"Generative Models"의 두 판 사이의 차이
ph
(→GAN) |
|||
| 3번째 줄: | 3번째 줄: | ||
* [https://github.com/soumith/ganhacks How to Train a GAN? Tips and tricks to make GANs work] | * [https://github.com/soumith/ganhacks How to Train a GAN? Tips and tricks to make GANs work] | ||
* [https://medium.com/@devnag/generative-adversarial-networks-gans-in-50-lines-of-code-pytorch-e81b79659e3f Generative Adversarial Networks (GANs) in 50 lines of code (PyTorch)] | * [https://medium.com/@devnag/generative-adversarial-networks-gans-in-50-lines-of-code-pytorch-e81b79659e3f Generative Adversarial Networks (GANs) in 50 lines of code (PyTorch)] | ||
| + | ** real/fake 두 데이터 셋이 있어야 한다. D를 먼저 훈련시키고 다음에 G를 훈련시킨다. | ||
=VAE= | =VAE= | ||
2017년 5월 4일 (목) 14:18 판
GAN
- http://kvfrans.com/generative-adversial-networks-explained/
- How to Train a GAN? Tips and tricks to make GANs work
- Generative Adversarial Networks (GANs) in 50 lines of code (PyTorch)
- real/fake 두 데이터 셋이 있어야 한다. D를 먼저 훈련시키고 다음에 G를 훈련시킨다.
VAE
- http://kvfrans.com/variational-autoencoders-explained/
- autoencoder와 동일하나 latent vector를 생성할 때 (unit) gaussian으로만 생성하도록 constraint를 줌. 그래서 unit gaussian random variable로부터 generate.
- In practice, there's a tradeoff between how accurate our network can be and how close its latent variables can match the unit gaussian distribution.
- latent vector를 바로 만들지도 않고 mean, std만 만들어낸다.
- we can compare generated images directly to the originals, which is not possible when using a GAN.
- VAE in tensorflow