PyTorch vs TensorFlow | Ishan Misra and Lex Fridman

แชร์
ฝัง
  • เผยแพร่เมื่อ 11 ธ.ค. 2024

ความคิดเห็น • 53

  • @ogrendang7810
    @ogrendang7810 3 ปีที่แล้ว +280

    Asking a Facebook employee about pytorch vs tensorflow. 🤔

    • @ghostman3329
      @ghostman3329 ปีที่แล้ว

      Yup ..

    • @kidzeus2433
      @kidzeus2433 10 หลายเดือนก่อน

      Lol

    • @niranjan_7891
      @niranjan_7891 8 หลายเดือนก่อน +2

      They make the largest no of open-source AI models so why not.

    • @niranjan_7891
      @niranjan_7891 8 หลายเดือนก่อน

      They have currently 1907models.Refer Hugging Face

    • @2dapoint424
      @2dapoint424 5 หลายเดือนก่อน +1

      😂

  • @BapiKAR
    @BapiKAR 2 ปีที่แล้ว +30

    PyTorch is what I made a transition to from Tf2.x(x>=7). So far I see it quite cool & friendly to research community. And yes, I converted my entire TF code to PyTorch in less than 2weeks.

  • @Fordance100
    @Fordance100 ปีที่แล้ว +43

    TF usually has some features 1-2 year ahead pytorch. Pytorch is more flexible for tweaking the model. TF2.4-2.6 was very buggy with strange errors that took long time to fix. That was the time I switched to mainly pytorch. I think TF is better now.

    • @StEvUgnIn
      @StEvUgnIn 6 หลายเดือนก่อน

      That pretty much sums it up

    • @sidgirase
      @sidgirase 3 หลายเดือนก่อน

      Your reply was a year ago but you seem to be very familiar with the 2 frameworks. I am starting out with one of the two. I am interested in vision based research and academia. Which one should I pick? Thanks in advance!

    • @Fordance100
      @Fordance100 3 หลายเดือนก่อน +1

      @@sidgirase Pytorch

  • @perceptron5983
    @perceptron5983 ปีที่แล้ว +14

    Both are great. TF with Keras has better performance, strong community support and robustness 👍PyTorch better for research and experimentation. Easier to use and debug since is more pythonic. Better Dynamic computation graph. Easier to deploy on web and mobile. Your choice will be determine on: use case and developer's preferences.

    • @GChief117
      @GChief117 ปีที่แล้ว +1

      I mean there are more applications with PyTorch for computer vision purposes over tensorflow

  • @ravipratapmishra7013
    @ravipratapmishra7013 8 หลายเดือนก่อน +2

    For me pytorch can give you more granular control with small learning curve, but when it comes to deplotment and documentation tf is way ahead.

  • @carlossegura403
    @carlossegura403 3 ปีที่แล้ว +81

    PyTorch’s source code is elegant and well thought out.

    • @noli-timere-crede-tantum
      @noli-timere-crede-tantum 2 ปีที่แล้ว +12

      In other words, TF's source code is complete garbage with no forethought taken? Jeff Dean just sat down one day and started typing until a framework emerged. Got it...

    • @cristian-bull
      @cristian-bull 2 ปีที่แล้ว +20

      @@noli-timere-crede-tantum Pytorch's source code is more elegant and better thought out.

    • @noli-timere-crede-tantum
      @noli-timere-crede-tantum 2 ปีที่แล้ว +2

      @@cristian-bull I'm sure you can give examples of that, as well as examples of when TF's source code lesser elegance makes it less effective at run time or solving a bug or adding features?

    • @generichuman_
      @generichuman_ 2 ปีที่แล้ว +29

      @@noli-timere-crede-tantum When someone tells you they like pepperoni pizza, do you say "oh... so what you're saying is that ham and pineapple pizza is garbage?!". No one is saying what you are accusing them of saying. Here's a better, more productive pathway. Why don't you tell us why you think tensorflow is better, instead of asking everyone else to do that for you.

    • @manny7662
      @manny7662 2 ปีที่แล้ว

      @@generichuman_ would PyTorch better for startups?

  • @abrahamsong6913
    @abrahamsong6913 8 หลายเดือนก่อน +4

    RIP tensorflow

  • @stephennfernandes
    @stephennfernandes 3 ปีที่แล้ว +22

    Pytorch Forever 🔥🔥🔥 ... I know the XLA TPU support isn't almost there yet but yeah Pytorch 🔥

    • @anmolmonga1933
      @anmolmonga1933 2 ปีที่แล้ว +2

      Using TPU very niche thought

  • @GChief117
    @GChief117 ปีที่แล้ว +5

    PyTorch has more applications over tensorflow

  • @Ikaikaalika95
    @Ikaikaalika95 2 ปีที่แล้ว +10

    pytorch is more intuitive for SWEs, tensorflow is killer now with the keras integration

  • @adityanjsg99
    @adityanjsg99 ปีที่แล้ว +2

    Tensorflow...!
    Great support, model integration and model deployment.

  • @os2002n77
    @os2002n77 ปีที่แล้ว +2

    I like calling pytorch imperative! Because it you would understand machine learning in better way! Unlike declarative approaches similar to Unix like command and SQL you give it a command or query and it would run. Even through that Tensorflow uses procedural language, coding with it similar to declaring command. And static graph structuring making it difficult especially for beginners debugging code!

  • @user-co1xw7wg6o
    @user-co1xw7wg6o หลายเดือนก่อน

    the key he is saying is which open source code is avail free for download

  •  4 หลายเดือนก่อน

    Thank you

  • @totheknee
    @totheknee ปีที่แล้ว

    More like collaboration than competition. The open source _COMMUN_-ity shows how a _commune_ environment that _shares_ resources can be so vastly superior to the capitalistic wealth redistribution scheme, it isn't even funny.

  • @ritapravadutta7939
    @ritapravadutta7939 2 ปีที่แล้ว +14

    After keras integration tf is winner

  • @qedqubit
    @qedqubit 2 ปีที่แล้ว +2

    wow 😀 ! you are diverse in your topics ! luv 'it 😘!

  • @davisonyeoguzoro9232
    @davisonyeoguzoro9232 8 หลายเดือนก่อน +1

    Now ask a Google employee the same question

  • @SubliminalJ-Official
    @SubliminalJ-Official 3 ปีที่แล้ว +26

    Tensorflow is bread and butter

  • @gorgolyt
    @gorgolyt ปีที่แล้ว +5

    Pretty useless clip tbh, all he says is "I prefer Pytorch because I've been using it for longer". He mentions that the imperative style is easier to debug, but TensorFlow 2 also uses an imperative style.

  • @tashinahmed5745
    @tashinahmed5745 3 ปีที่แล้ว +14

    doesn't answer the question at all :|

    • @noli-timere-crede-tantum
      @noli-timere-crede-tantum 2 ปีที่แล้ว +24

      I think his initial disclaimer completely disqualifies him from answering the question. If he hasn't built something meaningful in TF2, how can he make any comparisons whatsoever?

    • @chillydoog
      @chillydoog 2 ปีที่แล้ว +1

      read between the lines

    • @generichuman_
      @generichuman_ 2 ปีที่แล้ว +1

      @@noli-timere-crede-tantum Have you used Pytorch?

  • @BobF510
    @BobF510 ปีที่แล้ว

    This content is incredibly moving. I read a book with akin material that reshaped my worldview. "AWS Unleashed: Mastering Amazon Web Services for Software Engineers" by Harrison Quill

  • @MrEmbrance
    @MrEmbrance ปีที่แล้ว +4

    jax

  • @MrGeorgetudo
    @MrGeorgetudo ปีที่แล้ว +5

    WHY THE FUCK IS LEX FRIDMAN TALKING ABOUT MACHINE LEARNING

  • @AutoDidact-o9s
    @AutoDidact-o9s ปีที่แล้ว

    #throwbacksundays

  • @francismumbi49
    @francismumbi49 3 ปีที่แล้ว +15

    Interesting

  • @arods
    @arods 5 หลายเดือนก่อน +1

    Very respectfully, but it's quite hard to understand what he is telling.

  • @paveldanilov4869
    @paveldanilov4869 8 หลายเดือนก่อน

    trrrrrrrrrrrrr