inference results with noise

[winnechan]

Hi, thanks for your excellent project !

I am new to diffusion models and I am now training a vanilla diffusion model over a small dataset (100 images). After being trained for 3000 epoches (around 10k iterations) with initial learning rate 5e-5, the trained model with small training loss produces images with much noises just like

How can I resolve the problem ? Should I train it for longer time or enlarge the learning rate ? Some useful tricks to debug ?

Appreciate any help !

[lucidrains]

@winnechan Hi Winne! So 100 images may not be enough, but eventually I want to add the augmentation techniques from https://arxiv.org/abs/2206.00364, and that should allow DDPMs to work on small datasets just as well