Fix Progressive Growing justification
Browse files
README.md
CHANGED
@@ -30,12 +30,12 @@ The Generator uses Transposed Convolutions (2x2 kernel) with strides for upsampl
|
|
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,
|
34 |
|
35 |
| Flat Growing (50K steps) | Progressive Growing (50K steps) |
|
36 |
| ----------- | ------------ |
|
37 |
-
| .
|
32 |
|
33 |
+
For 32x32 images of Airplanes, even a short initial round of Progressive Growing clearly has an impact:
|
34 |
|
35 |
| Flat Growing (50K steps) | Progressive Growing (50K steps) |
|
36 |
| ----------- | ------------ |
|
37 |
+
|  |  |
|
38 |
|
39 |
+
Moreover, 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?
|