-
Hi, I'm trying to train the UniversalODE model of the predator-prey example but sciml_train fails (apparently caused by Zygote.gradient)
```
using DiffEqFlux, Flux, Optim, OrdinaryDiffEq, CUDA, Di…
-
There's a lot of parts of the documentation that can be better described:
- [ ] MNIST example can get a lot more text on what it's doing. Especially how it's performing minibatching.
- [ ] Every t…
-
Hi,
There is a tutorial on mini-batch for a single initial condition https://diffeqflux.sciml.ai/dev/examples/minibatch/.
However, what I am going to do is to train neural ode for multiple initi…
-
Posting here after asking on Gitter.
I was trying to make a `SecondOrderODEProblem` work in a neural ODE layer. This is what I have so far:
```julia
using DifferentialEquations
using Flux
usi…
-
After the upgrade from OPNsense 19.7.6 to 19.7.7, Rspamd, on my side, stoped working correctly.
Mails from amazon and ebay are delivered twice or more often.
I think the problem is a timeout in po…
-
 like leaky int…
-
Following neural_sde.md line-by-line results in an error when invoking DiffEqFlux.sciml_train:
ERROR: MethodError: no method matching Float32(::Tracker.TrackedReal{Float32})
Closest candidates are…
-
https://arxiv.org/pdf/1909.12790.pdf
Need a good name for it. Tracking it here, and we should make sure to have a good implementation of it that's easy to plug and play for "non-diffeq people".