Welcome to the Neural Compute Application Zoo (_ncappzoo_), a collaborative playground for developers interested in utilizing the Intel® Neural Compute Stick and the OpenVINO™ toolkit. This repository is designed to provide a wealth of projects, code, and neural network models aimed at enhancing your experience with AI deployment on Intel hardware. In this guide, we’ll walk through the steps to get you started with _ncappzoo_ and help you troubleshoot common issues. Let’s dive in!

Quick Start Guide

If you have an Intel® NCS2 or the original Intel® Movidius™ NCS device, follow these straightforward steps to start experimenting with the _ncappzoo_:

• Clone the repository by running the following command:

git clone https://github.com/movidius/ncappzoo.git

• Navigate into any application network folder and check for software dependencies:

make install_reqs

• If the installation returns successfully, you’re ready to run the app or network sample!

Exploring Apps and Networks

To explore what _ncappzoo_ has to offer:

• Open a terminal and navigate to any directory under _ncappzoo_apps and execute:

make run

• For the neural networks, navigate to any network directory under _ncappzoo_networks and execute the same command:

make run

• All directories contain simple and consistent makefiles. Use the following command for more options:

make help

Understanding Repository Branches

The _ncappzoo_ repository contains three primary branches which cater to different user needs:

• master branch: The most current branch, compatible with both the Intel® NCS2 and original Movidius™ NCS device.
• ncsdk2 branch: A legacy branch for original Intel® Movidius™ NCS, not compatible with the NCS2.
• ncsdk1 branch: Another legacy branch for the original Movidius™ NCS only, not suitable for NCS2.

Compatibility Requirements

Let’s ensure your environment is set up correctly:

Hardware Compatibility

The projects in _ncappzoo_ are generally tested on Intel® x86-64 Systems. They should also work on hardware capable of running the OpenVINO™ toolkit, including Raspberry Pi models.

Operating System Compatibility

These projects are tested on Ubuntu 18.04 but may work on other Linux-based systems with some minor adjustments.

OpenVINO and DLDT Compatibility

For successful deployment, the projects depend on the Deep Learning Deployment Toolkit (DLDT) through OpenVINO™ toolkit. You will find resources for both Intel Distribution and open-source variations to assist with setup for various environments.

Code Analogy

Imagine learning to ride a bicycle. Initially, you gather all necessary equipment (repositories and dependencies). Next, you’ll find the right bike (choosing the right branch) that matches your style (hardware compatibility). Once you get on, you start pedaling (running experiments), but as you ride you might run into bumps (issues) along the path. Just like learning to navigate these bumps, troubleshooting will become part of the learning experience!

Troubleshooting Tips

If you run into issues during your journey with _ncappzoo_, here are some suggestions:

• Make sure all dependencies are properly installed.
• Check that you are using the correct command for your specific app or network sample.
• Review the README file in individual project directories for project-specific instructions.
• Encourage a collaborative spirit—connect with the community if you hit a wall!

For more insights, updates, or to collaborate on AI development projects, stay connected with fxis.ai.

Your Contribution Matters

The _ncappzoo_ thrives on community and sharing! If you’ve created something cool or have ideas to enhance what’s already here, consider contributing. Your input helps not just you but everyone in the community.

Final Thoughts

At fxis.ai, we believe that such advancements are crucial for the future of AI, as they enable more comprehensive and effective solutions. Our team is continually exploring new methodologies to push the envelope in artificial intelligence, ensuring that our clients benefit from the latest technological innovations.