Question about algorithm
tuning12 opened this issue · 3 comments
Thank you for your great work! In algorithm 1, the noise added is fixed (determined by unet and x_0). However, in the "train_step_perpneg" function, a random noise is added which is different from the algorithm 1.
Hi, thanks for your attention.
I just checked our code, and it seems like we don't have this bug,
I think there is a misleading in :
prev_noisy_lat = self.scheduler.add_noise(latents, noise, self.timesteps[ind_prev_t])
However, the ind_prev_t will always be set to 0 at each step. Apologize for it.
Thank you for your patient reply!
Hi, how do you sample the viewpoint in training? I log the azimuths in the training script and find that most of them are lower than 100. Are there any tricks on it?