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 the pix2pix paper they mention using dropout to add randomness and use using the normalization using the statistics of
the test batch, rather than aggregated statistics of the train-set.
But in your code you use self.generator.predict
dropout is turned off, and normalization uses aggregated stasitics
The text was updated successfully, but these errors were encountered:
In the pix2pix paper they mention using dropout to add randomness and use using the normalization using the statistics of
the test batch, rather than aggregated statistics of the train-set.
But in your code you use
self.generator.predict
dropout is turned off, and normalization uses aggregated stasitics
The text was updated successfully, but these errors were encountered: