ML/OD on dedicated hardware

[dmidthun]

I have searched for some time for (dummy-proof) documentation on how to correctly set up remote object detection and machine learning on a separate server with no real luck. Hoping someone might have some insight or at least a general guide for how to do this.

I did find this thread but haven't found much on HOW to configure the objectdetection or mlapi config files to accomplish that.

Anyone have a dummy-proof guide for this?

Setup:

ZM 1.37 on a Virtual Machine (oVirt)
- ZMES is installed and, and while it is working, I want to extend GPU / TPU support to a server connected via LAN.
Google TPU and NVIDIA GTX 1060 available to 2nd server dedicated for OD/ML


Thanks,
Dan

[Magic919]

ZMES is pretty well documented as Asker did a great job of that. You then set up the MLAPI service and point the ZMES to it. That’s all in the config file from what I recall.

[serenematernal]

I have searched for some time for (dummy-proof) documentation on how to correctly set up remote object detection and machine learning on a separate server with no real luck. Hoping someone might have some insight or at least a general guide for how to do this.

I did find this threadgeometry dash lite but haven't found much on HOW to configure the objectdetection or mlapi config files to accomplish that.

Anyone have a dummy-proof guide for this?

Setup:

ZM 1.37 on a Virtual Machine (oVirt)
- ZMES is installed and, and while it is working, I want to extend GPU / TPU support to a server connected via LAN.
Google TPU and NVIDIA GTX 1060 available to 2nd server dedicated for OD/ML

Thanks,
Dan

I have a fully operational version of Ubuntu 22.04 installed and ready to go. Set up the MLAPI service, and then direct the ZMES to it. Everything you need to know is, if memory serves, contained in the configuration file.