Hugging Face's logo

qualcomm
/
Person-Foot-Detection-Quantized

Object Detection
PyTorch
TF Lite
ONNX
real_time
quantized
android
Model card Files Community

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 1.296 ms 0 - 6 MB INT8 NPU Person-Foot-Detection-Quantized.tflite
Person-Foot-Detection-Quantized Samsung Galaxy S23 Snapdragon® 8 Gen 2 QNN 1.246 ms 0 - 3 MB INT8 NPU Person-Foot-Detection-Quantized.so
Person-Foot-Detection-Quantized Samsung Galaxy S23 Snapdragon® 8 Gen 2 ONNX 1.727 ms 0 - 18 MB INT8 NPU Person-Foot-Detection-Quantized.onnx
Person-Foot-Detection-Quantized Samsung Galaxy S24 Snapdragon® 8 Gen 3 TFLITE 0.88 ms 0 - 34 MB INT8 NPU Person-Foot-Detection-Quantized.tflite
Person-Foot-Detection-Quantized Samsung Galaxy S24 Snapdragon® 8 Gen 3 QNN 0.841 ms 1 - 22 MB INT8 NPU Person-Foot-Detection-Quantized.so
Person-Foot-Detection-Quantized Samsung Galaxy S24 Snapdragon® 8 Gen 3 ONNX 1.242 ms 0 - 38 MB INT8 NPU Person-Foot-Detection-Quantized.onnx
Person-Foot-Detection-Quantized Snapdragon 8 Elite QRD Snapdragon® 8 Elite TFLITE 0.88 ms 0 - 29 MB INT8 NPU Person-Foot-Detection-Quantized.tflite
Person-Foot-Detection-Quantized Snapdragon 8 Elite QRD Snapdragon® 8 Elite QNN 0.738 ms 1 - 30 MB INT8 NPU Use Export Script
Person-Foot-Detection-Quantized Snapdragon 8 Elite QRD Snapdragon® 8 Elite ONNX 0.969 ms 0 - 33 MB INT8 NPU Person-Foot-Detection-Quantized.onnx
Person-Foot-Detection-Quantized SA7255P ADP SA7255P TFLITE 19.56 ms 1 - 22 MB INT8 NPU Person-Foot-Detection-Quantized.tflite
Person-Foot-Detection-Quantized SA7255P ADP SA7255P QNN 19.579 ms 1 - 9 MB INT8 NPU Use Export Script
Person-Foot-Detection-Quantized SA8255 (Proxy) SA8255P Proxy TFLITE 1.249 ms 0 - 11 MB INT8 NPU Person-Foot-Detection-Quantized.tflite
Person-Foot-Detection-Quantized SA8255 (Proxy) SA8255P Proxy QNN 1.24 ms 1 - 3 MB INT8 NPU Use Export Script
Person-Foot-Detection-Quantized SA8295P ADP SA8295P TFLITE 2.384 ms 0 - 23 MB INT8 NPU Person-Foot-Detection-Quantized.tflite
Person-Foot-Detection-Quantized SA8295P ADP SA8295P QNN 2.54 ms 1 - 14 MB INT8 NPU Use Export Script
Person-Foot-Detection-Quantized SA8650 (Proxy) SA8650P Proxy TFLITE 1.296 ms 0 - 13 MB INT8 NPU Person-Foot-Detection-Quantized.tflite
Person-Foot-Detection-Quantized SA8650 (Proxy) SA8650P Proxy QNN 1.245 ms 1 - 4 MB INT8 NPU Use Export Script
Person-Foot-Detection-Quantized SA8775P ADP SA8775P TFLITE 1.99 ms 0 - 21 MB INT8 NPU Person-Foot-Detection-Quantized.tflite
Person-Foot-Detection-Quantized SA8775P ADP SA8775P QNN 2.029 ms 1 - 9 MB INT8 NPU Use Export Script
Person-Foot-Detection-Quantized RB3 Gen 2 (Proxy) QCS6490 Proxy TFLITE 5.342 ms 1 - 28 MB INT8 NPU Person-Foot-Detection-Quantized.tflite
Person-Foot-Detection-Quantized RB3 Gen 2 (Proxy) QCS6490 Proxy QNN 7.194 ms 1 - 13 MB INT8 NPU Use Export Script
Person-Foot-Detection-Quantized RB5 (Proxy) QCS8250 Proxy TFLITE 27.833 ms 1 - 4 MB INT8 NPU Person-Foot-Detection-Quantized.tflite
Person-Foot-Detection-Quantized QCS8275 (Proxy) QCS8275 Proxy TFLITE 19.56 ms 1 - 22 MB INT8 NPU Person-Foot-Detection-Quantized.tflite
Person-Foot-Detection-Quantized QCS8275 (Proxy) QCS8275 Proxy QNN 19.579 ms 1 - 9 MB INT8 NPU Use Export Script
Person-Foot-Detection-Quantized QCS8550 (Proxy) QCS8550 Proxy TFLITE 1.256 ms 0 - 13 MB INT8 NPU Person-Foot-Detection-Quantized.tflite
Person-Foot-Detection-Quantized QCS8550 (Proxy) QCS8550 Proxy QNN 1.235 ms 1 - 3 MB INT8 NPU Use Export Script
Person-Foot-Detection-Quantized QCS9075 (Proxy) QCS9075 Proxy TFLITE 1.99 ms 0 - 21 MB INT8 NPU Person-Foot-Detection-Quantized.tflite
Person-Foot-Detection-Quantized QCS9075 (Proxy) QCS9075 Proxy QNN 2.029 ms 1 - 9 MB INT8 NPU Use Export Script
Person-Foot-Detection-Quantized QCS8450 (Proxy) QCS8450 Proxy TFLITE 1.579 ms 0 - 30 MB INT8 NPU Person-Foot-Detection-Quantized.tflite
Person-Foot-Detection-Quantized QCS8450 (Proxy) QCS8450 Proxy QNN 1.724 ms 1 - 30 MB INT8 NPU Use Export Script
Person-Foot-Detection-Quantized Snapdragon X Elite CRD Snapdragon® X Elite QNN 1.455 ms 1 - 1 MB INT8 NPU Use Export Script
Person-Foot-Detection-Quantized Snapdragon X Elite CRD Snapdragon® X Elite ONNX 1.876 ms 8 - 8 MB INT8 NPU Person-Foot-Detection-Quantized.onnx

Installation

Install the 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)   : 1.3                    
Estimated peak memory usage (MB): [0, 6]                 
Total # Ops                     : 145                    
Compute Unit(s)                 : NPU (145 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 Providers NEW
Object Detection
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The HF Inference API does not support object-detection models for pytorch library.