Enter your mobile number or email address below and we'll send you a link to download the free Kindle App. Then you can start reading Kindle books on your smartphone, tablet, or computer - no Kindle device required.
To get the free app, enter your mobile phone number.
|Print List Price:||£39.99|
Save £15.30 (38%)
Learning TensorFlow: A Guide to Building Deep Learning Systems 1st Edition, Kindle Edition
|New from||Used from|
|Length: 242 pages||Enhanced Typesetting: Enabled||Page Flip: Enabled|
Kindle e-ReadersKindle Fire TabletsFire Phones
- Due to its large file size, this book may take longer to download
Customers who bought this item also bought
Would you like to tell us about a lower price?
What other items do customers buy after viewing this item?
Top customer reviews
There was a problem filtering reviews right now. Please try again later.
There are two main defects with the book however: firstly, it is absolutely _full_ of mistakes in the code examples. Missing brackets, incorrect cases (python being case sensitive of course), which indicates an overall lack of care and checking of the work. Indeed the grammar of the running text is a little odd, to say the least. Secondly, as has been pointed out by other reviewers, there is nothing here that is not in the tensorflow free online documentation and tutorials (although some of it is slightly better explained in this book).
I have also noticed that the publishers info on the book says 242 pages, but it is in fact 228 including the index.
If you are prepared to read the online material then there's probably not much point in buying this book, so not recommended.
The google team gives us good insight for tensorflow.
But this is difficult for beginners, i think.
Most helpful customer reviews on Amazon.com
I am just amazed that these three authors were so incredibly lazy that having giving the opportunity to write a book, they decided not to spend even couple of weeks on it. if each of these three authors spend a month on the book, the book could have been something useful. They just decided to take the money and run.
The editors Nicole Tache and Shiny Kalapurakkel should be ashamed of themselves for letting a hodgepodge of collected code to be published as a book. And shame on O'Reilly for publishing this.
I suspect the positive ratings are by the authors's friends.
The book does an acceptable (if not particularly inspired) job of walking you through the basics of TensorFlow. Sure, the book covers the MNIST and CIFAR data sets (which are the same ones you'll find discussed on the TensorFlow website), but that's not a bad thing. the fact that they're the same data sets used elsewhere didn't make them useless here.
I'm not the kind of person who reads everything there is to read about my subject, so I haven't exhaustively read all of the online documentation there is on Tensor flow, and this book helped me learn skills that I didn't have before.
That said, I agree that this book needed more contextualization. I don't think anyone trying to learn TensorFlow is going to be unfamiliar with deep learning, but when you're talking about neural networks and modeling and such, maybe a bit more depth on what works where and why would be in order.