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

[Question] How to load pretrained model? #346

Open
3 tasks done
qimingRen opened this issue Jul 22, 2024 · 3 comments
Open
3 tasks done

[Question] How to load pretrained model? #346

qimingRen opened this issue Jul 22, 2024 · 3 comments
Labels
enhancement New feature or request question Further information is requested

Comments

@qimingRen
Copy link

Required prerequisites

Questions

If I have already trained a model and I want to use this model as a pre-trained model for another algorithm, how should I load it?

@qimingRen qimingRen added the question Further information is requested label Jul 22, 2024
@Gaiejj
Copy link
Member

Gaiejj commented Jul 23, 2024

It is regrettable that we do not currently support this feature. This is because the test environments in Safet-Gymnasium do not seem to require it at the moment. Could you provide a specific scenario? We will consider developing support for this scenario in future versions.

@qimingRen
Copy link
Author

For example, in order to speed up the convergence of a new environment model, I might use the previously trained model as a pre-trained model for the new model. Is this feasible? I hope it can support loading the trained model for retraining.

Thank you for your selfless open source spirit and super fast response speed

@Gaiejj
Copy link
Member

Gaiejj commented Aug 5, 2024

Sorry for the late reply. We have tried to implement this feature and will open a pull request soon!

@Gaiejj Gaiejj added the enhancement New feature or request label Aug 5, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request question Further information is requested
Projects
None yet
Development

No branches or pull requests

2 participants