Skip to content

Fix threshold in sam_predict #406

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
nidefawl wants to merge 2 commits into
base: Main
Choose a base branch
from
Open

Fix threshold in sam_predict #406

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2bfa33a
Fix threshold in sam_predict
nidefawl Dec 29, 2023
60cd7be
Fix size of empty mask
nidefawl Dec 30, 2023
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
25 changes: 5 additions & 20 deletions modules/impact/core.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -468,25 +468,10 @@ def sam_predict(predictor, points, plabs, bbox, threshold):

cur_masks, scores, _ = predictor.predict(point_coords=point_coords, point_labels=point_labels, box=box)

total_masks = []

selected = False
max_score = 0
for idx in range(len(scores)):
if scores[idx] > max_score:
max_score = scores[idx]
max_mask = cur_masks[idx]

if scores[idx] >= threshold:
selected = True
total_masks.append(cur_masks[idx])
else:
pass

if not selected:
total_masks.append(max_mask)

return total_masks
# take all 3 masks predict returns, or take none
if any([score >= threshold for score in scores]):
return [m for m in cur_masks]
return []


def make_sam_mask(sam_model, segs, image, detection_hint, dilation,
Expand Down Expand Up @@ -606,7 +591,7 @@ def make_sam_mask(sam_model, segs, image, detection_hint, dilation,
mask = dilate_mask(mask.cpu().numpy(), dilation)
mask = torch.from_numpy(mask)
else:
mask = torch.zeros((8, 8), dtype=torch.float32, device="cpu") # empty mask
mask = torch.zeros((image.shape[0], image.shape[1]), dtype=torch.float32, device="cpu") # empty mask

mask = utils.make_3d_mask(mask)
return mask
Expand Down