Clip output in model.py

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

Open shacharp opened 4 years ago

shacharp commented 4 years ago

Hey,

Why are you clipping the output of the model during eval (0.9m) but not during training?

Thanks