Biel Tura

Hi @ivanvovk, Thanks for the answering of the quesitons. Here's an update that my be helpful for future development: DataParallel can not be implemented in the current setup, as `compute_loss`...

Thanks! As a side note, we have been using the Energy metric (predicted-target difference) to check whether samples are "good enough" for evaluation. As you mentioned in your paper, diffusion...

Hi @roman-vygon, Thank you alot for the drive link, I missed it in the README. I completly understand the fact about hard/semihard examples, which makes also sense, but thanks for...

Hi, Sorry for the late reply. We did not implement this part finally. I hope the author could upload a new version as soon as possible. Best.