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

Use of project #31

Closed

zs001122 opened this issue May 10, 2024 · 1 comment

zs001122 commented May 10, 2024

Hello! How can I apply my own data

Collaborator

TheProjectsGuy commented May 11, 2024

Thanks for taking interest in our work. I guess you want to apply our method on your own dataset. There are multiple interpretations of this question

Inference on custom dataset (most common): You just want global descriptors using one of the AnyLoc domains (vocabulary). I suggest using torch.hub model for this. Refer to Releasing the model on torch.hub? #11 (comment) for more on this.
Custom vocabulary: You want to train anyloc from scratch (fit VLAD descriptors) on your own dataset. I'd suggest looking at this: vlad cluster center for custom dataset #22 (comment)

You can refer to this comment for more information on "vocabulary": #26 (comment)

TheProjectsGuy mentioned this issue

Downloading cache.zip #35

Closed

oravus closed this as completed

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment