facebookresearch / facebookresearch/sam2
About prompts in training
Open
- Dominant language
- Jupyter Notebook
- Stars
- 19.9k
- Forks
- 2.5k
- PR merge metrics
- No merged PRs in 30d
Description
Hello, about training, I have 2 questions: 1) If I want to feed both point and bbox prompts to fine-tune SAM2, should I split those 2 prompts to different training batch? i. e. In iteration k, I feed points as prompts, while in iteration k+1, I feed bboxes as prompts? 2) For one instance, could I feed multi-points as prompts?
Thanks sincerely for responding.
Contributor guide
Assessment
This issue has not been assessed yet.