Using a neural network inside a function for DifferentialEquations.jl solve

[ChrisRackauckas]

@dameka

MethodError: no method matching (::Flux.Dense{typeof(NNlib.relu), Matrix{Float32}, Vector{Float32}})(::Float32)
The object of type `Flux.Dense{typeof(NNlib.relu), Matrix{Float32}, Vector{Float32}}` exists, but no method is defined for this combination of argument types when trying to treat it as a callable object.

See this part. Flux requires an array input, but t is a scalar. m([t])[1]