Periodic 1D with large --max-t value produces nans

[xanderladd]

Hello!

I am trying to use latent ODE functionality to interpolate a set of points with over 5k irregularly sampled timesteps. When using the current version and python3 run_models.py --niters 500 -n 1000 -s 50 -l 10 --dataset periodic --latent-ode --noise-weight 0.01 --max-t 6000 I get an error in on line 275 : assert(not torch.isnan(inc).any()). A short-term solution for me is to just scale my time series down to ranges used in paper/examples. I am curious if you can also reproduce this error and if it is expected behavior. I am happy to follow up with any information needed to reproduce.

Also... this does not occur when I set extrapolate to True...perhaps that is pointing to some issue with how the series is sampled.

by the way I am using:
torchdiffeq 0.2.1
torch 1.8.0
Python 3.7.2

[xanderladd]

if anyone encountering this issue, do not try to interpolate over a large timescale. Either normalize the timescale, or segment /sample your data or both.