Udemy

Platform

English

Language

Data Science

Category

Accelerate Deep Learning on Raspberry Pi

How to Accelerate your AI Object Detection Models 5X faster on a Raspberry Pi 3, using Intel Movidius for Deep Learning

4.30 (153 reviews)

Students

2 hours

Content

Dec 2019

Last Update
Regular Price


What you will learn

Learn how to get Started with Raspberry Pi from Scratch

Discover various Object Detection models

Introduction to Deep Learning and Tensorflow lite

Implement Object Detection using Movidius NC SDK


Description

Learn how we implemented Deep Learning Object Detection Models on Raspberry Pi and accelerated them with Intel Movidius Neural Compute Stick.

When we first got started in Deep Learning particularly in Computer Vision, we were really excited at the possibilities of this technology to help people. The only problem is, that image classification and object detection runs just fine on our expensive, power consuming and bulky Deep Learning machines. However, not everyone can afford or implement AI for their practical applications.

This is when we went searching for an affordable, compact, less power hungry alternative. Generally if we'd want to shrink our IoT and automation projects, we'd often look to the Raspberry Pi which is versatile computing solution for numerous problems. This made us ponder about how we can port out deep learning models to this compact computing unit. Not only that, but how could we run it at close to real-time?

Amongst the possible solutions we arrived at using the raspberry pi in conjunction with an AI Accelerator USB stick that was made by Intel to boost our object detection frame-rate. However it was not so simple to get it up and running. Implementing the documentation, we landed up with a series of bugs after bugs, which became a bit tedious.

After endless posts on forums, tutorials and blogs, we have documented a seamless guide in the form of this course; which will show you, step-by-step, on how to implement your own Deep Learning Object Detection models on video and webcam without all the wasteful debugging. So essentially, we've structured this training to reduce debugging, speed up your time to market and get you results sooner.

In this course, here's some of the things that you will learn:

  • Getting Started with Raspberry Pi even if you are a beginner,

  • Deep Learning Basics,

  • Object Detection Models - Pros and Cons of each CNN,

  • Setup and Install Movidius Neural Compute Stick (NCS) SDK,
    Currently, the OpenVINO is available for Raspbian, so the NCS2 is already compatible with the Raspberry Pi, but this course is mainly for the Movidius (NCS version 1).

  • Run Yolo and Mobilenet SSD object detection models in recorded or live video

You also get helpful bonuses:

*OpenCV CPU inference

*Introduction to Custom Model Training

Personal help within the course

I donate my time to regularly hold office hours with students. During the office hours you can ask me any business question you want, and I will do my best to help you. The office hours are free. I don't try to sell anything.

Students can start discussions and message me with private questions. I answer 99% of questions within 24 hours. I love helping students who take my courses and I look forward to helping you. 

I regularly update this course to reflect the current marketing landscape.

Get a Career Boost with a Certificate of Completion  

Upon completing 100% of this course, you will be emailed a certificate of completion. You can show it as proof of your expertise and that you have completed a certain number of hours of instruction.

If you want to get a marketing job or freelancing clients, a certificate from this course can help you appear as a stronger candidate for Artificial Intelligence jobs.

Money-Back Guarantee

The course comes with an unconditional, Udemy-backed, 30-day money-back guarantee. This is not just a guarantee, it's my personal promise to you that I will go out of my way to help you succeed just like I've done for thousands of my other students. 

Let me help you get fast results.  Enroll now, by clicking the button and let us show you how to develop Accelerated AI on Raspberry Pi.


Screenshots

Accelerate Deep Learning on Raspberry Pi
Accelerate Deep Learning on Raspberry Pi
Accelerate Deep Learning on Raspberry Pi
Accelerate Deep Learning on Raspberry Pi

Content

Introduction to the Course

Introduction to the Course

Hardware Requirements for Deep Learning

How to take this course.

Frequently Asked Questions (FAQ)

The Super Simple Way to Get Started with Raspberry Pi

How to Install Raspbian Operating System on Raspberry Pi

Optional - Headless Raspberry Pi setup

Initial Raspbian OS Setup on Raspberry PI

4 Raspberry Pi/Linux Scripting Tricks

Deep learning Fundamentals (theory)

Multilayer Perceptron - Artificial Neural Network (Theory)

Convolutional Neural Network (Theory)

Nomenclature

Object Detection Models that AI Engineers Use

Tensorflow lite introduction and ARM Machine learning

Top 3 Object Detection Models

How to implement Object Detection using Intel Movidius Neural Compute Stick

Movidius install on Raspberry Pi

How to use Movidius NCAppZoo

What is Darkflow and How to Install It

Setting up and Testing YOLO

Setup GUI and VNC

Implementing Mobilenet SSD

[BONUS] How to Detect Age and Gender on Camera

Bonus: CPU Inference and Model training

OpenCV CPU inference

Introduction how to train a model on custom objects

[BONUS] Recurrent Neural Networks (Theory)

Cool Resources for Students

[NEW] XR Developers Podcast with Ritesh Kanjee


Reviews

R
Robert28 June 2020

Very knowledgable but is going too fast and the transcript is really miserable. Could not figure out what is CNN! explain. I think having a framework which is shared at the begining would have been helpful.

A
Alvaro4 January 2020

Las partes de programación pasan muy rápido, sin tiempo de digerirlo. Por otra parte, los videos sobre ANN son más ilustrativos y entendibles.

C
Carlos22 August 2019

The explanations for the installation and use of the Intel Movidius compute stick are not very involved, there are several configuration parameters that he changes without explaining why or what they mean. There is not a good explanation of how or why the compute stick improves the performance of the pi for ML. The use of the compute stick represents less than than 50 percent of the total duration of the course, the rest are introductory machine learning videos.

W
Wanjoo20 August 2019

You should focus on students so that they can actually learn from the "process" instead of showing off what you know.

E
Ed10 August 2019

Brief but to the point gives you enough information to get started and is a little easier then the online documentation by Intel

A
Asier8 August 2019

Muy flojo, presenta varias ideas pero las trata de manera superficial. La otra mitad del curso es una colección de recetas para instalar el entorno y varias demos. Solo aplica para la versión 1 de neural compute stick.

R
Robi12 July 2019

The theories were good but how it was applied was not aligned. The application portion was about installing and setting up the RPi and movidius. not much was also discussed about it except installation instructions.

A
Andras1 April 2019

it was correct and godd lecture. It was a little bit fast but I will check it more to understand it clearly.

H
Hassane16 February 2019

I was able to finish all the experiments. Learn how to use Movidius with videos to detect objects. For me, it was a fun experience. Laszlo is a good instructor. thank you for your insights and valuable resources. Best regards,

J
Joel23 December 2018

This course does not support the new version (v02) of the Movidius, now called exactly 'Neural Compute Stick 2'. Also this new hardware does not (yet) support any RPi Linux-dist. This should have been clearly stated in the course description. (I´ll refund the course.) Other than that it was ok. Not deep though, just a brief intro. More info here; https://ncsforum.movidius.com/discussion/1302/intel-neural-compute-stick-2-information

C
Christoph29 November 2018

Quick intro to the Movidius on Raspberry. Everything works as described. Very nice theoretical chapters on Neural Networks.

M
Mathew25 November 2018

Good mix of theory and practical - I especially enjoyed the level at which the theoretical components were presented. Not too in depth on the low level theory - just the right level. Lot of components installed that I wouldn't mind a little more info on - but I'm waiting for the Movidius. Hopefully I can reach out to Laszlo when the unit arrives if still unclear on those components. Even the bonus material was intriguing and pleasant surprise. Great course - thank you. Now I'll have to find your RNN course based on the bonus content!!!


1630654

Udemy ID

4/4/2018

Course created date

10/24/2019

Course Indexed date
Bot
Course Submitted by