-
Hi, I am currently learning about Neural ODEs, and to this end I have been experimenting with torchdyn. One problem I have encountered is having multiple arguments in the `forward` of the neural netwo…
-
MWE:
```julia
using DiffEqFlux, Flux, Optim, OrdinaryDiffEq, CUDA, DiffEqSensitivity, Plots
u0 = [1.1; 1.1] |> gpu
tspan = (0.0f0,25.0f0)
ann = FastChain(FastDense(2,16,tanh), FastDense(16,…
-
Flux.train! goes through the first iteration resulting in 1 call to the callback function after which the process seems to get stuck. We've used htop to verify that the Julia process stops using any C…
-
Hello, I was wondering if there was any way to do paralellization with cpu cores to train using this package? When I've tried to implement torch multiprocessing, it warns me about a fork and autograd …
-
I'm working on sequential MNIST with an RNN and using DepthCat to have access to time of the ODE. I set `s_span = torch.linspace(0, 27, 28)` for [0, 27] time interval. However, when extracting t from …
-
I am seeing in the docs ([classification ](https://torchdyn.readthedocs.io/en/latest/tutorials/02_classification.html) or [Lagrangian neural nets](https://torchdyn.readthedocs.io/en/latest/tutorials/0…
-
Please help me to understand the cause of the error when running the [DEQ example from Julia's blog](https://julialang.org/blog/2021/10/DEQ/) (Deep Equilibrium Models)
this code
```Julia
using Fl…
-
Hi,
I installed torchdyn and ran the Quickstart code, but it occurs: "ModuleNotFoundError: No module named 'torchdyn.core'".
How should I fix it?
Thanks for your help!
-
Please help me to understand the cause of the error when running the [DEQ example from Julia's blog](https://julialang.org/blog/2021/10/DEQ/) (Deep Equilibrium Models)
this code
```Julia
using Fl…
-
I tend to work with relatively small datasets, so I have found one nice advantage of working with Jax is that I can train an ensemble of networks on a single GPU via [Will Whitney's approach](https://…