Movenet: Optimized for Qualcomm Devices
Movenet performs pose estimation on human images.
This is based on the implementation of Movenet 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 | ONNX Runtime 1.23.0 | Download |
| ONNX | w8a16_mixed_int16 | Universal | ONNX Runtime 1.23.0 | Download |
| QNN_DLC | float | Universal | QAIRT 2.42 | Download |
| TFLITE | float | Universal | TFLite 2.17.0 | Download |
For more device-specific assets and performance metrics, visit Movenet 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 Movenet on GitHub for usage instructions.
Model Details
Model Type: Model_use_case.pose_estimation
Model Stats:
- Model checkpoint: None
- Input resolution: 192x192
- Number of parameters: 2.33M
- Model size (float): 8.91 MB
Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |
|---|---|---|---|---|---|---|
| Movenet | ONNX | w8a16_mixed_int16 | Snapdragon® X Elite | 12.485 ms | 15 - 15 MB | CPU |
| Movenet | ONNX | w8a16_mixed_int16 | Snapdragon® 8 Gen 3 Mobile | 13.131 ms | 14 - 29 MB | CPU |
| Movenet | ONNX | w8a16_mixed_int16 | Qualcomm® QCS6490 | 57.324 ms | 13 - 16 MB | CPU |
| Movenet | ONNX | w8a16_mixed_int16 | Qualcomm® QCS8550 (Proxy) | 14.479 ms | 12 - 22 MB | CPU |
| Movenet | ONNX | w8a16_mixed_int16 | Qualcomm® QCS9075 | 22.717 ms | 13 - 16 MB | CPU |
| Movenet | ONNX | w8a16_mixed_int16 | Qualcomm® QCM6690 | 28.585 ms | 15 - 24 MB | CPU |
| Movenet | ONNX | w8a16_mixed_int16 | Snapdragon® 8 Elite For Galaxy Mobile | 10.267 ms | 15 - 24 MB | CPU |
| Movenet | ONNX | w8a16_mixed_int16 | Snapdragon® 7 Gen 4 Mobile | 22.312 ms | 19 - 28 MB | CPU |
| Movenet | ONNX | w8a16_mixed_int16 | Snapdragon® 8 Elite Gen 5 Mobile | 9.227 ms | 13 - 26 MB | CPU |
License
- The license for the original implementation of Movenet 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.