1.1.14 Running a Model On Your Embedded Device
This documentation provides step-by-step instructions on executing the model for your embedded device. The process involves generating a Knowledge Pack to facilitate the operation.
Knowledge Packs
A Knowledge Pack takes the event detection model you generated in your pipeline and transforms it into a file that can be run on your hardware device at the edge. When the Knowledge Pack is on your device, it outputs classification IDs corresponding to the events of interest. The user can download a Knowledge Pack for the chosen platform in the Download Model page.More information about integrating Knowledge Pack APIs into firmware can be found in the Building a Knowledge Pack Library Documentation section.
Open the Download Model page.
For this tutorial, the SAMD21 platform was chosen as the development platform.
You can see information about the model, such as, Estimated Memory Usage or Latency, before download.
Select “Format” as Library and “Data Source” as Custom, then click Download.
Integrate the Knowledge Pack APIs into your embedded device firmware by following the Knowledge Pack Integration.
Connecting To Your Device
When a Knowledge Pack is flashed onto your device, you can connect the virtual COM port in a terminal application to view the results. Follow the steps below for viewing the recognition results:
Open a terminal emulator (such as Tera Term)
Set your serial speed to the baud rate of your device
Create a new connection to the serial port
You will now see the classification results printed in the terminal.