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
Hey, I believe there's a minor bug in NLayerDiscriminator: padding is set as padw = int(np.ceil((kw-1.0)/2)), but it should be floor, not ceil (assuming you want to have same padding, similar to pix2pix).
As a result, the output of NLayerDiscriminator is a tiny bit (5 pixels or so) bigger than pix2pix patchgan, but MSEloss/BCEloss will average over all outputs anyways, so I guess it shouldn't matter much performance-wise.
EDIT: fixed it and made a pull request in case you want to change it.
Best regards,
Felix
The text was updated successfully, but these errors were encountered:
fa9r
linked a pull request
Mar 8, 2020
that will
close
this issue
Hey, I believe there's a minor bug in NLayerDiscriminator: padding is set as
padw = int(np.ceil((kw-1.0)/2))
, but it should be floor, not ceil (assuming you want to have same padding, similar to pix2pix).As a result, the output of NLayerDiscriminator is a tiny bit (5 pixels or so) bigger than pix2pix patchgan, but MSEloss/BCEloss will average over all outputs anyways, so I guess it shouldn't matter much performance-wise.
EDIT: fixed it and made a pull request in case you want to change it.
Best regards,
Felix
The text was updated successfully, but these errors were encountered: