Training neural networks efficiently with high-level TensorFlow APIs

In this section, we will take a look at two high-level TensorFlow APIs—the Layers API (tensorflow.layers or tf.layers) and the Keras API (tensorflow.contrib.keras).

Keras can be installed as a separate package. It supports Theano or TensorFlow as backend (for more information, refer to the official website of Keras at https://keras.io/).

However, after the release of TensorFlow 1.1.0, Keras has been added to the TensorFlow contrib submodule. It is very likely that the Keras subpackage will be moved outside the experimental contrib submodule and become one of the main TensorFlow submodules soon.

Building multilayer neural networks using TensorFlow's Layers API

To see what neural ...

Get Python Machine Learning now with O’Reilly online learning.

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