Inference

[jdariasl]

Hi, thank you for sharing the code.

By analyzing the code, I found that, during inference, the network is conditioned on the same input batch:

epsilon_theta = net((x, cond, mask, diffusion_steps,)) # predict \epsilon according to \epsilon_\theta

Where cond is just the batch without applying any mask. Do I miss something? In a real imputation case scenario, should I replace the missing segment with zeros, similar to applying the mask to the cond variable?

Thank you in advance for your support.

[jdariasl]

Sorry, I didn't see this line: conditional = conditional * mask, which answers my question.