Book Image

TensorFlow Machine Learning Cookbook

By : Nick McClure
Book Image

TensorFlow Machine Learning Cookbook

By: Nick McClure

Overview of this book

TensorFlow is an open source software library for Machine Intelligence. The independent recipes in this book will teach you how to use TensorFlow for complex data computations and will let you dig deeper and gain more insights into your data than ever before. You’ll work through recipes on training models, model evaluation, sentiment analysis, regression analysis, clustering analysis, artificial neural networks, and deep learning – each using Google’s machine learning library TensorFlow. This guide starts with the fundamentals of the TensorFlow library which includes variables, matrices, and various data sources. Moving ahead, you will get hands-on experience with Linear Regression techniques with TensorFlow. The next chapters cover important high-level concepts such as neural networks, CNN, RNN, and NLP. Once you are familiar and comfortable with the TensorFlow ecosystem, the last chapter will show you how to take it to production.

Related Content you might be interested in

Current Title:

Small book image
TensorFlow Machine Learning Cookbook
Nick McClure
Feb, 2017 | 370 pages
Small book image
Machine Learning Using TensorFlow Cookbook
Alexia Audevart | Konrad Banachewicz | Luca Massaron
Feb, 2021 | 416 pages
Small book image
Predictive Analytics with TensorFlow
Md Rezaul Karim
Nov, 2017 | 522 pages
Small book image
Deep Learning with TensorFlow
Md Rezaul Karim | Giancarlo Zaccone
Mar, 2018 | 484 pages
Table of Contents (19 chapters)
TensorFlow Machine Learning Cookbook
TensorFlow Machine Learning Cookbook
Credits
Credits
About the Author
About the Author
About the Reviewer
About the Reviewer
www.PacktPub.com
www.PacktPub.com
Customer Feedback
Customer Feedback
Preface
Preface
Free Chapter
1
Getting Started with TensorFlow
Getting Started with TensorFlow
Introduction
How TensorFlow Works
Declaring Tensors
Using Placeholders and Variables
Working with Matrices
Declaring Operations
Implementing Activation Functions
Working with Data Sources
Additional Resources
2
The TensorFlow Way
The TensorFlow Way
Introduction
Operations in a Computational Graph
Layering Nested Operations
Working with Multiple Layers
Implementing Loss Functions
Implementing Back Propagation
Working with Batch and Stochastic Training
Combining Everything Together
Evaluating Models
3
Linear Regression
Linear Regression
Introduction
Using the Matrix Inverse Method
Implementing a Decomposition Method
Learning The TensorFlow Way of Linear Regression
Understanding Loss Functions in Linear Regression
Implementing Deming regression
Implementing Lasso and Ridge Regression
Implementing Elastic Net Regression
Implementing Logistic Regression
4
Support Vector Machines
Support Vector Machines
Introduction
Working with a Linear SVM
Reduction to Linear Regression
Working with Kernels in TensorFlow
Implementing a Non-Linear SVM
Implementing a Multi-Class SVM
5
Nearest Neighbor Methods
Nearest Neighbor Methods
Introduction
Working with Nearest Neighbors
Working with Text-Based Distances
Computing with Mixed Distance Functions
Using an Address Matching Example
Using Nearest Neighbors for Image Recognition
6
Neural Networks
Neural Networks
Introduction
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
Natural Language Processing
Natural Language Processing
Introduction
Working with bag of words
Implementing TF-IDF
Working with Skip-gram Embeddings
Working with CBOW Embeddings
Making Predictions with Word2vec
Using Doc2vec for Sentiment Analysis
8
Convolutional Neural Networks
Convolutional Neural Networks
Introduction
Implementing a Simpler CNN
Implementing an Advanced CNN
Retraining Existing CNNs models
Applying Stylenet/Neural-Style
Implementing DeepDream
9
Recurrent Neural Networks
Recurrent Neural Networks
Introduction
Implementing RNN for Spam Prediction
Implementing an LSTM Model
Stacking multiple LSTM Layers
Creating Sequence-to-Sequence Models
Training a Siamese Similarity Measure
10
Taking TensorFlow to Production
Taking TensorFlow to Production
Introduction
Implementing unit tests
Using Multiple Executors
Parallelizing TensorFlow
Taking TensorFlow to Production
Productionalizing TensorFlow – An Example
11
More with TensorFlow
More with TensorFlow
Introduction
Visualizing graphs in Tensorboard
There's more…
Working with a Genetic Algorithm
Clustering Using K-Means
Solving a System of ODEs
Index
Index

Taking TensorFlow to Production

If we want to use our machine learning scripts in a production setting, there are some points to consider for best practices. Here, we will help to point out some best practices.

Getting ready

In this recipe, we want to summarize and condense various tips for bringing TensorFlow to production. We will cover how to best save and load vocabularies, graphs, variables, and model checkpoints. We will also talk about how to use TensorFlow's command-line argument parser and change the logging verbosity of TensorFlow.

How to do it…

  1. When running a TensorFlow program, we may want to be sure that no other graph session is already in memory, or that we clear the graph session every time while debugging a program. We can accomplish this as follows:

    from tensorflow.python.framework import ops
ops.reset_default_graph()

  2. When dealing with text (or any data pipeline), we need to be sure that we save how we process the data, so that we can process future evaluation data the same way...

Previous Section
End of Section 6
Next Section