Search icon CANCEL
Subscription
0
Cart icon
Your Cart (0 item)
Close icon
You have no products in your basket yet
Arrow left icon
Explore Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
TensorFlow 2.0 Quick Start Guide

You're reading from   TensorFlow 2.0 Quick Start Guide Get up to speed with the newly introduced features of TensorFlow 2.0

Arrow left icon
Product type Paperback
Published in Mar 2019
Publisher Packt
ISBN-13 9781789530759
Length 196 pages
Edition 1st Edition
Languages
Arrow right icon
Author (1):
Arrow left icon
Tony Holdroyd Tony Holdroyd
Author Profile Icon Tony Holdroyd
Tony Holdroyd
Arrow right icon
View More author details
Toc

Table of Contents (15) Chapters Close

Preface 1. Section 1: Introduction to TensorFlow 2.00 Alpha FREE CHAPTER
2. Introducing TensorFlow 2 3. Keras, a High-Level API for TensorFlow 2 4. ANN Technologies Using TensorFlow 2 5. Section 2: Supervised and Unsupervised Learning in TensorFlow 2.00 Alpha
6. Supervised Machine Learning Using TensorFlow 2 7. Unsupervised Learning Using TensorFlow 2 8. Section 3: Neural Network Applications of TensorFlow 2.00 Alpha
9. Recognizing Images with TensorFlow 2 10. Neural Style Transfer Using TensorFlow 2 11. Recurrent Neural Networks Using TensorFlow 2 12. TensorFlow Estimators and TensorFlow Hub 13. Converting from tf1.12 to tf2
14. Other Books You May Enjoy

Using our model to get predictions

To get the predictions from our model, we need to take a sample from the output distribution. This sampling will get us the characters we need from that output distribution (sampling the output distribution is important because taking the argmax of it, as we would normally do, can easily get the model stuck in a loop).

tf.random.categorical does this sampling and tf.squeeze with axis=-1 removes the last dimension of the tensor, prior to displaying the indices.

The signature of tf.random.categorical is as follows:

tf.random.categorical(logits, num_samples, seed=None, name=None, output_dtype=None)

Comparing this with the call, we see that we are taking one sample (of length sequence_length = 100) from the predictions (example_batch_predictions[0]). The extra dimension is then removed, so we can look up the characters corresponding to the sample...

lock icon The rest of the chapter is locked
Register for a free Packt account to unlock a world of extra content!
A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.
Unlock this book and the full library FREE for 7 days
Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of
Renews at $19.99/month. Cancel anytime
Banner background image