ERROR: MethodError: no method matching NeuralPDE.Phi

[DrEmilGazazyan]

Dear all,

I cannot understand my problems. Could you please help me?

Julia v 1.7.3

testpde.zip

Warning: FastChain is being deprecated in favor of Lux.jl. Lux.jl uses functions with explicit parameters f(u,p) like FastChain, but is fully featured and documented machine learning library. See the Lux.jl documentation for more details.
└ @ DiffEqFlux C:\Users\XXX.julia\packages\DiffEqFlux\Em1Aj\src\fast_layers.jl:9
ERROR: MethodError: no method matching NeuralPDE.Phi(::FastChain{Tuple{FastDense{typeof(sigmoid_fast), DiffEqFlux.var"#initial_params#107"{Vector{Float32}}, Nothing}, FastDense{typeof(sigmoid_fast), DiffEqFlux.var"#initial_params#107"{Vector{Float32}}, Nothing}, FastDense{typeof(identity), DiffEqFlux.var"#initial_params#107"{Vector{Float32}}, Nothing}}})
Closest candidates are:
NeuralPDE.Phi(::Chain) at C:\Users\XXX.julia\packages\NeuralPDE\Qjcw1\src\pinn_types.jl:352
NeuralPDE.Phi(::Lux.AbstractExplicitLayer) at C:\Users\XXX.julia\packages\NeuralPDE\Qjcw1\src\pinn_types.jl:348
Stacktrace:
[1] PhysicsInformedNN(chain::FastChain{Tuple{FastDense{typeof(sigmoid_fast), DiffEqFlux.var"#initial_params#107"{Vector{Float32}}, Nothing}, FastDense{typeof(sigmoid_fast), DiffEqFlux.var"#initial_params#107"{Vector{Float32}}, Nothing}, FastDense{typeof(identity), DiffEqFlux.var"#initial_params#107"{Vector{Float32}}, Nothing}}}, strategy::QuadratureTraining{IntegralsCubature.CubatureJLh, Float64}; init_params::Nothing, phi::Nothing, derivative::Nothing, param_estim::Bool, additional_loss::Nothing, adaptive_loss::Nothing, logger::Nothing, log_options::LogOptions, iteration::Nothing, kwargs::Base.Pairs{Symbol, Union{}, Tuple{}, NamedTuple{(), Tuple{}}})
@ NeuralPDE C:\Users\XXX.julia\packages\NeuralPDE\Qjcw1\src\pinn_types.jl:115
[2] PhysicsInformedNN(chain::Function, strategy::QuadratureTraining{IntegralsCubature.CubatureJLh, Float64})
@ NeuralPDE C:\Users\XXX.julia\packages\NeuralPDE\Qjcw1\src\pinn_types.jl:109
[3] top-level scope
@ c:\Users\XXX\Repository\testpde.jl:25

CODE

using NeuralPDE, Flux, ModelingToolkit, GalacticOptim, DiffEqFlux
using Quadrature, Cubature

@parameters x y
@variables u(..)
Dxx = Differential(x)^2
Dyy = Differential(y)^2

2D PDE

eq = Dxx(u(x,y)) + Dyy(u(x,y)) ~ -sin(pi*x)sin(piy)

Boundary conditions

bcs = [u(0,y) ~ 0.f0, u(1,y) ~ -sin(pi1)sin(piy),
u(x,0) ~ 0.f0, u(x,1) ~ -sin(pix)sin(pi1)]

Space and time domains

domains = [x ∈ IntervalDomain(0.0,1.0),
y ∈ IntervalDomain(0.0,1.0)]

Discretization

dx = 0.1

Neural network

dim = 2 # number of dimensions
chain = FastChain(FastDense(dim,16,Flux.σ),FastDense(16,16,Flux.σ),FastDense(16,1))

discretization = PhysicsInformedNN(chain, QuadratureTraining())

pde_system = PDESystem(eq,bcs,domains,[x,y],[u])
prob = discretize(pde_system,discretization)

cb = function (p,l)
println("Current loss is: $l")
return false
end

res = GalacticOptim.solve(prob, ADAM(0.1); cb = cb, maxiters=4000)
prob = remake(prob,u0=res.minimizer)
res = GalacticOptim.solve(prob, ADAM(0.01); cb = cb, maxiters=2000)
phi = discretization.phi

xs,ys = [domain.domain.lower:dx/10:domain.domain.upper for domain in domains]
analytic_sol_func(x,y) = (sin(pi*x)sin(piy))/(2pi^2)

u_predict = reshape([first(phi([x,y],res.minimizer)) for x in xs for y in ys],(length(xs),length(ys)))
u_real = reshape([analytic_sol_func(x,y) for x in xs for y in ys], (length(xs),length(ys)))
diff_u = abs.(u_predict .- u_real)

using Plots
p1 = plot(xs, ys, u_real, linetype=:contourf,title = "analytic");
p2 = plot(xs, ys, u_predict, linetype=:contourf,title = "predict");
p3 = plot(xs, ys, diff_u,linetype=:contourf,title = "error");
plot(p1,p2,p3)

[ChrisRackauckas]

You're using v4 syntax with v5. Update to using Lux as the docs state if you want to use v5. https://neuralpde.sciml.ai/dev/tutorials/pdesystem/