facebookresearch / facebookresearch/sam2
Does incomplete labeling affect SAM2 training?
Open
- Dominant language
- Jupyter Notebook
- Stars
- 19.9k
- Forks
- 2.5k
- PR merge metrics
- No merged PRs in 30d
Description
I have some images with a lot of instances (>100) for each. I am wondering if I labeled only some of the instances, will the training be affected. I noticed that bounding boxes can be used as prompts in the training. Does this mean only information in a bounding box
is used when predict a single mask? If so, other part of image will not affect the training?
Contributor guide
Assessment
This issue has not been assessed yet.