search

maziarraissi / PINNs

Physics Informed Deep Learning: Data-driven Solutions and Discovery of Nonlinear Partial Differential Equations
https://maziarraissi.github.io/PINNs
MIT License
3.73k stars 1.25k forks source link

Faster response #44

Open amiralizadeh1 opened 1 year ago

amiralizadeh1 commented 1 year ago

How can I get a faster result from the code? I don't want anything accurate so 200000 iterations on the Navier-Stokes PDE is too much for me. I changed it to 10000, but the code keeps on running without showing the iteration count, which is strange.

amiralizadeh1 commented 1 year ago

this is the same with KdV! when the iteration count finishes, the code still runs (showing the loss value only) without printing the final results. there is a savefig() method at the end but it never leaves the training loop to reach it ...

Liqian0506 commented 1 year ago

you need to change the max iteritation of the LBFGSB optimizer