8000 GitHub - hailo-ai/hailo-apps-infra
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

hailo-ai/hailo-apps-infra

Repository files navigation

Hailo Applications Infrastructure

Hailo Applications

Ask DeepWiki

Welcome to the Hailo Applications repository! This project provides a foundational infrastructure, reusable components, and practical examples for building and deploying high-performance AI applications using Hailo hardware accelerators.

It includes everything you need to get started with computer vision pipelines on both x86_64 Ubuntu systems and Raspberry Pi platforms.

  • Ready-to-use AI pipelines for object detection, pose estimation, and more.
  • Modular infrastructure for rapid development and custom applications.
  • Packaged as a Python library for easy integration into your own projects.

Visit the Hailo Official Website and Hailo Community Forum for more information.

Getting Started

Hardware and Software Installation

For detailed instructions on setting up your hardware, including both x86_64 Ubuntu systems and Raspberry Pi devices, please refer to the Full Installation Guide. This guide covers everything from hardware setup to software installation, ensuring your environment is ready for deploying AI applications with Hailo hardware accelerators.

Hailo Apps Installation

Get up and running in minutes with the automated installation script.

# Clone the repository
git clone https://github.com/hailo-ai/hailo-apps-infra.git
cd hailo-apps-infra

# Run the installer
./install.sh

Running Applications

Here are a few of the ready-to-use applications included in this repository. Before running any application, ensure you activate the Python virtual environment created during installation. This ensures all dependencies are correctly loaded.

Setup environment:

This should be run on every new terminal session.

source setup_env.sh

Additionally, in the common case of a Raspberry Pi connected remotely via SSH, add:

export DISPLAY=:0

Simple Object Detection

A lightweight version focused on demonstrating raw Hailo performance with minimal CPU overhead.

Command:

hailo-detect-simple

Output:

Detection Example

Full Object Detection

A comprehensive detection application featuring object tracking and resolution scaling.

Command:

hailo-detect

Pose Estimation

Detects human pose keypoints (e.g., joints and limbs) in real-time.

Command:

hailo-pose

Output:

Pose Estimation Example

Instance Segmentation

Provides pixel-level masks for each detected object.

Command:

hailo-seg

Output:

Instance Segmentation Example

For a complete list of all available applications and their features, please see the Running Applications Guide.

Full Documentation

For detailed guides on installation, usage, and development, please see our complete documentation:

➡️ View the Full Documentation

The documentation includes:

License

This project is licensed under the MIT License - see the LICENSE file for complete details.

Getting Help

If you run into any issues, the best place to get help is the Hailo Community Forum. You can search for existing solutions or open a new topic to get help from the community and the Hailo team.

0