Code for NeurIPS 2019 paper "Learning to Predict Layout-to-image Conditional Convolutions for Semantic Image Synthesis"
128
stars
15
forks
source link
the channel number of fc in generator is not correct without vae #1
Closed
wenhuach closed 4 years ago
self.fc = nn.Conv2d(self.opt.semantic_nc, 16nfself.swself.sh, 3, padding=1) =>self.fc = nn.Conv2d(self.opt.semantic_nc, 16 nf, 3, padding=1)