You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
In your WGAN implementation, you have your n-critique loop around the Generator learning when it should actually be around the Discriminator's. Critique stands for Discriminator.
The text was updated successfully, but these errors were encountered:
The paper tells us that we should train the critic (discriminator) n_critic times for each generator update, just as WGAN is implemented here. The discriminator is updated on each batch but the generator is only updated every n_critic batch.
In your WGAN implementation, you have your n-critique loop around the Generator learning when it should actually be around the Discriminator's. Critique stands for Discriminator.
The text was updated successfully, but these errors were encountered: