Combine Impulses
You are not sure how to design your impulse? Here are some tips and tricks to help you design or combine your impulse to suit your needs:
Multi-impulse vs multi-model vs sensor fusion
Running multi-impulse refers to running two separate projects (different data, different DSP blocks and different models) on the same target. It will require modifying some files in the EI-generated SDKs. See the multi-impulse tutorial. We have a multi-impulse deployment block to generate the export package, available for Enterprise Plans.
Running multi-model refers to running two different models (same data, same DSP block but different tflite models) on the same target. See how to run a motion classifier model and an anomaly detection model on the same device in this tutorial. Currently, we only support stacking a Keras block with an anomaly detection block.
Sensor fusion refers to the process of combining data from different types of sensors to give more information to the neural network. To extract meaningful information from this data, you can use the same DSP block (like in the Sensor Fusion tutorial), multiples DSP blocks, or use neural networks embeddings like this Sensor Fusion using Embeddings tutorial.
Also see this video (starting min 13):
Last updated
