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 prepare training data? #3

Open
chaoer opened this issue Jun 26, 2018 · 2 comments
Open

How to prepare training data? #3

chaoer opened this issue Jun 26, 2018 · 2 comments

Comments

@chaoer
Copy link

chaoer commented Jun 26, 2018

Hi,

I was stuck when trying to train with hsp for some new things.
I had got the *.obj and *mtl file. But I don't know how to convert these files to the format you used.

Could you please share me the scripts to convert the file format?

Sincerely.

@chaene
Copy link
Owner

chaene commented Jul 2, 2018

Hi,

We have not released the code to convert the data. Unfortunately it is not a nice easy to use piece of software that I can easily release. We did release the converted ShapeNet data. You can follow this data to see what the format should be.

Best,
Christian

@chaoer
Copy link
Author

chaoer commented Jul 2, 2018

@chaene

Thanks for your kindly reply.

Actually, I want to use some new samples (create by myself using SFM) to do the training work. So, I need to figure out how to convert the obj to the files under modelBlocked{Voxel, Pyramid}256.

I look inside these mat files, but did not know what it stores. If it is convenient, could you please tell me what's the meaning of the data stored in the mat file? For example, the b1 vector. Maybe, I could try to write some code to do this conversion.

Thanks.

Sincerely,
Jianan He

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