metadata

library_name: pytorch
license: other
pipeline_tag: image-classification
tags:
  - android

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. This repository provides scripts to run OpenPose 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: body_pose_model.pth
- Input resolution: 240x320
- Number of parameters: 52.3M
- Model size: 200 MB

Device	Chipset	Target Runtime	Inference Time (ms)	Peak Memory Range (MB)	Precision	Primary Compute Unit	Target Model
Samsung Galaxy S23 Ultra (Android 13)	Snapdragon® 8 Gen 2	TFLite	11.747 ms	0 - 2 MB	FP16	NPU	OpenPose.tflite
Samsung Galaxy S23 Ultra (Android 13)	Snapdragon® 8 Gen 2	QNN Model Library	11.82 ms	1 - 231 MB	FP16	NPU	OpenPose.so

Installation

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

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

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.openpose.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.openpose.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.openpose.export

Profile Job summary of OpenPose
--------------------------------------------------
Device: Samsung Galaxy S23 Ultra (13)
Estimated Inference Time: 11.75 ms
Estimated Peak Memory Range: 0.22-2.35 MB
Compute Units: NPU (103) | Total (103)

Profile Job summary of OpenPose
--------------------------------------------------
Device: Samsung Galaxy S23 Ultra (13)
Estimated Inference Time: 11.82 ms
Estimated Peak Memory Range: 0.59-230.69 MB
Compute Units: NPU (187) | Total (187)

How does this work?

This export script leverages Qualcomm® AI Hub to optimize, validate, and deploy this model on-device. Lets go through each step below in detail:

Step 1: Compile model for on-device deployment

To compile a PyTorch model for on-device deployment, we first trace the model in memory using the jit.trace and then call the submit_compile_job API.

import torch

import qai_hub as hub
from qai_hub_models.models.openpose import Model

# Load the model
torch_model = Model.from_pretrained()
torch_model.eval()

# Device
device = hub.Device("Samsung Galaxy S23")

# Trace model
input_shape = torch_model.get_input_spec()
sample_inputs = torch_model.sample_inputs()

pt_model = torch.jit.trace(torch_model, [torch.tensor(data[0]) for _, data in sample_inputs.items()])

# Compile model on a specific device
compile_job = hub.submit_compile_job(
    model=pt_model,
    device=device,
    input_specs=torch_model.get_input_spec(),
)

# Get target model to run on-device
target_model = compile_job.get_target_model()

Step 2: Performance profiling on cloud-hosted device

After compiling models from step 1. Models can be profiled model on-device using the target_model. Note that this scripts runs the model on a device automatically provisioned in the cloud. Once the job is submitted, you can navigate to a provided job URL to view a variety of on-device performance metrics.

profile_job = hub.submit_profile_job(
    model=target_model,
    device=device,
)

Step 3: Verify on-device accuracy

To verify the accuracy of the model on-device, you can run on-device inference on sample input data on the same cloud hosted device.

input_data = torch_model.sample_inputs()
inference_job = hub.submit_inference_job(
    model=target_model,
    device=device,
    inputs=input_data,
)

on_device_output = inference_job.download_output_data()

With the output of the model, you can compute like PSNR, relative errors or spot check the output with expected output.

Note: This on-device profiling and inference requires access to Qualcomm® AI Hub. Sign up for access.

Run demo on a cloud-hosted device

You can also run the demo on-device.

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

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

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.