You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Your implementation has diffusion_projection for every residual block similar to DiffWave, but this is inconsistent with the paper as the original architecture directly adds E_t (output of the step embedding module) to the input before the first convolution layer. Is there a reason behind this change?
The text was updated successfully, but these errors were encountered:
Hi @tebin , sorry for the late response.
There is no special reason for that. I just borrowed the idea from them and let the model learn in an expected way. But I think the method in the paper might work better somehow, and if you have a room for it, it would be nice if you can try them and share the results for others.
Your implementation has
diffusion_projection
for every residual block similar to DiffWave, but this is inconsistent with the paper as the original architecture directly adds E_t (output of the step embedding module) to the input before the first convolution layer. Is there a reason behind this change?The text was updated successfully, but these errors were encountered: