repology-rules VS stylegan2

A lot, it's (also) a complete linux distribution. See https://guix.gnu.org/en/packages/ and for comparison with other distros: https://repology.org/ It looks like they entered the top ten since last time I checked.

I'm having a hard time believing it, but apparently nixpkgs is larger than AUR per https://repology.org/?

Generally, the easiest thing to do is to do nothing - if your software is useful and people are using it, then packagers will show up. You can track what distros packaged your project on https://repology.org/.

I remember when the internet was smaller (20 years ago?) some people would have a comparison of different package managers for linux distros where they would dive in to examples and use. Anyway, this is a high level of package currency : https://repology.org/

The last distros I've used that didn't really have their own package managers were Slackware (it is just a tarball) and PuppyLinux (adopted from slackware or debian).

Anyway, Slitaz is here https://repology.org/repository/slitaz_cooking

You can basically install nix packages on every Linux and even MacOS. They are imo better developed and less error prone. You are guaranteed to never have dependency issues. The hashing scheme and idea of representing and building packages from derivation logic is spectacular design. The design of Nix inherently supports atomic upgrades and the likes of an immutable system. Also, afaik, it has the largest package availability currently (at least as many pkgs as Arch's) https://repology.org/

Yep, it's no. 1 on https://repology.org/

Most have it on their website, but you can also check here

I don't know. If you're really curious, you can just try it: https://github.com/NVlabs/stylegan2

StyleGAN2 (Dec 2019) - Karras et al. and Nvidia

> The denoising part of a denoising autoencoder refers to the noise applied to its input

Agree, it converts a noisy image to a denoised image. But the odd thing is, when you put a noisy image into a StyleGAN2 encoder, you get latents which the decoder will turn into a de-noised image. So in practical use, you can take a trained StyleGAN2 encoder/decoder pair and use it as if it was a denoiser.

> These differences lead to learned distributions in the latent space that are entirely different

I also agree there. The training for a denoising auto-encoder and for a GAN network is different, leading to different distributions which are sampled for generating the images. But the architecture is still very similar, meaning the limits of what can be learned should be the same.

> Beyond that the comparison just doesn't work, yes there are two networks but the discriminator doesn't play the role of the AE's encoder at all

Yes, the discriminator in a GAN won't work like an encoder. But if you look at how StyleGAN 1/2 are used in practice, people combine it with a so-called "projection", which is effectively an encoder to convert images to latents. So people use a pipeline of "image to latent encoder" + "latent to image decoder".

That whole pipeline is very similar to an auto-encoder. For example, here's an NVIDIA paper about how they round-trip from image to latent to image with StyleGAN: https://arxiv.org/abs/1912.04958 My interpretation of what they did in that paper is that they effectively trained a StyleGAN-like model with the image L2 loss typically used for training a denoising auto-encoder.

These problems are usually done with CNN Encoder-Decoder frameworks. Usually GAN (Generative Adversarial Networks see StyleGan2).

This is the result of two different models. The first looks like a latent space interpolation of StyleGan2 and the mouth movements are without a doubt from wav2lip.

OP: if you want to run this at higher resolution, you should probably look at running it yourself, using something like this: https://github.com/NVlabs/stylegan2

StyleGAN2 (Dec 2019) - Karras et al. and Nvidia

A few of you might've seen an earlier post of mine about this project (Or the repost that got more upvotes 🙃), and I've improved the code and network since then after more thoroughly reading and understanding the official StyleGAN2 implementation.

So I've been a Pro+ subscriber since around November which I mainly use to train GANs. I have multiple Google accounts, let's call them Account 1, 2, and 3. Accounts 1 and 2 are normal Google accounts and Account 3 is an account I got from my university after I graduated which has unlimited storage.