Étiquette : generative adversarial networks

“We propose an alternative generator architecture for generative adversarial networks, borrowing from style transfer literature. The new architecture leads to an automatically learned, unsupervised separation of high-level attributes (e.g., pose and identity when trained on human faces) and stochastic variation in the generated images (e.g., freckles, hair), and it enables intuitive, scale-specific control of the synthesis. The new generator improves the state-of-the-art in terms of traditional distribution quality metrics, leads to demonstrably better interpolation properties, and also better disentangles the latent factors of variation. To quantify interpolation quality and disentanglement, we propose two new, automated methods that are applicable to any generator architecture. Finally, we introduce a new, highly varied and high-quality dataset of human faces.”

via Tero Karras FI (YouTube)

GitHub – robbiebarrat/art-DCGAN

GAN Art from Barrat

“Modified implementation of DCGAN focused on generative art. Includes pre-trained models for landscapes, nude-portraits, and others”.

Source : GitHub – robbiebarrat/art-DCGAN

Obvious Art

“The members of Obvious don’t deny that they borrowed substantially from Barrat’s code, but until recently, they didn’t publicize that fact either. This has created unease for some members of the AI art community, which is open and collaborative and taking its first steps into mainstream attention. Seeing an AI portrait on sale at Christie’s is a milestone that elevates the entire community, but has this event been hijacked by outsiders?”

Source : How three French students used borrowed code to put the first AI portrait in Christie’s – The Verge

these images took about 18 days for the computers to generate

«Each of these images took about 18 days for the computers to generate, before reaching a point that the system found them believable»

Source : How an A.I. ‘Cat-and-Mouse Game’ Generates Believable Fake Photos – The New York Times

«Goodfellow’s friends were just as adamant that this method wouldn’t work, either. So when he got home that night, he built the thing. « I went home still a little bit drunk. And my girlfriend had already gone to sleep. And I was sitting there thinking: ‘My friends at the bar are wrong!' » he remembers. « I stayed up and coded GANs on my laptop. » The way he tells it, the code worked on the first try. « That was really, really lucky, » he says, « because if it hadn’t of worked, I might have given up on the idea. »»

Source : Google’s Dueling Neural Networks Spar to Get Smarter, No Humans Required | WIRED

© 2020 no-Flux

Theme by Anders NorenUp ↑