Would you like to inspect the original subtitles? These are the user uploaded subtitles that are being translated:
1
00:00:02,050 --> 00:00:03,850
Hello and welcome to this video.
2
00:00:03,880 --> 00:00:04,780
We will explain.
3
00:00:04,790 --> 00:00:07,180
YOLO v seven Training on Custom Objects.
4
00:00:07,180 --> 00:00:09,550
The training will be done on windows at this time.
5
00:00:09,550 --> 00:00:12,240
Make sure all of seven is installed on windows.
6
00:00:12,250 --> 00:00:16,270
However, before we begin training we must first prepare the annotated dataset.
7
00:00:16,270 --> 00:00:19,030
The face mask dataset was used in this example.
8
00:00:23,140 --> 00:00:26,560
The dataset can be accessed and downloaded at the following URL.
9
00:00:26,980 --> 00:00:28,570
Download the following dataset.
10
00:00:34,000 --> 00:00:35,860
Wait until the download is finished.
11
00:00:44,750 --> 00:00:47,150
When you're finished, go to the downloads folder.
12
00:00:48,810 --> 00:00:51,510
This is a face mask deficit that has been annotated.
13
00:00:53,720 --> 00:00:55,400
Next extract the dataset.
14
00:00:55,430 --> 00:00:59,300
The dataset will be saved in the data folder of YOLO 5/7 root folder.
15
00:00:59,330 --> 00:01:05,870
In this example on the YOLO five seven Dpu data, we will use tools on Windows 11 for extraction to
16
00:01:05,870 --> 00:01:07,490
extract right click and select.
17
00:01:07,490 --> 00:01:08,450
Extract or.
18
00:01:10,920 --> 00:01:11,970
Click browse.
19
00:01:13,970 --> 00:01:14,660
On the.
20
00:01:15,720 --> 00:01:16,940
You know, he's 74.
21
00:01:16,950 --> 00:01:17,400
You.
22
00:01:18,530 --> 00:01:19,030
Data.
23
00:01:20,270 --> 00:01:21,560
Click Select folder.
24
00:01:22,600 --> 00:01:23,500
Click extra.
25
00:01:28,870 --> 00:01:30,850
Wait until the extraction is finished.
26
00:01:37,000 --> 00:01:39,520
When finished, it will be saved in the data folder.
27
00:01:39,550 --> 00:01:42,310
The following is the annotated face mask dataset.
28
00:01:44,160 --> 00:01:48,300
Following the split the dataset into train validation and test data.
29
00:01:48,420 --> 00:01:51,810
The split results must match the goal of seven folder structure.
30
00:01:56,230 --> 00:01:58,930
The all of seven folder structure is shown below.
31
00:01:59,140 --> 00:02:03,970
The images folder contains images and the labels folder contains annotations.
32
00:02:05,120 --> 00:02:06,560
For splitting in its folder.
33
00:02:06,560 --> 00:02:08,060
There are three more folders.
34
00:02:09,030 --> 00:02:12,120
Specifically the train well and test follows.
35
00:02:19,060 --> 00:02:21,550
We have provided Python code to split the dataset.
36
00:02:23,290 --> 00:02:25,580
Specifically split dataset dot pie.
37
00:02:25,600 --> 00:02:31,060
In this example, we open the code with Fisher's studio code, you can also use another text editor.
38
00:02:33,660 --> 00:02:34,470
Here is the code.
39
00:02:34,470 --> 00:02:36,660
There are several arguments that can be used.
40
00:02:36,690 --> 00:02:41,260
The first argument is the train argument, which is used to specify the percentage of train data.
41
00:02:41,280 --> 00:02:42,750
The default value is 80.
42
00:02:42,780 --> 00:02:47,560
Then there is the validation argument, which is used to specify the percentage of data validation.
43
00:02:47,580 --> 00:02:49,020
The default value is ten.
44
00:02:49,050 --> 00:02:53,230
Then there is the test argument, which is used to specify the percentage of data tests.
45
00:02:53,250 --> 00:02:54,730
The default value is ten.
46
00:02:54,750 --> 00:02:59,220
The further argument is used to specify the folder where the dataset is stored before splitting.
47
00:02:59,250 --> 00:03:03,390
The This argument is used to specify the folder where the split results will be safe.
48
00:03:03,600 --> 00:03:05,970
After that, we try to do the splitting with the code.
49
00:03:07,280 --> 00:03:09,620
Press the windows key, then type in a condom.
50
00:03:10,760 --> 00:03:12,260
Click on the Anaconda prompt.
51
00:03:13,550 --> 00:03:17,750
After that activate the all of seven CPU environment using the command.
52
00:03:22,870 --> 00:03:23,680
Activate.
53
00:03:24,750 --> 00:03:27,090
YOLO v seven to for you and v.
54
00:03:29,990 --> 00:03:30,860
Press enter.
55
00:03:35,220 --> 00:03:36,960
Then navigate to the data folder.
56
00:03:44,820 --> 00:03:46,050
We will split the death of it.
57
00:03:46,050 --> 00:03:47,430
Composition 80%.
58
00:03:47,430 --> 00:03:52,320
Train death 10% validation data and 10% test data using the command.
59
00:03:59,500 --> 00:04:01,900
Clayton Split Data set dot p.
60
00:04:04,890 --> 00:04:07,350
In the further argument, we read the face mask.
61
00:04:11,890 --> 00:04:13,870
In the train argument we wrote at the.
62
00:04:15,590 --> 00:04:16,850
Invalidates an argument.
63
00:04:16,850 --> 00:04:17,720
We write ten.
64
00:04:19,630 --> 00:04:21,579
In the test argument we write ten.
65
00:04:26,860 --> 00:04:30,160
We will save the split result in the Face mask dataset folder.
66
00:04:31,150 --> 00:04:31,990
First intro.
67
00:04:33,020 --> 00:04:34,760
Then we try to see the results.
68
00:04:39,530 --> 00:04:41,750
Here is the Face Mask dataset folder.
69
00:04:46,330 --> 00:04:48,280
There is an images and labels folder.
70
00:04:51,520 --> 00:04:53,380
And there are three speed folders.
71
00:04:54,390 --> 00:04:57,180
The following is an example of the photo's contents.
72
00:05:00,130 --> 00:05:03,100
In the next video, we will create a configuration file.
73
00:05:03,130 --> 00:05:03,850
See you then.
5886
Can't find what you're looking for?
Get subtitles in any language from opensubtitles.com, and translate them here.