Neural network based solvers for partial differential equations and inverse problems :milky_way:. Implementation of physics-informed neural networks in pytorch.
Learning Rate Annealing is now available and can be activated in the fit()function. This algorithm balances the weights for initial and boundary conditions depending on the stiffness of the underlying PDE
Logger are available and can be activated in the fit()function. Logger enable automatic tracking of all loss terms and theire weights for example with Weights and Biases which is implemented yet. By implementing the Logger_Interface you can build your own loggers.
Pretraining the fit() function allows a pretraining by optimizing only on the initial condition
Callbacks its possible to write custom callbacks in order to modify the behavior in the training loop. At the moment only callbacks at the end of epochs are supported
Bugfixes
Fix the bug in the calculation of neumann and robin boundary condition
New Features
Learning Rate Annealing is now available and can be activated in the
fit()
function. This algorithm balances the weights for initial and boundary conditions depending on the stiffness of the underlying PDELogger are available and can be activated in the
fit()
function. Logger enable automatic tracking of all loss terms and theire weights for example with Weights and Biases which is implemented yet. By implementing theLogger_Interface
you can build your own loggers.Pretraining the
fit()
function allows a pretraining by optimizing only on the initial conditionCallbacks its possible to write custom callbacks in order to modify the behavior in the training loop. At the moment only callbacks at the end of epochs are supported
Bugfixes
Fix the bug in the calculation of neumann and robin boundary condition
Resolved issues