You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I have observed that the current implementation of FastVPINNs supports only one variational form of loss. Given the flexibility required for my projects, I am interested in exploring additional variational forms. Are there more options available within your implementation that perhaps I have not yet discovered?
Additionally, I have encountered some challenges while attempting to modify the variational form of the loss function. These obstacles are proving to be a significant hurdle in my progress. I would greatly appreciate any guidance or resources you could provide to assist in overcoming these issues. This support would be invaluable, especially considering the form choice available in other publicly accessible VPINN codes.
I have been examining the implementation of variational forms in FastVPINNs and noticed that the boundary terms are omitted, leaving only the integral terms within the domain. Could you please explain the rationale behind this approach?
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
I have observed that the current implementation of FastVPINNs supports only one variational form of loss. Given the flexibility required for my projects, I am interested in exploring additional variational forms. Are there more options available within your implementation that perhaps I have not yet discovered?
Additionally, I have encountered some challenges while attempting to modify the variational form of the loss function. These obstacles are proving to be a significant hurdle in my progress. I would greatly appreciate any guidance or resources you could provide to assist in overcoming these issues. This support would be invaluable, especially considering the form choice available in other publicly accessible VPINN codes.
I have been examining the implementation of variational forms in FastVPINNs and noticed that the boundary terms are omitted, leaving only the integral terms within the domain. Could you please explain the rationale behind this approach?
Beta Was this translation helpful? Give feedback.
All reactions