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

Alias-Free GAN

nvlabs.github.io

Post reply on HN
Print view View original

41–50 of 83 posts

Re: Alias-Free GAN

#41

Post by varispeed »

ansk wrote: post #24
sillysaurusx wrote: post #21

Earlier quoted context omitted.

This isn't true. I do ML every day. You are mistaken. I click the website. I search "model". I see two results. Oh no, that means no download link to model. I go to the github. Maybe model download link is there. I see zero code : https://github.com/NVlabs/alias-free-gan Zero code. Zero model. You, and everyone like you, who are gushing with praise and hypnotized by pretty images and a nice-looking pdf, are doing dam…

You're clearly disillusioned with the general accessibility of ML research, but I don't think your cynicism is warranted here. Take a look at their prior works[1], and I think you'll agree they go above and beyond in making their work accessible and reproducible. There is no reason to doubt the open-source release of this work will be any different. As to why the release is delayed, I'd speculate it's because they pu…

When I was writing a paper I had to include all source code in a state to be published, otherwise it wouldn't be accepted. I guess today the bar is much lower.

Re: Alias-Free GAN

#44

Post by xwolfi »

phreeza wrote: post #26
sillysaurusx wrote: post #25

Earlier quoted context omitted.

There is no reason to doubt the open-source release of this work will be any different. Then this is not a scientific contribution yet. We must wait and see. The most important tenet of science, is to doubt. I didn’t even read the name on the paper before I wrote my comment. Yes, I know this group. They’re why I got into ML, along with the group from OpenAI who published GPT-2. Because A+ science. Their claims here a…

Expecting fully executable code to accompany every publication is kind of unique to the modern ML research Scene. As someone from a very different computational research field, where zero code is the norm, not the exception, this reads as a somewhat entitled rant. Reimplementation of a paper is actually a test of the robustness of the results. If you download the code of a previous paper, there may be some assumption…

Yeah but look at the first comment which said the opposite of what you say is normal. The first comment was praising the fact the code was published, the second that no it's not, followed by an autistic rant.

To his defense, the spirit of his rant was valid, the letter made it sound entitled.

Re: Alias-Free GAN

#45

Post by cout »

sbierwagen wrote: post #16
tyingq wrote: post #4

Earlier quoted context omitted.

>I couldn't image what improvements could be made over it Still has the telltale of mismatched ears and/or earrings. This seems the most reliable way to recognize them. Well, and the nondescript background.

Teeth too. Partially covered objects in 3D space have been hard for a GAN to figure out. (See also hands) I wonder what dataset you could even use to tell a GAN about human internals. 3D renders of a skull with various layers removed?

I've noticed the same thing with ESRGAN -- teeth are always awful. I'm looking forward to the day when someone figured out how to fix that; I have a few sentimental images taken with a cell phone I would love to see upscaled and cleaned up.

Re: Alias-Free GAN

#46

Post by xwolfi »

aaron-santos wrote: post #31
sillysaurusx wrote: post #23

Earlier quoted context omitted.

Unfortunately, I must call you out too, my friend. With love. Because it’s crucially important that we protect the scientific method here. The sole goal is to help people like me reproduce the model. If I can’t reproduce the model, I can’t verify the paper. When I saw “commercial” and then “open source” in your comment, I said “oh no…” My duty is to the scientific method, so I don’t care if it’s the most restrictive…

That's fine, at least you're open about the knowledge for knowledge's sake position. There's more than one way to judge something.

It's more than that. Here there's a fake demo we can only consider an advertisement. If they wanted it to be a scientific paper it should be reproducible and counter checked. What is the point of making a paper full of screenshot ?

It's not just a knowledge for knowledge's sake issue here, it's that it's not even knowledge they're publishing. They're publishing nothing.

They would make a license that says the code can only be provided for peer review and counter validation, then that'd be knowledge. Then, the sake of it is another secondary problem.

Re: Alias-Free GAN

#47

Post by godelski »

sillysaurusx wrote: post #21
ansk wrote: post #12

This group of researchers consistently demonstrates a degree of empirical rigor that is unmatched across any other ML lab in industry or academia - remarkable empirical results as always, reproducible experiments, open-source and well-engineered codebase, and valuable insights about low-level learning dynamics and high-level emergent artifacts. Applied ML wouldn't have such a bad rap if more researchers held themselv…

This isn't true. I do ML every day. You are mistaken. I click the website. I search "model". I see two results. Oh no, that means no download link to model. I go to the github. Maybe model download link is there. I see zero code : https://github.com/NVlabs/alias-free-gan Zero code. Zero model. You, and everyone like you, who are gushing with praise and hypnotized by pretty images and a nice-looking pdf, are doing dam…

> I do ML every day.

> I go to the github. Maybe model download link is there. I see zero code

Paper was released today. Chill. They said they will release the code in September (I'm guessing late September). The paper is also a pre-print. They're probably aiming for CVPR and don't want to get scooped.

> Model first. Code second. Paper third.

That's how you produce ML code and documentation but that is not how you release it. I guarantee you that they are still tuning and making the model better. They're were still updating ADA till pretty recently (last commit on the pytorch version is 4 months ago, to code).

I originally wasn't in CS, and when I first came over I wasn't in ML. We never had code. The fact that ML publishes models AND checkpoints is a godsend. I love it. Makes work so much easier and helps the community advance faster. I love this, but just chill. The paper isn't peer-reviewed. It is a pre-print. They're showing people what they've done in the last 6 months. It's part publicity stunt, part flex, part staking claim, but it is also part sharing with the community. Even without the code we learn a lot because they attached a paper to it. So chill.

Re: Alias-Free GAN

#48

Post by pabs3 »

sillysaurusx wrote: post #21
ansk wrote: post #12

This group of researchers consistently demonstrates a degree of empirical rigor that is unmatched across any other ML lab in industry or academia - remarkable empirical results as always, reproducible experiments, open-source and well-engineered codebase, and valuable insights about low-level learning dynamics and high-level emergent artifacts. Applied ML wouldn't have such a bad rap if more researchers held themselv…

This isn't true. I do ML every day. You are mistaken. I click the website. I search "model". I see two results. Oh no, that means no download link to model. I go to the github. Maybe model download link is there. I see zero code : https://github.com/NVlabs/alias-free-gan Zero code. Zero model. You, and everyone like you, who are gushing with praise and hypnotized by pretty images and a nice-looking pdf, are doing dam…

Would you not want the data and code used to train the model, rather than the trained model itself?

Edit: the Debian Deep Learning Team's Machine Learning Policy explains why.

https://salsa.debian.org/deeplearning-team/ml-policy

Re: Alias-Free GAN

#49

Post by sillysaurusx »

godelski wrote: post #47
sillysaurusx wrote: post #21

Earlier quoted context omitted.

This isn't true. I do ML every day. You are mistaken. I click the website. I search "model". I see two results. Oh no, that means no download link to model. I go to the github. Maybe model download link is there. I see zero code : https://github.com/NVlabs/alias-free-gan Zero code. Zero model. You, and everyone like you, who are gushing with praise and hypnotized by pretty images and a nice-looking pdf, are doing dam…

> I do ML every day. > I go to the github. Maybe model download link is there. I see zero code Paper was released today. Chill. They said they will release the code in September (I'm guessing late September). The paper is also a pre-print. They're probably aiming for CVPR and don't want to get scooped. > Model first. Code second. Paper third. That's how you produce ML code and documentation but that is not how you re…

The fact that you had to say "chill" three times indicates that you're trying to convince yourself, not me.

None of what you said is responsive to what I wrote. I think it's an opinion piece, but I'm not sure.

The issue here is the scientific method. I've listed the things that are required, as I see it. And I've also listed the reasons why I haven't been able to verify it exists here, despite trying for two years.

I'm glad that you like ML hacking, and I like it too. But models aren't a godsend; they're "the most basic, bare-minimum requirements of reproducibility."

Your reaction shouldn't be "I'm incredibly grateful you'd be willing to do this." It should be "You're required to do this, because if I can't verify your claims, your claims might be mistaken."

To leave it off on a softer note, normally I'd bond with you, ML hacker to ML hacker. Because I love ML, and I love hearing what you've been up to in ML. It's the best job in the world, as far as I'm concerned. (Could any other career give you the opportunity to be a developer advocate for high-performance computing in such an interesting way? https://github.com/google/jax/issues/2108#issuecomment-86623... Definitely looking for more examples of "Github Larping," if you know of any.)

If you agree that the scientific method is the reason ML moves forward, all I'm doing here is protecting it.

Re: Alias-Free GAN

#50

Post by sillysaurusx »

pabs3 wrote: post #48
sillysaurusx wrote: post #21

Earlier quoted context omitted.

This isn't true. I do ML every day. You are mistaken. I click the website. I search "model". I see two results. Oh no, that means no download link to model. I go to the github. Maybe model download link is there. I see zero code : https://github.com/NVlabs/alias-free-gan Zero code. Zero model. You, and everyone like you, who are gushing with praise and hypnotized by pretty images and a nice-looking pdf, are doing dam…

Would you not want the data and code used to train the model, rather than the trained model itself? Edit: the Debian Deep Learning Team's Machine Learning Policy explains why. https://salsa.debian.org/deeplearning-team/ml-policy

For various reasons, I left data out of the requirements because most interesting research uses data unavailable to the community. CLIP is such an example, and it's A+ science: Model, Code, Paper.

Having the model is enough to verify the paper's claims, and also to experiment with new approaches (since you can fine-tune the model).

That said, I make this concession as a "meet you halfway" compromise between hard-line positions: "We can't release models, because we trained them on private data" and "You must release both models and data."

In other words, you're technically correct, but in my estimation it would do more harm to the end goal: the whole reason the scientific method is useful, is because it makes the world more useful.

The world would be less useful if fewer commercial companies participated in the scientific method. It's an inclusive group, not an exclusive clique. All you have to do, is give me the tools to verify your claims.

Post reply on HN