Qualcomm® AI HubAI Hub

FFNet-78S

Semantic segmentation for automotive street scenes.

FFNet‑78S is a "fuss‑free network" that segments street scene images with per‑pixel classes like road, sidewalk, and pedestrian. Trained on the Cityscapes dataset.

Not supported

This model is currently not supported on any Compute chipset.

To see performance metrics for this model on other chipsets, click the button below.

View for other chipsets
Model RepositoryHugging FaceResearch Paper

Technical Details

Model checkpoint:ffnet78S_dBBB_cityscapes_state_dict_quarts
Input resolution:2048x1024
Number of output classes:19
Number of parameters:27.5M
Model size (float):105 MB
Model size (w8a8):26.7 MB

Applicable Scenarios

  • Automotive
  • Autonomous Driving
  • Camera

License

Model:BSD-3-CLAUSE

Supported Compute Devices

  • Snapdragon X Elite CRD
  • Snapdragon X Plus 8-Core CRD
  • Snapdragon X2 Elite CRD

Supported Compute Chipsets

  • Snapdragon® X Elite
  • Snapdragon® X Plus 8-Core
  • Snapdragon® X2 Elite

Related Models

See all models
View details for the FFNet-40S model.

FFNet-40S

Semantic segmentation for automotive street scenes.

View details for the FFNet-54S model.

FFNet-54S

Semantic segmentation for automotive street scenes.

View details for the Unet-Segmentation model.

Unet-Segmentation

Real-time segmentation optimized for mobile and edge.

Sample Appsfeaturing FFNet-78S

See all sample apps
View details for the Semantic Segmentation Android app.

Semantic Segmentation Android

Learn real-time image processing with TFLite and OpenCV

Looking for more? See models created by industry leaders.

Discover Model Makers