Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Face recognition produce poor results on Raspbian Buster #1047

Open
Unicode-Hater opened this issue Feb 5, 2020 · 2 comments
Open

Face recognition produce poor results on Raspbian Buster #1047

Unicode-Hater opened this issue Feb 5, 2020 · 2 comments

Comments

@Unicode-Hater
Copy link

Unicode-Hater commented Feb 5, 2020

  • face_recognition version: 1.2.3
  • Python version: 3.7.3
  • Operating System: Raspbian Linux Buster

Description

So, I installed the library via pip, everything ok, I've tried to install opencv (latest version) via pip as well, it installs, but when I tested opencv, it asks about __atomic_add_fetch_8. I found out that some devs have the same probelm. So what I did? I installed opencv via apt, which it has version 3.2.0. And after that I've tried testing it using facerec_from_webcam_faster script and it produces poor results.

Additional notes:
1 month ago, I was testing on the same machine, the same script, but made a custom loader for it, with a older version of Raspbian on which I can get the latest version of opencv and it worked and I have another machine with the same steps taken as this one with poor results and somehow it works

What I Did

pip3 install face_recognition
sudo apt install lib-opencv-dev python3-lib-opencv
@rohansh-tty
Copy link

What are the exact figures(Accuracy Rate...)?
Like what does "poor" mean?
I have implemented the same thing on the Raspbian buster. It worked like charm for me.

@TrevorC85
Copy link

I may have a similar problem and worked around this by using a different camera. Are you using the picamera by chance?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants