Qualcomm® AI HubAI Hub

HRNet-W48-OCR

Semantic segmentation in higher resolution.

HRNet‑W48‑OCR is a machine learning model that can segment images from the Cityscape dataset. It has lightweight and hardware‑efficient operations and thus delivers significant speedup on diverse hardware platforms

Not supported

This model is currently not supported on any Automotive 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:hrnet_ocr_cs_8162_torch11.pth
Input resolution:2048x1024
Number of output classes:19
Number of parameters:70.3M
Model size (float):268 MB
Model size (w8a16):70.3 MB

Applicable Scenarios

  • Automotive
  • Autonomous Driving
  • Camera

License

Model:BSD-3-CLAUSE

Tags

  • real-time

Supported Automotive Devices

  • SA7255P ADP
  • SA8255P ADP
  • SA8295P ADP
  • SA8650P ADP
  • SA8775P ADP

Supported Automotive Chipsets

  • Qualcomm® SA7255P
  • Qualcomm® SA8295P
  • Qualcomm® SA8775P

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.

View details for the DDRNet23-Slim model.

DDRNet23-Slim

Segment images or video by class in real-time on device.

Looking for more? See models created by industry leaders.

Discover Model Makers