Edge Impulse Inferencing Demo Error Message

[make-a-mark]

Question/Issue:
When running the generated nano_ble33_sense_accelerometer data, I run into ERR: EI_CLASSIFIER_RAW_SAMPLES_PER_FRAME should be equal to 3 (the 3 sensor axes). It doesn’t fail, just prints out the error, but I was wondering if it’s something on my end that the sensors used are 9 (shown in picture) rather than the 3 accelerometer axes.

Is there a way to specify to use only the accelerometer data when training the model? I’ve been following the coursera intro to embedded ML and ran into this issue.

Project ID:
182122

[louis]

Hello,

This issue is currently being investigating by our embedded engineering team.
You can modify the model_metadata.h in the meantime, it should fix your issue

Problems With Creating/Deploying a model For Arduino

Hello @Flomzey, Can you try to modify this line in the model_metadata.h: #define EI_CLASSIFIER_FUSION_AXES_STRING "accX + accY + accZ + gyrX + gyrY + gyrZ + magX + magY + magZ" to #define EI_CLASSIFIER_FUSION_AXES_STRING "accX + accY + accZ + gyrX + gyrY + gyrZ" I have the feeling that we automatically set the axis based on the axis on your dataset but not based on the ones used in your impulse. I’ll check with the embedded team if that’s the case to make a fix. Best, Lou…

Is there a way to specify to use only the accelerometer data when training the model?

Yes you can select which axis you need in the pre-processing block if you only want to use accX, acc,Y and accZ for example.

Best,

Louis

[louis]

Also note that you can try to run the sensor_fusion example.

Best,

Louis