search

mattpoggi / mono-uncertainty

CVPR 2020 - On the uncertainty of self-supervised monocular depth estimation
233 stars 24 forks source link

which split should I choose when training? #6

Closed freshjh closed 4 years ago

freshjh commented 4 years ago

Hi, thanks for your greate work! And I am confused about the dataset split in training, can you tell me which split files were choosed when you training the model? is 'eigen zhou' ? or 'benchmark'? or others. it is my first time to use kitti_dataset. Thanks!

mattpoggi commented 4 years ago

Hi @freshjh , as for monodepth2, we used eigen_zhou to train on sequences (M, MS) and eigen_full when using stereo pairs alone (S).

freshjh commented 4 years ago

thank you very much！