TensorFlow Deep Learning Projects

Book description

Leverage the power of Tensorflow to design deep learning systems for a variety of real-world scenarios

About This Book

  • Build efficient deep learning pipelines using the popular Tensorflow framework
  • Train neural networks such as ConvNets, generative models, and LSTMs
  • Includes projects related to Computer Vision, stock prediction, chatbots and more

Who This Book Is For

This book is for data scientists, machine learning developers as well as deep learning practitioners, who want to build interesting deep learning projects that leverage the power of Tensorflow. Some understanding of machine learning and deep learning, and familiarity with the TensorFlow framework is all you need to get started with this book.

What You Will Learn

  • Set up the TensorFlow environment for deep learning
  • Construct your own ConvNets for effective image processing
  • Use LSTMs for image caption generation
  • Forecast stock prediction accurately with an LSTM architecture
  • Learn what semantic matching is by detecting duplicate Quora questions
  • Set up an AWS instance with TensorFlow to train GANs
  • Train and set up a chatbot to understand and interpret human input
  • Build an AI capable of playing a video game by itself ?and win it!

In Detail

TensorFlow is one of the most popular frameworks used for machine learning and, more recently, deep learning. It provides a fast and efficient framework for training different kinds of deep learning models, with very high accuracy. This book is your guide to master deep learning with TensorFlow with the help of 10 real-world projects.

TensorFlow Deep Learning Projects starts with setting up the right TensorFlow environment for deep learning. Learn to train different types of deep learning models using TensorFlow, including Convolutional Neural Networks, Recurrent Neural Networks, LSTMs, and Generative Adversarial Networks. While doing so, you will build end-to-end deep learning solutions to tackle different real-world problems in image processing, recommendation systems, stock prediction, and building chatbots, to name a few. You will also develop systems that perform machine translation, and use reinforcement learning techniques to play games.

By the end of this book, you will have mastered all the concepts of deep learning and their implementation with TensorFlow, and will be able to build and train your own deep learning models with TensorFlow confidently.

Style and approach

This book contains 10 unique, end-to-end projects covering all aspects of deep learning and their implementations with TensorFlow. Each project will equip you with a unique skillset in training efficient deep learning models, and empower you to implement your own projects more confidently

Table of contents

  1. Title Page
  2. Copyright and Credits
    1. TensorFlow Deep Learning Projects
  3. Packt Upsell
    1. Why subscribe?
    2. PacktPub.com
  4. Contributors
    1. About the authors
    2. About the reviewer
    3. Packt is searching for authors like you
  5. Preface
    1. Who this book is for
    2. What this book covers
    3. To get the most out of this book
      1. Download the example code files
      2. Conventions used
    4. Get in touch
      1. Reviews
  6. Recognizing traffic signs using Convnets
    1. The dataset
    2. The CNN network
    3. Image preprocessing
    4. Train the model and make predictions
    5. Follow-up questions
    6. Summary
  7. Annotating Images with Object Detection API
    1. The Microsoft common objects in context
    2. The TensorFlow object detection API
      1. Grasping the basics of R-CNN, R-FCN and SSD models
    3. Presenting our project plan
      1. Setting up an environment suitable for the project
      2. Protobuf compilation
        1. Windows installation
        2. Unix installation
    4. Provisioning of the project code
      1. Some simple applications
      2. Real-time webcam detection
    5. Acknowledgements
    6. Summary
  8. Caption Generation for Images
    1. What is caption generation?
    2. Exploring image captioning datasets
      1. Downloading the dataset
    3. Converting words into embeddings
    4. Image captioning approaches
      1. Conditional random field
      2. Recurrent neural network on convolution neural network
      3. Caption ranking
      4. Dense captioning
      5. RNN captioning
      6. Multimodal captioning
      7. Attention-based captioning
    5. Implementing a caption generation model
    6. Summary
  9. Building GANs for Conditional Image Creation
    1. Introducing GANs
      1. The key is in the adversarial approach
      2. A cambrian explosion
        1. DCGANs
        2. Conditional GANs
    2. The project
      1. Dataset class
      2. CGAN class
    3. Putting CGAN to work on some examples
      1. MNIST
      2. Zalando MNIST
      3. EMNIST
      4. Reusing the trained CGANs
    4. Resorting to Amazon Web Service
    5. Acknowledgements
    6. Summary
  10. Stock Price Prediction with LSTM
    1. Input datasets – cosine and stock price
    2. Format the dataset
    3. Using regression to predict the future prices of a stock
    4. Long short-term memory – LSTM 101
    5. Stock price prediction with LSTM
    6. Possible follow - up questions
    7. Summary
  11. Create and Train Machine Translation Systems
    1. A walkthrough of the architecture
    2. Preprocessing of the corpora
    3. Training the machine translator
    4. Test and translate
      1. Home assignments
    5. Summary
  12. Train and Set up a Chatbot, Able to Discuss Like a Human
    1. Introduction to the project
    2. The input corpus
    3. Creating the training dataset
    4. Training the chatbot
    5. Chatbox API
      1. Home assignments
    6. Summary
  13. Detecting Duplicate Quora Questions
    1. Presenting the dataset
    2. Starting with basic feature engineering
    3. Creating fuzzy features
    4. Resorting to TF-IDF and SVD features
    5. Mapping with Word2vec embeddings
    6. Testing machine learning models
    7. Building a TensorFlow model
    8. Processing before deep neural networks
    9. Deep neural networks building blocks
    10. Designing the learning architecture
    11. Summary
  14. Building a TensorFlow Recommender System
    1. Recommender systems
    2. Matrix factorization for recommender systems
      1. Dataset preparation and baseline
      2. Matrix factorization
      3. Implicit feedback datasets
      4. SGD-based matrix factorization
      5. Bayesian personalized ranking
    3. RNN for recommender systems
      1. Data preparation and baseline
      2. RNN recommender system in TensorFlow
    4. Summary
  15. Video Games by Reinforcement Learning
    1. The game legacy
    2. The OpenAI version
    3. Installing OpenAI on Linux (Ubuntu 14.04 or 16.04)
      1. Lunar Lander in OpenAI Gym
    4. Exploring reinforcement learning through deep learning
      1. Tricks and tips for deep Q-learning
      2. Understanding the limitations of deep Q-learning
    5. Starting the project
      1. Defining the AI brain
      2. Creating memory for experience replay
      3. Creating the agent
      4. Specifying the environment
      5. Running the reinforcement learning process
    6. Acknowledgements
    7. Summary
  16. Other Books You May Enjoy
    1. Leave a review - let other readers know what you think

Product information

  • Title: TensorFlow Deep Learning Projects
  • Author(s): Luca Massaron, Alberto Boschetti, Alexey Grigorev, Abhishek Thakur, Rajalingappaa Shanmugamani
  • Release date: March 2018
  • Publisher(s): Packt Publishing
  • ISBN: 9781788398060