Chapter 8. Advanced TensorFlow Programming

The development of deep learning (DL) networks requires rapid prototyping when testing new models. For this reason, several TensorFlow-based libraries have been built, which abstract many programming concepts and provides high-level building blocks.

We'll describe the main characteristics of each library with an application example.

This chapter covers the following high-level TensorFlow APIs and their overviews:

  • tf.estimator
  • TFLearn
  • Pretty Tensor
  • Keras


tf.estimator is a high-level TensorFlow API for creating and training models by encapsulating the functionalities for training, evaluating, predicting and exporting. TensorFlow recently re-branded and released the TF Learn package within TensorFlow ...

Get Deep Learning with TensorFlow - Second Edition now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.