Vox-cpk.pth.tar
To use the model checkpoint in vox-cpk.pth.tar , you would typically:
import torch checkpoint = torch.load("vox-cpk.pth.tar", map_location="cpu") vox-cpk.pth.tar
In research (such as by learned geometric modelling groups), models are trained to take a 2D image of a face and output a 3D Voxel grid or a mesh. To use the model checkpoint in vox-cpk
: Indicates the model was trained on the VoxCeleb dataset , which consists of thousands of videos of human faces. vox-cpk.pth.tar