Would you like to inspect the original subtitles? These are the user uploaded subtitles that are being translated:
1
00:00:00,730 --> 00:00:06,340
In this video we will explain about dataset annotation because YOLO is a supervised learning object
2
00:00:06,340 --> 00:00:09,460
detection model, you must use annotated data to train the model.
3
00:00:09,460 --> 00:00:14,650
The annotation provides a bonding box for each object in the image along with the object class name.
4
00:00:16,250 --> 00:00:18,440
This is the annotation format on YOLO.
5
00:00:18,710 --> 00:00:24,130
The first of these values is object class, its value ranging from zero to total class minus one.
6
00:00:24,140 --> 00:00:27,620
The second and third values represent the bounding boxes midpoint.
7
00:00:27,650 --> 00:00:30,950
The midpoint value is relative to the width and height of the image.
8
00:00:31,990 --> 00:00:33,580
X relative to inmates with.
9
00:00:34,790 --> 00:00:36,530
Y relative to image height.
10
00:00:39,880 --> 00:00:42,270
The width of the bounding box is the fourth value.
11
00:00:42,280 --> 00:00:44,020
This width is relative to the image.
12
00:00:44,020 --> 00:00:46,720
With the fifth value is the bonding box is high.
13
00:00:46,750 --> 00:00:49,030
This height is relative to the image height.
14
00:00:50,210 --> 00:00:51,380
Here's an example.
15
00:00:52,130 --> 00:00:53,900
Consider the following example.
16
00:00:54,200 --> 00:00:59,330
There is an image that is 512 pixels wide and 366 pixels high.
17
00:00:59,360 --> 00:01:01,910
In this case, zero represents a mask.
18
00:01:05,090 --> 00:01:06,980
This is the burning boxes midpoint.
19
00:01:09,270 --> 00:01:10,830
X divided by image with.
20
00:01:12,180 --> 00:01:15,540
Equal to this, and it is written as the second value in the annotation.
21
00:01:16,740 --> 00:01:17,070
Why?
22
00:01:17,110 --> 00:01:18,150
Divided by the image.
23
00:01:19,930 --> 00:01:23,230
Equal to this, and it is written as the third value in the annotation.
24
00:01:24,470 --> 00:01:26,630
The width of the box divided by image with.
25
00:01:28,030 --> 00:01:28,750
Equal to this.
26
00:01:28,750 --> 00:01:31,360
And it is is the fourth value in the annotation.
27
00:01:33,150 --> 00:01:35,280
The height of the box divided by image height.
28
00:01:37,600 --> 00:01:40,960
Equal to this, and it is written as the fifth value in the annotation.
29
00:01:43,480 --> 00:01:46,240
There are also several tools available for any city.
30
00:01:47,420 --> 00:01:48,280
YOLO, Mark.
31
00:01:49,470 --> 00:01:50,430
Labor emits.
32
00:01:51,520 --> 00:01:52,480
And let me.
33
00:01:53,560 --> 00:01:56,350
In this course, we will use the label image tools.
34
00:01:56,380 --> 00:01:59,110
The next video will demonstrate how to use label image.
35
00:01:59,140 --> 00:01:59,770
See you then.
2917
Can't find what you're looking for?
Get subtitles in any language from opensubtitles.com, and translate them here.