-
**Problem:**
The documentation of sciml_train indicates the 4 args are:
_(neural_ode, param, data, optimizer)_
But the only available methods have 3 args:
_(neural_ode, param, optimizer)_
**Rep…
cems2 updated
4 years ago
-
@MikeInnes do you happen to know what this is? The adjoint itself works fine, and for some reason this error shows up only in Zygote even though it's a "hardcoded adjoint"
```julia
using OrdinaryD…
-
**UPDATE** See comments below for the resolution of this problem
It appears Flux training of the DiffEqFlux Package method *neural_ode* is incompatible with (fast) GPU operations. _But I'm hoping…
cems2 updated
4 years ago
-
[Lotka Ex](https://github.com/FluxML/model-zoo/blob/master/other/diffeq/lotka-volterra.jl)
[Neural ODE Ex](https://github.com/FluxML/model-zoo/blob/master/other/diffeq/neural_ode.jl)
`julia version …
-
Very excited to try out some of the demo code for UDEs, and I didn't have any trouble with the ODE example (starting at https://github.com/JuliaDiffEq/DiffEqFlux.jl#universal-differential-equations) b…
-
Hi guys,
I have been able to run successfully the Lotka-Voltera example.
I am now looking at a classical benchmark of optimal control, namely the inverted pendulum on a cart where my controller is…
-
Hi,
Thank you so much for open sourcing the paper. I was trying to reproduce the results before trying to build on top of it, and ran into some issues.
This is on a fresh install of juliapro af…
-
First of all thank you for all of the work that went into this!
I've been trying to get the gist of DiffEqFlux and I'm having a hard time solving a seemingly trivial problem: I'm trying to solve a Ne…
-
So, I tried to integrate a custom pre-processing layer into a Neural ODE and encountered an error that does not happen if the same model is trained as a regular ANN. Inserting very simple functions li…
-
Hello,
Thank you very much for the nice work. I am playing around your code and was wondering would it be possible for you to share the config files to train the NODE or ANODE on cifar10? I am able…