HomeIoT ModelsQuickSRNetMedium-Quantized

    QuickSRNetMedium-Quantized

    Upscale images and remove image noise.

    QuickSRNet Medium is designed for upscaling images on mobile platforms to sharpen in real-time.

    TorchScriptTFLite
    1.40ms
    Inference Time
    0-2MB
    Memory Usage
    16NPU
    3CPU
    Layers

    Technical Details

    Model checkpoint:quicksrnet_medium_4x_checkpoint_int8
    Input resolution:128x128
    Number of parameters:61.0K
    Model size:244 KB

    Applicable Scenarios

    • Virtual Real Estate Tours
    • Gaming
    • ARVR

    Licenses

    Source Model:OTHER
    Deployable Model:AI Model Hub License

    Tags

    • quantized
      A “quantized” model can run in low or mixed precision, which can substantially reduce inference latency.

    Supported IoT Devices

    • QCS6490 (Proxy)
    • QCS8250 (Proxy)
    • QCS8550 (Proxy)
    • RB3 Gen 2 (Proxy)
    • RB5 (Proxy)

    Supported IoT Chipsets

    • Qualcomm® QCS6490
    • Qualcomm® QCS8250
    • Qualcomm® QCS8550