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.

Sign up for GitHub

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

Jump to bottom

Random seed #321

Open

kamil2oster wants to merge 4 commits into KindXiaoming:master from kamil2oster:random_seed

Contributor

kamil2oster commented Jul 11, 2024

This pull request addresses the issue with:

KAN, MultKAN and utils set the random seed to be 0, unless argument as int is provided by the user.
The arguments were changed to None as default; In this instance, the init function will set the seed to a random integer [0, 1e3], unless argument as int is provided by the user.
This way the model will allow randomness in the initialisation instead of always using 0. Similar strategies are used in pytorch or sklearn.

kamil2oster added 4 commits

July 11, 2024 11:41


          Modify KAN to use random seed, instead of 0

261b59c


          Stop LBFGS from modifying torch seed to 0

9c42ba3


          Modify MultKAN to use random seed, instead of 0

2c0a632


          Modify utils to use random seed, instead of 0

f526ed5

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet