Galliot now hosts all Neuralet’s content and expertise gained in three years of work and completing high-quality applications, mainly in Computer Vision and Deep Learning. More Info
TensorRT OpenPifPaf Pose Estimation is a Jetson-friendly application that runs inference using a TensorRT engine to extract human poses. The provided TensorRT engine is generated from an ONNX model exported from OpenPifPaf version 0.12a4 using ONNX-TensorRT repo.
You can read this article on our website to learn more about the TensorRT OpenPifPaf Pose Estimation application.
The following instructions will help you get started.
Hardware
Software
git clone https://github.com/galliot-us/pose-estimation.git
cd pose-estimation/
openpifpaf_resnet50_321_193.onnx
and openpifpaf_resnet50_641_369.onnx
) are provided in Galliot-Models./etc/docker/daemon.json
to have GPU access during docker build
# 1) Download/Copy Sample input
./download_sample_video.sh
docker build -f jetson-4-4-openpifpaf.Dockerfile -t "galliot/pose-estimation-openpifpaf:latest-jetson-4-4" .
docker run --runtime nvidia --privileged -it -v $PWD:/repo galliot/pose-estimation-openpifpaf:latest-jetson-4-4