Using TensorBoard

Now that we've completely configured TensorBoard and told our networks how to send log data to it, we can start taking advantage of it. In the remainder of the chapter, I'm going to show you some of my favorite ways to use TensorBoard. There is more to TensorBoard than this, and we will revisit additional functionality throughout the remainder of the book.

Visualizing training

Since we've written log data from both the models in Chapter 2, Using Deep Learning to Solve Regression Problems, we can use TensorBoard to compare the two models graphically. Open up TensorBoard and head to the SCALARS tab. You should see something like this. You may need to click loss and val_loss to expand the graphs...