Lu Lu
Not sure what the problem is. For this type of complex problem, it is usually easier to start with a simplified 1D case.
`model.predict` cannot work with `PDEOperatorCartesianProd` yet. It is not a bug, but needs more code implementation. You may use other numerical methods to get the error now.
> Can PDEOperatorCartesianProd work with MIONetCartesianProd out-of-the-box? No. You need to implement your version.
Do you use dropbox to prevent overfitting?
I am curious how useful it is. In general, I found dropout is not that useful, and L1/L2 regularization seems good enough.
Yes, dropout is useful for UQ. How do you implement DeepONet UQ?
In fact, we have this callback https://deepxde.readthedocs.io/en/latest/modules/deepxde.html#deepxde.callbacks.DropoutUncertainty . Does this work for your case?
> My question is that why both outputs have the same shape since their initial and boundary conditions are different? Better explanation: consider there are two boundary conditions and two...
We are working on this type of problem and will publish the paper soon.
Good question. But I am not sure if it is OK to do this.