adeptflax

I think I got it working. I only have the first epoch of my model trained. I need to wait for it to finish to know for sure. I'll write...

I had to fix something, but I did seem to have gotten it working. I'll post guide tomorrow if it works well.

Sorry guys, I procrastinated for a couple of days. I have gotten code to work that can train and run a image2image model. I don't know how it compares to...

Here it is. Should work. https://github.com/adeptflax/image2image

@Guthman @1211sh I don't seem to get that good of results by epoch 36 on around 11,000 training examples. Does it just need to trained for longer or does something...

@Guthman I saved the model output. and I just used pix2pixHD. Through pix2pixHd doesn't do as good as I need. Do you think random crop would help?

Maybe using transformers instead of just vggan would work? Maybe it's possible to pretrain on a face dataset? I'm doing stuff with faces.

I'm trained on 2 RTX 3090s for 2 days I think. So I would have to train for another 6 days, because of training because 512x512 is 4 times larger...

@Guthman what's the resolution of your dataset?

Do transformer models first pre-train with vqgan and then do training on transformers?