MediaPipe Pose is a real-time human pose estimation model developed by Google, based on deep learning. The model captures and tracks 33 key points of the human body, including the head, torso, and limbs, using a single RGB camera. MediaPipe Pose employs a two-stage architecture: first, it detects the general pose region, and then a regression model accurately estimates the position of each key point. This model is efficient, accurate, and operates in real-time, making it suitable for mobile and edge devices. It is widely used in fitness tracking, motion recognition, virtual reality, and augmented reality, providing a high-quality pose estimation and tracking experience.

Source model

• Input shape: [1x3x128x128], [1x3x256x256]
• Number of parameters: 0.818M, 3.377M
• Model size: 3.40MB, 13.4MB
• Output shape: [1x896x12,1x896x1], [1,1x31x4,1x128x128]

Source model repository: MediaPipe-Pose

When the user has fine-tuned the source model, the model conversion process must be performed again.

Users can refer to either of the following two methods to complete the model conversion:

• Using AIMO for model conversion: Click Model Conversion Reference in the Performance Reference section on the right to view the conversion steps.

• Using Qualcomm QNN for model conversion: Please refer to the Qualcomm QNN Documentation.

The model performance benchmarks and example code provided by Model Farm are all implemented based on the APLUX AidLite SDK.

For models in .bin format, you can use either of the following two inference engines to run inference on Qualcomm chips:

Inference using APLUX AidLite: please refer to the APLUX AidLite Developer Documentation

Inference using Qualcomm QNN: Please refer to the Qualcomm QNN Documentation

Inference Example Code

The inference example code is implemented using the AidLite SDK.

Click Model & Code to download the model files and the inference code package. The file structure is as follows:

/model_farm_{model_name}_aidlite
    
    |__ models # folder where model files are stored

    |__ python # aidlite python model inference example

    |__ cpp # aidlite cpp model inference example

    |__ README.md