checkpoints/KITTI_comb/checkpoint_best.ckpt always gives occlusion maps of all zeros
RK621 opened this issue · 1 comments
Dear Authors,
1). I got occlusion maps of all zeros when evaluating using the pretrained model "checkpoints/KITTI_comb/checkpoint_best.ckpt".
2). However, when I overwrite "checkpoints/KITTI_comb/checkpoint_best.ckpt" with the files moving from "checkpoints/Sintel_comb/checkpoint_best.ckpt", and did the same thing in 1), the occlusion map is not zero.
Was the occlusion being trained when creating the checkpoint "checkpoints/KITTI_comb/checkpoint_best.ckpt"?
Thank you very much!
=====
PS.
My environment is
python 3.7.3
pytorch 1.1.0
CUDA 9.0
The correlation package has been installed based on the instruction in the IRR-PWC repository.
Hi @RK621,
You are correct, we trained the occlusion estimator only for the Sintel models.
In order to retrain it with occlusion you'll need to change the dataset loader of KITTI.
Regards,
Aviram