Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

This person does not exist

thispersondoesnotexist.com

Post reply on HN
Print view View original

121–130 of 185 posts

Re: This person does not exist

#121

Post by 6gvONxR4sf7o »

lsb wrote: post #9
jonplackett wrote: post #2

I have a question - When generating a new person (or whatever it is that does not exist) can you know that it isn’t like any of the images that went into the training data set? How likely is it for it to actually exist after all?

The model has 18x512 parameters, and all 9000 parameters are 32-bit floats. Even assuming only 16 bits of randomness for each parameter (to keep them small enough, so you don't get too wild, because the center of 0 is a pretty homogenized face), 16^9000 is a lot of permuations of faces. They will, of course, borrow from all of the 70k faces on Flickr that power StyleGAN, in varying degrees.

You could use this argument to say that GANs can't overfit if you provide them, say, 16 bits of randomness per parameter, which is patently not true.

Re: This person does not exist

#122

Post by gwern »

beefield wrote: post #36

Now, the next obvious question is, how do you pick one of these non-existing persons and generate images of him/her doing different things in different places? (Or, of course, real persons. Is there a service where I can upload my photo and it starts to generate images of me doing random - or not so random - things?)

You can reverse-engineer faces into the original random seed/embedding, and then tweak the embedding to 'edit' the face. (There are a bunch of tools and Colab notebooks for that, but the best tool is definitely Artbreeder, which does a lot of other GAN models too: https://artbreeder.com/ )

However, since the model only does faces centered in an image, you're restricted to different headshots: make them smile or frown, or wearing sunglasses, or different hair color, or animate lip flaps, yes, but not 'doing different things in different places', unless you can figure out some way to insert a headshot into a bigger photo.

Re: This person does not exist

#124

Post by pier25 »

hnuser123456 wrote: post #16
ackshually wrote: post #12

There was a pic of an older guy, but what was unsettling was the woman peeking over his shoulder; like a friend or a family member, leaning into the photo. Her eyes were melting into black and white streaks curling down over her sagging cheeks; her smile was perfectly white, and just a little too long. I refreshed on instinct, and haven't seen anything like it since.

https://i.imgur.com/RmSEnaT.jpg https://i.imgur.com/RhROFSf.jpg https://i.imgur.com/NTC2ZiN.jpg

Also this guy's hair: https://imgur.com/WbvCMin.jpg

Re: This person does not exist

#125

Post by lostinroutine »

bentcorner wrote: post #108
tomrod wrote: post #71

So, the specific person may not exist, but likely someone very, very similar in appearance does. I've come across people in life that I would have sworn were twins. I'm curious how combinatorically low the number of facial features need to be before people resemble one another.

On a similar tangent, privacy issues aside it would be fun to see if you had an unknown twin on social media. Upload your picture, see if there's other pictures that look like you but have a completely different friend graph.

Such service used to exist: FindFace. It was essentially for finding people's VK accounts having only their photo, but finding people who look like you was one of the popular use cases. It was since closed (kinda) due to privacy outrages.

A similar one called FindClone has recently appeared, though I haven't tried it.

Re: This person does not exist

#126

Post by stronglikedan »

martin_a wrote: post #106
tomrod wrote: post #71

So, the specific person may not exist, but likely someone very, very similar in appearance does. I've come across people in life that I would have sworn were twins. I'm curious how combinatorically low the number of facial features need to be before people resemble one another.

> I've come across people in life that I would have sworn were twins. Like some kind of dejavu?

doppelgangers

Re: This person does not exist

#127

Post by poizan42 »

RodgerTheGreat wrote: post #70

It has been interesting to see images clearly generated by this service (same artefacts, same resolution) start to flood online dating apps and social media profiles. Previously, fake accounts tended to use photos which could be reverse-image-searched to detect them. Luckily, it doesn't seem that this approach can be sensibly extended to generate entire scenes, or multiple entire-body photos from different angles. Be…

> see https://www.thiscatdoesnotexist.com for example.

That site is straight up nightmare fuel:

https://i.imgur.com/0lg9eNK.jpg

https://i.imgur.com/AL96Pvv.png

https://i.imgur.com/6s91BaD.png

https://i.imgur.com/NK8J35b.png

https://i.imgur.com/4lEdPOH.png

Re: This person does not exist

#128

Post by iamnothere »

OscarCunningham wrote: post #88
goodside wrote: post #81

Earlier quoted context omitted.

The training data contains examples of very dark skin: https://github.com/NVlabs/ffhq-dataset/blob/master/ffhq-teas...

Interesting. I just refreshed the site 100 times to get a large sample size and the darkest skinned image it produced was this girl ( https://i.imgur.com/ggJIG94.png ). Her skin is much lighter than many of the people in that sample of the training data. Assuming that that sample is representative of all the training data, it must be that the algorithm is 'choosing' not to produce images of dark skinned people. Perha…

> Assuming that that sample is representative of all the training data, it must be that the algorithm is 'choosing' not to produce images of dark skinned people. Perhaps because it isn't very good at them and 'knows' this? I wonder if there are other features it's deliberately avoiding?

An algorithm would not have this kind of insight. (This is just a GAN trained on face data.) To say that an algorithm like this is "deliberately" doing anything is a misunderstanding.

Most generators like this that I've seen, like GPT-2, require you to provide a "seed" of some sort, such as a sentence fragment. They then build off of this seed. I don't know if this is implemented that way, but if so, perhaps the developer provided a set of seed data that leads to this result. There may also be a sort of "averaging" involved (see another commenter's note about the women having similar features), and depending on both the training data and the seed, this may result in a preference towards certain features.

Edit: it's StyleGAN.

Re: This person does not exist

#129

Post by Balgair »

umvi wrote: post #69
angrygoat wrote: post #42

Here’s the Guardian article which linked the site: https://www.theguardian.com/culture/2020/feb/07/ai-in-the-ad... To my mind there is a massive need for us in the software world to pause and think about the ethics of all of this. Engineers more broadly have well developed ethical codes, we should too.

So are you saying software developers should have to take the equivalent of a Bar exam in order to practice software development in a given state? That way ethical code violations have teeth because you can be debarred. As of now anyone and their dog can practice software development and I'm not sure what a nebulous "ethical code" would imply for them.

Probably something more like a PE. From the NSPE website a PE entails:

"To become licensed, engineers must complete a four-year college degree, work under a Professional Engineer for at least four years, pass two intensive competency exams and earn a license from their state's licensure board. Then, to retain their licenses, PEs must continually maintain and improve their skills throughout their careers."

Most PEs that I have worked with are very diligent. You don't get yahoos going that far. Generally, they are top-notch engineers. Think '10X' engineers, but for oil wells and churches. I mean, look at any large structure on Wikipedia, most of the time you'll find the engineer's name in the side placard, not just the firm's name. PEs are serious, dedicated, and smart people. I mean, their stamp is on those documents and they go to jail when the bridge fails.

So, for software, if you have an exam of the PE's caliber, you essentially guarantee '10X' engineers. The workforce is more highly paid, yes, but it is of a much higher quality. Bugs get solved faster, stand-ups don't last 30 minutes, the wiki is updated by everyone, etc. Employers know that their candidates really are good stuff, less whiteboards or take-homes are needed. Also, possibly when something messes up, the engineer is the one responsible, not the company. So offloading the insurance to the employees is not the worst thing for a company.

Honestly, it would not be a bad system and I think would be a much calmer and better one.

Post reply on HN