Hi, I have a
NeuralODE defined as follows:
dudt = Chain(x -> Dense(10, 20, tanh)(x) + Dense(10, 20, tanh)(x)) n_ode = NeuralODE(dudt, (0., 1.), Tsit5(), saveat=range(0., 1., length=100), reltol=1e-7, abstol=1e-9)
which takes a tuple
x as input and pass its two components through two branches separately. When I check the trainable parameters with:
it looks like parameters for two
Dense layers are not detected as trainable parameters. I am wondering if there is a way to make them trainable?