OpenPose: Optimized for Mobile Deployment
Human pose estimation
OpenPose is a machine learning model that estimates body and hand pose in an image and returns location and confidence for each of 19 joints.
This model is an implementation of OpenPose found here.
More details on model performance accross various devices, can be found here.
Model Details
- Model Type: Pose estimation
- Model Stats:
- Model checkpoint: body_pose_model.pth
- Input resolution: 240x320
- Number of parameters: 52.3M
- Model size: 200 MB
Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model |
---|---|---|---|---|---|---|---|---|
OpenPose | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 11.709 ms | 0 - 2 MB | FP16 | NPU | -- |
OpenPose | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 11.889 ms | 1 - 215 MB | FP16 | NPU | -- |
OpenPose | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 11.986 ms | 0 - 114 MB | FP16 | NPU | -- |
OpenPose | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 8.706 ms | 0 - 39 MB | FP16 | NPU | -- |
OpenPose | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 8.756 ms | 1 - 20 MB | FP16 | NPU | -- |
OpenPose | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 8.805 ms | 0 - 44 MB | FP16 | NPU | -- |
OpenPose | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 8.656 ms | 0 - 23 MB | FP16 | NPU | -- |
OpenPose | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 8.705 ms | 0 - 14 MB | FP16 | NPU | -- |
OpenPose | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 7.157 ms | 1 - 27 MB | FP16 | NPU | -- |
OpenPose | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 11.645 ms | 0 - 2 MB | FP16 | NPU | -- |
OpenPose | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 12.061 ms | 1 - 2 MB | FP16 | NPU | -- |
OpenPose | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 11.745 ms | 0 - 8 MB | FP16 | NPU | -- |
OpenPose | SA8255 (Proxy) | SA8255P Proxy | QNN | 12.102 ms | 1 - 2 MB | FP16 | NPU | -- |
OpenPose | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 11.812 ms | 0 - 2 MB | FP16 | NPU | -- |
OpenPose | SA8775 (Proxy) | SA8775P Proxy | QNN | 12.119 ms | 1 - 2 MB | FP16 | NPU | -- |
OpenPose | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 11.762 ms | 0 - 2 MB | FP16 | NPU | -- |
OpenPose | SA8650 (Proxy) | SA8650P Proxy | QNN | 12.129 ms | 0 - 2 MB | FP16 | NPU | -- |
OpenPose | SA8295P ADP | SA8295P | TFLITE | 26.6 ms | 0 - 23 MB | FP16 | NPU | -- |
OpenPose | SA8295P ADP | SA8295P | QNN | 25.836 ms | 1 - 6 MB | FP16 | NPU | -- |
OpenPose | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 23.378 ms | 0 - 41 MB | FP16 | NPU | -- |
OpenPose | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 23.617 ms | 1 - 18 MB | FP16 | NPU | -- |
OpenPose | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 12.691 ms | 1 - 1 MB | FP16 | NPU | -- |
OpenPose | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 12.522 ms | 103 - 103 MB | FP16 | NPU | -- |
License
- The license for the original implementation of OpenPose can be found here.
- The license for the compiled assets for on-device deployment can be found here
References
- OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
- 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.
Usage and Limitations
Model may not be used for or in connection with any of the following applications:
- Accessing essential private and public services and benefits;
- Administration of justice and democratic processes;
- Assessing or recognizing the emotional state of a person;
- Biometric and biometrics-based systems, including categorization of persons based on sensitive characteristics;
- Education and vocational training;
- Employment and workers management;
- Exploitation of the vulnerabilities of persons resulting in harmful behavior;
- General purpose social scoring;
- Law enforcement;
- Management and operation of critical infrastructure;
- Migration, asylum and border control management;
- Predictive policing;
- Real-time remote biometric identification in public spaces;
- Recommender systems of social media platforms;
- Scraping of facial images (from the internet or otherwise); and/or
- Subliminal manipulation
Inference API (serverless) does not yet support pytorch models for this pipeline type.