Introduction to TensorFlow 2.0: Easier for beginners, and more powerful for experts (TF World '19)

Поділитися
Вставка
  • Опубліковано 16 лис 2024

КОМЕНТАРІ • 55

  • @devashishkprasad
    @devashishkprasad 3 роки тому

    Best introduction to Tensorflow 2.0 ever

  • @Ftur-57-fetr
    @Ftur-57-fetr 3 роки тому +1

    Josh is a God of explanations in my Universe.
    Thank you!

  • @sarthakgupta290
    @sarthakgupta290 4 роки тому +20

    Very well explained ! I am impressed with this guy's articulation skills.

  • @y-revar
    @y-revar 5 років тому +16

    Awesome presentation! I was attracted to simplicity of PyTorch, but the new features of TF 2.0 look very promising.

  • @MohakNarang07
    @MohakNarang07 4 роки тому +1

    I was a lot skeptical about tensorflow 2.0 when I heard that it has been made like Keras. Thb, I absolutely hate keras as something always feels missing in the framework (maybe a lack of control). But the introduction of subclassing really exites me now. Its good that TF is a lot like Torch now, the flexibility looks amazing. Good work tensorflow!

  • @joeya6635
    @joeya6635 4 роки тому

    Tensorflow 2.0 will make modelling so much expressive/artistic with the added touch of lower level control if needed , plus easier deployment? Wow! just wow! ! What an exciting time to exist.😂😂😂

  • @soon931111
    @soon931111 3 роки тому +1

    This is great, why did it take me so long to discover this?

  • @shivangitomar5557
    @shivangitomar5557 2 роки тому +1

    Amazing video!!

  • @ashishk81
    @ashishk81 5 років тому +2

    WOW ! i am very excited to try ...these new features of TF 2.0

  • @grahamgreen5497
    @grahamgreen5497 5 років тому +13

    Great presentation, thanks Josh and the TF2 team.

  • @kemchobhenchod
    @kemchobhenchod 4 роки тому

    Google programmers are so incredibly well spoken and good at presenting, either there must be some training internally or they select for this at interviews

  • @miguelalba2106
    @miguelalba2106 5 років тому

    Like this new way of writing custom stuff in the low level with tf.Module instead of keras

  • @RajkumarDarbar
    @RajkumarDarbar 5 років тому +2

    wow! super cool presentation! Thanks, Josh!!

  • @hydro1897
    @hydro1897 4 роки тому +2

    That's a super cool presentation! I believe even someone who is not familiar with TF and ML will have the motivation to try it out after this talk.

  • @AndreiPastramagiu
    @AndreiPastramagiu 5 років тому +4

    Great explanations Josh, as usual! Thanks!

  • @shunnie8482
    @shunnie8482 3 роки тому

    Amazing presentation, I really enjoyed it.

  • @rohan1427
    @rohan1427 3 роки тому

    This is an awesome tutorial !

  • @jamesmasaiii1569
    @jamesmasaiii1569 5 років тому +2

    Thanks for an excellent presentation.

  • @dokko1231
    @dokko1231 5 років тому +15

    Great presentation. Are there slides available for this?

  • @user-fy5go3rh8p
    @user-fy5go3rh8p 4 роки тому +1

    Absolutely fantastic talk, thank you

  • @许青-c4z
    @许青-c4z 4 роки тому +1

    Wonderful presentation! Thanks so much.

  • @JBoy340a
    @JBoy340a 5 років тому +1

    Nice job, Josh!

  • @fahemhamou6170
    @fahemhamou6170 2 роки тому

    تحياتي الخالصة

  • @alphatauri_
    @alphatauri_ 5 років тому +2

    Nice presentation, thaks Josh!

  • @milleniumsalman1984
    @milleniumsalman1984 2 місяці тому

    really good

  • @siyuanfeng1368
    @siyuanfeng1368 5 років тому +2

    TensorFlow 2 is so amazing!!!
    And I would use PyTorch 1.3

  • @JoeWong81
    @JoeWong81 5 років тому +3

    That was amazing Josh

  • @henrybottomsworth
    @henrybottomsworth 5 років тому

    Nice job team

  • @khadijakhaldi6468
    @khadijakhaldi6468 4 роки тому +2

    Where can we find the slides please ?

  • @gusteven3937
    @gusteven3937 3 роки тому

    good job!

  • @RARa12812
    @RARa12812 4 роки тому

    Is keras 100 percent comparible with tensorflow 2.0?

  • @auraSinhue
    @auraSinhue 5 років тому +1

    Great talk, josh!

  • @nathanas64
    @nathanas64 5 років тому

    Excellent!

  • @AltafHussain-gk2xe
    @AltafHussain-gk2xe 5 років тому +1

    Superb

  • @auslei
    @auslei 4 роки тому

    Anyone know where can I find the share collab projects?

  • @forevertheuni
    @forevertheuni 4 роки тому

    The tutorials for beginners in the website do not explain most things (what are all the lines doing). I code in python for 15 years. I have never have a trouble understanding any library anything until now.

  • @alkhashtee
    @alkhashtee 5 років тому +1

    Wonderful

  • @Chimendei
    @Chimendei 5 років тому

    17:18 Can we use callbacks on train_on_batch? Any references for that?

  • @khangspkt1
    @khangspkt1 5 років тому +1

    Hello, are someone exciting with new version TF2? I saw a lot of new things release. Let's discuss about it

  • @김범석-k5y
    @김범석-k5y 5 років тому

    IMPRESSED

  • @kiranlonikar
    @kiranlonikar 5 років тому +1

    slides for this presentation: it has lots of useful links... drive.google.com/file/d/1YG3QX8syS-t8WyWOjGaGrtrsvSDqSTLx/view

  • @adarshs2948
    @adarshs2948 4 роки тому

    Cannot install tensorflow as wrapt is not getting installed
    HELP!!!!!!!!!!!!!!!!!!!!!!!!!!!!!

  • @geoffreyanderson4719
    @geoffreyanderson4719 5 років тому +1

    When is CSV data going to be done? It's still in the experimental section, and TF has been out 4 years. Secondly, there is no instructional coverage of CSV at all in the brand new Tensorflow Specialization on coursera by Andrew Ng and Google's trainer. The whole UCI ML dataset lib is CSV, in case you didn't notice yet somehow. Unlike software app developers, data scientists don't get to create whatever dataset we want just like app developers seem to do. We have to do work on the data that the organization has provided and in case data science is a new concept for you, that is largely CSV for example Higgs Boson dataset. But both Microsoft and Google still seem to treat data scientists as if software apps with unstructured vision/NLP are all that really matters, and the structured datasets (ie, CSV) are for science nerds and don't really matter much so lets let our summer interns take care of CSV support while we're on vacation. "It should be easy." Did Microsoft actually try to use the CNTKTextFormatReader (later simply CTF Reader)? DUDES go to Kaggle and try the BOSCH dataset (not Titanic enough of that) and get back to me stories about easy CSVs again, bro. Try to use your own tf.data.experimental.CsvDataset and get back to us.

  • @ben6
    @ben6 4 роки тому

    Nothing simple conceptually? What does that mean? 9:35

  • @YovaniAchataFlores
    @YovaniAchataFlores 4 роки тому

    nice!

  • @pranshunema6719
    @pranshunema6719 4 роки тому

    But early stopping shouldn't be used because it will lead orthogonalization

  • @tktks9818
    @tktks9818 5 років тому

    need help in prediction from trained & saved model, same as 36:36 ,,, any one expert here ?

  • @gusteven3937
    @gusteven3937 3 роки тому

    Is it the google's server get down?

  • @abhashpr
    @abhashpr 5 років тому

    👍👍👍👍👍

  • @Denverse
    @Denverse 5 років тому

    import tensorflow as tf

  • @akashpawar9058
    @akashpawar9058 5 років тому

    I am learning

  • @tcgvsocg1458
    @tcgvsocg1458 2 роки тому

    What are you doing here?

  • @praveenvemula8250
    @praveenvemula8250 4 роки тому +1

    Excellent presentation. Thanks!

  • @adityaverma2037
    @adityaverma2037 3 роки тому

    Superb