search

shekkizh / WassersteinGAN.tensorflow

Tensorflow implementation of Wasserstein GAN - arxiv: https://arxiv.org/abs/1701.07875
MIT License
416 stars 130 forks source link

The construction of discriminator #11

Open YifanZuo opened 7 years ago

YifanZuo commented 7 years ago

I have a question on the discriminator construction. I find the final number of channel is "1" via convolutional layer in this implementation. However, I find in others, e.g., "improved wgan", the final layer is fully-connection layer with the out dimension "1". So, which one is better? Indeed, I do not find any description of discriminator construction in the original paper (Wasserstein GAN).

YifanZuo commented 7 years ago

Now，I confirm that this implementation has two errors. One is the optimizer should be rmsprop but not adam. The other is that the final output must use fully-connection to get one scalar according to the original paper.