search

shekkizh / WassersteinGAN.tensorflow

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

Discriminator loss function #12

Open baumgach opened 7 years ago

baumgach commented 7 years ago

I don't understand how exactly the loss function in line 5 of algorithm 1 in the original WGAN paper is implemented here. In your code you minimise

self.discriminator_loss = discriminator_loss_fake + discriminator_loss_real

However, according to the paper shouldn't it be maximising:

self.discriminator_loss = discriminator_loss_real - discriminator_loss_fake

or alternatively minimising:

self.discriminator_loss = discriminator_loss_fake - discriminator_loss_real

That is, should this be a minus in your total loss?

haleqiu commented 5 years ago

I thought the first algorithm is implemented for cross entropy, which discriminator_loss_fake + discriminator_loss_real