Hi,

I found with the converted pretrained CIFAR-10 DDPM,

I got a FID of 5.68 in the setting of timesteps=100, eta=0, which is a margin away from 4.16 reported in the paper. May I know is that about a model you trained by yourselves?

For FID calculation, I use https://github.com/mseitzer/pytorch-fid