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.

Sign up for GitHub

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

Jump to bottom

Is it possible to retrain my best.pt file with new images? #2541

Closed
gondimjoaom opened this issue Mar 21, 2021 · 3 comments
Closed

Is it possible to retrain my best.pt file with new images? #2541

gondimjoaom opened this issue Mar 21, 2021 · 3 comments
Labels
question Further information is requested

Comments

@gondimjoaom
Copy link

❔Question

Additional context

I trained my object detector and now I have new labeled data I would like to train too. Can I take the best.pt that I have from my last finished training and make it "learn more" from the new images?
@gondimjoaom gondimjoaom added the question Further information is requested label Mar 21, 2021
@lgeuder
Copy link

lgeuder commented Mar 21, 2021

you can use your best.pt with -weights in train.py

@gondimjoaom
Copy link
Author

But in this case, if I've trained m'y best.pt with 300 epochs for example, I must put 600 (or 300 + number of desired epochs) epochs to train?

@adrianholovaty
Copy link
Contributor

See the question/answers here: #2498

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
question Further information is requested
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@adrianholovaty @gondimjoaom @lgeuder