HRNet-PoseNet is a pose estimation model based on the HRNet (High-Resolution Network) architecture, specifically designed for human keypoint detection and pose estimation tasks. HRNet-PoseNet maintains high-resolution feature representations throughout the network, while processing features in parallel across multiple resolutions to capture both global and local information of the human body. This design enables high-precision keypoint localization, retaining high-quality pose estimation even in complex scenarios. HRNet-PoseNet performs exceptionally well in various pose estimation tasks and is widely applied in fields like sports analysis, action recognition, virtual reality, and human-computer interaction, providing robust support for real-time and precise pose estimation.

Source model

• Input shape: 256x192
• Number of parameters: 28.5M
• Model size: 108.94M
• Output shape: 1x17x64x48

Source model repository: HRNET-Posenet

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 AIDLux 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