Тёмный
No video :(

OpenAI CLIP | Machine Learning Coding Series 

Aleksa Gordić - The AI Epiphany
Подписаться 54 тыс.
Просмотров 17 тыс.
50% 1

Опубликовано:

 

29 авг 2024

Поделиться:

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист
Посмотреть позже
Комментарии : 40   
@TheAIEpiphany
@TheAIEpiphany 2 года назад
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 года назад
The best thing about this is you are really taking the time to explain the shapes which is appreciated!
@keeperofthelight9681
@keeperofthelight9681 2 года назад
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 года назад
someone give this man a nobel prize
@TheAIEpiphany
@TheAIEpiphany 2 года назад
humble
@PritishMishra
@PritishMishra 2 года назад
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 года назад
100%, CLIP is behind many of the recent interesting papers
@mikenashtech
@mikenashtech 2 года назад
Great explainer Aleska! This is going to be so useful for many. Thanks for sharing. Mike
@SinanAkkoyun
@SinanAkkoyun Год назад
Dude, I LOVE this format! Casual code AND math explanation, how awesome?!?!?!
@ahmadhamdan44
@ahmadhamdan44 2 года назад
It has been a while man! Always happy to watch your videos!
@TheAIEpiphany
@TheAIEpiphany 2 года назад
I know right! Frequency is going up now :))
@dingusagar
@dingusagar 2 года назад
thanks, these code walkthroughs are super helpful. keep doing more such videos.
@TheAIEpiphany
@TheAIEpiphany 2 года назад
Thank you!
@AZTECMAN
@AZTECMAN 2 года назад
I'm trying to contribute more to Disco Diffusion. This video is fantastic. Thank you for putting it together.
@minhajulhoque2113
@minhajulhoque2113 2 года назад
Great video! Loving these series
@keeperofthelight9681
@keeperofthelight9681 2 года назад
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 года назад
Thanks, nice feedback, if others want it upvote this comment!
@maciejbalawejder
@maciejbalawejder 2 года назад
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 года назад
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.
@vivswanshitole97
@vivswanshitole97 Год назад
1:20:25 - Its the temperature parameter (usually a tuned hyperparameter, but a learnt parameter in this case)
@pixelsandpointers
@pixelsandpointers 2 года назад
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 🥳
@haiwanwei
@haiwanwei Год назад
this vedio is so gorgeous! and it helps me a lot! Thank you so much!
@icejust9195
@icejust9195 Год назад
amazing job! Thank you!!
@vildanhuseynov6492
@vildanhuseynov6492 2 года назад
great explanation!
@bibiworm
@bibiworm 4 месяца назад
1:20:00 is there a proper explanation of why there is a logit scale factor when calculating similarity? Thanks.
@robotsai
@robotsai 2 года назад
great explanation. can you do a series on NeRF
@my_master55
@my_master55 Год назад
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 Год назад
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 Год назад
@@tahirmiriyev7003 thank you. But still, why is it exactly 77 ?
@SinanAkkoyun
@SinanAkkoyun Год назад
What does clip actually encode into the length? When normalizing, don't you lose some information?
@joegarland2224
@joegarland2224 Год назад
I'm not sure how I ended up here.. I must get back to the simple-minded RU-vid before brain explodes.. 🤯🤯
@davidro00
@davidro00 Месяц назад
2 years in, still tryin to understand that damn regex
@ahmedtech9590
@ahmedtech9590 2 года назад
I see you were watching Lawrence V Hamza Debate😉
@TheAIEpiphany
@TheAIEpiphany 2 года назад
?? 😅 What's that?
@TheAIEpiphany
@TheAIEpiphany 2 года назад
Oh hahah, just realized, my Chrome tab. I actually haven't watched it yet - just standing there lol
@ahmedtech9590
@ahmedtech9590 2 года назад
@@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
@machinelearning3518
@machinelearning3518 2 года назад
Where can I get this notebooks?
@masternobody1896
@masternobody1896 2 года назад
Brain 🧠 died
@machinelearning3518
@machinelearning3518 2 года назад
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 Год назад
Its not Jew biter note book 😂. It’s jew peter notebook 😂
Далее
This Algorithm is 1,606,240% FASTER
13:31
Просмотров 803 тыс.
How AI 'Understands' Images (CLIP) - Computerphile
18:05
OpenAI CLIP Explained | Multi-modal ML
33:33
Просмотров 22 тыс.
Why Does Diffusion Work Better than Auto-Regression?
20:18
The moment we stopped understanding AI [AlexNet]
17:38
Просмотров 979 тыс.
Why arguing generals matter for the Internet
17:42
Просмотров 16 тыс.