MIC-DKFZ / MIC-DKFZ/nnInteractive
Inquiry Regarding Multi-Point Input
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 493
- Forks
- 59
- PR merge metrics
- No merged PRs in 30d
Description
This work is absolutely fantastic. However, I have encountered a couple of issues during usage:
-
Is it possible to input multiple points simultaneously to infer a single target? For example, can both positive and negative points be used? In the example, I only found a method for inputting a single positive point.
session.add_point_interaction(POINT_COORDINATES, include_interaction=True) -
Is it possible to input multiple points at once to predict multiple targets? While there might be cases of mutually exclusive labels, inputting multiple points concurrently typically yields better predictions—especially when assuming that each point represents a separate instance.
I look forward to your reply.
Erick
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
Start with the example call to session.add_point_interaction(POINT_COORDINATES, include_interaction=True) and trace how point prompts are represented. Determine how positive and negative points, and points for separate targets, are currently handled. Done means the supported multi-point behavior is clear and demonstrated for both requested use cases.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 25/100