Beginning Anomaly Detection Using

Figure 7-60.  Training the data on the training sets

Figure 7-61.  This output is similar to what you should see after the training 

process ends

Chapter 7   temporal Convolutional networks

---

294

Now evaluate your model’s performance (see Figure 

7-62

).

You should see an output similar to Figure 

7-63

.

Pretty good, but how’s the AUC score? Run the code in Figure 

7-64

.

The output should look somewhat like Figure 

7-65

.

VFRUH 7&1HYDOXDWH [BWHVW\BWHVWYHUERVH 

SULQW

7HVWORVV VFRUH>@

SULQW

7HVWDFFXUDF\ VFRUH>@

Figure 7-62.  Evaluates the model’s performance in terms of loss and accuracy

Figure 7-63.  The generated outputs for loss and accuracy for the model when the 

test sets are passed in