Neural network based solvers for partial differential equations and inverse problems :milky_way:. Implementation of physics-informed neural networks in pytorch.
MIT License
141
stars
46
forks
source link
Adding an opportunity too add model specific losses #17
Models like the GatedPINN uses a model specific loss in order to balance the utilization of the experts.
An option would be to give the model an attribute called loss.
In the PINN loss we can call the loss function with :
if hasattr(self.model, 'loss'):
pinn_loss = pinn_loss + model.loss
Models like the GatedPINN uses a model specific loss in order to balance the utilization of the experts. An option would be to give the model an attribute called loss.
In the PINN loss we can call the loss function with :