facebookresearch / facebookresearch/SlowFast
Detectron model for AVA demo
Open
- Dominant language
- Python
- Stars
- 7.4k
- Forks
- 1.3k
- PR merge metrics
- No merged PRs in 30d
Description
Thank you for publishing the code for slowfast. I’m now running some video demos with the pre-trained model, I found that the detectron model used in the AVA yaml file provided in the DEMO folder is not very accurate for person detection in some of my videos.
Can you please publish the detectron model mentioned in the slowfast paper?
Contributor guide
Assessment
This issue has not been assessed yet.