Skip to content

Latest commit

 

History

History
17 lines (11 loc) · 582 Bytes

README.md

File metadata and controls

17 lines (11 loc) · 582 Bytes

Self-Attention-GAN

Tensorflow-2.0 implementation of Self-Attention-GAN

This barnch is still in progress

  • reassign Mirrored Variables in replica context.

Original paper: Self-Attention Generative Adversarial Networks by Han Zhang, Ian Goodfellow, Dimitris Metaxas, Augustus Odena. Original implementation: https://github.com/brain-research/self-attention-gan

Usage: python sagan/main.py --config_path <your-configuration-file.py>

Example: python sagan/main.py --config_path example_configs/church64_attn.py

Current results