- pggan_512.pth:
- Average SWD: 1559.362
![]() |
---|
4 × 4 |
![]() |
---|
8 × 8 |
![]() |
---|
16 × 16 |
![]() |
---|
32 × 32 |
![]() |
---|
64 × 64 |
![]() |
---|
128 × 128 |
![]() |
---|
256 × 256 |
![]() |
---|
512 × 512 |
![]() |
---|
1,024 × 1,024 |
![](https://private-user-images.githubusercontent.com/67457712/313528648-bbec36d2-9256-461c-980d-a43e9d5af3ff.jpg?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.5HnpIF1ElDl23cgHGEHgMTPP6Iq_K2aXzSewimvk4oE)
![](https://private-user-images.githubusercontent.com/67457712/313528651-bd9a39cf-7f13-4c27-8165-4a3811cb7471.jpg?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.6ORl028Xxi-a0tYWJTMRwMUNCYpa1m8aSOJ3Mh3oa8M)
![](https://private-user-images.githubusercontent.com/67457712/313528653-78cf3f90-cda0-42ab-8689-cd53d5c77c4d.jpg?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.YGCW6JHrAjErTmdW_Qd07eqWZ1VzL6ErGA57SE_xWtM)
![](https://private-user-images.githubusercontent.com/67457712/313528656-cd4ea9cd-6472-44ec-b28c-054a6caf7023.jpg?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.BykhV66nHb3Anf5Q3hfHEuFueCTicnzK10p152oUyqY)
![](https://private-user-images.githubusercontent.com/67457712/313528660-996cfa7d-f111-4e6f-81ef-992585cadfcf.jpg?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.F3a0MtVH1Kx0nnvGdQLSoJgqswkY7bjnFKfmCLaLu-I)
- 이전까지는 CelebA-HQ의 Training set에 대해 Mean과 Std를 계산해서 이걸 가지고 Normalize했습니다.
T.Normalize(mean=(0.517, 0.416, 0.363), std=(0.303, 0.275, 0.269))
- 논문에서는 "We represent training and generated images in
$[-1, 1]$ ."라는 표현이 있는 것을 알고 있었으나 이를 간과하고 있었습니다. - 다음과 같이 코드를 수정했습니다.
T.Normalize(mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5))