Counting 3,742 Big Data & Machine Learning Frameworks, Toolsets, and Examples...
Suggestion? Feedback? Tweet @stkim1

Last Commit
Apr. 20, 2019
Mar. 29, 2019


StyleGAN made with Keras (without growth)

alt text A set of 256x256 samples trained for 1 million steps with a batch size of 4.

alt text Rows: 4^2 to 32^2 styles Columns: 32^2 to 256^2 styles

This GAN is based off this paper:

"A Style-Based Generator Architecture for Generative Adversarial Networks"

Additionally, in, you will find code for Spatially Adaptive Denormalization (a.k.a SPADE) This is adapted (as best as I can) from this paper:

"Semantic Image Synthesis with Spatially-Adaptive Normalization"

This StyleGAN is missing growth. Feel free to contribute this, if you'd like!

Mixing regularities is left out in, but included in It complicates the inputs of the generator.

To train this on your own dataset, adjust lines 10 to 15 respectively, and load your own images into the /data/ folder under the naming convention 'im (n).suffix'.