Qualcomm® AI HubAI Hub

SINet

Lightweight portrait segmentation for background removal.

SINet is a machine learning model that is designed to segment people from close-up portrait images in real time.

Snapdragon® X Elite
1.35ms
Inference Time
1MB
Memory Usage
186NPU
Layers

Technical Details

Model checkpoint:SINet.pth
Input resolution:224x224
Number of parameters:91.9K
Model size:430 KB

Applicable Scenarios

  • Background replacement
  • Face removal

Licenses

Source Model:OTHER
Deployable Model:AI Model Hub License

Supported Compute Chipsets

  • Snapdragon® X Elite