microsoft / microsoft/OmniParser
How can I debug the result OmniParser?
Open
Nobody has claimed this yet.
- Dominant language
- Jupyter Notebook
- Stars
- 25.4k
- Forks
- 2.2k
- PR merge metrics
- No merged PRs in 30d
Description
Hello.
Great tool, thank you.
How can I debug the result?
I'm trying to understand why 101, 110, 115 areas appeared.
101overlaps the drag and drop ID.+ New- not have ID.1 Post- not have ID.
parsed_content_list[101]
{'type': 'icon',
'bbox': [0.6975948214530945,
0.2096961885690689,
0.7098326086997986,
0.2387903779745102],
'interactivity': True,
'content': 'Minimize',
'source': 'box_yolo_content_yolo'}
parsed_content_list[110]
{'type': 'icon',
'bbox': [0.6970685720443726,
0.26389992237091064,
0.709141194820404,
0.2959234118461609],
'interactivity': True,
'content': 'Slide',
'source': 'box_yolo_content_yolo'}
parsed_content_list[115]
{'type': 'icon',
'bbox': [0.6974940299987793,
0.3501269817352295,
0.7081704139709473,
0.37537238001823425],
'interactivity': True,
'content': 'Hide (Ctrl+Shift+F)',
'source': 'box_yolo_content_yolo'}
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
No file or test is named. Start by tracing how parsed_content_list is produced and inspect the shown entries' source and bounding boxes; confirm whether the reported areas are expected detections or a parsing error, then document the debugging path or reproduce the discrepancy.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- jupyter-notebook
- Domain
- computer-vision
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100