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

Random freezing of 'obama_face_encoding' on raspberry pi (Solved) #253

Closed
abhiTronix opened this issue Dec 6, 2017 · 1 comment
Closed

Comments

@abhiTronix
Copy link

abhiTronix commented Dec 6, 2017

  • face_recognition version:Latest
  • Python version:2.7.13
  • Operating System:Raspbian stretch
  • Dlib version: 19.7.99 (with neon support)
  • Scipy version: 0.17.0

Description

Hello everyone ,i'm testing 'obama_small image' on my raspberry pi 3 for facial recognition, my Raspberry pi CPU is randomly getting pegged at 100% when 'obama_face_encoding' is getting executed .....and moreover python get stuck with 80% CPU usage (Sometimes 100%) when i force stop the process 'obama_face_encoding' and therefore had to kill it manually!!!.

What I Did

Here is my test code:
import face_recognition
obama_image = face_recognition.load_image_file("home/pi/obama_small image")
print('1')
obama_face_encoding = face_recognition.face_encodings(obama_image)[0]
print('2')

Here is what i get : (Output)

1
not '2' and it happens randomly ..... sometimes i get '2' and sometimes don't ...... Moreover i have to kill process to end this by pressing 'Ctrl+Z' when this happens and therefore further results in CPU juggling at 80-100% and python freezes too, and have to reboot system in the end :(

Trace captured during this problem :

output.txt

any help is greatly appreciated :)

@abhiTronix abhiTronix changed the title Random freezing of 'obama_face_encoding' on raspberry pi Random freezing of 'obama_face_encoding' on raspberry pi (Solved) Dec 13, 2017
@xoul
Copy link

xoul commented Feb 10, 2018

I can't find the .deb package at the suggested address, @abhiTronix. :)
Moreover, I've managed to solve the same problem just adding some swap space or resizing the image (maybe using Image.thumbnail() from Pillow) before loading it within face_recognition.

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

1 participant