We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
When I initialize efficient KAN with a high number of nodes, I have to wait a long time
my test code is as follows:
from kan import KAN import time start_time=time.time() model=KAN([1024,3584,3584]) print(f'Initialization time: {time.time()-start_time}')
and the output is:
Initialization time: 330.3829219341278
Why does it take so long to initialize
The text was updated successfully, but these errors were encountered:
After a single step, I found that the problem came from the curve2coeff function's torch.linalg.lstsq(), which was taking an enormous amount of time
Sorry, something went wrong.
Do you have any ways to solve the issue of slow speed?
Not yet, I only found this problem on Ubuntu servers, not on windows laptops. Maybe it has something to do with cpu performance
No branches or pull requests
When I initialize efficient KAN with a high number of nodes, I have to wait a long time
my test code is as follows:
and the output is:
Why does it take so long to initialize
The text was updated successfully, but these errors were encountered: