Live classifications with the Edge Impulse data forwarder tool

Model testing is the step we should always take before exporting the final application to the target platform. Deploying on microcontrollers is error-prone because the code may contain bugs, the integration could be incorrect, or the model could not work reliably in the field. Therefore, model testing is necessary to exclude at least ML from the source of failures.

In this recipe, we will learn how to perform live classifications via Edge Impulse using the Raspberry Pi Pico.

Getting ready

The most effective way to evaluate the behavior of an ML model is to test the model's performance on the target platform.

In our case, we have already got a head start because the dataset was built with the Raspberry Pi Pico. Therefore, the accuracy of the test dataset should already give us a clear indication of how the model behaves. However, there are cases where the dataset may not be built on top of sensor data coming...