New example on http://keras.io : generate faces that don't exist with this complete StyleGAN implementation -- in less than 500 lines of code. https://keras.io/examples/generative/stylegan/ …pic.twitter.com/wHfkOa0Eqs
Show this thread
-
Hello. In your opinion, when training from scratch, what is the minimum size of a dataset to train styleGAN ? (I work on monkey faces, in behavioral ecology, so transfer learning is not necessarily adapted)
You dense sampling of the latent manifold (so can do interpolation on the manifold). What "dense" means depends on the variety/complexity of your data. Monkey faces all precisely facing the camera -- I'd guess you need 5-10k images for decent results and 50k for great results.
-
-
You need a *
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
thanks a lot !
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
With StyleGAN2 ADA (https://github.com/NVlabs/stylegan2-ada-pytorch …) leveraging data augmentation you can even do it with 1k images, I tried it myself :)
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.