Hands-On Reinforcement Learning with Python

TensorBoard

TensorBoard is TensorFlow's visualization tool that can be used to visualize the computational graph. It can also be used to plot various quantitative metrics and the results of several intermediate calculations. Using TensorBoard, we can easily visualize complex models, which will be useful for debugging and also sharing.

Now, let's build a basic computation graph and visualize that in TensorBoard.

First, let's import the library:

import tensorflow as tf

Next, we initialize the variables:

a = tf.constant(5)b = tf.constant(4)c = tf.multiply(a,b)d = tf.constant(2)e = tf.constant(3)f = tf.multiply(d,e)g = tf.add(c,f)

Now, we will create a TensorFlow session. We will write the results of our graph to a file called event using tf.summary.FileWriter() ...