FROM nvidia/cuda:12.2.0-runtime-ubuntu22.04
# Install dependencies
RUN apt-get update && apt-get install -y \
libopencv-core4.5 libavcodec58 libavformat58 libavutil56 \
libqt6widgets6 libqt6gui6 libqt6core6 ocl-icd-libopencl1 \
&& rm -rf /var/lib/apt/lists/*
# Copy pre‑built binaries
COPY KaamukShwetaCam /usr/local/bin/
COPY facemp4.so /usr/local/lib/
# Entry point
ENTRYPOINT ["/usr/local/bin/KaamukShwetaCam"]
Run with GPU access:
docker run --gpus all -v /dev/video0:/dev/video0 \
-v $(pwd)/output:/output kaamuk/shweta-cam:latest \
--camera /dev/video0 --output /output
git clone https://github.com/kaamuk/facemp4.git
cd facemp4
python -m venv .venv
source .venv/bin/activate # .\venv\Scripts\activate on Windows
pip install -e .[dev] # installs the package + development tools
The -e flag makes the install “editable”, so any code changes are reflected instantly. kaamuk shweta cam show wid facemp4 install
# 1️⃣ Create a workspace
mkdir -p ~/facemp4_build && cd ~/facemp4_build
# 2️⃣ Clone the official repo (replace with the correct URL if you have a fork)
git clone https://github.com/facemp4/facemp4.git
cd facemp4
What’s inside?