-
I'm looking to taking in a sequence of values and output a sequence as well.
So instead of doing `flatten` and computing the final output from neural ode, I would like to make use of each intermediat…
-
I'm running into issues when trying out the following GPU example: https://diffeqflux.sciml.ai/dev/GPUs/.
At the line
```
# Make the data into a GPU-based array if the user has a GPU
ode_dat…
-
Hi all,
I was looking at this documentation (https://diffeqflux.sciml.ai/dev/examples/neural_ode_sciml/#Usage-without-the-layer) about not using the NeuralODE wrapper, and noticed there might be a …
-
Training NN by splitting the datapoints and training on smaller intervals, to avoid being stuck in local minima while training.
Function I tried to train NN to predict values according to function,…
-
The model that I am training is very similar to ANODE as defined in torchdyn/tutorials/04_augmentation_strategies.ipynb
Given a time step in [0,1], I would like to get the "flow" of the model at th…
-
Hi ,
the example of NeuralODE using componentarrays gives following error
```julia
ERROR: Gradient (L1 = (W = Float32[0.0 0.0; 0.0 0.0; 0.0 0.0; 0.0 0.0; 0.0 0.0; 0.0 0.0; 0.0 0.0; 0.0 0.0; 0.0 0…
-
Hi @jiweiqi ,In robertson's code.. shouldn't one solve for `_prob` and not `prob` .. copying here code for the reference from
https://github.com/DENG-MIT/CRNN/blob/main/robertson/rober_crnn.jl
```…
-
```Julia
using DiffEqFlux, OrdinaryDiffEq, Flux, Optim, Plots
function trueODEfunc(dydt, y, k, t)
dydt[1] = -2 * k[1] * y[1]^2
dydt[2] = k[1] * y[1]^2
end
u0 = Float64[1.0;0.5]
data…
-
I was trying to set up a sequential learning problem as follows:
```
using Flux, DiffEqFlux
using DifferentialEquations
using Random
ndata= 11;
tspan = (0.0f0, 1.0f0);
tdata = range(tspan[1],…
-
```Julia
using DiffEqFlux, OrdinaryDiffEq, Flux, Optim, Plots
function trueODEfunc(dydt, y, k, t)
dydt[1] = -2 * k[1] * y[1]^2 - k[2] * y[1]
dydt[2] = k[1] * y[1]^2 - k[4] * y[2] * y[4]
…