FastSam-X

    Generate high quality segmentation mask on device.

    The Fast Segment Anything Model (FastSAM) is a novel, real-time CNN-based solution for the Segment Anything task. This task is designed to segment any object within an image based on various possible user interaction prompts. The model performs competitively despite significantly reduced computation, making it a practical choice for a variety of vision tasks.

    Qualcomm® QCS8550
    QCS8550 (Proxy)
    TorchScriptTFLite
    52.1ms
    Inference Time
    9-13MB
    Memory Usage
    420NPU
    Layers

    Technical Details

    Model checkpoint:fastsam-x.pt
    Inference latency:RealTime
    Input resolution:640x640
    Number of parameters:72.2M
    Model size:276 MB

    Applicable Scenarios

    • Camera
    • Photo Editing

    Licenses

    Source Model:AGPL-3.0
    Deployable Model:AGPL-3.0

    Supported IoT Devices

    • QCS8550 (Proxy)

    Supported IoT Chipsets

    • Qualcomm® QCS8550