/face_recognition_docker

Run face_recognition on GPU easily with Docker.

Primary LanguageDockerfileGNU General Public License v3.0GPL-3.0

face_recognition_docker

Run face_recognition on GPU easily with Docker.

Setup

To run on GPU you need a computer with a CUDA-capable GPU and the NVIDIA driver >= 418.39 (because it uses CUDA 10.1; see the CUDA Toolkit and Compatible Driver Versions table for more information). Otherwise, you can run on the CPU.

You also need a camera connected to the computer. Otherwise, you can run other scripts within the container.

  1. Install Docker.
  2. Install the NVIDIA Container Toolkit.
  3. Run:
host +local:root
docker run \
  --rm \
  --gpus all \
  -v /tmp/.X11-unix:/tmp/.X11-unix:rw \
  -e QT_X11_NO_MITSHM=1 \
  -e DISPLAY \
  --device=/dev/video0:/dev/video0 \
  bryant1410/face_recognition \
    python3 facerec_from_webcam_faster.py