Closed Maydaybye closed 10 months ago
(1) During the final implementation, we found that there is not much performance difference between optimizing the global corrector at all times and optimizing only when sqrt(1-α¯t/α¯t) > γ. However, during inference, this condition must still be met. Anyway, you can set gamma_limit_train as 1.0 to be consistent with the paper. (2) x_recon_detach may have noise. x_start_shift has no noise, which only has color shift.
Thanks for your patience and detailed answers!
Hi, I'm a little confused about the following regarding the calculation of loss.
Really confused /_ \
Looking forward to your help.