Book Image

Mastering TensorFlow 1.x

Book Image

Mastering TensorFlow 1.x

Overview of this book

TensorFlow is the most popular numerical computation library built from the ground up for distributed, cloud, and mobile environments. TensorFlow represents the data as tensors and the computation as graphs. This book is a comprehensive guide that lets you explore the advanced features of TensorFlow 1.x. Gain insight into TensorFlow Core, Keras, TF Estimators, TFLearn, TF Slim, Pretty Tensor, and Sonnet. Leverage the power of TensorFlow and Keras to build deep learning models, using concepts such as transfer learning, generative adversarial networks, and deep reinforcement learning. Throughout the book, you will obtain hands-on experience with varied datasets, such as MNIST, CIFAR-10, PTB, text8, and COCO-Images. You will learn the advanced features of TensorFlow1.x, such as distributed TensorFlow with TF Clusters, deploy production models with TensorFlow Serving, and build and deploy TensorFlow models for mobile and embedded devices on Android and iOS platforms. You will see how to call TensorFlow and Keras API within the R statistical software, and learn the required techniques for debugging when the TensorFlow API-based code does not work as expected. The book helps you obtain in-depth knowledge of TensorFlow, making you the go-to person for solving artificial intelligence problems. By the end of this guide, you will have mastered the offerings of TensorFlow and Keras, and gained the skills you need to build smarter, faster, and efficient machine learning and deep learning systems.

Preface

Who this book is for

What this book covers

To get the most out of this book

Free Chapter

TensorFlow 101

What is TensorFlow?

TensorFlow core

Data flow graph or computation graph

High-Level Libraries for TensorFlow

High-Level Libraries for TensorFlow

TF Estimator - previously TF Learn

Keras 101

Installing Keras

Neural Network Models in Keras

Creating the Keras model

Adding Layers to the Keras Model

Compiling the Keras model

Training the Keras model

Predicting with the Keras model

Additional modules in Keras

Keras sequential model example for MNIST dataset

Classical Machine Learning with TensorFlow

Classical Machine Learning with TensorFlow

Simple linear regression

Multi-regression

Regularized regression

Classification using logistic regression

Binary classification

Multiclass classification

Neural Networks and MLP with TensorFlow and Keras

Neural Networks and MLP with TensorFlow and Keras

MultiLayer Perceptron

MLP for image classification

MLP for time series regression

RNN with TensorFlow and Keras

RNN with TensorFlow and Keras

Simple Recurrent Neural Network

TensorFlow for RNN

Application areas of RNNs

RNN in Keras for MNIST data

RNN for Time Series Data with TensorFlow and Keras

RNN for Time Series Data with TensorFlow and Keras

Airline Passengers dataset

Preprocessing the dataset for RNN models with TensorFlow

Simple RNN in TensorFlow

LSTM in TensorFlow

GRU in TensorFlow

Preprocessing the dataset for RNN models with Keras

Simple RNN with Keras

LSTM with Keras

RNN for Text Data with TensorFlow and Keras

RNN for Text Data with TensorFlow and Keras

Word vector representations

Preparing the data for word2vec models

skip-gram model with TensorFlow

Visualize the word embeddings using t-SNE

skip-gram model with Keras

Text generation with RNN models in TensorFlow and Keras

CNN with TensorFlow and Keras

CNN with TensorFlow and Keras

Understanding convolution

Understanding pooling

CNN architecture pattern - LeNet

LeNet for MNIST data

LeNet for CIFAR10 Data

Autoencoder with TensorFlow and Keras

Autoencoder with TensorFlow and Keras

Autoencoder types

Stacked autoencoder in TensorFlow

Stacked autoencoder in Keras

Denoising autoencoder in TensorFlow

Denoising autoencoder in Keras

Variational autoencoder in TensorFlow

Variational autoencoder in Keras

TensorFlow Models in Production with TF Serving

TensorFlow Models in Production with TF Serving

Saving and Restoring models in TensorFlow

Saving and restoring Keras models

TensorFlow Serving

TF Serving in the Docker containers

TensorFlow Serving on Kubernetes

Transfer Learning and Pre-Trained Models

Transfer Learning and Pre-Trained Models

ImageNet dataset

Retraining or fine-tuning models

COCO animals dataset and pre-processing images

VGG16 in TensorFlow

Image preprocessing in TensorFlow for pre-trained VGG16

Inception v3 in TensorFlow

Deep Reinforcement Learning

Deep Reinforcement Learning

Applying simple policies to a cartpole game

Reinforcement learning 101

Naive Neural Network policy for Reinforcement Learning

Implementing Q-Learning

Generative Adversarial Networks

Generative Adversarial Networks

Generative Adversarial Networks 101

Best practices for building and training GANs

Simple GAN with TensorFlow

Simple GAN with Keras

Deep Convolutional GAN with TensorFlow and Keras

Distributed Models with TensorFlow Clusters

Distributed Models with TensorFlow Clusters

Strategies for distributed execution

TensorFlow clusters

TensorFlow Models on Mobile and Embedded Platforms

TensorFlow Models on Mobile and Embedded Platforms

TensorFlow on mobile platforms

TF Mobile in Android apps

TF Mobile demo on Android

TF Mobile in iOS apps

TF Mobile demo on iOS

TensorFlow Lite

TF Lite Demo on Android

TF Lite demo on iOS

TensorFlow and Keras in R

TensorFlow and Keras in R

Installing TensorFlow and Keras packages in R

TF core API in R

TF estimator API in R

TensorBoard in R

The tfruns package in R

Debugging TensorFlow Models

Debugging TensorFlow Models

Fetching tensor values with tf.Session.run()

Printing tensor values with tf.Print()

Asserting on conditions with tf.Assert()

Debugging with the TensorFlow debugger (tfdbg)

Tensor Processing Units

Tensor Processing Units

Other Books You May Enjoy

Other Books You May Enjoy

Leave a review - let other readers know what you think

Customer Reviews

5 star

0

4 star

0

3 star

0

2 star

0

1 star

0

Strategies for distributed execution

For distributing the training of the single model across multiple devices or nodes, there are the following strategies:

Model Parallel: Divide the model into multiple subgraphs and place the separate graphs on different nodes or devices. The subgraphs perform their computation and exchange the variables as required.
Data Parallel: Divide the data into batches and run the same model on multiple nodes or devices, combining the parameters on a master node. Thus the worker nodes train the model on batches of data and send the parameter updates to the master node, also known as the parameter server.

The preceding diagram shows the data parallel approach where the model replicas read the partitions of data in batches and send the parameter updates to the parameter servers, and parameter servers send the updated parameters back to the model replicas...