search

github-pengge / PyTorch-progressive_growing_of_gans

PyTorch implementation of Progressive Growing of GANs for Improved Quality, Stability, and Variation.
580 stars 98 forks source link

Why update_lr() ? #14

Open oneHuster opened 6 years ago

oneHuster commented 6 years ago

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.

github-pengge commented 6 years ago

This is a trick taken from official code.