facebookresearch / facebookresearch/sam2
sam2 gave the complement of the target object
Open
- Dominant language
- Jupyter Notebook
- Stars
- 19.9k
- Forks
- 2.5k
- PR merge metrics
- No merged PRs in 30d
Description
Hi! I am feeding bounding box to `SAM2ImagePredictor`, but for this specific image, it gives the exact complement of the target object (human). This frame was taken from a video, and all the images before this frame works fine. I was wondering if anyone has any insights into why this might be happening? Thank!
for reference, this is a similar frame which works fine
Contributor guide
Assessment
This issue has not been assessed yet.