galliot-us / PifPaf-TensorRT-Pose-Estimation

43 stars 18 forks source link

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

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.

Getting Started

The following instructions will help you get started.

Prerequisites

Hardware

Software

Install

git clone https://github.com/galliot-us/pose-estimation.git
cd pose-estimation/

Usage

Run on Jetson

3) Build Docker image for Jetson (This step is optional, you can skip it if you want to pull the container from neuralet dockerhub)

docker build -f jetson-4-4-openpifpaf.Dockerfile -t "galliot/pose-estimation-openpifpaf:latest-jetson-4-4" .

4) Run Docker container:

docker run --runtime nvidia --privileged -it -v $PWD:/repo galliot/pose-estimation-openpifpaf:latest-jetson-4-4