Original subtitles

1

Hello and welcome to this new tutorial in the previous Statoil we tackled the first two steps steps

2

of the training of the discriminator.

3

We trained it on real images and then on fake images.

4

And so now it's almost over.

5

We are ready for the third substate which is to get the total air as the sum of the to the R R D real

6

and b r d fake.

7

So we'll get this some that will get as little error and then we'll back propagate the stall error back

8

into the new one that work at the discriminator to then update the weights through to get to Graylands

9

descent according to how much they're responsible for the error.

10

So very easy now.

11

Let's start by getting the total error.

12

We're going to call it the R R D.

13

It's the total error of the discriminator.

14

So e r d equals well R R D real which I am copying and pasting Plus R D fake again which I'm copying

15

and pasting.

16

And there we go we have all error.

17

So now let's back propagate it back into the new one that work of the discriminator and to do this.

18

Thanks Supai torch.

19

It's really simple we just need to take the error the total error the R D and then dot and then we use

20

the back word function to back propagate it.

21

Perfect.

22

And now one final step of this first big step of the training we need to apply is to cast a grade in

23

the center of the weight and to do this guess what we're going to take right now.

24

We're going to take the optimizer of the discriminator.

25

And so I'm copying this I'm pasting it here and there we go almost over.

26

We just need to add a dirt and apply the step function to step function applies the optimizer on the

27

neural network to discriminator to have they the weight of the discriminator according to how much they're

28

responsible for the total loss error which is the sum of the real error and the fake error.

29

And so now well done.

30

Good job.

31

You're ready to move on to the second step of the training and we'll take care of that in the next tutorial.

32

Until then enjoy computer vision.