Beginning Anomaly Detection Using

n samples, where n is the integer passed in. Note: 

Writing to TensorBoard too frequently can slow down the training 

process.

With that being said, Figure 

A-33

 shows an example of using TensorBoard as a 

callback when training a convolutional neural network on the MNIST data set.

Appendix A   intro to KerAs

---

354

Once you execute that code, you will notice the training process will begin. At this 

point, enter the line

tensorboard --logdir=/full_path_to_your_logs

 into your command prompt and press Enter. It should show you something like  

Figure 

A-34

.

WHQVRUERDUG NHUDVFDOOEDFNV7HQVRU%RDUG ORJBGLU *UDSK 

KLVWRJUDPBIUHT 

ZULWHBJUDSK 7UXHZULWHBLPDJHV 7UXH

FKHFNSRLQW 

NHUDVFDOOEDFNV0RGHO&KHFNSRLQW ILOHSDWK NHUDVB01,67B&11K

YHUERVH 

VDYHBEHVWBRQO\ 7UXH

PRGHOILW [BWUDLQ\BWUDLQ

EDWFKBVL]H EDWFKBVL]H

HSRFKV QBHSRFKV

YHUERVH 

YDOLGDWLRQBGDWD [BWHVW\BWHVW 

FDOOEDFNV >FKHFNSRLQWWHQVRUERDUG@

Figure A-33.  Code to define a TensorBoard callback and use that when training

Appendix A   intro to KerAs

---

355