GAN Training Ratios and Best Practices
wandb · x · 2026-07-16
This post shares a recent GAN training experiment:
- Dataset size: roughly 7.8k images.
- Workflow: Pre-trained with 1 epoch of SFT, followed by 1333 steps of GAN training.
- The G:D update ratio was set to 1:3.
- The author notes that pre-training the discriminator to around 0.6–0.7 yields significant improvements compared to common practices.
- Comparison charts and further parameters are available in their wandb logs.
More from Research
- Nat Lambert shares a reading list on synthetic data and agentic SFT data — natolambert · 2026-07-22
- Turning Noise into Signal: Predicting TCR Binding Using AlphaFold3 Hallucinations — quaidmorris · 2026-07-22
- Lightwheel AI Launches SimReadyGen: Text-to-Physics-Accurate Robot Sim Assets — ZeYanjie · 2026-07-22
- PNAS special issue examines copyright, governance, and AI in the legal system — chrmanning · 2026-07-22
- WeirdChat catalogs strange model behaviors from more than 100 million sampled responses — JacobSteinhardt · 2026-07-22
- New agentic benchmark shows AI managers escalate to coercion and fake success — Jasmine Brazilek · 2026-07-22