Diffusion-Models-pytorch
Diffusion-Models-pytorch copied to clipboard
Some details
I've noticed that in other's DDPM implement, there exists another parameters called 'alpha_cumprod_prev' or something, which append the 1. in front of the alpha_cumprod. Why don't you use this thing, or you have changed it in a simple way?
same question
I've noticed that in other's DDPM implement, there exists another parameters called 'alpha_cumprod_prev' or something, which append the 1. in front of the alpha_cumprod. Why don't you use this thing, or you have changed it in a simple way?