Python for TensorFlow Pocket Primer

By: Oswald Campesato

Write A Review

Paperback | 3 June 2019

At a Glance

Paperback
236 Pages

Dimensions(cm)
23.5 x 15.88 x 1.27

Paperback

RRP $57.67

$53.75

or 4 interest-free payments of $13.44 with

Ships in 5 to 7 business days

As part of the best-selling PocketPrimer series, this book is designed to prepare programmersfor machine learning and deep learning/TensorFlow topics. It begins with aquick introduction to Python, followed by chapters that discuss NumPy, Pandas,Matplotlib, and scikit-learn. The final two chapters contain an assortment ofTensorFlow 1.x code samples, including detailed code samples for TensorFlowDataset (which is used heavily in TensorFlow 2 as well). A TensorFlow Datasetrefers to the classes in the tf.data.Dataset namespace that enables programmersto construct a pipeline of data by means of method chaining so-called lazyoperators, e.g., map(), filter(), batch(), and so forth, based on data from oneor more data sources.

Companion files with source code areavailable for downloading from the publisher by writing info@merclearning.com.

Features:

A practical introductionto Python, NumPy, Pandas, Matplotlib, and introductory aspects of TensorFlow1.x
Contains relevant NumPy/Pandascode samples that are typical in machine learning topics, and also usefulTensorFlow 1.x code samples for deep learning/TensorFlow topics
Includes many examples of TensorFlow Dataset APIswith lazy operators, e.g., map(), filter(), batch(), take() and also methodchaining such operators
Assumes the reader hasvery limited experience
Companion files with all of thesource code examples (download from the publisher)

Shipping

	Standard Shipping	Express Shipping
Metro postcodes:	$9.99	$14.95
Regional postcodes:	$9.99	$14.95
Rural postcodes:	$9.99	$14.95

How to return your order

At Booktopia, we offer hassle-free returns in accordance with our returns policy. If you wish to return an item, please get in touch with Booktopia Customer Care.

Additional postage charges may be applicable.