1 00:00:02,000 --> 00:00:07,000 And now we will run it on webcam and see what results do we get. 2 00:00:07,000 --> 00:00:14,000 So I will just click over here and create a new directory by the name running YOLO. 3 00:00:15,000 --> 00:00:16,000 V8. 4 00:00:16,000 --> 00:00:17,000 Webcam. 5 00:00:17,000 --> 00:00:21,000 Okay, so now we will be running YOLO V8 on the webcam. 6 00:00:21,000 --> 00:00:24,000 So just create a new folder over here. 7 00:00:24,000 --> 00:00:25,000 Yolo. 8 00:00:27,000 --> 00:00:29,000 He end webcam dot pi. 9 00:00:30,000 --> 00:00:33,000 So I'm just created a new file over here. 10 00:00:33,000 --> 00:00:36,000 Yolo v8 webcam.py. 11 00:00:36,000 --> 00:00:38,000 And first of all, I will just write. 12 00:00:38,000 --> 00:00:40,000 Just close the previous ones. 13 00:00:41,000 --> 00:00:42,000 From Ultralytics. 14 00:00:44,000 --> 00:00:44,000 Import. 15 00:00:45,000 --> 00:00:46,000 Yolo. 16 00:00:47,000 --> 00:00:51,000 Okay, so we have just imported the YOLO V8 version over here. 17 00:00:53,000 --> 00:00:56,000 And I will write import cv2. 18 00:00:56,000 --> 00:00:58,000 Then I will just write import math. 19 00:00:58,000 --> 00:01:02,000 Over here will read. 20 00:01:03,000 --> 00:01:04,000 Currently just remove this. 21 00:01:04,000 --> 00:01:07,000 I will just explain this as we go further on. 22 00:01:08,000 --> 00:01:08,000 So. 23 00:01:08,000 --> 00:01:08,000 Okay. 24 00:01:10,000 --> 00:01:11,000 Then just right. 25 00:01:11,000 --> 00:01:15,000 App is equal to Cv2 dot videocapture. 26 00:01:16,000 --> 00:01:21,000 And just right as I just want to run YOLO on V8 on my webcam. 27 00:01:21,000 --> 00:01:23,000 So I will just write zero over here. 28 00:01:23,000 --> 00:01:29,000 But if you have multiple webcams or connected with your system, then you can just check which webcam 29 00:01:29,000 --> 00:01:30,000 are you using? 30 00:01:30,000 --> 00:01:32,000 It can be 1 or 0 in any case. 31 00:01:35,000 --> 00:01:38,000 Then I will just calculate the frame rate over here. 32 00:01:39,000 --> 00:01:39,000 It. 33 00:01:43,000 --> 00:01:46,000 Or to get the frame rate just right. 34 00:01:47,000 --> 00:01:51,000 And app dot get three. 35 00:01:51,000 --> 00:01:54,000 And to just get the frame height just right. 36 00:01:54,000 --> 00:01:58,000 Frame height is equal to end cap. 37 00:01:59,000 --> 00:02:01,000 Dot get four. 38 00:02:01,000 --> 00:02:05,000 So in this way we are just getting the frame width and the frame height. 39 00:02:09,000 --> 00:02:16,000 I just want to save the output video with detection I will just write out is equal to cv2.video writer. 40 00:02:22,000 --> 00:02:24,000 And just write a name. 41 00:02:24,000 --> 00:02:26,000 Output dot you. 42 00:02:26,000 --> 00:02:30,000 This is the name, uh, the name of my output file. 43 00:02:30,000 --> 00:02:38,000 Like after doing the detections or after doing detection on video or using webcam, the output video 44 00:02:38,000 --> 00:02:41,000 will be saved by the name output dot avi. 45 00:02:44,000 --> 00:02:52,000 I mean, we just write cv2.video writer dash for CC and. 46 00:02:54,000 --> 00:02:54,000 That's right. 47 00:02:57,000 --> 00:02:57,000 That's right. 48 00:02:57,000 --> 00:02:58,000 I'm over here. 49 00:02:59,000 --> 00:03:01,000 And Omar J. 50 00:03:02,000 --> 00:03:02,000 Omar. 51 00:03:04,000 --> 00:03:04,000 Anyway. 52 00:03:07,000 --> 00:03:08,000 Okay. 53 00:03:10,000 --> 00:03:19,000 Then just pass the frame rate over here and then just pass the frame rate and frame height over here. 54 00:03:19,000 --> 00:03:21,000 Okay, so just define my output. 55 00:03:21,000 --> 00:03:25,000 Video writer function over here using cv2.video writer. 56 00:03:25,000 --> 00:03:27,000 Then just click on enter. 57 00:03:30,000 --> 00:03:32,000 Just right model is equal to. 58 00:03:33,000 --> 00:03:35,000 Journal and. 59 00:03:37,000 --> 00:03:41,000 If I just go to the YOLO V it's for YOLO weights folder over here. 60 00:03:41,000 --> 00:03:46,000 You can see that here we have the YOLO V8 and our Pre-trained weights placed over here. 61 00:03:46,000 --> 00:03:50,000 So just write dot dot and just say that go to store. 62 00:03:50,000 --> 00:03:56,000 We just need to get out this out of this running YOLO V8 webcam folder and just need to go to the YOLO 63 00:03:56,000 --> 00:03:57,000 weights folder. 64 00:03:58,000 --> 00:04:00,000 So just write YOLO dash weights. 65 00:04:00,000 --> 00:04:01,000 Okay. 66 00:04:01,000 --> 00:04:06,000 And just write YOLO V8 and Dot over here. 67 00:04:06,000 --> 00:04:12,000 So here I'm just passing the Pre-trained weights path over here and just click on enter over here. 68 00:04:15,000 --> 00:04:15,000 Then just right. 69 00:04:16,000 --> 00:04:17,000 Wine through. 70 00:04:18,000 --> 00:04:19,000 Okay. 71 00:04:22,000 --> 00:04:24,000 Success is a common image. 72 00:04:27,000 --> 00:04:30,000 Is equal to cap dot read. 73 00:04:30,000 --> 00:04:32,000 So we are just. 74 00:04:34,000 --> 00:04:35,000 Reading frame by frame. 75 00:04:35,000 --> 00:04:36,000 Okay. 76 00:04:39,000 --> 00:04:41,000 Okay, so let's just test this. 77 00:04:41,000 --> 00:04:44,000 Either our webcam is working fine or is there an issue? 78 00:04:47,000 --> 00:04:50,000 Or just write CV two dot I am show. 79 00:04:52,000 --> 00:04:52,000 Image. 80 00:04:54,000 --> 00:05:02,000 My image over here and just write Cv2 dot, wait key over here and just click over here. 81 00:05:02,000 --> 00:05:05,000 One and I think. 82 00:05:06,000 --> 00:05:10,000 That's fine or just further elaborated. 83 00:05:10,000 --> 00:05:11,000 Cv2 dot Waitkey is one. 84 00:05:13,000 --> 00:05:13,000 And. 85 00:05:16,000 --> 00:05:17,000 Order is equal to. 86 00:05:19,000 --> 00:05:20,000 One then. 87 00:05:22,000 --> 00:05:22,000 Great. 88 00:05:22,000 --> 00:05:25,000 Okay, so that's completely fine. 89 00:05:32,000 --> 00:05:37,000 So let me just run it and see if I am able to access the webcam or not. 90 00:05:37,000 --> 00:05:40,000 And if I'm able to save the output video or not. 91 00:05:40,000 --> 00:05:45,000 So let's just click over here and click on Run YOLO V8 Webcam. 92 00:05:45,000 --> 00:05:46,000 Okay. 93 00:05:46,000 --> 00:05:53,000 So let me just I think it might take a few seconds for it to appear, so let's just wait. 94 00:05:54,000 --> 00:05:54,000 Okay. 95 00:05:56,000 --> 00:05:57,000 I don't think any other. 96 00:05:57,000 --> 00:05:58,000 Okay, let's just. 97 00:05:58,000 --> 00:06:00,000 Just navigate my screen over here. 98 00:06:00,000 --> 00:06:01,000 Just give me a minute. 99 00:06:01,000 --> 00:06:04,000 So now you can see over here the webcam is working fine. 100 00:06:04,000 --> 00:06:08,000 And now you can see by the image on your screens. 101 00:06:08,000 --> 00:06:12,000 Okay, So I think the webcam is working fine. 102 00:06:12,000 --> 00:06:16,000 Let's see if this output video is being saved into the directory or not. 103 00:06:16,000 --> 00:06:19,000 Okay, so let me just go back over here. 104 00:06:19,000 --> 00:06:19,000 Okay. 105 00:06:19,000 --> 00:06:25,000 So now you can see that here we have the output for file has been created over here. 106 00:06:25,000 --> 00:06:34,000 But let me just go back from here and just let me just pause, stop this process by just clicking over 107 00:06:34,000 --> 00:06:35,000 here. 108 00:06:35,000 --> 00:06:35,000 Okay. 109 00:06:35,000 --> 00:06:40,000 And let me just see if the output video is working or is there an issue. 110 00:06:40,000 --> 00:06:41,000 So just click over here. 111 00:06:42,000 --> 00:06:46,000 So now we can see that our output video is being saved. 112 00:06:46,000 --> 00:06:46,000 Okay. 113 00:06:46,000 --> 00:06:47,000 So now you can see that. 114 00:06:48,000 --> 00:06:53,000 Uh, as when we run the webcam, our video has been saved, so that's fine. 115 00:06:53,000 --> 00:06:54,000 That's perfectly fine. 116 00:06:55,000 --> 00:06:57,000 Okay, so let me just go back towards the code. 117 00:06:58,000 --> 00:06:59,000 For now. 118 00:06:59,000 --> 00:07:06,000 Now, I will just add the I'm not using the V8 model, which I've just called over here and just saved 119 00:07:06,000 --> 00:07:07,000 in the variable model. 120 00:07:08,000 --> 00:07:11,000 Now I will just run the detections on the live web feed. 121 00:07:11,000 --> 00:07:17,000 So let me just add that code over here and run detection on the live webcam feed as well. 122 00:07:20,000 --> 00:07:21,000 Read it. 123 00:07:21,000 --> 00:07:25,000 Well, here I have just written the complete code, so let me just explain you the complete code over 124 00:07:25,000 --> 00:07:26,000 here. 125 00:07:26,000 --> 00:07:33,000 So now here you can see that we are just doing the detections using YOLO V8 model on frame by frame. 126 00:07:33,000 --> 00:07:34,000 So here we have Stata. 127 00:07:34,000 --> 00:07:37,000 Stream is equal to true, so stream is equal to true. 128 00:07:37,000 --> 00:07:42,000 We'll use the generator and it is more efficient than the than if we just don't write stream is equal 129 00:07:42,000 --> 00:07:43,000 to true. 130 00:07:43,000 --> 00:07:43,000 Okay. 131 00:07:43,000 --> 00:07:49,000 So we are doing detection using YOLO v8 frame by frame and our result is are saved in this variable 132 00:07:49,000 --> 00:07:50,000 results. 133 00:07:50,000 --> 00:07:55,000 So once we have the results, we can check for individual bounding boxes and see how does it performs. 134 00:07:55,000 --> 00:08:00,000 So here you can see here, once we have the results, we can check for the individual bounding boxes 135 00:08:00,000 --> 00:08:02,000 and see how well it performs. 136 00:08:02,000 --> 00:08:10,000 So we will just look through each of the bounding boxes and for each of the result and see how how it 137 00:08:10,000 --> 00:08:11,000 detections are performing. 138 00:08:11,000 --> 00:08:12,000 Okay. 139 00:08:12,000 --> 00:08:16,000 So now you can see that here we are just looping through each of the individual bounding boxes. 140 00:08:17,000 --> 00:08:18,000 You can see over here. 141 00:08:18,000 --> 00:08:25,000 So here we have the X1Y1 coordinate of the bounding box and here we have the x2 and y2 coordinate of 142 00:08:25,000 --> 00:08:26,000 the bounding box. 143 00:08:26,000 --> 00:08:28,000 So let me just show you how it is. 144 00:08:28,000 --> 00:08:29,000 Basically it works. 145 00:08:29,000 --> 00:08:32,000 So let me just open the paint over here. 146 00:08:33,000 --> 00:08:33,000 Um. 147 00:08:33,000 --> 00:08:34,000 Okay. 148 00:08:34,000 --> 00:08:34,000 Just give me a minute. 149 00:08:35,000 --> 00:08:35,000 I'm just opening. 150 00:08:35,000 --> 00:08:35,000 Okay. 151 00:08:36,000 --> 00:08:38,000 So, for example, if we have this bounding box. 152 00:08:38,000 --> 00:08:44,000 Okay, so you can see here we have the four coordinates for each of the bounding box. 153 00:08:44,000 --> 00:08:45,000 Let me just write over here. 154 00:08:45,000 --> 00:08:47,000 So this is the x one. 155 00:08:48,000 --> 00:08:53,000 Y1 coordinate and this is the x2 and y2 coordinate. 156 00:08:53,000 --> 00:08:53,000 Okay. 157 00:08:53,000 --> 00:09:00,000 So for each of the bounding box we have the X1Y1 coordinate and this is the X2Y2 coordinate. 158 00:09:00,000 --> 00:09:09,000 So X1Y1 is the like you can see that at top left corner coordinate and this x2 y2 is the bottom right 159 00:09:09,000 --> 00:09:10,000 corner coordinate. 160 00:09:10,000 --> 00:09:10,000 Okay. 161 00:09:10,000 --> 00:09:13,000 So if you just go back towards the board again. 162 00:09:14,000 --> 00:09:20,000 Okay, so now you can see for each of the bounding box we have the x1, y1 and x2 y2 coordinates. 163 00:09:20,000 --> 00:09:22,000 Okay, that's perfectly fine. 164 00:09:22,000 --> 00:09:24,000 If we just go over here. 165 00:09:24,000 --> 00:09:28,000 So now you can see that we are just converting this coordinates values to integers. 166 00:09:28,000 --> 00:09:28,000 Why? 167 00:09:28,000 --> 00:09:31,000 We just need to convert this coordinate value to integers. 168 00:09:31,000 --> 00:09:35,000 Because the output which we are getting over here is in the form of tensors. 169 00:09:35,000 --> 00:09:37,000 We need to convert this output into integers. 170 00:09:37,000 --> 00:09:40,000 So let me just show you what kind of output we are getting. 171 00:09:40,000 --> 00:09:44,000 And after converting into integers, what kind of output do we get? 172 00:09:44,000 --> 00:09:49,000 So just run this from here and just let me just show you the output which we are getting. 173 00:09:51,000 --> 00:09:58,000 The webcam is just currently on, so might take a few seconds to just make the webcam working. 174 00:09:58,000 --> 00:09:58,000 So. 175 00:09:59,000 --> 00:09:59,000 Okay. 176 00:09:59,000 --> 00:10:05,000 So now you can see over here we have the output in the form of tensors by two further processes and 177 00:10:05,000 --> 00:10:07,000 create bounding boxes around the detected object. 178 00:10:07,000 --> 00:10:11,000 We need to convert this output from tensors into integers. 179 00:10:11,000 --> 00:10:14,000 So now we will just convert this output from the tensors into integers. 180 00:10:14,000 --> 00:10:18,000 So to convert this output from tensors into integers. 181 00:10:18,000 --> 00:10:23,000 So just comment this out from here and suggest you need to write int X1Y1. 182 00:10:23,000 --> 00:10:27,000 So we are just converting each of the coordinates from tensor into integer. 183 00:10:27,000 --> 00:10:32,000 So now just run this again and see what output do actually we get. 184 00:10:33,000 --> 00:10:39,000 So now basically our output is being converted from tensors into integers over here. 185 00:10:39,000 --> 00:10:43,000 So we will have the output very soon over here. 186 00:10:44,000 --> 00:10:45,000 Okay. 187 00:10:46,000 --> 00:10:49,000 So now you can see over here, now we have the output in the form of integers. 188 00:10:49,000 --> 00:10:52,000 So we can't see the tensors over here. 189 00:10:52,000 --> 00:10:55,000 So you can see that we have the output in the form of not integer. 190 00:10:55,000 --> 00:10:57,000 So let me just pause this down here. 191 00:10:57,000 --> 00:11:02,000 So now you can see that previously we have the tensors around each of the coordinate, but now we don't 192 00:11:02,000 --> 00:11:04,000 have the tensors around each of the coordinate. 193 00:11:04,000 --> 00:11:09,000 We have the output in the form of integer for zero are the X1Y1 coordinate value. 194 00:11:09,000 --> 00:11:11,000 This is the x one coordinate value. 195 00:11:11,000 --> 00:11:12,000 This is the y one. 196 00:11:12,000 --> 00:11:13,000 Coordinate value. 197 00:11:13,000 --> 00:11:16,000 This is the x two coordinate value and this is the y coordinate value. 198 00:11:16,000 --> 00:11:17,000 Okay. 199 00:11:18,000 --> 00:11:22,000 So now we just need to create a rectangle over here. 200 00:11:22,000 --> 00:11:27,000 So we use a or you can say that we need to create a bounding box around each of the directory object. 201 00:11:27,000 --> 00:11:33,000 So basically we have the coordinate value for each of the detected object, like we have the coordinates 202 00:11:33,000 --> 00:11:35,000 value for each of the detected object. 203 00:11:35,000 --> 00:11:39,000 We just need to create a rectangle around each of the detected object. 204 00:11:39,000 --> 00:11:43,000 So using cv2 dot rectangle, we will create a rectangle around each of the detected object. 205 00:11:45,000 --> 00:11:46,000 Okay. 206 00:11:46,000 --> 00:11:51,000 So if I just go over here and show you what are the parameters we have. 207 00:11:52,000 --> 00:11:53,000 CV to tango. 208 00:11:54,000 --> 00:11:55,000 Okay. 209 00:11:55,000 --> 00:11:56,000 So let me just open this from here. 210 00:11:57,000 --> 00:11:58,000 So. 211 00:12:00,000 --> 00:12:01,000 Okay. 212 00:12:01,000 --> 00:12:07,000 So now you can see over here in the rectangle we just passed the our image or the current frame. 213 00:12:07,000 --> 00:12:07,000 Okay. 214 00:12:08,000 --> 00:12:14,000 And then we have the starting point and then we have the ending point and the color of the rectangle. 215 00:12:14,000 --> 00:12:15,000 And then we have the thickness. 216 00:12:16,000 --> 00:12:16,000 Okay. 217 00:12:18,000 --> 00:12:21,000 So now you can see over here if you just see this. 218 00:12:21,000 --> 00:12:22,000 So this is our starting point. 219 00:12:23,000 --> 00:12:25,000 You can see over here, this is the ending point. 220 00:12:25,000 --> 00:12:30,000 And we will just define the color and the thickness of this bounding box. 221 00:12:30,000 --> 00:12:32,000 So if I just go back towards the code. 222 00:12:32,000 --> 00:12:38,000 So now you can see over here we have this is the current frame and this is our starting point. 223 00:12:38,000 --> 00:12:42,000 This is our ending point and this is the color of the bounding box. 224 00:12:42,000 --> 00:12:45,000 It's around pink and this is the thickness of the bounding box. 225 00:12:45,000 --> 00:12:45,000 Okay. 226 00:12:47,000 --> 00:12:50,000 So let me just comment this out currently. 227 00:12:50,000 --> 00:12:54,000 Let me just display the bounding boxes first and then we will discuss the. 228 00:12:55,000 --> 00:12:56,000 Okay. 229 00:12:56,000 --> 00:12:56,000 So. 230 00:12:58,000 --> 00:13:00,000 I am just currently focused on displaying the bounding box. 231 00:13:00,000 --> 00:13:03,000 I am not interesting in displaying anything else. 232 00:13:03,000 --> 00:13:10,000 Okay, so let me just display the bounding boxes and see what results do actually we get. 233 00:13:10,000 --> 00:13:16,000 Okay, so let me just just checking a few things over here. 234 00:13:16,000 --> 00:13:18,000 If there is an issue so I can just correct it. 235 00:13:18,000 --> 00:13:20,000 So let me just comment this out correctly as well. 236 00:13:22,000 --> 00:13:26,000 Okay, so let me just run this and see what what do we get? 237 00:13:26,000 --> 00:13:29,000 Are we able to draw bounding boxes around detected object or not? 238 00:13:29,000 --> 00:13:35,000 So currently our goal is to draw bounding boxes around each of the detected object and then we'll go 239 00:13:35,000 --> 00:13:36,000 ahead and see further work. 240 00:13:39,000 --> 00:13:43,000 Now you can see that a bounding box is being drawn around the as in a person. 241 00:13:43,000 --> 00:13:45,000 So a bounding box is are drawn around me. 242 00:13:46,000 --> 00:13:47,000 So that's perfectly fine. 243 00:13:47,000 --> 00:13:49,000 That's what we are expecting. 244 00:13:52,000 --> 00:13:55,000 You can see over here, a bounding box is being drawn around me. 245 00:13:55,000 --> 00:13:58,000 So this is the output which we expect. 246 00:13:58,000 --> 00:14:02,000 Basically, that bounding box should be drawn around each of the detected objects. 247 00:14:03,000 --> 00:14:09,000 Okay, so this is our server expectation, but now we just want to have the label and the confidence 248 00:14:09,000 --> 00:14:10,000 score as well. 249 00:14:11,000 --> 00:14:16,000 Like label means if a person there should be shown that I'm a person label above the bounding box, 250 00:14:16,000 --> 00:14:22,000 there should be a label that am person and the confidence score like how much our YOLO V8 model is confident 251 00:14:22,000 --> 00:14:23,000 that am a person. 252 00:14:25,000 --> 00:14:31,000 So I have already told you as our V8 model we are just using the V8 Pre-trained model which is trained 253 00:14:31,000 --> 00:14:32,000 on coco dataset. 254 00:14:32,000 --> 00:14:35,000 So the Coco dataset consists of 80 different classes. 255 00:14:35,000 --> 00:14:38,000 So I have just written the name of all those classes over here. 256 00:14:38,000 --> 00:14:43,000 These are all the classes which we have in the Coco dataset, which are around 80 different classes. 257 00:14:43,000 --> 00:14:44,000 Okay. 258 00:14:44,000 --> 00:14:49,000 So to get the confidence over over here, I'm just passing this using bad dot. 259 00:14:49,000 --> 00:14:52,000 See, we are just getting the confidence score values. 260 00:14:52,000 --> 00:14:55,000 The confidence score basically appears in the form of tensors. 261 00:14:55,000 --> 00:14:55,000 Okay. 262 00:14:55,000 --> 00:14:59,000 So to just convert into integer, I'm just using this math dot. 263 00:14:59,000 --> 00:15:03,000 See, let me show you what originally we have the confidence score value. 264 00:15:03,000 --> 00:15:09,000 So just write print box dot three sense, okay? 265 00:15:09,000 --> 00:15:14,000 And just write zero and let's see, what does the confidence score value do we get? 266 00:15:14,000 --> 00:15:17,000 So then we will discuss later, few things later. 267 00:15:17,000 --> 00:15:19,000 So just comment this out. 268 00:15:23,000 --> 00:15:26,000 We just don't want to show the output currently. 269 00:15:26,000 --> 00:15:28,000 I just want to show you the confidence score value. 270 00:15:28,000 --> 00:15:31,000 So just click on Run YOLO V8 Webcam. 271 00:15:36,000 --> 00:15:39,000 So now we'll have the confidence score value over here as well. 272 00:15:40,000 --> 00:15:43,000 So this might take a few seconds. 273 00:15:43,000 --> 00:15:45,000 So now you can see here. 274 00:15:46,000 --> 00:15:50,000 Okay, So just let me just stop this so you can see that we have the confidence score value in the form 275 00:15:50,000 --> 00:15:51,000 of tensors. 276 00:15:51,000 --> 00:15:54,000 We just need to convert this value into integers. 277 00:15:54,000 --> 00:15:58,000 So I'm just converting this value into integers over here. 278 00:15:58,000 --> 00:15:59,000 Okay. 279 00:16:00,000 --> 00:16:05,000 Thus now you can see over here we have the confidence pour value into it. 280 00:16:05,000 --> 00:16:11,000 We are just converting the confidence score value into integers and now using int box dot zero. 281 00:16:11,000 --> 00:16:13,000 We are just getting the class ID. 282 00:16:13,000 --> 00:16:14,000 Okay. 283 00:16:14,000 --> 00:16:20,000 So here will give us the class ID and here I've just written the class name. 284 00:16:20,000 --> 00:16:22,000 So if the class ID is zero, it means it is a person. 285 00:16:22,000 --> 00:16:25,000 If the class ID is one, it means it is a bicycle. 286 00:16:25,000 --> 00:16:28,000 And if the class ID is two, it means it is a car. 287 00:16:28,000 --> 00:16:34,000 Okay, so here I'm just getting the class ID and here I'm just finding the class name. 288 00:16:34,000 --> 00:16:38,000 And in the label I am just putting the class name and confidence value combined. 289 00:16:38,000 --> 00:16:42,000 And here I'm just finding using cv2 dot get text size function. 290 00:16:42,000 --> 00:16:49,000 I'm finding the size of this label so I can just create a rectangle with rectangle. 291 00:16:50,000 --> 00:16:52,000 Yes, but the size of this table. 292 00:16:54,000 --> 00:17:00,000 And here I'm just creating the rectangle above the bounding box so that I'm just can just put text around 293 00:17:00,000 --> 00:17:01,000 it. 294 00:17:01,000 --> 00:17:02,000 Okay. 295 00:17:02,000 --> 00:17:02,000 Okay. 296 00:17:02,000 --> 00:17:12,000 And just I'm just saving the my detections in the out in the file name as output.in this output dot 297 00:17:12,000 --> 00:17:12,000 file. 298 00:17:12,000 --> 00:17:14,000 My detections will be saved. 299 00:17:15,000 --> 00:17:19,000 And just let me just show you the reductions frame by frame, Right? 300 00:17:19,000 --> 00:17:26,000 And if I just click on one, the process will stop and just clicking auto release. 301 00:17:26,000 --> 00:17:29,000 So let's just run this and see what results do actually we get. 302 00:17:29,000 --> 00:17:32,000 And is our output saved or not? 303 00:17:32,000 --> 00:17:34,000 Or production video saved or not? 304 00:17:34,000 --> 00:17:39,000 So just run Yolo v webcam and see what results are we are getting now. 305 00:17:42,000 --> 00:17:45,000 Okay, so this might take a few seconds more. 306 00:17:51,000 --> 00:17:53,000 Mike can see that over here. 307 00:17:53,000 --> 00:17:58,000 The label person as well as you can see over here, the contents pour over here as well. 308 00:17:58,000 --> 00:18:01,000 Plus on the back side, I have the sofa so you can see that. 309 00:18:01,000 --> 00:18:02,000 So over here as well. 310 00:18:02,000 --> 00:18:06,000 Plus, you can see that a bounding box is created around me. 311 00:18:06,000 --> 00:18:09,000 And as I'm a person, so you can see the person over here. 312 00:18:09,000 --> 00:18:14,000 Plus on the back side, I can see the sofa and see the label soap over here as well. 313 00:18:15,000 --> 00:18:15,000 Okay. 314 00:18:15,000 --> 00:18:17,000 So let me just show all this. 315 00:18:18,000 --> 00:18:21,000 Can see that so far And. 316 00:18:26,000 --> 00:18:27,000 Now, the questions are very well. 317 00:18:27,000 --> 00:18:29,000 You can see over here. 318 00:18:29,000 --> 00:18:31,000 So these are the results which we expect. 319 00:18:31,000 --> 00:18:37,000 And this is all from this let me just show you, is our output video is saved or not? 320 00:18:39,000 --> 00:18:41,000 I'm just stopping this video. 321 00:18:41,000 --> 00:18:44,000 And let me show you if our output video is saved or not. 322 00:18:44,000 --> 00:18:49,000 So let me just go YOLO V8. 323 00:18:49,000 --> 00:18:50,000 Okay. 324 00:18:50,000 --> 00:18:55,000 So let me just go towards the YOLO V8 Crash course run, YOLO V8 Webcam. 325 00:18:55,000 --> 00:18:58,000 And so you can see over here, here we have the output video. 326 00:18:58,000 --> 00:19:04,000 So if I just click over here, okay, so now you can see that that's the results are very impressive. 327 00:19:04,000 --> 00:19:06,000 Our output is being saved. 328 00:19:06,000 --> 00:19:07,000 You can see over here. 329 00:19:08,000 --> 00:19:09,000 Okay, so. 330 00:19:10,000 --> 00:19:16,000 You can see that we are able to do the on the live webcam and our output video is saved there as well. 331 00:19:16,000 --> 00:19:18,000 So that's perfectly fine. 332 00:19:18,000 --> 00:19:23,000 That's the results which we am expecting and that's pretty impressive. 333 00:19:25,000 --> 00:19:26,000 So. 334 00:19:27,000 --> 00:19:32,000 The next video tutorial, we will run on Windows and see what results do we get.