Would you like to inspect the original subtitles? These are the user uploaded subtitles that are being translated:
1
00:00:03,070 --> 00:00:03,400
Okay.
2
00:00:03,400 --> 00:00:09,790
Then in the previous video, we have trained up to 63 epochs and got accuracy with P of 0.72.
3
00:00:09,820 --> 00:00:13,380
In this video we will try to detect face mask using the train weights.
4
00:00:13,390 --> 00:00:15,370
The notebook use is the same as before.
5
00:00:15,370 --> 00:00:16,840
The goal of seven notebook.
6
00:00:18,060 --> 00:00:21,990
If you haven't already mounted Google Drive, run the following three cells.
7
00:00:24,020 --> 00:00:27,110
If so, skip ahead to the face mask detection section.
8
00:00:31,030 --> 00:00:31,870
For detection.
9
00:00:31,870 --> 00:00:34,000
We have provided an image that can be downloaded.
10
00:00:34,030 --> 00:00:37,300
Therefore, the first code cell is used to download the image.
11
00:00:40,980 --> 00:00:43,770
Use the command g down, then link the image.
12
00:00:45,010 --> 00:00:47,410
When the sale by pressing the following button.
13
00:00:52,180 --> 00:00:54,430
The image is facemask doc PNC.
14
00:00:57,090 --> 00:00:59,550
Next move the image to the inference folder.
15
00:01:01,030 --> 00:01:04,870
Use the command mv face, mask, dock and Z inference.
16
00:01:06,050 --> 00:01:08,390
When the sale by pressing the following button.
17
00:01:11,060 --> 00:01:14,900
Next we will detect object on the face mask, dot P and G image.
18
00:01:14,930 --> 00:01:17,390
Use the following command to perform detection.
19
00:01:18,160 --> 00:01:20,170
Titan detect the pine.
20
00:01:22,130 --> 00:01:28,250
That's that's why it's we use what's best, not pity, which is the words that have the highest p value.
21
00:01:29,060 --> 00:01:31,580
In contrast, we use 0.5.
22
00:01:33,120 --> 00:01:35,730
In the image size, we use 640.
23
00:01:35,970 --> 00:01:39,150
In source read inference face Mass dot three and G.
24
00:01:40,060 --> 00:01:42,430
When the sale by pressing the following button.
25
00:01:48,010 --> 00:01:50,350
Wait until the detection process is finished.
26
00:01:53,790 --> 00:01:57,510
When finished, the detection results will be stored in the following folder.
27
00:02:00,830 --> 00:02:04,040
Next, we add a function to display the image in this code cell.
28
00:02:04,070 --> 00:02:07,160
This function is also used in the detection on image section.
29
00:02:08,810 --> 00:02:11,120
When the sale by pressing the following button.
30
00:02:13,920 --> 00:02:15,480
Continue to the next cell.
31
00:02:16,080 --> 00:02:19,380
This cell will call the cell image function to display the detection result.
32
00:02:20,920 --> 00:02:22,570
Blocking its path like this.
33
00:02:24,290 --> 00:02:26,030
Then copy by pressing control.
34
00:02:26,070 --> 00:02:26,510
See?
35
00:02:29,010 --> 00:02:30,240
And there were quotes.
36
00:02:31,160 --> 00:02:33,740
Place the image pad by pressing control fee.
37
00:02:36,880 --> 00:02:39,250
When the sale by pressing the following button.
38
00:02:47,690 --> 00:02:48,650
Here are the results.
39
00:02:48,650 --> 00:02:50,450
The mask is detected properly.
40
00:03:02,810 --> 00:03:05,560
Four masks are correctly detected in this image.
41
00:03:08,720 --> 00:03:12,200
You can save the training results and run detection on your own computer.
42
00:03:17,810 --> 00:03:19,040
To perform the detection.
43
00:03:19,040 --> 00:03:23,150
You just need to download the weights with the highest MLP memory based doped.
44
00:03:24,650 --> 00:03:25,790
Congratulations.
45
00:03:25,790 --> 00:03:27,860
You have finished the detection project.
46
00:03:28,400 --> 00:03:29,870
See you in the next video.
3846
Can't find what you're looking for?
Get subtitles in any language from opensubtitles.com, and translate them here.