Qualcomm® AI HubAI Hub

    HomeIoT ModelsDETR-ResNet50

    DETR-ResNet50

    Transformer based object detector with ResNet50 backbone.

    DETR is a machine learning model that can detect objects (trained on COCO dataset).

    Qualcomm® QCS8550
    QCS8550 (Proxy)
    TorchScriptTFLite
    38.9ms
    Inference Time
    1-8MB
    Memory Usage
    842NPU
    2GPU
    Layers
    See more metrics
    Model RepositoryHugging FaceResearch Paper

    Technical Details

    Model checkpoint:ResNet50
    Input resolution:480x480
    Number of parameters:41.3M
    Model size:158 MB

    Applicable Scenarios

    • Factory Automation
    • Robotic Navigation
    • Camera

    Licenses

    Source Model:APACHE-2.0
    Deployable Model:AI Model Hub License

    Supported IoT Devices

    • QCS8550 (Proxy)

    Supported IoT Chipsets

    • Qualcomm® QCS8550