robust_loss_pytorch

robust_loss_pytorch copied to clipboard

Loss drives below zero for self-supervised depth estimation and training fails

12

Hi, unfortunately we don't have a code release for the monocular depth estimation experiments of the paper (though that code is in TF anyways so it likely isn't what you're...

rvarun7777

[Question] Regarding optimizing the adaptive loss function: optimizer always increments c to reduce loss while trying to overfit.

1

Hi, I was trying out your work and was trying to overfit my model on a single example first to get a feel of how it works, and what I...

Somdyuti2

fixed shape mismatch in AdaptiveImageLossFunction

3

rvarun7777

I would like to know how this loss function is applied to the clustering algorithm. Since the input to the clustering task is a data matrix X (two dimensions), what...

caolei2000