MediaPipe-Pose-Estimation: Optimized for Mobile Deployment
Detect and track human body poses in real-time images and video streams
The MediaPipe Pose Landmark Detector is a machine learning pipeline that predicts bounding boxes and pose skeletons of poses in an image.
This model is an implementation of MediaPipe-Pose-Estimation found here.
This repository provides scripts to run MediaPipe-Pose-Estimation on Qualcomm® devices. More details on model performance across various devices, can be found here.
Model Details
- Model Type: Pose estimation
- Model Stats:
- Input resolution: 256x256
- Number of parameters (MediaPipePoseDetector): 815K
- Model size (MediaPipePoseDetector): 3.14 MB
- Number of parameters (MediaPipePoseLandmarkDetector): 3.37M
- Model size (MediaPipePoseLandmarkDetector): 12.9 MB
Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model |
---|---|---|---|---|---|---|---|---|
MediaPipePoseDetector | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.772 ms | 0 - 1 MB | FP16 | NPU | MediaPipe-Pose-Estimation.tflite |
MediaPipePoseDetector | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 0.988 ms | 0 - 4 MB | FP16 | NPU | MediaPipe-Pose-Estimation.onnx |
MediaPipePoseDetector | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.556 ms | 0 - 47 MB | FP16 | NPU | MediaPipe-Pose-Estimation.tflite |
MediaPipePoseDetector | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 0.747 ms | 0 - 49 MB | FP16 | NPU | MediaPipe-Pose-Estimation.onnx |
MediaPipePoseDetector | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.567 ms | 0 - 23 MB | FP16 | NPU | MediaPipe-Pose-Estimation.tflite |
MediaPipePoseDetector | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 0.755 ms | 0 - 26 MB | FP16 | NPU | MediaPipe-Pose-Estimation.onnx |
MediaPipePoseDetector | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.772 ms | 0 - 1 MB | FP16 | NPU | MediaPipe-Pose-Estimation.tflite |
MediaPipePoseDetector | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.77 ms | 0 - 1 MB | FP16 | NPU | MediaPipe-Pose-Estimation.tflite |
MediaPipePoseDetector | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 0.775 ms | 0 - 1 MB | FP16 | NPU | MediaPipe-Pose-Estimation.tflite |
MediaPipePoseDetector | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.779 ms | 0 - 1 MB | FP16 | NPU | MediaPipe-Pose-Estimation.tflite |
MediaPipePoseDetector | SA8295P ADP | SA8295P | TFLITE | 2.36 ms | 0 - 20 MB | FP16 | NPU | MediaPipe-Pose-Estimation.tflite |
MediaPipePoseDetector | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 1.899 ms | 0 - 41 MB | FP16 | NPU | MediaPipe-Pose-Estimation.tflite |
MediaPipePoseDetector | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 1.057 ms | 4 - 4 MB | FP16 | NPU | MediaPipe-Pose-Estimation.onnx |
MediaPipePoseLandmarkDetector | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.822 ms | 0 - 26 MB | FP16 | NPU | MediaPipe-Pose-Estimation.tflite |
MediaPipePoseLandmarkDetector | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 1.39 ms | 0 - 10 MB | FP16 | NPU | MediaPipe-Pose-Estimation.onnx |
MediaPipePoseLandmarkDetector | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.586 ms | 0 - 90 MB | FP16 | NPU | MediaPipe-Pose-Estimation.tflite |
MediaPipePoseLandmarkDetector | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 0.949 ms | 0 - 95 MB | FP16 | NPU | MediaPipe-Pose-Estimation.onnx |
MediaPipePoseLandmarkDetector | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.549 ms | 0 - 35 MB | FP16 | NPU | MediaPipe-Pose-Estimation.tflite |
MediaPipePoseLandmarkDetector | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 0.769 ms | 0 - 42 MB | FP16 | NPU | MediaPipe-Pose-Estimation.onnx |
MediaPipePoseLandmarkDetector | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.799 ms | 0 - 1 MB | FP16 | NPU | MediaPipe-Pose-Estimation.tflite |
MediaPipePoseLandmarkDetector | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.825 ms | 0 - 1 MB | FP16 | NPU | MediaPipe-Pose-Estimation.tflite |
MediaPipePoseLandmarkDetector | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 0.796 ms | 0 - 2 MB | FP16 | NPU | MediaPipe-Pose-Estimation.tflite |
MediaPipePoseLandmarkDetector | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.81 ms | 0 - 175 MB | FP16 | NPU | MediaPipe-Pose-Estimation.tflite |
MediaPipePoseLandmarkDetector | SA8295P ADP | SA8295P | TFLITE | 4.984 ms | 0 - 39 MB | FP16 | GPU | MediaPipe-Pose-Estimation.tflite |
MediaPipePoseLandmarkDetector | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 1.745 ms | 0 - 78 MB | FP16 | NPU | MediaPipe-Pose-Estimation.tflite |
MediaPipePoseLandmarkDetector | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 1.357 ms | 8 - 8 MB | FP16 | NPU | MediaPipe-Pose-Estimation.onnx |
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.mediapipe_pose.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.mediapipe_pose.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.mediapipe_pose.export
Profiling Results
------------------------------------------------------------
MediaPipePoseDetector
Device : Samsung Galaxy S23 (13)
Runtime : TFLITE
Estimated inference time (ms) : 0.8
Estimated peak memory usage (MB): [0, 1]
Total # Ops : 106
Compute Unit(s) : NPU (106 ops)
------------------------------------------------------------
MediaPipePoseLandmarkDetector
Device : Samsung Galaxy S23 (13)
Runtime : TFLITE
Estimated inference time (ms) : 0.8
Estimated peak memory usage (MB): [0, 26]
Total # Ops : 219
Compute Unit(s) : NPU (219 ops)
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.mediapipe_pose import MediaPipePoseDetector,MediaPipePoseLandmarkDetector
# Load the model
pose_detector_model = MediaPipePoseDetector.from_pretrained()
pose_landmark_detector_model = MediaPipePoseLandmarkDetector.from_pretrained()
# Device
device = hub.Device("Samsung Galaxy S23")
# Trace model
pose_detector_input_shape = pose_detector_model.get_input_spec()
pose_detector_sample_inputs = pose_detector_model.sample_inputs()
traced_pose_detector_model = torch.jit.trace(pose_detector_model, [torch.tensor(data[0]) for _, data in pose_detector_sample_inputs.items()])
# Compile model on a specific device
pose_detector_compile_job = hub.submit_compile_job(
model=traced_pose_detector_model ,
device=device,
input_specs=pose_detector_model.get_input_spec(),
)
# Get target model to run on-device
pose_detector_target_model = pose_detector_compile_job.get_target_model()
# Trace model
pose_landmark_detector_input_shape = pose_landmark_detector_model.get_input_spec()
pose_landmark_detector_sample_inputs = pose_landmark_detector_model.sample_inputs()
traced_pose_landmark_detector_model = torch.jit.trace(pose_landmark_detector_model, [torch.tensor(data[0]) for _, data in pose_landmark_detector_sample_inputs.items()])
# Compile model on a specific device
pose_landmark_detector_compile_job = hub.submit_compile_job(
model=traced_pose_landmark_detector_model ,
device=device,
input_specs=pose_landmark_detector_model.get_input_spec(),
)
# Get target model to run on-device
pose_landmark_detector_target_model = pose_landmark_detector_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.
pose_detector_profile_job = hub.submit_profile_job(
model=pose_detector_target_model,
device=device,
)
pose_landmark_detector_profile_job = hub.submit_profile_job(
model=pose_landmark_detector_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.
pose_detector_input_data = pose_detector_model.sample_inputs()
pose_detector_inference_job = hub.submit_inference_job(
model=pose_detector_target_model,
device=device,
inputs=pose_detector_input_data,
)
pose_detector_inference_job.download_output_data()
pose_landmark_detector_input_data = pose_landmark_detector_model.sample_inputs()
pose_landmark_detector_inference_job = hub.submit_inference_job(
model=pose_landmark_detector_target_model,
device=device,
inputs=pose_landmark_detector_input_data,
)
pose_landmark_detector_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.
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 MediaPipe-Pose-Estimation's performance across various devices here. Explore all available models on Qualcomm® AI Hub
License
- The license for the original implementation of MediaPipe-Pose-Estimation 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.