Popular open source libraries – an introduction
There are several Open Source libraries available that allow the creation of deep neural nets in Python without having to explicitly write the code from scratch. The most commonly used are: Keras, Theano, TensorFlow, Caffe, and Torch. In this book we will provide examples using the first three libraries, which can all be used in Python. The reason for this is that Torch is not based on Python, but on a different language, called Lua, while Caffe is mainly used for Image recognition only. For these libraries, we will quickly describe how to turn on the GPU switch we discussed in the previous paragraph. Much of the code in this book can then be run on a CPU or a GPU, depending on the hardware available ...
Get Python Deep Learning now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
