, and classification code - up into a single library that you can run on your development board. See the end of the Blues Wireless' [Using Swan with Edge Impulse] (https://dev.blues.io/swan/using-swan-with-edge-impulse) tutorial for more information on deploying your model onto the device.

The Nordic Semiconductor nRF52840 DK is a development board with a Cortex-M4 microcontroller, QSPI flash, and an integrated BLE radio - and it's fully supported by Edge Impulse. You'll be able to sample raw data, build models, and deploy trained machine learning models directly from the studio. As the nRF52840 DK does not have any built-in sensors we recommend you to pair this development board with the shield (with a MEMS accelerometer and a MEMS microphone).

If you don't have the X-NUCLEO-IKS02A1 shield you can use the to capture data from any other sensor, and then follow the tutorial to run your impulse. Or, you can modify the example firmware (based on nRF Connect) to interact with other accelerometers or PDM microphones that are supported by Zephyr.

The Edge Impulse firmware for this development board is open source and hosted on GitHub: .

Installing dependencies

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

2. On Linux:

   • GNU Screen: install for example via sudo apt install screen.

Connecting to Edge Impulse

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

1. Plugging in the X-NUCLEO-IKS02A1 MEMS expansion shield

Remove the pin header protectors on the nRF52840 DK and plug the X-NUCLEO-IKS02A1 shield into the development board.

Note: Make sure that the shield does not touch any of the pins in the middle of the development board. This might cause issues when flashing the board or running applications.

2. Connect the development board to your computer

Use a micro-USB cable to connect the development board to your computer. There are two USB ports on the development board, use the one on the short side of the board. Then, set the power switch to 'on'.

3. Update the firmware

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

1. The development board is mounted as a USB mass-storage device (like a USB flash drive), with the name JLINK. Make sure you can see this drive.
3. Drag the nrf52840-dk.bin file to the JLINK drive.

4. Wait 20 seconds and press the BOOT/RESET button.

4. 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.

5. Verifying that the device is connected

Next steps: building a machine learning model

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

Troubleshooting

No JLINK drive

If you don't see the JLINK drive show up when you connect your nRF52840 DK you'll have to update the interface firmware.

1. Set the power switch to 'off'.

2. Hold BOOT/RESET while you set the power switch to 'on'.

3. Your development board should be mounted as BOOTLOADER.

5. After 20 seconds disconnect the USB cable, and plug the cable back in.

6. The development board should now be mounted as JLINK.

Failed to flash

If your board fails to flash new firmware (a FAIL.txt file might appear on the JLINK drive) you can also flash using nrfjprog.

2. Flash new firmware via:

The Nordic Semiconductor nRF5340 DK is a development board with dual Cortex-M33 microcontrollers, QSPI flash, and an integrated BLE radio - and it's fully supported by Edge Impulse. You'll be able to sample raw data, build models, and deploy trained machine learning models directly from the studio. As the nRF5340 DK does not have any built-in sensors we recommend you to pair this development board with the shield (with a MEMS accelerometer and a MEMS microphone).

If you don't have the X-NUCLEO-IKS02A1 shield you can use the to capture data from any other sensor, and then follow the tutorial to run your impulse. Or, you can modify the example firmware (based on nRF Connect) to interact with other accelerometers or PDM microphones that are supported by Zephyr.

The Edge Impulse firmware for this development board is open source and hosted on GitHub: .

Installing dependencies

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

2. On Linux:

   • GNU Screen: install for example via sudo apt install screen.

Connecting to Edge Impulse

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

1. Plugging in the X-NUCLEO-IKS02A1 MEMS expansion shield

Remove the pin header protectors on the nRF5340 DK and plug the X-NUCLEO-IKS02A1 shield into the development board.

Note: Make sure that the shield does not touch any of the pins in the middle of the development board. This might cause issues when flashing the board or running applications.

2. Connect the development board to your computer

Use a micro-USB cable to connect the development board to your computer. There are two USB ports on the development board, use the one on the short side of the board. Then, set the power switch to 'on'.

3. Update the firmware

The development board does not come with the right firmware yet. To update the Firmware + Networking Component:

1. The development board is mounted as a USB mass-storage device (like a USB flash drive), with the name JLINK. Make sure you can see this drive.

4. Drag and drop the nrf5340-dk-full.hex firmware from the downloaded zip in this Programmer application (this firmware contains both application and networking core firmware).

5. Click “Erase & Write” and wait for device to boot up.

4. Setting keys

From a command prompt or terminal, run:

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

The nRF5340 DK exposes multiple UARTs. If prompted, choose the bottom one:

5. Verifying that the device is connected

Next steps: building a machine learning model

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

Troubleshooting

Failed to flash

If your board fails to flash new firmware (a FAIL.txt file might appear on the JLINK drive) you can also flash using nrfjprog.

2. Flash new firmware via:

The Nordic Semiconductor nRF9160 DK is a development board with an nRF9160 SIP incorporating a Cortex M-33 for your application, a full LTE-M/NB-IoT modem with GPS along with 1 MB of flash and 256 KB RAM. It also includes an nRF52840 board controller with Bluetooth Low Energy connectivity. The Development Kit is fully supported by Edge Impulse. You'll be able to sample raw data, build models, and deploy trained machine learning models directly from the studio. As the nRF9160 DK does not have any built-in sensors we recommend you to pair this development board with the shield (with a MEMS accelerometer and a MEMS microphone).

If you don't have the X-NUCLEO-IKS02A1 shield you can use the to capture data from any other sensor, and then follow the tutorial to run your impulse. Or, you can modify the example firmware (based on nRF Connect) to interact with other accelerometers or PDM microphones that are supported by Zephyr.

The Edge Impulse firmware for this development board is open source and hosted on GitHub: .

Installing dependencies

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

2. On Linux:

   • GNU Screen: install for example via sudo apt install screen.

Connecting to Edge Impulse

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

1. Plugging in the X-NUCLEO-IKS02A1 MEMS expansion shield

Remove the pin header protectors on the nRF9160 DK and plug the X-NUCLEO-IKS02A1 shield into the development board.

Note: Make sure that the shield does not touch any of the pins in the middle of the development board. This might cause issues when flashing the board or running applications. You can also remove the shield before flashing the board.

2. Connect the development board to your computer

Use a micro-USB cable to connect the development board to your computer. There are two USB ports on the development board, use the one on the short side of the board. Then, set the power switch to 'on'.

3. Update the firmware

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

1. The development board is mounted as a USB mass-storage device (like a USB flash drive), with the name JLINK. Make sure you can see this drive.

4. Flash the board controller, you only need to do this once. Go to step 4 if you've performed this step before.

   • Ensure that the PROG/DEBUG switch is in nRF52 position.

   • Copy board-controller.bin to the JLINK mass storage device.

1. Flash the application:

   • Ensure that the PROG/DEBUG switch is in nRF91 position.

   • Run the flash script for your Operating System.

2. Wait 20 seconds and press the BOOT/RESET button.

4. Setting keys

From a command prompt or terminal, run:

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

The nRF9160 DK exposes multiple UARTs. If prompted, choose the top one:

5. Verifying that the device is connected

Next steps: building a machine learning model

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

The Nordic Semiconductor nRF9151 DK is a development board with an nRF9151 SIP incorporating a Cortex M33 for your application, a full LTE-M/NB-IoT and DECT NR+ modem with GPS along with 1 MB of flash and 256 KB RAM. The Development Kit is fully supported by Edge Impulse. You'll be able to sample raw data, build models, and deploy trained machine learning models directly from the studio. As the nRF9151 DK does not have any built-in sensors we recommend you to pair this development board with the shield (with a MEMS accelerometer and a MEMS microphone).

If you don't have the X-NUCLEO-IKS02A1 shield you can use the to capture data from any other sensor, and then follow the tutorial to run your impulse. Or, you can modify the example firmware (based on nRF Connect) to interact with other accelerometers or PDM microphones that are supported by Zephyr.

The Edge Impulse firmware for this development board is open source and hosted on GitHub: .

Installing dependencies

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

2. On Linux:

   • GNU Screen: install for example via sudo apt install screen.

Connecting to Edge Impulse

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

1. Plugging in the X-NUCLEO-IKS02A1 MEMS expansion shield

Remove the pin header protectors on the nRF9151 DK and plug the X-NUCLEO-IKS02A1 shield into the development board.

Note: Make sure that the shield does not touch any of the pins in the middle of the development board. This might cause issues when flashing the board or running applications. You can also remove the shield before flashing the board.

2. Connect the development board to your computer

Use a USB-C cable to connect the development board to your computer. Then, set the power switch to 'on'.

3. Configure the board

4. Update the firmware

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

1. The development board is mounted as a USB mass-storage device (like a USB flash drive), with the name JLINK. Make sure you can see this drive.

4. Flash the application by running the flash script for your Operating System.

5. Wait 20 seconds and press the BOOT/RESET button.

5. Setting keys

From a command prompt or terminal, run:

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

The nRF9151 DK exposes multiple UARTs. If prompted, choose the top one:

6. Verifying that the device is connected

Next steps: building a machine learning model

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

The Nordic Semiconductor nRF7002 DK is the development kit for the nRF7002 WiFi 6 companion IC. The kit contains everything you need to get started with your development on a single board. It features an nRF5340 multiprotocol System-on-a-Chip (SoC) as a host processor for the nRF7002 - and it is now supported by Edge Impulse.

The nRF7002 is a Wi-Fi 6 companion IC, providing seamless connectivity and Wi-Fi-based locationing (SSID sniffing of local Wi-Fi hubs). It is designed to be used alongside Nordic’s existing nRF52 and nRF53 Series Bluetooth SoCs, and nRF91 Series cellular IoT Systems-in-Package (SiPs). The nRF7002 can also be used in conjunction with non-Nordic host devices.

With its integration with Edge Impulse, you will be able to sample raw data, build models, and deploy trained machine learning models directly from the studio. As the nRF7002 DK does not have any built-in sensors, we recommend pairing this development board with the shield (with a MEMS accelerometer).

If you don't have access to the X-NUCLEO-IKS02A1 shield, you can use our to capture data from any other sensor, and then follow the tutorial to run your impulse. Or, you can modify the example firmware (based on nRF Connect) to interact with other accelerometers or PDM microphones that are supported by Zephyr.

The Edge Impulse firmware for this development board is open source and hosted on GitHub: .

Installing dependencies

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

2. On Linux:

   • GNU Screen: install for example via sudo apt install screen.

3. • Note that for the nRF7002 DK, the required J-Link version is V7.94e

Connecting to Edge Impulse

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

1. Plugging in the X-NUCLEO-IKS02A1 MEMS expansion shield

Remove the pin header protectors on the nRF7002 DK and plug the X-NUCLEO-IKS02A1 shield into the development board.

Note: Make sure that the shield does not touch any of the pins in the middle of the development board. This might cause issues when flashing the board or running applications.

2. Connect the development board to your computer

Use a micro-USB cable to connect the development board to your computer. There are two USB ports on the development board, use the one on the short side of the board. Then, set the power switch on the bottom left to 'on'.

3. Update the firmware

The development board does not come with the right firmware yet. To update the Firmware + Networking Component:

1. The development board is mounted as a USB mass-storage device (like a USB flash drive), with the name JLINK. Make sure you can see this drive.

4. Drag and drop the nrf7002-dk-full.hex firmware from the downloaded zip in this Programmer application (this firmware contains both application and networking core firmware).

5. Click “Erase & Write” and wait for device to boot up.

4. Connecting to Edge Impulse Studio

From a command prompt or terminal, run:

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

The nRF5340 DK exposes multiple UARTs. If prompted, choose the bottom one:

5. Setting up WiFI connection

Once the nRF7002 DK is connected to a project in your profile, it will prompt to setup a WiFi connection:

Select 'Yes' at this step to connect your device to your local WiFi network. After selecting 'Yes', the daemon will scan for WiFi networks in the vicinity and print out a list for you to choose:

Navigate to your WiFi network to select it and enter password when prompted. Your kit will then connect to the WiFi and then connect to the project you selected in step 4.

6. Verify that the device is connected

Since your device is now connected via WiFi, you should be able to disconnect the daemon and collect your sensor data over the WiFi connection.

7. Flashing your model

8. Inferencing

This will then display the inference results, in this case classify the motion of the nRF7002 DK board, in the terminal:

Note: In order to receive and view these inference results, you will need to have the X-NUCLEO-IKS02A1 shield connected to the DK since there are no sensors on the DK board itself.

Next steps: building a machine learning model

With everything set up you can now build your first machine learning model with this tutorial:

Troubleshooting

Failed to flash

If your board fails to flash new firmware (a FAIL.txt file might appear on the JLINK drive) you can also flash using nrfjprog.

2. Flash new firmware via:

The Nordic Semiconductor Thingy:91 is an easy-to-use battery-operated prototyping platform for cellular IoT using LTE-M, NB-IoT and GPS. It is ideal for creating Proof-of-Concept (PoC), demos and initial prototypes in your cIoT development phase. Thingy:91 is built around the nRF9160 SiP and is certified for a broad range of LTE bands globally, meaning the Nordic Thingy:91 can be used just about anywhere in the world. There is an nRF52840 multiprotocol SoC on the Thingy:91. This offers the option of adding Bluetooth Low Energy connectivity to your project.

Nordic's Thingy:91 is fully supported by Edge Impulse. You'll be able to sample raw data, build models, and deploy trained machine learning models directly from the studio.

The Edge Impulse firmware for this development board is open source and hosted on GitHub: edgeimpulse/firmware-nordic-thingy91.

Installing dependencies

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

1. nRF Connect for Desktop.

2. Edge Impulse CLI.

3. On Linux:

   • GNU Screen: install for example via sudo apt install screen.

Updating the firmware

Before you start a new project, you need to update the Thingy:91 firmware to our latest build.

1. Connect the development board to your computer

Use a micro-USB cable to connect the development board to your computer. Then, set the power switch to 'on'.

2. Download the firmware

Download the latest Edge Impulse firmware. The extracted archive contains the following files:

1. firmware.hex: the Edge Impulse firmware image for the nRF9160 SoC, and

2. connectivity-bridge.hex: a connectivity application for the nRF52840 that you only need on older boards (hardware version < 1.4)

3. Update the firmware

1. Open nRF Connect for Desktop and launch the Programmer application.

2. Scroll down in the menu on the right and make sure Enable MCUboot is selected.

1. Switch off the Nordic Thingy:91.

2. Press the multi-function button (SW3) while switching SW1 to the ON position.

1. In the Programmer navigation bar, click Select device.

2. In the menu on the right, click Add HEX file > Browse, and select the firmware.hex file from the firmware previously downloaded.

3. Scroll down in the menu on the right to Device and click Write:

1. In the MCUboot DFU window, click Write. When the update is complete, a Completed successfully message appears.

2. You can now disconnect the board.

[SER] Serial is connected, trying to read config...
[SER] Failed to get info off device Timeout when waiting for >  (timeout: 5000) onConnected

Connecting to Edge Impulse

With all the software in place it's time to connect the development board to Edge Impulse. From a command prompt or terminal, run:

edge-impulse-daemon

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

The Thingy:91 exposes multiple UARTs. If prompted, choose the first one:

? Which device do you want to connect to? (Use arrow keys)
❯ /dev/tty.usbmodem14401 (Nordic Semiconductor)
  /dev/tty.usbmodem14403 (Nordic Semiconductor)

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.

Next steps: building a machine learning model

With everything set up you can now build your first machine learning model with this tutorial:

• Building a continuous motion recognition system.

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

The Nordic Semiconductor nRF9161 DK is a development board with an nRF9161 SIP incorporating a Cortex M33 for your application, a full LTE-M/NB-IoT and DECT NR+ modem with GPS along with 1 MB of flash and 256 KB RAM. The Development Kit is fully supported by Edge Impulse. You'll be able to sample raw data, build models, and deploy trained machine learning models directly from the studio. As the nRF9161 DK does not have any built-in sensors we recommend you to pair this development board with the X-NUCLEO-IKS02A1 shield (with a MEMS accelerometer and a MEMS microphone).

If you don't have the X-NUCLEO-IKS02A1 shield you can use the Data forwarder to capture data from any other sensor, and then follow the Running your impulse locally: On your Zephyr-based Nordic Semiconductor development board tutorial to run your impulse. Or, you can modify the example firmware (based on nRF Connect) to interact with other accelerometers or PDM microphones that are supported by Zephyr.

The Edge Impulse firmware for this development board is open source and hosted on GitHub: edgeimpulse/firmware-nrf-9161.

Installing dependencies

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

1. Edge Impulse CLI.

2. On Linux:

   • GNU Screen: install for example via sudo apt install screen.

Connecting to Edge Impulse

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

1. Plugging in the X-NUCLEO-IKS02A1 MEMS expansion shield

Remove the pin header protectors on the nRF9161 DK and plug the X-NUCLEO-IKS02A1 shield into the development board.

Note: Make sure that the shield does not touch any of the pins in the middle of the development board. This might cause issues when flashing the board or running applications. You can also remove the shield before flashing the board.

2. Connect the development board to your computer

Use a USB-C cable to connect the development board to your computer. Then, set the power switch to 'on'.

3. Configure the board

nRF9161 DK can be configured with Board Configurator tool that is inside nRF Connect for Desktop. All information on how this tool works and how to install it can be found in the document page. For our application the board need to have following configuration:

4. Update the firmware

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

1. The development board is mounted as a USB mass-storage device (like a USB flash drive), with the name JLINK. Make sure you can see this drive.

2. Install the nRF Command Line Tools.

3. Download the latest Edge Impulse firmware.

4. Flash the application by running the flash script for your Operating System.

5. Wait 20 seconds and press the BOOT/RESET button.

5. Setting keys

From a command prompt or terminal, run:

edge-impulse-daemon

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

The nRF9161 DK exposes multiple UARTs. If prompted, choose the top one:

? Which device do you want to connect to? (Use arrow keys)
❯ /dev/tty.usbmodem0010509762101 (SEGGER)
   /dev/tty.usbmodem0010509762103 (SEGGER)

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.

6. 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.

Next steps: building a machine learning model

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

• Building a continuous motion recognition system.

• Recognizing sounds from audio.

• Responding to your voice.

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

The Nordic Thingy:53™ is an easy-to-use prototyping platform, it makes it possible to create prototypes and proof-of-concepts without the need to build custom hardware. Thingy:53 is built around the nRF5340 SoC. The capacity of its dual Arm Cortex-M33 processors enables it to do embedded machine learning (ML), both collecting data and running trained ML models on the device. The Bluetooth Low Energy radio allows it to connect to smart phones, tablets, laptops and similar devices, without the need for a wired connection. Other protocols like Thread, Zigbee and proprietary 2.4 GHz protocols are also supported by the radio. It also includes a well of different integrated sensors, an NFC antenna, and has two buttons and one RGB LED that simplifies input and output.

Nordic's Thingy:53 is fully supported by Edge Impulse and every Thingy:53 is shipped with Edge Impulse firmware already flashed. You'll be able to sample raw data, build models, and deploy trained machine learning models directly out-of-the-box via the Edge Impulse Studio or the Nordic nRF Edge Impulse iPhone and Android apps over BLE connection.

The Edge Impulse firmware for this development board is open source and hosted on GitHub: edgeimpulse/firmware-nordic-thingy53.

Installing dependencies

To set this device up in Edge Impulse via USB serial or external debug probe, you will need to install the following software:

1. nRF Connect for Desktop v3.11.1 (only needed to update device firmware through USB or external debug probe).

2. Edge Impulse CLI.

3. On Linux:

   • GNU Screen: install for example via sudo apt install screen.

Updating the firmware

A brand new Thingy:53 devices will work out-of-the-box with the Edge Impulse Studio and the Nordic nRF Edge Impulse iPhone and Android apps. However, if your device has been flashed with some other firmware, then follow the steps below to update your device to the latest Edge Impulse firmware.

1. Connect the development board to your computer

Use a USB cable to connect the development board to your computer. Then, set the power switch to 'on'.

2. Download the firmware

Download the latest Edge Impulse firmware:

• Edge Impulse firmware: nordic-thingy53-full.zip

  • *-full.zip contains HEX files to upgrade the device through the external probe.

• Edge Impulse firmware: nordic-thingy53-dfu.zip

  • *-dfu.zip contains dfu_application.zip package to upgrade the already flashed device through the Serial/USB bootloader.

3. Update the firmware

Follow Nordic's instructions to update the firmware on the Thingy:53 through your choice of debugging connection:

• Updating through Bluetooth LE.

• Updating through USB.

• Updating through external debug probe.

Connecting to Edge Impulse

Through nRF Edge Impulse mobile app

See the section below on Connecting to the nRF Edge Impulse mobile application.

Through serial connection

With all the software in place it's time to connect the development board to Edge Impulse. From a command prompt or terminal, run:

edge-impulse-daemon

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

If prompted to select a device, choose ZEPHYR:

? Which device do you want to connect to?
❯ /dev/tty.usbmodem141301 (ZEPHYR)

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 connection of device

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.

Next steps: building a machine learning model

With everything set up you can now build your first machine learning model with this tutorial:

• Building a continuous motion recognition system.

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

Connecting to the nRF Edge Impulse mobile application

Now that you have created an Edge Impulse account and trained your first Edge Impulse machine learning model, using the Nordic nRF Edge Impulse app you can deploy your impulse to your Nordic Thingy:53 and acquire/upload new sensor data into your Edge Impulse projects.

Installation & Login

1. Download and install the Nordic nRF Edge Impulse app for your iPhone or Android phone.

Connect or remove a device

Select the Devices tab to connect to your Thingy:53 device to your mobile phone:

To remove your connected Thingy:53 from your project, select the connected device name and scroll to the bottom of the device page to remove it.

Data Acquisition

To view existing data samples in your Edge Impulse project, select the Data Acquisition tab. To record and upload a new data sample into your project, click on the "+" button at the top right of the app. Select your sensor, type in the sample label, and choose a sample length and frequency, then select Start Sampling.

Deployment

Build and deploy your Edge Impulse model to your Thingy:53 via the Deployment tab. Select your project from the top drop-down, select your connected Thingy:53 device, and click Build:

The app will start building your project and uploading the firmware to the connected Thingy:53:

If you encounter connection errors during deployment, please see Troubleshooting.

Inferencing

Every Thingy:53 is shipped with a default Edge Impulse model. This model is created from the Tutorial: Continuous motion recognition and it's corresponding Edge Impulse project.

Select the Inferencing tab to view the inference results of the model flashed to the connected Thingy:53:

Using Thingy53 with WiFi

The Nordic Thingy53 can also be using with the nRF7002eb expansion board as shown below.

The nRF7002eb is a companion IC, providing seamless WiFi connectivity and WiFi-based locationing (SSID sniffing of local WiFi hubs). With WiFi 6 the nRF7002eb brings added benefits to IoT applications including further efficiency gains that support long-life, battery-powered WiFi operation.

With this expansion board, you will be able to collect and upload data from your Thingy53 to your application over a WiFi connection.

Update the firmware

The WiFi capabilities of the Thingy53 are sandboxed in a different firmware. This helps users to choose whether they want to use the WiFi module or not and prevents consumption of extra memory if they choose not to. Therefore, to enable the WiFi capabilities of Thingy53, download the following Edge Impulse firmware:

• Edge Impulse firmware: nordic-thingy53-WiFi-full.zip

  • *-full.zip contains HEX files to upgrade the device through the external probe.

• Edge Impulse firmware: nordic-thingy53-WiFi-dfu.zip

  • *-dfu.zip contains dfu_application.zip package to upgrade the already flashed device through the Serial/USB.

Connect the Thingy53 to your computer with a USB-C cable and update the firmware following instructions described in section 3 of updating the firmware.

Connect the Thingy53 to your WiFi

Once the firmware has been updated, you will need to set up the WiFi connection between the Thingy53 and your WiFi. Make sure that the nRF7002eb WiFi module is plugged into the Thingy53 as shown in the image above. To setup the WiFi connection, simply run:

edge-impulse-daemon

This starts a wizard that helps you login to your Edge Impulse account and choose a project you want to connect your device to.

Note: If you want to switch accounts, projects or WiFi network, run the command with --clean

When prompted to select a device, choose the option with the higher USB modem number:

? Which device do you want to connect to? (Use arrow keys)
❯ /dev/tty.usbmodem103 (ZEPHYR) 
  /dev/tty.usbmodem101 (ZEPHYR) 

The wizard will now proceed to read the configuration of the device. If no WiFi connection is found, you will be prompted to connect to one. After you select Yes, it will proceed to scan for available WiFi networks:

? WiFi is not connected, do you want to set up a WiFi net
work now? Yes
Scanning WiFi networks...

Once scanning is complete, it will show you a list of available networks. You can use the arrow keys to select your network and proceed to enter the password. Once the Thingy53 is connected to the WiFi, the daemon will automatically disconnect as there's no need to keep a serial connection open.

? Select WiFi network (Use arrow keys)
❯ SSID: Vodafone-174C, Security: WPA2-PSK (1),RSSI: -54 dBm 
  SSID: Coyote, Security: WPA2-PSK (1),RSSI: -57 dBm 
  SSID: FRITZ!Box 7590 SH, Security: WPA2-PSK (1),RSSI: -64 dBm 
  SSID: Vodafone-7047, Security: WPA2-PSK (1),RSSI: -65 dBm 
  SSID: Vodafone-174C, Security: WPA2-PSK (1),RSSI: -66 dBm 
  SSID: FRITZ!Repeater 1200, Security: WPA2-PSK (1),RSSI: -73 dBm 

? Enter password for network "Vodafone-174C" ...
Connecting to "Vodafone-174C"...

[SER] Serial is connected, trying to read config...
[SER] Retrieved configuration
[SER] Device is running AT command version 1.8.0

[SER] Device is connected over WiFi to remote management API, no need to run the daemon. Exiting...

You can now disconnect the USB-C cable and remove the physical connection of the Thingy53 to your computer.

Verifying connection of device

Now your device should be connected to the project you chose during the initial setup. To verify that the device is connected, navigate to the Devices tab of your project. The connected device should be listed here:

You can now move to the Data acquisition tab of your project and start collecting data without being restricted to where your computer is.

Flashing your model

When using the nRF7002eb expansion board, you will not be able to connect to the Nordic nRF Edge Impulse app on your phone. The best way to flash your model is by navigating to the Deployment tab of your project and downloading the built firmware from there. You can follow the instructions in section 3 of updating the firmware to flash your model onto your device.

Inferencing

The firmware for the Thingy53 provided above, ships with a default motion detection model. This model is created from the Tutorial: Continuous motion recognition and it's corresponding Edge Impulse project. To see the inferencing results of this model, reconnect the the device to your computer with a USB-C cable and run:

edge-impulse-run-inference

This will then display the inference results, in this case classify the motion of the Thingy53, in the terminal:

Inferencing settings:
	Interval: 16.0000ms.
	Frame size: 375
	Sample length: 2000.00 ms.
	No. of classes: 4
Starting inferencing in 2 seconds...
Predictions (DSP: 25 ms., Classification: 0 ms., Anomaly: 0 ms.): 
    idle: 	0.996094
    snake: 	0.000000
    updown: 	0.000000
    wave: 	0.000000
    anomaly score: -0.375301

The integration of the nRF7002eb with Edge Impulse allows users to integrate advanced machine learning models, enabling smarter and more responsive IoT applications with even more ease. The synergy between the nRF7002eb EK and Edge Impulse paves the way for innovative applications in areas such as predictive maintenance, anomaly detection, and real-time data analysis.

Settings

Select the Settings tab to view your logged-in account information, BLE scanner settings, and application version. Click on your account name to view your Edge Impulse projects and logout of your account.

Troubleshooting

Lost BLE connection to device

• Reconnect your device by selecting your device name on the Devices tab and click "Reconnect".

• Make sure power cables are plugged in properly.

• Do not use iPhone/Android app multitasking during data acquisition, firmware deployment, or inferencing tasks, as the BLE streaming connection will be closed.

Switch WiFi network or project

• Reconnect your device to your computer using a USB-C cable.

• Run edge-impulse-daemon --clean. End the process by pressing CTRL+c on your keyboard, do not login at this step.

• Disconnect the Thingy53 and restart using the switch on the side.

• Reconnect to your computer and run edge-impulse-daemon. Follow instructions above to choose a different project of WiFi network.

The RAKwireless WisBlock is a modular development system that lets you combine different cores and sensors to easily construct your next Internet of Things (IoT) device. The following WisBlock cores work with Edge Impulse:

• RAK11200 (ESP32)

• RAK4631 (nRF52840)

• RAK11310 (RP2040)

RAKwireless has created an in-depth tutorial on how to get started using the WisBlock with Edge Impulse, including collecting raw data from a 3-axis accelerometer or a microphone, training a machine learning, and deploying the model to the WisBlock core.

A WisBlock starter kit can be found in the RAKwireless store.

Install dependencies

Install the following software:

• Edge Impulse CLI

• Arduino IDE

• Visual Studio Code

Using your WisBlock with Edge Impulse

Follow the guide for your particular core to collect data, train a machine learning model, and deploy it to your WisBlock:

• RAK11200 (ESP32) Edge Impulse Guide

• RAK4631 (nRF52840) Edge Impulse Guide

• RAK11310 (RP2040) Edge Impulse Guide

By the end of the guide, you should have machine learning inference running locally on your WisBlock!

The Boron is a powerful cellular enabled development kit.

Equipped with the Nordic nRF52840 and u-blox SARA U201 (2G/3G) or R410M/R510S LTE Cat M1 module, the Boron has built-in battery charging circuitry which makes it easier to connect a Li-Po battery and 20 mixed signal GPIOs to interface with sensors, actuators, and other electronics.

The Boron is great for connecting existing projects to the Particle Device Cloud or as a gateway to connect an entire group of local endpoints where Wi-Fi is missing or unreliable.

Installing dependencies

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

1. Edge Impulse CLI

2. Particle CLI

3. Particle Workbench (Optional, only required if deploying to Particle Library)

Setup the Particle Boron with the accelerometer and PDM microphone

1. Connect the ADXL345 to the Boron as follows:

Studio

Create an Edge Impulse account if you haven't already. Also, be sure to setup the device per the instructions above.

Build your first machine learning model with this tutorial:

• Particle Motion Detection

Deployment

Flash a Particle Boron Project via the Particle Library Deployment option

If you choose to deploy your project to a Particle Library and not a binary follow these steps to flash the your firmware from Particle Workbench:

1. Open a new VS Code window, ensure that Particle Workbench has been installed (see above)

2. Use VS Code Command Palette and type in Particle: Import Project

   1. Select the project.properties file in the directory that you just downloaded and extracted from the section above.

3. Use VS Code Command Palette and type in Particle: Configure Project for Device

   1. Select deviceOS@5.5.0

   2. Choose a target. (e.g. P2 , this option is also used for the Boron).

4. It is sometimes needed to manually put your Device into DFU Mode. You may proceed to the next step, but if you get an error indicating that "No DFU capable USB device available" then please follow these step.

   1. Hold down both the RESET and MODE buttons.

   2. Release only the RESET button, while holding the MODE button.

   3. Wait for the LED to start flashing yellow.

   4. Release the MODE button.

5. Compile and Flash in one command with: Particle: Flash application & DeviceOS (local)

The following video demonstrates how to collect raw data from an accelerometer and develop an application around the Edge Impulse inferencing library with the Boron.

Flash a Particle Boron Binary

Flashing your Particle device requires the Particle command line tool. Follow these instructions to install the tools.

Navigate to the directory where your Boron firmware downloaded and decompress the zip file. Open a terminal and use the following command to flash your device:

particle flash --local firmware-particle.bin

The OpenMV Cam is a small and low-power development board with a Cortex-M7 microcontroller supporting MicroPython, a μSD card socket and a camera module capable of taking 5MP images - and it's fully supported by Edge Impulse. You'll be able to sample raw data, build models, and deploy trained machine learning models through the studio and the OpenMV IDE.

Installing dependencies

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

1. Edge Impulse CLI.

2. OpenMV IDE.

Connecting to Edge Impulse

With all the software in place it's time to connect the development board to Edge Impulse. To make this easy we've put some tutorials together which takes you through all the steps to acquire data, train a model, and deploy this model back to your device.

• Adding sight to your sensors - end-to-end tutorial.

• Detecting objects using FOMO.

• Collecting image data with the OpenMV Cam H7 Plus - collecting datasets using the OpenMV IDE.

• Running your impulse on your OpenMV camera - run your trained impulse on the OpenMV Cam H7 Plus.

The Photon 2 with Edge ML Kit is a development system with a microcontroller and Wi-Fi networking containing a Realtek RTL8721DM MCU ARM Cortex M33. The form-factor is similar to the Argon (Adafruit Feather), but the Photon 2 supports 2.4 GHz and 5 GHz Wi-Fi, BLE, and has much larger RAM and flash that can support larger applications. Included in the kit are sensors used for embedded machine learning inferencing.

It is intended to replace both the Photon and Argon modules. It contains the same module as the P2, making it easier to migrate from a pin-based development module to a SMD mass-production module if desired.

Installing dependencies

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

1. Edge Impulse CLI

2. Particle CLI

3. Particle Workbench (Optional, only required if deploying to Particle Library)

Setup the Particle Photon 2 with the accelerometer and PDM microphone

1. Connect the ADXL362 to the Photon 2 as follows:

1. Connect the microphone to the Photon 2 as follows:

1. Plug in the USB Cable to the device

Connecting to Edge Impulse

Working directly with the device through the Particle Library deployment option involves the use of the Particle Workbench in VS Code, but if you simply want to start gathering data for a project you only need to install the Edge Impulse CLI and flash the following firmware to your device with your sensor(s) connected as described in the section below.

• Particle Photon2 Firmware.

Alternatively you can clone the Particle Firmware repo and build the firmware locally.

Flash a Particle Photon 2 Binary

Flashing your Particle device requires the Particle command line tool. Follow these instructions to install the tools.

Navigate to the directory where your Photon2 firmware downloaded and decompress the zip file. Open a terminal and use the following command to flash your device:

particle flash --local firmware-particle.bin

Collecting Data from the Particle Photon 2

Before starting ingestion create an Edge Impulse account if you haven't already. Also, be sure to setup the device per the instructions above.

To collect data from the Photon 2 please follow these steps:

1. Create a new Edge Impulse Studio project, remember the name you create for it.

2. Connect your device to the Edge Impulse studio by running following command in a terminal:

edge-impulse-daemon --clean

1. After connecting, the Edge Impulse Daemon will ask to login to your account and select the project. Alternatively, you can copy the API Key from the Keys section of your project and use the --api-key flag instead of --clean.

3. Start gathering data by clicking on Data acquisition

Next steps: Building a machine learning model

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

• Audio Event Detection with Particle Boards - Particle Project: Doorbell SMS

• Responding to your voice - Particle Project: You’re Muted

• Recognize sounds from audio

• Recognize gestures from motion

• Particle Energy Monitoring Demo

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

Advanced Deployment

Flash a Particle Photon 2 Project via the Particle Library Deployment option

If you choose to deploy your project to a Particle Library and not a binary follow these steps to flash the your firmware from Particle Workbench:

1. Open a new VS Code window, ensure that Particle Workbench has been installed (see above)

2. Use VS Code Command Palette and type in Particle: Import Project

   1. Select the project.properties file in the directory that you just downloaded and extracted from the section above.

3. Use VS Code Command Palette and type in Particle: Configure Project for Device

   1. Select deviceOS@5.5.0

   2. Choose a target. (e.g. P2 , this option is also used for the Photon 2).

4. It is sometimes needed to manually put your Device into DFU Mode. You may proceed to the next step, but if you get an error indicating that "No DFU capable USB device available" then please follow these step.

   1. Hold down both the RESET and MODE buttons.

   2. Release only the RESET button, while holding the MODE button.

   3. Wait for the LED to start flashing yellow.

   4. Release the MODE button.

5. Compile and Flash in one command with: Particle: Flash application & DeviceOS (local)

The following video demonstrates how to collect raw data from an accelerometer and develop an application around the Edge Impulse inferencing library with the Photon 2.

Training data Ingestion via Particle Webhook:

If you would like to use the Particle webhook to send training data from your particle board directly to Edge Impulse, or indeed any other of our apis follow these steps:

1. Access Particle Console:

   • Visit Particle Console.

   • Log in with your Particle account credentials.

2. Navigate to Integrations:

   • Click on the "Integrations" tab in the left-hand menu.

   • Select "Webhooks" from the available options.

3. Create a New Webhook:

   • Click "New Integration".

   • Choose "Webhook".

4. Webhook Configuration:

   • Name: Assign a descriptive name to your webhook.

   • Event Name: Specify the event name that triggers the webhook (e.g., "edge/ingest").

   • URL: Set this to the Edge Impulse ingestion API URL, typically something like https://ingestion.edgeimpulse.com/api/training/data.

   • Request Type: Choose "POST".

   • Request Format: Select "Custom".

5. Custom Request Body:

   • Input the JSON structure required by Edge Impulse. This will vary based on your project's data schema.

6. HTTP Headers:

   • Add necessary headers:

     • x-api-key: Your Edge Impulse API key.

     • Content-Type: "application/json".

     • x-file-name: Use a dynamic data field like {{PARTICLE_EVENT_NAME}}.

7. Advanced Settings:

   • Response Topic: Create a custom topic for webhook responses, e.g., {{PARTICLE_DEVICE_ID}}/hook-response/{{PARTICLE_EVENT_NAME}}.

   • Enforce SSL: Choose "Yes" for secure transmission.

8. Save the Webhook:

   • After entering all details, click "Save".

9. Test the Webhook:

   • Use example device firmware to trigger the webhook.

   • Observe the responses in the Particle Console.

10. Debugging:

• If errors occur, review the logs for detailed information.

• Ensure payload format aligns with Edge Impulse requirements.

• Verify the accuracy of your API key and other details.

Custom Template Example:

If you have any trouble with the config you can copy and paste the following into the Custom Template section of the webhook:

{
    "name": "edgeimpulse.com",
    "event": "edge/ingest",
    "responseTopic": "",
    "disabled": true,
    "url": "http://ingestion.edgeimpulse.com/api/training/data",
    "requestType": "POST",
    "noDefaults": true,
    "rejectUnauthorized": false,
    "headers": {
        "x-api-key": "ei_1855db...",
        "x-file-name": "{{PARTICLE_EVENT_NAME}}",
        "x-label": "coffee"
    },
    "json": "{\n  \"payload\": {\n    \"device_name\": \"0a10a...\",\n    \"device_type\": \"photon2\",\n    \"interval_ms\": 20,\n    \"sensors\": [\n      {\n        \"name\": \"volt\",\n        \"units\": \"V\"\n      },\n      {\n        \"name\": \"curr\",\n        \"units\": \"A\"\n      }\n    ],\n    \"values\": [\n{{{PARTICLE_EVENT_VALUE}}}\n    ]\n  },\n  \"protected\": {\n    \"alg\": \"none\",\n    \"ver\": \"v1\"\n  },\n  \"signature\": \"00\"\n}"
}

Lifecycle Management and OTA (over-the-air) Updates

The Photon 2 is capable of OTA and updating to the latest model in your Edge Impulse project. Follow this example that shows how to deploy updated impulses over-the-air (OTA) using the Particle Workbench.

Troubleshooting

Should you have any issues with your Particle device please review Particle's Support & Troubleshooting page.

If you have issues with Edge Impulse please reach out!

The Seeed Wio Terminal is a development board from Seeed Studios with a Cortex-M4 microcontroller, motion sensors, an LCD-display, and Grove connectors to easily connect external sensors. Seeed Studio has added support for this development board to Edge Impulse, so you can sample raw data and build machine learning models from the studio.

Setting up your development board

Next steps: building a machine learning model

Deploying back to device

With the impulse designed, trained and verified you can deploy this model back to your Wio Terminal. This makes the model run without an internet connection, minimizes latency, and runs with minimum power consumption. Edge Impulse can package up the complete impulse - including the signal processing code, neural network weights, and classification code - up in a single library that you can run on your development board.

Troubleshooting

ESP-NN conflict

If you see an error like the following Arduino, it means the Wio Terminal build process is attempting to link to the ESP-NN library (which is not supported):

While we work on a permanent solution, the workaround is to remove the ESP-NN/ folder found in Arduino/libraries/<ei-project-name>/src/edge-impulse-sdk/porting/espressif/

The Seeed Studio XIAO nRF52840 Sense incorporates the Nordic nRF52840 chip with FPU, operating up to 64 MHz, mounted multiple development ports, carrying Bluetooth 5.0 wireless capability and can operate with low power consumption. Featuring onboard IMU and PDM, it can be your best tool for embedded Machine Learning projects. Seeed Studio has added support for this development board to Edge Impulse, so you can sample raw data and build machine learning models from the studio.

Setting up your development board

Next steps: building a machine learning model

Deploying back to device

With the impulse designed, trained and verified you can deploy this model back to your XIAO nRF52840 Sense. This makes the model run without an internet connection, minimizes latency, and runs with minimum power consumption. Edge Impulse can package up the complete impulse - including the signal processing code, neural network weights, and classification code - up in a single library that you can run on your development board.

The Seeed Studio XIAO ESP32S3 Sense is a powerful development board that utilizes the dual-core ESP32S3 chip, featuring an Xtensa processor running at speeds of up to 240 MHz. This board offers support for both 2.4GHz Wi-Fi and Bluetooth Low Energy (BLE) connectivity. Additionally, it is equipped with a detachable OV2640 camera sensor, boasting an impressive resolution of 1600*1200, and a digital microphone.

With 8MB of PSRAM and 8MB of FLASH, as well as an external SD card slot, the XIAO ESP32S3 Sense provides ample memory and storage capacity, making it well-suited for embedded machine learning (ML) applications.

Seeed Studio has integrated support for this development board into Edge Impulse, allowing users to sample raw data and build machine learning models directly from the studio. This integration simplifies the process of leveraging the XIAO ESP32S3 Sense for ML projects.

With its impressive specifications and Edge Impulse compatibility, the XIAO ESP32S3 Sense is an excellent choice for developers seeking to explore embedded machine learning applications.

Setting up your development board

Next steps: building a machine learning model

Deploying back to device

With the impulse designed, trained and verified you can deploy this model back to your XIAO ESP32S3 Sense. This makes the model run without an internet connection, minimizes latency, and runs with minimum power consumption. Edge Impulse can package up the complete impulse - including the signal processing code, neural network weights, and classification code - up in a single library that you can run on your development board.

The Renesas CK-RA6M5, Cloud Kit for RA6M5 MCU Group, enables users to experience the cloud connectivity options available from Renesas and Renesas Partners. A broad array of sensors on the CK-RA6M5 provide multiple options for observing user interaction with the Cloud Kit. By selecting from a choice of add-on devices, multiple cloud connectivity options are available.

The Edge Impulse firmware for this development board is open source and hosted on GitHub: .

Installing dependencies

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

2. On Linux:

   • GNU Screen: install for example via sudo apt install screen.

Updating the firmware

Edge Impulse Studio can collect data directly from your CK-RA6M5 Cloud Kit and also help you trigger in-system inferences to debug your model, but in order to allow Edge Impulse Studio to interact with your CK-RA6M5 Cloud Kit you first need to flash it with our base firmware image.

1. Download the base firmware image

2. Connect the CK-RA6M5 Cloud Kit to your computer

1. Check that:

   • J22 is set to link pins 2-3

   • J21 link is closed

   • J16 Link is open

2. Connect J14 and J20 on the CK-RA6M5 board to USB ports on the host PC using the 2 micro USB cables supplied.

3. Power LED (LED6) on the CK-RA6M5 board lights up white, indicating that the CK-RA6M5 board is powered on.

3. Load the base firmware image

Open the flash script for your operating system (flash_windows.bat, flash_mac.command or flash_linux.sh) to flash the firmware.

Connecting to Edge Impulse

1. 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.

2. Verifying that the device is connected

Next steps: Build a machine learning model

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

The RA8 is the first Cortex-M85 microcontroller in the market. The EK-RA8D1, an Evaluation Kit for the RA8D1 MCU Group, enables users to seamlessly evaluate the features of the RA8D1 MCU group and develop embedded systems applications using the Renesas Flexible Software Package (FSP) and e2 studio IDE. Users can use rich on-board features along with their choice of popular ecosystems add-ons to bring their big ideas to life.

The evaluation kit comes with a MIPI graphics expansion board mounted with an LCD display and a camera expansion board mounted with the OV3640 CSI camera. The kit can be assembled as follows:

This kit is put together primarily for image based applications. This document will get you started so you can create your own image based applications using Edge Impulse.

Getting started

Installing dependencies

The RA8D1 supports all of Edge Impulse’s device features, including ingestion, remote management and inferencing. To set the device up in Edge Impulse, you will need to install the following software:

Updating the firmware

Edge Impulse Studio can collect image data directly from your EK-RA8D1 and also help you trigger in-system inferences to debug your model. In order to allow Edge Impulse Studio to interact with your device, you first need to flash it with our base firmware image.

1. Download the base firmware image

2. Connect the EK-RA8D1 to your computer

To flash the board, you need to connect to the debug port J10:

The LCD screen will turn on and display the home screen as shown.

3. Load the base firmware image

Open the flash script for your operating system (flash_win.bat, flash_mac.command or flash_linux.sh) to flash the firmware. Once you flash the firmware, the display will switch to show the default Edge Impulse Face Detection using FOMO project.

Now you are ready to connect the RA8D1 to the studio and create your own project.

Connecting to Edge Impulse

To connect to the Edge Impulse Studio, you need to connect to the USB Full Speed port J11. Please make sure that the jumpers J12 and J15 are in the correct position (J12 in position 2-3 and J15 connected). The correct configuration is shown in the image below:

It is important to remember that to run inference, to collect data from the RA8D1, and use the Edge Impulse CLI tools, you have to connect via port J11. Port J10 is only used for flashing the firmware.

Note that it is safe to connect two cables to your board at ports J10 and J11 simultaneously. Then you can flash it and run inference without having to change ports.

1. Setting up your account

After connecting to port J11, 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.

2. Verifying that the device is connected

3. Collecting data

Once the device is connected, you can proceed to the data acquisition tab and start collecting your image data directly from the device.

Running NVIDIA TAO models on the RA8D1

Next steps: Build a machine learning model

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

The is the debut microcontroller from Raspberry Pi - and it's fully supported by Edge Impulse. You'll be able to sample raw data, build models, and deploy trained machine learning models directly from the studio. It's available for around $4 from Raspberry Pi foundation and a wide range of distributors.

To get started with the Raspberry Pi RP2040 and Edge Impulse you'll need:

• A . The pre-built firmware and Edge Impulse Studio exported binary are tailored for , but with a few simple steps you can collect the data and run your models with other RP2040-based boards, such as . For more details, check out .

• (Optional) If you are using the , the makes it easier to connect external sensors for data collection/inference.

The Edge Impulse firmware for this development board is open source and hosted on GitHub: .

Installing dependencies