You can deploy this model and start earning money today!

qualcomm/
HRNet-W48-OCR

Name: HRNet-W48-OCR
Availability: InStock

Views

No views yet

HRNet-W48-OCR: Optimized for Qualcomm Devices

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

This is based on the implementation of HRNet-W48-OCR found here. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.

Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up to run these models on a hosted Qualcomm® device.

Getting Started

There are two ways to deploy this model on your device:

Option 1: Download Pre-Exported Models

Below are pre-exported model assets ready for deployment.

Runtime	Precision	Chipset	SDK Versions	Download
ONNX	float	Universal	QAIRT 2.45, ONNX Runtime 1.27.1	Download

For more device-specific assets and performance metrics, visit HRNet-W48-OCR on Qualcomm® AI Hub.

Option 2: Export with Custom Configurations

Use the Qualcomm® AI Hub Models Python library to compile and export the model with your own:

Custom weights (e.g., fine-tuned checkpoints)
Custom input shapes
Target device and runtime configurations

This option is ideal if you need to customize the model beyond the default configuration provided here.

See our repository for HRNet-W48-OCR on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.semantic_segmentation

Model Stats:

Input resolution: 2048x1024
Model checkpoint: hrnet_ocr_cs_8162_torch11.pth
Model size (float): 268 MB
Model size (w8a16): 70.3 MB
Number of output classes: 19
Number of parameters: 70.3M

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
HRNet-W48-OCR	ONNX	float	Snapdragon® X2 Elite	617.735 ms	32 - 32 MB	NPU
HRNet-W48-OCR	ONNX	float	Snapdragon® X Elite	988.054 ms	132 - 132 MB	NPU
HRNet-W48-OCR	ONNX	float	Snapdragon® 8 Gen 3 Mobile	802.136 ms	36 - 2306 MB	NPU
HRNet-W48-OCR	ONNX	float	Snapdragon® 8 Gen 1 Mobile	1999.906 ms	34 - 2177 MB	NPU
HRNet-W48-OCR	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	1225.897 ms	24 - 52 MB	NPU
HRNet-W48-OCR	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	1113.717 ms	0 - 135 MB	NPU
HRNet-W48-OCR	ONNX	float	Qualcomm® QCS8450	1999.906 ms	34 - 2177 MB	NPU
HRNet-W48-OCR	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	1581.21 ms	24 - 50 MB	NPU
HRNet-W48-OCR	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	988.054 ms	132 - 132 MB	NPU
HRNet-W48-OCR	ONNX	float	Qualcomm® Dragonwing™ Q-8750	686.836 ms	17 - 1136 MB	NPU
HRNet-W48-OCR	ONNX	float	Snapdragon® 8 Elite Mobile	686.836 ms	17 - 1136 MB	NPU
HRNet-W48-OCR	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	534.785 ms	13 - 1238 MB	NPU

License

The license for the original implementation of HRNet-W48-OCR can be found here.

References

Community

Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
For questions or feedback please reach out to us.

qualcomm/HRNet-W48-OCR