-
Notifications
You must be signed in to change notification settings - Fork 281
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
Better random init of factorized tensors #521
Comments
Merged
I had a look at your code @JeanKossaifi, if I got it correctly its simply a matter of scaling the standard deviation with the rank and the order; seems like we could indeed very easily have this is pure tensorly code without any issue. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
I wrote a better init in TensorLy-Torch) we should probably bring it in at some point, it allows the reconstruction to have zero mean and given standard deviation.
The text was updated successfully, but these errors were encountered: