devnag/pytorch-generative-adversarial-networks
A minimal 50-line PyTorch implementation of Generative Adversarial Networks training on synthetic Gaussian data.

Velocity · 7d
+0.5
★ / day
Trend
→steady
star history
This repository provides a simple GAN implementation in PyTorch, demonstrating the adversarial training process where a generator and discriminator network compete. The code trains on a synthetic shifted/scaled Gaussian distribution, illustrating how the generator learns to match the real data distribution. It serves as an educational example accompanying a blog post tutorial.