1
00:00:00,720 --> 00:00:06,890
Drawn the spectacle part of this goes, you will find that we didn't mention of get us an authentic

2
00:00:06,910 --> 00:00:07,230
Lou.

3
00:00:08,360 --> 00:00:12,610
In this video, we will try to understand what get us and then to blow up.

4
00:00:13,760 --> 00:00:14,320
So let's see.

5
00:00:16,020 --> 00:00:23,340
Get US is a deep learning framework that provides a convenient way to define and train almost any kind

6
00:00:23,340 --> 00:00:24,540
of deep learning model.

7
00:00:26,020 --> 00:00:28,950
Basically, get us works at any model living.

8
00:00:29,820 --> 00:00:31,380
It will help you define the model.

9
00:00:31,800 --> 00:00:33,240
That is how many lives.

10
00:00:33,630 --> 00:00:34,750
How many lives.

11
00:00:35,490 --> 00:00:36,660
What does the added function?

12
00:00:36,720 --> 00:00:38,330
What is the optimizer, etc..

13
00:00:39,600 --> 00:00:42,120
But it does not handle any lower level operations.

14
00:00:43,200 --> 00:00:49,770
If you remember in the previous two reflectors, we learned that while training a neural network, we

15
00:00:49,770 --> 00:00:57,010
need a lot of differentiation, matrix, manipulation, etc., all these are not done by us.

16
00:00:57,910 --> 00:01:04,560
Instead, this low level manipulation and differentiation of data is done by certain specialized and

17
00:01:04,560 --> 00:01:06,030
well optimized libraries.

18
00:01:08,460 --> 00:01:14,760
Good thing about Get US is that it can vote seamlessly with several such lower level libraries.

19
00:01:16,270 --> 00:01:23,930
Currently, there are three main backend libraries in Tetlow, which is done by Google s.M Begaye,

20
00:01:24,040 --> 00:01:30,760
which stands for Cognitive Toolkit and is developed by Microsoft and Tierno, which is Dell'Abate Miller

21
00:01:30,760 --> 00:01:32,630
Lab at University of Montreal.

22
00:01:34,800 --> 00:01:40,890
Any piece of code written in Get US can be done with any of these back end without having to change

23
00:01:40,980 --> 00:01:41,940
anything in the code.

24
00:01:43,360 --> 00:01:49,900
But as of now, denser flow is the most widely adopted, more scalable and most production ready.

25
00:01:50,500 --> 00:01:52,960
So we will be using pensive of law and discourse.

26
00:01:55,360 --> 00:01:59,320
Now, denser flow or any other such low level library.

27
00:01:59,980 --> 00:02:04,990
These libraries need processing power from our system to do all this data manipulation.

28
00:02:05,920 --> 00:02:12,610
This processing power can be provided by either C.P.U or DIPU, which stands for Central Processing

29
00:02:12,610 --> 00:02:16,510
Unit or demographical processing it by default.

30
00:02:17,140 --> 00:02:21,060
We do all C.P.U based installation of care doesn't antiflu.

31
00:02:21,940 --> 00:02:29,830
But if you are running on a system with End Radio Deepu and a properly configured libraries of Invidia

32
00:02:29,980 --> 00:02:34,590
such as Kouda or so you'd be an in which I would be Blanning.

33
00:02:34,930 --> 00:02:40,060
Then you can install the deep you based virgin of data and to flow back in InGen as well.

34
00:02:42,360 --> 00:02:43,930
So that's all we need to know about.

35
00:02:43,950 --> 00:02:44,860
Get us intense upload.

36
00:02:45,600 --> 00:02:47,960
No need to be overwhelmed by these domes now.

37
00:02:48,570 --> 00:02:53,010
You will see how using guitars will define definer neural network model.

38
00:02:53,940 --> 00:03:00,540
And then we will take it us to use Tenzer flow backing to train the model in the next video.

39
00:03:00,630 --> 00:03:03,930
We will learn how to install guitars and tens of low in our system.
