Book Image

Machine Learning Using TensorFlow Cookbook

By : Luca Massaron, Alexia Audevart, Konrad Banachewicz
Book Image

Machine Learning Using TensorFlow Cookbook

By: Luca Massaron, Alexia Audevart, Konrad Banachewicz

Overview of this book

The independent recipes in Machine Learning Using TensorFlow Cookbook will teach you how to perform complex data computations and gain valuable insights into your data. Dive into recipes on training models, model evaluation, sentiment analysis, regression analysis, artificial neural networks, and deep learning - each using Google’s machine learning library, TensorFlow. This cookbook covers the fundamentals of the TensorFlow library, including variables, matrices, and various data sources. You’ll discover real-world implementations of Keras and TensorFlow and learn how to use estimators to train linear models and boosted trees, both for classification and regression. Explore the practical applications of a variety of deep learning architectures, such as recurrent neural networks and Transformers, and see how they can be used to solve computer vision and natural language processing (NLP) problems. With the help of this book, you will be proficient in using TensorFlow, understand deep learning from the basics, and be able to implement machine learning algorithms in real-world scenarios.

Related Content you might be interested in

Current Title:

Small book image
Machine Learning Using TensorFlow Cookbook
Luca Massaron | Alexia Audevart | Konrad Banachewicz
Feb, 2021 | 416 pages
Small book image
TensorFlow Machine Learning Cookbook
Nick McClure
Feb, 2017 | 370 pages
Small book image
TensorFlow 2.0 Quick Start Guide
Tony Holdroyd
Mar, 2019 | 196 pages
Small book image
What's New in TensorFlow 2.0
Alizishaan Khatri | Ajay Baranwal | Tanish Baranwal
Aug, 2019 | 202 pages
Table of Contents (15 chapters)
Preface
Preface
Who this book is for
What this book covers
To get the most out of this book
Get in touch
1
Getting Started with TensorFlow 2.x
Getting Started with TensorFlow 2.x
How TensorFlow works
Declaring variables and tensors
Using eager execution
Working with matrices
Declaring operations
Implementing activation functions
Working with data sources
Additional resources
Free Chapter
2
The TensorFlow Way
The TensorFlow Way
Operations using eager execution
Layering nested operations
Working with multiple layers
Implementing loss functions
Implementing backpropagation
Working with batch and stochastic training
Combining everything together
3
Keras
Keras
Introduction
Understanding Keras layers
Using the Keras Sequential API
Using the Keras Functional API
Using the Keras Subclassing API
Using the Keras Preprocessing API
4
Linear Regression
Linear Regression
Learning the TensorFlow way of linear regression
Turning a Keras model into an Estimator
Understanding loss functions in linear regression
Implementing Lasso and Ridge regression
Implementing logistic regression
Resorting to non-linear solutions
Using Wide & Deep models
5
Boosted Trees
Boosted Trees
Introduction
6
Neural Networks
Neural Networks
Implementing operational gates
Working with gates and activation functions
Implementing a one-layer neural network
Implementing different layers
Using a multilayer neural network
Improving the predictions of linear models
Learning to play Tic-Tac-Toe
7
Predicting with Tabular Data
Predicting with Tabular Data
Processing numerical data
Processing dates
Processing categorical data
Processing ordinal data
Processing high-cardinality categorical data
Wrapping up all the processing
Setting up a data generator
Creating custom activations for tabular data
Running a test on a difficult problem
8
Convolutional Neural Networks
Convolutional Neural Networks
Introduction
Implementing a simple CNN
Implementing an advanced CNN
Retraining existing CNN models
Applying StyleNet and the neural style project
Implementing DeepDream
9
Recurrent Neural Networks
Recurrent Neural Networks
Text generation
Sentiment classification
Stock price prediction
Open-domain question answering
Summary
10
Transformers
Transformers
Text generation
Sentiment analysis
Open-domain question answering
11
Reinforcement Learning with TensorFlow and TF-Agents
Reinforcement Learning with TensorFlow and TF-Agents
GridWorld
CartPole
MAB
12
Taking TensorFlow to Production
Taking TensorFlow to Production
Visualizing Graphs in TensorBoard
Managing Hyperparameter tuning with TensorBoard's HParams
Implementing unit tests
Using multiple executors
Parallelizing TensorFlow
Saving and restoring a TensorFlow model
Using TensorFlow Serving
13
Other Books You May Enjoy
Other Books You May Enjoy
14
Index
Index

Retraining existing CNN models

Training a new image recognition model from scratch requires a lot of time and computational power. If we can take a pre-trained network and retrain it with our images, it may save us computational time. For this recipe, we will show how to use a pre-trained TensorFlow image recognition model and fine-tune it to work on a different set of images.

We will illustrate how to use transfer learning from a pre-trained network for CIFAR-10. The idea is to reuse the weights and structure of the prior model from the convolutional layers and retrain the fully connected layers at the top of the network. This method is called fine-tuning.

Getting ready

The CNN network we are going to employ uses a very popular architecture called Inception. The Inception CNN model was created by Google and has performed very well on many image recognition benchmarks. For details, see the paper referenced in the second bullet point of the See also section...

Previous Section
End of Section 5
Next Section