# NeuralODE not taking multiple inputs although neural network is able to do so

**URL:** <https://discourse.julialang.org/t/neuralode-not-taking-multiple-inputs-although-neural-network-is-able-to-do-so/67042>\
**Category:** Machine Learning\
**Created:** [August 26, 2021, 2:58pm UTC](https://discourse.julialang.org/t/neuralode-not-taking-multiple-inputs-although-neural-network-is-able-to-do-so/67042 "2021-08-26T14:58:15Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![DiracFermion1](https://avatars.discourse-cdn.com/v4/letter/d/2acd7d/32.png) [@DiracFermion1](https://discourse.julialang.org/u/DiracFermion1)\
**Post date:** [August 26, 2021, 2:58pm UTC](https://discourse.julialang.org/t/neuralode-not-taking-multiple-inputs-although-neural-network-is-able-to-do-so/67042/1 "2021-08-26T14:58:15Z")

</div>

(this question is related to [How to use multiple inputs in `NeuralODE` object?](https://discourse.julialang.org/t/how-to-use-multiple-inputs-in-neuralode-object/66955) with a concrete example)

Hi, I am trying to define a NeuralODE that takes two inputs (one input is a Float array, another is an Int array). First I define a neural network as derivative:

```julia
using Flux
# following struct is used to take two inputs
struct TwoInputsLayer # layer take two inputs and aggregate with `op`
    layer1
    layer2
    op # operation to aggregate them
end

(m::TwoInputsLayer)(x) = m.op(m.layer1(x[1]), m.layer2(x[2]))
Flux.@functor TwoInputsLayer

dudt = Chain(TwoInputsLayer(Dense(10, 16), Flux.Embedding(5, 16), +), Dense(16, 4));

```

This derivative neural network `dudt` works fine that following code

```julia
emb_input = rand(1:5, (100))
dense_input = rand(10, 100);
dudt((dense_input, emb_input))

```

gives outputs correctly:

```julia
4×100 Matrix{Float64}:
  2.06809 0.692935 -0.0242472 … -0.492044 0.197574 1.71923
 -1.1337 1.1563 1.05582 -0.27764 0.596584 -1.46373
 -1.33768 -0.357405 0.0795294 -0.257927 -0.345279 -0.933275
 -2.12861 -0.844005 0.0125842 0.270249 -0.304456 -1.40022

```

However, when I pass `dudt` to construct a `NeuralODE`:

```julia
tspan = (0., 1.)
t = range(0., 1., length=10)
n_ode = NeuralODE(dudt, tspan, Tsit5(), saveat=t, reltol=1e-3, abstol=1e-5)

```

and pass the same inputs:

```julia
n_ode((dense_input, emb_input))

```

I got following error:

```julia
StackOverflowError:

Stacktrace:
 [1] recursive_unitless_bottom_eltype(a::Type{Any}) (repeats 79984 times)
   @ RecursiveArrayTools ~/.julia/packages/RecursiveArrayTools/cbsoB/src/utils.jl:91

```

If I remove parathesis:

```julia
n_ode(dense_input, emb_input)

```

I still have following error:

```julia
BoundsError: attempt to access 100-element Vector{Int64} at index [1:160]

```

Does anyone know what is the correct way to pass two inputs to `NeuralODE`? Here we only want the derivatives for first input `dense_input` not on second one `emb_input` since `emb_input` is an Int array.

Any ideas or suggestions would be much appreciated, thanks!