github-pengge

I had fixed it.

BEGAN did not work! I had change a lot of things, but still not working...

My bad. Now it's fixed.

Thx. Now I have no device to run such a large experiment, will have a try if devices are available.

However, using repeat suffers from severe perturbation when fading in. Besides, the author used repeat to implement nearest neighbor upsampling. You can verify that via numpy.repeat(PyTorch can not achieve this...

Hi, all. The master branch might collapse when resolution is larger than 128x128. If you want to obtain similar result in README, you can fall back to this [commit](https://github.com/github-pengge/PyTorch-progressive_growing_of_gans/tree/2c04be1d9ee76f9c83335547785c6559c1164a29), however,...

I did not use the same batch size as the paper used cause I ran the code on 1080 GPU with only 8GB memory, not P100, which has 16GB memory....

I found that learning rate was not fixed in official code, and I'm changing the scheduler of learning rate now.