LiteHRNet: Optimized for Qualcomm Devices
LiteHRNet is a machine learning model that detects human pose and returns a location and confidence for each of 17 joints.
This is based on the implementation of LiteHRNet 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 2.51, ONNX Runtime 1.30.0 | Download |
| QNN_DLC | float | Universal | QAIRT 2.51 | Download |
| TFLITE | float | Universal | QAIRT 2.51 | Download |
For more device-specific assets and performance metrics, visit LiteHRNet 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 LiteHRNet on GitHub for usage instructions.
Model Details
Model Type: Model_use_case.pose_estimation
Model Stats:
- Input resolution: 256x192
- Model size (float): 4.49 MB
- Number of parameters: 1.11M
Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |
|---|---|---|---|---|---|---|
| LiteHRNet | ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 1.968 ms | 0 - 106 MB | NPU |
| LiteHRNet | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.215 ms | 0 - 105 MB | NPU |
| LiteHRNet | ONNX | float | Snapdragon® X2 Elite | 2.069 ms | 2 - 2 MB | NPU |
| LiteHRNet | ONNX | float | Snapdragon® X Elite | 4.499 ms | 6 - 6 MB | NPU |
| LiteHRNet | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 2.986 ms | 0 - 125 MB | NPU |
| LiteHRNet | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 5.164 ms | 1 - 127 MB | NPU |
| LiteHRNet | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 3.688 ms | 1 - 5 MB | NPU |
| LiteHRNet | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.229 ms | 0 - 8 MB | NPU |
| LiteHRNet | ONNX | float | Qualcomm® QCS8450 | 5.164 ms | 1 - 127 MB | NPU |
| LiteHRNet | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 4.404 ms | 1 - 4 MB | NPU |
| LiteHRNet | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 4.499 ms | 6 - 6 MB | NPU |
| LiteHRNet | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 2.215 ms | 0 - 105 MB | NPU |
| LiteHRNet | ONNX | float | Snapdragon® 8 Elite Extreme Gen 6 Mobile | 1.778 ms | 1 - 103 MB | NPU |
| LiteHRNet | ONNX | float | Snapdragon® 8 Elite Gen 6 Mobile | 2.095 ms | 0 - 101 MB | NPU |
| LiteHRNet | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 1.826 ms | 1 - 90 MB | NPU |
| LiteHRNet | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.118 ms | 1 - 91 MB | NPU |
| LiteHRNet | QNN_DLC | float | Snapdragon® X2 Elite | 2.218 ms | 1 - 1 MB | NPU |
| LiteHRNet | QNN_DLC | float | Snapdragon® X Elite | 4.515 ms | 1 - 1 MB | NPU |
| LiteHRNet | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.395 ms | 0 - 100 MB | NPU |
| LiteHRNet | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 5.061 ms | 0 - 108 MB | NPU |
| LiteHRNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 3.493 ms | 1 - 4 MB | NPU |
| LiteHRNet | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.067 ms | 1 - 2 MB | NPU |
| LiteHRNet | QNN_DLC | float | Qualcomm® QCS8450 | 5.061 ms | 0 - 108 MB | NPU |
| LiteHRNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 4.37 ms | 1 - 4 MB | NPU |
| LiteHRNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 4.515 ms | 1 - 1 MB | NPU |
| LiteHRNet | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 2.118 ms | 1 - 91 MB | NPU |
| LiteHRNet | QNN_DLC | float | Qualcomm® SA8295P | 5.409 ms | 1 - 85 MB | NPU |
| LiteHRNet | QNN_DLC | float | Snapdragon® 8 Elite Extreme Gen 6 Mobile | 1.716 ms | 0 - 85 MB | NPU |
| LiteHRNet | QNN_DLC | float | Snapdragon® 8 Elite Gen 6 Mobile | 2.01 ms | 0 - 85 MB | NPU |
| LiteHRNet | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 1.536 ms | 0 - 81 MB | NPU |
| LiteHRNet | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.709 ms | 0 - 85 MB | NPU |
| LiteHRNet | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 2.673 ms | 0 - 146 MB | NPU |
| LiteHRNet | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 3.957 ms | 1 - 103 MB | NPU |
| LiteHRNet | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 3.128 ms | 1 - 12 MB | NPU |
| LiteHRNet | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 3.353 ms | 0 - 2 MB | NPU |
| LiteHRNet | TFLITE | float | Qualcomm® SA8775P | 4.346 ms | 1 - 81 MB | NPU |
| LiteHRNet | TFLITE | float | Qualcomm® SA8650P | 4.346 ms | 1 - 81 MB | NPU |
| LiteHRNet | TFLITE | float | Qualcomm® SA8255P | 4.346 ms | 1 - 81 MB | NPU |
| LiteHRNet | TFLITE | float | Qualcomm® QCS8450 | 3.957 ms | 1 - 103 MB | NPU |
| LiteHRNet | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 3.731 ms | 1 - 12 MB | NPU |
| LiteHRNet | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 1.709 ms | 0 - 85 MB | NPU |
| LiteHRNet | TFLITE | float | Qualcomm® SA7255P | 20.985 ms | 4 - 17 MB | CPU |
| LiteHRNet | TFLITE | float | Qualcomm® SA8295P | 4.787 ms | 1 - 82 MB | NPU |
| LiteHRNet | TFLITE | float | Snapdragon® 8 Elite Extreme Gen 6 Mobile | 1.427 ms | 0 - 83 MB | NPU |
| LiteHRNet | TFLITE | float | Snapdragon® 8 Elite Gen 6 Mobile | 1.653 ms | 0 - 84 MB | NPU |
License
- The license for the original implementation of LiteHRNet 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.
