I run Frigate with 5 IP cameras (3 Hikvisions, 2 Amcrests) and 1 USB camera. I'm using a USB Coral TPU, which does a good enough job that Frigate can keep up with an average of only 30% CPU usage on an old Dell with 4 core i7-6700.
Frigate's better than anything else I tried, but not perfect. As mentioned in another thread, it has some issues with codecs from some cameras (playing clips from Amcrests is fine, Hikvisions not so much) and therefore you may need to transcode. Also it has no built in option for sending your recorded clips offsite; theoretically you could mirror its storage directory, but as far as I've found it's not organized in a way that you can separate just important events.
> Turn on face recognition & upload your first face via Face Library → Add Face.
> Train and improve accuracy: New detections appear in Face Library → Train with a confidence score-assign each to a new or existing person to refine future recognition.
I also ran Doublestake and Compreface with Frigate. Found out that it didn't really provide any benefits for me. The default native person detection in Frigate using the TPU is more than adequate. I've seen some interesting stuff people have done using a mix of locally hosted LLM vision model with Home Assistant and Frigate to do image interpretation. Including facial recognition and License plate reader. It's something I want to eventually explore.
Frigate's better than anything else I tried, but not perfect. As mentioned in another thread, it has some issues with codecs from some cameras (playing clips from Amcrests is fine, Hikvisions not so much) and therefore you may need to transcode. Also it has no built in option for sending your recorded clips offsite; theoretically you could mirror its storage directory, but as far as I've found it's not organized in a way that you can separate just important events.