facebookresearch / facebookresearch/sam2
Achieving Higher FPS with Multiple Object Tracking
Open
- Dominant language
- Jupyter Notebook
- Stars
- 19.9k
- Forks
- 2.5k
- PR merge metrics
- No merged PRs in 30d
Description
Hey,
I am using SAM2 to analyze videos recorded at 30 FPS and currently tracking around 16 objects, achieving a tracking speed only of 2 FPS (propagating every 4 frames). I am interested in understanding the factors impacting this performance, for example the number of frames loaded for the video predictor.
Could you provide insights on optimizations or adjustments that might help improve performance? For example, would loading object IDs directly into tensors enhance processing speed? Any guidance on potential changes to reach my desired FPS would be greatly appreciated.
Dania
Contributor guide
Assessment
This issue has not been assessed yet.