RuntimeError when running multiprocessing example

• face_recognition version: 1.2.3
• Python version: 3.7
• Operating System: Pop!_OS 19.04
• CUDA + CuDNN version: 10.0

I'm trying to use the facerec_from_webcam_multiprocessing.py example with cuda support, but everytime I run it I get this error:

Width: 640, Height: 480, FPS: 30
Process Process-5:
Traceback (most recent call last):
  File "/usr/lib/python3.7/multiprocessing/process.py", line 297, in _bootstrap
    self.run()
  File "/usr/lib/python3.7/multiprocessing/process.py", line 99, in run
    self._target(*self._args, **self._kwargs)
  File "facerec_from_webcam_multiprocessing.py", line 78, in process
    face_locations = face_recognition.face_locations(rgb_frame, model="cnn")
  File "/usr/local/lib/python3.7/dist-packages/face_recognition/api.py", line 116, in face_locations
    return [_trim_css_to_bounds(_rect_to_css(face.rect), img.shape) for face in _raw_face_locations(img, number_of_times_to_upsample, "cnn")]
  File "/usr/local/lib/python3.7/dist-packages/face_recognition/api.py", line 100, in _raw_face_locations
    return cnn_face_detector(img, number_of_times_to_upsample)
RuntimeError: Error while calling cudaGetDevice(&the_device_id) in file /home/han/dlib-19.17/dlib/cuda/gpu_data.cpp:201. code: 3, reason: initialization error
Process Process-6:
Traceback (most recent call last):
  File "/usr/lib/python3.7/multiprocessing/process.py", line 297, in _bootstrap
    self.run()
  File "/usr/lib/python3.7/multiprocessing/process.py", line 99, in run
    self._target(*self._args, **self._kwargs)
  File "facerec_from_webcam_multiprocessing.py", line 78, in process
    face_locations = face_recognition.face_locations(rgb_frame, model="cnn")
  File "/usr/local/lib/python3.7/dist-packages/face_recognition/api.py", line 116, in face_locations
    return [_trim_css_to_bounds(_rect_to_css(face.rect), img.shape) for face in _raw_face_locations(img, number_of_times_to_upsample, "cnn")]
  File "/usr/local/lib/python3.7/dist-packages/face_recognition/api.py", line 100, in _raw_face_locations
    return cnn_face_detector(img, number_of_times_to_upsample)
RuntimeError: Error while calling cudaGetDevice(&the_device_id) in file /home/han/dlib-19.17/dlib/cuda/gpu_data.cpp:201. code: 3, reason: initialization error
Process Process-7:
Traceback (most recent call last):
  File "/usr/lib/python3.7/multiprocessing/process.py", line 297, in _bootstrap
    self.run()
  File "/usr/lib/python3.7/multiprocessing/process.py", line 99, in run
    self._target(*self._args, **self._kwargs)
  File "facerec_from_webcam_multiprocessing.py", line 78, in process
    face_locations = face_recognition.face_locations(rgb_frame, model="cnn")
  File "/usr/local/lib/python3.7/dist-packages/face_recognition/api.py", line 116, in face_locations
    return [_trim_css_to_bounds(_rect_to_css(face.rect), img.shape) for face in _raw_face_locations(img, number_of_times_to_upsample, "cnn")]
  File "/usr/local/lib/python3.7/dist-packages/face_recognition/api.py", line 100, in _raw_face_locations
    return cnn_face_detector(img, number_of_times_to_upsample)
RuntimeError: Error while calling cudaGetDevice(&the_device_id) in file /home/han/dlib-19.17/dlib/cuda/gpu_data.cpp:201. code: 3, reason: initialization error
Process Process-8:
Traceback (most recent call last):
  File "/usr/lib/python3.7/multiprocessing/process.py", line 297, in _bootstrap
    self.run()
  File "/usr/lib/python3.7/multiprocessing/process.py", line 99, in run
    self._target(*self._args, **self._kwargs)
  File "facerec_from_webcam_multiprocessing.py", line 78, in process
    face_locations = face_recognition.face_locations(rgb_frame, model="cnn")
  File "/usr/local/lib/python3.7/dist-packages/face_recognition/api.py", line 116, in face_locations
    return [_trim_css_to_bounds(_rect_to_css(face.rect), img.shape) for face in _raw_face_locations(img, number_of_times_to_upsample, "cnn")]
  File "/usr/local/lib/python3.7/dist-packages/face_recognition/api.py", line 100, in _raw_face_locations
    return cnn_face_detector(img, number_of_times_to_upsample)
RuntimeError: Error while calling cudaGetDevice(&the_device_id) in file /home/han/dlib-19.17/dlib/cuda/gpu_data.cpp:201. code: 3, reason: initialization error

I looked at the multiprocessing documentation and made a few changes in the script without success. Could you give me a hint on how could I make it work? Thanks in advance.

Start with facerec_from_webcam_multiprocessing.py at line 78, where face_recognition.face_locations is called with model="cnn". Reproduce the example with the reported Python, CUDA, and dlib setup, then investigate multiprocessing CUDA initialization around the cudaGetDevice error. Done means the multiprocessing webcam example runs without the RuntimeError.