Merge branch 'SciML:master' into Bpinn_pde

SciML · Nov 30, 2023 · f91adc3 · f91adc3
2 parents dc3dceb + 80a7849
commit f91adc3
Show file tree

Hide file tree

Showing 7 changed files with 15 additions and 16 deletions.
diff --git a/.gitignore b/.gitignore
@@ -7,4 +7,5 @@ Manifest.toml
 */testlogs
 docs/build/*
 scratch
-scratch/*
+scratch/*
+.DS_store
diff --git a/Project.toml b/Project.toml
@@ -66,11 +66,12 @@ MonteCarloMeasurements = "1"
 Optim = ">= 1.7.8"
 Optimisers = "0.2, 0.3"
 Optimization = "3"
-QuasiMonteCarlo = "0.2.1"
+QuasiMonteCarlo = "0.3.2"
 RecursiveArrayTools = "2.31"
 Reexport = "1.0"
 RuntimeGeneratedFunctions = "0.5"
 SciMLBase = "1.91, 2"
+Statistics = "1"
 StochasticDiffEq = "6.13"
 SymbolicUtils = "1"
 Symbolics = "5"
@@ -80,7 +81,6 @@ julia = "1.6"
 
 [extras]
 CUDA = "052768ef-5323-5732-b1bb-66c8b64840ba"
-IntegralsCuba = "1e5cbd8a-c439-4026-92c2-98742b2c817b"
 OptimizationOptimJL = "36348300-93cb-4f02-beb5-3c3902f8871e"
 OptimizationOptimisers = "42dfb2eb-d2b4-4451-abcd-913932933ac1"
 OrdinaryDiffEq = "1dea7af3-3e70-54e6-95c3-0bf5283fa5ed"
@@ -89,4 +89,4 @@ SafeTestsets = "1bc83da4-3b8d-516f-aca4-4fe02f6d838f"
 Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
 
 [targets]
-test = ["Test", "CUDA", "SafeTestsets", "OptimizationOptimisers", "OptimizationOptimJL", "Pkg", "OrdinaryDiffEq", "IntegralsCuba"]
+test = ["Test", "CUDA", "SafeTestsets", "OptimizationOptimisers", "OptimizationOptimJL", "Pkg", "OrdinaryDiffEq"]
diff --git a/docs/src/index.md b/docs/src/index.md
@@ -3,7 +3,7 @@
 [NeuralPDE.jl](https://github.com/SciML/NeuralPDE.jl) is a solver package which 
 consists of neural network solvers for partial differential equations using 
 physics-informed neural networks (PINNs) and the ability to generate neural
-networks which both approximate physical laws and real data simultaniously.
+networks which both approximate physical laws and real data simultaneously.
 
 ## Features
 

diff --git a/docs/src/tutorials/ode.md b/docs/src/tutorials/ode.md
@@ -3,7 +3,7 @@
 !!! note
 
     It is highly recommended you first read the [solving ordinary differential
-    equations with DifferentialEquations.jl tutorial](https://docs.sciml.ai/DiffEqDocs/stable/tutorials/ode_example/)
+    equations with DifferentialEquations.jl tutorial](https://docs.sciml.ai/DiffEqDocs/stable/getting_started/)
     before reading this tutorial.
 
 This tutorial is an introduction to using physics-informed neural networks (PINNs) for solving ordinary differential equations (ODEs). In contrast to the later parts of this documentation which use the symbolic interface, here we will focus on the simplified [`NNODE`](@ref) which uses the `ODEProblem` specification for the ODE.

diff --git a/src/BPINN_ode.jl b/src/BPINN_ode.jl
@@ -83,7 +83,7 @@ Kevin Linka, Amelie Schäfer, Xuhui Meng, Zongren Zou, George Em Karniadakis, El
 struct BNNODE{C, K, IT <: NamedTuple,
     A <: NamedTuple, H <: NamedTuple,
     ST <: Union{Nothing, AbstractTrainingStrategy},
-    I <: Union{Nothing, Vector{<:AbstractFloat}},
+    I <: Union{Nothing, <:NamedTuple, Vector{<:AbstractFloat}},
     P <: Union{Nothing, Vector{<:Distribution}},
     D <:
     Union{Vector{Nothing}, Vector{<:Vector{<:AbstractFloat}}}} <:

diff --git a/src/advancedHMC_MCMC.jl b/src/advancedHMC_MCMC.jl
@@ -109,9 +109,8 @@ function L2LossData(Tar::LogTargetDensity, θ)
         for i in 1:length(Tar.prob.u0)
             # for u[i] ith vector must be added to dataset,nn[1,:] is the dx in lotka_volterra
             L2logprob += logpdf(MvNormal(nn[i, :],
-                    LinearAlgebra.Diagonal(map(abs2,
-                        Tar.l2std[i] .*
-                        ones(length(Tar.dataset[i]))))),
+                    LinearAlgebra.Diagonal(abs2.(Tar.l2std[i] .*
+                                                 ones(length(Tar.dataset[i]))))),
                 Tar.dataset[i])
         end
         return L2logprob
@@ -250,9 +249,8 @@ function innerdiff(Tar::LogTargetDensity, f, autodiff::Bool, t::AbstractVector,
 
     # N dimensional vector if N outputs for NN(each row has logpdf of i[i] where u is vector of dependant variables)
     return [logpdf(MvNormal(vals[i, :],
-            LinearAlgebra.Diagonal(map(abs2,
-                Tar.phystd[i] .*
-                ones(length(vals[i, :]))))),
+            LinearAlgebra.Diagonal(abs2.(Tar.phystd[i] .*
+                                         ones(length(vals[i, :]))))),
         zeros(length(vals[i, :]))) for i in 1:length(Tar.prob.u0)]
 end
 
@@ -497,7 +495,7 @@ function ahmc_bayesian_pinn_ode(prob::DiffEqBase.ODEProblem, chain;
     strategy = strategy == GridTraining ? strategy(physdt) : strategy
 
     if dataset != [nothing] &&
-       (length(dataset) < 2 || !(typeof(dataset) <: Vector{<:Vector{<:AbstractFloat}}))
+       (length(dataset) < 2 || !(dataset isa Vector{<:Vector{<:AbstractFloat}}))
         throw(error("Invalid dataset. dataset would be timeseries (x̂,t) where type: Vector{Vector{AbstractFloat}"))
     end
 
@@ -534,7 +532,7 @@ function ahmc_bayesian_pinn_ode(prob::DiffEqBase.ODEProblem, chain;
     ninv = length(param)
     priors = [
         MvNormal(priorsNNw[1] * ones(nparameters),
-            LinearAlgebra.Diagonal(map(abs2, priorsNNw[2] .* ones(nparameters)))),
+            LinearAlgebra.Diagonal(abs2.(priorsNNw[2] .* ones(nparameters)))),
     ]
 
     # append Ode params to all paramvector

diff --git a/src/pinn_types.jl b/src/pinn_types.jl
@@ -106,7 +106,7 @@ struct PhysicsInformedNN{T, P, PH, DER, PE, AL, ADA, LOG, K} <: AbstractPINN
                                            log_options = LogOptions(),
                                            iteration = nothing,
                                            kwargs...)
-        multioutput = typeof(chain) <: AbstractArray
+        multioutput = chain isa AbstractArray
 
         if phi === nothing
             if multioutput