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

[question] how to do single image inference? #1

Open
eisneim opened this issue Oct 29, 2024 · 1 comment
Open

[question] how to do single image inference? #1

eisneim opened this issue Oct 29, 2024 · 1 comment

Comments

@eisneim
Copy link

eisneim commented Oct 29, 2024

Hi authors of this great project! i would like to ask how to do a simple inference without preparing the Dataset listed in the README.md, i'm trying to compare this project with DrBokeh

@chinatownlittlewhite
Copy link
Collaborator

Hi authors of this great project! i would like to ask how to do a simple inference without preparing the Dataset listed in the README.md, i'm trying to compare this project with DrBokeh

Thank you for your interest in this project. Before inference, you need to obtain the depth map through Depth-Anything-V2, and separate the depth map to get the focal plane or use the segmentation model to get the subject's mask as the focal plane. We will update the data layout in the readme, and then you can directly use test_ebb.py and test_vabd.py for batch testing. Pre-trained weights and VABD datasets are coming soon.

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