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

Generate custom dataset #65

Open
nfyfamr opened this issue Aug 4, 2024 · 2 comments
Open

Generate custom dataset #65

nfyfamr opened this issue Aug 4, 2024 · 2 comments

Comments

@nfyfamr
Copy link

nfyfamr commented Aug 4, 2024

Dear author, thanks for sharing the great work! I am creating a private dataset to test matching on the DKM. I tried to follow the instructions in https://github.com/Parskatt/DKM/blob/main/docs/training.md. But the d2-net generates scene info file as npz, while it seems yours use npy file. On top of the file extension, the npz file doesn't contain 'pairs' key, which is used in the training. I am wondering how you generated your scene info file. Could you share your processing code? Thanks!

@ZhouShunlong
Copy link

I also encountered this problem. Are there any good solutions?

@Parskatt
Copy link
Owner

Hi I thought I put my modifications here but maybe not. The only difference is that I save all pairs with overlap > 0 instead of an overlap matrix. This is due to the matrix being extremely sparse for lsrge scenes, so basically we save space. Regarding npy vs npy its just using np save instead of savez iirc.

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

3 participants