HomeAI & Machine LearningGenerative Adversarial Networks (GAN) Simulator

🎭 Generative Adversarial Networks (GAN) Simulator

Watch a generator learn to fool a discriminator: random latent points converge onto a real-data manifold. Tune the learning rate, latent diversity and batch size, and watch generator loss and discriminator accuracy evolve live.

AI & Machine Learning3DAdvanced60 FPS
generative-adversarial-networks-gan-simulator ↗ Open standalone
⚙ Under the hood

Watch a generator learn to fool a discriminator: latent noise points converge onto a real-data manifold over training epochs. Tune the learning rate, latent diversity and batch size, and watch generator loss and discriminator accuracy evolve live.

Three.jsAIGANGenerative Adversarial NetworksInstancedMesh

3D · Three.js / WebGL renderer · 60 FPS target · runs fully client-side, no install

What did you find?

Add reproduction steps (optional)