IMvision12
commited on
Commit
•
722506e
1
Parent(s):
4c6e522
Update README.md
Browse files
README.md
CHANGED
@@ -4,6 +4,11 @@ tags:
|
|
4 |
- GAN
|
5 |
---
|
6 |
|
|
|
|
|
|
|
|
|
|
|
7 |
## Wasserstein GAN (WGAN) with Gradient Penalty (GP)
|
8 |
|
9 |
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.
|
|
|
4 |
- GAN
|
5 |
---
|
6 |
|
7 |
+
## Generative Adversarial Network
|
8 |
+
|
9 |
+
This repo contains the model and the notebook to this [this Keras example on WGAN](https://keras.io/examples/generative/wgan_gp/).
|
10 |
+
Full credits to: [A_K_Nain](https://twitter.com/A_K_Nain)
|
11 |
+
|
12 |
## Wasserstein GAN (WGAN) with Gradient Penalty (GP)
|
13 |
|
14 |
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.
|