Look Inside
FREE
You can see any available part of this book for free.Click the table of contents to start reading.
This practical guide to building deep learning models with the new features of TensorFlow 2.0 is filled with engaging projects, simple language, and coverage of the latest algorithms.Excellent explanations and walkthroughs to help bring you up to speed in Tensorflow 2.
In TensorFlow 2.0 in Action, you'll dig into the newest version of Google's amazing TensorFlow framework as you learn to create incredible deep learning applications. You'll develop a sentiment analyzer for movie reviews, an NLP spam classifier, and other hands-on projects.
About the Technology
TensorFlow is the go-to framework for putting deep learning into production. Created by Google, this groundbreaking tool handles repetitive low-level operations and frees you up to focus on innovating your AIs. TensorFlow encompasses almost every element of a deep learning pipeline—a one-stop solution for building, monitoring, optimizing, and deploying your models.About the book
TensorFlow 2.0 in Action teaches you to use the new features of TensorFlow 2.0 to create advanced deep learning models. You’ll learn by building hands-on projects, including an image classifier that can recognize objects, a French-to-English machine translator, and even a neural network that can write fiction.Thushan Ganegedara draws on his experience as a practitioner and teacher of deep learning to demystify concepts otherwise trapped in dense academic papers. A top StackOverflow contributor for deep learning and NLP, Thushan’s quirky stories, real-world advice, and behind-the-scenes explanations make even complex ideas easy to understand! You’ll dive into the details of modern deep learning techniques, including both transformer and attention models, and learn how pretrained models can solve your tricky data science problems. When you’re done, you’ll be ready to implement state-of-the-art deep learning applications and know the design secrets behind their success.
Table of Contents takes you straight to the bookdetailed table of contents
Part 1: Basics of TensorFlow 2.0
1 The amazing world of TensorFlow
1.1 What is TensorFlow?
1.2 Central Processing Unit (CPU) vs Graphical Processing Unit (GPU)
1.3 When and when not to use TensorFlow?
1.3.1 When to use TensorFlow?
1.3.2 When not to use TensorFlow?
1.4 What will this book teach you?
1.4.1 TensorFlow fundamentals
1.4.2 Deep learning algorithms
1.4.3 Monitoring and optimization
1.5 Who is this book for?
1.6 Should we really care about Python and TensorFlow 2?
1.7 Summary
2 TensorFlow 2
2.1 TensorFlow 2 vs TensorFlow 1
2.1.1 How does TensorFlow operate under the hood?
2.1.2 Visiting an old friend: TensorFlow 1
2.2 Building blocks in TensorFlow
2.2.1 Understanding tf.Variable
2.2.2 Understanding tf.Tensor
2.2.3 Understanding tf.Operation
2.3 Neural network related computations in TensorFlow
2.3.1 Matrix multiplication
2.3.2 Convolution operation
2.3.3 Pooling operation
2.4 Summary
2.5 Answers to exercises:
3 Keras & Data Retrieval in TensorFlow 2
3.1 Keras model building APIs
3.1.1 Introducing the dataset
3.1.2 The Sequential API
3.1.3 The Functional API
3.1.4 The Sub-Classing API
3.2 Retrieving data for TensorFlow/Keras models
3.2.1 tf.data API
3.2.2 Keras DataGenerators
3.2.3 tensorflow-datasets package
3.3 Summary
4 Dipping toes in Deep Learning
4.1 Fully connected networks
4.1.1 Understanding the data
4.1.2 Autoencoder model
4.2 Convolution neural networks
4.2.1 Understanding the data
4.2.2 Implementing the network
4.3 One Step at a Time: Recurrent neural networks
4.3.1 Understanding the data
4.3.2 Implementing the model
4.3.3 Predicting future CO2 values with the trained model
4.3.4 Summary
4.4 Answers
5 State-of-the-art in deep learning: Transformers
5.1 Representing text as numbers
5.2 Understanding the Transformer model
5.2.1 The encoder-decoder view of the Transformer
5.2.2 Diving deeper
5.2.3 Self-attention layer
5.2.4 Understanding self-attention using scalars
5.2.5 Self-attention as a cooking competition
5.2.6 Masked self-attention layers
5.2.7 Multi-head attention
5.2.8 Fully-connected layer
5.2.9 Putting everything together
5.3 Summary
5.4 Answers
Part 2: Look Ma No Hands! Deep Networks in Real World
6 Teaching machines to see: Image classification with CNNs
7 Teaching machines to see better and making CNNs confess
8 Telling things apart: Image Segmentation in TensorFlow
9 Natural Language Processing in TensorFlow 2
Part 3: Advance Deep Networks for Complex Problems
10 Sequence-to-sequence learning with TensorFlow
11 Transfer learning with Transformers
12 What to watch next? Recommenders in TensorFlow
13 TensorBoard: Big brother of TensorFlow
Appendixes
Appendix A: Setting up the environment
What's inside
- Fundamentals of TensorFlow
- Implement deep learning networks
- Picking a high-level Keras API
- Write comprehensive end-to-end data pipelines
- Build models for computer vision and natural language processing
- Utilize pretrained NLP models
- Recent algorithms including transformers, attention models, and ElMo
About the author
Thushan Ganegedara is a data scientist with QBE. He holds a PhD in machine learning from the University of Sydney and he has worked with TensorFlow for almost 5 years. Thushan is also one of the most active answer providers for TensorFlow and TensorFlow2.0 tags on Stackoverflow, a DataCamp instructor, and has authored a book and video course on NLP with TensorFlow.placing your order...
Don't refresh or navigate away from the page.
Manning Early Access Program (MEAP)
Read chapters as they are written, get the finished eBook as soon as it’s ready, and receive the pBook long before it's in bookstores.
Prices displayed in rupees will be charged in USD when you check out.
customers also reading
This book
1°
2°
3°
FREE domestic shipping on three or more pBooks