If you go with the GPU go with one with as much memory as you can afford. And then don't let stuff update. We see posts here all the time where someone's CodeProject stopped working at is was because the GPU updated CUUDA or something and it wasn't compatible with their GPU and CodeProject.
My GT1030 just didn't cut it. I am getting faster response times with the CPU version.
While I run the plates, I was hoping I could then eliminate the paid OpenALPR, but the CodeProject version just isn't as accurate. It is improving, but don't expect it to be the savior.
Same with facial recognition. We see lots of posts where it either doesn't work or isn't very accurate. So unless you are just looking to increase your time with this hobby LOL, don't count on it being very successful.
Most of us have found that facial identification is more gimmicky and novelty than anything else. If you have to put in 5 or 10 or 15 or 35 pictures or more of yourself in the system for it to recognize it is you...then you shouldn't expect much.... My success rate was under 5% so I moved on to other hobbies LOL. YMMV.
It can work in certain situations like a business that requires everyone to stop in front of the camera and the camera is at head height. Outside of that, the percentage of being accurate is probably not going to be super high. You will get a lot of false "confirmations" doing a search.
Someone here posted once how horrible it was inside his house identifying his neighbors and others as him. Another guy his kids and wife were being tagged as him inside the house.
Unless you spend the big bucks that casinos and airports have LOL.
As always YMMV and some here use it and say it is acceptable for their use case.
Heck even in ideal situations like a business with the camera at ideal height and optimal lighting it fails...
A similar discussion except on this side of the pond...
US government tests find even top-performing facial recognition systems misidentify black people at rates 5 to 10 times higher than they do white people.
www.wired.com
If police are authorized to deploy invasive face surveillance technologies against our communities, these technologies will unquestionably be used to target Black and Brown people merely for existing.
www.aclu.org
The application of face recognition technology in the criminal justice system threatens to perpetuate racial inequality.
sitn.hms.harvard.edu
What can Google’s algorithmic workaround tell us about biased AI?
www.theverge.com
People of color are more likely to be misidentified by facial recognition software.
www.axios.com
...