TensorFlow and training performance
TensorFlow can speed up our machine learning tasks significantly. To understand how it can do this, let's begin by discussing some of the performance challenges we typically run into when we run expensive calculations on our hardware.
The performance of computer processors has, of course, been improving continuously over recent years, and that's allowed us to train more powerful and complex learning systems, and so to improve the predictive performance of our machine learning models. Even the cheapest desktop computer hardware that's available right now comes with processing units that have multiple cores.
Also, in the previous chapters, we saw that many functions in scikit-learn allowed us to spread those computations over multiple processing units. However, by default, Python is limited to execution on one core due to the Global Interpreter Lock (GIL). So, although we, indeed, take advantage of its multiprocessing library to distribute...
