This repository implements a demo of the networks described in "How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)" paper.
this option enable swapping between loaded 2D and 3D models if 3D-full prediction required to save some memory for who works on less or equal to 2GB GPU memory.
this option enable swapping between loaded 2D and 3D models if 3D-full prediction required to save some memory for who works on less or equal to 2GB GPU memory.