|
--- |
|
library_name: keras |
|
tags: |
|
- GAN |
|
--- |
|
|
|
## Generative Adversarial Network |
|
|
|
This repo contains the model and the notebook to this [this Keras example on WGAN](https://keras.io/examples/generative/wgan_gp/).<br> |
|
Full credits to: [A_K_Nain](https://twitter.com/A_K_Nain)<br> |
|
Space link : [Demo](https://huggingface.co./spaces/IMvision12/WGAN-GP) |
|
## Wasserstein GAN (WGAN) with Gradient Penalty (GP) |
|
|
|
Original Paper Of WGAN : [Paper](https://arxiv.org/abs/1701.07875)<br> |
|
Wasserstein GANs With with Gradient Penalty : [Paper](https://arxiv.org/abs/1704.00028) |
|
|
|
The original Wasserstein GAN leverages the Wasserstein distance to produce a value function that has better theoretical properties than the value function used in the original GAN paper. WGAN requires that the discriminator (aka the critic) lie within the space of 1-Lipschitz functions. The authors proposed the idea of weight clipping to achieve this constraint. Though weight clipping works, it can be a problematic way to enforce 1-Lipschitz constraint and can cause undesirable behavior, e.g. a very deep WGAN discriminator (critic) often fails to converge. |
|
|
|
The WGAN-GP method proposes an alternative to weight clipping to ensure smooth training. Instead of clipping the weights, the authors proposed a "gradient penalty" by adding a loss term that keeps the L2 norm of the discriminator gradients close to 1. |
