Merge pull request #405 from SciML/fix_neural_adapter_tests

Update neural adapter tests with heterogeneous inputs

docs/src/pinn/neural_adapter.md

@@ -144,7 +144,7 @@ domains_map = map(xs_domain) do (xs_dom)
 end
 
 analytic_sol_func(x,y) = (sin(pi*x)*sin(pi*y))/(2pi^2)
-function create_bcs(bcs,x_domain_,phi_bound)
+function create_bcs(x_domain_,phi_bound)
     x_0, x_e =  x_domain_.left, x_domain_.right
     if x_0 == 0.0
         bcs = [u(0,y) ~ 0.0,
@@ -171,7 +171,7 @@ for i in 1:count_decomp
     phi_bound(x,y) = phi_in(vcat(x,y))
     @register phi_bound(x,y)
     Base.Broadcast.broadcasted(::typeof(phi_bound), x,y) = phi_bound(x,y)
-    bcs_ = create_bcs(bcs,domains_[1].domain, phi_bound)
+    bcs_ = create_bcs(domains_[1].domain, phi_bound)
     @named pde_system_ = PDESystem(eq, bcs_, domains_, [x, y], [u(x, y)])
     push!(pde_system_map,pde_system_)
     strategy = NeuralPDE.GridTraining([0.1/count_decomp, 0.1])

test/neural_adapter_tests.jl

@@ -50,7 +50,7 @@ discretization = NeuralPDE.PhysicsInformedNN(chain1,
                                              quadrature_strategy;
                                              init_params = initθ)
 
-@named pde_system = PDESystem(eq,bcs,domains,[x,y],[u])
+@named pde_system = PDESystem(eq,bcs,domains,[x,y],[u(x,y)])
 prob = NeuralPDE.discretize(pde_system,discretization)
 sym_prob = NeuralPDE.symbolic_discretize(pde_system,discretization)
 res = GalacticOptim.solve(prob, BFGS();  maxiters=2000)
@@ -169,7 +169,7 @@ domains_map = map(xs_domain) do (xs_dom)
 end
 
 analytic_sol_func(x,y) = (sin(pi*x)*sin(pi*y))/(2pi^2)
-function create_bcs(bcs,x_domain_,phi_bound)
+function create_bcs(x_domain_,phi_bound)
     x_0, x_e =  x_domain_.left, x_domain_.right
     if x_0 == 0.0
         bcs = [u(0,y) ~ 0.0,
@@ -196,10 +196,9 @@ for i in 1:count_decomp
     # phi_bound(x,y) = if (x isa Matrix)  phi_in(vcat(x, fill(y,size(x)))) else  phi_in(vcat(fill(x,size(y)),y)) end
     phi_bound(x,y) = phi_in(vcat(x,y))
     @register phi_bound(x,y)
-    #TODO fix broadcast
     Base.Broadcast.broadcasted(::typeof(phi_bound), x,y) = phi_bound(x,y)
-    bcs_ = create_bcs(bcs,domains_[1].domain, phi_bound)
-    @named pde_system_ = PDESystem(eq, bcs_, domains_, [x, y], [u])
+    bcs_ = create_bcs(domains_[1].domain, phi_bound)
+    @named pde_system_ = PDESystem(eq, bcs_, domains_, [x, y], [u(x,y)])
     push!(pde_system_map,pde_system_)
     strategy = NeuralPDE.GridTraining([0.1/count_decomp, 0.1])
 
@@ -265,7 +264,7 @@ chain2 = FastChain(FastDense(2,inner_,af),
 
 initθ2 =Float64.(DiffEqFlux.initial_params(chain2))
 
-@named pde_system = PDESystem(eq, bcs, domains, [x, y], [u])
+@named pde_system = PDESystem(eq, bcs, domains, [x, y], [u(x,y)])
 
 losses = map(1:count_decomp) do i
     loss(cord,θ) = chain2(cord,θ) .- phis[i](cord,reses[i].minimizer)