Ambiq Apollo510
Last updated
Was this helpful?
Last updated
Was this helpful?
Introducing Apollo510 System-on-Chip (SoC), a cutting-edge solution engineered to revolutionize the landscape of ultra-low-power performance in conventional edge and AI applications. Leveraging Ambiq's advanced Subthreshold Power Optimized Technology (SPOT®), Apollo510 delivers exceptional energy efficiency, operating on minimal power while providing unparalleled performance. Equipped with an Arm® Cortex®-M55 application processor running at up to 250MHz, this SoC enables efficient and high-performance computing, empowering developers to design innovative devices with ease.
Apollo510 incorporates advanced security features in secureSPOT® 3.0 with TrustZone® technology, such as secure boot and secure firmware updates, ensuring the integrity and confidentiality of data transmitted and processed by connected devices, making it an ideal choice for secure deployment in bodyworn and ambient AI applications. Designed to meet the evolving needs of conventional edge and AI devices, the Apollo510 represents a significant leap forward in energy efficiency, performance, and security. With its unparalleled combination of ultra-low power operation, high-performance computing capabilities, and robust security features, this wireless SoC is designed to drive innovation and enable the next generation of smart and connected devices.
Features
Up to 250 MHz Arm Cortex-M55 application processor with turboSPOT® and Helium™ technology
Enhanced memory performance with 64KB I-Cache and 64KB D-Cache, 3.75MB of system RAM, and 4MB of embedded non-volatile memory for code/data
Ultra-low power ADC and stereo digital microphone PDM interfaces for truly always-on voice
High-fidelity telco-quality audio
High-speed USB 2.0
Wide range of integrated sensor interfaces including ADC, SPI, I²C, and UART
To set this device up in Edge Impulse, you will need to install the following software:
Problems installing the CLI?
See the Installation and troubleshooting guide.
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.
Connect the microphone board to the Apollo510-EVB as shown below.
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 Apollo510-EVB pins as shown in the table below:
GND
Any EVB GND
5V/VDD
Any EVB 5V
SCK
Pin 47
MISO
Pin 49
MOSI
Pin 48
CS
Pin 60
The wiring harness provided with the camera can be sensitive, so pin jumpers or another wiring harness may help
Pre-built image with only audio support and "Hello World" detector example here
Get started by extracting the archive and choose the appropriate script for your system architecture to flash the firmware:
From a command prompt or terminal, run:
This will start a wizard which will ask you to log in and choose an Edge Impulse project. If you want to switch projects run the command with --clean.
Alternatively, 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:
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.
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:
With everything set up you can now build your first machine learning model with these tutorials:
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 Apollo5:
Then add the DSP block:
Then the keyword spotting learn block:
And finally save the impulse:
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:
Select the learning block:
Then click Save & train and you'll eventually see an output like this:
Go to the Model testing section and enable int8 testing:
And run the test:
Navigate to the Deployment section and choose the Apollo 5:
Now click Build and wait for the job to finish, when it does a zip archive will be downloaded to your computer.
See the previous section on flashing the board.
You can run your impulse by using edge-impulse-run-impulse:
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 Apollo510-EVB from Ambiq!
