Automatic syncing object models across multiple VOXL2s

Denver Bennett

Hello,

I'm trying to get an object-detection-model-guided drone. I am also trying to get it so that I can have an object detection model (like the MobileNet) on one VOXL2 and then be able to sync that same model onto other VOXL2s. I would like to have it so that the modifications I make to the model (weights, parameters, training data, etc), can automatically be pushed or synchronized across all the other VOXL2s I am using.

How can I do this?

I typed voxl-{TAB}{TAB} in terminal, and it seems to me like voxl-configure-docker-support, voxl-configure-mavlink-server, voxl-configure-tflife, voxl-inspect-mavlink, voxl--mavcam-manager, voxl-mavlink-server, and voxl-tflife-server are the places to start, but I am not sure as I am new to this.

Where should I start?

Thank you!

Moderator

@Denver-Bennett look at https://docs.modalai.com/voxl-tflite-server

Denver Bennett

@Moderator So is voxl-tflite-server what is used to communicate and transfer the model across different voxls?

Moderator

@Denver-Bennett Hi Denver, no voxl-tflite-server is a TensorFlow Lite runtime environment for VOXL.

You will need to write your own code if you want to somehow mesh models together over a network. We aren't familiar with any software that handles that today