Would you like to inspect the original subtitles? These are the user uploaded subtitles that are being translated:
1
00:00:05,910 --> 00:00:07,440
Welcome back everyone.
2
00:00:07,440 --> 00:00:11,310
In this lecture we're going to discuss the difference between tensor flow and carries.
3
00:00:12,390 --> 00:00:16,470
So before we begin learning how to code our own neural networks I want to quickly clarify the differences
4
00:00:16,710 --> 00:00:18,540
between tense flow and cares.
5
00:00:18,540 --> 00:00:21,220
Since this is a common point of confusion for students.
6
00:00:21,360 --> 00:00:24,410
So we already learned all the theoretical aspects of neural networks.
7
00:00:24,480 --> 00:00:30,990
Now right before we start coding I want to clarify a few things tensor flow is an open source Deep Learning
8
00:00:30,990 --> 00:00:36,850
library developed by Google with tensor flow 2.0 being officially released in late 2019.
9
00:00:38,290 --> 00:00:44,260
TENSOR flow has large ecosystem of related components including libraries like tech support for visualization
10
00:00:44,530 --> 00:00:49,810
deployment options and production API side as well as support for various programming languages not
11
00:00:49,810 --> 00:00:57,830
just Python cares is a high level python library that can use a variety of Deep Learning libraries underneath
12
00:00:58,340 --> 00:01:07,060
so it can operate on top of libraries such as tensor flow C A.K. or Athena tensor flow one point X or
13
00:01:07,060 --> 00:01:13,120
any of the one point versions had a complex python class system for building models and because it was
14
00:01:13,120 --> 00:01:14,660
a little more complex.
15
00:01:14,950 --> 00:01:22,870
The Caris library ended up being a simpler more abstract API that could run on top of tensor flow so
16
00:01:22,870 --> 00:01:28,570
Caris ended up becoming very popular and it was so popular that when the developers for tensor flow
17
00:01:28,630 --> 00:01:34,770
ended up releasing 2.0 they adopted Caris as the official API for tensor flow.
18
00:01:34,820 --> 00:01:41,270
So while Caris still also remains as a separate library from tensor flow it can also now be officially
19
00:01:41,270 --> 00:01:46,670
imported through tensor flow so there's no need to do an additional installation of carers cares is
20
00:01:46,670 --> 00:01:53,900
now officially part of tensor flow in it's the official API for tensor flow 2.0 and going forward because
21
00:01:53,900 --> 00:02:00,170
it's simpler to use than the more complex subclass system that was used in tensor flow one point X versions
22
00:02:01,580 --> 00:02:02,530
the curious API.
23
00:02:02,570 --> 00:02:07,760
It's easy to use and build models by simply adding layers on top of each other through simple calls.
24
00:02:07,790 --> 00:02:12,230
So in the next lecture let's begin exploring the basics of the cares API for tensor flow.
25
00:02:12,260 --> 00:02:12,850
I'll see you there.
2981
Can't find what you're looking for?
Get subtitles in any language from opensubtitles.com, and translate them here.
Afrikaans
Akan
Albanian
Amharic
Armenian
Azerbaijani
Basque
Belarusian
Bemba
Bengali
Bihari
Bosnian
Breton
Bulgarian
Cambodian
Catalan
Cebuano
Cherokee
Chichewa
Chinese (Simplified)
Chinese (Traditional)
Corsican
Croatian
Czech
Danish
Dutch
English
Esperanto
Estonian
Faroese
Finnish
Galician
Georgian
German
Greek
Guarani
Haitian Creole
Hausa
Hawaiian
Hebrew
Hmong
Hungarian
Icelandic
Indonesian
Irish
Italian
Japanese
Kazakh
Kinyarwanda
Kirundi
Kongo
Korean
Krio (Sierra Leone)
Kurdish
Kyrgyz
Laothian
Latin
Latvian
Lithuanian
Luganda
Luo
Luxembourgish
Macedonian
Malagasy
Malay
Maltese
Maori
Mauritian Creole
Moldavian
Mongolian
Myanmar (Burmese)
Montenegrin
Nepali
Norwegian
Pashto
Persian
Polish
Portuguese (Brazil)
Portuguese (Portugal)
Quechua
Romanian
Romansh
Russian
Samoan
Scots Gaelic
Serbian
Sesotho
Setswana
Seychellois Creole
Shona
Sindhi
Sinhalese
Slovak
Slovenian
Somali
Spanish
Swedish
Tajik
Thai
Tigrinya
Tonga
Turkish
Turkmen
Ukrainian
Uzbek
Vietnamese
Welsh
Wolof