TensorDiffEq
TensorDiffEq copied to clipboard
tensordiffeq
Efficient and Scalable Physics-Informed Deep Learning and Scientific Machine Learning on top of Tensorflow for multi-worker distributed computing
Is there a way to generate an array of the loss printed in terminal during iterations? For the purposes of plotting the loss over the iterations?
Thank you for the great contribution! I'm trying to extend the 1D example problems to 2D, but I want to make sure my changes are in the correct place: 1....
Hello @levimcclenny and thanks for recommending this library! I have modified the 1D burger example to be in 2D, but I did not get good comparison results. Any suggestions? ```...
Dear @levimcclenny, Have you considered in adapt TensorDiffEq to be deterministic? In the way the code is implemented, we can find two sources of randomness: - The function `Domain.generate_collocation_points` has...
Heterogenous heat conduction problem works when implemented using baseline PINN code but not TDQ. Opening this issue for internal tracking.
Hi, How can I apply neumann or initial velocity conditions in Sa-PINN solver? For example: U_t(0,x) = 0 or h(x)
Thank you for sharing this great work. I am reading the script "TensorDiffEq/tensordiffeq/models.py". In line 208 and 209, those two values, self.isAdaptive and self.dist, cannot be true at the same...
Metadata
Owner
Metadata
Efficient and Scalable Physics-Informed Deep Learning and Scientific Machine Learning on top of Tensorflow for multi-worker distributed computing