Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Given points training #722

Closed
wants to merge 8 commits into from
Closed

Given points training #722

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
61c6c3c
Initial changes to ode_solve, added NNDAE to get this solver working …
Jun 27, 2023
c56922c
Added test file to commit
Jun 27, 2023
595359f
Added changes to make DAE function definitions include u, but it stil…
Jul 18, 2023
41c9084
Fixed some of the issues with problem definitions and loss function g…
Jul 26, 2023
685a688
Merge branch 'SciML:master' into nnode_training_edits
sdesai1287 Jul 26, 2023
fe9274f
New edits to DAE loss function generation, solving runs forever
Aug 14, 2023
957d20a
Merge branch 'SciML:master' into nnode_training_edits
sdesai1287 Aug 17, 2023
e253a4d
Initial commit for GivenPointsTraining
Aug 17, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions src/NeuralPDE.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,12 +51,12 @@ include("discretize.jl")
include("neural_adapter.jl")
include("advancedHMC_MCMC.jl")

export NNODE, TerminalPDEProblem, NNPDEHan, NNPDENS, NNRODE,
export NNODE, NNDAE, TerminalPDEProblem, NNPDEHan, NNPDENS, NNRODE,
KolmogorovPDEProblem, NNKolmogorov, NNStopping, ParamKolmogorovPDEProblem,
KolmogorovParamDomain, NNParamKolmogorov,
PhysicsInformedNN, discretize,
GridTraining, StochasticTraining, QuadratureTraining, QuasiRandomTraining,
WeightedIntervalTraining,
WeightedIntervalTraining, GivenPointsTraining,
build_loss_function, get_loss_function,
generate_training_sets, get_variables, get_argument, get_bounds,
get_phi, get_numeric_derivative, get_numeric_integral,
Expand Down
27 changes: 27 additions & 0 deletions src/my_test.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,27 @@

using OrdinaryDiffEq, OptimizationPolyalgorithms, Lux, OptimizationOptimJL, Test, Statistics, Plots, Optimisers

function fu(u, p, t)
[p[1] * u[1] - p[2] * u[1] * u[2], -p[3] * u[2] + p[4] * u[1] * u[2]]
end

p = [1.5, 1.0, 3.0, 1.0]
u0 = [1.0, 1.0]
prob_oop = ODEProblem{false}(fu, u0, (0.0, 3.0), p)
true_sol = solve(prob_oop, Tsit5(), saveat = 0.01)
func = Lux.σ
N = 12
chain = Lux.Chain(Lux.Dense(1, N, func), Lux.Dense(N, length(u0)))

opt = Optimisers.Adam(0.01)
dx=0.05
alg = NeuralPDE.NNODE(chain, opt, autodiff = false, strategy = NeuralPDE.GridTraining(dx))
sol = solve(prob_oop, alg, verbose=true, maxiters = 3, saveat = 0.01)

@test abs(mean(sol) - mean(true_sol)) < 0.2

# using Plots

# plot(sol)
# plot!(true_sol)
# ylims!(0,8)
Loading
Loading