Open cyduoot opened 4 years ago
Yeah, It should be 3 to keep the same shape after using nn.Conv2d(channels, out_features, 7)
In the class
GeneratorResNet
, in line 49 and line 82, the parameter ofnn.ReflectionPad2d
should be namely3
but notchannels
. It should be decided by the kernel size but not the channels.
This change is efficient and correct, especially for multi-channels images (e.g. 1x256x256 or 2x256x256).
In the class
GeneratorResNet
, in line 49 and line 82, the parameter ofnn.ReflectionPad2d
should be namely3
but notchannels
. It should be decided by the kernel size but not the channels.