WisconsinAIVision/yolact_edge
A real-time instance segmentation model optimized to run on edge devices like Jetson AGX Xavier.

Velocity · 7d
+0.7
★ / day
Trend
→steady
star history
YolactEdge is a competitive instance segmentation approach designed to run on small edge devices at real-time speeds. Built with PyTorch, it achieves up to 30.8 FPS on Jetson AGX Xavier and 172.7 FPS on RTX 2080 Ti using a ResNet-101 backbone at 550x550 resolution. The project provides model weights and inference code for deploying instance segmentation on resource-constrained hardware.