-
Notifications
You must be signed in to change notification settings - Fork 19
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
parameter #10
Comments
Hi, reducing the batch size will change the performance and may reduce the results. I have never met this situation before and have no ideas about how to modify it without changing performance. You can run some experiments to select the best parameters for your specific memory requirements. It is possible to simply double the —test_every to keep the total iterations number unchanged but again there is no guarantee to reproduce the results. |
thank you
…------------------ 原始邮件 ------------------
发件人: ***@***.***>;
发送时间: 2021年9月8日(星期三) 晚上8:42
收件人: ***@***.***>;
抄送: ***@***.***>; ***@***.***>;
主题: Re: [HarukiYqM/Non-Local-Sparse-Attention] parameter (#10)
Hi, reducing the batch size will change the performance and may reduce the results.
It is possible to simply double the —test_every to keep the total iterations number unchanged but again there is no guarantee to reproduce the results.
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub, or unsubscribe.
Triage notifications on the go with GitHub Mobile for iOS or Android.
|
I want to set the value of --batch_size to 8.How do I set the value of --test_every and --epochs because of the limitation of GPU'S memory.
thank you
The text was updated successfully, but these errors were encountered: