Closed nprasadmm closed 2 years ago
Sounds like the solver is stuck rejecting the step due to high local error estimation. Are you using an adaptive solver i.e dopri5
or tsit5
? Does the issue persist with a fixed-step solver like rk4
?
I switched to rk4
and it worked! Thank you!
I created a Graph Neural ODE using
torchdyn
wheref
is a 2-layer GCN made fromtorch_geometric
layers and the model seems to run forever on the first epoch. When I print the output in the forward function forf
, I constantly print the same values without end. I am unsure of any possible reasons for this. Could it be that the solver is failing to converge? Where should I look to debug this issue? I would appreciate any help.