Diego Porres

It is possible, but you need to load the Generator in the correct way, so you'll most likely have to tinker with the code. For example, to load the Generator...

#142 has added some files to do just this. Try testing out their code to further check it works as intended.

I like this idea, sounds like a latent "stop motion" (in the end, you'd have a bit of a movie going on). Perhaps the issue is to decide the naming...

Previously, there was a way to use AMD on the implementation of StyleGAN in TensorFLow via changing `impl='cuda'` to `impl='ref'` in the custom ops (see @l4rz's semi-NSFW writeup [here](https://github.com/l4rz/practical-aspects-of-stylegan2-training#hardware)). Haven't...

Basically, the mismatch says it's when trying to load the pre-trained `.pkl` on the newly constructed `stylegan3-t` configuration. I'll try to fix it, as it also failed with me with...

I removed certain things to make it easier, but completely forgot to thoroughly removed these extra parameters. I removed lines 275 and 277 in `train.py` (both say `c.G_kwargs.extended_sgan2 = True`),...

Hmm this is related to #39. Thing is, I cannot reproduce it all the time, as I'm able to load pre-trained models as starting points (using `--resume`), but sometimes it...

Ok thanks that helps, I was thinking that since it worked then and there were no issues like this. I don't remember updating much, but I'll see the diff in...

Sorry, I hadn't seen this issue before. I'd like to fix the issue, but since the RGBA data I tested with worked fine, I think you can give me one...

With a low amount of data you usually see some leakage, so what you can do is either: transfer learn from another model (e.g. don't randomly initialize the networks but...