pytorch-normalizing-flows icon indicating copy to clipboard operation
pytorch-normalizing-flows copied to clipboard

Published 20 hours ago • verified publisher icon karpathy

Loss becomes NAN with the Glow model

Open ashispati opened this issue 5 years ago • 2 comments

The loss for the Glow model becomes NAN (sometimes). I have only tested it with the half-moons dataset with the default model in the Jupyter notebook. Did not face the same issue with the other models.

Screen Shot 2020-07-09 at 10 51 48 AM Screen Shot 2020-07-09 at 10 51 19 AM

ashispati avatar Jul 09 '20 14:07 ashispati

For NaN values, you may try decreasing batch size.

YeonwooSung avatar Aug 04 '20 04:08 YeonwooSung

@YeonwooSung Why? Also, this issue seems to happen often

richardrl avatar Jul 22 '21 22:07 richardrl