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

how many data used to train the model from scratch? #8

Open
MonolithFoundation opened this issue Dec 10, 2024 · 3 comments
Open

how many data used to train the model from scratch? #8

MonolithFoundation opened this issue Dec 10, 2024 · 3 comments

Comments

@MonolithFoundation
Copy link

how many data used to train the model from scratch?

@flymin
Copy link
Owner

flymin commented Dec 10, 2024

We only use the nuScenes dataset, which contains 700 training videos for ~20s@12fps each.

@MonolithFoundation
Copy link
Author

the generation result is good, is that able to replicate easily with only nuScens data training from scratch?

@flymin
Copy link
Owner

flymin commented Dec 10, 2024

To confirm, we only use the nuScenes data in all three stages. All the implementations are released.

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