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

Continue training #106

Closed
vivekbharadhwajsa opened this issue Oct 4, 2021 · 4 comments
Closed

Continue training #106

vivekbharadhwajsa opened this issue Oct 4, 2021 · 4 comments

Comments

@vivekbharadhwajsa
Copy link

vivekbharadhwajsa commented Oct 4, 2021

Hello,

My training stopped after 7000 kimg and is it possible to continue training from the last kimg(where the training stopped) instead of starting the training again from 0 kimg?

Thanks

@WuZongWei6
Copy link

I am facing the same problem.

@WuZongWei6
Copy link

Hello,

My training stopped after 7000 kimg and is it possible to continue training from the last kimg(where the training stopped) instead of starting the training again from 0 kimg?

Thanks

Can you tell me how to solve it? Thanks!

@vivekbharadhwajsa
Copy link
Author

Hello,

My training stopped after 7000 kimg and is it possible to continue training from the last kimg(where the training stopped) instead of starting the training again from 0 kimg?

Thanks

Can you tell me how to solve it? Thanks!

During training command, use the "--resume" command and give the previous .pkl file as the argument

@WuZongWei6
Copy link

Hello,
My training stopped after 7000 kimg and is it possible to continue training from the last kimg(where the training stopped) instead of starting the training again from 0 kimg?
Thanks

Can you tell me how to solve it? Thanks!

During training command, use the "--resume" command and give the previous .pkl file as the argument

Thanks for your reply! I tried this method, but the kimg and tick change back to 0, and the augment also starts from zero. From the intermediate results, it seems that the network started a new training. If so, there seem to be no difference from training from scratch. Or am I misunderstanding at any step?

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