Connecting Keras to TensorBoard

Now that TensorBoard is up and running, all that's left is to tell Keras to write TensorBoard logs to the directory we specified above. Luckily, this is really easy to do, and it gives us a great opportunity to learn about a special class of functions in Keras called Keras callbacks.

Introducing Keras callbacks

Callbacks in Keras are functions that can be run during the training process. They can do all kinds of great things, such as saving your model weights after an epoch, logging things, changing your hyperparameters, or conveniently writing TensorBoard log files. You can even create your own custom callbacks.

We will be using the TensorBoard callback in the next section; however, I'd encourage you to take a look at all the callbacks available in Keras at https://keras.io/callbacks.

TensorBoard callbacks are objects that can be configured and instantiated before model training.  We will be creating a list of these callbacks.  Once we have created a list of...