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
HI, authors,
Great work! My question about the implementation is as follows:
During training, I found that you randomly set 20% of CLIP's input as zeros tensors,
however, during testing, you concatenate the output of clip embedding with zero tensors, like this:
As far as I am concerned, to align the training and testing, should we randomly set 20% of the output of CLIP as zero tensors rather than the input of CLIP model?
The text was updated successfully, but these errors were encountered:
TianpengBu
changed the title
Inconsistency between classifier-free guidance between training and testing.
Inconsistency of classifier-free guidance between training and testing.
Mar 29, 2024
HI, authors,
Great work! My question about the implementation is as follows:
During training, I found that you randomly set 20% of CLIP's input as zeros tensors,
however, during testing, you concatenate the output of clip embedding with zero tensors, like this:
As far as I am concerned, to align the training and testing, should we randomly set 20% of the output of CLIP as zero tensors rather than the input of CLIP model?
The text was updated successfully, but these errors were encountered: