by Laszlo Benke | Publisher: Packt Publishing | Release Date: February 2019 | ISBN: 9781838640453

Learn how to Accelerate your AI Object Detection Models 5X faster on a Raspberry Pi 3, using Intel Movidius for Deep Learning.About This VideoGetting 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 NCS2 (the newest version of the Movidius) is not supported by the Raspberry Pi, if there will be some useful information about that, then we will make an announcement (or lecture) as soon as possible.Run Yolo and Mobilenet SSD object detection models in the recorded or live videoIn DetailLearn 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 run 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 a 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. Let me help you get fast results. Enrol now, by clicking the button and let us show you how to develop Accelerated AI on Raspberry Pi.All the code files are placed at https://github.com/PacktPublishing/-Accelerate-Deep-Learning-on-Raspberry-Pi-Downloading the example code for this course: You can download the example code files for all Packt video courses you have purchased from your account at http://www.PacktPub.com. If you purchased this course elsewhere, you can visit http://www.PacktPub.com/support and register to have the files e-mailed directly to you.

1. Chapter 1 : Introduction to the Course
   • Introduction to the Course 00:01:06
   • Hardware Requirements for Deep Learning 00:01:50
2. Chapter 2 : The Super Simple Way to Get Started with Raspberry Pi
   • How to Install Raspbian Operating System on Raspberry Pi 00:03:40
   • Initial Raspbian OS Setup on Raspberry PI 00:06:11
3. Chapter 3 : Deep learning Fundamentals (theory)
   • Multilayer Perceptron - Artificial Neural Network (Theory) 00:18:31
   • Convolutional Neural Network (Theory) 00:11:18
4. Chapter 4 : Object Detection Models that AI Engineers Use
   • Tensorflow lite introduction and ARM Machine learning 00:02:28
   • Top 3 Object Detection Models 00:02:33
5. Chapter 5 : How to implement Object Detection using Intel Movidius Neural Compute Stick
   • Movidius install on Raspberry Pi 00:05:54
   • How to use Movidius NCAppZoo 00:01:37
   • What is Darkflow and How to Install It 00:02:03
   • Setting up and Testing YOLO 00:04:30
   • Implementing Mobilenet SSD 00:02:02
   • [BONUS] How to Detect Age and Gender on Camera 00:01:57
6. Chapter 6 : Bonus: CPU Inference and Model training
   • [BONUS] Recurrent Neural Networks (Theory) 00:11:52