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

Questions about the code #7

Open

qsisi opened this issue Jul 12, 2022 · 0 comments

qsisi commented Jul 12, 2022 •

edited

Loading

Hello! I got several questions about the code:

DHVR/src/dhvr.py

Lines 113 to 114 in 83cede6

angle = (max_value[:3] + 0.5) * self.r_binsize

t = (max_value[3:] + 0.5) * self.t_binsize

When projecting from the 6D tensor space back to the axis-angle and the translation space, why add a 0.5 bin shift on the tensor space?

DHVR/src/dhvr.py

Lines 52 to 55 in 83cede6

    
           dup_check = torch.logical_and( 
        
               torch.all(li > self.voxel_size * 1.5, dim=1), 
        
               torch.all(lj > self.voxel_size * 1.5, dim=1), 
        
           ).cpu()

During triplets sampling, why filter out those triplets with close spatial distances (< 1.5 voxel_size)? Is it related to the training performance?

Thanks for your reply.

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