What type of loss did you use during training?

[Le1Elayne]

I try to train this network using multiscale loss described in the paper. But it failed. It works when I use L2 loss. So what type of loss did you use during training? Could you please explain why it does not work with multiscale loss? Thank you!

[sniklaus]

This question might be better suited for the official repository. Please kindly reach out to the authors there: https://github.com/NVlabs/PWC-Net