BiseNet
Segment images or video by class in real‑time on device.
BiSeNet (Bilateral Segmentation Network) is a novel architecture designed for real‑time semantic segmentation. It addresses the challenge of balancing spatial resolution and receptive field by employing a Spatial Path to preserve high‑resolution features and a context path to capture sufficient receptive field.
Technical Details
Model checkpoint:best_dice_loss_miou_0.655.pth
Inference latency:RealTime
Input resolution:720x960
Number of parameters:12.0M
Model size:45.7 MB
Applicable Scenarios
- Self-driving cars
Licenses
Deployable Model:AI Model Hub License
Tags
- real-time
Supported Automotive Devices
- SA7255P ADP
- SA8255 (Proxy)
- SA8295P ADP
- SA8650 (Proxy)
- SA8775P ADP
Supported Automotive Chipsets
- Qualcomm® SA7255P
- Qualcomm® SA8255P (Proxy)
- Qualcomm® SA8295P
- Qualcomm® SA8650P (Proxy)
- Qualcomm® SA8775P
Related Models
See all modelsLooking for more? See models created by industry leaders.
Discover Model Makers