Generative Adversarial Networks with Python
Deep Learning Generative Models for Image Synthesis and Image Translation
Generative Adversarial Networks are a type of deep learning generative model that can achieve startlingly photorealistic results on a range of image synthesis and image-to-image translation problems.
In this new Ebook written in the friendly Machine Learning Mastery style that you’re used to, skip the math and jump straight to getting results.
With clear explanations, standard Python libraries, and step-by-step tutorial lessons, you’ll discover how to develop Generative Adversarial Networks for your own computer vision projects.
About this Ebook:
- Read on all devices: English PDF format EBook, no DRM.
- Tons of tutorials: 29 step-by-step lessons, 652 pages.
- Foundations: intuitions behind generators, discriminator, more.
- Real-world projects: detect objects, recognize faces, more.
- Working code: 113 Python (.py) code files included.
Clear, Complete End-to-End Examples.
Click to jump straight to the packages.
…so, What are Generative Adversarial Networks?
Generative Adversarial Networks, or GANs, are a deep-learning-based generative model.
More generally, GANs are a model architecture for training a generative model, and it is most common to use deep learning models in this architecture, such as convolutional neural networks or CNNs for short.
GANs are a clever way of training a generative model by framing the problem as supervised learning with two sub-models: the generator model that we train to generate new examples, and the discriminator model that tries to classify examples as either real (from your dataset) or fake (generated).
- Generator. Model that is used to generate new plausible examples from the problem domain.
- Discriminator. Model that is used to classify examples as real (from the domain) or fake (generated).
The two models are trained together in a zero-sum game, adversarially, until the discriminator model is fooled about half the time, meaning the generator model is generating plausible examples.
This is most unlike training “normal” neural network models that involve training the model to minimize loss to some point of convergence.
…so, Why are Generative Adversarial Networks so Compelling?
One of the many major advancements in the use of deep learning methods in domains such as computer vision is a technique called data augmentation.
Successful generative modeling provides an alternative and potentially more domain-specific approach for data augmentation.
In complex domains or domains with a limited amount of data, generative modeling provides a path towards more training for modeling. GANs have seen much success in this use case in domains such as deep reinforcement learning.
There are many research reasons why GANs are interesting, important, and require further study.
Among these reasons is GANs successful ability to model high-dimensional data, handle missing data, and the capacity of GANs to provide multi-modal outputs or “multiple plausible answers“.
Perhaps the most compelling application of GANs is in conditional GANs for tasks that require the generation of new examples. Three examples include:
- Image Synthesis: The ability to generate plausible images for a given collection of photographs.
- Creating Art. The ability to great new and artistic images, sketches, painting, and more.
- Image Translation. The ability to translate photographs across domains, such as from summer to winter, and more.
Perhaps the most compelling reason that GANs are widely studied, developed, and used is because of their success. GANs have been able to generate photos so realistic that humans are unable to tell that they are of objects, scenes, and people that do not exist in real life.
Astonishing is not a sufficient adjective for their capability and success.
The Challenge of Getting Started with GANs
The study and application of GANs is very new.
The technique was only first described just a few years ago.
Because the field is so young, it can be challenging to know how to get started, what to focus on, and how to best use the available techniques.
There are no good theories for how to implement and configure GAN models. All advice for applying GAN models is based on hard earned empirical findings, the same as any nascent field of study. This makes it both exciting and frustrating.
It’s exciting because although the results achieved so far, such as the automatic synthesis of large photo-realistic faces and translation of photographs from day to night, we have only scratched the surface on the capabilities of these methods.
It is frustrating because the models are fussy and prone to failure modes, even after all care was taken in the choice of model architecture, model configuration hyperparameters, and data preparation.
I study the field and carefully designed a book to give you the foundation required to begin developing and applying generative adversarial networks quickly on your own projects.
So, how can you get started and get good at using GANs fast?
This is the book I wish I had when I was getting started with Generative Adversarial Networks.
This book was born out of one thought:
How can I get you to be proficient with GANs as fast as possible?
The Machine Learning Mastery method describes that the best way of learning this material is by doing. This means the focus of the book is hands-on with projects and tutorials.
This book was designed to teach you step-by-step how to develop Generative Adversarial Networks using modern deep learning methods for your own computer vision projects.
You will be led along the critical path from a practitioner interested in GANs to a practitioner that can confidently design, configure, train and use GAN models.
This is the fastest process that I can devise for getting you proficient with Generative Adversarial Networks.
Develop Real Practical Skills That You Can Apply Immediately, such as:
- GAN Overview. Discover the GAN modeling architecture including the generator and discriminator.
- Keras API. Discover the life cycle for developing a deep learning neural network model using the Keras library.
- Upsampling Layers. Discover the specialized layers used in convolutional neural networks required for image generation.
- Training Algorithm. Discover the training algorithm used to train all GAN models in an adversarial two-player game.
- GAN Hacks. Discover the empirical tips, tricks and hacks required for the stable training of GAN models using deep convolutional networks or DCGAN.
- 1D GAN. Discover how to develop the simplest GAN for modeling a one-dimensional function.
- B&W GAN. Discover how to develop a DCGAN to synthesize simple black and white images.
- Color GAN. Discover how to develop a DCGAN to synthesize small color images.
- Latent Space. Discover how to explore the latent space of the generator model with interpolation and vector arithmetic.
- Failure Modes. Discover the ways that GAN training can fail and how to identify the different failure modes.
- Conditional Models. Discover how additional information about an image can be incorporated into the GAN architecture.
- Conditional GAN. Discover how the generator and discriminator can be made class-conditional in order to control the type of image generated.
- InfoGAN. Discover how control variables can be added to the GAN architecture to influence the image generation process.
- AC-GAN. Discover how an auxiliary classifier model can be added to the architecture to improve the performance of the GAN.
- Semi-Supervised GAN. Discover how the GAN architecture can be adapted to train a semi-supervised model for problems with very little labeled data.
- Loss Challenge. Discover the challenge of simultaneously training two interacting neural networks.
- Standard GAN loss. Discover the two approaches to implementing the GAN loss function proposed in the original paper.
- Alternate Loss. Discover a range of loss function proposed as possible beneficial alternatives to the original GAN loss.
- Least Squares Loss. Discover the Least Squares GAN or LSGAN that uses L2 loss to fit the discriminator and generator models.
- Wasserstein Loss. Discover the Wasserstein GAN or WGAN that uses Wasserstein loss to fit the discriminator and generator models.
- Image-to-image Translation. Discover the challenge of image-to-image translation in computer vision.
- Pix2Pix. Discover the Pix2Pix GAN architecture for image-to-image translation with paired training examples.
- Paired Translation. Discover how to implement the Pix2Pix models and train a model to translate satellite photos to Google maps, and the reverse.
- CycleGAN. Discover the CycleGAN architecture for image-to-image translation with unpaired training examples.
- Unpaired Translation. Discover how to implement the CycleGAN models and train a model to translate photos of horses to zebra and the reverse.
- Advanced GANs. Discover advancements in the GAN models, architecture and training that dramatically improve the state-of-the-art.
- BigGAN. Discover how the scaling up of the model capacity and training process can result in higher quality images.
- Progressive Growing GAN. Discover the incremental increase in model capacity during training can result in the generation of very high quality images.
- StyleGAN. Discover how a radical redesign of the generator model architecture can give fine-grained control over the image generation process.
…so, is this book right for YOU?
Who Is This Book For?
Let’s make sure you are in the right place.
This book is for developers that know some applied machine learning and some deep learning.
Maybe you want or need to start using GANs for image synthesis or translation on your research project or on a project at work. This book was written to help you do that quickly and efficiently by compressing years of knowledge and experience into a laser-focused course of hands-on tutorials.
This guide was written in the top-down and results-first style that you’re used to from Machine Learning Mastery.
The lessons in this book assume a few things about you.
You need to know:
- You need to know your way around basic Python.
- You may know a little of basic modeling with scikit-learn.
- You may know a little of basic modeling with Keras.
You do NOT need to be:
- You do not need to be a math wiz!
- You do not need to be a deep learning expert!
- You do not need to be a master of computer vision!
…so what will YOU know after reading it?
About Your Learning Outcomes
This book will teach you how to get results.
After reading and working through this book,
you will know:
- How to use upsampling and inverse convolutional layers in deep convolutional neural network models.
- How to implement the training procedure for fitting GAN models with the Keras deep learning library.
- How to implement best practice heuristics for the successful configuration and training of GAN models.
- How to develop and train simple GAN models for image synthesis for black and white and color images.
- How to explore the latent space for image generation with point interpolation and vector arithmetic.
- How to evaluate GAN models using qualitative and quantitative measures such as the inception score.
- How to train GAN models with alternate loss functions such as least squares and Wasserstein loss.
- How to structure the latent space and influence the generation of synthetic images with conditional GANs.
- How to develop image translation models with Pix2Pix for paired images and CycleGAN for unpaired images.
- How sophisticated GAN models such as Progressive Growing GAN are used to achieve remarkable results.
This book will NOT teach you how to be a research scientist nor all the theory behind why specific methods work (if such theories exist for GANs). For that, I would recommend good research papers and textbooks.
This new understanding of applied deep learning methods will impact your practice of working with GANs in the following ways:
- You will be able to confidently design, configure and train a GAN model.
- You will be able to use trained GAN models for image synthesis and evaluate model performance.
- You will be able to effortlessly harness world-class GANs for image-to-image translation tasks.
This book is not a substitute for an undergraduate course in deep learning, computer vision, or GANs, nor is it a textbook for such courses, although it could be a useful complement. For a good list of top textbooks and other resources, see the “Further Reading” section at the end of each tutorial lesson.
…so what is in the Ebook?
29 Step-by-Step Tutorials to Transform You into a GAN Practitioner
This book was designed around major deep learning techniques that are directly relevant to Generative Adversarial Networks.
There are a lot of things you could learn about GANs, from theory to abstract concepts to APIs. My goal is to take you straight to developing an intuition for the elements you must understand with laser-focused tutorials.
The tutorials were designed to focus on how to get results with deep learning methods. As such, they will give you the tools to both rapidly understand and apply each technique or operation. There is a mixture of both tutorial lessons and projects to both introduce the methods and give plenty of examples and opportunities to practice using them.
Each of the tutorials is designed to take you about one hour to read through and complete, excluding running time and the extensions and further reading sections.
You can choose to work through the lessons one per day, one per week, or at your own pace. I think momentum is critically important, and this book is intended to be read and used, not to sit idle. I would recommend picking a schedule and sticking to it.
The tutorials are divided into 7 parts; they are:
- Part 1: Foundations. Discover the convolutional layers for upsampling, the GAN architecture, the algorithms for training the model and the best practices for configuring and training GANs.
- Part 2: GAN Basics. Discover how to develop GANs starting with a 1D GAN, and progressing through black and white and color images and ending with performing vector arithmetic in latent space.
- Part 3: GAN Evaluation. Discover qualitative and quantitative methods for evaluating GAN models based on their generated images.
- Part 4: GAN Loss. Discover alternate loss functions for GAN models and how to implement some of the more widely used approaches.
- Part 5: Conditional GANs. Discover how to incorporate class conditional information into GANs and add controls over the types of images generated by the model.
- Part 6: Image Translation. Discover advanced GAN models used for image translation both with and without paired examples in the training data.
- Part 7: Advanced GANs. Discover the advanced GAN models that push the limits of the architecture and are the basis for some of the impressive state-of-the-art results.
Tutorial Lessons Breakdown
Below is an overview of the step-by-step tutorial lessons you will complete:
Each lesson was designed to be completed in about 30-to-60 minutes by the average developer.
- I. Introduction
Part 1: Foundations
- Lesson 01: What are Generative Adversarial Networks
- Lesson 02: How to Develop Deep Learning Models With Keras
- Lesson 03: How to Upsample with Convolutional Neural Networks
- Lesson 04: How to Implement the GAN Training Algorithm
- Lesson 05: How to Implement GAN Hacks to Train Stable Models
Part 2: GAN Basics
- Lesson 06: How to Develop a 1D GAN from Scratch
- Lesson 07: How to Develop a DCGAN for Grayscale Handwritten Digits
- Lesson 08: How to Develop a DCGAN for Small Color Photographs
- Lesson 09: How to Explore the Latent Space When Generating Faces
- Lesson 10: How to Identify and Diagnose GAN Failure Modes
Part 3: GAN Evaluation
- Lesson 11: How to Evaluate Generative Adversarial Networks
- Lesson 12: How to Implement the Inception Score
- Lesson 13: How to Implement the Frechet Inception Distance
Part 4: GAN Loss
- Lesson 14: How to Use Different GAN Loss Functions
- Lesson 15: How to Develop a Least Squares GAN (LSGAN)
- Lesson 16: How to Develop a Wasserstein GAN (WGAN)
Part 5: Conditional GANs
- Lesson 17: How to Develop a Conditional GAN (cGAN)
- Lesson 18: How to Develop an Information Maximizing GAN (InfoGAN)
- Lesson 19: How to Develop an Auxiliary Classifier GAN (AC-GAN)
- Lesson 20: How to Develop a Semi-Supervised GAN (SGAN)
Part 6: Image Translation
- Lesson 21: Introduction to Pix2Pix
- Lesson 22: How to Implement Pix2Pix Models
- Lesson 23: How to Develop a Pix2Pix End-to-End
- Lesson 24: Introduction to the CycleGAN
- Lesson 25: How to Implement CycleGAN Models
- Lesson 26: How to Develop the CycleGAN End-to-End
Part 7: Advanced GANs
- Lesson 27: Introduction to the BigGAN
- Lesson 28: Introduction to the Progressive Growing GAN
- Lesson 29: Introduction to the StyleGAN
- Appendix A: Getting Help
- Appendix B: How to Set Up Your Workstation
- Appendix C: How to Setup Amazon EC2 for Deep Learning on GPUs
- I. Conclusions
Ebook Table of Contents
The screenshot below was taken from the PDF Ebook.
It provides you a full overview of the table of contents from the book.
Each part targets a specific learning outcomes, and so does each tutorial within each part.
This acts as a filter to ensure you are only focused on the things you need to know to get to a specific result and do not get bogged down in the math or near-infinite number of digressions.
Learn by Doing
The tutorials were not designed to teach you everything there is to know about each of the methods.
They were designed to give you an understanding of how they work, how to use them, and how to interpret the results the fastest way I know how: to learn by doing.
Take a Sneak Peek Inside The Ebook
Click an image to Enlarge.
…you’ll also get 113 fully working Python scripts
BONUS: Generative Adversarial Networks Code Recipes
Sample Code Recipes
Each recipe presented in the book is standalone, meaning that you can copy and paste it into your project and use it immediately.
- You get one Python script (.py) for each example provided in the book.
This means that you can follow along and compare your answers to a known working implementation of each example in the provided Python files.
This helps a lot to speed up your progress when working through the details of a specific task, such as:
- Implementing a GAN.
- Configuring a GAN.
- Training a GAN.
- Saving a GAN.
- Using a GAN for Inference.
- Evaluating a GAN.
- Developing GAN variants.
The provided code was developed in a text editor and intended to be run on the command line. No special editor or notebooks are required.
All code examples were tested with Python 3 and Keras 2 with a TensorFlow backend.
All code examples will run on modest and modern computer hardware and were executed on a CPU and GPU.
A GPU is not required, but is strongly recommended. A GPU will accelerate the execution of some of the larger examples and is strongly recommended.
Python Technical Details
This section provides some technical details about the code provided with the book.
- Python Version: You can use Python 3.
- SciPy: You will use NumPy and scikit-learn.
- Keras: You will need Keras version 2 with either a Theano or TensorFlow backend.
- Operating System: You can use Windows, Linux, or Mac OS X.
- Hardware: A standard modern workstation will do, GPU is recommended (e.g. on AWS EC2).
- Editor: You can use a text editor and run the examples from the command line.
Don’t have a Python Environment Set Up?
No problem! The appendix contains step-by-step tutorials showing you exactly how to set up a Python deep learning environment.
Don’t have a GPU?
No problem! The appendix contains step-by-step tutorials showing you how to use cheap cloud computing to fit models much faster using GPUs.
About The Author
Hi, I'm Jason Brownlee. I run this site and I wrote and published this book.
I live in Australia with my wife and sons. I love to read books, write tutorials, and develop systems.
I have a computer science and software engineering background as well as Masters and PhD degrees in Artificial Intelligence with a focus on stochastic optimization.
I've written books on algorithms, won and ranked well in competitions, consulted for startups, and spent years in industry. (Yes, I have spend a long time building and maintaining REAL operational systems!)
I get a lot of satisfaction helping developers get started and get really good at applied machine learning.
I teach an unconventional top-down and results-first approach to machine learning where we start by working through tutorials and problems, then later wade into theory as we need it.
I'm here to help if you ever have any questions. I want you to be awesome at machine learning.
Download Your Sample Chapter
Do you want to take a closer look at the book? Download a free sample chapter PDF.
Enter your email address and your sample chapter will be sent to your inbox.
Check Out What Customers Are Saying:
You're Not Alone in Choosing Machine Learning Mastery
Trusted by Over 36,858 Practitioners
...including employees from companies like:
...students and faculty from universities like:
and many thousands more...
Absolutely No Risk with...
100% Money Back Guarantee
Plus, as you should expect of any great product on the market, every Machine Learning Mastery Ebook
comes with the surest sign of confidence: my gold-standard 100% money-back guarantee.
100% Money-Back Guarantee
If you're not happy with your purchase of any of the Machine Learning Mastery Ebooks,
just email me within 90 days of buying, and I'll give you your money back ASAP.
No waiting. No questions asked. No risk.
…it’s time to take the next step.
Bring GANs to Your Computer Vision Projects NOW!
Choose Your Package:
You will get the Ebook:
- Generative Adversarial Networks with Python
(including bonus source code)
(a great deal!)
All prices are in US Dollars (USD).
(1) Click the button. (2) Enter your details. (3) Download immediately.
Secure Payment Processing With SSL Encryption
Are you a Student, Teacher or Retiree?
Do you have any Questions?
What Are Skills in Machine Learning Worth?
Your boss asks you:
Hey, can you build a predictive model for this?
Imagine you had the skills and confidence to say:
...and follow through.
I have been there. It feels great!
How much is that worth to you?
The industry is demanding skills in machine learning.
The market wants people that can deliver results, not write academic papers.
Business knows what these skills are worth and are paying sky-high starting salaries.
A Data Scientists Salary Begins at:
$100,000 to $150,000.
A Machine Learning Engineers Salary is Even Higher.
What Are Your Alternatives?
You made it this far.
You're ready to take action.
But, what are your alternatives? What options are there?
(1) A Theoretical Textbook for $100+
...it's boring, math-heavy and you'll probably never finish it.
(2) An On-site Boot Camp for $10,000+
...it's full of young kids, you must travel and it can take months.
(3) A Higher Degree for $100,000+
...it's expensive, takes years, and you'll be an academic.
For the Hands-On Skills You Get...
And the Speed of Results You See...
And the Low Price You Pay...
Machine Learning Mastery Ebooks are
And they work. That's why I offer the money-back guarantee.
You're A Professional
The field moves quickly,
...how long can you wait?
You think you have all the time in the world, but...
- New methods are devised and algorithms change.
- New books get released and prices increase.
- New graduates come along and jobs get filled.
Right Now is the Best Time to make your start.
Bottom-up is Slow and Frustrating,
...don't you want a faster way?
Can you really go on another day, week or month...
- Scraping ideas and code from incomplete posts.
- Skimming theory and insight from short videos.
- Parsing Greek letters from academic textbooks.
Targeted Training is your Shortest Path to a result.
Professionals Stay On Top Of Their Field
Get The Training You Need!
You don't want to fall behind or miss the opportunity.
Frequently Asked Questions
Customer Questions (71)
Thanks for your interest.
Sorry, I do not support third-party resellers for my books (e.g. reselling in other bookstores).
My books are self-published and I think of my website as a small boutique, specialized for developers that are deeply interested in applied machine learning.
As such I prefer to keep control over the sales and marketing for my books.
I’m sorry, I don’t support exchanging books within a bundle.
The collections of books in the offered bundles are fixed.
My e-commerce system is not sophisticated and it does not support ad-hoc bundles. I’m sure you can understand. You can see the full catalog of books and bundles here:
If you have already purchased a bundle and would like to exchange one of the books in the bundle, then I’m very sorry, I don’t support book exchanges or partial refunds.
If you are unhappy, please contact me directly and I can organize a refund.
Thanks for your interest.
I’m sorry, I cannot create a customized bundle of books for you. It would create a maintenance nightmare for me. I’m sure you can understand.
My e-commerce system is not very sophisticated. It cannot support ad-hoc bundles of books or the a la carte ordering of books.
I do have existing bundles of books that I think go well together.
You can see the full catalog of my books and bundles available here:
Sorry, I don’t sell hard copies of my books.
All of the books and bundles are Ebooks in PDF file format.
This is intentional and I put a lot of thought into the decision:
- The books are full of tutorials that must be completed on the computer.
- The books assume that you are working through the tutorials, not reading passively.
- The books are intended to be read on the computer screen, next to a code editor.
- The books are playbooks, they are not intended to be used as references texts and sit the shelf.
- The books are updated frequently, to keep pace with changes to the field and APIs.
I hope that explains my rationale.
If you really do want a hard copy, you can purchase the book or bundle and create a printed version for your own personal use. There is no digital rights management (DRM) on the PDF files to prevent you from printing them.
Sorry, I cannot create a purchase order for you.
After you complete the purchase, I can prepare a PDF invoice for you for tax or other purposes.
I cannot issue a partial refund. It is not supported by my e-commerce system.
If you are truly unhappy with your purchase, please contact me about getting a full refund.
I stand behind my books, I know the tutorials work and have helped tens of thousands of readers.
I am sorry to hear that you want a refund.
Please contact me directly with your purchase details:
- Book Name: The name of the book or bundle that you purchased.
- Your Email: The email address that you used to make the purchase (note, this may be different to the email address you used to pay with via PayPal).
- Order Number: The order number in your purchase receipt email.
I will then organize a refund for you.
I would love to hear why the book is a bad fit for you.
Anything that you can tell me to help improve my materials will be greatly appreciated.
I have a thick skin, so please be honest.
Sample chapters are provided for each book.
Each book has its own webpage, you can access them from the catalog.
On each book’s page, you can access the sample chapter.
- Find the section on the book’s page titled “Download Your Sample Chapter“.
- Click the link, provide your email address and submit the form.
- Check your email, you will be sent a link to download the sample.
If you have trouble with this process or cannot find the email, contact me and I will send the PDF to you directly.
I can provide an invoice that you can use for reimbursement from your company or for tax purposes.
Please contact me directly with your purchase details:
- The name of the book or bundle that you purchased.
- The email address that you used to make the purchase.
- Ideally, the order number in your purchase receipt email.
- Your full name/company name/company address that you would like to appear on the invoice.
I will create a PDF invoice for you and email it back.
Sorry, I no longer distribute evaluation copies of my books due to some past abuse of the privilege.
If you are a teacher or lecturer, I’m happy to offer you a student discount.
Contact me directly and I can organize a discount for you.
Sorry, I do not offer Kindle (mobi) or ePub versions of the books.
The books are only available in PDF file format.
This is by design and I put a lot of thought into it. My rationale is as follows:
- I use LaTeX to layout the text and code to give a professional look and I am afraid that EBook readers would mess this up.
- The increase in supported formats would create a maintenance headache that would take a large amount of time away from updating the books and working on new books.
- Most critically, reading on an e-reader or iPad is antithetical to the book-open-next-to-code-editor approach the PDF format was chosen to support.
My materials are playbooks intended to be open on the computer, next to a text editor and a command line.
They are not textbooks to be read away from the computer.
Sorry, all of my books are self-published and do not have ISBNs.
I offer a discount on my books to:
If you fall into one of these groups and would like a discount, please contact me and ask.
I support payment via PayPal and Credit Card.
You may be able to set up a PayPal account that accesses your debit card. I recommend contacting PayPal or reading their documentation.
I do not support WeChat Pay or Alipay at this stage.
I only support payment via PayPal and Credit Card.
Yes, you can print the purchased PDF books for your own personal interest.
There is no digital rights management (DRM) on the PDFs to prevent you from printing them.
Please do not distribute printed copies of your purchased books.
You can review the table of contents for any book.
I provide two copies of the table of contents for each book on the book’s page.
- A written summary that lists the tutorials/lessons in the book and their order.
- A screenshot of the table of contents taken from the PDF.
If you are having trouble finding the table of contents, search the page for the section titled “Table of Contents”.
I only support payment via PayPal or Credit Card.
If you purchase a book or bundle and later decide that you want to upgrade to the super bundle, I can arrange it for you.
Contact me and let me know that you would like to upgrade and what books or bundles you have already purchased and which email address you used to make the purchases.
I will create a special offer code that you can use to get the price of books and bundles purchased so far deducted from the price of the super bundle.
I am happy for you to use parts of my material in the development of your own course material, such as lecture slides for an in person class or homework exercises.
I am not happy if you share my material for free or use it verbatim. This would be copyright infringement.
All code on my site and in my books was developed and provided for educational purposes only. I take no responsibility for the code, what it might do, or how you might use it.
If you use my material to teach, please reference the source, including:
- The Name of the author, e.g. “Jason Brownlee”.
- The Title of the tutorial or book.
- The Name of the website, e.g. “Machine Learning Mastery”.
- The URL of the tutorial or book.
- The Date you accessed or copied the code.
- Jason Brownlee, Machine Learning Algorithms in Python, Machine Learning Mastery, Available from https://machinelearningmastery.com/machine-learning-with-python/, accessed April 15th, 2018.
Also, if your work is public, contact me, I’d love to see it out of general interest.
Thanks for asking.
I prefer to keep complete control over my content for now.
My books are self-published and are only available from my website.
I don’t have exercises or assignments in my books.
I do have end-to-end projects in some of the books, but they are in a tutorial format where I lead you through each step.
The book chapters are written as self-contained tutorials with a specific learning outcome. You will learn how to do something at the end of the tutorial.
Some books have a section titled “Extensions” with ideas for how to modify the code in the tutorial in some advanced ways. They are like self-study exercises.
Sorry, I do not offer a certificate of completion for my books or my email courses.
Sorry, new books are not included in your super bundle.
I release new books every few months and develop a new super bundle at those times.
All existing customers will get early access to new books at a discount price.
Note, that you do get free updates to all of the books in your super bundle. This includes bug fixes, changes to APIs and even new chapters sometimes. I send out an email to customers for major book updates or you can contact me any time and ask for the latest version of a book.
I have books that do not require any skill in programming, for example:
Other books do have code examples in a given programming language.
You must know the basics of the programming language, such as how to install the environment and how to write simple programs. I do not teach programming, I teach machine learning for developers.
You do not need to be a good programmer.
That being said, I do offer tutorials on how to setup your environment efficiently and even crash courses on programming languages for developers that may not be familiar with the given language.
My books do not cover the theory or derivations of machine learning methods.
This is by design.
My books are focused on the practical concern of applied machine learning. Specifically, how algorithms work and how to use them effectively with modern open source tools.
If you are interested in the theory and derivations of equations, I recommend a machine learning textbook. Some good examples of machine learning textbooks that cover theory include:
I generally don’t run sales.
If I do have a special, such as around the launch of a new book, I only offer it to past customers and subscribers on my email list.
I do offer book bundles that offer a discount for a collection of related books.
I do offer a discount to students, teachers, and retirees. Contact me to find out about discounts.
Sorry, I don’t have videos.
I only have tutorial lessons and projects in text format.
This is by design. I used to have video content and I found the completion rate much lower.
I want you to put the material into practice. I have found that text-based tutorials are the best way of achieving this. With text-based tutorials you must read, implement and run the code.
With videos, you are passively watching and not required to take any action.
After reading and working through the tutorials you are far more likely to use what you have learned.
Yes, I offer a 90-day no questions asked money-back guarantee.
I stand behind my books. They contain my best knowledge on a specific machine learning topic, and each book as been read, tested and used by tens of thousands of readers.
Nevertheless, if you find that one of my Ebooks is a bad fit for you, I will issue a full refund.
There are no physical books, therefore no shipping is required.
All books are EBooks that you can download immediately after you complete your purchase.
I support purchases from any country via PayPal or Credit Card.
The book “Long Short-Term Memory Networks with Python” is not focused on time series forecasting, instead, it is focused on the LSTM method for a suite of sequence prediction problems.
The book “Deep Learning for Time Series Forecasting” shows you how to develop MLP, CNN and LSTM models for univariate, multivariate and multi-step time series forecasting problems.
Mini-courses are free courses offered on a range of machine learning topics and made available via email, PDF and blog posts.
- Short, typically 7 days or 14 days in length.
- Terse, typically giving one tip or code snippet per lesson.
- Limited, typically narrow in scope to a few related areas.
Ebooks are provided on many of the same topics providing full training courses on the topics.
- Longer, typically 25+ complete tutorial lessons, each taking up to an hour to complete.
- Complete, providing a gentle introduction into each lesson and includes full working code and further reading.
- Broad, covering all of the topics required on the topic to get productive quickly and bring the techniques to your own projects.
The mini-courses are designed for you to get a quick result. If you would like more information or fuller code examples on the topic then you can purchase the related Ebook.
The book “Master Machine Learning Algorithms” is for programmers and non-programmers alike. It teaches you how 10 top machine learning algorithms work, with worked examples in arithmetic, and spreadsheets, not code. The focus is on an understanding on how each model learns and makes predictions.
The book “Machine Learning Algorithms From Scratch” is for programmers that learn by writing code to understand. It provides step-by-step tutorials on how to implement top algorithms as well as how to load data, evaluate models and more. It has less on how the algorithms work, instead focusing exclusively on how to implement each in code.
The two books can support each other.
The books are a concentrated and more convenient version of what I put on the blog.
I design my books to be a combination of lessons and projects to teach you how to use a specific machine learning tool or library and then apply it to real predictive modeling problems.
The books get updated with bug fixes, updates for API changes and the addition of new chapters, and these updates are totally free.
I do put some of the book chapters on the blog as examples, but they are not tied to the surrounding chapters or the narrative that a book offers and do not offer the standalone code files.
With each book, you also get all of the source code files used in the book that you can use as recipes to jump-start your own predictive modeling problems.
My books are playbooks. Not textbooks.
They have no deep explanations of theory, just working examples that are laser-focused on the information that you need to know to bring machine learning to your project.
There is little math, no theory or derivations.
My readers really appreciate the top-down, rather than bottom-up approach used in my material. It is the one aspect I get the most feedback about.
My books are not for everyone, they are carefully designed for practitioners that need to get results, fast.
Ebooks can be purchased from my website directly.
- First, find the book or bundle that you wish to purchase, you can see the full catalog here:
- Click on the book or bundle that you would like to purchase to go to the book’s details page.
- Click the “Buy Now” button for the book or bundle to go to the shopping cart page.
- Fill in the shopping cart with your details and payment details, and click the “Place Order” button.
- After completing the purchase you will be emailed a link to download your book or bundle.
All prices are in US dollars (USD).
Books can be purchased with PayPal or Credit Card.
All prices on Machine Learning Mastery are in US dollars.
Payments can be made by using either PayPal or a Credit Card that supports international payments (e.g. most credit cards).
You do not have to explicitly convert money from your currency to US dollars.
Currency conversion is performed automatically when you make a payment using PayPal or Credit Card.
After you complete your purchase you will receive an email with a link to download your bundle.
The download will include the book or books and any bonus material.
There are no physical books, therefore no shipping is required.
All books are EBooks that you can download immediately after you complete your purchase.
I recommend reading one chapter per day.
Momentum is important.
Some readers finish a book in a weekend.
Most readers finish a book in a few weeks by working through it during nights and weekends.
You will get your book immediately.
After you complete and submit the payment form, you will be immediately redirected to a webpage with a link to download your purchase.
You will also immediately be sent an email with a link to download your purchase.
Generally, I would recommend starting with the book or topic that most interests you.
Nevertheless, one suggested order for reading the books is as follows:
- Probability for Machine Learning
- Statistical Methods for Machine Learning
- Linear Algebra for Machine Learning
- Master Machine Learning Algorithms
- Machine Learning Algorithms From Scratch
- Machine Learning Mastery With Weka
- Machine Learning Mastery With Python
- Machine Learning Mastery With R
- Time Series Forecasting With Python
- XGBoost With Python
- Deep Learning With Python
- Long Short-Term Memory Networks with Python
- Deep Learning for Natural Language Processing
- Deep Learning for Computer Vision
- Deep Learning for Time Series Forecasting
- Better Deep Learning
I hope that helps.
Sorry, I do not have a license to purchase my books or bundles for libraries.
The books are for individual use only.
Multi-seat licenses create a bit of a maintenance nightmare for me, sorry. It takes time away from reading, writing and helping my readers.
If you have a big order, such as for a class of students or a large team, please contact me and we will work something out.
There are no physical books, therefore no delivery is required.
All books are Ebooks in PDF format that you can download immediately after you complete your purchase.
You will receive an email with a link to download your purchase. You can also contact me any time to get a new download link.
I support purchases from any country via PayPal or Credit Card.
My best advice is to start with a book on a topic that you can use immediately.
Baring that, pick a topic that interests you the most.
If you are unsure, perhaps try working through some of the free tutorials to see what area that you gravitate towards.
Generally, I recommend focusing on the process of working through a predictive modeling problem end-to-end:
I have three books that show you how to do this, with three top open source platforms:
- Master Machine Learning With Weka (no programming)
- Master Machine Learning With R (caret)
- Master Machine Learning With Python (pandas and scikit-learn)
These are great places to start.
You can always circle back and pick-up a book on algorithms later to learn more about how specific methods work in greater detail.
Thanks for your interest.
You can see the full catalog of my books and bundles here:
Thanks for asking.
I try not to plan my books too far into the future. I try to write about the topics that I am asked about the most or topics where I see the most misunderstanding.
If you would like me to write more about a topic, I would love to know.
Contact me directly and let me know the topic and even the types of tutorials you would love for me to write.
Contact me and let me know the email address (or email addresses) that you think you used to make purchases.
I can look up what purchases you have made and resend purchase receipts to you so that you can redownload your books and bundles.
All prices are in US Dollars (USD).
All currency conversion is handled by PayPal for PayPal purchases, or by Stripe and your bank for credit card purchases.
It is possible that your link to download your purchase will expire after a few days.
This is a security precaution.
Please contact me and I will resend you purchase receipt with an updated download link.
The book “Deep Learning With Python” could be a prerequisite to”Long Short-Term Memory Networks with Python“. It teaches you how to get started with Keras and how to develop your first MLP, CNN and LSTM.
The book “Long Short-Term Memory Networks with Python” goes deep on LSTMs and teaches you how to prepare data, how to develop a suite of different LSTM architectures, parameter tuning, updating models and more.
Both books focus on deep learning in Python using the Keras library.
The book “Long Short-Term Memory Networks in Python” focuses on how to develop a suite of different LSTM networks for sequence prediction, in general.
The book “Deep Learning for Time Series Forecasting” focuses on how to use a suite of different deep learning models (MLPs, CNNs, LSTMs, and hybrids) to address a suite of different time series forecasting problems (univariate, multivariate, multistep and combinations).
The LSTM book teaches LSTMs only and does not focus on time series. The Deep Learning for Time Series book focuses on time series and teaches how to use many different models including LSTMs.
The book “Long Short-Term Memory Networks With Python” focuses on how to implement different types of LSTM models.
The book “Deep Learning for Natural Language Processing” focuses on how to use a variety of different networks (including LSTMs) for text prediction problems.
The LSTM book can support the NLP book, but it is not a prerequisite.
You may need a business or corporate tax number for “Machine Learning Mastery“, the company, for your own tax purposes. This is common in EU companies for example.
The Machine Learning Mastery company is registered and operated out of Australia.
As such, the company does not have a VAT identification number for the EU or similar for your country or regional area.
The company does have an Australian Company Number or ACN. The details are as follows:
- Trading Name: Machine Learning Mastery Pty Ltd
- ACN: 626 223 336
Linux, MacOS, and Windows.
There are no code examples in “Master Machine Learning Algorithms“, therefore no programming language is used.
Algorithms are described and their working is summarized using basic arithmetic. The algorithm behavior is also demonstrated in excel spreadsheets, that are available with the book.
It is a great book for learning how algorithms work, without getting side-tracked with theory or programming syntax.
If you are interested in learning about machine learning algorithms by coding them from scratch (using the Python programming language), I would recommend a different book:
I write the content for the books (words and code) using a text editor, specifically sublime.
I typeset the books and create a PDF using LaTeX.
All of the books have been tested and work with Python 3 (e.g. 3.5 or 3.6).
Most of the books have also been tested and work with Python 2.7.
Where possible, I recommend using the latest version of Python 3.
After you fill in the order form and submit it, two things will happen:
- You will be redirected to a webpage where you can download your purchase.
- You will be sent an email (to the email address used in the order form) with a link to download your purchase.
The redirect in the browser and the email will happen immediately after you complete the purchase.
You can download your purchase from either the webpage or the email.
If you cannot find the email, perhaps check other email folders, such as the “spam” folder?
If you have any concerns, contact me and I can resend your purchase receipt email with the download link.
I do test my tutorials and projects on the blog first. It’s like the early access to ideas, and many of them do not make it to my training.
Much of the material in the books appeared in some form on my blog first and is later refined, improved and repackaged into a chapter format. I find this helps greatly with quality and bug fixing.
The books provide a more convenient packaging of the material, including source code, datasets and PDF format. They also include updates for new APIs, new chapters, bug and typo fixing, and direct access to me for all the support and help I can provide.
I believe my books offer thousands of dollars of education for tens of dollars each.
They are months if not years of experience distilled into a few hundred pages of carefully crafted and well-tested tutorials.
I think they are a bargain for professional developers looking to rapidly build skills in applied machine learning or use machine learning on a project.
Also, what are skills in machine learning worth to you? to your next project? and you’re current or next employer?
Nevertheless, the price of my books may appear expensive if you are a student or if you are not used to the high salaries for developers in North America, Australia, UK and similar parts of the world. For that, I am sorry.
I do offer discounts to students, teachers and retirees.
Please contact me to find out more.
I offer a ton of free content on my blog, you can get started with my best free material here:
About my Books
My books are playbooks.
They are intended for developers who want to know how to use a specific library to actually solve problems and deliver value at work.
- My books guide you only through the elements you need to know in order to get results.
- My books are in PDF format and come with code and datasets, specifically designed for you to read and work-through on your computer.
- My books give you direct access to me via email (what other books offer that?)
- My books are a tiny business expense for a professional developer that can be charged to the company and is tax deductible in most regions.
Very few training materials on machine learning are focused on how to get results.
The vast majority are about repeating the same math and theory and ignore the one thing you really care about: how to use the methods on a project.
Comparison to Other Options
Let me provide some context for you on the pricing of the books:
There are free videos on youtube and tutorials on blogs.
- Great, I encourage you to use them, including my own free tutorials.
There are very cheap video courses that teach you one or two tricks with an API.
- My books teach you how to use a library to work through a project end-to-end and deliver value, not just a few tricks
A textbook on machine learning can cost $50 to $100.
- All of my books are cheaper than the average machine learning textbook, and I expect you may be more productive, sooner.
A bootcamp or other in-person training can cost $1000+ dollars and last for days to weeks.
- A bundle of all of my books is far cheaper than this, they allow you to work at your own pace, and the bundle covers more content than the average bootcamp.
Sorry, my books are not available on websites like Amazon.com.
I carefully decided to not put my books on Amazon for a number of reasons:
- Amazon takes 65% of the sale price of self-published books, which would put me out of business.
- Amazon offers very little control over the sales page and shopping cart experience.
- Amazon does not allow me to contact my customers via email and offer direct support and updates.
- Amazon does not allow me to deliver my book to customers as a PDF, the preferred format for my customers to read on the screen.
I hope that helps you understand my rationale.
I am sorry to hear that you’re having difficulty purchasing a book or bundle.
I use Stripe and PayPal services to support secure and encrypted payment processing on my website.
Some common problems when customers have a problem include:
- Perhaps you can double check that your details are correct, just in case of a typo?
- Perhaps you could try a different payment method, such as PayPal or Credit Card?
- Perhaps you’re able to talk to your bank, just in case they blocked the transaction?
I often see customers trying to purchase with a domestic credit card that does not allow international purchases. This is easy to overcome by talking to your bank.
If you’re still having difficulty, please contact me and I can help investigate further.
I give away a lot of content for free. Most of it in fact.
It is important to me to help students and practitioners that are not well off, hence the enormous amount of free content that I provide.
You can access the free content:
I have thought very hard about this and I sell machine learning Ebooks for a few important reasons:
- I use the revenue to support the site and all the non-paying customers.
- I use the revenue to support my family so that I can continue to create content.
- Practitioners that pay for tutorials are far more likely to work through them and learn something.
- I target my books towards working professionals that are more likely to afford the materials.
All updates to the book or books in your purchase are free.
Books are usually updated once every few months to fix bugs, typos and keep abreast of API changes.
Contact me anytime and check if there have been updates. Let me know what version of the book you have (version is listed on the copyright page).
Please contact me anytime with questions about machine learning or the books.
One question at a time please.
Also, each book has a final chapter on getting more help and further reading and points to resources that you can use to get more help.
Yes, the books can help you get a job, but indirectly.
Getting a job is up to you.
It is a matching problem between an organization looking for someone to fill a role and you with your skills and background.
That being said, there are companies that are more interested in the value that you can provide to the business than the degrees that you have. Often, these are smaller companies and start-ups.
You can focus on providing value with machine learning by learning and getting very good at working through predictive modeling problems end-to-end. You can show this skill by developing a machine learning portfolio of completed projects.
My books are specifically designed to help you toward these ends. They teach you exactly how to use open source tools and libraries to get results in a predictive modeling project.