Original subtitles

1

Hello and welcome to this new tutorial.

2

All right.

3

So in the previous Statoil we created our as is the neural network.

4

So now we have the frame and the net the neural network.

5

So we have one less thing to create before we are ready to apply the detect function.

6

It's the transformation.

7

So that's exactly what we're going to do in the Statoil.

8

We're going to create that transformation.

9

I'm saying create because we're actually going to create a new object of the base transform class.

10

So it is exactly this object that will do the transformation itself on the image so that this image

11

is compatible with the neural network that is this transformation will make sure that this frame can

12

get in to the neural network net.

13

All right.

14

So let's do this.

15

It's going to be very easy and fast.

16

We just need one line of code because we have the base friends from class.

17

We just need to create an object of this class so let's do this.

18

We're going to call this transformation transform obviously.

19

And since this transform transformation is going to be an object of the base transform class.

20

Well I'm calling this class and now we have to input several arguments.

21

So the first argument is not that size and not that size is the target size of the images to feed to

22

the neural network.

23

So here we go net that size that the second argument is a couple of three arguments a triplet is going

24

to be a triplet of three numbers that will allow to put the color values at the right scale.

25

And what is this right scale.

26

Well that's exactly the scale under which the neural network was trained.

27

That is this new will network from which we're losing the weight was trained it was trained under some

28

certain convention and part of this convention concerns the skill.

29

And what we're doing now is exactly putting the right scale for the color values.

30

So now I'm just going to put three numbers don't worry about the numbers.

31

These are just numbers to get the red scale.

32

But it's not the most important.

33

So these numbers are the first one is 104 divided by 256 point zero.

34

Then the second number is 117 divided by 256 point zero and the third and final number is 123 divided

35

by 256 point zero.

36

All right.

37

So net size is the target size of the images to be given to the neural network.

38

And these three values here are some scale values to make sure that the color values are in the right

39

scale and that's it.

40

Actually our transformation is ready.

41

So now time for some exciting stuff in the next tutorial we will actually open the video then we will

42

iterate on the frames of this video because I remind that this technique is a frame by frame detection.

43

So we playing the detect function on each frame of the video you're going to see that this two seconds

44

video has sixty eight frames I think something like that 67 or 68.

45

And we're going to play the detect function on the 68 frames of this video.

46

So the first thing we'll do after opening the video is that we'll get all these frames.

47

Then we'll apply that to check function on each of these frames.

48

Then there's the deck function will detect some dogs humans or whatever on the frames will print the

49

rectangles on each of these frames and then we will reassemble the whole frames to make a new video.

50

That is the original video with the detector rectangles detecting the objects.

51

So I can't wait to do that in the next tutorial.

52

We're about to see the final video.

53

Can't wait to show you this.

54

Until then enjoy computer vision.