by Christian Fanli Ramsey, Haohan Wang | Released July 2018 | ISBN: 9781788621601

Take your Deep Learning skills to the next level using TensorFlow and Google Cloud AIAbout This VideoCover the fundamental concepts of Deep Learning Design your model from data ingestion to deployment at scaleUse distributed techniques using TensorFlow and deploy your model with Google Cloud MLE.In DetailDeep Learning uses a cascade of multiple layers of nonlinear processing units for feature extraction and transformation on large volumes of data in order to make decisions about high dimensional data.If you're looking to scale out your Deep Learning models and deploy your model into production then look no further because this video course will help you get the most out of TensorFlow and Keras to accelerate the training of your Deep Learning models and deploy your model at scale on the Cloud. Tools and frameworks such as TensorFlow, Keras, and Google Cloud MLE are used to showcase the strengths of various approaches, trade-offs, and building blocks for creating, training and evaluating your distributed deep learning models with GPU(s) and deploying your model to the Cloud. You will learn how to design and train your deep learning models and scale them out for larger datasets and complex neural network architectures on multiple GPUs using Google Cloud ML Engine. You'll learn distributed techniques such as how parallelism and distribution work using low-level TensorFlow and high-level TensorFlow APIs and Keras.Towards the end of the course, you will develop, train, and deploy your models using TensorFlow and Google Cloud Machine Learning Engine.The code bundle for this video course is available at - https://github.com/PacktPublishing/Applied-Deep-Learning-with-TensorFlow-and-Google-Cloud-AI Show and hide more Publisher Resources Download Example Code

1. Chapter 1 : Installation
   • The Course Overview 00:10:34
   • Installation 00:23:17
2. Chapter 2 : Keras Introduction
   • Introduction 00:06:28
   • Keras Backends 00:11:38
   • Design and Compile a Model 00:17:59
   • Model Training, Evaluation, and Prediction 00:11:20
   • Training with Data Augmentation 00:18:04
   • Training with Transfer Learning and Data Augmentation 00:15:34
3. Chapter 3 : Scaling Deep Learning Using Keras and TensorFlow
   • Introduction to TensorFlow 00:20:31
   • Introduction to TensorBoard 00:23:13
   • Types of Parallelism in Deep Learning – Synchronous and Asynchronous 00:12:46
   • Distributed TensorFlow 00:33:00
   • Configuring Keras to use TensorFlow for Distributed Problems 00:22:29
4. Chapter 4 : Training, Tuning, and Serving Our Model in the Cloud
   • Introduction 00:03:25
   • Introduction to Google Cloud Machine Learning Engine 00:04:29
   • Datasets, Feature Columns, and Estimators 00:10:36
   • Representing Data in TensorFlow 00:08:16
   • Quick Dive into TensorFlow Estimators 00:08:16
   • Creating Data Input Pipelines 00:05:21
   • Setting Up Our Estimator 00:05:59
   • Packaging Our Model 00:06:00
   • Training with Google Cloud ML Engine 00:12:11
   • Hyperparameter Tuning in the Cloud 00:22:10
   • Deploying Our Model for Prediction 00:21:09
   • Creating Our Prediction API 00:07:54
   • Wrapping Up 00:04:33
   • Course Summary 00:10:12
Show and hide more