Beginning Anomaly Detection Using

Figure 4-15.  Plotting of mae shown in TensorBoard

Figure 4-16.  Plotting of loss shown in TensorBoard

Chapter 4   autoenCoders

---

136

Figure 

4-17

 shows the plotting of the accuracy of validation during the training 

process through the epochs of training.

Now that the training process is complete, let’s evaluate the model for loss and 

accuracy. Figure 

4-19

 shows that the accuracy is 0.81, which is pretty good. It also shows 

the code to evaluate the model.

Figure 4-17.  Plotting of validation accuracy shown in TensorBoard

Figure 4-18.  Plotting of validation loss shown in TensorBoard

Figure 

4-18

 shows the plotting of the loss of validation during the training process 

through the epochs of training.

Chapter 4   autoenCoders

---

137

The next step is to calculate the errors, and detect and also plot the anomalies and 

errors. Choose a threshold of 10. Figure 

4-20

 shows the code to measure anomalies 

based on that threshold.