MFW when I look up from my GAN at the latest psych paper but then realize it's a Registered Report.pic.twitter.com/7jJw17Ekqk
Показване на тази нишка
-
The StyleGAN anime face interpolations are solid: - https://www.dropbox.com/s/sqt761i9o1osjxq/2019-02-11-stylegan-danbooru2017faces-interpolations-fine_503.mp4?dl=0 … - https://www.dropbox.com/s/z0iqlkj4e0nxkfc/2019-02-11-stylegan-danbooru2017faces-interpolations-coarse.mp4?dl=0 … - https://www.dropbox.com/s/ux9p9wtu88v8c4t/2019-02-11-stylegan-danbooru2017faces-interpolations-random_grid_404.mp4?dl=0 …pic.twitter.com/7T7hoCDXMg
Показване на тази нишка
-
-
Here's a more recent model: https://drive.google.com/file/d/1z8N_-xZW9AU45rHYGj1_tDHkIkbnMW-R/view … You can use it in the Colab notebook by changing the URL to 'https://drive.google.com/uc?id=1z8N_-xZW9AU45rHYGj1_tDHkIkbnMW-R …' (Google Drive direct download links are tricky to figure out...)
-
Thanks, here is 60 random samples interpolation with the more recent modelpic.twitter.com/eo1cYwBER8
- още 1 отговор
Нов разговор -
-
-
I've been looking at how to do GAN stuff for a while, but I could never understand how to get them configured. Is there a place I can go to learn how to run these types of files? I just want to run the models and possibly train them.
-
Most GANs are easy to run with commandline options. ProGAN/StyleGAN are highly unusual in that they have no CLI interface. You have to edit training/training_loop.py to change (most) hyperparameters although some are reset in http://train.py so you have to edit it too.
-
(In general, you can say that very few people would write or design the ProGAN/StyleGAN codebase the way the original researchers did...)
Край на разговора
Нов разговор -
-
-
Someone need to take a snapshot of one of the interpolation frames.
Благодаря. Twitter ще използва това, за да подобри хрониката ти. ОтмянаОтмяна
-
-
-
Someone needs to do this but taking all the samples from one key animator or character designer
Благодаря. Twitter ще използва това, за да подобри хрониката ти. ОтмянаОтмяна
-
Изглежда зареждането отнема известно време.
Twitter може да е претоварен или да изпитва моментно затруднение. Опитай отново или виж Twitter Status за повече информация.