Beginning Anomaly Detection Using

steps: If None, then ignored. Otherwise, it’s the integer parameter n 

number of steps (batches of samples) before declaring the evaluation 

as done.

• 

callbacks: Works the same way as the callbacks parameter for model.

fit().

Finally, to make predictions, you can run code similar to Figure 

A-10

.

Appendix A   intro to KerAs

---

328

In this case, the parameters are

• 

x: The Numpy array representing the prediction data. Pass in a list of 

Numpy arrays if the model has multiple inputs.

• 

batch_size: If none is specified, the default is 32. This parameter 

expects an integer value that dictates how many samples there are 

per batch.

•