Closed TusharNimbhorkar closed 6 years ago
Our published models for Sintel and KITTI are pretrained on FlyingThings3D, then finetuned on the respective dataset’s training set.
The solver.prototxt
file is exactly the same as the one for pretraining—with the exception of the crop parameters. Sintel and KITTI have different image sizes and aspect ratios, and the crop size for FlyingThings3D would not work.
Thanks for the reply.
One more thing. Do you have anything to check epe while training?
We just print loss values from the loss layers, nothing more fancy
Most of the statistics in the Flownet2 paper are given in EPE. Do you calculate that separately?
FlowNet2 is trained directly on EPE as loss, so we don't have to do that separately.
Ah okay, so the Loss which is shown during training is basically EPE.
Yes
Thanks again closing the issue.
Hey
I was wondering what
solver.prototxt
files you used forsintel
andkitti
models.And are these models got only trained on this two dataset.