Person-Foot-Detection-Quantized: Optimized for Mobile Deployment

Multi-task Human detector

Real-time multiple person detection with accurate feet localization optimized for mobile and edge.

This model is an implementation of Person-Foot-Detection-Quantized found here.

This repository provides scripts to run Person-Foot-Detection-Quantized on Qualcomm® devices. More details on model performance across various devices, can be found here.

Model Details

  • Model Type: Object detection
  • Model Stats:
    • Model checkpoint: SA-e30_finetune50.pth
    • Inference latency: RealTime
    • Input resolution: 640x480
    • Number of output classes: 2
    • Number of parameters: 2.53M
    • Model size: 9.69 MB
Model Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Precision Primary Compute Unit Target Model
Person-Foot-Detection-Quantized Samsung Galaxy S23 Snapdragon® 8 Gen 2 TFLITE 1.145 ms 0 - 9 MB INT8 NPU Person-Foot-Detection-Quantized.tflite
Person-Foot-Detection-Quantized Samsung Galaxy S23 Snapdragon® 8 Gen 2 QNN 1.291 ms 0 - 66 MB INT8 NPU Person-Foot-Detection-Quantized.so
Person-Foot-Detection-Quantized Samsung Galaxy S23 Snapdragon® 8 Gen 2 ONNX 1.665 ms 0 - 4 MB INT8 NPU Person-Foot-Detection-Quantized.onnx
Person-Foot-Detection-Quantized Samsung Galaxy S24 Snapdragon® 8 Gen 3 TFLITE 0.797 ms 0 - 22 MB INT8 NPU Person-Foot-Detection-Quantized.tflite
Person-Foot-Detection-Quantized Samsung Galaxy S24 Snapdragon® 8 Gen 3 QNN 0.87 ms 1 - 26 MB INT8 NPU Person-Foot-Detection-Quantized.so
Person-Foot-Detection-Quantized Samsung Galaxy S24 Snapdragon® 8 Gen 3 ONNX 1.117 ms 0 - 57 MB INT8 NPU Person-Foot-Detection-Quantized.onnx
Person-Foot-Detection-Quantized Snapdragon 8 Elite QRD Snapdragon® 8 Elite TFLITE 0.771 ms 0 - 20 MB INT8 NPU Person-Foot-Detection-Quantized.tflite
Person-Foot-Detection-Quantized Snapdragon 8 Elite QRD Snapdragon® 8 Elite QNN 0.901 ms 0 - 21 MB INT8 NPU Use Export Script
Person-Foot-Detection-Quantized Snapdragon 8 Elite QRD Snapdragon® 8 Elite ONNX 1.086 ms 0 - 40 MB INT8 NPU Person-Foot-Detection-Quantized.onnx
Person-Foot-Detection-Quantized RB3 Gen 2 (Proxy) QCS6490 Proxy TFLITE 5.568 ms 1 - 26 MB INT8 NPU Person-Foot-Detection-Quantized.tflite
Person-Foot-Detection-Quantized RB3 Gen 2 (Proxy) QCS6490 Proxy QNN 6.908 ms 1 - 9 MB INT8 NPU Use Export Script
Person-Foot-Detection-Quantized RB5 (Proxy) QCS8250 Proxy TFLITE 27.211 ms 1 - 7 MB INT8 NPU Person-Foot-Detection-Quantized.tflite
Person-Foot-Detection-Quantized QCS8550 (Proxy) QCS8550 Proxy TFLITE 1.189 ms 0 - 7 MB INT8 NPU Person-Foot-Detection-Quantized.tflite
Person-Foot-Detection-Quantized QCS8550 (Proxy) QCS8550 Proxy QNN 1.229 ms 1 - 2 MB INT8 NPU Use Export Script
Person-Foot-Detection-Quantized SA7255P ADP SA7255P TFLITE 19.54 ms 1 - 23 MB INT8 NPU Person-Foot-Detection-Quantized.tflite
Person-Foot-Detection-Quantized SA7255P ADP SA7255P QNN 19.788 ms 1 - 6 MB INT8 NPU Use Export Script
Person-Foot-Detection-Quantized SA8255 (Proxy) SA8255P Proxy TFLITE 1.15 ms 0 - 9 MB INT8 NPU Person-Foot-Detection-Quantized.tflite
Person-Foot-Detection-Quantized SA8255 (Proxy) SA8255P Proxy QNN 1.233 ms 1 - 3 MB INT8 NPU Use Export Script
Person-Foot-Detection-Quantized SA8295P ADP SA8295P TFLITE 2.23 ms 0 - 20 MB INT8 NPU Person-Foot-Detection-Quantized.tflite
Person-Foot-Detection-Quantized SA8295P ADP SA8295P QNN 2.363 ms 0 - 6 MB INT8 NPU Use Export Script
Person-Foot-Detection-Quantized SA8650 (Proxy) SA8650P Proxy TFLITE 1.188 ms 0 - 9 MB INT8 NPU Person-Foot-Detection-Quantized.tflite
Person-Foot-Detection-Quantized SA8650 (Proxy) SA8650P Proxy QNN 1.235 ms 1 - 2 MB INT8 NPU Use Export Script
Person-Foot-Detection-Quantized SA8775P ADP SA8775P TFLITE 1.859 ms 0 - 20 MB INT8 NPU Person-Foot-Detection-Quantized.tflite
Person-Foot-Detection-Quantized SA8775P ADP SA8775P QNN 2.092 ms 0 - 5 MB INT8 NPU Use Export Script
Person-Foot-Detection-Quantized QCS8450 (Proxy) QCS8450 Proxy TFLITE 1.402 ms 0 - 24 MB INT8 NPU Person-Foot-Detection-Quantized.tflite
Person-Foot-Detection-Quantized QCS8450 (Proxy) QCS8450 Proxy QNN 1.508 ms 1 - 27 MB INT8 NPU Use Export Script
Person-Foot-Detection-Quantized Snapdragon X Elite CRD Snapdragon® X Elite QNN 2.026 ms 1 - 1 MB INT8 NPU Use Export Script
Person-Foot-Detection-Quantized Snapdragon X Elite CRD Snapdragon® X Elite ONNX 1.79 ms 8 - 8 MB INT8 NPU Person-Foot-Detection-Quantized.onnx

Installation

This model can be installed as a Python package via pip.

pip install "qai-hub-models[foot_track_net_quantized]"

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.foot_track_net_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.foot_track_net_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.foot_track_net_quantized.export
Profiling Results
------------------------------------------------------------
Person-Foot-Detection-Quantized
Device                          : Samsung Galaxy S23 (13)
Runtime                         : TFLITE                 
Estimated inference time (ms)   : 1.1                    
Estimated peak memory usage (MB): [0, 9]                 
Total # Ops                     : 146                    
Compute Unit(s)                 : NPU (146 ops)          

Run demo on a cloud-hosted device

You can also run the demo on-device.

python -m qai_hub_models.models.foot_track_net_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.foot_track_net_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 Person-Foot-Detection-Quantized's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

  • The license for the original implementation of Person-Foot-Detection-Quantized can be found here.
  • The license for the compiled assets for on-device deployment can be found here

References

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Examples
Inference API (serverless) does not yet support pytorch models for this pipeline type.