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
Hello,
Why are there fully connected layers at the end of the discriminator? Isn't the original PatchGAN architecture fully convolutional? I looked at the pytorch implementation of original DeblurGAN and could not see the fc layers. Sorry in advance if I am overlooking something in both your and original deblurgan implementations.
Thank you.
The text was updated successfully, but these errors were encountered:
Hello,
Why are there fully connected layers at the end of the discriminator? Isn't the original PatchGAN architecture fully convolutional? I looked at the pytorch implementation of original DeblurGAN and could not see the fc layers. Sorry in advance if I am overlooking something in both your and original deblurgan implementations.
Thank you.
The text was updated successfully, but these errors were encountered: