8000 HPatches Dataset in correct file format · Issue #28 · Shiaoming/ALIKE · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

HPatches Dataset in correct file format #28

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.

Sign up for GitHub

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

Jump to bottom
Open
Odin-byte opened this issue Mar 26, 2025 · 1 comment
Open

HPatches Dataset in correct file format #28

Odin-byte opened this issue Mar 26, 2025 · 1 comment

Comments

@Odin-byte
Copy link

Hey there,

I am currently trying to implement the training code for ALIKE and I was wondering where to find the HPatches Dataset used within the evaluation.
The only mirror I was able to find is this one:

https://www.kaggle.com/datasets/javidtheimmortal/hpatches

This dataset seems to have wrong file formats and folder structure as its not compatible with the Dataloader defined within the hpatches.py python script, which can be found within the training code zip.

Is there any way to get the HPatches dataset in the needed file format and filetypes?
@Odin-byte
Copy link
Author

Edit: It seems like the data format expected is not actually the HPatches dataset structure, but the HPatches-sequence dataset structure.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@Odin-byte
0