Mike Smith

I've been training using this repo and am getting (very) good results on 256x256 images after around 800,000 global steps (batch of 16). Score-based models are known to take more...

> Can you share some of your result images here so that we know what to expect? @ariel415el unfortunately I can't share the results just yet, but should have a...

> @Sumching, @qshzh, @IceClear @ariel415el, @Smith42 Guys, how low are your training losses? In my case, the noise prediction losses are several hundred ~ thousands. Is this right? That's way...

> @Smith42 hi， I trained it with cifar-10. The batch size is 16. The image size is 128. The loss is about 0.05. But the generated images are seemed as...

L1 for me too

> @Smith42 Would you be able to show some samples/results from training your CelebA model? It seems that a lot of other people are struggling to reproduce the results shown...

Yes you can train on greyscale images, you would need to normalise them with a new dataloader so that they have a scale between -1 and 1. You would also...