Objects as Points
Paper • 1904.07850 • Published
CenterNet-Pose: Optimized for Qualcomm Devices
CenterNet-Pose 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 CenterNet-Pose 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 |
|---|---|---|---|---|
| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.42, ONNX Runtime 1.24.1 | Download |
| PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | QAIRT 2.42, ONNX Runtime 1.24.1 | Download |
| PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | QAIRT 2.42, ONNX Runtime 1.24.1 | Download |
| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.42, ONNX Runtime 1.24.1 | Download |
| PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8550 (Proxy) | QAIRT 2.42, ONNX Runtime 1.24.1 | Download |
| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | QAIRT 2.42, ONNX Runtime 1.24.1 | Download |
| PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS9075 | QAIRT 2.42, ONNX Runtime 1.24.1 | Download |
| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.43 | Download |
| QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | QAIRT 2.43 | Download |
| QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | QAIRT 2.43 | Download |
| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.43 | Download |
| QNN_CONTEXT_BINARY | float | Qualcomm® QCS8550 (Proxy) | QAIRT 2.43 | Download |
| QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P | QAIRT 2.43 | Download |
| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite For Galaxy Mobile | QAIRT 2.43 | Download |
| QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | QAIRT 2.43 | Download |
| QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | QAIRT 2.43 | Download |
| QNN_CONTEXT_BINARY | float | Qualcomm® QCS9075 | QAIRT 2.43 | Download |
| QNN_CONTEXT_BINARY | float | Qualcomm® QCS8450 (Proxy) | QAIRT 2.43 | Download |
For more device-specific assets and performance metrics, visit CenterNet-Pose 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 CenterNet-Pose on GitHub for usage instructions.
Model Details
Model Type: Model_use_case.pose_estimation
Model Stats:
- Model checkpoint: multi_pose_dla_3x.pth
- Input resolution: 1 x 3 x 512 x 512
- Number of parameters: 20.6M
- Model size: 57.8 MB
Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |
|---|---|---|---|---|---|---|
| CenterNet-Pose | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 27.212 ms | 3 - 13 MB | NPU |
| CenterNet-Pose | PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | 27.759 ms | 44 - 44 MB | NPU |
| CenterNet-Pose | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | 60.546 ms | 43 - 43 MB | NPU |
| CenterNet-Pose | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | 39.044 ms | 3 - 10 MB | NPU |
| CenterNet-Pose | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8550 (Proxy) | 55.251 ms | 0 - 49 MB | NPU |
| CenterNet-Pose | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS9075 | 59.23 ms | 3 - 6 MB | NPU |
| CenterNet-Pose | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 30.157 ms | 4 - 10 MB | NPU |
| CenterNet-Pose | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | 26.903 ms | 1 - 11 MB | NPU |
| CenterNet-Pose | QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | 28.089 ms | 1 - 1 MB | NPU |
| CenterNet-Pose | QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | 58.106 ms | 1 - 1 MB | NPU |
| CenterNet-Pose | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | 38.997 ms | 1 - 8 MB | NPU |
| CenterNet-Pose | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8275 (Proxy) | 104.8 ms | 1 - 9 MB | NPU |
| CenterNet-Pose | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8550 (Proxy) | 56.289 ms | 1 - 2 MB | NPU |
| CenterNet-Pose | QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P | 58.825 ms | 1 - 10 MB | NPU |
| CenterNet-Pose | QNN_CONTEXT_BINARY | float | Qualcomm® QCS9075 | 60.09 ms | 1 - 4 MB | NPU |
| CenterNet-Pose | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8450 (Proxy) | 91.928 ms | 1 - 11 MB | NPU |
| CenterNet-Pose | QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | 104.8 ms | 1 - 9 MB | NPU |
| CenterNet-Pose | QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | 77.352 ms | 0 - 5 MB | NPU |
| CenterNet-Pose | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite For Galaxy Mobile | 30.986 ms | 1 - 10 MB | NPU |
License
- The license for the original implementation of CenterNet-Pose 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.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support