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

Can I download partial ScanNet to train ImVoxelNet? #76

Open
Cindy0725 opened this issue Nov 24, 2023 · 4 comments
Open

Can I download partial ScanNet to train ImVoxelNet? #76

Cindy0725 opened this issue Nov 24, 2023 · 4 comments

Comments

@Cindy0725
Copy link

Hi, it's great work!

I tried to download the 1.2T full ScanNet dataset but the speed is too slow (like taking 20 days to download). Since ImvoxelNet only uses hundred images for each scene. Is it possible that we only download partial version of ScanNet and use it to train ImVoxelNet? And which partial version should I choose? Like how to choose rgb/rgbd images for each scene?

Thank you very much! Looking forward to your kind reply.

@filaPro
Copy link
Contributor

filaPro commented Nov 24, 2023

Unfotunately, we didn't fix the random seed while sampling 100 images per scene, so you can try random ones.

@Cindy0725
Copy link
Author

Thank you very much for your reply!
I will try random sampling 100 images per scene and in your opinion, will random sampling affect the performance of ImvoxelNet?

@filaPro
Copy link
Contributor

filaPro commented Nov 24, 2023

As I remember we provide the confidence interval in our paper. The randomness is less then 1%.

@Cindy0725
Copy link
Author

Okay, I will check the paper and the code. Have a nice day!

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