Deep neural network
Now, we're going to create an actual deep neural network using convolution.
In this section, we'll cover how to check to make sure we're running on a GPU, which is an important performance tip. Then, we'll load up our image data, and then we'll build a multiple block deep neural network, which is much deeper than anything we've created before. Finally, we'll compare the results of this deep neural network with our shallow convolutional neural network in the previous section.
Here, at the top, we're importing the necessary Python packages:

Importing packages
This is the same as we did for the standard convolutional neural network. The difference regarding making a deep neural network is that we're simply going to be using the same layers even more. In this next block, we're going directly to tensorflow
and importing the python
library. What is this device_lib
we're seeing? Well, device_lib
actually lets us list all of the devices that we have access to in order to run our...