search

fangchangma / self-supervised-depth-completion

ICRA 2019 "Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Camera"
MIT License
623 stars 135 forks source link

Fixing a bug of mixing data stored on gpu and a model stored on cpu w… #42

Open mac137 opened 4 years ago

mac137 commented 4 years ago

my PR fixes the following bug: RuntimeError: expected device cuda:0 but got device cpu

... while running this command: python main.py --cpu --evaluate [path2checkpoint]