stylegan2encoder
stylegan2encoder copied to clipboard
Tiled-mode for project_images.py and resumable training
This PR contains two improvements:
- new command-line argument for
project_images.py
:--no-tiled
which allows to switch to factory-default projection into1x512
dlatents-space (useful for evaluation of "semantic" quality of the model); - a tweak in training loop to resume from the latest network-snapshot if one is found in the
--result-dir
Yes this both makes sense. I'll try and add it to the next release. There are going to be a few major changes, mostly for video encoding.
Would you mind explaining the idea behind tiled mode? I found your PR while looking for information about this exact change. I suspect tiled mode leads to better projection results.
That could explain why I get different projection results with Nvidia's original project and this one.
Alright, I discovered this thread #2 and will read about it tomorrow. I think it might contain the answer.