HomeIoT ModelsUnet-Segmentation

    Unet-Segmentation

    Real-time segmentation optimized for mobile and edge.

    UNet is a machine learning model that produces a segmentation mask for an image. The most basic use case will label each pixel in the image as being in the foreground or the background. More advanced usage will assign a class label to each pixel.

    Qualcomm® QCS8550
    QCS8550 (Proxy)
    161ms
    Inference Time
    0-226MB
    Memory Usage
    31NPU
    Layers

    Technical Details

    Model checkpoint:unet_carvana_scale1.0_epoch2
    Input resolution:224x224
    Number of parameters:31.0M
    Model size:118 MB

    Applicable Scenarios

    • Autonomous Vehicles
    • Medical Imaging
    • Factory Quality Control

    Licenses

    Source Model:GPL-3.0
    Deployable Model:GPL-3.0

    Tags

    • backbone
      A “backbone” model is designed to extract task-agnostic representations from specific data modalities (e.g., images, text, speech). This representation can then be fine-tuned for specialized tasks.
    • 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