Posenet-Mobilenet-Quantized: Optimized for Mobile Deployment
Quantized human pose estimator
Posenet performs pose estimation on human images.
This model is an implementation of Posenet-Mobilenet-Quantized found here.
This repository provides scripts to run Posenet-Mobilenet-Quantized on Qualcomm® devices. More details on model performance across various devices, can be found here.
Model Details
- Model Type: Pose estimation
- Model Stats:
- Model checkpoint: mobilenet_v1_101
- Input resolution: 513x257
- Number of parameters: 3.31M
- Model size: 3.47 MB
Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model |
---|---|---|---|---|---|---|---|---|
Posenet-Mobilenet-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.566 ms | 0 - 8 MB | INT8 | NPU | Posenet-Mobilenet-Quantized.tflite |
Posenet-Mobilenet-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 0.628 ms | 0 - 106 MB | INT8 | NPU | Posenet-Mobilenet-Quantized.so |
Posenet-Mobilenet-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.393 ms | 0 - 23 MB | INT8 | NPU | Posenet-Mobilenet-Quantized.tflite |
Posenet-Mobilenet-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.442 ms | 0 - 19 MB | INT8 | NPU | Posenet-Mobilenet-Quantized.so |
Posenet-Mobilenet-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.41 ms | 0 - 17 MB | INT8 | NPU | Posenet-Mobilenet-Quantized.tflite |
Posenet-Mobilenet-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.472 ms | 0 - 17 MB | INT8 | NPU | Use Export Script |
Posenet-Mobilenet-Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | TFLITE | 2.288 ms | 0 - 21 MB | INT8 | NPU | Posenet-Mobilenet-Quantized.tflite |
Posenet-Mobilenet-Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | QNN | 3.064 ms | 0 - 8 MB | INT8 | NPU | Use Export Script |
Posenet-Mobilenet-Quantized | RB5 (Proxy) | QCS8250 Proxy | TFLITE | 12.463 ms | 0 - 7 MB | INT8 | NPU | Posenet-Mobilenet-Quantized.tflite |
Posenet-Mobilenet-Quantized | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.552 ms | 0 - 11 MB | INT8 | NPU | Posenet-Mobilenet-Quantized.tflite |
Posenet-Mobilenet-Quantized | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 0.556 ms | 0 - 1 MB | INT8 | NPU | Use Export Script |
Posenet-Mobilenet-Quantized | SA7255P ADP | SA7255P | TFLITE | 7.968 ms | 0 - 17 MB | INT8 | NPU | Posenet-Mobilenet-Quantized.tflite |
Posenet-Mobilenet-Quantized | SA7255P ADP | SA7255P | QNN | 8.167 ms | 0 - 5 MB | INT8 | NPU | Use Export Script |
Posenet-Mobilenet-Quantized | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.566 ms | 0 - 112 MB | INT8 | NPU | Posenet-Mobilenet-Quantized.tflite |
Posenet-Mobilenet-Quantized | SA8255 (Proxy) | SA8255P Proxy | QNN | 0.564 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
Posenet-Mobilenet-Quantized | SA8295P ADP | SA8295P | TFLITE | 1.206 ms | 0 - 16 MB | INT8 | NPU | Posenet-Mobilenet-Quantized.tflite |
Posenet-Mobilenet-Quantized | SA8295P ADP | SA8295P | QNN | 1.461 ms | 0 - 6 MB | INT8 | NPU | Use Export Script |
Posenet-Mobilenet-Quantized | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.569 ms | 0 - 8 MB | INT8 | NPU | Posenet-Mobilenet-Quantized.tflite |
Posenet-Mobilenet-Quantized | SA8650 (Proxy) | SA8650P Proxy | QNN | 0.565 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
Posenet-Mobilenet-Quantized | SA8775P ADP | SA8775P | TFLITE | 0.993 ms | 0 - 16 MB | INT8 | NPU | Posenet-Mobilenet-Quantized.tflite |
Posenet-Mobilenet-Quantized | SA8775P ADP | SA8775P | QNN | 1.173 ms | 0 - 6 MB | INT8 | NPU | Use Export Script |
Posenet-Mobilenet-Quantized | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 0.737 ms | 0 - 21 MB | INT8 | NPU | Posenet-Mobilenet-Quantized.tflite |
Posenet-Mobilenet-Quantized | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 0.798 ms | 0 - 22 MB | INT8 | NPU | Use Export Script |
Posenet-Mobilenet-Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 0.685 ms | 0 - 0 MB | INT8 | NPU | Use Export Script |
Installation
This model can be installed as a Python package via pip.
pip install qai-hub-models
Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
Sign-in to Qualcomm® AI Hub with your
Qualcomm® ID. Once signed in navigate to Account -> Settings -> API Token
.
With this API token, you can configure your client to run models on the cloud hosted devices.
qai-hub configure --api_token API_TOKEN
Navigate to docs for more information.
Demo off target
The package contains a simple end-to-end demo that downloads pre-trained weights and runs this model on a sample input.
python -m qai_hub_models.models.posenet_mobilenet_quantized.demo
The above demo runs a reference implementation of pre-processing, model inference, and post processing.
NOTE: If you want running in a Jupyter Notebook or Google Colab like environment, please add the following to your cell (instead of the above).
%run -m qai_hub_models.models.posenet_mobilenet_quantized.demo
Run model on a cloud-hosted device
In addition to the demo, you can also run the model on a cloud-hosted Qualcomm® device. This script does the following:
- Performance check on-device on a cloud-hosted device
- Downloads compiled assets that can be deployed on-device for Android.
- Accuracy check between PyTorch and on-device outputs.
python -m qai_hub_models.models.posenet_mobilenet_quantized.export
Profiling Results
------------------------------------------------------------
Posenet-Mobilenet-Quantized
Device : Samsung Galaxy S23 (13)
Runtime : TFLITE
Estimated inference time (ms) : 0.6
Estimated peak memory usage (MB): [0, 8]
Total # Ops : 48
Compute Unit(s) : NPU (48 ops)
Run demo on a cloud-hosted device
You can also run the demo on-device.
python -m qai_hub_models.models.posenet_mobilenet_quantized.demo --on-device
NOTE: If you want running in a Jupyter Notebook or Google Colab like environment, please add the following to your cell (instead of the above).
%run -m qai_hub_models.models.posenet_mobilenet_quantized.demo -- --on-device
Deploying compiled model to Android
The models can be deployed using multiple runtimes:
TensorFlow Lite (
.tflite
export): This tutorial provides a guide to deploy the .tflite model in an Android application.QNN (
.so
export ): This sample app provides instructions on how to use the.so
shared library in an Android application.
View on Qualcomm® AI Hub
Get more details on Posenet-Mobilenet-Quantized's performance across various devices here. Explore all available models on Qualcomm® AI Hub
License
- The license for the original implementation of Posenet-Mobilenet-Quantized can be found here.
- The license for the compiled assets for on-device deployment can be found here
References
- PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model
- 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.