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.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We鈥檒l occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Faster implementation of torchvision.ops.boxes::masks_to_boxes #8194

Open
wants to merge 4 commits into
base: main
Choose a base branch
from
Open

Faster implementation of torchvision.ops.boxes::masks_to_boxes #8194

Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
8b0daac
Fixes #8184
atharvas Jan 3, 2024
a4e4278
Update to #8194
atharvas Jan 15, 2024
24fedf7
Merge branch 'main' into enhancement/masks_to_boxes
atharvas Jan 23, 2024
2a4f9ab
Merge branch 'main' into enhancement/masks_to_boxes
atharvas Jan 29, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
15 changes: 7 additions & 8 deletions torchvision/ops/boxes.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -402,16 +402,15 @@ def masks_to_boxes(masks: torch.Tensor) -> torch.Tensor:
if masks.numel() == 0:
return torch.zeros((0, 4), device=masks.device, dtype=torch.float)

n = masks.shape[0]
non_zero_ys = torch.any(masks, axis=1).float()
non_zero_xs = torch.any(masks, axis=2).float()

bounding_boxes = torch.zeros((n, 4), device=masks.device, dtype=torch.float)
y1 = non_zero_ys.argmax(dim=1)
x1 = non_zero_xs.argmax(dim=1)

for index, mask in enumerate(masks):
y, x = torch.where(mask != 0)
y2 = (masks.shape[1] - 1) - non_zero_ys.flip(dims=[1]).argmax(dim=1)
x2 = (masks.shape[2] - 1) - non_zero_xs.flip(dims=[1]).argmax(dim=1)

bounding_boxes[index, 0] = torch.min(x)
bounding_boxes[index, 1] = torch.min(y)
bounding_boxes[index, 2] = torch.max(x)
bounding_boxes[index, 3] = torch.max(y)
bounding_boxes = torch.stack((x1, y1, x2, y2), dim=1).float()

return bounding_boxes