Editing Faces using Artificial Intelligence
Ғылым және технология
Link to Notebooks:
drive.google.com/open?id=1LBW...
Link to the StyleGAN paper: arxiv.org/abs/1812.04948
Link to GAN blogpost: hunterheidenreich.com/blog/gan...
If you want to support this channel, here is my patreon link:
/ arxivinsights --- You are amazing!! ;)
If you have questions you would like to discuss with me personally, you can book a 1-on-1 video call through Pensight: pensight.com/x/xander-steenbr...
--------------------------------
This episode covers one of the greatest ideas in Deep Learning of the past couple of years: Generative Adversarial Networks.
I first explain how a generative adversarial network (GAN) really works. After this general overview, we go into the specific objective function that is optimized during training. We then dive into Nvidia's StyleGAN model and learn how we can manipulate it's latent space to morph arbitrary images of faces.
This video comes with a complete Google Colab notebook to reproduce & play with all the examples shown in the video!
::Chapters::
00:00 Intro
02:55 Video overview
03:35 Introduction to GANs
05:40 5 min Deepdive on the Training Objective for GANs
10:07 State-of-the-art GAN techniques: StyleGAN
14:40 Manipulating the latent space of GANs
Пікірлер: 428
Why do we not get people like that in college? I just had a 2 period course about _basic_ ML techniques (linear and logistic regression, classification and basic concepts like features, labels and hypothesis space) that took 2 hours to introduce each concept and then 10+ hours of self-study, most of which was spent ploughing through insane math jargon to realize just how unnecessary it is to explain the relatively simple concepts underneath. This is 100 times more complicated and the guy just explained the whole thing in 25 minutes and I have no questions! Bravo to him, this is why online education is replacing universities. Good teachers get a chance to reach people through platforms like this.
@ugestacoolie5998
4 ай бұрын
I know right, overcomplicating things so much, and justify in their defense that it's only "rigour" to learn this way
I swear some college professors spends a year of lectures to convey the same amount of information that this video does in 25 mins
@ReaperOnRepo
3 жыл бұрын
Or maybe it's because you don't pay attention bro lmao
@ugestacoolie5998
4 ай бұрын
or maybe the prof just sucks? Both ways@@ReaperOnRepo
I miss your videos. Your channel is definitely the single best ML youtube channel I've seen. And that, by very far. Please tell us you're alive and that you'll do more videos. We miss you.
Really impressive presentation and storytelling!
@kwea123
4 жыл бұрын
the creepy thing is, you can now find a latent code of your own face, then generate a true alter ego!
@pixel7038
4 жыл бұрын
I love your weekly updates in A.I. Henry
@connorshorten6311
4 жыл бұрын
@@pixel7038 Thank you so much!!
@milyreina204
4 жыл бұрын
@@connorshorten6311 Hey i have a question: where can i get GAN? Is it a page or something? I don't get it 😭
@milyreina204
4 жыл бұрын
@@kwea123 Hey i have a question: where can i get GAN? Is it a page or something? I don't get it 😭
So happy to see you're back! I needed a styleGAN video so much. Thank you for your great job, keep doing this!
WOW!! That was simply excellent!!! That has to be one of the best videos on GAN's I have seen yet. Please continue doing more of these videos (with a notebook) - that is just outstanding work.
You solved in 20 minutes problems and questions I was trying to find out in weeks. Thank you.
@milyreina204
4 жыл бұрын
Hey i have a question: where can i get GAN? Is it a page or something? I don't get it 😭
Fantastic explanation and presentation. I have been learning GANs for a few days and your video is by far the best resource I have found. Keep the hard work and the good content come in. Thank you!
Extremely well explained where a beginner can easily get a gist of GANs and its overview. This channel is so useful who tries to read and understand ideas through papers and finds difficult to catch up to the complexity explained
It was really great. You had done really an awesome job clarifying the issues after reading the original papers. Really a great fan. Hats off to you.
This guy explains the concepts correctly. There are a lot of channels here on youtube that explain a paper based on their speculations and not facts or the information presented in the paper. You get my sub :)
With the first-ever video I watched on this channel it took second place in my favorite channels list, just after the TwoMinutePapers. And boy the placement may change any moment. I cannot make a list of things done very good in this video. Thank you for the work.
Hands down the best GANs video I've seen on KZread so far!
I m glad that KZread suggested me this channel,there are very few channels having quality content on these topics and this is the best
These videos are gold. Cleanly explained, let me grasp the concept even if i am an entusiast (and not an expert on the field).
Well done! Clear and informative! So far the best DL channel I know
Incredible video, Xander!! Thanks so much for this. GANs are one of the most interesting topics in ML and AI at the moment. This is definitely one of the best, if not the best, video on GANs I've seen. And thanks for providing the notebook. I'm sure I will have a lot of fun messing around with it :)
Very good work! The notebook to play/learn with is an awesome idea. Thanks!
Your presentation style was superb. It made a complex topic more understandable. Thank you.
Great that your are back Xander ! Keep doing your videos, they are awesome !
A fantastic talk about GAN. A lot of ideas are incorporated. I get a great brainstorming as I watch this video
I've watch all the videos you have posted, and it was amazing. I hope you guys can bring more exciting videos : )
This channel is so good! Thanks for sharing your code. I am excited to dive in and play with it.
Thank you! Im new to GAN's but the explanation was so intuitive and clear! Kudos and keep up the good work mate!
Very impressive, this gives a really good insight & intuition into GANs. Thanks & also thanks to Ian Goodfellow and everyone who has in one way or another contributed POSITIVELY to this powerful Innovation.
This is a beautiful explanation of GANs! Amazing work!
Superb - lucid, comprehensive, well-paced, and designed to for human beings, unlike so much material in this space!
This channel is criminally under subscribed. Keep up the good work!
this is the most amazing thing I've seen on KZread!
I've seen other video explanations of this, but they were not clear at all, expecially for people outside the deep learning environment, this was so well explained that made me make a good leap in understanding the whole process. Even the notebooks are so well curated on the accompanying informations that makes those notebooks important to keep safe. Great job, and keep it up.
One of the best explanation of gans. The way you presented it was awesome.
The most useful channel I've even seen. You should start your Patreon page. Please keep doing what you are doing.
Wonderful presentation! Looking forward to your other videos!
Fantastic work and clear exposition. Very close to what I wish I could do. Thanks.
Best video on GAN & StyleGAN! You should do those more often. And I hope to see one on StyleGAN2. With such a high quality videos you should consider making an online course or something so we can help sponsor your work and creation of more videos.
thank you so much for this video. i struggled to understand GANs as someone with no background in AI but your video simplified it for me.
Highly motivational presentation. Deserves a lot more attention. Subbed and followed you on Twitter.
What a brillant video! Thanks a ton, I finally understood why the mapping network is needed and how we find the latent vector for an image :)
You are simply Great !! Thanks for such nice video on the GAN topic
props for good notes and some humor in your notebooks. awesome
It's an in-depth video, but it feels casual. It's technical, but it feels fun. It's 25 minutes but it feels short. Marvelous!
From the first insight, really impressed. Thank you!
Hey, it's amazing. Your video totally sums up the paper. Keep posting more videos. Your explanations are far far better than siraj.
One of the best KZread channels. Is it possible for you to do a detailed hands on course for GAN???
Best video I have watched about GAN. Great job!
For some reason I previously thought that there wasn't a latent vector for most REAL images (Think: partial mode collapse). But now you show me that even cars and others stuff are possible! Brilliant video! Btw: Wouldn't getting the latent vector be much easier if you used VQ-VAE instead of the GAN, since VAE's provide an encoder? VQ-VAE generated images are pretty close in quality to GANs.
Perfect KZread channel doesn't exis...
@pooorman-diy1104
4 жыл бұрын
and.somewhere inside the latent space ... there is ''coordinates'' where psychopaths and serial killers are located ... who knows..
@dayhookah
4 жыл бұрын
How is this not the top KZread comment of all time??
@meowzerzzz
4 жыл бұрын
Anyone else looking at people that can't get the corona virus at the website before they came here?
@vsiegel
4 жыл бұрын
@@dayhookah Because the comment rating is part of the channel, it does not exist!
It looks like a movie. :) Thanks a lot, you saved a lot of time for me to understand the actual paper. Now I can understand it easily and faster. Good presentation.
Your presentation skill is outstanding, thank you so much sir :)
cant find any better explaination that this. Thanks a lot for all the efforts.
excellent presentation Arxiv Insights. Thank you very much.
2:14 you don't have to make Emilia Clark smile... She is always smiling...
@ErdTirdMans
4 жыл бұрын
Truth
one of the most informative GAN videos I've seen
Awesome presentation, thanks a lot! Very helpful to get a better understanding.
men love your videos, you disappeared a long time ago, thanks for coming back
The efficiency of this video has gone through the roof!!!
Wow, excelent video! You explain very clearly the concepts!
I've always been a fan of Autoencoders over GANs because of all the control you get with autoencoders, but damn it appears GANs have came a long way since I last checked up on the. Amazing video Xander!
@thatscienceguy5824
4 жыл бұрын
Mah boi @Jabrils!
@karlkastor
4 жыл бұрын
VQ-VAE for the win!
@superaluis
3 жыл бұрын
There's a new autoencoder paper that leverages these ideas from StyleGan on CVPR 2020, its called Adversarial Latent autoencoders. Pretty cool Idea too
@bahaatamer1245
3 жыл бұрын
I literally wrote an AutoEncoder (with a precision error of +- 0.95) ONCE, and now it's popping up everywhere!
Thanks a lot man, esp for the notebooks. Great work!
Excellent video, congrats Xander!
Excelent presentation, very intuitive explanations, completed by ready to play code, pre-optimized and trained? 🤯
i can not convey how i adore your diamond cellar channel
great video! thanks. However when running notebook II I get an error because of the tensorflow version required (1.12.2). It seems like colab made some changes recently. Do you have a fix to this?
This video is super freaking AWESOME! Very clearly explained.
Beautifully explained, you removed a lot of the uncertainty I had whilst reading the paper and have made it far easier for me to begin implementing myself!
Neat and clear as crystal. Well done!
HI Xander! You explained every complicated concept beautifully. I bet you spent a lot of time in preparations of this video. Perhaps we need another GAN to help us generate the videos that we create like this one :)
Glad to see you back!
Very nicely explained..............especially for someone who starts it afresh
Wonderful explanation! Thank you very much for such an interesting video!
Beautiful explanations! This channel is like a needle in a haystack
@milyreina204
4 жыл бұрын
Hey i have a question: where can i get GAN? Is it a page or something? I don't get it 😭
@uddhavdave908
4 жыл бұрын
@@milyreina204 GAN as the name suggest is a neural net. you can get the code on GitHUB or kaggle but depends on your use case.
@milyreina204
4 жыл бұрын
@@uddhavdave908 i still don't get it, i just want to create faces for fun 😭😂
Very clear and precise explanation, Thanks!
Really well explained! Amazing video.
Thank you for the course, it was very interesting!
Incredible starting point for paper. U r amazing
Thanks for those video, they're always interesting.
Thanks for the video, very well explained. How can I be sure that I am getting decent results (not distorted faces) when I move through that normal of the hyperplane (for example doing the male-female conversion)? Also how can I avoid that the transformation lose initial important attributes as the shape of the nose, lips and get a complete different face that does not resemble at all with the initial one?
Just discovered this channel and it's a huge shame you aren't uploading anymore, hope you come back soon. Really great content.
Another amazing video ... thanks ... any chance of some new videos coming out on recent papers?
wow !! what a content... and such an easily understandable pictorial way of explaination..
Burh are you god how did you explain it so simply... great job keep it up :D
Exceptional video. Well done.
Really nice video - thanks! As GANs for tabular data are getting more attention, would you consider covering this topic as well?
Found this treasure! Really really really helpful and impressive!
Fantastic presentation indeed
Dude, do you have a Pateon? Your videos are so good we, need more of them.
Amazing Explanation !!
Great video. The most interesting video on GAN. I am just wondering, when train the GAN, instead of using a random seed, can we predefined a coordinate of certain properties. Hence in the end, we don’t need to find that feature direction in the latent space, as we have defined that at the first place.
Love your videos - Please make more
Awesome video please make a complete course on GANs if possible
ERROR: Could not find a version that satisfies the requirement tensorflow-gpu==1.12.2, as your notebook works on this tensorflow version, but this version is outdated and not available now. What to do in this case?
I'm glad I clicked [2] on thispersondoesnotexist.com because [1] is complete gibberish to me. This video is very clear and easy to understand and you speak at an easy to understand pace. Thank you for making this.
really (really) well done! thanks!
I was so excited to try out 2. Face Editing Notebook (with pretrained networks), so I could prepare this as a project for my high school class next year. BUT it failed at the point of installing/downgradng to TFv1.12.2 and CUDA 9.0. Apparently Colab is default TFv15 now, and the oldest tensorflow-gpu its pip can see is 13.1. If you could update the notebooks, it would be so awesome!
You should make a video that covers how an app called Remini upscales faces. I think it uses some type of Stylegan or Cyclegan to do so.
You really need to post more content. One video in 6 months is too less for such amazing content.
Excellent explanation
Been following your channel since the Variational Auto Encoders, is an actual treat to watch such educating content for free particularly for students like me.
Great work guys
Goed uitgelegd, fijne video man!