Typo fixes and a better plot
Browse files
README.md
CHANGED
|
@@ -40,18 +40,18 @@ The idea is to start learning at lower resolutions, and growing the resolution o
|
|
| 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
|
| 44 |
|
| 45 |
-
|
| 54 |
|
| 55 |
# Training Progression
|
| 56 |
|
| 57 |
-
<video controls src="https://cdn-uploads.huggingface.co/production/uploads/649f9483d76ca0fe679011c2/
|
|
|
|
| 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 constrains 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 |
+
|
| 46 |
|
| 47 |
# Latent Space Interpolation
|
| 48 |
|
| 49 |
+
Latent Space Interpolation can be an educational exercise to get deeper insight into the model.
|
| 50 |
|
| 51 |
+
It is observed below that several aspects of the generated image, such as the color of the sky, the grounded-ness of the plane, and the plane shape and color, are frequently continuous through the latent space.
|
| 52 |
|
| 53 |
|
| 54 |
|
| 55 |
# Training Progression
|
| 56 |
|
| 57 |
+
<video controls src="https://cdn-uploads.huggingface.co/production/uploads/649f9483d76ca0fe679011c2/xwHwDXm6nOF1yzYJdbIkE.mp4"></video>
|