Segment images or video by class in real‑time on device.
PIDNet (Proportional‑Integral‑Derivative Network) is a real‑time semantic segmentation model based on PID controllers
Model checkpoint:PIDNet_S_Cityscapes_val.pt
Inference latency:RealTime
Input resolution:1024x2048
Number of output classes:19
Number of parameters:8.06M
Model size (float):29.1 MB
Model size (w8a8):8.02 MB
autonomous driving,medical imaging
Source Model: MIT
Deployable Model: AI-HUB-MODELS-LICENSE