Hugging Face's logo

qualcomm
/
HRNetPoseQuantized

Keypoint Detection
PyTorch
TF Lite
quantized
android
Model card Files Community
HRNetPoseQuantized / README.md
qaihm-bot's picture
qaihm-bot
Upload README.md with huggingface_hub
c261043 verified
preview code
|
raw
history blame
9.12 kB
metadata
library_name: pytorch
license: other
pipeline_tag: keypoint-detection
tags:
  - quantized
  - android

HRNetPoseQuantized: Optimized for Mobile Deployment

Perform accurate human pose estimation

HRNet performs pose estimation in high-resolution representations.

This model is an implementation of HRNetPoseQuantized found here.

This repository provides scripts to run HRNetPoseQuantized 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: hrnet_posenet_FP32_state_dict
    • Input resolution: 256x192
    • Number of parameters: 28.5M
    • Model size: 109 MB
Model Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Precision Primary Compute Unit Target Model
HRNetPoseQuantized Samsung Galaxy S23 Snapdragon® 8 Gen 2 TFLITE 0.951 ms 0 - 2 MB INT8 NPU HRNetPoseQuantized.tflite
HRNetPoseQuantized Samsung Galaxy S23 Snapdragon® 8 Gen 2 QNN 1.24 ms 0 - 12 MB INT8 NPU HRNetPoseQuantized.so
HRNetPoseQuantized Samsung Galaxy S24 Snapdragon® 8 Gen 3 TFLITE 0.707 ms 0 - 107 MB INT8 NPU HRNetPoseQuantized.tflite
HRNetPoseQuantized Samsung Galaxy S24 Snapdragon® 8 Gen 3 QNN 0.925 ms 0 - 35 MB INT8 NPU HRNetPoseQuantized.so
HRNetPoseQuantized Snapdragon 8 Elite QRD Snapdragon® 8 Elite TFLITE 0.643 ms 0 - 63 MB INT8 NPU HRNetPoseQuantized.tflite
HRNetPoseQuantized Snapdragon 8 Elite QRD Snapdragon® 8 Elite QNN 0.746 ms 0 - 31 MB INT8 NPU Use Export Script
HRNetPoseQuantized RB3 Gen 2 (Proxy) QCS6490 Proxy TFLITE 3.687 ms 0 - 69 MB INT8 NPU HRNetPoseQuantized.tflite
HRNetPoseQuantized RB3 Gen 2 (Proxy) QCS6490 Proxy QNN 5.289 ms 0 - 8 MB INT8 NPU Use Export Script
HRNetPoseQuantized RB5 (Proxy) QCS8250 Proxy TFLITE 17.632 ms 0 - 7 MB INT8 NPU HRNetPoseQuantized.tflite
HRNetPoseQuantized QCS8550 (Proxy) QCS8550 Proxy TFLITE 0.953 ms 0 - 212 MB INT8 NPU HRNetPoseQuantized.tflite
HRNetPoseQuantized QCS8550 (Proxy) QCS8550 Proxy QNN 1.199 ms 0 - 1 MB INT8 NPU Use Export Script
HRNetPoseQuantized SA8255 (Proxy) SA8255P Proxy TFLITE 0.97 ms 0 - 4 MB INT8 NPU HRNetPoseQuantized.tflite
HRNetPoseQuantized SA8255 (Proxy) SA8255P Proxy QNN 1.226 ms 0 - 1 MB INT8 NPU Use Export Script
HRNetPoseQuantized SA8775 (Proxy) SA8775P Proxy TFLITE 0.966 ms 0 - 2 MB INT8 NPU HRNetPoseQuantized.tflite
HRNetPoseQuantized SA8775 (Proxy) SA8775P Proxy QNN 1.212 ms 0 - 1 MB INT8 NPU Use Export Script
HRNetPoseQuantized SA8650 (Proxy) SA8650P Proxy TFLITE 0.954 ms 0 - 2 MB INT8 NPU HRNetPoseQuantized.tflite
HRNetPoseQuantized SA8650 (Proxy) SA8650P Proxy QNN 1.229 ms 0 - 2 MB INT8 NPU Use Export Script
HRNetPoseQuantized SA8295P ADP SA8295P TFLITE 1.662 ms 0 - 63 MB INT8 NPU HRNetPoseQuantized.tflite
HRNetPoseQuantized SA8295P ADP SA8295P QNN 2.003 ms 0 - 5 MB INT8 NPU Use Export Script
HRNetPoseQuantized QCS8450 (Proxy) QCS8450 Proxy TFLITE 1.17 ms 0 - 109 MB INT8 NPU HRNetPoseQuantized.tflite
HRNetPoseQuantized QCS8450 (Proxy) QCS8450 Proxy QNN 1.467 ms 0 - 34 MB INT8 NPU Use Export Script
HRNetPoseQuantized Snapdragon X Elite CRD Snapdragon® X Elite QNN 1.353 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[hrnet_pose_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.hrnet_pose_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.hrnet_pose_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.hrnet_pose_quantized.export

Profiling Results
------------------------------------------------------------
HRNetPoseQuantized
Device                          : Samsung Galaxy S23 (13)
Runtime                         : TFLITE                 
Estimated inference time (ms)   : 1.0                    
Estimated peak memory usage (MB): [0, 2]                 
Total # Ops                     : 518                    
Compute Unit(s)                 : NPU (518 ops)

Run demo on a cloud-hosted device

You can also run the demo on-device.

python -m qai_hub_models.models.hrnet_pose_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.hrnet_pose_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 HRNetPoseQuantized's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

  • The license for the original implementation of HRNetPoseQuantized can be found here.
  • The license for the compiled assets for on-device deployment can be found here

References

Community