Open bennymi opened 2 months ago
Hi, thank you for providing the code. I have a question about the ddim_sample_loop_known function. Why do we set the timesteps in this line (https://github.com/JuliaWolleb/Diffusion-based-Segmentation/blob/676f214035e90edd0357f51feab45841e4aefcfb/guided_diffusion/gaussian_diffusion.py#L792) to be 499?
ddim_sample_loop_known
Shouldn't the SpacedDiffusion model and the timestep_respacing with something like ddim 50 automatically take care of the correct beta scheduling to reduce the number of timesteps?
SpacedDiffusion
timestep_respacing
ddim 50
In the original ddim_sample_loop implementation, there is no such thing: https://github.com/openai/improved-diffusion/blob/1bc7bbbdc414d83d4abf2ad8cc1446dc36c4e4d5/improved_diffusion/gaussian_diffusion.py#L562
ddim_sample_loop
Hi, thank you for providing the code. I have a question about the
ddim_sample_loop_known
function. Why do we set the timesteps in this line (https://github.com/JuliaWolleb/Diffusion-based-Segmentation/blob/676f214035e90edd0357f51feab45841e4aefcfb/guided_diffusion/gaussian_diffusion.py#L792) to be 499?Shouldn't the
SpacedDiffusion
model and thetimestep_respacing
with something likeddim 50
automatically take care of the correct beta scheduling to reduce the number of timesteps?In the original
ddim_sample_loop
implementation, there is no such thing: https://github.com/openai/improved-diffusion/blob/1bc7bbbdc414d83d4abf2ad8cc1446dc36c4e4d5/improved_diffusion/gaussian_diffusion.py#L562