FBPINNs
FBPINNs copied to clipboard
Solve forward and inverse problems related to partial differential equations using finite basis physics-informed neural networks (FBPINNs)
Good morning, I was wondering if it would be possible to force the NN to find the solution within 0, 1 for u[0] and between 2 and 3 for u[1]...
Hi. FBPINNTrainer works without any problems, but when I tried to solve the same PDE using PINNTrainer, I got an error: INTERNAL: Failed to enqueue async memset operation: CUDA_ERROR_ILLEGAL_ADDRESS: an...
Thank you for sharing your work, it's very interesting! The new version using JAX is indeed much faster, but I'm not very familiar with it (I use PyTorch more). Recently,...
I want to know that how to use it in a irregular domain and could you provide an example. By the way,could you explain more about the following code. I...
Dear Ben, Hello, when I run the example such as 1D harmonic oscillator problem , a code error was encountered in trainers.py as following: Traceback (most recent call last): \test.py",...