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

Starting off with pretrained models #613

Open
rabhishek100 opened this issue Jan 3, 2025 · 2 comments
Open

Starting off with pretrained models #613

rabhishek100 opened this issue Jan 3, 2025 · 2 comments

Comments

@rabhishek100
Copy link

Are there any pretrained models available that can be fine tuned using our own dataset for tasks like pick and place and manipulation?
@aliberts
Copy link
Collaborator

aliberts commented Jan 9, 2025

Currently it's not super easy to fine-tune pretrained policies due to several limitations in the configs design. We're addressing this in #550 and we'll keep improving usability afterwards.
In the meantime, you can have a look at examples/2_evaluate_pretrained_policy.py to get an idea of how to use (in eval) a pretrained policy but keep in mind it's going to obsolete very soon. Our pretrained policies are available on https://huggingface.co/lerobot but we'll have to retrain them with the current redesign.

@rabhishek100
Copy link
Author

Got it. Thanks!

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

No branches or pull requests
2 participants
@rabhishek100 @aliberts