New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Additional parameters for 3d Poisson's equation for electrostatic potential computation #273
Comments
You can specify the range when you define the geometry https://deepxde.readthedocs.io/en/latest/modules/deepxde.geometry.html#deepxde.geometry.geometry_nd.Hypercube |
Thank you! I appreciate your taking time to help me. Now I understand that the geometry can refer to more than the physical geometry of the PDE. I have modified my program to try to implement this but I'm getting an error which indicates that I don't have it quite right:
|
You should use Hypercube |
NotImplementedError: Hypercube.random_boundary_points to be implemented |
Ah, yeah, the sampling on the boundary of a hypercube has not been implemented yet. You can set 'num_boundary=0' and manually generate the points on the boundary and then pass them using 'anchors'. |
@harshil-patel-code I wasn't able to get this working and ended up using Julia's SciML suite of tools instead. The above code is basically as far as I got. Sorry. |
Thanks @troyrock for your reply. Hi @lululxvi, I have developed the missing random_boundary_points function for Hypercube. I have tested it on my problem. It works fine. Feel free to include it in the repo. If you like, I can send merge request.
|
@harshil-patel-code Great. Feel free to send a pull request. |
I'm trying to model a the electrostatic potential in a 3D volume with 3 electrodes on the boundary. I would like to include the voltage of the electrodes as parameters to the model so that I can quickly produce the potential in the volume for a variety of different values of voltages. Is there a way to specify the range over which I would like to have the model valid for? In this example, I would like to try to develop a model for values between -1 an 1. The input values to the neural network are: x, y, z, v_left, v_middle, v_right.
Here are some code snippets:
Thank you.
The text was updated successfully, but these errors were encountered: