esp-who

I guess, but it’s also pretty open code these days now that the S3’s LX7 has some nice vector extensions and other additions for ML applications :) https://github.com/espressif/esp-who It’s not out of reach for hobbyists, I think, though getting it to run very well might be. And I would certainly tell anyone interested to start with something more powerful first! I’m currently experimenting with porting Arraymancer to the S3, just to see how it can run, outside of work time mind you. https://github.com/mratsim/Arraymancer Slightly orthogonal to what we are discussing above, but more to show that these weird micros have some surprising grunt if you know how to make them sing. Though I still wish ESP-IDFs malloc was better behaved.

Face recognition is possible on a tiny and cheap ESP32-CAM[0] using Espressif's own ESP-WHO[1] framwork. Apparently it can process images at around 3 fps. I have an ESP32-CAM on order to try this out as part of a side project of mine[2], so I can make the eyes look at faces :) I would also love to get hold of a Person Sensor[3] which runs custom firmware specificially designed for face detection and would be absolutely perfect for this, but they're not in stock currently. There's other libraries[4][5][6] that look like they could work too and I plan to try. As far as microcontrollers goes, the Teensy 4.0[7] should be powerful enough for reasonably fast processing (and it has a floating point unit!), though I'm yet to find a good library for doing so. [0] https://robotzero.one/face-tracking-esp32-cam/ [1] https://github.com/espressif/esp-w