What do you think?
Rate this book
Deep Learning with Python, Third Edition
The bestselling book on Python deep learning, now covering generative AI, Keras 3, PyTorch, and JAX!
Deep Learning with Python, Third Edition puts the power of deep learning in your hands. This new edition includes the latest Keras and TensorFlow features, generative AI models, and added coverage of PyTorch and JAX. Learn directly from the creator of Keras and step confidently into the world of deep learning with Python.
In Deep Learning with Python, Third Edition you’ll
• Deep learning from first principles
• The latest features of Keras 3
• A primer on JAX, PyTorch, and TensorFlow
• Image classification and image segmentation
• Time series forecasting
• Large Language models
• Text classification and machine translation
• Text and image generation—build your own GPT and diffusion models!
• Scaling and tuning models
With over 100,000 copies sold, Deep Learning with Python makes it possible for developers, data scientists, and machine learning enthusiasts to put deep learning into action. In this expanded and updated third edition, Keras creator François Chollet offers insights for both novice and experienced machine learning practitioners. You'll master state-of-the-art deep learning tools and techniques, from the latest features of Keras 3 to building AI models that can generate text and images.
About the technology
In less than a decade, deep learning has changed the world—twice. First, Python-based libraries like Keras, TensorFlow, and PyTorch elevated neural networks from lab experiments to high-performance production systems deployed at scale. And now, through Large Language Models and other generative AI tools, deep learning is again transforming business and society. In this new edition, Keras creator François Chollet invites you into this amazing subject in the fluid, mentoring style of a true insider.
About the book
Deep Learning with Python, Third Edition makes the concepts behind deep learning and generative AI understandable and approachable. This complete rewrite of the bestselling original includes fresh chapters on transformers, building your own GPT-like LLM, and generating images with diffusion models. Each chapter introduces practical projects and code examples that build your understanding of deep learning, layer by layer.
What's inside
• Hands-on, code-first learning
• Comprehensive, from basics to generative AI
• Intuitive and easy math explanations
• Examples in Keras, PyTorch, JAX, and TensorFlow
About the reader
For readers with intermediate Python skills. No previous experience with machine learning or linear algebra required.
About the author
François Chollet is the co-founder of Ndea and the creator of Keras. Matthew Watson is a software engineer at Google working on Gemini and a core maintainer of Keras.
Table of Contents
1 What is deep learning?
2 The mathematical building blocks of neural networks
3 Introduction to TensorFlow, PyTorch, JAX, and Keras
4 Classification and regression
5 Fundamentals of machine learning
6 The universal workflow of machine learning
7 A deep dive on Keras
8 Image classification
9 Co
Deep Learning with Python, Third Edition puts the power of deep learning in your hands. This new edition includes the latest Keras and TensorFlow features, generative AI models, and added coverage of PyTorch and JAX. Learn directly from the creator of Keras and step confidently into the world of deep learning with Python.
In Deep Learning with Python, Third Edition you’ll
• Deep learning from first principles
• The latest features of Keras 3
• A primer on JAX, PyTorch, and TensorFlow
• Image classification and image segmentation
• Time series forecasting
• Large Language models
• Text classification and machine translation
• Text and image generation—build your own GPT and diffusion models!
• Scaling and tuning models
With over 100,000 copies sold, Deep Learning with Python makes it possible for developers, data scientists, and machine learning enthusiasts to put deep learning into action. In this expanded and updated third edition, Keras creator François Chollet offers insights for both novice and experienced machine learning practitioners. You'll master state-of-the-art deep learning tools and techniques, from the latest features of Keras 3 to building AI models that can generate text and images.
About the technology
In less than a decade, deep learning has changed the world—twice. First, Python-based libraries like Keras, TensorFlow, and PyTorch elevated neural networks from lab experiments to high-performance production systems deployed at scale. And now, through Large Language Models and other generative AI tools, deep learning is again transforming business and society. In this new edition, Keras creator François Chollet invites you into this amazing subject in the fluid, mentoring style of a true insider.
About the book
Deep Learning with Python, Third Edition makes the concepts behind deep learning and generative AI understandable and approachable. This complete rewrite of the bestselling original includes fresh chapters on transformers, building your own GPT-like LLM, and generating images with diffusion models. Each chapter introduces practical projects and code examples that build your understanding of deep learning, layer by layer.
What's inside
• Hands-on, code-first learning
• Comprehensive, from basics to generative AI
• Intuitive and easy math explanations
• Examples in Keras, PyTorch, JAX, and TensorFlow
About the reader
For readers with intermediate Python skills. No previous experience with machine learning or linear algebra required.
About the author
François Chollet is the co-founder of Ndea and the creator of Keras. Matthew Watson is a software engineer at Google working on Gemini and a core maintainer of Keras.
Table of Contents
1 What is deep learning?
2 The mathematical building blocks of neural networks
3 Introduction to TensorFlow, PyTorch, JAX, and Keras
4 Classification and regression
5 Fundamentals of machine learning
6 The universal workflow of machine learning
7 A deep dive on Keras
8 Image classification
9 Co
648 pages, Paperback
Published November 18, 2025
24 people are currently reading
10 people want to read
About the author
François Chollet
22 books132 followersFrançois Chollet is a French engineer and researcher in artificial intelligence.
Ratings & Reviews
Friends & Following
Create a free account to discover what your friends think of this book!
Community Reviews
Displaying 1 - 10 of 10 reviews
December 6, 2025
LLMs are here and seem to be the go-to for everything; however, there is still space for the traditional methods. Ironically, this is exactly what I said in my speech at the AI World Congress 2025, and Deep Learning with Python, Third Edition illustrates that point perfectly.
This substantial volume - around 600 pages across 20 chapters - delivers a comprehensive and structured journey into modern deep learning. As a 3rd edition, it feels mature and refined. The opening chapter provides clear, high-level definitions of fundamental concepts, offering a gentle introduction to the principles behind machine learning, deep learning’s rise in popularity, and where the field is heading.
From there, the book moves rapidly into practical territory. It covers all the major frameworks - Keras, TensorFlow, PyTorch, and JAX - supported by plenty of code examples that allow concepts to be applied immediately. It does not shy away from breadth either: image classification, time series modelling, object detection, and, as is now essential, transformers, all receive well-structured treatment. Each chapter ends with a concise, very useful summary that reinforces understanding and highlights key takeaways.
A standout section for this reader was “Best Practices for the Real World”, which provides grounded guidance on hyperparameter tuning, ensembles, and quantisation. These topics are often overlooked in introductory texts but are essential for real deployments.
Some reasonable Python knowledge is needed, but the book remains approachable. It suits beginners aiming to break into deep learning as well as experienced practitioners looking to broaden their toolkit.
Highly recommended.
This substantial volume - around 600 pages across 20 chapters - delivers a comprehensive and structured journey into modern deep learning. As a 3rd edition, it feels mature and refined. The opening chapter provides clear, high-level definitions of fundamental concepts, offering a gentle introduction to the principles behind machine learning, deep learning’s rise in popularity, and where the field is heading.
From there, the book moves rapidly into practical territory. It covers all the major frameworks - Keras, TensorFlow, PyTorch, and JAX - supported by plenty of code examples that allow concepts to be applied immediately. It does not shy away from breadth either: image classification, time series modelling, object detection, and, as is now essential, transformers, all receive well-structured treatment. Each chapter ends with a concise, very useful summary that reinforces understanding and highlights key takeaways.
A standout section for this reader was “Best Practices for the Real World”, which provides grounded guidance on hyperparameter tuning, ensembles, and quantisation. These topics are often overlooked in introductory texts but are essential for real deployments.
Some reasonable Python knowledge is needed, but the book remains approachable. It suits beginners aiming to break into deep learning as well as experienced practitioners looking to broaden their toolkit.
Highly recommended.
November 26, 2025
As a working programmer who has been trying to deepen my understanding of modern machine learning, I found this book to be one of the clearest and most practical introductions to deep learning. François Chollet has a talent for explaining complex ideas in a way that feels intuitive without oversimplifying them. The third edition is especially valuable because it reflects the current state of the field, including Keras 3 and its integration with TensorFlow, PyTorch and JAX.
The book follows a very hands-on approach. Nearly every concept is paired with code that you can run and experiment with, which makes the learning experience far more concrete. The examples feel modern and relevant, covering everything from image classification and sequence modeling to generative techniques like text and image generation. As someone who learns best by building, this style worked extremely well for me.
A small note for beginners: the book assumes you are comfortable with Python. You do not need a math-heavy background, but you should be ready to write and tweak code. Some of the later chapters move faster and may require revisiting if you’re new to the field, but the progression is well-structured and worth the effort.
Overall, this is one of the most practical and accessible deep learning resources available. It combines clarity, modern techniques and immediately usable code examples. If you’re a developer looking to get into deep learning or refresh your understanding with up-to-date practices, this book is an excellent choice. I would highly recommend it.
The book follows a very hands-on approach. Nearly every concept is paired with code that you can run and experiment with, which makes the learning experience far more concrete. The examples feel modern and relevant, covering everything from image classification and sequence modeling to generative techniques like text and image generation. As someone who learns best by building, this style worked extremely well for me.
A small note for beginners: the book assumes you are comfortable with Python. You do not need a math-heavy background, but you should be ready to write and tweak code. Some of the later chapters move faster and may require revisiting if you’re new to the field, but the progression is well-structured and worth the effort.
Overall, this is one of the most practical and accessible deep learning resources available. It combines clarity, modern techniques and immediately usable code examples. If you’re a developer looking to get into deep learning or refresh your understanding with up-to-date practices, this book is an excellent choice. I would highly recommend it.
December 3, 2025
I've read this book on my journey to learn AI and Deep Learning and I must say, it's the most complete and updated about Deep Learning with Python.
It covers everything from the basics—chapter 1 gives a very accessible introduction to AI and deep learning, from modern topics like transformers, GPT-like language models, and diffusion models for image generation.
Every chapter includes clean, and, very important, examples that run in Keras, TensorFlow, PyTorch, and JAX.
You build classifiers, CNNs, RNNs, LSTMs, etc... You named it. It describes modern techniques that most books don't have, like a step-by-step implementation of language models an transformers.
It's a great balance between theory and practice. Chollet explains in a natural and intuitive way.
The feature-engineering explanation using the clock-hand metaphor is brilliant. :)
For what I think is not so good:
- For someone looking to learn something in a weekend, this is not your book. It's a bit overwhelming - a fantastic learning guide, but a bit bulky for a weekend reading.
You need to know Python and have the heart to learn some math ! :)
- You need to have a decent GPU for the examples and some advance models. With only the CPU you will suffer a bit.
Overall, and in my opinion, it's one of the best (if not the best) book to learn deep learning with Python. It's clear, modern and did I mention it was written by the creator of Keras ?
It's essential for anyone working with AI in 2025 .
It covers everything from the basics—chapter 1 gives a very accessible introduction to AI and deep learning, from modern topics like transformers, GPT-like language models, and diffusion models for image generation.
Every chapter includes clean, and, very important, examples that run in Keras, TensorFlow, PyTorch, and JAX.
You build classifiers, CNNs, RNNs, LSTMs, etc... You named it. It describes modern techniques that most books don't have, like a step-by-step implementation of language models an transformers.
It's a great balance between theory and practice. Chollet explains in a natural and intuitive way.
The feature-engineering explanation using the clock-hand metaphor is brilliant. :)
For what I think is not so good:
- For someone looking to learn something in a weekend, this is not your book. It's a bit overwhelming - a fantastic learning guide, but a bit bulky for a weekend reading.
You need to know Python and have the heart to learn some math ! :)
- You need to have a decent GPU for the examples and some advance models. With only the CPU you will suffer a bit.
Overall, and in my opinion, it's one of the best (if not the best) book to learn deep learning with Python. It's clear, modern and did I mention it was written by the creator of Keras ?
It's essential for anyone working with AI in 2025 .
December 7, 2025
One of the best books on the topic - the author has done an excellent job making complex AI concepts understandable without dumbing them down.
What I loved most was how practical it is. Every concept comes with actual code you can run and experiment with. You're not just reading theory—you're building real things like image classifiers, language models, and even your own GPT-style systems. The examples work across multiple frameworks (Keras, TensorFlow, PyTorch, and JAX), which is incredibly useful for real-world applications.
A few things to know: you need to be comfortable with Python, and it takes time to work through. You'll also want a decent GPU for some of the examples. But if you're serious about learning AI, the time investment is absolutely worth it.
Whether you're just getting started or looking to update your skills with modern techniques, this book is essential. It's clear, practical, and written by someone who actually created one of the tools (Keras) you'll be using.
Highly recommended.
What I loved most was how practical it is. Every concept comes with actual code you can run and experiment with. You're not just reading theory—you're building real things like image classifiers, language models, and even your own GPT-style systems. The examples work across multiple frameworks (Keras, TensorFlow, PyTorch, and JAX), which is incredibly useful for real-world applications.
A few things to know: you need to be comfortable with Python, and it takes time to work through. You'll also want a decent GPU for some of the examples. But if you're serious about learning AI, the time investment is absolutely worth it.
Whether you're just getting started or looking to update your skills with modern techniques, this book is essential. It's clear, practical, and written by someone who actually created one of the tools (Keras) you'll be using.
Highly recommended.
November 25, 2025
Deep Learning moves fast, and this Third Edition finally catches up to the Generative AI boom. The addition of Matthew Watson as a co-author is felt in the NLP sections, which are much more robust now.
The key value prop here is Keras 3. Seeing how to build a model once and deploy it on JAX or PyTorch is invaluable for production workflows. The book cuts through the hype of LLMs and Diffusion models to show you exactly how they are architected.
It’s a dense read but incredibly high ROI for your time. A must-have reference for 2025.
The key value prop here is Keras 3. Seeing how to build a model once and deploy it on JAX or PyTorch is invaluable for production workflows. The book cuts through the hype of LLMs and Diffusion models to show you exactly how they are architected.
It’s a dense read but incredibly high ROI for your time. A must-have reference for 2025.
November 25, 2025
This book is an excellent, hands-on introduction to modern deep learning that stays both practical and accessible. Chollet and Watson explain complex ideas clearly, with clean Keras examples and up-to-date coverage of topics like transformers and large language models, making it a great choice for both learners and working engineers.
November 26, 2025
I really enjoyed reading this book. It's rare for a technical text to be both informative and genuinely engaging, and that's what sets it apart from many modern ML books that are often filled with cliches and lack real depth. This book provides a solid foundation in deep learning and is an excellent guide for keeping up with the fast moving world of ML
December 21, 2025
This book does an excellent job of giving a bird’s-eye view of deep learning before zooming into detailed practical examples. I particularly appreciated the real-world use cases and the authors’ insights on current limitations and the future of AI. It’s an excellent resource for beginners who want to deepen their knowledge while staying aware of where the field is heading.
November 19, 2025
It’s an excellent book. It starts with the basics and builds up to the state-of-the-art of Deep Learning. I especially enjoyed the chapter "Future of AI".
If you prefer learning by doing, you’ll appreciate that every chapter comes with code.
If you prefer learning by doing, you’ll appreciate that every chapter comes with code.
November 27, 2025
I liked this book more than I expected. The writing is clear, and the examples are straightforward to follow. I think it works well for beginners, but even with some experience in ML I still picked up useful insights.
Displaying 1 - 10 of 10 reviews