OpenAI CLIP | Machine Learning Coding Series

Поділитися
Вставка
  • Опубліковано 17 гру 2024

КОМЕНТАРІ • 43

  • @TheAIEpiphany
    @TheAIEpiphany  2 роки тому +11

    Super hyped about this one! Kicking off a machine learning coding series! I'll be walking through the code behind many of the papers I've covered over the last few years - starting with OpenAI's CLIP!
    Do let me know how you find this one - feedback is very much welcome! Is the code too tiny? Too many details? You love/hate the format? Whatever do let me know!

    • @PritishMishra
      @PritishMishra 2 роки тому +1

      The best thing about this is you are really taking the time to explain the shapes which is appreciated!

    • @keeperofthelight9681
      @keeperofthelight9681 2 роки тому +1

      Please do for topological graphs. Clip is easy but the hyperbolic convolution, neural sheaf diffusion and ricci flows went over my head. I only barely understood some high level concepts but like to make proper use. So if you can do coding series on that it will be uber helpful

  • @soumyadrip
    @soumyadrip 2 роки тому +11

    someone give this man a nobel prize

  • @PritishMishra
    @PritishMishra 2 роки тому +6

    This is great! With all the new fancy models I kind off felt left behind, but this is surely going to help me to learn how these models work under the hood. Thanks, and make more like this!

    • @TheAIEpiphany
      @TheAIEpiphany  2 роки тому +1

      100%, CLIP is behind many of the recent interesting papers

  • @sawantbhardwaj6111
    @sawantbhardwaj6111 2 місяці тому +1

    Thanks Aleksa for this long and well explained videos. Really helped a lot.

  • @vivswanshitole97
    @vivswanshitole97 2 роки тому

    1:20:25 - Its the temperature parameter (usually a tuned hyperparameter, but a learnt parameter in this case)

  • @fortuneolawale9113
    @fortuneolawale9113 Місяць тому

    came across this channel today! thanks a lot

  • @SinanAkkoyun
    @SinanAkkoyun Рік тому

    Dude, I LOVE this format! Casual code AND math explanation, how awesome?!?!?!

  • @mikenashtech
    @mikenashtech 2 роки тому +2

    Great explainer Aleska! This is going to be so useful for many. Thanks for sharing. Mike

  • @ahmadhamdan44
    @ahmadhamdan44 2 роки тому +1

    It has been a while man!
    Always happy to watch your videos!

    • @TheAIEpiphany
      @TheAIEpiphany  2 роки тому +1

      I know right! Frequency is going up now :))

  • @minhajulhoque2113
    @minhajulhoque2113 2 роки тому +1

    Great video! Loving these series

  • @dingusagar
    @dingusagar 2 роки тому +1

    thanks, these code walkthroughs are super helpful. keep doing more such videos.

  • @AZTECMAN
    @AZTECMAN 2 роки тому +1

    I'm trying to contribute more to Disco Diffusion.
    This video is fantastic. Thank you for putting it together.

  • @keeperofthelight9681
    @keeperofthelight9681 2 роки тому +2

    Can we have code implementation of neural sheaf diffusion, ricci flows and hyperbolic graph convolution. I was liking that flow of works…. So maybe some code demos will be very helpful to see how i can implement them

    • @TheAIEpiphany
      @TheAIEpiphany  2 роки тому +2

      Thanks, nice feedback, if others want it upvote this comment!

  • @DED_Search
    @DED_Search 7 місяців тому

    1:20:00 is there a proper explanation of why there is a logit scale factor when calculating similarity? Thanks.

  • @vildanhuseynov6492
    @vildanhuseynov6492 2 роки тому

    watch with 1.5x and in some text encoding moments think this guy is little fast,(lol) but it was great. go ahead and wait new content like this.

  • @haiwanwei
    @haiwanwei Рік тому

    this vedio is so gorgeous! and it helps me a lot! Thank you so much!

  • @icejust9195
    @icejust9195 Рік тому

    amazing job! Thank you!!

  • @maciejbalawejder
    @maciejbalawejder 2 роки тому +2

    Good content! I actually want to work on something similar🤣 When it comes to feedback, I would suggest more high-level overview of functions(maybe like a list or visualisation) and overall model structure before you dive deep into the explanation of nitty-gritty details of the code. Nevertheless, great job bud!

  • @vildanhuseynov6492
    @vildanhuseynov6492 2 роки тому

    great explanation!

  • @pixelsandpointers
    @pixelsandpointers 2 роки тому +1

    Great stuff as always! A not necessarily related question (but came to my mind after seeing you using PyTorch here): Do you have the freedom of what framework to use at work, or is DM fixed on their JAX ecosystem? Looking forward to the next episode in the series 🥳

  • @berkayates6254
    @berkayates6254 2 місяці тому +1

    Video was something great

  • @my_master55
    @my_master55 Рік тому +1

    Thanks, Aleksa 👋
    But why the size after the text encoder is always 77 ?
    Seems like we have different text lengths for imagenet prompts 😲

    • @tahirmiriyev7003
      @tahirmiriyev7003 Рік тому

      we fix the size to be 77, in order to be independent of the text lengths, so the token is going to look smth like [ # # # # 0 0 0 0 0 0 0 0 ... 0] where # correspond to text value and 0 to the empty. In short, think of texts encoded as [ word word word word word empty empty empty empty empty] --> [ # # # # # 0 0 0 0 0 0...]

    • @my_master55
      @my_master55 Рік тому

      @@tahirmiriyev7003 thank you. But still, why is it exactly 77 ?

  • @robotsai
    @robotsai 2 роки тому

    great explanation. can you do a series on NeRF

  • @joegarland2224
    @joegarland2224 2 роки тому

    I'm not sure how I ended up here.. I must get back to the simple-minded UA-cam before brain explodes.. 🤯🤯

  • @SinanAkkoyun
    @SinanAkkoyun Рік тому

    What does clip actually encode into the length? When normalizing, don't you lose some information?

  • @davidro00
    @davidro00 5 місяців тому

    2 years in, still tryin to understand that damn regex

  • @machinelearning3518
    @machinelearning3518 2 роки тому

    Where can I get this notebooks?

  • @ahmedtech9590
    @ahmedtech9590 2 роки тому

    I see you were watching Lawrence V Hamza Debate😉

    • @TheAIEpiphany
      @TheAIEpiphany  2 роки тому +1

      ?? 😅 What's that?

    • @TheAIEpiphany
      @TheAIEpiphany  2 роки тому +1

      Oh hahah, just realized, my Chrome tab. I actually haven't watched it yet - just standing there lol

    • @ahmedtech9590
      @ahmedtech9590 2 роки тому +1

      @@TheAIEpiphany 😂😂I thought you were being like sarcastic or something and just trying to hide it 😂
      Well I hope you enjoy it, it’s pretty good I think.
      Also thanks a lot for your videos, they are really helpful and inspiring , I too will soon want to make teaching videos and stuff once I get a grip on more concepts

  • @masternobody1896
    @masternobody1896 2 роки тому +2

    Brain 🧠 died

  • @machinelearning3518
    @machinelearning3518 2 роки тому

    Great Video
    I am not able to join the Discord Channel
    Actually my account was hacked by my frnd and he spammed some channel
    Did you block me for this? Plz un-block?
    Thanks

  • @productknowledgebot6561
    @productknowledgebot6561 2 роки тому

    Its not Jew biter note book 😂. It’s jew peter notebook 😂