-
Notifications
You must be signed in to change notification settings - Fork 10
Issues: CommissarMa/MCNN-pytorch
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
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
您好，可以提供下权重文件吗，我发现我在我的显卡上batchsize调为1以上的数字会报错，只能batchsize为1训练，但是很慢。
#11
opened Jul 29, 2021 by
wong1998
Hi! I have a question, these are so many epochs to run so that i can't work it out in one time. If i need to save the model, should i save the min_mae epoch' model or the newest(break point) epoch.And,in the next time,which one(best one?or break one?) should i load to continue train.Hoping to get your help,Thx
#8
opened Apr 11, 2020 by
simonchance
ProTip!
no:milestone will show everything without a milestone.