Skip to content

Latest commit

 

History

History
55 lines (38 loc) · 2.19 KB

README.md

File metadata and controls

55 lines (38 loc) · 2.19 KB

Qualcomm® AI Hub Models

HRNetPoseQuantized: Perform accurate human pose estimation

HRNet performs pose estimation in high-resolution representations.

This is based on the implementation of HRNetPoseQuantized found here. This repository contains scripts for optimized on-device export suitable to run on Qualcomm® devices. More details on model performance accross various devices, can be found here.

Sign up for early access to run these models on a hosted Qualcomm® device.

Example & Usage

Install the package via pip:

pip install "qai_hub_models[hrnet_pose_quantized]"

Once installed, run the following simple CLI demo:

python -m qai_hub_models.models.hrnet_pose_quantized.demo

More details on the CLI tool can be found with the --help option. See demo.py for sample usage of the model including pre/post processing scripts. Please refer to our general instructions on using models for more usage instructions.

Export for on-device deployment

This repository contains export scripts that produce a model optimized for on-device deployment. This can be run as follows:

python -m qai_hub_models.models.hrnet_pose_quantized.export

Additional options are documented with the --help option. Note that the above script requires access to Deployment instructions for Qualcomm® AI Hub.

License

  • Code in the Qualcomm® AI Hub Models repository is covered by the LICENSE file at the repository root.
  • The license for the original implementation of HRNetPoseQuantized can be found here.

References