The code of this project needs to run on Linux or WSL and Anaconda to install the environment.
- Clone the repository
git clone https://github.com/brohoya/moAI
cd moAI
- Clone MegaPose6d, create megapose module and download pre-trained pose estimation models
git clone https://github.com/megapose6d/megapose6d.git
cd megapose6d && git submodule update --init
cd ..
- Setup the environment
conda init
bash setup.sh
conda activate moAI
- Download MegaPose6d pre-trained models:
python -m megapose.scripts.download --megapose_models
- Install the X/Qt/Mesa bits needed by OpenCV Qt and GLX (Ubuntu/Debian example):
sudo apt-get update
sudo apt-get install -y \
libgl1-mesa-dri mesa-utils libglx-mesa0 libopengl0 libegl1 \
libx11-6 libxext6 libxrender1 libxcb1 libxcb-xinerama0 libxcb-cursor0 \
libxkbcommon0 libxkbcommon-x11-0 qtbase5-dev
- Set environment variables (optional) For convenience, the MegaPose data directory can be changed by setting the environment variable MEGAPOSE_DATA_DIR. Check out MegaPose6D repository for more details.