search

gengshan-y / VCN

Volumetric Correspondence Networks for Optical Flow, NeurIPS 2019.
https://gengshan-y.github.io/VCN/
MIT License
154 stars 25 forks source link

About loss #24

Open ChangyuLNeu opened 2 years ago

ChangyuLNeu commented 2 years ago

Hi,

Thank you for sharing your codes.

I am little confused that in your supplemental material for paper you said that you used L1 loss + OOR loss when finetuned Sintel and KITTI dataset.

However, in you code, it shows that you use L2 loss and OOR loss.

I would like to know which loss I should use.

gengshan-y commented 2 years ago

Hi, it was a mistake in the paper, we were using L2 norm following PWC-Net (Eq3). See this part of the code. Thanks for point it out.

ChangyuLNeu commented 2 years ago

Thank you for replying to me!