0
0

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?

More than 3 years have passed since last update.

一个成功的GAN实验

Posted at

一两个星期以前我做了一个最初版本的GAN(没有卷积层),效果如下:

image.png

至于为什么可以指定数字输出是因为我用了conditional GAN的架构(如下图,左1),不过我想说的是vanilla GAN的效果很差,噪点很多。

image.png

DCGAN可以说是GAN的第一次进化,只是简单地在vanilla GAN架构里加入了卷积层,效果如下图(epoch=60):

anima.gif

我把代码放在github,请随意参照。后续GAN的实验都会摆在这个仓库里:

Fool GAN

0
0
0

Register as a new user and use Qiita more conveniently

  1. You get articles that match your needs
  2. You can efficiently read back useful information
  3. You can use dark theme
What you can do with signing up
0
0

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?