Training Datasets and schedule

[orram]

RAFT-Stereo/train_stereo.py

Line 222 in 0e2a127

parser.add_argument('--train_datasets', nargs='+', default=['sceneflow'], help="training datasets.")

Hi there, thank you for supplying such a clear code!
I have a question regarding the training procedure; as I understand, the training you suggest on the git page includes only sceneflow (and refine on Middlebury) with no reference to other datasets - FallingThings and Tartanair, which you reference in the paper. Do you use them in any additional training?
Can you clarify?
Thank you!

[lahavlipson]

The model weights in this git repo are pre-trained only on Sceneflow, and refined on Middlebury, ETH3D or KITTI.