Читать книгу Algorithms For Dummies - John Paul Mueller, John Mueller Paul, Luca Massaron - Страница 77

Even though you won’t need it for the examples in this book, Colab does offer hardware acceleration in the form of a Graphics Processing Unit (GPU) or Tensor Processing Unit (TPU). Both of these special processors offer the ability to process multiple sets of data in parallel at high speed. When working with big data (see Chapter 12) in a machine learning or deep learning environment, a GPU or TPU can make a huge difference in the time required to accomplish a task. The main difference between a GPU and a TPU is that a GPU appears as part of most high-end display adapters today and can double for rendering complex graphics, while a TPU is a custom processor designed by Google specifically for machine learning and deep learning tasks. (There are other differences, but they aren’t important for this book.)

GPU and TPU support are disabled by default in Colab. To enable GPU or TPU support, choose Runtime ⇒ Change Runtime Type. A Notebook Settings dialog box appears. In this dialog box is the Hardware Accelerator drop-down list, from which you can choose None (the default), GPU, or TPU.