changed discretize_full_functions to discretize_inner_functions

Author: zoemcc

src/pinns_pde_solve.jl

@@ -1247,7 +1247,7 @@ function SciMLBase.symbolic_discretize(pde_system::PDESystem, discretization::Ph
 end
 
 
-function discretize_full_functions(pde_system::PDESystem, discretization::PhysicsInformedNN)
+function discretize_inner_functions(pde_system::PDESystem, discretization::PhysicsInformedNN)
     eqs = pde_system.eqs
     bcs = pde_system.bcs
 
@@ -1490,7 +1490,7 @@ end
 
 # Convert a PDE problem into an OptimizationProblem
 function SciMLBase.discretize(pde_system::PDESystem, discretization::PhysicsInformedNN)
-    discretized_functions = discretize_full_functions(pde_system, discretization)
+    discretized_functions = discretize_inner_functions(pde_system, discretization)
     f = OptimizationFunction(discretized_functions.full_loss_function, GalacticOptim.AutoZygote())
     GalacticOptim.OptimizationProblem(f, discretized_functions.flat_initθ)
 end

test/NNPDE_tests.jl

@@ -358,7 +358,7 @@ discretization = NeuralPDE.PhysicsInformedNN(chain,quasirandom_strategy;init_par
 
 prob = NeuralPDE.discretize(pde_system,discretization)
 sym_prob = NeuralPDE.symbolic_discretize(pde_system,discretization)
-discretized_functions = NeuralPDE.discretize_full_functions(pde_system,discretization)
+discretized_functions = NeuralPDE.discretize_inner_functions(pde_system,discretization)
 
 pde_inner_loss_functions = discretized_functions.pde_loss_functions
 bcs_inner_loss_functions = discretized_functions.bc_loss_functions
@@ -646,7 +646,7 @@ discretization = NeuralPDE.PhysicsInformedNN(chain,
 
 @named pde_system = PDESystem(eq,bcs,domains,[x],[p(x)])
 prob = NeuralPDE.discretize(pde_system,discretization)
-discretized_functions = NeuralPDE.discretize_full_functions(pde_system,discretization)
+discretized_functions = NeuralPDE.discretize_inner_functions(pde_system,discretization)
 
 pde_inner_loss_functions = discretized_functions.pde_loss_functions
 bcs_inner_loss_functions = discretized_functions.bc_loss_functions
@@ -741,7 +741,7 @@ additional_loss(discretization.phi, testθ, nothing)
                       defaults=Dict([p => 1.0 for p in [σ_, ρ, β]]))
 prob = NeuralPDE.discretize(pde_system,discretization)
 sym_prob = NeuralPDE.symbolic_discretize(pde_system,discretization)
-discretized_functions = NeuralPDE.discretize_full_functions(pde_system,discretization)
+discretized_functions = NeuralPDE.discretize_inner_functions(pde_system,discretization)
 discretized_functions.full_loss_function([testθ;ones(3)], Float64[])
 
 res = GalacticOptim.solve(prob, Optim.BFGS(); maxiters=6000)
@@ -869,7 +869,7 @@ discretization = NeuralPDE.PhysicsInformedNN(chain,strategy; initial_params=init
 @named pde_system = PDESystem(eq,bc,domain,[x,y],[u(x, y)])
 prob = NeuralPDE.discretize(pde_system,discretization)
 symprob = NeuralPDE.symbolic_discretize(pde_system,discretization)
-discretized_functions = NeuralPDE.discretize_full_functions(pde_system,discretization)
+discretized_functions = NeuralPDE.discretize_inner_functions(pde_system,discretization)
 discretized_functions.full_loss_function(initθ, Float64[])
 
 res  = GalacticOptim.solve(prob,ADAM(0.01),maxiters=500)

test/forward_tests.jl

@@ -25,7 +25,7 @@ import ModelingToolkit: Interval
     discretization = NeuralPDE.PhysicsInformedNN(chain,strategy_;init_params = Float64[])
     @named pde_system = PDESystem(eq,bcs,domains,[x],[u(x)])
     prob = NeuralPDE.discretize(pde_system,discretization)
-    discretized_functions = NeuralPDE.discretize_full_functions(pde_system,discretization)
+    discretized_functions = NeuralPDE.discretize_inner_functions(pde_system,discretization)
 
     eqs = pde_system.eqs
     bcs = pde_system.bcs
@@ -112,7 +112,7 @@ end
     @named pde_system = PDESystem(eq,bcs,domains,[x],[u(x)])
     sym_prob = SciMLBase.symbolic_discretize(pde_system, discretization)
     prob = NeuralPDE.discretize(pde_system,discretization)
-    discretized_functions = NeuralPDE.discretize_full_functions(pde_system,discretization)
+    discretized_functions = NeuralPDE.discretize_inner_functions(pde_system,discretization)
     inner_loss =discretized_functions.inner_pde_loss_functions[1]
     exact_u = π/(3*sqrt(3))
     @test  inner_loss(ones(1,1), Float64[])[1] ≈ exact_u  rtol = 1e-5
@@ -132,7 +132,7 @@ end
     @named pde_system = PDESystem(eqs, bcs, domains, [x], [u(x)])
     sym_prob = SciMLBase.symbolic_discretize(pde_system, discretization)
     prob = SciMLBase.discretize(pde_system, discretization)
-    discretized_functions = NeuralPDE.discretize_full_functions(pde_system,discretization)
+    discretized_functions = NeuralPDE.discretize_inner_functions(pde_system,discretization)
     inner_loss =discretized_functions.inner_pde_loss_functions[1]
     exact_u = 0
     @test  inner_loss(ones(1,1), Float64[])[1] ≈ exact_u  rtol = 1e-9