pytorch-normalizing-flows icon indicating copy to clipboard operation
pytorch-normalizing-flows copied to clipboard
verified publisher icon karpathy

2D -> ND

Open sadegh-aa opened this issue 6 years ago • 2 comments

Thanks for sharing a fairly complete repo of NFs. What kind of assumptions the code considers in the case of 2D that does not hold in ND? I have a dataset of 100D and the loss is nan all the time.

sadegh-aa avatar Jan 29 '20 15:01 sadegh-aa

I guess this is related to the ActNorm which becomes nan. Also there is relation between the batch size and the dimension of the data. Do you have any comment on that?

sadegh-aa avatar Jan 29 '20 16:01 sadegh-aa

For nan, you may try decreasing batch size.

kfzyqin avatar Apr 07 '20 11:04 kfzyqin