HomeIoT ModelsFFNet-54S-Quantized

    FFNet-54S-Quantized

    Semantic segmentation for automotive street scenes.

    FFNet-54S-Quantized is a "fuss-free network" that segments street scene images with per-pixel classes like road, sidewalk, and pedestrian. Trained on the Cityscapes dataset.

    TorchScriptTFLite
    10.2ms
    Inference Time
    2-4MB
    Memory Usage
    120NPU
    Layers

    Technical Details

    Model checkpoint:ffnet54S_dBBB_cityscapes_state_dict_quarts
    Input resolution:2048x1024
    Number of parameters:18.0M
    Model size:17.5 MB

    Applicable Scenarios

    • Automotive
    • Autonomous Driving
    • Camera

    Licenses

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

    Tags

    • quantized
      A “quantized” model can run in low or mixed precision, which can substantially reduce inference latency.
    • 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

    • QCS6490 (Proxy)
    • QCS8250 (Proxy)
    • QCS8550 (Proxy)
    • RB3 Gen 2 (Proxy)
    • RB5 (Proxy)

    Supported IoT Chipsets

    • Qualcomm® QCS6490
    • Qualcomm® QCS8250
    • Qualcomm® QCS8550