Qualcomm® AI HubAI Hub

    HomeIoT ModelsDDRNet23-Slim

    DDRNet23-Slim

    Segment images or video by class in real-time on device.

    DDRNet23Slim is a machine learning model that segments an image into semantic classes, specifically designed for road-based scenes. It is designed for the application of self-driving cars.

    Qualcomm® QCS8550
    QCS8550 (Proxy)
    TorchScriptTFLite
    6.68ms
    Inference Time
    1-3MB
    Memory Usage
    131NPU
    Layers
    See more metrics
    Model RepositoryHugging FaceResearch Paper

    Technical Details

    Model checkpoint:DDRNet23s_imagenet.pth
    Inference latency:RealTime
    Input resolution:2048x1024
    Number of parameters:5.69M
    Model size:21.7 MB

    Applicable Scenarios

    • Self-driving cars

    Licenses

    Source Model:MIT
    Deployable Model:AI Model Hub License

    Tags

    • real-time
      A “real-time” model can typically achieve 5-60 predictions per second. This translates to latency ranging up to 200 ms per prediction.

    Supported IoT Devices

    • QCS8550 (Proxy)

    Supported IoT Chipsets

    • Qualcomm® QCS8550