Skip to content

Update multistage-diagram-segmentation preprocessor #1181

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

Merged
jeffbl merged 1 commit into from
Nov 25, 2025
Merged

Update multistage-diagram-segmentation preprocessor #1181

Show file tree
Hide file tree
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
2 changes: 2 additions & 0 deletions utils/llm/prompts.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -142,6 +142,8 @@
Output a only JSON list of bounding boxes where each entry contains
the 2D bounding box in the key "box_2d",
and the stage name in the key "label".
Include in the bounding boxes only the illustrations of the objects themselves,
not any surrounding text or arrows.

"""

Expand Down
21 changes: 19 additions & 2 deletions utils/segmentation/sam_processor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -136,8 +136,25 @@ def segment_with_boxes(
)
continue

logging.pii(f"Processing bounding box for label: '{label}'")
bboxes.append(bbox)
logging.pii(
f"Processing bounding box for label: '{label}' "
f"(normalized coords: {bbox})"
)

# Convert normalized coordinates (0-1000) received from Qwen 3
# to pixel coordinates
bbox_pixels = [
(bbox[0] / 1000.0) * width,
(bbox[1] / 1000.0) * height,
(bbox[2] / 1000.0) * width,
(bbox[3] / 1000.0) * height
]

logging.pii(
f"Converted to pixel coords: {bbox_pixels}"
)

bboxes.append(bbox_pixels)
labels.append(label)

if not bboxes:
Expand Down