WassersteinGAN.tensorflow
WassersteinGAN.tensorflow copied to clipboard
The construction of discriminator
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).
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.