HomeIoT ModelsFCN-ResNet50

    FCN-ResNet50

    Fully-convolutional network model for image segmentation.

    FCN_ResNet50 is a machine learning model that can segment images from the COCO dataset. It uses ResNet50 as a backbone.

    Qualcomm® QCS8550
    QCS8550 (Proxy)
    8.53ms
    Inference Time
    4-6MB
    Memory Usage
    84NPU
    Layers

    Technical Details

    Model checkpoint:COCO_WITH_VOC_LABELS_V1
    Input resolution:224x224
    Number of parameters:32.9M
    Model size:126 MB

    Applicable Scenarios

    • Anomaly Detection
    • Inventory Management

    Licenses

    Source Model:BSD-3-CLAUSE
    Deployable Model:AI Model Hub License

    Supported IoT Devices

    • QCS8550 (Proxy)

    Supported IoT Chipsets

    • Qualcomm® QCS8550