Qualcomm® AI HubAI Hub
HomeCompute ModelsFFNet-122NS-LowRes

FFNet-122NS-LowRes

Semantic segmentation for automotive street scenes.

FFNet-122NS-LowRes is a "fuss-free network" that segments street scene images with per-pixel classes like road, sidewalk, and pedestrian. Trained on the Cityscapes dataset.

Snapdragon® X Elite
7.52ms
Inference Time
6MB
Memory Usage
350NPU
Layers

Technical Details

Model checkpoint:ffnet122NS_CCC_cityscapes_state_dict_quarts_pre_down
Input resolution:1024x512
Number of parameters:32.1M
Model size:123 MB

Applicable Scenarios

  • Automotive
  • Autonomous Driving
  • Camera

Licenses

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

Supported Compute Chipsets

  • Snapdragon® X Elite