search

mingyuliutw / UNIT

Unsupervised Image-to-Image Translation
Other
1.98k stars 360 forks source link

Several Question #55

Closed penincillin closed 5 years ago

penincillin commented 6 years ago

Hi, thanks for making the code public available. It is really an amazing work. After read the paper and the source code, I have several questions.

  1. In file cocogan_trainer.py, from line 73 to line 82, those member variables, self.gen_xx_loss_xx. I only find their definition, but I haven't find where they are used. So, what's these variables for?
  2. I try to train CelebA blondhair, and I find the batch size was set to 1, could the batch size be bigger than 1?
  3. I find the generated image of CelebA blondhair is a little blurred. Is this phenomenon normal?
mingyuliutw commented 5 years ago

Batch size 1 renders the best performance for many of the datasets I tested.

Yes, you might want to adjust the loss weights to mitigate the blurry issue.