PrakhAI commited on
Commit
45ea774
·
1 Parent(s): 92221c0

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -0
README.md CHANGED
@@ -36,6 +36,14 @@ The idea is to start learning at lower resolutions, and growing the resolution o
36
 
37
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/649f9483d76ca0fe679011c2/r8HWxaSkHArS_89VCiKZi.png)
38
 
 
 
 
 
 
 
 
 
39
  # Latent Space Interpolation
40
 
41
  Latent Space Interpolation can an educational exercise to get deeper insight into the model.
 
36
 
37
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/649f9483d76ca0fe679011c2/r8HWxaSkHArS_89VCiKZi.png)
38
 
39
+ # Spectral Normalization
40
+
41
+ Spectral Normalization for GANs was first suggested in [Spectral Normalization for Generative Adversarial Networks](https://arxiv.org/pdf/1802.05957.pdf).
42
+
43
+ Spectral Normalization constraints the Gradient Norm of the Discriminator with respect to the input, yielding a much smoother loss landscape for the Generator to navigate through.
44
+
45
+ ![image/gif](https://cdn-uploads.huggingface.co/production/uploads/649f9483d76ca0fe679011c2/7nE-TiaDfCErsPC9N0aZN.gif)
46
+
47
  # Latent Space Interpolation
48
 
49
  Latent Space Interpolation can an educational exercise to get deeper insight into the model.