Qualcomm® AI HubAI Hub

FFNet-40S

Semantic segmentation for automotive street scenes.

FFNet‑40S 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:ffnet40S_dBBB_cityscapes_state_dict_quarts
Input resolution:2048x1024
Number of output classes:19
Number of parameters:13.9M
Model size (float):53.1 MB
Model size (w8a8):13.5 MB

Applicable Scenarios

  • Automotive
  • Autonomous Driving
  • Camera

License

Model:BSD-3-CLAUSE

Tags

  • real-time

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-54S model.

FFNet-54S

Semantic segmentation for automotive street scenes.

View details for the FFNet-78S model.

FFNet-78S

Semantic segmentation for automotive street scenes.

View details for the DeepLabV3-Plus-MobileNet model.

DeepLabV3-Plus-MobileNet

Deep Convolutional Neural Network model for semantic segmentation.

Sample Appsfeaturing FFNet-40S

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