1
00:00:00,320 --> 00:00:03,240
In the last few lessons,
you've been building a binary classifier.

2
00:00:03,240 --> 00:00:07,580
One which detects two different types
of objects, horse or human, cat or

3
00:00:07,580 --> 00:00:09,530
dog, that type of thing.

4
00:00:09,530 --> 00:00:14,170
In this lesson, we'll take a look at how
we can extend that for multiple classes.

5
00:00:14,170 --> 00:00:16,016
Remember when we were
classifying horses or

6
00:00:16,016 --> 00:00:17,850
human, we had a file structure like this.

7
00:00:17,850 --> 00:00:23,100
There were subdirectories for each class,
where in this case we only had two.

8
00:00:23,100 --> 00:00:25,470
The first thing that you'll need
to do is replicate this for

9
00:00:25,470 --> 00:00:27,500
multiple classes like this.

10
00:00:27,500 --> 00:00:31,650
It's very similar and here you can
see that both the training and

11
00:00:31,650 --> 00:00:34,390
validation have three subdirectories.

12
00:00:34,390 --> 00:00:37,990
One for Rock, one for Paper,
and one for Scissors.

13
00:00:37,990 --> 00:00:41,817
In these, we can put training and
validation images for Rock, Paper, and

14
00:00:41,817 --> 00:00:42,436
Scissors.