Would you like to inspect the original subtitles? These are the user uploaded subtitles that are being translated:
1
00:00:00,150 --> 00:00:03,790
In this video, I will explain the program called Use for the Squad counter.
2
00:00:05,190 --> 00:00:08,460
First open the squad contact by using a text editor.
3
00:00:08,910 --> 00:00:11,610
In this example, we are using Visual Studio Code.
4
00:00:13,250 --> 00:00:16,190
First, some libraries and functions must be imported.
5
00:00:16,700 --> 00:00:18,740
The library use is described below.
6
00:00:19,800 --> 00:00:20,330
Up first.
7
00:00:20,340 --> 00:00:23,640
It's used to press arguments to the Python code via the command line.
8
00:00:24,150 --> 00:00:28,290
Finally, it's used to obtain the time, which is then used to calculate the detection time.
9
00:00:28,900 --> 00:00:34,140
So if it is used to open images, display images draw bounding boxes on images and so on.
10
00:00:34,650 --> 00:00:40,170
False is used because the model used is based on python's numpy is used to manipulate arrays.
11
00:00:41,470 --> 00:00:42,540
Next is the function.
12
00:00:42,550 --> 00:00:46,990
This function is imported from the utils and models from each of these seven repository.
13
00:00:47,970 --> 00:00:50,810
Attempt blood is used to load all of these seven models.
14
00:00:51,840 --> 00:00:56,610
Box is used to add pending to the image so that it becomes squared according to the image size.
15
00:00:57,180 --> 00:01:02,760
Non max Suppressing CPT is used to perform non maximal suppression on the results of object detection
16
00:01:02,760 --> 00:01:05,730
in order to reduce overlapping of the detection results.
17
00:01:06,640 --> 00:01:10,060
Care costs capped is used to rescale bonding boxes.
18
00:01:10,720 --> 00:01:13,510
Colors is used to give a color to the detection results.
19
00:01:14,450 --> 00:01:14,660
Lot.
20
00:01:14,660 --> 00:01:20,450
One box kept is used to draw bounding boxes, key points, class names and confidence scores.
21
00:01:21,110 --> 00:01:24,620
Select devices used to choose a device based on the device argument.
22
00:01:25,970 --> 00:01:30,200
After an explanation of import libraries and functions didn't go to the main function.
23
00:01:32,030 --> 00:01:35,300
The arguments that can be used are first defined in the main function.
24
00:01:35,750 --> 00:01:37,430
There are 14 arguments here.
25
00:01:38,240 --> 00:01:40,070
First there is the weight argument.
26
00:01:40,340 --> 00:01:44,030
This argument specifies the of these seven weights file to be used.
27
00:01:44,360 --> 00:01:48,020
YOLO v7w6 Postscript is the default value.
28
00:01:48,740 --> 00:01:50,510
The source argument comes next.
29
00:01:50,900 --> 00:01:53,720
This argument is used to accept the source to be detected.
30
00:01:54,080 --> 00:01:56,930
Only video and webcam are supported in this source code.
31
00:01:57,440 --> 00:02:02,720
The default value is zero, which indicates webcam then the image size argument.
32
00:02:03,110 --> 00:02:05,360
This argument is for inference size.
33
00:02:06,050 --> 00:02:08,240
The default value is 640.
34
00:02:09,020 --> 00:02:10,729
Next is the contract argument.
35
00:02:11,090 --> 00:02:13,760
This argument is an object confidence threshold.
36
00:02:14,240 --> 00:02:18,170
The detection results that will be displayed are those with a score greater than this threshold.
37
00:02:18,980 --> 00:02:21,200
0.25 is the default value.
38
00:02:21,920 --> 00:02:23,840
Makes the A02s argument.
39
00:02:24,230 --> 00:02:27,380
This argument is the threshold for non suppression.
40
00:02:28,120 --> 00:02:29,680
Next is the device argument.
41
00:02:30,070 --> 00:02:31,200
This argument is cute.
42
00:02:31,200 --> 00:02:31,960
A device.
43
00:02:32,350 --> 00:02:35,680
If you want to use CPU, you replace zero with CPU.
44
00:02:36,400 --> 00:02:38,320
The view image argument comes next.
45
00:02:38,740 --> 00:02:41,680
This is an argument for displaying the detection results.
46
00:02:42,460 --> 00:02:42,990
Next.
47
00:02:43,000 --> 00:02:44,110
No safe argument.
48
00:02:44,470 --> 00:02:48,100
This argument is used if you don't want to save the detection results.
49
00:02:48,920 --> 00:02:51,200
Then there are the project and name arguments.
50
00:02:51,620 --> 00:02:55,280
This argument specifies the location of the detection results folder.
51
00:02:56,130 --> 00:02:57,960
Next is the line thickness argument.
52
00:02:58,440 --> 00:03:01,560
This argument is used to set the thickness of the bonding box.
53
00:03:02,010 --> 00:03:03,600
The default value is three.
54
00:03:04,290 --> 00:03:06,390
Next is the height labels argument.
55
00:03:06,780 --> 00:03:09,420
This argument is used to hide the confidence score.
56
00:03:10,200 --> 00:03:12,450
Next is the capital level argument.
57
00:03:12,870 --> 00:03:15,450
This argument is used to display the key points.
58
00:03:16,350 --> 00:03:18,240
Finally, there is the argument angle.
59
00:03:18,690 --> 00:03:22,350
This argument is used to set the angle that determines the squad position.
60
00:03:22,710 --> 00:03:24,330
The default value is 80.
61
00:03:25,970 --> 00:03:26,690
Following them.
62
00:03:26,690 --> 00:03:33,140
This program code is used to check the sources extension because we only accept video and webcam if
63
00:03:33,140 --> 00:03:35,200
the source extension is in the following array.
64
00:03:35,240 --> 00:03:38,600
Image type would be true, otherwise it will be false.
65
00:03:39,170 --> 00:03:40,610
Next, there is a condition.
66
00:03:40,910 --> 00:03:45,350
If the source is an image, the following string will be displayed and the detection process will be
67
00:03:45,350 --> 00:03:45,830
aborted.
68
00:03:46,640 --> 00:03:51,380
If it is not an image, the detection process will be initiated by calling the detect function.
69
00:03:52,110 --> 00:03:53,580
Let me call you Detective Thompson.
70
00:03:53,610 --> 00:03:59,520
We used to have snow graft to prevent pilots from calculating the gradients, because completing gradients
71
00:03:59,520 --> 00:04:01,590
would result in a GPU memory leak.
72
00:04:02,320 --> 00:04:04,270
Next go to the detect function.
73
00:04:06,020 --> 00:04:09,620
This program called is used to store several arguments in variables.
74
00:04:10,460 --> 00:04:14,510
This program called is used to determine the folder where the detection results are safe.
75
00:04:15,280 --> 00:04:19,660
This program called is responsible for selecting the device based on the device argument.
76
00:04:20,690 --> 00:04:24,620
The problem code is used to determine whether the model can be run with half precision.
77
00:04:25,040 --> 00:04:28,310
Half precision has the advantage of requiring less memory.
78
00:04:28,700 --> 00:04:33,590
The condition for using half is that the device use has a GPU with a compute capability greater than
79
00:04:33,590 --> 00:04:33,890
eight.
80
00:04:34,310 --> 00:04:37,460
If it meets these criteria, the half variable will be true.
81
00:04:38,380 --> 00:04:39,160
In this column.
82
00:04:39,160 --> 00:04:43,900
The attempt not function with weights and device parameters is used to load all of these seven model.
83
00:04:44,650 --> 00:04:47,330
This condition is used to use half precision in the model.
84
00:04:47,350 --> 00:04:49,090
If the half variable is true.
85
00:04:49,960 --> 00:04:54,970
Furthermore, this program called is used to check the source and open the video to open the video.
86
00:04:55,000 --> 00:04:57,640
We use the video capture function from open cfy.
87
00:04:58,090 --> 00:04:59,960
This function requires a parameter.
88
00:04:59,980 --> 00:05:00,460
The video.
89
00:05:01,700 --> 00:05:04,940
This program called determines whether or not the source is a webcam.
90
00:05:05,240 --> 00:05:10,340
If it's a webcam, we must cast the source from string to integer in the video capture function parameter.
91
00:05:10,880 --> 00:05:12,710
If not, leave it as it is.
92
00:05:13,790 --> 00:05:16,850
Furthermore, this program code is to obtain class names.
93
00:05:17,680 --> 00:05:20,020
Next, we initialize two variables.
94
00:05:20,710 --> 00:05:23,410
The control variable is initialized with a value of zero.
95
00:05:23,440 --> 00:05:26,140
This variable is used to calculate the squad movement.
96
00:05:26,650 --> 00:05:29,300
The states variable is initialized with an empty string.
97
00:05:29,320 --> 00:05:31,240
This variable is used to store more.
98
00:05:31,980 --> 00:05:34,830
Then you looking to access all the frames in the video?
99
00:05:35,660 --> 00:05:38,210
To retrieve a frame use kept up with function.
100
00:05:38,600 --> 00:05:42,980
This function will return a frame value and whether or not the frame was successfully retrieved.
101
00:05:43,340 --> 00:05:47,150
If it is not successfully retrieved, the program will automatically exit.
102
00:05:47,920 --> 00:05:48,410
Next.
103
00:05:48,430 --> 00:05:50,380
Copy the frame to the image variable.
104
00:05:50,890 --> 00:05:56,110
Then resize the frame according to the image size argument and appending to the frame to make it square.
105
00:05:57,340 --> 00:06:00,820
This program called is used to convert from BGR to RCB.
106
00:06:01,210 --> 00:06:06,070
In addition, convert dimension from height with channels to channels height with.
107
00:06:07,000 --> 00:06:09,790
This problem code is used to convert image to tensor.
108
00:06:11,030 --> 00:06:17,150
This program called is used to normalize the pixel values from 0 to 255 becomes 0 to 1.
109
00:06:18,190 --> 00:06:21,310
For the Texan, you have to add a better dimension to the image.
110
00:06:21,850 --> 00:06:24,190
This program code will add a better dimension.
111
00:06:25,140 --> 00:06:29,850
Furthermore, for detection, use the mode of function with one parameter, namely the image or video
112
00:06:29,850 --> 00:06:33,450
frame detection results are stored in the prep variable.
113
00:06:34,250 --> 00:06:34,880
After that.
114
00:06:34,880 --> 00:06:39,140
This program called is used to perform non max suppression under detection results.
115
00:06:39,990 --> 00:06:43,590
The t one and t two variables are used to calculate the detection time.
116
00:06:44,490 --> 00:06:47,040
Next, we assess the detection results.
117
00:06:47,490 --> 00:06:51,360
This variable is of type list, but the detection results are in the first list.
118
00:06:51,750 --> 00:06:54,390
We start the detection results to the date variable.
119
00:06:55,400 --> 00:06:57,650
This program called determines the safe path.
120
00:06:58,070 --> 00:07:03,200
This safe path is a combination of the folder name and the file name that stores the detection results.
121
00:07:04,280 --> 00:07:07,820
There are conditions that are used to check whether there is a detection result or not.
122
00:07:08,420 --> 00:07:11,120
If there is, it will proceed to the next process.
123
00:07:12,410 --> 00:07:17,390
This program called is used to rescaled the detection results to the original image of frame size.
124
00:07:18,180 --> 00:07:19,830
Makes you slip into access.
125
00:07:19,830 --> 00:07:26,160
All the tests and results, the detection results are bonding boxes, confidence scores and class ID.
126
00:07:27,050 --> 00:07:31,640
In this section, we will calculate the squad and draw the detection results in the image or frame.
127
00:07:32,790 --> 00:07:35,820
This program called is used to convert class ed integer.
128
00:07:36,570 --> 00:07:38,970
This program code is for the label to be displayed.
129
00:07:39,360 --> 00:07:42,660
If there is a Hide Labels argument, then this label will be empty.
130
00:07:43,050 --> 00:07:45,720
If not, then this label is a confidence score.
131
00:07:46,470 --> 00:07:49,290
This program code is used to get a list of key points.
132
00:07:50,040 --> 00:07:52,770
Key points will be stored in the kept as variable.
133
00:07:53,580 --> 00:07:55,310
So identify squad movements.
134
00:07:55,320 --> 00:07:58,020
Three points are required to hit me and Hill.
135
00:07:58,590 --> 00:08:01,020
We used to get calls from soon to find a point.
136
00:08:02,830 --> 00:08:06,670
The course function accepts one parameter, namely this key points.
137
00:08:07,770 --> 00:08:11,250
Following are the key points of the hip, knee and heal on the left leg.
138
00:08:11,640 --> 00:08:12,830
And here are the key points.
139
00:08:12,830 --> 00:08:15,000
The idea of the hit me and heel on the right leg.
140
00:08:15,660 --> 00:08:21,780
Next, we take one of the key points that exists in the text and results we use to get hip knee function.
141
00:08:22,720 --> 00:08:26,680
This function accepts two parameters, namely, list key points and list ID.
142
00:08:27,480 --> 00:08:32,130
This looping is used to check whether the hit me and hill points are present in the detection results.
143
00:08:32,919 --> 00:08:35,110
If there is, it will be added to the array.
144
00:08:36,030 --> 00:08:40,470
This function will return an array containing the coordinates of the hit me and heal points.
145
00:08:41,860 --> 00:08:43,390
First we take on the left leg.
146
00:08:43,900 --> 00:08:45,820
If not, then take on the right leg.
147
00:08:46,240 --> 00:08:51,070
If it's not on the left and right legs, then it's not a squat movement to determine the squat movement
148
00:08:51,070 --> 00:08:51,520
or not.
149
00:08:51,550 --> 00:08:53,680
We will store it in a squat post variable.
150
00:08:54,490 --> 00:08:57,010
After that, we will return the array and the variable.
151
00:08:58,850 --> 00:09:00,200
Return to this section.
152
00:09:00,910 --> 00:09:05,590
If you have got an array that stores the coordinates of the hit me and he points, then we will calculate
153
00:09:05,590 --> 00:09:07,270
the angle between these points.
154
00:09:08,100 --> 00:09:11,820
This angle calculation is performed if the squat pulse variable is true.
155
00:09:12,600 --> 00:09:15,780
To calculate the angle used to calculate angle function.
156
00:09:17,550 --> 00:09:22,470
This function accepts one parameter, which is an array that stores the coordinates of the NI and hill
157
00:09:22,470 --> 00:09:23,160
points.
158
00:09:23,940 --> 00:09:26,640
This program code is used to calculate angles.
159
00:09:27,420 --> 00:09:30,090
After that, we will return the angle that has been obtained.
160
00:09:31,850 --> 00:09:33,260
We turn to this section.
161
00:09:34,210 --> 00:09:38,170
After getting the anger used the squad from him to compute the squad movement.
162
00:09:39,920 --> 00:09:43,970
This function requires three parameters angle, stage and counter.
163
00:09:45,310 --> 00:09:48,340
What are counted when you stand squat and then stand again.
164
00:09:49,090 --> 00:09:51,310
There are several conditions for this function.
165
00:09:52,030 --> 00:09:56,620
The first condition is if the angle is greater than 160, it will enter this condition.
166
00:09:57,500 --> 00:09:59,150
Was the previous movement down?
167
00:09:59,150 --> 00:10:01,700
If yes, then the counter will be increased by one.
168
00:10:02,030 --> 00:10:04,160
After that, the states will become a stand.
169
00:10:05,070 --> 00:10:09,810
The second condition, which is used to change the stage to down if the angle is less than the angle
170
00:10:09,810 --> 00:10:12,000
argument and the stage is equal to the stem.
171
00:10:12,690 --> 00:10:16,320
This function will return the angle states and counter values.
172
00:10:18,150 --> 00:10:19,500
We turn to this section.
173
00:10:20,300 --> 00:10:25,430
After calculating the squad use this program called to draw bounding boxes and key points on the image
174
00:10:25,430 --> 00:10:26,000
of frame.
175
00:10:27,340 --> 00:10:31,570
This program called is used to display time of detection and non mock suppression.
176
00:10:32,810 --> 00:10:37,070
Furthermore, this program called is used to display the counter and states in the upper left corner
177
00:10:37,070 --> 00:10:37,970
of the image.
178
00:10:38,540 --> 00:10:42,800
This program's called creates a black box using the cfy two rectangle function.
179
00:10:43,520 --> 00:10:45,500
This program called the soda counter.
180
00:10:46,280 --> 00:10:48,800
This program called is used to display the state.
181
00:10:49,250 --> 00:10:51,710
If you are standing, the state's writing will be green.
182
00:10:52,250 --> 00:10:54,350
If you are done squatting, it will be read.
183
00:10:55,850 --> 00:10:59,690
Furthermore, the detection results will be displayed if the few IMC is true.
184
00:11:00,680 --> 00:11:04,460
However, before displaying the image or frame, we will take its width and height.
185
00:11:04,970 --> 00:11:10,430
If the width or height exceed 1500 pixels, the image will be resized by 70%.
186
00:11:11,650 --> 00:11:15,490
The inmates of frame is then displayed using the cv2 dot himself function.
187
00:11:16,740 --> 00:11:21,960
Next, if Chef Ramsay is set to throw, the detection results will be saved as a video using the program
188
00:11:21,960 --> 00:11:22,710
code below.
189
00:11:24,090 --> 00:11:27,720
This program called is used to stop detection by pressing the key.
190
00:11:28,560 --> 00:11:32,520
Finally, this program called is used to display the time of the entire process.
191
00:11:33,840 --> 00:11:36,390
That's all the explanation of this squad code.
192
00:11:36,600 --> 00:11:37,170
Thank you.
193
00:11:37,170 --> 00:11:38,010
And see you then.
18382
Can't find what you're looking for?
Get subtitles in any language from opensubtitles.com, and translate them here.