PyTorch-progressive_growing_of_gans icon indicating copy to clipboard operation
PyTorch-progressive_growing_of_gans copied to clipboard

Published 20 hours ago • verified publisher icon github-pengge

Why update_lr() ?

Open oneHuster opened this issue 7 years ago • 1 comments

I was so confused about using self.update_lr(cur_nimg) in train.py train.py#L281 which may produce negative learning rate coefficient during the training process.

I have no idea about why we should use this func --- a func just make learning rate fluctuating.

oneHuster avatar Jan 09 '18 00:01 oneHuster

This is a trick taken from official code.

github-pengge avatar Jan 19 '18 05:01 github-pengge