Shawn Hymel demonstrates how to deploy a machine learning model from Edge Impulse to work with custom sensors on Arduino. This process involves reading data directly from the sensors (accelerometer and gyroscope in this case) over the sampling period, performing standardization using the mean and standard deviation calculated from a previous episode, and using the standardized data to perform inference. The output of inference is a set of confidence scores from the classes that the model believes belong to the input data.
The project used in this video can be found here: studio.edgeimp...
Get started: docs.edgeimpul...
Watch more ML Microsessions: • ML Microsessions
Негізгі бет Inference with Custom Sensor
Пікірлер: 4