Skip to content
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

Total number of epochs #48

Closed
absqh opened this issue Jul 14, 2024 · 3 comments
Closed

Total number of epochs #48

absqh opened this issue Jul 14, 2024 · 3 comments

Comments

@absqh
Copy link

absqh commented Jul 14, 2024

Could you please tell me what are the approximate epochs of the three datasets in the BCD task?

@ChenHongruixuan
Copy link
Owner

Hi,

Please refer to our paper:

The batch size is set to 16. Except for the SYSU dataset, for which we set the number of training iterations to 20000, we set the number of training iterations to 50000 on the remaining four datasets.

@absqh
Copy link
Author

absqh commented Jul 14, 2024

Hello, I saw this, but most of the training settings in the paper are presented in epochs. I would like to know what the corresponding epoch is. I don't quite understand their correspondence.

@ChenHongruixuan
Copy link
Owner

ChenHongruixuan commented Jul 15, 2024

Hi,

You can get the so-called epoch number by batch size * iteration_num / training_num.

But I would like to remind you that the number of epochs I think of is the number of times the model has seen all the samples. Since we use random cropping, the model only sees part of each sample each time. So I don't think it makes much sense to keep the epoch number consistent with other work here.

Best,

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants