Development of deep learning networks, especially when testing new models, may require rapid prototyping. For this reason, there have been developed several TensorFlow-based libraries, abstracting many programming concepts and providing higher-level building blocks.
In this chapter, we'll give an overview of the libraries such as, Keras, Pretty Tensor, and TFLearn.
For each library, we'll describe its main characteristics, with an application example.
The chapter is organized as follows:
- Introducing Keras
- Building deep learning models
- Sentiment classification of movie reviews
- Adding a convolutional layer
- Pretty Tensor
- Digit classifier
- TFLearn
- Titanic survival predictor
