denoising-diffusion-pytorch icon indicating copy to clipboard operation
denoising-diffusion-pytorch copied to clipboard

Published 20 hours ago • verified publisher icon lucidrains

How do epochs work with ddpm?

Open sgbaird opened this issue 3 years ago • 1 comments

For example, if I set 700k training steps, and stop at ~30k when there are 15k images, is there an idea of how many times the training data has been cycled through?

sgbaird avatar Jun 11 '22 13:06 sgbaird

The number of training is related to your data set. You may need to observe loss, FID and generation quality. In my personal experience, too many training times will lose diversity.

wangqiang9 avatar Jul 01 '22 14:07 wangqiang9