Update README.md
Browse files
README.md
CHANGED
|
@@ -28,4 +28,14 @@ The Generator uses Transposed Convolutions (2x2 kernel) with strides for upsampl
|
|
| 28 |
|
| 29 |
# Progressive Growing
|
| 30 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
# Does the model simply memorize the images?
|
|
|
|
| 28 |
|
| 29 |
# Progressive Growing
|
| 30 |
|
| 31 |
+
Progressive Growing of GAN resolutions is suggested to improve the Quality and Stability of GAN training, especially for higher resolution models (1024x1024).
|
| 32 |
+
|
| 33 |
+
For 32x32 images of Airplanes, it is unclear if there is a positive impact on the Image Quality at comparable points during model training:
|
| 34 |
+
|
| 35 |
+
| Flat Growing (50K steps) | Progressive Growing (50K steps) |
|
| 36 |
+
| ----------- | ------------ |
|
| 37 |
+
|  |  |
|
| 38 |
+
|
| 39 |
+
However, it doesn't negatively impact the training process and the additional parameter cost is very small (876.6 KB vs 855.1 KB for the generator).
|
| 40 |
+
|
| 41 |
# Does the model simply memorize the images?
|