by Shuai Zheng | Released October 2018 | ISBN: 9781788625814

Practical use cases will teach you to code once and run your Deep Learning models anywhereAbout This VideoGet acquainted with Caffe2 for fast, effective deep learningTrain your own neural networks with ease A quick concise guide filled with practical examplesIn DetailCaffe2, open-sourced by Facebook, is a simple, flexible framework for efficient deep learning. This course will teach you about Caffe2 and show you how to train your deep learning models.The course starts off with the basics of Caffe2 such as blobs, workspaces, operators, and nets; moving on, you will learn how to build a model using Caffe2's new API brew. You will also learn how to create Convolutional Neural Networks (CNNs) that can identify not only handwriting but also fashion items from an image. You will work on transferring learning to allow you to work with CNN's for image recognition by fine-tuning models that are already pre-trained on a large-scale dataset. We cover common models such as ResNet-50. Finally, the course will show you how to deploy your models on any platform.By the end of this course, you will be able to effectively train Deep Learning models with Caffe2, providing you with high-performance and first-class support for large-scale distributed training, mobile deployment, new hardware support, and flexibility.All the code files for this course are available on Github at https://github.com/PacktPublishing/Hands-On-Deep-Learning-with-Caffe2 Show and hide more

1. Chapter 1 : Getting Started with Caffe2
   • The Course Overview 00:01:39
   • Why Deep Learning? 00:03:39
   • Machine Learning Categories 00:04:29
   • Why Caffe2? 00:05:02
   • Install and Set Up Caffe2 00:07:00
   • Build a Caffe2 Docker 00:08:14
2. Chapter 2 : Basic Elements
   • Definition of a Computational Graph Through Examples 00:04:22
   • Introduce Workspace, Operators, and Nets 00:01:23
   • Working with Computational Graphs 00:09:21
3. Chapter 3 : Building Blocks of a Training Model
   • Housing Price Prediction 00:03:04
   • Representing a Linear Regression Model in a Computational Graph 00:04:30
   • Training Procedure 00:03:15
   • Training a Linear Regression Model 00:01:58
4. Chapter 4 : Supervised Learning and Transfer Learning
   • Fashion Product Recognition Problem 00:01:20
   • What Is Supervised Learning? 00:09:41
   • What Is Transfer Learning? 00:00:53
   • Model Zoo in Caffe2 00:01:19
   • Fine-Tune a Model for Recognizing Fashion Products 00:03:22
5. Chapter 5 : Sequence-to-Sequence Learning
   • Chatbot Customer Service 00:03:22
   • What Is Sequence-to-Sequence Learning? 00:02:38
   • What Are RNNs and LSTMs? 00:01:38
   • Training an RNN-Based Model to Write like Shakespeare 00:12:01
6. Chapter 6 : Reinforcement Learning
   • Why Deep Reinforcement Learning? 00:02:39
   • What Is Deep Reinforcement Learning? 00:03:04
   • What Is Deep Q-Network? 00:02:46
   • Training a Deep Q- Network for Solving the Cart-Pole Problem 00:08:09
7. Chapter 7 : Running AI in Your Hands
   • AI on Mobile Devices Using Face ID 00:02:39
   • Challenges in Running AI Models on Mobile Devices 00:02:42
   • SequeezeNet 00:01:30
   • Deploy SequeezeNet on a Mobile Device 00:01:44
Show and hide more