Change and visualize bounding boxes for Mask R-CNN
Open
Nobody has claimed this yet.
awaiting response
module: models
question
topic: object detection
- Dominant language
- Python
- Stars
- 17.9k
- Forks
- 7.3k
- Avg merge
- 1d 15h
- Merged PRs (30d)
- 13
Description
I'm interested in implementing rotated Mask R-CNN similar to https://github.com/mrlooi/rotated_maskrcnn.
How would I go about accessing and visualizing the bounding boxes? Any help regarding this would be highly appreciated!
Contributor guide
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
The issue points to the rotated_maskrcnn repository and asks generally about implementing rotated Mask R-CNN and visualizing bounding boxes. Start by reviewing that reference implementation and the project's existing computer-vision model and visualization entry points; done would require an agreed design and a defined implementation scope.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100