1
00:00:00,000 --> 00:00:01,000
Hello guys!

2
00:00:01,000 --> 00:00:07,000
So finally we will also see how you can implement this entire project with the help of GRU RNN.

3
00:00:07,000 --> 00:00:12,000
There is only one difference that you really need to use over here, right?

4
00:00:12,000 --> 00:00:17,000
So if you see over here we are completely implemented with the help of LSTM RNN, right?

5
00:00:17,000 --> 00:00:24,000
We imported the LSTM layers and all right along with this, in the layer itself you also have an option

6
00:00:24,000 --> 00:00:25,000
to add GRU.

7
00:00:25,000 --> 00:00:25,000
Okay.

8
00:00:25,000 --> 00:00:31,000
So if I just go ahead and use this attribute called as uh this library called as GRU.

9
00:00:31,000 --> 00:00:33,000
Sorry, it should be capital letter.

10
00:00:33,000 --> 00:00:37,000
So here you will be able to see that this grew.

11
00:00:37,000 --> 00:00:42,000
Will you will also be able to use for a specific grew instead of LSTM, RNN.

12
00:00:42,000 --> 00:00:46,000
And if I really want to write the same thing with respect to GRU.

13
00:00:46,000 --> 00:00:50,000
So here I will just give you with GRU RNN.

14
00:00:50,000 --> 00:00:53,000
Okay, here I can just copy paste over here.

15
00:00:53,000 --> 00:00:54,000
Okay.

16
00:00:54,000 --> 00:00:56,000
And remember this is imported over here.

17
00:00:56,000 --> 00:01:01,000
Instead of writing LSTM you can go ahead and write GRU here itself okay.

18
00:01:01,000 --> 00:01:03,000
Similarly here you can go ahead and write GRU, grew.

19
00:01:03,000 --> 00:01:04,000
Right.

20
00:01:04,000 --> 00:01:08,000
So as you know this is a different variant of LSTM RNN.

21
00:01:08,000 --> 00:01:10,000
So you can specifically use this.

22
00:01:10,000 --> 00:01:13,000
And uh you can go ahead and execute this right.

23
00:01:13,000 --> 00:01:16,000
If you really want to work with GRU in itself.

24
00:01:16,000 --> 00:01:16,000
Right.

25
00:01:16,000 --> 00:01:18,000
This is the only change that will happen.

26
00:01:18,000 --> 00:01:23,000
And based on this, whether you are using this or whether you are using LSTM, RNN, uh, you can go

27
00:01:23,000 --> 00:01:26,000
ahead and update that and you can go ahead and continuously train it.

28
00:01:26,000 --> 00:01:26,000
Okay.

29
00:01:26,000 --> 00:01:31,000
So this is the only difference with respect to the adding layers with respect to GRU.

30
00:01:31,000 --> 00:01:35,000
Now with respect to an assignment, I will just go ahead and give it to you.

31
00:01:35,000 --> 00:01:40,000
Please go ahead and go ahead and solve this entire problem statement with the help of GRU, and see

32
00:01:40,000 --> 00:01:43,000
how much difference you are able to get with respect to the accuracy.

33
00:01:43,000 --> 00:01:48,000
But if I talk with respect to GRU over here, you have less number of gates when compared to the LSTM

34
00:01:48,000 --> 00:01:49,000
RNN.

35
00:01:49,000 --> 00:01:54,000
So, uh, this is the only difference, uh, with GRU and LSTM.

36
00:01:54,000 --> 00:01:58,000
I hope you like this particular video, and I hope you like this all entire series of videos where we

37
00:01:58,000 --> 00:01:59,000
have created this amazing project.

38
00:01:59,000 --> 00:02:01,000
So yes, this was it from my side.

39
00:02:01,000 --> 00:02:02,000
I will see you all in the next video.

40
00:02:02,000 --> 00:02:03,000
Thank you.