Output looks different at inference time versus at training time

jerryli27 / TwinGAN

Twin-GAN -- Unpaired Cross-Domain Image Translation with Weight-Sharing GANs

Apache License 2.0

719 stars 98 forks source link

Output looks different at inference time versus at training time #4

Open jerryli27 opened 6 years ago

jerryli27 commented 6 years ago

I noticed that when training from scratch the inference output images looks different. I have seen this issue multiple times during development and it is probably due to some misconfiguration in batch renormalization.

Opening this bug to track progress on fixing that.