16fb/deepheadpose repository overview

⁠deepheadpose

Docker Container of natanielruiz/deep-head-pose,
Includes CUDA support
Includes OpenCV + most dependacies to run deep-head-pose.
Uses Anaconda to manage dependacies.

Uses a modified version of natanielruiz original code, modifications are to allow python 3 compatiability

⁠Usage

⁠Run interactively and expose GPU

docker run -it --gpus all 16fb/deepheadpose:GPU

⁠Activate conda environment

conda activate pytorch

⁠Use New Model

python code/test_on_video_dlib.py --snapshot models\mysnap_epoch_29.pkl --face_model dlib\mmod_human_face_detector.dat  --video conan-cruise.gif --fps 15 --n_frames 100