I just checked the loss of GeoNet on training, and its seems that it has a high variance. How did you selected your best model for evaluation on depth and camera motion tasks?.
Hi, you are right. Training on the KITTI dataset is painful for the loss of scene diversity. You can select the KITTI 2012 training set as a validation set.
I just checked the loss of GeoNet on training, and its seems that it has a high variance. How did you selected your best model for evaluation on depth and camera motion tasks?.