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 to run inference on custom point clouds? #10

Open
anikimmel opened this issue Dec 16, 2024 · 4 comments
Open

How to run inference on custom point clouds? #10

anikimmel opened this issue Dec 16, 2024 · 4 comments

Comments

@anikimmel
Copy link

Hello!

How would I run inference on custom point clouds that I want to segment?

Thanks!

@yhyang-myron
Copy link
Member

Hi, Thanks for your interest in our work!
You can replace the coordinates and normals sampled from the mesh surface with your custom point clouds and estimated normals.

@anikimmel
Copy link
Author

Hey! Thanks for your response! Could you by any chance direct me to which script I would be using for that to fine-tune or evaluate segmentation without labels? I was trying to figure out which script I should be using to input the .xyz files and their normals.

@yhyang-myron
Copy link
Member

Hi, you need to change the code at here. And you also need to delete the parameters like "face_index" or "inverse".

@anikimmel
Copy link
Author

Generally, we want to train on an entire dataset. This command trains on a specific object:
sh scripts/train.sh -g 1 -d sampart3d -c sampart3d-trainmlp-render16views -n knight -o knight

How would we finetune the existing model on a new dataset? Which commands would we call/parameters to pass in?

Thanks!

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