torchgan

The torchgan package consists of various generative adversarial networks and utilities that have been found useful in training them. This package provides an easy to use API which can be used to train popular gans as well as develop newer variants.

Getting Started

• Installation
  • Pip Installation
  • Conda Installation
  • Install from Source
• Contributing
• Starter Example

Documentation

• 1. torchgan.losses
  • 1.1. Loss
  • 1.2. Least Squares Loss
  • 1.3. Minimax Loss
  • 1.4. Boundary Equilibrium Loss
  • 1.5. Energy Based Loss
  • 1.6. Wasserstein Loss
  • 1.7. Mutual Information Penalty
• 2. torchgan.metrics
  • 2.1. Metric
  • 2.2. Classifier Score
• 3. torchgan.models
  • 3.1. GAN
  • 3.2. DCGAN
  • 3.3. Conditional GAN
  • 3.4. InfoGAN
• 4. torchgan.trainer

Examples

• 1. Example