neil

Hi neil ,
I am not that familiar with NNs and have never done it myself (so it's probably best to google this), but there are some tools (eg. onnx-processing-tools) that allow you to change/edit trained model.
Thanks, Erik

Hi neil ,
This isn't limitation of the model - see How demo works here. So the model (arcface, see here) just gets one face frame at a time, so if you would have 100 faces in the frame it would (in theory) send each of these 100 faces one at a time to the model.

So the limitation is likely in the pipeline implementation coupled with VPU performance. As with eg. 100 faces, you will need to do a lot of inferences (one after another) which takes some time. So you could configure the pipeline to be able to handle 5 faces as well (probably by configuring queue/pool sizes..), but it would limit the FPS. Another approach would be to edit the model itself so it would allow multiple faces at once, perhaps performance would be better. Another approach would be to run face recognition model on the host computer.

Thoughts?
Thanks, Erik

(WRT firmware on ESP32; I am not familiar with ESP IDF and can provide much info on it. Best to check their documentation page though)

neil I would suppose so, but I am really not an expert when it comes to ESP32 programming.
@erik would be able to better confirm the implementation when he gets a chance.

WRT other modules, we don't really have many only OAK-D-IoT-40 and OAK-D-IoT-75 does come with ESP32 and there is not much of difference between them. Depends on your use case and how you use SPI connection between OAK-SoM and ESP32 you may be able to connect to one of the AUX connectors which might be easier.

Please note that we do not normally offer a support on IoT modules anymore as we sort of deprecated those modules due to low interest, but we will continue with the production for the requested demand.

Regards,
David