1 00:00:03,000 --> 00:00:09,000 YOLO 11 is the new state of the art model introduced by Ultralytics. 2 00:00:09,000 --> 00:00:15,000 YOLO 11 outperforms all the previous object detection models, including YOLO ten. 3 00:00:15,000 --> 00:00:16,000 Yolo v nine. 4 00:00:16,000 --> 00:00:17,000 Yolo v eight. 5 00:00:17,000 --> 00:00:26,000 In terms of speed and accuracy, YOLO 11 can be used for a variety of computer vision tasks, including 6 00:00:26,000 --> 00:00:29,000 object detection, instance segmentation. 7 00:00:29,000 --> 00:00:30,000 Object tracking. 8 00:00:30,000 --> 00:00:32,000 Pose estimation. 9 00:00:32,000 --> 00:00:40,000 Some of the key improvements in YOLO 11 include enhanced feature extraction, greater accuracy with 10 00:00:40,000 --> 00:00:44,000 fewer parameters, and faster processing speed. 11 00:00:46,000 --> 00:00:55,000 So YOLO 11 is basically built on the advancements introduced in Yolo v nine and Yolo v ten, incorporating 12 00:00:55,000 --> 00:01:00,000 improved architectural design, enhanced feature extraction techniques, and optimizing the their training 13 00:01:00,000 --> 00:01:01,000 methods. 14 00:01:02,000 --> 00:01:11,000 Yellow 11 medium model achieves a higher mean average precision on the benchmark data set, while using 15 00:01:11,000 --> 00:01:15,000 22% fewer parameters than yellow eight medium model. 16 00:01:16,000 --> 00:01:24,000 Along with this, yellow 11 brings a faster processing speed, with inference time around 2% quicker 17 00:01:24,000 --> 00:01:26,000 than YOLO v ten. 18 00:01:26,000 --> 00:01:29,000 So this makes this like this. 19 00:01:29,000 --> 00:01:38,000 Feature enhancement techniques and make a faster processing speed makes YOLO 11 ideal for real time 20 00:01:38,000 --> 00:01:39,000 applications. 21 00:01:43,000 --> 00:01:46,000 So this is a quick introduction about YOLO 11. 22 00:01:46,000 --> 00:01:54,000 Let's dive into the code and see how we can do object detection, instance segmentation, image classification, 23 00:01:54,000 --> 00:01:58,000 object tracking and pose estimation with YOLO 11. 24 00:02:02,000 --> 00:02:07,000 So this is the Ultralytics repository, which contains all the code for your 11. 25 00:02:07,000 --> 00:02:13,000 And you can see YOLO 11 is a cutting edge, state of the art model that builds upon the success of previous 26 00:02:14,000 --> 00:02:15,000 versions. 27 00:02:15,000 --> 00:02:15,000 Okay. 28 00:02:15,000 --> 00:02:20,000 And you can see over here this blue line is width of YOLO 11. 29 00:02:20,000 --> 00:02:27,000 And you can see that YOLO 11 outperforms all the previous object detection models, including YOLO, 30 00:02:28,000 --> 00:02:32,000 YOLO v9, YOLO, V8, Yolov7 in terms of mean average precision. 31 00:02:32,000 --> 00:02:34,000 And you can see the latency. 32 00:02:34,000 --> 00:02:42,000 Latency is basically the time that is, uh, is basically the time, uh, to do object detection on 33 00:02:42,000 --> 00:02:49,000 an input image, like the time taken to do object detection on an input image is basically the latency, 34 00:02:49,000 --> 00:02:55,000 like how much times time it takes to do object detection on an input image is the latency. 35 00:02:55,000 --> 00:03:01,000 So you can see that, uh, YOLO 11 takes less time and you know. 36 00:03:01,000 --> 00:03:07,000 11 also outperforms in terms of mean average precision then all the other YOLO models. 37 00:03:07,000 --> 00:03:14,000 So YOLO 11 outperforms all the other object detection models in terms of mean average precision. 38 00:03:14,000 --> 00:03:18,000 And it takes less time as compared to other YOLO models. 39 00:03:18,000 --> 00:03:19,000 Okay. 40 00:03:21,000 --> 00:03:26,000 And you can see that YOLO can be used directly in the command line interface with the YOLO command. 41 00:03:26,000 --> 00:03:32,000 And you can also use YOLO 11 directly in the Python environment as well. 42 00:03:32,000 --> 00:03:34,000 So all these steps are provided. 43 00:03:34,000 --> 00:03:40,000 So your YOLO uh 11 comes with 25 open source models. 44 00:03:40,000 --> 00:03:40,000 Okay. 45 00:03:40,000 --> 00:03:46,000 So there are five models for the classification, five models for the detection, five models for the 46 00:03:46,000 --> 00:03:50,000 segmentation and five models for the pose estimation. 47 00:03:50,000 --> 00:03:53,000 And you can use tracking feature with any of these models. 48 00:03:53,000 --> 00:03:58,000 So these are the models that the YOLO 11 comes with YOLO 11 nano YOLO 11. 49 00:03:58,000 --> 00:04:01,000 Small YOLO 11, YOLO 11. 50 00:04:01,000 --> 00:04:05,000 Medium, YOLO 11 large and YOLO 11 extra large model. 51 00:04:05,000 --> 00:04:05,000 Okay. 52 00:04:05,000 --> 00:04:15,000 And you can see that, um, YOLO 11 nano model is has a mean average precision validation score of 39.5. 53 00:04:16,000 --> 00:04:24,000 Uh, but you can see that YOLO 11 Nano gives us is very much faster than other YOLO model. 54 00:04:24,000 --> 00:04:32,000 But YOLO 11 X like extra large model is uh, in in is better in terms of mean average precision score 55 00:04:32,000 --> 00:04:39,000 like with 54.7, but it takes, uh, more time and then other YOLO 11 models. 56 00:04:39,000 --> 00:04:39,000 Okay. 57 00:04:39,000 --> 00:04:44,000 So there is a trade off between, uh, speed and accuracy, which we can see over here. 58 00:04:44,000 --> 00:04:45,000 Okay. 59 00:04:46,000 --> 00:04:51,000 And similarly, you can see these are all the models for the segmentation. 60 00:04:51,000 --> 00:04:54,000 And these are all the models for the pose estimation. 61 00:04:54,000 --> 00:04:59,000 And these are all the models for the oriented bounding boxes okay. 62 00:04:59,000 --> 00:05:02,000 And here these are all the models for the classification okay. 63 00:05:03,000 --> 00:05:05,000 And these are all the details. 64 00:05:05,000 --> 00:05:08,000 You can find all these details over here. 65 00:05:08,000 --> 00:05:13,000 And you can simply use install the Ultralytics package. 66 00:05:13,000 --> 00:05:16,000 And then you can use your 11 simply okay. 67 00:05:16,000 --> 00:05:19,000 So this is all the repository. 68 00:05:19,000 --> 00:05:21,000 You can check out this repository as well. 69 00:05:21,000 --> 00:05:25,000 And you can see different examples over here as well okay. 70 00:05:25,000 --> 00:05:28,000 So here is our Google Colab notebook. 71 00:05:28,000 --> 00:05:36,000 And let's go over here I have written all the code uh to do object detection uh instance segmentation, 72 00:05:36,000 --> 00:05:42,000 image classification, pose estimation using Ultralytics YOLO 11 okay. 73 00:05:42,000 --> 00:05:49,000 So first of all, uh, you can um, set the runtime as default GPU because Google Colab offers free 74 00:05:49,000 --> 00:05:51,000 GPU and you can use this. 75 00:05:51,000 --> 00:05:52,000 Okay. 76 00:05:53,000 --> 00:05:56,000 So first of all we will install the Ultralytics package over here. 77 00:06:00,000 --> 00:06:02,000 So this will take two seconds. 78 00:06:05,000 --> 00:06:07,000 So now you can see the analytics package is installed. 79 00:06:07,000 --> 00:06:11,000 Now we will download some sample image and video from drive. 80 00:06:11,000 --> 00:06:15,000 So I have added some an image and a video on my drive. 81 00:06:15,000 --> 00:06:20,000 So I'm directly downloading that image and video from drive into this Google Colab notebook. 82 00:06:20,000 --> 00:06:27,000 And I will be doing uh, object detection, image classification, instance segmentation and pose estimation 83 00:06:27,000 --> 00:06:30,000 on this image and on this video. 84 00:06:30,000 --> 00:06:34,000 So let's see how we can do object detection in images using YOLO 11. 85 00:06:34,000 --> 00:06:40,000 So first of all we are using the YOLO 11 pre-trained model. 86 00:06:40,000 --> 00:06:45,000 And we only want to do the prediction using YOLO 11 pre-trained model. 87 00:06:45,000 --> 00:06:47,000 And we are using YOLO 11 nano model. 88 00:06:47,000 --> 00:06:49,000 You can use uh other models as well. 89 00:06:49,000 --> 00:06:59,000 But YOLO 11 nano is the most fastest model, but it is less accurate as compared to other YOLO 11 models 90 00:06:59,000 --> 00:06:59,000 okay. 91 00:06:59,000 --> 00:07:02,000 And we are doing detection okay. 92 00:07:02,000 --> 00:07:03,000 Object detection. 93 00:07:03,000 --> 00:07:07,000 And we are doing prediction using YOLO 11 and a model. 94 00:07:07,000 --> 00:07:11,000 And we are doing prediction on this sample image okay. 95 00:07:16,000 --> 00:07:18,000 So let's see. 96 00:07:18,000 --> 00:07:21,000 So now you can see YOLO 11 is very much fast. 97 00:07:21,000 --> 00:07:25,000 And like it took few seconds like 10 to 15 seconds over here. 98 00:07:26,000 --> 00:07:31,000 And now you can see over here we have our runs folder. 99 00:07:31,000 --> 00:07:34,000 And inside this we have prediction detection prediction. 100 00:07:34,000 --> 00:07:36,000 And here is our output image. 101 00:07:36,000 --> 00:07:38,000 So you can just copy the path from here. 102 00:07:38,000 --> 00:07:40,000 And you can just add this path over here. 103 00:07:40,000 --> 00:07:42,000 And you can say. 104 00:07:45,000 --> 00:07:45,000 Okay. 105 00:07:45,000 --> 00:07:47,000 So you now you can see the output. 106 00:07:47,000 --> 00:07:49,000 We are able to detect the person bus traffic light. 107 00:07:49,000 --> 00:07:52,000 We are able to detect both the traffic lights over here. 108 00:07:52,000 --> 00:07:54,000 We are able to detect the handbag over here. 109 00:07:54,000 --> 00:07:56,000 So the results look very good. 110 00:07:56,000 --> 00:07:59,000 From now Okay. 111 00:07:59,000 --> 00:08:07,000 So, like, on using, uh, your command over here, uh, we are able to do object detection on an input 112 00:08:07,000 --> 00:08:08,000 image. 113 00:08:08,000 --> 00:08:13,000 Okay, let's see how we can do object detection in videos using 11. 114 00:08:13,000 --> 00:08:19,000 So you just need to, uh, add the path of your video file in the source as all the other things will 115 00:08:19,000 --> 00:08:20,000 remain the same. 116 00:08:20,000 --> 00:08:21,000 Okay. 117 00:08:21,000 --> 00:08:23,000 So let's run this up. 118 00:08:28,000 --> 00:08:32,000 So our complete video is being divided into 458 frames. 119 00:08:32,000 --> 00:08:33,000 Like you can see over here. 120 00:08:33,000 --> 00:08:38,000 And we are doing, uh, object detection on each of the frame one by one. 121 00:08:39,000 --> 00:08:39,000 Okay. 122 00:08:40,000 --> 00:08:42,000 So this will take few seconds. 123 00:08:42,000 --> 00:08:43,000 Like this is very quick. 124 00:08:43,000 --> 00:08:46,000 Like you can see as we are using GPU. 125 00:08:46,000 --> 00:08:51,000 So you can see that, uh, processing is very fast and you can see it's done. 126 00:08:51,000 --> 00:08:57,000 And uh, we'll use this code to display the output video in this Google Colab notebook over here. 127 00:08:58,000 --> 00:08:58,000 well. 128 00:09:01,000 --> 00:09:03,000 And this will take two seconds. 129 00:09:03,000 --> 00:09:05,000 And we have the output video over here. 130 00:09:05,000 --> 00:09:09,000 So you can also download the output video from here. 131 00:09:09,000 --> 00:09:11,000 But the size is very large. 132 00:09:11,000 --> 00:09:15,000 And here we have the complex output video being displayed over here. 133 00:09:15,000 --> 00:09:16,000 So we can download this. 134 00:09:16,000 --> 00:09:18,000 So let's wait for a few seconds before we. 135 00:09:23,000 --> 00:09:29,000 After this we will see how we can do object segmentation or in images or instance segmentation in images 136 00:09:29,000 --> 00:09:30,000 using YOLO 11. 137 00:09:30,000 --> 00:09:36,000 And then you will see how we can do instance segmentation in videos using your 11 as well. 138 00:09:36,000 --> 00:09:38,000 So let's wait for this to finish up. 139 00:09:38,000 --> 00:09:42,000 And you can see that a compressed file is being created. 140 00:09:42,000 --> 00:09:47,000 Now you can see over here the size of this output video was 94.81 MB. 141 00:09:47,000 --> 00:09:52,000 And now the compressed video size is around 10.34 MB. 142 00:09:53,000 --> 00:09:57,000 Or you can see we have this recipe file over here okay. 143 00:09:57,000 --> 00:09:58,000 And you can see here is our output video. 144 00:09:58,000 --> 00:10:01,000 And let me download this video and show you. 145 00:10:06,000 --> 00:10:06,000 Okay. 146 00:10:11,000 --> 00:10:17,000 So now you can see over here we are able to do object detection on on this object. 147 00:10:17,000 --> 00:10:20,000 Like we are able to detect a traffic light person bicycle. 148 00:10:20,000 --> 00:10:22,000 So the results look quite good. 149 00:10:22,000 --> 00:10:29,000 Like you can see over here we are able to tag the back bicycle person traffic lights uh road signs as 150 00:10:29,000 --> 00:10:29,000 well. 151 00:10:29,000 --> 00:10:32,000 So the results are very promising. 152 00:10:32,000 --> 00:10:39,000 Okay, uh, let's move ahead and see how we can do instance segmentation in images using YOLO 11. 153 00:10:39,000 --> 00:10:43,000 So we are using YOLO 11 nano dash segmentation model. 154 00:10:43,000 --> 00:10:48,000 If you see over here uh we have the segmentation models available over here. 155 00:10:48,000 --> 00:10:51,000 Like you can see over here we have the post model. 156 00:10:51,000 --> 00:10:54,000 So you can use any of these models okay. 157 00:10:58,000 --> 00:10:59,000 So let me just. 158 00:10:59,000 --> 00:11:07,000 So now you can see over here we are able to do segment instance segmentation on this input image. 159 00:11:07,000 --> 00:11:12,000 And you can see over here we have our output saved in the predict folder. 160 00:11:13,000 --> 00:11:20,000 So if we just refresh this up so you can see segment and the predict folder we have our output image. 161 00:11:20,000 --> 00:11:25,000 So you can simply copy path from here and add this path over here. 162 00:11:25,000 --> 00:11:25,000 Okay. 163 00:11:25,000 --> 00:11:27,000 And let's run this. 164 00:11:29,000 --> 00:11:35,000 So now you can see over here we are able to do instance segmentation on the bus traffic light handbag 165 00:11:35,000 --> 00:11:36,000 or son backpack. 166 00:11:36,000 --> 00:11:37,000 Okay. 167 00:11:37,000 --> 00:11:39,000 So you can see the results look very promising. 168 00:11:39,000 --> 00:11:40,000 Okay. 169 00:11:40,000 --> 00:11:44,000 Uh let's see how we can do object segmentation in videos using YOLO 11. 170 00:11:45,000 --> 00:11:45,000 Okay. 171 00:11:45,000 --> 00:11:46,000 So let's run this up now. 172 00:11:52,000 --> 00:11:55,000 So you just need to add a video path over here. 173 00:11:55,000 --> 00:11:56,000 And nothing else. 174 00:11:58,000 --> 00:12:01,000 But now you can see over here the processing is very quick. 175 00:12:01,000 --> 00:12:01,000 Okay. 176 00:12:16,000 --> 00:12:20,000 So okay so our output is saved to run segment predictor. 177 00:12:20,000 --> 00:12:24,000 So if you just refresh this up and here you can find the output video. 178 00:12:24,000 --> 00:12:28,000 And you can simply run these two cells from here. 179 00:12:28,000 --> 00:12:30,000 And you can see. 180 00:12:31,000 --> 00:12:38,000 So if I just run this again uh this will take a few seconds before I have my output video being displayed 181 00:12:38,000 --> 00:12:39,000 over here. 182 00:12:40,000 --> 00:12:42,000 So let's wait for few seconds. 183 00:12:48,000 --> 00:12:53,000 After this, we will see how we can do pose estimation in images using YOLO 11. 184 00:12:53,000 --> 00:12:54,000 Okay. 185 00:12:54,000 --> 00:13:00,000 And we will also see how we can do pose estimation in videos using YOLO 11 and then you will see how 186 00:13:00,000 --> 00:13:02,000 we can do image classification over here. 187 00:13:02,000 --> 00:13:06,000 And we will take an image of a sports card over there. 188 00:13:06,000 --> 00:13:06,000 Okay. 189 00:13:09,000 --> 00:13:14,000 So this will take a few seconds before we have our output video over here. 190 00:13:14,000 --> 00:13:16,000 So let's wait for a few seconds. 191 00:13:22,000 --> 00:13:24,000 So you can see here we have our output video. 192 00:13:24,000 --> 00:13:29,000 Let me download this video and show you on a full screen how our output looks like. 193 00:13:34,000 --> 00:13:36,000 Okay so let me just navigate this. 194 00:13:38,000 --> 00:13:41,000 So you can see over here we are able to do instance segmentation. 195 00:13:41,000 --> 00:13:42,000 Like you can see over here. 196 00:13:42,000 --> 00:13:46,000 We are able to detect bicycle person traffic light road signs. 197 00:13:46,000 --> 00:13:49,000 And the results look very promising. 198 00:13:49,000 --> 00:13:53,000 Like you can see over here we are able to detect bicycle person traffic lights. 199 00:13:53,000 --> 00:13:56,000 And the results are very very promising. 200 00:13:56,000 --> 00:13:58,000 Like, these results are very impressive. 201 00:13:59,000 --> 00:13:59,000 Okay. 202 00:14:02,000 --> 00:14:05,000 Let's go back over here and let me just save this up now. 203 00:14:07,000 --> 00:14:07,000 Okay. 204 00:14:08,000 --> 00:14:15,000 So next we will see how we can do over estimation in images using YOLO 11 over here. 205 00:14:15,000 --> 00:14:16,000 Okay. 206 00:14:16,000 --> 00:14:22,000 So we will just like the task is equal to post mod is equal to predict. 207 00:14:22,000 --> 00:14:25,000 And we are using your 11 and dash post model. 208 00:14:25,000 --> 00:14:31,000 And you can see over here uh we have this post models in the repository. 209 00:14:31,000 --> 00:14:33,000 You can just use any of these models. 210 00:14:33,000 --> 00:14:34,000 Okay. 211 00:14:34,000 --> 00:14:38,000 And so you go for object detection we use dot is equal to detect. 212 00:14:38,000 --> 00:14:42,000 For instance segmentation we use toss is equal to segment. 213 00:14:42,000 --> 00:14:47,000 And uh for pose estimation we use the toss is equal to pose over here. 214 00:14:47,000 --> 00:14:50,000 And we are using basically pre-trained model. 215 00:14:50,000 --> 00:14:52,000 We are not fine tuning the model. 216 00:14:52,000 --> 00:14:54,000 So we are using the pre-trained model over here. 217 00:14:54,000 --> 00:14:57,000 And we are just setting the mod mode is equal to prediction. 218 00:14:57,000 --> 00:15:02,000 If you are using doing that training or fine tuning the YOLO 11 model, you can see set mode is equal 219 00:15:02,000 --> 00:15:05,000 to train, but we are currently doing predictions. 220 00:15:05,000 --> 00:15:07,000 So we have set mode is equal to prediction. 221 00:15:07,000 --> 00:15:10,000 And here we have passed our input image okay. 222 00:15:17,000 --> 00:15:22,000 So you can see over here we have the post folder and the predict we have the output image. 223 00:15:22,000 --> 00:15:26,000 And you can just simply copy path and just add this path over here. 224 00:15:26,000 --> 00:15:32,000 And here you can see we are able to do the pose estimation on this on the person over here. 225 00:15:32,000 --> 00:15:36,000 And the results look quite promising like results are good okay. 226 00:15:37,000 --> 00:15:41,000 And let's see how we can do over estimation in videos using YOLO 11. 227 00:15:41,000 --> 00:15:44,000 So you just need to add the video path over here. 228 00:15:44,000 --> 00:15:46,000 And we are using YOLO 11. 229 00:15:46,000 --> 00:15:50,000 And postmodern mode is equal to predict and toss is equal to pose estimation. 230 00:15:50,000 --> 00:15:51,000 Let's run this up now. 231 00:15:59,000 --> 00:16:01,000 So this will take few seconds. 232 00:16:01,000 --> 00:16:04,000 Like you can see we are able to drag the person over here. 233 00:16:04,000 --> 00:16:12,000 So YOLO 11 pre-trained word estimation model can only do pose estimation of person. 234 00:16:13,000 --> 00:16:20,000 Uh, to do pose estimation of an animal or a class, you need to fine tune the YOLO 11 pose estimation 235 00:16:20,000 --> 00:16:21,000 model. 236 00:16:21,000 --> 00:16:28,000 But the pre-trained YOLO 11 pose estimation model or other pose estimation models, YOLO pose estimation 237 00:16:28,000 --> 00:16:36,000 models including uh yolo, YOLO v eight can do pose estimation, or only person to do any other for 238 00:16:36,000 --> 00:16:39,000 any other animal, or to do pose estimation of any object. 239 00:16:39,000 --> 00:16:43,000 You need to fine tune the the pose estimation model of YOLO. 240 00:16:43,000 --> 00:16:44,000 Okay, so it's done now. 241 00:16:44,000 --> 00:16:48,000 And let's display this output video over here. 242 00:16:51,000 --> 00:16:51,000 Okay. 243 00:16:51,000 --> 00:16:56,000 So after this we are only left with one task which is image classification. 244 00:16:56,000 --> 00:16:57,000 Yeah. 245 00:16:58,000 --> 00:17:04,000 And we will do the classification of this, uh, this sports car. 246 00:17:05,000 --> 00:17:05,000 Okay. 247 00:17:05,000 --> 00:17:11,000 And let's see how it is, but let's display this output video first over here. 248 00:17:11,000 --> 00:17:15,000 And then we'll go ahead towards the image classification task as well. 249 00:17:29,000 --> 00:17:33,000 So this will take a few more seconds before we have everything ready over here. 250 00:17:38,000 --> 00:17:41,000 So here you can see we are our output video. 251 00:17:41,000 --> 00:17:43,000 You can just run this output video over here. 252 00:17:43,000 --> 00:17:47,000 But let me download this video and show you a big screen over here. 253 00:17:50,000 --> 00:17:53,000 So it's downloading and let me open over here. 254 00:17:53,000 --> 00:17:56,000 And let me just navigate my screen towards it. 255 00:17:59,000 --> 00:18:03,000 So you can see over here we are able to do pose estimation of person over here. 256 00:18:03,000 --> 00:18:05,000 And the results you can see are very promising. 257 00:18:05,000 --> 00:18:08,000 You can see we are also doing the detection over here as well. 258 00:18:08,000 --> 00:18:11,000 And we are also doing the pose estimation. 259 00:18:11,000 --> 00:18:15,000 So we are doing two things uh object detection and pose estimation. 260 00:18:15,000 --> 00:18:18,000 And the results look very very promising okay. 261 00:18:19,000 --> 00:18:25,000 So let's go ahead and go to our last task which is image classification. 262 00:18:27,000 --> 00:18:28,000 Okay. 263 00:18:29,000 --> 00:18:32,000 So let me just save this up now. 264 00:18:35,000 --> 00:18:41,000 So now for image classification we will download a car image or sports car image from the drive directly 265 00:18:41,000 --> 00:18:48,000 to this, uh, Google Colab notebook over here and we will select the task is equal to classify mode 266 00:18:48,000 --> 00:18:49,000 is equal to predict. 267 00:18:49,000 --> 00:18:52,000 And we are using a YOLO 11 extra large model. 268 00:18:52,000 --> 00:18:56,000 And we are doing classification image classification over here. 269 00:18:56,000 --> 00:18:58,000 And let's run this up now. 270 00:19:02,000 --> 00:19:08,000 And you can see the size of the YOLO 11 extra large model is quite large like it's 56.9 MB. 271 00:19:08,000 --> 00:19:12,000 The YOLO 11 nano model is around 5.6 MB. 272 00:19:12,000 --> 00:19:20,000 Okay, so we have our output image in saved into the folder or run classify predict okay over here. 273 00:19:20,000 --> 00:19:25,000 So let me just display the output image over here okay. 274 00:19:25,000 --> 00:19:32,000 So if I just open this image into the new tab over here you know we can say. 275 00:19:38,000 --> 00:19:43,000 So if I just open this output image into a bigger window. 276 00:19:44,000 --> 00:19:49,000 So now you can see over here we are able to like for the sports card. 277 00:19:49,000 --> 00:19:53,000 Uh, the model is 66% confident that this is a sports car. 278 00:19:53,000 --> 00:19:55,000 And this is for the car will. 279 00:19:55,000 --> 00:19:57,000 The model is 11% confident for the cab. 280 00:19:57,000 --> 00:19:59,000 The model is 10% confidence. 281 00:19:59,000 --> 00:20:02,000 For the wagon, the model is 0.05% confident. 282 00:20:02,000 --> 00:20:05,000 For the dresser, the model is 0.03% confident. 283 00:20:05,000 --> 00:20:13,000 But um, as we can see over here, this is a sports car and the model is 66% confident that this is 284 00:20:13,000 --> 00:20:14,000 a sports car. 285 00:20:14,000 --> 00:20:19,000 So you can see that how accurately we can do, uh, image classification. 286 00:20:19,000 --> 00:20:20,000 Like you can see over here. 287 00:20:20,000 --> 00:20:23,000 Our model is able to classify correctly that this is a sports car. 288 00:20:23,000 --> 00:20:26,000 And you can see over here 0.66. 289 00:20:26,000 --> 00:20:28,000 This is 66%. 290 00:20:28,000 --> 00:20:30,000 Our model is confident that this is a sports car. 291 00:20:30,000 --> 00:20:35,000 So in this tutorial I have presented you an introduction to YOLO 11. 292 00:20:35,000 --> 00:20:41,000 We have seen that how we can do, uh, object detection, instance segmentation, image classification 293 00:20:41,000 --> 00:20:49,000 and pose estimation using YOLO 11 I hope you have learned something in this tutorial are some exciting 294 00:20:49,000 --> 00:20:52,000 tutorials are coming ahead and do subscribe my channel. 295 00:20:52,000 --> 00:20:53,000 Thank you for watching. 296 00:20:53,000 --> 00:20:53,000 Bye bye.