facebookresearch / facebookresearch/sam2

About prompts in training

Open
#662 0 comments 0 reactions 0 assignees View on GitHub
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

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.