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

Estimated training time of UniAD and VAD on Bench2Drive-Base #51

Open
kemaloksuz opened this issue Nov 2, 2024 · 1 comment
Open

Estimated training time of UniAD and VAD on Bench2Drive-Base #51

kemaloksuz opened this issue Nov 2, 2024 · 1 comment

Comments

@kemaloksuz
Copy link

Thanks for the great work. I think you used 8xA100 to train UniAD (tiny and base) and VAD (only base) by using 1 image/GPU. Please correct me if there is a mistake in this information. Also, how long should it take to train each of these models using this setting?

@jayyoung0802
Copy link
Member

jayyoung0802 commented Nov 4, 2024

Hi @kemaloksuz , batch_size_per_gpu=1. As you train, you can see the time remaining in real time. And the details about training, you can refer to #5.

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