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 paper they use dropout instead of sampled noise as input to the generator.
In initial experiments, we did not
find this strategy effective – the generator simply learned
to ignore the noise – which is consistent with Mathieu et
al. [39]. Instead, for our final models, we provide noise
only in the form of dropout, applied on several layers of our
generator at both training and test time
If you look at the generator's definition you can see that I have used dropout in several layers of the generator.
Original paper used a noise with the input of the generator. why did you not use it?
PyTorch-GAN/implementations/pix2pix/pix2pix.py
Line 127 in 3a00900
The text was updated successfully, but these errors were encountered: