Beginning Anomaly Detection Using

Figure 4-34.  Code to evaluate the model

Figure 4-33.  The model being trained

Chapter 4   autoenCoders

---

148

The next step is to use the model to generate the output images for the testing subset. 

This will show how well the reconstruction phase is going. Figure 

4-35

 shows the code to 

predict based on the model.

Figure 4-35.  Code to predict based on the model

You can also see how the encoder phase is working by displaying the test subset 

images in this phase. Figure 

4-36

 shows the code to display the encoded images.

Chapter 4   autoenCoders

---

149

Figure 

4-37

 shows the graph of the model as visualized by TensorBoard.

Figure 4-36.  Code to display encoded images

Chapter 4   autoenCoders

---

150

Figure 

4-38

 shows the plotting of the accuracy during the training process through 

the epochs of training.

Figure 4-37.  A model graph shown in TensorBoard

Chapter 4   autoenCoders

---

151

Figure 

4-39

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

epochs of training.