I’ve created a simple impulse that uses_time-series audio data as an input block, processes that data with an Audio MFCC block, and learns using a Classification block for the learning.
I’ve trained this model and successfully deployed it on an Arduino Nano 33 BLE board.
Next, I’d like to deploy this model on a Raspberry Pi running Linux.
However, when following the tutorials on how to deploy the model in the web user interface, I don’t have the option to deploy to a C++ library.
Does anybody know what the issue behind this might be? Based on research and other observations it could be related to one of the following:
- I’m using Edge Impulse via https://mltools.arduino.cc/
- the Classification learning block is incompatible with the C++ library deployment type, similar to this issue
- when configuring the Classification learning block in detail before starting the training, I can select as Target device only three options:
- Arduino Nano 33 BLE Sense
- Arduino Nicla Vision
- Arduino Portenta H7