Open jikim-research opened 3 months ago
There was a a bit of misunderstanding. I've realized that the classifier takes the original image as input :) thanks
Hi Jeongin, I'm happy you were able to solve the issue by yourself. Please let me know if you have any other problems :)
Thank you for the great work.
Based on my understanding of the joint diffusion model described in your paper, I believe that when the FLAG
train_noised_classifier
is set to False, the fully denoised x_0 from the reverse process should be input to the classifier's forward function. However, in the actual code, particularly in thecalculate_classifier_loss
function within theguided_diffusion/gaussian_diffusion.py
script, I noticed the following implementation:Here,
x_start
is being used as the input to the classifier when train_noised_classifier is False. Could you please clarify ifx_start
corresponds to thepred_xstart
returned by thep_mean_variance
function, or if the original image is just being input to the classifier?Thank you.