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.

    Qualcomm® QCS8550
    QCS8550 (Proxy)
    1.82ms
    Inference Time
    0-2MB
    Memory Usage
    240NPU
    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 IoT Devices

    • QCS8550 (Proxy)

    Supported IoT Chipsets

    • Qualcomm® QCS8550