Tag: gan

StyleGAN trained on paintings (512x512) https://t.co/xHoDbQ4ctm pic.twitter.com/2NhQABT1rA

— hardmaru (@hardmaru) April 8, 2019

Progress towards stable and scalable training of energy-based models:
💻Blog: https://t.co/gMo8g5sctT
📝Paper: https://t.co/F9UlHf8JzI
🔤Code: https://t.co/WGIOX4OKxZ pic.twitter.com/6TaoNQtljZ

— OpenAI (@OpenAI) March 21, 2019

Should be super easy to install & use (see the image above)
👉 pip install pytorch-pretrained-biggan
👉 https://t.co/L2RGZUWeIc

Implemented from the raw computational graph of the TF Hub module. Pretrained weights are the ones pre-trained by @ajmooch at DeepMind. Thanks Andrew!

— Thomas Wolf (@Thom_Wolf) March 21, 2019

I needed a good GAN to tweak for a CV+NLP project so here is a *pretrained* version of BigGAN in PyTorch

Sweet stuff:
-AFAIK code is not public yet so here is an op-for-op implem to read/tweak
-Checkpoints 2x smaller (no dead vars)
-Print images in terminal (icing on the cake)👇 pic.twitter.com/GbE7cDfVcX

— Thomas Wolf (@Thom_Wolf) March 21, 2019

https://t.co/pwPvR22Ynp

— Ian Goodfellow (@goodfellow_ian) March 21, 2019

Great work from Brain ZRH team on putting label-hungry GANs on a diet :)

Want to train similar GANs easily? Check out the new release of our compare_gan library! https://t.co/iwnSqznb3J https://t.co/3Xl59GFc1A

— Karol Kurach (@karol_kurach) March 20, 2019

No GAN is complete without Ramen 🍜 https://t.co/w0M38XsAR5

— hardmaru (@hardmaru) March 5, 2019

Several samples from @nvidia's Style-Based GAN generator in real-time: https://t.co/IjijwZK4m3

📰: https://t.co/SCvD1QYwaU pic.twitter.com/YN3vIxevFQ

— 👩‍💻 DynamicWebPaige 🔜 GDG SV DevFest (@DynamicWebPaige) February 14, 2019

Pretty cool how StyleGAN can generate entire fonts in one shot. https://t.co/Jiv0eY0E7I

— hardmaru (@hardmaru) February 13, 2019

NVIDIA's StyleGAN implementation just open-sourced. Very cool stuff, please use responsibly! https://t.co/9P83Ohzf1d

— Eric Jang (@ericjang11) February 6, 2019

A new Gandreeder is live at https://t.co/MNoegnCLv7 ! Higher resolution, built in 1024px upscaling, user accounts, plenty of UI improvements and still free to use! Thanks everyone for the feedback. Enjoy :) pic.twitter.com/1CCMJS2Z7z

— Joel Simon (@_joelsimon) January 26, 2019

Excellent thread about GAN progress, read! 👇 https://t.co/rKRVWbytcX

— Denny Britz (@dennybritz) January 18, 2019