problem with Helmholtz.ipynb, wrong result

[feima0011]

I have run your code "Helmholtz.ipynb",
the result is here

which seems to be wrong.

It is the parameter you set up is incorrent?

[Q1Zeng]

Hi, I also ran into the same problem. Did you find a fix for this issue?

[feima0011]

Hi, I also ran into the same problem. Did you find a fix for this issue?

No, I give it up.

[lrk612]

Just change the code for calculating the second derivative in loss_PDE to

u_x1 = u_x[:, [0]]
u_x2 = u_x[:, [1]]
u_xx1 = autograd.grad(u_x1, g, grad_outputs=torch.ones_like(u_x1), create_graph=True)[0][:, [0]]
u_xx2 = autograd.grad(u_x2, g, grad_outputs=torch.ones_like(u_x2), create_graph=True)[0][:, [1]]

The original code will wrongly mix the partial derivative into the Laplace term.