How to determine the value of σn in Algorithm 1
448357739 opened this issue · 1 comments
In the code, σn is generated by 'sigmas.append(reduced_alpha_cumprod[num_train_timesteps-1-i])', but I can't find the relevant description from the paper. Can you tell me the reason? Thank you very much.
Hi @448357739 ,
The reduced_alpha_cumprod is defined as the ratio
In DiffPIR, at each timestep in the sub-sequence, the equivalent sigma (curr_sigma in the code) is used as noise levels and hence input to the diffusion model https://github.com/yuanzhi-zhu/DiffPIR/blob/main/main_ddpir_sisr.py#LL296C62-L296C88.
That's to say, the sigma is a variable introduced for the convenience of the noise level (the common noise level in IR tasks following DPIR's setting).
Moreover, we use function utils_model.find_nearest to find the corresponding
It's also worth mentioning that one can find definitions like
Please do not hesitate if you have any other questions.