Improve latency of facial recognition
Currently there is a lot of latency in the camera for facial recognition. This will only get worse as we deploy the code onto a slower processor (namely, the raspberry pi). Need to make sure that the code is as efficient as possible.
Currently, the way I'm looking at doing this is by removing the library we use for facial identification and recognition and doing these tasks ourselves, which should allow more control.
To upload designs, you'll need to enable LFS and have an admin enable hashed storage. More information