Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation
Paper • 1909.11065 • Published
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 1.25.0 | 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:
- 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
Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |
|---|---|---|---|---|---|---|
| HRNet-W48-OCR | ONNX | float | Snapdragon® X2 Elite | 616.845 ms | 33 - 33 MB | NPU |
| HRNet-W48-OCR | ONNX | float | Snapdragon® X Elite | 987.152 ms | 132 - 132 MB | NPU |
| HRNet-W48-OCR | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 801.276 ms | 36 - 2302 MB | NPU |
| HRNet-W48-OCR | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 2032.074 ms | 32 - 2173 MB | NPU |
| HRNet-W48-OCR | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1096.947 ms | 0 - 3 MB | NPU |
| HRNet-W48-OCR | ONNX | float | Qualcomm® QCS8450 | 2032.074 ms | 32 - 2173 MB | NPU |
| HRNet-W48-OCR | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 534.089 ms | 13 - 1227 MB | NPU |
| HRNet-W48-OCR | ONNX | float | Snapdragon® 8 Elite Mobile | 681.911 ms | 12 - 1133 MB | NPU |
| HRNet-W48-OCR | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 681.911 ms | 12 - 1133 MB | NPU |
| HRNet-W48-OCR | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 987.152 ms | 132 - 132 MB | NPU |
| HRNet-W48-OCR | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 1568.909 ms | 24 - 93 MB | NPU |
License
- The license for the original implementation of HRNet-W48-OCR can be found here.
References
- Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation
- Source Model Implementation
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.