-
-
Notifications
You must be signed in to change notification settings - Fork 153
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
initial changes for neuraldsde and neuralsde #736
Conversation
Based off of the old one. Might be easiest to just make this Flux based?
p1 = Lux.ComponentArray(p1) | ||
p2 = Lux.ComponentArray(p2) | ||
#Component Arrays doesn't provide a name to the first ComponentVector, only subsequent ones get a name for dereferencing | ||
p = [p1, p2] | ||
|
||
neuralsde = NeuralDSDE(drift_dudt, diffusion_dudt, tspan, SOSRI(), |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The choice of the solver here is leading to https://github.com/SciML/DiffEqFlux.jl/runs/7005695604?check_suite_focus=true#step:5:22
We'll either need a different sensealg for NeuralDSDE(currently InterpolatingAdjoint) which is compatible with Lux or change the solver
Mark the Lux version of this broken and make the example with Flux. Get that done, open an issue, and we can handle the ReverseDiff/Tracker stuff on it later. |
0b45582
to
a9d252a
Compare
No description provided.