TensorFlow 生成对抗网络对比

GANs comparison without cherry-picking

生成对抗模型对比

实现了一些生成对抗网络理论：: DCGAN, EBGAN, LSGAN, WGAN, WGAN-GP, BEGAN, and DRAGAN.使用同一个 CelebA 数据集，来对比这些生成对抗网络。

项目地址：https://github.com/khanrc/tf.gans-comparison

Implementations of some theoretical generative adversarial nets: DCGAN, EBGAN, LSGAN, WGAN, WGAN-GP, BEGAN, and DRAGAN.

I implemented the structure of model equal to the structure in paper and compared it on the CelebA dataset without cherry-picking.