Skip to content

fix calculation of PSNR(if only_in_mask) #19

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix calculation of PSNR(if only_in_mask) #19

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion nr3d_lib/graphics/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -94,7 +94,9 @@ def PSNR(x: torch.Tensor, y: torch.Tensor, mask: torch.BoolTensor=None, only_in_
if (mask is not None):
mask = mask.view(*x.shape[:-1])
if only_in_mask:
mse = ((x - y)**2)[mask].sum() / mask.sum().clip(1e-5)
# NOTE: The mask should be expanded to match the shape of x (or y); otherwise, the PSNR may be lower than expected.
mask_expanded = mask.view(*x.shape[:-1]).unsqueeze(-1).expand_as(x)
mse = ((x - y)**2)[mask_expanded].sum() / mask_expanded.sum().clip(1e-5)
else:
# NOTE: x should not be masked;
# and the convergence of mask will also affect performance here (which is expected)
Expand Down