AIPython★ 221⑂ 13 forksApache-2.0
aryamandarda/tamserve
Live Multi-Camera SAM Tracking
Serves multiple cameras with one SAM model per GPU, achieving 4x memory reduction and faster inference than original implementations.
// KEY FEATURES
- One SAM model per GPU handles all connected cameras simultaneously
- 4x less GPU memory with identical mask quality to original code
- Supports SAM 2, SAM3, and EdgeTAM across single or multi-GPU setups
#batching#computer-vision#edgetam#gpu#inference#model-serving#object-tracking#pytorch#sam2#segment-anything#video-segmentation
Open on GitHub →New repositories every 30 minutes
REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.
Join on Telegram