Face_recognition: Use face_recognition on raspberry, “segmentation fault” occurred
- face_recognition version:0.2.0
- Python version:3.5
- Operating System:raspbian
python facerec_on_raspberry_pi.py
segmentation fault
sxyzzzzzzz
All 10 comments
sxyzzzzzzz
on 11 Jan 2018
cpu 100%，then segmentation fault. raspberry pi 3.
sxyzzzzzzz
on 11 Jan 2018
seems to freeze the function "face_encodings"
sxyzzzzzzz
on 11 Jan 2018
Do you found a solution for this?
jparedesj
on 7 Jun 2018
Any solution found for this? Been debugging for many hours now to no avail.
andrewda
on 2 Aug 2018
Have you found the solution? I met the same problem
xyG67
on 3 Sep 2018
Unfortunately I never found a solution to this, besides using some faster hardware. I'd love to hear if others have figured this out, though!
andrewda
on 3 Sep 2018
I was experiencing the same problem, segmentation fault when calling the face_encodings on the raspberry pi 3. In my case, I compiled dlib with OpenBLAS for linear algebra optimizations which allows dlib functionality to execute faster. However, OpenBLAS itself is multi-threaded and if you try and use it in a muilt-threaded application it will peg the CPU and cause the seg fault. For use in multi-threaded applications, OpenBlas recommends you set it to single thread mode.
In my case, I set some environmental variables in my virtual environment to tell OpenBLAS to only use a single thread by doing the following:
$ workon myvenv
$ nano VIRTUAL_ENV/bin/postactivate
add the following lines and save:
export OPENBLAS_NUM_THREADS=1
export OPENBLAS_MAIN_FREE=1
By doing this, I was able to achieve ~15 fps of facial recognition in my application that was previously crashing on my pi.
andrewplesniak
on 22 Feb 2019
I was experiencing the same problem, segmentation fault when calling the
face_encodingson the raspberry pi 3. In my case, I compiled dlib with OpenBLAS for linear algebra optimizations which allows dlib functionality to execute faster. However, OpenBLAS itself is multi-threaded and if you try and use it in a muilt-threaded application it will peg the CPU and cause the seg fault. For use in multi-threaded applications, OpenBlas recommends you set it to single thread mode.In my case, I set some environmental variables in my virtual environment to tell OpenBLAS to only use a single thread by doing the following:
$ workon myvenv
$ nano VIRTUAL_ENV/bin/postactivateadd the following lines and save:
export OPENBLAS_NUM_THREADS=1
export OPENBLAS_MAIN_FREE=1By doing this, I was able to achieve ~15 fps of facial recognition in my application that was previously crashing on my pi.
This solved my issue too. The Pi is now using only one CPU core instead of 4 but does not crash when calling face_encodings!
Any idea how all 4 cores could be used to increase the FPS?
AlexBdx
on 7 Jun 2019
I have the same issue, but I'm not working within a virtual environment, so where would i write
export OPENBLAS_NUM_THREADS=1
export OPENBLAS_MAIN_FREE=1
to?
SeanIsAllRobot
on 19 Oct 2019
Related issues
dickyj
·
3Comments
cjosephson
·
5Comments
Nijinsha
·
5Comments
ramineniraviteja
·
5Comments
xiao543348405
·
5Comments
Most helpful comment
I was experiencing the same problem, segmentation fault when calling the
face_encodingson the raspberry pi 3. In my case, I compiled dlib with OpenBLAS for linear algebra optimizations which allows dlib functionality to execute faster. However, OpenBLAS itself is multi-threaded and if you try and use it in a muilt-threaded application it will peg the CPU and cause the seg fault. For use in multi-threaded applications, OpenBlas recommends you set it to single thread mode.In my case, I set some environmental variables in my virtual environment to tell OpenBLAS to only use a single thread by doing the following:
$ workon myvenv$ nano VIRTUAL_ENV/bin/postactivateadd the following lines and save:
export OPENBLAS_NUM_THREADS=1export OPENBLAS_MAIN_FREE=1By doing this, I was able to achieve ~15 fps of facial recognition in my application that was previously crashing on my pi.