1
00:00:04,000 --> 00:00:11,000
You know, 11 is the new state of the art model released by Ultralytics that outperforms all the previous

2
00:00:11,000 --> 00:00:15,000
object detection models, including YOLO B10, YOLO v9, Yolo v eight.

3
00:00:15,000 --> 00:00:23,000
In terms of speed and accuracy, YOLO 11 can be used for a variety of tasks such as object detection,

4
00:00:23,000 --> 00:00:28,000
instance segmentation, image classification, and pose estimation.

5
00:00:28,000 --> 00:00:33,000
In this tutorial, we will look at how we can run YOLO 11 in our windows.

6
00:00:34,000 --> 00:00:36,000
And here you can see the GitHub repo.

7
00:00:36,000 --> 00:00:39,000
So this is the Ultralytics GitHub repo over here.

8
00:00:39,000 --> 00:00:41,000
And here you can see the graph.

9
00:00:41,000 --> 00:00:47,000
So you can clearly see that YOLO 11 models outperforms all the previous object detection model in terms

10
00:00:47,000 --> 00:00:50,000
of speed and accuracy as well.

11
00:00:50,000 --> 00:00:55,000
And here if you want to check the documentation you can click on the link over here.

12
00:00:55,000 --> 00:01:02,000
And YOLO 11 can be used directly in the command line interface with the yellow command, and in this

13
00:01:02,000 --> 00:01:08,000
tutorial we will look at how we can use the other 11 directly in the command line interface with the

14
00:01:08,000 --> 00:01:13,000
yellow command, and you can also set up a Python script, and you can just write down this script and

15
00:01:13,000 --> 00:01:15,000
you can use the other 11 model as well.

16
00:01:15,000 --> 00:01:22,000
But in this tutorial we will see how we can use yellow 11 directly in the command line interface with

17
00:01:22,000 --> 00:01:24,000
the yellow command okay.

18
00:01:24,000 --> 00:01:30,000
And in the later videos we will see how we can set up the Python environment and just set up all the

19
00:01:30,000 --> 00:01:31,000
scripts and we can.

20
00:01:31,000 --> 00:01:37,000
But in this tutorial we will focus on how we can use yellow 11 directly in the command line interface

21
00:01:37,000 --> 00:01:38,000
with the yellow command.

22
00:01:39,000 --> 00:01:45,000
So yellow 11 comes with five different models which include yellow 11 nano yellow 11 small yellow 11

23
00:01:45,000 --> 00:01:49,000
medium yellow 11 large and yellow 11 extra large.

24
00:01:49,000 --> 00:01:55,000
So yellow 11 nano is the fastest among the yellow 11 models, but it is less accurate.

25
00:01:55,000 --> 00:01:57,000
Like you can see over here.

26
00:01:57,000 --> 00:02:03,000
The mean average precision validation is 39.5, while 11 extra large is the most accurate.

27
00:02:03,000 --> 00:02:10,000
As we can see over here, the mean average precision is 54.7, but it is less passed over like it.

28
00:02:10,000 --> 00:02:14,000
Uh, it is not very fast as compared to other YOLO models.

29
00:02:14,000 --> 00:02:16,000
YOLO 11 models.

30
00:02:17,000 --> 00:02:20,000
So there is a trade off between speed and accuracy.

31
00:02:20,000 --> 00:02:26,000
Okay, the other 11 extra large give us the better mean average precision as compared to other 11 models.

32
00:02:26,000 --> 00:02:28,000
But there is a trade off with the speed.

33
00:02:28,000 --> 00:02:34,000
Like, uh, the speed is slow or it is less fast as compared to other YOLO 11 models.

34
00:02:35,000 --> 00:02:36,000
So here we have that.

35
00:02:36,000 --> 00:02:38,000
These are the object detection models.

36
00:02:38,000 --> 00:02:41,000
Here we have the models for segment and segmentation.

37
00:02:41,000 --> 00:02:44,000
And here we have the models for pose estimation.

38
00:02:44,000 --> 00:02:48,000
And here we have all the models for image classification as well.

39
00:02:48,000 --> 00:02:51,000
So you can just check out this repository.

40
00:02:51,000 --> 00:02:56,000
You can check out different examples on the Ultralytics documentation as well.

41
00:02:56,000 --> 00:03:02,000
So let's start writing down the code and see how we can run goto 11 in our windows.

42
00:03:04,000 --> 00:03:07,000
So here you can see I've just opened Anaconda prompt.

43
00:03:07,000 --> 00:03:11,000
You know, if you have installed Anaconda Navigator you can open the Anaconda Navigator.

44
00:03:11,000 --> 00:03:14,000
And over there you can open the Anaconda prompt.

45
00:03:14,000 --> 00:03:18,000
So over here you can see that I have opened the Anaconda prompt.

46
00:03:18,000 --> 00:03:21,000
So the step number one will be to set up the virtual environment.

47
00:03:21,000 --> 00:03:25,000
So in the step number one I will set up a virtual environment.

48
00:03:30,000 --> 00:03:38,000
So to set up the virtual environment I will write conda create python n.

49
00:03:39,000 --> 00:03:42,000
And here we will write the name of the virtual environment.

50
00:03:42,000 --> 00:03:48,000
I will write your 11 um 40 okay.

51
00:03:49,000 --> 00:03:52,000
So this is the name of my virtual environment.

52
00:03:52,000 --> 00:03:57,000
And I will be using Python 3.10 which is stored on my system.

53
00:04:00,000 --> 00:04:04,000
So first of all is we need to set up a virtual environment.

54
00:04:07,000 --> 00:04:11,000
So this will take few seconds to set up the virtual environment.

55
00:04:16,000 --> 00:04:18,000
Going right over here.

56
00:04:31,000 --> 00:04:33,000
So this will take few more seconds.

57
00:04:33,000 --> 00:04:33,000
So let's wait.

58
00:04:33,000 --> 00:04:36,000
So now we need to activate our environment.

59
00:04:36,000 --> 00:04:37,000
So I will write Conda activate.

60
00:04:37,000 --> 00:04:42,000
And the name of my environment is YOLO 11 dash 4d.

61
00:04:43,000 --> 00:04:44,000
So let's run this.

62
00:04:44,000 --> 00:04:48,000
So now now you can see that I have just activated my environment.

63
00:04:48,000 --> 00:04:51,000
And you can see the name over here so we can clear the screen.

64
00:04:52,000 --> 00:04:52,000
Okay.

65
00:04:52,000 --> 00:04:55,000
So now we have set up the virtual environment.

66
00:04:55,000 --> 00:04:58,000
Now in the next step we will set up the YOLO 11.

67
00:04:58,000 --> 00:05:02,000
So we will install the Ultralytics package over here.

68
00:05:02,000 --> 00:05:06,000
So I will just write pip install Ultralytics over here.

69
00:05:11,000 --> 00:05:14,000
So I am installing the Ultralytics package.

70
00:05:18,000 --> 00:05:23,000
So with the Ultralytics package like you can see that many other packages like NumPy, matplotlib,

71
00:05:23,000 --> 00:05:31,000
OpenCV, Python, SciPy, pandas, Seaborn and many other packages also gets installed as well.

72
00:05:32,000 --> 00:05:36,000
Now you can see there are large number of packages which are just getting installed.

73
00:05:38,000 --> 00:05:40,000
So this will take few more seconds.

74
00:05:41,000 --> 00:05:44,000
So now you can see that it's installing all the connected packages.

75
00:05:44,000 --> 00:05:49,000
So they are like many packages that are installed along with the latest package.

76
00:05:52,000 --> 00:05:54,000
So let's wait for a few seconds.

77
00:06:21,000 --> 00:06:24,000
Now you can see that all the packages are installed.

78
00:06:24,000 --> 00:06:26,000
So we can first clear the screen.

79
00:06:26,000 --> 00:06:30,000
And then I will just write Python over here.

80
00:06:31,000 --> 00:06:34,000
I will just write Import torch.

81
00:06:42,000 --> 00:06:47,000
And over here I will just write torch dash version to check the torch version.

82
00:06:47,000 --> 00:06:55,000
So we have 2.4.1 and our I'll keep you on because I don't have GPU available in my local machine.

83
00:06:58,000 --> 00:07:01,000
Then what you can do over here is, uh, with git.

84
00:07:01,000 --> 00:07:04,000
From here we can simply write this git.

85
00:07:04,000 --> 00:07:05,000
And we have.

86
00:07:05,000 --> 00:07:11,000
So if you have a GPU available in your local machine, you can simply write PyTorch dot.

87
00:07:12,000 --> 00:07:14,000
Org from here.

88
00:07:17,000 --> 00:07:20,000
And then you can click on Get started from here.

89
00:07:21,000 --> 00:07:21,000
Okay.

90
00:07:21,000 --> 00:07:28,000
And if you want to install a torch with GPU so you can simply type 2.1.4 over here.

91
00:07:28,000 --> 00:07:29,000
Okay.

92
00:07:29,000 --> 00:07:31,000
And just call same.

93
00:07:31,000 --> 00:07:33,000
And then you can just copy this command from here.

94
00:07:33,000 --> 00:07:41,000
And then you can go back over here and you can just, uh, write this over here as I don't have a GPU

95
00:07:41,000 --> 00:07:43,000
in my machine, so it's of no usage.

96
00:07:44,000 --> 00:07:46,000
So I will simply stop this operation.

97
00:07:46,000 --> 00:07:52,000
But if you have a GPU available in your local machine, then you can simply use torch with GPU.

98
00:07:52,000 --> 00:07:59,000
And after installing or installing this command over here, you can then just write Python over here,

99
00:07:59,000 --> 00:08:03,000
and then you can write Import Torch over here.

100
00:08:07,000 --> 00:08:08,000
And you can.

101
00:08:12,000 --> 00:08:16,000
Simply write torch dot dash dash version.

102
00:08:18,000 --> 00:08:20,000
So currently I don't have a GPU.

103
00:08:20,000 --> 00:08:22,000
So you can clearly see CPU over here.

104
00:08:23,000 --> 00:08:28,000
Uh, but if you have a GPU available in your local machine, like if you have Nvidia GPU available in

105
00:08:28,000 --> 00:08:33,000
your local machine, then you can install GPU version of PyTorch.

106
00:08:33,000 --> 00:08:37,000
So to install GPU version of PyTorch, you just need to simply run this command.

107
00:08:37,000 --> 00:08:40,000
After the installation gets finished.

108
00:08:40,000 --> 00:08:44,000
Then you can simply write Import Torch and you can check the version of torch.

109
00:08:44,000 --> 00:08:47,000
So here you will see that Cuda over here.

110
00:08:47,000 --> 00:08:57,000
So if acuta appears instead of CPU, so it means that you are using GPU version of PyTorch and the CPU

111
00:08:57,000 --> 00:08:59,000
version will be automatically deleted.

112
00:08:59,000 --> 00:08:59,000
Okay.

113
00:09:00,000 --> 00:09:02,000
So we can simply exit from here.

114
00:09:06,000 --> 00:09:09,000
Uh, one thing, uh, I just forgot to tell you.

115
00:09:09,000 --> 00:09:19,000
So you can further check is import torch if you want to check if you have, uh, if the PyTorch GPU

116
00:09:19,000 --> 00:09:19,000
is working.

117
00:09:19,000 --> 00:09:22,000
So one thing you can do is you can write torch dot.

118
00:09:24,000 --> 00:09:27,000
Tilde dot is cache available?

119
00:09:32,000 --> 00:09:36,000
So you can see false because as the GPU is not working.

120
00:09:36,000 --> 00:09:37,000
So you can clearly see false over here.

121
00:09:37,000 --> 00:09:43,000
But if you have a GPU working then you will see true over here as well.

122
00:09:43,000 --> 00:09:45,000
So we can simply exit from here.

123
00:09:48,000 --> 00:09:50,000
And I can just clear the screen.

124
00:09:51,000 --> 00:09:54,000
So let's we have set up everything.

125
00:09:54,000 --> 00:09:56,000
So now what we can do over here is.

126
00:09:58,000 --> 00:10:04,000
We will see how we can do object detection on images and on videos over here.

127
00:10:04,000 --> 00:10:05,000
Okay.

128
00:10:05,000 --> 00:10:11,000
So we will be using YOLO 11 directly in the command line interface with this YOLO command over here.

129
00:10:11,000 --> 00:10:12,000
Okay.

130
00:10:16,000 --> 00:10:21,000
So what we can do over here is we can simply write yolo.

131
00:10:21,000 --> 00:10:29,000
Toss is equal to detect mod is equal to predict okay.

132
00:10:29,000 --> 00:10:33,000
And model is equal to YOLO 11.

133
00:10:33,000 --> 00:10:35,000
We are using YOLO 11 nano model.

134
00:10:36,000 --> 00:10:43,000
And for the source and inside this folder over here YOLO 11 window record.

135
00:10:43,000 --> 00:10:44,000
If I just show you.

136
00:10:44,000 --> 00:10:47,000
So I have added these two images and one videos.

137
00:10:47,000 --> 00:10:56,000
I will use this image dot jpg over here so I can simply write source is equal to image dot zip.

138
00:11:04,000 --> 00:11:08,000
And let's see if you are able to do object detection on this image or not.

139
00:11:14,000 --> 00:11:15,000
So this will take few seconds.

140
00:11:16,000 --> 00:11:19,000
First is installing the YOLO 11 nano model.

141
00:11:24,000 --> 00:11:26,000
In the meanwhile it gets installed.

142
00:11:26,000 --> 00:11:27,000
Let me just.

143
00:11:38,000 --> 00:11:43,000
So you can see that our output is saved into runs detect predict okay.

144
00:11:43,000 --> 00:11:49,000
And we are able to predict one person, one bus, two traffic light, three backpacks and one handbag.

145
00:11:49,000 --> 00:11:49,000
Okay.

146
00:11:49,000 --> 00:11:51,000
And let's go to this folder.

147
00:11:51,000 --> 00:11:53,000
So you can see here we have the runs folder being created.

148
00:11:53,000 --> 00:11:55,000
And inside this we have predict.

149
00:11:55,000 --> 00:11:57,000
And over here.

150
00:12:01,000 --> 00:12:08,000
You can see over here we are able to predict bus person backpack handbag person traffic lights.

151
00:12:08,000 --> 00:12:12,000
So the bus prediction results are quite good.

152
00:12:12,000 --> 00:12:14,000
Okay so let's go back over here.

153
00:12:14,000 --> 00:12:20,000
And similarly we can do object detection on video as well.

154
00:12:20,000 --> 00:12:26,000
What you need to do is instead of source over here you just need to pass the video dot mp4.

155
00:12:26,000 --> 00:12:32,000
So as I'm running on CPU the processing will be very slow, but I will just show you how this works.

156
00:12:45,000 --> 00:12:49,000
So now you can see the complete video is divided into 458 frames.

157
00:12:49,000 --> 00:12:51,000
And we are doing detection.

158
00:12:51,000 --> 00:12:54,000
Object detection on each of the frame one by one.

159
00:12:54,000 --> 00:12:55,000
Okay.

160
00:12:55,000 --> 00:12:56,000
So let's wait for it to get finished.

161
00:12:56,000 --> 00:12:59,000
And then I will show you the output video as well.

162
00:13:03,000 --> 00:13:05,000
For the processing on the video is done.

163
00:13:05,000 --> 00:13:12,000
Let me just show you over here we have predict two and over here we have our output video.

164
00:13:13,000 --> 00:13:16,000
Let me just show you the output video over here.

165
00:13:19,000 --> 00:13:25,000
So over here you can see that we are able to detect person bicycle traffic lights over here.

166
00:13:25,000 --> 00:13:29,000
And we can also able to detect the road signs over here as well.

167
00:13:29,000 --> 00:13:32,000
So the results look very promising.

168
00:13:32,000 --> 00:13:36,000
Like you can see we are able to detect handbag person traffic lights.

169
00:13:36,000 --> 00:13:39,000
So overall the results look quite good.

170
00:13:39,000 --> 00:13:44,000
Okay So we have seen that how we can do object detection on image and video.

171
00:13:44,000 --> 00:13:53,000
Now we will see how we can do instance segmentation or object segmentation on image and video.

172
00:13:54,000 --> 00:13:59,000
So first I will just write down here.

173
00:14:01,000 --> 00:14:03,000
Let's just clear the screen.

174
00:14:03,000 --> 00:14:04,000
Over here I will just write CLS.

175
00:14:05,000 --> 00:14:14,000
And to do object segmentation or instance segmentation I will just write toss is equal to segment over

176
00:14:14,000 --> 00:14:15,000
here.

177
00:14:18,000 --> 00:14:21,000
And I will also write over here.

178
00:14:25,000 --> 00:14:32,000
And the source I will pass the input image over here I will just write image one dot jpg.

179
00:14:32,000 --> 00:14:39,000
So now what we are doing over here is we are doing instance segmentation on this input image over here.

180
00:14:43,000 --> 00:14:46,000
And currently we are using the pre-trained model.

181
00:14:46,000 --> 00:14:49,000
So we are just writing what is equal to predict.

182
00:14:49,000 --> 00:14:53,000
And we are doing the prediction using the pre-trained model.

183
00:14:53,000 --> 00:14:54,000
Okay.

184
00:14:54,000 --> 00:14:55,000
So it's done.

185
00:14:55,000 --> 00:15:02,000
And results of a model is equal to segment mod is equal to predict.

186
00:15:03,000 --> 00:15:04,000
Okay let's see.

187
00:15:13,000 --> 00:15:16,000
So it's doing object detection I might have made a mistake.

188
00:15:16,000 --> 00:15:17,000
So let me just see.

189
00:15:18,000 --> 00:15:22,000
Source is equal to segment mod is equal to okay.

190
00:15:22,000 --> 00:15:28,000
So basically I'm using object detection model I need to use a segmentation model.

191
00:15:28,000 --> 00:15:29,000
That is the mistake.

192
00:15:29,000 --> 00:15:37,000
So if you just go over here and see we have the segmentation model I need to use this model I was using

193
00:15:37,000 --> 00:15:37,000
direct Object detection model.

194
00:15:38,000 --> 00:15:40,000
Therefore I was just getting this issue.

195
00:15:40,000 --> 00:15:43,000
So hopefully this issue will be sorted out.

196
00:15:46,000 --> 00:15:47,000
So let's see.

197
00:15:47,000 --> 00:15:49,000
This will take few seconds.

198
00:15:52,000 --> 00:15:56,000
So now first downloading and downloading the segmentation model.

199
00:15:56,000 --> 00:15:58,000
As you can clearly see over here.

200
00:16:00,000 --> 00:16:04,000
Now its results are saved in segment predict folder.

201
00:16:04,000 --> 00:16:06,000
And let me just go towards this folder.

202
00:16:06,000 --> 00:16:09,000
And here you can see we have the segmentation folder and the predict.

203
00:16:09,000 --> 00:16:12,000
And here you can see we have the output image.

204
00:16:13,000 --> 00:16:19,000
So now you can see that we are able to do instance segmentation on bus traffic light person handbag

205
00:16:19,000 --> 00:16:20,000
backpack.

206
00:16:20,000 --> 00:16:22,000
And the results look quite impressive.

207
00:16:22,000 --> 00:16:25,000
Like you can see these are the instance segmentation results.

208
00:16:25,000 --> 00:16:28,000
And the results look quite promising as well.

209
00:16:28,000 --> 00:16:35,000
And to do instance segmentation on videos, what you can do is you can simply replace the source with

210
00:16:35,000 --> 00:16:42,000
the name of the video, a file name like video or mp4, I will not go towards it because I'm just running

211
00:16:42,000 --> 00:16:45,000
it on CPU and the processing on CPU takes a lot of time.

212
00:16:45,000 --> 00:16:50,000
So we have seen that how we can do object detection and instance segmentation.

213
00:16:50,000 --> 00:16:54,000
Now we will see how we can do both estimation on image and video.

214
00:16:56,000 --> 00:17:04,000
So to do pose estimation first of all what I will just clear the screen over here and we can just update

215
00:17:04,000 --> 00:17:12,000
our this is um toss will be equal to pose now and we will be using YOLO.

216
00:17:15,000 --> 00:17:19,000
Post model over here and over here.

217
00:17:19,000 --> 00:17:21,000
What we can use we can use simply this image that's what.

218
00:17:25,000 --> 00:17:29,000
Let's see if we are able to do pose estimation on this input image or not.

219
00:17:32,000 --> 00:17:39,000
So this will take few seconds before it explodes, downloading the YOLO 11 pose estimation model.

220
00:17:45,000 --> 00:17:48,000
So now you can see that your 11th pose estimation model is downloading.

221
00:17:48,000 --> 00:17:52,000
And we are able to do pose estimation on this input image.

222
00:17:52,000 --> 00:17:57,000
So let me just go over here and you can see the pose folder over here.

223
00:17:57,000 --> 00:17:59,000
And here you can see that.

224
00:18:02,000 --> 00:18:06,000
So now you can see that we are able to do pose estimation on this input image.

225
00:18:06,000 --> 00:18:11,000
So YOLO 11 pose estimation model is being trained on the for the person poses.

226
00:18:11,000 --> 00:18:14,000
So it will only detect pose for the person.

227
00:18:14,000 --> 00:18:20,000
And if you want to detect uh, the pose estimation for any element or for any object, you need to fine

228
00:18:20,000 --> 00:18:22,000
tune the YOLO 11 model.

229
00:18:22,000 --> 00:18:29,000
Okay, because YOLO 11 pose estimation model is being trained to do pose estimation of only person.

230
00:18:29,000 --> 00:18:34,000
And if you want to do pose estimation of any object or any animal, you need to fine tune the YOLO 11

231
00:18:34,000 --> 00:18:36,000
pose estimation model.

232
00:18:36,000 --> 00:18:36,000
Okay.

233
00:18:36,000 --> 00:18:44,000
And in the same way we can also we will also see how we can do, uh, for estimation on our video.

234
00:18:44,000 --> 00:18:48,000
So we can simply right over here video dot mp4.

235
00:18:48,000 --> 00:18:54,000
So now we are doing pose estimation using YOLO 11 pose estimation model on the input video.

236
00:19:01,000 --> 00:19:03,000
So this will take quite some time.

237
00:19:03,000 --> 00:19:04,000
Like you can see over here.

238
00:19:04,000 --> 00:19:07,000
The complete video is being divided into 458 frames.

239
00:19:07,000 --> 00:19:10,000
And the processing on each of the frame is done one by one.

240
00:19:10,000 --> 00:19:12,000
So let's wait for it to get finished.

241
00:19:12,000 --> 00:19:14,000
And then I will show you the output video as well.

242
00:19:18,000 --> 00:19:21,000
So the processing on this input video is done.

243
00:19:21,000 --> 00:19:25,000
So I will just go over here and open the predict to folder over here.

244
00:19:25,000 --> 00:19:31,000
And let's see if we are able to do all the estimation on this input video or not.

245
00:19:33,000 --> 00:19:37,000
So now you can see that we are able to do the detection and pose estimation as well.

246
00:19:37,000 --> 00:19:40,000
So you can see the results look quite promising.

247
00:19:40,000 --> 00:19:43,000
Like you can see we are able to detect the person.

248
00:19:43,000 --> 00:19:47,000
And we are also able to do the pose estimation as well.

249
00:19:47,000 --> 00:19:54,000
Okay, so now we are left with only one task which is classification like image classification.

250
00:19:54,000 --> 00:20:00,000
So what we can do is first I will just clear the screen and I will just write over here.

251
00:20:01,000 --> 00:20:05,000
Task is equal to classify I think this is correct.

252
00:20:06,000 --> 00:20:12,000
And um we will use uh classification.

253
00:20:16,000 --> 00:20:17,000
Okay.

254
00:20:17,000 --> 00:20:19,000
Let me just check it once.

255
00:20:20,000 --> 00:20:21,000
Okay.

256
00:20:22,000 --> 00:20:30,000
Uh, for the classification we have SNS, so why not use the extra large model X CLS and I will just

257
00:20:30,000 --> 00:20:32,000
pass the car image.

258
00:20:33,000 --> 00:20:35,000
So what's the spelling or the car image?

259
00:20:39,000 --> 00:20:42,000
That's in the PNG or JPEG that's in the picture.

260
00:20:42,000 --> 00:20:47,000
That works for image dot.

261
00:20:48,000 --> 00:20:49,000
So let's run this.

262
00:20:55,000 --> 00:20:58,000
So first it will download this model.

263
00:20:58,000 --> 00:20:59,000
Uh let's see.

264
00:21:01,000 --> 00:21:03,000
Now you can see the model is downloading.

265
00:21:03,000 --> 00:21:05,000
The size of the model is 6.9.

266
00:21:05,000 --> 00:21:08,000
Like the YOLO and YOLO 11.

267
00:21:08,000 --> 00:21:15,000
Extra large model is ten times larger in size than the YOLO 11 nano model.

268
00:21:15,000 --> 00:21:21,000
YOLO 11 nano model is around 5.69 MB, and your 11 extra large model is 56.9 MB.

269
00:21:22,000 --> 00:21:29,000
So it's around ten times enlarged in size as compared to the YOLO 11 nano model.

270
00:21:29,000 --> 00:21:34,000
So now you're done and you can see we have saved our result in runs classifier.predict.

271
00:21:34,000 --> 00:21:41,000
So if we just go over here and predict, let's see how it works.

272
00:21:43,000 --> 00:21:47,000
So over here you can see that if you can zoom in the screen.

273
00:21:47,000 --> 00:21:52,000
So you can clearly see over here the model has given me like the splits.

274
00:21:52,000 --> 00:21:59,000
The model is 66% confident that the sports car and yes this is a sports car, while the model is, uh,

275
00:21:59,000 --> 00:22:07,000
11% confident that this the car will 10% confident that is the cap and only 3% confident that this is

276
00:22:07,000 --> 00:22:07,000
a racer.

277
00:22:07,000 --> 00:22:12,000
So like 66% the model is confident that this is the sports car.

278
00:22:12,000 --> 00:22:14,000
So we are just getting impressive results.

279
00:22:14,000 --> 00:22:18,000
So in this tutorial we have seen that how we can run Dx11 in windows.

280
00:22:18,000 --> 00:22:25,000
And we have seen that how we can run YOLO 11 directly in the command line interface with the YOLO command.

281
00:22:25,000 --> 00:22:26,000
So that's all from this tutorial.

282
00:22:26,000 --> 00:22:27,000
Thank you for watching.