-
In keras the label is the real label, but in pytorch it is the random label.
Tenyn updated
3 years ago
-
-
-
Hi! I read your paper ,and I saw a lot of cgan only use the y(condition) in the begining， but I see "conditional image generation task" in this paper, it use a lot of y into the resblock.
Why？
Than…
-
Hi! Thank you for the excellent work of the shadow removal, and where can i get the demo. The proposed ST-CGAN inspires me in other areas of research.
-
It is noticed that the google drive link for ID-CGAN dataset is empty. Is it deleted? Or will it be udpated? Many thanks!!
-
Are you planning to add the conditional batch normalization and projection discriminator similar to cGANs with Projection Discriminator (https://arxiv.org/abs/1802.05637)?
-
The model is not detecting the actual shadow.
It only detect dark colors as shadow in the input images during Testing using test.py and ST-CGAN_G2_1500.pth weights.
I wondered, if this model actuall…
-
## Goal
ani2pic로 사진을 캐릭터로 변환하여 데이터를 생성하고, 이 캐릭터를 다시 사진으로 복구하는 모델을 만든다
## Checklist
### TODO - paper review
- [x] [VanillaGAN](https://22-22.tistory.com/36) 리뷰
- [x] [cGAN](https://22-22.t…
-
When I run ./scripts/train_cGAN.sh Capitals64.
There are a problem.
This is my curre…