-
Notifications
You must be signed in to change notification settings - Fork 75
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
Questions about result reproducibility. #14
Comments
No, I didn't change the hyperparameters except that I use different GPUs for training. As you have changed the batch size, I feel that such a degree of deviation in performance is acceptable. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
@ZikangZhou Hi, I followed the script provided in your readme file to reproduce the results, but encountered two issues.
Firstly, when I set the batch size to 4 on my 3090 GPU, I encountered out of memory problem.
So I adjusted the batch size to 2, while keeping the other hyperparameters unchanged.
The resulting reproduction shows that minade=0.732 and minfde=1.294, which has a small deviation from the results reported in the paper.
However, there is a significant difference from the pre-trained model that you uploaded, where minade=1.25.
I would like to ask if the hyperparameters or other training configurations of the pre-trained model in this version have been changed?
Thank you very much.
The text was updated successfully, but these errors were encountered: