Want to run model on wio terminal

hi ya’ll

I want to run a model which I trained from edge impulse in wio terminal. I want it to be continuous i.e it should collect data and predict simultaneously. the one provided as static_buffer does not do that. I saw the wio terminal tutorial on youtube this, but it didn’t explain how to properly write the code.

can someone help? thanks

Hi @f20190094,

We provide instructions on continuous inferencing in the Arduino library deployment option from the Studio, these examples are then included in the Arduino IDE: File > Examples > Your custom library > i.e. nano_ble33_sense_accelerometer_continuous

These continuous inferencing code examples are very similar to the code used in that Youtube video tutorial.

@AIWintermuteAI Also describes the code he used in his video’s blog post and how to compile for the Wio Terminal: https://www.seeedstudio.com/blog/2021/02/03/learn-tinyml-using-wio-terminal-and-arduino-ide-2-audio-scene-recognition-and-mobile-notifications/

Thanks!

1 Like

Hi there! So, for wio terminal, I have actually made two tutorials on continuous inference:

  1. Using FreeRTOS for low sampling rate data
    https://www.hackster.io/dmitrywat/tinyml-course-3-people-counting-and-azure-iot-integration-00f6b3
  2. Using DMA ADC for microphone (16k sampling rate)
    https://wiki.seeedstudio.com/Wio-Terminal-TinyML-EI-3/

I really should update hackster.io article too xD

2 Likes